Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6
Pull crypto updates from Herbert Xu:
"API:
- Decryption test vectors are now automatically generated from
encryption test vectors.
Algorithms:
- Fix unaligned access issues in crc32/crc32c.
- Add zstd compression algorithm.
- Add AEGIS.
- Add MORUS.
Drivers:
- Add accelerated AEGIS/MORUS on x86.
- Add accelerated SM4 on arm64.
- Removed x86 assembly salsa implementation as it is slower than C.
- Add authenc(hmac(sha*), cbc(aes)) support in inside-secure.
- Add ctr(aes) support in crypto4xx.
- Add hardware key support in ccree.
- Add support for new Centaur CPU in via-rng"
* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (112 commits)
crypto: chtls - free beyond end rspq_skb_cache
crypto: chtls - kbuild warnings
crypto: chtls - dereference null variable
crypto: chtls - wait for memory sendmsg, sendpage
crypto: chtls - key len correction
crypto: salsa20 - Revert "crypto: salsa20 - export generic helpers"
crypto: x86/salsa20 - remove x86 salsa20 implementations
crypto: ccp - Add GET_ID SEV command
crypto: ccp - Add DOWNLOAD_FIRMWARE SEV command
crypto: qat - Add MODULE_FIRMWARE for all qat drivers
crypto: ccree - silence debug prints
crypto: ccree - better clock handling
crypto: ccree - correct host regs offset
crypto: chelsio - Remove separate buffer used for DMA map B0 block in CCM
crypt: chelsio - Send IV as Immediate for cipher algo
crypto: chelsio - Return -ENOSPC for transient busy indication.
crypto: caam/qi - fix warning in init_cgr()
crypto: caam - fix rfc4543 descriptors
crypto: caam - fix MC firmware detection
crypto: clarify licensing of OpenSSL asm code
...
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 708dc4c..2754fe8 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -64,8 +64,6 @@
- misc. LCD driver documentation (cfag12864b, ks0108).
backlight/
- directory with info on controlling backlights in flat panel displays
-bcache.txt
- - Block-layer cache on fast SSDs to improve slow (raid) I/O performance.
block/
- info on the Block I/O (BIO) layer.
blockdev/
@@ -78,18 +76,10 @@
- directory with info on TI GPMC (General Purpose Memory Controller)
bus-virt-phys-mapping.txt
- how to access I/O mapped memory from within device drivers.
-cachetlb.txt
- - describes the cache/TLB flushing interfaces Linux uses.
cdrom/
- directory with information on the CD-ROM drivers that Linux has.
cgroup-v1/
- cgroups v1 features, including cpusets and memory controller.
-cgroup-v2.txt
- - cgroups v2 features, including cpusets and memory controller.
-circular-buffers.txt
- - how to make use of the existing circular buffer infrastructure
-clk.txt
- - info on the common clock framework
cma/
- Continuous Memory Area (CMA) debugfs interface.
conf.py
diff --git a/Documentation/ABI/stable/sysfs-devices-node b/Documentation/ABI/stable/sysfs-devices-node
index 5b2d0f0..3e90e1f 100644
--- a/Documentation/ABI/stable/sysfs-devices-node
+++ b/Documentation/ABI/stable/sysfs-devices-node
@@ -90,4 +90,4 @@
Contact: Lee Schermerhorn <lee.schermerhorn@hp.com>
Description:
The node's huge page size control/query attributes.
- See Documentation/vm/hugetlbpage.txt
\ No newline at end of file
+ See Documentation/admin-guide/mm/hugetlbpage.rst
\ No newline at end of file
diff --git a/Documentation/ABI/testing/sysfs-class-cxl b/Documentation/ABI/testing/sysfs-class-cxl
index 640f65e..8e69345 100644
--- a/Documentation/ABI/testing/sysfs-class-cxl
+++ b/Documentation/ABI/testing/sysfs-class-cxl
@@ -244,3 +244,11 @@
Returns 1 if the psl timebase register is synchronized
with the core timebase register, 0 otherwise.
Users: https://github.com/ibm-capi/libcxl
+
+What: /sys/class/cxl/<card>/tunneled_ops_supported
+Date: May 2018
+Contact: linuxppc-dev@lists.ozlabs.org
+Description: read only
+ Returns 1 if tunneled operations are supported in capi mode,
+ 0 otherwise.
+Users: https://github.com/ibm-capi/libcxl
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 025b7cf..bd4975e 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -478,6 +478,7 @@
/sys/devices/system/cpu/vulnerabilities/meltdown
/sys/devices/system/cpu/vulnerabilities/spectre_v1
/sys/devices/system/cpu/vulnerabilities/spectre_v2
+ /sys/devices/system/cpu/vulnerabilities/spec_store_bypass
Date: January 2018
Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
Description: Information about CPU vulnerabilities
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-hugepages b/Documentation/ABI/testing/sysfs-kernel-mm-hugepages
index e21c005..fdaa216 100644
--- a/Documentation/ABI/testing/sysfs-kernel-mm-hugepages
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-hugepages
@@ -12,4 +12,4 @@
free_hugepages
surplus_hugepages
resv_hugepages
- See Documentation/vm/hugetlbpage.txt for details.
+ See Documentation/admin-guide/mm/hugetlbpage.rst for details.
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-ksm b/Documentation/ABI/testing/sysfs-kernel-mm-ksm
index 73e653e..dfc1324 100644
--- a/Documentation/ABI/testing/sysfs-kernel-mm-ksm
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-ksm
@@ -40,7 +40,7 @@
sleep_millisecs: how many milliseconds ksm should sleep between
scans.
- See Documentation/vm/ksm.txt for more information.
+ See Documentation/vm/ksm.rst for more information.
What: /sys/kernel/mm/ksm/merge_across_nodes
Date: January 2013
diff --git a/Documentation/ABI/testing/sysfs-kernel-slab b/Documentation/ABI/testing/sysfs-kernel-slab
index 2cc0a72..29601d9 100644
--- a/Documentation/ABI/testing/sysfs-kernel-slab
+++ b/Documentation/ABI/testing/sysfs-kernel-slab
@@ -37,7 +37,7 @@
The alloc_calls file is read-only and lists the kernel code
locations from which allocations for this cache were performed.
The alloc_calls file only contains information if debugging is
- enabled for that cache (see Documentation/vm/slub.txt).
+ enabled for that cache (see Documentation/vm/slub.rst).
What: /sys/kernel/slab/cache/alloc_fastpath
Date: February 2008
@@ -219,7 +219,7 @@
Description:
The free_calls file is read-only and lists the locations of
object frees if slab debugging is enabled (see
- Documentation/vm/slub.txt).
+ Documentation/vm/slub.rst).
What: /sys/kernel/slab/cache/free_fastpath
Date: February 2008
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index a27fbfb..65eb856 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -1,3 +1,5 @@
+What is RCU? -- "Read, Copy, Update"
+
Please note that the "What is RCU?" LWN series is an excellent place
to start learning about RCU:
diff --git a/Documentation/acpi/cppc_sysfs.txt b/Documentation/acpi/cppc_sysfs.txt
new file mode 100644
index 0000000..f20fb44
--- /dev/null
+++ b/Documentation/acpi/cppc_sysfs.txt
@@ -0,0 +1,69 @@
+
+ Collaborative Processor Performance Control (CPPC)
+
+CPPC defined in the ACPI spec describes a mechanism for the OS to manage the
+performance of a logical processor on a contigious and abstract performance
+scale. CPPC exposes a set of registers to describe abstract performance scale,
+to request performance levels and to measure per-cpu delivered performance.
+
+For more details on CPPC please refer to the ACPI specification at:
+
+http://uefi.org/specifications
+
+Some of the CPPC registers are exposed via sysfs under:
+
+/sys/devices/system/cpu/cpuX/acpi_cppc/
+
+for each cpu X
+
+--------------------------------------------------------------------------------
+
+$ ls -lR /sys/devices/system/cpu/cpu0/acpi_cppc/
+/sys/devices/system/cpu/cpu0/acpi_cppc/:
+total 0
+-r--r--r-- 1 root root 65536 Mar 5 19:38 feedback_ctrs
+-r--r--r-- 1 root root 65536 Mar 5 19:38 highest_perf
+-r--r--r-- 1 root root 65536 Mar 5 19:38 lowest_freq
+-r--r--r-- 1 root root 65536 Mar 5 19:38 lowest_nonlinear_perf
+-r--r--r-- 1 root root 65536 Mar 5 19:38 lowest_perf
+-r--r--r-- 1 root root 65536 Mar 5 19:38 nominal_freq
+-r--r--r-- 1 root root 65536 Mar 5 19:38 nominal_perf
+-r--r--r-- 1 root root 65536 Mar 5 19:38 reference_perf
+-r--r--r-- 1 root root 65536 Mar 5 19:38 wraparound_time
+
+--------------------------------------------------------------------------------
+
+* highest_perf : Highest performance of this processor (abstract scale).
+* nominal_perf : Highest sustained performance of this processor (abstract scale).
+* lowest_nonlinear_perf : Lowest performance of this processor with nonlinear
+ power savings (abstract scale).
+* lowest_perf : Lowest performance of this processor (abstract scale).
+
+* lowest_freq : CPU frequency corresponding to lowest_perf (in MHz).
+* nominal_freq : CPU frequency corresponding to nominal_perf (in MHz).
+ The above frequencies should only be used to report processor performance in
+ freqency instead of abstract scale. These values should not be used for any
+ functional decisions.
+
+* feedback_ctrs : Includes both Reference and delivered performance counter.
+ Reference counter ticks up proportional to processor's reference performance.
+ Delivered counter ticks up proportional to processor's delivered performance.
+* wraparound_time: Minimum time for the feedback counters to wraparound (seconds).
+* reference_perf : Performance level at which reference performance counter
+ accumulates (abstract scale).
+
+--------------------------------------------------------------------------------
+
+ Computing Average Delivered Performance
+
+Below describes the steps to compute the average performance delivered by taking
+two different snapshots of feedback counters at time T1 and T2.
+
+T1: Read feedback_ctrs as fbc_t1
+ Wait or run some workload
+T2: Read feedback_ctrs as fbc_t2
+
+delivered_counter_delta = fbc_t2[del] - fbc_t1[del]
+reference_counter_delta = fbc_t2[ref] - fbc_t1[ref]
+
+delivered_perf = (refernce_perf x delivered_counter_delta) / reference_counter_delta
diff --git a/Documentation/bcache.txt b/Documentation/admin-guide/bcache.rst
similarity index 100%
rename from Documentation/bcache.txt
rename to Documentation/admin-guide/bcache.rst
diff --git a/Documentation/cgroup-v2.txt b/Documentation/admin-guide/cgroup-v2.rst
similarity index 100%
rename from Documentation/cgroup-v2.txt
rename to Documentation/admin-guide/cgroup-v2.rst
diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst
index 5bb9161..48d70af 100644
--- a/Documentation/admin-guide/index.rst
+++ b/Documentation/admin-guide/index.rst
@@ -48,6 +48,7 @@
:maxdepth: 1
initrd
+ cgroup-v2
serial-console
braille-console
parport
@@ -60,9 +61,11 @@
mono
java
ras
+ bcache
pm/index
thunderbolt
LSM/index
+ mm/index
.. only:: subproject and html
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 11fc28e..9d699c8 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -106,11 +106,11 @@
use by PCI
Format: <irq>,<irq>...
- acpi_mask_gpe= [HW,ACPI]
+ acpi_mask_gpe= [HW,ACPI]
Due to the existence of _Lxx/_Exx, some GPEs triggered
by unsupported hardware/firmware features can result in
- GPE floodings that cannot be automatically disabled by
- the GPE dispatcher.
+ GPE floodings that cannot be automatically disabled by
+ the GPE dispatcher.
This facility can be used to prevent such uncontrolled
GPE floodings.
Format: <int>
@@ -472,10 +472,10 @@
for platform specific values (SB1, Loongson3 and
others).
- ccw_timeout_log [S390]
+ ccw_timeout_log [S390]
See Documentation/s390/CommonIO for details.
- cgroup_disable= [KNL] Disable a particular controller
+ cgroup_disable= [KNL] Disable a particular controller
Format: {name of the controller(s) to disable}
The effects of cgroup_disable=foo are:
- foo isn't auto-mounted if you mount all cgroups in
@@ -518,7 +518,7 @@
those clocks in any way. This parameter is useful for
debug and development, but should not be needed on a
platform with proper driver support. For more
- information, see Documentation/clk.txt.
+ information, see Documentation/driver-api/clk.rst.
clock= [BUGS=X86-32, HW] gettimeofday clocksource override.
[Deprecated]
@@ -587,11 +587,6 @@
Sets the size of memory pool for coherent, atomic dma
allocations, by default set to 256K.
- code_bytes [X86] How many bytes of object code to print
- in an oops report.
- Range: 0 - 8192
- Default: 64
-
com20020= [HW,NET] ARCnet - COM20020 chipset
Format:
<io>[,<irq>[,<nodeID>[,<backplane>[,<ckp>[,<timeout>]]]]]
@@ -641,8 +636,8 @@
hvc<n> Use the hypervisor console device <n>. This is for
both Xen and PowerPC hypervisors.
- If the device connected to the port is not a TTY but a braille
- device, prepend "brl," before the device type, for instance
+ If the device connected to the port is not a TTY but a braille
+ device, prepend "brl," before the device type, for instance
console=brl,ttyS0
For now, only VisioBraille is supported.
@@ -662,7 +657,7 @@
consoleblank= [KNL] The console blank (screen saver) timeout in
seconds. A value of 0 disables the blank timer.
- Defaults to 0.
+ Defaults to 0.
coredump_filter=
[KNL] Change the default value for
@@ -730,7 +725,7 @@
or memory reserved is below 4G.
cryptomgr.notests
- [KNL] Disable crypto self-tests
+ [KNL] Disable crypto self-tests
cs89x0_dma= [HW,NET]
Format: <dma>
@@ -746,7 +741,7 @@
Format: <port#>,<type>
See also Documentation/input/devices/joystick-parport.rst
- ddebug_query= [KNL,DYNAMIC_DEBUG] Enable debug messages at early boot
+ ddebug_query= [KNL,DYNAMIC_DEBUG] Enable debug messages at early boot
time. See
Documentation/admin-guide/dynamic-debug-howto.rst for
details. Deprecated, see dyndbg.
@@ -833,7 +828,7 @@
causing system reset or hang due to sending
INIT from AP to BSP.
- disable_ddw [PPC/PSERIES]
+ disable_ddw [PPC/PSERIES]
Disable Dynamic DMA Window support. Use this if
to workaround buggy firmware.
@@ -1188,7 +1183,7 @@
parameter will force ia64_sal_cache_flush to call
ia64_pal_cache_flush instead of SAL_CACHE_FLUSH.
- forcepae [X86-32]
+ forcepae [X86-32]
Forcefully enable Physical Address Extension (PAE).
Many Pentium M systems disable PAE but may have a
functionally usable PAE implementation.
@@ -1247,7 +1242,7 @@
gamma= [HW,DRM]
- gart_fix_e820= [X86_64] disable the fix e820 for K8 GART
+ gart_fix_e820= [X86_64] disable the fix e820 for K8 GART
Format: off | on
default: on
@@ -1341,23 +1336,32 @@
x86-64 are 2M (when the CPU supports "pse") and 1G
(when the CPU supports the "pdpe1gb" cpuinfo flag).
- hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC)
- terminal devices. Valid values: 0..8
- hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs.
- If specified, z/VM IUCV HVC accepts connections
- from listed z/VM user IDs only.
+ hung_task_panic=
+ [KNL] Should the hung task detector generate panics.
+ Format: <integer>
+ A nonzero value instructs the kernel to panic when a
+ hung task is detected. The default value is controlled
+ by the CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time
+ option. The value selected by this boot parameter can
+ be changed later by the kernel.hung_task_panic sysctl.
+
+ hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC)
+ terminal devices. Valid values: 0..8
+ hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs.
+ If specified, z/VM IUCV HVC accepts connections
+ from listed z/VM user IDs only.
keep_bootcon [KNL]
Do not unregister boot console at start. This is only
useful for debugging when something happens in the window
between unregistering the boot console and initializing
the real console.
- i2c_bus= [HW] Override the default board specific I2C bus speed
- or register an additional I2C bus that is not
- registered from board initialization code.
- Format:
- <bus_id>,<clkrate>
+ i2c_bus= [HW] Override the default board specific I2C bus speed
+ or register an additional I2C bus that is not
+ registered from board initialization code.
+ Format:
+ <bus_id>,<clkrate>
i8042.debug [HW] Toggle i8042 debug mode
i8042.unmask_kbd_data
@@ -1386,7 +1390,7 @@
Default: only on s2r transitions on x86; most other
architectures force reset to be always executed
i8042.unlock [HW] Unlock (ignore) the keylock
- i8042.kbdreset [HW] Reset device connected to KBD port
+ i8042.kbdreset [HW] Reset device connected to KBD port
i810= [HW,DRM]
@@ -1548,13 +1552,13 @@
programs exec'd, files mmap'd for exec, and all files
opened for read by uid=0.
- ima_template= [IMA]
+ ima_template= [IMA]
Select one of defined IMA measurements template formats.
Formats: { "ima" | "ima-ng" | "ima-sig" }
Default: "ima-ng"
ima_template_fmt=
- [IMA] Define a custom template format.
+ [IMA] Define a custom template format.
Format: { "field1|...|fieldN" }
ima.ahash_minsize= [IMA] Minimum file size for asynchronous hash usage
@@ -1597,7 +1601,7 @@
inport.irq= [HW] Inport (ATI XL and Microsoft) busmouse driver
Format: <irq>
- int_pln_enable [x86] Enable power limit notification interrupt
+ int_pln_enable [x86] Enable power limit notification interrupt
integrity_audit=[IMA]
Format: { "0" | "1" }
@@ -1650,39 +1654,39 @@
0 disables intel_idle and fall back on acpi_idle.
1 to 9 specify maximum depth of C-state.
- intel_pstate= [X86]
- disable
- Do not enable intel_pstate as the default
- scaling driver for the supported processors
- passive
- Use intel_pstate as a scaling driver, but configure it
- to work with generic cpufreq governors (instead of
- enabling its internal governor). This mode cannot be
- used along with the hardware-managed P-states (HWP)
- feature.
- force
- Enable intel_pstate on systems that prohibit it by default
- in favor of acpi-cpufreq. Forcing the intel_pstate driver
- instead of acpi-cpufreq may disable platform features, such
- as thermal controls and power capping, that rely on ACPI
- P-States information being indicated to OSPM and therefore
- should be used with caution. This option does not work with
- processors that aren't supported by the intel_pstate driver
- or on platforms that use pcc-cpufreq instead of acpi-cpufreq.
- no_hwp
- Do not enable hardware P state control (HWP)
- if available.
- hwp_only
- Only load intel_pstate on systems which support
- hardware P state control (HWP) if available.
- support_acpi_ppc
- Enforce ACPI _PPC performance limits. If the Fixed ACPI
- Description Table, specifies preferred power management
- profile as "Enterprise Server" or "Performance Server",
- then this feature is turned on by default.
- per_cpu_perf_limits
- Allow per-logical-CPU P-State performance control limits using
- cpufreq sysfs interface
+ intel_pstate= [X86]
+ disable
+ Do not enable intel_pstate as the default
+ scaling driver for the supported processors
+ passive
+ Use intel_pstate as a scaling driver, but configure it
+ to work with generic cpufreq governors (instead of
+ enabling its internal governor). This mode cannot be
+ used along with the hardware-managed P-states (HWP)
+ feature.
+ force
+ Enable intel_pstate on systems that prohibit it by default
+ in favor of acpi-cpufreq. Forcing the intel_pstate driver
+ instead of acpi-cpufreq may disable platform features, such
+ as thermal controls and power capping, that rely on ACPI
+ P-States information being indicated to OSPM and therefore
+ should be used with caution. This option does not work with
+ processors that aren't supported by the intel_pstate driver
+ or on platforms that use pcc-cpufreq instead of acpi-cpufreq.
+ no_hwp
+ Do not enable hardware P state control (HWP)
+ if available.
+ hwp_only
+ Only load intel_pstate on systems which support
+ hardware P state control (HWP) if available.
+ support_acpi_ppc
+ Enforce ACPI _PPC performance limits. If the Fixed ACPI
+ Description Table, specifies preferred power management
+ profile as "Enterprise Server" or "Performance Server",
+ then this feature is turned on by default.
+ per_cpu_perf_limits
+ Allow per-logical-CPU P-State performance control limits using
+ cpufreq sysfs interface
intremap= [X86-64, Intel-IOMMU]
on enable Interrupt Remapping (default)
@@ -1705,7 +1709,6 @@
nopanic
merge
nomerge
- forcesac
soft
pt [x86, IA-64]
nobypass [PPC/POWERNV]
@@ -2027,7 +2030,7 @@
* [no]ncqtrim: Turn off queued DSM TRIM.
* nohrst, nosrst, norst: suppress hard, soft
- and both resets.
+ and both resets.
* rstonce: only attempt one reset during
hot-unplug link recovery
@@ -2215,7 +2218,7 @@
[KNL,SH] Allow user to override the default size for
per-device physically contiguous DMA buffers.
- memhp_default_state=online/offline
+ memhp_default_state=online/offline
[KNL] Set the initial state for the memory hotplug
onlining policy. If not specified, the default value is
set according to the
@@ -2600,6 +2603,9 @@
emulation library even if a 387 maths coprocessor
is present.
+ no5lvl [X86-64] Disable 5-level paging mode. Forces
+ kernel to use 4-level paging instead.
+
no_console_suspend
[HW] Never suspend the console
Disable suspending of consoles during suspend and
@@ -2680,6 +2686,9 @@
allow data leaks with this option, which is equivalent
to spectre_v2=off.
+ nospec_store_bypass_disable
+ [HW] Disable all mitigations for the Speculative Store Bypass vulnerability
+
noxsave [BUGS=X86] Disables x86 extended register state save
and restore using xsave. The kernel will fallback to
enabling legacy floating-point and sse state.
@@ -2762,7 +2771,7 @@
[X86,PV_OPS] Disable paravirtualized VMware scheduler
clock and use the default one.
- no-steal-acc [X86,KVM] Disable paravirtualized steal time accounting.
+ no-steal-acc [X86,KVM] Disable paravirtualized steal time accounting.
steal time is computed, but won't influence scheduler
behaviour
@@ -2823,7 +2832,7 @@
notsc [BUGS=X86-32] Disable Time Stamp Counter
nowatchdog [KNL] Disable both lockup detectors, i.e.
- soft-lockup and NMI watchdog (hard-lockup).
+ soft-lockup and NMI watchdog (hard-lockup).
nowb [ARM]
@@ -2843,7 +2852,7 @@
If the dependencies are under your control, you can
turn on cpu0_hotplug.
- nps_mtm_hs_ctr= [KNL,ARC]
+ nps_mtm_hs_ctr= [KNL,ARC]
This parameter sets the maximum duration, in
cycles, each HW thread of the CTOP can run
without interruptions, before HW switches it.
@@ -2984,7 +2993,7 @@
pci=option[,option...] [PCI] various PCI subsystem options:
earlydump [X86] dump PCI config space before the kernel
- changes anything
+ changes anything
off [X86] don't probe for the PCI bus
bios [X86-32] force use of PCI BIOS, don't access
the hardware directly. Use this if your machine
@@ -3072,7 +3081,7 @@
is enabled by default. If you need to use this,
please report a bug.
nocrs [X86] Ignore PCI host bridge windows from ACPI.
- If you need to use this, please report a bug.
+ If you need to use this, please report a bug.
routeirq Do IRQ routing for all PCI devices.
This is normally done in pci_enable_device(),
so this option is a temporary workaround
@@ -3915,7 +3924,7 @@
cache (risks via metadata attacks are mostly
unchanged). Debug options disable merging on their
own.
- For more information see Documentation/vm/slub.txt.
+ For more information see Documentation/vm/slub.rst.
slab_max_order= [MM, SLAB]
Determines the maximum allowed order for slabs.
@@ -3929,7 +3938,7 @@
slub_debug can create guard zones around objects and
may poison objects when not in use. Also tracks the
last alloc / free. For more information see
- Documentation/vm/slub.txt.
+ Documentation/vm/slub.rst.
slub_memcg_sysfs= [MM, SLUB]
Determines whether to enable sysfs directories for
@@ -3943,7 +3952,7 @@
Determines the maximum allowed order for slabs.
A high setting may cause OOMs due to memory
fragmentation. For more information see
- Documentation/vm/slub.txt.
+ Documentation/vm/slub.rst.
slub_min_objects= [MM, SLUB]
The minimum number of objects per slab. SLUB will
@@ -3952,12 +3961,12 @@
the number of objects indicated. The higher the number
of objects the smaller the overhead of tracking slabs
and the less frequently locks need to be acquired.
- For more information see Documentation/vm/slub.txt.
+ For more information see Documentation/vm/slub.rst.
slub_min_order= [MM, SLUB]
Determines the minimum page order for slabs. Must be
lower than slub_max_order.
- For more information see Documentation/vm/slub.txt.
+ For more information see Documentation/vm/slub.rst.
slub_nomerge [MM, SLUB]
Same with slab_nomerge. This is supported for legacy.
@@ -4025,6 +4034,48 @@
Not specifying this option is equivalent to
spectre_v2=auto.
+ spec_store_bypass_disable=
+ [HW] Control Speculative Store Bypass (SSB) Disable mitigation
+ (Speculative Store Bypass vulnerability)
+
+ Certain CPUs are vulnerable to an exploit against a
+ a common industry wide performance optimization known
+ as "Speculative Store Bypass" in which recent stores
+ to the same memory location may not be observed by
+ later loads during speculative execution. The idea
+ is that such stores are unlikely and that they can
+ be detected prior to instruction retirement at the
+ end of a particular speculation execution window.
+
+ In vulnerable processors, the speculatively forwarded
+ store can be used in a cache side channel attack, for
+ example to read memory to which the attacker does not
+ directly have access (e.g. inside sandboxed code).
+
+ This parameter controls whether the Speculative Store
+ Bypass optimization is used.
+
+ on - Unconditionally disable Speculative Store Bypass
+ off - Unconditionally enable Speculative Store Bypass
+ auto - Kernel detects whether the CPU model contains an
+ implementation of Speculative Store Bypass and
+ picks the most appropriate mitigation. If the
+ CPU is not vulnerable, "off" is selected. If the
+ CPU is vulnerable the default mitigation is
+ architecture and Kconfig dependent. See below.
+ prctl - Control Speculative Store Bypass per thread
+ via prctl. Speculative Store Bypass is enabled
+ for a process by default. The state of the control
+ is inherited on fork.
+ seccomp - Same as "prctl" above, but all seccomp threads
+ will disable SSB unless they explicitly opt out.
+
+ Not specifying this option is equivalent to
+ spec_store_bypass_disable=auto.
+
+ Default mitigations:
+ X86: If CONFIG_SECCOMP=y "seccomp", otherwise "prctl"
+
spia_io_base= [HW,MTD]
spia_fio_base=
spia_pedr=
@@ -4313,7 +4364,8 @@
Format: [always|madvise|never]
Can be used to control the default behavior of the system
with respect to transparent hugepages.
- See Documentation/vm/transhuge.txt for more details.
+ See Documentation/admin-guide/mm/transhuge.rst
+ for more details.
tsc= Disable clocksource stability checks for TSC.
Format: <string>
@@ -4391,7 +4443,7 @@
usbcore.initial_descriptor_timeout=
[USB] Specifies timeout for the initial 64-byte
- USB_REQ_GET_DESCRIPTOR request in milliseconds
+ USB_REQ_GET_DESCRIPTOR request in milliseconds
(default 5000 = 5.0 seconds).
usbcore.nousb [USB] Disable the USB subsystem
diff --git a/Documentation/admin-guide/mm/concepts.rst b/Documentation/admin-guide/mm/concepts.rst
new file mode 100644
index 0000000..291699c
--- /dev/null
+++ b/Documentation/admin-guide/mm/concepts.rst
@@ -0,0 +1,222 @@
+.. _mm_concepts:
+
+=================
+Concepts overview
+=================
+
+The memory management in Linux is complex system that evolved over the
+years and included more and more functionality to support variety of
+systems from MMU-less microcontrollers to supercomputers. The memory
+management for systems without MMU is called ``nommu`` and it
+definitely deserves a dedicated document, which hopefully will be
+eventually written. Yet, although some of the concepts are the same,
+here we assume that MMU is available and CPU can translate a virtual
+address to a physical address.
+
+.. contents:: :local:
+
+Virtual Memory Primer
+=====================
+
+The physical memory in a computer system is a limited resource and
+even for systems that support memory hotplug there is a hard limit on
+the amount of memory that can be installed. The physical memory is not
+necessary contiguous, it might be accessible as a set of distinct
+address ranges. Besides, different CPU architectures, and even
+different implementations of the same architecture have different view
+how these address ranges defined.
+
+All this makes dealing directly with physical memory quite complex and
+to avoid this complexity a concept of virtual memory was developed.
+
+The virtual memory abstracts the details of physical memory from the
+application software, allows to keep only needed information in the
+physical memory (demand paging) and provides a mechanism for the
+protection and controlled sharing of data between processes.
+
+With virtual memory, each and every memory access uses a virtual
+address. When the CPU decodes the an instruction that reads (or
+writes) from (or to) the system memory, it translates the `virtual`
+address encoded in that instruction to a `physical` address that the
+memory controller can understand.
+
+The physical system memory is divided into page frames, or pages. The
+size of each page is architecture specific. Some architectures allow
+selection of the page size from several supported values; this
+selection is performed at the kernel build time by setting an
+appropriate kernel configuration option.
+
+Each physical memory page can be mapped as one or more virtual
+pages. These mappings are described by page tables that allow
+translation from virtual address used by programs to real address in
+the physical memory. The page tables organized hierarchically.
+
+The tables at the lowest level of the hierarchy contain physical
+addresses of actual pages used by the software. The tables at higher
+levels contain physical addresses of the pages belonging to the lower
+levels. The pointer to the top level page table resides in a
+register. When the CPU performs the address translation, it uses this
+register to access the top level page table. The high bits of the
+virtual address are used to index an entry in the top level page
+table. That entry is then used to access the next level in the
+hierarchy with the next bits of the virtual address as the index to
+that level page table. The lowest bits in the virtual address define
+the offset inside the actual page.
+
+Huge Pages
+==========
+
+The address translation requires several memory accesses and memory
+accesses are slow relatively to CPU speed. To avoid spending precious
+processor cycles on the address translation, CPUs maintain a cache of
+such translations called Translation Lookaside Buffer (or
+TLB). Usually TLB is pretty scarce resource and applications with
+large memory working set will experience performance hit because of
+TLB misses.
+
+Many modern CPU architectures allow mapping of the memory pages
+directly by the higher levels in the page table. For instance, on x86,
+it is possible to map 2M and even 1G pages using entries in the second
+and the third level page tables. In Linux such pages are called
+`huge`. Usage of huge pages significantly reduces pressure on TLB,
+improves TLB hit-rate and thus improves overall system performance.
+
+There are two mechanisms in Linux that enable mapping of the physical
+memory with the huge pages. The first one is `HugeTLB filesystem`, or
+hugetlbfs. It is a pseudo filesystem that uses RAM as its backing
+store. For the files created in this filesystem the data resides in
+the memory and mapped using huge pages. The hugetlbfs is described at
+:ref:`Documentation/admin-guide/mm/hugetlbpage.rst <hugetlbpage>`.
+
+Another, more recent, mechanism that enables use of the huge pages is
+called `Transparent HugePages`, or THP. Unlike the hugetlbfs that
+requires users and/or system administrators to configure what parts of
+the system memory should and can be mapped by the huge pages, THP
+manages such mappings transparently to the user and hence the
+name. See
+:ref:`Documentation/admin-guide/mm/transhuge.rst <admin_guide_transhuge>`
+for more details about THP.
+
+Zones
+=====
+
+Often hardware poses restrictions on how different physical memory
+ranges can be accessed. In some cases, devices cannot perform DMA to
+all the addressable memory. In other cases, the size of the physical
+memory exceeds the maximal addressable size of virtual memory and
+special actions are required to access portions of the memory. Linux
+groups memory pages into `zones` according to their possible
+usage. For example, ZONE_DMA will contain memory that can be used by
+devices for DMA, ZONE_HIGHMEM will contain memory that is not
+permanently mapped into kernel's address space and ZONE_NORMAL will
+contain normally addressed pages.
+
+The actual layout of the memory zones is hardware dependent as not all
+architectures define all zones, and requirements for DMA are different
+for different platforms.
+
+Nodes
+=====
+
+Many multi-processor machines are NUMA - Non-Uniform Memory Access -
+systems. In such systems the memory is arranged into banks that have
+different access latency depending on the "distance" from the
+processor. Each bank is referred as `node` and for each node Linux
+constructs an independent memory management subsystem. A node has it's
+own set of zones, lists of free and used pages and various statistics
+counters. You can find more details about NUMA in
+:ref:`Documentation/vm/numa.rst <numa>` and in
+:ref:`Documentation/admin-guide/mm/numa_memory_policy.rst <numa_memory_policy>`.
+
+Page cache
+==========
+
+The physical memory is volatile and the common case for getting data
+into the memory is to read it from files. Whenever a file is read, the
+data is put into the `page cache` to avoid expensive disk access on
+the subsequent reads. Similarly, when one writes to a file, the data
+is placed in the page cache and eventually gets into the backing
+storage device. The written pages are marked as `dirty` and when Linux
+decides to reuse them for other purposes, it makes sure to synchronize
+the file contents on the device with the updated data.
+
+Anonymous Memory
+================
+
+The `anonymous memory` or `anonymous mappings` represent memory that
+is not backed by a filesystem. Such mappings are implicitly created
+for program's stack and heap or by explicit calls to mmap(2) system
+call. Usually, the anonymous mappings only define virtual memory areas
+that the program is allowed to access. The read accesses will result
+in creation of a page table entry that references a special physical
+page filled with zeroes. When the program performs a write, regular
+physical page will be allocated to hold the written data. The page
+will be marked dirty and if the kernel will decide to repurpose it,
+the dirty page will be swapped out.
+
+Reclaim
+=======
+
+Throughout the system lifetime, a physical page can be used for storing
+different types of data. It can be kernel internal data structures,
+DMA'able buffers for device drivers use, data read from a filesystem,
+memory allocated by user space processes etc.
+
+Depending on the page usage it is treated differently by the Linux
+memory management. The pages that can be freed at any time, either
+because they cache the data available elsewhere, for instance, on a
+hard disk, or because they can be swapped out, again, to the hard
+disk, are called `reclaimable`. The most notable categories of the
+reclaimable pages are page cache and anonymous memory.
+
+In most cases, the pages holding internal kernel data and used as DMA
+buffers cannot be repurposed, and they remain pinned until freed by
+their user. Such pages are called `unreclaimable`. However, in certain
+circumstances, even pages occupied with kernel data structures can be
+reclaimed. For instance, in-memory caches of filesystem metadata can
+be re-read from the storage device and therefore it is possible to
+discard them from the main memory when system is under memory
+pressure.
+
+The process of freeing the reclaimable physical memory pages and
+repurposing them is called (surprise!) `reclaim`. Linux can reclaim
+pages either asynchronously or synchronously, depending on the state
+of the system. When system is not loaded, most of the memory is free
+and allocation request will be satisfied immediately from the free
+pages supply. As the load increases, the amount of the free pages goes
+down and when it reaches a certain threshold (high watermark), an
+allocation request will awaken the ``kswapd`` daemon. It will
+asynchronously scan memory pages and either just free them if the data
+they contain is available elsewhere, or evict to the backing storage
+device (remember those dirty pages?). As memory usage increases even
+more and reaches another threshold - min watermark - an allocation
+will trigger the `direct reclaim`. In this case allocation is stalled
+until enough memory pages are reclaimed to satisfy the request.
+
+Compaction
+==========
+
+As the system runs, tasks allocate and free the memory and it becomes
+fragmented. Although with virtual memory it is possible to present
+scattered physical pages as virtually contiguous range, sometimes it is
+necessary to allocate large physically contiguous memory areas. Such
+need may arise, for instance, when a device driver requires large
+buffer for DMA, or when THP allocates a huge page. Memory `compaction`
+addresses the fragmentation issue. This mechanism moves occupied pages
+from the lower part of a memory zone to free pages in the upper part
+of the zone. When a compaction scan is finished free pages are grouped
+together at the beginning of the zone and allocations of large
+physically contiguous areas become possible.
+
+Like reclaim, the compaction may happen asynchronously in ``kcompactd``
+daemon or synchronously as a result of memory allocation request.
+
+OOM killer
+==========
+
+It may happen, that on a loaded machine memory will be exhausted. When
+the kernel detects that the system runs out of memory (OOM) it invokes
+`OOM killer`. Its mission is simple: all it has to do is to select a
+task to sacrifice for the sake of the overall system health. The
+selected task is killed in a hope that after it exits enough memory
+will be freed to continue normal operation.
diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/admin-guide/mm/hugetlbpage.rst
similarity index 61%
rename from Documentation/vm/hugetlbpage.txt
rename to Documentation/admin-guide/mm/hugetlbpage.rst
index faf077d..1cc0bc7 100644
--- a/Documentation/vm/hugetlbpage.txt
+++ b/Documentation/admin-guide/mm/hugetlbpage.rst
@@ -1,3 +1,11 @@
+.. _hugetlbpage:
+
+=============
+HugeTLB Pages
+=============
+
+Overview
+========
The intent of this file is to give a brief summary of hugetlbpage support in
the Linux kernel. This support is built on top of multiple page size support
@@ -18,53 +26,59 @@
automatically when CONFIG_HUGETLBFS is selected) configuration
options.
-The /proc/meminfo file provides information about the total number of
+The ``/proc/meminfo`` file provides information about the total number of
persistent hugetlb pages in the kernel's huge page pool. It also displays
default huge page size and information about the number of free, reserved
and surplus huge pages in the pool of huge pages of default size.
The huge page size is needed for generating the proper alignment and
size of the arguments to system calls that map huge page regions.
-The output of "cat /proc/meminfo" will include lines like:
+The output of ``cat /proc/meminfo`` will include lines like::
-.....
-HugePages_Total: uuu
-HugePages_Free: vvv
-HugePages_Rsvd: www
-HugePages_Surp: xxx
-Hugepagesize: yyy kB
-Hugetlb: zzz kB
+ HugePages_Total: uuu
+ HugePages_Free: vvv
+ HugePages_Rsvd: www
+ HugePages_Surp: xxx
+ Hugepagesize: yyy kB
+ Hugetlb: zzz kB
where:
-HugePages_Total is the size of the pool of huge pages.
-HugePages_Free is the number of huge pages in the pool that are not yet
- allocated.
-HugePages_Rsvd is short for "reserved," and is the number of huge pages for
- which a commitment to allocate from the pool has been made,
- but no allocation has yet been made. Reserved huge pages
- guarantee that an application will be able to allocate a
- huge page from the pool of huge pages at fault time.
-HugePages_Surp is short for "surplus," and is the number of huge pages in
- the pool above the value in /proc/sys/vm/nr_hugepages. The
- maximum number of surplus huge pages is controlled by
- /proc/sys/vm/nr_overcommit_hugepages.
-Hugepagesize is the default hugepage size (in Kb).
-Hugetlb is the total amount of memory (in kB), consumed by huge
- pages of all sizes.
- If huge pages of different sizes are in use, this number
- will exceed HugePages_Total * Hugepagesize. To get more
- detailed information, please, refer to
- /sys/kernel/mm/hugepages (described below).
+
+HugePages_Total
+ is the size of the pool of huge pages.
+HugePages_Free
+ is the number of huge pages in the pool that are not yet
+ allocated.
+HugePages_Rsvd
+ is short for "reserved," and is the number of huge pages for
+ which a commitment to allocate from the pool has been made,
+ but no allocation has yet been made. Reserved huge pages
+ guarantee that an application will be able to allocate a
+ huge page from the pool of huge pages at fault time.
+HugePages_Surp
+ is short for "surplus," and is the number of huge pages in
+ the pool above the value in ``/proc/sys/vm/nr_hugepages``. The
+ maximum number of surplus huge pages is controlled by
+ ``/proc/sys/vm/nr_overcommit_hugepages``.
+Hugepagesize
+ is the default hugepage size (in Kb).
+Hugetlb
+ is the total amount of memory (in kB), consumed by huge
+ pages of all sizes.
+ If huge pages of different sizes are in use, this number
+ will exceed HugePages_Total \* Hugepagesize. To get more
+ detailed information, please, refer to
+ ``/sys/kernel/mm/hugepages`` (described below).
-/proc/filesystems should also show a filesystem of type "hugetlbfs" configured
-in the kernel.
+``/proc/filesystems`` should also show a filesystem of type "hugetlbfs"
+configured in the kernel.
-/proc/sys/vm/nr_hugepages indicates the current number of "persistent" huge
+``/proc/sys/vm/nr_hugepages`` indicates the current number of "persistent" huge
pages in the kernel's huge page pool. "Persistent" huge pages will be
returned to the huge page pool when freed by a task. A user with root
privileges can dynamically allocate more or free some persistent huge pages
-by increasing or decreasing the value of 'nr_hugepages'.
+by increasing or decreasing the value of ``nr_hugepages``.
Pages that are used as huge pages are reserved inside the kernel and cannot
be used for other purposes. Huge pages cannot be swapped out under
@@ -73,7 +87,7 @@
Once a number of huge pages have been pre-allocated to the kernel huge page
pool, a user with appropriate privilege can use either the mmap system call
or shared memory system calls to use the huge pages. See the discussion of
-Using Huge Pages, below.
+:ref:`Using Huge Pages <using_huge_pages>`, below.
The administrator can allocate persistent huge pages on the kernel boot
command line by specifying the "hugepages=N" parameter, where 'N' = the
@@ -86,10 +100,10 @@
be specified in bytes with optional scale suffix [kKmMgG]. The default huge
page size may be selected with the "default_hugepagesz=<size>" boot parameter.
-When multiple huge page sizes are supported, /proc/sys/vm/nr_hugepages
+When multiple huge page sizes are supported, ``/proc/sys/vm/nr_hugepages``
indicates the current number of pre-allocated huge pages of the default size.
Thus, one can use the following command to dynamically allocate/deallocate
-default sized persistent huge pages:
+default sized persistent huge pages::
echo 20 > /proc/sys/vm/nr_hugepages
@@ -98,11 +112,12 @@
On a NUMA platform, the kernel will attempt to distribute the huge page pool
over all the set of allowed nodes specified by the NUMA memory policy of the
-task that modifies nr_hugepages. The default for the allowed nodes--when the
+task that modifies ``nr_hugepages``. The default for the allowed nodes--when the
task has default memory policy--is all on-line nodes with memory. Allowed
nodes with insufficient available, contiguous memory for a huge page will be
-silently skipped when allocating persistent huge pages. See the discussion
-below of the interaction of task memory policy, cpusets and per node attributes
+silently skipped when allocating persistent huge pages. See the
+:ref:`discussion below <mem_policy_and_hp_alloc>`
+of the interaction of task memory policy, cpusets and per node attributes
with the allocation and freeing of persistent huge pages.
The success or failure of huge page allocation depends on the amount of
@@ -117,51 +132,52 @@
the boot process when the possibility of getting physical contiguous pages
is still very high. Administrators can verify the number of huge pages
actually allocated by checking the sysctl or meminfo. To check the per node
-distribution of huge pages in a NUMA system, use:
+distribution of huge pages in a NUMA system, use::
cat /sys/devices/system/node/node*/meminfo | fgrep Huge
-/proc/sys/vm/nr_overcommit_hugepages specifies how large the pool of
-huge pages can grow, if more huge pages than /proc/sys/vm/nr_hugepages are
+``/proc/sys/vm/nr_overcommit_hugepages`` specifies how large the pool of
+huge pages can grow, if more huge pages than ``/proc/sys/vm/nr_hugepages`` are
requested by applications. Writing any non-zero value into this file
indicates that the hugetlb subsystem is allowed to try to obtain that
number of "surplus" huge pages from the kernel's normal page pool, when the
persistent huge page pool is exhausted. As these surplus huge pages become
unused, they are freed back to the kernel's normal page pool.
-When increasing the huge page pool size via nr_hugepages, any existing surplus
-pages will first be promoted to persistent huge pages. Then, additional
+When increasing the huge page pool size via ``nr_hugepages``, any existing
+surplus pages will first be promoted to persistent huge pages. Then, additional
huge pages will be allocated, if necessary and if possible, to fulfill
the new persistent huge page pool size.
The administrator may shrink the pool of persistent huge pages for
-the default huge page size by setting the nr_hugepages sysctl to a
+the default huge page size by setting the ``nr_hugepages`` sysctl to a
smaller value. The kernel will attempt to balance the freeing of huge pages
-across all nodes in the memory policy of the task modifying nr_hugepages.
+across all nodes in the memory policy of the task modifying ``nr_hugepages``.
Any free huge pages on the selected nodes will be freed back to the kernel's
normal page pool.
-Caveat: Shrinking the persistent huge page pool via nr_hugepages such that
+Caveat: Shrinking the persistent huge page pool via ``nr_hugepages`` such that
it becomes less than the number of huge pages in use will convert the balance
of the in-use huge pages to surplus huge pages. This will occur even if
-the number of surplus pages it would exceed the overcommit value. As long as
-this condition holds--that is, until nr_hugepages+nr_overcommit_hugepages is
+the number of surplus pages would exceed the overcommit value. As long as
+this condition holds--that is, until ``nr_hugepages+nr_overcommit_hugepages`` is
increased sufficiently, or the surplus huge pages go out of use and are freed--
no more surplus huge pages will be allowed to be allocated.
With support for multiple huge page pools at run-time available, much of
-the huge page userspace interface in /proc/sys/vm has been duplicated in sysfs.
-The /proc interfaces discussed above have been retained for backwards
-compatibility. The root huge page control directory in sysfs is:
+the huge page userspace interface in ``/proc/sys/vm`` has been duplicated in
+sysfs.
+The ``/proc`` interfaces discussed above have been retained for backwards
+compatibility. The root huge page control directory in sysfs is::
/sys/kernel/mm/hugepages
For each huge page size supported by the running kernel, a subdirectory
-will exist, of the form:
+will exist, of the form::
hugepages-${size}kB
-Inside each of these directories, the same set of files will exist:
+Inside each of these directories, the same set of files will exist::
nr_hugepages
nr_hugepages_mempolicy
@@ -172,37 +188,39 @@
which function as described above for the default huge page-sized case.
+.. _mem_policy_and_hp_alloc:
Interaction of Task Memory Policy with Huge Page Allocation/Freeing
===================================================================
-Whether huge pages are allocated and freed via the /proc interface or
-the /sysfs interface using the nr_hugepages_mempolicy attribute, the NUMA
-nodes from which huge pages are allocated or freed are controlled by the
-NUMA memory policy of the task that modifies the nr_hugepages_mempolicy
-sysctl or attribute. When the nr_hugepages attribute is used, mempolicy
+Whether huge pages are allocated and freed via the ``/proc`` interface or
+the ``/sysfs`` interface using the ``nr_hugepages_mempolicy`` attribute, the
+NUMA nodes from which huge pages are allocated or freed are controlled by the
+NUMA memory policy of the task that modifies the ``nr_hugepages_mempolicy``
+sysctl or attribute. When the ``nr_hugepages`` attribute is used, mempolicy
is ignored.
The recommended method to allocate or free huge pages to/from the kernel
-huge page pool, using the nr_hugepages example above, is:
+huge page pool, using the ``nr_hugepages`` example above, is::
numactl --interleave <node-list> echo 20 \
>/proc/sys/vm/nr_hugepages_mempolicy
-or, more succinctly:
+or, more succinctly::
numactl -m <node-list> echo 20 >/proc/sys/vm/nr_hugepages_mempolicy
-This will allocate or free abs(20 - nr_hugepages) to or from the nodes
+This will allocate or free ``abs(20 - nr_hugepages)`` to or from the nodes
specified in <node-list>, depending on whether number of persistent huge pages
is initially less than or greater than 20, respectively. No huge pages will be
allocated nor freed on any node not included in the specified <node-list>.
-When adjusting the persistent hugepage count via nr_hugepages_mempolicy, any
+When adjusting the persistent hugepage count via ``nr_hugepages_mempolicy``, any
memory policy mode--bind, preferred, local or interleave--may be used. The
resulting effect on persistent huge page allocation is as follows:
-1) Regardless of mempolicy mode [see Documentation/vm/numa_memory_policy.txt],
+#. Regardless of mempolicy mode [see
+ :ref:`Documentation/admin-guide/mm/numa_memory_policy.rst <numa_memory_policy>`],
persistent huge pages will be distributed across the node or nodes
specified in the mempolicy as if "interleave" had been specified.
However, if a node in the policy does not contain sufficient contiguous
@@ -212,7 +230,7 @@
possibly, allocation of persistent huge pages on nodes not allowed by
the task's memory policy.
-2) One or more nodes may be specified with the bind or interleave policy.
+#. One or more nodes may be specified with the bind or interleave policy.
If more than one node is specified with the preferred policy, only the
lowest numeric id will be used. Local policy will select the node where
the task is running at the time the nodes_allowed mask is constructed.
@@ -222,20 +240,20 @@
indeterminate. Thus, local policy is not very useful for this purpose.
Any of the other mempolicy modes may be used to specify a single node.
-3) The nodes allowed mask will be derived from any non-default task mempolicy,
+#. The nodes allowed mask will be derived from any non-default task mempolicy,
whether this policy was set explicitly by the task itself or one of its
ancestors, such as numactl. This means that if the task is invoked from a
shell with non-default policy, that policy will be used. One can specify a
node list of "all" with numactl --interleave or --membind [-m] to achieve
interleaving over all nodes in the system or cpuset.
-4) Any task mempolicy specified--e.g., using numactl--will be constrained by
+#. Any task mempolicy specified--e.g., using numactl--will be constrained by
the resource limits of any cpuset in which the task runs. Thus, there will
be no way for a task with non-default policy running in a cpuset with a
subset of the system nodes to allocate huge pages outside the cpuset
without first moving to a cpuset that contains all of the desired nodes.
-5) Boot-time huge page allocation attempts to distribute the requested number
+#. Boot-time huge page allocation attempts to distribute the requested number
of huge pages over all on-lines nodes with memory.
Per Node Hugepages Attributes
@@ -243,22 +261,22 @@
A subset of the contents of the root huge page control directory in sysfs,
described above, will be replicated under each the system device of each
-NUMA node with memory in:
+NUMA node with memory in::
/sys/devices/system/node/node[0-9]*/hugepages/
Under this directory, the subdirectory for each supported huge page size
-contains the following attribute files:
+contains the following attribute files::
nr_hugepages
free_hugepages
surplus_hugepages
-The free_' and surplus_' attribute files are read-only. They return the number
+The free\_' and surplus\_' attribute files are read-only. They return the number
of free and surplus [overcommitted] huge pages, respectively, on the parent
node.
-The nr_hugepages attribute returns the total number of huge pages on the
+The ``nr_hugepages`` attribute returns the total number of huge pages on the
specified node. When this attribute is written, the number of persistent huge
pages on the parent node will be adjusted to the specified value, if sufficient
resources exist, regardless of the task's mempolicy or cpuset constraints.
@@ -267,43 +285,58 @@
as we don't know until fault time, when the faulting task's mempolicy is
applied, from which node the huge page allocation will be attempted.
+.. _using_huge_pages:
Using Huge Pages
================
If the user applications are going to request huge pages using mmap system
call, then it is required that system administrator mount a file system of
-type hugetlbfs:
+type hugetlbfs::
mount -t hugetlbfs \
-o uid=<value>,gid=<value>,mode=<value>,pagesize=<value>,size=<value>,\
min_size=<value>,nr_inodes=<value> none /mnt/huge
This command mounts a (pseudo) filesystem of type hugetlbfs on the directory
-/mnt/huge. Any files created on /mnt/huge uses huge pages. The uid and gid
-options sets the owner and group of the root of the file system. By default
-the uid and gid of the current process are taken. The mode option sets the
-mode of root of file system to value & 01777. This value is given in octal.
-By default the value 0755 is picked. If the platform supports multiple huge
-page sizes, the pagesize option can be used to specify the huge page size and
-associated pool. pagesize is specified in bytes. If pagesize is not specified
-the platform's default huge page size and associated pool will be used. The
-size option sets the maximum value of memory (huge pages) allowed for that
-filesystem (/mnt/huge). The size option can be specified in bytes, or as a
-percentage of the specified huge page pool (nr_hugepages). The size is
-rounded down to HPAGE_SIZE boundary. The min_size option sets the minimum
-value of memory (huge pages) allowed for the filesystem. min_size can be
-specified in the same way as size, either bytes or a percentage of the
-huge page pool. At mount time, the number of huge pages specified by
-min_size are reserved for use by the filesystem. If there are not enough
-free huge pages available, the mount will fail. As huge pages are allocated
-to the filesystem and freed, the reserve count is adjusted so that the sum
-of allocated and reserved huge pages is always at least min_size. The option
-nr_inodes sets the maximum number of inodes that /mnt/huge can use. If the
-size, min_size or nr_inodes option is not provided on command line then
-no limits are set. For pagesize, size, min_size and nr_inodes options, you
-can use [G|g]/[M|m]/[K|k] to represent giga/mega/kilo. For example, size=2K
-has the same meaning as size=2048.
+``/mnt/huge``. Any file created on ``/mnt/huge`` uses huge pages.
+
+The ``uid`` and ``gid`` options sets the owner and group of the root of the
+file system. By default the ``uid`` and ``gid`` of the current process
+are taken.
+
+The ``mode`` option sets the mode of root of file system to value & 01777.
+This value is given in octal. By default the value 0755 is picked.
+
+If the platform supports multiple huge page sizes, the ``pagesize`` option can
+be used to specify the huge page size and associated pool. ``pagesize``
+is specified in bytes. If ``pagesize`` is not specified the platform's
+default huge page size and associated pool will be used.
+
+The ``size`` option sets the maximum value of memory (huge pages) allowed
+for that filesystem (``/mnt/huge``). The ``size`` option can be specified
+in bytes, or as a percentage of the specified huge page pool (``nr_hugepages``).
+The size is rounded down to HPAGE_SIZE boundary.
+
+The ``min_size`` option sets the minimum value of memory (huge pages) allowed
+for the filesystem. ``min_size`` can be specified in the same way as ``size``,
+either bytes or a percentage of the huge page pool.
+At mount time, the number of huge pages specified by ``min_size`` are reserved
+for use by the filesystem.
+If there are not enough free huge pages available, the mount will fail.
+As huge pages are allocated to the filesystem and freed, the reserve count
+is adjusted so that the sum of allocated and reserved huge pages is always
+at least ``min_size``.
+
+The option ``nr_inodes`` sets the maximum number of inodes that ``/mnt/huge``
+can use.
+
+If the ``size``, ``min_size`` or ``nr_inodes`` option is not provided on
+command line then no limits are set.
+
+For ``pagesize``, ``size``, ``min_size`` and ``nr_inodes`` options, you can
+use [G|g]/[M|m]/[K|k] to represent giga/mega/kilo.
+For example, size=2K has the same meaning as size=2048.
While read system calls are supported on files that reside on hugetlb
file systems, write system calls are not.
@@ -313,12 +346,12 @@
Also, it is important to note that no such mount command is required if
applications are going to use only shmat/shmget system calls or mmap with
-MAP_HUGETLB. For an example of how to use mmap with MAP_HUGETLB see map_hugetlb
-below.
+MAP_HUGETLB. For an example of how to use mmap with MAP_HUGETLB see
+:ref:`map_hugetlb <map_hugetlb>` below.
-Users who wish to use hugetlb memory via shared memory segment should be a
-member of a supplementary group and system admin needs to configure that gid
-into /proc/sys/vm/hugetlb_shm_group. It is possible for same or different
+Users who wish to use hugetlb memory via shared memory segment should be
+members of a supplementary group and system admin needs to configure that gid
+into ``/proc/sys/vm/hugetlb_shm_group``. It is possible for same or different
applications to use any combination of mmaps and shm* calls, though the mount of
filesystem will be required for using mmap calls without MAP_HUGETLB.
@@ -332,20 +365,18 @@
Examples
========
-1) map_hugetlb: see tools/testing/selftests/vm/map_hugetlb.c
+.. _map_hugetlb:
-2) hugepage-shm: see tools/testing/selftests/vm/hugepage-shm.c
+``map_hugetlb``
+ see tools/testing/selftests/vm/map_hugetlb.c
-3) hugepage-mmap: see tools/testing/selftests/vm/hugepage-mmap.c
+``hugepage-shm``
+ see tools/testing/selftests/vm/hugepage-shm.c
-4) The libhugetlbfs (https://github.com/libhugetlbfs/libhugetlbfs) library
- provides a wide range of userspace tools to help with huge page usability,
- environment setup, and control.
+``hugepage-mmap``
+ see tools/testing/selftests/vm/hugepage-mmap.c
-Kernel development regression testing
-=====================================
+The `libhugetlbfs`_ library provides a wide range of userspace tools
+to help with huge page usability, environment setup, and control.
-The most complete set of hugetlb tests are in the libhugetlbfs repository.
-If you modify any hugetlb related code, use the libhugetlbfs test suite
-to check for regressions. In addition, if you add any new hugetlb
-functionality, please add appropriate tests to libhugetlbfs.
+.. _libhugetlbfs: https://github.com/libhugetlbfs/libhugetlbfs
diff --git a/Documentation/vm/idle_page_tracking.txt b/Documentation/admin-guide/mm/idle_page_tracking.rst
similarity index 71%
rename from Documentation/vm/idle_page_tracking.txt
rename to Documentation/admin-guide/mm/idle_page_tracking.rst
index 85dcc3b..6f7b7ca 100644
--- a/Documentation/vm/idle_page_tracking.txt
+++ b/Documentation/admin-guide/mm/idle_page_tracking.rst
@@ -1,4 +1,11 @@
-MOTIVATION
+.. _idle_page_tracking:
+
+==================
+Idle Page Tracking
+==================
+
+Motivation
+==========
The idle page tracking feature allows to track which memory pages are being
accessed by a workload and which are idle. This information can be useful for
@@ -8,10 +15,14 @@
It is enabled by CONFIG_IDLE_PAGE_TRACKING=y.
-USER API
+.. _user_api:
-The idle page tracking API is located at /sys/kernel/mm/page_idle. Currently,
-it consists of the only read-write file, /sys/kernel/mm/page_idle/bitmap.
+User API
+========
+
+The idle page tracking API is located at ``/sys/kernel/mm/page_idle``.
+Currently, it consists of the only read-write file,
+``/sys/kernel/mm/page_idle/bitmap``.
The file implements a bitmap where each bit corresponds to a memory page. The
bitmap is represented by an array of 8-byte integers, and the page at PFN #i is
@@ -19,8 +30,9 @@
set, the corresponding page is idle.
A page is considered idle if it has not been accessed since it was marked idle
-(for more details on what "accessed" actually means see the IMPLEMENTATION
-DETAILS section). To mark a page idle one has to set the bit corresponding to
+(for more details on what "accessed" actually means see the :ref:`Implementation
+Details <impl_details>` section).
+To mark a page idle one has to set the bit corresponding to
the page by writing to the file. A value written to the file is OR-ed with the
current bitmap value.
@@ -30,9 +42,9 @@
and hence such pages are never reported idle.
For huge pages the idle flag is set only on the head page, so one has to read
-/proc/kpageflags in order to correctly count idle huge pages.
+``/proc/kpageflags`` in order to correctly count idle huge pages.
-Reading from or writing to /sys/kernel/mm/page_idle/bitmap will return
+Reading from or writing to ``/sys/kernel/mm/page_idle/bitmap`` will return
-EINVAL if you are not starting the read/write on an 8-byte boundary, or
if the size of the read/write is not a multiple of 8 bytes. Writing to
this file beyond max PFN will return -ENXIO.
@@ -41,21 +53,26 @@
workload one should:
1. Mark all the workload's pages as idle by setting corresponding bits in
- /sys/kernel/mm/page_idle/bitmap. The pages can be found by reading
- /proc/pid/pagemap if the workload is represented by a process, or by
- filtering out alien pages using /proc/kpagecgroup in case the workload is
- placed in a memory cgroup.
+ ``/sys/kernel/mm/page_idle/bitmap``. The pages can be found by reading
+ ``/proc/pid/pagemap`` if the workload is represented by a process, or by
+ filtering out alien pages using ``/proc/kpagecgroup`` in case the workload
+ is placed in a memory cgroup.
2. Wait until the workload accesses its working set.
- 3. Read /sys/kernel/mm/page_idle/bitmap and count the number of bits set. If
- one wants to ignore certain types of pages, e.g. mlocked pages since they
- are not reclaimable, he or she can filter them out using /proc/kpageflags.
+ 3. Read ``/sys/kernel/mm/page_idle/bitmap`` and count the number of bits set.
+ If one wants to ignore certain types of pages, e.g. mlocked pages since they
+ are not reclaimable, he or she can filter them out using
+ ``/proc/kpageflags``.
-See Documentation/vm/pagemap.txt for more information about /proc/pid/pagemap,
-/proc/kpageflags, and /proc/kpagecgroup.
+See :ref:`Documentation/admin-guide/mm/pagemap.rst <pagemap>` for more
+information about ``/proc/pid/pagemap``, ``/proc/kpageflags``, and
+``/proc/kpagecgroup``.
-IMPLEMENTATION DETAILS
+.. _impl_details:
+
+Implementation Details
+======================
The kernel internally keeps track of accesses to user memory pages in order to
reclaim unreferenced pages first on memory shortage conditions. A page is
@@ -77,7 +94,8 @@
exceeding the dirty memory limit, it is not marked referenced.
The idle memory tracking feature adds a new page flag, the Idle flag. This flag
-is set manually, by writing to /sys/kernel/mm/page_idle/bitmap (see the USER API
+is set manually, by writing to ``/sys/kernel/mm/page_idle/bitmap`` (see the
+:ref:`User API <user_api>`
section), and cleared automatically whenever a page is referenced as defined
above.
diff --git a/Documentation/admin-guide/mm/index.rst b/Documentation/admin-guide/mm/index.rst
new file mode 100644
index 0000000..ceead68
--- /dev/null
+++ b/Documentation/admin-guide/mm/index.rst
@@ -0,0 +1,36 @@
+=================
+Memory Management
+=================
+
+Linux memory management subsystem is responsible, as the name implies,
+for managing the memory in the system. This includes implemnetation of
+virtual memory and demand paging, memory allocation both for kernel
+internal structures and user space programms, mapping of files into
+processes address space and many other cool things.
+
+Linux memory management is a complex system with many configurable
+settings. Most of these settings are available via ``/proc``
+filesystem and can be quired and adjusted using ``sysctl``. These APIs
+are described in Documentation/sysctl/vm.txt and in `man 5 proc`_.
+
+.. _man 5 proc: http://man7.org/linux/man-pages/man5/proc.5.html
+
+Linux memory management has its own jargon and if you are not yet
+familiar with it, consider reading
+:ref:`Documentation/admin-guide/mm/concepts.rst <mm_concepts>`.
+
+Here we document in detail how to interact with various mechanisms in
+the Linux memory management.
+
+.. toctree::
+ :maxdepth: 1
+
+ concepts
+ hugetlbpage
+ idle_page_tracking
+ ksm
+ numa_memory_policy
+ pagemap
+ soft-dirty
+ transhuge
+ userfaultfd
diff --git a/Documentation/admin-guide/mm/ksm.rst b/Documentation/admin-guide/mm/ksm.rst
new file mode 100644
index 0000000..9303786
--- /dev/null
+++ b/Documentation/admin-guide/mm/ksm.rst
@@ -0,0 +1,189 @@
+.. _admin_guide_ksm:
+
+=======================
+Kernel Samepage Merging
+=======================
+
+Overview
+========
+
+KSM is a memory-saving de-duplication feature, enabled by CONFIG_KSM=y,
+added to the Linux kernel in 2.6.32. See ``mm/ksm.c`` for its implementation,
+and http://lwn.net/Articles/306704/ and http://lwn.net/Articles/330589/
+
+KSM was originally developed for use with KVM (where it was known as
+Kernel Shared Memory), to fit more virtual machines into physical memory,
+by sharing the data common between them. But it can be useful to any
+application which generates many instances of the same data.
+
+The KSM daemon ksmd periodically scans those areas of user memory
+which have been registered with it, looking for pages of identical
+content which can be replaced by a single write-protected page (which
+is automatically copied if a process later wants to update its
+content). The amount of pages that KSM daemon scans in a single pass
+and the time between the passes are configured using :ref:`sysfs
+intraface <ksm_sysfs>`
+
+KSM only merges anonymous (private) pages, never pagecache (file) pages.
+KSM's merged pages were originally locked into kernel memory, but can now
+be swapped out just like other user pages (but sharing is broken when they
+are swapped back in: ksmd must rediscover their identity and merge again).
+
+Controlling KSM with madvise
+============================
+
+KSM only operates on those areas of address space which an application
+has advised to be likely candidates for merging, by using the madvise(2)
+system call::
+
+ int madvise(addr, length, MADV_MERGEABLE)
+
+The app may call
+
+::
+
+ int madvise(addr, length, MADV_UNMERGEABLE)
+
+to cancel that advice and restore unshared pages: whereupon KSM
+unmerges whatever it merged in that range. Note: this unmerging call
+may suddenly require more memory than is available - possibly failing
+with EAGAIN, but more probably arousing the Out-Of-Memory killer.
+
+If KSM is not configured into the running kernel, madvise MADV_MERGEABLE
+and MADV_UNMERGEABLE simply fail with EINVAL. If the running kernel was
+built with CONFIG_KSM=y, those calls will normally succeed: even if the
+the KSM daemon is not currently running, MADV_MERGEABLE still registers
+the range for whenever the KSM daemon is started; even if the range
+cannot contain any pages which KSM could actually merge; even if
+MADV_UNMERGEABLE is applied to a range which was never MADV_MERGEABLE.
+
+If a region of memory must be split into at least one new MADV_MERGEABLE
+or MADV_UNMERGEABLE region, the madvise may return ENOMEM if the process
+will exceed ``vm.max_map_count`` (see Documentation/sysctl/vm.txt).
+
+Like other madvise calls, they are intended for use on mapped areas of
+the user address space: they will report ENOMEM if the specified range
+includes unmapped gaps (though working on the intervening mapped areas),
+and might fail with EAGAIN if not enough memory for internal structures.
+
+Applications should be considerate in their use of MADV_MERGEABLE,
+restricting its use to areas likely to benefit. KSM's scans may use a lot
+of processing power: some installations will disable KSM for that reason.
+
+.. _ksm_sysfs:
+
+KSM daemon sysfs interface
+==========================
+
+The KSM daemon is controlled by sysfs files in ``/sys/kernel/mm/ksm/``,
+readable by all but writable only by root:
+
+pages_to_scan
+ how many pages to scan before ksmd goes to sleep
+ e.g. ``echo 100 > /sys/kernel/mm/ksm/pages_to_scan``.
+
+ Default: 100 (chosen for demonstration purposes)
+
+sleep_millisecs
+ how many milliseconds ksmd should sleep before next scan
+ e.g. ``echo 20 > /sys/kernel/mm/ksm/sleep_millisecs``
+
+ Default: 20 (chosen for demonstration purposes)
+
+merge_across_nodes
+ specifies if pages from different NUMA nodes can be merged.
+ When set to 0, ksm merges only pages which physically reside
+ in the memory area of same NUMA node. That brings lower
+ latency to access of shared pages. Systems with more nodes, at
+ significant NUMA distances, are likely to benefit from the
+ lower latency of setting 0. Smaller systems, which need to
+ minimize memory usage, are likely to benefit from the greater
+ sharing of setting 1 (default). You may wish to compare how
+ your system performs under each setting, before deciding on
+ which to use. ``merge_across_nodes`` setting can be changed only
+ when there are no ksm shared pages in the system: set run 2 to
+ unmerge pages first, then to 1 after changing
+ ``merge_across_nodes``, to remerge according to the new setting.
+
+ Default: 1 (merging across nodes as in earlier releases)
+
+run
+ * set to 0 to stop ksmd from running but keep merged pages,
+ * set to 1 to run ksmd e.g. ``echo 1 > /sys/kernel/mm/ksm/run``,
+ * set to 2 to stop ksmd and unmerge all pages currently merged, but
+ leave mergeable areas registered for next run.
+
+ Default: 0 (must be changed to 1 to activate KSM, except if
+ CONFIG_SYSFS is disabled)
+
+use_zero_pages
+ specifies whether empty pages (i.e. allocated pages that only
+ contain zeroes) should be treated specially. When set to 1,
+ empty pages are merged with the kernel zero page(s) instead of
+ with each other as it would happen normally. This can improve
+ the performance on architectures with coloured zero pages,
+ depending on the workload. Care should be taken when enabling
+ this setting, as it can potentially degrade the performance of
+ KSM for some workloads, for example if the checksums of pages
+ candidate for merging match the checksum of an empty
+ page. This setting can be changed at any time, it is only
+ effective for pages merged after the change.
+
+ Default: 0 (normal KSM behaviour as in earlier releases)
+
+max_page_sharing
+ Maximum sharing allowed for each KSM page. This enforces a
+ deduplication limit to avoid high latency for virtual memory
+ operations that involve traversal of the virtual mappings that
+ share the KSM page. The minimum value is 2 as a newly created
+ KSM page will have at least two sharers. The higher this value
+ the faster KSM will merge the memory and the higher the
+ deduplication factor will be, but the slower the worst case
+ virtual mappings traversal could be for any given KSM
+ page. Slowing down this traversal means there will be higher
+ latency for certain virtual memory operations happening during
+ swapping, compaction, NUMA balancing and page migration, in
+ turn decreasing responsiveness for the caller of those virtual
+ memory operations. The scheduler latency of other tasks not
+ involved with the VM operations doing the virtual mappings
+ traversal is not affected by this parameter as these
+ traversals are always schedule friendly themselves.
+
+stable_node_chains_prune_millisecs
+ specifies how frequently KSM checks the metadata of the pages
+ that hit the deduplication limit for stale information.
+ Smaller milllisecs values will free up the KSM metadata with
+ lower latency, but they will make ksmd use more CPU during the
+ scan. It's a noop if not a single KSM page hit the
+ ``max_page_sharing`` yet.
+
+The effectiveness of KSM and MADV_MERGEABLE is shown in ``/sys/kernel/mm/ksm/``:
+
+pages_shared
+ how many shared pages are being used
+pages_sharing
+ how many more sites are sharing them i.e. how much saved
+pages_unshared
+ how many pages unique but repeatedly checked for merging
+pages_volatile
+ how many pages changing too fast to be placed in a tree
+full_scans
+ how many times all mergeable areas have been scanned
+stable_node_chains
+ the number of KSM pages that hit the ``max_page_sharing`` limit
+stable_node_dups
+ number of duplicated KSM pages
+
+A high ratio of ``pages_sharing`` to ``pages_shared`` indicates good
+sharing, but a high ratio of ``pages_unshared`` to ``pages_sharing``
+indicates wasted effort. ``pages_volatile`` embraces several
+different kinds of activity, but a high proportion there would also
+indicate poor use of madvise MADV_MERGEABLE.
+
+The maximum possible ``pages_sharing/pages_shared`` ratio is limited by the
+``max_page_sharing`` tunable. To increase the ratio ``max_page_sharing`` must
+be increased accordingly.
+
+--
+Izik Eidus,
+Hugh Dickins, 17 Nov 2009
diff --git a/Documentation/admin-guide/mm/numa_memory_policy.rst b/Documentation/admin-guide/mm/numa_memory_policy.rst
new file mode 100644
index 0000000..d78c5b3
--- /dev/null
+++ b/Documentation/admin-guide/mm/numa_memory_policy.rst
@@ -0,0 +1,495 @@
+.. _numa_memory_policy:
+
+==================
+NUMA Memory Policy
+==================
+
+What is NUMA Memory Policy?
+============================
+
+In the Linux kernel, "memory policy" determines from which node the kernel will
+allocate memory in a NUMA system or in an emulated NUMA system. Linux has
+supported platforms with Non-Uniform Memory Access architectures since 2.4.?.
+The current memory policy support was added to Linux 2.6 around May 2004. This
+document attempts to describe the concepts and APIs of the 2.6 memory policy
+support.
+
+Memory policies should not be confused with cpusets
+(``Documentation/cgroup-v1/cpusets.txt``)
+which is an administrative mechanism for restricting the nodes from which
+memory may be allocated by a set of processes. Memory policies are a
+programming interface that a NUMA-aware application can take advantage of. When
+both cpusets and policies are applied to a task, the restrictions of the cpuset
+takes priority. See :ref:`Memory Policies and cpusets <mem_pol_and_cpusets>`
+below for more details.
+
+Memory Policy Concepts
+======================
+
+Scope of Memory Policies
+------------------------
+
+The Linux kernel supports _scopes_ of memory policy, described here from
+most general to most specific:
+
+System Default Policy
+ this policy is "hard coded" into the kernel. It is the policy
+ that governs all page allocations that aren't controlled by
+ one of the more specific policy scopes discussed below. When
+ the system is "up and running", the system default policy will
+ use "local allocation" described below. However, during boot
+ up, the system default policy will be set to interleave
+ allocations across all nodes with "sufficient" memory, so as
+ not to overload the initial boot node with boot-time
+ allocations.
+
+Task/Process Policy
+ this is an optional, per-task policy. When defined for a
+ specific task, this policy controls all page allocations made
+ by or on behalf of the task that aren't controlled by a more
+ specific scope. If a task does not define a task policy, then
+ all page allocations that would have been controlled by the
+ task policy "fall back" to the System Default Policy.
+
+ The task policy applies to the entire address space of a task. Thus,
+ it is inheritable, and indeed is inherited, across both fork()
+ [clone() w/o the CLONE_VM flag] and exec*(). This allows a parent task
+ to establish the task policy for a child task exec()'d from an
+ executable image that has no awareness of memory policy. See the
+ :ref:`Memory Policy APIs <memory_policy_apis>` section,
+ below, for an overview of the system call
+ that a task may use to set/change its task/process policy.
+
+ In a multi-threaded task, task policies apply only to the thread
+ [Linux kernel task] that installs the policy and any threads
+ subsequently created by that thread. Any sibling threads existing
+ at the time a new task policy is installed retain their current
+ policy.
+
+ A task policy applies only to pages allocated after the policy is
+ installed. Any pages already faulted in by the task when the task
+ changes its task policy remain where they were allocated based on
+ the policy at the time they were allocated.
+
+.. _vma_policy:
+
+VMA Policy
+ A "VMA" or "Virtual Memory Area" refers to a range of a task's
+ virtual address space. A task may define a specific policy for a range
+ of its virtual address space. See the
+ :ref:`Memory Policy APIs <memory_policy_apis>` section,
+ below, for an overview of the mbind() system call used to set a VMA
+ policy.
+
+ A VMA policy will govern the allocation of pages that back
+ this region of the address space. Any regions of the task's
+ address space that don't have an explicit VMA policy will fall
+ back to the task policy, which may itself fall back to the
+ System Default Policy.
+
+ VMA policies have a few complicating details:
+
+ * VMA policy applies ONLY to anonymous pages. These include
+ pages allocated for anonymous segments, such as the task
+ stack and heap, and any regions of the address space
+ mmap()ed with the MAP_ANONYMOUS flag. If a VMA policy is
+ applied to a file mapping, it will be ignored if the mapping
+ used the MAP_SHARED flag. If the file mapping used the
+ MAP_PRIVATE flag, the VMA policy will only be applied when
+ an anonymous page is allocated on an attempt to write to the
+ mapping-- i.e., at Copy-On-Write.
+
+ * VMA policies are shared between all tasks that share a
+ virtual address space--a.k.a. threads--independent of when
+ the policy is installed; and they are inherited across
+ fork(). However, because VMA policies refer to a specific
+ region of a task's address space, and because the address
+ space is discarded and recreated on exec*(), VMA policies
+ are NOT inheritable across exec(). Thus, only NUMA-aware
+ applications may use VMA policies.
+
+ * A task may install a new VMA policy on a sub-range of a
+ previously mmap()ed region. When this happens, Linux splits
+ the existing virtual memory area into 2 or 3 VMAs, each with
+ it's own policy.
+
+ * By default, VMA policy applies only to pages allocated after
+ the policy is installed. Any pages already faulted into the
+ VMA range remain where they were allocated based on the
+ policy at the time they were allocated. However, since
+ 2.6.16, Linux supports page migration via the mbind() system
+ call, so that page contents can be moved to match a newly
+ installed policy.
+
+Shared Policy
+ Conceptually, shared policies apply to "memory objects" mapped
+ shared into one or more tasks' distinct address spaces. An
+ application installs shared policies the same way as VMA
+ policies--using the mbind() system call specifying a range of
+ virtual addresses that map the shared object. However, unlike
+ VMA policies, which can be considered to be an attribute of a
+ range of a task's address space, shared policies apply
+ directly to the shared object. Thus, all tasks that attach to
+ the object share the policy, and all pages allocated for the
+ shared object, by any task, will obey the shared policy.
+
+ As of 2.6.22, only shared memory segments, created by shmget() or
+ mmap(MAP_ANONYMOUS|MAP_SHARED), support shared policy. When shared
+ policy support was added to Linux, the associated data structures were
+ added to hugetlbfs shmem segments. At the time, hugetlbfs did not
+ support allocation at fault time--a.k.a lazy allocation--so hugetlbfs
+ shmem segments were never "hooked up" to the shared policy support.
+ Although hugetlbfs segments now support lazy allocation, their support
+ for shared policy has not been completed.
+
+ As mentioned above in :ref:`VMA policies <vma_policy>` section,
+ allocations of page cache pages for regular files mmap()ed
+ with MAP_SHARED ignore any VMA policy installed on the virtual
+ address range backed by the shared file mapping. Rather,
+ shared page cache pages, including pages backing private
+ mappings that have not yet been written by the task, follow
+ task policy, if any, else System Default Policy.
+
+ The shared policy infrastructure supports different policies on subset
+ ranges of the shared object. However, Linux still splits the VMA of
+ the task that installs the policy for each range of distinct policy.
+ Thus, different tasks that attach to a shared memory segment can have
+ different VMA configurations mapping that one shared object. This
+ can be seen by examining the /proc/<pid>/numa_maps of tasks sharing
+ a shared memory region, when one task has installed shared policy on
+ one or more ranges of the region.
+
+Components of Memory Policies
+-----------------------------
+
+A NUMA memory policy consists of a "mode", optional mode flags, and
+an optional set of nodes. The mode determines the behavior of the
+policy, the optional mode flags determine the behavior of the mode,
+and the optional set of nodes can be viewed as the arguments to the
+policy behavior.
+
+Internally, memory policies are implemented by a reference counted
+structure, struct mempolicy. Details of this structure will be
+discussed in context, below, as required to explain the behavior.
+
+NUMA memory policy supports the following 4 behavioral modes:
+
+Default Mode--MPOL_DEFAULT
+ This mode is only used in the memory policy APIs. Internally,
+ MPOL_DEFAULT is converted to the NULL memory policy in all
+ policy scopes. Any existing non-default policy will simply be
+ removed when MPOL_DEFAULT is specified. As a result,
+ MPOL_DEFAULT means "fall back to the next most specific policy
+ scope."
+
+ For example, a NULL or default task policy will fall back to the
+ system default policy. A NULL or default vma policy will fall
+ back to the task policy.
+
+ When specified in one of the memory policy APIs, the Default mode
+ does not use the optional set of nodes.
+
+ It is an error for the set of nodes specified for this policy to
+ be non-empty.
+
+MPOL_BIND
+ This mode specifies that memory must come from the set of
+ nodes specified by the policy. Memory will be allocated from
+ the node in the set with sufficient free memory that is
+ closest to the node where the allocation takes place.
+
+MPOL_PREFERRED
+ This mode specifies that the allocation should be attempted
+ from the single node specified in the policy. If that
+ allocation fails, the kernel will search other nodes, in order
+ of increasing distance from the preferred node based on
+ information provided by the platform firmware.
+
+ Internally, the Preferred policy uses a single node--the
+ preferred_node member of struct mempolicy. When the internal
+ mode flag MPOL_F_LOCAL is set, the preferred_node is ignored
+ and the policy is interpreted as local allocation. "Local"
+ allocation policy can be viewed as a Preferred policy that
+ starts at the node containing the cpu where the allocation
+ takes place.
+
+ It is possible for the user to specify that local allocation
+ is always preferred by passing an empty nodemask with this
+ mode. If an empty nodemask is passed, the policy cannot use
+ the MPOL_F_STATIC_NODES or MPOL_F_RELATIVE_NODES flags
+ described below.
+
+MPOL_INTERLEAVED
+ This mode specifies that page allocations be interleaved, on a
+ page granularity, across the nodes specified in the policy.
+ This mode also behaves slightly differently, based on the
+ context where it is used:
+
+ For allocation of anonymous pages and shared memory pages,
+ Interleave mode indexes the set of nodes specified by the
+ policy using the page offset of the faulting address into the
+ segment [VMA] containing the address modulo the number of
+ nodes specified by the policy. It then attempts to allocate a
+ page, starting at the selected node, as if the node had been
+ specified by a Preferred policy or had been selected by a
+ local allocation. That is, allocation will follow the per
+ node zonelist.
+
+ For allocation of page cache pages, Interleave mode indexes
+ the set of nodes specified by the policy using a node counter
+ maintained per task. This counter wraps around to the lowest
+ specified node after it reaches the highest specified node.
+ This will tend to spread the pages out over the nodes
+ specified by the policy based on the order in which they are
+ allocated, rather than based on any page offset into an
+ address range or file. During system boot up, the temporary
+ interleaved system default policy works in this mode.
+
+NUMA memory policy supports the following optional mode flags:
+
+MPOL_F_STATIC_NODES
+ This flag specifies that the nodemask passed by
+ the user should not be remapped if the task or VMA's set of allowed
+ nodes changes after the memory policy has been defined.
+
+ Without this flag, any time a mempolicy is rebound because of a
+ change in the set of allowed nodes, the node (Preferred) or
+ nodemask (Bind, Interleave) is remapped to the new set of
+ allowed nodes. This may result in nodes being used that were
+ previously undesired.
+
+ With this flag, if the user-specified nodes overlap with the
+ nodes allowed by the task's cpuset, then the memory policy is
+ applied to their intersection. If the two sets of nodes do not
+ overlap, the Default policy is used.
+
+ For example, consider a task that is attached to a cpuset with
+ mems 1-3 that sets an Interleave policy over the same set. If
+ the cpuset's mems change to 3-5, the Interleave will now occur
+ over nodes 3, 4, and 5. With this flag, however, since only node
+ 3 is allowed from the user's nodemask, the "interleave" only
+ occurs over that node. If no nodes from the user's nodemask are
+ now allowed, the Default behavior is used.
+
+ MPOL_F_STATIC_NODES cannot be combined with the
+ MPOL_F_RELATIVE_NODES flag. It also cannot be used for
+ MPOL_PREFERRED policies that were created with an empty nodemask
+ (local allocation).
+
+MPOL_F_RELATIVE_NODES
+ This flag specifies that the nodemask passed
+ by the user will be mapped relative to the set of the task or VMA's
+ set of allowed nodes. The kernel stores the user-passed nodemask,
+ and if the allowed nodes changes, then that original nodemask will
+ be remapped relative to the new set of allowed nodes.
+
+ Without this flag (and without MPOL_F_STATIC_NODES), anytime a
+ mempolicy is rebound because of a change in the set of allowed
+ nodes, the node (Preferred) or nodemask (Bind, Interleave) is
+ remapped to the new set of allowed nodes. That remap may not
+ preserve the relative nature of the user's passed nodemask to its
+ set of allowed nodes upon successive rebinds: a nodemask of
+ 1,3,5 may be remapped to 7-9 and then to 1-3 if the set of
+ allowed nodes is restored to its original state.
+
+ With this flag, the remap is done so that the node numbers from
+ the user's passed nodemask are relative to the set of allowed
+ nodes. In other words, if nodes 0, 2, and 4 are set in the user's
+ nodemask, the policy will be effected over the first (and in the
+ Bind or Interleave case, the third and fifth) nodes in the set of
+ allowed nodes. The nodemask passed by the user represents nodes
+ relative to task or VMA's set of allowed nodes.
+
+ If the user's nodemask includes nodes that are outside the range
+ of the new set of allowed nodes (for example, node 5 is set in
+ the user's nodemask when the set of allowed nodes is only 0-3),
+ then the remap wraps around to the beginning of the nodemask and,
+ if not already set, sets the node in the mempolicy nodemask.
+
+ For example, consider a task that is attached to a cpuset with
+ mems 2-5 that sets an Interleave policy over the same set with
+ MPOL_F_RELATIVE_NODES. If the cpuset's mems change to 3-7, the
+ interleave now occurs over nodes 3,5-7. If the cpuset's mems
+ then change to 0,2-3,5, then the interleave occurs over nodes
+ 0,2-3,5.
+
+ Thanks to the consistent remapping, applications preparing
+ nodemasks to specify memory policies using this flag should
+ disregard their current, actual cpuset imposed memory placement
+ and prepare the nodemask as if they were always located on
+ memory nodes 0 to N-1, where N is the number of memory nodes the
+ policy is intended to manage. Let the kernel then remap to the
+ set of memory nodes allowed by the task's cpuset, as that may
+ change over time.
+
+ MPOL_F_RELATIVE_NODES cannot be combined with the
+ MPOL_F_STATIC_NODES flag. It also cannot be used for
+ MPOL_PREFERRED policies that were created with an empty nodemask
+ (local allocation).
+
+Memory Policy Reference Counting
+================================
+
+To resolve use/free races, struct mempolicy contains an atomic reference
+count field. Internal interfaces, mpol_get()/mpol_put() increment and
+decrement this reference count, respectively. mpol_put() will only free
+the structure back to the mempolicy kmem cache when the reference count
+goes to zero.
+
+When a new memory policy is allocated, its reference count is initialized
+to '1', representing the reference held by the task that is installing the
+new policy. When a pointer to a memory policy structure is stored in another
+structure, another reference is added, as the task's reference will be dropped
+on completion of the policy installation.
+
+During run-time "usage" of the policy, we attempt to minimize atomic operations
+on the reference count, as this can lead to cache lines bouncing between cpus
+and NUMA nodes. "Usage" here means one of the following:
+
+1) querying of the policy, either by the task itself [using the get_mempolicy()
+ API discussed below] or by another task using the /proc/<pid>/numa_maps
+ interface.
+
+2) examination of the policy to determine the policy mode and associated node
+ or node lists, if any, for page allocation. This is considered a "hot
+ path". Note that for MPOL_BIND, the "usage" extends across the entire
+ allocation process, which may sleep during page reclaimation, because the
+ BIND policy nodemask is used, by reference, to filter ineligible nodes.
+
+We can avoid taking an extra reference during the usages listed above as
+follows:
+
+1) we never need to get/free the system default policy as this is never
+ changed nor freed, once the system is up and running.
+
+2) for querying the policy, we do not need to take an extra reference on the
+ target task's task policy nor vma policies because we always acquire the
+ task's mm's mmap_sem for read during the query. The set_mempolicy() and
+ mbind() APIs [see below] always acquire the mmap_sem for write when
+ installing or replacing task or vma policies. Thus, there is no possibility
+ of a task or thread freeing a policy while another task or thread is
+ querying it.
+
+3) Page allocation usage of task or vma policy occurs in the fault path where
+ we hold them mmap_sem for read. Again, because replacing the task or vma
+ policy requires that the mmap_sem be held for write, the policy can't be
+ freed out from under us while we're using it for page allocation.
+
+4) Shared policies require special consideration. One task can replace a
+ shared memory policy while another task, with a distinct mmap_sem, is
+ querying or allocating a page based on the policy. To resolve this
+ potential race, the shared policy infrastructure adds an extra reference
+ to the shared policy during lookup while holding a spin lock on the shared
+ policy management structure. This requires that we drop this extra
+ reference when we're finished "using" the policy. We must drop the
+ extra reference on shared policies in the same query/allocation paths
+ used for non-shared policies. For this reason, shared policies are marked
+ as such, and the extra reference is dropped "conditionally"--i.e., only
+ for shared policies.
+
+ Because of this extra reference counting, and because we must lookup
+ shared policies in a tree structure under spinlock, shared policies are
+ more expensive to use in the page allocation path. This is especially
+ true for shared policies on shared memory regions shared by tasks running
+ on different NUMA nodes. This extra overhead can be avoided by always
+ falling back to task or system default policy for shared memory regions,
+ or by prefaulting the entire shared memory region into memory and locking
+ it down. However, this might not be appropriate for all applications.
+
+.. _memory_policy_apis:
+
+Memory Policy APIs
+==================
+
+Linux supports 3 system calls for controlling memory policy. These APIS
+always affect only the calling task, the calling task's address space, or
+some shared object mapped into the calling task's address space.
+
+.. note::
+ the headers that define these APIs and the parameter data types for
+ user space applications reside in a package that is not part of the
+ Linux kernel. The kernel system call interfaces, with the 'sys\_'
+ prefix, are defined in <linux/syscalls.h>; the mode and flag
+ definitions are defined in <linux/mempolicy.h>.
+
+Set [Task] Memory Policy::
+
+ long set_mempolicy(int mode, const unsigned long *nmask,
+ unsigned long maxnode);
+
+Set's the calling task's "task/process memory policy" to mode
+specified by the 'mode' argument and the set of nodes defined by
+'nmask'. 'nmask' points to a bit mask of node ids containing at least
+'maxnode' ids. Optional mode flags may be passed by combining the
+'mode' argument with the flag (for example: MPOL_INTERLEAVE |
+MPOL_F_STATIC_NODES).
+
+See the set_mempolicy(2) man page for more details
+
+
+Get [Task] Memory Policy or Related Information::
+
+ long get_mempolicy(int *mode,
+ const unsigned long *nmask, unsigned long maxnode,
+ void *addr, int flags);
+
+Queries the "task/process memory policy" of the calling task, or the
+policy or location of a specified virtual address, depending on the
+'flags' argument.
+
+See the get_mempolicy(2) man page for more details
+
+
+Install VMA/Shared Policy for a Range of Task's Address Space::
+
+ long mbind(void *start, unsigned long len, int mode,
+ const unsigned long *nmask, unsigned long maxnode,
+ unsigned flags);
+
+mbind() installs the policy specified by (mode, nmask, maxnodes) as a
+VMA policy for the range of the calling task's address space specified
+by the 'start' and 'len' arguments. Additional actions may be
+requested via the 'flags' argument.
+
+See the mbind(2) man page for more details.
+
+Memory Policy Command Line Interface
+====================================
+
+Although not strictly part of the Linux implementation of memory policy,
+a command line tool, numactl(8), exists that allows one to:
+
++ set the task policy for a specified program via set_mempolicy(2), fork(2) and
+ exec(2)
+
++ set the shared policy for a shared memory segment via mbind(2)
+
+The numactl(8) tool is packaged with the run-time version of the library
+containing the memory policy system call wrappers. Some distributions
+package the headers and compile-time libraries in a separate development
+package.
+
+.. _mem_pol_and_cpusets:
+
+Memory Policies and cpusets
+===========================
+
+Memory policies work within cpusets as described above. For memory policies
+that require a node or set of nodes, the nodes are restricted to the set of
+nodes whose memories are allowed by the cpuset constraints. If the nodemask
+specified for the policy contains nodes that are not allowed by the cpuset and
+MPOL_F_RELATIVE_NODES is not used, the intersection of the set of nodes
+specified for the policy and the set of nodes with memory is used. If the
+result is the empty set, the policy is considered invalid and cannot be
+installed. If MPOL_F_RELATIVE_NODES is used, the policy's nodes are mapped
+onto and folded into the task's set of allowed nodes as previously described.
+
+The interaction of memory policies and cpusets can be problematic when tasks
+in two cpusets share access to a memory region, such as shared memory segments
+created by shmget() of mmap() with the MAP_ANONYMOUS and MAP_SHARED flags, and
+any of the tasks install shared policy on the region, only nodes whose
+memories are allowed in both cpusets may be used in the policies. Obtaining
+this information requires "stepping outside" the memory policy APIs to use the
+cpuset information and requires that one know in what cpusets other task might
+be attaching to the shared region. Furthermore, if the cpusets' allowed
+memory sets are disjoint, "local" allocation is the only valid policy.
diff --git a/Documentation/admin-guide/mm/pagemap.rst b/Documentation/admin-guide/mm/pagemap.rst
new file mode 100644
index 0000000..577af85
--- /dev/null
+++ b/Documentation/admin-guide/mm/pagemap.rst
@@ -0,0 +1,201 @@
+.. _pagemap:
+
+=============================
+Examining Process Page Tables
+=============================
+
+pagemap is a new (as of 2.6.25) set of interfaces in the kernel that allow
+userspace programs to examine the page tables and related information by
+reading files in ``/proc``.
+
+There are four components to pagemap:
+
+ * ``/proc/pid/pagemap``. This file lets a userspace process find out which
+ physical frame each virtual page is mapped to. It contains one 64-bit
+ value for each virtual page, containing the following data (from
+ ``fs/proc/task_mmu.c``, above pagemap_read):
+
+ * Bits 0-54 page frame number (PFN) if present
+ * Bits 0-4 swap type if swapped
+ * Bits 5-54 swap offset if swapped
+ * Bit 55 pte is soft-dirty (see
+ :ref:`Documentation/admin-guide/mm/soft-dirty.rst <soft_dirty>`)
+ * Bit 56 page exclusively mapped (since 4.2)
+ * Bits 57-60 zero
+ * Bit 61 page is file-page or shared-anon (since 3.5)
+ * Bit 62 page swapped
+ * Bit 63 page present
+
+ Since Linux 4.0 only users with the CAP_SYS_ADMIN capability can get PFNs.
+ In 4.0 and 4.1 opens by unprivileged fail with -EPERM. Starting from
+ 4.2 the PFN field is zeroed if the user does not have CAP_SYS_ADMIN.
+ Reason: information about PFNs helps in exploiting Rowhammer vulnerability.
+
+ If the page is not present but in swap, then the PFN contains an
+ encoding of the swap file number and the page's offset into the
+ swap. Unmapped pages return a null PFN. This allows determining
+ precisely which pages are mapped (or in swap) and comparing mapped
+ pages between processes.
+
+ Efficient users of this interface will use ``/proc/pid/maps`` to
+ determine which areas of memory are actually mapped and llseek to
+ skip over unmapped regions.
+
+ * ``/proc/kpagecount``. This file contains a 64-bit count of the number of
+ times each page is mapped, indexed by PFN.
+
+ * ``/proc/kpageflags``. This file contains a 64-bit set of flags for each
+ page, indexed by PFN.
+
+ The flags are (from ``fs/proc/page.c``, above kpageflags_read):
+
+ 0. LOCKED
+ 1. ERROR
+ 2. REFERENCED
+ 3. UPTODATE
+ 4. DIRTY
+ 5. LRU
+ 6. ACTIVE
+ 7. SLAB
+ 8. WRITEBACK
+ 9. RECLAIM
+ 10. BUDDY
+ 11. MMAP
+ 12. ANON
+ 13. SWAPCACHE
+ 14. SWAPBACKED
+ 15. COMPOUND_HEAD
+ 16. COMPOUND_TAIL
+ 17. HUGE
+ 18. UNEVICTABLE
+ 19. HWPOISON
+ 20. NOPAGE
+ 21. KSM
+ 22. THP
+ 23. BALLOON
+ 24. ZERO_PAGE
+ 25. IDLE
+
+ * ``/proc/kpagecgroup``. This file contains a 64-bit inode number of the
+ memory cgroup each page is charged to, indexed by PFN. Only available when
+ CONFIG_MEMCG is set.
+
+Short descriptions to the page flags
+====================================
+
+0 - LOCKED
+ page is being locked for exclusive access, e.g. by undergoing read/write IO
+7 - SLAB
+ page is managed by the SLAB/SLOB/SLUB/SLQB kernel memory allocator
+ When compound page is used, SLUB/SLQB will only set this flag on the head
+ page; SLOB will not flag it at all.
+10 - BUDDY
+ a free memory block managed by the buddy system allocator
+ The buddy system organizes free memory in blocks of various orders.
+ An order N block has 2^N physically contiguous pages, with the BUDDY flag
+ set for and _only_ for the first page.
+15 - COMPOUND_HEAD
+ A compound page with order N consists of 2^N physically contiguous pages.
+ A compound page with order 2 takes the form of "HTTT", where H donates its
+ head page and T donates its tail page(s). The major consumers of compound
+ pages are hugeTLB pages
+ (:ref:`Documentation/admin-guide/mm/hugetlbpage.rst <hugetlbpage>`),
+ the SLUB etc. memory allocators and various device drivers.
+ However in this interface, only huge/giga pages are made visible
+ to end users.
+16 - COMPOUND_TAIL
+ A compound page tail (see description above).
+17 - HUGE
+ this is an integral part of a HugeTLB page
+19 - HWPOISON
+ hardware detected memory corruption on this page: don't touch the data!
+20 - NOPAGE
+ no page frame exists at the requested address
+21 - KSM
+ identical memory pages dynamically shared between one or more processes
+22 - THP
+ contiguous pages which construct transparent hugepages
+23 - BALLOON
+ balloon compaction page
+24 - ZERO_PAGE
+ zero page for pfn_zero or huge_zero page
+25 - IDLE
+ page has not been accessed since it was marked idle (see
+ :ref:`Documentation/admin-guide/mm/idle_page_tracking.rst <idle_page_tracking>`).
+ Note that this flag may be stale in case the page was accessed via
+ a PTE. To make sure the flag is up-to-date one has to read
+ ``/sys/kernel/mm/page_idle/bitmap`` first.
+
+IO related page flags
+---------------------
+
+1 - ERROR
+ IO error occurred
+3 - UPTODATE
+ page has up-to-date data
+ ie. for file backed page: (in-memory data revision >= on-disk one)
+4 - DIRTY
+ page has been written to, hence contains new data
+ i.e. for file backed page: (in-memory data revision > on-disk one)
+8 - WRITEBACK
+ page is being synced to disk
+
+LRU related page flags
+----------------------
+
+5 - LRU
+ page is in one of the LRU lists
+6 - ACTIVE
+ page is in the active LRU list
+18 - UNEVICTABLE
+ page is in the unevictable (non-)LRU list It is somehow pinned and
+ not a candidate for LRU page reclaims, e.g. ramfs pages,
+ shmctl(SHM_LOCK) and mlock() memory segments
+2 - REFERENCED
+ page has been referenced since last LRU list enqueue/requeue
+9 - RECLAIM
+ page will be reclaimed soon after its pageout IO completed
+11 - MMAP
+ a memory mapped page
+12 - ANON
+ a memory mapped page that is not part of a file
+13 - SWAPCACHE
+ page is mapped to swap space, i.e. has an associated swap entry
+14 - SWAPBACKED
+ page is backed by swap/RAM
+
+The page-types tool in the tools/vm directory can be used to query the
+above flags.
+
+Using pagemap to do something useful
+====================================
+
+The general procedure for using pagemap to find out about a process' memory
+usage goes like this:
+
+ 1. Read ``/proc/pid/maps`` to determine which parts of the memory space are
+ mapped to what.
+ 2. Select the maps you are interested in -- all of them, or a particular
+ library, or the stack or the heap, etc.
+ 3. Open ``/proc/pid/pagemap`` and seek to the pages you would like to examine.
+ 4. Read a u64 for each page from pagemap.
+ 5. Open ``/proc/kpagecount`` and/or ``/proc/kpageflags``. For each PFN you
+ just read, seek to that entry in the file, and read the data you want.
+
+For example, to find the "unique set size" (USS), which is the amount of
+memory that a process is using that is not shared with any other process,
+you can go through every map in the process, find the PFNs, look those up
+in kpagecount, and tally up the number of pages that are only referenced
+once.
+
+Other notes
+===========
+
+Reading from any of the files will return -EINVAL if you are not starting
+the read on an 8-byte boundary (e.g., if you sought an odd number of bytes
+into the file), or if the size of the read is not a multiple of 8 bytes.
+
+Before Linux 3.11 pagemap bits 55-60 were used for "page-shift" (which is
+always 12 at most architectures). Since Linux 3.11 their meaning changes
+after first clear of soft-dirty bits. Since Linux 4.2 they are used for
+flags unconditionally.
diff --git a/Documentation/vm/soft-dirty.txt b/Documentation/admin-guide/mm/soft-dirty.rst
similarity index 67%
rename from Documentation/vm/soft-dirty.txt
rename to Documentation/admin-guide/mm/soft-dirty.rst
index 55684d1..cb0cfd6 100644
--- a/Documentation/vm/soft-dirty.txt
+++ b/Documentation/admin-guide/mm/soft-dirty.rst
@@ -1,34 +1,38 @@
- SOFT-DIRTY PTEs
+.. _soft_dirty:
- The soft-dirty is a bit on a PTE which helps to track which pages a task
+===============
+Soft-Dirty PTEs
+===============
+
+The soft-dirty is a bit on a PTE which helps to track which pages a task
writes to. In order to do this tracking one should
1. Clear soft-dirty bits from the task's PTEs.
- This is done by writing "4" into the /proc/PID/clear_refs file of the
+ This is done by writing "4" into the ``/proc/PID/clear_refs`` file of the
task in question.
2. Wait some time.
3. Read soft-dirty bits from the PTEs.
- This is done by reading from the /proc/PID/pagemap. The bit 55 of the
+ This is done by reading from the ``/proc/PID/pagemap``. The bit 55 of the
64-bit qword is the soft-dirty one. If set, the respective PTE was
written to since step 1.
- Internally, to do this tracking, the writable bit is cleared from PTEs
+Internally, to do this tracking, the writable bit is cleared from PTEs
when the soft-dirty bit is cleared. So, after this, when the task tries to
modify a page at some virtual address the #PF occurs and the kernel sets
the soft-dirty bit on the respective PTE.
- Note, that although all the task's address space is marked as r/o after the
+Note, that although all the task's address space is marked as r/o after the
soft-dirty bits clear, the #PF-s that occur after that are processed fast.
This is so, since the pages are still mapped to physical memory, and thus all
the kernel does is finds this fact out and puts both writable and soft-dirty
bits on the PTE.
- While in most cases tracking memory changes by #PF-s is more than enough
+While in most cases tracking memory changes by #PF-s is more than enough
there is still a scenario when we can lose soft dirty bits -- a task
unmaps a previously mapped memory region and then maps a new one at exactly
the same place. When unmap is called, the kernel internally clears PTE values
@@ -36,7 +40,7 @@
memory region renewal the kernel always marks new memory regions (and
expanded regions) as soft dirty.
- This feature is actively used by the checkpoint-restore project. You
+This feature is actively used by the checkpoint-restore project. You
can find more details about it on http://criu.org
diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
new file mode 100644
index 0000000..7ab93a8
--- /dev/null
+++ b/Documentation/admin-guide/mm/transhuge.rst
@@ -0,0 +1,418 @@
+.. _admin_guide_transhuge:
+
+============================
+Transparent Hugepage Support
+============================
+
+Objective
+=========
+
+Performance critical computing applications dealing with large memory
+working sets are already running on top of libhugetlbfs and in turn
+hugetlbfs. Transparent HugePage Support (THP) is an alternative mean of
+using huge pages for the backing of virtual memory with huge pages
+that supports the automatic promotion and demotion of page sizes and
+without the shortcomings of hugetlbfs.
+
+Currently THP only works for anonymous memory mappings and tmpfs/shmem.
+But in the future it can expand to other filesystems.
+
+.. note::
+ in the examples below we presume that the basic page size is 4K and
+ the huge page size is 2M, although the actual numbers may vary
+ depending on the CPU architecture.
+
+The reason applications are running faster is because of two
+factors. The first factor is almost completely irrelevant and it's not
+of significant interest because it'll also have the downside of
+requiring larger clear-page copy-page in page faults which is a
+potentially negative effect. The first factor consists in taking a
+single page fault for each 2M virtual region touched by userland (so
+reducing the enter/exit kernel frequency by a 512 times factor). This
+only matters the first time the memory is accessed for the lifetime of
+a memory mapping. The second long lasting and much more important
+factor will affect all subsequent accesses to the memory for the whole
+runtime of the application. The second factor consist of two
+components:
+
+1) the TLB miss will run faster (especially with virtualization using
+ nested pagetables but almost always also on bare metal without
+ virtualization)
+
+2) a single TLB entry will be mapping a much larger amount of virtual
+ memory in turn reducing the number of TLB misses. With
+ virtualization and nested pagetables the TLB can be mapped of
+ larger size only if both KVM and the Linux guest are using
+ hugepages but a significant speedup already happens if only one of
+ the two is using hugepages just because of the fact the TLB miss is
+ going to run faster.
+
+THP can be enabled system wide or restricted to certain tasks or even
+memory ranges inside task's address space. Unless THP is completely
+disabled, there is ``khugepaged`` daemon that scans memory and
+collapses sequences of basic pages into huge pages.
+
+The THP behaviour is controlled via :ref:`sysfs <thp_sysfs>`
+interface and using madivse(2) and prctl(2) system calls.
+
+Transparent Hugepage Support maximizes the usefulness of free memory
+if compared to the reservation approach of hugetlbfs by allowing all
+unused memory to be used as cache or other movable (or even unmovable
+entities). It doesn't require reservation to prevent hugepage
+allocation failures to be noticeable from userland. It allows paging
+and all other advanced VM features to be available on the
+hugepages. It requires no modifications for applications to take
+advantage of it.
+
+Applications however can be further optimized to take advantage of
+this feature, like for example they've been optimized before to avoid
+a flood of mmap system calls for every malloc(4k). Optimizing userland
+is by far not mandatory and khugepaged already can take care of long
+lived page allocations even for hugepage unaware applications that
+deals with large amounts of memory.
+
+In certain cases when hugepages are enabled system wide, application
+may end up allocating more memory resources. An application may mmap a
+large region but only touch 1 byte of it, in that case a 2M page might
+be allocated instead of a 4k page for no good. This is why it's
+possible to disable hugepages system-wide and to only have them inside
+MADV_HUGEPAGE madvise regions.
+
+Embedded systems should enable hugepages only inside madvise regions
+to eliminate any risk of wasting any precious byte of memory and to
+only run faster.
+
+Applications that gets a lot of benefit from hugepages and that don't
+risk to lose memory by using hugepages, should use
+madvise(MADV_HUGEPAGE) on their critical mmapped regions.
+
+.. _thp_sysfs:
+
+sysfs
+=====
+
+Global THP controls
+-------------------
+
+Transparent Hugepage Support for anonymous memory can be entirely disabled
+(mostly for debugging purposes) or only enabled inside MADV_HUGEPAGE
+regions (to avoid the risk of consuming more memory resources) or enabled
+system wide. This can be achieved with one of::
+
+ echo always >/sys/kernel/mm/transparent_hugepage/enabled
+ echo madvise >/sys/kernel/mm/transparent_hugepage/enabled
+ echo never >/sys/kernel/mm/transparent_hugepage/enabled
+
+It's also possible to limit defrag efforts in the VM to generate
+anonymous hugepages in case they're not immediately free to madvise
+regions or to never try to defrag memory and simply fallback to regular
+pages unless hugepages are immediately available. Clearly if we spend CPU
+time to defrag memory, we would expect to gain even more by the fact we
+use hugepages later instead of regular pages. This isn't always
+guaranteed, but it may be more likely in case the allocation is for a
+MADV_HUGEPAGE region.
+
+::
+
+ echo always >/sys/kernel/mm/transparent_hugepage/defrag
+ echo defer >/sys/kernel/mm/transparent_hugepage/defrag
+ echo defer+madvise >/sys/kernel/mm/transparent_hugepage/defrag
+ echo madvise >/sys/kernel/mm/transparent_hugepage/defrag
+ echo never >/sys/kernel/mm/transparent_hugepage/defrag
+
+always
+ means that an application requesting THP will stall on
+ allocation failure and directly reclaim pages and compact
+ memory in an effort to allocate a THP immediately. This may be
+ desirable for virtual machines that benefit heavily from THP
+ use and are willing to delay the VM start to utilise them.
+
+defer
+ means that an application will wake kswapd in the background
+ to reclaim pages and wake kcompactd to compact memory so that
+ THP is available in the near future. It's the responsibility
+ of khugepaged to then install the THP pages later.
+
+defer+madvise
+ will enter direct reclaim and compaction like ``always``, but
+ only for regions that have used madvise(MADV_HUGEPAGE); all
+ other regions will wake kswapd in the background to reclaim
+ pages and wake kcompactd to compact memory so that THP is
+ available in the near future.
+
+madvise
+ will enter direct reclaim like ``always`` but only for regions
+ that are have used madvise(MADV_HUGEPAGE). This is the default
+ behaviour.
+
+never
+ should be self-explanatory.
+
+By default kernel tries to use huge zero page on read page fault to
+anonymous mapping. It's possible to disable huge zero page by writing 0
+or enable it back by writing 1::
+
+ echo 0 >/sys/kernel/mm/transparent_hugepage/use_zero_page
+ echo 1 >/sys/kernel/mm/transparent_hugepage/use_zero_page
+
+Some userspace (such as a test program, or an optimized memory allocation
+library) may want to know the size (in bytes) of a transparent hugepage::
+
+ cat /sys/kernel/mm/transparent_hugepage/hpage_pmd_size
+
+khugepaged will be automatically started when
+transparent_hugepage/enabled is set to "always" or "madvise, and it'll
+be automatically shutdown if it's set to "never".
+
+Khugepaged controls
+-------------------
+
+khugepaged runs usually at low frequency so while one may not want to
+invoke defrag algorithms synchronously during the page faults, it
+should be worth invoking defrag at least in khugepaged. However it's
+also possible to disable defrag in khugepaged by writing 0 or enable
+defrag in khugepaged by writing 1::
+
+ echo 0 >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag
+ echo 1 >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag
+
+You can also control how many pages khugepaged should scan at each
+pass::
+
+ /sys/kernel/mm/transparent_hugepage/khugepaged/pages_to_scan
+
+and how many milliseconds to wait in khugepaged between each pass (you
+can set this to 0 to run khugepaged at 100% utilization of one core)::
+
+ /sys/kernel/mm/transparent_hugepage/khugepaged/scan_sleep_millisecs
+
+and how many milliseconds to wait in khugepaged if there's an hugepage
+allocation failure to throttle the next allocation attempt::
+
+ /sys/kernel/mm/transparent_hugepage/khugepaged/alloc_sleep_millisecs
+
+The khugepaged progress can be seen in the number of pages collapsed::
+
+ /sys/kernel/mm/transparent_hugepage/khugepaged/pages_collapsed
+
+for each pass::
+
+ /sys/kernel/mm/transparent_hugepage/khugepaged/full_scans
+
+``max_ptes_none`` specifies how many extra small pages (that are
+not already mapped) can be allocated when collapsing a group
+of small pages into one large page::
+
+ /sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_none
+
+A higher value leads to use additional memory for programs.
+A lower value leads to gain less thp performance. Value of
+max_ptes_none can waste cpu time very little, you can
+ignore it.
+
+``max_ptes_swap`` specifies how many pages can be brought in from
+swap when collapsing a group of pages into a transparent huge page::
+
+ /sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_swap
+
+A higher value can cause excessive swap IO and waste
+memory. A lower value can prevent THPs from being
+collapsed, resulting fewer pages being collapsed into
+THPs, and lower memory access performance.
+
+Boot parameter
+==============
+
+You can change the sysfs boot time defaults of Transparent Hugepage
+Support by passing the parameter ``transparent_hugepage=always`` or
+``transparent_hugepage=madvise`` or ``transparent_hugepage=never``
+to the kernel command line.
+
+Hugepages in tmpfs/shmem
+========================
+
+You can control hugepage allocation policy in tmpfs with mount option
+``huge=``. It can have following values:
+
+always
+ Attempt to allocate huge pages every time we need a new page;
+
+never
+ Do not allocate huge pages;
+
+within_size
+ Only allocate huge page if it will be fully within i_size.
+ Also respect fadvise()/madvise() hints;
+
+advise
+ Only allocate huge pages if requested with fadvise()/madvise();
+
+The default policy is ``never``.
+
+``mount -o remount,huge= /mountpoint`` works fine after mount: remounting
+``huge=never`` will not attempt to break up huge pages at all, just stop more
+from being allocated.
+
+There's also sysfs knob to control hugepage allocation policy for internal
+shmem mount: /sys/kernel/mm/transparent_hugepage/shmem_enabled. The mount
+is used for SysV SHM, memfds, shared anonymous mmaps (of /dev/zero or
+MAP_ANONYMOUS), GPU drivers' DRM objects, Ashmem.
+
+In addition to policies listed above, shmem_enabled allows two further
+values:
+
+deny
+ For use in emergencies, to force the huge option off from
+ all mounts;
+force
+ Force the huge option on for all - very useful for testing;
+
+Need of application restart
+===========================
+
+The transparent_hugepage/enabled values and tmpfs mount option only affect
+future behavior. So to make them effective you need to restart any
+application that could have been using hugepages. This also applies to the
+regions registered in khugepaged.
+
+Monitoring usage
+================
+
+The number of anonymous transparent huge pages currently used by the
+system is available by reading the AnonHugePages field in ``/proc/meminfo``.
+To identify what applications are using anonymous transparent huge pages,
+it is necessary to read ``/proc/PID/smaps`` and count the AnonHugePages fields
+for each mapping.
+
+The number of file transparent huge pages mapped to userspace is available
+by reading ShmemPmdMapped and ShmemHugePages fields in ``/proc/meminfo``.
+To identify what applications are mapping file transparent huge pages, it
+is necessary to read ``/proc/PID/smaps`` and count the FileHugeMapped fields
+for each mapping.
+
+Note that reading the smaps file is expensive and reading it
+frequently will incur overhead.
+
+There are a number of counters in ``/proc/vmstat`` that may be used to
+monitor how successfully the system is providing huge pages for use.
+
+thp_fault_alloc
+ is incremented every time a huge page is successfully
+ allocated to handle a page fault. This applies to both the
+ first time a page is faulted and for COW faults.
+
+thp_collapse_alloc
+ is incremented by khugepaged when it has found
+ a range of pages to collapse into one huge page and has
+ successfully allocated a new huge page to store the data.
+
+thp_fault_fallback
+ is incremented if a page fault fails to allocate
+ a huge page and instead falls back to using small pages.
+
+thp_collapse_alloc_failed
+ is incremented if khugepaged found a range
+ of pages that should be collapsed into one huge page but failed
+ the allocation.
+
+thp_file_alloc
+ is incremented every time a file huge page is successfully
+ allocated.
+
+thp_file_mapped
+ is incremented every time a file huge page is mapped into
+ user address space.
+
+thp_split_page
+ is incremented every time a huge page is split into base
+ pages. This can happen for a variety of reasons but a common
+ reason is that a huge page is old and is being reclaimed.
+ This action implies splitting all PMD the page mapped with.
+
+thp_split_page_failed
+ is incremented if kernel fails to split huge
+ page. This can happen if the page was pinned by somebody.
+
+thp_deferred_split_page
+ is incremented when a huge page is put onto split
+ queue. This happens when a huge page is partially unmapped and
+ splitting it would free up some memory. Pages on split queue are
+ going to be split under memory pressure.
+
+thp_split_pmd
+ is incremented every time a PMD split into table of PTEs.
+ This can happen, for instance, when application calls mprotect() or
+ munmap() on part of huge page. It doesn't split huge page, only
+ page table entry.
+
+thp_zero_page_alloc
+ is incremented every time a huge zero page is
+ successfully allocated. It includes allocations which where
+ dropped due race with other allocation. Note, it doesn't count
+ every map of the huge zero page, only its allocation.
+
+thp_zero_page_alloc_failed
+ is incremented if kernel fails to allocate
+ huge zero page and falls back to using small pages.
+
+thp_swpout
+ is incremented every time a huge page is swapout in one
+ piece without splitting.
+
+thp_swpout_fallback
+ is incremented if a huge page has to be split before swapout.
+ Usually because failed to allocate some continuous swap space
+ for the huge page.
+
+As the system ages, allocating huge pages may be expensive as the
+system uses memory compaction to copy data around memory to free a
+huge page for use. There are some counters in ``/proc/vmstat`` to help
+monitor this overhead.
+
+compact_stall
+ is incremented every time a process stalls to run
+ memory compaction so that a huge page is free for use.
+
+compact_success
+ is incremented if the system compacted memory and
+ freed a huge page for use.
+
+compact_fail
+ is incremented if the system tries to compact memory
+ but failed.
+
+compact_pages_moved
+ is incremented each time a page is moved. If
+ this value is increasing rapidly, it implies that the system
+ is copying a lot of data to satisfy the huge page allocation.
+ It is possible that the cost of copying exceeds any savings
+ from reduced TLB misses.
+
+compact_pagemigrate_failed
+ is incremented when the underlying mechanism
+ for moving a page failed.
+
+compact_blocks_moved
+ is incremented each time memory compaction examines
+ a huge page aligned range of pages.
+
+It is possible to establish how long the stalls were using the function
+tracer to record how long was spent in __alloc_pages_nodemask and
+using the mm_page_alloc tracepoint to identify which allocations were
+for huge pages.
+
+Optimizing the applications
+===========================
+
+To be guaranteed that the kernel will map a 2M page immediately in any
+memory region, the mmap region has to be hugepage naturally
+aligned. posix_memalign() can provide that guarantee.
+
+Hugetlbfs
+=========
+
+You can use hugetlbfs on a kernel that has transparent hugepage
+support enabled just fine as always. No difference can be noted in
+hugetlbfs other than there will be less overall fragmentation. All
+usual features belonging to hugetlbfs are preserved and
+unaffected. libhugetlbfs will also work fine as usual.
diff --git a/Documentation/vm/userfaultfd.txt b/Documentation/admin-guide/mm/userfaultfd.rst
similarity index 88%
rename from Documentation/vm/userfaultfd.txt
rename to Documentation/admin-guide/mm/userfaultfd.rst
index bb2f945..5048cf6 100644
--- a/Documentation/vm/userfaultfd.txt
+++ b/Documentation/admin-guide/mm/userfaultfd.rst
@@ -1,6 +1,11 @@
-= Userfaultfd =
+.. _userfaultfd:
-== Objective ==
+===========
+Userfaultfd
+===========
+
+Objective
+=========
Userfaults allow the implementation of on-demand paging from userland
and more generally they allow userland to take control of various
@@ -9,7 +14,8 @@
For example userfaults allows a proper and more optimal implementation
of the PROT_NONE+SIGSEGV trick.
-== Design ==
+Design
+======
Userfaults are delivered and resolved through the userfaultfd syscall.
@@ -41,7 +47,8 @@
themselves on the same region the manager is already tracking, which
is a corner case that would currently return -EBUSY).
-== API ==
+API
+===
When first opened the userfaultfd must be enabled invoking the
UFFDIO_API ioctl specifying a uffdio_api.api value set to UFFD_API (or
@@ -101,7 +108,8 @@
half copied page since it'll keep userfaulting until the copy has
finished.
-== QEMU/KVM ==
+QEMU/KVM
+========
QEMU/KVM is using the userfaultfd syscall to implement postcopy live
migration. Postcopy live migration is one form of memory
@@ -163,7 +171,8 @@
postcopy thread just before UFFDIO_COPY|ZEROPAGE runs in the migration
thread).
-== Non-cooperative userfaultfd ==
+Non-cooperative userfaultfd
+===========================
When the userfaultfd is monitored by an external manager, the manager
must be able to track changes in the process virtual memory
@@ -172,27 +181,30 @@
manager has to explicitly enable these events by setting appropriate
bits in uffdio_api.features passed to UFFDIO_API ioctl:
-UFFD_FEATURE_EVENT_FORK - enable userfaultfd hooks for fork(). When
-this feature is enabled, the userfaultfd context of the parent process
-is duplicated into the newly created process. The manager receives
-UFFD_EVENT_FORK with file descriptor of the new userfaultfd context in
-the uffd_msg.fork.
+UFFD_FEATURE_EVENT_FORK
+ enable userfaultfd hooks for fork(). When this feature is
+ enabled, the userfaultfd context of the parent process is
+ duplicated into the newly created process. The manager
+ receives UFFD_EVENT_FORK with file descriptor of the new
+ userfaultfd context in the uffd_msg.fork.
-UFFD_FEATURE_EVENT_REMAP - enable notifications about mremap()
-calls. When the non-cooperative process moves a virtual memory area to
-a different location, the manager will receive UFFD_EVENT_REMAP. The
-uffd_msg.remap will contain the old and new addresses of the area and
-its original length.
+UFFD_FEATURE_EVENT_REMAP
+ enable notifications about mremap() calls. When the
+ non-cooperative process moves a virtual memory area to a
+ different location, the manager will receive
+ UFFD_EVENT_REMAP. The uffd_msg.remap will contain the old and
+ new addresses of the area and its original length.
-UFFD_FEATURE_EVENT_REMOVE - enable notifications about
-madvise(MADV_REMOVE) and madvise(MADV_DONTNEED) calls. The event
-UFFD_EVENT_REMOVE will be generated upon these calls to madvise. The
-uffd_msg.remove will contain start and end addresses of the removed
-area.
+UFFD_FEATURE_EVENT_REMOVE
+ enable notifications about madvise(MADV_REMOVE) and
+ madvise(MADV_DONTNEED) calls. The event UFFD_EVENT_REMOVE will
+ be generated upon these calls to madvise. The uffd_msg.remove
+ will contain start and end addresses of the removed area.
-UFFD_FEATURE_EVENT_UNMAP - enable notifications about memory
-unmapping. The manager will get UFFD_EVENT_UNMAP with uffd_msg.remove
-containing start and end addresses of the unmapped area.
+UFFD_FEATURE_EVENT_UNMAP
+ enable notifications about memory unmapping. The manager will
+ get UFFD_EVENT_UNMAP with uffd_msg.remove containing start and
+ end addresses of the unmapped area.
Although the UFFD_FEATURE_EVENT_REMOVE and UFFD_FEATURE_EVENT_UNMAP
are pretty similar, they quite differ in the action expected from the
diff --git a/Documentation/admin-guide/pm/intel_pstate.rst b/Documentation/admin-guide/pm/intel_pstate.rst
index d2b6fda..ab2fe0e 100644
--- a/Documentation/admin-guide/pm/intel_pstate.rst
+++ b/Documentation/admin-guide/pm/intel_pstate.rst
@@ -145,7 +145,7 @@
In this mode ``intel_pstate`` registers utilization update callbacks with the
CPU scheduler in order to run a P-state selection algorithm, either
-``powersave`` or ``performance``, depending on the ``scaling_cur_freq`` policy
+``powersave`` or ``performance``, depending on the ``scaling_governor`` policy
setting in ``sysfs``. The current CPU frequency information to be made
available from the ``scaling_cur_freq`` policy attribute in ``sysfs`` is
periodically updated by those utilization update callbacks too.
diff --git a/Documentation/admin-guide/pm/sleep-states.rst b/Documentation/admin-guide/pm/sleep-states.rst
index 1e5c0f0..dbf5acd 100644
--- a/Documentation/admin-guide/pm/sleep-states.rst
+++ b/Documentation/admin-guide/pm/sleep-states.rst
@@ -15,7 +15,7 @@
==================================
Depending on its configuration and the capabilities of the platform it runs on,
-the Linux kernel can support up to four system sleep states, includig
+the Linux kernel can support up to four system sleep states, including
hibernation and up to three variants of system suspend. The sleep states that
can be supported by the kernel are listed below.
diff --git a/Documentation/admin-guide/ramoops.rst b/Documentation/admin-guide/ramoops.rst
index 4efd7ce..6dbcc54 100644
--- a/Documentation/admin-guide/ramoops.rst
+++ b/Documentation/admin-guide/ramoops.rst
@@ -61,7 +61,7 @@
mem=128M ramoops.mem_address=0x8000000 ramoops.ecc=1
B. Use Device Tree bindings, as described in
- ``Documentation/device-tree/bindings/reserved-memory/admin-guide/ramoops.rst``.
+ ``Documentation/devicetree/bindings/reserved-memory/ramoops.txt``.
For example::
reserved-memory {
diff --git a/Documentation/arm/Marvell/README b/Documentation/arm/Marvell/README
index b5bb7f5..56ada27c5 100644
--- a/Documentation/arm/Marvell/README
+++ b/Documentation/arm/Marvell/README
@@ -302,19 +302,15 @@
88DE3010, Armada 1000 (no Linux support)
Core: Marvell PJ1 (ARMv5TE), Dual-core
Product Brief: http://www.marvell.com.cn/digital-entertainment/assets/armada_1000_pb.pdf
- 88DE3005, Armada 1500-mini
88DE3005, Armada 1500 Mini
Design name: BG2CD
Core: ARM Cortex-A9, PL310 L2CC
- Homepage: http://www.marvell.com/multimedia-solutions/armada-1500-mini/
- 88DE3006, Armada 1500 Mini Plus
- Design name: BG2CDP
- Core: Dual Core ARM Cortex-A7
- Homepage: http://www.marvell.com/multimedia-solutions/armada-1500-mini-plus/
+ 88DE3006, Armada 1500 Mini Plus
+ Design name: BG2CDP
+ Core: Dual Core ARM Cortex-A7
88DE3100, Armada 1500
Design name: BG2
Core: Marvell PJ4B-MP (ARMv7), Tauros3 L2CC
- Product Brief: http://www.marvell.com/digital-entertainment/armada-1500/assets/Marvell-ARMADA-1500-Product-Brief.pdf
88DE3114, Armada 1500 Pro
Design name: BG2Q
Core: Quad Core ARM Cortex-A9, PL310 L2CC
@@ -324,13 +320,16 @@
88DE3218, ARMADA 1500 Ultra
Core: ARM Cortex-A53
- Homepage: http://www.marvell.com/multimedia-solutions/
+ Homepage: https://www.synaptics.com/products/multimedia-solutions
Directory: arch/arm/mach-berlin
Comments:
+
* This line of SoCs is based on Marvell Sheeva or ARM Cortex CPUs
with Synopsys DesignWare (IRQ, GPIO, Timers, ...) and PXA IP (SDHCI, USB, ETH, ...).
+ * The Berlin family was acquired by Synaptics from Marvell in 2017.
+
CPU Cores
---------
diff --git a/Documentation/block/cmdline-partition.txt b/Documentation/block/cmdline-partition.txt
index 525b9f6..760a3f7 100644
--- a/Documentation/block/cmdline-partition.txt
+++ b/Documentation/block/cmdline-partition.txt
@@ -1,7 +1,9 @@
Embedded device command line partition parsing
=====================================================================
-Support for reading the block device partition table from the command line.
+The "blkdevparts" command line option adds support for reading the
+block device partition table from the kernel command line.
+
It is typically used for fixed block (eMMC) embedded devices.
It has no MBR, so saves storage space. Bootloader can be easily accessed
by absolute address of data on the block device.
@@ -14,22 +16,27 @@
<partdef> := <size>[@<offset>](part-name)
<blkdev-id>
- block device disk name, embedded device used fixed block device,
- it's disk name also fixed. such as: mmcblk0, mmcblk1, mmcblk0boot0.
+ block device disk name. Embedded device uses fixed block device.
+ Its disk name is also fixed, such as: mmcblk0, mmcblk1, mmcblk0boot0.
<size>
partition size, in bytes, such as: 512, 1m, 1G.
+ size may contain an optional suffix of (upper or lower case):
+ K, M, G, T, P, E.
+ "-" is used to denote all remaining space.
<offset>
partition start address, in bytes.
+ offset may contain an optional suffix of (upper or lower case):
+ K, M, G, T, P, E.
(part-name)
- partition name, kernel send uevent with "PARTNAME". application can create
- a link to block device partition with the name "PARTNAME".
- user space application can access partition by partition name.
+ partition name. Kernel sends uevent with "PARTNAME". Application can
+ create a link to block device partition with the name "PARTNAME".
+ User space application can access partition by partition name.
Example:
- eMMC disk name is "mmcblk0" and "mmcblk0boot0"
+ eMMC disk names are "mmcblk0" and "mmcblk0boot0".
bootargs:
'blkdevparts=mmcblk0:1G(data0),1G(data1),-;mmcblk0boot0:1m(boot),-(kernel)'
diff --git a/Documentation/block/null_blk.txt b/Documentation/block/null_blk.txt
index 733927a..07f1473 100644
--- a/Documentation/block/null_blk.txt
+++ b/Documentation/block/null_blk.txt
@@ -71,13 +71,16 @@
1: The multi-queue block layer is instantiated with a hardware dispatch
queue for each CPU node in the system.
-use_lightnvm=[0/1]: Default: 0
- Register device with LightNVM. Requires blk-mq and CONFIG_NVM to be enabled.
-
no_sched=[0/1]: Default: 0
0: nullb* use default blk-mq io scheduler.
1: nullb* doesn't use io scheduler.
+blocking=[0/1]: Default: 0
+ 0: Register as a non-blocking blk-mq driver device.
+ 1: Register as a blocking blk-mq driver device, null_blk will set
+ the BLK_MQ_F_BLOCKING flag, indicating that it sometimes/always
+ needs to block in its ->queue_rq() function.
+
shared_tags=[0/1]: Default: 0
0: Tag set is not shared.
1: Tag set shared between devices for blk-mq. Only makes sense with
diff --git a/Documentation/bpf/bpf_devel_QA.txt b/Documentation/bpf/bpf_devel_QA.txt
index 1a0b704e..da57601 100644
--- a/Documentation/bpf/bpf_devel_QA.txt
+++ b/Documentation/bpf/bpf_devel_QA.txt
@@ -557,6 +557,14 @@
pulls in some header files containing file scope host assembly codes.
- You can add "-fno-jump-tables" to work around the switch table issue.
- Otherwise, you can use bpf target.
+ Otherwise, you can use bpf target. Additionally, you _must_ use bpf target
+ when:
+
+ - Your program uses data structures with pointer or long / unsigned long
+ types that interface with BPF helpers or context data structures. Access
+ into these structures is verified by the BPF verifier and may result
+ in verification failures if the native architecture is not aligned with
+ the BPF architecture, e.g. 64-bit. An example of this is
+ BPF_PROG_TYPE_SK_MSG require '-target bpf'
Happy BPF hacking!
diff --git a/Documentation/core-api/atomic_ops.rst b/Documentation/core-api/atomic_ops.rst
index fce9291..2e7165f 100644
--- a/Documentation/core-api/atomic_ops.rst
+++ b/Documentation/core-api/atomic_ops.rst
@@ -111,7 +111,6 @@
variable a, then the compiler is within its rights transforming this to
the following::
- tmp = a;
if (a > 0)
for (;;)
do_something();
@@ -119,7 +118,7 @@
If you don't want the compiler to do this (and you probably don't), then
you should use something like the following::
- while (READ_ONCE(a) < 0)
+ while (READ_ONCE(a) > 0)
do_something();
Alternatively, you could place a barrier() call in the loop.
@@ -467,10 +466,12 @@
indicates whether the changed bit was set _BEFORE_ the atomic bit
operation.
-WARNING! It is incredibly important that the value be a boolean,
-ie. "0" or "1". Do not try to be fancy and save a few instructions by
-declaring the above to return "long" and just returning something like
-"old_val & mask" because that will not work.
+
+.. warning::
+ It is incredibly important that the value be a boolean, ie. "0" or "1".
+ Do not try to be fancy and save a few instructions by declaring the
+ above to return "long" and just returning something like "old_val &
+ mask" because that will not work.
For one thing, this return value gets truncated to int in many code
paths using these interfaces, so on 64-bit if the bit is set in the
diff --git a/Documentation/cachetlb.txt b/Documentation/core-api/cachetlb.rst
similarity index 100%
rename from Documentation/cachetlb.txt
rename to Documentation/core-api/cachetlb.rst
diff --git a/Documentation/circular-buffers.txt b/Documentation/core-api/circular-buffers.rst
similarity index 100%
rename from Documentation/circular-buffers.txt
rename to Documentation/core-api/circular-buffers.rst
diff --git a/Documentation/core-api/gfp_mask-from-fs-io.rst b/Documentation/core-api/gfp_mask-from-fs-io.rst
new file mode 100644
index 0000000..e0df8f4
--- /dev/null
+++ b/Documentation/core-api/gfp_mask-from-fs-io.rst
@@ -0,0 +1,66 @@
+=================================
+GFP masks used from FS/IO context
+=================================
+
+:Date: May, 2018
+:Author: Michal Hocko <mhocko@kernel.org>
+
+Introduction
+============
+
+Code paths in the filesystem and IO stacks must be careful when
+allocating memory to prevent recursion deadlocks caused by direct
+memory reclaim calling back into the FS or IO paths and blocking on
+already held resources (e.g. locks - most commonly those used for the
+transaction context).
+
+The traditional way to avoid this deadlock problem is to clear __GFP_FS
+respectively __GFP_IO (note the latter implies clearing the first as well) in
+the gfp mask when calling an allocator. GFP_NOFS respectively GFP_NOIO can be
+used as shortcut. It turned out though that above approach has led to
+abuses when the restricted gfp mask is used "just in case" without a
+deeper consideration which leads to problems because an excessive use
+of GFP_NOFS/GFP_NOIO can lead to memory over-reclaim or other memory
+reclaim issues.
+
+New API
+========
+
+Since 4.12 we do have a generic scope API for both NOFS and NOIO context
+``memalloc_nofs_save``, ``memalloc_nofs_restore`` respectively ``memalloc_noio_save``,
+``memalloc_noio_restore`` which allow to mark a scope to be a critical
+section from a filesystem or I/O point of view. Any allocation from that
+scope will inherently drop __GFP_FS respectively __GFP_IO from the given
+mask so no memory allocation can recurse back in the FS/IO.
+
+.. kernel-doc:: include/linux/sched/mm.h
+ :functions: memalloc_nofs_save memalloc_nofs_restore
+.. kernel-doc:: include/linux/sched/mm.h
+ :functions: memalloc_noio_save memalloc_noio_restore
+
+FS/IO code then simply calls the appropriate save function before
+any critical section with respect to the reclaim is started - e.g.
+lock shared with the reclaim context or when a transaction context
+nesting would be possible via reclaim. The restore function should be
+called when the critical section ends. All that ideally along with an
+explanation what is the reclaim context for easier maintenance.
+
+Please note that the proper pairing of save/restore functions
+allows nesting so it is safe to call ``memalloc_noio_save`` or
+``memalloc_noio_restore`` respectively from an existing NOIO or NOFS
+scope.
+
+What about __vmalloc(GFP_NOFS)
+==============================
+
+vmalloc doesn't support GFP_NOFS semantic because there are hardcoded
+GFP_KERNEL allocations deep inside the allocator which are quite non-trivial
+to fix up. That means that calling ``vmalloc`` with GFP_NOFS/GFP_NOIO is
+almost always a bug. The good news is that the NOFS/NOIO semantic can be
+achieved by the scope API.
+
+In the ideal world, upper layers should already mark dangerous contexts
+and so no special care is required and vmalloc should be called without
+any problems. Sometimes if the context is not really clear or there are
+layering violations then the recommended way around that is to wrap ``vmalloc``
+by the scope API with a comment explaining the problem.
diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
index c670a80..f5a66b7 100644
--- a/Documentation/core-api/index.rst
+++ b/Documentation/core-api/index.rst
@@ -14,6 +14,7 @@
kernel-api
assoc_array
atomic_ops
+ cachetlb
refcount-vs-atomic
cpu_hotplug
idr
@@ -25,6 +26,8 @@
genalloc
errseq
printk-formats
+ circular-buffers
+ gfp_mask-from-fs-io
Interfaces for kernel debugging
===============================
diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst
index ff335f8..8e44aea 100644
--- a/Documentation/core-api/kernel-api.rst
+++ b/Documentation/core-api/kernel-api.rst
@@ -39,17 +39,17 @@
.. kernel-doc:: lib/string.c
:export:
+Basic Kernel Library Functions
+==============================
+
+The Linux kernel provides more basic utility functions.
+
Bit Operations
--------------
.. kernel-doc:: arch/x86/include/asm/bitops.h
:internal:
-Basic Kernel Library Functions
-==============================
-
-The Linux kernel provides more basic utility functions.
-
Bitmap Operations
-----------------
@@ -80,6 +80,31 @@
.. kernel-doc:: lib/cmdline.c
:export:
+Sorting
+-------
+
+.. kernel-doc:: lib/sort.c
+ :export:
+
+.. kernel-doc:: lib/list_sort.c
+ :export:
+
+Text Searching
+--------------
+
+.. kernel-doc:: lib/textsearch.c
+ :doc: ts_intro
+
+.. kernel-doc:: lib/textsearch.c
+ :export:
+
+.. kernel-doc:: include/linux/textsearch.h
+ :functions: textsearch_find textsearch_next \
+ textsearch_get_pattern textsearch_get_pattern_len
+
+CRC and Math Functions in Linux
+===============================
+
CRC Functions
-------------
@@ -103,9 +128,6 @@
.. kernel-doc:: lib/crc-itu-t.c
:export:
-Math Functions in Linux
-=======================
-
Base 2 log and power Functions
------------------------------
@@ -127,15 +149,6 @@
.. kernel-doc:: lib/gcd.c
:export:
-Sorting
--------
-
-.. kernel-doc:: lib/sort.c
- :export:
-
-.. kernel-doc:: lib/list_sort.c
- :export:
-
UUID/GUID
---------
diff --git a/Documentation/core-api/refcount-vs-atomic.rst b/Documentation/core-api/refcount-vs-atomic.rst
index 83351c2..322851b 100644
--- a/Documentation/core-api/refcount-vs-atomic.rst
+++ b/Documentation/core-api/refcount-vs-atomic.rst
@@ -17,7 +17,7 @@
these memory ordering guarantees.
The terms used through this document try to follow the formal LKMM defined in
-github.com/aparri/memory-model/blob/master/Documentation/explanation.txt
+tools/memory-model/Documentation/explanation.txt.
memory-barriers.txt and atomic_t.txt provide more background to the
memory ordering in general and for atomic operations specifically.
diff --git a/Documentation/crypto/index.rst b/Documentation/crypto/index.rst
index 94c4786..c4ff5d7 100644
--- a/Documentation/crypto/index.rst
+++ b/Documentation/crypto/index.rst
@@ -20,5 +20,6 @@
architecture
devel-algos
userspace-if
+ crypto_engine
api
api-samples
diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst
index f7a18f2..aabc873 100644
--- a/Documentation/dev-tools/kasan.rst
+++ b/Documentation/dev-tools/kasan.rst
@@ -120,7 +120,7 @@
The header of the report discribe what kind of bug happened and what kind of
access caused it. It's followed by the description of the accessed slub object
-(see 'SLUB Debug output' section in Documentation/vm/slub.txt for details) and
+(see 'SLUB Debug output' section in Documentation/vm/slub.rst for details) and
the description of the accessed memory page.
In the last section the report shows memory state around the accessed address.
diff --git a/Documentation/dev-tools/kselftest.rst b/Documentation/dev-tools/kselftest.rst
index e80850e..3bf371a 100644
--- a/Documentation/dev-tools/kselftest.rst
+++ b/Documentation/dev-tools/kselftest.rst
@@ -151,6 +151,11 @@
TEST_FILES, TEST_GEN_FILES mean it is the file which is used by
test.
+ * First use the headers inside the kernel source and/or git repo, and then the
+ system headers. Headers for the kernel release as opposed to headers
+ installed by the distro on the system should be the primary focus to be able
+ to find regressions.
+
Test Harness
============
diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt
index 4bcd4b7..3d01948 100644
--- a/Documentation/device-mapper/thin-provisioning.txt
+++ b/Documentation/device-mapper/thin-provisioning.txt
@@ -264,7 +264,10 @@
data device, but just remove the mapping.
read_only: Don't allow any changes to be made to the pool
- metadata.
+ metadata. This mode is only available after the
+ thin-pool has been created and first used in full
+ read/write mode. It cannot be specified on initial
+ thin-pool creation.
error_if_no_space: Error IOs, instead of queueing, if no space.
diff --git a/Documentation/devicetree/bindings/ata/ahci-platform.txt b/Documentation/devicetree/bindings/ata/ahci-platform.txt
index f4006d3..c760ecb 100644
--- a/Documentation/devicetree/bindings/ata/ahci-platform.txt
+++ b/Documentation/devicetree/bindings/ata/ahci-platform.txt
@@ -30,7 +30,6 @@
Optional properties:
- dma-coherent : Present if dma operations are coherent
- clocks : a list of phandle + clock specifier pairs
-- resets : a list of phandle + reset specifier pairs
- target-supply : regulator for SATA target power
- phys : reference to the SATA PHY node
- phy-names : must be "sata-phy"
diff --git a/Documentation/devicetree/bindings/display/panel/panel-common.txt b/Documentation/devicetree/bindings/display/panel/panel-common.txt
index 557fa76..5d2519a 100644
--- a/Documentation/devicetree/bindings/display/panel/panel-common.txt
+++ b/Documentation/devicetree/bindings/display/panel/panel-common.txt
@@ -38,7 +38,7 @@
require specific display timings. The panel-timing subnode expresses those
timings as specified in the timing subnode section of the display timing
bindings defined in
- Documentation/devicetree/bindings/display/display-timing.txt.
+ Documentation/devicetree/bindings/display/panel/display-timing.txt.
Connectivity
diff --git a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt
index aadfb23..61315ea 100644
--- a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt
+++ b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt
@@ -26,6 +26,7 @@
- "renesas,dmac-r8a7794" (R-Car E2)
- "renesas,dmac-r8a7795" (R-Car H3)
- "renesas,dmac-r8a7796" (R-Car M3-W)
+ - "renesas,dmac-r8a77965" (R-Car M3-N)
- "renesas,dmac-r8a77970" (R-Car V3M)
- "renesas,dmac-r8a77980" (R-Car V3H)
diff --git a/Documentation/devicetree/bindings/hwmon/gpio-fan.txt b/Documentation/devicetree/bindings/hwmon/gpio-fan.txt
index 439a743..2becdcf 100644
--- a/Documentation/devicetree/bindings/hwmon/gpio-fan.txt
+++ b/Documentation/devicetree/bindings/hwmon/gpio-fan.txt
@@ -11,7 +11,7 @@
must have the RPM values in ascending order.
- alarm-gpios: This pin going active indicates something is wrong with
the fan, and a udev event will be fired.
-- cooling-cells: If used as a cooling device, must be <2>
+- #cooling-cells: If used as a cooling device, must be <2>
Also see: Documentation/devicetree/bindings/thermal/thermal.txt
min and max states are derived from the speed-map of the fan.
diff --git a/Documentation/devicetree/bindings/hwmon/ltc2990.txt b/Documentation/devicetree/bindings/hwmon/ltc2990.txt
new file mode 100644
index 0000000..f92f540
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/ltc2990.txt
@@ -0,0 +1,36 @@
+ltc2990: Linear Technology LTC2990 power monitor
+
+Required properties:
+- compatible: Must be "lltc,ltc2990"
+- reg: I2C slave address
+- lltc,meas-mode:
+ An array of two integers for configuring the chip measurement mode.
+
+ The first integer defines the bits 2..0 in the control register. In all
+ cases the internal temperature and supply voltage are measured. In
+ addition the following input measurements are enabled per mode:
+
+ 0: V1, V2, TR2
+ 1: V1-V2, TR2
+ 2: V1-V2, V3, V4
+ 3: TR1, V3, V4
+ 4: TR1, V3-V4
+ 5: TR1, TR2
+ 6: V1-V2, V3-V4
+ 7: V1, V2, V3, V4
+
+ The second integer defines the bits 4..3 in the control register. This
+ allows a subset of the measurements to be enabled:
+
+ 0: Internal temperature and supply voltage only
+ 1: TR1, V1 or V1-V2 only per mode
+ 2: TR2, V3 or V3-V4 only per mode
+ 3: All measurements per mode
+
+Example:
+
+ltc2990@4c {
+ compatible = "lltc,ltc2990";
+ reg = <0x4c>;
+ lltc,meas-mode = <7 3>; /* V1, V2, V3, V4 */
+};
diff --git a/Documentation/devicetree/bindings/input/atmel,maxtouch.txt b/Documentation/devicetree/bindings/input/atmel,maxtouch.txt
index 23e3abc..c889194 100644
--- a/Documentation/devicetree/bindings/input/atmel,maxtouch.txt
+++ b/Documentation/devicetree/bindings/input/atmel,maxtouch.txt
@@ -4,6 +4,13 @@
- compatible:
atmel,maxtouch
+ The following compatibles have been used in various products but are
+ deprecated:
+ atmel,qt602240_ts
+ atmel,atmel_mxt_ts
+ atmel,atmel_mxt_tp
+ atmel,mXT224
+
- reg: The I2C address of the device
- interrupts: The sink for the touchpad's IRQ output
diff --git a/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt
index a83f9a5..89674ad 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt
@@ -9,11 +9,12 @@
Required properties:
-- compatible : must have "amlogic,meson8-gpio-intc” and either
- “amlogic,meson8-gpio-intc” for meson8 SoCs (S802) or
- “amlogic,meson8b-gpio-intc” for meson8b SoCs (S805) or
- “amlogic,meson-gxbb-gpio-intc” for GXBB SoCs (S905) or
- “amlogic,meson-gxl-gpio-intc” for GXL SoCs (S905X, S912)
+- compatible : must have "amlogic,meson8-gpio-intc" and either
+ "amlogic,meson8-gpio-intc" for meson8 SoCs (S802) or
+ "amlogic,meson8b-gpio-intc" for meson8b SoCs (S805) or
+ "amlogic,meson-gxbb-gpio-intc" for GXBB SoCs (S905) or
+ "amlogic,meson-gxl-gpio-intc" for GXL SoCs (S905X, S912)
+ "amlogic,meson-axg-gpio-intc" for AXG SoCs (A113D, A113X)
- interrupt-parent : a phandle to the GIC the interrupts are routed to.
Usually this is provided at the root level of the device tree as it is
common to most of the SoC.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt
index 0a57f2f..3ea78c4 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt
@@ -57,6 +57,20 @@
occupied by the redistributors. Required if more than one such
region is present.
+- msi-controller: Boolean property. Identifies the node as an MSI
+ controller. Only present if the Message Based Interrupt
+ functionnality is being exposed by the HW, and the mbi-ranges
+ property present.
+
+- mbi-ranges: A list of pairs <intid span>, where "intid" is the first
+ SPI of a range that can be used an MBI, and "span" the size of that
+ range. Multiple ranges can be provided. Requires "msi-controller" to
+ be set.
+
+- mbi-alias: Address property. Base address of an alias of the GICD
+ region containing only the {SET,CLR}SPI registers to be used if
+ isolation is required, and if supported by the HW.
+
Sub-nodes:
PPI affinity can be expressed as a single "ppi-partitions" node,
@@ -99,6 +113,9 @@
<0x0 0x2c020000 0 0x2000>; // GICV
interrupts = <1 9 4>;
+ msi-controller;
+ mbi-ranges = <256 128>;
+
gic-its@2c200000 {
compatible = "arm,gic-v3-its";
msi-controller;
diff --git a/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt b/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt
index edf03f0..136bd61 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt
@@ -5,11 +5,14 @@
- compatible: Should be:
"st,stm32-exti"
"st,stm32h7-exti"
+ "st,stm32mp1-exti"
- reg: Specifies base physical address and size of the registers
- interrupt-controller: Indentifies the node as an interrupt controller
- #interrupt-cells: Specifies the number of cells to encode an interrupt
specifier, shall be 2
- interrupts: interrupts references to primary interrupt controller
+ (only needed for exti controller with multiple exti under
+ same parent interrupt: st,stm32-exti and st,stm32h7-exti")
Example:
diff --git a/Documentation/devicetree/bindings/net/can/rcar_canfd.txt b/Documentation/devicetree/bindings/net/can/rcar_canfd.txt
index 93c3a6a..ac71daa 100644
--- a/Documentation/devicetree/bindings/net/can/rcar_canfd.txt
+++ b/Documentation/devicetree/bindings/net/can/rcar_canfd.txt
@@ -5,7 +5,9 @@
- compatible: Must contain one or more of the following:
- "renesas,rcar-gen3-canfd" for R-Car Gen3 compatible controller.
- "renesas,r8a7795-canfd" for R8A7795 (R-Car H3) compatible controller.
- - "renesas,r8a7796-canfd" for R8A7796 (R-Car M3) compatible controller.
+ - "renesas,r8a7796-canfd" for R8A7796 (R-Car M3-W) compatible controller.
+ - "renesas,r8a77970-canfd" for R8A77970 (R-Car V3M) compatible controller.
+ - "renesas,r8a77980-canfd" for R8A77980 (R-Car V3H) compatible controller.
When compatible with the generic version, nodes must list the
SoC-specific version corresponding to the platform first, followed by the
diff --git a/Documentation/devicetree/bindings/net/dsa/b53.txt b/Documentation/devicetree/bindings/net/dsa/b53.txt
index 8acf51a..47a6a7f 100644
--- a/Documentation/devicetree/bindings/net/dsa/b53.txt
+++ b/Documentation/devicetree/bindings/net/dsa/b53.txt
@@ -10,6 +10,7 @@
"brcm,bcm53128"
"brcm,bcm5365"
"brcm,bcm5395"
+ "brcm,bcm5389"
"brcm,bcm5397"
"brcm,bcm5398"
diff --git a/Documentation/devicetree/bindings/net/marvell-pp2.txt b/Documentation/devicetree/bindings/net/marvell-pp2.txt
index 1814fa1..fc019df 100644
--- a/Documentation/devicetree/bindings/net/marvell-pp2.txt
+++ b/Documentation/devicetree/bindings/net/marvell-pp2.txt
@@ -21,9 +21,10 @@
- main controller clock (for both armada-375-pp2 and armada-7k-pp2)
- GOP clock (for both armada-375-pp2 and armada-7k-pp2)
- MG clock (only for armada-7k-pp2)
+ - MG Core clock (only for armada-7k-pp2)
- AXI clock (only for armada-7k-pp2)
-- clock-names: names of used clocks, must be "pp_clk", "gop_clk", "mg_clk"
- and "axi_clk" (the 2 latter only for armada-7k-pp2).
+- clock-names: names of used clocks, must be "pp_clk", "gop_clk", "mg_clk",
+ "mg_core_clk" and "axi_clk" (the 3 latter only for armada-7k-pp2).
The ethernet ports are represented by subnodes. At least one port is
required.
@@ -80,8 +81,8 @@
compatible = "marvell,armada-7k-pp22";
reg = <0x0 0x100000>, <0x129000 0xb000>;
clocks = <&cpm_syscon0 1 3>, <&cpm_syscon0 1 9>,
- <&cpm_syscon0 1 5>, <&cpm_syscon0 1 18>;
- clock-names = "pp_clk", "gop_clk", "gp_clk", "axi_clk";
+ <&cpm_syscon0 1 5>, <&cpm_syscon0 1 6>, <&cpm_syscon0 1 18>;
+ clock-names = "pp_clk", "gop_clk", "mg_clk", "mg_core_clk", "axi_clk";
eth0: eth0 {
interrupts = <ICU_GRP_NSR 39 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt
index 42a2483..e22d8cf 100644
--- a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt
+++ b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt
@@ -57,6 +57,13 @@
- txd2-skew-ps : Skew control of TX data 2 pad
- txd3-skew-ps : Skew control of TX data 3 pad
+ - micrel,force-master:
+ Boolean, force phy to master mode. Only set this option if the phy
+ reference clock provided at CLK125_NDO pin is used as MAC reference
+ clock because the clock jitter in slave mode is to high (errata#2).
+ Attention: The link partner must be configurable as slave otherwise
+ no link will be established.
+
Examples:
mdio {
diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt
index c306f55..890526d 100644
--- a/Documentation/devicetree/bindings/net/renesas,ravb.txt
+++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt
@@ -18,6 +18,7 @@
- "renesas,etheravb-r8a7795" for the R8A7795 SoC.
- "renesas,etheravb-r8a7796" for the R8A7796 SoC.
+ - "renesas,etheravb-r8a77965" for the R8A77965 SoC.
- "renesas,etheravb-r8a77970" for the R8A77970 SoC.
- "renesas,etheravb-r8a77980" for the R8A77980 SoC.
- "renesas,etheravb-r8a77995" for the R8A77995 SoC.
diff --git a/Documentation/devicetree/bindings/opp/kryo-cpufreq.txt b/Documentation/devicetree/bindings/opp/kryo-cpufreq.txt
new file mode 100644
index 0000000..c2127b9
--- /dev/null
+++ b/Documentation/devicetree/bindings/opp/kryo-cpufreq.txt
@@ -0,0 +1,680 @@
+Qualcomm Technologies, Inc. KRYO CPUFreq and OPP bindings
+===================================
+
+In Certain Qualcomm Technologies, Inc. SoCs like apq8096 and msm8996
+that have KRYO processors, the CPU ferequencies subset and voltage value
+of each OPP varies based on the silicon variant in use.
+Qualcomm Technologies, Inc. Process Voltage Scaling Tables
+defines the voltage and frequency value based on the msm-id in SMEM
+and speedbin blown in the efuse combination.
+The qcom-cpufreq-kryo driver reads the msm-id and efuse value from the SoC
+to provide the OPP framework with required information (existing HW bitmap).
+This is used to determine the voltage and frequency value for each OPP of
+operating-points-v2 table when it is parsed by the OPP framework.
+
+Required properties:
+--------------------
+In 'cpus' nodes:
+- operating-points-v2: Phandle to the operating-points-v2 table to use.
+
+In 'operating-points-v2' table:
+- compatible: Should be
+ - 'operating-points-v2-kryo-cpu' for apq8096 and msm8996.
+- nvmem-cells: A phandle pointing to a nvmem-cells node representing the
+ efuse registers that has information about the
+ speedbin that is used to select the right frequency/voltage
+ value pair.
+ Please refer the for nvmem-cells
+ bindings Documentation/devicetree/bindings/nvmem/nvmem.txt
+ and also examples below.
+
+In every OPP node:
+- opp-supported-hw: A single 32 bit bitmap value, representing compatible HW.
+ Bitmap:
+ 0: MSM8996 V3, speedbin 0
+ 1: MSM8996 V3, speedbin 1
+ 2: MSM8996 V3, speedbin 2
+ 3: unused
+ 4: MSM8996 SG, speedbin 0
+ 5: MSM8996 SG, speedbin 1
+ 6: MSM8996 SG, speedbin 2
+ 7-31: unused
+
+Example 1:
+---------
+
+ cpus {
+ #address-cells = <2>;
+ #size-cells = <0>;
+
+ CPU0: cpu@0 {
+ device_type = "cpu";
+ compatible = "qcom,kryo";
+ reg = <0x0 0x0>;
+ enable-method = "psci";
+ clocks = <&kryocc 0>;
+ cpu-supply = <&pm8994_s11_saw>;
+ operating-points-v2 = <&cluster0_opp>;
+ #cooling-cells = <2>;
+ next-level-cache = <&L2_0>;
+ L2_0: l2-cache {
+ compatible = "cache";
+ cache-level = <2>;
+ };
+ };
+
+ CPU1: cpu@1 {
+ device_type = "cpu";
+ compatible = "qcom,kryo";
+ reg = <0x0 0x1>;
+ enable-method = "psci";
+ clocks = <&kryocc 0>;
+ cpu-supply = <&pm8994_s11_saw>;
+ operating-points-v2 = <&cluster0_opp>;
+ #cooling-cells = <2>;
+ next-level-cache = <&L2_0>;
+ };
+
+ CPU2: cpu@100 {
+ device_type = "cpu";
+ compatible = "qcom,kryo";
+ reg = <0x0 0x100>;
+ enable-method = "psci";
+ clocks = <&kryocc 1>;
+ cpu-supply = <&pm8994_s11_saw>;
+ operating-points-v2 = <&cluster1_opp>;
+ #cooling-cells = <2>;
+ next-level-cache = <&L2_1>;
+ L2_1: l2-cache {
+ compatible = "cache";
+ cache-level = <2>;
+ };
+ };
+
+ CPU3: cpu@101 {
+ device_type = "cpu";
+ compatible = "qcom,kryo";
+ reg = <0x0 0x101>;
+ enable-method = "psci";
+ clocks = <&kryocc 1>;
+ cpu-supply = <&pm8994_s11_saw>;
+ operating-points-v2 = <&cluster1_opp>;
+ #cooling-cells = <2>;
+ next-level-cache = <&L2_1>;
+ };
+
+ cpu-map {
+ cluster0 {
+ core0 {
+ cpu = <&CPU0>;
+ };
+
+ core1 {
+ cpu = <&CPU1>;
+ };
+ };
+
+ cluster1 {
+ core0 {
+ cpu = <&CPU2>;
+ };
+
+ core1 {
+ cpu = <&CPU3>;
+ };
+ };
+ };
+ };
+
+ cluster0_opp: opp_table0 {
+ compatible = "operating-points-v2-kryo-cpu";
+ nvmem-cells = <&speedbin_efuse>;
+ opp-shared;
+
+ opp-307200000 {
+ opp-hz = /bits/ 64 <307200000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x77>;
+ clock-latency-ns = <200000>;
+ };
+ opp-384000000 {
+ opp-hz = /bits/ 64 <384000000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-422400000 {
+ opp-hz = /bits/ 64 <422400000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-460800000 {
+ opp-hz = /bits/ 64 <460800000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-480000000 {
+ opp-hz = /bits/ 64 <480000000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-537600000 {
+ opp-hz = /bits/ 64 <537600000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-556800000 {
+ opp-hz = /bits/ 64 <556800000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-614400000 {
+ opp-hz = /bits/ 64 <614400000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-652800000 {
+ opp-hz = /bits/ 64 <652800000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-691200000 {
+ opp-hz = /bits/ 64 <691200000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-729600000 {
+ opp-hz = /bits/ 64 <729600000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-768000000 {
+ opp-hz = /bits/ 64 <768000000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-844800000 {
+ opp-hz = /bits/ 64 <844800000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x77>;
+ clock-latency-ns = <200000>;
+ };
+ opp-902400000 {
+ opp-hz = /bits/ 64 <902400000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-960000000 {
+ opp-hz = /bits/ 64 <960000000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-979200000 {
+ opp-hz = /bits/ 64 <979200000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1036800000 {
+ opp-hz = /bits/ 64 <1036800000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1056000000 {
+ opp-hz = /bits/ 64 <1056000000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1113600000 {
+ opp-hz = /bits/ 64 <1113600000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1132800000 {
+ opp-hz = /bits/ 64 <1132800000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1190400000 {
+ opp-hz = /bits/ 64 <1190400000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1209600000 {
+ opp-hz = /bits/ 64 <1209600000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1228800000 {
+ opp-hz = /bits/ 64 <1228800000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1286400000 {
+ opp-hz = /bits/ 64 <1286400000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1324800000 {
+ opp-hz = /bits/ 64 <1324800000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x5>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1363200000 {
+ opp-hz = /bits/ 64 <1363200000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x72>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1401600000 {
+ opp-hz = /bits/ 64 <1401600000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x5>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1440000000 {
+ opp-hz = /bits/ 64 <1440000000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1478400000 {
+ opp-hz = /bits/ 64 <1478400000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x1>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1497600000 {
+ opp-hz = /bits/ 64 <1497600000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x4>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1516800000 {
+ opp-hz = /bits/ 64 <1516800000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1593600000 {
+ opp-hz = /bits/ 64 <1593600000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x71>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1996800000 {
+ opp-hz = /bits/ 64 <1996800000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x20>;
+ clock-latency-ns = <200000>;
+ };
+ opp-2188800000 {
+ opp-hz = /bits/ 64 <2188800000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x10>;
+ clock-latency-ns = <200000>;
+ };
+ };
+
+ cluster1_opp: opp_table1 {
+ compatible = "operating-points-v2-kryo-cpu";
+ nvmem-cells = <&speedbin_efuse>;
+ opp-shared;
+
+ opp-307200000 {
+ opp-hz = /bits/ 64 <307200000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x77>;
+ clock-latency-ns = <200000>;
+ };
+ opp-384000000 {
+ opp-hz = /bits/ 64 <384000000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-403200000 {
+ opp-hz = /bits/ 64 <403200000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-460800000 {
+ opp-hz = /bits/ 64 <460800000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-480000000 {
+ opp-hz = /bits/ 64 <480000000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-537600000 {
+ opp-hz = /bits/ 64 <537600000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-556800000 {
+ opp-hz = /bits/ 64 <556800000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-614400000 {
+ opp-hz = /bits/ 64 <614400000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-652800000 {
+ opp-hz = /bits/ 64 <652800000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-691200000 {
+ opp-hz = /bits/ 64 <691200000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-729600000 {
+ opp-hz = /bits/ 64 <729600000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-748800000 {
+ opp-hz = /bits/ 64 <748800000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-806400000 {
+ opp-hz = /bits/ 64 <806400000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-825600000 {
+ opp-hz = /bits/ 64 <825600000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-883200000 {
+ opp-hz = /bits/ 64 <883200000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-902400000 {
+ opp-hz = /bits/ 64 <902400000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-940800000 {
+ opp-hz = /bits/ 64 <940800000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-979200000 {
+ opp-hz = /bits/ 64 <979200000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1036800000 {
+ opp-hz = /bits/ 64 <1036800000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1056000000 {
+ opp-hz = /bits/ 64 <1056000000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1113600000 {
+ opp-hz = /bits/ 64 <1113600000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1132800000 {
+ opp-hz = /bits/ 64 <1132800000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1190400000 {
+ opp-hz = /bits/ 64 <1190400000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1209600000 {
+ opp-hz = /bits/ 64 <1209600000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1248000000 {
+ opp-hz = /bits/ 64 <1248000000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1286400000 {
+ opp-hz = /bits/ 64 <1286400000>;
+ opp-microvolt = <905000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1324800000 {
+ opp-hz = /bits/ 64 <1324800000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1363200000 {
+ opp-hz = /bits/ 64 <1363200000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1401600000 {
+ opp-hz = /bits/ 64 <1401600000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1440000000 {
+ opp-hz = /bits/ 64 <1440000000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1478400000 {
+ opp-hz = /bits/ 64 <1478400000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1516800000 {
+ opp-hz = /bits/ 64 <1516800000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1555200000 {
+ opp-hz = /bits/ 64 <1555200000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1593600000 {
+ opp-hz = /bits/ 64 <1593600000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1632000000 {
+ opp-hz = /bits/ 64 <1632000000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1670400000 {
+ opp-hz = /bits/ 64 <1670400000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1708800000 {
+ opp-hz = /bits/ 64 <1708800000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1747200000 {
+ opp-hz = /bits/ 64 <1747200000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x70>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1785600000 {
+ opp-hz = /bits/ 64 <1785600000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x7>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1804800000 {
+ opp-hz = /bits/ 64 <1804800000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x6>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1824000000 {
+ opp-hz = /bits/ 64 <1824000000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x71>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1900800000 {
+ opp-hz = /bits/ 64 <1900800000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x74>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1920000000 {
+ opp-hz = /bits/ 64 <1920000000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x1>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1977600000 {
+ opp-hz = /bits/ 64 <1977600000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x30>;
+ clock-latency-ns = <200000>;
+ };
+ opp-1996800000 {
+ opp-hz = /bits/ 64 <1996800000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x1>;
+ clock-latency-ns = <200000>;
+ };
+ opp-2054400000 {
+ opp-hz = /bits/ 64 <2054400000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x30>;
+ clock-latency-ns = <200000>;
+ };
+ opp-2073600000 {
+ opp-hz = /bits/ 64 <2073600000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x1>;
+ clock-latency-ns = <200000>;
+ };
+ opp-2150400000 {
+ opp-hz = /bits/ 64 <2150400000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x31>;
+ clock-latency-ns = <200000>;
+ };
+ opp-2246400000 {
+ opp-hz = /bits/ 64 <2246400000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x10>;
+ clock-latency-ns = <200000>;
+ };
+ opp-2342400000 {
+ opp-hz = /bits/ 64 <2342400000>;
+ opp-microvolt = <1140000 905000 1140000>;
+ opp-supported-hw = <0x10>;
+ clock-latency-ns = <200000>;
+ };
+ };
+
+....
+
+reserved-memory {
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+....
+ smem_mem: smem-mem@86000000 {
+ reg = <0x0 0x86000000 0x0 0x200000>;
+ no-map;
+ };
+....
+};
+
+smem {
+ compatible = "qcom,smem";
+ memory-region = <&smem_mem>;
+ hwlocks = <&tcsr_mutex 3>;
+};
+
+soc {
+....
+ qfprom: qfprom@74000 {
+ compatible = "qcom,qfprom";
+ reg = <0x00074000 0x8ff>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+ ....
+ speedbin_efuse: speedbin@133 {
+ reg = <0x133 0x1>;
+ bits = <5 3>;
+ };
+ };
+};
diff --git a/Documentation/devicetree/bindings/opp/opp.txt b/Documentation/devicetree/bindings/opp/opp.txt
index 4e4f302..c396c4c 100644
--- a/Documentation/devicetree/bindings/opp/opp.txt
+++ b/Documentation/devicetree/bindings/opp/opp.txt
@@ -82,7 +82,10 @@
properties.
Required properties:
-- opp-hz: Frequency in Hz, expressed as a 64-bit big-endian integer.
+- opp-hz: Frequency in Hz, expressed as a 64-bit big-endian integer. This is a
+ required property for all device nodes but devices like power domains. The
+ power domain nodes must have another (implementation dependent) property which
+ uniquely identifies the OPP nodes.
Optional properties:
- opp-microvolt: voltage in micro Volts.
@@ -159,7 +162,7 @@
- status: Marks the node enabled/disabled.
-- required-opp: This contains phandle to an OPP node in another device's OPP
+- required-opps: This contains phandle to an OPP node in another device's OPP
table. It may contain an array of phandles, where each phandle points to an
OPP of a different device. It should not contain multiple phandles to the OPP
nodes in the same OPP table. This specifies the minimum required OPP of the
diff --git a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
index ed5eb54..64bc5c2 100644
--- a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
@@ -56,9 +56,9 @@
configuration, drive strength and pullups. If one of these options is
not set, its actual value will be unspecified.
-This driver supports the generic pin multiplexing and configuration
-bindings. For details on each properties, you can refer to
-./pinctrl-bindings.txt.
+Allwinner A1X Pin Controller supports the generic pin multiplexing and
+configuration bindings. For details on each properties, you can refer to
+ ./pinctrl-bindings.txt.
Required sub-node properties:
- pins
diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt
index f335531..4733f76 100644
--- a/Documentation/devicetree/bindings/power/power_domain.txt
+++ b/Documentation/devicetree/bindings/power/power_domain.txt
@@ -127,7 +127,7 @@
with the label "power".
Optional properties:
-- required-opp: This contains phandle to an OPP node in another device's OPP
+- required-opps: This contains phandle to an OPP node in another device's OPP
table. It may contain an array of phandles, where each phandle points to an
OPP of a different device. It should not contain multiple phandles to the OPP
nodes in the same OPP table. This specifies the minimum required OPP of the
@@ -175,14 +175,14 @@
compatible = "foo,i-leak-current";
reg = <0x12350000 0x1000>;
power-domains = <&power 0>;
- required-opp = <&domain0_opp_0>;
+ required-opps = <&domain0_opp_0>;
};
leaky-device1@12350000 {
compatible = "foo,i-leak-current";
reg = <0x12350000 0x1000>;
power-domains = <&power 1>;
- required-opp = <&domain1_opp_1>;
+ required-opps = <&domain1_opp_1>;
};
[1]. Documentation/devicetree/bindings/power/domain-idle-state.txt
diff --git a/Documentation/devicetree/bindings/power/rockchip-io-domain.txt b/Documentation/devicetree/bindings/power/rockchip-io-domain.txt
index 4a4766e..e66fd4e 100644
--- a/Documentation/devicetree/bindings/power/rockchip-io-domain.txt
+++ b/Documentation/devicetree/bindings/power/rockchip-io-domain.txt
@@ -31,6 +31,8 @@
Required properties:
- compatible: should be one of:
+ - "rockchip,px30-io-voltage-domain" for px30
+ - "rockchip,px30-pmu-io-voltage-domain" for px30 pmu-domains
- "rockchip,rk3188-io-voltage-domain" for rk3188
- "rockchip,rk3228-io-voltage-domain" for rk3228
- "rockchip,rk3288-io-voltage-domain" for rk3288
@@ -51,6 +53,19 @@
to report their voltage. The IO Voltage Domain for any non-specified
supplies will be not be touched.
+Possible supplies for PX30:
+- vccio6-supply: The supply connected to VCCIO6.
+- vccio1-supply: The supply connected to VCCIO1.
+- vccio2-supply: The supply connected to VCCIO2.
+- vccio3-supply: The supply connected to VCCIO3.
+- vccio4-supply: The supply connected to VCCIO4.
+- vccio5-supply: The supply connected to VCCIO5.
+- vccio-oscgpi-supply: The supply connected to VCCIO_OSCGPI.
+
+Possible supplies for PX30 pmu-domains:
+- pmuio1-supply: The supply connected to PMUIO1.
+- pmuio2-supply: The supply connected to PMUIO2.
+
Possible supplies for rk3188:
- ap0-supply: The supply connected to AP0_VCC.
- ap1-supply: The supply connected to AP1_VCC.
diff --git a/Documentation/devicetree/bindings/serial/amlogic,meson-uart.txt b/Documentation/devicetree/bindings/serial/amlogic,meson-uart.txt
index 8ff65fa..c06c045 100644
--- a/Documentation/devicetree/bindings/serial/amlogic,meson-uart.txt
+++ b/Documentation/devicetree/bindings/serial/amlogic,meson-uart.txt
@@ -21,7 +21,7 @@
- interrupts : identifier to the device interrupt
- clocks : a list of phandle + clock-specifier pairs, one for each
entry in clock names.
-- clocks-names :
+- clock-names :
* "xtal" for external xtal clock identifier
* "pclk" for the bus core clock, either the clk81 clock or the gate clock
* "baud" for the source of the baudrate generator, can be either the xtal
diff --git a/Documentation/devicetree/bindings/serial/mvebu-uart.txt b/Documentation/devicetree/bindings/serial/mvebu-uart.txt
index 2ae2fee..b7e0e32 100644
--- a/Documentation/devicetree/bindings/serial/mvebu-uart.txt
+++ b/Documentation/devicetree/bindings/serial/mvebu-uart.txt
@@ -24,7 +24,7 @@
- Must contain two elements for the extended variant of the IP
(marvell,armada-3700-uart-ext): "uart-tx" and "uart-rx",
respectively the UART TX interrupt and the UART RX interrupt. A
- corresponding interrupts-names property must be defined.
+ corresponding interrupt-names property must be defined.
- For backward compatibility reasons, a single element interrupts
property is also supported for the standard variant of the IP,
containing only the UART sum interrupt. This form is deprecated
diff --git a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
index ad962f4..106808b 100644
--- a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
+++ b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
@@ -17,6 +17,8 @@
- "renesas,scifa-r8a7745" for R8A7745 (RZ/G1E) SCIFA compatible UART.
- "renesas,scifb-r8a7745" for R8A7745 (RZ/G1E) SCIFB compatible UART.
- "renesas,hscif-r8a7745" for R8A7745 (RZ/G1E) HSCIF compatible UART.
+ - "renesas,scif-r8a77470" for R8A77470 (RZ/G1C) SCIF compatible UART.
+ - "renesas,hscif-r8a77470" for R8A77470 (RZ/G1C) HSCIF compatible UART.
- "renesas,scif-r8a7778" for R8A7778 (R-Car M1) SCIF compatible UART.
- "renesas,scif-r8a7779" for R8A7779 (R-Car H1) SCIF compatible UART.
- "renesas,scif-r8a7790" for R8A7790 (R-Car H2) SCIF compatible UART.
@@ -41,6 +43,8 @@
- "renesas,hscif-r8a7795" for R8A7795 (R-Car H3) HSCIF compatible UART.
- "renesas,scif-r8a7796" for R8A7796 (R-Car M3-W) SCIF compatible UART.
- "renesas,hscif-r8a7796" for R8A7796 (R-Car M3-W) HSCIF compatible UART.
+ - "renesas,scif-r8a77965" for R8A77965 (R-Car M3-N) SCIF compatible UART.
+ - "renesas,hscif-r8a77965" for R8A77965 (R-Car M3-N) HSCIF compatible UART.
- "renesas,scif-r8a77970" for R8A77970 (R-Car V3M) SCIF compatible UART.
- "renesas,hscif-r8a77970" for R8A77970 (R-Car V3M) HSCIF compatible UART.
- "renesas,scif-r8a77980" for R8A77980 (R-Car V3H) SCIF compatible UART.
diff --git a/Documentation/devicetree/bindings/thermal/exynos-thermal.txt b/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
index 1b596fd..b957acf 100644
--- a/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
@@ -49,19 +49,6 @@
- samsung,exynos5433-tmu: 8
- samsung,exynos7-tmu: 8
-Following properties are mandatory (depending on SoC):
-- samsung,tmu_gain: Gain value for internal TMU operation.
-- samsung,tmu_reference_voltage: Value of TMU IP block's reference voltage
-- samsung,tmu_noise_cancel_mode: Mode for noise cancellation
-- samsung,tmu_efuse_value: Default level of temperature - it is needed when
- in factory fusing produced wrong value
-- samsung,tmu_min_efuse_value: Minimum temperature fused value
-- samsung,tmu_max_efuse_value: Maximum temperature fused value
-- samsung,tmu_first_point_trim: First point trimming value
-- samsung,tmu_second_point_trim: Second point trimming value
-- samsung,tmu_default_temp_offset: Default temperature offset
-- samsung,tmu_cal_type: Callibration type
-
** Optional properties:
- vtmu-supply: This entry is optional and provides the regulator node supplying
@@ -78,7 +65,7 @@
clocks = <&clock 383>;
clock-names = "tmu_apbif";
vtmu-supply = <&tmu_regulator_node>;
- #include "exynos4412-tmu-sensor-conf.dtsi"
+ #thermal-sensor-cells = <0>;
};
Example 2):
@@ -89,7 +76,7 @@
interrupts = <0 58 0>;
clocks = <&clock 21>;
clock-names = "tmu_apbif";
- #include "exynos5440-tmu-sensor-conf.dtsi"
+ #thermal-sensor-cells = <0>;
};
Example 3): (In case of Exynos5420 "with misplaced TRIMINFO register")
@@ -99,7 +86,7 @@
interrupts = <0 184 0>;
clocks = <&clock 318>, <&clock 318>;
clock-names = "tmu_apbif", "tmu_triminfo_apbif";
- #include "exynos4412-tmu-sensor-conf.dtsi"
+ #thermal-sensor-cells = <0>;
};
tmu_cpu3: tmu@1006c000 {
@@ -108,7 +95,7 @@
interrupts = <0 185 0>;
clocks = <&clock 318>, <&clock 319>;
clock-names = "tmu_apbif", "tmu_triminfo_apbif";
- #include "exynos4412-tmu-sensor-conf.dtsi"
+ #thermal-sensor-cells = <0>;
};
tmu_gpu: tmu@100a0000 {
@@ -117,7 +104,7 @@
interrupts = <0 215 0>;
clocks = <&clock 319>, <&clock 318>;
clock-names = "tmu_apbif", "tmu_triminfo_apbif";
- #include "exynos4412-tmu-sensor-conf.dtsi"
+ #thermal-sensor-cells = <0>;
};
Note: For multi-instance tmu each instance should have an alias correctly
diff --git a/Documentation/devicetree/bindings/thermal/thermal.txt b/Documentation/devicetree/bindings/thermal/thermal.txt
index 1719d47..cc553f0 100644
--- a/Documentation/devicetree/bindings/thermal/thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/thermal.txt
@@ -55,8 +55,7 @@
the different fan speeds possible. Cooling states are referred to by
single unsigned integers, where larger numbers mean greater heat
dissipation. The precise set of cooling states associated with a device
-(as referred to by the cooling-min-level and cooling-max-level
-properties) should be defined in a particular device's binding.
+should be defined in a particular device's binding.
For more examples of cooling devices, refer to the example sections below.
Required properties:
@@ -69,15 +68,6 @@
See Cooling device maps section below for more details
on how consumers refer to cooling devices.
-Optional properties:
-- cooling-min-level: An integer indicating the smallest
- Type: unsigned cooling state accepted. Typically 0.
- Size: one cell
-
-- cooling-max-level: An integer indicating the largest
- Type: unsigned cooling state accepted.
- Size: one cell
-
* Trip points
The trip node is a node to describe a point in the temperature domain
@@ -226,8 +216,6 @@
396000 950000
198000 850000
>;
- cooling-min-level = <0>;
- cooling-max-level = <3>;
#cooling-cells = <2>; /* min followed by max */
};
...
@@ -241,8 +229,6 @@
*/
fan0: fan@48 {
...
- cooling-min-level = <0>;
- cooling-max-level = <9>;
#cooling-cells = <2>; /* min followed by max */
};
};
diff --git a/Documentation/devicetree/bindings/timer/nuvoton,npcm7xx-timer.txt b/Documentation/devicetree/bindings/timer/nuvoton,npcm7xx-timer.txt
new file mode 100644
index 0000000..ea22dfe
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/nuvoton,npcm7xx-timer.txt
@@ -0,0 +1,21 @@
+Nuvoton NPCM7xx timer
+
+Nuvoton NPCM7xx have three timer modules, each timer module provides five 24-bit
+timer counters.
+
+Required properties:
+- compatible : "nuvoton,npcm750-timer" for Poleg NPCM750.
+- reg : Offset and length of the register set for the device.
+- interrupts : Contain the timer interrupt with flags for
+ falling edge.
+- clocks : phandle of timer reference clock (usually a 25 MHz clock).
+
+Example:
+
+timer@f0008000 {
+ compatible = "nuvoton,npcm750-timer";
+ interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
+ reg = <0xf0008000 0x50>;
+ clocks = <&clk NPCM7XX_CLK_TIMER>;
+};
+
diff --git a/Documentation/devicetree/bindings/timer/nxp,tpm-timer.txt b/Documentation/devicetree/bindings/timer/nxp,tpm-timer.txt
index b4aa7dd..f82087b 100644
--- a/Documentation/devicetree/bindings/timer/nxp,tpm-timer.txt
+++ b/Documentation/devicetree/bindings/timer/nxp,tpm-timer.txt
@@ -15,7 +15,7 @@
- interrupts : Should be the clock event device interrupt.
- clocks : The clocks provided by the SoC to drive the timer, must contain
an entry for each entry in clock-names.
-- clock-names : Must include the following entries: "igp" and "per".
+- clock-names : Must include the following entries: "ipg" and "per".
Example:
tpm5: tpm@40260000 {
diff --git a/Documentation/devicetree/bindings/usb/usb-xhci.txt b/Documentation/devicetree/bindings/usb/usb-xhci.txt
index c4c00df..bd1dd31 100644
--- a/Documentation/devicetree/bindings/usb/usb-xhci.txt
+++ b/Documentation/devicetree/bindings/usb/usb-xhci.txt
@@ -28,7 +28,10 @@
- interrupts: one XHCI interrupt should be described here.
Optional properties:
- - clocks: reference to a clock
+ - clocks: reference to the clocks
+ - clock-names: mandatory if there is a second clock, in this case
+ the name must be "core" for the first clock and "reg" for the
+ second one
- usb2-lpm-disable: indicate if we don't want to enable USB2 HW LPM
- usb3-lpm-capable: determines if platform is USB3 LPM capable
- quirk-broken-port-ped: set if the controller has broken port disable mechanism
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index b5f978a..a38d8bf 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -182,6 +182,7 @@
keithkoep Keith & Koep GmbH
keymile Keymile GmbH
khadas Khadas
+kiebackpeter Kieback & Peter GmbH
kinetic Kinetic Technologies
kingnovel Kingnovel Technology Co., Ltd.
kosagi Sutajio Ko-Usagi PTE Ltd.
diff --git a/Documentation/devicetree/overlay-notes.txt b/Documentation/devicetree/overlay-notes.txt
index a4feb6d..725fb8d 100644
--- a/Documentation/devicetree/overlay-notes.txt
+++ b/Documentation/devicetree/overlay-notes.txt
@@ -98,6 +98,14 @@
of_overlay_remove_all() which will remove every single one in the correct
order.
+In addition, there is the option to register notifiers that get called on
+overlay operations. See of_overlay_notifier_register/unregister and
+enum of_overlay_notify_action for details.
+
+Note that a notifier callback is not supposed to store pointers to a device
+tree node or its content beyond OF_OVERLAY_POST_REMOVE corresponding to the
+respective node it received.
+
Overlay DTS Format
------------------
diff --git a/Documentation/doc-guide/parse-headers.rst b/Documentation/doc-guide/parse-headers.rst
index 96a0423..82a3e43b6 100644
--- a/Documentation/doc-guide/parse-headers.rst
+++ b/Documentation/doc-guide/parse-headers.rst
@@ -177,14 +177,14 @@
****
-Report bugs to Mauro Carvalho Chehab <mchehab@s-opensource.com>
+Report bugs to Mauro Carvalho Chehab <mchehab@kernel.org>
COPYRIGHT
*********
-Copyright (c) 2016 by Mauro Carvalho Chehab <mchehab@s-opensource.com>.
+Copyright (c) 2016 by Mauro Carvalho Chehab <mchehab+samsung@kernel.org>.
License GPLv2: GNU GPL version 2 <http://gnu.org/licenses/gpl.html>.
diff --git a/Documentation/clk.txt b/Documentation/driver-api/clk.rst
similarity index 100%
rename from Documentation/clk.txt
rename to Documentation/driver-api/clk.rst
diff --git a/Documentation/driver-api/device_connection.rst b/Documentation/driver-api/device_connection.rst
index affbc556..ba36422 100644
--- a/Documentation/driver-api/device_connection.rst
+++ b/Documentation/driver-api/device_connection.rst
@@ -40,4 +40,4 @@
---
.. kernel-doc:: drivers/base/devcon.c
- : functions: device_connection_find_match device_connection_find device_connection_add device_connection_remove
+ :functions: device_connection_find_match device_connection_find device_connection_add device_connection_remove
diff --git a/Documentation/driver-api/firmware/request_firmware.rst b/Documentation/driver-api/firmware/request_firmware.rst
index cf4516d..d5ec95a 100644
--- a/Documentation/driver-api/firmware/request_firmware.rst
+++ b/Documentation/driver-api/firmware/request_firmware.rst
@@ -17,17 +17,17 @@
request_firmware
----------------
-.. kernel-doc:: drivers/base/firmware_class.c
+.. kernel-doc:: drivers/base/firmware_loader/main.c
:functions: request_firmware
request_firmware_direct
-----------------------
-.. kernel-doc:: drivers/base/firmware_class.c
+.. kernel-doc:: drivers/base/firmware_loader/main.c
:functions: request_firmware_direct
request_firmware_into_buf
-------------------------
-.. kernel-doc:: drivers/base/firmware_class.c
+.. kernel-doc:: drivers/base/firmware_loader/main.c
:functions: request_firmware_into_buf
Asynchronous firmware requests
@@ -41,7 +41,7 @@
request_firmware_nowait
-----------------------
-.. kernel-doc:: drivers/base/firmware_class.c
+.. kernel-doc:: drivers/base/firmware_loader/main.c
:functions: request_firmware_nowait
Special optimizations on reboot
@@ -50,12 +50,12 @@
Some devices have an optimization in place to enable the firmware to be
retained during system reboot. When such optimizations are used the driver
author must ensure the firmware is still available on resume from suspend,
-this can be done with firmware_request_cache() insted of requesting for the
-firmare to be loaded.
+this can be done with firmware_request_cache() instead of requesting for the
+firmware to be loaded.
firmware_request_cache()
------------------------
-.. kernel-doc:: drivers/base/firmware_class.c
+------------------------
+.. kernel-doc:: drivers/base/firmware_loader/main.c
:functions: firmware_request_cache
request firmware API expected driver use
diff --git a/Documentation/driver-api/gpio/driver.rst b/Documentation/driver-api/gpio/driver.rst
index 505ee90..cbe0242 100644
--- a/Documentation/driver-api/gpio/driver.rst
+++ b/Documentation/driver-api/gpio/driver.rst
@@ -44,7 +44,7 @@
- methods to establish GPIO line direction
- methods used to access GPIO line values
- - method to set electrical configuration to a a given GPIO line
+ - method to set electrical configuration for a given GPIO line
- method to return the IRQ number associated to a given GPIO line
- flag saying whether calls to its methods may sleep
- optional line names array to identify lines
@@ -143,7 +143,7 @@
the rail actively pulls it down.
The level on the line will go as high as the VDD on the pull-up resistor, which
-may be higher than the level supported by the transistor, achieveing a
+may be higher than the level supported by the transistor, achieving a
level-shift to the higher VDD.
Integrated electronics often have an output driver stage in the form of a CMOS
@@ -382,7 +382,7 @@
Any provider of irqchips needs to be carefully tailored to support Real Time
preemption. It is desirable that all irqchips in the GPIO subsystem keep this
-in mind and does the proper testing to assure they are real time-enabled.
+in mind and do the proper testing to assure they are real time-enabled.
So, pay attention on above " RT_FULL:" notes, please.
The following is a checklist to follow when preparing a driver for real
time-compliance:
diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst
index 6d8352c..5d04296 100644
--- a/Documentation/driver-api/index.rst
+++ b/Documentation/driver-api/index.rst
@@ -17,7 +17,9 @@
basics
infrastructure
pm/index
+ clk
device-io
+ device_connection
dma-buf
device_link
message-based
diff --git a/Documentation/driver-api/infrastructure.rst b/Documentation/driver-api/infrastructure.rst
index 6d9ff31..bee1b9a 100644
--- a/Documentation/driver-api/infrastructure.rst
+++ b/Documentation/driver-api/infrastructure.rst
@@ -28,7 +28,7 @@
.. kernel-doc:: drivers/base/node.c
:internal:
-.. kernel-doc:: drivers/base/firmware_class.c
+.. kernel-doc:: drivers/base/firmware_loader/main.c
:export:
.. kernel-doc:: drivers/base/transport_class.c
diff --git a/Documentation/driver-api/uio-howto.rst b/Documentation/driver-api/uio-howto.rst
index 92056c2..fb2eb73 100644
--- a/Documentation/driver-api/uio-howto.rst
+++ b/Documentation/driver-api/uio-howto.rst
@@ -711,7 +711,8 @@
If a subchannel is created by a request to host, then the uio_hv_generic
device driver will create a sysfs binary file for the per-channel ring buffer.
-For example:
+For example::
+
/sys/bus/vmbus/devices/3811fe4d-0fa0-4b62-981a-74fc1084c757/channels/21/ring
Further information
diff --git a/Documentation/driver-api/usb/typec.rst b/Documentation/driver-api/usb/typec.rst
index feb3194..48ff580 100644
--- a/Documentation/driver-api/usb/typec.rst
+++ b/Documentation/driver-api/usb/typec.rst
@@ -210,7 +210,7 @@
role. USB Type-C Connector Class does not supply separate API for them. The
port drivers can use USB Role Class API with those.
-Illustration of the muxes behind a connector that supports an alternate mode:
+Illustration of the muxes behind a connector that supports an alternate mode::
------------------------
| Connector |
diff --git a/Documentation/features/lib/strncasecmp/arch-support.txt b/Documentation/features/core/cBPF-JIT/arch-support.txt
similarity index 70%
rename from Documentation/features/lib/strncasecmp/arch-support.txt
rename to Documentation/features/core/cBPF-JIT/arch-support.txt
index 4f3a6a0..90459cd 100644
--- a/Documentation/features/lib/strncasecmp/arch-support.txt
+++ b/Documentation/features/core/cBPF-JIT/arch-support.txt
@@ -1,7 +1,7 @@
#
-# Feature name: strncasecmp
-# Kconfig: __HAVE_ARCH_STRNCASECMP
-# description: arch provides an optimized strncasecmp() function
+# Feature name: cBPF-JIT
+# Kconfig: HAVE_CBPF_JIT
+# description: arch supports cBPF JIT optimizations
#
-----------------------
| arch |status|
@@ -16,14 +16,16 @@
| ia64: | TODO |
| m68k: | TODO |
| microblaze: | TODO |
- | mips: | TODO |
+ | mips: | ok |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
- | powerpc: | TODO |
+ | powerpc: | ok |
+ | riscv: | TODO |
| s390: | TODO |
| sh: | TODO |
- | sparc: | TODO |
+ | sparc: | ok |
| um: | TODO |
| unicore32: | TODO |
| x86: | TODO |
diff --git a/Documentation/features/core/BPF-JIT/arch-support.txt b/Documentation/features/core/eBPF-JIT/arch-support.txt
similarity index 79%
rename from Documentation/features/core/BPF-JIT/arch-support.txt
rename to Documentation/features/core/eBPF-JIT/arch-support.txt
index 0b96b4e..c90a038 100644
--- a/Documentation/features/core/BPF-JIT/arch-support.txt
+++ b/Documentation/features/core/eBPF-JIT/arch-support.txt
@@ -1,7 +1,7 @@
#
-# Feature name: BPF-JIT
-# Kconfig: HAVE_BPF_JIT
-# description: arch supports BPF JIT optimizations
+# Feature name: eBPF-JIT
+# Kconfig: HAVE_EBPF_JIT
+# description: arch supports eBPF JIT optimizations
#
-----------------------
| arch |status|
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | ok |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
+ | riscv: | TODO |
| s390: | ok |
| sh: | TODO |
| sparc: | ok |
diff --git a/Documentation/features/core/generic-idle-thread/arch-support.txt b/Documentation/features/core/generic-idle-thread/arch-support.txt
index 372a2b1..0ef6acd 100644
--- a/Documentation/features/core/generic-idle-thread/arch-support.txt
+++ b/Documentation/features/core/generic-idle-thread/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | ok |
+ | nds32: | TODO |
| nios2: | TODO |
- | openrisc: | TODO |
+ | openrisc: | ok |
| parisc: | ok |
| powerpc: | ok |
+ | riscv: | ok |
| s390: | ok |
| sh: | ok |
| sparc: | ok |
diff --git a/Documentation/features/core/jump-labels/arch-support.txt b/Documentation/features/core/jump-labels/arch-support.txt
index ad97217..27cbd63a 100644
--- a/Documentation/features/core/jump-labels/arch-support.txt
+++ b/Documentation/features/core/jump-labels/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | ok |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
+ | riscv: | TODO |
| s390: | ok |
| sh: | TODO |
| sparc: | ok |
diff --git a/Documentation/features/core/tracehook/arch-support.txt b/Documentation/features/core/tracehook/arch-support.txt
index 36ee7be..f44c274 100644
--- a/Documentation/features/core/tracehook/arch-support.txt
+++ b/Documentation/features/core/tracehook/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | ok |
+ | nds32: | ok |
| nios2: | ok |
| openrisc: | ok |
| parisc: | ok |
| powerpc: | ok |
+ | riscv: | ok |
| s390: | ok |
| sh: | ok |
| sparc: | ok |
diff --git a/Documentation/features/debug/KASAN/arch-support.txt b/Documentation/features/debug/KASAN/arch-support.txt
index f5c99fa..282ecc8 100644
--- a/Documentation/features/debug/KASAN/arch-support.txt
+++ b/Documentation/features/debug/KASAN/arch-support.txt
@@ -17,15 +17,17 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | TODO |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | TODO |
+ | riscv: | TODO |
| s390: | TODO |
| sh: | TODO |
| sparc: | TODO |
| um: | TODO |
| unicore32: | TODO |
- | x86: | ok | 64-bit only
+ | x86: | ok |
| xtensa: | ok |
-----------------------
diff --git a/Documentation/features/debug/gcov-profile-all/arch-support.txt b/Documentation/features/debug/gcov-profile-all/arch-support.txt
index 5170a993..01b2b30 100644
--- a/Documentation/features/debug/gcov-profile-all/arch-support.txt
+++ b/Documentation/features/debug/gcov-profile-all/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | ok |
| mips: | TODO |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
+ | riscv: | TODO |
| s390: | ok |
| sh: | ok |
| sparc: | TODO |
diff --git a/Documentation/features/debug/kgdb/arch-support.txt b/Documentation/features/debug/kgdb/arch-support.txt
index 13b6e99..3b4dff2 100644
--- a/Documentation/features/debug/kgdb/arch-support.txt
+++ b/Documentation/features/debug/kgdb/arch-support.txt
@@ -11,16 +11,18 @@
| arm: | ok |
| arm64: | ok |
| c6x: | TODO |
- | h8300: | TODO |
+ | h8300: | ok |
| hexagon: | ok |
| ia64: | TODO |
| m68k: | TODO |
| microblaze: | ok |
| mips: | ok |
+ | nds32: | TODO |
| nios2: | ok |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
+ | riscv: | TODO |
| s390: | TODO |
| sh: | ok |
| sparc: | ok |
diff --git a/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt b/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt
index 419bb38..7e963d0 100644
--- a/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt
+++ b/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | TODO |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
+ | riscv: | TODO |
| s390: | TODO |
| sh: | TODO |
| sparc: | TODO |
diff --git a/Documentation/features/debug/kprobes/arch-support.txt b/Documentation/features/debug/kprobes/arch-support.txt
index 52b3ace..4ada027 100644
--- a/Documentation/features/debug/kprobes/arch-support.txt
+++ b/Documentation/features/debug/kprobes/arch-support.txt
@@ -9,7 +9,7 @@
| alpha: | TODO |
| arc: | ok |
| arm: | ok |
- | arm64: | TODO |
+ | arm64: | ok |
| c6x: | TODO |
| h8300: | TODO |
| hexagon: | TODO |
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | ok |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
+ | riscv: | ok |
| s390: | ok |
| sh: | ok |
| sparc: | ok |
diff --git a/Documentation/features/debug/kretprobes/arch-support.txt b/Documentation/features/debug/kretprobes/arch-support.txt
index 180d244..044e13f 100644
--- a/Documentation/features/debug/kretprobes/arch-support.txt
+++ b/Documentation/features/debug/kretprobes/arch-support.txt
@@ -9,7 +9,7 @@
| alpha: | TODO |
| arc: | ok |
| arm: | ok |
- | arm64: | TODO |
+ | arm64: | ok |
| c6x: | TODO |
| h8300: | TODO |
| hexagon: | TODO |
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | ok |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
+ | riscv: | TODO |
| s390: | ok |
| sh: | ok |
| sparc: | ok |
diff --git a/Documentation/features/debug/optprobes/arch-support.txt b/Documentation/features/debug/optprobes/arch-support.txt
index 0a1241f..dce7669 100644
--- a/Documentation/features/debug/optprobes/arch-support.txt
+++ b/Documentation/features/debug/optprobes/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | TODO |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
- | powerpc: | TODO |
+ | powerpc: | ok |
+ | riscv: | TODO |
| s390: | TODO |
| sh: | TODO |
| sparc: | TODO |
diff --git a/Documentation/features/debug/stackprotector/arch-support.txt b/Documentation/features/debug/stackprotector/arch-support.txt
index 5700195..74b89a9 100644
--- a/Documentation/features/debug/stackprotector/arch-support.txt
+++ b/Documentation/features/debug/stackprotector/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | ok |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | TODO |
+ | riscv: | TODO |
| s390: | TODO |
| sh: | ok |
| sparc: | TODO |
diff --git a/Documentation/features/debug/uprobes/arch-support.txt b/Documentation/features/debug/uprobes/arch-support.txt
index 0b8d922..1a3f9d3 100644
--- a/Documentation/features/debug/uprobes/arch-support.txt
+++ b/Documentation/features/debug/uprobes/arch-support.txt
@@ -9,7 +9,7 @@
| alpha: | TODO |
| arc: | TODO |
| arm: | ok |
- | arm64: | TODO |
+ | arm64: | ok |
| c6x: | TODO |
| h8300: | TODO |
| hexagon: | TODO |
@@ -17,13 +17,15 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | ok |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
+ | riscv: | TODO |
| s390: | ok |
| sh: | TODO |
- | sparc: | TODO |
+ | sparc: | ok |
| um: | TODO |
| unicore32: | TODO |
| x86: | ok |
diff --git a/Documentation/features/debug/user-ret-profiler/arch-support.txt b/Documentation/features/debug/user-ret-profiler/arch-support.txt
index 13852ae..1d78d10 100644
--- a/Documentation/features/debug/user-ret-profiler/arch-support.txt
+++ b/Documentation/features/debug/user-ret-profiler/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | TODO |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | TODO |
+ | riscv: | TODO |
| s390: | TODO |
| sh: | TODO |
| sparc: | TODO |
diff --git a/Documentation/features/io/dma-api-debug/arch-support.txt b/Documentation/features/io/dma-api-debug/arch-support.txt
deleted file mode 100644
index e438ed67..0000000
--- a/Documentation/features/io/dma-api-debug/arch-support.txt
+++ /dev/null
@@ -1,31 +0,0 @@
-#
-# Feature name: dma-api-debug
-# Kconfig: HAVE_DMA_API_DEBUG
-# description: arch supports DMA debug facilities
-#
- -----------------------
- | arch |status|
- -----------------------
- | alpha: | TODO |
- | arc: | TODO |
- | arm: | ok |
- | arm64: | ok |
- | c6x: | ok |
- | h8300: | TODO |
- | hexagon: | TODO |
- | ia64: | ok |
- | m68k: | TODO |
- | microblaze: | ok |
- | mips: | ok |
- | nios2: | TODO |
- | openrisc: | TODO |
- | parisc: | TODO |
- | powerpc: | ok |
- | s390: | ok |
- | sh: | ok |
- | sparc: | ok |
- | um: | TODO |
- | unicore32: | TODO |
- | x86: | ok |
- | xtensa: | ok |
- -----------------------
diff --git a/Documentation/features/io/dma-contiguous/arch-support.txt b/Documentation/features/io/dma-contiguous/arch-support.txt
index 47f64a4..30c072d 100644
--- a/Documentation/features/io/dma-contiguous/arch-support.txt
+++ b/Documentation/features/io/dma-contiguous/arch-support.txt
@@ -17,11 +17,13 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | ok |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | TODO |
- | s390: | TODO |
+ | riscv: | ok |
+ | s390: | ok |
| sh: | TODO |
| sparc: | TODO |
| um: | TODO |
diff --git a/Documentation/features/io/sg-chain/arch-support.txt b/Documentation/features/io/sg-chain/arch-support.txt
index 07f357f..6554f03 100644
--- a/Documentation/features/io/sg-chain/arch-support.txt
+++ b/Documentation/features/io/sg-chain/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | TODO |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
+ | riscv: | TODO |
| s390: | ok |
| sh: | TODO |
| sparc: | ok |
diff --git a/Documentation/features/locking/cmpxchg-local/arch-support.txt b/Documentation/features/locking/cmpxchg-local/arch-support.txt
index 482a0b0..51704a2 100644
--- a/Documentation/features/locking/cmpxchg-local/arch-support.txt
+++ b/Documentation/features/locking/cmpxchg-local/arch-support.txt
@@ -9,7 +9,7 @@
| alpha: | TODO |
| arc: | TODO |
| arm: | TODO |
- | arm64: | TODO |
+ | arm64: | ok |
| c6x: | TODO |
| h8300: | TODO |
| hexagon: | TODO |
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | TODO |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | TODO |
+ | riscv: | TODO |
| s390: | ok |
| sh: | TODO |
| sparc: | TODO |
diff --git a/Documentation/features/locking/lockdep/arch-support.txt b/Documentation/features/locking/lockdep/arch-support.txt
index bb35c5b..bd39c5e 100644
--- a/Documentation/features/locking/lockdep/arch-support.txt
+++ b/Documentation/features/locking/lockdep/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | ok |
| mips: | ok |
+ | nds32: | ok |
| nios2: | TODO |
- | openrisc: | TODO |
+ | openrisc: | ok |
| parisc: | TODO |
| powerpc: | ok |
+ | riscv: | TODO |
| s390: | ok |
| sh: | ok |
| sparc: | ok |
diff --git a/Documentation/features/locking/queued-rwlocks/arch-support.txt b/Documentation/features/locking/queued-rwlocks/arch-support.txt
index 627e9a6..da7aff3 100644
--- a/Documentation/features/locking/queued-rwlocks/arch-support.txt
+++ b/Documentation/features/locking/queued-rwlocks/arch-support.txt
@@ -9,21 +9,23 @@
| alpha: | TODO |
| arc: | TODO |
| arm: | TODO |
- | arm64: | TODO |
+ | arm64: | ok |
| c6x: | TODO |
| h8300: | TODO |
| hexagon: | TODO |
| ia64: | TODO |
| m68k: | TODO |
| microblaze: | TODO |
- | mips: | TODO |
+ | mips: | ok |
+ | nds32: | TODO |
| nios2: | TODO |
- | openrisc: | TODO |
+ | openrisc: | ok |
| parisc: | TODO |
| powerpc: | TODO |
+ | riscv: | TODO |
| s390: | TODO |
| sh: | TODO |
- | sparc: | TODO |
+ | sparc: | ok |
| um: | TODO |
| unicore32: | TODO |
| x86: | ok |
diff --git a/Documentation/features/locking/queued-spinlocks/arch-support.txt b/Documentation/features/locking/queued-spinlocks/arch-support.txt
index 9edda21..478e910 100644
--- a/Documentation/features/locking/queued-spinlocks/arch-support.txt
+++ b/Documentation/features/locking/queued-spinlocks/arch-support.txt
@@ -16,14 +16,16 @@
| ia64: | TODO |
| m68k: | TODO |
| microblaze: | TODO |
- | mips: | TODO |
+ | mips: | ok |
+ | nds32: | TODO |
| nios2: | TODO |
- | openrisc: | TODO |
+ | openrisc: | ok |
| parisc: | TODO |
| powerpc: | TODO |
+ | riscv: | TODO |
| s390: | TODO |
| sh: | TODO |
- | sparc: | TODO |
+ | sparc: | ok |
| um: | TODO |
| unicore32: | TODO |
| x86: | ok |
diff --git a/Documentation/features/locking/rwsem-optimized/arch-support.txt b/Documentation/features/locking/rwsem-optimized/arch-support.txt
index 8d9afb1..e54b1f1 100644
--- a/Documentation/features/locking/rwsem-optimized/arch-support.txt
+++ b/Documentation/features/locking/rwsem-optimized/arch-support.txt
@@ -1,6 +1,6 @@
#
# Feature name: rwsem-optimized
-# Kconfig: Optimized asm/rwsem.h
+# Kconfig: !RWSEM_GENERIC_SPINLOCK
# description: arch provides optimized rwsem APIs
#
-----------------------
@@ -8,8 +8,8 @@
-----------------------
| alpha: | ok |
| arc: | TODO |
- | arm: | TODO |
- | arm64: | TODO |
+ | arm: | ok |
+ | arm64: | ok |
| c6x: | TODO |
| h8300: | TODO |
| hexagon: | TODO |
@@ -17,14 +17,16 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | TODO |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | TODO |
+ | riscv: | TODO |
| s390: | ok |
| sh: | ok |
| sparc: | ok |
- | um: | TODO |
+ | um: | ok |
| unicore32: | TODO |
| x86: | ok |
| xtensa: | ok |
diff --git a/Documentation/features/perf/kprobes-event/arch-support.txt b/Documentation/features/perf/kprobes-event/arch-support.txt
index d01239e..7331402 100644
--- a/Documentation/features/perf/kprobes-event/arch-support.txt
+++ b/Documentation/features/perf/kprobes-event/arch-support.txt
@@ -9,7 +9,7 @@
| alpha: | TODO |
| arc: | TODO |
| arm: | ok |
- | arm64: | TODO |
+ | arm64: | ok |
| c6x: | TODO |
| h8300: | TODO |
| hexagon: | ok |
@@ -17,13 +17,15 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | ok |
+ | nds32: | ok |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
+ | riscv: | TODO |
| s390: | ok |
| sh: | ok |
- | sparc: | TODO |
+ | sparc: | ok |
| um: | TODO |
| unicore32: | TODO |
| x86: | ok |
diff --git a/Documentation/features/perf/perf-regs/arch-support.txt b/Documentation/features/perf/perf-regs/arch-support.txt
index 458faba..53feeee 100644
--- a/Documentation/features/perf/perf-regs/arch-support.txt
+++ b/Documentation/features/perf/perf-regs/arch-support.txt
@@ -17,11 +17,13 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | TODO |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
- | s390: | TODO |
+ | riscv: | TODO |
+ | s390: | ok |
| sh: | TODO |
| sparc: | TODO |
| um: | TODO |
diff --git a/Documentation/features/perf/perf-stackdump/arch-support.txt b/Documentation/features/perf/perf-stackdump/arch-support.txt
index 545d01c..1616434 100644
--- a/Documentation/features/perf/perf-stackdump/arch-support.txt
+++ b/Documentation/features/perf/perf-stackdump/arch-support.txt
@@ -17,11 +17,13 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | TODO |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
- | s390: | TODO |
+ | riscv: | TODO |
+ | s390: | ok |
| sh: | TODO |
| sparc: | TODO |
| um: | TODO |
diff --git a/Documentation/features/sched/membarrier-sync-core/arch-support.txt b/Documentation/features/sched/membarrier-sync-core/arch-support.txt
index 85a6c9d..dbdf629 100644
--- a/Documentation/features/sched/membarrier-sync-core/arch-support.txt
+++ b/Documentation/features/sched/membarrier-sync-core/arch-support.txt
@@ -40,10 +40,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | TODO |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | TODO |
+ | riscv: | TODO |
| s390: | TODO |
| sh: | TODO |
| sparc: | TODO |
diff --git a/Documentation/features/sched/numa-balancing/arch-support.txt b/Documentation/features/sched/numa-balancing/arch-support.txt
index 3475088..c68bb2c 100644
--- a/Documentation/features/sched/numa-balancing/arch-support.txt
+++ b/Documentation/features/sched/numa-balancing/arch-support.txt
@@ -9,7 +9,7 @@
| alpha: | TODO |
| arc: | .. |
| arm: | .. |
- | arm64: | .. |
+ | arm64: | ok |
| c6x: | .. |
| h8300: | .. |
| hexagon: | .. |
@@ -17,11 +17,13 @@
| m68k: | .. |
| microblaze: | .. |
| mips: | TODO |
+ | nds32: | TODO |
| nios2: | .. |
| openrisc: | .. |
| parisc: | .. |
| powerpc: | ok |
- | s390: | .. |
+ | riscv: | TODO |
+ | s390: | ok |
| sh: | .. |
| sparc: | TODO |
| um: | .. |
diff --git a/Documentation/features/scripts/features-refresh.sh b/Documentation/features/scripts/features-refresh.sh
new file mode 100755
index 0000000..9e72d38
--- /dev/null
+++ b/Documentation/features/scripts/features-refresh.sh
@@ -0,0 +1,98 @@
+#
+# Small script that refreshes the kernel feature support status in place.
+#
+
+for F_FILE in Documentation/features/*/*/arch-support.txt; do
+ F=$(grep "^# Kconfig:" "$F_FILE" | cut -c26-)
+
+ #
+ # Each feature F is identified by a pair (O, K), where 'O' can
+ # be either the empty string (for 'nop') or "not" (the logical
+ # negation operator '!'); other operators are not supported.
+ #
+ O=""
+ K=$F
+ if [[ "$F" == !* ]]; then
+ O="not"
+ K=$(echo $F | sed -e 's/^!//g')
+ fi
+
+ #
+ # F := (O, K) is 'valid' iff there is a Kconfig file (for some
+ # arch) which contains K.
+ #
+ # Notice that this definition entails an 'asymmetry' between
+ # the case 'O = ""' and the case 'O = "not"'. E.g., F may be
+ # _invalid_ if:
+ #
+ # [case 'O = ""']
+ # 1) no arch provides support for F,
+ # 2) K does not exist (e.g., it was renamed/mis-typed);
+ #
+ # [case 'O = "not"']
+ # 3) all archs provide support for F,
+ # 4) as in (2).
+ #
+ # The rationale for adopting this definition (and, thus, for
+ # keeping the asymmetry) is:
+ #
+ # We want to be able to 'detect' (2) (or (4)).
+ #
+ # (1) and (3) may further warn the developers about the fact
+ # that K can be removed.
+ #
+ F_VALID="false"
+ for ARCH_DIR in arch/*/; do
+ K_FILES=$(find $ARCH_DIR -name "Kconfig*")
+ K_GREP=$(grep "$K" $K_FILES)
+ if [ ! -z "$K_GREP" ]; then
+ F_VALID="true"
+ break
+ fi
+ done
+ if [ "$F_VALID" = "false" ]; then
+ printf "WARNING: '%s' is not a valid Kconfig\n" "$F"
+ fi
+
+ T_FILE="$F_FILE.tmp"
+ grep "^#" $F_FILE > $T_FILE
+ echo " -----------------------" >> $T_FILE
+ echo " | arch |status|" >> $T_FILE
+ echo " -----------------------" >> $T_FILE
+ for ARCH_DIR in arch/*/; do
+ ARCH=$(echo $ARCH_DIR | sed -e 's/arch//g' | sed -e 's/\///g')
+ K_FILES=$(find $ARCH_DIR -name "Kconfig*")
+ K_GREP=$(grep "$K" $K_FILES)
+ #
+ # Arch support status values for (O, K) are updated according
+ # to the following rules.
+ #
+ # - ("", K) is 'supported by a given arch', if there is a
+ # Kconfig file for that arch which contains K;
+ #
+ # - ("not", K) is 'supported by a given arch', if there is
+ # no Kconfig file for that arch which contains K;
+ #
+ # - otherwise: preserve the previous status value (if any),
+ # default to 'not yet supported'.
+ #
+ # Notice that, according these rules, invalid features may be
+ # updated/modified.
+ #
+ if [ "$O" = "" ] && [ ! -z "$K_GREP" ]; then
+ printf " |%12s: | ok |\n" "$ARCH" >> $T_FILE
+ elif [ "$O" = "not" ] && [ -z "$K_GREP" ]; then
+ printf " |%12s: | ok |\n" "$ARCH" >> $T_FILE
+ else
+ S=$(grep -v "^#" "$F_FILE" | grep " $ARCH:")
+ if [ ! -z "$S" ]; then
+ echo "$S" >> $T_FILE
+ else
+ printf " |%12s: | TODO |\n" "$ARCH" \
+ >> $T_FILE
+ fi
+ fi
+ done
+ echo " -----------------------" >> $T_FILE
+ mv $T_FILE $F_FILE
+done
diff --git a/Documentation/features/seccomp/seccomp-filter/arch-support.txt b/Documentation/features/seccomp/seccomp-filter/arch-support.txt
index e4fad58..d4271b4 100644
--- a/Documentation/features/seccomp/seccomp-filter/arch-support.txt
+++ b/Documentation/features/seccomp/seccomp-filter/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | ok |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
- | parisc: | TODO |
- | powerpc: | TODO |
+ | parisc: | ok |
+ | powerpc: | ok |
+ | riscv: | TODO |
| s390: | ok |
| sh: | TODO |
| sparc: | TODO |
diff --git a/Documentation/features/time/arch-tick-broadcast/arch-support.txt b/Documentation/features/time/arch-tick-broadcast/arch-support.txt
index 8052904..83d9e68 100644
--- a/Documentation/features/time/arch-tick-broadcast/arch-support.txt
+++ b/Documentation/features/time/arch-tick-broadcast/arch-support.txt
@@ -17,12 +17,14 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | ok |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
+ | riscv: | TODO |
| s390: | TODO |
- | sh: | TODO |
+ | sh: | ok |
| sparc: | TODO |
| um: | TODO |
| unicore32: | TODO |
diff --git a/Documentation/features/time/clockevents/arch-support.txt b/Documentation/features/time/clockevents/arch-support.txt
index 7c76b94..3d4908f 100644
--- a/Documentation/features/time/clockevents/arch-support.txt
+++ b/Documentation/features/time/clockevents/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | ok |
| microblaze: | ok |
| mips: | ok |
+ | nds32: | ok |
| nios2: | ok |
| openrisc: | ok |
- | parisc: | TODO |
+ | parisc: | ok |
| powerpc: | ok |
+ | riscv: | ok |
| s390: | ok |
| sh: | ok |
| sparc: | ok |
diff --git a/Documentation/features/time/context-tracking/arch-support.txt b/Documentation/features/time/context-tracking/arch-support.txt
index 9433b3e..c29974a 100644
--- a/Documentation/features/time/context-tracking/arch-support.txt
+++ b/Documentation/features/time/context-tracking/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | ok |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
+ | riscv: | TODO |
| s390: | TODO |
| sh: | TODO |
| sparc: | ok |
diff --git a/Documentation/features/time/irq-time-acct/arch-support.txt b/Documentation/features/time/irq-time-acct/arch-support.txt
index 212dde0..8d73c46 100644
--- a/Documentation/features/time/irq-time-acct/arch-support.txt
+++ b/Documentation/features/time/irq-time-acct/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | ok |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | .. |
- | powerpc: | .. |
+ | powerpc: | ok |
+ | riscv: | TODO |
| s390: | .. |
| sh: | TODO |
| sparc: | .. |
diff --git a/Documentation/features/time/modern-timekeeping/arch-support.txt b/Documentation/features/time/modern-timekeeping/arch-support.txt
index 4074028..e7c6ea6 100644
--- a/Documentation/features/time/modern-timekeeping/arch-support.txt
+++ b/Documentation/features/time/modern-timekeeping/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | ok |
| mips: | ok |
+ | nds32: | ok |
| nios2: | ok |
| openrisc: | ok |
| parisc: | ok |
| powerpc: | ok |
+ | riscv: | ok |
| s390: | ok |
| sh: | ok |
| sparc: | ok |
diff --git a/Documentation/features/time/virt-cpuacct/arch-support.txt b/Documentation/features/time/virt-cpuacct/arch-support.txt
index a394d88..4646457 100644
--- a/Documentation/features/time/virt-cpuacct/arch-support.txt
+++ b/Documentation/features/time/virt-cpuacct/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | ok |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | ok |
| powerpc: | ok |
+ | riscv: | TODO |
| s390: | ok |
| sh: | TODO |
| sparc: | ok |
diff --git a/Documentation/features/vm/ELF-ASLR/arch-support.txt b/Documentation/features/vm/ELF-ASLR/arch-support.txt
index 082f93d..1f71d09 100644
--- a/Documentation/features/vm/ELF-ASLR/arch-support.txt
+++ b/Documentation/features/vm/ELF-ASLR/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | ok |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
- | parisc: | TODO |
+ | parisc: | ok |
| powerpc: | ok |
+ | riscv: | TODO |
| s390: | ok |
| sh: | TODO |
| sparc: | TODO |
diff --git a/Documentation/features/vm/PG_uncached/arch-support.txt b/Documentation/features/vm/PG_uncached/arch-support.txt
index 605e0ab..fbd5aa4 100644
--- a/Documentation/features/vm/PG_uncached/arch-support.txt
+++ b/Documentation/features/vm/PG_uncached/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | TODO |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | TODO |
+ | riscv: | TODO |
| s390: | TODO |
| sh: | TODO |
| sparc: | TODO |
diff --git a/Documentation/features/vm/THP/arch-support.txt b/Documentation/features/vm/THP/arch-support.txt
index 7a8eb0b..5d7ecc3 100644
--- a/Documentation/features/vm/THP/arch-support.txt
+++ b/Documentation/features/vm/THP/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | .. |
| microblaze: | .. |
| mips: | ok |
+ | nds32: | TODO |
| nios2: | .. |
| openrisc: | .. |
| parisc: | TODO |
| powerpc: | ok |
+ | riscv: | TODO |
| s390: | ok |
| sh: | .. |
| sparc: | ok |
diff --git a/Documentation/features/vm/TLB/arch-support.txt b/Documentation/features/vm/TLB/arch-support.txt
index 35fb99b..f7af967 100644
--- a/Documentation/features/vm/TLB/arch-support.txt
+++ b/Documentation/features/vm/TLB/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | .. |
| microblaze: | .. |
| mips: | TODO |
+ | nds32: | TODO |
| nios2: | .. |
| openrisc: | .. |
| parisc: | TODO |
| powerpc: | TODO |
+ | riscv: | TODO |
| s390: | TODO |
| sh: | TODO |
| sparc: | TODO |
diff --git a/Documentation/features/vm/huge-vmap/arch-support.txt b/Documentation/features/vm/huge-vmap/arch-support.txt
index ed8b943..d0713cc 100644
--- a/Documentation/features/vm/huge-vmap/arch-support.txt
+++ b/Documentation/features/vm/huge-vmap/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | TODO |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | TODO |
+ | riscv: | TODO |
| s390: | TODO |
| sh: | TODO |
| sparc: | TODO |
diff --git a/Documentation/features/vm/ioremap_prot/arch-support.txt b/Documentation/features/vm/ioremap_prot/arch-support.txt
index 589947b..8527601 100644
--- a/Documentation/features/vm/ioremap_prot/arch-support.txt
+++ b/Documentation/features/vm/ioremap_prot/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | TODO |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
+ | riscv: | TODO |
| s390: | TODO |
| sh: | ok |
| sparc: | TODO |
diff --git a/Documentation/features/vm/numa-memblock/arch-support.txt b/Documentation/features/vm/numa-memblock/arch-support.txt
index 8b8bea0..1a98805 100644
--- a/Documentation/features/vm/numa-memblock/arch-support.txt
+++ b/Documentation/features/vm/numa-memblock/arch-support.txt
@@ -9,7 +9,7 @@
| alpha: | TODO |
| arc: | .. |
| arm: | .. |
- | arm64: | .. |
+ | arm64: | ok |
| c6x: | .. |
| h8300: | .. |
| hexagon: | .. |
@@ -17,10 +17,12 @@
| m68k: | .. |
| microblaze: | ok |
| mips: | ok |
+ | nds32: | TODO |
| nios2: | .. |
| openrisc: | .. |
| parisc: | .. |
| powerpc: | ok |
+ | riscv: | ok |
| s390: | ok |
| sh: | ok |
| sparc: | ok |
diff --git a/Documentation/features/vm/pte_special/arch-support.txt b/Documentation/features/vm/pte_special/arch-support.txt
index 055004f..6a608a6 100644
--- a/Documentation/features/vm/pte_special/arch-support.txt
+++ b/Documentation/features/vm/pte_special/arch-support.txt
@@ -17,10 +17,12 @@
| m68k: | TODO |
| microblaze: | TODO |
| mips: | TODO |
+ | nds32: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
+ | riscv: | TODO |
| s390: | ok |
| sh: | ok |
| sparc: | ok |
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 75d2d57..2c39133 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -69,31 +69,31 @@
locking rules:
all may block
- i_mutex(inode)
-lookup: yes
-create: yes
-link: yes (both)
-mknod: yes
-symlink: yes
-mkdir: yes
-unlink: yes (both)
-rmdir: yes (both) (see below)
-rename: yes (all) (see below)
+ i_rwsem(inode)
+lookup: shared
+create: exclusive
+link: exclusive (both)
+mknod: exclusive
+symlink: exclusive
+mkdir: exclusive
+unlink: exclusive (both)
+rmdir: exclusive (both)(see below)
+rename: exclusive (all) (see below)
readlink: no
get_link: no
-setattr: yes
+setattr: exclusive
permission: no (may not block if called in rcu-walk mode)
get_acl: no
getattr: no
listxattr: no
fiemap: no
update_time: no
-atomic_open: yes
+atomic_open: exclusive
tmpfile: no
- Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
-victim.
+ Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_rwsem
+ exclusive on victim.
cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.
See Documentation/filesystems/directory-locking for more detailed discussion
@@ -111,10 +111,10 @@
locking rules:
all may block
- i_mutex(inode)
+ i_rwsem(inode)
list: no
get: no
-set: yes
+set: exclusive
--------------------------- super_operations ---------------------------
prototypes:
@@ -217,14 +217,14 @@
locking rules:
All except set_page_dirty and freepage may block
- PageLocked(page) i_mutex
+ PageLocked(page) i_rwsem
writepage: yes, unlocks (see below)
readpage: yes, unlocks
writepages:
set_page_dirty no
readpages:
-write_begin: locks the page yes
-write_end: yes, unlocks yes
+write_begin: locks the page exclusive
+write_end: yes, unlocks exclusive
bmap:
invalidatepage: yes
releasepage: yes
@@ -439,7 +439,10 @@
ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
int (*iterate) (struct file *, struct dir_context *);
- unsigned int (*poll) (struct file *, struct poll_table_struct *);
+ int (*iterate_shared) (struct file *, struct dir_context *);
+ __poll_t (*poll) (struct file *, struct poll_table_struct *);
+ struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
+ __poll_t (*poll_mask) (struct file *, __poll_t);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
@@ -470,7 +473,7 @@
};
locking rules:
- All may block.
+ All except for ->poll_mask may block.
->llseek() locking has moved from llseek to the individual llseek
implementations. If your fs is not using generic_file_llseek, you
@@ -480,6 +483,10 @@
Note: this does not protect the file->f_pos against concurrent modifications
since this is something the userspace has to take care about.
+->iterate() is called with i_rwsem exclusive.
+
+->iterate_shared() is called with i_rwsem at least shared.
+
->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags.
Most instances call fasync_helper(), which does that maintenance, so it's
not normally something one needs to worry about. Return values > 0 will be
@@ -498,6 +505,9 @@
the lease within the individual filesystem to record the result of the
operation
+->poll_mask can be called with or without the waitqueue lock for the waitqueue
+returned from ->get_poll_head.
+
--------------------------- dquot_operations -------------------------------
prototypes:
int (*write_dquot) (struct dquot *);
diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst
index cfbc18f..48b424d 100644
--- a/Documentation/filesystems/fscrypt.rst
+++ b/Documentation/filesystems/fscrypt.rst
@@ -191,11 +191,21 @@
- AES-256-XTS for contents and AES-256-CTS-CBC for filenames
- AES-128-CBC for contents and AES-128-CTS-CBC for filenames
+- Speck128/256-XTS for contents and Speck128/256-CTS-CBC for filenames
It is strongly recommended to use AES-256-XTS for contents encryption.
AES-128-CBC was added only for low-powered embedded devices with
crypto accelerators such as CAAM or CESA that do not support XTS.
+Similarly, Speck128/256 support was only added for older or low-end
+CPUs which cannot do AES fast enough -- especially ARM CPUs which have
+NEON instructions but not the Cryptography Extensions -- and for which
+it would not otherwise be feasible to use encryption at all. It is
+not recommended to use Speck on CPUs that have AES instructions.
+Speck support is only available if it has been enabled in the crypto
+API via CONFIG_CRYPTO_SPECK. Also, on ARM platforms, to get
+acceptable performance CONFIG_CRYPTO_SPECK_NEON must be enabled.
+
New encryption modes can be added relatively easily, without changes
to individual filesystems. However, authenticated encryption (AE)
modes are not currently supported because of the difficulty of dealing
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 2a84bb3..520f6a8 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -515,7 +515,8 @@
The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
bits on both physical and virtual pages associated with a process, and the
-soft-dirty bit on pte (see Documentation/vm/soft-dirty.txt for details).
+soft-dirty bit on pte (see Documentation/admin-guide/mm/soft-dirty.rst
+for details).
To clear the bits for all the pages associated with the process
> echo 1 > /proc/PID/clear_refs
@@ -536,7 +537,8 @@
The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
using /proc/kpageflags and number of times a page is mapped using
-/proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.txt.
+/proc/kpagecount. For detailed explanation, see
+Documentation/admin-guide/mm/pagemap.rst.
The /proc/pid/numa_maps is an extension based on maps, showing the memory
locality and binding policy, as well as the memory usage (in pages) of
@@ -564,7 +566,7 @@
Where:
"address" is the starting address for the mapping;
-"policy" reports the NUMA memory policy set for the mapping (see vm/numa_memory_policy.txt);
+"policy" reports the NUMA memory policy set for the mapping (see Documentation/admin-guide/mm/numa_memory_policy.rst);
"mapping details" summarizes mapping data such as mapping type, page usage counters,
node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page
size, in KB, that is backing the mapping up.
diff --git a/Documentation/filesystems/tmpfs.txt b/Documentation/filesystems/tmpfs.txt
index a85355c..d06e9a5 100644
--- a/Documentation/filesystems/tmpfs.txt
+++ b/Documentation/filesystems/tmpfs.txt
@@ -105,8 +105,9 @@
NUMA memory allocation policies have optional flags that can be used in
conjunction with their modes. These optional flags can be specified
when tmpfs is mounted by appending them to the mode before the NodeList.
-See Documentation/vm/numa_memory_policy.txt for a list of all available
-memory allocation policy mode flags and their effect on memory policy.
+See Documentation/admin-guide/mm/numa_memory_policy.rst for a list of
+all available memory allocation policy mode flags and their effect on
+memory policy.
=static is equivalent to MPOL_F_STATIC_NODES
=relative is equivalent to MPOL_F_RELATIVE_NODES
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 5fd325d..829a7b7 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -856,7 +856,9 @@
ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
int (*iterate) (struct file *, struct dir_context *);
- unsigned int (*poll) (struct file *, struct poll_table_struct *);
+ __poll_t (*poll) (struct file *, struct poll_table_struct *);
+ struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
+ __poll_t (*poll_mask) (struct file *, __poll_t);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
@@ -901,6 +903,17 @@
activity on this file and (optionally) go to sleep until there
is activity. Called by the select(2) and poll(2) system calls
+ get_poll_head: Returns the struct wait_queue_head that callers can
+ wait on. Callers need to check the returned events using ->poll_mask
+ once woken. Can return NULL to indicate polling is not supported,
+ or any error code using the ERR_PTR convention to indicate that a
+ grave error occured and ->poll_mask shall not be called.
+
+ poll_mask: return the mask of EPOLL* values describing the file descriptor
+ state. Called either before going to sleep on the waitqueue returned by
+ get_poll_head, or after it has been woken. If ->get_poll_head and
+ ->poll_mask are implemented ->poll does not need to be implement.
+
unlocked_ioctl: called by the ioctl(2) system call.
compat_ioctl: called by the ioctl(2) system call when 32 bit system calls
diff --git a/Documentation/hwmon/hwmon-kernel-api.txt b/Documentation/hwmon/hwmon-kernel-api.txt
index 53a8066..eb7a78a 100644
--- a/Documentation/hwmon/hwmon-kernel-api.txt
+++ b/Documentation/hwmon/hwmon-kernel-api.txt
@@ -71,7 +71,8 @@
to register a hardware monitoring device. It creates the standard sysfs
attributes in the hardware monitoring core, letting the driver focus on reading
from and writing to the chip instead of having to bother with sysfs attributes.
-Its parameters are described in more detail below.
+The parent device parameter cannot be NULL with non-NULL chip info. Its
+parameters are described in more detail below.
devm_hwmon_device_register_with_info is similar to
hwmon_device_register_with_info. However, it is device managed, meaning the
diff --git a/Documentation/hwmon/ltc2990 b/Documentation/hwmon/ltc2990
index c25211e..3ed68f6 100644
--- a/Documentation/hwmon/ltc2990
+++ b/Documentation/hwmon/ltc2990
@@ -8,6 +8,7 @@
Datasheet: http://www.linear.com/product/ltc2990
Author: Mike Looijmans <mike.looijmans@topic.nl>
+ Tom Levens <tom.levens@cern.ch>
Description
@@ -16,10 +17,8 @@
LTC2990 is a Quad I2C Voltage, Current and Temperature Monitor.
The chip's inputs can measure 4 voltages, or two inputs together (1+2 and 3+4)
can be combined to measure a differential voltage, which is typically used to
-measure current through a series resistor, or a temperature.
-
-This driver currently uses the 2x differential mode only. In order to support
-other modes, the driver will need to be expanded.
+measure current through a series resistor, or a temperature with an external
+diode.
Usage Notes
@@ -32,12 +31,19 @@
Sysfs attributes
----------------
+in0_input Voltage at Vcc pin in millivolt (range 2.5V to 5V)
+temp1_input Internal chip temperature in millidegrees Celcius
+
+A subset of the following attributes are visible, depending on the measurement
+mode of the chip.
+
+in[1-4]_input Voltage at V[1-4] pin in millivolt
+temp2_input External temperature sensor TR1 in millidegrees Celcius
+temp3_input External temperature sensor TR2 in millidegrees Celcius
+curr1_input Current in mA across V1-V2 assuming a 1mOhm sense resistor
+curr2_input Current in mA across V3-V4 assuming a 1mOhm sense resistor
+
The "curr*_input" measurements actually report the voltage drop across the
input pins in microvolts. This is equivalent to the current through a 1mOhm
sense resistor. Divide the reported value by the actual sense resistor value
in mOhm to get the actual value.
-
-in0_input Voltage at Vcc pin in millivolt (range 2.5V to 5V)
-temp1_input Internal chip temperature in millidegrees Celcius
-curr1_input Current in mA across v1-v2 assuming a 1mOhm sense resistor.
-curr2_input Current in mA across v3-v4 assuming a 1mOhm sense resistor.
diff --git a/Documentation/i2c/busses/i2c-ocores b/Documentation/i2c/busses/i2c-ocores
index c269aaa..9e1dfe7 100644
--- a/Documentation/i2c/busses/i2c-ocores
+++ b/Documentation/i2c/busses/i2c-ocores
@@ -2,7 +2,7 @@
Supported adapters:
* OpenCores.org I2C controller by Richard Herveille (see datasheet link)
- Datasheet: http://www.opencores.org/projects.cgi/web/i2c/overview
+ https://opencores.org/project/i2c/overview
Author: Peter Korsgaard <jacmet@sunsite.dk>
diff --git a/Documentation/i2c/dev-interface b/Documentation/i2c/dev-interface
index d04e6e4..fbed645 100644
--- a/Documentation/i2c/dev-interface
+++ b/Documentation/i2c/dev-interface
@@ -9,8 +9,8 @@
the i2c-tools package.
I2C device files are character device files with major device number 89
-and a minor device number corresponding to the number assigned as
-explained above. They should be called "i2c-%d" (i2c-0, i2c-1, ...,
+and a minor device number corresponding to the number assigned as
+explained above. They should be called "i2c-%d" (i2c-0, i2c-1, ...,
i2c-10, ...). All 256 minor device numbers are reserved for i2c.
@@ -23,11 +23,6 @@
#include <linux/i2c-dev.h>
#include <i2c/smbus.h>
-(Please note that there are two files named "i2c-dev.h" out there. One is
-distributed with the Linux kernel and the other one is included in the
-source tree of i2c-tools. They used to be different in content but since 2012
-they're identical. You should use "linux/i2c-dev.h").
-
Now, you have to decide which adapter you want to access. You should
inspect /sys/class/i2c-dev/ or run "i2cdetect -l" to decide this.
Adapter numbers are assigned somewhat dynamically, so you can not
@@ -38,7 +33,7 @@
int file;
int adapter_nr = 2; /* probably dynamically determined */
char filename[20];
-
+
snprintf(filename, 19, "/dev/i2c-%d", adapter_nr);
file = open(filename, O_RDWR);
if (file < 0) {
@@ -72,8 +67,10 @@
/* res contains the read word */
}
- /* Using I2C Write, equivalent of
- i2c_smbus_write_word_data(file, reg, 0x6543) */
+ /*
+ * Using I2C Write, equivalent of
+ * i2c_smbus_write_word_data(file, reg, 0x6543)
+ */
buf[0] = reg;
buf[1] = 0x43;
buf[2] = 0x65;
@@ -140,14 +137,14 @@
set in each message, overriding the values set with the above ioctl's.
ioctl(file, I2C_SMBUS, struct i2c_smbus_ioctl_data *args)
- Not meant to be called directly; instead, use the access functions
- below.
+ If possible, use the provided i2c_smbus_* methods described below instead
+ of issuing direct ioctls.
You can do plain i2c transactions by using read(2) and write(2) calls.
You do not need to pass the address byte; instead, set it through
ioctl I2C_SLAVE before you try to access the device.
-You can do SMBus level transactions (see documentation file smbus-protocol
+You can do SMBus level transactions (see documentation file smbus-protocol
for details) through the following functions:
__s32 i2c_smbus_write_quick(int file, __u8 value);
__s32 i2c_smbus_read_byte(int file);
@@ -158,7 +155,7 @@
__s32 i2c_smbus_write_word_data(int file, __u8 command, __u16 value);
__s32 i2c_smbus_process_call(int file, __u8 command, __u16 value);
__s32 i2c_smbus_read_block_data(int file, __u8 command, __u8 *values);
- __s32 i2c_smbus_write_block_data(int file, __u8 command, __u8 length,
+ __s32 i2c_smbus_write_block_data(int file, __u8 command, __u8 length,
__u8 *values);
All these transactions return -1 on failure; you can read errno to see
what happened. The 'write' transactions return 0 on success; the
@@ -166,10 +163,9 @@
returns the number of values read. The block buffers need not be longer
than 32 bytes.
-The above functions are all inline functions, that resolve to calls to
-the i2c_smbus_access function, that on its turn calls a specific ioctl
-with the data in a specific format. Read the source code if you
-want to know what happens behind the screens.
+The above functions are made available by linking against the libi2c library,
+which is provided by the i2c-tools project. See:
+https://git.kernel.org/pub/scm/utils/i2c-tools/i2c-tools.git/.
Implementation details
diff --git a/Documentation/index.rst b/Documentation/index.rst
index 3b99ab9..fdc5857 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -45,7 +45,7 @@
.. toctree::
:maxdepth: 2
- userspace-api/index
+ userspace-api/index
Introduction to kernel development
@@ -89,6 +89,7 @@
sound/index
crypto/index
filesystems/index
+ vm/index
Architecture-specific documentation
-----------------------------------
diff --git a/Documentation/ioctl/botching-up-ioctls.txt b/Documentation/ioctl/botching-up-ioctls.txt
index d02cfb4..883fb03 100644
--- a/Documentation/ioctl/botching-up-ioctls.txt
+++ b/Documentation/ioctl/botching-up-ioctls.txt
@@ -73,7 +73,9 @@
future extensions is going right down the gutters since someone will submit
an ioctl struct with random stack garbage in the yet unused parts. Which
then bakes in the ABI that those fields can never be used for anything else
- but garbage.
+ but garbage. This is also the reason why you must explicitly pad all
+ structures, even if you never use them in an array - the padding the compiler
+ might insert could contain garbage.
* Have simple testcases for all of the above.
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 84bb74d..27c1b7b 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -217,7 +217,6 @@
'd' 02-40 pcmcia/ds.h conflict!
'd' F0-FF linux/digi1.h
'e' all linux/digi1.h conflict!
-'e' 00-1F drivers/net/irda/irtty-sir.h conflict!
'f' 00-1F linux/ext2_fs.h conflict!
'f' 00-1F linux/ext3_fs.h conflict!
'f' 00-0F fs/jfs/jfs_dinode.h conflict!
@@ -247,7 +246,6 @@
'm' all linux/synclink.h conflict!
'm' 00-19 drivers/message/fusion/mptctl.h conflict!
'm' 00 drivers/scsi/megaraid/megaraid_ioctl.h conflict!
-'m' 00-1F net/irda/irmod.h conflict!
'n' 00-7F linux/ncp_fs.h and fs/ncpfs/ioctl.c
'n' 80-8F uapi/linux/nilfs2_api.h NILFS2
'n' E0-FF linux/matroxfb.h matroxfb
@@ -298,7 +296,8 @@
0x90 00 drivers/cdrom/sbpcd.h
0x92 00-0F drivers/usb/mon/mon_bin.c
0x93 60-7F linux/auto_fs.h
-0x94 all fs/btrfs/ioctl.h
+0x94 all fs/btrfs/ioctl.h Btrfs filesystem
+ and linux/fs.h some lifted to vfs/generic
0x97 00-7F fs/ceph/ioctl.h Ceph file system
0x99 00-0F 537-Addinboard driver
<mailto:buk@buks.ipn.de>
diff --git a/Documentation/livepatch/shadow-vars.txt b/Documentation/livepatch/shadow-vars.txt
index 89c6663..ecc09a7 100644
--- a/Documentation/livepatch/shadow-vars.txt
+++ b/Documentation/livepatch/shadow-vars.txt
@@ -34,9 +34,13 @@
- data[] - storage for shadow data
It is important to note that the klp_shadow_alloc() and
-klp_shadow_get_or_alloc() calls, described below, store a *copy* of the
-data that the functions are provided. Callers should provide whatever
-mutual exclusion is required of the shadow data.
+klp_shadow_get_or_alloc() are zeroing the variable by default.
+They also allow to call a custom constructor function when a non-zero
+value is needed. Callers should provide whatever mutual exclusion
+is required.
+
+Note that the constructor is called under klp_shadow_lock spinlock. It allows
+to do actions that can be done only once when a new variable is allocated.
* klp_shadow_get() - retrieve a shadow variable data pointer
- search hashtable for <obj, id> pair
@@ -47,7 +51,7 @@
- WARN and return NULL
- if <obj, id> doesn't already exist
- allocate a new shadow variable
- - copy data into the new shadow variable
+ - initialize the variable using a custom constructor and data when provided
- add <obj, id> to the global hashtable
* klp_shadow_get_or_alloc() - get existing or alloc a new shadow variable
@@ -56,16 +60,20 @@
- return existing shadow variable
- if <obj, id> doesn't already exist
- allocate a new shadow variable
- - copy data into the new shadow variable
+ - initialize the variable using a custom constructor and data when provided
- add <obj, id> pair to the global hashtable
* klp_shadow_free() - detach and free a <obj, id> shadow variable
- find and remove a <obj, id> reference from global hashtable
- - if found, free shadow variable
+ - if found
+ - call destructor function if defined
+ - free shadow variable
* klp_shadow_free_all() - detach and free all <*, id> shadow variables
- find and remove any <*, id> references from global hashtable
- - if found, free shadow variable
+ - if found
+ - call destructor function if defined
+ - free shadow variable
2. Use cases
@@ -107,7 +115,8 @@
sta = kzalloc(sizeof(*sta) + hw->sta_data_size, gfp);
/* Attach a corresponding shadow variable, then initialize it */
- ps_lock = klp_shadow_alloc(sta, PS_LOCK, NULL, sizeof(*ps_lock), gfp);
+ ps_lock = klp_shadow_alloc(sta, PS_LOCK, sizeof(*ps_lock), gfp,
+ NULL, NULL);
if (!ps_lock)
goto shadow_fail;
spin_lock_init(ps_lock);
@@ -131,7 +140,7 @@
void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
{
- klp_shadow_free(sta, PS_LOCK);
+ klp_shadow_free(sta, PS_LOCK, NULL);
kfree(sta);
...
@@ -148,16 +157,24 @@
For commit 1d147bfa6429, a good spot to allocate a shadow spinlock is
inside ieee80211_sta_ps_deliver_wakeup():
+int ps_lock_shadow_ctor(void *obj, void *shadow_data, void *ctor_data)
+{
+ spinlock_t *lock = shadow_data;
+
+ spin_lock_init(lock);
+ return 0;
+}
+
#define PS_LOCK 1
void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
{
- DEFINE_SPINLOCK(ps_lock_fallback);
spinlock_t *ps_lock;
/* sync with ieee80211_tx_h_unicast_ps_buf */
ps_lock = klp_shadow_get_or_alloc(sta, PS_LOCK,
- &ps_lock_fallback, sizeof(ps_lock_fallback),
- GFP_ATOMIC);
+ sizeof(*ps_lock), GFP_ATOMIC,
+ ps_lock_shadow_ctor, NULL);
+
if (ps_lock)
spin_lock(ps_lock);
...
diff --git a/Documentation/media/uapi/rc/keytable.c.rst b/Documentation/media/uapi/rc/keytable.c.rst
index e6ce1e3f..217237f 100644
--- a/Documentation/media/uapi/rc/keytable.c.rst
+++ b/Documentation/media/uapi/rc/keytable.c.rst
@@ -7,7 +7,7 @@
/* keytable.c - This program allows checking/replacing keys at IR
- Copyright (C) 2006-2009 Mauro Carvalho Chehab <mchehab@infradead.org>
+ Copyright (C) 2006-2009 Mauro Carvalho Chehab <mchehab@kernel.org>
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
diff --git a/Documentation/media/uapi/v4l/v4l2grab.c.rst b/Documentation/media/uapi/v4l/v4l2grab.c.rst
index 5aabd0b..f0d0ab6 100644
--- a/Documentation/media/uapi/v4l/v4l2grab.c.rst
+++ b/Documentation/media/uapi/v4l/v4l2grab.c.rst
@@ -6,7 +6,7 @@
.. code-block:: c
/* V4L2 video picture grabber
- Copyright (C) 2009 Mauro Carvalho Chehab <mchehab@infradead.org>
+ Copyright (C) 2009 Mauro Carvalho Chehab <mchehab@kernel.org>
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 6dafc80..a02d6bb 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -1920,9 +1920,6 @@
/* assign ownership */
desc->status = DEVICE_OWN;
- /* force memory to sync before notifying device via MMIO */
- wmb();
-
/* notify device of new descriptors */
writel(DESC_NOTIFY, doorbell);
}
@@ -1930,11 +1927,15 @@
The dma_rmb() allows us guarantee the device has released ownership
before we read the data from the descriptor, and the dma_wmb() allows
us to guarantee the data is written to the descriptor before the device
- can see it now has ownership. The wmb() is needed to guarantee that the
- cache coherent memory writes have completed before attempting a write to
- the cache incoherent MMIO region.
+ can see it now has ownership. Note that, when using writel(), a prior
+ wmb() is not needed to guarantee that the cache coherent memory writes
+ have completed before writing to the MMIO region. The cheaper
+ writel_relaxed() does not provide this guarantee and must not be used
+ here.
- See Documentation/DMA-API.txt for more information on consistent memory.
+ See the subsection "Kernel I/O barrier effects" for more information on
+ relaxed I/O accessors and the Documentation/DMA-API.txt file for more
+ information on consistent memory.
MMIO WRITE BARRIER
@@ -2903,7 +2904,7 @@
appropriate part of the kernel must invalidate the overlapping bits of the
cache on each CPU.
-See Documentation/cachetlb.txt for more information on cache management.
+See Documentation/core-api/cachetlb.rst for more information on cache management.
CACHE COHERENCY VS MMIO
@@ -3083,7 +3084,7 @@
Memory barriers can be used to implement circular buffering without the need
of a lock to serialise the producer with the consumer. See:
- Documentation/circular-buffers.txt
+ Documentation/core-api/circular-buffers.rst
for details.
diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt
index a4508ec..fd55c7d 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/networking/filter.txt
@@ -169,7 +169,7 @@
BPF engine and instruction set
------------------------------
-Under tools/net/ there's a small helper tool called bpf_asm which can
+Under tools/bpf/ there's a small helper tool called bpf_asm which can
be used to write low-level filters for example scenarios mentioned in the
previous section. Asm-like syntax mentioned here has been implemented in
bpf_asm and will be used for further explanations (instead of dealing with
@@ -359,7 +359,7 @@
In particular, as usage with xt_bpf or cls_bpf can result in more complex BPF
filters that might not be obvious at first, it's good to test filters before
attaching to a live system. For that purpose, there's a small tool called
-bpf_dbg under tools/net/ in the kernel source directory. This debugger allows
+bpf_dbg under tools/bpf/ in the kernel source directory. This debugger allows
for testing BPF filters against given pcap files, single stepping through the
BPF code on the pcap's packets and to do BPF machine register dumps.
@@ -483,7 +483,7 @@
[ 3389.935851] JIT code: 00000030: 00 e8 28 94 ff e0 83 f8 01 75 07 b8 ff ff 00 00
[ 3389.935852] JIT code: 00000040: eb 02 31 c0 c9 c3
-In the kernel source tree under tools/net/, there's bpf_jit_disasm for
+In the kernel source tree under tools/bpf/, there's bpf_jit_disasm for
generating disassembly out of the kernel log's hexdump:
# ./bpf_jit_disasm
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 5dc1a04..35ffaa2 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1390,26 +1390,26 @@
Default: 2 (as specified by RFC3810 9.1)
Minimum: 1 (as specified by RFC6636 4.5)
-max_dst_opts_cnt - INTEGER
+max_dst_opts_number - INTEGER
Maximum number of non-padding TLVs allowed in a Destination
options extension header. If this value is less than zero
then unknown options are disallowed and the number of known
TLVs allowed is the absolute value of this number.
Default: 8
-max_hbh_opts_cnt - INTEGER
+max_hbh_opts_number - INTEGER
Maximum number of non-padding TLVs allowed in a Hop-by-Hop
options extension header. If this value is less than zero
then unknown options are disallowed and the number of known
TLVs allowed is the absolute value of this number.
Default: 8
-max dst_opts_len - INTEGER
+max_dst_opts_length - INTEGER
Maximum length allowed for a Destination options extension
header.
Default: INT_MAX (unlimited)
-max hbh_opts_len - INTEGER
+max_hbh_length - INTEGER
Maximum length allowed for a Hop-by-Hop options extension
header.
Default: INT_MAX (unlimited)
@@ -2126,18 +2126,3 @@
Default: 10
-
-UNDOCUMENTED:
-
-/proc/sys/net/irda/*
- fast_poll_increase FIXME
- warn_noreply_time FIXME
- discovery_slots FIXME
- slot_timeout FIXME
- max_baud_rate FIXME
- discovery_timeout FIXME
- lap_keepalive_time FIXME
- max_noreply_time FIXME
- max_tx_data_size FIXME
- max_tx_window FIXME
- min_tx_turn_time FIXME
diff --git a/Documentation/networking/ppp_generic.txt b/Documentation/networking/ppp_generic.txt
index 091d202..61daf4b 100644
--- a/Documentation/networking/ppp_generic.txt
+++ b/Documentation/networking/ppp_generic.txt
@@ -300,12 +300,6 @@
The ioctl calls available on an instance of /dev/ppp attached to a
channel are:
-* PPPIOCDETACH detaches the instance from the channel. This ioctl is
- deprecated since the same effect can be achieved by closing the
- instance. In order to prevent possible races this ioctl will fail
- with an EINVAL error if more than one file descriptor refers to this
- instance (i.e. as a result of dup(), dup2() or fork()).
-
* PPPIOCCONNECT connects this channel to a PPP interface. The
argument should point to an int containing the interface unit
number. It will return an EINVAL error if the channel is already
diff --git a/Documentation/power/suspend-and-cpuhotplug.txt b/Documentation/power/suspend-and-cpuhotplug.txt
index 31abd04..6f55eb9 100644
--- a/Documentation/power/suspend-and-cpuhotplug.txt
+++ b/Documentation/power/suspend-and-cpuhotplug.txt
@@ -168,7 +168,7 @@
[Please bear in mind that the kernel requests the microcode images from
userspace, using the request_firmware() function defined in
-drivers/base/firmware_class.c]
+drivers/base/firmware_loader/main.c]
a. When all the CPUs are identical:
diff --git a/Documentation/process/2.Process.rst b/Documentation/process/2.Process.rst
index ce5561b..a9c46dd 100644
--- a/Documentation/process/2.Process.rst
+++ b/Documentation/process/2.Process.rst
@@ -18,17 +18,17 @@
release history looks like this:
====== =================
- 2.6.38 March 14, 2011
- 2.6.37 January 4, 2011
- 2.6.36 October 20, 2010
- 2.6.35 August 1, 2010
- 2.6.34 May 15, 2010
- 2.6.33 February 24, 2010
+ 4.11 April 30, 2017
+ 4.12 July 2, 2017
+ 4.13 September 3, 2017
+ 4.14 November 12, 2017
+ 4.15 January 28, 2018
+ 4.16 April 1, 2018
====== =================
-Every 2.6.x release is a major kernel release with new features, internal
-API changes, and more. A typical 2.6 release can contain nearly 10,000
-changesets with changes to several hundred thousand lines of code. 2.6 is
+Every 4.x release is a major kernel release with new features, internal
+API changes, and more. A typical 4.x release contain about 13,000
+changesets with changes to several hundred thousand lines of code. 4.x is
thus the leading edge of Linux kernel development; the kernel uses a
rolling development model which is continually integrating major changes.
@@ -70,20 +70,19 @@
considered to be sufficiently stable and the final 2.6.x release is made.
At that point the whole process starts over again.
-As an example, here is how the 2.6.38 development cycle went (all dates in
-2011):
+As an example, here is how the 4.16 development cycle went (all dates in
+2018):
============== ===============================
- January 4 2.6.37 stable release
- January 18 2.6.38-rc1, merge window closes
- January 21 2.6.38-rc2
- February 1 2.6.38-rc3
- February 7 2.6.38-rc4
- February 15 2.6.38-rc5
- February 21 2.6.38-rc6
- March 1 2.6.38-rc7
- March 7 2.6.38-rc8
- March 14 2.6.38 stable release
+ January 28 4.15 stable release
+ February 11 4.16-rc1, merge window closes
+ February 18 4.16-rc2
+ February 25 4.16-rc3
+ March 4 4.16-rc4
+ March 11 4.16-rc5
+ March 18 4.16-rc6
+ March 25 4.16-rc7
+ April 1 4.17 stable release
============== ===============================
How do the developers decide when to close the development cycle and create
@@ -99,37 +98,42 @@
achieve; there are just too many variables in a project of this size.
There comes a point where delaying the final release just makes the problem
worse; the pile of changes waiting for the next merge window will grow
-larger, creating even more regressions the next time around. So most 2.6.x
+larger, creating even more regressions the next time around. So most 4.x
kernels go out with a handful of known regressions though, hopefully, none
of them are serious.
Once a stable release is made, its ongoing maintenance is passed off to the
"stable team," currently consisting of Greg Kroah-Hartman. The stable team
-will release occasional updates to the stable release using the 2.6.x.y
+will release occasional updates to the stable release using the 4.x.y
numbering scheme. To be considered for an update release, a patch must (1)
fix a significant bug, and (2) already be merged into the mainline for the
next development kernel. Kernels will typically receive stable updates for
a little more than one development cycle past their initial release. So,
-for example, the 2.6.36 kernel's history looked like:
+for example, the 4.13 kernel's history looked like:
============== ===============================
- October 10 2.6.36 stable release
- November 22 2.6.36.1
- December 9 2.6.36.2
- January 7 2.6.36.3
- February 17 2.6.36.4
+ September 3 4.13 stable release
+ September 13 4.13.1
+ September 20 4.13.2
+ September 27 4.13.3
+ October 5 4.13.4
+ October 12 4.13.5
+ ... ...
+ November 24 4.13.16
============== ===============================
-2.6.36.4 was the final stable update for the 2.6.36 release.
+4.13.16 was the final stable update of the 4.13 release.
Some kernels are designated "long term" kernels; they will receive support
for a longer period. As of this writing, the current long term kernels
and their maintainers are:
- ====== ====================== ===========================
- 2.6.27 Willy Tarreau (Deep-frozen stable kernel)
- 2.6.32 Greg Kroah-Hartman
- 2.6.35 Andi Kleen (Embedded flag kernel)
+ ====== ====================== ==============================
+ 3.16 Ben Hutchings (very long-term stable kernel)
+ 4.1 Sasha Levin
+ 4.4 Greg Kroah-Hartman (very long-term stable kernel)
+ 4.9 Greg Kroah-Hartman
+ 4.14 Greg Kroah-Hartman
====== ====================== ===========================
The selection of a kernel for long-term support is purely a matter of a
diff --git a/Documentation/process/5.Posting.rst b/Documentation/process/5.Posting.rst
index c209d70..c418c5d 100644
--- a/Documentation/process/5.Posting.rst
+++ b/Documentation/process/5.Posting.rst
@@ -10,8 +10,8 @@
following them will make life much easier for everybody involved. This
document will attempt to cover these expectations in reasonable detail;
more information can also be found in the files process/submitting-patches.rst,
-process/submitting-drivers.rst, and process/submit-checklist.rst in the kernel documentation
-directory.
+process/submitting-drivers.rst, and process/submit-checklist.rst in the kernel
+documentation directory.
When to post
@@ -198,8 +198,8 @@
The tags mentioned above are used to describe how various developers have
been associated with the development of this patch. They are described in
-detail in the process/submitting-patches.rst document; what follows here is a brief
-summary. Each of these lines has the format:
+detail in the process/submitting-patches.rst document; what follows here is a
+brief summary. Each of these lines has the format:
::
@@ -210,8 +210,8 @@
- Signed-off-by: this is a developer's certification that he or she has
the right to submit the patch for inclusion into the kernel. It is an
agreement to the Developer's Certificate of Origin, the full text of
- which can be found in Documentation/process/submitting-patches.rst. Code without a
- proper signoff cannot be merged into the mainline.
+ which can be found in Documentation/process/submitting-patches.rst. Code
+ without a proper signoff cannot be merged into the mainline.
- Co-developed-by: states that the patch was also created by another developer
along with the original author. This is useful at times when multiple
@@ -226,8 +226,8 @@
it to work.
- Reviewed-by: the named developer has reviewed the patch for correctness;
- see the reviewer's statement in Documentation/process/submitting-patches.rst for more
- detail.
+ see the reviewer's statement in Documentation/process/submitting-patches.rst
+ for more detail.
- Reported-by: names a user who reported a problem which is fixed by this
patch; this tag is used to give credit to the (often underappreciated)
diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst
index 1c9fe65..37bd062 100644
--- a/Documentation/process/index.rst
+++ b/Documentation/process/index.rst
@@ -52,6 +52,7 @@
adding-syscalls
magic-number
volatile-considered-harmful
+ clang-format
.. only:: subproject and html
diff --git a/Documentation/process/magic-number.rst b/Documentation/process/magic-number.rst
index 00cecf1f..633be10 100644
--- a/Documentation/process/magic-number.rst
+++ b/Documentation/process/magic-number.rst
@@ -157,8 +157,5 @@
OSS sound drivers have their magic numbers constructed from the soundcard PCI
ID - these are not listed here as well.
-IrDA subsystem also uses large number of own magic numbers, see
-``include/net/irda/irda.h`` for a complete list of them.
-
HFS is another larger user of magic numbers - you can find them in
``fs/hfs/hfs.h``.
diff --git a/Documentation/process/maintainer-pgp-guide.rst b/Documentation/process/maintainer-pgp-guide.rst
index b453561..aff9b1a 100644
--- a/Documentation/process/maintainer-pgp-guide.rst
+++ b/Documentation/process/maintainer-pgp-guide.rst
@@ -219,7 +219,7 @@
if you only have a combined **[SC]** key, then you should create a separate
signing subkey::
- $ gpg --quick-add-key [fpr] ed25519 sign
+ $ gpg --quick-addkey [fpr] ed25519 sign
Remember to tell the keyservers about this change, so others can pull down
your new subkey::
@@ -450,11 +450,18 @@
others. If you want to use ECC keys, your best bet among commercially
available devices is the Nitrokey Start.
+.. note::
+
+ If you are listed in MAINTAINERS or have an account at kernel.org,
+ you `qualify for a free Nitrokey Start`_ courtesy of The Linux
+ Foundation.
+
.. _`Nitrokey Start`: https://shop.nitrokey.com/shop/product/nitrokey-start-6
.. _`Nitrokey Pro`: https://shop.nitrokey.com/shop/product/nitrokey-pro-3
.. _`Yubikey 4`: https://www.yubico.com/product/yubikey-4-series/
.. _Gnuk: http://www.fsij.org/doc-gnuk/
.. _`LWN has a good review`: https://lwn.net/Articles/736231/
+.. _`qualify for a free Nitrokey Start`: https://www.kernel.org/nitrokey-digital-tokens-for-kernel-developers.html
Configure your smartcard device
-------------------------------
@@ -482,7 +489,7 @@
You should set the user PIN (1), Admin PIN (3), and the Reset Code (4).
Please make sure to record and store these in a safe place -- especially
the Admin PIN and the Reset Code (which allows you to completely wipe
-the smartcard). You so rarely need to use the Admin PIN, that you will
+the smartcard). You so rarely need to use the Admin PIN, that you will
inevitably forget what it is if you do not record it.
Getting back to the main card menu, you can also set other values (such
@@ -494,6 +501,12 @@
Despite having the name "PIN", neither the user PIN nor the admin
PIN on the card need to be numbers.
+.. warning::
+
+ Some devices may require that you move the subkeys onto the device
+ before you can change the passphrase. Please check the documentation
+ provided by the device manufacturer.
+
Move the subkeys to your smartcard
----------------------------------
@@ -655,6 +668,20 @@
$ gpg --export | gpg --homedir ~/.gnupg --import
$ unset GNUPGHOME
+Using gpg-agent over ssh
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+You can forward your gpg-agent over ssh if you need to sign tags or
+commits on a remote system. Please refer to the instructions provided
+on the GnuPG wiki:
+
+- `Agent Forwarding over SSH`_
+
+It works more smoothly if you can modify the sshd server settings on the
+remote end.
+
+.. _`Agent Forwarding over SSH`: https://wiki.gnupg.org/AgentForwarding
+
Using PGP with Git
==================
@@ -692,6 +719,7 @@
tell git to always use it instead of the legacy ``gpg`` from version 1::
$ git config --global gpg.program gpg2
+ $ git config --global gpgv.program gpgv2
How to work with signed tags
----------------------------
@@ -731,6 +759,13 @@
import their PGP key. Please refer to the
":ref:`verify_identities`" section below.
+.. note::
+
+ If you get "``gpg: Can't check signature: unknown pubkey
+ algorithm``" error, you need to tell git to use gpgv2 for
+ verification, so it properly processes signatures made by ECC keys.
+ See instructions at the start of this section.
+
Configure git to always sign annotated tags
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/Documentation/process/submitting-patches.rst b/Documentation/process/submitting-patches.rst
index f7152ed..908bb55 100644
--- a/Documentation/process/submitting-patches.rst
+++ b/Documentation/process/submitting-patches.rst
@@ -761,7 +761,7 @@
the pull request as the cover letter for a normal posting of the patch
series, giving the maintainer the option of using either.
-A pull request should have [GIT] or [PULL] in the subject line. The
+A pull request should have [GIT PULL] in the subject line. The
request itself should include the repository name and the branch of
interest on a single line; it should look something like::
diff --git a/Documentation/scheduler/sched-deadline.txt b/Documentation/scheduler/sched-deadline.txt
index 8ce78f8..b14e03f 100644
--- a/Documentation/scheduler/sched-deadline.txt
+++ b/Documentation/scheduler/sched-deadline.txt
@@ -49,7 +49,7 @@
2.1 Main algorithm
------------------
- SCHED_DEADLINE uses three parameters, named "runtime", "period", and
+ SCHED_DEADLINE [18] uses three parameters, named "runtime", "period", and
"deadline", to schedule tasks. A SCHED_DEADLINE task should receive
"runtime" microseconds of execution time every "period" microseconds, and
these "runtime" microseconds are available within "deadline" microseconds
@@ -117,6 +117,10 @@
scheduling deadline = scheduling deadline + period
remaining runtime = remaining runtime + runtime
+ The SCHED_FLAG_DL_OVERRUN flag in sched_attr's sched_flags field allows a task
+ to get informed about runtime overruns through the delivery of SIGXCPU
+ signals.
+
2.2 Bandwidth reclaiming
------------------------
@@ -279,6 +283,19 @@
running_bw is incremented.
+2.3 Energy-aware scheduling
+------------------------
+
+ When cpufreq's schedutil governor is selected, SCHED_DEADLINE implements the
+ GRUB-PA [19] algorithm, reducing the CPU operating frequency to the minimum
+ value that still allows to meet the deadlines. This behavior is currently
+ implemented only for ARM architectures.
+
+ A particular care must be taken in case the time needed for changing frequency
+ is of the same order of magnitude of the reservation period. In such cases,
+ setting a fixed CPU frequency results in a lower amount of deadline misses.
+
+
3. Scheduling Real-Time Tasks
=============================
@@ -505,6 +522,12 @@
17 - L. Abeni, G. Lipari, A. Parri, Y. Sun, Multicore CPU reclaiming: parallel
or sequential?. In Proceedings of the 31st Annual ACM Symposium on Applied
Computing, 2016.
+ 18 - J. Lelli, C. Scordino, L. Abeni, D. Faggioli, Deadline scheduling in the
+ Linux kernel, Software: Practice and Experience, 46(6): 821-839, June
+ 2016.
+ 19 - C. Scordino, L. Abeni, J. Lelli, Energy-Aware Real-Time Scheduling in
+ the Linux Kernel, 33rd ACM/SIGAPP Symposium On Applied Computing (SAC
+ 2018), Pau, France, April 2018.
4. Bandwidth management
diff --git a/Documentation/scsi/scsi_eh.txt b/Documentation/scsi/scsi_eh.txt
index 11e447b..1b74369 100644
--- a/Documentation/scsi/scsi_eh.txt
+++ b/Documentation/scsi/scsi_eh.txt
@@ -82,24 +82,13 @@
1. invokes optional hostt->eh_timed_out() callback. Return value can
be one of
- - BLK_EH_HANDLED
- This indicates that eh_timed_out() dealt with the timeout.
- The command is passed back to the block layer and completed
- via __blk_complete_requests().
-
- *NOTE* After returning BLK_EH_HANDLED the SCSI layer is
- assumed to be finished with the command, and no other
- functions from the SCSI layer will be called. So this
- should typically only be returned if the eh_timed_out()
- handler raced with normal completion.
-
- BLK_EH_RESET_TIMER
This indicates that more time is required to finish the
command. Timer is restarted. This action is counted as a
retry and only allowed scmd->allowed + 1(!) times. Once the
- limit is reached, action for BLK_EH_NOT_HANDLED is taken instead.
+ limit is reached, action for BLK_EH_DONE is taken instead.
- - BLK_EH_NOT_HANDLED
+ - BLK_EH_DONE
eh_timed_out() callback did not handle the command.
Step #2 is taken.
diff --git a/Documentation/security/index.rst b/Documentation/security/index.rst
index 298a94a..85492bf 100644
--- a/Documentation/security/index.rst
+++ b/Documentation/security/index.rst
@@ -9,5 +9,7 @@
IMA-templates
keys/index
LSM
+ LSM-sctp
+ SELinux-sctp
self-protection
tpm/index
diff --git a/Documentation/sound/alsa-configuration.rst b/Documentation/sound/alsa-configuration.rst
index aed6b4f..ab57611 100644
--- a/Documentation/sound/alsa-configuration.rst
+++ b/Documentation/sound/alsa-configuration.rst
@@ -1062,7 +1062,7 @@
ML (see the section `Links and Addresses`_).
``power_save`` and ``power_save_controller`` options are for power-saving
-mode. See powersave.txt for details.
+mode. See powersave.rst for details.
Note 2: If you get click noises on output, try the module option
``position_fix=1`` or ``2``. ``position_fix=1`` will use the SD_LPIB
@@ -1133,7 +1133,7 @@
enable_monitor
Enable Analog Out on Channel 63/64 by default.
-See hdspm.txt for details.
+See hdspm.rst for details.
Module snd-ice1712
------------------
diff --git a/Documentation/sound/soc/codec.rst b/Documentation/sound/soc/codec.rst
index f87612b..240770e 100644
--- a/Documentation/sound/soc/codec.rst
+++ b/Documentation/sound/soc/codec.rst
@@ -139,7 +139,7 @@
----------------
The Dynamic Audio Power Management description describes the codec power
components and their relationships and registers to the ASoC core.
-Please read dapm.txt for details of building the description.
+Please read dapm.rst for details of building the description.
Please also see the examples in other codec drivers.
diff --git a/Documentation/sound/soc/platform.rst b/Documentation/sound/soc/platform.rst
index d557490..02c93a8 100644
--- a/Documentation/sound/soc/platform.rst
+++ b/Documentation/sound/soc/platform.rst
@@ -66,7 +66,7 @@
4. SYSCLK configuration
5. Suspend and resume (optional)
-Please see codec.txt for a description of items 1 - 4.
+Please see codec.rst for a description of items 1 - 4.
SoC DSP Drivers
diff --git a/Documentation/sphinx/parse-headers.pl b/Documentation/sphinx/parse-headers.pl
index a958d8b..d410f47 100755
--- a/Documentation/sphinx/parse-headers.pl
+++ b/Documentation/sphinx/parse-headers.pl
@@ -387,11 +387,11 @@
=head1 BUGS
-Report bugs to Mauro Carvalho Chehab <mchehab@s-opensource.com>
+Report bugs to Mauro Carvalho Chehab <mchehab@kernel.org>
=head1 COPYRIGHT
-Copyright (c) 2016 by Mauro Carvalho Chehab <mchehab@s-opensource.com>.
+Copyright (c) 2016 by Mauro Carvalho Chehab <mchehab+samsung@kernel.org>.
License GPLv2: GNU GPL version 2 <http://gnu.org/licenses/gpl.html>.
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 17256f2..697ef8c 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -515,7 +515,7 @@
Change the minimum size of the hugepage pool.
-See Documentation/vm/hugetlbpage.txt
+See Documentation/admin-guide/mm/hugetlbpage.rst
==============================================================
@@ -524,7 +524,7 @@
Change the maximum size of the hugepage pool. The maximum is
nr_hugepages + nr_overcommit_hugepages.
-See Documentation/vm/hugetlbpage.txt
+See Documentation/admin-guide/mm/hugetlbpage.rst
==============================================================
@@ -667,7 +667,7 @@
The default value is 0.
-See Documentation/vm/overcommit-accounting and
+See Documentation/vm/overcommit-accounting.rst and
mm/mmap.c::__vm_enough_memory() for more information.
==============================================================
diff --git a/Documentation/trace/coresight.txt b/Documentation/trace/coresight.txt
index 6f0120c..1d74ad0 100644
--- a/Documentation/trace/coresight.txt
+++ b/Documentation/trace/coresight.txt
@@ -187,13 +187,19 @@
specific to that component only. "Implementation defined" customisations are
expected to be accessed and controlled using those entries.
-Last but not least, "struct module *owner" is expected to be set to reflect
-the information carried in "THIS_MODULE".
How to use the tracer modules
-----------------------------
-Before trace collection can start, a coresight sink needs to be identify.
+There are two ways to use the Coresight framework: 1) using the perf cmd line
+tools and 2) interacting directly with the Coresight devices using the sysFS
+interface. Preference is given to the former as using the sysFS interface
+requires a deep understanding of the Coresight HW. The following sections
+provide details on using both methods.
+
+1) Using the sysFS interface:
+
+Before trace collection can start, a coresight sink needs to be identified.
There is no limit on the amount of sinks (nor sources) that can be enabled at
any given moment. As a generic operation, all device pertaining to the sink
class will have an "active" entry in sysfs:
@@ -298,42 +304,48 @@
Instruction 0 0x8026B588 E8BD8000 true LDM sp!,{pc}
Timestamp Timestamp: 17107041535
-How to use the STM module
--------------------------
+2) Using perf framework:
-Using the System Trace Macrocell module is the same as the tracers - the only
-difference is that clients are driving the trace capture rather
-than the program flow through the code.
+Coresight tracers are represented using the Perf framework's Performance
+Monitoring Unit (PMU) abstraction. As such the perf framework takes charge of
+controlling when tracing gets enabled based on when the process of interest is
+scheduled. When configured in a system, Coresight PMUs will be listed when
+queried by the perf command line tool:
-As with any other CoreSight component, specifics about the STM tracer can be
-found in sysfs with more information on each entry being found in [1]:
+ linaro@linaro-nano:~$ ./perf list pmu
-root@genericarmv8:~# ls /sys/bus/coresight/devices/20100000.stm
-enable_source hwevent_select port_enable subsystem uevent
-hwevent_enable mgmt port_select traceid
-root@genericarmv8:~#
+ List of pre-defined events (to be used in -e):
-Like any other source a sink needs to be identified and the STM enabled before
-being used:
+ cs_etm// [Kernel PMU event]
-root@genericarmv8:~# echo 1 > /sys/bus/coresight/devices/20010000.etf/enable_sink
-root@genericarmv8:~# echo 1 > /sys/bus/coresight/devices/20100000.stm/enable_source
+ linaro@linaro-nano:~$
-From there user space applications can request and use channels using the devfs
-interface provided for that purpose by the generic STM API:
+Regardless of the number of tracers available in a system (usually equal to the
+amount of processor cores), the "cs_etm" PMU will be listed only once.
-root@genericarmv8:~# ls -l /dev/20100000.stm
-crw------- 1 root root 10, 61 Jan 3 18:11 /dev/20100000.stm
-root@genericarmv8:~#
+A Coresight PMU works the same way as any other PMU, i.e the name of the PMU is
+listed along with configuration options within forward slashes '/'. Since a
+Coresight system will typically have more than one sink, the name of the sink to
+work with needs to be specified as an event option. Names for sink to choose
+from are listed in sysFS under ($SYSFS)/bus/coresight/devices:
-Details on how to use the generic STM API can be found here [2].
+ root@linaro-nano:~# ls /sys/bus/coresight/devices/
+ 20010000.etf 20040000.funnel 20100000.stm 22040000.etm
+ 22140000.etm 230c0000.funnel 23240000.etm 20030000.tpiu
+ 20070000.etr 20120000.replicator 220c0000.funnel
+ 23040000.etm 23140000.etm 23340000.etm
-[1]. Documentation/ABI/testing/sysfs-bus-coresight-devices-stm
-[2]. Documentation/trace/stm.txt
+ root@linaro-nano:~# perf record -e cs_etm/@20070000.etr/u --per-thread program
+The syntax within the forward slashes '/' is important. The '@' character
+tells the parser that a sink is about to be specified and that this is the sink
+to use for the trace session.
-Using perf tools
-----------------
+More information on the above and other example on how to use Coresight with
+the perf tools can be found in the "HOWTO.md" file of the openCSD gitHub
+repository [3].
+
+2.1) AutoFDO analysis using the perf tools:
perf can be used to record and analyze trace of programs.
@@ -381,3 +393,38 @@
$ taskset -c 2 ./sort_autofdo
Bubble sorting array of 30000 elements
5806 ms
+
+
+How to use the STM module
+-------------------------
+
+Using the System Trace Macrocell module is the same as the tracers - the only
+difference is that clients are driving the trace capture rather
+than the program flow through the code.
+
+As with any other CoreSight component, specifics about the STM tracer can be
+found in sysfs with more information on each entry being found in [1]:
+
+root@genericarmv8:~# ls /sys/bus/coresight/devices/20100000.stm
+enable_source hwevent_select port_enable subsystem uevent
+hwevent_enable mgmt port_select traceid
+root@genericarmv8:~#
+
+Like any other source a sink needs to be identified and the STM enabled before
+being used:
+
+root@genericarmv8:~# echo 1 > /sys/bus/coresight/devices/20010000.etf/enable_sink
+root@genericarmv8:~# echo 1 > /sys/bus/coresight/devices/20100000.stm/enable_source
+
+From there user space applications can request and use channels using the devfs
+interface provided for that purpose by the generic STM API:
+
+root@genericarmv8:~# ls -l /dev/20100000.stm
+crw------- 1 root root 10, 61 Jan 3 18:11 /dev/20100000.stm
+root@genericarmv8:~#
+
+Details on how to use the generic STM API can be found here [2].
+
+[1]. Documentation/ABI/testing/sysfs-bus-coresight-devices-stm
+[2]. Documentation/trace/stm.txt
+[3]. https://github.com/Linaro/perf-opencsd
diff --git a/Documentation/trace/ftrace-uses.rst b/Documentation/trace/ftrace-uses.rst
index 998a60a..00283b6 100644
--- a/Documentation/trace/ftrace-uses.rst
+++ b/Documentation/trace/ftrace-uses.rst
@@ -12,7 +12,7 @@
Introduction
============
-The ftrace infrastructure was originially created to attach callbacks to the
+The ftrace infrastructure was originally created to attach callbacks to the
beginning of functions in order to record and trace the flow of the kernel.
But callbacks to the start of a function can have other use cases. Either
for live kernel patching, or for security monitoring. This document describes
@@ -30,7 +30,7 @@
This requires extra care to what can be done inside a callback. A callback
can be called outside the protective scope of RCU.
-The ftrace infrastructure has some protections agains recursions and RCU
+The ftrace infrastructure has some protections against recursions and RCU
but one must still be very careful how they use the callbacks.
diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst
index e45f078..6b80ac4 100644
--- a/Documentation/trace/ftrace.rst
+++ b/Documentation/trace/ftrace.rst
@@ -224,6 +224,8 @@
has a side effect of enabling or disabling specific functions
to be traced. Echoing names of functions into this file
will limit the trace to only those functions.
+ This influences the tracers "function" and "function_graph"
+ and thus also function profiling (see "function_profile_enabled").
The functions listed in "available_filter_functions" are what
can be written into this file.
@@ -265,6 +267,8 @@
Functions listed in this file will cause the function graph
tracer to only trace these functions and the functions that
they call. (See the section "dynamic ftrace" for more details).
+ Note, set_ftrace_filter and set_ftrace_notrace still affects
+ what functions are being traced.
set_graph_notrace:
@@ -277,7 +281,8 @@
This lists the functions that ftrace has processed and can trace.
These are the function names that you can pass to
- "set_ftrace_filter" or "set_ftrace_notrace".
+ "set_ftrace_filter", "set_ftrace_notrace",
+ "set_graph_function", or "set_graph_notrace".
(See the section "dynamic ftrace" below for more details.)
dyn_ftrace_total_info:
@@ -461,9 +466,17 @@
and ticks at the same rate as the hardware clocksource.
boot:
- Same as mono. Used to be a separate clock which accounted
- for the time spent in suspend while CLOCK_MONOTONIC did
- not.
+ This is the boot clock (CLOCK_BOOTTIME) and is based on the
+ fast monotonic clock, but also accounts for time spent in
+ suspend. Since the clock access is designed for use in
+ tracing in the suspend path, some side effects are possible
+ if clock is accessed after the suspend time is accounted before
+ the fast mono clock is updated. In this case, the clock update
+ appears to happen slightly sooner than it normally would have.
+ Also on 32-bit systems, it's possible that the 64-bit boot offset
+ sees a partial update. These effects are rare and post
+ processing should be able to handle them. See comments in the
+ ktime_get_boot_fast_ns() function for more information.
To set a clock, simply echo the clock name into this file::
diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt
index 0a0930a..921739d 100644
--- a/Documentation/translations/ko_KR/memory-barriers.txt
+++ b/Documentation/translations/ko_KR/memory-barriers.txt
@@ -36,6 +36,9 @@
부분도 있고, 의도하진 않았지만 사람에 의해 쓰였다보니 불완전한 부분도 있습니다.
이 문서는 리눅스에서 제공하는 다양한 메모리 배리어들을 사용하기 위한
안내서입니다만, 뭔가 이상하다 싶으면 (그런게 많을 겁니다) 질문을 부탁드립니다.
+일부 이상한 점들은 공식적인 메모리 일관성 모델과 tools/memory-model/ 에 있는
+관련 문서를 참고해서 해결될 수 있을 겁니다. 그러나, 이 메모리 모델조차도 그
+관리자들의 의견의 집합으로 봐야지, 절대 옳은 예언자로 신봉해선 안될 겁니다.
다시 말하지만, 이 문서는 리눅스가 하드웨어에 기대하는 사항에 대한 명세서가
아닙니다.
@@ -77,7 +80,7 @@
- 메모리 배리어의 종류.
- 메모리 배리어에 대해 가정해선 안될 것.
- - 데이터 의존성 배리어.
+ - 데이터 의존성 배리어 (역사적).
- 컨트롤 의존성.
- SMP 배리어 짝맞추기.
- 메모리 배리어 시퀀스의 예.
@@ -255,17 +258,20 @@
(*) 어떤 CPU 든, 의존성이 존재하는 메모리 액세스들은 해당 CPU 자신에게
있어서는 순서대로 메모리 시스템에 수행 요청됩니다. 즉, 다음에 대해서:
- Q = READ_ONCE(P); smp_read_barrier_depends(); D = READ_ONCE(*Q);
+ Q = READ_ONCE(P); D = READ_ONCE(*Q);
CPU 는 다음과 같은 메모리 오퍼레이션 시퀀스를 수행 요청합니다:
Q = LOAD P, D = LOAD *Q
- 그리고 그 시퀀스 내에서의 순서는 항상 지켜집니다. 대부분의 시스템에서
- smp_read_barrier_depends() 는 아무일도 안하지만 DEC Alpha 에서는
- 명시적으로 사용되어야 합니다. 보통의 경우에는 smp_read_barrier_depends()
- 를 직접 사용하는 대신 rcu_dereference() 같은 것들을 사용해야 함을
- 알아두세요.
+ 그리고 그 시퀀스 내에서의 순서는 항상 지켜집니다. 하지만, DEC Alpha 에서
+ READ_ONCE() 는 메모리 배리어 명령도 내게 되어 있어서, DEC Alpha CPU 는
+ 다음과 같은 메모리 오퍼레이션들을 내놓게 됩니다:
+
+ Q = LOAD P, MEMORY_BARRIER, D = LOAD *Q, MEMORY_BARRIER
+
+ DEC Alpha 에서 수행되든 아니든, READ_ONCE() 는 컴파일러로부터의 악영향
+ 또한 제거합니다.
(*) 특정 CPU 내에서 겹치는 영역의 메모리에 행해지는 로드와 스토어 들은 해당
CPU 안에서는 순서가 바뀌지 않은 것으로 보여집니다. 즉, 다음에 대해서:
@@ -421,8 +427,8 @@
데이터 의존성 배리어는 읽기 배리어의 보다 완화된 형태입니다. 두개의 로드
오퍼레이션이 있고 두번째 것이 첫번째 것의 결과에 의존하고 있을 때(예:
두번째 로드가 참조할 주소를 첫번째 로드가 읽는 경우), 두번째 로드가 읽어올
- 데이터는 첫번째 로드에 의해 그 주소가 얻어지기 전에 업데이트 되어 있음을
- 보장하기 위해서 데이터 의존성 배리어가 필요할 수 있습니다.
+ 데이터는 첫번째 로드에 의해 그 주소가 얻어진 뒤에 업데이트 됨을 보장하기
+ 위해서 데이터 의존성 배리어가 필요할 수 있습니다.
데이터 의존성 배리어는 상호 의존적인 로드 오퍼레이션들 사이의 부분적 순서
세우기입니다; 스토어 오퍼레이션들이나 독립적인 로드들, 또는 중복되는
@@ -570,8 +576,14 @@
Documentation/DMA-API.txt
-데이터 의존성 배리어
---------------------
+데이터 의존성 배리어 (역사적)
+-----------------------------
+
+리눅스 커널 v4.15 기준으로, smp_read_barrier_depends() 가 READ_ONCE() 에
+추가되었는데, 이는 이 섹션에 주의를 기울여야 하는 사람들은 DEC Alpha 아키텍쳐
+전용 코드를 만드는 사람들과 READ_ONCE() 자체를 만드는 사람들 뿐임을 의미합니다.
+그런 분들을 위해, 그리고 역사에 관심 있는 분들을 위해, 여기 데이터 의존성
+배리어에 대한 이야기를 적습니다.
데이터 의존성 배리어의 사용에 있어 지켜야 하는 사항들은 약간 미묘하고, 데이터
의존성 배리어가 사용되어야 하는 상황도 항상 명백하지는 않습니다. 설명을 위해
@@ -1787,7 +1799,7 @@
범용 mb() smp_mb()
쓰기 wmb() smp_wmb()
읽기 rmb() smp_rmb()
- 데이터 의존성 read_barrier_depends() smp_read_barrier_depends()
+ 데이터 의존성 READ_ONCE()
데이터 의존성 배리어를 제외한 모든 메모리 배리어는 컴파일러 배리어를
@@ -2796,8 +2808,9 @@
여기에 개입하기 위해선, 데이터 의존성 배리어나 읽기 배리어를 로드 오퍼레이션들
-사이에 넣어야 합니다. 이렇게 함으로써 캐시가 다음 요청을 처리하기 전에 일관성
-큐를 처리하도록 강제하게 됩니다.
+사이에 넣어야 합니다 (v4.15 부터는 READ_ONCE() 매크로에 의해 무조건적으로
+그렇게 됩니다). 이렇게 함으로써 캐시가 다음 요청을 처리하기 전에 일관성 큐를
+처리하도록 강제하게 됩니다.
CPU 1 CPU 2 COMMENT
=============== =============== =======================================
@@ -2826,7 +2839,10 @@
다른 CPU 들도 분할된 캐시를 가지고 있을 수 있지만, 그런 CPU 들은 평범한 메모리
액세스를 위해서도 이 분할된 캐시들 사이의 조정을 해야만 합니다. Alpha 는 가장
약한 메모리 순서 시맨틱 (semantic) 을 선택함으로써 메모리 배리어가 명시적으로
-사용되지 않았을 때에는 그런 조정이 필요하지 않게 했습니다.
+사용되지 않았을 때에는 그런 조정이 필요하지 않게 했으며, 이는 Alpha 가 당시에
+더 높은 CPU 클락 속도를 가질 수 있게 했습니다. 하지만, (다시 말하건대, v4.15
+이후부터는) Alpha 아키텍쳐 전용 코드와 READ_ONCE() 매크로 내부에서를 제외하고는
+smp_read_barrier_depends() 가 사용되지 않아야 함을 알아두시기 바랍니다.
캐시 일관성 VS DMA
@@ -2846,7 +2862,7 @@
문제를 해결하기 위해선, 커널의 적절한 부분에서 각 CPU 의 캐시 안의 문제가 되는
비트들을 무효화 시켜야 합니다.
-캐시 관리에 대한 더 많은 정보를 위해선 Documentation/cachetlb.txt 를
+캐시 관리에 대한 더 많은 정보를 위해선 Documentation/core-api/cachetlb.rst 를
참고하세요.
@@ -2988,7 +3004,9 @@
메모리 일관성 시스템과 함께 두개의 캐시를 동기화 시켜서, 포인터 변경과 새로운
데이터의 발견을 올바른 순서로 일어나게 하기 때문입니다.
-리눅스 커널의 메모리 배리어 모델은 Alpha 에 기초해서 정의되었습니다.
+리눅스 커널의 메모리 배리어 모델은 Alpha 에 기초해서 정의되었습니다만, v4.15
+부터는 리눅스 커널이 READ_ONCE() 내에 smp_read_barrier_depends() 를 추가해서
+Alpha 의 메모리 모델로의 영향력이 크게 줄어들긴 했습니다.
위의 "캐시 일관성" 서브섹션을 참고하세요.
@@ -3023,7 +3041,7 @@
동기화에 락을 사용하지 않고 구현하는데에 사용될 수 있습니다. 더 자세한 내용을
위해선 다음을 참고하세요:
- Documentation/circular-buffers.txt
+ Documentation/core-api/circular-buffers.rst
=========
diff --git a/Documentation/translations/zh_CN/video4linux/v4l2-framework.txt b/Documentation/translations/zh_CN/video4linux/v4l2-framework.txt
index 698660b..c77c0f0 100644
--- a/Documentation/translations/zh_CN/video4linux/v4l2-framework.txt
+++ b/Documentation/translations/zh_CN/video4linux/v4l2-framework.txt
@@ -6,7 +6,7 @@
help. Contact the Chinese maintainer if this translation is outdated
or if there is a problem with the translation.
-Maintainer: Mauro Carvalho Chehab <mchehab@infradead.org>
+Maintainer: Mauro Carvalho Chehab <mchehab@kernel.org>
Chinese maintainer: Fu Wei <tekkamanninja@gmail.com>
---------------------------------------------------------------------
Documentation/video4linux/v4l2-framework.txt 的中文翻译
@@ -14,7 +14,7 @@
如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文
交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻
译存在问题，请联系中文版维护者。
-英文版维护者： Mauro Carvalho Chehab <mchehab@infradead.org>
+英文版维护者： Mauro Carvalho Chehab <mchehab@kernel.org>
中文版维护者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
中文版翻译者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
中文版校译者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst
index 7b2eb1b..a3233da7 100644
--- a/Documentation/userspace-api/index.rst
+++ b/Documentation/userspace-api/index.rst
@@ -19,6 +19,7 @@
no_new_privs
seccomp_filter
unshare
+ spec_ctrl
.. only:: subproject and html
diff --git a/Documentation/userspace-api/spec_ctrl.rst b/Documentation/userspace-api/spec_ctrl.rst
new file mode 100644
index 0000000..32f3d55
--- /dev/null
+++ b/Documentation/userspace-api/spec_ctrl.rst
@@ -0,0 +1,94 @@
+===================
+Speculation Control
+===================
+
+Quite some CPUs have speculation-related misfeatures which are in
+fact vulnerabilities causing data leaks in various forms even across
+privilege domains.
+
+The kernel provides mitigation for such vulnerabilities in various
+forms. Some of these mitigations are compile-time configurable and some
+can be supplied on the kernel command line.
+
+There is also a class of mitigations which are very expensive, but they can
+be restricted to a certain set of processes or tasks in controlled
+environments. The mechanism to control these mitigations is via
+:manpage:`prctl(2)`.
+
+There are two prctl options which are related to this:
+
+ * PR_GET_SPECULATION_CTRL
+
+ * PR_SET_SPECULATION_CTRL
+
+PR_GET_SPECULATION_CTRL
+-----------------------
+
+PR_GET_SPECULATION_CTRL returns the state of the speculation misfeature
+which is selected with arg2 of prctl(2). The return value uses bits 0-3 with
+the following meaning:
+
+==== ===================== ===================================================
+Bit Define Description
+==== ===================== ===================================================
+0 PR_SPEC_PRCTL Mitigation can be controlled per task by
+ PR_SET_SPECULATION_CTRL.
+1 PR_SPEC_ENABLE The speculation feature is enabled, mitigation is
+ disabled.
+2 PR_SPEC_DISABLE The speculation feature is disabled, mitigation is
+ enabled.
+3 PR_SPEC_FORCE_DISABLE Same as PR_SPEC_DISABLE, but cannot be undone. A
+ subsequent prctl(..., PR_SPEC_ENABLE) will fail.
+==== ===================== ===================================================
+
+If all bits are 0 the CPU is not affected by the speculation misfeature.
+
+If PR_SPEC_PRCTL is set, then the per-task control of the mitigation is
+available. If not set, prctl(PR_SET_SPECULATION_CTRL) for the speculation
+misfeature will fail.
+
+PR_SET_SPECULATION_CTRL
+-----------------------
+
+PR_SET_SPECULATION_CTRL allows to control the speculation misfeature, which
+is selected by arg2 of :manpage:`prctl(2)` per task. arg3 is used to hand
+in the control value, i.e. either PR_SPEC_ENABLE or PR_SPEC_DISABLE or
+PR_SPEC_FORCE_DISABLE.
+
+Common error codes
+------------------
+======= =================================================================
+Value Meaning
+======= =================================================================
+EINVAL The prctl is not implemented by the architecture or unused
+ prctl(2) arguments are not 0.
+
+ENODEV arg2 is selecting a not supported speculation misfeature.
+======= =================================================================
+
+PR_SET_SPECULATION_CTRL error codes
+-----------------------------------
+======= =================================================================
+Value Meaning
+======= =================================================================
+0 Success
+
+ERANGE arg3 is incorrect, i.e. it's neither PR_SPEC_ENABLE nor
+ PR_SPEC_DISABLE nor PR_SPEC_FORCE_DISABLE.
+
+ENXIO Control of the selected speculation misfeature is not possible.
+ See PR_GET_SPECULATION_CTRL.
+
+EPERM Speculation was disabled with PR_SPEC_FORCE_DISABLE and caller
+ tried to enable it again.
+======= =================================================================
+
+Speculation misfeature controls
+-------------------------------
+- PR_SPEC_STORE_BYPASS: Speculative Store Bypass
+
+ Invocations:
+ * prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, 0, 0, 0);
+ * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_ENABLE, 0, 0);
+ * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE, 0, 0);
+ * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_FORCE_DISABLE, 0, 0);
diff --git a/Documentation/vfio.txt b/Documentation/vfio.txt
index ef6a511..f1a4d3c 100644
--- a/Documentation/vfio.txt
+++ b/Documentation/vfio.txt
@@ -252,15 +252,14 @@
the driver should call vfio_add_group_dev() and vfio_del_group_dev()
respectively::
- extern int vfio_add_group_dev(struct iommu_group *iommu_group,
- struct device *dev,
+ extern int vfio_add_group_dev(struct device *dev,
const struct vfio_device_ops *ops,
void *device_data);
extern void *vfio_del_group_dev(struct device *dev);
vfio_add_group_dev() indicates to the core to begin tracking the
-specified iommu_group and register the specified dev as owned by
+iommu_group of the specified dev and register the dev as owned by
a VFIO bus driver. The driver provides an ops structure for callbacks
similar to a file operations structure::
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 1c7958b..758bf40 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1960,6 +1960,9 @@
ARM 64-bit FP registers have the following id bit patterns:
0x4030 0000 0012 0 <regno:12>
+ARM firmware pseudo-registers have the following bit pattern:
+ 0x4030 0000 0014 <regno:16>
+
arm64 registers are mapped using the lower 32 bits. The upper 16 of
that is the register group type, or coprocessor number:
@@ -1976,6 +1979,9 @@
arm64 system registers have the following id bit patterns:
0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <crm:4> <op2:3>
+arm64 firmware pseudo-registers have the following bit pattern:
+ 0x6030 0000 0014 <regno:16>
+
MIPS registers are mapped using the lower 32 bits. The upper 16 of that is
the register group type:
@@ -2510,7 +2516,8 @@
and execute guest code when KVM_RUN is called.
- KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode.
Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
- - KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 for the CPU.
+ - KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 (or a future revision
+ backward compatible with v0.2) for the CPU.
Depends on KVM_CAP_ARM_PSCI_0_2.
- KVM_ARM_VCPU_PMU_V3: Emulate PMUv3 for the CPU.
Depends on KVM_CAP_ARM_PMU_V3.
diff --git a/Documentation/virtual/kvm/arm/psci.txt b/Documentation/virtual/kvm/arm/psci.txt
new file mode 100644
index 0000000..aafdab8
--- /dev/null
+++ b/Documentation/virtual/kvm/arm/psci.txt
@@ -0,0 +1,30 @@
+KVM implements the PSCI (Power State Coordination Interface)
+specification in order to provide services such as CPU on/off, reset
+and power-off to the guest.
+
+The PSCI specification is regularly updated to provide new features,
+and KVM implements these updates if they make sense from a virtualization
+point of view.
+
+This means that a guest booted on two different versions of KVM can
+observe two different "firmware" revisions. This could cause issues if
+a given guest is tied to a particular PSCI revision (unlikely), or if
+a migration causes a different PSCI version to be exposed out of the
+blue to an unsuspecting guest.
+
+In order to remedy this situation, KVM exposes a set of "firmware
+pseudo-registers" that can be manipulated using the GET/SET_ONE_REG
+interface. These registers can be saved/restored by userspace, and set
+to a convenient value if required.
+
+The following register is defined:
+
+* KVM_REG_ARM_PSCI_VERSION:
+
+ - Only valid if the vcpu has the KVM_ARM_VCPU_PSCI_0_2 feature set
+ (and thus has already been initialized)
+ - Returns the current PSCI version on GET_ONE_REG (defaulting to the
+ highest PSCI version implemented by KVM and compatible with v0.2)
+ - Allows any PSCI version implemented by KVM and compatible with
+ v0.2 to be set with SET_ONE_REG
+ - Affects the whole VM (even if the register view is per-vcpu)
diff --git a/Documentation/virtual/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt
index d4f33eb8..ab022dc 100644
--- a/Documentation/virtual/kvm/cpuid.txt
+++ b/Documentation/virtual/kvm/cpuid.txt
@@ -72,8 +72,8 @@
flag || value || meaning
==================================================================================
-KVM_HINTS_DEDICATED || 0 || guest checks this feature bit to
- || || determine if there is vCPU pinning
- || || and there is no vCPU over-commitment,
+KVM_HINTS_REALTIME || 0 || guest checks this feature bit to
+ || || determine that vCPUs are never
+ || || preempted for an unlimited time,
|| || allowing optimizations
----------------------------------------------------------------------------------
diff --git a/Documentation/vm/00-INDEX b/Documentation/vm/00-INDEX
index 0278f2c..f4a4f3e 100644
--- a/Documentation/vm/00-INDEX
+++ b/Documentation/vm/00-INDEX
@@ -1,62 +1,50 @@
00-INDEX
- this file.
-active_mm.txt
+active_mm.rst
- An explanation from Linus about tsk->active_mm vs tsk->mm.
-balance
+balance.rst
- various information on memory balancing.
-cleancache.txt
+cleancache.rst
- Intro to cleancache and page-granularity victim cache.
-frontswap.txt
+frontswap.rst
- Outline frontswap, part of the transcendent memory frontend.
-highmem.txt
+highmem.rst
- Outline of highmem and common issues.
-hmm.txt
+hmm.rst
- Documentation of heterogeneous memory management
-hugetlbpage.txt
- - a brief summary of hugetlbpage support in the Linux kernel.
-hugetlbfs_reserv.txt
+hugetlbfs_reserv.rst
- A brief overview of hugetlbfs reservation design/implementation.
-hwpoison.txt
+hwpoison.rst
- explains what hwpoison is
-idle_page_tracking.txt
- - description of the idle page tracking feature.
-ksm.txt
+ksm.rst
- how to use the Kernel Samepage Merging feature.
-mmu_notifier.txt
+mmu_notifier.rst
- a note about clearing pte/pmd and mmu notifications
-numa
+numa.rst
- information about NUMA specific code in the Linux vm.
-numa_memory_policy.txt
- - documentation of concepts and APIs of the 2.6 memory policy support.
-overcommit-accounting
+overcommit-accounting.rst
- description of the Linux kernels overcommit handling modes.
-page_frags
+page_frags.rst
- description of page fragments allocator
-page_migration
+page_migration.rst
- description of page migration in NUMA systems.
-pagemap.txt
- - pagemap, from the userspace perspective
-page_owner.txt
+page_owner.rst
- tracking about who allocated each page
-remap_file_pages.txt
+remap_file_pages.rst
- a note about remap_file_pages() system call
-slub.txt
+slub.rst
- a short users guide for SLUB.
-soft-dirty.txt
- - short explanation for soft-dirty PTEs
-split_page_table_lock
+split_page_table_lock.rst
- Separate per-table lock to improve scalability of the old page_table_lock.
-swap_numa.txt
+swap_numa.rst
- automatic binding of swap device to numa node
-transhuge.txt
+transhuge.rst
- Transparent Hugepage Support, alternative way of using hugepages.
-unevictable-lru.txt
+unevictable-lru.rst
- Unevictable LRU infrastructure
-userfaultfd.txt
- - description of userfaultfd system call
z3fold.txt
- outline of z3fold allocator for storing compressed pages
-zsmalloc.txt
+zsmalloc.rst
- outline of zsmalloc allocator for storing compressed pages
-zswap.txt
+zswap.rst
- Intro to compressed cache for swap pages
diff --git a/Documentation/vm/active_mm.rst b/Documentation/vm/active_mm.rst
new file mode 100644
index 0000000..c84471b
--- /dev/null
+++ b/Documentation/vm/active_mm.rst
@@ -0,0 +1,91 @@
+.. _active_mm:
+
+=========
+Active MM
+=========
+
+::
+
+ List: linux-kernel
+ Subject: Re: active_mm
+ From: Linus Torvalds <torvalds () transmeta ! com>
+ Date: 1999-07-30 21:36:24
+
+ Cc'd to linux-kernel, because I don't write explanations all that often,
+ and when I do I feel better about more people reading them.
+
+ On Fri, 30 Jul 1999, David Mosberger wrote:
+ >
+ > Is there a brief description someplace on how "mm" vs. "active_mm" in
+ > the task_struct are supposed to be used? (My apologies if this was
+ > discussed on the mailing lists---I just returned from vacation and
+ > wasn't able to follow linux-kernel for a while).
+
+ Basically, the new setup is:
+
+ - we have "real address spaces" and "anonymous address spaces". The
+ difference is that an anonymous address space doesn't care about the
+ user-level page tables at all, so when we do a context switch into an
+ anonymous address space we just leave the previous address space
+ active.
+
+ The obvious use for a "anonymous address space" is any thread that
+ doesn't need any user mappings - all kernel threads basically fall into
+ this category, but even "real" threads can temporarily say that for
+ some amount of time they are not going to be interested in user space,
+ and that the scheduler might as well try to avoid wasting time on
+ switching the VM state around. Currently only the old-style bdflush
+ sync does that.
+
+ - "tsk->mm" points to the "real address space". For an anonymous process,
+ tsk->mm will be NULL, for the logical reason that an anonymous process
+ really doesn't _have_ a real address space at all.
+
+ - however, we obviously need to keep track of which address space we
+ "stole" for such an anonymous user. For that, we have "tsk->active_mm",
+ which shows what the currently active address space is.
+
+ The rule is that for a process with a real address space (ie tsk->mm is
+ non-NULL) the active_mm obviously always has to be the same as the real
+ one.
+
+ For a anonymous process, tsk->mm == NULL, and tsk->active_mm is the
+ "borrowed" mm while the anonymous process is running. When the
+ anonymous process gets scheduled away, the borrowed address space is
+ returned and cleared.
+
+ To support all that, the "struct mm_struct" now has two counters: a
+ "mm_users" counter that is how many "real address space users" there are,
+ and a "mm_count" counter that is the number of "lazy" users (ie anonymous
+ users) plus one if there are any real users.
+
+ Usually there is at least one real user, but it could be that the real
+ user exited on another CPU while a lazy user was still active, so you do
+ actually get cases where you have a address space that is _only_ used by
+ lazy users. That is often a short-lived state, because once that thread
+ gets scheduled away in favour of a real thread, the "zombie" mm gets
+ released because "mm_users" becomes zero.
+
+ Also, a new rule is that _nobody_ ever has "init_mm" as a real MM any
+ more. "init_mm" should be considered just a "lazy context when no other
+ context is available", and in fact it is mainly used just at bootup when
+ no real VM has yet been created. So code that used to check
+
+ if (current->mm == &init_mm)
+
+ should generally just do
+
+ if (!current->mm)
+
+ instead (which makes more sense anyway - the test is basically one of "do
+ we have a user context", and is generally done by the page fault handler
+ and things like that).
+
+ Anyway, I put a pre-patch-2.3.13-1 on ftp.kernel.org just a moment ago,
+ because it slightly changes the interfaces to accommodate the alpha (who
+ would have thought it, but the alpha actually ends up having one of the
+ ugliest context switch codes - unlike the other architectures where the MM
+ and register state is separate, the alpha PALcode joins the two, and you
+ need to switch both together).
+
+ (From http://marc.info/?l=linux-kernel&m=93337278602211&w=2)
diff --git a/Documentation/vm/active_mm.txt b/Documentation/vm/active_mm.txt
deleted file mode 100644
index dbf4581..0000000
--- a/Documentation/vm/active_mm.txt
+++ /dev/null
@@ -1,83 +0,0 @@
-List: linux-kernel
-Subject: Re: active_mm
-From: Linus Torvalds <torvalds () transmeta ! com>
-Date: 1999-07-30 21:36:24
-
-Cc'd to linux-kernel, because I don't write explanations all that often,
-and when I do I feel better about more people reading them.
-
-On Fri, 30 Jul 1999, David Mosberger wrote:
->
-> Is there a brief description someplace on how "mm" vs. "active_mm" in
-> the task_struct are supposed to be used? (My apologies if this was
-> discussed on the mailing lists---I just returned from vacation and
-> wasn't able to follow linux-kernel for a while).
-
-Basically, the new setup is:
-
- - we have "real address spaces" and "anonymous address spaces". The
- difference is that an anonymous address space doesn't care about the
- user-level page tables at all, so when we do a context switch into an
- anonymous address space we just leave the previous address space
- active.
-
- The obvious use for a "anonymous address space" is any thread that
- doesn't need any user mappings - all kernel threads basically fall into
- this category, but even "real" threads can temporarily say that for
- some amount of time they are not going to be interested in user space,
- and that the scheduler might as well try to avoid wasting time on
- switching the VM state around. Currently only the old-style bdflush
- sync does that.
-
- - "tsk->mm" points to the "real address space". For an anonymous process,
- tsk->mm will be NULL, for the logical reason that an anonymous process
- really doesn't _have_ a real address space at all.
-
- - however, we obviously need to keep track of which address space we
- "stole" for such an anonymous user. For that, we have "tsk->active_mm",
- which shows what the currently active address space is.
-
- The rule is that for a process with a real address space (ie tsk->mm is
- non-NULL) the active_mm obviously always has to be the same as the real
- one.
-
- For a anonymous process, tsk->mm == NULL, and tsk->active_mm is the
- "borrowed" mm while the anonymous process is running. When the
- anonymous process gets scheduled away, the borrowed address space is
- returned and cleared.
-
-To support all that, the "struct mm_struct" now has two counters: a
-"mm_users" counter that is how many "real address space users" there are,
-and a "mm_count" counter that is the number of "lazy" users (ie anonymous
-users) plus one if there are any real users.
-
-Usually there is at least one real user, but it could be that the real
-user exited on another CPU while a lazy user was still active, so you do
-actually get cases where you have a address space that is _only_ used by
-lazy users. That is often a short-lived state, because once that thread
-gets scheduled away in favour of a real thread, the "zombie" mm gets
-released because "mm_users" becomes zero.
-
-Also, a new rule is that _nobody_ ever has "init_mm" as a real MM any
-more. "init_mm" should be considered just a "lazy context when no other
-context is available", and in fact it is mainly used just at bootup when
-no real VM has yet been created. So code that used to check
-
- if (current->mm == &init_mm)
-
-should generally just do
-
- if (!current->mm)
-
-instead (which makes more sense anyway - the test is basically one of "do
-we have a user context", and is generally done by the page fault handler
-and things like that).
-
-Anyway, I put a pre-patch-2.3.13-1 on ftp.kernel.org just a moment ago,
-because it slightly changes the interfaces to accommodate the alpha (who
-would have thought it, but the alpha actually ends up having one of the
-ugliest context switch codes - unlike the other architectures where the MM
-and register state is separate, the alpha PALcode joins the two, and you
-need to switch both together).
-
-(From http://marc.info/?l=linux-kernel&m=93337278602211&w=2)
diff --git a/Documentation/vm/balance b/Documentation/vm/balance.rst
similarity index 95%
rename from Documentation/vm/balance
rename to Documentation/vm/balance.rst
index 9645954..6a1fadf 100644
--- a/Documentation/vm/balance
+++ b/Documentation/vm/balance.rst
@@ -1,3 +1,9 @@
+.. _balance:
+
+================
+Memory Balancing
+================
+
Started Jan 2000 by Kanoj Sarcar <kanoj@sgi.com>
Memory balancing is needed for !__GFP_ATOMIC and !__GFP_KSWAPD_RECLAIM as
@@ -62,11 +68,11 @@
so as to give a fighting chance for replace_with_highmem() to get a
HIGHMEM page, as well as to ensure that HIGHMEM allocations do not
fall back into regular zone. This also makes sure that HIGHMEM pages
-are not leaked (for example, in situations where a HIGHMEM page is in
+are not leaked (for example, in situations where a HIGHMEM page is in
the swapcache but is not being used by anyone)
kswapd also needs to know about the zones it should balance. kswapd is
-primarily needed in a situation where balancing can not be done,
+primarily needed in a situation where balancing can not be done,
probably because all allocation requests are coming from intr context
and all process contexts are sleeping. For 2.3, kswapd does not really
need to balance the highmem zone, since intr context does not request
@@ -89,7 +95,8 @@
(Good) Ideas that I have heard:
+
1. Dynamic experience should influence balancing: number of failed requests
-for a zone can be tracked and fed into the balancing scheme (jalvo@mbay.net)
+ for a zone can be tracked and fed into the balancing scheme (jalvo@mbay.net)
2. Implement a replace_with_highmem()-like replace_with_regular() to preserve
-dma pages. (lkd@tantalophile.demon.co.uk)
+ dma pages. (lkd@tantalophile.demon.co.uk)
diff --git a/Documentation/vm/cleancache.txt b/Documentation/vm/cleancache.rst
similarity index 83%
rename from Documentation/vm/cleancache.txt
rename to Documentation/vm/cleancache.rst
index e4b49df..68cba91 100644
--- a/Documentation/vm/cleancache.txt
+++ b/Documentation/vm/cleancache.rst
@@ -1,4 +1,11 @@
-MOTIVATION
+.. _cleancache:
+
+==========
+Cleancache
+==========
+
+Motivation
+==========
Cleancache is a new optional feature provided by the VFS layer that
potentially dramatically increases page cache effectiveness for
@@ -21,9 +28,10 @@
in Xen (using hypervisor memory) and zcache (using in-kernel compressed
memory) and other implementations are in development.
-FAQs are included below.
+:ref:`FAQs <faq>` are included below.
-IMPLEMENTATION OVERVIEW
+Implementation Overview
+=======================
A cleancache "backend" that provides transcendent memory registers itself
to the kernel's cleancache "frontend" by calling cleancache_register_ops,
@@ -80,22 +88,33 @@
with the same handle, the results are indeterminate. Callers must
lock the page to ensure serial behavior.
-CLEANCACHE PERFORMANCE METRICS
+Cleancache Performance Metrics
+==============================
If properly configured, monitoring of cleancache is done via debugfs in
-the /sys/kernel/debug/cleancache directory. The effectiveness of cleancache
+the `/sys/kernel/debug/cleancache` directory. The effectiveness of cleancache
can be measured (across all filesystems) with:
-succ_gets - number of gets that were successful
-failed_gets - number of gets that failed
-puts - number of puts attempted (all "succeed")
-invalidates - number of invalidates attempted
+``succ_gets``
+ number of gets that were successful
+
+``failed_gets``
+ number of gets that failed
+
+``puts``
+ number of puts attempted (all "succeed")
+
+``invalidates``
+ number of invalidates attempted
A backend implementation may provide additional metrics.
-FAQ
+.. _faq:
-1) Where's the value? (Andrew Morton)
+FAQ
+===
+
+* Where's the value? (Andrew Morton)
Cleancache provides a significant performance benefit to many workloads
in many environments with negligible overhead by improving the
@@ -137,8 +156,8 @@
the proposed "RAMster" driver shares RAM across multiple physical
systems.
-2) Why does cleancache have its sticky fingers so deep inside the
- filesystems and VFS? (Andrew Morton and Christoph Hellwig)
+* Why does cleancache have its sticky fingers so deep inside the
+ filesystems and VFS? (Andrew Morton and Christoph Hellwig)
The core hooks for cleancache in VFS are in most cases a single line
and the minimum set are placed precisely where needed to maintain
@@ -168,9 +187,9 @@
The total impact of the hooks to existing fs and mm files is only
about 40 lines added (not counting comments and blank lines).
-3) Why not make cleancache asynchronous and batched so it can
- more easily interface with real devices with DMA instead
- of copying each individual page? (Minchan Kim)
+* Why not make cleancache asynchronous and batched so it can more
+ easily interface with real devices with DMA instead of copying each
+ individual page? (Minchan Kim)
The one-page-at-a-time copy semantics simplifies the implementation
on both the frontend and backend and also allows the backend to
@@ -182,8 +201,8 @@
or for real kernel-addressable RAM, it makes perfect sense for
transcendent memory.
-4) Why is non-shared cleancache "exclusive"? And where is the
- page "invalidated" after a "get"? (Minchan Kim)
+* Why is non-shared cleancache "exclusive"? And where is the
+ page "invalidated" after a "get"? (Minchan Kim)
The main reason is to free up space in transcendent memory and
to avoid unnecessary cleancache_invalidate calls. If you want inclusive,
@@ -193,7 +212,7 @@
The invalidate is done by the cleancache backend implementation.
-5) What's the performance impact?
+* What's the performance impact?
Performance analysis has been presented at OLS'09 and LCA'10.
Briefly, performance gains can be significant on most workloads,
@@ -206,7 +225,7 @@
has little value, but in newer multicore machines, especially
consolidated/virtualized machines, it has great value.
-6) How do I add cleancache support for filesystem X? (Boaz Harrash)
+* How do I add cleancache support for filesystem X? (Boaz Harrash)
Filesystems that are well-behaved and conform to certain
restrictions can utilize cleancache simply by making a call to
@@ -217,26 +236,26 @@
Some points for a filesystem to consider:
-- The FS should be block-device-based (e.g. a ram-based FS such
- as tmpfs should not enable cleancache)
-- To ensure coherency/correctness, the FS must ensure that all
- file removal or truncation operations either go through VFS or
- add hooks to do the equivalent cleancache "invalidate" operations
-- To ensure coherency/correctness, either inode numbers must
- be unique across the lifetime of the on-disk file OR the
- FS must provide an "encode_fh" function.
-- The FS must call the VFS superblock alloc and deactivate routines
- or add hooks to do the equivalent cleancache calls done there.
-- To maximize performance, all pages fetched from the FS should
- go through the do_mpag_readpage routine or the FS should add
- hooks to do the equivalent (cf. btrfs)
-- Currently, the FS blocksize must be the same as PAGESIZE. This
- is not an architectural restriction, but no backends currently
- support anything different.
-- A clustered FS should invoke the "shared_init_fs" cleancache
- hook to get best performance for some backends.
+ - The FS should be block-device-based (e.g. a ram-based FS such
+ as tmpfs should not enable cleancache)
+ - To ensure coherency/correctness, the FS must ensure that all
+ file removal or truncation operations either go through VFS or
+ add hooks to do the equivalent cleancache "invalidate" operations
+ - To ensure coherency/correctness, either inode numbers must
+ be unique across the lifetime of the on-disk file OR the
+ FS must provide an "encode_fh" function.
+ - The FS must call the VFS superblock alloc and deactivate routines
+ or add hooks to do the equivalent cleancache calls done there.
+ - To maximize performance, all pages fetched from the FS should
+ go through the do_mpag_readpage routine or the FS should add
+ hooks to do the equivalent (cf. btrfs)
+ - Currently, the FS blocksize must be the same as PAGESIZE. This
+ is not an architectural restriction, but no backends currently
+ support anything different.
+ - A clustered FS should invoke the "shared_init_fs" cleancache
+ hook to get best performance for some backends.
-7) Why not use the KVA of the inode as the key? (Christoph Hellwig)
+* Why not use the KVA of the inode as the key? (Christoph Hellwig)
If cleancache would use the inode virtual address instead of
inode/filehandle, the pool id could be eliminated. But, this
@@ -251,7 +270,7 @@
is potentially much larger than the kernel pagecache and is most
useful if the pages survive inode cache removal.
-8) Why is a global variable required?
+* Why is a global variable required?
The cleancache_enabled flag is checked in all of the frequently-used
cleancache hooks. The alternative is a function call to check a static
@@ -262,14 +281,14 @@
time, but have insignificant performance impact when cleancache remains
disabled at runtime.
-9) Does cleanache work with KVM?
+* Does cleanache work with KVM?
The memory model of KVM is sufficiently different that a cleancache
backend may have less value for KVM. This remains to be tested,
especially in an overcommitted system.
-10) Does cleancache work in userspace? It sounds useful for
- memory hungry caches like web browsers. (Jamie Lokier)
+* Does cleancache work in userspace? It sounds useful for
+ memory hungry caches like web browsers. (Jamie Lokier)
No plans yet, though we agree it sounds useful, at least for
apps that bypass the page cache (e.g. O_DIRECT).
diff --git a/Documentation/vm/conf.py b/Documentation/vm/conf.py
new file mode 100644
index 0000000..3b0b601
--- /dev/null
+++ b/Documentation/vm/conf.py
@@ -0,0 +1,10 @@
+# -*- coding: utf-8; mode: python -*-
+
+project = "Linux Memory Management Documentation"
+
+tags.add("subproject")
+
+latex_documents = [
+ ('index', 'memory-management.tex', project,
+ 'The kernel development community', 'manual'),
+]
diff --git a/Documentation/vm/frontswap.txt b/Documentation/vm/frontswap.rst
similarity index 91%
rename from Documentation/vm/frontswap.txt
rename to Documentation/vm/frontswap.rst
index c71a019..1979f43 100644
--- a/Documentation/vm/frontswap.txt
+++ b/Documentation/vm/frontswap.rst
@@ -1,13 +1,20 @@
+.. _frontswap:
+
+=========
+Frontswap
+=========
+
Frontswap provides a "transcendent memory" interface for swap pages.
In some environments, dramatic performance savings may be obtained because
swapped pages are saved in RAM (or a RAM-like device) instead of a swap disk.
-(Note, frontswap -- and cleancache (merged at 3.0) -- are the "frontends"
+(Note, frontswap -- and :ref:`cleancache` (merged at 3.0) -- are the "frontends"
and the only necessary changes to the core kernel for transcendent memory;
all other supporting code -- the "backends" -- is implemented as drivers.
-See the LWN.net article "Transcendent memory in a nutshell" for a detailed
-overview of frontswap and related kernel parts:
-https://lwn.net/Articles/454795/ )
+See the LWN.net article `Transcendent memory in a nutshell`_
+for a detailed overview of frontswap and related kernel parts)
+
+.. _Transcendent memory in a nutshell: https://lwn.net/Articles/454795/
Frontswap is so named because it can be thought of as the opposite of
a "backing" store for a swap device. The storage is assumed to be
@@ -50,19 +57,27 @@
never be obtained from frontswap.
If properly configured, monitoring of frontswap is done via debugfs in
-the /sys/kernel/debug/frontswap directory. The effectiveness of
+the `/sys/kernel/debug/frontswap` directory. The effectiveness of
frontswap can be measured (across all swap devices) with:
-failed_stores - how many store attempts have failed
-loads - how many loads were attempted (all should succeed)
-succ_stores - how many store attempts have succeeded
-invalidates - how many invalidates were attempted
+``failed_stores``
+ how many store attempts have failed
+
+``loads``
+ how many loads were attempted (all should succeed)
+
+``succ_stores``
+ how many store attempts have succeeded
+
+``invalidates``
+ how many invalidates were attempted
A backend implementation may provide additional metrics.
FAQ
+===
-1) Where's the value?
+* Where's the value?
When a workload starts swapping, performance falls through the floor.
Frontswap significantly increases performance in many such workloads by
@@ -117,8 +132,8 @@
using frontswap, investigation is also underway on the use of NVM as
a memory extension technology.
-2) Sure there may be performance advantages in some situations, but
- what's the space/time overhead of frontswap?
+* Sure there may be performance advantages in some situations, but
+ what's the space/time overhead of frontswap?
If CONFIG_FRONTSWAP is disabled, every frontswap hook compiles into
nothingness and the only overhead is a few extra bytes per swapon'ed
@@ -148,8 +163,8 @@
backend, such as zcache, must implement policies to carefully (but
dynamically) manage memory limits to ensure this doesn't happen.
-3) OK, how about a quick overview of what this frontswap patch does
- in terms that a kernel hacker can grok?
+* OK, how about a quick overview of what this frontswap patch does
+ in terms that a kernel hacker can grok?
Let's assume that a frontswap "backend" has registered during
kernel initialization; this registration indicates that this
@@ -188,9 +203,9 @@
store" and (possibly) a "frontswap backend loads", which are presumably much
faster.
-4) Can't frontswap be configured as a "special" swap device that is
- just higher priority than any real swap device (e.g. like zswap,
- or maybe swap-over-nbd/NFS)?
+* Can't frontswap be configured as a "special" swap device that is
+ just higher priority than any real swap device (e.g. like zswap,
+ or maybe swap-over-nbd/NFS)?
No. First, the existing swap subsystem doesn't allow for any kind of
swap hierarchy. Perhaps it could be rewritten to accommodate a hierarchy,
@@ -240,9 +255,9 @@
can still use frontswap but a backend for such devices must configure
some kind of "ghost" swap device and ensure that it is never used.
-5) Why this weird definition about "duplicate stores"? If a page
- has been previously successfully stored, can't it always be
- successfully overwritten?
+* Why this weird definition about "duplicate stores"? If a page
+ has been previously successfully stored, can't it always be
+ successfully overwritten?
Nearly always it can, but no, sometimes it cannot. Consider an example
where data is compressed and the original 4K page has been compressed
@@ -254,7 +269,7 @@
swap subsystem then writes the new data to the read swap device,
this is the correct course of action to ensure coherency.
-6) What is frontswap_shrink for?
+* What is frontswap_shrink for?
When the (non-frontswap) swap subsystem swaps out a page to a real
swap device, that page is only taking up low-value pre-allocated disk
@@ -267,7 +282,7 @@
this is driven using the frontswap_shrink mechanism when memory pressure
subsides.
-7) Why does the frontswap patch create the new include file swapfile.h?
+* Why does the frontswap patch create the new include file swapfile.h?
The frontswap code depends on some swap-subsystem-internal data
structures that have, over the years, moved back and forth between
diff --git a/Documentation/vm/highmem.txt b/Documentation/vm/highmem.rst
similarity index 64%
rename from Documentation/vm/highmem.txt
rename to Documentation/vm/highmem.rst
index 4324d24..0f69a9f 100644
--- a/Documentation/vm/highmem.txt
+++ b/Documentation/vm/highmem.rst
@@ -1,25 +1,14 @@
+.. _highmem:
- ====================
- HIGH MEMORY HANDLING
- ====================
+====================
+High Memory Handling
+====================
By: Peter Zijlstra <a.p.zijlstra@chello.nl>
-Contents:
+.. contents:: :local:
- (*) What is high memory?
-
- (*) Temporary virtual mappings.
-
- (*) Using kmap_atomic.
-
- (*) Cost of temporary mappings.
-
- (*) i386 PAE.
-
-
-====================
-WHAT IS HIGH MEMORY?
+What Is High Memory?
====================
High memory (highmem) is used when the size of physical memory approaches or
@@ -38,7 +27,7 @@
i386) has to be divided between user and kernel space.
The traditional split for architectures using this approach is 3:1, 3GiB for
-userspace and the top 1GiB for kernel space:
+userspace and the top 1GiB for kernel space::
+--------+ 0xffffffff
| Kernel |
@@ -58,40 +47,38 @@
space when they use mm context tags.
-==========================
-TEMPORARY VIRTUAL MAPPINGS
+Temporary Virtual Mappings
==========================
The kernel contains several ways of creating temporary mappings:
- (*) vmap(). This can be used to make a long duration mapping of multiple
- physical pages into a contiguous virtual space. It needs global
- synchronization to unmap.
+* vmap(). This can be used to make a long duration mapping of multiple
+ physical pages into a contiguous virtual space. It needs global
+ synchronization to unmap.
- (*) kmap(). This permits a short duration mapping of a single page. It needs
- global synchronization, but is amortized somewhat. It is also prone to
- deadlocks when using in a nested fashion, and so it is not recommended for
- new code.
+* kmap(). This permits a short duration mapping of a single page. It needs
+ global synchronization, but is amortized somewhat. It is also prone to
+ deadlocks when using in a nested fashion, and so it is not recommended for
+ new code.
- (*) kmap_atomic(). This permits a very short duration mapping of a single
- page. Since the mapping is restricted to the CPU that issued it, it
- performs well, but the issuing task is therefore required to stay on that
- CPU until it has finished, lest some other task displace its mappings.
+* kmap_atomic(). This permits a very short duration mapping of a single
+ page. Since the mapping is restricted to the CPU that issued it, it
+ performs well, but the issuing task is therefore required to stay on that
+ CPU until it has finished, lest some other task displace its mappings.
- kmap_atomic() may also be used by interrupt contexts, since it is does not
- sleep and the caller may not sleep until after kunmap_atomic() is called.
+ kmap_atomic() may also be used by interrupt contexts, since it is does not
+ sleep and the caller may not sleep until after kunmap_atomic() is called.
- It may be assumed that k[un]map_atomic() won't fail.
+ It may be assumed that k[un]map_atomic() won't fail.
-=================
-USING KMAP_ATOMIC
+Using kmap_atomic
=================
When and where to use kmap_atomic() is straightforward. It is used when code
wants to access the contents of a page that might be allocated from high memory
(see __GFP_HIGHMEM), for example a page in the pagecache. The API has two
-functions, and they can be used in a manner similar to the following:
+functions, and they can be used in a manner similar to the following::
/* Find the page of interest. */
struct page *page = find_get_page(mapping, offset);
@@ -109,7 +96,7 @@
not the argument.
If you need to map two pages because you want to copy from one page to
-another you need to keep the kmap_atomic calls strictly nested, like:
+another you need to keep the kmap_atomic calls strictly nested, like::
vaddr1 = kmap_atomic(page1);
vaddr2 = kmap_atomic(page2);
@@ -120,8 +107,7 @@
kunmap_atomic(vaddr1);
-==========================
-COST OF TEMPORARY MAPPINGS
+Cost of Temporary Mappings
==========================
The cost of creating temporary mappings can be quite high. The arch has to
@@ -136,25 +122,24 @@
highmem. In such a case, the arithmetic approach will also be used.
-========
i386 PAE
========
The i386 arch, under some circumstances, will permit you to stick up to 64GiB
of RAM into your 32-bit machine. This has a number of consequences:
- (*) Linux needs a page-frame structure for each page in the system and the
- pageframes need to live in the permanent mapping, which means:
+* Linux needs a page-frame structure for each page in the system and the
+ pageframes need to live in the permanent mapping, which means:
- (*) you can have 896M/sizeof(struct page) page-frames at most; with struct
- page being 32-bytes that would end up being something in the order of 112G
- worth of pages; the kernel, however, needs to store more than just
- page-frames in that memory...
+* you can have 896M/sizeof(struct page) page-frames at most; with struct
+ page being 32-bytes that would end up being something in the order of 112G
+ worth of pages; the kernel, however, needs to store more than just
+ page-frames in that memory...
- (*) PAE makes your page tables larger - which slows the system down as more
- data has to be accessed to traverse in TLB fills and the like. One
- advantage is that PAE has more PTE bits and can provide advanced features
- like NX and PAT.
+* PAE makes your page tables larger - which slows the system down as more
+ data has to be accessed to traverse in TLB fills and the like. One
+ advantage is that PAE has more PTE bits and can provide advanced features
+ like NX and PAT.
The general recommendation is that you don't use more than 8GiB on a 32-bit
machine - although more might work for you and your workload, you're pretty
diff --git a/Documentation/vm/hmm.txt b/Documentation/vm/hmm.rst
similarity index 90%
rename from Documentation/vm/hmm.txt
rename to Documentation/vm/hmm.rst
index 2d1d6f6..cdf3911 100644
--- a/Documentation/vm/hmm.txt
+++ b/Documentation/vm/hmm.rst
@@ -1,4 +1,8 @@
+.. hmm:
+
+=====================================
Heterogeneous Memory Management (HMM)
+=====================================
Provide infrastructure and helpers to integrate non-conventional memory (device
memory like GPU on board memory) into regular kernel path, with the cornerstone
@@ -6,10 +10,10 @@
this document).
HMM also provides optional helpers for SVM (Share Virtual Memory), i.e.,
-allowing a device to transparently access program address coherently with the
-CPU meaning that any valid pointer on the CPU is also a valid pointer for the
-device. This is becoming mandatory to simplify the use of advanced hetero-
-geneous computing where GPU, DSP, or FPGA are used to perform various
+allowing a device to transparently access program address coherently with
+the CPU meaning that any valid pointer on the CPU is also a valid pointer
+for the device. This is becoming mandatory to simplify the use of advanced
+heterogeneous computing where GPU, DSP, or FPGA are used to perform various
computations on behalf of a process.
This document is divided as follows: in the first section I expose the problems
@@ -21,19 +25,10 @@
Finally, the last section presents a new migration helper that allows lever-
aging the device DMA engine.
+.. contents:: :local:
-1) Problems of using a device specific memory allocator:
-2) I/O bus, device memory characteristics
-3) Shared address space and migration
-4) Address space mirroring implementation and API
-5) Represent and manage device memory from core kernel point of view
-6) Migration to and from device memory
-7) Memory cgroup (memcg) and rss accounting
-
-
--------------------------------------------------------------------------------
-
-1) Problems of using a device specific memory allocator:
+Problems of using a device specific memory allocator
+====================================================
Devices with a large amount of on board memory (several gigabytes) like GPUs
have historically managed their memory through dedicated driver specific APIs.
@@ -77,9 +72,8 @@
a shared address space for all other patterns.
--------------------------------------------------------------------------------
-
-2) I/O bus, device memory characteristics
+I/O bus, device memory characteristics
+======================================
I/O buses cripple shared address spaces due to a few limitations. Most I/O
buses only allow basic memory access from device to main memory; even cache
@@ -109,9 +103,8 @@
memory while device is using it (blocking CPU access while it happens).
--------------------------------------------------------------------------------
-
-3) Shared address space and migration
+Shared address space and migration
+==================================
HMM intends to provide two main features. First one is to share the address
space by duplicating the CPU page table in the device page table so the same
@@ -148,23 +141,23 @@
used by the device.
--------------------------------------------------------------------------------
-
-4) Address space mirroring implementation and API
+Address space mirroring implementation and API
+==============================================
Address space mirroring's main objective is to allow duplication of a range of
CPU page table into a device page table; HMM helps keep both synchronized. A
device driver that wants to mirror a process address space must start with the
-registration of an hmm_mirror struct:
+registration of an hmm_mirror struct::
int hmm_mirror_register(struct hmm_mirror *mirror,
struct mm_struct *mm);
int hmm_mirror_register_locked(struct hmm_mirror *mirror,
struct mm_struct *mm);
+
The locked variant is to be used when the driver is already holding mmap_sem
of the mm in write mode. The mirror struct has a set of callbacks that are used
-to propagate CPU page tables:
+to propagate CPU page tables::
struct hmm_mirror_ops {
/* sync_cpu_device_pagetables() - synchronize page tables
@@ -193,10 +186,10 @@
read only, or fully unmap, ...). The device must be done with the update before
the driver callback returns.
-
When the device driver wants to populate a range of virtual addresses, it can
-use either:
- int hmm_vma_get_pfns(struct vm_area_struct *vma,
+use either::
+
+ int hmm_vma_get_pfns(struct vm_area_struct *vma,
struct hmm_range *range,
unsigned long start,
unsigned long end,
@@ -221,7 +214,7 @@
entries.
Locking with the update() callback is the most important aspect the driver must
-respect in order to keep things properly synchronized. The usage pattern is:
+respect in order to keep things properly synchronized. The usage pattern is::
int driver_populate_range(...)
{
@@ -262,9 +255,8 @@
concurrently).
--------------------------------------------------------------------------------
-
-5) Represent and manage device memory from core kernel point of view
+Represent and manage device memory from core kernel point of view
+=================================================================
Several different designs were tried to support device memory. First one used
a device specific data structure to keep information about migrated memory and
@@ -280,14 +272,14 @@
map those pages from the CPU side.
HMM provides a set of helpers to register and hotplug device memory as a new
-region needing a struct page. This is offered through a very simple API:
+region needing a struct page. This is offered through a very simple API::
struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
struct device *device,
unsigned long size);
void hmm_devmem_remove(struct hmm_devmem *devmem);
-The hmm_devmem_ops is where most of the important things are:
+The hmm_devmem_ops is where most of the important things are::
struct hmm_devmem_ops {
void (*free)(struct hmm_devmem *devmem, struct page *page);
@@ -306,13 +298,12 @@
system memory.
--------------------------------------------------------------------------------
-
-6) Migration to and from device memory
+Migration to and from device memory
+===================================
Because the CPU cannot access device memory, migration must use the device DMA
engine to perform copy from and to device memory. For this we need a new
-migration helper:
+migration helper::
int migrate_vma(const struct migrate_vma_ops *ops,
struct vm_area_struct *vma,
@@ -331,7 +322,7 @@
The migrate_vma_ops struct defines two callbacks. First one (alloc_and_copy())
controls destination memory allocation and copy operation. Second one is there
-to allow the device driver to perform cleanup operations after migration.
+to allow the device driver to perform cleanup operations after migration::
struct migrate_vma_ops {
void (*alloc_and_copy)(struct vm_area_struct *vma,
@@ -365,9 +356,8 @@
willing to pay to keep all the code simpler.
--------------------------------------------------------------------------------
-
-7) Memory cgroup (memcg) and rss accounting
+Memory cgroup (memcg) and rss accounting
+========================================
For now device memory is accounted as any regular page in rss counters (either
anonymous if device page is used for anonymous, file if device page is used for
diff --git a/Documentation/vm/hugetlbfs_reserv.txt b/Documentation/vm/hugetlbfs_reserv.rst
similarity index 86%
rename from Documentation/vm/hugetlbfs_reserv.txt
rename to Documentation/vm/hugetlbfs_reserv.rst
index 9aca09a..9d20076 100644
--- a/Documentation/vm/hugetlbfs_reserv.txt
+++ b/Documentation/vm/hugetlbfs_reserv.rst
@@ -1,6 +1,13 @@
-Hugetlbfs Reservation Overview
-------------------------------
-Huge pages as described at 'Documentation/vm/hugetlbpage.txt' are typically
+.. _hugetlbfs_reserve:
+
+=====================
+Hugetlbfs Reservation
+=====================
+
+Overview
+========
+
+Huge pages as described at :ref:`hugetlbpage` are typically
preallocated for application use. These huge pages are instantiated in a
task's address space at page fault time if the VMA indicates huge pages are
to be used. If no huge page exists at page fault time, the task is sent
@@ -17,47 +24,55 @@
Audience
---------
+========
This description is primarily targeted at kernel developers who are modifying
hugetlbfs code.
The Data Structures
--------------------
+===================
+
resv_huge_pages
This is a global (per-hstate) count of reserved huge pages. Reserved
huge pages are only available to the task which reserved them.
Therefore, the number of huge pages generally available is computed
- as (free_huge_pages - resv_huge_pages).
+ as (``free_huge_pages - resv_huge_pages``).
Reserve Map
- A reserve map is described by the structure:
- struct resv_map {
- struct kref refs;
- spinlock_t lock;
- struct list_head regions;
- long adds_in_progress;
- struct list_head region_cache;
- long region_cache_count;
- };
+ A reserve map is described by the structure::
+
+ struct resv_map {
+ struct kref refs;
+ spinlock_t lock;
+ struct list_head regions;
+ long adds_in_progress;
+ struct list_head region_cache;
+ long region_cache_count;
+ };
+
There is one reserve map for each huge page mapping in the system.
The regions list within the resv_map describes the regions within
- the mapping. A region is described as:
- struct file_region {
- struct list_head link;
- long from;
- long to;
- };
+ the mapping. A region is described as::
+
+ struct file_region {
+ struct list_head link;
+ long from;
+ long to;
+ };
+
The 'from' and 'to' fields of the file region structure are huge page
indices into the mapping. Depending on the type of mapping, a
region in the reserv_map may indicate reservations exist for the
range, or reservations do not exist.
Flags for MAP_PRIVATE Reservations
These are stored in the bottom bits of the reservation map pointer.
- #define HPAGE_RESV_OWNER (1UL << 0) Indicates this task is the
- owner of the reservations associated with the mapping.
- #define HPAGE_RESV_UNMAPPED (1UL << 1) Indicates task originally
- mapping this range (and creating reserves) has unmapped a
- page from this task (the child) due to a failed COW.
+
+ ``#define HPAGE_RESV_OWNER (1UL << 0)``
+ Indicates this task is the owner of the reservations
+ associated with the mapping.
+ ``#define HPAGE_RESV_UNMAPPED (1UL << 1)``
+ Indicates task originally mapping this range (and creating
+ reserves) has unmapped a page from this task (the child)
+ due to a failed COW.
Page Flags
The PagePrivate page flag is used to indicate that a huge page
reservation must be restored when the huge page is freed. More
@@ -65,12 +80,14 @@
Reservation Map Location (Private or Shared)
---------------------------------------------
+============================================
+
A huge page mapping or segment is either private or shared. If private,
it is typically only available to a single address space (task). If shared,
it can be mapped into multiple address spaces (tasks). The location and
semantics of the reservation map is significantly different for two types
of mappings. Location differences are:
+
- For private mappings, the reservation map hangs off the the VMA structure.
Specifically, vma->vm_private_data. This reserve map is created at the
time the mapping (mmap(MAP_PRIVATE)) is created.
@@ -82,15 +99,15 @@
Creating Reservations
----------------------
+=====================
Reservations are created when a huge page backed shared memory segment is
created (shmget(SHM_HUGETLB)) or a mapping is created via mmap(MAP_HUGETLB).
-These operations result in a call to the routine hugetlb_reserve_pages()
+These operations result in a call to the routine hugetlb_reserve_pages()::
-int hugetlb_reserve_pages(struct inode *inode,
- long from, long to,
- struct vm_area_struct *vma,
- vm_flags_t vm_flags)
+ int hugetlb_reserve_pages(struct inode *inode,
+ long from, long to,
+ struct vm_area_struct *vma,
+ vm_flags_t vm_flags)
The first thing hugetlb_reserve_pages() does is check for the NORESERVE
flag was specified in either the shmget() or mmap() call. If NORESERVE
@@ -105,6 +122,7 @@
One of the big differences between PRIVATE and SHARED mappings is the way
in which reservations are represented in the reservation map.
+
- For shared mappings, an entry in the reservation map indicates a reservation
exists or did exist for the corresponding page. As reservations are
consumed, the reservation map is not modified.
@@ -121,12 +139,13 @@
The reservation map is consulted to determine how many huge page reservations
are needed for the current mapping/segment. For private mappings, this is
always the value (to - from). However, for shared mappings it is possible that some reservations may already exist within the range (to - from). See the
-section "Reservation Map Modifications" for details on how this is accomplished.
+section :ref:`Reservation Map Modifications <resv_map_modifications>`
+for details on how this is accomplished.
The mapping may be associated with a subpool. If so, the subpool is consulted
to ensure there is sufficient space for the mapping. It is possible that the
subpool has set aside reservations that can be used for the mapping. See the
-section "Subpool Reservations" for more details.
+section :ref:`Subpool Reservations <sub_pool_resv>` for more details.
After consulting the reservation map and subpool, the number of needed new
reservations is known. The routine hugetlb_acct_memory() is called to check
@@ -135,9 +154,11 @@
However, within those routines the code is simply checking to ensure there
are enough free huge pages to accommodate the reservation. If there are,
the global reservation count resv_huge_pages is adjusted something like the
-following.
+following::
+
if (resv_needed <= (resv_huge_pages - free_huge_pages))
resv_huge_pages += resv_needed;
+
Note that the global lock hugetlb_lock is held when checking and adjusting
these counters.
@@ -152,14 +173,18 @@
reservation map associated with the mapping will be modified as required to
ensure reservations exist for the range 'from' - 'to'.
+.. _consume_resv:
Consuming Reservations/Allocating a Huge Page
----------------------------------------------
+=============================================
+
Reservations are consumed when huge pages associated with the reservations
are allocated and instantiated in the corresponding mapping. The allocation
-is performed within the routine alloc_huge_page().
-struct page *alloc_huge_page(struct vm_area_struct *vma,
- unsigned long addr, int avoid_reserve)
+is performed within the routine alloc_huge_page()::
+
+ struct page *alloc_huge_page(struct vm_area_struct *vma,
+ unsigned long addr, int avoid_reserve)
+
alloc_huge_page is passed a VMA pointer and a virtual address, so it can
consult the reservation map to determine if a reservation exists. In addition,
alloc_huge_page takes the argument avoid_reserve which indicates reserves
@@ -170,8 +195,9 @@
The helper routine vma_needs_reservation() is called to determine if a
reservation exists for the address within the mapping(vma). See the section
-"Reservation Map Helper Routines" for detailed information on what this
-routine does. The value returned from vma_needs_reservation() is generally
+:ref:`Reservation Map Helper Routines <resv_map_helpers>` for detailed
+information on what this routine does.
+The value returned from vma_needs_reservation() is generally
0 or 1. 0 if a reservation exists for the address, 1 if no reservation exists.
If a reservation does not exist, and there is a subpool associated with the
mapping the subpool is consulted to determine if it contains reservations.
@@ -180,21 +206,25 @@
a reservation for the allocation. After determining whether a reservation
exists and can be used for the allocation, the routine dequeue_huge_page_vma()
is called. This routine takes two arguments related to reservations:
+
- avoid_reserve, this is the same value/argument passed to alloc_huge_page()
- chg, even though this argument is of type long only the values 0 or 1 are
passed to dequeue_huge_page_vma. If the value is 0, it indicates a
reservation exists (see the section "Memory Policy and Reservations" for
possible issues). If the value is 1, it indicates a reservation does not
exist and the page must be taken from the global free pool if possible.
+
The free lists associated with the memory policy of the VMA are searched for
a free page. If a page is found, the value free_huge_pages is decremented
when the page is removed from the free list. If there was a reservation
-associated with the page, the following adjustments are made:
+associated with the page, the following adjustments are made::
+
SetPagePrivate(page); /* Indicates allocating this page consumed
* a reservation, and if an error is
* encountered such that the page must be
* freed, the reservation will be restored. */
resv_huge_pages--; /* Decrement the global reservation count */
+
Note, if no huge page can be found that satisfies the VMA's memory policy
an attempt will be made to allocate one using the buddy allocator. This
brings up the issue of surplus huge pages and overcommit which is beyond
@@ -222,12 +252,14 @@
will be off by one. This rare condition can be identified by comparing the
return value from vma_needs_reservation and vma_commit_reservation. If such
a race is detected, the subpool and global reserve counts are adjusted to
-compensate. See the section "Reservation Map Helper Routines" for more
+compensate. See the section
+:ref:`Reservation Map Helper Routines <resv_map_helpers>` for more
information on these routines.
Instantiate Huge Pages
-----------------------
+======================
+
After huge page allocation, the page is typically added to the page tables
of the allocating task. Before this, pages in a shared mapping are added
to the page cache and pages in private mappings are added to an anonymous
@@ -237,7 +269,8 @@
Freeing Huge Pages
-------------------
+==================
+
Huge page freeing is performed by the routine free_huge_page(). This routine
is the destructor for hugetlbfs compound pages. As a result, it is only
passed a pointer to the page struct. When a huge page is freed, reservation
@@ -247,7 +280,8 @@
The page->private field points to any subpool associated with the page.
If the PagePrivate flag is set, it indicates the global reserve count should
-be adjusted (see the section "Consuming Reservations/Allocating a Huge Page"
+be adjusted (see the section
+:ref:`Consuming Reservations/Allocating a Huge Page <consume_resv>`
for information on how these are set).
The routine first calls hugepage_subpool_put_pages() for the page. If this
@@ -259,9 +293,11 @@
If the PagePrivate flag was set in the page, the global resv_huge_pages counter
will always be incremented.
+.. _sub_pool_resv:
Subpool Reservations
---------------------
+====================
+
There is a struct hstate associated with each huge page size. The hstate
tracks all huge pages of the specified size. A subpool represents a subset
of pages within a hstate that is associated with a mounted hugetlbfs
@@ -295,7 +331,8 @@
COW and Reservations
---------------------
+====================
+
Since shared mappings all point to and use the same underlying pages, the
biggest reservation concern for COW is private mappings. In this case,
two tasks can be pointing at the same previously allocated page. One task
@@ -326,30 +363,36 @@
mapping/reservation will behave as expected.
+.. _resv_map_modifications:
+
Reservation Map Modifications
------------------------------
+=============================
+
The following low level routines are used to make modifications to a
reservation map. Typically, these routines are not called directly. Rather,
a reservation map helper routine is called which calls one of these low level
routines. These low level routines are fairly well documented in the source
-code (mm/hugetlb.c). These routines are:
-long region_chg(struct resv_map *resv, long f, long t);
-long region_add(struct resv_map *resv, long f, long t);
-void region_abort(struct resv_map *resv, long f, long t);
-long region_count(struct resv_map *resv, long f, long t);
+code (mm/hugetlb.c). These routines are::
+
+ long region_chg(struct resv_map *resv, long f, long t);
+ long region_add(struct resv_map *resv, long f, long t);
+ void region_abort(struct resv_map *resv, long f, long t);
+ long region_count(struct resv_map *resv, long f, long t);
Operations on the reservation map typically involve two operations:
+
1) region_chg() is called to examine the reserve map and determine how
many pages in the specified range [f, t) are NOT currently represented.
The calling code performs global checks and allocations to determine if
there are enough huge pages for the operation to succeed.
-2a) If the operation can succeed, region_add() is called to actually modify
- the reservation map for the same range [f, t) previously passed to
- region_chg().
-2b) If the operation can not succeed, region_abort is called for the same range
- [f, t) to abort the operation.
+2)
+ a) If the operation can succeed, region_add() is called to actually modify
+ the reservation map for the same range [f, t) previously passed to
+ region_chg().
+ b) If the operation can not succeed, region_abort is called for the same
+ range [f, t) to abort the operation.
Note that this is a two step process where region_add() and region_abort()
are guaranteed to succeed after a prior call to region_chg() for the same
@@ -371,6 +414,7 @@
The routine region_del() is called to remove regions from a reservation map.
It is typically called in the following situations:
+
- When a file in the hugetlbfs filesystem is being removed, the inode will
be released and the reservation map freed. Before freeing the reservation
map, all the individual file_region structures must be freed. In this case
@@ -384,6 +428,7 @@
removed, region_del() is called to remove the corresponding entry from the
reservation map. In this case, region_del is passed the range
[page_idx, page_idx + 1).
+
In every case, region_del() will return the number of pages removed from the
reservation map. In VERY rare cases, region_del() can fail. This can only
happen in the hole punch case where it has to split an existing file_region
@@ -403,9 +448,11 @@
Since the mapping is going away, the subpool and global reservation counts
are decremented by the number of outstanding reservations.
+.. _resv_map_helpers:
Reservation Map Helper Routines
--------------------------------
+===============================
+
Several helper routines exist to query and modify the reservation maps.
These routines are only interested with reservations for a specific huge
page, so they just pass in an address instead of a range. In addition,
@@ -414,32 +461,40 @@
determined. These routines simply call the underlying routines described
in the section "Reservation Map Modifications". However, they do take into
account the 'opposite' meaning of reservation map entries for private and
-shared mappings and hide this detail from the caller.
+shared mappings and hide this detail from the caller::
-long vma_needs_reservation(struct hstate *h,
- struct vm_area_struct *vma, unsigned long addr)
+ long vma_needs_reservation(struct hstate *h,
+ struct vm_area_struct *vma,
+ unsigned long addr)
+
This routine calls region_chg() for the specified page. If no reservation
-exists, 1 is returned. If a reservation exists, 0 is returned.
+exists, 1 is returned. If a reservation exists, 0 is returned::
-long vma_commit_reservation(struct hstate *h,
- struct vm_area_struct *vma, unsigned long addr)
+ long vma_commit_reservation(struct hstate *h,
+ struct vm_area_struct *vma,
+ unsigned long addr)
+
This calls region_add() for the specified page. As in the case of region_chg
and region_add, this routine is to be called after a previous call to
vma_needs_reservation. It will add a reservation entry for the page. It
returns 1 if the reservation was added and 0 if not. The return value should
be compared with the return value of the previous call to
vma_needs_reservation. An unexpected difference indicates the reservation
-map was modified between calls.
+map was modified between calls::
-void vma_end_reservation(struct hstate *h,
- struct vm_area_struct *vma, unsigned long addr)
+ void vma_end_reservation(struct hstate *h,
+ struct vm_area_struct *vma,
+ unsigned long addr)
+
This calls region_abort() for the specified page. As in the case of region_chg
and region_abort, this routine is to be called after a previous call to
vma_needs_reservation. It will abort/end the in progress reservation add
-operation.
+operation::
-long vma_add_reservation(struct hstate *h,
- struct vm_area_struct *vma, unsigned long addr)
+ long vma_add_reservation(struct hstate *h,
+ struct vm_area_struct *vma,
+ unsigned long addr)
+
This is a special wrapper routine to help facilitate reservation cleanup
on error paths. It is only called from the routine restore_reserve_on_error().
This routine is used in conjunction with vma_needs_reservation in an attempt
@@ -453,8 +508,10 @@
Reservation Cleanup in Error Paths
-----------------------------------
-As mentioned in the section "Reservation Map Helper Routines", reservation
+==================================
+
+As mentioned in the section
+:ref:`Reservation Map Helper Routines <resv_map_helpers>`, reservation
map modifications are performed in two steps. First vma_needs_reservation
is called before a page is allocated. If the allocation is successful,
then vma_commit_reservation is called. If not, vma_end_reservation is called.
@@ -494,13 +551,14 @@
Reservations and Memory Policy
-------------------------------
+==============================
Per-node huge page lists existed in struct hstate when git was first used
to manage Linux code. The concept of reservations was added some time later.
When reservations were added, no attempt was made to take memory policy
into account. While cpusets are not exactly the same as memory policy, this
comment in hugetlb_acct_memory sums up the interaction between reservations
-and cpusets/memory policy.
+and cpusets/memory policy::
+
/*
* When cpuset is configured, it breaks the strict hugetlb page
* reservation as the accounting is done on a global variable. Such
@@ -525,5 +583,13 @@
available on the required nodes. This is true even if there are a sufficient
number of global reservations.
+Hugetlbfs regression testing
+============================
+The most complete set of hugetlb tests are in the libhugetlbfs repository.
+If you modify any hugetlb related code, use the libhugetlbfs test suite
+to check for regressions. In addition, if you add any new hugetlb
+functionality, please add appropriate tests to libhugetlbfs.
+
+--
Mike Kravetz, 7 April 2017
diff --git a/Documentation/vm/hwpoison.txt b/Documentation/vm/hwpoison.rst
similarity index 60%
rename from Documentation/vm/hwpoison.txt
rename to Documentation/vm/hwpoison.rst
index e912d7e..09bd24a 100644
--- a/Documentation/vm/hwpoison.txt
+++ b/Documentation/vm/hwpoison.rst
@@ -1,7 +1,14 @@
+.. hwpoison:
+
+========
+hwpoison
+========
+
What is hwpoison?
+=================
Upcoming Intel CPUs have support for recovering from some memory errors
-(``MCA recovery''). This requires the OS to declare a page "poisoned",
+(``MCA recovery``). This requires the OS to declare a page "poisoned",
kill the processes associated with it and avoid using it in the future.
This patchkit implements the necessary infrastructure in the VM.
@@ -46,9 +53,10 @@
memory failures too. The expection is that near all applications
won't do that, but some very specialized ones might.
----
+Failure recovery modes
+======================
-There are two (actually three) modi memory failure recovery can be in:
+There are two (actually three) modes memory failure recovery can be in:
vm.memory_failure_recovery sysctl set to zero:
All memory failures cause a panic. Do not attempt recovery.
@@ -67,9 +75,8 @@
This is best for memory error unaware applications and default
Note some pages are always handled as late kill.
----
-
-User control:
+User control
+============
vm.memory_failure_recovery
See sysctl.txt
@@ -79,11 +86,19 @@
PR_MCE_KILL
Set early/late kill mode/revert to system default
- arg1: PR_MCE_KILL_CLEAR: Revert to system default
- arg1: PR_MCE_KILL_SET: arg2 defines thread specific mode
- PR_MCE_KILL_EARLY: Early kill
- PR_MCE_KILL_LATE: Late kill
- PR_MCE_KILL_DEFAULT: Use system global default
+
+ arg1: PR_MCE_KILL_CLEAR:
+ Revert to system default
+ arg1: PR_MCE_KILL_SET:
+ arg2 defines thread specific mode
+
+ PR_MCE_KILL_EARLY:
+ Early kill
+ PR_MCE_KILL_LATE:
+ Late kill
+ PR_MCE_KILL_DEFAULT
+ Use system global default
+
Note that if you want to have a dedicated thread which handles
the SIGBUS(BUS_MCEERR_AO) on behalf of the process, you should
call prctl(PR_MCE_KILL_EARLY) on the designated thread. Otherwise,
@@ -92,77 +107,64 @@
PR_MCE_KILL_GET
return current mode
+Testing
+=======
----
+* madvise(MADV_HWPOISON, ....) (as root) - Poison a page in the
+ process for testing
-Testing:
+* hwpoison-inject module through debugfs ``/sys/kernel/debug/hwpoison/``
-madvise(MADV_HWPOISON, ....)
- (as root)
- Poison a page in the process for testing
+ corrupt-pfn
+ Inject hwpoison fault at PFN echoed into this file. This does
+ some early filtering to avoid corrupted unintended pages in test suites.
+ unpoison-pfn
+ Software-unpoison page at PFN echoed into this file. This way
+ a page can be reused again. This only works for Linux
+ injected failures, not for real memory failures.
-hwpoison-inject module through debugfs
+ Note these injection interfaces are not stable and might change between
+ kernel versions
-/sys/kernel/debug/hwpoison/
+ corrupt-filter-dev-major, corrupt-filter-dev-minor
+ Only handle memory failures to pages associated with the file
+ system defined by block device major/minor. -1U is the
+ wildcard value. This should be only used for testing with
+ artificial injection.
-corrupt-pfn
+ corrupt-filter-memcg
+ Limit injection to pages owned by memgroup. Specified by inode
+ number of the memcg.
-Inject hwpoison fault at PFN echoed into this file. This does
-some early filtering to avoid corrupted unintended pages in test suites.
+ Example::
-unpoison-pfn
+ mkdir /sys/fs/cgroup/mem/hwpoison
-Software-unpoison page at PFN echoed into this file. This
-way a page can be reused again.
-This only works for Linux injected failures, not for real
-memory failures.
+ usemem -m 100 -s 1000 &
+ echo `jobs -p` > /sys/fs/cgroup/mem/hwpoison/tasks
-Note these injection interfaces are not stable and might change between
-kernel versions
+ memcg_ino=$(ls -id /sys/fs/cgroup/mem/hwpoison | cut -f1 -d' ')
+ echo $memcg_ino > /debug/hwpoison/corrupt-filter-memcg
-corrupt-filter-dev-major
-corrupt-filter-dev-minor
+ page-types -p `pidof init` --hwpoison # shall do nothing
+ page-types -p `pidof usemem` --hwpoison # poison its pages
-Only handle memory failures to pages associated with the file system defined
-by block device major/minor. -1U is the wildcard value.
-This should be only used for testing with artificial injection.
+ corrupt-filter-flags-mask, corrupt-filter-flags-value
+ When specified, only poison pages if ((page_flags & mask) ==
+ value). This allows stress testing of many kinds of
+ pages. The page_flags are the same as in /proc/kpageflags. The
+ flag bits are defined in include/linux/kernel-page-flags.h and
+ documented in Documentation/admin-guide/mm/pagemap.rst
-corrupt-filter-memcg
+* Architecture specific MCE injector
-Limit injection to pages owned by memgroup. Specified by inode number
-of the memcg.
+ x86 has mce-inject, mce-test
-Example:
- mkdir /sys/fs/cgroup/mem/hwpoison
+ Some portable hwpoison test programs in mce-test, see below.
- usemem -m 100 -s 1000 &
- echo `jobs -p` > /sys/fs/cgroup/mem/hwpoison/tasks
-
- memcg_ino=$(ls -id /sys/fs/cgroup/mem/hwpoison | cut -f1 -d' ')
- echo $memcg_ino > /debug/hwpoison/corrupt-filter-memcg
-
- page-types -p `pidof init` --hwpoison # shall do nothing
- page-types -p `pidof usemem` --hwpoison # poison its pages
-
-corrupt-filter-flags-mask
-corrupt-filter-flags-value
-
-When specified, only poison pages if ((page_flags & mask) == value).
-This allows stress testing of many kinds of pages. The page_flags
-are the same as in /proc/kpageflags. The flag bits are defined in
-include/linux/kernel-page-flags.h and documented in
-Documentation/vm/pagemap.txt
-
-Architecture specific MCE injector
-
-x86 has mce-inject, mce-test
-
-Some portable hwpoison test programs in mce-test, see blow.
-
----
-
-References:
+References
+==========
http://halobates.de/mce-lc09-2.pdf
Overview presentation from LinuxCon 09
@@ -174,14 +176,11 @@
x86 specific injector
----
-
-Limitations:
-
+Limitations
+===========
- Not all page types are supported and never will. Most kernel internal
-objects cannot be recovered, only LRU pages for now.
+ objects cannot be recovered, only LRU pages for now.
- Right now hugepage support is missing.
---
Andi Kleen, Oct 2009
-
diff --git a/Documentation/vm/index.rst b/Documentation/vm/index.rst
new file mode 100644
index 0000000..c4ded22
--- /dev/null
+++ b/Documentation/vm/index.rst
@@ -0,0 +1,50 @@
+=====================================
+Linux Memory Management Documentation
+=====================================
+
+This is a collection of documents about Linux memory management (mm) subsystem.
+
+User guides for MM features
+===========================
+
+The following documents provide guides for controlling and tuning
+various features of the Linux memory management
+
+.. toctree::
+ :maxdepth: 1
+
+ swap_numa
+ zswap
+
+Kernel developers MM documentation
+==================================
+
+The below documents describe MM internals with different level of
+details ranging from notes and mailing list responses to elaborate
+descriptions of data structures and algorithms.
+
+.. toctree::
+ :maxdepth: 1
+
+ active_mm
+ balance
+ cleancache
+ frontswap
+ highmem
+ hmm
+ hwpoison
+ hugetlbfs_reserv
+ ksm
+ mmu_notifier
+ numa
+ overcommit-accounting
+ page_migration
+ page_frags
+ page_owner
+ remap_file_pages
+ slub
+ split_page_table_lock
+ transhuge
+ unevictable-lru
+ z3fold
+ zsmalloc
diff --git a/Documentation/vm/ksm.rst b/Documentation/vm/ksm.rst
new file mode 100644
index 0000000..d32016d
--- /dev/null
+++ b/Documentation/vm/ksm.rst
@@ -0,0 +1,87 @@
+.. _ksm:
+
+=======================
+Kernel Samepage Merging
+=======================
+
+KSM is a memory-saving de-duplication feature, enabled by CONFIG_KSM=y,
+added to the Linux kernel in 2.6.32. See ``mm/ksm.c`` for its implementation,
+and http://lwn.net/Articles/306704/ and http://lwn.net/Articles/330589/
+
+The userspace interface of KSM is described in :ref:`Documentation/admin-guide/mm/ksm.rst <admin_guide_ksm>`
+
+Design
+======
+
+Overview
+--------
+
+.. kernel-doc:: mm/ksm.c
+ :DOC: Overview
+
+Reverse mapping
+---------------
+KSM maintains reverse mapping information for KSM pages in the stable
+tree.
+
+If a KSM page is shared between less than ``max_page_sharing`` VMAs,
+the node of the stable tree that represents such KSM page points to a
+list of :c:type:`struct rmap_item` and the ``page->mapping`` of the
+KSM page points to the stable tree node.
+
+When the sharing passes this threshold, KSM adds a second dimension to
+the stable tree. The tree node becomes a "chain" that links one or
+more "dups". Each "dup" keeps reverse mapping information for a KSM
+page with ``page->mapping`` pointing to that "dup".
+
+Every "chain" and all "dups" linked into a "chain" enforce the
+invariant that they represent the same write protected memory content,
+even if each "dup" will be pointed by a different KSM page copy of
+that content.
+
+This way the stable tree lookup computational complexity is unaffected
+if compared to an unlimited list of reverse mappings. It is still
+enforced that there cannot be KSM page content duplicates in the
+stable tree itself.
+
+The deduplication limit enforced by ``max_page_sharing`` is required
+to avoid the virtual memory rmap lists to grow too large. The rmap
+walk has O(N) complexity where N is the number of rmap_items
+(i.e. virtual mappings) that are sharing the page, which is in turn
+capped by ``max_page_sharing``. So this effectively spreads the linear
+O(N) computational complexity from rmap walk context over different
+KSM pages. The ksmd walk over the stable_node "chains" is also O(N),
+but N is the number of stable_node "dups", not the number of
+rmap_items, so it has not a significant impact on ksmd performance. In
+practice the best stable_node "dup" candidate will be kept and found
+at the head of the "dups" list.
+
+High values of ``max_page_sharing`` result in faster memory merging
+(because there will be fewer stable_node dups queued into the
+stable_node chain->hlist to check for pruning) and higher
+deduplication factor at the expense of slower worst case for rmap
+walks for any KSM page which can happen during swapping, compaction,
+NUMA balancing and page migration.
+
+The ``stable_node_dups/stable_node_chains`` ratio is also affected by the
+``max_page_sharing`` tunable, and an high ratio may indicate fragmentation
+in the stable_node dups, which could be solved by introducing
+fragmentation algorithms in ksmd which would refile rmap_items from
+one stable_node dup to another stable_node dup, in order to free up
+stable_node "dups" with few rmap_items in them, but that may increase
+the ksmd CPU usage and possibly slowdown the readonly computations on
+the KSM pages of the applications.
+
+The whole list of stable_node "dups" linked in the stable_node
+"chains" is scanned periodically in order to prune stale stable_nodes.
+The frequency of such scans is defined by
+``stable_node_chains_prune_millisecs`` sysfs tunable.
+
+Reference
+---------
+.. kernel-doc:: mm/ksm.c
+ :functions: mm_slot ksm_scan stable_node rmap_item
+
+--
+Izik Eidus,
+Hugh Dickins, 17 Nov 2009
diff --git a/Documentation/vm/ksm.txt b/Documentation/vm/ksm.txt
deleted file mode 100644
index 6686bd2..0000000
--- a/Documentation/vm/ksm.txt
+++ /dev/null
@@ -1,178 +0,0 @@
-How to use the Kernel Samepage Merging feature
-----------------------------------------------
-
-KSM is a memory-saving de-duplication feature, enabled by CONFIG_KSM=y,
-added to the Linux kernel in 2.6.32. See mm/ksm.c for its implementation,
-and http://lwn.net/Articles/306704/ and http://lwn.net/Articles/330589/
-
-The KSM daemon ksmd periodically scans those areas of user memory which
-have been registered with it, looking for pages of identical content which
-can be replaced by a single write-protected page (which is automatically
-copied if a process later wants to update its content).
-
-KSM was originally developed for use with KVM (where it was known as
-Kernel Shared Memory), to fit more virtual machines into physical memory,
-by sharing the data common between them. But it can be useful to any
-application which generates many instances of the same data.
-
-KSM only merges anonymous (private) pages, never pagecache (file) pages.
-KSM's merged pages were originally locked into kernel memory, but can now
-be swapped out just like other user pages (but sharing is broken when they
-are swapped back in: ksmd must rediscover their identity and merge again).
-
-KSM only operates on those areas of address space which an application
-has advised to be likely candidates for merging, by using the madvise(2)
-system call: int madvise(addr, length, MADV_MERGEABLE).
-
-The app may call int madvise(addr, length, MADV_UNMERGEABLE) to cancel
-that advice and restore unshared pages: whereupon KSM unmerges whatever
-it merged in that range. Note: this unmerging call may suddenly require
-more memory than is available - possibly failing with EAGAIN, but more
-probably arousing the Out-Of-Memory killer.
-
-If KSM is not configured into the running kernel, madvise MADV_MERGEABLE
-and MADV_UNMERGEABLE simply fail with EINVAL. If the running kernel was
-built with CONFIG_KSM=y, those calls will normally succeed: even if the
-the KSM daemon is not currently running, MADV_MERGEABLE still registers
-the range for whenever the KSM daemon is started; even if the range
-cannot contain any pages which KSM could actually merge; even if
-MADV_UNMERGEABLE is applied to a range which was never MADV_MERGEABLE.
-
-If a region of memory must be split into at least one new MADV_MERGEABLE
-or MADV_UNMERGEABLE region, the madvise may return ENOMEM if the process
-will exceed vm.max_map_count (see Documentation/sysctl/vm.txt).
-
-Like other madvise calls, they are intended for use on mapped areas of
-the user address space: they will report ENOMEM if the specified range
-includes unmapped gaps (though working on the intervening mapped areas),
-and might fail with EAGAIN if not enough memory for internal structures.
-
-Applications should be considerate in their use of MADV_MERGEABLE,
-restricting its use to areas likely to benefit. KSM's scans may use a lot
-of processing power: some installations will disable KSM for that reason.
-
-The KSM daemon is controlled by sysfs files in /sys/kernel/mm/ksm/,
-readable by all but writable only by root:
-
-pages_to_scan - how many present pages to scan before ksmd goes to sleep
- e.g. "echo 100 > /sys/kernel/mm/ksm/pages_to_scan"
- Default: 100 (chosen for demonstration purposes)
-
-sleep_millisecs - how many milliseconds ksmd should sleep before next scan
- e.g. "echo 20 > /sys/kernel/mm/ksm/sleep_millisecs"
- Default: 20 (chosen for demonstration purposes)
-
-merge_across_nodes - specifies if pages from different numa nodes can be merged.
- When set to 0, ksm merges only pages which physically
- reside in the memory area of same NUMA node. That brings
- lower latency to access of shared pages. Systems with more
- nodes, at significant NUMA distances, are likely to benefit
- from the lower latency of setting 0. Smaller systems, which
- need to minimize memory usage, are likely to benefit from
- the greater sharing of setting 1 (default). You may wish to
- compare how your system performs under each setting, before
- deciding on which to use. merge_across_nodes setting can be
- changed only when there are no ksm shared pages in system:
- set run 2 to unmerge pages first, then to 1 after changing
- merge_across_nodes, to remerge according to the new setting.
- Default: 1 (merging across nodes as in earlier releases)
-
-run - set 0 to stop ksmd from running but keep merged pages,
- set 1 to run ksmd e.g. "echo 1 > /sys/kernel/mm/ksm/run",
- set 2 to stop ksmd and unmerge all pages currently merged,
- but leave mergeable areas registered for next run
- Default: 0 (must be changed to 1 to activate KSM,
- except if CONFIG_SYSFS is disabled)
-
-use_zero_pages - specifies whether empty pages (i.e. allocated pages
- that only contain zeroes) should be treated specially.
- When set to 1, empty pages are merged with the kernel
- zero page(s) instead of with each other as it would
- happen normally. This can improve the performance on
- architectures with coloured zero pages, depending on
- the workload. Care should be taken when enabling this
- setting, as it can potentially degrade the performance
- of KSM for some workloads, for example if the checksums
- of pages candidate for merging match the checksum of
- an empty page. This setting can be changed at any time,
- it is only effective for pages merged after the change.
- Default: 0 (normal KSM behaviour as in earlier releases)
-
-max_page_sharing - Maximum sharing allowed for each KSM page. This
- enforces a deduplication limit to avoid the virtual
- memory rmap lists to grow too large. The minimum
- value is 2 as a newly created KSM page will have at
- least two sharers. The rmap walk has O(N)
- complexity where N is the number of rmap_items
- (i.e. virtual mappings) that are sharing the page,
- which is in turn capped by max_page_sharing. So
- this effectively spread the the linear O(N)
- computational complexity from rmap walk context
- over different KSM pages. The ksmd walk over the
- stable_node "chains" is also O(N), but N is the
- number of stable_node "dups", not the number of
- rmap_items, so it has not a significant impact on
- ksmd performance. In practice the best stable_node
- "dup" candidate will be kept and found at the head
- of the "dups" list. The higher this value the
- faster KSM will merge the memory (because there
- will be fewer stable_node dups queued into the
- stable_node chain->hlist to check for pruning) and
- the higher the deduplication factor will be, but
- the slowest the worst case rmap walk could be for
- any given KSM page. Slowing down the rmap_walk
- means there will be higher latency for certain
- virtual memory operations happening during
- swapping, compaction, NUMA balancing and page
- migration, in turn decreasing responsiveness for
- the caller of those virtual memory operations. The
- scheduler latency of other tasks not involved with
- the VM operations doing the rmap walk is not
- affected by this parameter as the rmap walks are
- always schedule friendly themselves.
-
-stable_node_chains_prune_millisecs - How frequently to walk the whole
- list of stable_node "dups" linked in the
- stable_node "chains" in order to prune stale
- stable_nodes. Smaller milllisecs values will free
- up the KSM metadata with lower latency, but they
- will make ksmd use more CPU during the scan. This
- only applies to the stable_node chains so it's a
- noop if not a single KSM page hit the
- max_page_sharing yet (there would be no stable_node
- chains in such case).
-
-The effectiveness of KSM and MADV_MERGEABLE is shown in /sys/kernel/mm/ksm/:
-
-pages_shared - how many shared pages are being used
-pages_sharing - how many more sites are sharing them i.e. how much saved
-pages_unshared - how many pages unique but repeatedly checked for merging
-pages_volatile - how many pages changing too fast to be placed in a tree
-full_scans - how many times all mergeable areas have been scanned
-
-stable_node_chains - number of stable node chains allocated, this is
- effectively the number of KSM pages that hit the
- max_page_sharing limit
-stable_node_dups - number of stable node dups queued into the
- stable_node chains
-
-A high ratio of pages_sharing to pages_shared indicates good sharing, but
-a high ratio of pages_unshared to pages_sharing indicates wasted effort.
-pages_volatile embraces several different kinds of activity, but a high
-proportion there would also indicate poor use of madvise MADV_MERGEABLE.
-
-The maximum possible page_sharing/page_shared ratio is limited by the
-max_page_sharing tunable. To increase the ratio max_page_sharing must
-be increased accordingly.
-
-The stable_node_dups/stable_node_chains ratio is also affected by the
-max_page_sharing tunable, and an high ratio may indicate fragmentation
-in the stable_node dups, which could be solved by introducing
-fragmentation algorithms in ksmd which would refile rmap_items from
-one stable_node dup to another stable_node dup, in order to freeup
-stable_node "dups" with few rmap_items in them, but that may increase
-the ksmd CPU usage and possibly slowdown the readonly computations on
-the KSM pages of the applications.
-
-Izik Eidus,
-Hugh Dickins, 17 Nov 2009
diff --git a/Documentation/vm/mmu_notifier.rst b/Documentation/vm/mmu_notifier.rst
new file mode 100644
index 0000000..47baa1c
--- /dev/null
+++ b/Documentation/vm/mmu_notifier.rst
@@ -0,0 +1,99 @@
+.. _mmu_notifier:
+
+When do you need to notify inside page table lock ?
+===================================================
+
+When clearing a pte/pmd we are given a choice to notify the event through
+(notify version of \*_clear_flush call mmu_notifier_invalidate_range) under
+the page table lock. But that notification is not necessary in all cases.
+
+For secondary TLB (non CPU TLB) like IOMMU TLB or device TLB (when device use
+thing like ATS/PASID to get the IOMMU to walk the CPU page table to access a
+process virtual address space). There is only 2 cases when you need to notify
+those secondary TLB while holding page table lock when clearing a pte/pmd:
+
+ A) page backing address is free before mmu_notifier_invalidate_range_end()
+ B) a page table entry is updated to point to a new page (COW, write fault
+ on zero page, __replace_page(), ...)
+
+Case A is obvious you do not want to take the risk for the device to write to
+a page that might now be used by some completely different task.
+
+Case B is more subtle. For correctness it requires the following sequence to
+happen:
+
+ - take page table lock
+ - clear page table entry and notify ([pmd/pte]p_huge_clear_flush_notify())
+ - set page table entry to point to new page
+
+If clearing the page table entry is not followed by a notify before setting
+the new pte/pmd value then you can break memory model like C11 or C++11 for
+the device.
+
+Consider the following scenario (device use a feature similar to ATS/PASID):
+
+Two address addrA and addrB such that \|addrA - addrB\| >= PAGE_SIZE we assume
+they are write protected for COW (other case of B apply too).
+
+::
+
+ [Time N] --------------------------------------------------------------------
+ CPU-thread-0 {try to write to addrA}
+ CPU-thread-1 {try to write to addrB}
+ CPU-thread-2 {}
+ CPU-thread-3 {}
+ DEV-thread-0 {read addrA and populate device TLB}
+ DEV-thread-2 {read addrB and populate device TLB}
+ [Time N+1] ------------------------------------------------------------------
+ CPU-thread-0 {COW_step0: {mmu_notifier_invalidate_range_start(addrA)}}
+ CPU-thread-1 {COW_step0: {mmu_notifier_invalidate_range_start(addrB)}}
+ CPU-thread-2 {}
+ CPU-thread-3 {}
+ DEV-thread-0 {}
+ DEV-thread-2 {}
+ [Time N+2] ------------------------------------------------------------------
+ CPU-thread-0 {COW_step1: {update page table to point to new page for addrA}}
+ CPU-thread-1 {COW_step1: {update page table to point to new page for addrB}}
+ CPU-thread-2 {}
+ CPU-thread-3 {}
+ DEV-thread-0 {}
+ DEV-thread-2 {}
+ [Time N+3] ------------------------------------------------------------------
+ CPU-thread-0 {preempted}
+ CPU-thread-1 {preempted}
+ CPU-thread-2 {write to addrA which is a write to new page}
+ CPU-thread-3 {}
+ DEV-thread-0 {}
+ DEV-thread-2 {}
+ [Time N+3] ------------------------------------------------------------------
+ CPU-thread-0 {preempted}
+ CPU-thread-1 {preempted}
+ CPU-thread-2 {}
+ CPU-thread-3 {write to addrB which is a write to new page}
+ DEV-thread-0 {}
+ DEV-thread-2 {}
+ [Time N+4] ------------------------------------------------------------------
+ CPU-thread-0 {preempted}
+ CPU-thread-1 {COW_step3: {mmu_notifier_invalidate_range_end(addrB)}}
+ CPU-thread-2 {}
+ CPU-thread-3 {}
+ DEV-thread-0 {}
+ DEV-thread-2 {}
+ [Time N+5] ------------------------------------------------------------------
+ CPU-thread-0 {preempted}
+ CPU-thread-1 {}
+ CPU-thread-2 {}
+ CPU-thread-3 {}
+ DEV-thread-0 {read addrA from old page}
+ DEV-thread-2 {read addrB from new page}
+
+So here because at time N+2 the clear page table entry was not pair with a
+notification to invalidate the secondary TLB, the device see the new value for
+addrB before seing the new value for addrA. This break total memory ordering
+for the device.
+
+When changing a pte to write protect or to point to a new write protected page
+with same content (KSM) it is fine to delay the mmu_notifier_invalidate_range
+call to mmu_notifier_invalidate_range_end() outside the page table lock. This
+is true even if the thread doing the page table update is preempted right after
+releasing page table lock but before call mmu_notifier_invalidate_range_end().
diff --git a/Documentation/vm/mmu_notifier.txt b/Documentation/vm/mmu_notifier.txt
deleted file mode 100644
index 23b4625..0000000
--- a/Documentation/vm/mmu_notifier.txt
+++ /dev/null
@@ -1,93 +0,0 @@
-When do you need to notify inside page table lock ?
-
-When clearing a pte/pmd we are given a choice to notify the event through
-(notify version of *_clear_flush call mmu_notifier_invalidate_range) under
-the page table lock. But that notification is not necessary in all cases.
-
-For secondary TLB (non CPU TLB) like IOMMU TLB or device TLB (when device use
-thing like ATS/PASID to get the IOMMU to walk the CPU page table to access a
-process virtual address space). There is only 2 cases when you need to notify
-those secondary TLB while holding page table lock when clearing a pte/pmd:
-
- A) page backing address is free before mmu_notifier_invalidate_range_end()
- B) a page table entry is updated to point to a new page (COW, write fault
- on zero page, __replace_page(), ...)
-
-Case A is obvious you do not want to take the risk for the device to write to
-a page that might now be used by some completely different task.
-
-Case B is more subtle. For correctness it requires the following sequence to
-happen:
- - take page table lock
- - clear page table entry and notify ([pmd/pte]p_huge_clear_flush_notify())
- - set page table entry to point to new page
-
-If clearing the page table entry is not followed by a notify before setting
-the new pte/pmd value then you can break memory model like C11 or C++11 for
-the device.
-
-Consider the following scenario (device use a feature similar to ATS/PASID):
-
-Two address addrA and addrB such that |addrA - addrB| >= PAGE_SIZE we assume
-they are write protected for COW (other case of B apply too).
-
-[Time N] --------------------------------------------------------------------
-CPU-thread-0 {try to write to addrA}
-CPU-thread-1 {try to write to addrB}
-CPU-thread-2 {}
-CPU-thread-3 {}
-DEV-thread-0 {read addrA and populate device TLB}
-DEV-thread-2 {read addrB and populate device TLB}
-[Time N+1] ------------------------------------------------------------------
-CPU-thread-0 {COW_step0: {mmu_notifier_invalidate_range_start(addrA)}}
-CPU-thread-1 {COW_step0: {mmu_notifier_invalidate_range_start(addrB)}}
-CPU-thread-2 {}
-CPU-thread-3 {}
-DEV-thread-0 {}
-DEV-thread-2 {}
-[Time N+2] ------------------------------------------------------------------
-CPU-thread-0 {COW_step1: {update page table to point to new page for addrA}}
-CPU-thread-1 {COW_step1: {update page table to point to new page for addrB}}
-CPU-thread-2 {}
-CPU-thread-3 {}
-DEV-thread-0 {}
-DEV-thread-2 {}
-[Time N+3] ------------------------------------------------------------------
-CPU-thread-0 {preempted}
-CPU-thread-1 {preempted}
-CPU-thread-2 {write to addrA which is a write to new page}
-CPU-thread-3 {}
-DEV-thread-0 {}
-DEV-thread-2 {}
-[Time N+3] ------------------------------------------------------------------
-CPU-thread-0 {preempted}
-CPU-thread-1 {preempted}
-CPU-thread-2 {}
-CPU-thread-3 {write to addrB which is a write to new page}
-DEV-thread-0 {}
-DEV-thread-2 {}
-[Time N+4] ------------------------------------------------------------------
-CPU-thread-0 {preempted}
-CPU-thread-1 {COW_step3: {mmu_notifier_invalidate_range_end(addrB)}}
-CPU-thread-2 {}
-CPU-thread-3 {}
-DEV-thread-0 {}
-DEV-thread-2 {}
-[Time N+5] ------------------------------------------------------------------
-CPU-thread-0 {preempted}
-CPU-thread-1 {}
-CPU-thread-2 {}
-CPU-thread-3 {}
-DEV-thread-0 {read addrA from old page}
-DEV-thread-2 {read addrB from new page}
-
-So here because at time N+2 the clear page table entry was not pair with a
-notification to invalidate the secondary TLB, the device see the new value for
-addrB before seing the new value for addrA. This break total memory ordering
-for the device.
-
-When changing a pte to write protect or to point to a new write protected page
-with same content (KSM) it is fine to delay the mmu_notifier_invalidate_range
-call to mmu_notifier_invalidate_range_end() outside the page table lock. This
-is true even if the thread doing the page table update is preempted right after
-releasing page table lock but before call mmu_notifier_invalidate_range_end().
diff --git a/Documentation/vm/numa b/Documentation/vm/numa.rst
similarity index 98%
rename from Documentation/vm/numa
rename to Documentation/vm/numa.rst
index a31b85b..185d8a5 100644
--- a/Documentation/vm/numa
+++ b/Documentation/vm/numa.rst
@@ -1,6 +1,10 @@
+.. _numa:
+
Started Nov 1999 by Kanoj Sarcar <kanoj@sgi.com>
+=============
What is NUMA?
+=============
This question can be answered from a couple of perspectives: the
hardware view and the Linux software view.
@@ -106,7 +110,7 @@
such as taskset(1) and numactl(1), and program interfaces such as
sched_setaffinity(2). Further, one can modify the kernel's default local
allocation behavior using Linux NUMA memory policy.
-[see Documentation/vm/numa_memory_policy.txt.]
+[see Documentation/admin-guide/mm/numa_memory_policy.rst.]
System administrators can restrict the CPUs and nodes' memories that a non-
privileged user can specify in the scheduling or NUMA commands and functions
diff --git a/Documentation/vm/numa_memory_policy.txt b/Documentation/vm/numa_memory_policy.txt
deleted file mode 100644
index 622b927..0000000
--- a/Documentation/vm/numa_memory_policy.txt
+++ /dev/null
@@ -1,452 +0,0 @@
-
-What is Linux Memory Policy?
-
-In the Linux kernel, "memory policy" determines from which node the kernel will
-allocate memory in a NUMA system or in an emulated NUMA system. Linux has
-supported platforms with Non-Uniform Memory Access architectures since 2.4.?.
-The current memory policy support was added to Linux 2.6 around May 2004. This
-document attempts to describe the concepts and APIs of the 2.6 memory policy
-support.
-
-Memory policies should not be confused with cpusets
-(Documentation/cgroup-v1/cpusets.txt)
-which is an administrative mechanism for restricting the nodes from which
-memory may be allocated by a set of processes. Memory policies are a
-programming interface that a NUMA-aware application can take advantage of. When
-both cpusets and policies are applied to a task, the restrictions of the cpuset
-takes priority. See "MEMORY POLICIES AND CPUSETS" below for more details.
-
-MEMORY POLICY CONCEPTS
-
-Scope of Memory Policies
-
-The Linux kernel supports _scopes_ of memory policy, described here from
-most general to most specific:
-
- System Default Policy: this policy is "hard coded" into the kernel. It
- is the policy that governs all page allocations that aren't controlled
- by one of the more specific policy scopes discussed below. When the
- system is "up and running", the system default policy will use "local
- allocation" described below. However, during boot up, the system
- default policy will be set to interleave allocations across all nodes
- with "sufficient" memory, so as not to overload the initial boot node
- with boot-time allocations.
-
- Task/Process Policy: this is an optional, per-task policy. When defined
- for a specific task, this policy controls all page allocations made by or
- on behalf of the task that aren't controlled by a more specific scope.
- If a task does not define a task policy, then all page allocations that
- would have been controlled by the task policy "fall back" to the System
- Default Policy.
-
- The task policy applies to the entire address space of a task. Thus,
- it is inheritable, and indeed is inherited, across both fork()
- [clone() w/o the CLONE_VM flag] and exec*(). This allows a parent task
- to establish the task policy for a child task exec()'d from an
- executable image that has no awareness of memory policy. See the
- MEMORY POLICY APIS section, below, for an overview of the system call
- that a task may use to set/change its task/process policy.
-
- In a multi-threaded task, task policies apply only to the thread
- [Linux kernel task] that installs the policy and any threads
- subsequently created by that thread. Any sibling threads existing
- at the time a new task policy is installed retain their current
- policy.
-
- A task policy applies only to pages allocated after the policy is
- installed. Any pages already faulted in by the task when the task
- changes its task policy remain where they were allocated based on
- the policy at the time they were allocated.
-
- VMA Policy: A "VMA" or "Virtual Memory Area" refers to a range of a task's
- virtual address space. A task may define a specific policy for a range
- of its virtual address space. See the MEMORY POLICIES APIS section,
- below, for an overview of the mbind() system call used to set a VMA
- policy.
-
- A VMA policy will govern the allocation of pages that back this region of
- the address space. Any regions of the task's address space that don't
- have an explicit VMA policy will fall back to the task policy, which may
- itself fall back to the System Default Policy.
-
- VMA policies have a few complicating details:
-
- VMA policy applies ONLY to anonymous pages. These include pages
- allocated for anonymous segments, such as the task stack and heap, and
- any regions of the address space mmap()ed with the MAP_ANONYMOUS flag.
- If a VMA policy is applied to a file mapping, it will be ignored if
- the mapping used the MAP_SHARED flag. If the file mapping used the
- MAP_PRIVATE flag, the VMA policy will only be applied when an
- anonymous page is allocated on an attempt to write to the mapping--
- i.e., at Copy-On-Write.
-
- VMA policies are shared between all tasks that share a virtual address
- space--a.k.a. threads--independent of when the policy is installed; and
- they are inherited across fork(). However, because VMA policies refer
- to a specific region of a task's address space, and because the address
- space is discarded and recreated on exec*(), VMA policies are NOT
- inheritable across exec(). Thus, only NUMA-aware applications may
- use VMA policies.
-
- A task may install a new VMA policy on a sub-range of a previously
- mmap()ed region. When this happens, Linux splits the existing virtual
- memory area into 2 or 3 VMAs, each with it's own policy.
-
- By default, VMA policy applies only to pages allocated after the policy
- is installed. Any pages already faulted into the VMA range remain
- where they were allocated based on the policy at the time they were
- allocated. However, since 2.6.16, Linux supports page migration via
- the mbind() system call, so that page contents can be moved to match
- a newly installed policy.
-
- Shared Policy: Conceptually, shared policies apply to "memory objects"
- mapped shared into one or more tasks' distinct address spaces. An
- application installs a shared policies the same way as VMA policies--using
- the mbind() system call specifying a range of virtual addresses that map
- the shared object. However, unlike VMA policies, which can be considered
- to be an attribute of a range of a task's address space, shared policies
- apply directly to the shared object. Thus, all tasks that attach to the
- object share the policy, and all pages allocated for the shared object,
- by any task, will obey the shared policy.
-
- As of 2.6.22, only shared memory segments, created by shmget() or
- mmap(MAP_ANONYMOUS|MAP_SHARED), support shared policy. When shared
- policy support was added to Linux, the associated data structures were
- added to hugetlbfs shmem segments. At the time, hugetlbfs did not
- support allocation at fault time--a.k.a lazy allocation--so hugetlbfs
- shmem segments were never "hooked up" to the shared policy support.
- Although hugetlbfs segments now support lazy allocation, their support
- for shared policy has not been completed.
-
- As mentioned above [re: VMA policies], allocations of page cache
- pages for regular files mmap()ed with MAP_SHARED ignore any VMA
- policy installed on the virtual address range backed by the shared
- file mapping. Rather, shared page cache pages, including pages backing
- private mappings that have not yet been written by the task, follow
- task policy, if any, else System Default Policy.
-
- The shared policy infrastructure supports different policies on subset
- ranges of the shared object. However, Linux still splits the VMA of
- the task that installs the policy for each range of distinct policy.
- Thus, different tasks that attach to a shared memory segment can have
- different VMA configurations mapping that one shared object. This
- can be seen by examining the /proc/<pid>/numa_maps of tasks sharing
- a shared memory region, when one task has installed shared policy on
- one or more ranges of the region.
-
-Components of Memory Policies
-
- A Linux memory policy consists of a "mode", optional mode flags, and an
- optional set of nodes. The mode determines the behavior of the policy,
- the optional mode flags determine the behavior of the mode, and the
- optional set of nodes can be viewed as the arguments to the policy
- behavior.
-
- Internally, memory policies are implemented by a reference counted
- structure, struct mempolicy. Details of this structure will be discussed
- in context, below, as required to explain the behavior.
-
- Linux memory policy supports the following 4 behavioral modes:
-
- Default Mode--MPOL_DEFAULT: This mode is only used in the memory
- policy APIs. Internally, MPOL_DEFAULT is converted to the NULL
- memory policy in all policy scopes. Any existing non-default policy
- will simply be removed when MPOL_DEFAULT is specified. As a result,
- MPOL_DEFAULT means "fall back to the next most specific policy scope."
-
- For example, a NULL or default task policy will fall back to the
- system default policy. A NULL or default vma policy will fall
- back to the task policy.
-
- When specified in one of the memory policy APIs, the Default mode
- does not use the optional set of nodes.
-
- It is an error for the set of nodes specified for this policy to
- be non-empty.
-
- MPOL_BIND: This mode specifies that memory must come from the
- set of nodes specified by the policy. Memory will be allocated from
- the node in the set with sufficient free memory that is closest to
- the node where the allocation takes place.
-
- MPOL_PREFERRED: This mode specifies that the allocation should be
- attempted from the single node specified in the policy. If that
- allocation fails, the kernel will search other nodes, in order of
- increasing distance from the preferred node based on information
- provided by the platform firmware.
-
- Internally, the Preferred policy uses a single node--the
- preferred_node member of struct mempolicy. When the internal
- mode flag MPOL_F_LOCAL is set, the preferred_node is ignored and
- the policy is interpreted as local allocation. "Local" allocation
- policy can be viewed as a Preferred policy that starts at the node
- containing the cpu where the allocation takes place.
-
- It is possible for the user to specify that local allocation is
- always preferred by passing an empty nodemask with this mode.
- If an empty nodemask is passed, the policy cannot use the
- MPOL_F_STATIC_NODES or MPOL_F_RELATIVE_NODES flags described
- below.
-
- MPOL_INTERLEAVED: This mode specifies that page allocations be
- interleaved, on a page granularity, across the nodes specified in
- the policy. This mode also behaves slightly differently, based on
- the context where it is used:
-
- For allocation of anonymous pages and shared memory pages,
- Interleave mode indexes the set of nodes specified by the policy
- using the page offset of the faulting address into the segment
- [VMA] containing the address modulo the number of nodes specified
- by the policy. It then attempts to allocate a page, starting at
- the selected node, as if the node had been specified by a Preferred
- policy or had been selected by a local allocation. That is,
- allocation will follow the per node zonelist.
-
- For allocation of page cache pages, Interleave mode indexes the set
- of nodes specified by the policy using a node counter maintained
- per task. This counter wraps around to the lowest specified node
- after it reaches the highest specified node. This will tend to
- spread the pages out over the nodes specified by the policy based
- on the order in which they are allocated, rather than based on any
- page offset into an address range or file. During system boot up,
- the temporary interleaved system default policy works in this
- mode.
-
- Linux memory policy supports the following optional mode flags:
-
- MPOL_F_STATIC_NODES: This flag specifies that the nodemask passed by
- the user should not be remapped if the task or VMA's set of allowed
- nodes changes after the memory policy has been defined.
-
- Without this flag, anytime a mempolicy is rebound because of a
- change in the set of allowed nodes, the node (Preferred) or
- nodemask (Bind, Interleave) is remapped to the new set of
- allowed nodes. This may result in nodes being used that were
- previously undesired.
-
- With this flag, if the user-specified nodes overlap with the
- nodes allowed by the task's cpuset, then the memory policy is
- applied to their intersection. If the two sets of nodes do not
- overlap, the Default policy is used.
-
- For example, consider a task that is attached to a cpuset with
- mems 1-3 that sets an Interleave policy over the same set. If
- the cpuset's mems change to 3-5, the Interleave will now occur
- over nodes 3, 4, and 5. With this flag, however, since only node
- 3 is allowed from the user's nodemask, the "interleave" only
- occurs over that node. If no nodes from the user's nodemask are
- now allowed, the Default behavior is used.
-
- MPOL_F_STATIC_NODES cannot be combined with the
- MPOL_F_RELATIVE_NODES flag. It also cannot be used for
- MPOL_PREFERRED policies that were created with an empty nodemask
- (local allocation).
-
- MPOL_F_RELATIVE_NODES: This flag specifies that the nodemask passed
- by the user will be mapped relative to the set of the task or VMA's
- set of allowed nodes. The kernel stores the user-passed nodemask,
- and if the allowed nodes changes, then that original nodemask will
- be remapped relative to the new set of allowed nodes.
-
- Without this flag (and without MPOL_F_STATIC_NODES), anytime a
- mempolicy is rebound because of a change in the set of allowed
- nodes, the node (Preferred) or nodemask (Bind, Interleave) is
- remapped to the new set of allowed nodes. That remap may not
- preserve the relative nature of the user's passed nodemask to its
- set of allowed nodes upon successive rebinds: a nodemask of
- 1,3,5 may be remapped to 7-9 and then to 1-3 if the set of
- allowed nodes is restored to its original state.
-
- With this flag, the remap is done so that the node numbers from
- the user's passed nodemask are relative to the set of allowed
- nodes. In other words, if nodes 0, 2, and 4 are set in the user's
- nodemask, the policy will be effected over the first (and in the
- Bind or Interleave case, the third and fifth) nodes in the set of
- allowed nodes. The nodemask passed by the user represents nodes
- relative to task or VMA's set of allowed nodes.
-
- If the user's nodemask includes nodes that are outside the range
- of the new set of allowed nodes (for example, node 5 is set in
- the user's nodemask when the set of allowed nodes is only 0-3),
- then the remap wraps around to the beginning of the nodemask and,
- if not already set, sets the node in the mempolicy nodemask.
-
- For example, consider a task that is attached to a cpuset with
- mems 2-5 that sets an Interleave policy over the same set with
- MPOL_F_RELATIVE_NODES. If the cpuset's mems change to 3-7, the
- interleave now occurs over nodes 3,5-7. If the cpuset's mems
- then change to 0,2-3,5, then the interleave occurs over nodes
- 0,2-3,5.
-
- Thanks to the consistent remapping, applications preparing
- nodemasks to specify memory policies using this flag should
- disregard their current, actual cpuset imposed memory placement
- and prepare the nodemask as if they were always located on
- memory nodes 0 to N-1, where N is the number of memory nodes the
- policy is intended to manage. Let the kernel then remap to the
- set of memory nodes allowed by the task's cpuset, as that may
- change over time.
-
- MPOL_F_RELATIVE_NODES cannot be combined with the
- MPOL_F_STATIC_NODES flag. It also cannot be used for
- MPOL_PREFERRED policies that were created with an empty nodemask
- (local allocation).
-
-MEMORY POLICY REFERENCE COUNTING
-
-To resolve use/free races, struct mempolicy contains an atomic reference
-count field. Internal interfaces, mpol_get()/mpol_put() increment and
-decrement this reference count, respectively. mpol_put() will only free
-the structure back to the mempolicy kmem cache when the reference count
-goes to zero.
-
-When a new memory policy is allocated, its reference count is initialized
-to '1', representing the reference held by the task that is installing the
-new policy. When a pointer to a memory policy structure is stored in another
-structure, another reference is added, as the task's reference will be dropped
-on completion of the policy installation.
-
-During run-time "usage" of the policy, we attempt to minimize atomic operations
-on the reference count, as this can lead to cache lines bouncing between cpus
-and NUMA nodes. "Usage" here means one of the following:
-
-1) querying of the policy, either by the task itself [using the get_mempolicy()
- API discussed below] or by another task using the /proc/<pid>/numa_maps
- interface.
-
-2) examination of the policy to determine the policy mode and associated node
- or node lists, if any, for page allocation. This is considered a "hot
- path". Note that for MPOL_BIND, the "usage" extends across the entire
- allocation process, which may sleep during page reclaimation, because the
- BIND policy nodemask is used, by reference, to filter ineligible nodes.
-
-We can avoid taking an extra reference during the usages listed above as
-follows:
-
-1) we never need to get/free the system default policy as this is never
- changed nor freed, once the system is up and running.
-
-2) for querying the policy, we do not need to take an extra reference on the
- target task's task policy nor vma policies because we always acquire the
- task's mm's mmap_sem for read during the query. The set_mempolicy() and
- mbind() APIs [see below] always acquire the mmap_sem for write when
- installing or replacing task or vma policies. Thus, there is no possibility
- of a task or thread freeing a policy while another task or thread is
- querying it.
-
-3) Page allocation usage of task or vma policy occurs in the fault path where
- we hold them mmap_sem for read. Again, because replacing the task or vma
- policy requires that the mmap_sem be held for write, the policy can't be
- freed out from under us while we're using it for page allocation.
-
-4) Shared policies require special consideration. One task can replace a
- shared memory policy while another task, with a distinct mmap_sem, is
- querying or allocating a page based on the policy. To resolve this
- potential race, the shared policy infrastructure adds an extra reference
- to the shared policy during lookup while holding a spin lock on the shared
- policy management structure. This requires that we drop this extra
- reference when we're finished "using" the policy. We must drop the
- extra reference on shared policies in the same query/allocation paths
- used for non-shared policies. For this reason, shared policies are marked
- as such, and the extra reference is dropped "conditionally"--i.e., only
- for shared policies.
-
- Because of this extra reference counting, and because we must lookup
- shared policies in a tree structure under spinlock, shared policies are
- more expensive to use in the page allocation path. This is especially
- true for shared policies on shared memory regions shared by tasks running
- on different NUMA nodes. This extra overhead can be avoided by always
- falling back to task or system default policy for shared memory regions,
- or by prefaulting the entire shared memory region into memory and locking
- it down. However, this might not be appropriate for all applications.
-
-MEMORY POLICY APIs
-
-Linux supports 3 system calls for controlling memory policy. These APIS
-always affect only the calling task, the calling task's address space, or
-some shared object mapped into the calling task's address space.
-
- Note: the headers that define these APIs and the parameter data types
- for user space applications reside in a package that is not part of
- the Linux kernel. The kernel system call interfaces, with the 'sys_'
- prefix, are defined in <linux/syscalls.h>; the mode and flag
- definitions are defined in <linux/mempolicy.h>.
-
-Set [Task] Memory Policy:
-
- long set_mempolicy(int mode, const unsigned long *nmask,
- unsigned long maxnode);
-
- Set's the calling task's "task/process memory policy" to mode
- specified by the 'mode' argument and the set of nodes defined
- by 'nmask'. 'nmask' points to a bit mask of node ids containing
- at least 'maxnode' ids. Optional mode flags may be passed by
- combining the 'mode' argument with the flag (for example:
- MPOL_INTERLEAVE | MPOL_F_STATIC_NODES).
-
- See the set_mempolicy(2) man page for more details
-
-
-Get [Task] Memory Policy or Related Information
-
- long get_mempolicy(int *mode,
- const unsigned long *nmask, unsigned long maxnode,
- void *addr, int flags);
-
- Queries the "task/process memory policy" of the calling task, or
- the policy or location of a specified virtual address, depending
- on the 'flags' argument.
-
- See the get_mempolicy(2) man page for more details
-
-
-Install VMA/Shared Policy for a Range of Task's Address Space
-
- long mbind(void *start, unsigned long len, int mode,
- const unsigned long *nmask, unsigned long maxnode,
- unsigned flags);
-
- mbind() installs the policy specified by (mode, nmask, maxnodes) as
- a VMA policy for the range of the calling task's address space
- specified by the 'start' and 'len' arguments. Additional actions
- may be requested via the 'flags' argument.
-
- See the mbind(2) man page for more details.
-
-MEMORY POLICY COMMAND LINE INTERFACE
-
-Although not strictly part of the Linux implementation of memory policy,
-a command line tool, numactl(8), exists that allows one to:
-
-+ set the task policy for a specified program via set_mempolicy(2), fork(2) and
- exec(2)
-
-+ set the shared policy for a shared memory segment via mbind(2)
-
-The numactl(8) tool is packaged with the run-time version of the library
-containing the memory policy system call wrappers. Some distributions
-package the headers and compile-time libraries in a separate development
-package.
-
-
-MEMORY POLICIES AND CPUSETS
-
-Memory policies work within cpusets as described above. For memory policies
-that require a node or set of nodes, the nodes are restricted to the set of
-nodes whose memories are allowed by the cpuset constraints. If the nodemask
-specified for the policy contains nodes that are not allowed by the cpuset and
-MPOL_F_RELATIVE_NODES is not used, the intersection of the set of nodes
-specified for the policy and the set of nodes with memory is used. If the
-result is the empty set, the policy is considered invalid and cannot be
-installed. If MPOL_F_RELATIVE_NODES is used, the policy's nodes are mapped
-onto and folded into the task's set of allowed nodes as previously described.
-
-The interaction of memory policies and cpusets can be problematic when tasks
-in two cpusets share access to a memory region, such as shared memory segments
-created by shmget() of mmap() with the MAP_ANONYMOUS and MAP_SHARED flags, and
-any of the tasks install shared policy on the region, only nodes whose
-memories are allowed in both cpusets may be used in the policies. Obtaining
-this information requires "stepping outside" the memory policy APIs to use the
-cpuset information and requires that one know in what cpusets other task might
-be attaching to the shared region. Furthermore, if the cpusets' allowed
-memory sets are disjoint, "local" allocation is the only valid policy.
diff --git a/Documentation/vm/overcommit-accounting b/Documentation/vm/overcommit-accounting
deleted file mode 100644
index cbfaaa6..0000000
--- a/Documentation/vm/overcommit-accounting
+++ /dev/null
@@ -1,80 +0,0 @@
-The Linux kernel supports the following overcommit handling modes
-
-0 - Heuristic overcommit handling. Obvious overcommits of
- address space are refused. Used for a typical system. It
- ensures a seriously wild allocation fails while allowing
- overcommit to reduce swap usage. root is allowed to
- allocate slightly more memory in this mode. This is the
- default.
-
-1 - Always overcommit. Appropriate for some scientific
- applications. Classic example is code using sparse arrays
- and just relying on the virtual memory consisting almost
- entirely of zero pages.
-
-2 - Don't overcommit. The total address space commit
- for the system is not permitted to exceed swap + a
- configurable amount (default is 50%) of physical RAM.
- Depending on the amount you use, in most situations
- this means a process will not be killed while accessing
- pages but will receive errors on memory allocation as
- appropriate.
-
- Useful for applications that want to guarantee their
- memory allocations will be available in the future
- without having to initialize every page.
-
-The overcommit policy is set via the sysctl `vm.overcommit_memory'.
-
-The overcommit amount can be set via `vm.overcommit_ratio' (percentage)
-or `vm.overcommit_kbytes' (absolute value).
-
-The current overcommit limit and amount committed are viewable in
-/proc/meminfo as CommitLimit and Committed_AS respectively.
-
-Gotchas
--------
-
-The C language stack growth does an implicit mremap. If you want absolute
-guarantees and run close to the edge you MUST mmap your stack for the
-largest size you think you will need. For typical stack usage this does
-not matter much but it's a corner case if you really really care
-
-In mode 2 the MAP_NORESERVE flag is ignored.
-
-
-How It Works
-------------
-
-The overcommit is based on the following rules
-
-For a file backed map
- SHARED or READ-only - 0 cost (the file is the map not swap)
- PRIVATE WRITABLE - size of mapping per instance
-
-For an anonymous or /dev/zero map
- SHARED - size of mapping
- PRIVATE READ-only - 0 cost (but of little use)
- PRIVATE WRITABLE - size of mapping per instance
-
-Additional accounting
- Pages made writable copies by mmap
- shmfs memory drawn from the same pool
-
-Status
-------
-
-o We account mmap memory mappings
-o We account mprotect changes in commit
-o We account mremap changes in size
-o We account brk
-o We account munmap
-o We report the commit status in /proc
-o Account and check on fork
-o Review stack handling/building on exec
-o SHMfs accounting
-o Implement actual limit enforcement
-
-To Do
------
-o Account ptrace pages (this is hard)
diff --git a/Documentation/vm/overcommit-accounting.rst b/Documentation/vm/overcommit-accounting.rst
new file mode 100644
index 0000000..0dd54bb
--- /dev/null
+++ b/Documentation/vm/overcommit-accounting.rst
@@ -0,0 +1,87 @@
+.. _overcommit_accounting:
+
+=====================
+Overcommit Accounting
+=====================
+
+The Linux kernel supports the following overcommit handling modes
+
+0
+ Heuristic overcommit handling. Obvious overcommits of address
+ space are refused. Used for a typical system. It ensures a
+ seriously wild allocation fails while allowing overcommit to
+ reduce swap usage. root is allowed to allocate slightly more
+ memory in this mode. This is the default.
+
+1
+ Always overcommit. Appropriate for some scientific
+ applications. Classic example is code using sparse arrays and
+ just relying on the virtual memory consisting almost entirely
+ of zero pages.
+
+2
+ Don't overcommit. The total address space commit for the
+ system is not permitted to exceed swap + a configurable amount
+ (default is 50%) of physical RAM. Depending on the amount you
+ use, in most situations this means a process will not be
+ killed while accessing pages but will receive errors on memory
+ allocation as appropriate.
+
+ Useful for applications that want to guarantee their memory
+ allocations will be available in the future without having to
+ initialize every page.
+
+The overcommit policy is set via the sysctl ``vm.overcommit_memory``.
+
+The overcommit amount can be set via ``vm.overcommit_ratio`` (percentage)
+or ``vm.overcommit_kbytes`` (absolute value).
+
+The current overcommit limit and amount committed are viewable in
+``/proc/meminfo`` as CommitLimit and Committed_AS respectively.
+
+Gotchas
+=======
+
+The C language stack growth does an implicit mremap. If you want absolute
+guarantees and run close to the edge you MUST mmap your stack for the
+largest size you think you will need. For typical stack usage this does
+not matter much but it's a corner case if you really really care
+
+In mode 2 the MAP_NORESERVE flag is ignored.
+
+
+How It Works
+============
+
+The overcommit is based on the following rules
+
+For a file backed map
+ | SHARED or READ-only - 0 cost (the file is the map not swap)
+ | PRIVATE WRITABLE - size of mapping per instance
+
+For an anonymous or ``/dev/zero`` map
+ | SHARED - size of mapping
+ | PRIVATE READ-only - 0 cost (but of little use)
+ | PRIVATE WRITABLE - size of mapping per instance
+
+Additional accounting
+ | Pages made writable copies by mmap
+ | shmfs memory drawn from the same pool
+
+Status
+======
+
+* We account mmap memory mappings
+* We account mprotect changes in commit
+* We account mremap changes in size
+* We account brk
+* We account munmap
+* We report the commit status in /proc
+* Account and check on fork
+* Review stack handling/building on exec
+* SHMfs accounting
+* Implement actual limit enforcement
+
+To Do
+=====
+* Account ptrace pages (this is hard)
diff --git a/Documentation/vm/page_frags b/Documentation/vm/page_frags.rst
similarity index 97%
rename from Documentation/vm/page_frags
rename to Documentation/vm/page_frags.rst
index a671456..637cc49 100644
--- a/Documentation/vm/page_frags
+++ b/Documentation/vm/page_frags.rst
@@ -1,5 +1,8 @@
+.. _page_frags:
+
+==============
Page fragments
---------------
+==============
A page fragment is an arbitrary-length arbitrary-offset area of memory
which resides within a 0 or higher order compound page. Multiple
diff --git a/Documentation/vm/page_migration b/Documentation/vm/page_migration.rst
similarity index 63%
rename from Documentation/vm/page_migration
rename to Documentation/vm/page_migration.rst
index 4968680..f68d613 100644
--- a/Documentation/vm/page_migration
+++ b/Documentation/vm/page_migration.rst
@@ -1,5 +1,8 @@
+.. _page_migration:
+
+==============
Page migration
---------------
+==============
Page migration allows the moving of the physical location of pages between
nodes in a numa system while the process is running. This means that the
@@ -20,7 +23,7 @@
(a version later than 0.9.3 is required. Get it from
ftp://oss.sgi.com/www/projects/libnuma/download/). numactl provides libnuma
which provides an interface similar to other numa functionality for page
-migration. cat /proc/<pid>/numa_maps allows an easy review of where the
+migration. cat ``/proc/<pid>/numa_maps`` allows an easy review of where the
pages of a process are located. See also the numa_maps documentation in the
proc(5) man page.
@@ -56,8 +59,8 @@
(for userspace usage see the Andi Kleen's numactl package mentioned above)
and then a low level description of how the low level details work.
-A. In kernel use of migrate_pages()
------------------------------------
+In kernel use of migrate_pages()
+================================
1. Remove pages from the LRU.
@@ -78,8 +81,8 @@
the new page for each page that is considered for
moving.
-B. How migrate_pages() works
-----------------------------
+How migrate_pages() works
+=========================
migrate_pages() does several passes over its list of pages. A page is moved
if all references to a page are removable at the time. The page has
@@ -142,8 +145,8 @@
20. The new page is moved to the LRU and can be scanned by the swapper
etc again.
-C. Non-LRU page migration
--------------------------
+Non-LRU page migration
+======================
Although original migration aimed for reducing the latency of memory access
for NUMA, compaction who want to create high-order page is also main customer.
@@ -164,89 +167,91 @@
If a driver want to make own pages movable, it should define three functions
which are function pointers of struct address_space_operations.
-1. bool (*isolate_page) (struct page *page, isolate_mode_t mode);
+1. ``bool (*isolate_page) (struct page *page, isolate_mode_t mode);``
-What VM expects on isolate_page function of driver is to return *true*
-if driver isolates page successfully. On returing true, VM marks the page
-as PG_isolated so concurrent isolation in several CPUs skip the page
-for isolation. If a driver cannot isolate the page, it should return *false*.
+ What VM expects on isolate_page function of driver is to return *true*
+ if driver isolates page successfully. On returing true, VM marks the page
+ as PG_isolated so concurrent isolation in several CPUs skip the page
+ for isolation. If a driver cannot isolate the page, it should return *false*.
-Once page is successfully isolated, VM uses page.lru fields so driver
-shouldn't expect to preserve values in that fields.
+ Once page is successfully isolated, VM uses page.lru fields so driver
+ shouldn't expect to preserve values in that fields.
-2. int (*migratepage) (struct address_space *mapping,
- struct page *newpage, struct page *oldpage, enum migrate_mode);
+2. ``int (*migratepage) (struct address_space *mapping,``
+| ``struct page *newpage, struct page *oldpage, enum migrate_mode);``
-After isolation, VM calls migratepage of driver with isolated page.
-The function of migratepage is to move content of the old page to new page
-and set up fields of struct page newpage. Keep in mind that you should
-indicate to the VM the oldpage is no longer movable via __ClearPageMovable()
-under page_lock if you migrated the oldpage successfully and returns
-MIGRATEPAGE_SUCCESS. If driver cannot migrate the page at the moment, driver
-can return -EAGAIN. On -EAGAIN, VM will retry page migration in a short time
-because VM interprets -EAGAIN as "temporal migration failure". On returning
-any error except -EAGAIN, VM will give up the page migration without retrying
-in this time.
+ After isolation, VM calls migratepage of driver with isolated page.
+ The function of migratepage is to move content of the old page to new page
+ and set up fields of struct page newpage. Keep in mind that you should
+ indicate to the VM the oldpage is no longer movable via __ClearPageMovable()
+ under page_lock if you migrated the oldpage successfully and returns
+ MIGRATEPAGE_SUCCESS. If driver cannot migrate the page at the moment, driver
+ can return -EAGAIN. On -EAGAIN, VM will retry page migration in a short time
+ because VM interprets -EAGAIN as "temporal migration failure". On returning
+ any error except -EAGAIN, VM will give up the page migration without retrying
+ in this time.
-Driver shouldn't touch page.lru field VM using in the functions.
+ Driver shouldn't touch page.lru field VM using in the functions.
-3. void (*putback_page)(struct page *);
+3. ``void (*putback_page)(struct page *);``
-If migration fails on isolated page, VM should return the isolated page
-to the driver so VM calls driver's putback_page with migration failed page.
-In this function, driver should put the isolated page back to the own data
-structure.
+ If migration fails on isolated page, VM should return the isolated page
+ to the driver so VM calls driver's putback_page with migration failed page.
+ In this function, driver should put the isolated page back to the own data
+ structure.
4. non-lru movable page flags
-There are two page flags for supporting non-lru movable page.
+ There are two page flags for supporting non-lru movable page.
-* PG_movable
+ * PG_movable
-Driver should use the below function to make page movable under page_lock.
+ Driver should use the below function to make page movable under page_lock::
void __SetPageMovable(struct page *page, struct address_space *mapping)
-It needs argument of address_space for registering migration family functions
-which will be called by VM. Exactly speaking, PG_movable is not a real flag of
-struct page. Rather than, VM reuses page->mapping's lower bits to represent it.
+ It needs argument of address_space for registering migration
+ family functions which will be called by VM. Exactly speaking,
+ PG_movable is not a real flag of struct page. Rather than, VM
+ reuses page->mapping's lower bits to represent it.
+::
#define PAGE_MAPPING_MOVABLE 0x2
page->mapping = page->mapping | PAGE_MAPPING_MOVABLE;
-so driver shouldn't access page->mapping directly. Instead, driver should
-use page_mapping which mask off the low two bits of page->mapping under
-page lock so it can get right struct address_space.
+ so driver shouldn't access page->mapping directly. Instead, driver should
+ use page_mapping which mask off the low two bits of page->mapping under
+ page lock so it can get right struct address_space.
-For testing of non-lru movable page, VM supports __PageMovable function.
-However, it doesn't guarantee to identify non-lru movable page because
-page->mapping field is unified with other variables in struct page.
-As well, if driver releases the page after isolation by VM, page->mapping
-doesn't have stable value although it has PAGE_MAPPING_MOVABLE
-(Look at __ClearPageMovable). But __PageMovable is cheap to catch whether
-page is LRU or non-lru movable once the page has been isolated. Because
-LRU pages never can have PAGE_MAPPING_MOVABLE in page->mapping. It is also
-good for just peeking to test non-lru movable pages before more expensive
-checking with lock_page in pfn scanning to select victim.
+ For testing of non-lru movable page, VM supports __PageMovable function.
+ However, it doesn't guarantee to identify non-lru movable page because
+ page->mapping field is unified with other variables in struct page.
+ As well, if driver releases the page after isolation by VM, page->mapping
+ doesn't have stable value although it has PAGE_MAPPING_MOVABLE
+ (Look at __ClearPageMovable). But __PageMovable is cheap to catch whether
+ page is LRU or non-lru movable once the page has been isolated. Because
+ LRU pages never can have PAGE_MAPPING_MOVABLE in page->mapping. It is also
+ good for just peeking to test non-lru movable pages before more expensive
+ checking with lock_page in pfn scanning to select victim.
-For guaranteeing non-lru movable page, VM provides PageMovable function.
-Unlike __PageMovable, PageMovable functions validates page->mapping and
-mapping->a_ops->isolate_page under lock_page. The lock_page prevents sudden
-destroying of page->mapping.
+ For guaranteeing non-lru movable page, VM provides PageMovable function.
+ Unlike __PageMovable, PageMovable functions validates page->mapping and
+ mapping->a_ops->isolate_page under lock_page. The lock_page prevents sudden
+ destroying of page->mapping.
-Driver using __SetPageMovable should clear the flag via __ClearMovablePage
-under page_lock before the releasing the page.
+ Driver using __SetPageMovable should clear the flag via __ClearMovablePage
+ under page_lock before the releasing the page.
-* PG_isolated
+ * PG_isolated
-To prevent concurrent isolation among several CPUs, VM marks isolated page
-as PG_isolated under lock_page. So if a CPU encounters PG_isolated non-lru
-movable page, it can skip it. Driver doesn't need to manipulate the flag
-because VM will set/clear it automatically. Keep in mind that if driver
-sees PG_isolated page, it means the page have been isolated by VM so it
-shouldn't touch page.lru field.
-PG_isolated is alias with PG_reclaim flag so driver shouldn't use the flag
-for own purpose.
+ To prevent concurrent isolation among several CPUs, VM marks isolated page
+ as PG_isolated under lock_page. So if a CPU encounters PG_isolated non-lru
+ movable page, it can skip it. Driver doesn't need to manipulate the flag
+ because VM will set/clear it automatically. Keep in mind that if driver
+ sees PG_isolated page, it means the page have been isolated by VM so it
+ shouldn't touch page.lru field.
+ PG_isolated is alias with PG_reclaim flag so driver shouldn't use the flag
+ for own purpose.
Christoph Lameter, May 8, 2006.
Minchan Kim, Mar 28, 2016.
diff --git a/Documentation/vm/page_owner.txt b/Documentation/vm/page_owner.rst
similarity index 85%
rename from Documentation/vm/page_owner.txt
rename to Documentation/vm/page_owner.rst
index ffff143..0ed5ab8 100644
--- a/Documentation/vm/page_owner.txt
+++ b/Documentation/vm/page_owner.rst
@@ -1,7 +1,11 @@
-page owner: Tracking about who allocated each page
------------------------------------------------------------
+.. _page_owner:
-* Introduction
+==================================================
+page owner: Tracking about who allocated each page
+==================================================
+
+Introduction
+============
page owner is for the tracking about who allocated each page.
It can be used to debug memory leak or to find a memory hogger.
@@ -34,13 +38,15 @@
label patching functionality is available. Following is the kernel's code
size change due to this facility.
-- Without page owner
- text data bss dec hex filename
- 40662 1493 644 42799 a72f mm/page_alloc.o
+- Without page owner::
-- With page owner
text data bss dec hex filename
- 40892 1493 644 43029 a815 mm/page_alloc.o
+ 40662 1493 644 42799 a72f mm/page_alloc.o
+
+- With page owner::
+
+ text data bss dec hex filename
+ 40892 1493 644 43029 a815 mm/page_alloc.o
1427 24 8 1459 5b3 mm/page_ext.o
2722 50 0 2772 ad4 mm/page_owner.o
@@ -62,21 +68,23 @@
page extension feature. Anyway, after that, no page is left in
un-tracking state.
-* Usage
+Usage
+=====
-1) Build user-space helper
+1) Build user-space helper::
+
cd tools/vm
make page_owner_sort
-2) Enable page owner
- Add "page_owner=on" to boot cmdline.
+2) Enable page owner: add "page_owner=on" to boot cmdline.
3) Do the job what you want to debug
-4) Analyze information from page owner
+4) Analyze information from page owner::
+
cat /sys/kernel/debug/page_owner > page_owner_full.txt
grep -v ^PFN page_owner_full.txt > page_owner.txt
./page_owner_sort page_owner.txt sorted_page_owner.txt
- See the result about who allocated each page
- in the sorted_page_owner.txt.
+ See the result about who allocated each page
+ in the ``sorted_page_owner.txt``.
diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt
deleted file mode 100644
index eafcefa..0000000
--- a/Documentation/vm/pagemap.txt
+++ /dev/null
@@ -1,183 +0,0 @@
-pagemap, from the userspace perspective
----------------------------------------
-
-pagemap is a new (as of 2.6.25) set of interfaces in the kernel that allow
-userspace programs to examine the page tables and related information by
-reading files in /proc.
-
-There are four components to pagemap:
-
- * /proc/pid/pagemap. This file lets a userspace process find out which
- physical frame each virtual page is mapped to. It contains one 64-bit
- value for each virtual page, containing the following data (from
- fs/proc/task_mmu.c, above pagemap_read):
-
- * Bits 0-54 page frame number (PFN) if present
- * Bits 0-4 swap type if swapped
- * Bits 5-54 swap offset if swapped
- * Bit 55 pte is soft-dirty (see Documentation/vm/soft-dirty.txt)
- * Bit 56 page exclusively mapped (since 4.2)
- * Bits 57-60 zero
- * Bit 61 page is file-page or shared-anon (since 3.5)
- * Bit 62 page swapped
- * Bit 63 page present
-
- Since Linux 4.0 only users with the CAP_SYS_ADMIN capability can get PFNs.
- In 4.0 and 4.1 opens by unprivileged fail with -EPERM. Starting from
- 4.2 the PFN field is zeroed if the user does not have CAP_SYS_ADMIN.
- Reason: information about PFNs helps in exploiting Rowhammer vulnerability.
-
- If the page is not present but in swap, then the PFN contains an
- encoding of the swap file number and the page's offset into the
- swap. Unmapped pages return a null PFN. This allows determining
- precisely which pages are mapped (or in swap) and comparing mapped
- pages between processes.
-
- Efficient users of this interface will use /proc/pid/maps to
- determine which areas of memory are actually mapped and llseek to
- skip over unmapped regions.
-
- * /proc/kpagecount. This file contains a 64-bit count of the number of
- times each page is mapped, indexed by PFN.
-
- * /proc/kpageflags. This file contains a 64-bit set of flags for each
- page, indexed by PFN.
-
- The flags are (from fs/proc/page.c, above kpageflags_read):
-
- 0. LOCKED
- 1. ERROR
- 2. REFERENCED
- 3. UPTODATE
- 4. DIRTY
- 5. LRU
- 6. ACTIVE
- 7. SLAB
- 8. WRITEBACK
- 9. RECLAIM
- 10. BUDDY
- 11. MMAP
- 12. ANON
- 13. SWAPCACHE
- 14. SWAPBACKED
- 15. COMPOUND_HEAD
- 16. COMPOUND_TAIL
- 17. HUGE
- 18. UNEVICTABLE
- 19. HWPOISON
- 20. NOPAGE
- 21. KSM
- 22. THP
- 23. BALLOON
- 24. ZERO_PAGE
- 25. IDLE
-
- * /proc/kpagecgroup. This file contains a 64-bit inode number of the
- memory cgroup each page is charged to, indexed by PFN. Only available when
- CONFIG_MEMCG is set.
-
-Short descriptions to the page flags:
-
- 0. LOCKED
- page is being locked for exclusive access, eg. by undergoing read/write IO
-
- 7. SLAB
- page is managed by the SLAB/SLOB/SLUB/SLQB kernel memory allocator
- When compound page is used, SLUB/SLQB will only set this flag on the head
- page; SLOB will not flag it at all.
-
-10. BUDDY
- a free memory block managed by the buddy system allocator
- The buddy system organizes free memory in blocks of various orders.
- An order N block has 2^N physically contiguous pages, with the BUDDY flag
- set for and _only_ for the first page.
-
-15. COMPOUND_HEAD
-16. COMPOUND_TAIL
- A compound page with order N consists of 2^N physically contiguous pages.
- A compound page with order 2 takes the form of "HTTT", where H donates its
- head page and T donates its tail page(s). The major consumers of compound
- pages are hugeTLB pages (Documentation/vm/hugetlbpage.txt), the SLUB etc.
- memory allocators and various device drivers. However in this interface,
- only huge/giga pages are made visible to end users.
-17. HUGE
- this is an integral part of a HugeTLB page
-
-19. HWPOISON
- hardware detected memory corruption on this page: don't touch the data!
-
-20. NOPAGE
- no page frame exists at the requested address
-
-21. KSM
- identical memory pages dynamically shared between one or more processes
-
-22. THP
- contiguous pages which construct transparent hugepages
-
-23. BALLOON
- balloon compaction page
-
-24. ZERO_PAGE
- zero page for pfn_zero or huge_zero page
-
-25. IDLE
- page has not been accessed since it was marked idle (see
- Documentation/vm/idle_page_tracking.txt). Note that this flag may be
- stale in case the page was accessed via a PTE. To make sure the flag
- is up-to-date one has to read /sys/kernel/mm/page_idle/bitmap first.
-
- [IO related page flags]
- 1. ERROR IO error occurred
- 3. UPTODATE page has up-to-date data
- ie. for file backed page: (in-memory data revision >= on-disk one)
- 4. DIRTY page has been written to, hence contains new data
- ie. for file backed page: (in-memory data revision > on-disk one)
- 8. WRITEBACK page is being synced to disk
-
- [LRU related page flags]
- 5. LRU page is in one of the LRU lists
- 6. ACTIVE page is in the active LRU list
-18. UNEVICTABLE page is in the unevictable (non-)LRU list
- It is somehow pinned and not a candidate for LRU page reclaims,
- eg. ramfs pages, shmctl(SHM_LOCK) and mlock() memory segments
- 2. REFERENCED page has been referenced since last LRU list enqueue/requeue
- 9. RECLAIM page will be reclaimed soon after its pageout IO completed
-11. MMAP a memory mapped page
-12. ANON a memory mapped page that is not part of a file
-13. SWAPCACHE page is mapped to swap space, ie. has an associated swap entry
-14. SWAPBACKED page is backed by swap/RAM
-
-The page-types tool in the tools/vm directory can be used to query the
-above flags.
-
-Using pagemap to do something useful:
-
-The general procedure for using pagemap to find out about a process' memory
-usage goes like this:
-
- 1. Read /proc/pid/maps to determine which parts of the memory space are
- mapped to what.
- 2. Select the maps you are interested in -- all of them, or a particular
- library, or the stack or the heap, etc.
- 3. Open /proc/pid/pagemap and seek to the pages you would like to examine.
- 4. Read a u64 for each page from pagemap.
- 5. Open /proc/kpagecount and/or /proc/kpageflags. For each PFN you just
- read, seek to that entry in the file, and read the data you want.
-
-For example, to find the "unique set size" (USS), which is the amount of
-memory that a process is using that is not shared with any other process,
-you can go through every map in the process, find the PFNs, look those up
-in kpagecount, and tally up the number of pages that are only referenced
-once.
-
-Other notes:
-
-Reading from any of the files will return -EINVAL if you are not starting
-the read on an 8-byte boundary (e.g., if you sought an odd number of bytes
-into the file), or if the size of the read is not a multiple of 8 bytes.
-
-Before Linux 3.11 pagemap bits 55-60 were used for "page-shift" (which is
-always 12 at most architectures). Since Linux 3.11 their meaning changes
-after first clear of soft-dirty bits. Since Linux 4.2 they are used for
-flags unconditionally.
diff --git a/Documentation/vm/remap_file_pages.txt b/Documentation/vm/remap_file_pages.rst
similarity index 92%
rename from Documentation/vm/remap_file_pages.txt
rename to Documentation/vm/remap_file_pages.rst
index f609142..7bef671 100644
--- a/Documentation/vm/remap_file_pages.txt
+++ b/Documentation/vm/remap_file_pages.rst
@@ -1,3 +1,9 @@
+.. _remap_file_pages:
+
+==============================
+remap_file_pages() system call
+==============================
+
The remap_file_pages() system call is used to create a nonlinear mapping,
that is, a mapping in which the pages of the file are mapped into a
nonsequential order in memory. The advantage of using remap_file_pages()
diff --git a/Documentation/vm/slub.rst b/Documentation/vm/slub.rst
new file mode 100644
index 0000000..3a775fd
--- /dev/null
+++ b/Documentation/vm/slub.rst
@@ -0,0 +1,361 @@
+.. _slub:
+
+==========================
+Short users guide for SLUB
+==========================
+
+The basic philosophy of SLUB is very different from SLAB. SLAB
+requires rebuilding the kernel to activate debug options for all
+slab caches. SLUB always includes full debugging but it is off by default.
+SLUB can enable debugging only for selected slabs in order to avoid
+an impact on overall system performance which may make a bug more
+difficult to find.
+
+In order to switch debugging on one can add an option ``slub_debug``
+to the kernel command line. That will enable full debugging for
+all slabs.
+
+Typically one would then use the ``slabinfo`` command to get statistical
+data and perform operation on the slabs. By default ``slabinfo`` only lists
+slabs that have data in them. See "slabinfo -h" for more options when
+running the command. ``slabinfo`` can be compiled with
+::
+
+ gcc -o slabinfo tools/vm/slabinfo.c
+
+Some of the modes of operation of ``slabinfo`` require that slub debugging
+be enabled on the command line. F.e. no tracking information will be
+available without debugging on and validation can only partially
+be performed if debugging was not switched on.
+
+Some more sophisticated uses of slub_debug:
+-------------------------------------------
+
+Parameters may be given to ``slub_debug``. If none is specified then full
+debugging is enabled. Format:
+
+slub_debug=<Debug-Options>
+ Enable options for all slabs
+slub_debug=<Debug-Options>,<slab name>
+ Enable options only for select slabs
+
+
+Possible debug options are::
+
+ F Sanity checks on (enables SLAB_DEBUG_CONSISTENCY_CHECKS
+ Sorry SLAB legacy issues)
+ Z Red zoning
+ P Poisoning (object and padding)
+ U User tracking (free and alloc)
+ T Trace (please only use on single slabs)
+ A Toggle failslab filter mark for the cache
+ O Switch debugging off for caches that would have
+ caused higher minimum slab orders
+ - Switch all debugging off (useful if the kernel is
+ configured with CONFIG_SLUB_DEBUG_ON)
+
+F.e. in order to boot just with sanity checks and red zoning one would specify::
+
+ slub_debug=FZ
+
+Trying to find an issue in the dentry cache? Try::
+
+ slub_debug=,dentry
+
+to only enable debugging on the dentry cache.
+
+Red zoning and tracking may realign the slab. We can just apply sanity checks
+to the dentry cache with::
+
+ slub_debug=F,dentry
+
+Debugging options may require the minimum possible slab order to increase as
+a result of storing the metadata (for example, caches with PAGE_SIZE object
+sizes). This has a higher liklihood of resulting in slab allocation errors
+in low memory situations or if there's high fragmentation of memory. To
+switch off debugging for such caches by default, use::
+
+ slub_debug=O
+
+In case you forgot to enable debugging on the kernel command line: It is
+possible to enable debugging manually when the kernel is up. Look at the
+contents of::
+
+ /sys/kernel/slab/<slab name>/
+
+Look at the writable files. Writing 1 to them will enable the
+corresponding debug option. All options can be set on a slab that does
+not contain objects. If the slab already contains objects then sanity checks
+and tracing may only be enabled. The other options may cause the realignment
+of objects.
+
+Careful with tracing: It may spew out lots of information and never stop if
+used on the wrong slab.
+
+Slab merging
+============
+
+If no debug options are specified then SLUB may merge similar slabs together
+in order to reduce overhead and increase cache hotness of objects.
+``slabinfo -a`` displays which slabs were merged together.
+
+Slab validation
+===============
+
+SLUB can validate all object if the kernel was booted with slub_debug. In
+order to do so you must have the ``slabinfo`` tool. Then you can do
+::
+
+ slabinfo -v
+
+which will test all objects. Output will be generated to the syslog.
+
+This also works in a more limited way if boot was without slab debug.
+In that case ``slabinfo -v`` simply tests all reachable objects. Usually
+these are in the cpu slabs and the partial slabs. Full slabs are not
+tracked by SLUB in a non debug situation.
+
+Getting more performance
+========================
+
+To some degree SLUB's performance is limited by the need to take the
+list_lock once in a while to deal with partial slabs. That overhead is
+governed by the order of the allocation for each slab. The allocations
+can be influenced by kernel parameters:
+
+.. slub_min_objects=x (default 4)
+.. slub_min_order=x (default 0)
+.. slub_max_order=x (default 3 (PAGE_ALLOC_COSTLY_ORDER))
+
+``slub_min_objects``
+ allows to specify how many objects must at least fit into one
+ slab in order for the allocation order to be acceptable. In
+ general slub will be able to perform this number of
+ allocations on a slab without consulting centralized resources
+ (list_lock) where contention may occur.
+
+``slub_min_order``
+ specifies a minim order of slabs. A similar effect like
+ ``slub_min_objects``.
+
+``slub_max_order``
+ specified the order at which ``slub_min_objects`` should no
+ longer be checked. This is useful to avoid SLUB trying to
+ generate super large order pages to fit ``slub_min_objects``
+ of a slab cache with large object sizes into one high order
+ page. Setting command line parameter
+ ``debug_guardpage_minorder=N`` (N > 0), forces setting
+ ``slub_max_order`` to 0, what cause minimum possible order of
+ slabs allocation.
+
+SLUB Debug output
+=================
+
+Here is a sample of slub debug output::
+
+ ====================================================================
+ BUG kmalloc-8: Redzone overwritten
+ --------------------------------------------------------------------
+
+ INFO: 0xc90f6d28-0xc90f6d2b. First byte 0x00 instead of 0xcc
+ INFO: Slab 0xc528c530 flags=0x400000c3 inuse=61 fp=0xc90f6d58
+ INFO: Object 0xc90f6d20 @offset=3360 fp=0xc90f6d58
+ INFO: Allocated in get_modalias+0x61/0xf5 age=53 cpu=1 pid=554
+
+ Bytes b4 0xc90f6d10: 00 00 00 00 00 00 00 00 5a 5a 5a 5a 5a 5a 5a 5a ........ZZZZZZZZ
+ Object 0xc90f6d20: 31 30 31 39 2e 30 30 35 1019.005
+ Redzone 0xc90f6d28: 00 cc cc cc .
+ Padding 0xc90f6d50: 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZ
+
+ [<c010523d>] dump_trace+0x63/0x1eb
+ [<c01053df>] show_trace_log_lvl+0x1a/0x2f
+ [<c010601d>] show_trace+0x12/0x14
+ [<c0106035>] dump_stack+0x16/0x18
+ [<c017e0fa>] object_err+0x143/0x14b
+ [<c017e2cc>] check_object+0x66/0x234
+ [<c017eb43>] __slab_free+0x239/0x384
+ [<c017f446>] kfree+0xa6/0xc6
+ [<c02e2335>] get_modalias+0xb9/0xf5
+ [<c02e23b7>] dmi_dev_uevent+0x27/0x3c
+ [<c027866a>] dev_uevent+0x1ad/0x1da
+ [<c0205024>] kobject_uevent_env+0x20a/0x45b
+ [<c020527f>] kobject_uevent+0xa/0xf
+ [<c02779f1>] store_uevent+0x4f/0x58
+ [<c027758e>] dev_attr_store+0x29/0x2f
+ [<c01bec4f>] sysfs_write_file+0x16e/0x19c
+ [<c0183ba7>] vfs_write+0xd1/0x15a
+ [<c01841d7>] sys_write+0x3d/0x72
+ [<c0104112>] sysenter_past_esp+0x5f/0x99
+ [<b7f7b410>] 0xb7f7b410
+ =======================
+
+ FIX kmalloc-8: Restoring Redzone 0xc90f6d28-0xc90f6d2b=0xcc
+
+If SLUB encounters a corrupted object (full detection requires the kernel
+to be booted with slub_debug) then the following output will be dumped
+into the syslog:
+
+1. Description of the problem encountered
+
+ This will be a message in the system log starting with::
+
+ ===============================================
+ BUG <slab cache affected>: <What went wrong>
+ -----------------------------------------------
+
+ INFO: <corruption start>-<corruption_end> <more info>
+ INFO: Slab <address> <slab information>
+ INFO: Object <address> <object information>
+ INFO: Allocated in <kernel function> age=<jiffies since alloc> cpu=<allocated by
+ cpu> pid=<pid of the process>
+ INFO: Freed in <kernel function> age=<jiffies since free> cpu=<freed by cpu>
+ pid=<pid of the process>
+
+ (Object allocation / free information is only available if SLAB_STORE_USER is
+ set for the slab. slub_debug sets that option)
+
+2. The object contents if an object was involved.
+
+ Various types of lines can follow the BUG SLUB line:
+
+ Bytes b4 <address> : <bytes>
+ Shows a few bytes before the object where the problem was detected.
+ Can be useful if the corruption does not stop with the start of the
+ object.
+
+ Object <address> : <bytes>
+ The bytes of the object. If the object is inactive then the bytes
+ typically contain poison values. Any non-poison value shows a
+ corruption by a write after free.
+
+ Redzone <address> : <bytes>
+ The Redzone following the object. The Redzone is used to detect
+ writes after the object. All bytes should always have the same
+ value. If there is any deviation then it is due to a write after
+ the object boundary.
+
+ (Redzone information is only available if SLAB_RED_ZONE is set.
+ slub_debug sets that option)
+
+ Padding <address> : <bytes>
+ Unused data to fill up the space in order to get the next object
+ properly aligned. In the debug case we make sure that there are
+ at least 4 bytes of padding. This allows the detection of writes
+ before the object.
+
+3. A stackdump
+
+ The stackdump describes the location where the error was detected. The cause
+ of the corruption is may be more likely found by looking at the function that
+ allocated or freed the object.
+
+4. Report on how the problem was dealt with in order to ensure the continued
+ operation of the system.
+
+ These are messages in the system log beginning with::
+
+ FIX <slab cache affected>: <corrective action taken>
+
+ In the above sample SLUB found that the Redzone of an active object has
+ been overwritten. Here a string of 8 characters was written into a slab that
+ has the length of 8 characters. However, a 8 character string needs a
+ terminating 0. That zero has overwritten the first byte of the Redzone field.
+ After reporting the details of the issue encountered the FIX SLUB message
+ tells us that SLUB has restored the Redzone to its proper value and then
+ system operations continue.
+
+Emergency operations
+====================
+
+Minimal debugging (sanity checks alone) can be enabled by booting with::
+
+ slub_debug=F
+
+This will be generally be enough to enable the resiliency features of slub
+which will keep the system running even if a bad kernel component will
+keep corrupting objects. This may be important for production systems.
+Performance will be impacted by the sanity checks and there will be a
+continual stream of error messages to the syslog but no additional memory
+will be used (unlike full debugging).
+
+No guarantees. The kernel component still needs to be fixed. Performance
+may be optimized further by locating the slab that experiences corruption
+and enabling debugging only for that cache
+
+I.e.::
+
+ slub_debug=F,dentry
+
+If the corruption occurs by writing after the end of the object then it
+may be advisable to enable a Redzone to avoid corrupting the beginning
+of other objects::
+
+ slub_debug=FZ,dentry
+
+Extended slabinfo mode and plotting
+===================================
+
+The ``slabinfo`` tool has a special 'extended' ('-X') mode that includes:
+ - Slabcache Totals
+ - Slabs sorted by size (up to -N <num> slabs, default 1)
+ - Slabs sorted by loss (up to -N <num> slabs, default 1)
+
+Additionally, in this mode ``slabinfo`` does not dynamically scale
+sizes (G/M/K) and reports everything in bytes (this functionality is
+also available to other slabinfo modes via '-B' option) which makes
+reporting more precise and accurate. Moreover, in some sense the `-X'
+mode also simplifies the analysis of slabs' behaviour, because its
+output can be plotted using the ``slabinfo-gnuplot.sh`` script. So it
+pushes the analysis from looking through the numbers (tons of numbers)
+to something easier -- visual analysis.
+
+To generate plots:
+
+a) collect slabinfo extended records, for example::
+
+ while [ 1 ]; do slabinfo -X >> FOO_STATS; sleep 1; done
+
+b) pass stats file(-s) to ``slabinfo-gnuplot.sh`` script::
+
+ slabinfo-gnuplot.sh FOO_STATS [FOO_STATS2 .. FOO_STATSN]
+
+ The ``slabinfo-gnuplot.sh`` script will pre-processes the collected records
+ and generates 3 png files (and 3 pre-processing cache files) per STATS
+ file:
+ - Slabcache Totals: FOO_STATS-totals.png
+ - Slabs sorted by size: FOO_STATS-slabs-by-size.png
+ - Slabs sorted by loss: FOO_STATS-slabs-by-loss.png
+
+Another use case, when ``slabinfo-gnuplot.sh`` can be useful, is when you
+need to compare slabs' behaviour "prior to" and "after" some code
+modification. To help you out there, ``slabinfo-gnuplot.sh`` script
+can 'merge' the `Slabcache Totals` sections from different
+measurements. To visually compare N plots:
+
+a) Collect as many STATS1, STATS2, .. STATSN files as you need::
+
+ while [ 1 ]; do slabinfo -X >> STATS<X>; sleep 1; done
+
+b) Pre-process those STATS files::
+
+ slabinfo-gnuplot.sh STATS1 STATS2 .. STATSN
+
+c) Execute ``slabinfo-gnuplot.sh`` in '-t' mode, passing all of the
+ generated pre-processed \*-totals::
+
+ slabinfo-gnuplot.sh -t STATS1-totals STATS2-totals .. STATSN-totals
+
+ This will produce a single plot (png file).
+
+ Plots, expectedly, can be large so some fluctuations or small spikes
+ can go unnoticed. To deal with that, ``slabinfo-gnuplot.sh`` has two
+ options to 'zoom-in'/'zoom-out':
+
+ a) ``-s %d,%d`` -- overwrites the default image width and heigh
+ b) ``-r %d,%d`` -- specifies a range of samples to use (for example,
+ in ``slabinfo -X >> FOO_STATS; sleep 1;`` case, using a ``-r
+ 40,60`` range will plot only samples collected between 40th and
+ 60th seconds).
+
+Christoph Lameter, May 30, 2007
+Sergey Senozhatsky, October 23, 2015
diff --git a/Documentation/vm/slub.txt b/Documentation/vm/slub.txt
deleted file mode 100644
index 8465241..0000000
--- a/Documentation/vm/slub.txt
+++ /dev/null
@@ -1,342 +0,0 @@
-Short users guide for SLUB
---------------------------
-
-The basic philosophy of SLUB is very different from SLAB. SLAB
-requires rebuilding the kernel to activate debug options for all
-slab caches. SLUB always includes full debugging but it is off by default.
-SLUB can enable debugging only for selected slabs in order to avoid
-an impact on overall system performance which may make a bug more
-difficult to find.
-
-In order to switch debugging on one can add an option "slub_debug"
-to the kernel command line. That will enable full debugging for
-all slabs.
-
-Typically one would then use the "slabinfo" command to get statistical
-data and perform operation on the slabs. By default slabinfo only lists
-slabs that have data in them. See "slabinfo -h" for more options when
-running the command. slabinfo can be compiled with
-
-gcc -o slabinfo tools/vm/slabinfo.c
-
-Some of the modes of operation of slabinfo require that slub debugging
-be enabled on the command line. F.e. no tracking information will be
-available without debugging on and validation can only partially
-be performed if debugging was not switched on.
-
-Some more sophisticated uses of slub_debug:
--------------------------------------------
-
-Parameters may be given to slub_debug. If none is specified then full
-debugging is enabled. Format:
-
-slub_debug=<Debug-Options> Enable options for all slabs
-slub_debug=<Debug-Options>,<slab name>
- Enable options only for select slabs
-
-Possible debug options are
- F Sanity checks on (enables SLAB_DEBUG_CONSISTENCY_CHECKS
- Sorry SLAB legacy issues)
- Z Red zoning
- P Poisoning (object and padding)
- U User tracking (free and alloc)
- T Trace (please only use on single slabs)
- A Toggle failslab filter mark for the cache
- O Switch debugging off for caches that would have
- caused higher minimum slab orders
- - Switch all debugging off (useful if the kernel is
- configured with CONFIG_SLUB_DEBUG_ON)
-
-F.e. in order to boot just with sanity checks and red zoning one would specify:
-
- slub_debug=FZ
-
-Trying to find an issue in the dentry cache? Try
-
- slub_debug=,dentry
-
-to only enable debugging on the dentry cache.
-
-Red zoning and tracking may realign the slab. We can just apply sanity checks
-to the dentry cache with
-
- slub_debug=F,dentry
-
-Debugging options may require the minimum possible slab order to increase as
-a result of storing the metadata (for example, caches with PAGE_SIZE object
-sizes). This has a higher liklihood of resulting in slab allocation errors
-in low memory situations or if there's high fragmentation of memory. To
-switch off debugging for such caches by default, use
-
- slub_debug=O
-
-In case you forgot to enable debugging on the kernel command line: It is
-possible to enable debugging manually when the kernel is up. Look at the
-contents of:
-
-/sys/kernel/slab/<slab name>/
-
-Look at the writable files. Writing 1 to them will enable the
-corresponding debug option. All options can be set on a slab that does
-not contain objects. If the slab already contains objects then sanity checks
-and tracing may only be enabled. The other options may cause the realignment
-of objects.
-
-Careful with tracing: It may spew out lots of information and never stop if
-used on the wrong slab.
-
-Slab merging
-------------
-
-If no debug options are specified then SLUB may merge similar slabs together
-in order to reduce overhead and increase cache hotness of objects.
-slabinfo -a displays which slabs were merged together.
-
-Slab validation
----------------
-
-SLUB can validate all object if the kernel was booted with slub_debug. In
-order to do so you must have the slabinfo tool. Then you can do
-
-slabinfo -v
-
-which will test all objects. Output will be generated to the syslog.
-
-This also works in a more limited way if boot was without slab debug.
-In that case slabinfo -v simply tests all reachable objects. Usually
-these are in the cpu slabs and the partial slabs. Full slabs are not
-tracked by SLUB in a non debug situation.
-
-Getting more performance
-------------------------
-
-To some degree SLUB's performance is limited by the need to take the
-list_lock once in a while to deal with partial slabs. That overhead is
-governed by the order of the allocation for each slab. The allocations
-can be influenced by kernel parameters:
-
-slub_min_objects=x (default 4)
-slub_min_order=x (default 0)
-slub_max_order=x (default 3 (PAGE_ALLOC_COSTLY_ORDER))
-
-slub_min_objects allows to specify how many objects must at least fit
-into one slab in order for the allocation order to be acceptable.
-In general slub will be able to perform this number of allocations
-on a slab without consulting centralized resources (list_lock) where
-contention may occur.
-
-slub_min_order specifies a minim order of slabs. A similar effect like
-slub_min_objects.
-
-slub_max_order specified the order at which slub_min_objects should no
-longer be checked. This is useful to avoid SLUB trying to generate
-super large order pages to fit slub_min_objects of a slab cache with
-large object sizes into one high order page. Setting command line
-parameter debug_guardpage_minorder=N (N > 0), forces setting
-slub_max_order to 0, what cause minimum possible order of slabs
-allocation.
-
-SLUB Debug output
------------------
-
-Here is a sample of slub debug output:
-
-====================================================================
-BUG kmalloc-8: Redzone overwritten
---------------------------------------------------------------------
-
-INFO: 0xc90f6d28-0xc90f6d2b. First byte 0x00 instead of 0xcc
-INFO: Slab 0xc528c530 flags=0x400000c3 inuse=61 fp=0xc90f6d58
-INFO: Object 0xc90f6d20 @offset=3360 fp=0xc90f6d58
-INFO: Allocated in get_modalias+0x61/0xf5 age=53 cpu=1 pid=554
-
-Bytes b4 0xc90f6d10: 00 00 00 00 00 00 00 00 5a 5a 5a 5a 5a 5a 5a 5a ........ZZZZZZZZ
- Object 0xc90f6d20: 31 30 31 39 2e 30 30 35 1019.005
- Redzone 0xc90f6d28: 00 cc cc cc .
- Padding 0xc90f6d50: 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZ
-
- [<c010523d>] dump_trace+0x63/0x1eb
- [<c01053df>] show_trace_log_lvl+0x1a/0x2f
- [<c010601d>] show_trace+0x12/0x14
- [<c0106035>] dump_stack+0x16/0x18
- [<c017e0fa>] object_err+0x143/0x14b
- [<c017e2cc>] check_object+0x66/0x234
- [<c017eb43>] __slab_free+0x239/0x384
- [<c017f446>] kfree+0xa6/0xc6
- [<c02e2335>] get_modalias+0xb9/0xf5
- [<c02e23b7>] dmi_dev_uevent+0x27/0x3c
- [<c027866a>] dev_uevent+0x1ad/0x1da
- [<c0205024>] kobject_uevent_env+0x20a/0x45b
- [<c020527f>] kobject_uevent+0xa/0xf
- [<c02779f1>] store_uevent+0x4f/0x58
- [<c027758e>] dev_attr_store+0x29/0x2f
- [<c01bec4f>] sysfs_write_file+0x16e/0x19c
- [<c0183ba7>] vfs_write+0xd1/0x15a
- [<c01841d7>] sys_write+0x3d/0x72
- [<c0104112>] sysenter_past_esp+0x5f/0x99
- [<b7f7b410>] 0xb7f7b410
- =======================
-
-FIX kmalloc-8: Restoring Redzone 0xc90f6d28-0xc90f6d2b=0xcc
-
-If SLUB encounters a corrupted object (full detection requires the kernel
-to be booted with slub_debug) then the following output will be dumped
-into the syslog:
-
-1. Description of the problem encountered
-
-This will be a message in the system log starting with
-
-===============================================
-BUG <slab cache affected>: <What went wrong>
------------------------------------------------
-
-INFO: <corruption start>-<corruption_end> <more info>
-INFO: Slab <address> <slab information>
-INFO: Object <address> <object information>
-INFO: Allocated in <kernel function> age=<jiffies since alloc> cpu=<allocated by
- cpu> pid=<pid of the process>
-INFO: Freed in <kernel function> age=<jiffies since free> cpu=<freed by cpu>
- pid=<pid of the process>
-
-(Object allocation / free information is only available if SLAB_STORE_USER is
-set for the slab. slub_debug sets that option)
-
-2. The object contents if an object was involved.
-
-Various types of lines can follow the BUG SLUB line:
-
-Bytes b4 <address> : <bytes>
- Shows a few bytes before the object where the problem was detected.
- Can be useful if the corruption does not stop with the start of the
- object.
-
-Object <address> : <bytes>
- The bytes of the object. If the object is inactive then the bytes
- typically contain poison values. Any non-poison value shows a
- corruption by a write after free.
-
-Redzone <address> : <bytes>
- The Redzone following the object. The Redzone is used to detect
- writes after the object. All bytes should always have the same
- value. If there is any deviation then it is due to a write after
- the object boundary.
-
- (Redzone information is only available if SLAB_RED_ZONE is set.
- slub_debug sets that option)
-
-Padding <address> : <bytes>
- Unused data to fill up the space in order to get the next object
- properly aligned. In the debug case we make sure that there are
- at least 4 bytes of padding. This allows the detection of writes
- before the object.
-
-3. A stackdump
-
-The stackdump describes the location where the error was detected. The cause
-of the corruption is may be more likely found by looking at the function that
-allocated or freed the object.
-
-4. Report on how the problem was dealt with in order to ensure the continued
-operation of the system.
-
-These are messages in the system log beginning with
-
-FIX <slab cache affected>: <corrective action taken>
-
-In the above sample SLUB found that the Redzone of an active object has
-been overwritten. Here a string of 8 characters was written into a slab that
-has the length of 8 characters. However, a 8 character string needs a
-terminating 0. That zero has overwritten the first byte of the Redzone field.
-After reporting the details of the issue encountered the FIX SLUB message
-tells us that SLUB has restored the Redzone to its proper value and then
-system operations continue.
-
-Emergency operations:
----------------------
-
-Minimal debugging (sanity checks alone) can be enabled by booting with
-
- slub_debug=F
-
-This will be generally be enough to enable the resiliency features of slub
-which will keep the system running even if a bad kernel component will
-keep corrupting objects. This may be important for production systems.
-Performance will be impacted by the sanity checks and there will be a
-continual stream of error messages to the syslog but no additional memory
-will be used (unlike full debugging).
-
-No guarantees. The kernel component still needs to be fixed. Performance
-may be optimized further by locating the slab that experiences corruption
-and enabling debugging only for that cache
-
-I.e.
-
- slub_debug=F,dentry
-
-If the corruption occurs by writing after the end of the object then it
-may be advisable to enable a Redzone to avoid corrupting the beginning
-of other objects.
-
- slub_debug=FZ,dentry
-
-Extended slabinfo mode and plotting
------------------------------------
-
-The slabinfo tool has a special 'extended' ('-X') mode that includes:
- - Slabcache Totals
- - Slabs sorted by size (up to -N <num> slabs, default 1)
- - Slabs sorted by loss (up to -N <num> slabs, default 1)
-
-Additionally, in this mode slabinfo does not dynamically scale sizes (G/M/K)
-and reports everything in bytes (this functionality is also available to
-other slabinfo modes via '-B' option) which makes reporting more precise and
-accurate. Moreover, in some sense the `-X' mode also simplifies the analysis
-of slabs' behaviour, because its output can be plotted using the
-slabinfo-gnuplot.sh script. So it pushes the analysis from looking through
-the numbers (tons of numbers) to something easier -- visual analysis.
-
-To generate plots:
-a) collect slabinfo extended records, for example:
-
- while [ 1 ]; do slabinfo -X >> FOO_STATS; sleep 1; done
-
-b) pass stats file(-s) to slabinfo-gnuplot.sh script:
- slabinfo-gnuplot.sh FOO_STATS [FOO_STATS2 .. FOO_STATSN]
-
-The slabinfo-gnuplot.sh script will pre-processes the collected records
-and generates 3 png files (and 3 pre-processing cache files) per STATS
-file:
- - Slabcache Totals: FOO_STATS-totals.png
- - Slabs sorted by size: FOO_STATS-slabs-by-size.png
- - Slabs sorted by loss: FOO_STATS-slabs-by-loss.png
-
-Another use case, when slabinfo-gnuplot can be useful, is when you need
-to compare slabs' behaviour "prior to" and "after" some code modification.
-To help you out there, slabinfo-gnuplot.sh script can 'merge' the
-`Slabcache Totals` sections from different measurements. To visually
-compare N plots:
-
-a) Collect as many STATS1, STATS2, .. STATSN files as you need
- while [ 1 ]; do slabinfo -X >> STATS<X>; sleep 1; done
-
-b) Pre-process those STATS files
- slabinfo-gnuplot.sh STATS1 STATS2 .. STATSN
-
-c) Execute slabinfo-gnuplot.sh in '-t' mode, passing all of the
-generated pre-processed *-totals
- slabinfo-gnuplot.sh -t STATS1-totals STATS2-totals .. STATSN-totals
-
-This will produce a single plot (png file).
-
-Plots, expectedly, can be large so some fluctuations or small spikes
-can go unnoticed. To deal with that, `slabinfo-gnuplot.sh' has two
-options to 'zoom-in'/'zoom-out':
- a) -s %d,%d overwrites the default image width and heigh
- b) -r %d,%d specifies a range of samples to use (for example,
- in `slabinfo -X >> FOO_STATS; sleep 1;' case, using
- a "-r 40,60" range will plot only samples collected
- between 40th and 60th seconds).
-
-Christoph Lameter, May 30, 2007
-Sergey Senozhatsky, October 23, 2015
diff --git a/Documentation/vm/split_page_table_lock b/Documentation/vm/split_page_table_lock.rst
similarity index 95%
rename from Documentation/vm/split_page_table_lock
rename to Documentation/vm/split_page_table_lock.rst
index 62842a8..889b00b 100644
--- a/Documentation/vm/split_page_table_lock
+++ b/Documentation/vm/split_page_table_lock.rst
@@ -1,3 +1,6 @@
+.. _split_page_table_lock:
+
+=====================
Split page table lock
=====================
@@ -11,6 +14,7 @@
tables. Access to higher level tables protected by mm->page_table_lock.
There are helpers to lock/unlock a table and other accessor functions:
+
- pte_offset_map_lock()
maps pte and takes PTE table lock, returns pointer to the taken
lock;
@@ -34,12 +38,13 @@
tables and the architecture supports it (see below).
Hugetlb and split page table lock
----------------------------------
+=================================
Hugetlb can support several page sizes. We use split lock only for PMD
level, but not for PUD.
Hugetlb-specific helpers:
+
- huge_pte_lock()
takes pmd split lock for PMD_SIZE page, mm->page_table_lock
otherwise;
@@ -47,7 +52,7 @@
returns pointer to table lock;
Support of split page table lock by an architecture
----------------------------------------------------
+===================================================
There's no need in special enabling of PTE split page table lock:
everything required is done by pgtable_page_ctor() and pgtable_page_dtor(),
@@ -73,7 +78,7 @@
be handled properly.
page->ptl
----------
+=========
page->ptl is used to access split page table lock, where 'page' is struct
page of page containing the table. It shares storage with page->private
@@ -81,6 +86,7 @@
To avoid increasing size of struct page and have best performance, we use a
trick:
+
- if spinlock_t fits into long, we use page->ptr as spinlock, so we
can avoid indirect access and save a cache line.
- if size of spinlock_t is bigger then size of long, we use page->ptl as
diff --git a/Documentation/vm/swap_numa.txt b/Documentation/vm/swap_numa.rst
similarity index 74%
rename from Documentation/vm/swap_numa.txt
rename to Documentation/vm/swap_numa.rst
index d5960c9..e0466f2 100644
--- a/Documentation/vm/swap_numa.txt
+++ b/Documentation/vm/swap_numa.rst
@@ -1,5 +1,8 @@
+.. _swap_numa:
+
+===========================================
Automatically bind swap device to numa node
--------------------------------------------
+===========================================
If the system has more than one swap device and swap device has the node
information, we can make use of this information to decide which swap
@@ -7,15 +10,16 @@
How to use this feature
------------------------
+=======================
Swap device has priority and that decides the order of it to be used. To make
use of automatically binding, there is no need to manipulate priority settings
for swap devices. e.g. on a 2 node machine, assume 2 swap devices swapA and
swapB, with swapA attached to node 0 and swapB attached to node 1, are going
-to be swapped on. Simply swapping them on by doing:
-# swapon /dev/swapA
-# swapon /dev/swapB
+to be swapped on. Simply swapping them on by doing::
+
+ # swapon /dev/swapA
+ # swapon /dev/swapB
Then node 0 will use the two swap devices in the order of swapA then swapB and
node 1 will use the two swap devices in the order of swapB then swapA. Note
@@ -24,32 +28,39 @@
A more complex example on a 4 node machine. Assume 6 swap devices are going to
be swapped on: swapA and swapB are attached to node 0, swapC is attached to
node 1, swapD and swapE are attached to node 2 and swapF is attached to node3.
-The way to swap them on is the same as above:
-# swapon /dev/swapA
-# swapon /dev/swapB
-# swapon /dev/swapC
-# swapon /dev/swapD
-# swapon /dev/swapE
-# swapon /dev/swapF
+The way to swap them on is the same as above::
-Then node 0 will use them in the order of:
-swapA/swapB -> swapC -> swapD -> swapE -> swapF
+ # swapon /dev/swapA
+ # swapon /dev/swapB
+ # swapon /dev/swapC
+ # swapon /dev/swapD
+ # swapon /dev/swapE
+ # swapon /dev/swapF
+
+Then node 0 will use them in the order of::
+
+ swapA/swapB -> swapC -> swapD -> swapE -> swapF
+
swapA and swapB will be used in a round robin mode before any other swap device.
-node 1 will use them in the order of:
-swapC -> swapA -> swapB -> swapD -> swapE -> swapF
+node 1 will use them in the order of::
-node 2 will use them in the order of:
-swapD/swapE -> swapA -> swapB -> swapC -> swapF
+ swapC -> swapA -> swapB -> swapD -> swapE -> swapF
+
+node 2 will use them in the order of::
+
+ swapD/swapE -> swapA -> swapB -> swapC -> swapF
+
Similaly, swapD and swapE will be used in a round robin mode before any
other swap devices.
-node 3 will use them in the order of:
-swapF -> swapA -> swapB -> swapC -> swapD -> swapE
+node 3 will use them in the order of::
+
+ swapF -> swapA -> swapB -> swapC -> swapD -> swapE
Implementation details
-----------------------
+======================
The current code uses a priority based list, swap_avail_list, to decide
which swap device to use and if multiple swap devices share the same
diff --git a/Documentation/vm/transhuge.rst b/Documentation/vm/transhuge.rst
new file mode 100644
index 0000000..a8cf680
--- /dev/null
+++ b/Documentation/vm/transhuge.rst
@@ -0,0 +1,197 @@
+.. _transhuge:
+
+============================
+Transparent Hugepage Support
+============================
+
+This document describes design principles Transparent Hugepage (THP)
+Support and its interaction with other parts of the memory management.
+
+Design principles
+=================
+
+- "graceful fallback": mm components which don't have transparent hugepage
+ knowledge fall back to breaking huge pmd mapping into table of ptes and,
+ if necessary, split a transparent hugepage. Therefore these components
+ can continue working on the regular pages or regular pte mappings.
+
+- if a hugepage allocation fails because of memory fragmentation,
+ regular pages should be gracefully allocated instead and mixed in
+ the same vma without any failure or significant delay and without
+ userland noticing
+
+- if some task quits and more hugepages become available (either
+ immediately in the buddy or through the VM), guest physical memory
+ backed by regular pages should be relocated on hugepages
+ automatically (with khugepaged)
+
+- it doesn't require memory reservation and in turn it uses hugepages
+ whenever possible (the only possible reservation here is kernelcore=
+ to avoid unmovable pages to fragment all the memory but such a tweak
+ is not specific to transparent hugepage support and it's a generic
+ feature that applies to all dynamic high order allocations in the
+ kernel)
+
+get_user_pages and follow_page
+==============================
+
+get_user_pages and follow_page if run on a hugepage, will return the
+head or tail pages as usual (exactly as they would do on
+hugetlbfs). Most gup users will only care about the actual physical
+address of the page and its temporary pinning to release after the I/O
+is complete, so they won't ever notice the fact the page is huge. But
+if any driver is going to mangle over the page structure of the tail
+page (like for checking page->mapping or other bits that are relevant
+for the head page and not the tail page), it should be updated to jump
+to check head page instead. Taking reference on any head/tail page would
+prevent page from being split by anyone.
+
+.. note::
+ these aren't new constraints to the GUP API, and they match the
+ same constrains that applies to hugetlbfs too, so any driver capable
+ of handling GUP on hugetlbfs will also work fine on transparent
+ hugepage backed mappings.
+
+In case you can't handle compound pages if they're returned by
+follow_page, the FOLL_SPLIT bit can be specified as parameter to
+follow_page, so that it will split the hugepages before returning
+them. Migration for example passes FOLL_SPLIT as parameter to
+follow_page because it's not hugepage aware and in fact it can't work
+at all on hugetlbfs (but it instead works fine on transparent
+hugepages thanks to FOLL_SPLIT). migration simply can't deal with
+hugepages being returned (as it's not only checking the pfn of the
+page and pinning it during the copy but it pretends to migrate the
+memory in regular page sizes and with regular pte/pmd mappings).
+
+Graceful fallback
+=================
+
+Code walking pagetables but unaware about huge pmds can simply call
+split_huge_pmd(vma, pmd, addr) where the pmd is the one returned by
+pmd_offset. It's trivial to make the code transparent hugepage aware
+by just grepping for "pmd_offset" and adding split_huge_pmd where
+missing after pmd_offset returns the pmd. Thanks to the graceful
+fallback design, with a one liner change, you can avoid to write
+hundred if not thousand of lines of complex code to make your code
+hugepage aware.
+
+If you're not walking pagetables but you run into a physical hugepage
+but you can't handle it natively in your code, you can split it by
+calling split_huge_page(page). This is what the Linux VM does before
+it tries to swapout the hugepage for example. split_huge_page() can fail
+if the page is pinned and you must handle this correctly.
+
+Example to make mremap.c transparent hugepage aware with a one liner
+change::
+
+ diff --git a/mm/mremap.c b/mm/mremap.c
+ --- a/mm/mremap.c
+ +++ b/mm/mremap.c
+ @@ -41,6 +41,7 @@ static pmd_t *get_old_pmd(struct mm_stru
+ return NULL;
+
+ pmd = pmd_offset(pud, addr);
+ + split_huge_pmd(vma, pmd, addr);
+ if (pmd_none_or_clear_bad(pmd))
+ return NULL;
+
+Locking in hugepage aware code
+==============================
+
+We want as much code as possible hugepage aware, as calling
+split_huge_page() or split_huge_pmd() has a cost.
+
+To make pagetable walks huge pmd aware, all you need to do is to call
+pmd_trans_huge() on the pmd returned by pmd_offset. You must hold the
+mmap_sem in read (or write) mode to be sure an huge pmd cannot be
+created from under you by khugepaged (khugepaged collapse_huge_page
+takes the mmap_sem in write mode in addition to the anon_vma lock). If
+pmd_trans_huge returns false, you just fallback in the old code
+paths. If instead pmd_trans_huge returns true, you have to take the
+page table lock (pmd_lock()) and re-run pmd_trans_huge. Taking the
+page table lock will prevent the huge pmd to be converted into a
+regular pmd from under you (split_huge_pmd can run in parallel to the
+pagetable walk). If the second pmd_trans_huge returns false, you
+should just drop the page table lock and fallback to the old code as
+before. Otherwise you can proceed to process the huge pmd and the
+hugepage natively. Once finished you can drop the page table lock.
+
+Refcounts and transparent huge pages
+====================================
+
+Refcounting on THP is mostly consistent with refcounting on other compound
+pages:
+
+ - get_page()/put_page() and GUP operate in head page's ->_refcount.
+
+ - ->_refcount in tail pages is always zero: get_page_unless_zero() never
+ succeed on tail pages.
+
+ - map/unmap of the pages with PTE entry increment/decrement ->_mapcount
+ on relevant sub-page of the compound page.
+
+ - map/unmap of the whole compound page accounted in compound_mapcount
+ (stored in first tail page). For file huge pages, we also increment
+ ->_mapcount of all sub-pages in order to have race-free detection of
+ last unmap of subpages.
+
+PageDoubleMap() indicates that the page is *possibly* mapped with PTEs.
+
+For anonymous pages PageDoubleMap() also indicates ->_mapcount in all
+subpages is offset up by one. This additional reference is required to
+get race-free detection of unmap of subpages when we have them mapped with
+both PMDs and PTEs.
+
+This is optimization required to lower overhead of per-subpage mapcount
+tracking. The alternative is alter ->_mapcount in all subpages on each
+map/unmap of the whole compound page.
+
+For anonymous pages, we set PG_double_map when a PMD of the page got split
+for the first time, but still have PMD mapping. The additional references
+go away with last compound_mapcount.
+
+File pages get PG_double_map set on first map of the page with PTE and
+goes away when the page gets evicted from page cache.
+
+split_huge_page internally has to distribute the refcounts in the head
+page to the tail pages before clearing all PG_head/tail bits from the page
+structures. It can be done easily for refcounts taken by page table
+entries. But we don't have enough information on how to distribute any
+additional pins (i.e. from get_user_pages). split_huge_page() fails any
+requests to split pinned huge page: it expects page count to be equal to
+sum of mapcount of all sub-pages plus one (split_huge_page caller must
+have reference for head page).
+
+split_huge_page uses migration entries to stabilize page->_refcount and
+page->_mapcount of anonymous pages. File pages just got unmapped.
+
+We safe against physical memory scanners too: the only legitimate way
+scanner can get reference to a page is get_page_unless_zero().
+
+All tail pages have zero ->_refcount until atomic_add(). This prevents the
+scanner from getting a reference to the tail page up to that point. After the
+atomic_add() we don't care about the ->_refcount value. We already known how
+many references should be uncharged from the head page.
+
+For head page get_page_unless_zero() will succeed and we don't mind. It's
+clear where reference should go after split: it will stay on head page.
+
+Note that split_huge_pmd() doesn't have any limitation on refcounting:
+pmd can be split at any point and never fails.
+
+Partial unmap and deferred_split_huge_page()
+============================================
+
+Unmapping part of THP (with munmap() or other way) is not going to free
+memory immediately. Instead, we detect that a subpage of THP is not in use
+in page_remove_rmap() and queue the THP for splitting if memory pressure
+comes. Splitting will free up unused subpages.
+
+Splitting the page right away is not an option due to locking context in
+the place where we can detect partial unmap. It's also might be
+counterproductive since in many cases partial unmap happens during exit(2) if
+a THP crosses a VMA boundary.
+
+Function deferred_split_huge_page() is used to queue page for splitting.
+The splitting itself will happen when we get memory pressure via shrinker
+interface.
diff --git a/Documentation/vm/transhuge.txt b/Documentation/vm/transhuge.txt
deleted file mode 100644
index 4dde03b..0000000
--- a/Documentation/vm/transhuge.txt
+++ /dev/null
@@ -1,527 +0,0 @@
-= Transparent Hugepage Support =
-
-== Objective ==
-
-Performance critical computing applications dealing with large memory
-working sets are already running on top of libhugetlbfs and in turn
-hugetlbfs. Transparent Hugepage Support is an alternative means of
-using huge pages for the backing of virtual memory with huge pages
-that supports the automatic promotion and demotion of page sizes and
-without the shortcomings of hugetlbfs.
-
-Currently it only works for anonymous memory mappings and tmpfs/shmem.
-But in the future it can expand to other filesystems.
-
-The reason applications are running faster is because of two
-factors. The first factor is almost completely irrelevant and it's not
-of significant interest because it'll also have the downside of
-requiring larger clear-page copy-page in page faults which is a
-potentially negative effect. The first factor consists in taking a
-single page fault for each 2M virtual region touched by userland (so
-reducing the enter/exit kernel frequency by a 512 times factor). This
-only matters the first time the memory is accessed for the lifetime of
-a memory mapping. The second long lasting and much more important
-factor will affect all subsequent accesses to the memory for the whole
-runtime of the application. The second factor consist of two
-components: 1) the TLB miss will run faster (especially with
-virtualization using nested pagetables but almost always also on bare
-metal without virtualization) and 2) a single TLB entry will be
-mapping a much larger amount of virtual memory in turn reducing the
-number of TLB misses. With virtualization and nested pagetables the
-TLB can be mapped of larger size only if both KVM and the Linux guest
-are using hugepages but a significant speedup already happens if only
-one of the two is using hugepages just because of the fact the TLB
-miss is going to run faster.
-
-== Design ==
-
-- "graceful fallback": mm components which don't have transparent hugepage
- knowledge fall back to breaking huge pmd mapping into table of ptes and,
- if necessary, split a transparent hugepage. Therefore these components
- can continue working on the regular pages or regular pte mappings.
-
-- if a hugepage allocation fails because of memory fragmentation,
- regular pages should be gracefully allocated instead and mixed in
- the same vma without any failure or significant delay and without
- userland noticing
-
-- if some task quits and more hugepages become available (either
- immediately in the buddy or through the VM), guest physical memory
- backed by regular pages should be relocated on hugepages
- automatically (with khugepaged)
-
-- it doesn't require memory reservation and in turn it uses hugepages
- whenever possible (the only possible reservation here is kernelcore=
- to avoid unmovable pages to fragment all the memory but such a tweak
- is not specific to transparent hugepage support and it's a generic
- feature that applies to all dynamic high order allocations in the
- kernel)
-
-Transparent Hugepage Support maximizes the usefulness of free memory
-if compared to the reservation approach of hugetlbfs by allowing all
-unused memory to be used as cache or other movable (or even unmovable
-entities). It doesn't require reservation to prevent hugepage
-allocation failures to be noticeable from userland. It allows paging
-and all other advanced VM features to be available on the
-hugepages. It requires no modifications for applications to take
-advantage of it.
-
-Applications however can be further optimized to take advantage of
-this feature, like for example they've been optimized before to avoid
-a flood of mmap system calls for every malloc(4k). Optimizing userland
-is by far not mandatory and khugepaged already can take care of long
-lived page allocations even for hugepage unaware applications that
-deals with large amounts of memory.
-
-In certain cases when hugepages are enabled system wide, application
-may end up allocating more memory resources. An application may mmap a
-large region but only touch 1 byte of it, in that case a 2M page might
-be allocated instead of a 4k page for no good. This is why it's
-possible to disable hugepages system-wide and to only have them inside
-MADV_HUGEPAGE madvise regions.
-
-Embedded systems should enable hugepages only inside madvise regions
-to eliminate any risk of wasting any precious byte of memory and to
-only run faster.
-
-Applications that gets a lot of benefit from hugepages and that don't
-risk to lose memory by using hugepages, should use
-madvise(MADV_HUGEPAGE) on their critical mmapped regions.
-
-== sysfs ==
-
-Transparent Hugepage Support for anonymous memory can be entirely disabled
-(mostly for debugging purposes) or only enabled inside MADV_HUGEPAGE
-regions (to avoid the risk of consuming more memory resources) or enabled
-system wide. This can be achieved with one of:
-
-echo always >/sys/kernel/mm/transparent_hugepage/enabled
-echo madvise >/sys/kernel/mm/transparent_hugepage/enabled
-echo never >/sys/kernel/mm/transparent_hugepage/enabled
-
-It's also possible to limit defrag efforts in the VM to generate
-anonymous hugepages in case they're not immediately free to madvise
-regions or to never try to defrag memory and simply fallback to regular
-pages unless hugepages are immediately available. Clearly if we spend CPU
-time to defrag memory, we would expect to gain even more by the fact we
-use hugepages later instead of regular pages. This isn't always
-guaranteed, but it may be more likely in case the allocation is for a
-MADV_HUGEPAGE region.
-
-echo always >/sys/kernel/mm/transparent_hugepage/defrag
-echo defer >/sys/kernel/mm/transparent_hugepage/defrag
-echo defer+madvise >/sys/kernel/mm/transparent_hugepage/defrag
-echo madvise >/sys/kernel/mm/transparent_hugepage/defrag
-echo never >/sys/kernel/mm/transparent_hugepage/defrag
-
-"always" means that an application requesting THP will stall on allocation
-failure and directly reclaim pages and compact memory in an effort to
-allocate a THP immediately. This may be desirable for virtual machines
-that benefit heavily from THP use and are willing to delay the VM start
-to utilise them.
-
-"defer" means that an application will wake kswapd in the background
-to reclaim pages and wake kcompactd to compact memory so that THP is
-available in the near future. It's the responsibility of khugepaged
-to then install the THP pages later.
-
-"defer+madvise" will enter direct reclaim and compaction like "always", but
-only for regions that have used madvise(MADV_HUGEPAGE); all other regions
-will wake kswapd in the background to reclaim pages and wake kcompactd to
-compact memory so that THP is available in the near future.
-
-"madvise" will enter direct reclaim like "always" but only for regions
-that are have used madvise(MADV_HUGEPAGE). This is the default behaviour.
-
-"never" should be self-explanatory.
-
-By default kernel tries to use huge zero page on read page fault to
-anonymous mapping. It's possible to disable huge zero page by writing 0
-or enable it back by writing 1:
-
-echo 0 >/sys/kernel/mm/transparent_hugepage/use_zero_page
-echo 1 >/sys/kernel/mm/transparent_hugepage/use_zero_page
-
-Some userspace (such as a test program, or an optimized memory allocation
-library) may want to know the size (in bytes) of a transparent hugepage:
-
-cat /sys/kernel/mm/transparent_hugepage/hpage_pmd_size
-
-khugepaged will be automatically started when
-transparent_hugepage/enabled is set to "always" or "madvise, and it'll
-be automatically shutdown if it's set to "never".
-
-khugepaged runs usually at low frequency so while one may not want to
-invoke defrag algorithms synchronously during the page faults, it
-should be worth invoking defrag at least in khugepaged. However it's
-also possible to disable defrag in khugepaged by writing 0 or enable
-defrag in khugepaged by writing 1:
-
-echo 0 >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag
-echo 1 >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag
-
-You can also control how many pages khugepaged should scan at each
-pass:
-
-/sys/kernel/mm/transparent_hugepage/khugepaged/pages_to_scan
-
-and how many milliseconds to wait in khugepaged between each pass (you
-can set this to 0 to run khugepaged at 100% utilization of one core):
-
-/sys/kernel/mm/transparent_hugepage/khugepaged/scan_sleep_millisecs
-
-and how many milliseconds to wait in khugepaged if there's an hugepage
-allocation failure to throttle the next allocation attempt.
-
-/sys/kernel/mm/transparent_hugepage/khugepaged/alloc_sleep_millisecs
-
-The khugepaged progress can be seen in the number of pages collapsed:
-
-/sys/kernel/mm/transparent_hugepage/khugepaged/pages_collapsed
-
-for each pass:
-
-/sys/kernel/mm/transparent_hugepage/khugepaged/full_scans
-
-max_ptes_none specifies how many extra small pages (that are
-not already mapped) can be allocated when collapsing a group
-of small pages into one large page.
-
-/sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_none
-
-A higher value leads to use additional memory for programs.
-A lower value leads to gain less thp performance. Value of
-max_ptes_none can waste cpu time very little, you can
-ignore it.
-
-max_ptes_swap specifies how many pages can be brought in from
-swap when collapsing a group of pages into a transparent huge page.
-
-/sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_swap
-
-A higher value can cause excessive swap IO and waste
-memory. A lower value can prevent THPs from being
-collapsed, resulting fewer pages being collapsed into
-THPs, and lower memory access performance.
-
-== Boot parameter ==
-
-You can change the sysfs boot time defaults of Transparent Hugepage
-Support by passing the parameter "transparent_hugepage=always" or
-"transparent_hugepage=madvise" or "transparent_hugepage=never"
-(without "") to the kernel command line.
-
-== Hugepages in tmpfs/shmem ==
-
-You can control hugepage allocation policy in tmpfs with mount option
-"huge=". It can have following values:
-
- - "always":
- Attempt to allocate huge pages every time we need a new page;
-
- - "never":
- Do not allocate huge pages;
-
- - "within_size":
- Only allocate huge page if it will be fully within i_size.
- Also respect fadvise()/madvise() hints;
-
- - "advise:
- Only allocate huge pages if requested with fadvise()/madvise();
-
-The default policy is "never".
-
-"mount -o remount,huge= /mountpoint" works fine after mount: remounting
-huge=never will not attempt to break up huge pages at all, just stop more
-from being allocated.
-
-There's also sysfs knob to control hugepage allocation policy for internal
-shmem mount: /sys/kernel/mm/transparent_hugepage/shmem_enabled. The mount
-is used for SysV SHM, memfds, shared anonymous mmaps (of /dev/zero or
-MAP_ANONYMOUS), GPU drivers' DRM objects, Ashmem.
-
-In addition to policies listed above, shmem_enabled allows two further
-values:
-
- - "deny":
- For use in emergencies, to force the huge option off from
- all mounts;
- - "force":
- Force the huge option on for all - very useful for testing;
-
-== Need of application restart ==
-
-The transparent_hugepage/enabled values and tmpfs mount option only affect
-future behavior. So to make them effective you need to restart any
-application that could have been using hugepages. This also applies to the
-regions registered in khugepaged.
-
-== Monitoring usage ==
-
-The number of anonymous transparent huge pages currently used by the
-system is available by reading the AnonHugePages field in /proc/meminfo.
-To identify what applications are using anonymous transparent huge pages,
-it is necessary to read /proc/PID/smaps and count the AnonHugePages fields
-for each mapping.
-
-The number of file transparent huge pages mapped to userspace is available
-by reading ShmemPmdMapped and ShmemHugePages fields in /proc/meminfo.
-To identify what applications are mapping file transparent huge pages, it
-is necessary to read /proc/PID/smaps and count the FileHugeMapped fields
-for each mapping.
-
-Note that reading the smaps file is expensive and reading it
-frequently will incur overhead.
-
-There are a number of counters in /proc/vmstat that may be used to
-monitor how successfully the system is providing huge pages for use.
-
-thp_fault_alloc is incremented every time a huge page is successfully
- allocated to handle a page fault. This applies to both the
- first time a page is faulted and for COW faults.
-
-thp_collapse_alloc is incremented by khugepaged when it has found
- a range of pages to collapse into one huge page and has
- successfully allocated a new huge page to store the data.
-
-thp_fault_fallback is incremented if a page fault fails to allocate
- a huge page and instead falls back to using small pages.
-
-thp_collapse_alloc_failed is incremented if khugepaged found a range
- of pages that should be collapsed into one huge page but failed
- the allocation.
-
-thp_file_alloc is incremented every time a file huge page is successfully
- allocated.
-
-thp_file_mapped is incremented every time a file huge page is mapped into
- user address space.
-
-thp_split_page is incremented every time a huge page is split into base
- pages. This can happen for a variety of reasons but a common
- reason is that a huge page is old and is being reclaimed.
- This action implies splitting all PMD the page mapped with.
-
-thp_split_page_failed is incremented if kernel fails to split huge
- page. This can happen if the page was pinned by somebody.
-
-thp_deferred_split_page is incremented when a huge page is put onto split
- queue. This happens when a huge page is partially unmapped and
- splitting it would free up some memory. Pages on split queue are
- going to be split under memory pressure.
-
-thp_split_pmd is incremented every time a PMD split into table of PTEs.
- This can happen, for instance, when application calls mprotect() or
- munmap() on part of huge page. It doesn't split huge page, only
- page table entry.
-
-thp_zero_page_alloc is incremented every time a huge zero page is
- successfully allocated. It includes allocations which where
- dropped due race with other allocation. Note, it doesn't count
- every map of the huge zero page, only its allocation.
-
-thp_zero_page_alloc_failed is incremented if kernel fails to allocate
- huge zero page and falls back to using small pages.
-
-As the system ages, allocating huge pages may be expensive as the
-system uses memory compaction to copy data around memory to free a
-huge page for use. There are some counters in /proc/vmstat to help
-monitor this overhead.
-
-compact_stall is incremented every time a process stalls to run
- memory compaction so that a huge page is free for use.
-
-compact_success is incremented if the system compacted memory and
- freed a huge page for use.
-
-compact_fail is incremented if the system tries to compact memory
- but failed.
-
-compact_pages_moved is incremented each time a page is moved. If
- this value is increasing rapidly, it implies that the system
- is copying a lot of data to satisfy the huge page allocation.
- It is possible that the cost of copying exceeds any savings
- from reduced TLB misses.
-
-compact_pagemigrate_failed is incremented when the underlying mechanism
- for moving a page failed.
-
-compact_blocks_moved is incremented each time memory compaction examines
- a huge page aligned range of pages.
-
-It is possible to establish how long the stalls were using the function
-tracer to record how long was spent in __alloc_pages_nodemask and
-using the mm_page_alloc tracepoint to identify which allocations were
-for huge pages.
-
-== get_user_pages and follow_page ==
-
-get_user_pages and follow_page if run on a hugepage, will return the
-head or tail pages as usual (exactly as they would do on
-hugetlbfs). Most gup users will only care about the actual physical
-address of the page and its temporary pinning to release after the I/O
-is complete, so they won't ever notice the fact the page is huge. But
-if any driver is going to mangle over the page structure of the tail
-page (like for checking page->mapping or other bits that are relevant
-for the head page and not the tail page), it should be updated to jump
-to check head page instead. Taking reference on any head/tail page would
-prevent page from being split by anyone.
-
-NOTE: these aren't new constraints to the GUP API, and they match the
-same constrains that applies to hugetlbfs too, so any driver capable
-of handling GUP on hugetlbfs will also work fine on transparent
-hugepage backed mappings.
-
-In case you can't handle compound pages if they're returned by
-follow_page, the FOLL_SPLIT bit can be specified as parameter to
-follow_page, so that it will split the hugepages before returning
-them. Migration for example passes FOLL_SPLIT as parameter to
-follow_page because it's not hugepage aware and in fact it can't work
-at all on hugetlbfs (but it instead works fine on transparent
-hugepages thanks to FOLL_SPLIT). migration simply can't deal with
-hugepages being returned (as it's not only checking the pfn of the
-page and pinning it during the copy but it pretends to migrate the
-memory in regular page sizes and with regular pte/pmd mappings).
-
-== Optimizing the applications ==
-
-To be guaranteed that the kernel will map a 2M page immediately in any
-memory region, the mmap region has to be hugepage naturally
-aligned. posix_memalign() can provide that guarantee.
-
-== Hugetlbfs ==
-
-You can use hugetlbfs on a kernel that has transparent hugepage
-support enabled just fine as always. No difference can be noted in
-hugetlbfs other than there will be less overall fragmentation. All
-usual features belonging to hugetlbfs are preserved and
-unaffected. libhugetlbfs will also work fine as usual.
-
-== Graceful fallback ==
-
-Code walking pagetables but unaware about huge pmds can simply call
-split_huge_pmd(vma, pmd, addr) where the pmd is the one returned by
-pmd_offset. It's trivial to make the code transparent hugepage aware
-by just grepping for "pmd_offset" and adding split_huge_pmd where
-missing after pmd_offset returns the pmd. Thanks to the graceful
-fallback design, with a one liner change, you can avoid to write
-hundred if not thousand of lines of complex code to make your code
-hugepage aware.
-
-If you're not walking pagetables but you run into a physical hugepage
-but you can't handle it natively in your code, you can split it by
-calling split_huge_page(page). This is what the Linux VM does before
-it tries to swapout the hugepage for example. split_huge_page() can fail
-if the page is pinned and you must handle this correctly.
-
-Example to make mremap.c transparent hugepage aware with a one liner
-change:
-
-diff --git a/mm/mremap.c b/mm/mremap.c
---- a/mm/mremap.c
-+++ b/mm/mremap.c
-@@ -41,6 +41,7 @@ static pmd_t *get_old_pmd(struct mm_stru
- return NULL;
-
- pmd = pmd_offset(pud, addr);
-+ split_huge_pmd(vma, pmd, addr);
- if (pmd_none_or_clear_bad(pmd))
- return NULL;
-
-== Locking in hugepage aware code ==
-
-We want as much code as possible hugepage aware, as calling
-split_huge_page() or split_huge_pmd() has a cost.
-
-To make pagetable walks huge pmd aware, all you need to do is to call
-pmd_trans_huge() on the pmd returned by pmd_offset. You must hold the
-mmap_sem in read (or write) mode to be sure an huge pmd cannot be
-created from under you by khugepaged (khugepaged collapse_huge_page
-takes the mmap_sem in write mode in addition to the anon_vma lock). If
-pmd_trans_huge returns false, you just fallback in the old code
-paths. If instead pmd_trans_huge returns true, you have to take the
-page table lock (pmd_lock()) and re-run pmd_trans_huge. Taking the
-page table lock will prevent the huge pmd to be converted into a
-regular pmd from under you (split_huge_pmd can run in parallel to the
-pagetable walk). If the second pmd_trans_huge returns false, you
-should just drop the page table lock and fallback to the old code as
-before. Otherwise you can proceed to process the huge pmd and the
-hugepage natively. Once finished you can drop the page table lock.
-
-== Refcounts and transparent huge pages ==
-
-Refcounting on THP is mostly consistent with refcounting on other compound
-pages:
-
- - get_page()/put_page() and GUP operate in head page's ->_refcount.
-
- - ->_refcount in tail pages is always zero: get_page_unless_zero() never
- succeed on tail pages.
-
- - map/unmap of the pages with PTE entry increment/decrement ->_mapcount
- on relevant sub-page of the compound page.
-
- - map/unmap of the whole compound page accounted in compound_mapcount
- (stored in first tail page). For file huge pages, we also increment
- ->_mapcount of all sub-pages in order to have race-free detection of
- last unmap of subpages.
-
-PageDoubleMap() indicates that the page is *possibly* mapped with PTEs.
-
-For anonymous pages PageDoubleMap() also indicates ->_mapcount in all
-subpages is offset up by one. This additional reference is required to
-get race-free detection of unmap of subpages when we have them mapped with
-both PMDs and PTEs.
-
-This is optimization required to lower overhead of per-subpage mapcount
-tracking. The alternative is alter ->_mapcount in all subpages on each
-map/unmap of the whole compound page.
-
-For anonymous pages, we set PG_double_map when a PMD of the page got split
-for the first time, but still have PMD mapping. The additional references
-go away with last compound_mapcount.
-
-File pages get PG_double_map set on first map of the page with PTE and
-goes away when the page gets evicted from page cache.
-
-split_huge_page internally has to distribute the refcounts in the head
-page to the tail pages before clearing all PG_head/tail bits from the page
-structures. It can be done easily for refcounts taken by page table
-entries. But we don't have enough information on how to distribute any
-additional pins (i.e. from get_user_pages). split_huge_page() fails any
-requests to split pinned huge page: it expects page count to be equal to
-sum of mapcount of all sub-pages plus one (split_huge_page caller must
-have reference for head page).
-
-split_huge_page uses migration entries to stabilize page->_refcount and
-page->_mapcount of anonymous pages. File pages just got unmapped.
-
-We safe against physical memory scanners too: the only legitimate way
-scanner can get reference to a page is get_page_unless_zero().
-
-All tail pages have zero ->_refcount until atomic_add(). This prevents the
-scanner from getting a reference to the tail page up to that point. After the
-atomic_add() we don't care about the ->_refcount value. We already known how
-many references should be uncharged from the head page.
-
-For head page get_page_unless_zero() will succeed and we don't mind. It's
-clear where reference should go after split: it will stay on head page.
-
-Note that split_huge_pmd() doesn't have any limitation on refcounting:
-pmd can be split at any point and never fails.
-
-== Partial unmap and deferred_split_huge_page() ==
-
-Unmapping part of THP (with munmap() or other way) is not going to free
-memory immediately. Instead, we detect that a subpage of THP is not in use
-in page_remove_rmap() and queue the THP for splitting if memory pressure
-comes. Splitting will free up unused subpages.
-
-Splitting the page right away is not an option due to locking context in
-the place where we can detect partial unmap. It's also might be
-counterproductive since in many cases partial unmap happens during exit(2) if
-a THP crosses a VMA boundary.
-
-Function deferred_split_huge_page() is used to queue page for splitting.
-The splitting itself will happen when we get memory pressure via shrinker
-interface.
diff --git a/Documentation/vm/unevictable-lru.txt b/Documentation/vm/unevictable-lru.rst
similarity index 91%
rename from Documentation/vm/unevictable-lru.txt
rename to Documentation/vm/unevictable-lru.rst
index e147185..fdd84cb 100644
--- a/Documentation/vm/unevictable-lru.txt
+++ b/Documentation/vm/unevictable-lru.rst
@@ -1,37 +1,13 @@
- ==============================
- UNEVICTABLE LRU INFRASTRUCTURE
- ==============================
+.. _unevictable_lru:
-========
-CONTENTS
-========
+==============================
+Unevictable LRU Infrastructure
+==============================
- (*) The Unevictable LRU
-
- - The unevictable page list.
- - Memory control group interaction.
- - Marking address spaces unevictable.
- - Detecting Unevictable Pages.
- - vmscan's handling of unevictable pages.
-
- (*) mlock()'d pages.
-
- - History.
- - Basic management.
- - mlock()/mlockall() system call handling.
- - Filtering special vmas.
- - munlock()/munlockall() system call handling.
- - Migrating mlocked pages.
- - Compacting mlocked pages.
- - mmap(MAP_LOCKED) system call handling.
- - munmap()/exit()/exec() system call handling.
- - try_to_unmap().
- - try_to_munlock() reverse map scan.
- - Page reclaim in shrink_*_list().
+.. contents:: :local:
-============
-INTRODUCTION
+Introduction
============
This document describes the Linux memory manager's "Unevictable LRU"
@@ -46,8 +22,8 @@
descriptions below add value by provide the answer to "why does it do that?".
-===================
-THE UNEVICTABLE LRU
+
+The Unevictable LRU
===================
The Unevictable LRU facility adds an additional LRU list to track unevictable
@@ -66,17 +42,17 @@
The unevictable list addresses the following classes of unevictable pages:
- (*) Those owned by ramfs.
+ * Those owned by ramfs.
- (*) Those mapped into SHM_LOCK'd shared memory regions.
+ * Those mapped into SHM_LOCK'd shared memory regions.
- (*) Those mapped into VM_LOCKED [mlock()ed] VMAs.
+ * Those mapped into VM_LOCKED [mlock()ed] VMAs.
The infrastructure may also be able to handle other conditions that make pages
unevictable, either by definition or by circumstance, in the future.
-THE UNEVICTABLE PAGE LIST
+The Unevictable Page List
-------------------------
The Unevictable LRU infrastructure consists of an additional, per-zone, LRU list
@@ -118,7 +94,7 @@
tasks are changing the "evictability" state of the page.
-MEMORY CONTROL GROUP INTERACTION
+Memory Control Group Interaction
--------------------------------
The unevictable LRU facility interacts with the memory control group [aka
@@ -144,7 +120,9 @@
the control group to thrash or to OOM-kill tasks.
-MARKING ADDRESS SPACES UNEVICTABLE
+.. _mark_addr_space_unevict:
+
+Marking Address Spaces Unevictable
----------------------------------
For facilities such as ramfs none of the pages attached to the address space
@@ -152,15 +130,15 @@
address space flag is provided, and this can be manipulated by a filesystem
using a number of wrapper functions:
- (*) void mapping_set_unevictable(struct address_space *mapping);
+ * ``void mapping_set_unevictable(struct address_space *mapping);``
Mark the address space as being completely unevictable.
- (*) void mapping_clear_unevictable(struct address_space *mapping);
+ * ``void mapping_clear_unevictable(struct address_space *mapping);``
Mark the address space as being evictable.
- (*) int mapping_unevictable(struct address_space *mapping);
+ * ``int mapping_unevictable(struct address_space *mapping);``
Query the address space, and return true if it is completely
unevictable.
@@ -177,12 +155,13 @@
ensure they're in memory.
-DETECTING UNEVICTABLE PAGES
+Detecting Unevictable Pages
---------------------------
The function page_evictable() in vmscan.c determines whether a page is
-evictable or not using the query function outlined above [see section "Marking
-address spaces unevictable"] to check the AS_UNEVICTABLE flag.
+evictable or not using the query function outlined above [see section
+:ref:`Marking address spaces unevictable <mark_addr_space_unevict>`]
+to check the AS_UNEVICTABLE flag.
For address spaces that are so marked after being populated (as SHM regions
might be), the lock action (eg: SHM_LOCK) can be lazy, and need not populate
@@ -202,7 +181,7 @@
faulted into a VM_LOCKED vma, or found in a vma being VM_LOCKED.
-VMSCAN'S HANDLING OF UNEVICTABLE PAGES
+Vmscan's Handling of Unevictable Pages
--------------------------------------
If unevictable pages are culled in the fault path, or moved to the unevictable
@@ -233,8 +212,7 @@
putback_lru_page().
-=============
-MLOCKED PAGES
+MLOCKED Pages
=============
The unevictable page list is also useful for mlock(), in addition to ramfs and
@@ -242,7 +220,7 @@
NOMMU situations, all mappings are effectively mlocked.
-HISTORY
+History
-------
The "Unevictable mlocked Pages" infrastructure is based on work originally
@@ -263,7 +241,7 @@
mapped the page. More on this below.
-BASIC MANAGEMENT
+Basic Management
----------------
mlocked pages - pages mapped into a VM_LOCKED VMA - are a class of unevictable
@@ -304,10 +282,10 @@
(4) before a page is COW'd in a VM_LOCKED VMA.
-mlock()/mlockall() SYSTEM CALL HANDLING
+mlock()/mlockall() System Call Handling
---------------------------------------
-Both [do_]mlock() and [do_]mlockall() system call handlers call mlock_fixup()
+Both [do\_]mlock() and [do\_]mlockall() system call handlers call mlock_fixup()
for each VMA in the range specified by the call. In the case of mlockall(),
this is the entire active address space of the task. Note that mlock_fixup()
is used for both mlocking and munlocking a range of memory. A call to mlock()
@@ -351,7 +329,7 @@
it later if and when it attempts to reclaim the page.
-FILTERING SPECIAL VMAS
+Filtering Special VMAs
----------------------
mlock_fixup() filters several classes of "special" VMAs:
@@ -379,8 +357,9 @@
munlock(), munmap() or task exit. Neither does mlock_fixup() account these
VMAs against the task's "locked_vm".
+.. _munlock_munlockall_handling:
-munlock()/munlockall() SYSTEM CALL HANDLING
+munlock()/munlockall() System Call Handling
-------------------------------------------
The munlock() and munlockall() system calls are handled by the same functions -
@@ -426,7 +405,7 @@
the page. This should be relatively rare.
-MIGRATING MLOCKED PAGES
+Migrating MLOCKED Pages
-----------------------
A page that is being migrated has been isolated from the LRU lists and is held
@@ -451,7 +430,7 @@
putback_lru_page() function to add migrated pages back to the LRU.
-COMPACTING MLOCKED PAGES
+Compacting MLOCKED Pages
------------------------
The unevictable LRU can be scanned for compactable regions and the default
@@ -461,7 +440,7 @@
the page migration code and the same work flow as described in MIGRATING
MLOCKED PAGES will apply.
-MLOCKING TRANSPARENT HUGE PAGES
+MLOCKING Transparent Huge Pages
-------------------------------
A transparent huge page is represented by a single entry on an LRU list.
@@ -483,7 +462,7 @@
See also comment in follow_trans_huge_pmd().
-mmap(MAP_LOCKED) SYSTEM CALL HANDLING
+mmap(MAP_LOCKED) System Call Handling
-------------------------------------
In addition the mlock()/mlockall() system calls, an application can request
@@ -514,7 +493,7 @@
and pages allocated into that region.
-munmap()/exit()/exec() SYSTEM CALL HANDLING
+munmap()/exit()/exec() System Call Handling
-------------------------------------------
When unmapping an mlocked region of memory, whether by an explicit call to
@@ -568,16 +547,18 @@
holepunching, and truncation of file pages and their anonymous COWed pages.
-try_to_munlock() REVERSE MAP SCAN
+try_to_munlock() Reverse Map Scan
---------------------------------
- [!] TODO/FIXME: a better name might be page_mlocked() - analogous to the
- page_referenced() reverse map walker.
+.. warning::
+ [!] TODO/FIXME: a better name might be page_mlocked() - analogous to the
+ page_referenced() reverse map walker.
-When munlock_vma_page() [see section "munlock()/munlockall() System Call
-Handling" above] tries to munlock a page, it needs to determine whether or not
-the page is mapped by any VM_LOCKED VMA without actually attempting to unmap
-all PTEs from the page. For this purpose, the unevictable/mlock infrastructure
+When munlock_vma_page() [see section :ref:`munlock()/munlockall() System Call
+Handling <munlock_munlockall_handling>` above] tries to munlock a
+page, it needs to determine whether or not the page is mapped by any
+VM_LOCKED VMA without actually attempting to unmap all PTEs from the
+page. For this purpose, the unevictable/mlock infrastructure
introduced a variant of try_to_unmap() called try_to_munlock().
try_to_munlock() calls the same functions as try_to_unmap() for anonymous and
@@ -595,7 +576,7 @@
mlockall(), overall this is a fairly rare event.
-PAGE RECLAIM IN shrink_*_list()
+Page Reclaim in shrink_*_list()
-------------------------------
shrink_active_list() culls any obviously unevictable pages - i.e.
diff --git a/Documentation/vm/z3fold.txt b/Documentation/vm/z3fold.rst
similarity index 97%
rename from Documentation/vm/z3fold.txt
rename to Documentation/vm/z3fold.rst
index 38e4dac..224e3c6 100644
--- a/Documentation/vm/z3fold.txt
+++ b/Documentation/vm/z3fold.rst
@@ -1,5 +1,8 @@
+.. _z3fold:
+
+======
z3fold
-------
+======
z3fold is a special purpose allocator for storing compressed pages.
It is designed to store up to three compressed pages per physical page.
@@ -7,6 +10,7 @@
ratio keeping the simplicity and determinism of its predecessor.
The main differences between z3fold and zbud are:
+
* unlike zbud, z3fold allows for up to PAGE_SIZE allocations
* z3fold can hold up to 3 compressed pages in its page
* z3fold doesn't export any API itself and is thus intended to be used
diff --git a/Documentation/vm/zsmalloc.txt b/Documentation/vm/zsmalloc.rst
similarity index 71%
rename from Documentation/vm/zsmalloc.txt
rename to Documentation/vm/zsmalloc.rst
index 64ed63c..6e79893 100644
--- a/Documentation/vm/zsmalloc.txt
+++ b/Documentation/vm/zsmalloc.rst
@@ -1,5 +1,8 @@
+.. _zsmalloc:
+
+========
zsmalloc
---------
+========
This allocator is designed for use with zram. Thus, the allocator is
supposed to work well under low memory conditions. In particular, it
@@ -31,40 +34,49 @@
unmapped using zs_unmap_object().
stat
-----
+====
With CONFIG_ZSMALLOC_STAT, we could see zsmalloc internal information via
-/sys/kernel/debug/zsmalloc/<user name>. Here is a sample of stat output:
+``/sys/kernel/debug/zsmalloc/<user name>``. Here is a sample of stat output::
-# cat /sys/kernel/debug/zsmalloc/zram0/classes
+ # cat /sys/kernel/debug/zsmalloc/zram0/classes
class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage
- ..
- ..
+ ...
+ ...
9 176 0 1 186 129 8 4
10 192 1 0 2880 2872 135 3
11 208 0 1 819 795 42 2
12 224 0 1 219 159 12 4
- ..
- ..
+ ...
+ ...
-class: index
-size: object size zspage stores
-almost_empty: the number of ZS_ALMOST_EMPTY zspages(see below)
-almost_full: the number of ZS_ALMOST_FULL zspages(see below)
-obj_allocated: the number of objects allocated
-obj_used: the number of objects allocated to the user
-pages_used: the number of pages allocated for the class
-pages_per_zspage: the number of 0-order pages to make a zspage
+class
+ index
+size
+ object size zspage stores
+almost_empty
+ the number of ZS_ALMOST_EMPTY zspages(see below)
+almost_full
+ the number of ZS_ALMOST_FULL zspages(see below)
+obj_allocated
+ the number of objects allocated
+obj_used
+ the number of objects allocated to the user
+pages_used
+ the number of pages allocated for the class
+pages_per_zspage
+ the number of 0-order pages to make a zspage
-We assign a zspage to ZS_ALMOST_EMPTY fullness group when:
- n <= N / f, where
-n = number of allocated objects
-N = total number of objects zspage can store
-f = fullness_threshold_frac(ie, 4 at the moment)
+We assign a zspage to ZS_ALMOST_EMPTY fullness group when n <= N / f, where
+
+* n = number of allocated objects
+* N = total number of objects zspage can store
+* f = fullness_threshold_frac(ie, 4 at the moment)
Similarly, we assign zspage to:
- ZS_ALMOST_FULL when n > N / f
- ZS_EMPTY when n == 0
- ZS_FULL when n == N
+
+* ZS_ALMOST_FULL when n > N / f
+* ZS_EMPTY when n == 0
+* ZS_FULL when n == N
diff --git a/Documentation/vm/zswap.txt b/Documentation/vm/zswap.rst
similarity index 74%
rename from Documentation/vm/zswap.txt
rename to Documentation/vm/zswap.rst
index 0b3a114..1444ecd 100644
--- a/Documentation/vm/zswap.txt
+++ b/Documentation/vm/zswap.rst
@@ -1,4 +1,11 @@
-Overview:
+.. _zswap:
+
+=====
+zswap
+=====
+
+Overview
+========
Zswap is a lightweight compressed cache for swap pages. It takes pages that are
in the process of being swapped out and attempts to compress them into a
@@ -7,32 +14,34 @@
significant performance improvement if reads from the compressed cache are
faster than reads from a swap device.
-NOTE: Zswap is a new feature as of v3.11 and interacts heavily with memory
-reclaim. This interaction has not been fully explored on the large set of
-potential configurations and workloads that exist. For this reason, zswap
-is a work in progress and should be considered experimental.
+.. note::
+ Zswap is a new feature as of v3.11 and interacts heavily with memory
+ reclaim. This interaction has not been fully explored on the large set of
+ potential configurations and workloads that exist. For this reason, zswap
+ is a work in progress and should be considered experimental.
-Some potential benefits:
+ Some potential benefits:
+
* Desktop/laptop users with limited RAM capacities can mitigate the
- performance impact of swapping.
+ performance impact of swapping.
* Overcommitted guests that share a common I/O resource can
- dramatically reduce their swap I/O pressure, avoiding heavy handed I/O
- throttling by the hypervisor. This allows more work to get done with less
- impact to the guest workload and guests sharing the I/O subsystem
+ dramatically reduce their swap I/O pressure, avoiding heavy handed I/O
+ throttling by the hypervisor. This allows more work to get done with less
+ impact to the guest workload and guests sharing the I/O subsystem
* Users with SSDs as swap devices can extend the life of the device by
- drastically reducing life-shortening writes.
+ drastically reducing life-shortening writes.
Zswap evicts pages from compressed cache on an LRU basis to the backing swap
device when the compressed pool reaches its size limit. This requirement had
been identified in prior community discussions.
Zswap is disabled by default but can be enabled at boot time by setting
-the "enabled" attribute to 1 at boot time. ie: zswap.enabled=1. Zswap
+the ``enabled`` attribute to 1 at boot time. ie: ``zswap.enabled=1``. Zswap
can also be enabled and disabled at runtime using the sysfs interface.
An example command to enable zswap at runtime, assuming sysfs is mounted
-at /sys, is:
+at ``/sys``, is::
-echo 1 > /sys/module/zswap/parameters/enabled
+ echo 1 > /sys/module/zswap/parameters/enabled
When zswap is disabled at runtime it will stop storing pages that are
being swapped out. However, it will _not_ immediately write out or fault
@@ -43,7 +52,8 @@
fault back into memory all swapped out pages, including those in the
compressed pool.
-Design:
+Design
+======
Zswap receives pages for compression through the Frontswap API and is able to
evict pages from its own compressed pool on an LRU basis and write them back to
@@ -53,12 +63,12 @@
allocation in zpool is not directly accessible by address. Rather, a handle is
returned by the allocation routine and that handle must be mapped before being
accessed. The compressed memory pool grows on demand and shrinks as compressed
-pages are freed. The pool is not preallocated. By default, a zpool of type
-zbud is created, but it can be selected at boot time by setting the "zpool"
-attribute, e.g. zswap.zpool=zbud. It can also be changed at runtime using the
-sysfs "zpool" attribute, e.g.
+pages are freed. The pool is not preallocated. By default, a zpool
+of type zbud is created, but it can be selected at boot time by
+setting the ``zpool`` attribute, e.g. ``zswap.zpool=zbud``. It can
+also be changed at runtime using the sysfs ``zpool`` attribute, e.g.::
-echo zbud > /sys/module/zswap/parameters/zpool
+ echo zbud > /sys/module/zswap/parameters/zpool
The zbud type zpool allocates exactly 1 page to store 2 compressed pages, which
means the compression ratio will always be 2:1 or worse (because of half-full
@@ -83,14 +93,16 @@
Zswap seeks to be simple in its policies. Sysfs attributes allow for one user
controlled policy:
+
* max_pool_percent - The maximum percentage of memory that the compressed
- pool can occupy.
+ pool can occupy.
-The default compressor is lzo, but it can be selected at boot time by setting
-the “compressor” attribute, e.g. zswap.compressor=lzo. It can also be changed
-at runtime using the sysfs "compressor" attribute, e.g.
+The default compressor is lzo, but it can be selected at boot time by
+setting the ``compressor`` attribute, e.g. ``zswap.compressor=lzo``.
+It can also be changed at runtime using the sysfs "compressor"
+attribute, e.g.::
-echo lzo > /sys/module/zswap/parameters/compressor
+ echo lzo > /sys/module/zswap/parameters/compressor
When the zpool and/or compressor parameter is changed at runtime, any existing
compressed pages are not modified; they are left in their own zpool. When a
@@ -106,11 +118,12 @@
value is stored.
Same-value filled pages identification feature is enabled by default and can be
-disabled at boot time by setting the "same_filled_pages_enabled" attribute to 0,
-e.g. zswap.same_filled_pages_enabled=0. It can also be enabled and disabled at
-runtime using the sysfs "same_filled_pages_enabled" attribute, e.g.
+disabled at boot time by setting the ``same_filled_pages_enabled`` attribute
+to 0, e.g. ``zswap.same_filled_pages_enabled=0``. It can also be enabled and
+disabled at runtime using the sysfs ``same_filled_pages_enabled``
+attribute, e.g.::
-echo 1 > /sys/module/zswap/parameters/same_filled_pages_enabled
+ echo 1 > /sys/module/zswap/parameters/same_filled_pages_enabled
When zswap same-filled page identification is disabled at runtime, it will stop
checking for the same-value filled pages during store operation. However, the
diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt
index 71c30984..a16aa21 100644
--- a/Documentation/x86/intel_rdt_ui.txt
+++ b/Documentation/x86/intel_rdt_ui.txt
@@ -17,12 +17,14 @@
To use the feature mount the file system:
- # mount -t resctrl resctrl [-o cdp[,cdpl2]] /sys/fs/resctrl
+ # mount -t resctrl resctrl [-o cdp[,cdpl2][,mba_MBps]] /sys/fs/resctrl
mount options are:
"cdp": Enable code/data prioritization in L3 cache allocations.
"cdpl2": Enable code/data prioritization in L2 cache allocations.
+"mba_MBps": Enable the MBA Software Controller(mba_sc) to specify MBA
+ bandwidth in MBps
L2 and L3 CDP are controlled seperately.
@@ -270,10 +272,11 @@
of the capacity of the cache. You could partition the cache into four
equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000.
-Memory bandwidth(b/w) percentage
---------------------------------
-For Memory b/w resource, user controls the resource by indicating the
-percentage of total memory b/w.
+Memory bandwidth Allocation and monitoring
+------------------------------------------
+
+For Memory bandwidth resource, by default the user controls the resource
+by indicating the percentage of total memory bandwidth.
The minimum bandwidth percentage value for each cpu model is predefined
and can be looked up through "info/MB/min_bandwidth". The bandwidth
@@ -285,7 +288,47 @@
The bandwidth throttling is a core specific mechanism on some of Intel
SKUs. Using a high bandwidth and a low bandwidth setting on two threads
sharing a core will result in both threads being throttled to use the
-low bandwidth.
+low bandwidth. The fact that Memory bandwidth allocation(MBA) is a core
+specific mechanism where as memory bandwidth monitoring(MBM) is done at
+the package level may lead to confusion when users try to apply control
+via the MBA and then monitor the bandwidth to see if the controls are
+effective. Below are such scenarios:
+
+1. User may *not* see increase in actual bandwidth when percentage
+ values are increased:
+
+This can occur when aggregate L2 external bandwidth is more than L3
+external bandwidth. Consider an SKL SKU with 24 cores on a package and
+where L2 external is 10GBps (hence aggregate L2 external bandwidth is
+240GBps) and L3 external bandwidth is 100GBps. Now a workload with '20
+threads, having 50% bandwidth, each consuming 5GBps' consumes the max L3
+bandwidth of 100GBps although the percentage value specified is only 50%
+<< 100%. Hence increasing the bandwidth percentage will not yeild any
+more bandwidth. This is because although the L2 external bandwidth still
+has capacity, the L3 external bandwidth is fully used. Also note that
+this would be dependent on number of cores the benchmark is run on.
+
+2. Same bandwidth percentage may mean different actual bandwidth
+ depending on # of threads:
+
+For the same SKU in #1, a 'single thread, with 10% bandwidth' and '4
+thread, with 10% bandwidth' can consume upto 10GBps and 40GBps although
+they have same percentage bandwidth of 10%. This is simply because as
+threads start using more cores in an rdtgroup, the actual bandwidth may
+increase or vary although user specified bandwidth percentage is same.
+
+In order to mitigate this and make the interface more user friendly,
+resctrl added support for specifying the bandwidth in MBps as well. The
+kernel underneath would use a software feedback mechanism or a "Software
+Controller(mba_sc)" which reads the actual bandwidth using MBM counters
+and adjust the memowy bandwidth percentages to ensure
+
+ "actual bandwidth < user specified bandwidth".
+
+By default, the schemata would take the bandwidth percentage values
+where as user can switch to the "MBA software controller" mode using
+a mount option 'mba_MBps'. The schemata format is specified in the below
+sections.
L3 schemata file details (code and data prioritization disabled)
----------------------------------------------------------------
@@ -308,13 +351,20 @@
L2:<cache_id0>=<cbm>;<cache_id1>=<cbm>;...
-Memory b/w Allocation details
------------------------------
+Memory bandwidth Allocation (default mode)
+------------------------------------------
Memory b/w domain is L3 cache.
MB:<cache_id0>=bandwidth0;<cache_id1>=bandwidth1;...
+Memory bandwidth Allocation specified in MBps
+---------------------------------------------
+
+Memory bandwidth domain is L3 cache.
+
+ MB:<cache_id0>=bw_MBps0;<cache_id1>=bw_MBps1;...
+
Reading/writing the schemata file
---------------------------------
Reading the schemata file will show the state of all resources
@@ -358,6 +408,15 @@
b/w that the group may be able to use and the system admin can configure
the b/w accordingly.
+If the MBA is specified in MB(megabytes) then user can enter the max b/w in MB
+rather than the percentage values.
+
+# echo "L3:0=3;1=c\nMB:0=1024;1=500" > /sys/fs/resctrl/p0/schemata
+# echo "L3:0=3;1=3\nMB:0=1024;1=500" > /sys/fs/resctrl/p1/schemata
+
+In the above example the tasks in "p1" and "p0" on socket 0 would use a max b/w
+of 1024MB where as on socket 1 they would use 500MB.
+
Example 2
---------
Again two sockets, but this time with a more realistic 20-bit mask.
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index b297c48..8d109ef 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -187,9 +187,9 @@
IOMMU (input/output memory management unit)
- Currently four x86-64 PCI-DMA mapping implementations exist:
+ Multiple x86-64 PCI-DMA mapping implementations exist, for example:
- 1. <arch/x86_64/kernel/pci-nommu.c>: use no hardware/software IOMMU at all
+ 1. <lib/dma-direct.c>: use no hardware/software IOMMU at all
(e.g. because you have < 3 GB memory).
Kernel boot message: "PCI-DMA: Disabling IOMMU"
@@ -208,7 +208,7 @@
Kernel boot message: "PCI-DMA: Using Calgary IOMMU"
iommu=[<size>][,noagp][,off][,force][,noforce][,leak[=<nr_of_leak_pages>]
- [,memaper[=<order>]][,merge][,forcesac][,fullflush][,nomerge]
+ [,memaper[=<order>]][,merge][,fullflush][,nomerge]
[,noaperture][,calgary]
General iommu options:
@@ -235,14 +235,7 @@
(experimental).
nomerge Don't do scatter-gather (SG) merging.
noaperture Ask the IOMMU not to touch the aperture for AGP.
- forcesac Force single-address cycle (SAC) mode for masks <40bits
- (experimental).
noagp Don't initialize the AGP driver and use full aperture.
- allowdac Allow double-address cycle (DAC) mode, i.e. DMA >4GB.
- DAC is used with 32-bit PCI to push a 64-bit address in
- two cycles. When off all DMA over >4GB is forced through
- an IOMMU or software bounce buffering.
- nodac Forbid DAC mode, i.e. DMA >4GB.
panic Always panic when IOMMU overflows.
calgary Use the Calgary IOMMU if it is available
diff --git a/LICENSES/exceptions/Linux-syscall-note b/LICENSES/exceptions/Linux-syscall-note
index 6b60b61..9abdad7 100644
--- a/LICENSES/exceptions/Linux-syscall-note
+++ b/LICENSES/exceptions/Linux-syscall-note
@@ -1,6 +1,6 @@
SPDX-Exception-Identifier: Linux-syscall-note
SPDX-URL: https://spdx.org/licenses/Linux-syscall-note.html
-SPDX-Licenses: GPL-2.0, GPL-2.0+, GPL-1.0+, LGPL-2.0, LGPL-2.0+, LGPL-2.1, LGPL-2.1+
+SPDX-Licenses: GPL-2.0, GPL-2.0+, GPL-1.0+, LGPL-2.0, LGPL-2.0+, LGPL-2.1, LGPL-2.1+, GPL-2.0-only, GPL-2.0-or-later
Usage-Guide:
This exception is used together with one of the above SPDX-Licenses
to mark user space API (uapi) header files so they can be included
diff --git a/LICENSES/other/Apache-2.0 b/LICENSES/other/Apache-2.0
new file mode 100644
index 0000000..7cd903f
--- /dev/null
+++ b/LICENSES/other/Apache-2.0
@@ -0,0 +1,183 @@
+Valid-License-Identifier: Apache-2.0
+SPDX-URL: https://spdx.org/licenses/Apache-2.0.html
+Usage-Guide:
+ To use the Apache License version 2.0 put the following SPDX tag/value
+ pair into a comment according to the placement guidelines in the
+ licensing rules documentation:
+ SPDX-License-Identifier: Apache-2.0
+License-Text:
+
+Apache License
+
+Version 2.0, January 2004
+
+http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+"License" shall mean the terms and conditions for use, reproduction, and
+distribution as defined by Sections 1 through 9 of this document.
+
+"Licensor" shall mean the copyright owner or entity authorized by the
+copyright owner that is granting the License.
+
+"Legal Entity" shall mean the union of the acting entity and all other
+entities that control, are controlled by, or are under common control with
+that entity. For the purposes of this definition, "control" means (i) the
+power, direct or indirect, to cause the direction or management of such
+entity, whether by contract or otherwise, or (ii) ownership of fifty
+percent (50%) or more of the outstanding shares, or (iii) beneficial
+ownership of such entity.
+
+"You" (or "Your") shall mean an individual or Legal Entity exercising
+permissions granted by this License.
+
+"Source" form shall mean the preferred form for making modifications,
+including but not limited to software source code, documentation source,
+and configuration files.
+
+"Object" form shall mean any form resulting from mechanical transformation
+or translation of a Source form, including but not limited to compiled
+object code, generated documentation, and conversions to other media types.
+
+"Work" shall mean the work of authorship, whether in Source or Object form,
+made available under the License, as indicated by a copyright notice that
+is included in or attached to the work (an example is provided in the
+Appendix below).
+
+"Derivative Works" shall mean any work, whether in Source or Object form,
+that is based on (or derived from) the Work and for which the editorial
+revisions, annotations, elaborations, or other modifications represent, as
+a whole, an original work of authorship. For the purposes of this License,
+Derivative Works shall not include works that remain separable from, or
+merely link (or bind by name) to the interfaces of, the Work and Derivative
+Works thereof.
+
+"Contribution" shall mean any work of authorship, including the original
+version of the Work and any modifications or additions to that Work or
+Derivative Works thereof, that is intentionally submitted to Licensor for
+inclusion in the Work by the copyright owner or by an individual or Legal
+Entity authorized to submit on behalf of the copyright owner. For the
+purposes of this definition, "submitted" means any form of electronic,
+verbal, or written communication sent to the Licensor or its
+representatives, including but not limited to communication on electronic
+mailing lists, source code control systems, and issue tracking systems that
+are managed by, or on behalf of, the Licensor for the purpose of discussing
+and improving the Work, but excluding communication that is conspicuously
+marked or otherwise designated in writing by the copyright owner as "Not a
+Contribution."
+
+"Contributor" shall mean Licensor and any individual or Legal Entity on
+behalf of whom a Contribution has been received by Licensor and
+subsequently incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of this
+ License, each Contributor hereby grants to You a perpetual, worldwide,
+ non-exclusive, no-charge, royalty-free, irrevocable copyright license to
+ reproduce, prepare Derivative Works of, publicly display, publicly
+ perform, sublicense, and distribute the Work and such Derivative Works
+ in Source or Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of this
+ License, each Contributor hereby grants to You a perpetual, worldwide,
+ non-exclusive, no-charge, royalty-free, irrevocable (except as stated in
+ this section) patent license to make, have made, use, offer to sell,
+ sell, import, and otherwise transfer the Work, where such license
+ applies only to those patent claims licensable by such Contributor that
+ are necessarily infringed by their Contribution(s) alone or by
+ combination of their Contribution(s) with the Work to which such
+ Contribution(s) was submitted. If You institute patent litigation
+ against any entity (including a cross-claim or counterclaim in a
+ lawsuit) alleging that the Work or a Contribution incorporated within
+ the Work constitutes direct or contributory patent infringement, then
+ any patent licenses granted to You under this License for that Work
+ shall terminate as of the date such litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the Work or
+ Derivative Works thereof in any medium, with or without modifications,
+ and in Source or Object form, provided that You meet the following
+ conditions:
+
+ a. You must give any other recipients of the Work or Derivative Works a
+ copy of this License; and
+
+ b. You must cause any modified files to carry prominent notices stating
+ that You changed the files; and
+
+ c. You must retain, in the Source form of any Derivative Works that You
+ distribute, all copyright, patent, trademark, and attribution notices
+ from the Source form of the Work, excluding those notices that do not
+ pertain to any part of the Derivative Works; and
+
+ d. If the Work includes a "NOTICE" text file as part of its
+ distribution, then any Derivative Works that You distribute must
+ include a readable copy of the attribution notices contained within
+ such NOTICE file, excluding those notices that do not pertain to any
+ part of the Derivative Works, in at least one of the following
+ places: within a NOTICE text file distributed as part of the
+ Derivative Works; within the Source form or documentation, if
+ provided along with the Derivative Works; or, within a display
+ generated by the Derivative Works, if and wherever such third-party
+ notices normally appear. The contents of the NOTICE file are for
+ informational purposes only and do not modify the License. You may
+ add Your own attribution notices within Derivative Works that You
+ distribute, alongside or as an addendum to the NOTICE text from the
+ Work, provided that such additional attribution notices cannot be
+ construed as modifying the License.
+
+ You may add Your own copyright statement to Your modifications and may
+ provide additional or different license terms and conditions for use,
+ reproduction, or distribution of Your modifications, or for any such
+ Derivative Works as a whole, provided Your use, reproduction, and
+ distribution of the Work otherwise complies with the conditions stated
+ in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise, any
+ Contribution intentionally submitted for inclusion in the Work by You to
+ the Licensor shall be under the terms and conditions of this License,
+ without any additional terms or conditions. Notwithstanding the above,
+ nothing herein shall supersede or modify the terms of any separate
+ license agreement you may have executed with Licensor regarding such
+ Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade
+ names, trademarks, service marks, or product names of the Licensor,
+ except as required for reasonable and customary use in describing the
+ origin of the Work and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or agreed to
+ in writing, Licensor provides the Work (and each Contributor provides
+ its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS
+ OF ANY KIND, either express or implied, including, without limitation,
+ any warranties or conditions of TITLE, NON-INFRINGEMENT,
+ MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely
+ responsible for determining the appropriateness of using or
+ redistributing the Work and assume any risks associated with Your
+ exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory, whether
+ in tort (including negligence), contract, or otherwise, unless required
+ by applicable law (such as deliberate and grossly negligent acts) or
+ agreed to in writing, shall any Contributor be liable to You for
+ damages, including any direct, indirect, special, incidental, or
+ consequential damages of any character arising as a result of this
+ License or out of the use or inability to use the Work (including but
+ not limited to damages for loss of goodwill, work stoppage, computer
+ failure or malfunction, or any and all other commercial damages or
+ losses), even if such Contributor has been advised of the possibility of
+ such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing the
+ Work or Derivative Works thereof, You may choose to offer, and charge a
+ fee for, acceptance of support, warranty, indemnity, or other liability
+ obligations and/or rights consistent with this License. However, in
+ accepting such obligations, You may act only on Your own behalf and on
+ Your sole responsibility, not on behalf of any other Contributor, and
+ only if You agree to indemnify, defend, and hold each Contributor
+ harmless for any liability incurred by, or claims asserted against, such
+ Contributor by reason of your accepting any such warranty or additional
+ liability.
+
+END OF TERMS AND CONDITIONS
diff --git a/LICENSES/other/CC-BY-SA-4.0 b/LICENSES/other/CC-BY-SA-4.0
new file mode 100644
index 0000000..f9158e8
--- /dev/null
+++ b/LICENSES/other/CC-BY-SA-4.0
@@ -0,0 +1,397 @@
+Valid-License-Identifier: CC-BY-SA-4.0
+SPDX-URL: https://spdx.org/licenses/CC-BY-SA-4.0
+Usage-Guide:
+ To use the Creative Commons Attribution Share Alike 4.0 International
+ license put the following SPDX tag/value pair into a comment according to
+ the placement guidelines in the licensing rules documentation:
+ SPDX-License-Identifier: CC-BY-SA-4.0
+License-Text:
+
+Creative Commons Attribution-ShareAlike 4.0 International
+
+Creative Commons Corporation ("Creative Commons") is not a law firm and
+does not provide legal services or legal advice. Distribution of Creative
+Commons public licenses does not create a lawyer-client or other
+relationship. Creative Commons makes its licenses and related information
+available on an "as-is" basis. Creative Commons gives no warranties
+regarding its licenses, any material licensed under their terms and
+conditions, or any related information. Creative Commons disclaims all
+liability for damages resulting from their use to the fullest extent
+possible.
+
+Using Creative Commons Public Licenses
+
+Creative Commons public licenses provide a standard set of terms and
+conditions that creators and other rights holders may use to share original
+works of authorship and other material subject to copyright and certain
+other rights specified in the public license below. The following
+considerations are for informational purposes only, are not exhaustive, and
+do not form part of our licenses.
+
+Considerations for licensors: Our public licenses are intended for use by
+those authorized to give the public permission to use material in ways
+otherwise restricted by copyright and certain other rights. Our licenses
+are irrevocable. Licensors should read and understand the terms and
+conditions of the license they choose before applying it. Licensors should
+also secure all rights necessary before applying our licenses so that the
+public can reuse the material as expected. Licensors should clearly mark
+any material not subject to the license. This includes other CC-licensed
+material, or material used under an exception or limitation to
+copyright. More considerations for licensors :
+wiki.creativecommons.org/Considerations_for_licensors
+
+Considerations for the public: By using one of our public licenses, a
+licensor grants the public permission to use the licensed material under
+specified terms and conditions. If the licensor's permission is not
+necessary for any reason - for example, because of any applicable exception
+or limitation to copyright - then that use is not regulated by the
+license. Our licenses grant only permissions under copyright and certain
+other rights that a licensor has authority to grant. Use of the licensed
+material may still be restricted for other reasons, including because
+others have copyright or other rights in the material. A licensor may make
+special requests, such as asking that all changes be marked or described.
+
+Although not required by our licenses, you are encouraged to respect those
+requests where reasonable. More considerations for the public :
+wiki.creativecommons.org/Considerations_for_licensees
+
+Creative Commons Attribution-ShareAlike 4.0 International Public License
+
+By exercising the Licensed Rights (defined below), You accept and agree to
+be bound by the terms and conditions of this Creative Commons
+Attribution-ShareAlike 4.0 International Public License ("Public
+License"). To the extent this Public License may be interpreted as a
+contract, You are granted the Licensed Rights in consideration of Your
+acceptance of these terms and conditions, and the Licensor grants You such
+rights in consideration of benefits the Licensor receives from making the
+Licensed Material available under these terms and conditions.
+
+Section 1 - Definitions.
+
+ a. Adapted Material means material subject to Copyright and Similar
+ Rights that is derived from or based upon the Licensed Material and
+ in which the Licensed Material is translated, altered, arranged,
+ transformed, or otherwise modified in a manner requiring permission
+ under the Copyright and Similar Rights held by the Licensor. For
+ purposes of this Public License, where the Licensed Material is a
+ musical work, performance, or sound recording, Adapted Material is
+ always produced where the Licensed Material is synched in timed
+ relation with a moving image.
+
+ b. Adapter's License means the license You apply to Your Copyright and
+ Similar Rights in Your contributions to Adapted Material in
+ accordance with the terms and conditions of this Public License.
+
+ c. BY-SA Compatible License means a license listed at
+ creativecommons.org/compatiblelicenses, approved by Creative Commons
+ as essentially the equivalent of this Public License.
+
+ d. Copyright and Similar Rights means copyright and/or similar rights
+ closely related to copyright including, without limitation,
+ performance, broadcast, sound recording, and Sui Generis Database
+ Rights, without regard to how the rights are labeled or
+ categorized. For purposes of this Public License, the rights
+ specified in Section 2(b)(1)-(2) are not Copyright and Similar
+ Rights.
+
+ e. Effective Technological Measures means those measures that, in the
+ absence of proper authority, may not be circumvented under laws
+ fulfilling obligations under Article 11 of the WIPO Copyright Treaty
+ adopted on December 20, 1996, and/or similar international
+ agreements.
+
+ f. Exceptions and Limitations means fair use, fair dealing, and/or any
+ other exception or limitation to Copyright and Similar Rights that
+ applies to Your use of the Licensed Material.
+
+ g. License Elements means the license attributes listed in the name of
+ a Creative Commons Public License. The License Elements of this
+ Public License are Attribution and ShareAlike.
+
+ h. Licensed Material means the artistic or literary work, database, or
+ other material to which the Licensor applied this Public License.
+
+ i. Licensed Rights means the rights granted to You subject to the terms
+ and conditions of this Public License, which are limited to all
+ Copyright and Similar Rights that apply to Your use of the Licensed
+ Material and that the Licensor has authority to license.
+
+ j. Licensor means the individual(s) or entity(ies) granting rights
+ under this Public License.
+
+ k. Share means to provide material to the public by any means or
+ process that requires permission under the Licensed Rights, such as
+ reproduction, public display, public performance, distribution,
+ dissemination, communication, or importation, and to make material
+ available to the public including in ways that members of the public
+ may access the material from a place and at a time individually
+ chosen by them.
+
+ l. Sui Generis Database Rights means rights other than copyright
+ resulting from Directive 96/9/EC of the European Parliament and of
+ the Council of 11 March 1996 on the legal protection of databases,
+ as amended and/or succeeded, as well as other essentially equivalent
+ rights anywhere in the world. m. You means the individual or entity
+ exercising the Licensed Rights under this Public License. Your has a
+ corresponding meaning.
+
+Section 2 - Scope.
+
+ a. License grant.
+
+ 1. Subject to the terms and conditions of this Public License, the
+ Licensor hereby grants You a worldwide, royalty-free,
+ non-sublicensable, non-exclusive, irrevocable license to
+ exercise the Licensed Rights in the Licensed Material to:
+
+ A. reproduce and Share the Licensed Material, in whole or in part; and
+
+ B. produce, reproduce, and Share Adapted Material.
+
+ 2. Exceptions and Limitations. For the avoidance of doubt, where
+ Exceptions and Limitations apply to Your use, this Public
+ License does not apply, and You do not need to comply with its
+ terms and conditions.
+
+ 3. Term. The term of this Public License is specified in Section 6(a).
+
+ 4. Media and formats; technical modifications allowed. The Licensor
+ authorizes You to exercise the Licensed Rights in all media and
+ formats whether now known or hereafter created, and to make
+ technical modifications necessary to do so. The Licensor waives
+ and/or agrees not to assert any right or authority to forbid You
+ from making technical modifications necessary to exercise the
+ Licensed Rights, including technical modifications necessary to
+ circumvent Effective Technological Measures. For purposes of
+ this Public License, simply making modifications authorized by
+ this Section 2(a)(4) never produces Adapted Material.
+
+ 5. Downstream recipients.
+
+ A. Offer from the Licensor - Licensed Material. Every recipient
+ of the Licensed Material automatically receives an offer
+ from the Licensor to exercise the Licensed Rights under the
+ terms and conditions of this Public License.
+
+ B. Additional offer from the Licensor - Adapted Material. Every
+ recipient of Adapted Material from You automatically
+ receives an offer from the Licensor to exercise the Licensed
+ Rights in the Adapted Material under the conditions of the
+ Adapter's License You apply.
+
+ C. No downstream restrictions. You may not offer or impose any
+ additional or different terms or conditions on, or apply any
+ Effective Technological Measures to, the Licensed Material
+ if doing so restricts exercise of the Licensed Rights by any
+ recipient of the Licensed Material.
+
+ 6. No endorsement. Nothing in this Public License constitutes or
+ may be construed as permission to assert or imply that You are,
+ or that Your use of the Licensed Material is, connected with, or
+ sponsored, endorsed, or granted official status by, the Licensor
+ or others designated to receive attribution as provided in
+ Section 3(a)(1)(A)(i).
+
+ b. Other rights.
+
+ 1. Moral rights, such as the right of integrity, are not licensed
+ under this Public License, nor are publicity, privacy, and/or
+ other similar personality rights; however, to the extent
+ possible, the Licensor waives and/or agrees not to assert any
+ such rights held by the Licensor to the limited extent necessary
+ to allow You to exercise the Licensed Rights, but not otherwise.
+
+ 2. Patent and trademark rights are not licensed under this Public
+ License.
+
+ 3. To the extent possible, the Licensor waives any right to collect
+ royalties from You for the exercise of the Licensed Rights,
+ whether directly or through a collecting society under any
+ voluntary or waivable statutory or compulsory licensing
+ scheme. In all other cases the Licensor expressly reserves any
+ right to collect such royalties.
+
+Section 3 - License Conditions.
+
+Your exercise of the Licensed Rights is expressly made subject to the
+following conditions.
+
+ a. Attribution.
+
+ 1. If You Share the Licensed Material (including in modified form),
+ You must:
+
+ A. retain the following if it is supplied by the Licensor with
+ the Licensed Material:
+
+ i. identification of the creator(s) of the Licensed
+ Material and any others designated to receive
+ attribution, in any reasonable manner requested by the
+ Licensor (including by pseudonym if designated);
+
+ ii. a copyright notice;
+
+ iii. a notice that refers to this Public License;
+
+ iv. a notice that refers to the disclaimer of warranties;
+
+ v. a URI or hyperlink to the Licensed Material to the extent reasonably practicable;
+
+ B. indicate if You modified the Licensed Material and retain an
+ indication of any previous modifications; and
+
+ C. indicate the Licensed Material is licensed under this Public
+ License, and include the text of, or the URI or hyperlink to,
+ this Public License.
+
+ 2. You may satisfy the conditions in Section 3(a)(1) in any
+ reasonable manner based on the medium, means, and context in
+ which You Share the Licensed Material. For example, it may be
+ reasonable to satisfy the conditions by providing a URI or
+ hyperlink to a resource that includes the required information.
+
+ 3. If requested by the Licensor, You must remove any of the
+ information required by Section 3(a)(1)(A) to the extent
+ reasonably practicable. b. ShareAlike.In addition to the
+ conditions in Section 3(a), if You Share Adapted Material You
+ produce, the following conditions also apply.
+
+ 1. The Adapter's License You apply must be a Creative Commons
+ license with the same License Elements, this version or
+ later, or a BY-SA Compatible License.
+
+ 2. You must include the text of, or the URI or hyperlink to, the
+ Adapter's License You apply. You may satisfy this condition
+ in any reasonable manner based on the medium, means, and
+ context in which You Share Adapted Material.
+
+ 3. You may not offer or impose any additional or different terms
+ or conditions on, or apply any Effective Technological
+ Measures to, Adapted Material that restrict exercise of the
+ rights granted under the Adapter's License You apply.
+
+Section 4 - Sui Generis Database Rights.
+
+Where the Licensed Rights include Sui Generis Database Rights that apply to
+Your use of the Licensed Material:
+
+ a. for the avoidance of doubt, Section 2(a)(1) grants You the right to
+ extract, reuse, reproduce, and Share all or a substantial portion of
+ the contents of the database;
+
+ b. if You include all or a substantial portion of the database contents
+ in a database in which You have Sui Generis Database Rights, then
+ the database in which You have Sui Generis Database Rights (but not
+ its individual contents) is Adapted Material, including for purposes
+ of Section 3(b); and
+
+ c. You must comply with the conditions in Section 3(a) if You Share all
+ or a substantial portion of the contents of the database.
+
+ For the avoidance of doubt, this Section 4 supplements and does not
+ replace Your obligations under this Public License where the Licensed
+ Rights include other Copyright and Similar Rights.
+
+Section 5 - Disclaimer of Warranties and Limitation of Liability.
+
+ a. Unless otherwise separately undertaken by the Licensor, to the
+ extent possible, the Licensor offers the Licensed Material as-is and
+ as-available, and makes no representations or warranties of any kind
+ concerning the Licensed Material, whether express, implied,
+ statutory, or other. This includes, without limitation, warranties
+ of title, merchantability, fitness for a particular purpose,
+ non-infringement, absence of latent or other defects, accuracy, or
+ the presence or absence of errors, whether or not known or
+ discoverable. Where disclaimers of warranties are not allowed in
+ full or in part, this disclaimer may not apply to You.
+
+ b. To the extent possible, in no event will the Licensor be liable to
+ You on any legal theory (including, without limitation, negligence)
+ or otherwise for any direct, special, indirect, incidental,
+ consequential, punitive, exemplary, or other losses, costs,
+ expenses, or damages arising out of this Public License or use of
+ the Licensed Material, even if the Licensor has been advised of the
+ possibility of such losses, costs, expenses, or damages. Where a
+ limitation of liability is not allowed in full or in part, this
+ limitation may not apply to You.
+
+ c. The disclaimer of warranties and limitation of liability provided
+ above shall be interpreted in a manner that, to the extent possible,
+ most closely approximates an absolute disclaimer and waiver of all
+ liability.
+
+Section 6 - Term and Termination.
+
+ a. This Public License applies for the term of the Copyright and
+ Similar Rights licensed here. However, if You fail to comply with
+ this Public License, then Your rights under this Public License
+ terminate automatically.
+
+ b. Where Your right to use the Licensed Material has terminated under
+ Section 6(a), it reinstates:
+
+ 1. automatically as of the date the violation is cured, provided it
+ is cured within 30 days of Your discovery of the violation; or
+
+ 2. upon express reinstatement by the Licensor.
+
+ c. For the avoidance of doubt, this Section 6(b) does not affect any
+ right the Licensor may have to seek remedies for Your violations of
+ this Public License.
+
+ d. For the avoidance of doubt, the Licensor may also offer the Licensed
+ Material under separate terms or conditions or stop distributing the
+ Licensed Material at any time; however, doing so will not terminate
+ this Public License.
+
+ e. Sections 1, 5, 6, 7, and 8 survive termination of this Public License.
+
+Section 7 - Other Terms and Conditions.
+
+ a. The Licensor shall not be bound by any additional or different terms
+ or conditions communicated by You unless expressly agreed.
+
+ b. Any arrangements, understandings, or agreements regarding the
+ Licensed Material not stated herein are separate from and
+ independent of the terms and conditions of this Public License.
+
+Section 8 - Interpretation.
+
+ a. For the avoidance of doubt, this Public License does not, and shall
+ not be interpreted to, reduce, limit, restrict, or impose conditions
+ on any use of the Licensed Material that could lawfully be made
+ without permission under this Public License.
+
+ b. To the extent possible, if any provision of this Public License is
+ deemed unenforceable, it shall be automatically reformed to the
+ minimum extent necessary to make it enforceable. If the provision
+ cannot be reformed, it shall be severed from this Public License
+ without affecting the enforceability of the remaining terms and
+ conditions.
+
+ c. No term or condition of this Public License will be waived and no
+ failure to comply consented to unless expressly agreed to by the
+ Licensor.
+
+ d. Nothing in this Public License constitutes or may be interpreted as
+ a limitation upon, or waiver of, any privileges and immunities that
+ apply to the Licensor or You, including from the legal processes of
+ any jurisdiction or authority.
+
+Creative Commons is not a party to its public licenses. Notwithstanding,
+Creative Commons may elect to apply one of its public licenses to material
+it publishes and in those instances will be considered the "Licensor." The
+text of the Creative Commons public licenses is dedicated to the public
+domain under the CC0 Public Domain Dedication. Except for the limited
+purpose of indicating that material is shared under a Creative Commons
+public license or as otherwise permitted by the Creative Commons policies
+published at creativecommons.org/policies, Creative Commons does not
+authorize the use of the trademark "Creative Commons" or any other
+trademark or logo of Creative Commons without its prior written consent
+including, without limitation, in connection with any unauthorized
+modifications to any of its public licenses or any other arrangements,
+understandings, or agreements concerning use of licensed material. For the
+avoidance of doubt, this paragraph does not form part of the public
+licenses.
+
+Creative Commons may be contacted at creativecommons.org.
diff --git a/LICENSES/other/CDDL-1.0 b/LICENSES/other/CDDL-1.0
new file mode 100644
index 0000000..195a168
--- /dev/null
+++ b/LICENSES/other/CDDL-1.0
@@ -0,0 +1,364 @@
+Valid-License-Identifier: CDDL-1.0
+SPDX-URL: https://spdx.org/licenses/CDDL-1.0.html
+Usage-Guide:
+ To use the Common Development and Distribution License 1.0 put the
+ following SPDX tag/value pair into a comment according to the placement
+ guidelines in the licensing rules documentation:
+ SPDX-License-Identifier: CDDL-1.0
+
+License-Text:
+
+COMMON DEVELOPMENT AND DISTRIBUTION LICENSE (CDDL)
+Version 1.0
+
+ 1. Definitions.
+
+ 1.1. "Contributor" means each individual or entity that creates or
+ contributes to the creation of Modifications.
+
+ 1.2. "Contributor Version" means the combination of the Original
+ Software, prior Modifications used by a Contributor (if any),
+ and the Modifications made by that particular Contributor.
+
+ 1.3. "Covered Software" means (a) the Original Software, or (b)
+ Modifications, or (c) the combination of files containing
+ Original Software with files containing Modifications, in each
+ case including portions thereof.
+
+ 1.4. "Executable" means the Covered Software in any form other than
+ Source Code.
+
+ 1.5. "Initial Developer" means the individual or entity that first
+ makes Original Software available under this License.
+
+ 1.6. "Larger Work" means a work which combines Covered Software or
+ portions thereof with code not governed by the terms of this
+ License.
+
+ 1.7. "License" means this document.
+
+ 1.8. "Licensable" means having the right to grant, to the maximum
+ extent possible, whether at the time of the initial grant or
+ subsequently acquired, any and all of the rights conveyed herein.
+
+ 1.9. "Modifications" means the Source Code and Executable form of
+ any of the following:
+
+ A. Any file that results from an addition to, deletion from or
+ modification of the contents of a file containing Original
+ Software or previous Modifications;
+
+ B. Any new file that contains any part of the Original Software
+ or previous Modification; or
+
+ C. Any new file that is contributed or otherwise made available
+ under the terms of this License.
+
+ 1.10. "Original Software" means the Source Code and Executable form
+ of computer software code that is originally released under
+ this License.
+
+ 1.11. "Patent Claims" means any patent claim(s), now owned or
+ hereafter acquired, including without limitation, method,
+ process, and apparatus claims, in any patent Licensable by
+ grantor.
+
+ 1.12. "Source Code" means (a) the common form of computer software
+ code in which modifications are made and (b) associated
+ documentation included in or with such code.
+
+ 1.13. "You" (or "Your") means an individual or a legal entity
+ exercising rights under, and complying with all of the terms
+ of, this License. For legal entities, "You" includes any
+ entity which controls, is controlled by, or is under common
+ control with You. For purposes of this definition, "control"
+ means (a) the power, direct or indirect, to cause the
+ direction or management of such entity, whether by contract
+ or otherwise, or (b) ownership of more than fifty percent
+ (50%) of the outstanding shares or beneficial ownership of
+ such entity.
+
+ 2. License Grants.
+ 2.1. The Initial Developer Grant.
+
+ Conditioned upon Your compliance with Section 3.1 below and subject
+ to third party intellectual property claims, the Initial Developer
+ hereby grants You a world-wide, royalty-free, non-exclusive
+ license:
+
+ (a) under intellectual property rights (other than patent or
+ trademark) Licensable by Initial Developer, to use,
+ reproduce, modify, display, perform, sublicense and
+ distribute the Original Software (or portions thereof),
+ with or without Modifications, and/or as part of a Larger
+ Work; and
+
+ (b) under Patent Claims infringed by the making, using or
+ selling of Original Software, to make, have made, use,
+ practice, sell, and offer for sale, and/or otherwise
+ dispose of the Original Software (or portions thereof).
+
+ (c) The licenses granted in Sections 2.1(a) and (b) are
+ effective on the date Initial Developer first distributes
+ or otherwise makes the Original Software available to a
+ third party under the terms of this License.
+
+ (d) Notwithstanding Section 2.1(b) above, no patent license is
+ granted: (1) for code that You delete from the Original
+ Software, or (2) for infringements caused by: (i) the
+ modification of the Original Software, or (ii) the
+ combination of the Original Software with other software or
+ devices.
+
+ 2.2. Contributor Grant.
+
+ Conditioned upon Your compliance with Section 3.1 below and subject
+ to third party intellectual property claims, each Contributor
+ hereby grants You a world-wide, royalty-free, non-exclusive
+ license:
+
+ (a) under intellectual property rights (other than patent or
+ trademark) Licensable by Contributor to use, reproduce,
+ modify, display, perform, sublicense and distribute the
+ Modifications created by such Contributor (or portions
+ thereof), either on an unmodified basis, with other
+ Modifications, as Covered Software and/or as part of a
+ Larger Work; and
+
+ (b) under Patent Claims infringed by the making, using, or
+ selling of Modifications made by that Contributor either
+ alone and/or in combination with its Contributor Version
+ (or portions of such combination), to make, use, sell,
+ offer for sale, have made, and/or otherwise dispose of: (1)
+ Modifications made by that Contributor (or portions
+ thereof); and (2) the combination of Modifications made by
+ that Contributor with its Contributor Version (or portions
+ of such combination).
+
+ (c) The licenses granted in Sections 2.2(a) and 2.2(b) are
+ effective on the date Contributor first distributes or
+ otherwise makes the Modifications available to a third
+ party.
+
+ (d) Notwithstanding Section 2.2(b) above, no patent license is
+ granted: (1) for any code that Contributor has deleted from
+ the Contributor Version; (2) for infringements caused by:
+ (i) third party modifications of Contributor Version, or
+ (ii) the combination of Modifications made by that
+ Contributor with other software (except as part of the
+ Contributor Version) or other devices; or (3) under Patent
+ Claims infringed by Covered Software in the absence of
+ Modifications made by that Contributor.
+
+ 3. Distribution Obligations.
+ 3.1. Availability of Source Code.
+
+ Any Covered Software that You distribute or otherwise make
+ available in Executable form must also be made available in Source
+ Code form and that Source Code form must be distributed only under
+ the terms of this License. You must include a copy of this License
+ with every copy of the Source Code form of the Covered Software You
+ distribute or otherwise make available. You must inform recipients
+ of any such Covered Software in Executable form as to how they can
+ obtain such Covered Software in Source Code form in a reasonable
+ manner on or through a medium customarily used for software
+ exchange.
+
+ 3.2. Modifications.
+
+ The Modifications that You create or to which You contribute are
+ governed by the terms of this License. You represent that You
+ believe Your Modifications are Your original creation(s) and/or You
+ have sufficient rights to grant the rights conveyed by this
+ License.
+
+ 3.3. Required Notices.
+
+ You must include a notice in each of Your Modifications that
+ identifies You as the Contributor of the Modification. You may not
+ remove or alter any copyright, patent or trademark notices
+ contained within the Covered Software, or any notices of licensing
+ or any descriptive text giving attribution to any Contributor or
+ the Initial Developer.
+
+ 3.4. Application of Additional Terms.
+
+ You may not offer or impose any terms on any Covered Software in
+ Source Code form that alters or restricts the applicable version of
+ this License or the recipients' rights hereunder. You may choose to
+ offer, and to charge a fee for, warranty, support, indemnity or
+ liability obligations to one or more recipients of Covered
+ Software. However, you may do so only on Your own behalf, and not
+ on behalf of the Initial Developer or any Contributor. You must
+ make it absolutely clear that any such warranty, support, indemnity
+ or liability obligation is offered by You alone, and You hereby
+ agree to indemnify the Initial Developer and every Contributor for
+ any liability incurred by the Initial Developer or such Contributor
+ as a result of warranty, support, indemnity or liability terms You
+ offer.
+
+ 3.5. Distribution of Executable Versions.
+
+ You may distribute the Executable form of the Covered Software
+ under the terms of this License or under the terms of a license of
+ Your choice, which may contain terms different from this License,
+ provided that You are in compliance with the terms of this License
+ and that the license for the Executable form does not attempt to
+ limit or alter the recipient's rights in the Source Code form from
+ the rights set forth in this License. If You distribute the Covered
+ Software in Executable form under a different license, You must
+ make it absolutely clear that any terms which differ from this
+ License are offered by You alone, not by the Initial Developer or
+ Contributor. You hereby agree to indemnify the Initial Developer
+ and every Contributor for any liability incurred by the Initial
+ Developer or such Contributor as a result of any such terms You
+ offer.
+
+ 3.6. Larger Works.
+
+ You may create a Larger Work by combining Covered Software with
+ other code not governed by the terms of this License and distribute
+ the Larger Work as a single product. In such a case, You must make
+ sure the requirements of this License are fulfilled for the Covered
+ Software.
+
+ 4. Versions of the License.
+ 4.1. New Versions.
+
+ Sun Microsystems, Inc. is the initial license steward and may
+ publish revised and/or new versions of this License from time to
+ time. Each version will be given a distinguishing version
+ number. Except as provided in Section 4.3, no one other than the
+ license steward has the right to modify this License.
+
+ 4.2. Effect of New Versions.
+
+ You may always continue to use, distribute or otherwise make the
+ Covered Software available under the terms of the version of the
+ License under which You originally received the Covered
+ Software. If the Initial Developer includes a notice in the
+ Original Software prohibiting it from being distributed or
+ otherwise made available under any subsequent version of the
+ License, You must distribute and make the Covered Software
+ available under the terms of the version of the License under which
+ You originally received the Covered Software. Otherwise, You may
+ also choose to use, distribute or otherwise make the Covered
+ Software available under the terms of any subsequent version of the
+ License published by the license steward.
+
+ 4.3. Modified Versions.
+
+ When You are an Initial Developer and You want to create a new
+ license for Your Original Software, You may create and use a
+ modified version of this License if You: (a) rename the license and
+ remove any references to the name of the license steward (except to
+ note that the license differs from this License); and (b) otherwise
+ make it clear that the license contains terms which differ from
+ this License.
+
+ 5. DISCLAIMER OF WARRANTY.
+
+ COVERED SOFTWARE IS PROVIDED UNDER THIS LICENSE ON AN "AS IS" BASIS,
+ WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
+ WITHOUT LIMITATION, WARRANTIES THAT THE COVERED SOFTWARE IS FREE OF
+ DEFECTS, MERCHANTABLE, FIT FOR A PARTICULAR PURPOSE OR
+ NON-INFRINGING. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF
+ THE COVERED SOFTWARE IS WITH YOU. SHOULD ANY COVERED SOFTWARE PROVE
+ DEFECTIVE IN ANY RESPECT, YOU (NOT THE INITIAL DEVELOPER OR ANY OTHER
+ CONTRIBUTOR) ASSUME THE COST OF ANY NECESSARY SERVICING, REPAIR OR
+ CORRECTION. THIS DISCLAIMER OF WARRANTY CONSTITUTES AN ESSENTIAL PART
+ OF THIS LICENSE. NO USE OF ANY COVERED SOFTWARE IS AUTHORIZED HEREUNDER
+ EXCEPT UNDER THIS DISCLAIMER.
+
+ 6. TERMINATION.
+
+ 6.1. This License and the rights granted hereunder will terminate
+ automatically if You fail to comply with terms herein and fail to
+ cure such breach within 30 days of becoming aware of the
+ breach. Provisions which, by their nature, must remain in effect
+ beyond the termination of this License shall survive.
+
+ 6.2. If You assert a patent infringement claim (excluding
+ declaratory judgment actions) against Initial Developer or a
+ Contributor (the Initial Developer or Contributor against whom You
+ assert such claim is referred to as "Participant") alleging that
+ the Participant Software (meaning the Contributor Version where the
+ Participant is a Contributor or the Original Software where the
+ Participant is the Initial Developer) directly or indirectly
+ infringes any patent, then any and all rights granted directly or
+ indirectly to You by such Participant, the Initial Developer (if
+ the Initial Developer is not the Participant) and all Contributors
+ under Sections 2.1 and/or 2.2 of this License shall, upon 60 days
+ notice from Participant terminate prospectively and automatically
+ at the expiration of such 60 day notice period, unless if within
+ such 60 day period You withdraw Your claim with respect to the
+ Participant Software against such Participant either unilaterally
+ or pursuant to a written agreement with Participant.
+
+ 6.3. In the event of termination under Sections 6.1 or 6.2 above,
+ all end user licenses that have been validly granted by You or any
+ distributor hereunder prior to termination (excluding licenses
+ granted to You by any distributor) shall survive termination.
+
+ 7. LIMITATION OF LIABILITY.
+
+ UNDER NO CIRCUMSTANCES AND UNDER NO LEGAL THEORY, WHETHER TORT
+ (INCLUDING NEGLIGENCE), CONTRACT, OR OTHERWISE, SHALL YOU, THE INITIAL
+ DEVELOPER, ANY OTHER CONTRIBUTOR, OR ANY DISTRIBUTOR OF COVERED
+ SOFTWARE, OR ANY SUPPLIER OF ANY OF SUCH PARTIES, BE LIABLE TO ANY
+ PERSON FOR ANY INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES
+ OF ANY CHARACTER INCLUDING, WITHOUT LIMITATION, DAMAGES FOR LOST
+ PROFITS, LOSS OF GOODWILL, WORK STOPPAGE, COMPUTER FAILURE OR
+ MALFUNCTION, OR ANY AND ALL OTHER COMMERCIAL DAMAGES OR LOSSES, EVEN IF
+ SUCH PARTY SHALL HAVE BEEN INFORMED OF THE POSSIBILITY OF SUCH
+ DAMAGES. THIS LIMITATION OF LIABILITY SHALL NOT APPLY TO LIABILITY FOR
+ DEATH OR PERSONAL INJURY RESULTING FROM SUCH PARTY'S NEGLIGENCE TO THE
+ EXTENT APPLICABLE LAW PROHIBITS SUCH LIMITATION. SOME JURISDICTIONS DO
+ NOT ALLOW THE EXCLUSION OR LIMITATION OF INCIDENTAL OR CONSEQUENTIAL
+ DAMAGES, SO THIS EXCLUSION AND LIMITATION MAY NOT APPLY TO YOU.
+
+ 8. U.S. GOVERNMENT END USERS.
+
+ The Covered Software is a "commercial item," as that term is defined in
+ 48 C.F.R. 2.101 (Oct. 1995), consisting of "commercial computer
+ software" (as that term is defined at 48 C.F.R. $ 252.227-7014(a)(1))
+ and "commercial computer software documentation" as such terms are used
+ in 48 C.F.R. 12.212 (Sept. 1995). Consistent with 48 C.F.R. 12.212 and
+ 48 C.F.R. 227.7202-1 through 227.7202-4 (June 1995), all
+ U.S. Government End Users acquire Covered Software with only those
+ rights set forth herein. This U.S. Government Rights clause is in lieu
+ of, and supersedes, any other FAR, DFAR, or other clause or provision
+ that addresses Government rights in computer software under this
+ License.
+
+ 9. MISCELLANEOUS.
+
+ This License represents the complete agreement concerning subject
+ matter hereof. If any provision of this License is held to be
+ unenforceable, such provision shall be reformed only to the extent
+ necessary to make it enforceable. This License shall be governed by the
+ law of the jurisdiction specified in a notice contained within the
+ Original Software (except to the extent applicable law, if any,
+ provides otherwise), excluding such jurisdiction's conflict-of-law
+ provisions. Any litigation relating to this License shall be subject to
+ the jurisdiction of the courts located in the jurisdiction and venue
+ specified in a notice contained within the Original Software, with the
+ losing party responsible for costs, including, without limitation,
+ court costs and reasonable attorneys' fees and expenses. The
+ application of the United Nations Convention on Contracts for the
+ International Sale of Goods is expressly excluded. Any law or
+ regulation which provides that the language of a contract shall be
+ construed against the drafter shall not apply to this License. You
+ agree that You alone are responsible for compliance with the United
+ States export administration regulations (and the export control laws
+ and regulation of any other countries) when You use, distribute or
+ otherwise make available any Covered Software.
+
+ 10. RESPONSIBILITY FOR CLAIMS.
+
+ As between Initial Developer and the Contributors, each party is
+ responsible for claims and damages arising, directly or indirectly, out
+ of its utilization of rights under this License and You agree to work
+ with Initial Developer and Contributors to distribute such
+ responsibility on an equitable basis. Nothing herein is intended or
+ shall be deemed to constitute any admission of liability.
diff --git a/LICENSES/other/Linux-OpenIB b/LICENSES/other/Linux-OpenIB
new file mode 100644
index 0000000..1ad85f6
--- /dev/null
+++ b/LICENSES/other/Linux-OpenIB
@@ -0,0 +1,26 @@
+Valid-License-Identifier: Linux-OpenIB
+SPDX-URL: https://spdx.org/licenses/Linux-OpenIB.html
+Usage-Guide:
+ To use the Linux Kernel Variant of OpenIB.org license put the following
+ SPDX tag/value pair into a comment according to the placement guidelines
+ in the licensing rules documentation:
+ SPDX-License-Identifier: Linux-OpenIB
+License-Text:
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+ - Redistributions of source code must retain the above copyright
+ notice, this list of conditions and the following disclaimer.
+
+ - Redistributions in binary form must reproduce the above copyright
+ notice, this list of conditions and the following disclaimer in the
+ documentation and/or other materials provided with the distribution.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+DEALINGS IN THE SOFTWARE.
diff --git a/LICENSES/other/X11 b/LICENSES/other/X11
new file mode 100644
index 0000000..fe4353f
--- /dev/null
+++ b/LICENSES/other/X11
@@ -0,0 +1,37 @@
+Valid-License-Identifier: X11
+SPDX-URL: https://spdx.org/licenses/X11.html
+Usage-Guide:
+ To use the X11 put the following SPDX tag/value pair into a comment
+ according to the placement guidelines in the licensing rules
+ documentation:
+ SPDX-License-Identifier: X11
+License-Text:
+
+
+X11 License
+
+Copyright (C) 1996 X Consortium
+
+Permission is hereby granted, free of charge, to any person obtaining a
+copy of this software and associated documentation files (the "Software"),
+to deal in the Software without restriction, including without limitation
+the rights to use, copy, modify, merge, publish, distribute, sublicense,
+and/or sell copies of the Software, and to permit persons to whom the
+Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+X CONSORTIUM BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
+IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+Except as contained in this notice, the name of the X Consortium shall not
+be used in advertising or otherwise to promote the sale, use or other
+dealings in this Software without prior written authorization from the X
+Consortium.
+
+X Window System is a trademark of X Consortium, Inc.
diff --git a/LICENSES/preferred/GPL-2.0 b/LICENSES/preferred/GPL-2.0
index b8db91d..ff0812f 100644
--- a/LICENSES/preferred/GPL-2.0
+++ b/LICENSES/preferred/GPL-2.0
@@ -1,5 +1,7 @@
Valid-License-Identifier: GPL-2.0
+Valid-License-Identifier: GPL-2.0-only
Valid-License-Identifier: GPL-2.0+
+Valid-License-Identifier: GPL-2.0-or-later
SPDX-URL: https://spdx.org/licenses/GPL-2.0.html
Usage-Guide:
To use this license in source code, put one of the following SPDX
@@ -7,8 +9,12 @@
guidelines in the licensing rules documentation.
For 'GNU General Public License (GPL) version 2 only' use:
SPDX-License-Identifier: GPL-2.0
+ or
+ SPDX-License-Identifier: GPL-2.0-only
For 'GNU General Public License (GPL) version 2 or any later version' use:
SPDX-License-Identifier: GPL-2.0+
+ or
+ SPDX-License-Identifier: GPL-2.0-or-later
License-Text:
GNU GENERAL PUBLIC LICENSE
diff --git a/MAINTAINERS b/MAINTAINERS
index 0a1410d..a2254ac 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -137,9 +137,9 @@
-----------------------------------
3C59X NETWORK DRIVER
-M: Steffen Klassert <klassert@mathematik.tu-chemnitz.de>
+M: Steffen Klassert <klassert@kernel.org>
L: netdev@vger.kernel.org
-S: Maintained
+S: Odd Fixes
F: Documentation/networking/vortex.txt
F: drivers/net/ethernet/3com/3c59x.c
@@ -564,8 +564,9 @@
F: drivers/media/dvb-frontends/af9033*
AFFS FILE SYSTEM
+M: David Sterba <dsterba@suse.com>
L: linux-fsdevel@vger.kernel.org
-S: Orphan
+S: Odd Fixes
F: Documentation/filesystems/affs.txt
F: fs/affs/
@@ -905,6 +906,8 @@
M: Laura Abbott <labbott@redhat.com>
M: Sumit Semwal <sumit.semwal@linaro.org>
L: devel@driverdev.osuosl.org
+L: dri-devel@lists.freedesktop.org
+L: linaro-mm-sig@lists.linaro.org (moderated for non-subscribers)
S: Supported
F: drivers/staging/android/ion
F: drivers/staging/android/uapi/ion.h
@@ -1208,7 +1211,6 @@
ARM/ARTPEC MACHINE SUPPORT
M: Jesper Nilsson <jesper.nilsson@axis.com>
M: Lars Persson <lars.persson@axis.com>
-M: Niklas Cassel <niklas.cassel@axis.com>
S: Maintained
L: linux-arm-kernel@axis.com
F: arch/arm/mach-artpec
@@ -1373,7 +1375,8 @@
F: drivers/net/ethernet/amd/am79c961a.*
ARM/ENERGY MICRO (SILICON LABS) EFM32 SUPPORT
-M: Uwe Kleine-König <kernel@pengutronix.de>
+M: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+R: Pengutronix Kernel Team <kernel@pengutronix.de>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
N: efm32
@@ -1401,7 +1404,8 @@
ARM/FREESCALE IMX / MXC ARM ARCHITECTURE
M: Shawn Guo <shawnguo@kernel.org>
-M: Sascha Hauer <kernel@pengutronix.de>
+M: Sascha Hauer <s.hauer@pengutronix.de>
+R: Pengutronix Kernel Team <kernel@pengutronix.de>
R: Fabio Estevam <fabio.estevam@nxp.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
@@ -1416,7 +1420,8 @@
ARM/FREESCALE VYBRID ARM ARCHITECTURE
M: Shawn Guo <shawnguo@kernel.org>
-M: Sascha Hauer <kernel@pengutronix.de>
+M: Sascha Hauer <s.hauer@pengutronix.de>
+R: Pengutronix Kernel Team <kernel@pengutronix.de>
R: Stefan Agner <stefan@agner.ch>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
@@ -2327,7 +2332,7 @@
F: Documentation/devicetree/bindings/gpio/gpio-ath79.txt
ATHEROS ATH GENERIC UTILITIES
-M: "Luis R. Rodriguez" <mcgrof@do-not-panic.com>
+M: Kalle Valo <kvalo@codeaurora.org>
L: linux-wireless@vger.kernel.org
S: Supported
F: drivers/net/wireless/ath/*
@@ -2342,7 +2347,7 @@
F: drivers/net/wireless/ath/ath5k/
ATHEROS ATH6KL WIRELESS DRIVER
-M: Kalle Valo <kvalo@qca.qualcomm.com>
+M: Kalle Valo <kvalo@codeaurora.org>
L: linux-wireless@vger.kernel.org
W: http://wireless.kernel.org/en/users/Drivers/ath6kl
T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git
@@ -2549,7 +2554,6 @@
F: sound/soc/atmel/tse850-pcm5142.c
AZ6007 DVB DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
@@ -2614,7 +2618,7 @@
F: drivers/net/hamradio/baycom*
BCACHE (BLOCK LAYER CACHE)
-M: Michael Lyle <mlyle@lyle.org>
+M: Coly Li <colyli@suse.de>
M: Kent Overstreet <kent.overstreet@gmail.com>
L: linux-bcache@vger.kernel.org
W: http://bcache.evilpiepirate.org
@@ -3078,7 +3082,6 @@
F: include/uapi/linux/btrfs*
BTTV VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
@@ -3688,7 +3691,6 @@
CPU POWER MONITORING SUBSYSTEM
M: Thomas Renninger <trenn@suse.com>
-M: Shuah Khan <shuahkh@osg.samsung.com>
M: Shuah Khan <shuah@kernel.org>
L: linux-pm@vger.kernel.org
S: Maintained
@@ -3807,7 +3809,6 @@
F: drivers/media/dvb-frontends/cx24120*
CX88 VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
@@ -4245,6 +4246,9 @@
DEVICE DIRECT ACCESS (DAX)
M: Dan Williams <dan.j.williams@intel.com>
+M: Dave Jiang <dave.jiang@intel.com>
+M: Ross Zwisler <ross.zwisler@linux.intel.com>
+M: Vishal Verma <vishal.l.verma@intel.com>
L: linux-nvdimm@lists.01.org
S: Supported
F: drivers/dax/
@@ -4305,7 +4309,7 @@
T: git git://anongit.freedesktop.org/drm/drm-misc
DMA GENERIC OFFLOAD ENGINE SUBSYSTEM
-M: Vinod Koul <vinod.koul@intel.com>
+M: Vinod Koul <vkoul@kernel.org>
L: dmaengine@vger.kernel.org
Q: https://patchwork.kernel.org/project/linux-dmaengine/list/
S: Maintained
@@ -4326,12 +4330,14 @@
S: Supported
F: lib/dma-debug.c
F: lib/dma-direct.c
+F: lib/dma-noncoherent.c
F: lib/dma-virt.c
F: drivers/base/dma-mapping.c
F: drivers/base/dma-coherent.c
F: include/asm-generic/dma-mapping.h
F: include/linux/dma-direct.h
F: include/linux/dma-mapping.h
+F: include/linux/dma-noncoherent.h
DME1737 HARDWARE MONITOR DRIVER
M: Juerg Haefliger <juergh@gmail.com>
@@ -5045,7 +5051,6 @@
EDAC-CORE
M: Borislav Petkov <bp@alien8.de>
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-edac@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp.git for-next
@@ -5074,7 +5079,6 @@
F: drivers/edac/fsl_ddr_edac.*
EDAC-GHES
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-edac@vger.kernel.org
S: Maintained
@@ -5091,21 +5095,18 @@
F: drivers/edac/i5000_edac.c
EDAC-I5400
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-edac@vger.kernel.org
S: Maintained
F: drivers/edac/i5400_edac.c
EDAC-I7300
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-edac@vger.kernel.org
S: Maintained
F: drivers/edac/i7300_edac.c
EDAC-I7CORE
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-edac@vger.kernel.org
S: Maintained
@@ -5155,7 +5156,6 @@
F: drivers/edac/r82600_edac.c
EDAC-SBRIDGE
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-edac@vger.kernel.org
S: Maintained
@@ -5214,7 +5214,6 @@
F: drivers/net/ethernet/ibm/ehea/
EM28XX VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
@@ -5391,7 +5390,6 @@
F: drivers/iommu/exynos-iommu.c
EZchip NPS platform support
-M: Elad Kanfi <eladkan@mellanox.com>
M: Vineet Gupta <vgupta@synopsys.com>
S: Supported
F: arch/arc/plat-eznps
@@ -5417,6 +5415,11 @@
F: Documentation/hwmon/f71805f
F: drivers/hwmon/f71805f.c
+FADDR2LINE
+M: Josh Poimboeuf <jpoimboe@redhat.com>
+S: Maintained
+F: scripts/faddr2line
+
FANOTIFY
M: Jan Kara <jack@suse.cz>
R: Amir Goldstein <amir73il@gmail.com>
@@ -5652,7 +5655,8 @@
F: Documentation/devicetree/bindings/net/fsl-fec.txt
FREESCALE IMX / MXC FRAMEBUFFER DRIVER
-M: Sascha Hauer <kernel@pengutronix.de>
+M: Sascha Hauer <s.hauer@pengutronix.de>
+R: Pengutronix Kernel Team <kernel@pengutronix.de>
L: linux-fbdev@vger.kernel.org
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
@@ -5784,6 +5788,14 @@
F: include/linux/fscrypt*.h
F: Documentation/filesystems/fscrypt.rst
+FSNOTIFY: FILESYSTEM NOTIFICATION INFRASTRUCTURE
+M: Jan Kara <jack@suse.cz>
+R: Amir Goldstein <amir73il@gmail.com>
+L: linux-fsdevel@vger.kernel.org
+S: Maintained
+F: fs/notify/
+F: include/linux/fsnotify*.h
+
FUJITSU LAPTOP EXTRAS
M: Jonathan Woithe <jwoithe@just42.net>
L: platform-driver-x86@vger.kernel.org
@@ -5943,8 +5955,8 @@
F: scripts/get_maintainer.pl
GFS2 FILE SYSTEM
-M: Steven Whitehouse <swhiteho@redhat.com>
M: Bob Peterson <rpeterso@redhat.com>
+M: Andreas Gruenbacher <agruenba@redhat.com>
L: cluster-devel@redhat.com
W: http://sources.redhat.com/cluster/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2.git
@@ -6212,6 +6224,7 @@
W: http://hwmon.wiki.kernel.org/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging.git
S: Maintained
+F: Documentation/devicetree/bindings/hwmon/
F: Documentation/hwmon/
F: drivers/hwmon/
F: include/linux/hwmon*.h
@@ -6256,7 +6269,7 @@
F: drivers/media/usb/hdpvr/
HEWLETT PACKARD ENTERPRISE ILO NMI WATCHDOG DRIVER
-M: Jimmy Vance <jimmy.vance@hpe.com>
+M: Jerry Hoemann <jerry.hoemann@hpe.com>
S: Supported
F: Documentation/watchdog/hpwdt.txt
F: drivers/watchdog/hpwdt.c
@@ -6498,9 +6511,15 @@
F: drivers/net/ethernet/huawei/hinic/
HUGETLB FILESYSTEM
-M: Nadia Yvette Chambers <nyc@holomorphy.com>
+M: Mike Kravetz <mike.kravetz@oracle.com>
+L: linux-mm@kvack.org
S: Maintained
F: fs/hugetlbfs/
+F: mm/hugetlb.c
+F: include/linux/hugetlb.h
+F: Documentation/admin-guide/mm/hugetlbpage.rst
+F: Documentation/vm/hugetlbfs_reserv.rst
+F: Documentation/ABI/testing/sysfs-kernel-mm-hugepages
HVA ST MEDIA DRIVER
M: Jean-Christophe Trotin <jean-christophe.trotin@st.com>
@@ -7396,16 +7415,6 @@
F: include/uapi/linux/ipx.h
F: drivers/staging/ipx/
-IRDA SUBSYSTEM
-M: Samuel Ortiz <samuel@sortiz.org>
-L: irda-users@lists.sourceforge.net (subscribers-only)
-L: netdev@vger.kernel.org
-W: http://irda.sourceforge.net/
-S: Obsolete
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/sameo/irda-2.6.git
-F: Documentation/networking/irda.txt
-F: drivers/staging/irda/
-
IRQ DOMAINS (IRQ NUMBER MAPPING LIBRARY)
M: Marc Zyngier <marc.zyngier@arm.com>
S: Maintained
@@ -7670,9 +7679,11 @@
S: Maintained
F: Documentation/kbuild/
F: Makefile
-F: scripts/Makefile.*
+F: scripts/Kbuild*
+F: scripts/Makefile*
F: scripts/basic/
F: scripts/mk*
+F: scripts/mod/
F: scripts/package/
KERNEL JANITORS
@@ -7697,10 +7708,10 @@
F: include/uapi/linux/sunrpc/
KERNEL SELFTEST FRAMEWORK
-M: Shuah Khan <shuahkh@osg.samsung.com>
M: Shuah Khan <shuah@kernel.org>
L: linux-kselftest@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git
+Q: https://patchwork.kernel.org/project/linux-kselftest/list/
S: Maintained
F: tools/testing/selftests/
F: Documentation/dev-tools/kselftest*
@@ -7738,7 +7749,7 @@
F: arch/x86/kvm/svm.c
KERNEL VIRTUAL MACHINE FOR ARM (KVM/arm)
-M: Christoffer Dall <christoffer.dall@linaro.org>
+M: Christoffer Dall <christoffer.dall@arm.com>
M: Marc Zyngier <marc.zyngier@arm.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: kvmarm@lists.cs.columbia.edu
@@ -7752,7 +7763,7 @@
F: include/kvm/arm_*
KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64)
-M: Christoffer Dall <christoffer.dall@linaro.org>
+M: Christoffer Dall <christoffer.dall@arm.com>
M: Marc Zyngier <marc.zyngier@arm.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: kvmarm@lists.cs.columbia.edu
@@ -8048,6 +8059,9 @@
LIBNVDIMM BLK: MMIO-APERTURE DRIVER
M: Ross Zwisler <ross.zwisler@linux.intel.com>
+M: Dan Williams <dan.j.williams@intel.com>
+M: Vishal Verma <vishal.l.verma@intel.com>
+M: Dave Jiang <dave.jiang@intel.com>
L: linux-nvdimm@lists.01.org
Q: https://patchwork.kernel.org/project/linux-nvdimm/list/
S: Supported
@@ -8056,6 +8070,9 @@
LIBNVDIMM BTT: BLOCK TRANSLATION TABLE
M: Vishal Verma <vishal.l.verma@intel.com>
+M: Dan Williams <dan.j.williams@intel.com>
+M: Ross Zwisler <ross.zwisler@linux.intel.com>
+M: Dave Jiang <dave.jiang@intel.com>
L: linux-nvdimm@lists.01.org
Q: https://patchwork.kernel.org/project/linux-nvdimm/list/
S: Supported
@@ -8063,6 +8080,9 @@
LIBNVDIMM PMEM: PERSISTENT MEMORY DRIVER
M: Ross Zwisler <ross.zwisler@linux.intel.com>
+M: Dan Williams <dan.j.williams@intel.com>
+M: Vishal Verma <vishal.l.verma@intel.com>
+M: Dave Jiang <dave.jiang@intel.com>
L: linux-nvdimm@lists.01.org
Q: https://patchwork.kernel.org/project/linux-nvdimm/list/
S: Supported
@@ -8078,6 +8098,9 @@
LIBNVDIMM: NON-VOLATILE MEMORY DEVICE SUBSYSTEM
M: Dan Williams <dan.j.williams@intel.com>
+M: Ross Zwisler <ross.zwisler@linux.intel.com>
+M: Vishal Verma <vishal.l.verma@intel.com>
+M: Dave Jiang <dave.jiang@intel.com>
L: linux-nvdimm@lists.01.org
Q: https://patchwork.kernel.org/project/linux-nvdimm/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm.git
@@ -8194,7 +8217,7 @@
LINUX KERNEL MEMORY CONSISTENCY MODEL (LKMM)
M: Alan Stern <stern@rowland.harvard.edu>
-M: Andrea Parri <parri.andrea@gmail.com>
+M: Andrea Parri <andrea.parri@amarulasolutions.com>
M: Will Deacon <will.deacon@arm.com>
M: Peter Zijlstra <peterz@infradead.org>
M: Boqun Feng <boqun.feng@gmail.com>
@@ -8301,6 +8324,7 @@
LOCKING PRIMITIVES
M: Peter Zijlstra <peterz@infradead.org>
M: Ingo Molnar <mingo@redhat.com>
+M: Will Deacon <will.deacon@arm.com>
L: linux-kernel@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core
S: Maintained
@@ -8852,7 +8876,6 @@
F: drivers/staging/media/tegra-vde/
MEDIA INPUT INFRASTRUCTURE (V4L/DVB)
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
P: LinuxTV.org Project
L: linux-media@vger.kernel.org
@@ -9012,7 +9035,6 @@
F: drivers/net/ethernet/mellanox/mlx5/core/en_*
MELLANOX ETHERNET INNOVA DRIVER
-M: Ilan Tayari <ilant@mellanox.com>
R: Boris Pismenny <borisp@mellanox.com>
L: netdev@vger.kernel.org
S: Supported
@@ -9022,7 +9044,6 @@
F: include/linux/mlx5/mlx5_ifc_fpga.h
MELLANOX ETHERNET INNOVA IPSEC DRIVER
-M: Ilan Tayari <ilant@mellanox.com>
R: Boris Pismenny <borisp@mellanox.com>
L: netdev@vger.kernel.org
S: Supported
@@ -9078,7 +9099,6 @@
MELLANOX MLX5 core VPI driver
M: Saeed Mahameed <saeedm@mellanox.com>
-M: Matan Barak <matanb@mellanox.com>
M: Leon Romanovsky <leonro@mellanox.com>
L: netdev@vger.kernel.org
L: linux-rdma@vger.kernel.org
@@ -9089,7 +9109,6 @@
F: include/linux/mlx5/
MELLANOX MLX5 IB driver
-M: Matan Barak <matanb@mellanox.com>
M: Leon Romanovsky <leonro@mellanox.com>
L: linux-rdma@vger.kernel.org
W: http://www.mellanox.com
@@ -9690,7 +9709,7 @@
F: drivers/net/ethernet/netronome/
NETWORK BLOCK DEVICE (NBD)
-M: Josef Bacik <jbacik@fb.com>
+M: Josef Bacik <josef@toxicpanda.com>
S: Maintained
L: linux-block@vger.kernel.org
L: nbd@other.debian.org
@@ -9706,6 +9725,7 @@
F: net/core/drop_monitor.c
NETWORKING DRIVERS
+M: "David S. Miller" <davem@davemloft.net>
L: netdev@vger.kernel.org
W: http://www.linuxfoundation.org/en/Net
Q: http://patchwork.ozlabs.org/project/netdev/list/
@@ -9765,6 +9785,7 @@
F: tools/testing/selftests/net/
F: lib/net_utils.c
F: lib/random32.c
+F: Documentation/networking/
NETWORKING [IPSEC]
M: Steffen Klassert <steffen.klassert@secunet.com>
@@ -9821,7 +9842,6 @@
F: net/netfilter/xt_SECMARK.c
NETWORKING [TLS]
-M: Ilya Lesokhin <ilyal@mellanox.com>
M: Aviad Yehezkel <aviadye@mellanox.com>
M: Dave Watson <davejwatson@fb.com>
L: netdev@vger.kernel.org
@@ -9861,7 +9881,7 @@
F: Documentation/devicetree/bindings/net/nfc/
NFS, SUNRPC, AND LOCKD CLIENTS
-M: Trond Myklebust <trond.myklebust@primarydata.com>
+M: Trond Myklebust <trond.myklebust@hammerspace.com>
M: Anna Schumaker <anna.schumaker@netapp.com>
L: linux-nfs@vger.kernel.org
W: http://client.linux-nfs.org
@@ -10881,7 +10901,6 @@
F: drivers/pci/dwc/
PCIE DRIVER FOR AXIS ARTPEC
-M: Niklas Cassel <niklas.cassel@axis.com>
M: Jesper Nilsson <jesper.nilsson@axis.com>
L: linux-arm-kernel@axis.com
L: linux-pci@vger.kernel.org
@@ -11622,7 +11641,7 @@
F: drivers/media/tuners/qt1010*
QUALCOMM ATHEROS ATH10K WIRELESS DRIVER
-M: Kalle Valo <kvalo@qca.qualcomm.com>
+M: Kalle Valo <kvalo@codeaurora.org>
L: ath10k@lists.infradead.org
W: http://wireless.kernel.org/en/users/Drivers/ath10k
T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git
@@ -11644,6 +11663,13 @@
F: Documentation/media/v4l-drivers/qcom_camss.rst
F: drivers/media/platform/qcom/camss-8x16/
+QUALCOMM CPUFREQ DRIVER MSM8996/APQ8096
+M: Ilia Lin <ilia.lin@gmail.com>
+L: linux-pm@vger.kernel.org
+S: Maintained
+F: Documentation/devicetree/bindings/opp/kryo-cpufreq.txt
+F: drivers/cpufreq/qcom-cpufreq-kryo.c
+
QUALCOMM EMAC GIGABIT ETHERNET DRIVER
M: Timur Tabi <timur@codeaurora.org>
L: netdev@vger.kernel.org
@@ -11673,7 +11699,7 @@
F: drivers/media/platform/qcom/venus/
QUALCOMM WCN36XX WIRELESS DRIVER
-M: Eugene Krasnikov <k.eugene.e@gmail.com>
+M: Kalle Valo <kvalo@codeaurora.org>
L: wcn36xx@lists.infradead.org
W: http://wireless.kernel.org/en/users/Drivers/wcn36xx
T: git git://github.com/KrasnikovEugene/wcn36xx.git
@@ -12211,7 +12237,7 @@
F: include/uapi/linux/vfio_ccw.h
S390 ZCRYPT DRIVER
-M: Harald Freudenberger <freude@de.ibm.com>
+M: Harald Freudenberger <freude@linux.ibm.com>
L: linux-s390@vger.kernel.org
W: http://www.ibm.com/developerworks/linux/linux390/
S: Supported
@@ -12240,7 +12266,6 @@
F: drivers/media/i2c/saa6588*
SAA7134 VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
@@ -12479,6 +12504,7 @@
SCTP PROTOCOL
M: Vlad Yasevich <vyasevich@gmail.com>
M: Neil Horman <nhorman@tuxdriver.com>
+M: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
L: linux-sctp@vger.kernel.org
W: http://lksctp.sourceforge.net
S: Maintained
@@ -12744,7 +12770,6 @@
F: drivers/media/radio/si4713/radio-usb-si4713.c
SIANO DVB DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
@@ -12816,7 +12841,8 @@
SIOX
M: Gavin Schenk <g.schenk@eckelmann.de>
-M: Uwe Kleine-König <kernel@pengutronix.de>
+M: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+R: Pengutronix Kernel Team <kernel@pengutronix.de>
S: Supported
F: drivers/siox/*
F: include/trace/events/siox.h
@@ -13255,6 +13281,12 @@
S: Maintained
F: arch/alpha/kernel/srm_env.c
+ST STM32 I2C/SMBUS DRIVER
+M: Pierre-Yves MORDRET <pierre-yves.mordret@st.com>
+L: linux-i2c@vger.kernel.org
+S: Maintained
+F: drivers/i2c/busses/i2c-stm32*
+
STABLE BRANCH
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
L: stable@vger.kernel.org
@@ -13734,7 +13766,6 @@
F: drivers/media/i2c/tda9840*
TEA5761 TUNER DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
@@ -13743,7 +13774,6 @@
F: drivers/media/tuners/tea5761.*
TEA5767 TUNER DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
@@ -13833,7 +13863,6 @@
F: drivers/iommu/tegra*
TEGRA KBC DRIVER
-M: Rakesh Iyer <riyer@nvidia.com>
M: Laxman Dewangan <ldewangan@nvidia.com>
S: Supported
F: drivers/input/keyboard/tegra-kbc.c
@@ -13936,7 +13965,7 @@
M: Andreas Noever <andreas.noever@gmail.com>
M: Michael Jamet <michael.jamet@intel.com>
M: Mika Westerberg <mika.westerberg@linux.intel.com>
-M: Yehezkel Bernat <yehezkel.bernat@intel.com>
+M: Yehezkel Bernat <YehezkelShB@gmail.com>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/westeri/thunderbolt.git
S: Maintained
F: Documentation/admin-guide/thunderbolt.rst
@@ -13946,7 +13975,7 @@
THUNDERBOLT NETWORK DRIVER
M: Michael Jamet <michael.jamet@intel.com>
M: Mika Westerberg <mika.westerberg@linux.intel.com>
-M: Yehezkel Bernat <yehezkel.bernat@intel.com>
+M: Yehezkel Bernat <YehezkelShB@gmail.com>
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/thunderbolt.c
@@ -14160,7 +14189,6 @@
F: drivers/net/ethernet/ti/tlan.*
TM6000 VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
@@ -14359,6 +14387,15 @@
F: drivers/tc/
F: include/linux/tc.h
+TURBOSTAT UTILITY
+M: "Len Brown" <lenb@kernel.org>
+L: linux-pm@vger.kernel.org
+B: https://bugzilla.kernel.org
+Q: https://patchwork.kernel.org/project/linux-pm/list/
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux.git turbostat
+S: Supported
+F: tools/power/x86/turbostat/
+
TW5864 VIDEO4LINUX DRIVER
M: Bluecherry Maintainers <maintainers@bluecherrydvr.com>
M: Anton Sviridenko <anton@corp.bluecherry.net>
@@ -14643,7 +14680,6 @@
USB OVER IP DRIVER
M: Valentina Manea <valentina.manea.m@gmail.com>
-M: Shuah Khan <shuahkh@osg.samsung.com>
M: Shuah Khan <shuah@kernel.org>
L: linux-usb@vger.kernel.org
S: Maintained
@@ -15387,7 +15423,6 @@
F: arch/x86/entry/vdso/
XC2028/3028 TUNER DRIVER
-M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
W: https://linuxtv.org
@@ -15503,6 +15538,14 @@
S: Supported
F: drivers/char/xillybus/
+XLP9XX I2C DRIVER
+M: George Cherian <george.cherian@cavium.com>
+M: Jan Glauber <jglauber@cavium.com>
+L: linux-i2c@vger.kernel.org
+W: http://www.cavium.com
+S: Supported
+F: drivers/i2c/busses/i2c-xlp9xx.c
+
XRA1403 GPIO EXPANDER
M: Nandor Han <nandor.han@ge.com>
M: Semi Malinen <semi.malinen@ge.com>
@@ -15621,7 +15664,7 @@
S: Maintained
F: mm/zsmalloc.c
F: include/linux/zsmalloc.h
-F: Documentation/vm/zsmalloc.txt
+F: Documentation/vm/zsmalloc.rst
ZSWAP COMPRESSED SWAP CACHING
M: Seth Jennings <sjenning@redhat.com>
diff --git a/Makefile b/Makefile
index e811e0c..554dcad 100644
--- a/Makefile
+++ b/Makefile
@@ -2,8 +2,8 @@
VERSION = 4
PATCHLEVEL = 17
SUBLEVEL = 0
-EXTRAVERSION = -rc1
-NAME = Fearless Coyote
+EXTRAVERSION =
+NAME = Merciless Moray
# *DOCUMENTATION*
# To see a list of typical targets execute "make help"
@@ -500,6 +500,9 @@
RETPOLINE_CFLAGS := $(call cc-option,$(RETPOLINE_CFLAGS_GCC),$(call cc-option,$(RETPOLINE_CFLAGS_CLANG)))
export RETPOLINE_CFLAGS
+KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
+KBUILD_AFLAGS += $(call cc-option,-fno-PIE)
+
# check for 'asm goto'
ifeq ($(call shell-cached,$(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y)
CC_HAVE_ASM_GOTO := 1
@@ -621,9 +624,9 @@
# Defaults to vmlinux, but the arch makefile usually adds further targets
all: vmlinux
-KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
-KBUILD_AFLAGS += $(call cc-option,-fno-PIE)
-CFLAGS_GCOV := -fprofile-arcs -ftest-coverage -fno-tree-loop-im $(call cc-disable-warning,maybe-uninitialized,)
+CFLAGS_GCOV := -fprofile-arcs -ftest-coverage \
+ $(call cc-option,-fno-tree-loop-im) \
+ $(call cc-disable-warning,maybe-uninitialized,)
export CFLAGS_GCOV CFLAGS_KCOV
# The arch Makefile can set ARCH_{CPP,A,C}FLAGS to override the default
diff --git a/arch/Kconfig b/arch/Kconfig
index 8e0d665..b695a3e 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -278,9 +278,6 @@
The <linux/clk.h> calls support software clock gating and
thus are a key power management tool on many systems.
-config HAVE_DMA_API_DEBUG
- bool
-
config HAVE_HW_BREAKPOINT
bool
depends on PERF_EVENTS
@@ -464,6 +461,10 @@
config GCC_PLUGIN_STRUCTLEAK
bool "Force initialization of variables containing userspace addresses"
depends on GCC_PLUGINS
+ # Currently STRUCTLEAK inserts initialization out of live scope of
+ # variables from KASAN point of view. This leads to KASAN false
+ # positive reports. Prohibit this combination for now.
+ depends on !KASAN_EXTRA
help
This plugin zero-initializes any structures containing a
__user attribute. This can prevent some classes of information
@@ -870,6 +871,21 @@
config COMPAT_OLD_SIGACTION
bool
+config 64BIT_TIME
+ def_bool ARCH_HAS_64BIT_TIME
+ help
+ This should be selected by all architectures that need to support
+ new system calls with a 64-bit time_t. This is relevant on all 32-bit
+ architectures, and 64-bit architectures as part of compat syscall
+ handling.
+
+config COMPAT_32BIT_TIME
+ def_bool (!64BIT && 64BIT_TIME) || COMPAT
+ help
+ This enables 32 bit time_t support in addition to 64 bit time_t support.
+ This is relevant on all 32-bit architectures, and 64-bit architectures
+ as part of compat syscall handling.
+
config ARCH_NO_COHERENT_DMA_MMAP
bool
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index b202288..0c4805a 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -10,6 +10,8 @@
select HAVE_OPROFILE
select HAVE_PCSPKR_PLATFORM
select HAVE_PERF_EVENTS
+ select NEED_DMA_MAP_STATE
+ select NEED_SG_DMA_LENGTH
select VIRT_TO_BUS
select GENERIC_IRQ_PROBE
select AUTO_IRQ_AFFINITY if SMP
@@ -64,15 +66,6 @@
bool
default y
-config ARCH_DMA_ADDR_T_64BIT
- def_bool y
-
-config NEED_DMA_MAP_STATE
- def_bool y
-
-config NEED_SG_DMA_LENGTH
- def_bool y
-
config GENERIC_ISA_DMA
bool
default y
@@ -211,6 +204,7 @@
config ALPHA_JENSEN
bool "Jensen"
depends on BROKEN
+ select DMA_DIRECT_OPS
help
DEC PC 150 AXP (aka Jensen): This is a very old Digital system - one
of the first-generation Alpha systems. A number of these systems
@@ -345,9 +339,6 @@
config PCI_SYSCALL
def_bool PCI
-config IOMMU_HELPER
- def_bool PCI
-
config ALPHA_NONAME
bool
depends on ALPHA_BOOK1 || ALPHA_NONAME_CH
@@ -585,7 +576,7 @@
Say Y to support efficient handling of discontiguous physical memory,
for architectures which are either NUMA (Non-Uniform Memory Access)
or have huge holes in the physical address space for other reasons.
- See <file:Documentation/vm/numa> for more.
+ See <file:Documentation/vm/numa.rst> for more.
source "mm/Kconfig"
diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index 9b68790..0580cb8 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -1,6 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
+generic-y += compat.h
generic-y += exec.h
generic-y += export.h
generic-y += fb.h
diff --git a/arch/alpha/include/asm/dma-mapping.h b/arch/alpha/include/asm/dma-mapping.h
index b78f61f..8beeafd 100644
--- a/arch/alpha/include/asm/dma-mapping.h
+++ b/arch/alpha/include/asm/dma-mapping.h
@@ -2,11 +2,15 @@
#ifndef _ALPHA_DMA_MAPPING_H
#define _ALPHA_DMA_MAPPING_H
-extern const struct dma_map_ops *dma_ops;
+extern const struct dma_map_ops alpha_pci_ops;
static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
{
- return dma_ops;
+#ifdef CONFIG_ALPHA_JENSEN
+ return &dma_direct_ops;
+#else
+ return &alpha_pci_ops;
+#endif
}
#endif /* _ALPHA_DMA_MAPPING_H */
diff --git a/arch/alpha/include/asm/pci.h b/arch/alpha/include/asm/pci.h
index b9ec553..cf6bc1e 100644
--- a/arch/alpha/include/asm/pci.h
+++ b/arch/alpha/include/asm/pci.h
@@ -56,11 +56,6 @@ struct pci_controller {
/* IOMMU controls. */
-/* The PCI address space does not equal the physical memory address space.
- The networking and block device layers use this boolean for bounce buffer
- decisions. */
-#define PCI_DMA_BUS_IS_PHYS 0
-
/* TODO: integrate with include/asm-generic/pci.h ? */
static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
{
diff --git a/arch/alpha/include/uapi/asm/Kbuild b/arch/alpha/include/uapi/asm/Kbuild
index 9afaba5..1a5b7531 100644
--- a/arch/alpha/include/uapi/asm/Kbuild
+++ b/arch/alpha/include/uapi/asm/Kbuild
@@ -2,4 +2,8 @@
include include/uapi/asm-generic/Kbuild.asm
generic-y += bpf_perf_event.h
+generic-y += ipcbuf.h
+generic-y += msgbuf.h
generic-y += poll.h
+generic-y += sembuf.h
+generic-y += shmbuf.h
diff --git a/arch/alpha/include/uapi/asm/ipcbuf.h b/arch/alpha/include/uapi/asm/ipcbuf.h
deleted file mode 100644
index 90d6445..0000000
--- a/arch/alpha/include/uapi/asm/ipcbuf.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#include <asm-generic/ipcbuf.h>
diff --git a/arch/alpha/include/uapi/asm/msgbuf.h b/arch/alpha/include/uapi/asm/msgbuf.h
deleted file mode 100644
index 8c5d4d8..0000000
--- a/arch/alpha/include/uapi/asm/msgbuf.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ALPHA_MSGBUF_H
-#define _ALPHA_MSGBUF_H
-
-/*
- * The msqid64_ds structure for alpha architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 2 miscellaneous 64-bit values
- */
-
-struct msqid64_ds {
- struct ipc64_perm msg_perm;
- __kernel_time_t msg_stime; /* last msgsnd time */
- __kernel_time_t msg_rtime; /* last msgrcv time */
- __kernel_time_t msg_ctime; /* last change time */
- unsigned long msg_cbytes; /* current number of bytes on queue */
- unsigned long msg_qnum; /* number of messages in queue */
- unsigned long msg_qbytes; /* max number of bytes on queue */
- __kernel_pid_t msg_lspid; /* pid of last msgsnd */
- __kernel_pid_t msg_lrpid; /* last receive pid */
- unsigned long __unused1;
- unsigned long __unused2;
-};
-
-#endif /* _ALPHA_MSGBUF_H */
diff --git a/arch/alpha/include/uapi/asm/sembuf.h b/arch/alpha/include/uapi/asm/sembuf.h
deleted file mode 100644
index f28ffa6..0000000
--- a/arch/alpha/include/uapi/asm/sembuf.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ALPHA_SEMBUF_H
-#define _ALPHA_SEMBUF_H
-
-/*
- * The semid64_ds structure for alpha architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 2 miscellaneous 64-bit values
- */
-
-struct semid64_ds {
- struct ipc64_perm sem_perm; /* permissions .. see ipc.h */
- __kernel_time_t sem_otime; /* last semop time */
- __kernel_time_t sem_ctime; /* last change time */
- unsigned long sem_nsems; /* no. of semaphores in array */
- unsigned long __unused1;
- unsigned long __unused2;
-};
-
-#endif /* _ALPHA_SEMBUF_H */
diff --git a/arch/alpha/include/uapi/asm/shmbuf.h b/arch/alpha/include/uapi/asm/shmbuf.h
deleted file mode 100644
index 7e041ca..0000000
--- a/arch/alpha/include/uapi/asm/shmbuf.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ALPHA_SHMBUF_H
-#define _ALPHA_SHMBUF_H
-
-/*
- * The shmid64_ds structure for alpha architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 2 miscellaneous 64-bit values
- */
-
-struct shmid64_ds {
- struct ipc64_perm shm_perm; /* operation perms */
- size_t shm_segsz; /* size of segment (bytes) */
- __kernel_time_t shm_atime; /* last attach time */
- __kernel_time_t shm_dtime; /* last detach time */
- __kernel_time_t shm_ctime; /* last change time */
- __kernel_pid_t shm_cpid; /* pid of creator */
- __kernel_pid_t shm_lpid; /* pid of last operator */
- unsigned long shm_nattch; /* no. of current attaches */
- unsigned long __unused1;
- unsigned long __unused2;
-};
-
-struct shminfo64 {
- unsigned long shmmax;
- unsigned long shmmin;
- unsigned long shmmni;
- unsigned long shmseg;
- unsigned long shmall;
- unsigned long __unused1;
- unsigned long __unused2;
- unsigned long __unused3;
- unsigned long __unused4;
-};
-
-#endif /* _ALPHA_SHMBUF_H */
diff --git a/arch/alpha/include/uapi/asm/siginfo.h b/arch/alpha/include/uapi/asm/siginfo.h
index 0cf3b52..db3f013 100644
--- a/arch/alpha/include/uapi/asm/siginfo.h
+++ b/arch/alpha/include/uapi/asm/siginfo.h
@@ -7,18 +7,4 @@
#include <asm-generic/siginfo.h>
-/*
- * SIGFPE si_codes
- */
-#ifdef __KERNEL__
-#define FPE_FIXME 0 /* Broken dup of SI_USER */
-#endif /* __KERNEL__ */
-
-/*
- * SIGTRAP si_codes
- */
-#ifdef __KERNEL__
-#define TRAP_FIXME 0 /* Broken dup of SI_USER */
-#endif /* __KERNEL__ */
-
#endif
diff --git a/arch/alpha/kernel/io.c b/arch/alpha/kernel/io.c
index 3e3d49c..c025a3e 100644
--- a/arch/alpha/kernel/io.c
+++ b/arch/alpha/kernel/io.c
@@ -37,20 +37,20 @@ unsigned int ioread32(void __iomem *addr)
void iowrite8(u8 b, void __iomem *addr)
{
- IO_CONCAT(__IO_PREFIX,iowrite8)(b, addr);
mb();
+ IO_CONCAT(__IO_PREFIX,iowrite8)(b, addr);
}
void iowrite16(u16 b, void __iomem *addr)
{
- IO_CONCAT(__IO_PREFIX,iowrite16)(b, addr);
mb();
+ IO_CONCAT(__IO_PREFIX,iowrite16)(b, addr);
}
void iowrite32(u32 b, void __iomem *addr)
{
- IO_CONCAT(__IO_PREFIX,iowrite32)(b, addr);
mb();
+ IO_CONCAT(__IO_PREFIX,iowrite32)(b, addr);
}
EXPORT_SYMBOL(ioread8);
@@ -176,26 +176,26 @@ u64 readq(const volatile void __iomem *addr)
void writeb(u8 b, volatile void __iomem *addr)
{
- __raw_writeb(b, addr);
mb();
+ __raw_writeb(b, addr);
}
void writew(u16 b, volatile void __iomem *addr)
{
- __raw_writew(b, addr);
mb();
+ __raw_writew(b, addr);
}
void writel(u32 b, volatile void __iomem *addr)
{
- __raw_writel(b, addr);
mb();
+ __raw_writel(b, addr);
}
void writeq(u64 b, volatile void __iomem *addr)
{
- __raw_writeq(b, addr);
mb();
+ __raw_writeq(b, addr);
}
EXPORT_SYMBOL(readb);
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 89faa6f..6e92175 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -871,8 +871,7 @@ SYSCALL_DEFINE5(osf_setsysinfo, unsigned long, op, void __user *, buffer,
send a signal. Old exceptions are not signaled. */
fex = (exc >> IEEE_STATUS_TO_EXCSUM_SHIFT) & swcr;
if (fex) {
- siginfo_t info;
- int si_code = 0;
+ int si_code = FPE_FLTUNK;
if (fex & IEEE_TRAP_ENABLE_DNO) si_code = FPE_FLTUND;
if (fex & IEEE_TRAP_ENABLE_INE) si_code = FPE_FLTRES;
@@ -881,11 +880,9 @@ SYSCALL_DEFINE5(osf_setsysinfo, unsigned long, op, void __user *, buffer,
if (fex & IEEE_TRAP_ENABLE_DZE) si_code = FPE_FLTDIV;
if (fex & IEEE_TRAP_ENABLE_INV) si_code = FPE_FLTINV;
- info.si_signo = SIGFPE;
- info.si_errno = 0;
- info.si_code = si_code;
- info.si_addr = NULL; /* FIXME */
- send_sig_info(SIGFPE, &info, current);
+ send_sig_fault(SIGFPE, si_code,
+ (void __user *)NULL, /* FIXME */
+ 0, current);
}
return 0;
}
diff --git a/arch/alpha/kernel/pci-noop.c b/arch/alpha/kernel/pci-noop.c
index b6ebb65..c7c5879 100644
--- a/arch/alpha/kernel/pci-noop.c
+++ b/arch/alpha/kernel/pci-noop.c
@@ -102,36 +102,3 @@ SYSCALL_DEFINE5(pciconfig_write, unsigned long, bus, unsigned long, dfn,
else
return -ENODEV;
}
-
-static void *alpha_noop_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp,
- unsigned long attrs)
-{
- void *ret;
-
- if (!dev || *dev->dma_mask >= 0xffffffffUL)
- gfp &= ~GFP_DMA;
- ret = (void *)__get_free_pages(gfp, get_order(size));
- if (ret) {
- memset(ret, 0, size);
- *dma_handle = virt_to_phys(ret);
- }
- return ret;
-}
-
-static int alpha_noop_supported(struct device *dev, u64 mask)
-{
- return mask < 0x00ffffffUL ? 0 : 1;
-}
-
-const struct dma_map_ops alpha_noop_ops = {
- .alloc = alpha_noop_alloc_coherent,
- .free = dma_noop_free_coherent,
- .map_page = dma_noop_map_page,
- .map_sg = dma_noop_map_sg,
- .mapping_error = dma_noop_mapping_error,
- .dma_supported = alpha_noop_supported,
-};
-
-const struct dma_map_ops *dma_ops = &alpha_noop_ops;
-EXPORT_SYMBOL(dma_ops);
diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c
index 83b34b9..6923b0d 100644
--- a/arch/alpha/kernel/pci_iommu.c
+++ b/arch/alpha/kernel/pci_iommu.c
@@ -950,6 +950,4 @@ const struct dma_map_ops alpha_pci_ops = {
.mapping_error = alpha_pci_mapping_error,
.dma_supported = alpha_pci_supported,
};
-
-const struct dma_map_ops *dma_ops = &alpha_pci_ops;
-EXPORT_SYMBOL(dma_ops);
+EXPORT_SYMBOL(alpha_pci_ops);
diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c
index 9ebb3bc..8c0c4ee 100644
--- a/arch/alpha/kernel/signal.c
+++ b/arch/alpha/kernel/signal.c
@@ -219,14 +219,8 @@ do_sigreturn(struct sigcontext __user *sc)
/* Send SIGTRAP if we're single-stepping: */
if (ptrace_cancel_bpt (current)) {
- siginfo_t info;
-
- info.si_signo = SIGTRAP;
- info.si_errno = 0;
- info.si_code = TRAP_BRKPT;
- info.si_addr = (void __user *) regs->pc;
- info.si_trapno = 0;
- send_sig_info(SIGTRAP, &info, current);
+ send_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *) regs->pc, 0,
+ current);
}
return;
@@ -253,14 +247,8 @@ do_rt_sigreturn(struct rt_sigframe __user *frame)
/* Send SIGTRAP if we're single-stepping: */
if (ptrace_cancel_bpt (current)) {
- siginfo_t info;
-
- info.si_signo = SIGTRAP;
- info.si_errno = 0;
- info.si_code = TRAP_BRKPT;
- info.si_addr = (void __user *) regs->pc;
- info.si_trapno = 0;
- send_sig_info(SIGTRAP, &info, current);
+ send_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *) regs->pc, 0,
+ current);
}
return;
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index f43bd05..bc96276 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -213,7 +213,6 @@ do_entArith(unsigned long summary, unsigned long write_mask,
struct pt_regs *regs)
{
long si_code = FPE_FLTINV;
- siginfo_t info;
if (summary & 1) {
/* Software-completion summary bit is set, so try to
@@ -228,17 +227,12 @@ do_entArith(unsigned long summary, unsigned long write_mask,
}
die_if_kernel("Arithmetic fault", regs, 0, NULL);
- info.si_signo = SIGFPE;
- info.si_errno = 0;
- info.si_code = si_code;
- info.si_addr = (void __user *) regs->pc;
- send_sig_info(SIGFPE, &info, current);
+ send_sig_fault(SIGFPE, si_code, (void __user *) regs->pc, 0, current);
}
asmlinkage void
do_entIF(unsigned long type, struct pt_regs *regs)
{
- siginfo_t info;
int signo, code;
if ((regs->ps & ~IPL_MAX) == 0) {
@@ -270,31 +264,20 @@ do_entIF(unsigned long type, struct pt_regs *regs)
switch (type) {
case 0: /* breakpoint */
- info.si_signo = SIGTRAP;
- info.si_errno = 0;
- info.si_code = TRAP_BRKPT;
- info.si_trapno = 0;
- info.si_addr = (void __user *) regs->pc;
-
if (ptrace_cancel_bpt(current)) {
regs->pc -= 4; /* make pc point to former bpt */
}
- send_sig_info(SIGTRAP, &info, current);
+ send_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->pc, 0,
+ current);
return;
case 1: /* bugcheck */
- info.si_signo = SIGTRAP;
- info.si_errno = 0;
- info.si_code = TRAP_FIXME;
- info.si_addr = (void __user *) regs->pc;
- info.si_trapno = 0;
- send_sig_info(SIGTRAP, &info, current);
+ send_sig_fault(SIGTRAP, TRAP_UNK, (void __user *) regs->pc, 0,
+ current);
return;
case 2: /* gentrap */
- info.si_addr = (void __user *) regs->pc;
- info.si_trapno = regs->r16;
switch ((long) regs->r16) {
case GEN_INTOVF:
signo = SIGFPE;
@@ -326,7 +309,7 @@ do_entIF(unsigned long type, struct pt_regs *regs)
break;
case GEN_ROPRAND:
signo = SIGFPE;
- code = FPE_FIXME;
+ code = FPE_FLTUNK;
break;
case GEN_DECOVF:
@@ -348,15 +331,12 @@ do_entIF(unsigned long type, struct pt_regs *regs)
case GEN_SUBRNG7:
default:
signo = SIGTRAP;
- code = TRAP_FIXME;
+ code = TRAP_UNK;
break;
}
- info.si_signo = signo;
- info.si_errno = 0;
- info.si_code = code;
- info.si_addr = (void __user *) regs->pc;
- send_sig_info(signo, &info, current);
+ send_sig_fault(signo, code, (void __user *) regs->pc, regs->r16,
+ current);
return;
case 4: /* opDEC */
@@ -380,11 +360,9 @@ do_entIF(unsigned long type, struct pt_regs *regs)
if (si_code == 0)
return;
if (si_code > 0) {
- info.si_signo = SIGFPE;
- info.si_errno = 0;
- info.si_code = si_code;
- info.si_addr = (void __user *) regs->pc;
- send_sig_info(SIGFPE, &info, current);
+ send_sig_fault(SIGFPE, si_code,
+ (void __user *) regs->pc, 0,
+ current);
return;
}
}
@@ -409,11 +387,7 @@ do_entIF(unsigned long type, struct pt_regs *regs)
;
}
- info.si_signo = SIGILL;
- info.si_errno = 0;
- info.si_code = ILL_ILLOPC;
- info.si_addr = (void __user *) regs->pc;
- send_sig_info(SIGILL, &info, current);
+ send_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)regs->pc, 0, current);
}
/* There is an ifdef in the PALcode in MILO that enables a
@@ -426,15 +400,9 @@ do_entIF(unsigned long type, struct pt_regs *regs)
asmlinkage void
do_entDbg(struct pt_regs *regs)
{
- siginfo_t info;
-
die_if_kernel("Instruction fault", regs, 0, NULL);
- info.si_signo = SIGILL;
- info.si_errno = 0;
- info.si_code = ILL_ILLOPC;
- info.si_addr = (void __user *) regs->pc;
- force_sig_info(SIGILL, &info, current);
+ force_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)regs->pc, 0, current);
}
@@ -758,7 +726,7 @@ do_entUnaUser(void __user * va, unsigned long opcode,
unsigned long tmp1, tmp2, tmp3, tmp4;
unsigned long fake_reg, *reg_addr = &fake_reg;
- siginfo_t info;
+ int si_code;
long error;
/* Check the UAC bits to decide what the user wants us to do
@@ -981,34 +949,27 @@ do_entUnaUser(void __user * va, unsigned long opcode,
give_sigsegv:
regs->pc -= 4; /* make pc point to faulting insn */
- info.si_signo = SIGSEGV;
- info.si_errno = 0;
/* We need to replicate some of the logic in mm/fault.c,
since we don't have access to the fault code in the
exception handling return path. */
if ((unsigned long)va >= TASK_SIZE)
- info.si_code = SEGV_ACCERR;
+ si_code = SEGV_ACCERR;
else {
struct mm_struct *mm = current->mm;
down_read(&mm->mmap_sem);
if (find_vma(mm, (unsigned long)va))
- info.si_code = SEGV_ACCERR;
+ si_code = SEGV_ACCERR;
else
- info.si_code = SEGV_MAPERR;
+ si_code = SEGV_MAPERR;
up_read(&mm->mmap_sem);
}
- info.si_addr = va;
- send_sig_info(SIGSEGV, &info, current);
+ send_sig_fault(SIGSEGV, si_code, va, 0, current);
return;
give_sigbus:
regs->pc -= 4;
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_ADRALN;
- info.si_addr = va;
- send_sig_info(SIGBUS, &info, current);
+ send_sig_fault(SIGBUS, BUS_ADRALN, va, 0, current);
return;
}
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index cd3c572..de2bd21 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -88,7 +88,6 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
struct mm_struct *mm = current->mm;
const struct exception_table_entry *fixup;
int fault, si_code = SEGV_MAPERR;
- siginfo_t info;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
/* As of EV6, a load into $31/$f31 is a prefetch, and never faults
@@ -221,21 +220,13 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
up_read(&mm->mmap_sem);
/* Send a sigbus, regardless of whether we were in kernel
or user mode. */
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_ADRERR;
- info.si_addr = (void __user *) address;
- force_sig_info(SIGBUS, &info, current);
+ force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *) address, 0, current);
if (!user_mode(regs))
goto no_context;
return;
do_sigsegv:
- info.si_signo = SIGSEGV;
- info.si_errno = 0;
- info.si_code = si_code;
- info.si_addr = (void __user *) address;
- force_sig_info(SIGSEGV, &info, current);
+ force_sig_fault(SIGSEGV, si_code, (void __user *) address, 0, current);
return;
#ifdef CONFIG_ALPHA_LARGE_VMALLOC
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index d76bf4a..89d47ea 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -9,11 +9,15 @@
config ARC
def_bool y
select ARC_TIMERS
+ select ARCH_HAS_SYNC_DMA_FOR_CPU
+ select ARCH_HAS_SYNC_DMA_FOR_DEVICE
select ARCH_HAS_SG_CHAIN
select ARCH_SUPPORTS_ATOMIC_RMW if ARC_HAS_LLSC
select BUILDTIME_EXTABLE_SORT
select CLONE_BACKWARDS
select COMMON_CLK
+ select DMA_NONCOHERENT_OPS
+ select DMA_NONCOHERENT_MMAP
select GENERIC_ATOMIC64 if !ISA_ARCV2 || !(ARC_HAS_LL64 && ARC_HAS_LLSC)
select GENERIC_CLOCKEVENTS
select GENERIC_FIND_FIRST_BIT
@@ -453,16 +457,11 @@
default n
depends on ISA_ARCV2
select HIGHMEM
+ select PHYS_ADDR_T_64BIT
help
Enable access to physical memory beyond 4G, only supported on
ARC cores with 40 bit Physical Addressing support
-config ARCH_PHYS_ADDR_T_64BIT
- def_bool ARC_HAS_PAE40
-
-config ARCH_DMA_ADDR_T_64BIT
- bool
-
config ARC_KVADDR_SIZE
int "Kernel Virtual Address Space size (MB)"
range 0 512
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index 4bd5d43..feed50c 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -1,7 +1,9 @@
# SPDX-License-Identifier: GPL-2.0
generic-y += bugs.h
+generic-y += compat.h
generic-y += device.h
generic-y += div64.h
+generic-y += dma-mapping.h
generic-y += emergency-restart.h
generic-y += extable.h
generic-y += fb.h
diff --git a/arch/arc/include/asm/dma-mapping.h b/arch/arc/include/asm/dma-mapping.h
deleted file mode 100644
index 7a16824..0000000
--- a/arch/arc/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * DMA Mapping glue for ARC
- *
- * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef ASM_ARC_DMA_MAPPING_H
-#define ASM_ARC_DMA_MAPPING_H
-
-extern const struct dma_map_ops arc_dma_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
- return &arc_dma_ops;
-}
-
-#endif
diff --git a/arch/arc/include/asm/pci.h b/arch/arc/include/asm/pci.h
index ba56c23..4ff53c0 100644
--- a/arch/arc/include/asm/pci.h
+++ b/arch/arc/include/asm/pci.h
@@ -16,12 +16,6 @@
#define PCIBIOS_MIN_MEM 0x100000
#define pcibios_assign_all_busses() 1
-/*
- * The PCI address space does equal the physical memory address space.
- * The networking and block device layers use this boolean for bounce
- * buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS 1
#endif /* __KERNEL__ */
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 1dcc404..8c10718 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -16,13 +16,12 @@
* The default DMA address == Phy address which is 0x8000_0000 based.
*/
-#include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
#include <asm/cache.h>
#include <asm/cacheflush.h>
-
-static void *arc_dma_alloc(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t gfp, unsigned long attrs)
{
unsigned long order = get_order(size);
struct page *page;
@@ -89,7 +88,7 @@ static void *arc_dma_alloc(struct device *dev, size_t size,
return kvaddr;
}
-static void arc_dma_free(struct device *dev, size_t size, void *vaddr,
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_handle, unsigned long attrs)
{
phys_addr_t paddr = dma_handle;
@@ -105,9 +104,9 @@ static void arc_dma_free(struct device *dev, size_t size, void *vaddr,
__free_pages(page, get_order(size));
}
-static int arc_dma_mmap(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t dma_addr, size_t size,
- unsigned long attrs)
+int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs)
{
unsigned long user_count = vma_pages(vma);
unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
@@ -130,149 +129,14 @@ static int arc_dma_mmap(struct device *dev, struct vm_area_struct *vma,
return ret;
}
-/*
- * streaming DMA Mapping API...
- * CPU accesses page via normal paddr, thus needs to explicitly made
- * consistent before each use
- */
-static void _dma_cache_sync(phys_addr_t paddr, size_t size,
- enum dma_data_direction dir)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir)
{
- switch (dir) {
- case DMA_FROM_DEVICE:
- dma_cache_inv(paddr, size);
- break;
- case DMA_TO_DEVICE:
- dma_cache_wback(paddr, size);
- break;
- case DMA_BIDIRECTIONAL:
- dma_cache_wback_inv(paddr, size);
- break;
- default:
- pr_err("Invalid DMA dir [%d] for OP @ %pa[p]\n", dir, &paddr);
- }
+ dma_cache_wback(paddr, size);
}
-/*
- * arc_dma_map_page - map a portion of a page for streaming DMA
- *
- * Ensure that any data held in the cache is appropriately discarded
- * or written back.
- *
- * The device owns this memory once this call has completed. The CPU
- * can regain ownership by calling dma_unmap_page().
- *
- * Note: while it takes struct page as arg, caller can "abuse" it to pass
- * a region larger than PAGE_SIZE, provided it is physically contiguous
- * and this still works correctly
- */
-static dma_addr_t arc_dma_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size, enum dma_data_direction dir,
- unsigned long attrs)
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir)
{
- phys_addr_t paddr = page_to_phys(page) + offset;
-
- if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- _dma_cache_sync(paddr, size, dir);
-
- return paddr;
+ dma_cache_inv(paddr, size);
}
-
-/*
- * arc_dma_unmap_page - unmap a buffer previously mapped through dma_map_page()
- *
- * After this call, reads by the CPU to the buffer are guaranteed to see
- * whatever the device wrote there.
- *
- * Note: historically this routine was not implemented for ARC
- */
-static void arc_dma_unmap_page(struct device *dev, dma_addr_t handle,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- phys_addr_t paddr = handle;
-
- if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- _dma_cache_sync(paddr, size, dir);
-}
-
-static int arc_dma_map_sg(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction dir, unsigned long attrs)
-{
- struct scatterlist *s;
- int i;
-
- for_each_sg(sg, s, nents, i)
- s->dma_address = dma_map_page(dev, sg_page(s), s->offset,
- s->length, dir);
-
- return nents;
-}
-
-static void arc_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction dir,
- unsigned long attrs)
-{
- struct scatterlist *s;
- int i;
-
- for_each_sg(sg, s, nents, i)
- arc_dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir,
- attrs);
-}
-
-static void arc_dma_sync_single_for_cpu(struct device *dev,
- dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
-{
- _dma_cache_sync(dma_handle, size, DMA_FROM_DEVICE);
-}
-
-static void arc_dma_sync_single_for_device(struct device *dev,
- dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
-{
- _dma_cache_sync(dma_handle, size, DMA_TO_DEVICE);
-}
-
-static void arc_dma_sync_sg_for_cpu(struct device *dev,
- struct scatterlist *sglist, int nelems,
- enum dma_data_direction dir)
-{
- int i;
- struct scatterlist *sg;
-
- for_each_sg(sglist, sg, nelems, i)
- _dma_cache_sync(sg_phys(sg), sg->length, dir);
-}
-
-static void arc_dma_sync_sg_for_device(struct device *dev,
- struct scatterlist *sglist, int nelems,
- enum dma_data_direction dir)
-{
- int i;
- struct scatterlist *sg;
-
- for_each_sg(sglist, sg, nelems, i)
- _dma_cache_sync(sg_phys(sg), sg->length, dir);
-}
-
-static int arc_dma_supported(struct device *dev, u64 dma_mask)
-{
- /* Support 32 bit DMA mask exclusively */
- return dma_mask == DMA_BIT_MASK(32);
-}
-
-const struct dma_map_ops arc_dma_ops = {
- .alloc = arc_dma_alloc,
- .free = arc_dma_free,
- .mmap = arc_dma_mmap,
- .map_page = arc_dma_map_page,
- .unmap_page = arc_dma_unmap_page,
- .map_sg = arc_dma_map_sg,
- .unmap_sg = arc_dma_unmap_sg,
- .sync_single_for_device = arc_dma_sync_single_for_device,
- .sync_single_for_cpu = arc_dma_sync_single_for_cpu,
- .sync_sg_for_cpu = arc_dma_sync_sg_for_cpu,
- .sync_sg_for_device = arc_dma_sync_sg_for_device,
- .dma_supported = arc_dma_supported,
-};
-EXPORT_SYMBOL(arc_dma_ops);
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index a0b7bd6..b884bbd 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -70,6 +70,8 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
int write = regs->ecr_cause & ECR_C_PROTV_STORE; /* ST/EX */
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+ clear_siginfo(&info);
+
/*
* We fault-in kernel-space virtual memory on-demand. The
* 'reference' page table is init_mm.pgd.
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index a7f8e7f..c43f5bb 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -60,7 +60,6 @@
select HAVE_CONTEXT_TRACKING
select HAVE_C_RECORDMCOUNT
select HAVE_DEBUG_KMEMLEAK
- select HAVE_DMA_API_DEBUG
select HAVE_DMA_CONTIGUOUS if MMU
select HAVE_DYNAMIC_FTRACE if (!XIP_KERNEL) && !CPU_ENDIAN_BE32 && MMU
select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
@@ -96,6 +95,7 @@
select HAVE_VIRT_CPU_ACCOUNTING_GEN
select IRQ_FORCED_THREADING
select MODULES_USE_ELF_REL
+ select NEED_DMA_MAP_STATE
select NO_BOOTMEM
select OF_EARLY_FLATTREE if OF
select OF_RESERVED_MEM if OF
@@ -119,9 +119,6 @@
select ARCH_HAS_SG_CHAIN
bool
-config NEED_SG_DMA_LENGTH
- bool
-
config ARM_DMA_USE_IOMMU
bool
select ARM_HAS_SG_CHAIN
@@ -224,9 +221,6 @@
config ZONE_DMA
bool
-config NEED_DMA_MAP_STATE
- def_bool y
-
config ARCH_SUPPORTS_UPROBES
def_bool y
@@ -1778,12 +1772,6 @@
and the task is only allowed to execute a few safe syscalls
defined by each seccomp mode.
-config SWIOTLB
- def_bool y
-
-config IOMMU_HELPER
- def_bool SWIOTLB
-
config PARAVIRT
bool "Enable paravirtualization code"
help
@@ -1815,6 +1803,7 @@
depends on MMU
select ARCH_DMA_ADDR_T_64BIT
select ARM_PSCI
+ select SWIOTLB
select SWIOTLB_XEN
select PARAVIRT
help
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 45a6b9b..6a4e734 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -117,11 +117,9 @@
asflags-y := -DZIMAGE
# Supply kernel BSS size to the decompressor via a linker symbol.
-KBSS_SZ = $(shell $(CROSS_COMPILE)nm $(obj)/../../../../vmlinux | \
- perl -e 'while (<>) { \
- $$bss_start=hex($$1) if /^([[:xdigit:]]+) B __bss_start$$/; \
- $$bss_end=hex($$1) if /^([[:xdigit:]]+) B __bss_stop$$/; \
- }; printf "%d\n", $$bss_end - $$bss_start;')
+KBSS_SZ = $(shell echo $$(($$($(CROSS_COMPILE)nm $(obj)/../../../../vmlinux | \
+ sed -n -e 's/^\([^ ]*\) [AB] __bss_start$$/-0x\1/p' \
+ -e 's/^\([^ ]*\) [AB] __bss_stop$$/+0x\1/p') )) )
LDFLAGS_vmlinux = --defsym _kernel_bss_size=$(KBSS_SZ)
# Supply ZRELADDR to the decompressor via a linker symbol.
ifneq ($(CONFIG_AUTO_ZRELADDR),y)
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 45c8823..517e0e1 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -29,19 +29,19 @@
#if defined(CONFIG_DEBUG_ICEDCC)
#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K) || defined(CONFIG_CPU_V7)
- .macro loadsp, rb, tmp
+ .macro loadsp, rb, tmp1, tmp2
.endm
.macro writeb, ch, rb
mcr p14, 0, \ch, c0, c5, 0
.endm
#elif defined(CONFIG_CPU_XSCALE)
- .macro loadsp, rb, tmp
+ .macro loadsp, rb, tmp1, tmp2
.endm
.macro writeb, ch, rb
mcr p14, 0, \ch, c8, c0, 0
.endm
#else
- .macro loadsp, rb, tmp
+ .macro loadsp, rb, tmp1, tmp2
.endm
.macro writeb, ch, rb
mcr p14, 0, \ch, c1, c0, 0
@@ -57,7 +57,7 @@
.endm
#if defined(CONFIG_ARCH_SA1100)
- .macro loadsp, rb, tmp
+ .macro loadsp, rb, tmp1, tmp2
mov \rb, #0x80000000 @ physical base address
#ifdef CONFIG_DEBUG_LL_SER3
add \rb, \rb, #0x00050000 @ Ser3
@@ -66,8 +66,8 @@
#endif
.endm
#else
- .macro loadsp, rb, tmp
- addruart \rb, \tmp
+ .macro loadsp, rb, tmp1, tmp2
+ addruart \rb, \tmp1, \tmp2
.endm
#endif
#endif
@@ -561,8 +561,6 @@
bl decompress_kernel
bl cache_clean_flush
bl cache_off
- mov r1, r7 @ restore architecture number
- mov r2, r8 @ restore atags pointer
#ifdef CONFIG_ARM_VIRT_EXT
mrs r0, spsr @ Get saved CPU boot mode
@@ -1297,7 +1295,7 @@
b 1b
@ puts corrupts {r0, r1, r2, r3}
-puts: loadsp r3, r1
+puts: loadsp r3, r2, r1
1: ldrb r2, [r0], #1
teq r2, #0
moveq pc, lr
@@ -1314,8 +1312,8 @@
@ putc corrupts {r0, r1, r2, r3}
putc:
mov r2, r0
+ loadsp r3, r1, r0
mov r0, #0
- loadsp r3, r1
b 2b
@ memdump corrupts {r0, r1, r2, r3, r10, r11, r12, lr}
@@ -1365,6 +1363,8 @@
__enter_kernel:
mov r0, #0 @ must be 0
+ mov r1, r7 @ restore architecture number
+ mov r2, r8 @ restore atags pointer
ARM( mov pc, r4 ) @ call kernel
M_CLASS( add r4, r4, #1 ) @ enter in Thumb mode for M class
THUMB( bx r4 ) @ entry point is always ARM for A/R classes
diff --git a/arch/arm/boot/dts/bcm-cygnus.dtsi b/arch/arm/boot/dts/bcm-cygnus.dtsi
index 699fdf9..9fe4f5a6 100644
--- a/arch/arm/boot/dts/bcm-cygnus.dtsi
+++ b/arch/arm/boot/dts/bcm-cygnus.dtsi
@@ -69,7 +69,7 @@
timer@20200 {
compatible = "arm,cortex-a9-global-timer";
reg = <0x20200 0x100>;
- interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
clocks = <&periph_clk>;
};
diff --git a/arch/arm/boot/dts/da850-lcdk.dts b/arch/arm/boot/dts/da850-lcdk.dts
index a1f4d6d..0edf769 100644
--- a/arch/arm/boot/dts/da850-lcdk.dts
+++ b/arch/arm/boot/dts/da850-lcdk.dts
@@ -21,8 +21,8 @@
stdout-path = "serial2:115200n8";
};
- memory {
- device_type = "memory";
+ memory@c0000000 {
+ /* 128 MB DDR2 SDRAM @ 0xc0000000 */
reg = <0xc0000000 0x08000000>;
};
diff --git a/arch/arm/boot/dts/da850.dtsi b/arch/arm/boot/dts/da850.dtsi
index c66cf78..1201000 100644
--- a/arch/arm/boot/dts/da850.dtsi
+++ b/arch/arm/boot/dts/da850.dtsi
@@ -7,10 +7,19 @@
* Free Software Foundation; either version 2 of the License, or (at your
* option) any later version.
*/
-#include "skeleton.dtsi"
#include <dt-bindings/interrupt-controller/irq.h>
/ {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ chosen { };
+ aliases { };
+
+ memory@c0000000 {
+ device_type = "memory";
+ reg = <0xc0000000 0x0>;
+ };
+
arm {
#address-cells = <1>;
#size-cells = <1>;
@@ -46,8 +55,6 @@
pmx_core: pinmux@14120 {
compatible = "pinctrl-single";
reg = <0x14120 0x50>;
- #address-cells = <1>;
- #size-cells = <0>;
#pinctrl-cells = <2>;
pinctrl-single,bit-per-mux;
pinctrl-single,register-width = <32>;
diff --git a/arch/arm/boot/dts/dm8148-evm.dts b/arch/arm/boot/dts/dm8148-evm.dts
index d6657b3..85d7b51 100644
--- a/arch/arm/boot/dts/dm8148-evm.dts
+++ b/arch/arm/boot/dts/dm8148-evm.dts
@@ -10,7 +10,7 @@
/ {
model = "DM8148 EVM";
- compatible = "ti,dm8148-evm", "ti,dm8148";
+ compatible = "ti,dm8148-evm", "ti,dm8148", "ti,dm814";
memory@80000000 {
device_type = "memory";
diff --git a/arch/arm/boot/dts/dm8148-t410.dts b/arch/arm/boot/dts/dm8148-t410.dts
index 63883b3..6418f9c 100644
--- a/arch/arm/boot/dts/dm8148-t410.dts
+++ b/arch/arm/boot/dts/dm8148-t410.dts
@@ -9,7 +9,7 @@
/ {
model = "HP t410 Smart Zero Client";
- compatible = "hp,t410", "ti,dm8148";
+ compatible = "hp,t410", "ti,dm8148", "ti,dm814";
memory@80000000 {
device_type = "memory";
diff --git a/arch/arm/boot/dts/dm8168-evm.dts b/arch/arm/boot/dts/dm8168-evm.dts
index c72a213..1d030d56 100644
--- a/arch/arm/boot/dts/dm8168-evm.dts
+++ b/arch/arm/boot/dts/dm8168-evm.dts
@@ -10,7 +10,7 @@
/ {
model = "DM8168 EVM";
- compatible = "ti,dm8168-evm", "ti,dm8168";
+ compatible = "ti,dm8168-evm", "ti,dm8168", "ti,dm816";
memory@80000000 {
device_type = "memory";
diff --git a/arch/arm/boot/dts/dra62x-j5eco-evm.dts b/arch/arm/boot/dts/dra62x-j5eco-evm.dts
index fee0547..31b824a 100644
--- a/arch/arm/boot/dts/dra62x-j5eco-evm.dts
+++ b/arch/arm/boot/dts/dra62x-j5eco-evm.dts
@@ -10,7 +10,7 @@
/ {
model = "DRA62x J5 Eco EVM";
- compatible = "ti,dra62x-j5eco-evm", "ti,dra62x", "ti,dm8148";
+ compatible = "ti,dra62x-j5eco-evm", "ti,dra62x", "ti,dm8148", "ti,dm814";
memory@80000000 {
device_type = "memory";
diff --git a/arch/arm/boot/dts/gemini-nas4220b.dts b/arch/arm/boot/dts/gemini-nas4220b.dts
index 8bbb6f8..4785fbc 100644
--- a/arch/arm/boot/dts/gemini-nas4220b.dts
+++ b/arch/arm/boot/dts/gemini-nas4220b.dts
@@ -134,37 +134,37 @@
function = "gmii";
groups = "gmii_gmac0_grp";
};
- /* Settings come from OpenWRT */
+ /* Settings come from OpenWRT, pins on SL3516 */
conf0 {
- pins = "R8 GMAC0 RXDV", "U11 GMAC1 RXDV";
+ pins = "V8 GMAC0 RXDV", "T10 GMAC1 RXDV";
skew-delay = <0>;
};
conf1 {
- pins = "T8 GMAC0 RXC", "T11 GMAC1 RXC";
+ pins = "Y7 GMAC0 RXC", "Y11 GMAC1 RXC";
skew-delay = <15>;
};
conf2 {
- pins = "P8 GMAC0 TXEN", "V11 GMAC1 TXEN";
+ pins = "T8 GMAC0 TXEN", "W11 GMAC1 TXEN";
skew-delay = <7>;
};
conf3 {
- pins = "V7 GMAC0 TXC";
+ pins = "U8 GMAC0 TXC";
skew-delay = <11>;
};
conf4 {
- pins = "P10 GMAC1 TXC";
+ pins = "V11 GMAC1 TXC";
skew-delay = <10>;
};
conf5 {
/* The data lines all have default skew */
- pins = "U8 GMAC0 RXD0", "V8 GMAC0 RXD1",
- "P9 GMAC0 RXD2", "R9 GMAC0 RXD3",
- "U7 GMAC0 TXD0", "T7 GMAC0 TXD1",
- "R7 GMAC0 TXD2", "P7 GMAC0 TXD3",
- "R11 GMAC1 RXD0", "P11 GMAC1 RXD1",
- "V12 GMAC1 RXD2", "U12 GMAC1 RXD3",
- "R10 GMAC1 TXD0", "T10 GMAC1 TXD1",
- "U10 GMAC1 TXD2", "V10 GMAC1 TXD3";
+ pins = "W8 GMAC0 RXD0", "V9 GMAC0 RXD1",
+ "Y8 GMAC0 RXD2", "U9 GMAC0 RXD3",
+ "T7 GMAC0 TXD0", "U6 GMAC0 TXD1",
+ "V7 GMAC0 TXD2", "U7 GMAC0 TXD3",
+ "Y12 GMAC1 RXD0", "V12 GMAC1 RXD1",
+ "T11 GMAC1 RXD2", "W12 GMAC1 RXD3",
+ "U10 GMAC1 TXD0", "Y10 GMAC1 TXD1",
+ "W10 GMAC1 TXD2", "T9 GMAC1 TXD3";
skew-delay = <7>;
};
/* Set up drive strength on GMAC0 to 16 mA */
diff --git a/arch/arm/boot/dts/imx35.dtsi b/arch/arm/boot/dts/imx35.dtsi
index bf343195..54111ed 100644
--- a/arch/arm/boot/dts/imx35.dtsi
+++ b/arch/arm/boot/dts/imx35.dtsi
@@ -303,7 +303,7 @@
};
can1: can@53fe4000 {
- compatible = "fsl,imx35-flexcan";
+ compatible = "fsl,imx35-flexcan", "fsl,imx25-flexcan";
reg = <0x53fe4000 0x1000>;
clocks = <&clks 33>, <&clks 33>;
clock-names = "ipg", "per";
@@ -312,7 +312,7 @@
};
can2: can@53fe8000 {
- compatible = "fsl,imx35-flexcan";
+ compatible = "fsl,imx35-flexcan", "fsl,imx25-flexcan";
reg = <0x53fe8000 0x1000>;
clocks = <&clks 34>, <&clks 34>;
clock-names = "ipg", "per";
diff --git a/arch/arm/boot/dts/imx51-zii-rdu1.dts b/arch/arm/boot/dts/imx51-zii-rdu1.dts
index 0c99ac0..6464f25 100644
--- a/arch/arm/boot/dts/imx51-zii-rdu1.dts
+++ b/arch/arm/boot/dts/imx51-zii-rdu1.dts
@@ -523,7 +523,7 @@
};
touchscreen@20 {
- compatible = "syna,rmi4_i2c";
+ compatible = "syna,rmi4-i2c";
reg = <0x20>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_ts>;
@@ -541,8 +541,8 @@
rmi4-f11@11 {
reg = <0x11>;
- touch-inverted-y;
- touch-swapped-x-y;
+ touchscreen-inverted-y;
+ touchscreen-swapped-x-y;
syna,sensor-type = <1>;
};
};
diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi
index 7d647d0..3d65c01 100644
--- a/arch/arm/boot/dts/imx53.dtsi
+++ b/arch/arm/boot/dts/imx53.dtsi
@@ -551,7 +551,7 @@
};
can1: can@53fc8000 {
- compatible = "fsl,imx53-flexcan";
+ compatible = "fsl,imx53-flexcan", "fsl,imx25-flexcan";
reg = <0x53fc8000 0x4000>;
interrupts = <82>;
clocks = <&clks IMX5_CLK_CAN1_IPG_GATE>,
@@ -561,7 +561,7 @@
};
can2: can@53fcc000 {
- compatible = "fsl,imx53-flexcan";
+ compatible = "fsl,imx53-flexcan", "fsl,imx25-flexcan";
reg = <0x53fcc000 0x4000>;
interrupts = <83>;
clocks = <&clks IMX5_CLK_CAN2_IPG_GATE>,
diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi
index 4d42335..ce85b3c 100644
--- a/arch/arm/boot/dts/imx7s.dtsi
+++ b/arch/arm/boot/dts/imx7s.dtsi
@@ -868,6 +868,7 @@
crypto: caam@30900000 {
compatible = "fsl,sec-v4.0";
+ fsl,sec-era = <8>;
#address-cells = <1>;
#size-cells = <1>;
reg = <0x30900000 0x40000>;
diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi
index b47cac2..6fa7bba 100644
--- a/arch/arm/boot/dts/logicpd-som-lv.dtsi
+++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi
@@ -26,7 +26,7 @@
gpio = <&gpio1 3 0>; /* gpio_3 */
startup-delay-us = <70000>;
enable-active-high;
- vin-supply = <&vmmc2>;
+ vin-supply = <&vaux3>;
};
/* HS USB Host PHY on PORT 1 */
@@ -82,6 +82,7 @@
twl_audio: audio {
compatible = "ti,twl4030-audio";
codec {
+ ti,hs_extmute_gpio = <&gpio2 25 GPIO_ACTIVE_HIGH>;
};
};
};
@@ -199,6 +200,7 @@
pinctrl-single,pins = <
OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0) /* i2c1_scl.i2c1_scl */
OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0) /* i2c1_sda.i2c1_sda */
+ OMAP3_CORE1_IOPAD(0x20ba, PIN_OUTPUT | MUX_MODE4) /* gpmc_ncs6.gpio_57 */
>;
};
};
@@ -213,7 +215,7 @@
};
wl127x_gpio: pinmux_wl127x_gpio_pin {
pinctrl-single,pins = <
- OMAP3_WKUP_IOPAD(0x2a0c, PIN_INPUT | MUX_MODE4) /* sys_boot0.gpio_2 */
+ OMAP3_WKUP_IOPAD(0x2a0a, PIN_INPUT | MUX_MODE4) /* sys_boot0.gpio_2 */
OMAP3_WKUP_IOPAD(0x2a0c, PIN_OUTPUT | MUX_MODE4) /* sys_boot1.gpio_3 */
>;
};
@@ -260,6 +262,11 @@
#include "twl4030.dtsi"
#include "twl4030_omap3.dtsi"
+&vaux3 {
+ regulator-min-microvolt = <2800000>;
+ regulator-max-microvolt = <2800000>;
+};
+
&twl {
twl_power: power {
compatible = "ti,twl4030-power-idle-osc-off", "ti,twl4030-power-idle";
diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index 4759048..e554b6e 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -163,10 +163,10 @@
cm2: cm2@8000 {
compatible = "ti,omap4-cm2", "simple-bus";
- reg = <0x8000 0x3000>;
+ reg = <0x8000 0x2000>;
#address-cells = <1>;
#size-cells = <1>;
- ranges = <0 0x8000 0x3000>;
+ ranges = <0 0x8000 0x2000>;
cm2_clocks: clocks {
#address-cells = <1>;
@@ -250,11 +250,11 @@
prm: prm@6000 {
compatible = "ti,omap4-prm";
- reg = <0x6000 0x3000>;
+ reg = <0x6000 0x2000>;
interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <1>;
- ranges = <0 0x6000 0x3000>;
+ ranges = <0 0x6000 0x2000>;
prm_clocks: clocks {
#address-cells = <1>;
diff --git a/arch/arm/boot/dts/r8a7790-lager.dts b/arch/arm/boot/dts/r8a7790-lager.dts
index 063fdb6..f07f9018 100644
--- a/arch/arm/boot/dts/r8a7790-lager.dts
+++ b/arch/arm/boot/dts/r8a7790-lager.dts
@@ -379,7 +379,7 @@
port@0 {
reg = <0>;
adv7511_in: endpoint {
- remote-endpoint = <&du_out_lvds0>;
+ remote-endpoint = <&lvds0_out>;
};
};
@@ -467,10 +467,8 @@
status = "okay";
clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>, <&cpg CPG_MOD 722>,
- <&cpg CPG_MOD 726>, <&cpg CPG_MOD 725>,
<&x13_clk>, <&x2_clk>;
- clock-names = "du.0", "du.1", "du.2", "lvds.0", "lvds.1",
- "dclkin.0", "dclkin.1";
+ clock-names = "du.0", "du.1", "du.2", "dclkin.0", "dclkin.1";
ports {
port@0 {
@@ -478,12 +476,26 @@
remote-endpoint = <&adv7123_in>;
};
};
+ };
+};
+
+&lvds0 {
+ status = "okay";
+
+ ports {
port@1 {
endpoint {
remote-endpoint = <&adv7511_in>;
};
};
- port@2 {
+ };
+};
+
+&lvds1 {
+ status = "okay";
+
+ ports {
+ port@1 {
lvds_connector: endpoint {
};
};
diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index e4367ce..05a0fc2 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -1627,18 +1627,13 @@
du: display@feb00000 {
compatible = "renesas,du-r8a7790";
- reg = <0 0xfeb00000 0 0x70000>,
- <0 0xfeb90000 0 0x1c>,
- <0 0xfeb94000 0 0x1c>;
- reg-names = "du", "lvds.0", "lvds.1";
+ reg = <0 0xfeb00000 0 0x70000>;
interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 268 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 269 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>,
- <&cpg CPG_MOD 722>, <&cpg CPG_MOD 726>,
- <&cpg CPG_MOD 725>;
- clock-names = "du.0", "du.1", "du.2", "lvds.0",
- "lvds.1";
+ <&cpg CPG_MOD 722>;
+ clock-names = "du.0", "du.1", "du.2";
status = "disabled";
ports {
@@ -1653,11 +1648,65 @@
port@1 {
reg = <1>;
du_out_lvds0: endpoint {
+ remote-endpoint = <&lvds0_in>;
};
};
port@2 {
reg = <2>;
du_out_lvds1: endpoint {
+ remote-endpoint = <&lvds1_in>;
+ };
+ };
+ };
+ };
+
+ lvds0: lvds@feb90000 {
+ compatible = "renesas,r8a7790-lvds";
+ reg = <0 0xfeb90000 0 0x1c>;
+ clocks = <&cpg CPG_MOD 726>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
+ resets = <&cpg 726>;
+ status = "disabled";
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ reg = <0>;
+ lvds0_in: endpoint {
+ remote-endpoint = <&du_out_lvds0>;
+ };
+ };
+ port@1 {
+ reg = <1>;
+ lvds0_out: endpoint {
+ };
+ };
+ };
+ };
+
+ lvds1: lvds@feb94000 {
+ compatible = "renesas,r8a7790-lvds";
+ reg = <0 0xfeb94000 0 0x1c>;
+ clocks = <&cpg CPG_MOD 725>;
+ power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
+ resets = <&cpg 725>;
+ status = "disabled";
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ reg = <0>;
+ lvds1_in: endpoint {
+ remote-endpoint = <&du_out_lvds1>;
+ };
+ };
+ port@1 {
+ reg = <1>;
+ lvds1_out: endpoint {
};
};
};
diff --git a/arch/arm/boot/dts/r8a7791-koelsch.dts b/arch/arm/boot/dts/r8a7791-koelsch.dts
index f40321a..9d7213a 100644
--- a/arch/arm/boot/dts/r8a7791-koelsch.dts
+++ b/arch/arm/boot/dts/r8a7791-koelsch.dts
@@ -468,10 +468,9 @@
pinctrl-names = "default";
status = "okay";
- clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>, <&cpg CPG_MOD 726>,
+ clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>,
<&x13_clk>, <&x2_clk>;
- clock-names = "du.0", "du.1", "lvds.0",
- "dclkin.0", "dclkin.1";
+ clock-names = "du.0", "du.1", "dclkin.0", "dclkin.1";
ports {
port@0 {
@@ -479,6 +478,13 @@
remote-endpoint = <&adv7511_in>;
};
};
+ };
+};
+
+&lvds0 {
+ status = "okay";
+
+ ports {
port@1 {
lvds_connector: endpoint {
};
diff --git a/arch/arm/boot/dts/r8a7791-porter.dts b/arch/arm/boot/dts/r8a7791-porter.dts
index c14e6fe..ae9ed9f 100644
--- a/arch/arm/boot/dts/r8a7791-porter.dts
+++ b/arch/arm/boot/dts/r8a7791-porter.dts
@@ -441,10 +441,9 @@
pinctrl-names = "default";
status = "okay";
- clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>, <&cpg CPG_MOD 726>,
+ clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>,
<&x3_clk>, <&x16_clk>;
- clock-names = "du.0", "du.1", "lvds.0",
- "dclkin.0", "dclkin.1";
+ clock-names = "du.0", "du.1", "dclkin.0", "dclkin.1";
ports {
port@0 {
@@ -455,6 +454,17 @@
};
};
+&lvds0 {
+ status = "okay";
+
+ ports {
+ port@1 {
+ lvds_connector: endpoint {
+ };
+ };
+ };
+};
+
&rcar_sound {
pinctrl-0 = <&ssi_pins &audio_clk_pins>;
pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi
index f11dab7..506b208 100644
--- a/arch/arm/boot/dts/r8a7791.dtsi
+++ b/arch/arm/boot/dts/r8a7791.dtsi
@@ -1633,15 +1633,12 @@
du: display@feb00000 {
compatible = "renesas,du-r8a7791";
- reg = <0 0xfeb00000 0 0x40000>,
- <0 0xfeb90000 0 0x1c>;
- reg-names = "du", "lvds.0";
+ reg = <0 0xfeb00000 0 0x40000>;
interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 268 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 724>,
- <&cpg CPG_MOD 723>,
- <&cpg CPG_MOD 726>;
- clock-names = "du.0", "du.1", "lvds.0";
+ <&cpg CPG_MOD 723>;
+ clock-names = "du.0", "du.1";
status = "disabled";
ports {
@@ -1656,6 +1653,33 @@
port@1 {
reg = <1>;
du_out_lvds0: endpoint {
+ remote-endpoint = <&lvds0_in>;
+ };
+ };
+ };
+ };
+
+ lvds0: lvds@feb90000 {
+ compatible = "renesas,r8a7791-lvds";
+ reg = <0 0xfeb90000 0 0x1c>;
+ clocks = <&cpg CPG_MOD 726>;
+ power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
+ resets = <&cpg 726>;
+ status = "disabled";
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ reg = <0>;
+ lvds0_in: endpoint {
+ remote-endpoint = <&du_out_lvds0>;
+ };
+ };
+ port@1 {
+ reg = <1>;
+ lvds0_out: endpoint {
};
};
};
diff --git a/arch/arm/boot/dts/r8a7793-gose.dts b/arch/arm/boot/dts/r8a7793-gose.dts
index 9ed6961..96e117d 100644
--- a/arch/arm/boot/dts/r8a7793-gose.dts
+++ b/arch/arm/boot/dts/r8a7793-gose.dts
@@ -447,10 +447,9 @@
pinctrl-names = "default";
status = "okay";
- clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>, <&cpg CPG_MOD 726>,
+ clocks = <&cpg CPG_MOD 724>, <&cpg CPG_MOD 723>,
<&x13_clk>, <&x2_clk>;
- clock-names = "du.0", "du.1", "lvds.0",
- "dclkin.0", "dclkin.1";
+ clock-names = "du.0", "du.1", "dclkin.0", "dclkin.1";
ports {
port@0 {
@@ -458,6 +457,11 @@
remote-endpoint = <&adv7511_in>;
};
};
+ };
+};
+
+&lvds0 {
+ ports {
port@1 {
lvds_connector: endpoint {
};
diff --git a/arch/arm/boot/dts/r8a7793.dtsi b/arch/arm/boot/dts/r8a7793.dtsi
index f9c5a55..4f52603 100644
--- a/arch/arm/boot/dts/r8a7793.dtsi
+++ b/arch/arm/boot/dts/r8a7793.dtsi
@@ -1292,15 +1292,12 @@
du: display@feb00000 {
compatible = "renesas,du-r8a7793";
- reg = <0 0xfeb00000 0 0x40000>,
- <0 0xfeb90000 0 0x1c>;
- reg-names = "du", "lvds.0";
+ reg = <0 0xfeb00000 0 0x40000>;
interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 268 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD 724>,
- <&cpg CPG_MOD 723>,
- <&cpg CPG_MOD 726>;
- clock-names = "du.0", "du.1", "lvds.0";
+ <&cpg CPG_MOD 723>;
+ clock-names = "du.0", "du.1";
status = "disabled";
ports {
@@ -1315,6 +1312,34 @@
port@1 {
reg = <1>;
du_out_lvds0: endpoint {
+ remote-endpoint = <&lvds0_in>;
+ };
+ };
+ };
+ };
+
+ lvds0: lvds@feb90000 {
+ compatible = "renesas,r8a7793-lvds";
+ reg = <0 0xfeb90000 0 0x1c>;
+ clocks = <&cpg CPG_MOD 726>;
+ power-domains = <&sysc R8A7793_PD_ALWAYS_ON>;
+ resets = <&cpg 726>;
+
+ status = "disabled";
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ reg = <0>;
+ lvds0_in: endpoint {
+ remote-endpoint = <&du_out_lvds0>;
+ };
+ };
+ port@1 {
+ reg = <1>;
+ lvds0_out: endpoint {
};
};
};
diff --git a/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi b/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi
index c0743305..eb96ac3 100644
--- a/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi
+++ b/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi
@@ -12,6 +12,8 @@
#size-cells = <1>;
compatible = "st,stm32mp157-pinctrl";
ranges = <0 0x50002000 0xa400>;
+ interrupt-parent = <&exti>;
+ st,syscfg = <&exti 0x60 0xff>;
pins-are-numbered;
gpioa: gpio@50002000 {
@@ -166,6 +168,8 @@
compatible = "st,stm32mp157-z-pinctrl";
ranges = <0 0x54004000 0x400>;
pins-are-numbered;
+ interrupt-parent = <&exti>;
+ st,syscfg = <&exti 0x60 0xff>;
status = "disabled";
gpioz: gpio@54004000 {
diff --git a/arch/arm/boot/dts/stm32mp157c.dtsi b/arch/arm/boot/dts/stm32mp157c.dtsi
index 9e17e42..4fa0df8 100644
--- a/arch/arm/boot/dts/stm32mp157c.dtsi
+++ b/arch/arm/boot/dts/stm32mp157c.dtsi
@@ -183,6 +183,13 @@
status = "disabled";
};
+ exti: interrupt-controller@5000d000 {
+ compatible = "st,stm32mp1-exti", "syscon";
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ reg = <0x5000d000 0x400>;
+ };
+
usart1: serial@5c000000 {
compatible = "st,stm32h7-uart";
reg = <0x5c000000 0x400>;
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index 77e8436..3a1c6b4 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -76,7 +76,7 @@
allwinner,pipeline = "de_fe0-de_be0-lcd0-hdmi";
clocks = <&ccu CLK_AHB_LCD0>, <&ccu CLK_AHB_HDMI0>,
<&ccu CLK_AHB_DE_BE0>, <&ccu CLK_AHB_DE_FE0>,
- <&ccu CLK_DE_BE0>, <&ccu CLK_AHB_DE_FE0>,
+ <&ccu CLK_DE_BE0>, <&ccu CLK_DE_FE0>,
<&ccu CLK_TCON0_CH1>, <&ccu CLK_HDMI>,
<&ccu CLK_DRAM_DE_FE0>, <&ccu CLK_DRAM_DE_BE0>;
status = "disabled";
@@ -88,7 +88,7 @@
allwinner,pipeline = "de_fe0-de_be0-lcd0";
clocks = <&ccu CLK_AHB_LCD0>, <&ccu CLK_AHB_DE_BE0>,
<&ccu CLK_AHB_DE_FE0>, <&ccu CLK_DE_BE0>,
- <&ccu CLK_AHB_DE_FE0>, <&ccu CLK_TCON0_CH0>,
+ <&ccu CLK_DE_FE0>, <&ccu CLK_TCON0_CH0>,
<&ccu CLK_DRAM_DE_FE0>, <&ccu CLK_DRAM_DE_BE0>;
status = "disabled";
};
@@ -99,7 +99,7 @@
allwinner,pipeline = "de_fe0-de_be0-lcd0-tve0";
clocks = <&ccu CLK_AHB_TVE0>, <&ccu CLK_AHB_LCD0>,
<&ccu CLK_AHB_DE_BE0>, <&ccu CLK_AHB_DE_FE0>,
- <&ccu CLK_DE_BE0>, <&ccu CLK_AHB_DE_FE0>,
+ <&ccu CLK_DE_BE0>, <&ccu CLK_DE_FE0>,
<&ccu CLK_TCON0_CH1>, <&ccu CLK_DRAM_TVE0>,
<&ccu CLK_DRAM_DE_FE0>, <&ccu CLK_DRAM_DE_BE0>;
status = "disabled";
diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-one.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-one.dts
index 3328fe5..232f124 100644
--- a/arch/arm/boot/dts/sun8i-h3-orangepi-one.dts
+++ b/arch/arm/boot/dts/sun8i-h3-orangepi-one.dts
@@ -117,6 +117,7 @@
phy-handle = <&int_mii_phy>;
phy-mode = "mii";
allwinner,leds-active-low;
+ status = "okay";
};
&hdmi {
diff --git a/arch/arm/boot/dts/sun8i-v3s-licheepi-zero-dock.dts b/arch/arm/boot/dts/sun8i-v3s-licheepi-zero-dock.dts
index d131109..ad17360 100644
--- a/arch/arm/boot/dts/sun8i-v3s-licheepi-zero-dock.dts
+++ b/arch/arm/boot/dts/sun8i-v3s-licheepi-zero-dock.dts
@@ -51,7 +51,7 @@
leds {
/* The LEDs use PG0~2 pins, which conflict with MMC1 */
- status = "disbaled";
+ status = "disabled";
};
};
diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi
index 0a71364..983dd5c 100644
--- a/arch/arm/boot/dts/tegra20.dtsi
+++ b/arch/arm/boot/dts/tegra20.dtsi
@@ -741,7 +741,7 @@
phy_type = "ulpi";
clocks = <&tegra_car TEGRA20_CLK_USB2>,
<&tegra_car TEGRA20_CLK_PLL_U>,
- <&tegra_car TEGRA20_CLK_PLL_P_OUT4>;
+ <&tegra_car TEGRA20_CLK_CDEV2>;
clock-names = "reg", "pll_u", "ulpi-link";
resets = <&tegra_car 58>, <&tegra_car 22>;
reset-names = "usb", "utmi-pads";
diff --git a/arch/arm/configs/gemini_defconfig b/arch/arm/configs/gemini_defconfig
index 2a63fa1..553777a 100644
--- a/arch/arm/configs/gemini_defconfig
+++ b/arch/arm/configs/gemini_defconfig
@@ -1,6 +1,7 @@
# CONFIG_LOCALVERSION_AUTO is not set
CONFIG_SYSVIPC=y
CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_USER_NS=y
CONFIG_RELAY=y
@@ -12,15 +13,21 @@
CONFIG_PCI=y
CONFIG_PREEMPT=y
CONFIG_AEABI=y
+CONFIG_HIGHMEM=y
+CONFIG_CMA=y
CONFIG_CMDLINE="console=ttyS0,115200n8"
CONFIG_KEXEC=y
CONFIG_BINFMT_MISC=y
CONFIG_PM=y
+CONFIG_NET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_DEVTMPFS=y
CONFIG_MTD=y
CONFIG_MTD_BLOCK=y
CONFIG_MTD_CFI=y
+CONFIG_MTD_JEDECPROBE=y
CONFIG_MTD_CFI_INTELEXT=y
CONFIG_MTD_CFI_AMDSTD=y
CONFIG_MTD_CFI_STAA=y
@@ -33,6 +40,11 @@
# CONFIG_SCSI_LOWLEVEL is not set
CONFIG_ATA=y
CONFIG_PATA_FTIDE010=y
+CONFIG_NETDEVICES=y
+CONFIG_GEMINI_ETHERNET=y
+CONFIG_MDIO_BITBANG=y
+CONFIG_MDIO_GPIO=y
+CONFIG_REALTEK_PHY=y
CONFIG_INPUT_EVDEV=y
CONFIG_KEYBOARD_GPIO=y
# CONFIG_INPUT_MOUSE is not set
@@ -43,9 +55,19 @@
CONFIG_SERIAL_8250_RUNTIME_UARTS=1
CONFIG_SERIAL_OF_PLATFORM=y
# CONFIG_HW_RANDOM is not set
-# CONFIG_HWMON is not set
+CONFIG_I2C_GPIO=y
+CONFIG_SPI=y
+CONFIG_SPI_GPIO=y
+CONFIG_SENSORS_GPIO_FAN=y
+CONFIG_SENSORS_LM75=y
+CONFIG_THERMAL=y
CONFIG_WATCHDOG=y
-CONFIG_GEMINI_WATCHDOG=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
+CONFIG_DRM=y
+CONFIG_DRM_PANEL_ILITEK_IL9322=y
+CONFIG_DRM_TVE200=y
+CONFIG_LOGO=y
CONFIG_USB=y
CONFIG_USB_MON=y
CONFIG_USB_FOTG210_HCD=y
@@ -54,6 +76,7 @@
CONFIG_LEDS_CLASS=y
CONFIG_LEDS_GPIO=y
CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_DISK=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
CONFIG_RTC_CLASS=y
CONFIG_DMADEVICES=y
diff --git a/arch/arm/configs/socfpga_defconfig b/arch/arm/configs/socfpga_defconfig
index 2620ce7..371fca4 100644
--- a/arch/arm/configs/socfpga_defconfig
+++ b/arch/arm/configs/socfpga_defconfig
@@ -57,6 +57,7 @@
CONFIG_MTD_NAND=y
CONFIG_MTD_NAND_DENALI_DT=y
CONFIG_MTD_SPI_NOR=y
+# CONFIG_MTD_SPI_NOR_USE_4K_SECTORS is not set
CONFIG_SPI_CADENCE_QUADSPI=y
CONFIG_OF_OVERLAY=y
CONFIG_OF_CONFIGFS=y
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 873e3c1..1d66db9 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -1,3 +1,4 @@
+generic-y += compat.h
generic-y += current.h
generic-y += early_ioremap.h
generic-y += emergency-restart.h
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index bc8d4bb..9342904 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -536,4 +536,14 @@ THUMB( orr \reg , \reg , #PSR_T_BIT )
#endif
.endm
+#ifdef CONFIG_KPROBES
+#define _ASM_NOKPROBE(entry) \
+ .pushsection "_kprobe_blacklist", "aw" ; \
+ .balign 4 ; \
+ .long entry; \
+ .popsection
+#else
+#define _ASM_NOKPROBE(entry)
+#endif
+
#endif /* __ASM_ASSEMBLER_H__ */
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index c6a7495..c7c28c8 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -77,6 +77,9 @@ struct kvm_arch {
/* Interrupt controller */
struct vgic_dist vgic;
int max_vcpus;
+
+ /* Mandated version of PSCI */
+ u32 psci_version;
};
#define KVM_NR_MEM_OBJS 40
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 707a1f0..f6751626 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -309,6 +309,22 @@ static inline unsigned int kvm_get_vmid_bits(void)
return 8;
}
+/*
+ * We are not in the kvm->srcu critical section most of the time, so we take
+ * the SRCU read lock here. Since we copy the data from the user page, we
+ * can immediately drop the lock again.
+ */
+static inline int kvm_read_guest_lock(struct kvm *kvm,
+ gpa_t gpa, void *data, unsigned long len)
+{
+ int srcu_idx = srcu_read_lock(&kvm->srcu);
+ int ret = kvm_read_guest(kvm, gpa, data, len);
+
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+ return ret;
+}
+
static inline void *kvm_get_hyp_vector(void)
{
return kvm_ksym_ref(__kvm_hyp_vector);
diff --git a/arch/arm/include/asm/pci.h b/arch/arm/include/asm/pci.h
index 1f0de80..0abd389 100644
--- a/arch/arm/include/asm/pci.h
+++ b/arch/arm/include/asm/pci.h
@@ -19,13 +19,6 @@ static inline int pci_proc_domain(struct pci_bus *bus)
}
#endif /* CONFIG_PCI_DOMAINS */
-/*
- * The PCI address space does equal the physical memory address space.
- * The networking and block device layers use this boolean for bounce
- * buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS (1)
-
#define HAVE_PCI_MMAP
#define ARCH_GENERIC_PCI_MMAP_RESOURCE
diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
index 2ba95d6..caae484 100644
--- a/arch/arm/include/uapi/asm/kvm.h
+++ b/arch/arm/include/uapi/asm/kvm.h
@@ -195,6 +195,12 @@ struct kvm_arch_memory_slot {
#define KVM_REG_ARM_VFP_FPINST 0x1009
#define KVM_REG_ARM_VFP_FPINST2 0x100A
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM | KVM_REG_SIZE_U64 | \
+ KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0)
+
/* Device Control API: ARM VGIC */
#define KVM_DEV_ARM_VGIC_GRP_ADDR 0
#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1
diff --git a/arch/arm/include/uapi/asm/siginfo.h b/arch/arm/include/uapi/asm/siginfo.h
deleted file mode 100644
index d051388..0000000
--- a/arch/arm/include/uapi/asm/siginfo.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ASM_SIGINFO_H
-#define __ASM_SIGINFO_H
-
-#include <asm-generic/siginfo.h>
-
-/*
- * SIGFPE si_codes
- */
-#ifdef __KERNEL__
-#define FPE_FIXME 0 /* Broken dup of SI_USER */
-#endif /* __KERNEL__ */
-
-#endif
diff --git a/arch/arm/kernel/dma.c b/arch/arm/kernel/dma.c
index e651c4d..6739d37 100644
--- a/arch/arm/kernel/dma.c
+++ b/arch/arm/kernel/dma.c
@@ -276,21 +276,9 @@ static int proc_dma_show(struct seq_file *m, void *v)
return 0;
}
-static int proc_dma_open(struct inode *inode, struct file *file)
-{
- return single_open(file, proc_dma_show, NULL);
-}
-
-static const struct file_operations proc_dma_operations = {
- .open = proc_dma_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __init proc_dma_init(void)
{
- proc_create("dma", 0, NULL, &proc_dma_operations);
+ proc_create_single("dma", 0, NULL, proc_dma_show);
return 0;
}
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 6b38d7a..dd2eb5f 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -83,7 +83,7 @@ void machine_crash_nonpanic_core(void *unused)
{
struct pt_regs regs;
- crash_setup_regs(®s, NULL);
+ crash_setup_regs(®s, get_irq_regs());
printk(KERN_DEBUG "CPU %u will stop doing anything useful since another CPU has crashed\n",
smp_processor_id());
crash_save_cpu(®s, smp_processor_id());
@@ -95,6 +95,27 @@ void machine_crash_nonpanic_core(void *unused)
cpu_relax();
}
+void crash_smp_send_stop(void)
+{
+ static int cpus_stopped;
+ unsigned long msecs;
+
+ if (cpus_stopped)
+ return;
+
+ atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+ smp_call_function(machine_crash_nonpanic_core, NULL, false);
+ msecs = 1000; /* Wait at most a second for the other cpus to stop */
+ while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
+ mdelay(1);
+ msecs--;
+ }
+ if (atomic_read(&waiting_for_crash_ipi) > 0)
+ pr_warn("Non-crashing CPUs did not react to IPI\n");
+
+ cpus_stopped = 1;
+}
+
static void machine_kexec_mask_interrupts(void)
{
unsigned int i;
@@ -120,19 +141,8 @@ static void machine_kexec_mask_interrupts(void)
void machine_crash_shutdown(struct pt_regs *regs)
{
- unsigned long msecs;
-
local_irq_disable();
-
- atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
- smp_call_function(machine_crash_nonpanic_core, NULL, false);
- msecs = 1000; /* Wait at most a second for the other cpus to stop */
- while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
- mdelay(1);
- msecs--;
- }
- if (atomic_read(&waiting_for_crash_ipi) > 0)
- pr_warn("Non-crashing CPUs did not react to IPI\n");
+ crash_smp_send_stop();
crash_save_cpu(regs, smp_processor_id());
machine_kexec_mask_interrupts();
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 7724b0f..36718a4 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -205,6 +205,7 @@ void ptrace_break(struct task_struct *tsk, struct pt_regs *regs)
{
siginfo_t info;
+ clear_siginfo(&info);
info.si_signo = SIGTRAP;
info.si_errno = 0;
info.si_code = TRAP_BRKPT;
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index fc40a2b..35ca494 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -754,7 +754,7 @@ int __init arm_add_memory(u64 start, u64 size)
else
size -= aligned_start - start;
-#ifndef CONFIG_ARCH_PHYS_ADDR_T_64BIT
+#ifndef CONFIG_PHYS_ADDR_T_64BIT
if (aligned_start > ULONG_MAX) {
pr_crit("Ignoring memory at 0x%08llx outside 32-bit physical address space\n",
(long long)start);
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
index 3bda08be..80517f2 100644
--- a/arch/arm/kernel/swp_emulate.c
+++ b/arch/arm/kernel/swp_emulate.c
@@ -91,18 +91,6 @@ static int proc_status_show(struct seq_file *m, void *v)
seq_printf(m, "Last process:\t\t%d\n", previous_pid);
return 0;
}
-
-static int proc_status_open(struct inode *inode, struct file *file)
-{
- return single_open(file, proc_status_show, PDE_DATA(inode));
-}
-
-static const struct file_operations proc_status_fops = {
- .open = proc_status_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif
/*
@@ -112,6 +100,7 @@ static void set_segfault(struct pt_regs *regs, unsigned long addr)
{
siginfo_t info;
+ clear_siginfo(&info);
down_read(¤t->mm->mmap_sem);
if (find_vma(current->mm, addr) == NULL)
info.si_code = SEGV_MAPERR;
@@ -260,7 +249,8 @@ static int __init swp_emulation_init(void)
return 0;
#ifdef CONFIG_PROC_FS
- if (!proc_create("cpu/swp_emulation", S_IRUGO, NULL, &proc_status_fops))
+ if (!proc_create_single("cpu/swp_emulation", S_IRUGO, NULL,
+ proc_status_show))
return -ENOMEM;
#endif /* CONFIG_PROC_FS */
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 5e3633c..badf02c 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -19,6 +19,7 @@
#include <linux/uaccess.h>
#include <linux/hardirq.h>
#include <linux/kdebug.h>
+#include <linux/kprobes.h>
#include <linux/module.h>
#include <linux/kexec.h>
#include <linux/bug.h>
@@ -417,7 +418,8 @@ void unregister_undef_hook(struct undef_hook *hook)
raw_spin_unlock_irqrestore(&undef_lock, flags);
}
-static int call_undef_hook(struct pt_regs *regs, unsigned int instr)
+static nokprobe_inline
+int call_undef_hook(struct pt_regs *regs, unsigned int instr)
{
struct undef_hook *hook;
unsigned long flags;
@@ -439,6 +441,7 @@ asmlinkage void do_undefinstr(struct pt_regs *regs)
siginfo_t info;
void __user *pc;
+ clear_siginfo(&info);
pc = (void __user *)instruction_pointer(regs);
if (processor_mode(regs) == SVC_MODE) {
@@ -490,6 +493,7 @@ asmlinkage void do_undefinstr(struct pt_regs *regs)
arm_notify_die("Oops - undefined instruction", regs, &info, 0, 6);
}
+NOKPROBE_SYMBOL(do_undefinstr)
/*
* Handle FIQ similarly to NMI on x86 systems.
@@ -537,6 +541,7 @@ static int bad_syscall(int n, struct pt_regs *regs)
{
siginfo_t info;
+ clear_siginfo(&info);
if ((current->personality & PER_MASK) != PER_LINUX) {
send_sig(SIGSEGV, current, 1);
return regs->ARM_r0;
@@ -604,6 +609,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs)
{
siginfo_t info;
+ clear_siginfo(&info);
if ((no >> 16) != (__ARM_NR_BASE>> 16))
return bad_syscall(no, regs);
@@ -740,6 +746,8 @@ baddataabort(int code, unsigned long instr, struct pt_regs *regs)
unsigned long addr = instruction_pointer(regs);
siginfo_t info;
+ clear_siginfo(&info);
+
#ifdef CONFIG_DEBUG_USER
if (user_debug & UDBG_BADABORT) {
pr_err("[%d] %s: bad data abort: code %d instr 0x%08lx\n",
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 1e0784e..a18f33e 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -22,6 +22,7 @@
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
+#include <kvm/arm_psci.h>
#include <asm/cputype.h>
#include <linux/uaccess.h>
#include <asm/kvm.h>
@@ -176,6 +177,7 @@ static unsigned long num_core_regs(void)
unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
{
return num_core_regs() + kvm_arm_num_coproc_regs(vcpu)
+ + kvm_arm_get_fw_num_regs(vcpu)
+ NUM_TIMER_REGS;
}
@@ -196,6 +198,11 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
uindices++;
}
+ ret = kvm_arm_copy_fw_reg_indices(vcpu, uindices);
+ if (ret)
+ return ret;
+ uindices += kvm_arm_get_fw_num_regs(vcpu);
+
ret = copy_timer_indices(vcpu, uindices);
if (ret)
return ret;
@@ -214,6 +221,9 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
return get_core_reg(vcpu, reg);
+ if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
+ return kvm_arm_get_fw_reg(vcpu, reg);
+
if (is_timer_reg(reg->id))
return get_timer_reg(vcpu, reg);
@@ -230,6 +240,9 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
return set_core_reg(vcpu, reg);
+ if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
+ return kvm_arm_set_fw_reg(vcpu, reg);
+
if (is_timer_reg(reg->id))
return set_timer_reg(vcpu, reg);
diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S
index df73914..746e780 100644
--- a/arch/arm/lib/getuser.S
+++ b/arch/arm/lib/getuser.S
@@ -38,6 +38,7 @@
mov r0, #0
ret lr
ENDPROC(__get_user_1)
+_ASM_NOKPROBE(__get_user_1)
ENTRY(__get_user_2)
check_uaccess r0, 2, r1, r2, __get_user_bad
@@ -58,6 +59,7 @@
mov r0, #0
ret lr
ENDPROC(__get_user_2)
+_ASM_NOKPROBE(__get_user_2)
ENTRY(__get_user_4)
check_uaccess r0, 4, r1, r2, __get_user_bad
@@ -65,6 +67,7 @@
mov r0, #0
ret lr
ENDPROC(__get_user_4)
+_ASM_NOKPROBE(__get_user_4)
ENTRY(__get_user_8)
check_uaccess r0, 8, r1, r2, __get_user_bad8
@@ -78,6 +81,7 @@
mov r0, #0
ret lr
ENDPROC(__get_user_8)
+_ASM_NOKPROBE(__get_user_8)
#ifdef __ARMEB__
ENTRY(__get_user_32t_8)
@@ -91,6 +95,7 @@
mov r0, #0
ret lr
ENDPROC(__get_user_32t_8)
+_ASM_NOKPROBE(__get_user_32t_8)
ENTRY(__get_user_64t_1)
check_uaccess r0, 1, r1, r2, __get_user_bad8
@@ -98,6 +103,7 @@
mov r0, #0
ret lr
ENDPROC(__get_user_64t_1)
+_ASM_NOKPROBE(__get_user_64t_1)
ENTRY(__get_user_64t_2)
check_uaccess r0, 2, r1, r2, __get_user_bad8
@@ -114,6 +120,7 @@
mov r0, #0
ret lr
ENDPROC(__get_user_64t_2)
+_ASM_NOKPROBE(__get_user_64t_2)
ENTRY(__get_user_64t_4)
check_uaccess r0, 4, r1, r2, __get_user_bad8
@@ -121,6 +128,7 @@
mov r0, #0
ret lr
ENDPROC(__get_user_64t_4)
+_ASM_NOKPROBE(__get_user_64t_4)
#endif
__get_user_bad8:
@@ -131,6 +139,8 @@
ret lr
ENDPROC(__get_user_bad)
ENDPROC(__get_user_bad8)
+_ASM_NOKPROBE(__get_user_bad)
+_ASM_NOKPROBE(__get_user_bad8)
.pushsection __ex_table, "a"
.long 1b, __get_user_bad
diff --git a/arch/arm/mach-axxia/Kconfig b/arch/arm/mach-axxia/Kconfig
index bb2ce1c..d3eae60 100644
--- a/arch/arm/mach-axxia/Kconfig
+++ b/arch/arm/mach-axxia/Kconfig
@@ -2,7 +2,6 @@
config ARCH_AXXIA
bool "LSI Axxia platforms"
depends on ARCH_MULTI_V7 && ARM_LPAE
- select ARCH_DMA_ADDR_T_64BIT
select ARM_AMBA
select ARM_GIC
select ARM_TIMER_SP804
diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig
index c2f3b0d..c46a728 100644
--- a/arch/arm/mach-bcm/Kconfig
+++ b/arch/arm/mach-bcm/Kconfig
@@ -211,7 +211,6 @@
select BRCMSTB_L2_IRQ
select BCM7120_L2_IRQ
select ARCH_HAS_HOLES_MEMORYMODEL
- select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
select ZONE_DMA if ARM_LPAE
select SOC_BRCMSTB
select SOC_BUS
diff --git a/arch/arm/mach-davinci/board-da830-evm.c b/arch/arm/mach-davinci/board-da830-evm.c
index 004f9c8..d1e8ce7 100644
--- a/arch/arm/mach-davinci/board-da830-evm.c
+++ b/arch/arm/mach-davinci/board-da830-evm.c
@@ -205,12 +205,17 @@ static const short da830_evm_mmc_sd_pins[] = {
-1
};
+#define DA830_MMCSD_WP_PIN GPIO_TO_PIN(2, 1)
+#define DA830_MMCSD_CD_PIN GPIO_TO_PIN(2, 2)
+
static struct gpiod_lookup_table mmc_gpios_table = {
.dev_id = "da830-mmc.0",
.table = {
/* gpio chip 1 contains gpio range 32-63 */
- GPIO_LOOKUP("davinci_gpio.1", 2, "cd", GPIO_ACTIVE_LOW),
- GPIO_LOOKUP("davinci_gpio.1", 1, "wp", GPIO_ACTIVE_LOW),
+ GPIO_LOOKUP("davinci_gpio.0", DA830_MMCSD_CD_PIN, "cd",
+ GPIO_ACTIVE_LOW),
+ GPIO_LOOKUP("davinci_gpio.0", DA830_MMCSD_WP_PIN, "wp",
+ GPIO_ACTIVE_LOW),
},
};
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index 3063478..158ed9a 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -763,12 +763,17 @@ static const short da850_evm_mcasp_pins[] __initconst = {
-1
};
+#define DA850_MMCSD_CD_PIN GPIO_TO_PIN(4, 0)
+#define DA850_MMCSD_WP_PIN GPIO_TO_PIN(4, 1)
+
static struct gpiod_lookup_table mmc_gpios_table = {
.dev_id = "da830-mmc.0",
.table = {
/* gpio chip 2 contains gpio range 64-95 */
- GPIO_LOOKUP("davinci_gpio.2", 0, "cd", GPIO_ACTIVE_LOW),
- GPIO_LOOKUP("davinci_gpio.2", 1, "wp", GPIO_ACTIVE_LOW),
+ GPIO_LOOKUP("davinci_gpio.0", DA850_MMCSD_CD_PIN, "cd",
+ GPIO_ACTIVE_LOW),
+ GPIO_LOOKUP("davinci_gpio.0", DA850_MMCSD_WP_PIN, "wp",
+ GPIO_ACTIVE_LOW),
},
};
diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c
index cb30637..23ab9e8 100644
--- a/arch/arm/mach-davinci/board-dm355-evm.c
+++ b/arch/arm/mach-davinci/board-dm355-evm.c
@@ -19,6 +19,7 @@
#include <linux/gpio.h>
#include <linux/gpio/machine.h>
#include <linux/clk.h>
+#include <linux/dm9000.h>
#include <linux/videodev2.h>
#include <media/i2c/tvp514x.h>
#include <linux/spi/spi.h>
@@ -109,12 +110,15 @@ static struct platform_device davinci_nand_device = {
},
};
+#define DM355_I2C_SDA_PIN GPIO_TO_PIN(0, 15)
+#define DM355_I2C_SCL_PIN GPIO_TO_PIN(0, 14)
+
static struct gpiod_lookup_table i2c_recovery_gpiod_table = {
- .dev_id = "i2c_davinci",
+ .dev_id = "i2c_davinci.1",
.table = {
- GPIO_LOOKUP("davinci_gpio", 15, "sda",
+ GPIO_LOOKUP("davinci_gpio.0", DM355_I2C_SDA_PIN, "sda",
GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
- GPIO_LOOKUP("davinci_gpio", 14, "scl",
+ GPIO_LOOKUP("davinci_gpio.0", DM355_I2C_SCL_PIN, "scl",
GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
},
};
@@ -179,11 +183,16 @@ static struct resource dm355evm_dm9000_rsrc[] = {
},
};
+static struct dm9000_plat_data dm335evm_dm9000_platdata;
+
static struct platform_device dm355evm_dm9000 = {
.name = "dm9000",
.id = -1,
.resource = dm355evm_dm9000_rsrc,
.num_resources = ARRAY_SIZE(dm355evm_dm9000_rsrc),
+ .dev = {
+ .platform_data = &dm335evm_dm9000_platdata,
+ },
};
static struct tvp514x_platform_data tvp5146_pdata = {
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index 95b55aa..509e64a 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -17,6 +17,7 @@
#include <linux/i2c.h>
#include <linux/platform_data/pcf857x.h>
#include <linux/platform_data/at24.h>
+#include <linux/platform_data/gpio-davinci.h>
#include <linux/mtd/mtd.h>
#include <linux/mtd/rawnand.h>
#include <linux/mtd/partitions.h>
@@ -596,12 +597,15 @@ static struct i2c_board_info __initdata i2c_info[] = {
},
};
+#define DM644X_I2C_SDA_PIN GPIO_TO_PIN(2, 12)
+#define DM644X_I2C_SCL_PIN GPIO_TO_PIN(2, 11)
+
static struct gpiod_lookup_table i2c_recovery_gpiod_table = {
- .dev_id = "i2c_davinci",
+ .dev_id = "i2c_davinci.1",
.table = {
- GPIO_LOOKUP("davinci_gpio", 44, "sda",
+ GPIO_LOOKUP("davinci_gpio.0", DM644X_I2C_SDA_PIN, "sda",
GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
- GPIO_LOOKUP("davinci_gpio", 43, "scl",
+ GPIO_LOOKUP("davinci_gpio.0", DM644X_I2C_SCL_PIN, "scl",
GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
},
};
diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c
index 2d37f5b..a3c0d1e 100644
--- a/arch/arm/mach-davinci/board-dm646x-evm.c
+++ b/arch/arm/mach-davinci/board-dm646x-evm.c
@@ -532,11 +532,12 @@ static struct vpif_display_config dm646x_vpif_display_config = {
.set_clock = set_vpif_clock,
.subdevinfo = dm646x_vpif_subdev,
.subdev_count = ARRAY_SIZE(dm646x_vpif_subdev),
+ .i2c_adapter_id = 1,
.chan_config[0] = {
.outputs = dm6467_ch0_outputs,
.output_count = ARRAY_SIZE(dm6467_ch0_outputs),
},
- .card_name = "DM646x EVM",
+ .card_name = "DM646x EVM Video Display",
};
/**
@@ -674,6 +675,7 @@ static struct vpif_capture_config dm646x_vpif_capture_cfg = {
.setup_input_channel_mode = setup_vpif_input_channel_mode,
.subdev_info = vpif_capture_sdev_info,
.subdev_count = ARRAY_SIZE(vpif_capture_sdev_info),
+ .i2c_adapter_id = 1,
.chan_config[0] = {
.inputs = dm6467_ch0_inputs,
.input_count = ARRAY_SIZE(dm6467_ch0_inputs),
@@ -694,6 +696,7 @@ static struct vpif_capture_config dm646x_vpif_capture_cfg = {
.fid_pol = 0,
},
},
+ .card_name = "DM646x EVM Video Capture",
};
static void __init evm_init_video(void)
diff --git a/arch/arm/mach-davinci/board-omapl138-hawk.c b/arch/arm/mach-davinci/board-omapl138-hawk.c
index 0d32042..be8b892 100644
--- a/arch/arm/mach-davinci/board-omapl138-hawk.c
+++ b/arch/arm/mach-davinci/board-omapl138-hawk.c
@@ -123,12 +123,16 @@ static const short hawk_mmcsd0_pins[] = {
-1
};
+#define DA850_HAWK_MMCSD_CD_PIN GPIO_TO_PIN(3, 12)
+#define DA850_HAWK_MMCSD_WP_PIN GPIO_TO_PIN(3, 13)
+
static struct gpiod_lookup_table mmc_gpios_table = {
.dev_id = "da830-mmc.0",
.table = {
- /* CD: gpio3_12: gpio60: chip 1 contains gpio range 32-63*/
- GPIO_LOOKUP("davinci_gpio.0", 28, "cd", GPIO_ACTIVE_LOW),
- GPIO_LOOKUP("davinci_gpio.0", 29, "wp", GPIO_ACTIVE_LOW),
+ GPIO_LOOKUP("davinci_gpio.0", DA850_HAWK_MMCSD_CD_PIN, "cd",
+ GPIO_ACTIVE_LOW),
+ GPIO_LOOKUP("davinci_gpio.0", DA850_HAWK_MMCSD_WP_PIN, "wp",
+ GPIO_ACTIVE_LOW),
},
};
diff --git a/arch/arm/mach-davinci/dm646x.c b/arch/arm/mach-davinci/dm646x.c
index 109ab1f..c32ca27 100644
--- a/arch/arm/mach-davinci/dm646x.c
+++ b/arch/arm/mach-davinci/dm646x.c
@@ -488,7 +488,8 @@ static u8 dm646x_default_priorities[DAVINCI_N_AINTC_IRQ] = {
[IRQ_DM646X_MCASP0TXINT] = 7,
[IRQ_DM646X_MCASP0RXINT] = 7,
[IRQ_DM646X_RESERVED_3] = 7,
- [IRQ_DM646X_MCASP1TXINT] = 7, /* clockevent */
+ [IRQ_DM646X_MCASP1TXINT] = 7,
+ [IRQ_TINT0_TINT12] = 7, /* clockevent */
[IRQ_TINT0_TINT34] = 7, /* clocksource */
[IRQ_TINT1_TINT12] = 7, /* DSP timer */
[IRQ_TINT1_TINT34] = 7, /* system tick */
diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c
index e70feec..0581ffb 100644
--- a/arch/arm/mach-ep93xx/core.c
+++ b/arch/arm/mach-ep93xx/core.c
@@ -323,7 +323,7 @@ void __init ep93xx_register_eth(struct ep93xx_eth_data *data, int copy_addr)
/* All EP93xx devices use the same two GPIO pins for I2C bit-banging */
static struct gpiod_lookup_table ep93xx_i2c_gpiod_table = {
- .dev_id = "i2c-gpio",
+ .dev_id = "i2c-gpio.0",
.table = {
/* Use local offsets on gpiochip/port "G" */
GPIO_LOOKUP_IDX("G", 1, NULL, 0,
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index 647c319..2ca4058 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -112,7 +112,6 @@
bool "SAMSUNG EXYNOS5440"
default y
depends on ARCH_EXYNOS5
- select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
select HAVE_ARM_ARCH_TIMER
select AUTO_ZRELADDR
select PINCTRL_EXYNOS5440
diff --git a/arch/arm/mach-highbank/Kconfig b/arch/arm/mach-highbank/Kconfig
index 81110ec..5552968 100644
--- a/arch/arm/mach-highbank/Kconfig
+++ b/arch/arm/mach-highbank/Kconfig
@@ -1,7 +1,6 @@
config ARCH_HIGHBANK
bool "Calxeda ECX-1000/2000 (Highbank/Midway)"
depends on ARCH_MULTI_V7
- select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
select ARCH_HAS_HOLES_MEMORYMODEL
select ARCH_SUPPORTS_BIG_ENDIAN
select ARM_AMBA
diff --git a/arch/arm/mach-ixp4xx/avila-setup.c b/arch/arm/mach-ixp4xx/avila-setup.c
index 77def61..44cbbce 100644
--- a/arch/arm/mach-ixp4xx/avila-setup.c
+++ b/arch/arm/mach-ixp4xx/avila-setup.c
@@ -51,7 +51,7 @@ static struct platform_device avila_flash = {
};
static struct gpiod_lookup_table avila_i2c_gpiod_table = {
- .dev_id = "i2c-gpio",
+ .dev_id = "i2c-gpio.0",
.table = {
GPIO_LOOKUP_IDX("IXP4XX_GPIO_CHIP", AVILA_SDA_PIN,
NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
diff --git a/arch/arm/mach-ixp4xx/dsmg600-setup.c b/arch/arm/mach-ixp4xx/dsmg600-setup.c
index 0f5c999..397190f 100644
--- a/arch/arm/mach-ixp4xx/dsmg600-setup.c
+++ b/arch/arm/mach-ixp4xx/dsmg600-setup.c
@@ -70,7 +70,7 @@ static struct platform_device dsmg600_flash = {
};
static struct gpiod_lookup_table dsmg600_i2c_gpiod_table = {
- .dev_id = "i2c-gpio",
+ .dev_id = "i2c-gpio.0",
.table = {
GPIO_LOOKUP_IDX("IXP4XX_GPIO_CHIP", DSMG600_SDA_PIN,
NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
diff --git a/arch/arm/mach-ixp4xx/fsg-setup.c b/arch/arm/mach-ixp4xx/fsg-setup.c
index 033f79b..f0a152e 100644
--- a/arch/arm/mach-ixp4xx/fsg-setup.c
+++ b/arch/arm/mach-ixp4xx/fsg-setup.c
@@ -56,7 +56,7 @@ static struct platform_device fsg_flash = {
};
static struct gpiod_lookup_table fsg_i2c_gpiod_table = {
- .dev_id = "i2c-gpio",
+ .dev_id = "i2c-gpio.0",
.table = {
GPIO_LOOKUP_IDX("IXP4XX_GPIO_CHIP", FSG_SDA_PIN,
NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
diff --git a/arch/arm/mach-ixp4xx/ixdp425-setup.c b/arch/arm/mach-ixp4xx/ixdp425-setup.c
index b168e2f..3ec829d 100644
--- a/arch/arm/mach-ixp4xx/ixdp425-setup.c
+++ b/arch/arm/mach-ixp4xx/ixdp425-setup.c
@@ -124,7 +124,7 @@ static struct platform_device ixdp425_flash_nand = {
#endif /* CONFIG_MTD_NAND_PLATFORM */
static struct gpiod_lookup_table ixdp425_i2c_gpiod_table = {
- .dev_id = "i2c-gpio",
+ .dev_id = "i2c-gpio.0",
.table = {
GPIO_LOOKUP_IDX("IXP4XX_GPIO_CHIP", IXDP425_SDA_PIN,
NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
diff --git a/arch/arm/mach-ixp4xx/nas100d-setup.c b/arch/arm/mach-ixp4xx/nas100d-setup.c
index 76dfff0..4138d6a 100644
--- a/arch/arm/mach-ixp4xx/nas100d-setup.c
+++ b/arch/arm/mach-ixp4xx/nas100d-setup.c
@@ -102,7 +102,7 @@ static struct platform_device nas100d_leds = {
};
static struct gpiod_lookup_table nas100d_i2c_gpiod_table = {
- .dev_id = "i2c-gpio",
+ .dev_id = "i2c-gpio.0",
.table = {
GPIO_LOOKUP_IDX("IXP4XX_GPIO_CHIP", NAS100D_SDA_PIN,
NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
diff --git a/arch/arm/mach-ixp4xx/nslu2-setup.c b/arch/arm/mach-ixp4xx/nslu2-setup.c
index 91da63a..341b263 100644
--- a/arch/arm/mach-ixp4xx/nslu2-setup.c
+++ b/arch/arm/mach-ixp4xx/nslu2-setup.c
@@ -70,7 +70,7 @@ static struct platform_device nslu2_flash = {
};
static struct gpiod_lookup_table nslu2_i2c_gpiod_table = {
- .dev_id = "i2c-gpio",
+ .dev_id = "i2c-gpio.0",
.table = {
GPIO_LOOKUP_IDX("IXP4XX_GPIO_CHIP", NSLU2_SDA_PIN,
NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
diff --git a/arch/arm/mach-keystone/pm_domain.c b/arch/arm/mach-keystone/pm_domain.c
index fe57e26..abca83d 100644
--- a/arch/arm/mach-keystone/pm_domain.c
+++ b/arch/arm/mach-keystone/pm_domain.c
@@ -29,6 +29,7 @@ static struct dev_pm_domain keystone_pm_domain = {
static struct pm_clk_notifier_block platform_domain_notifier = {
.pm_domain = &keystone_pm_domain,
+ .con_ids = { NULL },
};
static const struct of_device_id of_keystone_table[] = {
diff --git a/arch/arm/mach-omap1/ams-delta-fiq.c b/arch/arm/mach-omap1/ams-delta-fiq.c
index 793a24a..d7ca9e2 100644
--- a/arch/arm/mach-omap1/ams-delta-fiq.c
+++ b/arch/arm/mach-omap1/ams-delta-fiq.c
@@ -58,22 +58,24 @@ static irqreturn_t deferred_fiq(int irq, void *dev_id)
irq_num = gpio_to_irq(gpio);
fiq_count = fiq_buffer[FIQ_CNT_INT_00 + gpio];
- while (irq_counter[gpio] < fiq_count) {
- if (gpio != AMS_DELTA_GPIO_PIN_KEYBRD_CLK) {
- struct irq_data *d = irq_get_irq_data(irq_num);
+ if (irq_counter[gpio] < fiq_count &&
+ gpio != AMS_DELTA_GPIO_PIN_KEYBRD_CLK) {
+ struct irq_data *d = irq_get_irq_data(irq_num);
- /*
- * It looks like handle_edge_irq() that
- * OMAP GPIO edge interrupts default to,
- * expects interrupt already unmasked.
- */
- if (irq_chip && irq_chip->irq_unmask)
+ /*
+ * handle_simple_irq() that OMAP GPIO edge
+ * interrupts default to since commit 80ac93c27441
+ * requires interrupt already acked and unmasked.
+ */
+ if (irq_chip) {
+ if (irq_chip->irq_ack)
+ irq_chip->irq_ack(d);
+ if (irq_chip->irq_unmask)
irq_chip->irq_unmask(d);
}
- generic_handle_irq(irq_num);
-
- irq_counter[gpio]++;
}
+ for (; irq_counter[gpio] < fiq_count; irq_counter[gpio]++)
+ generic_handle_irq(irq_num);
}
return IRQ_HANDLED;
}
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index 4603c30..0d9ce58 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -243,8 +243,4 @@
include/generated/ti-pm-asm-offsets.h: arch/arm/mach-omap2/pm-asm-offsets.s FORCE
$(call filechk,offsets,__TI_PM_ASM_OFFSETS_H__)
-# For rule to generate ti-emif-asm-offsets.h dependency
-include drivers/memory/Makefile.asm-offsets
-
-arch/arm/mach-omap2/sleep33xx.o: include/generated/ti-pm-asm-offsets.h include/generated/ti-emif-asm-offsets.h
-arch/arm/mach-omap2/sleep43xx.o: include/generated/ti-pm-asm-offsets.h include/generated/ti-emif-asm-offsets.h
+$(obj)/sleep33xx.o $(obj)/sleep43xx.o: include/generated/ti-pm-asm-offsets.h
diff --git a/arch/arm/mach-omap2/pm-asm-offsets.c b/arch/arm/mach-omap2/pm-asm-offsets.c
index 6d4392da..b9846b1 100644
--- a/arch/arm/mach-omap2/pm-asm-offsets.c
+++ b/arch/arm/mach-omap2/pm-asm-offsets.c
@@ -7,9 +7,12 @@
#include <linux/kbuild.h>
#include <linux/platform_data/pm33xx.h>
+#include <linux/ti-emif-sram.h>
int main(void)
{
+ ti_emif_asm_offsets();
+
DEFINE(AMX3_PM_WFI_FLAGS_OFFSET,
offsetof(struct am33xx_pm_sram_data, wfi_flags));
DEFINE(AMX3_PM_L2_AUX_CTRL_VAL_OFFSET,
diff --git a/arch/arm/mach-omap2/powerdomain.c b/arch/arm/mach-omap2/powerdomain.c
index 76eb6ec..1e6a967 100644
--- a/arch/arm/mach-omap2/powerdomain.c
+++ b/arch/arm/mach-omap2/powerdomain.c
@@ -188,7 +188,7 @@ static int _pwrdm_state_switch(struct powerdomain *pwrdm, int flag)
((prev & OMAP_POWERSTATE_MASK) << 0));
trace_power_domain_target_rcuidle(pwrdm->name,
trace_state,
- smp_processor_id());
+ raw_smp_processor_id());
}
break;
default:
@@ -518,7 +518,7 @@ int pwrdm_set_next_pwrst(struct powerdomain *pwrdm, u8 pwrst)
if (arch_pwrdm && arch_pwrdm->pwrdm_set_next_pwrst) {
/* Trace the pwrdm desired target state */
trace_power_domain_target_rcuidle(pwrdm->name, pwrst,
- smp_processor_id());
+ raw_smp_processor_id());
/* Program the pwrdm desired target state */
ret = arch_pwrdm->pwrdm_set_next_pwrst(pwrdm, pwrst);
}
diff --git a/arch/arm/mach-omap2/sleep33xx.S b/arch/arm/mach-omap2/sleep33xx.S
index 218d799..322b3bb 100644
--- a/arch/arm/mach-omap2/sleep33xx.S
+++ b/arch/arm/mach-omap2/sleep33xx.S
@@ -6,7 +6,6 @@
* Dave Gerlach, Vaibhav Bedia
*/
-#include <generated/ti-emif-asm-offsets.h>
#include <generated/ti-pm-asm-offsets.h>
#include <linux/linkage.h>
#include <linux/ti-emif-sram.h>
diff --git a/arch/arm/mach-omap2/sleep43xx.S b/arch/arm/mach-omap2/sleep43xx.S
index b24be62..8903814 100644
--- a/arch/arm/mach-omap2/sleep43xx.S
+++ b/arch/arm/mach-omap2/sleep43xx.S
@@ -6,7 +6,6 @@
* Dave Gerlach, Vaibhav Bedia
*/
-#include <generated/ti-emif-asm-offsets.h>
#include <generated/ti-pm-asm-offsets.h>
#include <linux/linkage.h>
#include <linux/ti-emif-sram.h>
diff --git a/arch/arm/mach-pxa/palmz72.c b/arch/arm/mach-pxa/palmz72.c
index 5877e54..0adb1bd 100644
--- a/arch/arm/mach-pxa/palmz72.c
+++ b/arch/arm/mach-pxa/palmz72.c
@@ -322,7 +322,7 @@ static struct soc_camera_link palmz72_iclink = {
};
static struct gpiod_lookup_table palmz72_i2c_gpiod_table = {
- .dev_id = "i2c-gpio",
+ .dev_id = "i2c-gpio.0",
.table = {
GPIO_LOOKUP_IDX("gpio-pxa", 118, NULL, 0,
GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
diff --git a/arch/arm/mach-pxa/viper.c b/arch/arm/mach-pxa/viper.c
index 90d0f27..207dcc2 100644
--- a/arch/arm/mach-pxa/viper.c
+++ b/arch/arm/mach-pxa/viper.c
@@ -460,7 +460,7 @@ static struct platform_device smc91x_device = {
/* i2c */
static struct gpiod_lookup_table viper_i2c_gpiod_table = {
- .dev_id = "i2c-gpio",
+ .dev_id = "i2c-gpio.1",
.table = {
GPIO_LOOKUP_IDX("gpio-pxa", VIPER_RTC_I2C_SDA_GPIO,
NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
@@ -789,7 +789,7 @@ static int __init viper_tpm_setup(char *str)
__setup("tpm=", viper_tpm_setup);
struct gpiod_lookup_table viper_tpm_i2c_gpiod_table = {
- .dev_id = "i2c-gpio",
+ .dev_id = "i2c-gpio.2",
.table = {
GPIO_LOOKUP_IDX("gpio-pxa", VIPER_TPM_I2C_SDA_GPIO,
NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
diff --git a/arch/arm/mach-rockchip/Kconfig b/arch/arm/mach-rockchip/Kconfig
index a406596..fafd3d7 100644
--- a/arch/arm/mach-rockchip/Kconfig
+++ b/arch/arm/mach-rockchip/Kconfig
@@ -3,7 +3,6 @@
depends on ARCH_MULTI_V7
select PINCTRL
select PINCTRL_ROCKCHIP
- select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
select ARCH_HAS_RESET_CONTROLLER
select ARM_AMBA
select ARM_GIC
diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c
index bdb5ec1..39aef48 100644
--- a/arch/arm/mach-rpc/ecard.c
+++ b/arch/arm/mach-rpc/ecard.c
@@ -657,25 +657,13 @@ static int ecard_devices_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int ecard_devices_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ecard_devices_proc_show, NULL);
-}
-
-static const struct file_operations bus_ecard_proc_fops = {
- .owner = THIS_MODULE,
- .open = ecard_devices_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static struct proc_dir_entry *proc_bus_ecard_dir = NULL;
static void ecard_proc_init(void)
{
proc_bus_ecard_dir = proc_mkdir("bus/ecard", NULL);
- proc_create("devices", 0, proc_bus_ecard_dir, &bus_ecard_proc_fops);
+ proc_create_single("devices", 0, proc_bus_ecard_dir,
+ ecard_devices_proc_show);
}
#define ec_set_resource(ec,nr,st,sz) \
diff --git a/arch/arm/mach-s3c24xx/mach-jive.c b/arch/arm/mach-s3c24xx/mach-jive.c
index 59589a4..885e8f1 100644
--- a/arch/arm/mach-s3c24xx/mach-jive.c
+++ b/arch/arm/mach-s3c24xx/mach-jive.c
@@ -427,9 +427,9 @@ static struct gpiod_lookup_table jive_wm8750_gpiod_table = {
.dev_id = "spi_gpio",
.table = {
GPIO_LOOKUP("GPIOB", 4,
- "gpio-sck", GPIO_ACTIVE_HIGH),
+ "sck", GPIO_ACTIVE_HIGH),
GPIO_LOOKUP("GPIOB", 9,
- "gpio-mosi", GPIO_ACTIVE_HIGH),
+ "mosi", GPIO_ACTIVE_HIGH),
GPIO_LOOKUP("GPIOH", 10,
"cs", GPIO_ACTIVE_HIGH),
{ },
diff --git a/arch/arm/mach-sa1100/simpad.c b/arch/arm/mach-sa1100/simpad.c
index ace0104..f45aed2 100644
--- a/arch/arm/mach-sa1100/simpad.c
+++ b/arch/arm/mach-sa1100/simpad.c
@@ -327,7 +327,7 @@ static struct platform_device simpad_gpio_leds = {
* i2c
*/
static struct gpiod_lookup_table simpad_i2c_gpiod_table = {
- .dev_id = "i2c-gpio",
+ .dev_id = "i2c-gpio.0",
.table = {
GPIO_LOOKUP_IDX("gpio", 21, NULL, 0,
GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index 280e731..fe60cd09 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -29,7 +29,6 @@
menuconfig ARCH_RENESAS
bool "Renesas ARM SoCs"
depends on ARCH_MULTI_V7 && MMU
- select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
select ARCH_SHMOBILE
select ARM_GIC
select GPIOLIB
diff --git a/arch/arm/mach-tegra/Kconfig b/arch/arm/mach-tegra/Kconfig
index 1e0aeb4..7f3b83e 100644
--- a/arch/arm/mach-tegra/Kconfig
+++ b/arch/arm/mach-tegra/Kconfig
@@ -15,6 +15,5 @@
select RESET_CONTROLLER
select SOC_BUS
select ZONE_DMA if ARM_LPAE
- select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
help
This enables support for NVIDIA Tegra based systems.
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 7f14acf..5a016bc 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -661,6 +661,7 @@
bool "Support for the Large Physical Address Extension"
depends on MMU && CPU_32v7 && !CPU_32v6 && !CPU_32v5 && \
!CPU_32v4 && !CPU_32v3
+ select PHYS_ADDR_T_64BIT
help
Say Y if you have an ARMv7 processor supporting the LPAE page
table format and you would like to access memory beyond the
@@ -673,12 +674,6 @@
def_bool y
depends on ARM_LPAE && ARM_PATCH_PHYS_VIRT && ARCH_KEYSTONE
-config ARCH_PHYS_ADDR_T_64BIT
- def_bool ARM_LPAE
-
-config ARCH_DMA_ADDR_T_64BIT
- bool
-
config ARM_THUMB
bool "Support Thumb user binaries" if !CPU_THUMBONLY && EXPERT
depends on CPU_THUMB_CAPABLE
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 2c96190..bd2c739 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -950,6 +950,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
if (ai_usermode & UM_SIGNAL) {
siginfo_t si;
+ clear_siginfo(&si);
si.si_signo = SIGBUS;
si.si_errno = 0;
si.si_code = BUS_ADRALN;
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index 619f24a..f448a06 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -241,12 +241,3 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
void arch_teardown_dma_ops(struct device *dev)
{
}
-
-#define PREALLOC_DMA_DEBUG_ENTRIES 4096
-
-static int __init dma_debug_do_init(void)
-{
- dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
- return 0;
-}
-core_initcall(dma_debug_do_init);
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 8c398fe..4b6613b 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -466,12 +466,6 @@ void __init dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
void __init dma_contiguous_remap(void)
{
int i;
-
- if (!dma_mmu_remap_num)
- return;
-
- /* call flush_cache_all() since CMA area would be large enough */
- flush_cache_all();
for (i = 0; i < dma_mmu_remap_num; i++) {
phys_addr_t start = dma_mmu_remap[i].base;
phys_addr_t end = start + dma_mmu_remap[i].size;
@@ -504,15 +498,7 @@ void __init dma_contiguous_remap(void)
flush_tlb_kernel_range(__phys_to_virt(start),
__phys_to_virt(end));
- /*
- * All the memory in CMA region will be on ZONE_MOVABLE.
- * If that zone is considered as highmem, the memory in CMA
- * region is also considered as highmem even if it's
- * physical address belong to lowmem. In this case,
- * re-mapping isn't required.
- */
- if (!is_highmem_idx(ZONE_MOVABLE))
- iotable_init(&map, 1);
+ iotable_init(&map, 1);
}
}
@@ -1165,15 +1151,6 @@ int arm_dma_supported(struct device *dev, u64 mask)
return __dma_supported(dev, mask, false);
}
-#define PREALLOC_DMA_DEBUG_ENTRIES 4096
-
-static int __init dma_debug_do_init(void)
-{
- dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
- return 0;
-}
-core_initcall(dma_debug_do_init);
-
#ifdef CONFIG_ARM_DMA_USE_IOMMU
static int __dma_info_to_prot(enum dma_data_direction dir, unsigned long attrs)
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index b75eada..32034543 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -163,6 +163,8 @@ __do_user_fault(struct task_struct *tsk, unsigned long addr,
{
struct siginfo si;
+ clear_siginfo(&si);
+
#ifdef CONFIG_DEBUG_USER
if (((user_debug & UDBG_SEGV) && (sig == SIGSEGV)) ||
((user_debug & UDBG_BUS) && (sig == SIGBUS))) {
@@ -557,6 +559,7 @@ do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
inf->name, fsr, addr);
show_pte(current->mm, addr);
+ clear_siginfo(&info);
info.si_signo = inf->sig;
info.si_errno = 0;
info.si_code = inf->code;
@@ -589,6 +592,7 @@ do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs)
pr_alert("Unhandled prefetch abort: %s (0x%03x) at 0x%08lx\n",
inf->name, ifsr, addr);
+ clear_siginfo(&info);
info.si_signo = inf->sig;
info.si_errno = 0;
info.si_code = inf->code;
diff --git a/arch/arm/probes/kprobes/opt-arm.c b/arch/arm/probes/kprobes/opt-arm.c
index bcdecc2..b2aa9b3 100644
--- a/arch/arm/probes/kprobes/opt-arm.c
+++ b/arch/arm/probes/kprobes/opt-arm.c
@@ -165,13 +165,14 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
{
unsigned long flags;
struct kprobe *p = &op->kp;
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+ struct kprobe_ctlblk *kcb;
/* Save skipped registers */
regs->ARM_pc = (unsigned long)op->kp.addr;
regs->ARM_ORIG_r0 = ~0UL;
local_irq_save(flags);
+ kcb = get_kprobe_ctlblk();
if (kprobe_running()) {
kprobes_inc_nmissed_count(&op->kp);
@@ -191,6 +192,7 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
local_irq_restore(flags);
}
+NOKPROBE_SYMBOL(optimized_callback)
int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *orig)
{
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 4c375e1..35d0f82 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -218,8 +218,7 @@ static void vfp_raise_sigfpe(unsigned int sicode, struct pt_regs *regs)
{
siginfo_t info;
- memset(&info, 0, sizeof(info));
-
+ clear_siginfo(&info);
info.si_signo = SIGFPE;
info.si_code = sicode;
info.si_addr = (void __user *)(instruction_pointer(regs) - 4);
@@ -257,7 +256,7 @@ static void vfp_raise_exceptions(u32 exceptions, u32 inst, u32 fpscr, struct pt_
if (exceptions == VFP_EXCEPTION_ERROR) {
vfp_panic("unhandled bounce", inst);
- vfp_raise_sigfpe(FPE_FIXME, regs);
+ vfp_raise_sigfpe(FPE_FLTINV, regs);
return;
}
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index eb2cf49..b25ed78 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -105,7 +105,6 @@
select HAVE_CONTEXT_TRACKING
select HAVE_DEBUG_BUGVERBOSE
select HAVE_DEBUG_KMEMLEAK
- select HAVE_DMA_API_DEBUG
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
select HAVE_EFFICIENT_UNALIGNED_ACCESS
@@ -133,6 +132,8 @@
select IRQ_FORCED_THREADING
select MODULES_USE_ELF_RELA
select MULTI_IRQ_HANDLER
+ select NEED_DMA_MAP_STATE
+ select NEED_SG_DMA_LENGTH
select NO_BOOTMEM
select OF
select OF_EARLY_FLATTREE
@@ -142,6 +143,7 @@
select POWER_SUPPLY
select REFCOUNT_FULL
select SPARSE_IRQ
+ select SWIOTLB
select SYSCTL_EXCEPTION_TRACE
select THREAD_INFO_IN_TASK
help
@@ -150,9 +152,6 @@
config 64BIT
def_bool y
-config ARCH_PHYS_ADDR_T_64BIT
- def_bool y
-
config MMU
def_bool y
@@ -237,24 +236,9 @@
config HAVE_GENERIC_GUP
def_bool y
-config ARCH_DMA_ADDR_T_64BIT
- def_bool y
-
-config NEED_DMA_MAP_STATE
- def_bool y
-
-config NEED_SG_DMA_LENGTH
- def_bool y
-
config SMP
def_bool y
-config SWIOTLB
- def_bool y
-
-config IOMMU_HELPER
- def_bool SWIOTLB
-
config KERNEL_MODE_NEON
def_bool y
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 1540286..87f7d2f 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -56,7 +56,11 @@
KBUILD_CFLAGS += $(call cc-option,-mabi=lp64)
KBUILD_AFLAGS += $(call cc-option,-mabi=lp64)
+ifeq ($(cc-name),clang)
+KBUILD_CFLAGS += -DCONFIG_ARCH_SUPPORTS_INT128
+else
KBUILD_CFLAGS += $(call cc-ifversion, -ge, 0500, -DCONFIG_ARCH_SUPPORTS_INT128)
+endif
ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
KBUILD_CPPFLAGS += -mbig-endian
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
index 4eef36b..88e712e 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
@@ -212,3 +212,7 @@
pinctrl-0 = <&uart_ao_a_pins>;
pinctrl-names = "default";
};
+
+&usb0 {
+ status = "okay";
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
index 22bf374..3e3eb31 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
@@ -271,3 +271,15 @@
pinctrl-0 = <&uart_ao_a_pins>;
pinctrl-names = "default";
};
+
+&usb0 {
+ status = "okay";
+};
+
+&usb2_phy0 {
+ /*
+ * even though the schematics don't show it:
+ * HDMI_5V is also used as supply for the USB VBUS.
+ */
+ phy-supply = <&hdmi_5v>;
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
index 69c721a..6739697 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
@@ -215,3 +215,7 @@
pinctrl-0 = <&uart_ao_a_pins>;
pinctrl-names = "default";
};
+
+&usb0 {
+ status = "okay";
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
index 0a0953f..0cfd701 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
@@ -185,3 +185,7 @@
pinctrl-0 = <&uart_ao_a_pins>;
pinctrl-names = "default";
};
+
+&usb0 {
+ status = "okay";
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index e1a39cb..dba365e 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -20,6 +20,67 @@
no-map;
};
};
+
+ soc {
+ usb0: usb@c9000000 {
+ status = "disabled";
+ compatible = "amlogic,meson-gxl-dwc3";
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+
+ clocks = <&clkc CLKID_USB>;
+ clock-names = "usb_general";
+ resets = <&reset RESET_USB_OTG>;
+ reset-names = "usb_otg";
+
+ dwc3: dwc3@c9000000 {
+ compatible = "snps,dwc3";
+ reg = <0x0 0xc9000000 0x0 0x100000>;
+ interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+ dr_mode = "host";
+ maximum-speed = "high-speed";
+ snps,dis_u2_susphy_quirk;
+ phys = <&usb3_phy>, <&usb2_phy0>, <&usb2_phy1>;
+ };
+ };
+ };
+};
+
+&apb {
+ usb2_phy0: phy@78000 {
+ compatible = "amlogic,meson-gxl-usb2-phy";
+ #phy-cells = <0>;
+ reg = <0x0 0x78000 0x0 0x20>;
+ clocks = <&clkc CLKID_USB>;
+ clock-names = "phy";
+ resets = <&reset RESET_USB_OTG>;
+ reset-names = "phy";
+ status = "okay";
+ };
+
+ usb2_phy1: phy@78020 {
+ compatible = "amlogic,meson-gxl-usb2-phy";
+ #phy-cells = <0>;
+ reg = <0x0 0x78020 0x0 0x20>;
+ clocks = <&clkc CLKID_USB>;
+ clock-names = "phy";
+ resets = <&reset RESET_USB_OTG>;
+ reset-names = "phy";
+ status = "okay";
+ };
+
+ usb3_phy: phy@78080 {
+ compatible = "amlogic,meson-gxl-usb3-phy";
+ #phy-cells = <0>;
+ reg = <0x0 0x78080 0x0 0x20>;
+ interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clkc CLKID_USB>, <&clkc_AO CLKID_AO_CEC_32K>;
+ clock-names = "phy", "peripheral";
+ resets = <&reset RESET_USB_OTG>, <&reset RESET_USB_OTG>;
+ reset-names = "phy", "peripheral";
+ status = "okay";
+ };
};
ðmac {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts
index 4fd46c1..0868da4 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts
@@ -406,3 +406,7 @@
status = "okay";
vref-supply = <&vddio_ao18>;
};
+
+&usb0 {
+ status = "okay";
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi
index d076a7c..247888d 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi
@@ -80,6 +80,19 @@
};
};
+&apb {
+ usb2_phy2: phy@78040 {
+ compatible = "amlogic,meson-gxl-usb2-phy";
+ #phy-cells = <0>;
+ reg = <0x0 0x78040 0x0 0x20>;
+ clocks = <&clkc CLKID_USB>;
+ clock-names = "phy";
+ resets = <&reset RESET_USB_OTG>;
+ reset-names = "phy";
+ status = "okay";
+ };
+};
+
&clkc_AO {
compatible = "amlogic,meson-gxm-aoclkc", "amlogic,meson-gx-aoclkc";
};
@@ -100,3 +113,7 @@
&hdmi_tx {
compatible = "amlogic,meson-gxm-dw-hdmi", "amlogic,meson-gx-dw-hdmi";
};
+
+&dwc3 {
+ phys = <&usb3_phy>, <&usb2_phy0>, <&usb2_phy1>, <&usb2_phy2>;
+};
diff --git a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
index 2ac4322..69804c5 100644
--- a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
@@ -56,8 +56,6 @@
gpio_keys {
compatible = "gpio-keys";
- #address-cells = <1>;
- #size-cells = <0>;
power-button {
debounce_interval = <50>;
diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray-sata.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray-sata.dtsi
index 4b5465d..8c68e0c 100644
--- a/arch/arm64/boot/dts/broadcom/stingray/stingray-sata.dtsi
+++ b/arch/arm64/boot/dts/broadcom/stingray/stingray-sata.dtsi
@@ -36,11 +36,11 @@
#size-cells = <1>;
ranges = <0x0 0x0 0x67d00000 0x00800000>;
- sata0: ahci@210000 {
+ sata0: ahci@0 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00210000 0x1000>;
+ reg = <0x00000000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 339 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 321 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -52,9 +52,9 @@
};
};
- sata_phy0: sata_phy@212100 {
+ sata_phy0: sata_phy@2100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00212100 0x1000>;
+ reg = <0x00002100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
@@ -66,11 +66,11 @@
};
};
- sata1: ahci@310000 {
+ sata1: ahci@10000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00310000 0x1000>;
+ reg = <0x00010000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 323 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -82,9 +82,9 @@
};
};
- sata_phy1: sata_phy@312100 {
+ sata_phy1: sata_phy@12100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00312100 0x1000>;
+ reg = <0x00012100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
@@ -96,11 +96,11 @@
};
};
- sata2: ahci@120000 {
+ sata2: ahci@20000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00120000 0x1000>;
+ reg = <0x00020000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 333 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 325 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -112,9 +112,9 @@
};
};
- sata_phy2: sata_phy@122100 {
+ sata_phy2: sata_phy@22100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00122100 0x1000>;
+ reg = <0x00022100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
@@ -126,11 +126,11 @@
};
};
- sata3: ahci@130000 {
+ sata3: ahci@30000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00130000 0x1000>;
+ reg = <0x00030000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 335 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 327 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -142,9 +142,9 @@
};
};
- sata_phy3: sata_phy@132100 {
+ sata_phy3: sata_phy@32100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00132100 0x1000>;
+ reg = <0x00032100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
@@ -156,11 +156,11 @@
};
};
- sata4: ahci@330000 {
+ sata4: ahci@100000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00330000 0x1000>;
+ reg = <0x00100000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 351 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 329 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -172,9 +172,9 @@
};
};
- sata_phy4: sata_phy@332100 {
+ sata_phy4: sata_phy@102100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00332100 0x1000>;
+ reg = <0x00102100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
@@ -186,11 +186,11 @@
};
};
- sata5: ahci@400000 {
+ sata5: ahci@110000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00400000 0x1000>;
+ reg = <0x00110000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 353 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 331 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -202,9 +202,9 @@
};
};
- sata_phy5: sata_phy@402100 {
+ sata_phy5: sata_phy@112100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00402100 0x1000>;
+ reg = <0x00112100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
@@ -216,11 +216,11 @@
};
};
- sata6: ahci@410000 {
+ sata6: ahci@120000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00410000 0x1000>;
+ reg = <0x00120000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 355 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 333 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -232,9 +232,9 @@
};
};
- sata_phy6: sata_phy@412100 {
+ sata_phy6: sata_phy@122100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00412100 0x1000>;
+ reg = <0x00122100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
@@ -246,11 +246,11 @@
};
};
- sata7: ahci@420000 {
+ sata7: ahci@130000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00420000 0x1000>;
+ reg = <0x00130000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 357 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 335 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -262,9 +262,9 @@
};
};
- sata_phy7: sata_phy@422100 {
+ sata_phy7: sata_phy@132100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00422100 0x1000>;
+ reg = <0x00132100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
diff --git a/arch/arm64/boot/dts/exynos/exynos5433.dtsi b/arch/arm64/boot/dts/exynos/exynos5433.dtsi
index c0231d0..1ad8677 100644
--- a/arch/arm64/boot/dts/exynos/exynos5433.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos5433.dtsi
@@ -1317,7 +1317,7 @@
reg = <0x14d60000 0x100>;
dmas = <&pdma0 31 &pdma0 30>;
dma-names = "tx", "rx";
- interrupts = <GIC_SPI 435 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 435 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cmu_peric CLK_PCLK_I2S1>,
<&cmu_peric CLK_PCLK_I2S1>,
<&cmu_peric CLK_SCLK_I2S1>;
diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
index 724a0d3..edb4ee0 100644
--- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
@@ -299,7 +299,6 @@
/* GPIO blocks 16 thru 19 do not appear to be routed to pins */
dwmmc_0: dwmmc0@f723d000 {
- max-frequency = <150000000>;
cap-mmc-highspeed;
mmc-hs200-1_8v;
non-removable;
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
index 48cad79..ed2f123 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
@@ -38,9 +38,10 @@
compatible = "marvell,armada-7k-pp22";
reg = <0x0 0x100000>, <0x129000 0xb000>;
clocks = <&CP110_LABEL(clk) 1 3>, <&CP110_LABEL(clk) 1 9>,
- <&CP110_LABEL(clk) 1 5>, <&CP110_LABEL(clk) 1 18>;
+ <&CP110_LABEL(clk) 1 5>, <&CP110_LABEL(clk) 1 6>,
+ <&CP110_LABEL(clk) 1 18>;
clock-names = "pp_clk", "gop_clk",
- "mg_clk", "axi_clk";
+ "mg_clk", "mg_core_clk", "axi_clk";
marvell,system-controller = <&CP110_LABEL(syscon0)>;
status = "disabled";
dma-coherent;
@@ -141,6 +142,8 @@
#size-cells = <0>;
compatible = "marvell,xmdio";
reg = <0x12a600 0x10>;
+ clocks = <&CP110_LABEL(clk) 1 5>,
+ <&CP110_LABEL(clk) 1 6>, <&CP110_LABEL(clk) 1 18>;
status = "disabled";
};
diff --git a/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi b/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi
index a8baad7..13f57ff 100644
--- a/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi
@@ -46,7 +46,7 @@
compatible = "ethernet-phy-ieee802.3-c22";
reg = <0x0>;
interrupt-parent = <&gpio>;
- interrupts = <TEGRA_MAIN_GPIO(M, 5) IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <TEGRA_MAIN_GPIO(M, 5) IRQ_TYPE_LEVEL_LOW>;
};
};
};
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld11.dtsi b/arch/arm64/boot/dts/socionext/uniphier-ld11.dtsi
index e62bda1..c32dd34 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld11.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld11.dtsi
@@ -414,7 +414,7 @@
mmc-ddr-1_8v;
mmc-hs200-1_8v;
mmc-pwrseq = <&emmc_pwrseq>;
- cdns,phy-input-delay-legacy = <4>;
+ cdns,phy-input-delay-legacy = <9>;
cdns,phy-input-delay-mmc-highspeed = <2>;
cdns,phy-input-delay-mmc-ddr = <3>;
cdns,phy-dll-delay-sdclk = <21>;
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts b/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts
index 2c1a92f..440c2e6 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts
@@ -67,3 +67,11 @@
reg = <0>;
};
};
+
+&pinctrl_ether_rgmii {
+ tx {
+ pins = "RGMII_TXCLK", "RGMII_TXD0", "RGMII_TXD1",
+ "RGMII_TXD2", "RGMII_TXD3", "RGMII_TXCTL";
+ drive-strength = <9>;
+ };
+};
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi b/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
index 9efe20d..3a5ed78 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
@@ -519,7 +519,7 @@
mmc-ddr-1_8v;
mmc-hs200-1_8v;
mmc-pwrseq = <&emmc_pwrseq>;
- cdns,phy-input-delay-legacy = <4>;
+ cdns,phy-input-delay-legacy = <9>;
cdns,phy-input-delay-mmc-highspeed = <2>;
cdns,phy-input-delay-mmc-ddr = <3>;
cdns,phy-dll-delay-sdclk = <21>;
diff --git a/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi b/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
index 7c8f710..e85d6dd 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
@@ -334,7 +334,7 @@
mmc-ddr-1_8v;
mmc-hs200-1_8v;
mmc-pwrseq = <&emmc_pwrseq>;
- cdns,phy-input-delay-legacy = <4>;
+ cdns,phy-input-delay-legacy = <9>;
cdns,phy-input-delay-mmc-highspeed = <2>;
cdns,phy-input-delay-mmc-ddr = <3>;
cdns,phy-dll-delay-sdclk = <21>;
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index 9ef0797..f9b0b09 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -117,7 +117,7 @@ static inline void atomic_and(int i, atomic_t *v)
/* LSE atomics */
" mvn %w[i], %w[i]\n"
" stclr %w[i], %[v]")
- : [i] "+r" (w0), [v] "+Q" (v->counter)
+ : [i] "+&r" (w0), [v] "+Q" (v->counter)
: "r" (x1)
: __LL_SC_CLOBBERS);
}
@@ -135,7 +135,7 @@ static inline int atomic_fetch_and##name(int i, atomic_t *v) \
/* LSE atomics */ \
" mvn %w[i], %w[i]\n" \
" ldclr" #mb " %w[i], %w[i], %[v]") \
- : [i] "+r" (w0), [v] "+Q" (v->counter) \
+ : [i] "+&r" (w0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
@@ -161,7 +161,7 @@ static inline void atomic_sub(int i, atomic_t *v)
/* LSE atomics */
" neg %w[i], %w[i]\n"
" stadd %w[i], %[v]")
- : [i] "+r" (w0), [v] "+Q" (v->counter)
+ : [i] "+&r" (w0), [v] "+Q" (v->counter)
: "r" (x1)
: __LL_SC_CLOBBERS);
}
@@ -180,7 +180,7 @@ static inline int atomic_sub_return##name(int i, atomic_t *v) \
" neg %w[i], %w[i]\n" \
" ldadd" #mb " %w[i], w30, %[v]\n" \
" add %w[i], %w[i], w30") \
- : [i] "+r" (w0), [v] "+Q" (v->counter) \
+ : [i] "+&r" (w0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS , ##cl); \
\
@@ -207,7 +207,7 @@ static inline int atomic_fetch_sub##name(int i, atomic_t *v) \
/* LSE atomics */ \
" neg %w[i], %w[i]\n" \
" ldadd" #mb " %w[i], %w[i], %[v]") \
- : [i] "+r" (w0), [v] "+Q" (v->counter) \
+ : [i] "+&r" (w0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
@@ -314,7 +314,7 @@ static inline void atomic64_and(long i, atomic64_t *v)
/* LSE atomics */
" mvn %[i], %[i]\n"
" stclr %[i], %[v]")
- : [i] "+r" (x0), [v] "+Q" (v->counter)
+ : [i] "+&r" (x0), [v] "+Q" (v->counter)
: "r" (x1)
: __LL_SC_CLOBBERS);
}
@@ -332,7 +332,7 @@ static inline long atomic64_fetch_and##name(long i, atomic64_t *v) \
/* LSE atomics */ \
" mvn %[i], %[i]\n" \
" ldclr" #mb " %[i], %[i], %[v]") \
- : [i] "+r" (x0), [v] "+Q" (v->counter) \
+ : [i] "+&r" (x0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
@@ -358,7 +358,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
/* LSE atomics */
" neg %[i], %[i]\n"
" stadd %[i], %[v]")
- : [i] "+r" (x0), [v] "+Q" (v->counter)
+ : [i] "+&r" (x0), [v] "+Q" (v->counter)
: "r" (x1)
: __LL_SC_CLOBBERS);
}
@@ -377,7 +377,7 @@ static inline long atomic64_sub_return##name(long i, atomic64_t *v) \
" neg %[i], %[i]\n" \
" ldadd" #mb " %[i], x30, %[v]\n" \
" add %[i], %[i], x30") \
- : [i] "+r" (x0), [v] "+Q" (v->counter) \
+ : [i] "+&r" (x0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
@@ -404,7 +404,7 @@ static inline long atomic64_fetch_sub##name(long i, atomic64_t *v) \
/* LSE atomics */ \
" neg %[i], %[i]\n" \
" ldadd" #mb " %[i], %[i], %[v]") \
- : [i] "+r" (x0), [v] "+Q" (v->counter) \
+ : [i] "+&r" (x0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
@@ -435,7 +435,7 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
" sub x30, x30, %[ret]\n"
" cbnz x30, 1b\n"
"2:")
- : [ret] "+r" (x0), [v] "+Q" (v->counter)
+ : [ret] "+&r" (x0), [v] "+Q" (v->counter)
:
: __LL_SC_CLOBBERS, "cc", "memory");
@@ -516,7 +516,7 @@ static inline long __cmpxchg_double##name(unsigned long old1, \
" eor %[old1], %[old1], %[oldval1]\n" \
" eor %[old2], %[old2], %[oldval2]\n" \
" orr %[old1], %[old1], %[old2]") \
- : [old1] "+r" (x0), [old2] "+r" (x1), \
+ : [old1] "+&r" (x0), [old2] "+&r" (x1), \
[v] "+Q" (*(unsigned long *)ptr) \
: [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4), \
[oldval1] "r" (oldval1), [oldval2] "r" (oldval2) \
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index c00c62e..1a037b9 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -34,7 +34,6 @@
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
-typedef s32 compat_time_t;
typedef s32 compat_clock_t;
typedef s32 compat_pid_t;
typedef u16 __compat_uid_t;
@@ -66,16 +65,6 @@ typedef u32 compat_ulong_t;
typedef u64 compat_u64;
typedef u32 compat_uptr_t;
-struct compat_timespec {
- compat_time_t tv_sec;
- s32 tv_nsec;
-};
-
-struct compat_timeval {
- compat_time_t tv_sec;
- s32 tv_usec;
-};
-
struct compat_stat {
#ifdef __AARCH64EB__
short st_dev;
@@ -192,10 +181,10 @@ struct compat_ipc64_perm {
struct compat_semid64_ds {
struct compat_ipc64_perm sem_perm;
- compat_time_t sem_otime;
- compat_ulong_t __unused1;
- compat_time_t sem_ctime;
- compat_ulong_t __unused2;
+ compat_ulong_t sem_otime;
+ compat_ulong_t sem_otime_high;
+ compat_ulong_t sem_ctime;
+ compat_ulong_t sem_ctime_high;
compat_ulong_t sem_nsems;
compat_ulong_t __unused3;
compat_ulong_t __unused4;
@@ -203,12 +192,12 @@ struct compat_semid64_ds {
struct compat_msqid64_ds {
struct compat_ipc64_perm msg_perm;
- compat_time_t msg_stime;
- compat_ulong_t __unused1;
- compat_time_t msg_rtime;
- compat_ulong_t __unused2;
- compat_time_t msg_ctime;
- compat_ulong_t __unused3;
+ compat_ulong_t msg_stime;
+ compat_ulong_t msg_stime_high;
+ compat_ulong_t msg_rtime;
+ compat_ulong_t msg_rtime_high;
+ compat_ulong_t msg_ctime;
+ compat_ulong_t msg_ctime_high;
compat_ulong_t msg_cbytes;
compat_ulong_t msg_qnum;
compat_ulong_t msg_qbytes;
@@ -221,12 +210,12 @@ struct compat_msqid64_ds {
struct compat_shmid64_ds {
struct compat_ipc64_perm shm_perm;
compat_size_t shm_segsz;
- compat_time_t shm_atime;
- compat_ulong_t __unused1;
- compat_time_t shm_dtime;
- compat_ulong_t __unused2;
- compat_time_t shm_ctime;
- compat_ulong_t __unused3;
+ compat_ulong_t shm_atime;
+ compat_ulong_t shm_atime_high;
+ compat_ulong_t shm_dtime;
+ compat_ulong_t shm_dtime_high;
+ compat_ulong_t shm_ctime;
+ compat_ulong_t shm_ctime_high;
compat_pid_t shm_cpid;
compat_pid_t shm_lpid;
compat_ulong_t shm_nattch;
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 30014a9..ea690b3 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -75,6 +75,7 @@
#define ARM_CPU_IMP_CAVIUM 0x43
#define ARM_CPU_IMP_BRCM 0x42
#define ARM_CPU_IMP_QCOM 0x51
+#define ARM_CPU_IMP_NVIDIA 0x4E
#define ARM_CPU_PART_AEM_V8 0xD0F
#define ARM_CPU_PART_FOUNDATION 0xD00
@@ -99,6 +100,9 @@
#define QCOM_CPU_PART_FALKOR 0xC00
#define QCOM_CPU_PART_KRYO 0x200
+#define NVIDIA_CPU_PART_DENVER 0x003
+#define NVIDIA_CPU_PART_CARMEL 0x004
+
#define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
#define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
#define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
@@ -114,6 +118,8 @@
#define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
#define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR)
#define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
+#define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER)
+#define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
#ifndef __ASSEMBLY__
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 23b33e8..1dab3a9 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -333,7 +333,7 @@ static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
} else {
u64 sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
sctlr |= (1 << 25);
- vcpu_write_sys_reg(vcpu, SCTLR_EL1, sctlr);
+ vcpu_write_sys_reg(vcpu, sctlr, SCTLR_EL1);
}
}
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index ab46bc7..469de8a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -75,6 +75,9 @@ struct kvm_arch {
/* Interrupt controller */
struct vgic_dist vgic;
+
+ /* Mandated version of PSCI */
+ u32 psci_version;
};
#define KVM_NR_MEM_OBJS 40
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 0821109..6128992 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -360,6 +360,22 @@ static inline unsigned int kvm_get_vmid_bits(void)
return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8;
}
+/*
+ * We are not in the kvm->srcu critical section most of the time, so we take
+ * the SRCU read lock here. Since we copy the data from the user page, we
+ * can immediately drop the lock again.
+ */
+static inline int kvm_read_guest_lock(struct kvm *kvm,
+ gpa_t gpa, void *data, unsigned long len)
+{
+ int srcu_idx = srcu_read_lock(&kvm->srcu);
+ int ret = kvm_read_guest(kvm, gpa, data, len);
+
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+ return ret;
+}
+
#ifdef CONFIG_KVM_INDIRECT_VECTORS
/*
* EL2 vectors can be mapped and rerouted in a number of ways,
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index b6dbbe3..97d0ef1 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -39,7 +39,7 @@ struct mod_arch_specific {
u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela,
Elf64_Sym *sym);
-u64 module_emit_adrp_veneer(struct module *mod, void *loc, u64 val);
+u64 module_emit_veneer_for_adrp(struct module *mod, void *loc, u64 val);
#ifdef CONFIG_RANDOMIZE_BASE
extern u64 module_alloc_base;
diff --git a/arch/arm64/include/asm/pci.h b/arch/arm64/include/asm/pci.h
index 8747f7c..9e69068 100644
--- a/arch/arm64/include/asm/pci.h
+++ b/arch/arm64/include/asm/pci.h
@@ -18,11 +18,6 @@
#define pcibios_assign_all_busses() \
(pci_has_flag(PCI_REASSIGN_ALL_BUS))
-/*
- * PCI address space differs from physical memory address space
- */
-#define PCI_DMA_BUS_IS_PHYS (0)
-
#define ARCH_GENERIC_PCI_MMAP_RESOURCE 1
extern int isa_dma_bridge_buggy;
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 7e2c27e..7c4c8f3 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -230,7 +230,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
}
}
-extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
+extern void __sync_icache_dcache(pte_t pteval);
/*
* PTE bits configuration in the presence of hardware Dirty Bit Management
@@ -253,7 +253,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t old_pte;
if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
- __sync_icache_dcache(pte, addr);
+ __sync_icache_dcache(pte);
/*
* If the existing pte is valid, check for potential race with
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index ebdae15..26c5bd7 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -122,11 +122,6 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
- /*
- * Ensure prior spin_lock operations to other locks have completed
- * on this CPU before we test whether "lock" is locked.
- */
- smp_mb(); /* ^^^ */
return !arch_spin_value_unlocked(READ_ONCE(*lock));
}
diff --git a/arch/arm64/include/asm/stat.h b/arch/arm64/include/asm/stat.h
index 15e3559..eab7380 100644
--- a/arch/arm64/include/asm/stat.h
+++ b/arch/arm64/include/asm/stat.h
@@ -20,6 +20,7 @@
#ifdef CONFIG_COMPAT
+#include <linux/compat_time.h>
#include <asm/compat.h>
/*
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 9abbf30..04b3256 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -206,6 +206,12 @@ struct kvm_arch_memory_slot {
#define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2)
#define KVM_REG_ARM_TIMER_CVAL ARM64_SYS_REG(3, 3, 14, 0, 2)
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
+ KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0)
+
/* Device Control API: ARM VGIC */
#define KVM_DEV_ARM_VGIC_GRP_ADDR 0
#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index 66be504..d894a20 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -75,3 +75,11 @@ NOKPROBE_SYMBOL(_mcount);
/* arm-smccc */
EXPORT_SYMBOL(__arm_smccc_smc);
EXPORT_SYMBOL(__arm_smccc_hvc);
+
+ /* tishift.S */
+extern long long __ashlti3(long long a, int b);
+EXPORT_SYMBOL(__ashlti3);
+extern long long __ashrti3(long long a, int b);
+EXPORT_SYMBOL(__ashrti3);
+extern long long __lshrti3(long long a, int b);
+EXPORT_SYMBOL(__lshrti3);
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index a900bef..e4a1182 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -316,6 +316,7 @@ static const struct midr_range arm64_bp_harden_smccc_cpus[] = {
MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1),
MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR),
+ MIDR_ALL_VERSIONS(MIDR_NVIDIA_DENVER),
{},
};
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 536d572..9d1b06d 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -868,6 +868,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
static const struct midr_range kpti_safe_list[] = {
MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
+ { /* sentinel */ }
};
char const *str = "command line option";
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 87a3536..4bcdd03 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -882,7 +882,7 @@ asmlinkage void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
si_code = FPE_FLTRES;
}
- memset(&info, 0, sizeof(info));
+ clear_siginfo(&info);
info.si_signo = SIGFPE;
info.si_code = si_code;
info.si_addr = (void __user *)instruction_pointer(regs);
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 74bb56f..413dbe5 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -30,7 +30,6 @@
#include <linux/smp.h>
#include <linux/uaccess.h>
-#include <asm/compat.h>
#include <asm/current.h>
#include <asm/debug-monitors.h>
#include <asm/hw_breakpoint.h>
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index fa363728..f0690c2 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -43,7 +43,7 @@ u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela,
}
#ifdef CONFIG_ARM64_ERRATUM_843419
-u64 module_emit_adrp_veneer(struct module *mod, void *loc, u64 val)
+u64 module_emit_veneer_for_adrp(struct module *mod, void *loc, u64 val)
{
struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core :
&mod->arch.init;
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 719fde8..155fd91 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -215,7 +215,7 @@ static int reloc_insn_adrp(struct module *mod, __le32 *place, u64 val)
insn &= ~BIT(31);
} else {
/* out of range for ADR -> emit a veneer */
- val = module_emit_adrp_veneer(mod, place, val & ~0xfff);
+ val = module_emit_veneer_for_adrp(mod, place, val & ~0xfff);
if (!val)
return -ENOEXEC;
insn = aarch64_insn_gen_branch_imm((u64)place, val,
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 1d091d0..0bbac61 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -1,11 +1,11 @@
// SPDX-License-Identifier: GPL-2.0
+#include <linux/compat.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/perf_event.h>
#include <linux/bug.h>
#include <linux/sched/task_stack.h>
-#include <asm/compat.h>
#include <asm/perf_regs.h>
#include <asm/ptrace.h>
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 71d99af..7ff81fe 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -25,6 +25,7 @@
#include <linux/sched/signal.h>
#include <linux/sched/task_stack.h>
#include <linux/mm.h>
+#include <linux/nospec.h>
#include <linux/smp.h>
#include <linux/ptrace.h>
#include <linux/user.h>
@@ -249,15 +250,20 @@ static struct perf_event *ptrace_hbp_get_event(unsigned int note_type,
switch (note_type) {
case NT_ARM_HW_BREAK:
- if (idx < ARM_MAX_BRP)
- bp = tsk->thread.debug.hbp_break[idx];
+ if (idx >= ARM_MAX_BRP)
+ goto out;
+ idx = array_index_nospec(idx, ARM_MAX_BRP);
+ bp = tsk->thread.debug.hbp_break[idx];
break;
case NT_ARM_HW_WATCH:
- if (idx < ARM_MAX_WRP)
- bp = tsk->thread.debug.hbp_watch[idx];
+ if (idx >= ARM_MAX_WRP)
+ goto out;
+ idx = array_index_nospec(idx, ARM_MAX_WRP);
+ bp = tsk->thread.debug.hbp_watch[idx];
break;
}
+out:
return bp;
}
@@ -1458,9 +1464,7 @@ static int compat_ptrace_gethbpregs(struct task_struct *tsk, compat_long_t num,
{
int ret;
u32 kdata;
- mm_segment_t old_fs = get_fs();
- set_fs(KERNEL_DS);
/* Watchpoint */
if (num < 0) {
ret = compat_ptrace_hbp_get(NT_ARM_HW_WATCH, tsk, num, &kdata);
@@ -1471,7 +1475,6 @@ static int compat_ptrace_gethbpregs(struct task_struct *tsk, compat_long_t num,
} else {
ret = compat_ptrace_hbp_get(NT_ARM_HW_BREAK, tsk, num, &kdata);
}
- set_fs(old_fs);
if (!ret)
ret = put_user(kdata, data);
@@ -1484,7 +1487,6 @@ static int compat_ptrace_sethbpregs(struct task_struct *tsk, compat_long_t num,
{
int ret;
u32 kdata = 0;
- mm_segment_t old_fs = get_fs();
if (num == 0)
return 0;
@@ -1493,12 +1495,10 @@ static int compat_ptrace_sethbpregs(struct task_struct *tsk, compat_long_t num,
if (ret)
return ret;
- set_fs(KERNEL_DS);
if (num < 0)
ret = compat_ptrace_hbp_set(NT_ARM_HW_WATCH, tsk, num, &kdata);
else
ret = compat_ptrace_hbp_set(NT_ARM_HW_BREAK, tsk, num, &kdata);
- set_fs(old_fs);
return ret;
}
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 93ab57d..a610982 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -112,6 +112,7 @@ long compat_arm_syscall(struct pt_regs *regs)
break;
}
+ clear_siginfo(&info);
info.si_signo = SIGILL;
info.si_errno = 0;
info.si_code = ILL_ILLTRP;
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index ba964da..d399d45 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -277,7 +277,8 @@ void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size)
* If we were single stepping, we want to get the step exception after
* we return from the trap.
*/
- user_fastforward_single_step(current);
+ if (user_mode(regs))
+ user_fastforward_single_step(current);
}
static LIST_HEAD(undef_hook);
@@ -366,7 +367,7 @@ void force_signal_inject(int signal, int code, unsigned long address)
}
/* Force signals we don't understand to SIGKILL */
- if (WARN_ON(signal != SIGKILL ||
+ if (WARN_ON(signal != SIGKILL &&
siginfo_layout(signal, code) != SIL_FAULT)) {
signal = SIGKILL;
}
@@ -634,6 +635,7 @@ asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
siginfo_t info;
void __user *pc = (void __user *)instruction_pointer(regs);
+ clear_siginfo(&info);
info.si_signo = SIGILL;
info.si_errno = 0;
info.si_code = ILL_ILLOPC;
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 959e50d..56a0260 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -25,6 +25,7 @@
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
+#include <kvm/arm_psci.h>
#include <asm/cputype.h>
#include <linux/uaccess.h>
#include <asm/kvm.h>
@@ -205,7 +206,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
{
return num_core_regs() + kvm_arm_num_sys_reg_descs(vcpu)
- + NUM_TIMER_REGS;
+ + kvm_arm_get_fw_num_regs(vcpu) + NUM_TIMER_REGS;
}
/**
@@ -225,6 +226,11 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
uindices++;
}
+ ret = kvm_arm_copy_fw_reg_indices(vcpu, uindices);
+ if (ret)
+ return ret;
+ uindices += kvm_arm_get_fw_num_regs(vcpu);
+
ret = copy_timer_indices(vcpu, uindices);
if (ret)
return ret;
@@ -243,6 +249,9 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
return get_core_reg(vcpu, reg);
+ if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
+ return kvm_arm_get_fw_reg(vcpu, reg);
+
if (is_timer_reg(reg->id))
return get_timer_reg(vcpu, reg);
@@ -259,6 +268,9 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
return set_core_reg(vcpu, reg);
+ if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
+ return kvm_arm_set_fw_reg(vcpu, reg);
+
if (is_timer_reg(reg->id))
return set_timer_reg(vcpu, reg);
diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
index 86801b6..39be799 100644
--- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
+++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
@@ -18,11 +18,20 @@
#include <linux/compiler.h>
#include <linux/irqchip/arm-gic.h>
#include <linux/kvm_host.h>
+#include <linux/swab.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
+static bool __hyp_text __is_be(struct kvm_vcpu *vcpu)
+{
+ if (vcpu_mode_is_32bit(vcpu))
+ return !!(read_sysreg_el2(spsr) & COMPAT_PSR_E_BIT);
+
+ return !!(read_sysreg(SCTLR_EL1) & SCTLR_ELx_EE);
+}
+
/*
* __vgic_v2_perform_cpuif_access -- perform a GICV access on behalf of the
* guest.
@@ -64,14 +73,19 @@ int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
addr += fault_ipa - vgic->vgic_cpu_base;
if (kvm_vcpu_dabt_iswrite(vcpu)) {
- u32 data = vcpu_data_guest_to_host(vcpu,
- vcpu_get_reg(vcpu, rd),
- sizeof(u32));
+ u32 data = vcpu_get_reg(vcpu, rd);
+ if (__is_be(vcpu)) {
+ /* guest pre-swabbed data, undo this for writel() */
+ data = swab32(data);
+ }
writel_relaxed(data, addr);
} else {
u32 data = readl_relaxed(addr);
- vcpu_set_reg(vcpu, rd, vcpu_data_host_to_guest(vcpu, data,
- sizeof(u32)));
+ if (__is_be(vcpu)) {
+ /* guest expects swabbed data */
+ data = swab32(data);
+ }
+ vcpu_set_reg(vcpu, rd, data);
}
return 1;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 806b0b12..6e3b969 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -996,14 +996,12 @@ static u64 read_id_reg(struct sys_reg_desc const *r, bool raz)
if (id == SYS_ID_AA64PFR0_EL1) {
if (val & (0xfUL << ID_AA64PFR0_SVE_SHIFT))
- pr_err_once("kvm [%i]: SVE unsupported for guests, suppressing\n",
- task_pid_nr(current));
+ kvm_debug("SVE unsupported for guests, suppressing\n");
val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
} else if (id == SYS_ID_AA64MMFR1_EL1) {
if (val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT))
- pr_err_once("kvm [%i]: LORegions unsupported for guests, suppressing\n",
- task_pid_nr(current));
+ kvm_debug("LORegions unsupported for guests, suppressing\n");
val &= ~(0xfUL << ID_AA64MMFR1_LOR_SHIFT);
}
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 0ead8a1..137710f 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -19,5 +19,9 @@
-fcall-saved-x13 -fcall-saved-x14 -fcall-saved-x15 \
-fcall-saved-x18 -fomit-frame-pointer
CFLAGS_REMOVE_atomic_ll_sc.o := -pg
+GCOV_PROFILE_atomic_ll_sc.o := n
+KASAN_SANITIZE_atomic_ll_sc.o := n
+KCOV_INSTRUMENT_atomic_ll_sc.o := n
+UBSAN_SANITIZE_atomic_ll_sc.o := n
lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o
diff --git a/arch/arm64/lib/tishift.S b/arch/arm64/lib/tishift.S
index d3db9b2..0fdff97 100644
--- a/arch/arm64/lib/tishift.S
+++ b/arch/arm64/lib/tishift.S
@@ -1,17 +1,6 @@
-/*
- * Copyright (C) 2017 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ * Copyright (C) 2017-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
*/
#include <linux/linkage.h>
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index a96ec01..db01f27 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -508,16 +508,6 @@ static int __init arm64_dma_init(void)
}
arch_initcall(arm64_dma_init);
-#define PREALLOC_DMA_DEBUG_ENTRIES 4096
-
-static int __init dma_debug_do_init(void)
-{
- dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
- return 0;
-}
-fs_initcall(dma_debug_do_init);
-
-
#ifdef CONFIG_IOMMU_DMA
#include <linux/dma-iommu.h>
#include <linux/platform_device.h>
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 4165485..576f151 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -293,6 +293,57 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
static void __do_user_fault(struct siginfo *info, unsigned int esr)
{
current->thread.fault_address = (unsigned long)info->si_addr;
+
+ /*
+ * If the faulting address is in the kernel, we must sanitize the ESR.
+ * From userspace's point of view, kernel-only mappings don't exist
+ * at all, so we report them as level 0 translation faults.
+ * (This is not quite the way that "no mapping there at all" behaves:
+ * an alignment fault not caused by the memory type would take
+ * precedence over translation fault for a real access to empty
+ * space. Unfortunately we can't easily distinguish "alignment fault
+ * not caused by memory type" from "alignment fault caused by memory
+ * type", so we ignore this wrinkle and just return the translation
+ * fault.)
+ */
+ if (current->thread.fault_address >= TASK_SIZE) {
+ switch (ESR_ELx_EC(esr)) {
+ case ESR_ELx_EC_DABT_LOW:
+ /*
+ * These bits provide only information about the
+ * faulting instruction, which userspace knows already.
+ * We explicitly clear bits which are architecturally
+ * RES0 in case they are given meanings in future.
+ * We always report the ESR as if the fault was taken
+ * to EL1 and so ISV and the bits in ISS[23:14] are
+ * clear. (In fact it always will be a fault to EL1.)
+ */
+ esr &= ESR_ELx_EC_MASK | ESR_ELx_IL |
+ ESR_ELx_CM | ESR_ELx_WNR;
+ esr |= ESR_ELx_FSC_FAULT;
+ break;
+ case ESR_ELx_EC_IABT_LOW:
+ /*
+ * Claim a level 0 translation fault.
+ * All other bits are architecturally RES0 for faults
+ * reported with that DFSC value, so we clear them.
+ */
+ esr &= ESR_ELx_EC_MASK | ESR_ELx_IL;
+ esr |= ESR_ELx_FSC_FAULT;
+ break;
+ default:
+ /*
+ * This should never happen (entry.S only brings us
+ * into this code for insn and data aborts from a lower
+ * exception level). Fail safe by not providing an ESR
+ * context record at all.
+ */
+ WARN(1, "ESR 0x%x is not DABT or IABT from EL0\n", esr);
+ esr = 0;
+ break;
+ }
+ }
+
current->thread.fault_code = esr;
arm64_force_sig_info(info, esr_to_fault_info(esr)->name, current);
}
@@ -305,11 +356,12 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re
*/
if (user_mode(regs)) {
const struct fault_info *inf = esr_to_fault_info(esr);
- struct siginfo si = {
- .si_signo = inf->sig,
- .si_code = inf->code,
- .si_addr = (void __user *)addr,
- };
+ struct siginfo si;
+
+ clear_siginfo(&si);
+ si.si_signo = inf->sig;
+ si.si_code = inf->code;
+ si.si_addr = (void __user *)addr;
__do_user_fault(&si, esr);
} else {
@@ -583,6 +635,7 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
nmi_exit();
}
+ clear_siginfo(&info);
info.si_signo = inf->sig;
info.si_errno = 0;
info.si_code = inf->code;
@@ -687,6 +740,7 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
show_pte(addr);
}
+ clear_siginfo(&info);
info.si_signo = inf->sig;
info.si_errno = 0;
info.si_code = inf->code;
@@ -729,6 +783,7 @@ asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
local_irq_enable();
}
+ clear_siginfo(&info);
info.si_signo = SIGBUS;
info.si_errno = 0;
info.si_code = BUS_ADRALN;
@@ -772,7 +827,6 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
struct pt_regs *regs)
{
const struct fault_info *inf = debug_fault_info + DBG_ESR_EVT(esr);
- struct siginfo info;
int rv;
/*
@@ -788,6 +842,9 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
if (!inf->fn(addr, esr, regs)) {
rv = 1;
} else {
+ struct siginfo info;
+
+ clear_siginfo(&info);
info.si_signo = inf->sig;
info.si_errno = 0;
info.si_code = inf->code;
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index e36ed50..1059884 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -58,7 +58,7 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
flush_ptrace_access(vma, page, uaddr, dst, len);
}
-void __sync_icache_dcache(pte_t pte, unsigned long addr)
+void __sync_icache_dcache(pte_t pte)
{
struct page *page = pte_page(pte);
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 9f3c47a..1b18b47 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -646,8 +646,10 @@ static int keep_initrd __initdata;
void __init free_initrd_mem(unsigned long start, unsigned long end)
{
- if (!keep_initrd)
+ if (!keep_initrd) {
free_reserved_area((void *)start, (void *)end, 0, "initrd");
+ memblock_free(__virt_to_phys(start), end - start);
+ }
}
static int __init keepinitrd_setup(char *__unused)
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index dabfc1e..1214587 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -204,7 +204,7 @@ void __init kasan_init(void)
clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
kasan_map_populate(kimg_shadow_start, kimg_shadow_end,
- pfn_to_nid(virt_to_pfn(lm_alias(_text))));
+ early_pfn_to_nid(virt_to_pfn(lm_alias(_text))));
kasan_populate_zero_shadow((void *)KASAN_SHADOW_START,
(void *)mod_shadow_start);
@@ -224,7 +224,7 @@ void __init kasan_init(void)
kasan_map_populate((unsigned long)kasan_mem_to_shadow(start),
(unsigned long)kasan_mem_to_shadow(end),
- pfn_to_nid(virt_to_pfn(start)));
+ early_pfn_to_nid(virt_to_pfn(start)));
}
/*
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 2dbb2c9..493ff75 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -933,13 +933,15 @@ int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot)
{
pgprot_t sect_prot = __pgprot(PUD_TYPE_SECT |
pgprot_val(mk_sect_prot(prot)));
+ pud_t new_pud = pfn_pud(__phys_to_pfn(phys), sect_prot);
- /* ioremap_page_range doesn't honour BBM */
- if (pud_present(READ_ONCE(*pudp)))
+ /* Only allow permission changes for now */
+ if (!pgattr_change_is_safe(READ_ONCE(pud_val(*pudp)),
+ pud_val(new_pud)))
return 0;
BUG_ON(phys & ~PUD_MASK);
- set_pud(pudp, pfn_pud(__phys_to_pfn(phys), sect_prot));
+ set_pud(pudp, new_pud);
return 1;
}
@@ -947,13 +949,15 @@ int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot)
{
pgprot_t sect_prot = __pgprot(PMD_TYPE_SECT |
pgprot_val(mk_sect_prot(prot)));
+ pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), sect_prot);
- /* ioremap_page_range doesn't honour BBM */
- if (pmd_present(READ_ONCE(*pmdp)))
+ /* Only allow permission changes for now */
+ if (!pgattr_change_is_safe(READ_ONCE(pmd_val(*pmdp)),
+ pmd_val(new_pmd)))
return 0;
BUG_ON(phys & ~PMD_MASK);
- set_pmd(pmdp, pfn_pmd(__phys_to_pfn(phys), sect_prot));
+ set_pmd(pmdp, new_pmd);
return 1;
}
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index c6b4dd1..bf598556 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -6,11 +6,13 @@
config C6X
def_bool y
+ select ARCH_HAS_SYNC_DMA_FOR_CPU
+ select ARCH_HAS_SYNC_DMA_FOR_DEVICE
select CLKDEV_LOOKUP
+ select DMA_NONCOHERENT_OPS
select GENERIC_ATOMIC64
select GENERIC_IRQ_SHOW
select HAVE_ARCH_TRACEHOOK
- select HAVE_DMA_API_DEBUG
select HAVE_MEMBLOCK
select SPARSE_IRQ
select IRQ_DOMAIN
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index fd4c840..33a2c94 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -1,10 +1,12 @@
generic-y += atomic.h
generic-y += barrier.h
generic-y += bugs.h
+generic-y += compat.h
generic-y += current.h
generic-y += device.h
generic-y += div64.h
generic-y += dma.h
+generic-y += dma-mapping.h
generic-y += emergency-restart.h
generic-y += exec.h
generic-y += extable.h
diff --git a/arch/c6x/include/asm/dma-mapping.h b/arch/c6x/include/asm/dma-mapping.h
deleted file mode 100644
index 05daf10..0000000
--- a/arch/c6x/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * Port on Texas Instruments TMS320C6x architecture
- *
- * Copyright (C) 2004, 2009, 2010, 2011 Texas Instruments Incorporated
- * Author: Aurelien Jacquiot <aurelien.jacquiot@ti.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
-#ifndef _ASM_C6X_DMA_MAPPING_H
-#define _ASM_C6X_DMA_MAPPING_H
-
-extern const struct dma_map_ops c6x_dma_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
- return &c6x_dma_ops;
-}
-
-extern void coherent_mem_init(u32 start, u32 size);
-void *c6x_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
- gfp_t gfp, unsigned long attrs);
-void c6x_dma_free(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_handle, unsigned long attrs);
-
-#endif /* _ASM_C6X_DMA_MAPPING_H */
diff --git a/arch/c6x/include/asm/setup.h b/arch/c6x/include/asm/setup.h
index 852afb2..350f34d 100644
--- a/arch/c6x/include/asm/setup.h
+++ b/arch/c6x/include/asm/setup.h
@@ -28,5 +28,7 @@ extern unsigned char c6x_fuse_mac[6];
extern void machine_init(unsigned long dt_ptr);
extern void time_init(void);
+extern void coherent_mem_init(u32 start, u32 size);
+
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_C6X_SETUP_H */
diff --git a/arch/c6x/kernel/Makefile b/arch/c6x/kernel/Makefile
index 02f340d..fbe7417 100644
--- a/arch/c6x/kernel/Makefile
+++ b/arch/c6x/kernel/Makefile
@@ -8,6 +8,6 @@
obj-y := process.o traps.o irq.o signal.o ptrace.o
obj-y += setup.o sys_c6x.o time.o devicetree.o
obj-y += switch_to.o entry.o vectors.o c6x_ksyms.o
-obj-y += soc.o dma.o
+obj-y += soc.o
obj-$(CONFIG_MODULES) += module.o
diff --git a/arch/c6x/kernel/dma.c b/arch/c6x/kernel/dma.c
deleted file mode 100644
index 9fff8be..0000000
--- a/arch/c6x/kernel/dma.c
+++ /dev/null
@@ -1,149 +0,0 @@
-/*
- * Copyright (C) 2011 Texas Instruments Incorporated
- * Author: Mark Salter <msalter@redhat.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/module.h>
-#include <linux/dma-mapping.h>
-#include <linux/mm.h>
-#include <linux/mm_types.h>
-#include <linux/scatterlist.h>
-
-#include <asm/cacheflush.h>
-
-static void c6x_dma_sync(dma_addr_t handle, size_t size,
- enum dma_data_direction dir)
-{
- unsigned long paddr = handle;
-
- BUG_ON(!valid_dma_direction(dir));
-
- switch (dir) {
- case DMA_FROM_DEVICE:
- L2_cache_block_invalidate(paddr, paddr + size);
- break;
- case DMA_TO_DEVICE:
- L2_cache_block_writeback(paddr, paddr + size);
- break;
- case DMA_BIDIRECTIONAL:
- L2_cache_block_writeback_invalidate(paddr, paddr + size);
- break;
- default:
- break;
- }
-}
-
-static dma_addr_t c6x_dma_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- dma_addr_t handle = virt_to_phys(page_address(page) + offset);
-
- if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- c6x_dma_sync(handle, size, dir);
-
- return handle;
-}
-
-static void c6x_dma_unmap_page(struct device *dev, dma_addr_t handle,
- size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
- if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- c6x_dma_sync(handle, size, dir);
-}
-
-static int c6x_dma_map_sg(struct device *dev, struct scatterlist *sglist,
- int nents, enum dma_data_direction dir, unsigned long attrs)
-{
- struct scatterlist *sg;
- int i;
-
- for_each_sg(sglist, sg, nents, i) {
- sg->dma_address = sg_phys(sg);
- if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- c6x_dma_sync(sg->dma_address, sg->length, dir);
- }
-
- return nents;
-}
-
-static void c6x_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
- int nents, enum dma_data_direction dir, unsigned long attrs)
-{
- struct scatterlist *sg;
- int i;
-
- if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
- return;
-
- for_each_sg(sglist, sg, nents, i)
- c6x_dma_sync(sg_dma_address(sg), sg->length, dir);
-}
-
-static void c6x_dma_sync_single_for_cpu(struct device *dev, dma_addr_t handle,
- size_t size, enum dma_data_direction dir)
-{
- c6x_dma_sync(handle, size, dir);
-
-}
-
-static void c6x_dma_sync_single_for_device(struct device *dev,
- dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
- c6x_dma_sync(handle, size, dir);
-
-}
-
-static void c6x_dma_sync_sg_for_cpu(struct device *dev,
- struct scatterlist *sglist, int nents,
- enum dma_data_direction dir)
-{
- struct scatterlist *sg;
- int i;
-
- for_each_sg(sglist, sg, nents, i)
- c6x_dma_sync_single_for_cpu(dev, sg_dma_address(sg),
- sg->length, dir);
-
-}
-
-static void c6x_dma_sync_sg_for_device(struct device *dev,
- struct scatterlist *sglist, int nents,
- enum dma_data_direction dir)
-{
- struct scatterlist *sg;
- int i;
-
- for_each_sg(sglist, sg, nents, i)
- c6x_dma_sync_single_for_device(dev, sg_dma_address(sg),
- sg->length, dir);
-
-}
-
-const struct dma_map_ops c6x_dma_ops = {
- .alloc = c6x_dma_alloc,
- .free = c6x_dma_free,
- .map_page = c6x_dma_map_page,
- .unmap_page = c6x_dma_unmap_page,
- .map_sg = c6x_dma_map_sg,
- .unmap_sg = c6x_dma_unmap_sg,
- .sync_single_for_device = c6x_dma_sync_single_for_device,
- .sync_single_for_cpu = c6x_dma_sync_single_for_cpu,
- .sync_sg_for_device = c6x_dma_sync_sg_for_device,
- .sync_sg_for_cpu = c6x_dma_sync_sg_for_cpu,
-};
-EXPORT_SYMBOL(c6x_dma_ops);
-
-/* Number of entries preallocated for DMA-API debugging */
-#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-
-static int __init dma_init(void)
-{
- dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
-
- return 0;
-}
-fs_initcall(dma_init);
diff --git a/arch/c6x/kernel/traps.c b/arch/c6x/kernel/traps.c
index 4c1d4b8..5c60aea 100644
--- a/arch/c6x/kernel/traps.c
+++ b/arch/c6x/kernel/traps.c
@@ -244,7 +244,6 @@ static struct exception_info eexcept_table[128] = {
static void do_trap(struct exception_info *except_info, struct pt_regs *regs)
{
unsigned long addr = instruction_pointer(regs);
- siginfo_t info;
if (except_info->code != TRAP_BRKPT)
pr_err("TRAP: %s PC[0x%lx] signo[%d] code[%d]\n",
@@ -253,12 +252,8 @@ static void do_trap(struct exception_info *except_info, struct pt_regs *regs)
die_if_kernel(except_info->kernel_str, regs, addr);
- info.si_signo = except_info->signo;
- info.si_errno = 0;
- info.si_code = except_info->code;
- info.si_addr = (void __user *)addr;
-
- force_sig_info(except_info->signo, &info, current);
+ force_sig_fault(except_info->signo, except_info->code,
+ (void __user *)addr, current);
}
/*
diff --git a/arch/c6x/mm/dma-coherent.c b/arch/c6x/mm/dma-coherent.c
index 95e38ad..d0a8e0c 100644
--- a/arch/c6x/mm/dma-coherent.c
+++ b/arch/c6x/mm/dma-coherent.c
@@ -19,10 +19,12 @@
#include <linux/bitops.h>
#include <linux/module.h>
#include <linux/interrupt.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
#include <linux/memblock.h>
+#include <asm/cacheflush.h>
#include <asm/page.h>
+#include <asm/setup.h>
/*
* DMA coherent memory management, can be redefined using the memdma=
@@ -73,7 +75,7 @@ static void __free_dma_pages(u32 addr, int order)
* Allocate DMA coherent memory space and return both the kernel
* virtual and DMA address for that space.
*/
-void *c6x_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
gfp_t gfp, unsigned long attrs)
{
u32 paddr;
@@ -98,7 +100,7 @@ void *c6x_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
/*
* Free DMA coherent memory as defined by the above mapping.
*/
-void c6x_dma_free(struct device *dev, size_t size, void *vaddr,
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_handle, unsigned long attrs)
{
int order;
@@ -139,3 +141,35 @@ void __init coherent_mem_init(phys_addr_t start, u32 size)
dma_bitmap = phys_to_virt(bitmap_phys);
memset(dma_bitmap, 0, dma_pages * PAGE_SIZE);
}
+
+static void c6x_dma_sync(struct device *dev, phys_addr_t paddr, size_t size,
+ enum dma_data_direction dir)
+{
+ BUG_ON(!valid_dma_direction(dir));
+
+ switch (dir) {
+ case DMA_FROM_DEVICE:
+ L2_cache_block_invalidate(paddr, paddr + size);
+ break;
+ case DMA_TO_DEVICE:
+ L2_cache_block_writeback(paddr, paddr + size);
+ break;
+ case DMA_BIDIRECTIONAL:
+ L2_cache_block_writeback_invalidate(paddr, paddr + size);
+ break;
+ default:
+ break;
+ }
+}
+
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir)
+{
+ return c6x_dma_sync(dev, paddr, size, dir);
+}
+
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir)
+{
+ return c6x_dma_sync(dev, paddr, size, dir);
+}
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
index 14bac06..a5d0b29 100644
--- a/arch/h8300/include/asm/Kbuild
+++ b/arch/h8300/include/asm/Kbuild
@@ -3,6 +3,7 @@
generic-y += bugs.h
generic-y += cacheflush.h
generic-y += checksum.h
+generic-y += compat.h
generic-y += current.h
generic-y += delay.h
generic-y += device.h
diff --git a/arch/h8300/include/asm/pci.h b/arch/h8300/include/asm/pci.h
index 7c9e55d..d4d345a 100644
--- a/arch/h8300/include/asm/pci.h
+++ b/arch/h8300/include/asm/pci.h
@@ -15,6 +15,4 @@ static inline void pcibios_penalize_isa_irq(int irq, int active)
/* We don't do dynamic PCI IRQ allocation */
}
-#define PCI_DMA_BUS_IS_PHYS (1)
-
#endif /* _ASM_H8300_PCI_H */
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 76d2f20..37adb20 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -19,6 +19,7 @@
select GENERIC_IRQ_SHOW
select HAVE_ARCH_KGDB
select HAVE_ARCH_TRACEHOOK
+ select NEED_SG_DMA_LENGTH
select NO_IOPORT_MAP
select GENERIC_IOMAP
select GENERIC_SMP_IDLE_THREAD
@@ -63,9 +64,6 @@
config GENERIC_IRQ_PROBE
def_bool y
-config NEED_SG_DMA_LENGTH
- def_bool y
-
config RWSEM_GENERIC_SPINLOCK
def_bool n
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index e9743f6..dd2fd9c 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -2,6 +2,7 @@
generic-y += barrier.h
generic-y += bug.h
generic-y += bugs.h
+generic-y += compat.h
generic-y += current.h
generic-y += device.h
generic-y += div64.h
diff --git a/arch/hexagon/include/asm/io.h b/arch/hexagon/include/asm/io.h
index 9e8621d..e17262a 100644
--- a/arch/hexagon/include/asm/io.h
+++ b/arch/hexagon/include/asm/io.h
@@ -216,6 +216,12 @@ static inline void memcpy_toio(volatile void __iomem *dst, const void *src,
memcpy((void *) dst, src, count);
}
+static inline void memset_io(volatile void __iomem *addr, int value,
+ size_t size)
+{
+ memset((void __force *)addr, value, size);
+}
+
#define PCI_IO_ADDR (volatile void __iomem *)
/*
diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c
index ad8347c..77459df 100644
--- a/arch/hexagon/kernel/dma.c
+++ b/arch/hexagon/kernel/dma.c
@@ -208,7 +208,6 @@ const struct dma_map_ops hexagon_dma_ops = {
.sync_single_for_cpu = hexagon_sync_single_for_cpu,
.sync_single_for_device = hexagon_sync_single_for_device,
.mapping_error = hexagon_mapping_error,
- .is_phys = 1,
};
void __init hexagon_dma_init(void)
diff --git a/arch/hexagon/kernel/traps.c b/arch/hexagon/kernel/traps.c
index 2942a92..91ee048 100644
--- a/arch/hexagon/kernel/traps.c
+++ b/arch/hexagon/kernel/traps.c
@@ -412,10 +412,6 @@ void do_trap0(struct pt_regs *regs)
case TRAP_DEBUG:
/* Trap0 0xdb is debug breakpoint */
if (user_mode(regs)) {
- struct siginfo info;
-
- info.si_signo = SIGTRAP;
- info.si_errno = 0;
/*
* Some architecures add some per-thread state
* to distinguish between breakpoint traps and
@@ -423,9 +419,8 @@ void do_trap0(struct pt_regs *regs)
* set the si_code value appropriately, or we
* may want to use a different trap0 flavor.
*/
- info.si_code = TRAP_BRKPT;
- info.si_addr = (void __user *) pt_elr(regs);
- force_sig_info(SIGTRAP, &info, current);
+ force_sig_fault(SIGTRAP, TRAP_BRKPT,
+ (void __user *) pt_elr(regs), current);
} else {
#ifdef CONFIG_KGDB
kgdb_handle_exception(pt_cause(regs), SIGTRAP,
diff --git a/arch/hexagon/lib/checksum.c b/arch/hexagon/lib/checksum.c
index 617506d..7cd0a22 100644
--- a/arch/hexagon/lib/checksum.c
+++ b/arch/hexagon/lib/checksum.c
@@ -199,3 +199,4 @@ csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
memcpy(dst, src, len);
return csum_partial(dst, len, sum);
}
+EXPORT_SYMBOL(csum_partial_copy_nocheck);
diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
index 3eec33c..933bbce 100644
--- a/arch/hexagon/mm/vm_fault.c
+++ b/arch/hexagon/mm/vm_fault.c
@@ -50,7 +50,7 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
- siginfo_t info;
+ int si_signo;
int si_code = SEGV_MAPERR;
int fault;
const struct exception_table_entry *fixup;
@@ -140,28 +140,22 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
* unable to fix up the page fault.
*/
if (fault & VM_FAULT_SIGBUS) {
- info.si_signo = SIGBUS;
- info.si_code = BUS_ADRERR;
+ si_signo = SIGBUS;
+ si_code = BUS_ADRERR;
}
/* Address is not in the memory map */
else {
- info.si_signo = SIGSEGV;
- info.si_code = SEGV_ACCERR;
+ si_signo = SIGSEGV;
+ si_code = SEGV_ACCERR;
}
- info.si_errno = 0;
- info.si_addr = (void __user *)address;
- force_sig_info(info.si_signo, &info, current);
+ force_sig_fault(si_signo, si_code, (void __user *)address, current);
return;
bad_area:
up_read(&mm->mmap_sem);
if (user_mode(regs)) {
- info.si_signo = SIGSEGV;
- info.si_errno = 0;
- info.si_code = si_code;
- info.si_addr = (void *)address;
- force_sig_info(info.si_signo, &info, current);
+ force_sig_fault(SIGSEGV, si_code, (void __user *)address, current);
return;
}
/* Kernel-mode fault falls through */
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index bbe12a0..792437d 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -29,7 +29,6 @@
select HAVE_FUNCTION_TRACER
select TTY
select HAVE_ARCH_TRACEHOOK
- select HAVE_DMA_API_DEBUG
select HAVE_MEMBLOCK
select HAVE_MEMBLOCK_NODE_MAP
select HAVE_VIRT_CPU_ACCOUNTING
@@ -54,6 +53,8 @@
select MODULES_USE_ELF_RELA
select ARCH_USE_CMPXCHG_LOCKREF
select HAVE_ARCH_AUDITSYSCALL
+ select NEED_DMA_MAP_STATE
+ select NEED_SG_DMA_LENGTH
default y
help
The Itanium Processor Family is Intel's 64-bit successor to
@@ -78,18 +79,6 @@
bool
default y
-config ARCH_DMA_ADDR_T_64BIT
- def_bool y
-
-config NEED_DMA_MAP_STATE
- def_bool y
-
-config NEED_SG_DMA_LENGTH
- def_bool y
-
-config SWIOTLB
- bool
-
config STACKTRACE_SUPPORT
def_bool y
@@ -146,7 +135,6 @@
bool "generic"
select NUMA
select ACPI_NUMA
- select DMA_DIRECT_OPS
select SWIOTLB
select PCI_MSI
help
@@ -167,7 +155,6 @@
config IA64_DIG
bool "DIG-compliant"
- select DMA_DIRECT_OPS
select SWIOTLB
config IA64_DIG_VTD
@@ -183,7 +170,6 @@
config IA64_HP_ZX1_SWIOTLB
bool "HP-zx1/sx1000 with software I/O TLB"
- select DMA_DIRECT_OPS
select SWIOTLB
help
Build a kernel that runs on HP zx1 and sx1000 systems even when they
@@ -207,7 +193,6 @@
bool "SGI-UV"
select NUMA
select ACPI_NUMA
- select DMA_DIRECT_OPS
select SWIOTLB
help
Selecting this option will optimize the kernel for use on UV based
@@ -218,7 +203,6 @@
config IA64_HP_SIM
bool "Ski-simulator"
- select DMA_DIRECT_OPS
select SWIOTLB
depends on !PM
@@ -397,7 +381,7 @@
Say Y to support efficient handling of discontiguous physical memory,
for architectures which are either NUMA (Non-Uniform Memory Access)
or have huge holes in the physical address space for other reasons.
- See <file:Documentation/vm/numa> for more.
+ See <file:Documentation/vm/numa.rst> for more.
config ARCH_FLATMEM_ENABLE
def_bool y
@@ -613,6 +597,3 @@
source "crypto/Kconfig"
source "lib/Kconfig"
-
-config IOMMU_HELPER
- def_bool (IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB || IA64_GENERIC || SWIOTLB)
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index aec4a33..ee5b652 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -1845,9 +1845,6 @@ static void ioc_init(unsigned long hpa, struct ioc *ioc)
ioc_resource_init(ioc);
ioc_sac_init(ioc);
- if ((long) ~iovp_mask > (long) ia64_max_iommu_merge_mask)
- ia64_max_iommu_merge_mask = ~iovp_mask;
-
printk(KERN_INFO PFX
"%s %d.%d HPA 0x%lx IOVA space %dMb at 0x%lx\n",
ioc->name, (ioc->rev >> 4) & 0xF, ioc->rev & 0xF,
@@ -1942,19 +1939,6 @@ static const struct seq_operations ioc_seq_ops = {
.show = ioc_show
};
-static int
-ioc_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &ioc_seq_ops);
-}
-
-static const struct file_operations ioc_fops = {
- .open = ioc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release
-};
-
static void __init
ioc_proc_init(void)
{
@@ -1964,7 +1948,7 @@ ioc_proc_init(void)
if (!dir)
return;
- proc_create(ioc_list->name, 0, dir, &ioc_fops);
+ proc_create_seq(ioc_list->name, 0, dir, &ioc_seq_ops);
}
#endif
diff --git a/arch/ia64/hp/sim/simserial.c b/arch/ia64/hp/sim/simserial.c
index a419ccf..663388a 100644
--- a/arch/ia64/hp/sim/simserial.c
+++ b/arch/ia64/hp/sim/simserial.c
@@ -435,19 +435,6 @@ static int rs_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int rs_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, rs_proc_show, NULL);
-}
-
-static const struct file_operations rs_proc_fops = {
- .owner = THIS_MODULE,
- .open = rs_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static const struct tty_operations hp_ops = {
.open = rs_open,
.close = rs_close,
@@ -462,7 +449,7 @@ static const struct tty_operations hp_ops = {
.unthrottle = rs_unthrottle,
.send_xchar = rs_send_xchar,
.hangup = rs_hangup,
- .proc_fops = &rs_proc_fops,
+ .proc_show = rs_proc_show,
};
static const struct tty_port_operations hp_port_ops = {
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index 6dd8678..557bbc8 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -1,3 +1,4 @@
+generic-y += compat.h
generic-y += exec.h
generic-y += irq_work.h
generic-y += mcs_spinlock.h
diff --git a/arch/ia64/include/asm/hardirq.h b/arch/ia64/include/asm/hardirq.h
index bdc4669..ccde7c2 100644
--- a/arch/ia64/include/asm/hardirq.h
+++ b/arch/ia64/include/asm/hardirq.h
@@ -13,7 +13,7 @@
#define __ARCH_IRQ_STAT 1
-#define local_softirq_pending() (local_cpu_data->softirq_pending)
+#define local_softirq_pending_ref ia64_cpu_info.softirq_pending
#include <linux/threads.h>
#include <linux/irq.h>
diff --git a/arch/ia64/include/asm/pci.h b/arch/ia64/include/asm/pci.h
index b1d04e8..780e874 100644
--- a/arch/ia64/include/asm/pci.h
+++ b/arch/ia64/include/asm/pci.h
@@ -30,23 +30,6 @@ struct pci_vector_struct {
#define PCIBIOS_MIN_IO 0x1000
#define PCIBIOS_MIN_MEM 0x10000000
-/*
- * PCI_DMA_BUS_IS_PHYS should be set to 1 if there is _necessarily_ a direct
- * correspondence between device bus addresses and CPU physical addresses.
- * Platforms with a hardware I/O MMU _must_ turn this off to suppress the
- * bounce buffer handling code in the block and network device layers.
- * Platforms with separate bus address spaces _must_ turn this off and provide
- * a device DMA mapping implementation that takes care of the necessary
- * address translation.
- *
- * For now, the ia64 platforms which may have separate/multiple bus address
- * spaces all have I/O MMUs which support the merging of physically
- * discontiguous buffers, so we can use that as the sole factor to determine
- * the setting of PCI_DMA_BUS_IS_PHYS.
- */
-extern unsigned long ia64_max_iommu_merge_mask;
-#define PCI_DMA_BUS_IS_PHYS (ia64_max_iommu_merge_mask == ~0UL)
-
#define HAVE_PCI_MMAP
#define ARCH_GENERIC_PCI_MMAP_RESOURCE
#define arch_can_pci_mmap_wc() 1
diff --git a/arch/ia64/include/uapi/asm/Kbuild b/arch/ia64/include/uapi/asm/Kbuild
index c0527cf..3982e67 100644
--- a/arch/ia64/include/uapi/asm/Kbuild
+++ b/arch/ia64/include/uapi/asm/Kbuild
@@ -2,5 +2,9 @@
include include/uapi/asm-generic/Kbuild.asm
generic-y += bpf_perf_event.h
+generic-y += ipcbuf.h
generic-y += kvm_para.h
+generic-y += msgbuf.h
generic-y += poll.h
+generic-y += sembuf.h
+generic-y += shmbuf.h
diff --git a/arch/ia64/include/uapi/asm/ipcbuf.h b/arch/ia64/include/uapi/asm/ipcbuf.h
deleted file mode 100644
index 90d6445..0000000
--- a/arch/ia64/include/uapi/asm/ipcbuf.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#include <asm-generic/ipcbuf.h>
diff --git a/arch/ia64/include/uapi/asm/msgbuf.h b/arch/ia64/include/uapi/asm/msgbuf.h
deleted file mode 100644
index aa25df9..0000000
--- a/arch/ia64/include/uapi/asm/msgbuf.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ASM_IA64_MSGBUF_H
-#define _ASM_IA64_MSGBUF_H
-
-/*
- * The msqid64_ds structure for IA-64 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 2 miscellaneous 64-bit values
- */
-
-struct msqid64_ds {
- struct ipc64_perm msg_perm;
- __kernel_time_t msg_stime; /* last msgsnd time */
- __kernel_time_t msg_rtime; /* last msgrcv time */
- __kernel_time_t msg_ctime; /* last change time */
- unsigned long msg_cbytes; /* current number of bytes on queue */
- unsigned long msg_qnum; /* number of messages in queue */
- unsigned long msg_qbytes; /* max number of bytes on queue */
- __kernel_pid_t msg_lspid; /* pid of last msgsnd */
- __kernel_pid_t msg_lrpid; /* last receive pid */
- unsigned long __unused1;
- unsigned long __unused2;
-};
-
-#endif /* _ASM_IA64_MSGBUF_H */
diff --git a/arch/ia64/include/uapi/asm/sembuf.h b/arch/ia64/include/uapi/asm/sembuf.h
deleted file mode 100644
index 6ed0587..0000000
--- a/arch/ia64/include/uapi/asm/sembuf.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ASM_IA64_SEMBUF_H
-#define _ASM_IA64_SEMBUF_H
-
-/*
- * The semid64_ds structure for IA-64 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 2 miscellaneous 64-bit values
- */
-
-struct semid64_ds {
- struct ipc64_perm sem_perm; /* permissions .. see ipc.h */
- __kernel_time_t sem_otime; /* last semop time */
- __kernel_time_t sem_ctime; /* last change time */
- unsigned long sem_nsems; /* no. of semaphores in array */
- unsigned long __unused1;
- unsigned long __unused2;
-};
-
-#endif /* _ASM_IA64_SEMBUF_H */
diff --git a/arch/ia64/include/uapi/asm/shmbuf.h b/arch/ia64/include/uapi/asm/shmbuf.h
deleted file mode 100644
index 6ef57cb..0000000
--- a/arch/ia64/include/uapi/asm/shmbuf.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ASM_IA64_SHMBUF_H
-#define _ASM_IA64_SHMBUF_H
-
-/*
- * The shmid64_ds structure for IA-64 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 2 miscellaneous 64-bit values
- */
-
-struct shmid64_ds {
- struct ipc64_perm shm_perm; /* operation perms */
- size_t shm_segsz; /* size of segment (bytes) */
- __kernel_time_t shm_atime; /* last attach time */
- __kernel_time_t shm_dtime; /* last detach time */
- __kernel_time_t shm_ctime; /* last change time */
- __kernel_pid_t shm_cpid; /* pid of creator */
- __kernel_pid_t shm_lpid; /* pid of last operator */
- unsigned long shm_nattch; /* no. of current attaches */
- unsigned long __unused1;
- unsigned long __unused2;
-};
-
-struct shminfo64 {
- unsigned long shmmax;
- unsigned long shmmin;
- unsigned long shmmni;
- unsigned long shmseg;
- unsigned long shmall;
- unsigned long __unused1;
- unsigned long __unused2;
- unsigned long __unused3;
- unsigned long __unused4;
-};
-
-#endif /* _ASM_IA64_SHMBUF_H */
diff --git a/arch/ia64/include/uapi/asm/siginfo.h b/arch/ia64/include/uapi/asm/siginfo.h
index 5aa454e..52b5af4 100644
--- a/arch/ia64/include/uapi/asm/siginfo.h
+++ b/arch/ia64/include/uapi/asm/siginfo.h
@@ -27,11 +27,4 @@
#define __ISR_VALID_BIT 0
#define __ISR_VALID (1 << __ISR_VALID_BIT)
-/*
- * SIGFPE si_codes
- */
-#ifdef __KERNEL__
-#define FPE_FIXME 0 /* Broken dup of SI_USER */
-#endif /* __KERNEL__ */
-
#endif /* _UAPI_ASM_IA64_SIGINFO_H */
diff --git a/arch/ia64/kernel/brl_emu.c b/arch/ia64/kernel/brl_emu.c
index 9bcc908..a61f6c6 100644
--- a/arch/ia64/kernel/brl_emu.c
+++ b/arch/ia64/kernel/brl_emu.c
@@ -62,6 +62,7 @@ ia64_emulate_brl (struct pt_regs *regs, unsigned long ar_ec)
struct illegal_op_return rv;
long tmp_taken, unimplemented_address;
+ clear_siginfo(&siginfo);
rv.fkt = (unsigned long) -1;
/*
diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c
index f2d57e6..7a471d8 100644
--- a/arch/ia64/kernel/dma-mapping.c
+++ b/arch/ia64/kernel/dma-mapping.c
@@ -9,16 +9,6 @@ int iommu_detected __read_mostly;
const struct dma_map_ops *dma_ops;
EXPORT_SYMBOL(dma_ops);
-#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-
-static int __init dma_init(void)
-{
- dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
-
- return 0;
-}
-fs_initcall(dma_init);
-
const struct dma_map_ops *dma_get_ops(struct device *dev)
{
return dma_ops;
diff --git a/arch/ia64/kernel/palinfo.c b/arch/ia64/kernel/palinfo.c
index b6e59786..f4a9424 100644
--- a/arch/ia64/kernel/palinfo.c
+++ b/arch/ia64/kernel/palinfo.c
@@ -920,18 +920,6 @@ static int proc_palinfo_show(struct seq_file *m, void *v)
return 0;
}
-static int proc_palinfo_open(struct inode *inode, struct file *file)
-{
- return single_open(file, proc_palinfo_show, PDE_DATA(inode));
-}
-
-static const struct file_operations proc_palinfo_fops = {
- .open = proc_palinfo_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int palinfo_add_proc(unsigned int cpu)
{
pal_func_cpu_u_t f;
@@ -948,8 +936,8 @@ static int palinfo_add_proc(unsigned int cpu)
for (j=0; j < NR_PALINFO_ENTRIES; j++) {
f.func_id = j;
- proc_create_data(palinfo_entries[j].name, 0, cpu_dir,
- &proc_palinfo_fops, (void *)f.value);
+ proc_create_single_data(palinfo_entries[j].name, 0, cpu_dir,
+ proc_palinfo_show, (void *)f.value);
}
return 0;
}
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 8fb280e..3b38c71 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -5708,13 +5708,6 @@ const struct seq_operations pfm_seq_ops = {
.show = pfm_proc_show
};
-static int
-pfm_proc_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &pfm_seq_ops);
-}
-
-
/*
* we come here as soon as local_cpu_data->pfm_syst_wide is set. this happens
* during pfm_enable() hence before pfm_start(). We cannot assume monitoring
@@ -6537,13 +6530,6 @@ pfm_probe_pmu(void)
return 0;
}
-static const struct file_operations pfm_proc_fops = {
- .open = pfm_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
int __init
pfm_init(void)
{
@@ -6615,7 +6601,7 @@ pfm_init(void)
/*
* create /proc/perfmon (mostly for debugging purposes)
*/
- perfmon_dir = proc_create("perfmon", S_IRUGO, NULL, &pfm_proc_fops);
+ perfmon_dir = proc_create_seq("perfmon", S_IRUGO, NULL, &pfm_seq_ops);
if (perfmon_dir == NULL) {
printk(KERN_ERR "perfmon: cannot create /proc entry, perfmon disabled\n");
pmu_conf = NULL;
diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c
index 52c404b..aba1f46 100644
--- a/arch/ia64/kernel/salinfo.c
+++ b/arch/ia64/kernel/salinfo.c
@@ -54,8 +54,6 @@ MODULE_AUTHOR("Jesse Barnes <jbarnes@sgi.com>");
MODULE_DESCRIPTION("/proc interface to IA-64 SAL features");
MODULE_LICENSE("GPL");
-static const struct file_operations proc_salinfo_fops;
-
typedef struct {
const char *name; /* name of the proc entry */
unsigned long feature; /* feature bit */
@@ -578,6 +576,17 @@ static int salinfo_cpu_pre_down(unsigned int cpu)
return 0;
}
+/*
+ * 'data' contains an integer that corresponds to the feature we're
+ * testing
+ */
+static int proc_salinfo_show(struct seq_file *m, void *v)
+{
+ unsigned long data = (unsigned long)v;
+ seq_puts(m, (sal_platform_features & data) ? "1\n" : "0\n");
+ return 0;
+}
+
static int __init
salinfo_init(void)
{
@@ -593,9 +602,9 @@ salinfo_init(void)
for (i=0; i < NR_SALINFO_ENTRIES; i++) {
/* pass the feature bit in question as misc data */
- *sdir++ = proc_create_data(salinfo_entries[i].name, 0, salinfo_dir,
- &proc_salinfo_fops,
- (void *)salinfo_entries[i].feature);
+ *sdir++ = proc_create_single_data(salinfo_entries[i].name, 0,
+ salinfo_dir, proc_salinfo_show,
+ (void *)salinfo_entries[i].feature);
}
for (i = 0; i < ARRAY_SIZE(salinfo_log_name); i++) {
@@ -633,27 +642,4 @@ salinfo_init(void)
return 0;
}
-/*
- * 'data' contains an integer that corresponds to the feature we're
- * testing
- */
-static int proc_salinfo_show(struct seq_file *m, void *v)
-{
- unsigned long data = (unsigned long)v;
- seq_puts(m, (sal_platform_features & data) ? "1\n" : "0\n");
- return 0;
-}
-
-static int proc_salinfo_open(struct inode *inode, struct file *file)
-{
- return single_open(file, proc_salinfo_show, PDE_DATA(inode));
-}
-
-static const struct file_operations proc_salinfo_fops = {
- .open = proc_salinfo_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
module_init(salinfo_init);
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index dee56bc..ad43cbf 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -124,18 +124,6 @@ unsigned long ia64_i_cache_stride_shift = ~0;
unsigned long ia64_cache_stride_shift = ~0;
/*
- * The merge_mask variable needs to be set to (max(iommu_page_size(iommu)) - 1). This
- * mask specifies a mask of address bits that must be 0 in order for two buffers to be
- * mergeable by the I/O MMU (i.e., the end address of the first buffer and the start
- * address of the second buffer must be aligned to (merge_mask+1) in order to be
- * mergeable). By default, we assume there is no I/O MMU which can merge physically
- * discontiguous buffers, so we set the merge_mask to ~0UL, which corresponds to a iommu
- * page-size of 2^64.
- */
-unsigned long ia64_max_iommu_merge_mask = ~0UL;
-EXPORT_SYMBOL(ia64_max_iommu_merge_mask);
-
-/*
* We use a special marker for the end of memory and it uses the extra (+1) slot
*/
struct rsvd_region rsvd_region[IA64_MAX_RSVD_REGIONS + 1] __initdata;
diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c
index 54547c7..d1234a5 100644
--- a/arch/ia64/kernel/signal.c
+++ b/arch/ia64/kernel/signal.c
@@ -153,6 +153,7 @@ ia64_rt_sigreturn (struct sigscratch *scr)
return retval;
give_sigsegv:
+ clear_siginfo(&si);
si.si_signo = SIGSEGV;
si.si_errno = 0;
si.si_code = SI_KERNEL;
@@ -236,6 +237,7 @@ force_sigsegv_info (int sig, void __user *addr)
unsigned long flags;
struct siginfo si;
+ clear_siginfo(&si);
if (sig == SIGSEGV) {
/*
* Acquiring siglock around the sa_handler-update is almost
diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c
index 6d4e76a..c6f4932 100644
--- a/arch/ia64/kernel/traps.c
+++ b/arch/ia64/kernel/traps.c
@@ -104,6 +104,7 @@ __kprobes ia64_bad_break (unsigned long break_num, struct pt_regs *regs)
int sig, code;
/* SIGILL, SIGFPE, SIGSEGV, and SIGBUS want these field initialized: */
+ clear_siginfo(&siginfo);
siginfo.si_addr = (void __user *) (regs->cr_iip + ia64_psr(regs)->ri);
siginfo.si_imm = break_num;
siginfo.si_flags = 0; /* clear __ISR_VALID */
@@ -293,7 +294,6 @@ handle_fpu_swa (int fp_fault, struct pt_regs *regs, unsigned long isr)
{
long exception, bundle[2];
unsigned long fault_ip;
- struct siginfo siginfo;
fault_ip = regs->cr_iip;
if (!fp_fault && (ia64_psr(regs)->ri == 0))
@@ -344,13 +344,16 @@ handle_fpu_swa (int fp_fault, struct pt_regs *regs, unsigned long isr)
printk(KERN_ERR "handle_fpu_swa: fp_emulate() returned -1\n");
return -1;
} else {
+ struct siginfo siginfo;
+
/* is next instruction a trap? */
if (exception & 2) {
ia64_increment_ip(regs);
}
+ clear_siginfo(&siginfo);
siginfo.si_signo = SIGFPE;
siginfo.si_errno = 0;
- siginfo.si_code = FPE_FIXME; /* default code */
+ siginfo.si_code = FPE_FLTUNK; /* default code */
siginfo.si_addr = (void __user *) (regs->cr_iip + ia64_psr(regs)->ri);
if (isr & 0x11) {
siginfo.si_code = FPE_FLTINV;
@@ -372,9 +375,12 @@ handle_fpu_swa (int fp_fault, struct pt_regs *regs, unsigned long isr)
return -1;
} else if (exception != 0) {
/* raise exception */
+ struct siginfo siginfo;
+
+ clear_siginfo(&siginfo);
siginfo.si_signo = SIGFPE;
siginfo.si_errno = 0;
- siginfo.si_code = FPE_FIXME; /* default code */
+ siginfo.si_code = FPE_FLTUNK; /* default code */
siginfo.si_addr = (void __user *) (regs->cr_iip + ia64_psr(regs)->ri);
if (isr & 0x880) {
siginfo.si_code = FPE_FLTOVF;
@@ -420,7 +426,7 @@ ia64_illegal_op_fault (unsigned long ec, long arg1, long arg2, long arg3,
if (die_if_kernel(buf, ®s, 0))
return rv;
- memset(&si, 0, sizeof(si));
+ clear_siginfo(&si);
si.si_signo = SIGILL;
si.si_code = ILL_ILLOPC;
si.si_addr = (void __user *) (regs.cr_iip + ia64_psr(®s)->ri);
@@ -434,7 +440,6 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa,
long arg7, struct pt_regs regs)
{
unsigned long code, error = isr, iip;
- struct siginfo siginfo;
char buf[128];
int result, sig;
static const char *reason[] = {
@@ -485,6 +490,7 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa,
case 26: /* NaT Consumption */
if (user_mode(®s)) {
+ struct siginfo siginfo;
void __user *addr;
if (((isr >> 4) & 0xf) == 2) {
@@ -499,6 +505,7 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa,
addr = (void __user *) (regs.cr_iip
+ ia64_psr(®s)->ri);
}
+ clear_siginfo(&siginfo);
siginfo.si_signo = sig;
siginfo.si_code = code;
siginfo.si_errno = 0;
@@ -515,6 +522,9 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa,
case 31: /* Unsupported Data Reference */
if (user_mode(®s)) {
+ struct siginfo siginfo;
+
+ clear_siginfo(&siginfo);
siginfo.si_signo = SIGILL;
siginfo.si_code = ILL_ILLOPN;
siginfo.si_errno = 0;
@@ -531,6 +541,10 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa,
case 29: /* Debug */
case 35: /* Taken Branch Trap */
case 36: /* Single Step Trap */
+ {
+ struct siginfo siginfo;
+
+ clear_siginfo(&siginfo);
if (fsys_mode(current, ®s)) {
extern char __kernel_syscall_via_break[];
/*
@@ -578,11 +592,15 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa,
siginfo.si_isr = isr;
force_sig_info(SIGTRAP, &siginfo, current);
return;
+ }
case 32: /* fp fault */
case 33: /* fp trap */
result = handle_fpu_swa((vector == 32) ? 1 : 0, ®s, isr);
if ((result < 0) || (current->thread.flags & IA64_THREAD_FPEMU_SIGFPE)) {
+ struct siginfo siginfo;
+
+ clear_siginfo(&siginfo);
siginfo.si_signo = SIGFPE;
siginfo.si_errno = 0;
siginfo.si_code = FPE_FLTINV;
@@ -616,6 +634,9 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa,
} else {
/* Unimplemented Instr. Address Trap */
if (user_mode(®s)) {
+ struct siginfo siginfo;
+
+ clear_siginfo(&siginfo);
siginfo.si_signo = SIGILL;
siginfo.si_code = ILL_BADIADDR;
siginfo.si_errno = 0;
diff --git a/arch/ia64/kernel/unaligned.c b/arch/ia64/kernel/unaligned.c
index 72e9b42..e309f98 100644
--- a/arch/ia64/kernel/unaligned.c
+++ b/arch/ia64/kernel/unaligned.c
@@ -1537,6 +1537,7 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs)
/* NOT_REACHED */
}
force_sigbus:
+ clear_siginfo(&si);
si.si_signo = SIGBUS;
si.si_errno = 0;
si.si_code = BUS_ADRALN;
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index dfdc152..817fa12 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -85,7 +85,6 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
int signal = SIGSEGV, code = SEGV_MAPERR;
struct vm_area_struct *vma, *prev_vma;
struct mm_struct *mm = current->mm;
- struct siginfo si;
unsigned long mask;
int fault;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -249,6 +248,9 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
return;
}
if (user_mode(regs)) {
+ struct siginfo si;
+
+ clear_siginfo(&si);
si.si_signo = signal;
si.si_errno = 0;
si.si_code = code;
diff --git a/arch/ia64/sn/kernel/io_common.c b/arch/ia64/sn/kernel/io_common.c
index 11f2275..8479e9a 100644
--- a/arch/ia64/sn/kernel/io_common.c
+++ b/arch/ia64/sn/kernel/io_common.c
@@ -480,11 +480,6 @@ sn_io_early_init(void)
tioca_init_provider();
tioce_init_provider();
- /*
- * This is needed to avoid bounce limit checks in the blk layer
- */
- ia64_max_iommu_merge_mask = ~PAGE_MASK;
-
sn_irq_lh_init();
INIT_LIST_HEAD(&sn_sysdata_list);
sn_init_cpei_timer();
diff --git a/arch/ia64/sn/kernel/sn2/prominfo_proc.c b/arch/ia64/sn/kernel/sn2/prominfo_proc.c
index ec4de2b0..e15457b 100644
--- a/arch/ia64/sn/kernel/sn2/prominfo_proc.c
+++ b/arch/ia64/sn/kernel/sn2/prominfo_proc.c
@@ -140,18 +140,6 @@ static int proc_fit_show(struct seq_file *m, void *v)
return 0;
}
-static int proc_fit_open(struct inode *inode, struct file *file)
-{
- return single_open(file, proc_fit_show, PDE_DATA(inode));
-}
-
-static const struct file_operations proc_fit_fops = {
- .open = proc_fit_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int proc_version_show(struct seq_file *m, void *v)
{
unsigned long nasid = (unsigned long)m->private;
@@ -174,18 +162,6 @@ static int proc_version_show(struct seq_file *m, void *v)
return 0;
}
-static int proc_version_open(struct inode *inode, struct file *file)
-{
- return single_open(file, proc_version_show, PDE_DATA(inode));
-}
-
-static const struct file_operations proc_version_fops = {
- .open = proc_version_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/* module entry points */
int __init prominfo_init(void);
void __exit prominfo_exit(void);
@@ -217,10 +193,10 @@ int __init prominfo_init(void)
if (!dir)
continue;
nasid = cnodeid_to_nasid(cnodeid);
- proc_create_data("fit", 0, dir,
- &proc_fit_fops, (void *)nasid);
- proc_create_data("version", 0, dir,
- &proc_version_fops, (void *)nasid);
+ proc_create_single_data("fit", 0, dir, proc_fit_show,
+ (void *)nasid);
+ proc_create_single_data("version", 0, dir, proc_version_show,
+ (void *)nasid);
}
return 0;
}
diff --git a/arch/ia64/sn/kernel/sn2/sn_proc_fs.c b/arch/ia64/sn/kernel/sn2/sn_proc_fs.c
index 29cf8f8..c2a4d84 100644
--- a/arch/ia64/sn/kernel/sn2/sn_proc_fs.c
+++ b/arch/ia64/sn/kernel/sn2/sn_proc_fs.c
@@ -18,33 +18,18 @@ static int partition_id_show(struct seq_file *s, void *p)
return 0;
}
-static int partition_id_open(struct inode *inode, struct file *file)
-{
- return single_open(file, partition_id_show, NULL);
-}
-
static int system_serial_number_show(struct seq_file *s, void *p)
{
seq_printf(s, "%s\n", sn_system_serial_number());
return 0;
}
-static int system_serial_number_open(struct inode *inode, struct file *file)
-{
- return single_open(file, system_serial_number_show, NULL);
-}
-
static int licenseID_show(struct seq_file *s, void *p)
{
seq_printf(s, "0x%llx\n", sn_partition_serial_number_val());
return 0;
}
-static int licenseID_open(struct inode *inode, struct file *file)
-{
- return single_open(file, licenseID_show, NULL);
-}
-
static int coherence_id_show(struct seq_file *s, void *p)
{
seq_printf(s, "%d\n", partition_coherence_id());
@@ -52,43 +37,10 @@ static int coherence_id_show(struct seq_file *s, void *p)
return 0;
}
-static int coherence_id_open(struct inode *inode, struct file *file)
-{
- return single_open(file, coherence_id_show, NULL);
-}
-
/* /proc/sgi_sn/sn_topology uses seq_file, see sn_hwperf.c */
extern int sn_topology_open(struct inode *, struct file *);
extern int sn_topology_release(struct inode *, struct file *);
-static const struct file_operations proc_partition_id_fops = {
- .open = partition_id_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-static const struct file_operations proc_system_sn_fops = {
- .open = system_serial_number_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-static const struct file_operations proc_license_id_fops = {
- .open = licenseID_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-static const struct file_operations proc_coherence_id_fops = {
- .open = coherence_id_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static const struct file_operations proc_sn_topo_fops = {
.open = sn_topology_open,
.read = seq_read,
@@ -104,13 +56,13 @@ void register_sn_procfs(void)
if (!(sgi_proc_dir = proc_mkdir("sgi_sn", NULL)))
return;
- proc_create("partition_id", 0444, sgi_proc_dir,
- &proc_partition_id_fops);
- proc_create("system_serial_number", 0444, sgi_proc_dir,
- &proc_system_sn_fops);
- proc_create("licenseID", 0444, sgi_proc_dir, &proc_license_id_fops);
- proc_create("coherence_id", 0444, sgi_proc_dir,
- &proc_coherence_id_fops);
+ proc_create_single("partition_id", 0444, sgi_proc_dir,
+ partition_id_show);
+ proc_create_single("system_serial_number", 0444, sgi_proc_dir,
+ system_serial_number_show);
+ proc_create_single("licenseID", 0444, sgi_proc_dir, licenseID_show);
+ proc_create_single("coherence_id", 0444, sgi_proc_dir,
+ coherence_id_show);
proc_create("sn_topology", 0444, sgi_proc_dir, &proc_sn_topo_fops);
}
diff --git a/arch/m68k/68000/timers.c b/arch/m68k/68000/timers.c
index 252455b..71ddb4c 100644
--- a/arch/m68k/68000/timers.c
+++ b/arch/m68k/68000/timers.c
@@ -125,7 +125,9 @@ int m68328_hwclk(int set, struct rtc_time *t)
{
if (!set) {
long now = RTCTIME;
- t->tm_year = t->tm_mon = t->tm_mday = 1;
+ t->tm_year = 1;
+ t->tm_mon = 0;
+ t->tm_mday = 1;
t->tm_hour = (now >> 24) % 24;
t->tm_min = (now >> 16) % 60;
t->tm_sec = now % 60;
diff --git a/arch/m68k/Kconfig.bus b/arch/m68k/Kconfig.bus
index d5e66ec..aef698f 100644
--- a/arch/m68k/Kconfig.bus
+++ b/arch/m68k/Kconfig.bus
@@ -59,6 +59,10 @@
config GENERIC_ISA_DMA
def_bool ISA
+source "drivers/zorro/Kconfig"
+
+endif
+
config PCI
bool "PCI support"
depends on M54xx
@@ -66,10 +70,8 @@
Enable the PCI bus. Support for the PCI bus hardware built into the
ColdFire 547x and 548x processors.
+if PCI
source "drivers/pci/Kconfig"
-
-source "drivers/zorro/Kconfig"
-
endif
if !MMU
diff --git a/arch/m68k/apollo/config.c b/arch/m68k/apollo/config.c
index 0d27706..b2a6bc6 100644
--- a/arch/m68k/apollo/config.c
+++ b/arch/m68k/apollo/config.c
@@ -221,8 +221,10 @@ int dn_dummy_hwclk(int op, struct rtc_time *t) {
t->tm_hour=rtc->hours;
t->tm_mday=rtc->day_of_month;
t->tm_wday=rtc->day_of_week;
- t->tm_mon=rtc->month;
+ t->tm_mon = rtc->month - 1;
t->tm_year=rtc->year;
+ if (t->tm_year < 70)
+ t->tm_year += 100;
} else {
rtc->second=t->tm_sec;
rtc->minute=t->tm_min;
@@ -230,8 +232,8 @@ int dn_dummy_hwclk(int op, struct rtc_time *t) {
rtc->day_of_month=t->tm_mday;
if(t->tm_wday!=-1)
rtc->day_of_week=t->tm_wday;
- rtc->month=t->tm_mon;
- rtc->year=t->tm_year;
+ rtc->month = t->tm_mon + 1;
+ rtc->year = t->tm_year % 100;
}
return 0;
diff --git a/arch/m68k/coldfire/pci.c b/arch/m68k/coldfire/pci.c
index 3097fa2..62b0eb6 100644
--- a/arch/m68k/coldfire/pci.c
+++ b/arch/m68k/coldfire/pci.c
@@ -23,20 +23,10 @@
/*
* Memory and IO mappings. We use a 1:1 mapping for local host memory to
- * PCI bus memory (no reason not to really). IO space doesn't matter, we
- * always use access functions for that. The device configuration space is
- * mapped over the IO map space when we enable it in the PCICAR register.
+ * PCI bus memory (no reason not to really). IO space is mapped in its own
+ * separate address region. The device configuration space is mapped over
+ * the IO map space when we enable it in the PCICAR register.
*/
-#define PCI_MEM_PA 0xf0000000 /* Host physical address */
-#define PCI_MEM_BA 0xf0000000 /* Bus physical address */
-#define PCI_MEM_SIZE 0x08000000 /* 128 MB */
-#define PCI_MEM_MASK (PCI_MEM_SIZE - 1)
-
-#define PCI_IO_PA 0xf8000000 /* Host physical address */
-#define PCI_IO_BA 0x00000000 /* Bus physical address */
-#define PCI_IO_SIZE 0x00010000 /* 64k */
-#define PCI_IO_MASK (PCI_IO_SIZE - 1)
-
static struct pci_bus *rootbus;
static unsigned long iospace;
@@ -56,13 +46,6 @@ static unsigned char mcf_host_irq[] = {
0, 69, 69, 71, 71,
};
-
-static inline void syncio(void)
-{
- /* The ColdFire "nop" instruction waits for all bus IO to complete */
- __asm__ __volatile__ ("nop");
-}
-
/*
* Configuration space access functions. Configuration space access is
* through the IO mapping window, enabling it via the PCICAR register.
@@ -84,9 +67,9 @@ static int mcf_pci_readconfig(struct pci_bus *bus, unsigned int devfn,
return PCIBIOS_SUCCESSFUL;
}
- syncio();
addr = mcf_mk_pcicar(bus->number, devfn, where);
__raw_writel(PCICAR_E | addr, PCICAR);
+ __raw_readl(PCICAR);
addr = iospace + (where & 0x3);
switch (size) {
@@ -101,8 +84,8 @@ static int mcf_pci_readconfig(struct pci_bus *bus, unsigned int devfn,
break;
}
- syncio();
__raw_writel(0, PCICAR);
+ __raw_readl(PCICAR);
return PCIBIOS_SUCCESSFUL;
}
@@ -116,9 +99,9 @@ static int mcf_pci_writeconfig(struct pci_bus *bus, unsigned int devfn,
return PCIBIOS_SUCCESSFUL;
}
- syncio();
addr = mcf_mk_pcicar(bus->number, devfn, where);
__raw_writel(PCICAR_E | addr, PCICAR);
+ __raw_readl(PCICAR);
addr = iospace + (where & 0x3);
switch (size) {
@@ -133,8 +116,8 @@ static int mcf_pci_writeconfig(struct pci_bus *bus, unsigned int devfn,
break;
}
- syncio();
__raw_writel(0, PCICAR);
+ __raw_readl(PCICAR);
return PCIBIOS_SUCCESSFUL;
}
@@ -144,89 +127,6 @@ static struct pci_ops mcf_pci_ops = {
};
/*
- * IO address space access functions. Pretty strait forward, these are
- * directly mapped in to the IO mapping window. And that is mapped into
- * virtual address space.
- */
-u8 mcf_pci_inb(u32 addr)
-{
- return __raw_readb(iospace + (addr & PCI_IO_MASK));
-}
-EXPORT_SYMBOL(mcf_pci_inb);
-
-u16 mcf_pci_inw(u32 addr)
-{
- return le16_to_cpu(__raw_readw(iospace + (addr & PCI_IO_MASK)));
-}
-EXPORT_SYMBOL(mcf_pci_inw);
-
-u32 mcf_pci_inl(u32 addr)
-{
- return le32_to_cpu(__raw_readl(iospace + (addr & PCI_IO_MASK)));
-}
-EXPORT_SYMBOL(mcf_pci_inl);
-
-void mcf_pci_insb(u32 addr, u8 *buf, u32 len)
-{
- for (; len; len--)
- *buf++ = mcf_pci_inb(addr);
-}
-EXPORT_SYMBOL(mcf_pci_insb);
-
-void mcf_pci_insw(u32 addr, u16 *buf, u32 len)
-{
- for (; len; len--)
- *buf++ = mcf_pci_inw(addr);
-}
-EXPORT_SYMBOL(mcf_pci_insw);
-
-void mcf_pci_insl(u32 addr, u32 *buf, u32 len)
-{
- for (; len; len--)
- *buf++ = mcf_pci_inl(addr);
-}
-EXPORT_SYMBOL(mcf_pci_insl);
-
-void mcf_pci_outb(u8 v, u32 addr)
-{
- __raw_writeb(v, iospace + (addr & PCI_IO_MASK));
-}
-EXPORT_SYMBOL(mcf_pci_outb);
-
-void mcf_pci_outw(u16 v, u32 addr)
-{
- __raw_writew(cpu_to_le16(v), iospace + (addr & PCI_IO_MASK));
-}
-EXPORT_SYMBOL(mcf_pci_outw);
-
-void mcf_pci_outl(u32 v, u32 addr)
-{
- __raw_writel(cpu_to_le32(v), iospace + (addr & PCI_IO_MASK));
-}
-EXPORT_SYMBOL(mcf_pci_outl);
-
-void mcf_pci_outsb(u32 addr, const u8 *buf, u32 len)
-{
- for (; len; len--)
- mcf_pci_outb(*buf++, addr);
-}
-EXPORT_SYMBOL(mcf_pci_outsb);
-
-void mcf_pci_outsw(u32 addr, const u16 *buf, u32 len)
-{
- for (; len; len--)
- mcf_pci_outw(*buf++, addr);
-}
-EXPORT_SYMBOL(mcf_pci_outsw);
-
-void mcf_pci_outsl(u32 addr, const u32 *buf, u32 len)
-{
- for (; len; len--)
- mcf_pci_outl(*buf++, addr);
-}
-EXPORT_SYMBOL(mcf_pci_outsl);
-
-/*
* Initialize the PCI bus registers, and scan the bus.
*/
static struct resource mcf_pci_mem = {
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 37a8e5a..a874e54 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -98,8 +98,8 @@
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
CONFIG_NFT_EXTHDR=m
CONFIG_NFT_META=m
CONFIG_NFT_RT=m
@@ -204,7 +204,7 @@
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
CONFIG_NF_FLOW_TABLE_IPV4=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -233,12 +233,12 @@
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
CONFIG_IP6_NF_MATCH_EUI64=m
@@ -259,7 +259,7 @@
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
@@ -310,7 +310,6 @@
CONFIG_MPLS_ROUTING=m
CONFIG_MPLS_IPTUNNEL=m
CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
CONFIG_PSAMPLE=m
@@ -414,6 +413,7 @@
# CONFIG_NET_VENDOR_MARVELL is not set
# CONFIG_NET_VENDOR_MICREL is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
CONFIG_HYDRA=y
CONFIG_APNE=y
CONFIG_ZORRO8390=y
@@ -485,6 +485,7 @@
CONFIG_RTC_DRV_RP5C01=m
# CONFIG_VIRTIO_MENU is not set
# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
CONFIG_HEARTBEAT=y
CONFIG_PROC_HARDWARE=y
CONFIG_AMIGA_BUILTIN_SERIAL=y
@@ -621,6 +622,7 @@
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
@@ -647,6 +649,8 @@
CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 6a46626..8ce39e2 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -96,8 +96,8 @@
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
CONFIG_NFT_EXTHDR=m
CONFIG_NFT_META=m
CONFIG_NFT_RT=m
@@ -202,7 +202,7 @@
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
CONFIG_NF_FLOW_TABLE_IPV4=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -231,12 +231,12 @@
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
CONFIG_IP6_NF_MATCH_EUI64=m
@@ -257,7 +257,7 @@
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
@@ -308,7 +308,6 @@
CONFIG_MPLS_ROUTING=m
CONFIG_MPLS_IPTUNNEL=m
CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
CONFIG_PSAMPLE=m
@@ -392,6 +391,7 @@
# CONFIG_NET_VENDOR_MICREL is not set
# CONFIG_NET_VENDOR_NATSEMI is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
# CONFIG_NET_VENDOR_QUALCOMM is not set
# CONFIG_NET_VENDOR_RENESAS is not set
# CONFIG_NET_VENDOR_ROCKER is not set
@@ -446,6 +446,7 @@
CONFIG_RTC_DRV_GENERIC=m
# CONFIG_VIRTIO_MENU is not set
# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
CONFIG_HEARTBEAT=y
CONFIG_PROC_HARDWARE=y
CONFIG_EXT4_FS=y
@@ -580,6 +581,7 @@
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
@@ -606,6 +608,8 @@
CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index b0691a7..346c4e7 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -96,8 +96,8 @@
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
CONFIG_NFT_EXTHDR=m
CONFIG_NFT_META=m
CONFIG_NFT_RT=m
@@ -202,7 +202,7 @@
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
CONFIG_NF_FLOW_TABLE_IPV4=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -231,12 +231,12 @@
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
CONFIG_IP6_NF_MATCH_EUI64=m
@@ -257,7 +257,7 @@
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
@@ -308,7 +308,6 @@
CONFIG_MPLS_ROUTING=m
CONFIG_MPLS_IPTUNNEL=m
CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
CONFIG_PSAMPLE=m
@@ -401,6 +400,7 @@
# CONFIG_NET_VENDOR_MARVELL is not set
# CONFIG_NET_VENDOR_MICREL is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
CONFIG_NE2000=y
# CONFIG_NET_VENDOR_QUALCOMM is not set
# CONFIG_NET_VENDOR_RENESAS is not set
@@ -461,6 +461,7 @@
CONFIG_RTC_DRV_GENERIC=m
# CONFIG_VIRTIO_MENU is not set
# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
CONFIG_HEARTBEAT=y
CONFIG_PROC_HARDWARE=y
CONFIG_NATFEAT=y
@@ -602,6 +603,7 @@
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
@@ -628,6 +630,8 @@
CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 6f6470f..fca9c7a 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -94,8 +94,8 @@
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
CONFIG_NFT_EXTHDR=m
CONFIG_NFT_META=m
CONFIG_NFT_RT=m
@@ -200,7 +200,7 @@
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
CONFIG_NF_FLOW_TABLE_IPV4=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -229,12 +229,12 @@
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
CONFIG_IP6_NF_MATCH_EUI64=m
@@ -255,7 +255,7 @@
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
@@ -306,7 +306,6 @@
CONFIG_MPLS_ROUTING=m
CONFIG_MPLS_IPTUNNEL=m
CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
CONFIG_PSAMPLE=m
@@ -391,6 +390,7 @@
# CONFIG_NET_VENDOR_MICREL is not set
# CONFIG_NET_VENDOR_NATSEMI is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
# CONFIG_NET_VENDOR_QUALCOMM is not set
# CONFIG_NET_VENDOR_RENESAS is not set
# CONFIG_NET_VENDOR_ROCKER is not set
@@ -439,6 +439,7 @@
CONFIG_RTC_DRV_GENERIC=m
# CONFIG_VIRTIO_MENU is not set
# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
CONFIG_PROC_HARDWARE=y
CONFIG_EXT4_FS=y
CONFIG_REISERFS_FS=m
@@ -572,6 +573,7 @@
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
@@ -598,6 +600,8 @@
CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 31a1a2b5..f9eab17 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -96,8 +96,8 @@
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
CONFIG_NFT_EXTHDR=m
CONFIG_NFT_META=m
CONFIG_NFT_RT=m
@@ -202,7 +202,7 @@
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
CONFIG_NF_FLOW_TABLE_IPV4=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -231,12 +231,12 @@
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
CONFIG_IP6_NF_MATCH_EUI64=m
@@ -257,7 +257,7 @@
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
@@ -308,7 +308,6 @@
CONFIG_MPLS_ROUTING=m
CONFIG_MPLS_IPTUNNEL=m
CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
CONFIG_PSAMPLE=m
@@ -393,6 +392,7 @@
# CONFIG_NET_VENDOR_MICREL is not set
# CONFIG_NET_VENDOR_NATSEMI is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
# CONFIG_NET_VENDOR_QUALCOMM is not set
# CONFIG_NET_VENDOR_RENESAS is not set
# CONFIG_NET_VENDOR_ROCKER is not set
@@ -449,6 +449,7 @@
CONFIG_RTC_DRV_GENERIC=m
# CONFIG_VIRTIO_MENU is not set
# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
CONFIG_PROC_HARDWARE=y
CONFIG_EXT4_FS=y
CONFIG_REISERFS_FS=m
@@ -582,6 +583,7 @@
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
@@ -608,6 +610,8 @@
CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 390d4a8..b52e597 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -95,8 +95,8 @@
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
CONFIG_NFT_EXTHDR=m
CONFIG_NFT_META=m
CONFIG_NFT_RT=m
@@ -201,7 +201,7 @@
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
CONFIG_NF_FLOW_TABLE_IPV4=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -230,12 +230,12 @@
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
CONFIG_IP6_NF_MATCH_EUI64=m
@@ -256,7 +256,7 @@
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
@@ -310,7 +310,6 @@
CONFIG_MPLS_ROUTING=m
CONFIG_MPLS_IPTUNNEL=m
CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
CONFIG_PSAMPLE=m
@@ -410,6 +409,7 @@
# CONFIG_NET_VENDOR_MICREL is not set
CONFIG_MACSONIC=y
# CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
CONFIG_MAC8390=y
# CONFIG_NET_VENDOR_QUALCOMM is not set
# CONFIG_NET_VENDOR_RENESAS is not set
@@ -471,6 +471,7 @@
CONFIG_RTC_DRV_GENERIC=m
# CONFIG_VIRTIO_MENU is not set
# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
CONFIG_PROC_HARDWARE=y
CONFIG_EXT4_FS=y
CONFIG_REISERFS_FS=m
@@ -604,6 +605,7 @@
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
@@ -630,6 +632,8 @@
CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 77be97d..2a84eee 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -105,8 +105,8 @@
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
CONFIG_NFT_EXTHDR=m
CONFIG_NFT_META=m
CONFIG_NFT_RT=m
@@ -211,7 +211,7 @@
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
CONFIG_NF_FLOW_TABLE_IPV4=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -240,12 +240,12 @@
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
CONFIG_IP6_NF_MATCH_EUI64=m
@@ -266,7 +266,7 @@
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
@@ -320,7 +320,6 @@
CONFIG_MPLS_ROUTING=m
CONFIG_MPLS_IPTUNNEL=m
CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
CONFIG_PSAMPLE=m
@@ -452,6 +451,7 @@
# CONFIG_NET_VENDOR_MICREL is not set
CONFIG_MACSONIC=y
# CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
CONFIG_HYDRA=y
CONFIG_MAC8390=y
CONFIG_NE2000=y
@@ -541,6 +541,7 @@
CONFIG_RTC_DRV_GENERIC=m
# CONFIG_VIRTIO_MENU is not set
# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
CONFIG_HEARTBEAT=y
CONFIG_PROC_HARDWARE=y
CONFIG_NATFEAT=y
@@ -684,6 +685,7 @@
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
@@ -710,6 +712,8 @@
CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 2ca1407..476e699 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -93,8 +93,8 @@
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
CONFIG_NFT_EXTHDR=m
CONFIG_NFT_META=m
CONFIG_NFT_RT=m
@@ -199,7 +199,7 @@
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
CONFIG_NF_FLOW_TABLE_IPV4=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -228,12 +228,12 @@
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
CONFIG_IP6_NF_MATCH_EUI64=m
@@ -254,7 +254,7 @@
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
@@ -305,7 +305,6 @@
CONFIG_MPLS_ROUTING=m
CONFIG_MPLS_IPTUNNEL=m
CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
CONFIG_PSAMPLE=m
@@ -391,6 +390,7 @@
# CONFIG_NET_VENDOR_MICREL is not set
# CONFIG_NET_VENDOR_NATSEMI is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
# CONFIG_NET_VENDOR_QUALCOMM is not set
# CONFIG_NET_VENDOR_RENESAS is not set
# CONFIG_NET_VENDOR_ROCKER is not set
@@ -439,6 +439,7 @@
CONFIG_RTC_DRV_GENERIC=m
# CONFIG_VIRTIO_MENU is not set
# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
CONFIG_PROC_HARDWARE=y
CONFIG_EXT4_FS=y
CONFIG_REISERFS_FS=m
@@ -572,6 +573,7 @@
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
@@ -598,6 +600,8 @@
CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 6a3b4dc..1477cda 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -94,8 +94,8 @@
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
CONFIG_NFT_EXTHDR=m
CONFIG_NFT_META=m
CONFIG_NFT_RT=m
@@ -200,7 +200,7 @@
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
CONFIG_NF_FLOW_TABLE_IPV4=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -229,12 +229,12 @@
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
CONFIG_IP6_NF_MATCH_EUI64=m
@@ -255,7 +255,7 @@
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
@@ -306,7 +306,6 @@
CONFIG_MPLS_ROUTING=m
CONFIG_MPLS_IPTUNNEL=m
CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
CONFIG_PSAMPLE=m
@@ -391,6 +390,7 @@
# CONFIG_NET_VENDOR_MICREL is not set
# CONFIG_NET_VENDOR_NATSEMI is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
# CONFIG_NET_VENDOR_QUALCOMM is not set
# CONFIG_NET_VENDOR_RENESAS is not set
# CONFIG_NET_VENDOR_ROCKER is not set
@@ -439,6 +439,7 @@
CONFIG_RTC_DRV_GENERIC=m
# CONFIG_VIRTIO_MENU is not set
# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
CONFIG_PROC_HARDWARE=y
CONFIG_EXT4_FS=y
CONFIG_REISERFS_FS=m
@@ -572,6 +573,7 @@
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
@@ -598,6 +600,8 @@
CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 2a3e29c..b3a543d 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -94,8 +94,8 @@
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
CONFIG_NFT_EXTHDR=m
CONFIG_NFT_META=m
CONFIG_NFT_RT=m
@@ -200,7 +200,7 @@
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
CONFIG_NF_FLOW_TABLE_IPV4=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -229,12 +229,12 @@
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
CONFIG_IP6_NF_MATCH_EUI64=m
@@ -255,7 +255,7 @@
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
@@ -306,7 +306,6 @@
CONFIG_MPLS_ROUTING=m
CONFIG_MPLS_IPTUNNEL=m
CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
CONFIG_PSAMPLE=m
@@ -400,6 +399,7 @@
# CONFIG_NET_VENDOR_MARVELL is not set
# CONFIG_NET_VENDOR_MICREL is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
CONFIG_NE2000=y
# CONFIG_NET_VENDOR_QUALCOMM is not set
# CONFIG_NET_VENDOR_RENESAS is not set
@@ -461,6 +461,7 @@
CONFIG_RTC_DRV_GENERIC=m
# CONFIG_VIRTIO_MENU is not set
# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
CONFIG_HEARTBEAT=y
CONFIG_PROC_HARDWARE=y
CONFIG_EXT4_FS=y
@@ -595,6 +596,7 @@
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
@@ -621,6 +623,8 @@
CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index cba2494..d543ed5 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -91,8 +91,8 @@
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
CONFIG_NFT_EXTHDR=m
CONFIG_NFT_META=m
CONFIG_NFT_RT=m
@@ -197,7 +197,7 @@
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
CONFIG_NF_FLOW_TABLE_IPV4=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -226,12 +226,12 @@
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
CONFIG_IP6_NF_MATCH_EUI64=m
@@ -252,7 +252,7 @@
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
@@ -303,7 +303,6 @@
CONFIG_MPLS_ROUTING=m
CONFIG_MPLS_IPTUNNEL=m
CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
CONFIG_PSAMPLE=m
@@ -388,6 +387,7 @@
# CONFIG_NET_VENDOR_MICREL is not set
# CONFIG_NET_VENDOR_NATSEMI is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
# CONFIG_NET_VENDOR_QUALCOMM is not set
# CONFIG_NET_VENDOR_RENESAS is not set
# CONFIG_NET_VENDOR_ROCKER is not set
@@ -441,6 +441,7 @@
CONFIG_RTC_DRV_GENERIC=m
# CONFIG_VIRTIO_MENU is not set
# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
CONFIG_PROC_HARDWARE=y
CONFIG_EXT4_FS=y
CONFIG_REISERFS_FS=m
@@ -573,6 +574,7 @@
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
@@ -599,6 +601,8 @@
CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index d911561..a67e542 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -91,8 +91,8 @@
CONFIG_NF_CONNTRACK_SIP=m
CONFIG_NF_CONNTRACK_TFTP=m
CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_INET=m
-CONFIG_NF_TABLES_NETDEV=m
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
CONFIG_NFT_EXTHDR=m
CONFIG_NFT_META=m
CONFIG_NFT_RT=m
@@ -197,7 +197,7 @@
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NFT_DUP_IPV4=m
CONFIG_NFT_FIB_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
CONFIG_NF_FLOW_TABLE_IPV4=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -226,12 +226,12 @@
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NF_SOCKET_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_DUP_IPV6=m
-CONFIG_NFT_FIB_IPV6=m
-CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
+CONFIG_NF_FLOW_TABLE_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
CONFIG_IP6_NF_MATCH_EUI64=m
@@ -252,7 +252,7 @@
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
CONFIG_IP6_NF_TARGET_NPT=m
-CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_NF_TABLES_BRIDGE=y
CONFIG_NFT_BRIDGE_META=m
CONFIG_NFT_BRIDGE_REJECT=m
CONFIG_NF_LOG_BRIDGE=m
@@ -303,7 +303,6 @@
CONFIG_MPLS_ROUTING=m
CONFIG_MPLS_IPTUNNEL=m
CONFIG_NET_NSH=m
-CONFIG_NET_L3_MASTER_DEV=y
CONFIG_AF_KCM=m
# CONFIG_WIRELESS is not set
CONFIG_PSAMPLE=m
@@ -389,6 +388,7 @@
# CONFIG_NET_VENDOR_MICREL is not set
# CONFIG_NET_VENDOR_NATSEMI is not set
# CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
# CONFIG_NET_VENDOR_QUALCOMM is not set
# CONFIG_NET_VENDOR_RENESAS is not set
# CONFIG_NET_VENDOR_ROCKER is not set
@@ -441,6 +441,7 @@
CONFIG_RTC_DRV_GENERIC=m
# CONFIG_VIRTIO_MENU is not set
# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_DAX=m
CONFIG_PROC_HARDWARE=y
CONFIG_EXT4_FS=y
CONFIG_REISERFS_FS=m
@@ -574,6 +575,7 @@
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
@@ -600,6 +602,8 @@
CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_LZO=m
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 88a9d27..4d8d68c 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -1,4 +1,5 @@
generic-y += barrier.h
+generic-y += compat.h
generic-y += device.h
generic-y += emergency-restart.h
generic-y += exec.h
diff --git a/arch/m68k/include/asm/atarihw.h b/arch/m68k/include/asm/atarihw.h
index 972c8f3..9000b24 100644
--- a/arch/m68k/include/asm/atarihw.h
+++ b/arch/m68k/include/asm/atarihw.h
@@ -23,6 +23,7 @@
#include <linux/types.h>
#include <asm/bootinfo-atari.h>
#include <asm/raw_io.h>
+#include <asm/kmap.h>
extern u_long atari_mch_cookie;
extern u_long atari_mch_type;
diff --git a/arch/m68k/include/asm/delay.h b/arch/m68k/include/asm/delay.h
index 7f47412..751712f 100644
--- a/arch/m68k/include/asm/delay.h
+++ b/arch/m68k/include/asm/delay.h
@@ -49,8 +49,6 @@ extern void __bad_udelay(void);
* The simpler m68k and ColdFire processors do not have a 32*32->64
* multiply instruction. So we need to handle them a little differently.
* We use a bit of shifting and a single 32*32->32 multiply to get close.
- * This is a macro so that the const version can factor out the first
- * multiply and shift.
*/
#define HZSCALE (268435456 / (1000000 / HZ))
@@ -115,6 +113,13 @@ static inline void __udelay(unsigned long usecs)
*/
#define HZSCALE (268435456 / (1000000 / HZ))
-#define ndelay(n) __delay(DIV_ROUND_UP((n) * ((((HZSCALE) >> 11) * (loops_per_jiffy >> 11)) >> 6), 1000))
+static inline void ndelay(unsigned long nsec)
+{
+ __delay(DIV_ROUND_UP(nsec *
+ ((((HZSCALE) >> 11) *
+ (loops_per_jiffy >> 11)) >> 6),
+ 1000));
+}
+#define ndelay(n) ndelay(n)
#endif /* defined(_M68K_DELAY_H) */
diff --git a/arch/m68k/include/asm/io.h b/arch/m68k/include/asm/io.h
index 756089c..ca2849a 100644
--- a/arch/m68k/include/asm/io.h
+++ b/arch/m68k/include/asm/io.h
@@ -1,14 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifdef __uClinux__
+#if defined(__uClinux__) || defined(CONFIG_COLDFIRE)
#include <asm/io_no.h>
#else
#include <asm/io_mm.h>
#endif
-
-#define readb_relaxed(addr) readb(addr)
-#define readw_relaxed(addr) readw(addr)
-#define readl_relaxed(addr) readl(addr)
-
-#define writeb_relaxed(b, addr) writeb(b, addr)
-#define writew_relaxed(b, addr) writew(b, addr)
-#define writel_relaxed(b, addr) writel(b, addr)
diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h
index ed5333e..fe485f4 100644
--- a/arch/m68k/include/asm/io_mm.h
+++ b/arch/m68k/include/asm/io_mm.h
@@ -26,6 +26,7 @@
#include <linux/compiler.h>
#include <asm/raw_io.h>
#include <asm/virtconvert.h>
+#include <asm/kmap.h>
#include <asm-generic/iomap.h>
@@ -85,53 +86,7 @@
#endif /* ATARI_ROM_ISA */
-#if defined(CONFIG_PCI) && defined(CONFIG_COLDFIRE)
-
-#define HAVE_ARCH_PIO_SIZE
-#define PIO_OFFSET 0
-#define PIO_MASK 0xffff
-#define PIO_RESERVED 0x10000
-
-u8 mcf_pci_inb(u32 addr);
-u16 mcf_pci_inw(u32 addr);
-u32 mcf_pci_inl(u32 addr);
-void mcf_pci_insb(u32 addr, u8 *buf, u32 len);
-void mcf_pci_insw(u32 addr, u16 *buf, u32 len);
-void mcf_pci_insl(u32 addr, u32 *buf, u32 len);
-
-void mcf_pci_outb(u8 v, u32 addr);
-void mcf_pci_outw(u16 v, u32 addr);
-void mcf_pci_outl(u32 v, u32 addr);
-void mcf_pci_outsb(u32 addr, const u8 *buf, u32 len);
-void mcf_pci_outsw(u32 addr, const u16 *buf, u32 len);
-void mcf_pci_outsl(u32 addr, const u32 *buf, u32 len);
-
-#define inb mcf_pci_inb
-#define inb_p mcf_pci_inb
-#define inw mcf_pci_inw
-#define inw_p mcf_pci_inw
-#define inl mcf_pci_inl
-#define inl_p mcf_pci_inl
-#define insb mcf_pci_insb
-#define insw mcf_pci_insw
-#define insl mcf_pci_insl
-
-#define outb mcf_pci_outb
-#define outb_p mcf_pci_outb
-#define outw mcf_pci_outw
-#define outw_p mcf_pci_outw
-#define outl mcf_pci_outl
-#define outl_p mcf_pci_outl
-#define outsb mcf_pci_outsb
-#define outsw mcf_pci_outsw
-#define outsl mcf_pci_outsl
-
-#define readb(addr) in_8(addr)
-#define writeb(v, addr) out_8((addr), (v))
-#define readw(addr) in_le16(addr)
-#define writew(v, addr) out_le16((addr), (v))
-
-#elif defined(CONFIG_ISA) || defined(CONFIG_ATARI_ROM_ISA)
+#if defined(CONFIG_ISA) || defined(CONFIG_ATARI_ROM_ISA)
#if MULTI_ISA == 0
#undef MULTI_ISA
@@ -414,8 +369,7 @@ static inline void isa_delay(void)
#define writew(val, addr) out_le16((addr), (val))
#endif /* CONFIG_ATARI_ROM_ISA */
-#if !defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA) && \
- !(defined(CONFIG_PCI) && defined(CONFIG_COLDFIRE))
+#if !defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA)
/*
* We need to define dummy functions for GENERIC_IOMAP support.
*/
@@ -461,39 +415,6 @@ static inline void isa_delay(void)
#define mmiowb()
-static inline void __iomem *ioremap(unsigned long physaddr, unsigned long size)
-{
- return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
-}
-static inline void __iomem *ioremap_nocache(unsigned long physaddr, unsigned long size)
-{
- return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
-}
-#define ioremap_uc ioremap_nocache
-static inline void __iomem *ioremap_wt(unsigned long physaddr,
- unsigned long size)
-{
- return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
-}
-static inline void __iomem *ioremap_fullcache(unsigned long physaddr,
- unsigned long size)
-{
- return __ioremap(physaddr, size, IOMAP_FULL_CACHING);
-}
-
-static inline void memset_io(volatile void __iomem *addr, unsigned char val, int count)
-{
- __builtin_memset((void __force *) addr, val, count);
-}
-static inline void memcpy_fromio(void *dst, const volatile void __iomem *src, int count)
-{
- __builtin_memcpy(dst, (void __force *) src, count);
-}
-static inline void memcpy_toio(volatile void __iomem *dst, const void *src, int count)
-{
- __builtin_memcpy((void __force *) dst, src, count);
-}
-
#ifndef CONFIG_SUN3
#define IO_SPACE_LIMIT 0xffff
#else
@@ -515,13 +436,12 @@ static inline void memcpy_toio(volatile void __iomem *dst, const void *src, int
*/
#define xlate_dev_kmem_ptr(p) p
-static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
-{
- return (void __iomem *) port;
-}
+#define readb_relaxed(addr) readb(addr)
+#define readw_relaxed(addr) readw(addr)
+#define readl_relaxed(addr) readl(addr)
-static inline void ioport_unmap(void __iomem *p)
-{
-}
+#define writeb_relaxed(b, addr) writeb(b, addr)
+#define writew_relaxed(b, addr) writew(b, addr)
+#define writel_relaxed(b, addr) writel(b, addr)
#endif /* _IO_H */
diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h
index 86f45b4..83a0a6d 100644
--- a/arch/m68k/include/asm/io_no.h
+++ b/arch/m68k/include/asm/io_no.h
@@ -2,191 +2,148 @@
#ifndef _M68KNOMMU_IO_H
#define _M68KNOMMU_IO_H
-#ifdef __KERNEL__
-
-#define ARCH_HAS_IOREMAP_WT
-
-#include <asm/virtconvert.h>
-#include <asm-generic/iomap.h>
+/*
+ * Convert a physical memory address into a IO memory address.
+ * For us this is trivially a type cast.
+ */
+#define iomem(a) ((void __iomem *) (a))
/*
- * These are for ISA/PCI shared memory _only_ and should never be used
- * on any other type of memory, including Zorro memory. They are meant to
- * access the bus in the bus byte order which is little-endian!.
- *
- * readX/writeX() are used to access memory mapped devices. On some
- * architectures the memory mapped IO stuff needs to be accessed
- * differently. On the m68k architecture, we just read/write the
- * memory location directly.
+ * The non-MMU m68k and ColdFire IO and memory mapped hardware access
+ * functions have always worked in CPU native endian. We need to define
+ * that behavior here first before we include asm-generic/io.h.
*/
-/* ++roman: The assignments to temp. vars avoid that gcc sometimes generates
- * two accesses to memory, which may be undesirable for some devices.
- */
-
-/*
- * swap functions are sometimes needed to interface little-endian hardware
- */
-static inline unsigned short _swapw(volatile unsigned short v)
-{
- return ((v << 8) | (v >> 8));
-}
-
-static inline unsigned int _swapl(volatile unsigned long v)
-{
- return ((v << 24) | ((v & 0xff00) << 8) | ((v & 0xff0000) >> 8) | (v >> 24));
-}
-
-#define readb(addr) \
+#define __raw_readb(addr) \
({ unsigned char __v = (*(volatile unsigned char *) (addr)); __v; })
-#define readw(addr) \
+#define __raw_readw(addr) \
({ unsigned short __v = (*(volatile unsigned short *) (addr)); __v; })
-#define readl(addr) \
+#define __raw_readl(addr) \
({ unsigned int __v = (*(volatile unsigned int *) (addr)); __v; })
-#define writeb(b,addr) (void)((*(volatile unsigned char *) (addr)) = (b))
-#define writew(b,addr) (void)((*(volatile unsigned short *) (addr)) = (b))
-#define writel(b,addr) (void)((*(volatile unsigned int *) (addr)) = (b))
+#define __raw_writeb(b, addr) (void)((*(volatile unsigned char *) (addr)) = (b))
+#define __raw_writew(b, addr) (void)((*(volatile unsigned short *) (addr)) = (b))
+#define __raw_writel(b, addr) (void)((*(volatile unsigned int *) (addr)) = (b))
-#define __raw_readb readb
-#define __raw_readw readw
-#define __raw_readl readl
-#define __raw_writeb writeb
-#define __raw_writew writew
-#define __raw_writel writel
+#if defined(CONFIG_COLDFIRE)
+/*
+ * For ColdFire platforms we may need to do some extra checks for what
+ * type of address range we are accessing. Include the ColdFire platform
+ * definitions so we can figure out if need to do something special.
+ */
+#include <asm/byteorder.h>
+#include <asm/coldfire.h>
+#include <asm/mcfsim.h>
+#endif /* CONFIG_COLDFIRE */
-static inline void io_outsb(unsigned int addr, const void *buf, int len)
+#if defined(IOMEMBASE)
+/*
+ * The ColdFire SoC internal peripherals are mapped into virtual address
+ * space using the ACR registers of the cache control unit. This means we
+ * are using a 1:1 physical:virtual mapping for them. We can quickly
+ * determine if we are accessing an internal peripheral device given the
+ * physical or vitrual address using the same range check. This check logic
+ * applies just the same of there is no MMU but something like a PCI bus
+ * is present.
+ */
+static int __cf_internalio(unsigned long addr)
{
- volatile unsigned char *ap = (volatile unsigned char *) addr;
- unsigned char *bp = (unsigned char *) buf;
- while (len--)
- *ap = *bp++;
+ return (addr >= IOMEMBASE) && (addr <= IOMEMBASE + IOMEMSIZE - 1);
}
-static inline void io_outsw(unsigned int addr, const void *buf, int len)
+static int cf_internalio(const volatile void __iomem *addr)
{
- volatile unsigned short *ap = (volatile unsigned short *) addr;
- unsigned short *bp = (unsigned short *) buf;
- while (len--)
- *ap = _swapw(*bp++);
+ return __cf_internalio((unsigned long) addr);
}
-static inline void io_outsl(unsigned int addr, const void *buf, int len)
-{
- volatile unsigned int *ap = (volatile unsigned int *) addr;
- unsigned int *bp = (unsigned int *) buf;
- while (len--)
- *ap = _swapl(*bp++);
-}
-
-static inline void io_insb(unsigned int addr, void *buf, int len)
-{
- volatile unsigned char *ap = (volatile unsigned char *) addr;
- unsigned char *bp = (unsigned char *) buf;
- while (len--)
- *bp++ = *ap;
-}
-
-static inline void io_insw(unsigned int addr, void *buf, int len)
-{
- volatile unsigned short *ap = (volatile unsigned short *) addr;
- unsigned short *bp = (unsigned short *) buf;
- while (len--)
- *bp++ = _swapw(*ap);
-}
-
-static inline void io_insl(unsigned int addr, void *buf, int len)
-{
- volatile unsigned int *ap = (volatile unsigned int *) addr;
- unsigned int *bp = (unsigned int *) buf;
- while (len--)
- *bp++ = _swapl(*ap);
-}
-
-#define mmiowb()
-
/*
- * make the short names macros so specific devices
- * can override them as required
+ * We need to treat built-in peripherals and bus based address ranges
+ * differently. Local built-in peripherals (and the ColdFire SoC parts
+ * have quite a lot of them) are always native endian - which is big
+ * endian on m68k/ColdFire. Bus based address ranges, like the PCI bus,
+ * are accessed little endian - so we need to byte swap those.
*/
-
-#define memset_io(a,b,c) memset((void *)(a),(b),(c))
-#define memcpy_fromio(a,b,c) memcpy((a),(void *)(b),(c))
-#define memcpy_toio(a,b,c) memcpy((void *)(a),(b),(c))
-
-#define inb(addr) readb(addr)
-#define inw(addr) readw(addr)
-#define inl(addr) readl(addr)
-#define outb(x,addr) ((void) writeb(x,addr))
-#define outw(x,addr) ((void) writew(x,addr))
-#define outl(x,addr) ((void) writel(x,addr))
-
-#define inb_p(addr) inb(addr)
-#define inw_p(addr) inw(addr)
-#define inl_p(addr) inl(addr)
-#define outb_p(x,addr) outb(x,addr)
-#define outw_p(x,addr) outw(x,addr)
-#define outl_p(x,addr) outl(x,addr)
-
-#define outsb(a,b,l) io_outsb(a,b,l)
-#define outsw(a,b,l) io_outsw(a,b,l)
-#define outsl(a,b,l) io_outsl(a,b,l)
-
-#define insb(a,b,l) io_insb(a,b,l)
-#define insw(a,b,l) io_insw(a,b,l)
-#define insl(a,b,l) io_insl(a,b,l)
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-
-/* Values for nocacheflag and cmode */
-#define IOMAP_FULL_CACHING 0
-#define IOMAP_NOCACHE_SER 1
-#define IOMAP_NOCACHE_NONSER 2
-#define IOMAP_WRITETHROUGH 3
-
-static inline void *__ioremap(unsigned long physaddr, unsigned long size, int cacheflag)
+#define readw readw
+static inline u16 readw(const volatile void __iomem *addr)
{
- return (void *) physaddr;
-}
-static inline void *ioremap(unsigned long physaddr, unsigned long size)
-{
- return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
-}
-static inline void *ioremap_nocache(unsigned long physaddr, unsigned long size)
-{
- return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
-}
-static inline void *ioremap_wt(unsigned long physaddr, unsigned long size)
-{
- return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
-}
-static inline void *ioremap_fullcache(unsigned long physaddr, unsigned long size)
-{
- return __ioremap(physaddr, size, IOMAP_FULL_CACHING);
+ if (cf_internalio(addr))
+ return __raw_readw(addr);
+ return __le16_to_cpu(__raw_readw(addr));
}
-#define iounmap(addr) do { } while(0)
+#define readl readl
+static inline u32 readl(const volatile void __iomem *addr)
+{
+ if (cf_internalio(addr))
+ return __raw_readl(addr);
+ return __le32_to_cpu(__raw_readl(addr));
+}
+
+#define writew writew
+static inline void writew(u16 value, volatile void __iomem *addr)
+{
+ if (cf_internalio(addr))
+ __raw_writew(value, addr);
+ else
+ __raw_writew(__cpu_to_le16(value), addr);
+}
+
+#define writel writel
+static inline void writel(u32 value, volatile void __iomem *addr)
+{
+ if (cf_internalio(addr))
+ __raw_writel(value, addr);
+ else
+ __raw_writel(__cpu_to_le32(value), addr);
+}
+
+#else
+
+#define readb __raw_readb
+#define readw __raw_readw
+#define readl __raw_readl
+#define writeb __raw_writeb
+#define writew __raw_writew
+#define writel __raw_writel
+
+#endif /* IOMEMBASE */
+
+#if defined(CONFIG_PCI)
+/*
+ * Support for PCI bus access uses the asm-generic access functions.
+ * We need to supply the base address and masks for the normal memory
+ * and IO address space mappings.
+ */
+#define PCI_MEM_PA 0xf0000000 /* Host physical address */
+#define PCI_MEM_BA 0xf0000000 /* Bus physical address */
+#define PCI_MEM_SIZE 0x08000000 /* 128 MB */
+#define PCI_MEM_MASK (PCI_MEM_SIZE - 1)
+
+#define PCI_IO_PA 0xf8000000 /* Host physical address */
+#define PCI_IO_BA 0x00000000 /* Bus physical address */
+#define PCI_IO_SIZE 0x00010000 /* 64k */
+#define PCI_IO_MASK (PCI_IO_SIZE - 1)
+
+#define HAVE_ARCH_PIO_SIZE
+#define PIO_OFFSET 0
+#define PIO_MASK 0xffff
+#define PIO_RESERVED 0x10000
+#define PCI_IOBASE ((void __iomem *) PCI_IO_PA)
+#define PCI_SPACE_LIMIT PCI_IO_MASK
+#endif /* CONFIG_PCI */
/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
+ * These are defined in kmap.h as static inline functions. To maintain
+ * previous behavior we put these define guards here so io_mm.h doesn't
+ * see them.
*/
-#define xlate_dev_mem_ptr(p) __va(p)
+#ifdef CONFIG_MMU
+#define memset_io memset_io
+#define memcpy_fromio memcpy_fromio
+#define memcpy_toio memcpy_toio
+#endif
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p) p
-
-static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
-{
- return (void __iomem *) port;
-}
-
-static inline void ioport_unmap(void __iomem *p)
-{
-}
-
-#endif /* __KERNEL__ */
+#include <asm/kmap.h>
+#include <asm/virtconvert.h>
+#include <asm-generic/io.h>
#endif /* _M68KNOMMU_IO_H */
diff --git a/arch/m68k/include/asm/kmap.h b/arch/m68k/include/asm/kmap.h
new file mode 100644
index 0000000..84b8333
--- /dev/null
+++ b/arch/m68k/include/asm/kmap.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _KMAP_H
+#define _KMAP_H
+
+#ifdef CONFIG_MMU
+
+/* Values for nocacheflag and cmode */
+#define IOMAP_FULL_CACHING 0
+#define IOMAP_NOCACHE_SER 1
+#define IOMAP_NOCACHE_NONSER 2
+#define IOMAP_WRITETHROUGH 3
+
+/*
+ * These functions exported by arch/m68k/mm/kmap.c.
+ * Only needed on MMU enabled systems.
+ */
+extern void __iomem *__ioremap(unsigned long physaddr, unsigned long size,
+ int cacheflag);
+extern void iounmap(void __iomem *addr);
+extern void __iounmap(void *addr, unsigned long size);
+
+#define ioremap ioremap
+static inline void __iomem *ioremap(unsigned long physaddr, unsigned long size)
+{
+ return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
+}
+
+#define ioremap_nocache ioremap_nocache
+static inline void __iomem *ioremap_nocache(unsigned long physaddr,
+ unsigned long size)
+{
+ return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
+}
+
+#define ioremap_uc ioremap_nocache
+static inline void __iomem *ioremap_wt(unsigned long physaddr,
+ unsigned long size)
+{
+ return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
+}
+
+#define ioremap_fillcache ioremap_fullcache
+static inline void __iomem *ioremap_fullcache(unsigned long physaddr,
+ unsigned long size)
+{
+ return __ioremap(physaddr, size, IOMAP_FULL_CACHING);
+}
+
+static inline void memset_io(volatile void __iomem *addr, unsigned char val,
+ int count)
+{
+ __builtin_memset((void __force *) addr, val, count);
+}
+
+static inline void memcpy_fromio(void *dst, const volatile void __iomem *src,
+ int count)
+{
+ __builtin_memcpy(dst, (void __force *) src, count);
+}
+
+static inline void memcpy_toio(volatile void __iomem *dst, const void *src,
+ int count)
+{
+ __builtin_memcpy((void __force *) dst, src, count);
+}
+
+#endif /* CONFIG_MMU */
+
+#define ioport_map ioport_map
+static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
+{
+ return (void __iomem *) port;
+}
+
+#define ioport_unmap ioport_unmap
+static inline void ioport_unmap(void __iomem *p)
+{
+}
+
+#endif /* _KMAP_H */
diff --git a/arch/m68k/include/asm/nubus.h b/arch/m68k/include/asm/nubus.h
index d0d2039..c2281da 100644
--- a/arch/m68k/include/asm/nubus.h
+++ b/arch/m68k/include/asm/nubus.h
@@ -3,6 +3,7 @@
#define _ASM_M68K_NUBUS_H
#include <asm/raw_io.h>
+#include <asm/kmap.h>
#define nubus_readb raw_inb
#define nubus_readw raw_inw
diff --git a/arch/m68k/include/asm/pci.h b/arch/m68k/include/asm/pci.h
index ef26fae..5a4bc22 100644
--- a/arch/m68k/include/asm/pci.h
+++ b/arch/m68k/include/asm/pci.h
@@ -4,12 +4,6 @@
#include <asm-generic/pci.h>
-/* The PCI address space does equal the physical memory
- * address space. The networking and block device layers use
- * this boolean for bounce buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS (1)
-
#define pcibios_assign_all_busses() 1
#define PCIBIOS_MIN_IO 0x00000100
diff --git a/arch/m68k/include/asm/q40_master.h b/arch/m68k/include/asm/q40_master.h
index 3a89c088..9b00fb8 100644
--- a/arch/m68k/include/asm/q40_master.h
+++ b/arch/m68k/include/asm/q40_master.h
@@ -8,7 +8,7 @@
#define _Q40_MASTER_H
#include <asm/raw_io.h>
-
+#include <asm/kmap.h>
#define q40_master_addr 0xff000000
diff --git a/arch/m68k/include/asm/raw_io.h b/arch/m68k/include/asm/raw_io.h
index 05e940c..8576125 100644
--- a/arch/m68k/include/asm/raw_io.h
+++ b/arch/m68k/include/asm/raw_io.h
@@ -13,20 +13,6 @@
#include <asm/byteorder.h>
-
-/* Values for nocacheflag and cmode */
-#define IOMAP_FULL_CACHING 0
-#define IOMAP_NOCACHE_SER 1
-#define IOMAP_NOCACHE_NONSER 2
-#define IOMAP_WRITETHROUGH 3
-
-extern void iounmap(void __iomem *addr);
-
-extern void __iomem *__ioremap(unsigned long physaddr, unsigned long size,
- int cacheflag);
-extern void __iounmap(void *addr, unsigned long size);
-
-
/* ++roman: The assignments to temp. vars avoid that gcc sometimes generates
* two accesses to memory, which may be undesirable for some devices.
*/
diff --git a/arch/m68k/include/asm/uaccess_mm.h b/arch/m68k/include/asm/uaccess_mm.h
index 75c172e..c4cb889 100644
--- a/arch/m68k/include/asm/uaccess_mm.h
+++ b/arch/m68k/include/asm/uaccess_mm.h
@@ -141,10 +141,12 @@ asm volatile ("\n" \
case 4: \
__get_user_asm(__gu_err, x, ptr, u32, l, r, -EFAULT); \
break; \
-/* case 8: disabled because gcc-4.1 has a broken typeof \
- { \
- const void *__gu_ptr = (ptr); \
- u64 __gu_val; \
+ case 8: { \
+ const void *__gu_ptr = (ptr); \
+ union { \
+ u64 l; \
+ __typeof__(*(ptr)) t; \
+ } __gu_val; \
asm volatile ("\n" \
"1: "MOVES".l (%2)+,%1\n" \
"2: "MOVES".l (%2),%R1\n" \
@@ -162,13 +164,13 @@ asm volatile ("\n" \
" .long 1b,10b\n" \
" .long 2b,10b\n" \
" .previous" \
- : "+d" (__gu_err), "=&r" (__gu_val), \
+ : "+d" (__gu_err), "=&r" (__gu_val.l), \
"+a" (__gu_ptr) \
: "i" (-EFAULT) \
: "memory"); \
- (x) = (__force typeof(*(ptr)))__gu_val; \
+ (x) = __gu_val.t; \
break; \
- } */ \
+ } \
default: \
__gu_err = __get_user_bad(); \
break; \
diff --git a/arch/m68k/include/asm/vga.h b/arch/m68k/include/asm/vga.h
index 010a624..4742e6b 100644
--- a/arch/m68k/include/asm/vga.h
+++ b/arch/m68k/include/asm/vga.h
@@ -2,7 +2,15 @@
#ifndef _ASM_M68K_VGA_H
#define _ASM_M68K_VGA_H
+/*
+ * Some ColdFire platforms do in fact have a PCI bus. So for those we want
+ * to use the real IO access functions, don't fake them out or redirect them
+ * for that case.
+ */
+#ifndef CONFIG_PCI
+
#include <asm/raw_io.h>
+#include <asm/kmap.h>
/*
* FIXME
@@ -25,4 +33,5 @@
#define writeb raw_outb
#define writew raw_outw
+#endif /* CONFIG_PCI */
#endif /* _ASM_M68K_VGA_H */
diff --git a/arch/m68k/include/asm/virtconvert.h b/arch/m68k/include/asm/virtconvert.h
index 4aea6be..dfe4308 100644
--- a/arch/m68k/include/asm/virtconvert.h
+++ b/arch/m68k/include/asm/virtconvert.h
@@ -16,11 +16,13 @@
/*
* Change virtual addresses to physical addresses and vv.
*/
+#define virt_to_phys virt_to_phys
static inline unsigned long virt_to_phys(void *address)
{
return __pa(address);
}
+#define phys_to_virt phys_to_virt
static inline void *phys_to_virt(unsigned long address)
{
return __va(address);
diff --git a/arch/m68k/include/asm/zorro.h b/arch/m68k/include/asm/zorro.h
index 96f64bf7..60fc4b6 100644
--- a/arch/m68k/include/asm/zorro.h
+++ b/arch/m68k/include/asm/zorro.h
@@ -3,6 +3,7 @@
#define _ASM_M68K_ZORRO_H
#include <asm/raw_io.h>
+#include <asm/kmap.h>
#define z_readb raw_inb
#define z_readw raw_inw
diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c
index c01b9b8..463572c 100644
--- a/arch/m68k/kernel/dma.c
+++ b/arch/m68k/kernel/dma.c
@@ -9,6 +9,7 @@
#include <linux/dma-mapping.h>
#include <linux/device.h>
#include <linux/kernel.h>
+#include <linux/platform_device.h>
#include <linux/scatterlist.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
@@ -165,3 +166,12 @@ const struct dma_map_ops m68k_dma_ops = {
.sync_sg_for_device = m68k_dma_sync_sg_for_device,
};
EXPORT_SYMBOL(m68k_dma_ops);
+
+void arch_setup_pdev_archdata(struct platform_device *pdev)
+{
+ if (pdev->dev.coherent_dma_mask == DMA_MASK_NONE &&
+ pdev->dev.dma_mask == NULL) {
+ pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
+ pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask;
+ }
+}
diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index dd25bfc..f35e3eb 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -527,21 +527,9 @@ static int hardware_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int hardware_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, hardware_proc_show, NULL);
-}
-
-static const struct file_operations hardware_proc_fops = {
- .open = hardware_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __init proc_hardware_init(void)
{
- proc_create("hardware", 0, NULL, &hardware_proc_fops);
+ proc_create_single("hardware", 0, NULL, hardware_proc_show);
return 0;
}
module_init(proc_hardware_init);
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index f7cd5ec..72850b8 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -576,41 +576,42 @@ static inline int rt_save_fpu_state(struct ucontext __user *uc, struct pt_regs *
static inline void siginfo_build_tests(void)
{
- /* This needs to be tested on m68k as it has a lesser
- * alignment requirment than x86 and that can cause surprises.
+ /*
+ * This needs to be tested on m68k as it has a lesser
+ * alignment requirement than x86 and that can cause surprises.
*/
/* This is part of the ABI and can never change in size: */
BUILD_BUG_ON(sizeof(siginfo_t) != 128);
- /* Ensure the know fields never change in location */
+ /* Ensure the known fields never change in location */
BUILD_BUG_ON(offsetof(siginfo_t, si_signo) != 0);
BUILD_BUG_ON(offsetof(siginfo_t, si_errno) != 4);
BUILD_BUG_ON(offsetof(siginfo_t, si_code) != 8);
/* _kill */
- BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x0C);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x0c);
BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x10);
/* _timer */
- BUILD_BUG_ON(offsetof(siginfo_t, si_tid) != 0x0C);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_tid) != 0x0c);
BUILD_BUG_ON(offsetof(siginfo_t, si_overrun) != 0x10);
BUILD_BUG_ON(offsetof(siginfo_t, si_value) != 0x14);
/* _rt */
- BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x0C);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x0c);
BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x10);
BUILD_BUG_ON(offsetof(siginfo_t, si_value) != 0x14);
/* _sigchld */
- BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x0C);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x0c);
BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x10);
BUILD_BUG_ON(offsetof(siginfo_t, si_status) != 0x14);
BUILD_BUG_ON(offsetof(siginfo_t, si_utime) != 0x18);
- BUILD_BUG_ON(offsetof(siginfo_t, si_stime) != 0x1C);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_stime) != 0x1c);
/* _sigfault */
- BUILD_BUG_ON(offsetof(siginfo_t, si_addr) != 0x0C);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_addr) != 0x0c);
/* _sigfault._mcerr */
BUILD_BUG_ON(offsetof(siginfo_t, si_addr_lsb) != 0x10);
@@ -623,11 +624,11 @@ static inline void siginfo_build_tests(void)
BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x12);
/* _sigpoll */
- BUILD_BUG_ON(offsetof(siginfo_t, si_band) != 0x0C);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_band) != 0x0c);
BUILD_BUG_ON(offsetof(siginfo_t, si_fd) != 0x10);
/* _sigsys */
- BUILD_BUG_ON(offsetof(siginfo_t, si_call_addr) != 0x0C);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_call_addr) != 0x0c);
BUILD_BUG_ON(offsetof(siginfo_t, si_syscall) != 0x10);
BUILD_BUG_ON(offsetof(siginfo_t, si_arch) != 0x14);
diff --git a/arch/m68k/kernel/time.c b/arch/m68k/kernel/time.c
index 97dd4e2..3a8b47f 100644
--- a/arch/m68k/kernel/time.c
+++ b/arch/m68k/kernel/time.c
@@ -71,23 +71,26 @@ static irqreturn_t timer_interrupt(int irq, void *dummy)
return IRQ_HANDLED;
}
-void read_persistent_clock(struct timespec *ts)
+#ifdef CONFIG_M68KCLASSIC
+#if !IS_BUILTIN(CONFIG_RTC_DRV_GENERIC)
+void read_persistent_clock64(struct timespec64 *ts)
{
struct rtc_time time;
+
ts->tv_sec = 0;
ts->tv_nsec = 0;
- if (mach_hwclk) {
- mach_hwclk(0, &time);
+ if (!mach_hwclk)
+ return;
- if ((time.tm_year += 1900) < 1970)
- time.tm_year += 100;
- ts->tv_sec = mktime(time.tm_year, time.tm_mon, time.tm_mday,
- time.tm_hour, time.tm_min, time.tm_sec);
- }
+ mach_hwclk(0, &time);
+
+ ts->tv_sec = mktime64(time.tm_year + 1900, time.tm_mon + 1, time.tm_mday,
+ time.tm_hour, time.tm_min, time.tm_sec);
}
+#endif
-#if defined(CONFIG_ARCH_USES_GETTIMEOFFSET) && IS_ENABLED(CONFIG_RTC_DRV_GENERIC)
+#if IS_ENABLED(CONFIG_RTC_DRV_GENERIC)
static int rtc_generic_get_time(struct device *dev, struct rtc_time *tm)
{
mach_hwclk(0, tm);
@@ -145,8 +148,8 @@ static int __init rtc_init(void)
}
module_init(rtc_init);
-
-#endif /* CONFIG_ARCH_USES_GETTIMEOFFSET */
+#endif /* CONFIG_RTC_DRV_GENERIC */
+#endif /* CONFIG M68KCLASSIC */
void __init time_init(void)
{
diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c
index c1cc4e9..b2fd000 100644
--- a/arch/m68k/kernel/traps.c
+++ b/arch/m68k/kernel/traps.c
@@ -1007,9 +1007,9 @@ void bad_super_trap (struct frame *fp)
asmlinkage void trap_c(struct frame *fp)
{
- int sig;
+ int sig, si_code;
+ void __user *addr;
int vector = (fp->ptregs.vector >> 2) & 0xff;
- siginfo_t info;
if (fp->ptregs.sr & PS_S) {
if (vector == VEC_TRACE) {
@@ -1029,21 +1029,21 @@ asmlinkage void trap_c(struct frame *fp)
/* send the appropriate signal to the user program */
switch (vector) {
case VEC_ADDRERR:
- info.si_code = BUS_ADRALN;
+ si_code = BUS_ADRALN;
sig = SIGBUS;
break;
case VEC_ILLEGAL:
case VEC_LINE10:
case VEC_LINE11:
- info.si_code = ILL_ILLOPC;
+ si_code = ILL_ILLOPC;
sig = SIGILL;
break;
case VEC_PRIV:
- info.si_code = ILL_PRVOPC;
+ si_code = ILL_PRVOPC;
sig = SIGILL;
break;
case VEC_COPROC:
- info.si_code = ILL_COPROC;
+ si_code = ILL_COPROC;
sig = SIGILL;
break;
case VEC_TRAP1:
@@ -1060,76 +1060,74 @@ asmlinkage void trap_c(struct frame *fp)
case VEC_TRAP12:
case VEC_TRAP13:
case VEC_TRAP14:
- info.si_code = ILL_ILLTRP;
+ si_code = ILL_ILLTRP;
sig = SIGILL;
break;
case VEC_FPBRUC:
case VEC_FPOE:
case VEC_FPNAN:
- info.si_code = FPE_FLTINV;
+ si_code = FPE_FLTINV;
sig = SIGFPE;
break;
case VEC_FPIR:
- info.si_code = FPE_FLTRES;
+ si_code = FPE_FLTRES;
sig = SIGFPE;
break;
case VEC_FPDIVZ:
- info.si_code = FPE_FLTDIV;
+ si_code = FPE_FLTDIV;
sig = SIGFPE;
break;
case VEC_FPUNDER:
- info.si_code = FPE_FLTUND;
+ si_code = FPE_FLTUND;
sig = SIGFPE;
break;
case VEC_FPOVER:
- info.si_code = FPE_FLTOVF;
+ si_code = FPE_FLTOVF;
sig = SIGFPE;
break;
case VEC_ZERODIV:
- info.si_code = FPE_INTDIV;
+ si_code = FPE_INTDIV;
sig = SIGFPE;
break;
case VEC_CHK:
case VEC_TRAP:
- info.si_code = FPE_INTOVF;
+ si_code = FPE_INTOVF;
sig = SIGFPE;
break;
case VEC_TRACE: /* ptrace single step */
- info.si_code = TRAP_TRACE;
+ si_code = TRAP_TRACE;
sig = SIGTRAP;
break;
case VEC_TRAP15: /* breakpoint */
- info.si_code = TRAP_BRKPT;
+ si_code = TRAP_BRKPT;
sig = SIGTRAP;
break;
default:
- info.si_code = ILL_ILLOPC;
+ si_code = ILL_ILLOPC;
sig = SIGILL;
break;
}
- info.si_signo = sig;
- info.si_errno = 0;
switch (fp->ptregs.format) {
default:
- info.si_addr = (void *) fp->ptregs.pc;
+ addr = (void __user *) fp->ptregs.pc;
break;
case 2:
- info.si_addr = (void *) fp->un.fmt2.iaddr;
+ addr = (void __user *) fp->un.fmt2.iaddr;
break;
case 7:
- info.si_addr = (void *) fp->un.fmt7.effaddr;
+ addr = (void __user *) fp->un.fmt7.effaddr;
break;
case 9:
- info.si_addr = (void *) fp->un.fmt9.iaddr;
+ addr = (void __user *) fp->un.fmt9.iaddr;
break;
case 10:
- info.si_addr = (void *) fp->un.fmta.daddr;
+ addr = (void __user *) fp->un.fmta.daddr;
break;
case 11:
- info.si_addr = (void *) fp->un.fmtb.daddr;
+ addr = (void __user*) fp->un.fmtb.daddr;
break;
}
- force_sig_info (sig, &info, current);
+ force_sig_fault(sig, si_code, addr, current);
}
void die_if_kernel (char *str, struct pt_regs *fp, int nr)
@@ -1161,12 +1159,6 @@ asmlinkage void fpsp040_die(void)
#ifdef CONFIG_M68KFPU_EMU
asmlinkage void fpemu_signal(int signal, int code, void *addr)
{
- siginfo_t info;
-
- info.si_signo = signal;
- info.si_errno = 0;
- info.si_code = code;
- info.si_addr = addr;
- force_sig_info(signal, &info, current);
+ force_sig_fault(signal, code, addr, current);
}
#endif
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index 0c3275a..e522307 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -1005,7 +1005,7 @@ int __init mac_platform_init(void)
struct resource swim_rsrc = {
.flags = IORESOURCE_MEM,
.start = (resource_size_t)swim_base,
- .end = (resource_size_t)swim_base + 0x2000,
+ .end = (resource_size_t)swim_base + 0x1FFF,
};
platform_device_register_simple("swim", -1, &swim_rsrc, 1);
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index 03253c4f..f2ff377 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -21,35 +21,32 @@ extern void die_if_kernel(char *, struct pt_regs *, long);
int send_fault_sig(struct pt_regs *regs)
{
- siginfo_t siginfo;
+ int signo, si_code;
+ void __user *addr;
- clear_siginfo(&siginfo);
- siginfo.si_signo = current->thread.signo;
- siginfo.si_code = current->thread.code;
- siginfo.si_addr = (void *)current->thread.faddr;
- pr_debug("send_fault_sig: %p,%d,%d\n", siginfo.si_addr,
- siginfo.si_signo, siginfo.si_code);
+ signo = current->thread.signo;
+ si_code = current->thread.code;
+ addr = (void __user *)current->thread.faddr;
+ pr_debug("send_fault_sig: %p,%d,%d\n", addr, signo, si_code);
if (user_mode(regs)) {
- force_sig_info(siginfo.si_signo,
- &siginfo, current);
+ force_sig_fault(signo, si_code, addr, current);
} else {
if (fixup_exception(regs))
return -1;
- //if (siginfo.si_signo == SIGBUS)
- // force_sig_info(siginfo.si_signo,
- // &siginfo, current);
+ //if (signo == SIGBUS)
+ // force_sig_fault(si_signo, si_code, addr, current);
/*
* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice.
*/
- if ((unsigned long)siginfo.si_addr < PAGE_SIZE)
+ if ((unsigned long)addr < PAGE_SIZE)
pr_alert("Unable to handle kernel NULL pointer dereference");
else
pr_alert("Unable to handle kernel access");
- pr_cont(" at virtual address %p\n", siginfo.si_addr);
+ pr_cont(" at virtual address %p\n", addr);
die_if_kernel("Oops", regs, 0 /*error_code*/);
do_exit(SIGKILL);
}
diff --git a/arch/m68k/mm/kmap.c b/arch/m68k/mm/kmap.c
index c2a3832..40a3b32 100644
--- a/arch/m68k/mm/kmap.c
+++ b/arch/m68k/mm/kmap.c
@@ -89,7 +89,8 @@ static inline void free_io_area(void *addr)
for (p = &iolist ; (tmp = *p) ; p = &tmp->next) {
if (tmp->addr == addr) {
*p = tmp->next;
- __iounmap(tmp->addr, tmp->size);
+ /* remove gap added in get_io_area() */
+ __iounmap(tmp->addr, tmp->size - IO_SIZE);
kfree(tmp);
return;
}
@@ -125,6 +126,10 @@ void __iomem *__ioremap(unsigned long physaddr, unsigned long size, int cachefla
return (void __iomem *)physaddr;
}
#endif
+#ifdef CONFIG_COLDFIRE
+ if (__cf_internalio(physaddr))
+ return (void __iomem *) physaddr;
+#endif
#ifdef DEBUG
printk("ioremap: 0x%lx,0x%lx(%d) - ", physaddr, size, cacheflag);
@@ -235,6 +240,10 @@ void iounmap(void __iomem *addr)
((unsigned long)addr > 0x60000000)))
free_io_area((__force void *)addr);
#else
+#ifdef CONFIG_COLDFIRE
+ if (cf_internalio(addr))
+ return;
+#endif
free_io_area((__force void *)addr);
#endif
}
diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c
index 8778612..f8a710f 100644
--- a/arch/m68k/mvme147/config.c
+++ b/arch/m68k/mvme147/config.c
@@ -153,12 +153,14 @@ int mvme147_hwclk(int op, struct rtc_time *t)
if (!op) {
m147_rtc->ctrl = RTC_READ;
t->tm_year = bcd2int (m147_rtc->bcd_year);
- t->tm_mon = bcd2int (m147_rtc->bcd_mth);
+ t->tm_mon = bcd2int(m147_rtc->bcd_mth) - 1;
t->tm_mday = bcd2int (m147_rtc->bcd_dom);
t->tm_hour = bcd2int (m147_rtc->bcd_hr);
t->tm_min = bcd2int (m147_rtc->bcd_min);
t->tm_sec = bcd2int (m147_rtc->bcd_sec);
m147_rtc->ctrl = 0;
+ if (t->tm_year < 70)
+ t->tm_year += 100;
}
return 0;
}
diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c
index 6fa06d4..4ffd9ef 100644
--- a/arch/m68k/mvme16x/config.c
+++ b/arch/m68k/mvme16x/config.c
@@ -400,12 +400,14 @@ int mvme16x_hwclk(int op, struct rtc_time *t)
if (!op) {
rtc->ctrl = RTC_READ;
t->tm_year = bcd2int (rtc->bcd_year);
- t->tm_mon = bcd2int (rtc->bcd_mth);
+ t->tm_mon = bcd2int(rtc->bcd_mth) - 1;
t->tm_mday = bcd2int (rtc->bcd_dom);
t->tm_hour = bcd2int (rtc->bcd_hr);
t->tm_min = bcd2int (rtc->bcd_min);
t->tm_sec = bcd2int (rtc->bcd_sec);
rtc->ctrl = 0;
+ if (t->tm_year < 70)
+ t->tm_year += 100;
}
return 0;
}
diff --git a/arch/m68k/sun3/intersil.c b/arch/m68k/sun3/intersil.c
index 2cd0bcb..d911070 100644
--- a/arch/m68k/sun3/intersil.c
+++ b/arch/m68k/sun3/intersil.c
@@ -48,9 +48,9 @@ int sun3_hwclk(int set, struct rtc_time *t)
todintersil->hour = t->tm_hour;
todintersil->minute = t->tm_min;
todintersil->second = t->tm_sec;
- todintersil->month = t->tm_mon;
+ todintersil->month = t->tm_mon + 1;
todintersil->day = t->tm_mday;
- todintersil->year = t->tm_year - 68;
+ todintersil->year = (t->tm_year - 68) % 100;
todintersil->weekday = t->tm_wday;
} else {
/* read clock */
@@ -58,10 +58,12 @@ int sun3_hwclk(int set, struct rtc_time *t)
t->tm_hour = todintersil->hour;
t->tm_min = todintersil->minute;
t->tm_sec = todintersil->second;
- t->tm_mon = todintersil->month;
+ t->tm_mon = todintersil->month - 1;
t->tm_mday = todintersil->day;
t->tm_year = todintersil->year + 68;
t->tm_wday = todintersil->weekday;
+ if (t->tm_year < 70)
+ t->tm_year += 100;
}
intersil_clock->cmd_reg = START_VAL;
diff --git a/arch/m68k/sun3x/time.c b/arch/m68k/sun3x/time.c
index 7a2c53d..047e2bc 100644
--- a/arch/m68k/sun3x/time.c
+++ b/arch/m68k/sun3x/time.c
@@ -52,8 +52,8 @@ int sun3x_hwclk(int set, struct rtc_time *t)
h->hour = bin2bcd(t->tm_hour);
h->wday = bin2bcd(t->tm_wday);
h->mday = bin2bcd(t->tm_mday);
- h->month = bin2bcd(t->tm_mon);
- h->year = bin2bcd(t->tm_year);
+ h->month = bin2bcd(t->tm_mon + 1);
+ h->year = bin2bcd(t->tm_year % 100);
h->csr &= ~C_WRITE;
} else {
h->csr |= C_READ;
@@ -62,9 +62,11 @@ int sun3x_hwclk(int set, struct rtc_time *t)
t->tm_hour = bcd2bin(h->hour);
t->tm_wday = bcd2bin(h->wday);
t->tm_mday = bcd2bin(h->mday);
- t->tm_mon = bcd2bin(h->month);
+ t->tm_mon = bcd2bin(h->month) - 1;
t->tm_year = bcd2bin(h->year);
h->csr &= ~C_READ;
+ if (t->tm_year < 70)
+ t->tm_year += 100;
}
local_irq_restore(flags);
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 3817a3e..d147821 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -19,7 +19,6 @@
select HAVE_ARCH_HASH
select HAVE_ARCH_KGDB
select HAVE_DEBUG_KMEMLEAK
- select HAVE_DMA_API_DEBUG
select HAVE_DYNAMIC_FTRACE
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_GRAPH_TRACER
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 3c80a5a..fe6a6c6 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -2,6 +2,7 @@
generic-y += bitops.h
generic-y += bug.h
generic-y += bugs.h
+generic-y += compat.h
generic-y += device.h
generic-y += div64.h
generic-y += emergency-restart.h
diff --git a/arch/microblaze/include/asm/pci.h b/arch/microblaze/include/asm/pci.h
index 5de871e..0033786 100644
--- a/arch/microblaze/include/asm/pci.h
+++ b/arch/microblaze/include/asm/pci.h
@@ -62,12 +62,6 @@ extern int pci_mmap_legacy_page_range(struct pci_bus *bus,
#define HAVE_PCI_LEGACY 1
-/* The PCI address space does equal the physical memory
- * address space (no IOMMU). The IDE and SCSI device layers use
- * this boolean for bounce buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS (1)
-
extern void pcibios_claim_one_bus(struct pci_bus *b);
extern void pcibios_finish_adding_to_bus(struct pci_bus *bus);
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index c91e8ce..3145e7d 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -184,14 +184,3 @@ const struct dma_map_ops dma_nommu_ops = {
.sync_sg_for_device = dma_nommu_sync_sg_for_device,
};
EXPORT_SYMBOL(dma_nommu_ops);
-
-/* Number of entries preallocated for DMA-API debugging */
-#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-
-static int __init dma_init(void)
-{
- dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
-
- return 0;
-}
-fs_initcall(dma_init);
diff --git a/arch/microblaze/kernel/exceptions.c b/arch/microblaze/kernel/exceptions.c
index e6f338d..eafff21 100644
--- a/arch/microblaze/kernel/exceptions.c
+++ b/arch/microblaze/kernel/exceptions.c
@@ -60,16 +60,10 @@ asmlinkage void sw_exception(struct pt_regs *regs)
void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
{
- siginfo_t info;
-
if (kernel_mode(regs))
die("Exception in kernel mode", regs, signr);
- info.si_signo = signr;
- info.si_errno = 0;
- info.si_code = code;
- info.si_addr = (void __user *) addr;
- force_sig_info(signr, &info, current);
+ force_sig_fault(signr, code, (void __user *)addr, current);
}
asmlinkage void full_exception(struct pt_regs *regs, unsigned int type,
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index f91b30f..af60744 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -88,7 +88,6 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
- siginfo_t info;
int code = SEGV_MAPERR;
int is_write = error_code & ESR_S;
int fault;
@@ -269,11 +268,6 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
/* User mode accesses cause a SIGSEGV */
if (user_mode(regs)) {
_exception(SIGSEGV, regs, code, address);
-/* info.si_signo = SIGSEGV;
- info.si_errno = 0;
- info.si_code = code;
- info.si_addr = (void *) address;
- force_sig_info(SIGSEGV, &info, current);*/
return;
}
@@ -295,11 +289,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
do_sigbus:
up_read(&mm->mmap_sem);
if (user_mode(regs)) {
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_ADRERR;
- info.si_addr = (void __user *)address;
- force_sig_info(SIGBUS, &info, current);
+ force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address, current);
return;
}
bad_page_fault(regs, address, SIGBUS);
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 225c95d..7074b22 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -42,7 +42,6 @@
select HAVE_C_RECORDMCOUNT
select HAVE_DEBUG_KMEMLEAK
select HAVE_DEBUG_STACKOVERFLOW
- select HAVE_DMA_API_DEBUG
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
select HAVE_EXIT_THREAD
@@ -132,7 +131,7 @@
config MIPS_ALCHEMY
bool "Alchemy processor based machines"
- select ARCH_PHYS_ADDR_T_64BIT
+ select PHYS_ADDR_T_64BIT
select CEVT_R4K
select CSRC_R4K
select IRQ_MIPS_CPU
@@ -890,7 +889,7 @@
bool "Cavium Networks Octeon SoC based boards"
select CEVT_R4K
select ARCH_HAS_PHYS_TO_DMA
- select ARCH_PHYS_ADDR_T_64BIT
+ select PHYS_ADDR_T_64BIT
select DMA_COHERENT
select SYS_SUPPORTS_64BIT_KERNEL
select SYS_SUPPORTS_BIG_ENDIAN
@@ -912,6 +911,7 @@
select MIPS_NR_CPU_NR_MAP_1024
select BUILTIN_DTB
select MTD_COMPLEX_MAPPINGS
+ select SWIOTLB
select SYS_SUPPORTS_RELOCATABLE
help
This option supports all of the Octeon reference boards from Cavium
@@ -936,7 +936,7 @@
select SWAP_IO_SPACE
select SYS_SUPPORTS_32BIT_KERNEL
select SYS_SUPPORTS_64BIT_KERNEL
- select ARCH_PHYS_ADDR_T_64BIT
+ select PHYS_ADDR_T_64BIT
select SYS_SUPPORTS_BIG_ENDIAN
select SYS_SUPPORTS_HIGHMEM
select DMA_COHERENT
@@ -962,7 +962,7 @@
select HW_HAS_PCI
select SYS_SUPPORTS_32BIT_KERNEL
select SYS_SUPPORTS_64BIT_KERNEL
- select ARCH_PHYS_ADDR_T_64BIT
+ select PHYS_ADDR_T_64BIT
select GPIOLIB
select SYS_SUPPORTS_BIG_ENDIAN
select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -1101,9 +1101,6 @@
config FW_CFE
bool
-config ARCH_DMA_ADDR_T_64BIT
- def_bool (HIGHMEM && ARCH_PHYS_ADDR_T_64BIT) || 64BIT
-
config ARCH_SUPPORTS_UPROBES
bool
@@ -1122,9 +1119,6 @@
bool
select NEED_DMA_MAP_STATE
-config NEED_DMA_MAP_STATE
- bool
-
config SYS_HAS_EARLY_PRINTK
bool
@@ -1373,6 +1367,7 @@
select MIPS_PGD_C0_CONTEXT
select MIPS_L1_CACHE_SHIFT_6
select GPIOLIB
+ select SWIOTLB
help
The Loongson 3 processor implements the MIPS64R2 instruction
set with many extensions.
@@ -1770,7 +1765,7 @@
depends on SYS_SUPPORTS_HIGHMEM
select XPA
select HIGHMEM
- select ARCH_PHYS_ADDR_T_64BIT
+ select PHYS_ADDR_T_64BIT
default n
help
Choose this option if you want to enable the Extended Physical
@@ -2402,9 +2397,6 @@
default y
-config ARCH_PHYS_ADDR_T_64BIT
- bool
-
choice
prompt "SmartMIPS or microMIPS ASE support"
@@ -2556,7 +2548,7 @@
Say Y to support efficient handling of discontiguous physical memory,
for architectures which are either NUMA (Non-Uniform Memory Access)
or have huge holes in the physical address space for other reasons.
- See <file:Documentation/vm/numa> for more.
+ See <file:Documentation/vm/numa.rst> for more.
config ARCH_SPARSEMEM_ENABLE
bool
diff --git a/arch/mips/boot/compressed/uart-16550.c b/arch/mips/boot/compressed/uart-16550.c
index b3043c0..aee8d7b 100644
--- a/arch/mips/boot/compressed/uart-16550.c
+++ b/arch/mips/boot/compressed/uart-16550.c
@@ -18,9 +18,9 @@
#define PORT(offset) (CKSEG1ADDR(AR7_REGS_UART0) + (4 * offset))
#endif
-#if defined(CONFIG_MACH_JZ4740) || defined(CONFIG_MACH_JZ4780)
-#include <asm/mach-jz4740/base.h>
-#define PORT(offset) (CKSEG1ADDR(JZ4740_UART0_BASE_ADDR) + (4 * offset))
+#ifdef CONFIG_MACH_INGENIC
+#define INGENIC_UART0_BASE_ADDR 0x10030000
+#define PORT(offset) (CKSEG1ADDR(INGENIC_UART0_BASE_ADDR) + (4 * offset))
#endif
#ifdef CONFIG_CPU_XLR
diff --git a/arch/mips/boot/dts/img/boston.dts b/arch/mips/boot/dts/img/boston.dts
index 1bd1054..65af3f6 100644
--- a/arch/mips/boot/dts/img/boston.dts
+++ b/arch/mips/boot/dts/img/boston.dts
@@ -51,6 +51,8 @@
ranges = <0x02000000 0 0x40000000
0x40000000 0 0x40000000>;
+ bus-range = <0x00 0xff>;
+
interrupt-map-mask = <0 0 0 7>;
interrupt-map = <0 0 0 1 &pci0_intc 1>,
<0 0 0 2 &pci0_intc 2>,
@@ -79,6 +81,8 @@
ranges = <0x02000000 0 0x20000000
0x20000000 0 0x20000000>;
+ bus-range = <0x00 0xff>;
+
interrupt-map-mask = <0 0 0 7>;
interrupt-map = <0 0 0 1 &pci1_intc 1>,
<0 0 0 2 &pci1_intc 2>,
@@ -107,6 +111,8 @@
ranges = <0x02000000 0 0x16000000
0x16000000 0 0x100000>;
+ bus-range = <0x00 0xff>;
+
interrupt-map-mask = <0 0 0 7>;
interrupt-map = <0 0 0 1 &pci2_intc 1>,
<0 0 0 2 &pci2_intc 2>,
diff --git a/arch/mips/boot/dts/xilfpga/Makefile b/arch/mips/boot/dts/xilfpga/Makefile
index 9987e0e3..69ca005 100644
--- a/arch/mips/boot/dts/xilfpga/Makefile
+++ b/arch/mips/boot/dts/xilfpga/Makefile
@@ -1,4 +1,2 @@
# SPDX-License-Identifier: GPL-2.0
dtb-$(CONFIG_FIT_IMAGE_FDT_XILFPGA) += nexys4ddr.dtb
-
-obj-y += $(patsubst %.dtb, %.dtb.o, $(dtb-y))
diff --git a/arch/mips/cavium-octeon/Kconfig b/arch/mips/cavium-octeon/Kconfig
index b5eee1a..4984e46 100644
--- a/arch/mips/cavium-octeon/Kconfig
+++ b/arch/mips/cavium-octeon/Kconfig
@@ -67,18 +67,6 @@
help
Lock the kernel's implementation of memcpy() into L2.
-config IOMMU_HELPER
- bool
-
-config NEED_SG_DMA_LENGTH
- bool
-
-config SWIOTLB
- def_bool y
- select DMA_DIRECT_OPS
- select IOMMU_HELPER
- select NEED_SG_DMA_LENGTH
-
config OCTEON_ILM
tristate "Module to measure interrupt latency using Octeon CIU Timer"
help
diff --git a/arch/mips/generic/Platform b/arch/mips/generic/Platform
index b51432d..0dd0d5d 100644
--- a/arch/mips/generic/Platform
+++ b/arch/mips/generic/Platform
@@ -16,3 +16,4 @@
its-y := vmlinux.its.S
its-$(CONFIG_FIT_IMAGE_FDT_BOSTON) += board-boston.its.S
its-$(CONFIG_FIT_IMAGE_FDT_NI169445) += board-ni169445.its.S
+its-$(CONFIG_FIT_IMAGE_FDT_XILFPGA) += board-xilfpga.its.S
diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h
index 9a0fa66..78675f1 100644
--- a/arch/mips/include/asm/compat.h
+++ b/arch/mips/include/asm/compat.h
@@ -14,7 +14,6 @@
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
-typedef s32 compat_time_t;
typedef s32 compat_clock_t;
typedef s32 compat_suseconds_t;
@@ -38,24 +37,16 @@ typedef struct {
typedef s32 compat_timer_t;
typedef s32 compat_key_t;
+typedef s16 compat_short_t;
typedef s32 compat_int_t;
typedef s32 compat_long_t;
typedef s64 compat_s64;
+typedef u16 compat_ushort_t;
typedef u32 compat_uint_t;
typedef u32 compat_ulong_t;
typedef u64 compat_u64;
typedef u32 compat_uptr_t;
-struct compat_timespec {
- compat_time_t tv_sec;
- s32 tv_nsec;
-};
-
-struct compat_timeval {
- compat_time_t tv_sec;
- s32 tv_usec;
-};
-
struct compat_stat {
compat_dev_t st_dev;
s32 st_pad1[3];
@@ -168,35 +159,35 @@ struct compat_ipc64_perm {
struct compat_semid64_ds {
struct compat_ipc64_perm sem_perm;
- compat_time_t sem_otime;
- compat_time_t sem_ctime;
+ compat_ulong_t sem_otime;
+ compat_ulong_t sem_ctime;
compat_ulong_t sem_nsems;
- compat_ulong_t __unused1;
- compat_ulong_t __unused2;
+ compat_ulong_t sem_otime_high;
+ compat_ulong_t sem_ctime_high;
};
struct compat_msqid64_ds {
struct compat_ipc64_perm msg_perm;
#ifndef CONFIG_CPU_LITTLE_ENDIAN
- compat_ulong_t __unused1;
+ compat_ulong_t msg_stime_high;
#endif
- compat_time_t msg_stime;
+ compat_ulong_t msg_stime;
#ifdef CONFIG_CPU_LITTLE_ENDIAN
- compat_ulong_t __unused1;
+ compat_ulong_t msg_stime_high;
#endif
#ifndef CONFIG_CPU_LITTLE_ENDIAN
- compat_ulong_t __unused2;
+ compat_ulong_t msg_rtime_high;
#endif
- compat_time_t msg_rtime;
+ compat_ulong_t msg_rtime;
#ifdef CONFIG_CPU_LITTLE_ENDIAN
- compat_ulong_t __unused2;
+ compat_ulong_t msg_rtime_high;
#endif
#ifndef CONFIG_CPU_LITTLE_ENDIAN
- compat_ulong_t __unused3;
+ compat_ulong_t msg_ctime_high;
#endif
- compat_time_t msg_ctime;
+ compat_ulong_t msg_ctime;
#ifdef CONFIG_CPU_LITTLE_ENDIAN
- compat_ulong_t __unused3;
+ compat_ulong_t msg_ctime_high;
#endif
compat_ulong_t msg_cbytes;
compat_ulong_t msg_qnum;
@@ -210,14 +201,16 @@ struct compat_msqid64_ds {
struct compat_shmid64_ds {
struct compat_ipc64_perm shm_perm;
compat_size_t shm_segsz;
- compat_time_t shm_atime;
- compat_time_t shm_dtime;
- compat_time_t shm_ctime;
+ compat_ulong_t shm_atime;
+ compat_ulong_t shm_dtime;
+ compat_ulong_t shm_ctime;
compat_pid_t shm_cpid;
compat_pid_t shm_lpid;
compat_ulong_t shm_nattch;
- compat_ulong_t __unused1;
- compat_ulong_t __unused2;
+ compat_ushort_t shm_atime_high;
+ compat_ushort_t shm_dtime_high;
+ compat_ushort_t shm_ctime_high;
+ compat_ushort_t __unused2;
};
/* MIPS has unusual order of fields in stack_t */
diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index 0cbf3af..a7d0b83 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -307,7 +307,7 @@ static inline void iounmap(const volatile void __iomem *addr)
#if defined(CONFIG_CPU_CAVIUM_OCTEON) || defined(CONFIG_LOONGSON3_ENHANCEMENT)
#define war_io_reorder_wmb() wmb()
#else
-#define war_io_reorder_wmb() do { } while (0)
+#define war_io_reorder_wmb() barrier()
#endif
#define __BUILD_MEMORY_SINGLE(pfx, bwlq, type, irq) \
@@ -377,6 +377,8 @@ static inline type pfx##read##bwlq(const volatile void __iomem *mem) \
BUG(); \
} \
\
+ /* prevent prefetching of coherent DMA data prematurely */ \
+ rmb(); \
return pfx##ioswab##bwlq(__mem, __val); \
}
diff --git a/arch/mips/include/asm/pci.h b/arch/mips/include/asm/pci.h
index 2339f42..4360998 100644
--- a/arch/mips/include/asm/pci.h
+++ b/arch/mips/include/asm/pci.h
@@ -121,13 +121,6 @@ extern unsigned long PCIBIOS_MIN_MEM;
#include <linux/string.h>
#include <asm/io.h>
-/*
- * The PCI address space does equal the physical memory address space.
- * The networking and block device layers use this boolean for bounce
- * buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS (1)
-
#ifdef CONFIG_PCI_DOMAINS_GENERIC
static inline int pci_proc_domain(struct pci_bus *bus)
{
diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h
index b713069..0662901 100644
--- a/arch/mips/include/asm/uaccess.h
+++ b/arch/mips/include/asm/uaccess.h
@@ -654,6 +654,13 @@ __clear_user(void __user *addr, __kernel_size_t size)
{
__kernel_size_t res;
+#ifdef CONFIG_CPU_MICROMIPS
+/* micromips memset / bzero also clobbers t7 & t8 */
+#define bzero_clobbers "$4", "$5", "$6", __UA_t0, __UA_t1, "$15", "$24", "$31"
+#else
+#define bzero_clobbers "$4", "$5", "$6", __UA_t0, __UA_t1, "$31"
+#endif /* CONFIG_CPU_MICROMIPS */
+
if (eva_kernel_access()) {
__asm__ __volatile__(
"move\t$4, %1\n\t"
@@ -663,7 +670,7 @@ __clear_user(void __user *addr, __kernel_size_t size)
"move\t%0, $6"
: "=r" (res)
: "r" (addr), "r" (size)
- : "$4", "$5", "$6", __UA_t0, __UA_t1, "$31");
+ : bzero_clobbers);
} else {
might_fault();
__asm__ __volatile__(
@@ -674,7 +681,7 @@ __clear_user(void __user *addr, __kernel_size_t size)
"move\t%0, $6"
: "=r" (res)
: "r" (addr), "r" (size)
- : "$4", "$5", "$6", __UA_t0, __UA_t1, "$31");
+ : bzero_clobbers);
}
return res;
diff --git a/arch/mips/include/uapi/asm/msgbuf.h b/arch/mips/include/uapi/asm/msgbuf.h
index eb4d0f9..46aa15b 100644
--- a/arch/mips/include/uapi/asm/msgbuf.h
+++ b/arch/mips/include/uapi/asm/msgbuf.h
@@ -9,33 +9,15 @@
* between kernel and user space.
*
* Pad space is left for:
- * - extension of time_t to 64-bit on 32-bitsystem to solve the y2038 problem
* - 2 miscellaneous unsigned long values
*/
+#if defined(__mips64)
struct msqid64_ds {
struct ipc64_perm msg_perm;
-#if !defined(__mips64) && defined(__MIPSEB__)
- unsigned long __unused1;
-#endif
__kernel_time_t msg_stime; /* last msgsnd time */
-#if !defined(__mips64) && defined(__MIPSEL__)
- unsigned long __unused1;
-#endif
-#if !defined(__mips64) && defined(__MIPSEB__)
- unsigned long __unused2;
-#endif
__kernel_time_t msg_rtime; /* last msgrcv time */
-#if !defined(__mips64) && defined(__MIPSEL__)
- unsigned long __unused2;
-#endif
-#if !defined(__mips64) && defined(__MIPSEB__)
- unsigned long __unused3;
-#endif
__kernel_time_t msg_ctime; /* last change time */
-#if !defined(__mips64) && defined(__MIPSEL__)
- unsigned long __unused3;
-#endif
unsigned long msg_cbytes; /* current number of bytes on queue */
unsigned long msg_qnum; /* number of messages in queue */
unsigned long msg_qbytes; /* max number of bytes on queue */
@@ -44,5 +26,42 @@ struct msqid64_ds {
unsigned long __unused4;
unsigned long __unused5;
};
+#elif defined (__MIPSEB__)
+struct msqid64_ds {
+ struct ipc64_perm msg_perm;
+ unsigned long msg_stime_high;
+ unsigned long msg_stime; /* last msgsnd time */
+ unsigned long msg_rtime_high;
+ unsigned long msg_rtime; /* last msgrcv time */
+ unsigned long msg_ctime_high;
+ unsigned long msg_ctime; /* last change time */
+ unsigned long msg_cbytes; /* current number of bytes on queue */
+ unsigned long msg_qnum; /* number of messages in queue */
+ unsigned long msg_qbytes; /* max number of bytes on queue */
+ __kernel_pid_t msg_lspid; /* pid of last msgsnd */
+ __kernel_pid_t msg_lrpid; /* last receive pid */
+ unsigned long __unused4;
+ unsigned long __unused5;
+};
+#elif defined (__MIPSEL__)
+struct msqid64_ds {
+ struct ipc64_perm msg_perm;
+ unsigned long msg_stime; /* last msgsnd time */
+ unsigned long msg_stime_high;
+ unsigned long msg_rtime; /* last msgrcv time */
+ unsigned long msg_rtime_high;
+ unsigned long msg_ctime; /* last change time */
+ unsigned long msg_ctime_high;
+ unsigned long msg_cbytes; /* current number of bytes on queue */
+ unsigned long msg_qnum; /* number of messages in queue */
+ unsigned long msg_qbytes; /* max number of bytes on queue */
+ __kernel_pid_t msg_lspid; /* pid of last msgsnd */
+ __kernel_pid_t msg_lrpid; /* last receive pid */
+ unsigned long __unused4;
+ unsigned long __unused5;
+};
+#else
+#warning no endianess set
+#endif
#endif /* _ASM_MSGBUF_H */
diff --git a/arch/mips/include/uapi/asm/sembuf.h b/arch/mips/include/uapi/asm/sembuf.h
index 2c0f507..60c89e6 100644
--- a/arch/mips/include/uapi/asm/sembuf.h
+++ b/arch/mips/include/uapi/asm/sembuf.h
@@ -7,10 +7,11 @@
* Note extra padding because this structure is passed back and forth
* between kernel and user space.
*
- * Pad space is left for:
- * - 2 miscellaneous 64-bit values
+ * Pad space is left for 2 miscellaneous 64-bit values on mips64,
+ * but used for the upper 32 bit of the time values on mips32.
*/
+#ifdef __mips64
struct semid64_ds {
struct ipc64_perm sem_perm; /* permissions .. see ipc.h */
__kernel_time_t sem_otime; /* last semop time */
@@ -19,5 +20,15 @@ struct semid64_ds {
unsigned long __unused1;
unsigned long __unused2;
};
+#else
+struct semid64_ds {
+ struct ipc64_perm sem_perm; /* permissions .. see ipc.h */
+ unsigned long sem_otime; /* last semop time */
+ unsigned long sem_ctime; /* last change time */
+ unsigned long sem_nsems; /* no. of semaphores in array */
+ unsigned long sem_otime_high;
+ unsigned long sem_ctime_high;
+};
+#endif
#endif /* _ASM_SEMBUF_H */
diff --git a/arch/mips/include/uapi/asm/shmbuf.h b/arch/mips/include/uapi/asm/shmbuf.h
index 379e6bc..9b9bba3 100644
--- a/arch/mips/include/uapi/asm/shmbuf.h
+++ b/arch/mips/include/uapi/asm/shmbuf.h
@@ -7,10 +7,13 @@
* Note extra padding because this structure is passed back and forth
* between kernel and user space.
*
- * Pad space is left for:
- * - 2 miscellaneous 32-bit rsp. 64-bit values
+ * As MIPS was lacking proper padding after shm_?time, we use 48 bits
+ * of the padding at the end to store a few additional bits of the time.
+ * libc implementations need to take care to convert this into a proper
+ * data structure when moving to 64-bit time_t.
*/
+#ifdef __mips64
struct shmid64_ds {
struct ipc64_perm shm_perm; /* operation perms */
size_t shm_segsz; /* size of segment (bytes) */
@@ -23,6 +26,22 @@ struct shmid64_ds {
unsigned long __unused1;
unsigned long __unused2;
};
+#else
+struct shmid64_ds {
+ struct ipc64_perm shm_perm; /* operation perms */
+ size_t shm_segsz; /* size of segment (bytes) */
+ unsigned long shm_atime; /* last attach time */
+ unsigned long shm_dtime; /* last detach time */
+ unsigned long shm_ctime; /* last change time */
+ __kernel_pid_t shm_cpid; /* pid of creator */
+ __kernel_pid_t shm_lpid; /* pid of last operator */
+ unsigned long shm_nattch; /* no. of current attaches */
+ unsigned short shm_atime_high;
+ unsigned short shm_dtime_high;
+ unsigned short shm_ctime_high;
+ unsigned short __unused1;
+};
+#endif
struct shminfo64 {
unsigned long shmmax;
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index b9e9bf6..3775a8d 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -721,6 +721,10 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
if (value & ~known_bits)
return -EOPNOTSUPP;
+ /* Setting FRE without FR is not supported. */
+ if ((value & (PR_FP_MODE_FR | PR_FP_MODE_FRE)) == PR_FP_MODE_FRE)
+ return -EOPNOTSUPP;
+
/* Avoid inadvertently triggering emulation */
if ((value & PR_FP_MODE_FR) && raw_cpu_has_fpu &&
!(raw_current_cpu_data.fpu_id & MIPS_FPIR_F64))
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 0b23b1a..0c0c23c 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -463,7 +463,7 @@ static int fpr_get_msa(struct task_struct *target,
/*
* Copy the floating-point context to the supplied NT_PRFPREG buffer.
* Choose the appropriate helper for general registers, and then copy
- * the FCSR register separately.
+ * the FCSR and FIR registers separately.
*/
static int fpr_get(struct task_struct *target,
const struct user_regset *regset,
@@ -471,6 +471,7 @@ static int fpr_get(struct task_struct *target,
void *kbuf, void __user *ubuf)
{
const int fcr31_pos = NUM_FPU_REGS * sizeof(elf_fpreg_t);
+ const int fir_pos = fcr31_pos + sizeof(u32);
int err;
if (sizeof(target->thread.fpu.fpr[0]) == sizeof(elf_fpreg_t))
@@ -483,6 +484,12 @@ static int fpr_get(struct task_struct *target,
err = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
&target->thread.fpu.fcr31,
fcr31_pos, fcr31_pos + sizeof(u32));
+ if (err)
+ return err;
+
+ err = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+ &boot_cpu_data.fpu_id,
+ fir_pos, fir_pos + sizeof(u32));
return err;
}
@@ -531,7 +538,8 @@ static int fpr_set_msa(struct task_struct *target,
/*
* Copy the supplied NT_PRFPREG buffer to the floating-point context.
* Choose the appropriate helper for general registers, and then copy
- * the FCSR register separately.
+ * the FCSR register separately. Ignore the incoming FIR register
+ * contents though, as the register is read-only.
*
* We optimize for the case where `count % sizeof(elf_fpreg_t) == 0',
* which is supposed to have been guaranteed by the kernel before
@@ -545,6 +553,7 @@ static int fpr_set(struct task_struct *target,
const void *kbuf, const void __user *ubuf)
{
const int fcr31_pos = NUM_FPU_REGS * sizeof(elf_fpreg_t);
+ const int fir_pos = fcr31_pos + sizeof(u32);
u32 fcr31;
int err;
@@ -572,6 +581,11 @@ static int fpr_set(struct task_struct *target,
ptrace_setfcr31(target, fcr31);
}
+ if (count > 0)
+ err = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ fir_pos,
+ fir_pos + sizeof(u32));
+
return err;
}
@@ -793,7 +807,7 @@ long arch_ptrace(struct task_struct *child, long request,
fregs = get_fpu_regs(child);
#ifdef CONFIG_32BIT
- if (test_thread_flag(TIF_32BIT_FPREGS)) {
+ if (test_tsk_thread_flag(child, TIF_32BIT_FPREGS)) {
/*
* The odd registers are actually the high
* order bits of the values stored in the even
@@ -804,7 +818,7 @@ long arch_ptrace(struct task_struct *child, long request,
break;
}
#endif
- tmp = get_fpr32(&fregs[addr - FPR_BASE], 0);
+ tmp = get_fpr64(&fregs[addr - FPR_BASE], 0);
break;
case PC:
tmp = regs->cp0_epc;
@@ -888,7 +902,7 @@ long arch_ptrace(struct task_struct *child, long request,
init_fp_ctx(child);
#ifdef CONFIG_32BIT
- if (test_thread_flag(TIF_32BIT_FPREGS)) {
+ if (test_tsk_thread_flag(child, TIF_32BIT_FPREGS)) {
/*
* The odd registers are actually the high
* order bits of the values stored in the even
diff --git a/arch/mips/kernel/ptrace32.c b/arch/mips/kernel/ptrace32.c
index 2b9260f..f30c381 100644
--- a/arch/mips/kernel/ptrace32.c
+++ b/arch/mips/kernel/ptrace32.c
@@ -99,7 +99,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
break;
}
fregs = get_fpu_regs(child);
- if (test_thread_flag(TIF_32BIT_FPREGS)) {
+ if (test_tsk_thread_flag(child, TIF_32BIT_FPREGS)) {
/*
* The odd registers are actually the high
* order bits of the values stored in the even
@@ -109,7 +109,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
addr & 1);
break;
}
- tmp = get_fpr32(&fregs[addr - FPR_BASE], 0);
+ tmp = get_fpr64(&fregs[addr - FPR_BASE], 0);
break;
case PC:
tmp = regs->cp0_epc;
@@ -212,7 +212,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
sizeof(child->thread.fpu));
child->thread.fpu.fcr31 = 0;
}
- if (test_thread_flag(TIF_32BIT_FPREGS)) {
+ if (test_tsk_thread_flag(child, TIF_32BIT_FPREGS)) {
/*
* The odd registers are actually the high
* order bits of the values stored in the even
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index c4db910..b5d9e17 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -8,13 +8,13 @@
* Copyright (C) 1999, 2000 Silicon Graphics, Inc.
* Copyright (C) 2016, Imagination Technologies Ltd.
*/
+#include <linux/compat.h>
#include <linux/compiler.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/signal.h>
#include <linux/syscalls.h>
-#include <asm/compat.h>
#include <asm/compat-signal.h>
#include <linux/uaccess.h>
#include <asm/unistd.h>
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 967e9e4..d67fa74 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -699,17 +699,11 @@ static int simulate_sync(struct pt_regs *regs, unsigned int opcode)
asmlinkage void do_ov(struct pt_regs *regs)
{
enum ctx_state prev_state;
- siginfo_t info;
-
- clear_siginfo(&info);
- info.si_signo = SIGFPE;
- info.si_code = FPE_INTOVF;
- info.si_addr = (void __user *)regs->cp0_epc;
prev_state = exception_enter();
die_if_kernel("Integer overflow", regs);
- force_sig_info(SIGFPE, &info, current);
+ force_sig_fault(SIGFPE, FPE_INTOVF, (void __user *)regs->cp0_epc, current);
exception_exit(prev_state);
}
@@ -722,32 +716,27 @@ asmlinkage void do_ov(struct pt_regs *regs)
void force_fcr31_sig(unsigned long fcr31, void __user *fault_addr,
struct task_struct *tsk)
{
- struct siginfo si;
-
- clear_siginfo(&si);
- si.si_addr = fault_addr;
- si.si_signo = SIGFPE;
+ int si_code = FPE_FLTUNK;
if (fcr31 & FPU_CSR_INV_X)
- si.si_code = FPE_FLTINV;
+ si_code = FPE_FLTINV;
else if (fcr31 & FPU_CSR_DIV_X)
- si.si_code = FPE_FLTDIV;
+ si_code = FPE_FLTDIV;
else if (fcr31 & FPU_CSR_OVF_X)
- si.si_code = FPE_FLTOVF;
+ si_code = FPE_FLTOVF;
else if (fcr31 & FPU_CSR_UDF_X)
- si.si_code = FPE_FLTUND;
+ si_code = FPE_FLTUND;
else if (fcr31 & FPU_CSR_INE_X)
- si.si_code = FPE_FLTRES;
+ si_code = FPE_FLTRES;
- force_sig_info(SIGFPE, &si, tsk);
+ force_sig_fault(SIGFPE, si_code, fault_addr, tsk);
}
int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31)
{
- struct siginfo si;
+ int si_code;
struct vm_area_struct *vma;
- clear_siginfo(&si);
switch (sig) {
case 0:
return 0;
@@ -757,23 +746,18 @@ int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31)
return 1;
case SIGBUS:
- si.si_addr = fault_addr;
- si.si_signo = sig;
- si.si_code = BUS_ADRERR;
- force_sig_info(sig, &si, current);
+ force_sig_fault(SIGBUS, BUS_ADRERR, fault_addr, current);
return 1;
case SIGSEGV:
- si.si_addr = fault_addr;
- si.si_signo = sig;
down_read(¤t->mm->mmap_sem);
vma = find_vma(current->mm, (unsigned long)fault_addr);
if (vma && (vma->vm_start <= (unsigned long)fault_addr))
- si.si_code = SEGV_ACCERR;
+ si_code = SEGV_ACCERR;
else
- si.si_code = SEGV_MAPERR;
+ si_code = SEGV_MAPERR;
up_read(¤t->mm->mmap_sem);
- force_sig_info(sig, &si, current);
+ force_sig_fault(SIGSEGV, si_code, fault_addr, current);
return 1;
default:
@@ -896,10 +880,8 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31)
void do_trap_or_bp(struct pt_regs *regs, unsigned int code, int si_code,
const char *str)
{
- siginfo_t info;
char b[40];
- clear_siginfo(&info);
#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
if (kgdb_ll_trap(DIE_TRAP, str, regs, code, current->thread.trap_nr,
SIGTRAP) == NOTIFY_STOP)
@@ -921,13 +903,9 @@ void do_trap_or_bp(struct pt_regs *regs, unsigned int code, int si_code,
case BRK_DIVZERO:
scnprintf(b, sizeof(b), "%s instruction in kernel code", str);
die_if_kernel(b, regs);
- if (code == BRK_DIVZERO)
- info.si_code = FPE_INTDIV;
- else
- info.si_code = FPE_INTOVF;
- info.si_signo = SIGFPE;
- info.si_addr = (void __user *) regs->cp0_epc;
- force_sig_info(SIGFPE, &info, current);
+ force_sig_fault(SIGFPE,
+ code == BRK_DIVZERO ? FPE_INTDIV : FPE_INTOVF,
+ (void __user *) regs->cp0_epc, current);
break;
case BRK_BUG:
die_if_kernel("Kernel bug detected", regs);
@@ -952,9 +930,7 @@ void do_trap_or_bp(struct pt_regs *regs, unsigned int code, int si_code,
scnprintf(b, sizeof(b), "%s instruction in kernel code", str);
die_if_kernel(b, regs);
if (si_code) {
- info.si_signo = SIGTRAP;
- info.si_code = si_code;
- force_sig_info(SIGTRAP, &info, current);
+ force_sig_fault(SIGTRAP, si_code, NULL, current);
} else {
force_sig(SIGTRAP, current);
}
@@ -1506,13 +1482,8 @@ asmlinkage void do_mdmx(struct pt_regs *regs)
*/
asmlinkage void do_watch(struct pt_regs *regs)
{
- siginfo_t info;
enum ctx_state prev_state;
- clear_siginfo(&info);
- info.si_signo = SIGTRAP;
- info.si_code = TRAP_HWBKPT;
-
prev_state = exception_enter();
/*
* Clear WP (bit 22) bit of cause register so we don't loop
@@ -1528,7 +1499,7 @@ asmlinkage void do_watch(struct pt_regs *regs)
if (test_tsk_thread_flag(current, TIF_LOAD_WATCH)) {
mips_read_watch_registers();
local_irq_enable();
- force_sig_info(SIGTRAP, &info, current);
+ force_sig_fault(SIGTRAP, TRAP_HWBKPT, NULL, current);
} else {
mips_clear_watch_registers();
local_irq_enable();
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 2549fdd..0f725e9 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -45,7 +45,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "cache", VCPU_STAT(cache_exits), KVM_STAT_VCPU },
{ "signal", VCPU_STAT(signal_exits), KVM_STAT_VCPU },
{ "interrupt", VCPU_STAT(int_exits), KVM_STAT_VCPU },
- { "cop_unsuable", VCPU_STAT(cop_unusable_exits), KVM_STAT_VCPU },
+ { "cop_unusable", VCPU_STAT(cop_unusable_exits), KVM_STAT_VCPU },
{ "tlbmod", VCPU_STAT(tlbmod_exits), KVM_STAT_VCPU },
{ "tlbmiss_ld", VCPU_STAT(tlbmiss_ld_exits), KVM_STAT_VCPU },
{ "tlbmiss_st", VCPU_STAT(tlbmiss_st_exits), KVM_STAT_VCPU },
diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S
index a145666..f732797 100644
--- a/arch/mips/lib/memset.S
+++ b/arch/mips/lib/memset.S
@@ -219,7 +219,7 @@
1: PTR_ADDIU a0, 1 /* fill bytewise */
R10KCBARRIER(0(ra))
bne t1, a0, 1b
- sb a1, -1(a0)
+ EX(sb, a1, -1(a0), .Lsmall_fixup\@)
2: jr ra /* done */
move a2, zero
@@ -252,13 +252,18 @@
PTR_L t0, TI_TASK($28)
andi a2, STORMASK
LONG_L t0, THREAD_BUADDR(t0)
- LONG_ADDU a2, t1
+ LONG_ADDU a2, a0
jr ra
LONG_SUBU a2, t0
.Llast_fixup\@:
jr ra
- andi v1, a2, STORMASK
+ nop
+
+.Lsmall_fixup\@:
+ PTR_SUBU a2, t1, a0
+ jr ra
+ PTR_ADDIU a2, 1
.endm
diff --git a/arch/mips/loongson64/Kconfig b/arch/mips/loongson64/Kconfig
index 72af0c1..c79e6a5 100644
--- a/arch/mips/loongson64/Kconfig
+++ b/arch/mips/loongson64/Kconfig
@@ -130,21 +130,6 @@
default y
depends on EARLY_PRINTK || SERIAL_8250
-config IOMMU_HELPER
- bool
-
-config NEED_SG_DMA_LENGTH
- bool
-
-config SWIOTLB
- bool "Soft IOMMU Support for All-Memory DMA"
- default y
- depends on CPU_LOONGSON3
- select DMA_DIRECT_OPS
- select IOMMU_HELPER
- select NEED_SG_DMA_LENGTH
- select NEED_DMA_MAP_STATE
-
config PHYS48_TO_HT40
bool
default y if CPU_LOONGSON3
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 6f534b20..e12dfa4 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -851,9 +851,12 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
/*
* Either no secondary cache or the available caches don't have the
* subset property so we have to flush the primary caches
- * explicitly
+ * explicitly.
+ * If we would need IPI to perform an INDEX-type operation, then
+ * we have to use the HIT-type alternative as IPI cannot be used
+ * here due to interrupts possibly being disabled.
*/
- if (size >= dcache_size) {
+ if (!r4k_op_needs_ipi(R4K_INDEX) && size >= dcache_size) {
r4k_blast_dcache();
} else {
R4600_HIT_CACHEOP_WAR_IMPL;
@@ -890,7 +893,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
return;
}
- if (size >= dcache_size) {
+ if (!r4k_op_needs_ipi(R4K_INDEX) && size >= dcache_size) {
r4k_blast_dcache();
} else {
R4600_HIT_CACHEOP_WAR_IMPL;
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index dcafa43..f9fef00 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -402,13 +402,3 @@ static const struct dma_map_ops mips_default_dma_map_ops = {
const struct dma_map_ops *mips_dma_map_ops = &mips_default_dma_map_ops;
EXPORT_SYMBOL(mips_dma_map_ops);
-
-#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-
-static int __init mips_dma_init(void)
-{
- dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
-
- return 0;
-}
-fs_initcall(mips_dma_init);
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 4f8f5bf..5f71f2b 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -42,7 +42,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
const int field = sizeof(unsigned long) * 2;
- siginfo_t info;
+ int si_code;
int fault;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -63,7 +63,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
return;
#endif
- info.si_code = SEGV_MAPERR;
+ si_code = SEGV_MAPERR;
/*
* We fault-in kernel-space virtual memory on-demand. The
@@ -112,7 +112,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
* we can handle it..
*/
good_area:
- info.si_code = SEGV_ACCERR;
+ si_code = SEGV_ACCERR;
if (write) {
if (!(vma->vm_flags & VM_WRITE))
@@ -223,11 +223,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
pr_cont("\n");
}
current->thread.trap_nr = (regs->cp0_cause >> 2) & 0x1f;
- info.si_signo = SIGSEGV;
- info.si_errno = 0;
- /* info.si_code has been set above */
- info.si_addr = (void __user *) address;
- force_sig_info(SIGSEGV, &info, tsk);
+ force_sig_fault(SIGSEGV, si_code, (void __user *)address, tsk);
return;
}
@@ -283,11 +279,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
#endif
current->thread.trap_nr = (regs->cp0_cause >> 2) & 0x1f;
tsk->thread.cp0_badvaddr = address;
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_ADRERR;
- info.si_addr = (void __user *) address;
- force_sig_info(SIGBUS, &info, tsk);
+ force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address, tsk);
return;
#ifndef CONFIG_64BIT
diff --git a/arch/mips/netlogic/Kconfig b/arch/mips/netlogic/Kconfig
index 7fcfc7f..412351c 100644
--- a/arch/mips/netlogic/Kconfig
+++ b/arch/mips/netlogic/Kconfig
@@ -83,10 +83,4 @@
config NLM_COMMON
bool
-config IOMMU_HELPER
- bool
-
-config NEED_SG_DMA_LENGTH
- bool
-
endif
diff --git a/arch/mips/pci/ops-pmcmsp.c b/arch/mips/pci/ops-pmcmsp.c
index dd2d9f7..7649372 100644
--- a/arch/mips/pci/ops-pmcmsp.c
+++ b/arch/mips/pci/ops-pmcmsp.c
@@ -83,18 +83,6 @@ static int show_msp_pci_counts(struct seq_file *m, void *v)
return 0;
}
-static int msp_pci_rd_cnt_open(struct inode *inode, struct file *file)
-{
- return single_open(file, show_msp_pci_counts, NULL);
-}
-
-static const struct file_operations msp_pci_rd_cnt_fops = {
- .open = msp_pci_rd_cnt_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/*****************************************************************************
*
* FUNCTION: gen_pci_cfg_wr_show
@@ -160,18 +148,6 @@ static int gen_pci_cfg_wr_show(struct seq_file *m, void *v)
return 0;
}
-static int gen_pci_cfg_wr_open(struct inode *inode, struct file *file)
-{
- return single_open(file, gen_pci_cfg_wr_show, NULL);
-}
-
-static const struct file_operations gen_pci_cfg_wr_fops = {
- .open = gen_pci_cfg_wr_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/*****************************************************************************
*
* FUNCTION: pci_proc_init
@@ -188,8 +164,8 @@ static const struct file_operations gen_pci_cfg_wr_fops = {
****************************************************************************/
static void pci_proc_init(void)
{
- proc_create("pmc_msp_pci_rd_cnt", 0, NULL, &msp_pci_rd_cnt_fops);
- proc_create("pmc_msp_pci_cfg_wr", 0, NULL, &gen_pci_cfg_wr_fops);
+ proc_create_single("pmc_msp_pci_rd_cnt", 0, NULL, show_msp_pci_counts);
+ proc_create_single("pmc_msp_pci_cfg_wr", 0, NULL, gen_pci_cfg_wr_show);
}
#endif /* CONFIG_PROC_FS && PCI_COUNTERS */
diff --git a/arch/mips/sibyte/common/bus_watcher.c b/arch/mips/sibyte/common/bus_watcher.c
index a4e55999..4bb85de 100644
--- a/arch/mips/sibyte/common/bus_watcher.c
+++ b/arch/mips/sibyte/common/bus_watcher.c
@@ -142,24 +142,12 @@ static int bw_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int bw_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, bw_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations bw_proc_fops = {
- .open = bw_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static void create_proc_decoder(struct bw_stats_struct *stats)
{
struct proc_dir_entry *ent;
- ent = proc_create_data("bus_watcher", S_IWUSR | S_IRUGO, NULL,
- &bw_proc_fops, stats);
+ ent = proc_create_single_data("bus_watcher", S_IWUSR | S_IRUGO, NULL,
+ bw_proc_show, stats);
if (!ent) {
printk(KERN_INFO "Unable to initialize bus_watcher /proc entry\n");
return;
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index 249f38d..6aed9742 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -5,10 +5,19 @@
config NDS32
def_bool y
+ select ARCH_HAS_SYNC_DMA_FOR_CPU
+ select ARCH_HAS_SYNC_DMA_FOR_DEVICE
select ARCH_WANT_FRAME_POINTERS if FTRACE
select CLKSRC_MMIO
select CLONE_BACKWARDS
select COMMON_CLK
+ select DMA_NONCOHERENT_OPS
+ select GENERIC_ASHLDI3
+ select GENERIC_ASHRDI3
+ select GENERIC_LSHRDI3
+ select GENERIC_CMPDI2
+ select GENERIC_MULDI3
+ select GENERIC_UCMPDI2
select GENERIC_ATOMIC64
select GENERIC_CPU_DEVICES
select GENERIC_CLOCKEVENTS
@@ -82,6 +91,7 @@
menu "Kernel Features"
source "kernel/Kconfig.preempt"
+source "kernel/Kconfig.freezer"
source "mm/Kconfig"
source "kernel/Kconfig.hz"
endmenu
diff --git a/arch/nds32/Kconfig.cpu b/arch/nds32/Kconfig.cpu
index ba44cc5..b8c8984 100644
--- a/arch/nds32/Kconfig.cpu
+++ b/arch/nds32/Kconfig.cpu
@@ -1,10 +1,11 @@
comment "Processor Features"
config CPU_BIG_ENDIAN
- bool "Big endian"
+ def_bool !CPU_LITTLE_ENDIAN
config CPU_LITTLE_ENDIAN
- def_bool !CPU_BIG_ENDIAN
+ bool "Little endian"
+ default y
config HWZOL
bool "hardware zero overhead loop support"
diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile
index 91f933d..513bb2e 100644
--- a/arch/nds32/Makefile
+++ b/arch/nds32/Makefile
@@ -23,9 +23,6 @@
# If we have a machine-specific directory, then include it in the build.
core-y += arch/nds32/kernel/ arch/nds32/mm/
libs-y += arch/nds32/lib/
-LIBGCC_PATH := \
- $(shell $(CC) $(KBUILD_CFLAGS) $(KCFLAGS) -print-libgcc-file-name)
-libs-y += $(LIBGCC_PATH)
ifneq '$(CONFIG_NDS32_BUILTIN_DTB)' '""'
BUILTIN_DTB := y
@@ -35,8 +32,12 @@
ifdef CONFIG_CPU_LITTLE_ENDIAN
KBUILD_CFLAGS += $(call cc-option, -EL)
+KBUILD_AFLAGS += $(call cc-option, -EL)
+LDFLAGS += $(call cc-option, -EL)
else
KBUILD_CFLAGS += $(call cc-option, -EB)
+KBUILD_AFLAGS += $(call cc-option, -EB)
+LDFLAGS += $(call cc-option, -EB)
endif
boot := arch/nds32/boot
diff --git a/arch/nds32/include/asm/Kbuild b/arch/nds32/include/asm/Kbuild
index 06bdf81..dbc4e54 100644
--- a/arch/nds32/include/asm/Kbuild
+++ b/arch/nds32/include/asm/Kbuild
@@ -9,13 +9,16 @@
generic-y += clkdev.h
generic-y += cmpxchg.h
generic-y += cmpxchg-local.h
+generic-y += compat.h
generic-y += cputime.h
generic-y += device.h
generic-y += div64.h
generic-y += dma.h
+generic-y += dma-mapping.h
generic-y += emergency-restart.h
generic-y += errno.h
generic-y += exec.h
+generic-y += export.h
generic-y += fb.h
generic-y += fcntl.h
generic-y += ftrace.h
@@ -49,6 +52,7 @@
generic-y += timex.h
generic-y += topology.h
generic-y += trace_clock.h
+generic-y += xor.h
generic-y += unaligned.h
generic-y += user.h
generic-y += vga.h
diff --git a/arch/nds32/include/asm/bitfield.h b/arch/nds32/include/asm/bitfield.h
index c73f71d..8e84fc3 100644
--- a/arch/nds32/include/asm/bitfield.h
+++ b/arch/nds32/include/asm/bitfield.h
@@ -336,7 +336,7 @@
#define INT_MASK_mskIDIVZE ( 0x1 << INT_MASK_offIDIVZE )
#define INT_MASK_mskDSSIM ( 0x1 << INT_MASK_offDSSIM )
-#define INT_MASK_INITAIAL_VAL 0x10003
+#define INT_MASK_INITAIAL_VAL (INT_MASK_mskDSSIM|INT_MASK_mskIDIVZE)
/******************************************************************************
* ir15: INT_PEND (Interrupt Pending Register)
@@ -396,6 +396,7 @@
#define MMU_CTL_D8KB 1
#define MMU_CTL_UNA ( 0x1 << MMU_CTL_offUNA )
+#define MMU_CTL_CACHEABLE_NON 0
#define MMU_CTL_CACHEABLE_WB 2
#define MMU_CTL_CACHEABLE_WT 3
diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h
index 1240f14..10b48f0 100644
--- a/arch/nds32/include/asm/cacheflush.h
+++ b/arch/nds32/include/asm/cacheflush.h
@@ -32,6 +32,8 @@ void flush_anon_page(struct vm_area_struct *vma,
#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
void flush_kernel_dcache_page(struct page *page);
+void flush_kernel_vmap_range(void *addr, int size);
+void invalidate_kernel_vmap_range(void *addr, int size);
void flush_icache_range(unsigned long start, unsigned long end);
void flush_icache_page(struct vm_area_struct *vma, struct page *page);
#define flush_dcache_mmap_lock(mapping) xa_lock_irq(&(mapping)->i_pages)
diff --git a/arch/nds32/include/asm/dma-mapping.h b/arch/nds32/include/asm/dma-mapping.h
deleted file mode 100644
index 2dd47d24..0000000
--- a/arch/nds32/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,14 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (C) 2005-2017 Andes Technology Corporation
-
-#ifndef ASMNDS32_DMA_MAPPING_H
-#define ASMNDS32_DMA_MAPPING_H
-
-extern struct dma_map_ops nds32_dma_ops;
-
-static inline struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
- return &nds32_dma_ops;
-}
-
-#endif
diff --git a/arch/nds32/include/asm/io.h b/arch/nds32/include/asm/io.h
index 966e71b..71cd226 100644
--- a/arch/nds32/include/asm/io.h
+++ b/arch/nds32/include/asm/io.h
@@ -4,6 +4,8 @@
#ifndef __ASM_NDS32_IO_H
#define __ASM_NDS32_IO_H
+#include <linux/types.h>
+
extern void iounmap(volatile void __iomem *addr);
#define __raw_writeb __raw_writeb
static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
diff --git a/arch/nds32/include/asm/page.h b/arch/nds32/include/asm/page.h
index e27365c..947f049 100644
--- a/arch/nds32/include/asm/page.h
+++ b/arch/nds32/include/asm/page.h
@@ -27,6 +27,9 @@ extern void copy_user_highpage(struct page *to, struct page *from,
unsigned long vaddr, struct vm_area_struct *vma);
extern void clear_user_highpage(struct page *page, unsigned long vaddr);
+void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
+ struct page *to);
+void clear_user_page(void *addr, unsigned long vaddr, struct page *page);
#define __HAVE_ARCH_COPY_USER_HIGHPAGE
#define clear_user_highpage clear_user_highpage
#else
diff --git a/arch/nds32/include/asm/pgtable.h b/arch/nds32/include/asm/pgtable.h
index 6783937..d3e19a5 100644
--- a/arch/nds32/include/asm/pgtable.h
+++ b/arch/nds32/include/asm/pgtable.h
@@ -152,6 +152,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
#define PAGE_CACHE_L1 __pgprot(_HAVE_PAGE_L | _PAGE_V | _PAGE_M_KRW | _PAGE_D | _PAGE_E | _PAGE_G | _PAGE_CACHE)
#define PAGE_MEMORY __pgprot(_HAVE_PAGE_L | _PAGE_V | _PAGE_M_KRW | _PAGE_D | _PAGE_E | _PAGE_G | _PAGE_CACHE_SHRD)
#define PAGE_KERNEL __pgprot(_PAGE_V | _PAGE_M_KRW | _PAGE_D | _PAGE_E | _PAGE_G | _PAGE_CACHE_SHRD)
+#define PAGE_SHARED __pgprot(_PAGE_V | _PAGE_M_URW_KRW | _PAGE_D | _PAGE_CACHE_SHRD)
#define PAGE_DEVICE __pgprot(_PAGE_V | _PAGE_M_KRW | _PAGE_D | _PAGE_G | _PAGE_C_DEV)
#endif /* __ASSEMBLY__ */
diff --git a/arch/nds32/kernel/dma.c b/arch/nds32/kernel/dma.c
index d291800..d0dbd4f 100644
--- a/arch/nds32/kernel/dma.c
+++ b/arch/nds32/kernel/dma.c
@@ -3,17 +3,14 @@
#include <linux/types.h>
#include <linux/mm.h>
-#include <linux/export.h>
#include <linux/string.h>
-#include <linux/scatterlist.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
#include <linux/io.h>
#include <linux/cache.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
-#include <asm/dma-mapping.h>
#include <asm/proc-fns.h>
/*
@@ -22,11 +19,6 @@
static pte_t *consistent_pte;
static DEFINE_RAW_SPINLOCK(consistent_lock);
-enum master_type {
- FOR_CPU = 0,
- FOR_DEVICE = 1,
-};
-
/*
* VM region handling support.
*
@@ -124,10 +116,8 @@ static struct arch_vm_region *vm_region_find(struct arch_vm_region *head,
return c;
}
-/* FIXME: attrs is not used. */
-static void *nds32_dma_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t * handle, gfp_t gfp,
- unsigned long attrs)
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+ gfp_t gfp, unsigned long attrs)
{
struct page *page;
struct arch_vm_region *c;
@@ -232,8 +222,8 @@ static void *nds32_dma_alloc_coherent(struct device *dev, size_t size,
return NULL;
}
-static void nds32_dma_free(struct device *dev, size_t size, void *cpu_addr,
- dma_addr_t handle, unsigned long attrs)
+void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
+ dma_addr_t handle, unsigned long attrs)
{
struct arch_vm_region *c;
unsigned long flags, addr;
@@ -333,145 +323,69 @@ static int __init consistent_init(void)
}
core_initcall(consistent_init);
-static void consistent_sync(void *vaddr, size_t size, int direction, int master_type);
-static dma_addr_t nds32_dma_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- unsigned long attrs)
+
+static inline void cache_op(phys_addr_t paddr, size_t size,
+ void (*fn)(unsigned long start, unsigned long end))
{
- if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- consistent_sync((void *)(page_address(page) + offset), size, dir, FOR_DEVICE);
- return page_to_phys(page) + offset;
-}
+ struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
+ unsigned offset = paddr & ~PAGE_MASK;
+ size_t left = size;
+ unsigned long start;
-static void nds32_dma_unmap_page(struct device *dev, dma_addr_t handle,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- consistent_sync(phys_to_virt(handle), size, dir, FOR_CPU);
-}
+ do {
+ size_t len = left;
-/*
- * Make an area consistent for devices.
- */
-static void consistent_sync(void *vaddr, size_t size, int direction, int master_type)
-{
- unsigned long start = (unsigned long)vaddr;
- unsigned long end = start + size;
-
- if (master_type == FOR_CPU) {
- switch (direction) {
- case DMA_TO_DEVICE:
- break;
- case DMA_FROM_DEVICE:
- case DMA_BIDIRECTIONAL:
- cpu_dma_inval_range(start, end);
- break;
- default:
- BUG();
- }
- } else {
- /* FOR_DEVICE */
- switch (direction) {
- case DMA_FROM_DEVICE:
- break;
- case DMA_TO_DEVICE:
- case DMA_BIDIRECTIONAL:
- cpu_dma_wb_range(start, end);
- break;
- default:
- BUG();
- }
- }
-}
-
-static int nds32_dma_map_sg(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction dir,
- unsigned long attrs)
-{
- int i;
-
- for (i = 0; i < nents; i++, sg++) {
- void *virt;
- unsigned long pfn;
- struct page *page = sg_page(sg);
-
- sg->dma_address = sg_phys(sg);
- pfn = page_to_pfn(page) + sg->offset / PAGE_SIZE;
- page = pfn_to_page(pfn);
if (PageHighMem(page)) {
- virt = kmap_atomic(page);
- consistent_sync(virt, sg->length, dir, FOR_CPU);
- kunmap_atomic(virt);
+ void *addr;
+
+ if (offset + len > PAGE_SIZE) {
+ if (offset >= PAGE_SIZE) {
+ page += offset >> PAGE_SHIFT;
+ offset &= ~PAGE_MASK;
+ }
+ len = PAGE_SIZE - offset;
+ }
+
+ addr = kmap_atomic(page);
+ start = (unsigned long)(addr + offset);
+ fn(start, start + len);
+ kunmap_atomic(addr);
} else {
- if (sg->offset > PAGE_SIZE)
- panic("sg->offset:%08x > PAGE_SIZE\n",
- sg->offset);
- virt = page_address(page) + sg->offset;
- consistent_sync(virt, sg->length, dir, FOR_CPU);
+ start = (unsigned long)phys_to_virt(paddr);
+ fn(start, start + size);
}
- }
- return nents;
+ offset = 0;
+ page++;
+ left -= len;
+ } while (left);
}
-static void nds32_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
- int nhwentries, enum dma_data_direction dir,
- unsigned long attrs)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir)
{
-}
-
-static void
-nds32_dma_sync_single_for_cpu(struct device *dev, dma_addr_t handle,
- size_t size, enum dma_data_direction dir)
-{
- consistent_sync((void *)phys_to_virt(handle), size, dir, FOR_CPU);
-}
-
-static void
-nds32_dma_sync_single_for_device(struct device *dev, dma_addr_t handle,
- size_t size, enum dma_data_direction dir)
-{
- consistent_sync((void *)phys_to_virt(handle), size, dir, FOR_DEVICE);
-}
-
-static void
-nds32_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nents,
- enum dma_data_direction dir)
-{
- int i;
-
- for (i = 0; i < nents; i++, sg++) {
- char *virt =
- page_address((struct page *)sg->page_link) + sg->offset;
- consistent_sync(virt, sg->length, dir, FOR_CPU);
+ switch (dir) {
+ case DMA_FROM_DEVICE:
+ break;
+ case DMA_TO_DEVICE:
+ case DMA_BIDIRECTIONAL:
+ cache_op(paddr, size, cpu_dma_wb_range);
+ break;
+ default:
+ BUG();
}
}
-static void
-nds32_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir)
{
- int i;
-
- for (i = 0; i < nents; i++, sg++) {
- char *virt =
- page_address((struct page *)sg->page_link) + sg->offset;
- consistent_sync(virt, sg->length, dir, FOR_DEVICE);
+ switch (dir) {
+ case DMA_TO_DEVICE:
+ break;
+ case DMA_FROM_DEVICE:
+ case DMA_BIDIRECTIONAL:
+ cache_op(paddr, size, cpu_dma_inval_range);
+ break;
+ default:
+ BUG();
}
}
-
-struct dma_map_ops nds32_dma_ops = {
- .alloc = nds32_dma_alloc_coherent,
- .free = nds32_dma_free,
- .map_page = nds32_dma_map_page,
- .unmap_page = nds32_dma_unmap_page,
- .map_sg = nds32_dma_map_sg,
- .unmap_sg = nds32_dma_unmap_sg,
- .sync_single_for_device = nds32_dma_sync_single_for_device,
- .sync_single_for_cpu = nds32_dma_sync_single_for_cpu,
- .sync_sg_for_cpu = nds32_dma_sync_sg_for_cpu,
- .sync_sg_for_device = nds32_dma_sync_sg_for_device,
-};
-
-EXPORT_SYMBOL(nds32_dma_ops);
diff --git a/arch/nds32/kernel/ex-entry.S b/arch/nds32/kernel/ex-entry.S
index a72e83d..b8ae4e9 100644
--- a/arch/nds32/kernel/ex-entry.S
+++ b/arch/nds32/kernel/ex-entry.S
@@ -118,7 +118,7 @@
/* interrupt */
2:
#ifdef CONFIG_TRACE_IRQFLAGS
- jal arch_trace_hardirqs_off
+ jal trace_hardirqs_off
#endif
move $r0, $sp
sethi $lp, hi20(ret_from_intr)
diff --git a/arch/nds32/kernel/head.S b/arch/nds32/kernel/head.S
index 71f57bd..c5fdae1 100644
--- a/arch/nds32/kernel/head.S
+++ b/arch/nds32/kernel/head.S
@@ -57,14 +57,32 @@
isb
mtsr $r4, $L1_PPTB ! load page table pointer\n"
-/* set NTC0 cacheable/writeback, mutliple page size in use */
- mfsr $r3, $MMU_CTL
- li $r0, #~MMU_CTL_mskNTC0
- and $r3, $r3, $r0
-#ifdef CONFIG_ANDES_PAGE_SIZE_4KB
- ori $r3, $r3, #(MMU_CTL_mskMPZIU|(MMU_CTL_CACHEABLE_WB << MMU_CTL_offNTC0))
+#ifdef CONFIG_CPU_DCACHE_DISABLE
+ #define MMU_CTL_NTCC MMU_CTL_CACHEABLE_NON
#else
- ori $r3, $r3, #(MMU_CTL_mskMPZIU|(MMU_CTL_CACHEABLE_WB << MMU_CTL_offNTC0)|MMU_CTL_D8KB)
+ #ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
+ #define MMU_CTL_NTCC MMU_CTL_CACHEABLE_WT
+ #else
+ #define MMU_CTL_NTCC MMU_CTL_CACHEABLE_WB
+ #endif
+#endif
+
+/* set NTC cacheability, mutliple page size in use */
+ mfsr $r3, $MMU_CTL
+#if CONFIG_MEMORY_START >= 0xc0000000
+ ori $r3, $r3, (MMU_CTL_NTCC << MMU_CTL_offNTC3)
+#elif CONFIG_MEMORY_START >= 0x80000000
+ ori $r3, $r3, (MMU_CTL_NTCC << MMU_CTL_offNTC2)
+#elif CONFIG_MEMORY_START >= 0x40000000
+ ori $r3, $r3, (MMU_CTL_NTCC << MMU_CTL_offNTC1)
+#else
+ ori $r3, $r3, (MMU_CTL_NTCC << MMU_CTL_offNTC0)
+#endif
+
+#ifdef CONFIG_ANDES_PAGE_SIZE_4KB
+ ori $r3, $r3, #(MMU_CTL_mskMPZIU)
+#else
+ ori $r3, $r3, #(MMU_CTL_mskMPZIU|MMU_CTL_D8KB)
#endif
#ifdef CONFIG_HW_SUPPORT_UNALIGNMENT_ACCESS
li $r0, #MMU_CTL_UNA
diff --git a/arch/nds32/kernel/setup.c b/arch/nds32/kernel/setup.c
index ba910e9..2f5b2cc 100644
--- a/arch/nds32/kernel/setup.c
+++ b/arch/nds32/kernel/setup.c
@@ -293,6 +293,9 @@ void __init setup_arch(char **cmdline_p)
/* paging_init() sets up the MMU and marks all pages as reserved */
paging_init();
+ /* invalidate all TLB entries because the new mapping is created */
+ __nds32__tlbop_flua();
+
/* use generic way to parse */
parse_early_param();
diff --git a/arch/nds32/kernel/stacktrace.c b/arch/nds32/kernel/stacktrace.c
index bc70113..8b231e9 100644
--- a/arch/nds32/kernel/stacktrace.c
+++ b/arch/nds32/kernel/stacktrace.c
@@ -9,6 +9,7 @@ void save_stack_trace(struct stack_trace *trace)
{
save_stack_trace_tsk(current, trace);
}
+EXPORT_SYMBOL_GPL(save_stack_trace);
void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
{
@@ -45,3 +46,4 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
fpn = (unsigned long *)fpp;
}
}
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
diff --git a/arch/nds32/kernel/traps.c b/arch/nds32/kernel/traps.c
index 6e34eb9..a6205fd 100644
--- a/arch/nds32/kernel/traps.c
+++ b/arch/nds32/kernel/traps.c
@@ -222,19 +222,13 @@ void die_if_kernel(const char *str, struct pt_regs *regs, int err)
int bad_syscall(int n, struct pt_regs *regs)
{
- siginfo_t info;
-
if (current->personality != PER_LINUX) {
send_sig(SIGSEGV, current, 1);
return regs->uregs[0];
}
- info.si_signo = SIGILL;
- info.si_errno = 0;
- info.si_code = ILL_ILLTRP;
- info.si_addr = (void __user *)instruction_pointer(regs) - 4;
-
- force_sig_info(SIGILL, &info, current);
+ force_sig_fault(SIGILL, ILL_ILLTRP,
+ (void __user *)instruction_pointer(regs) - 4, current);
die_if_kernel("Oops - bad syscall", regs, n);
return regs->uregs[0];
}
@@ -287,16 +281,11 @@ void __init early_trap_init(void)
void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
int error_code, int si_code)
{
- struct siginfo info;
-
tsk->thread.trap_no = ENTRY_DEBUG_RELATED;
tsk->thread.error_code = error_code;
- memset(&info, 0, sizeof(info));
- info.si_signo = SIGTRAP;
- info.si_code = si_code;
- info.si_addr = (void __user *)instruction_pointer(regs);
- force_sig_info(SIGTRAP, &info, tsk);
+ force_sig_fault(SIGTRAP, si_code,
+ (void __user *)instruction_pointer(regs), tsk);
}
void do_debug_trap(unsigned long entry, unsigned long addr,
@@ -318,29 +307,22 @@ void do_debug_trap(unsigned long entry, unsigned long addr,
void unhandled_interruption(struct pt_regs *regs)
{
- siginfo_t si;
pr_emerg("unhandled_interruption\n");
show_regs(regs);
if (!user_mode(regs))
do_exit(SIGKILL);
- si.si_signo = SIGKILL;
- si.si_errno = 0;
- force_sig_info(SIGKILL, &si, current);
+ force_sig(SIGKILL, current);
}
void unhandled_exceptions(unsigned long entry, unsigned long addr,
unsigned long type, struct pt_regs *regs)
{
- siginfo_t si;
pr_emerg("Unhandled Exception: entry: %lx addr:%lx itype:%lx\n", entry,
addr, type);
show_regs(regs);
if (!user_mode(regs))
do_exit(SIGKILL);
- si.si_signo = SIGKILL;
- si.si_errno = 0;
- si.si_addr = (void *)addr;
- force_sig_info(SIGKILL, &si, current);
+ force_sig(SIGKILL, current);
}
extern int do_page_fault(unsigned long entry, unsigned long addr,
@@ -363,14 +345,11 @@ void do_dispatch_tlb_misc(unsigned long entry, unsigned long addr,
void do_revinsn(struct pt_regs *regs)
{
- siginfo_t si;
pr_emerg("Reserved Instruction\n");
show_regs(regs);
if (!user_mode(regs))
do_exit(SIGILL);
- si.si_signo = SIGILL;
- si.si_errno = 0;
- force_sig_info(SIGILL, &si, current);
+ force_sig(SIGILL, current);
}
#ifdef CONFIG_ALIGNMENT_TRAP
diff --git a/arch/nds32/kernel/vdso.c b/arch/nds32/kernel/vdso.c
index f1198d7..016f158 100644
--- a/arch/nds32/kernel/vdso.c
+++ b/arch/nds32/kernel/vdso.c
@@ -23,7 +23,7 @@
#include <asm/vdso_timer_info.h>
#include <asm/cache_info.h>
extern struct cache_info L1_cache_info[2];
-extern char vdso_start, vdso_end;
+extern char vdso_start[], vdso_end[];
static unsigned long vdso_pages __ro_after_init;
static unsigned long timer_mapping_base;
@@ -66,16 +66,16 @@ static int __init vdso_init(void)
int i;
struct page **vdso_pagelist;
- if (memcmp(&vdso_start, "\177ELF", 4)) {
+ if (memcmp(vdso_start, "\177ELF", 4)) {
pr_err("vDSO is not a valid ELF object!\n");
return -EINVAL;
}
/* Creat a timer io mapping to get clock cycles counter */
get_timer_node_info();
- vdso_pages = (&vdso_end - &vdso_start) >> PAGE_SHIFT;
+ vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
pr_info("vdso: %ld pages (%ld code @ %p, %ld data @ %p)\n",
- vdso_pages + 1, vdso_pages, &vdso_start, 1L, vdso_data);
+ vdso_pages + 1, vdso_pages, vdso_start, 1L, vdso_data);
/* Allocate the vDSO pagelist */
vdso_pagelist = kcalloc(vdso_pages, sizeof(struct page *), GFP_KERNEL);
@@ -83,7 +83,7 @@ static int __init vdso_init(void)
return -ENOMEM;
for (i = 0; i < vdso_pages; i++)
- vdso_pagelist[i] = virt_to_page(&vdso_start + i * PAGE_SIZE);
+ vdso_pagelist[i] = virt_to_page(vdso_start + i * PAGE_SIZE);
vdso_spec[1].pages = &vdso_pagelist[0];
return 0;
diff --git a/arch/nds32/lib/copy_page.S b/arch/nds32/lib/copy_page.S
index 4a2ff85f..f8701ed 100644
--- a/arch/nds32/lib/copy_page.S
+++ b/arch/nds32/lib/copy_page.S
@@ -2,6 +2,7 @@
// Copyright (C) 2005-2017 Andes Technology Corporation
#include <linux/linkage.h>
+#include <asm/export.h>
#include <asm/page.h>
.text
@@ -16,6 +17,7 @@
popm $r2, $r10
ret
ENDPROC(copy_page)
+EXPORT_SYMBOL(copy_page)
ENTRY(clear_page)
pushm $r1, $r9
@@ -35,3 +37,4 @@
popm $r1, $r9
ret
ENDPROC(clear_page)
+EXPORT_SYMBOL(clear_page)
diff --git a/arch/nds32/mm/alignment.c b/arch/nds32/mm/alignment.c
index b96a01b..e1aed9d 100644
--- a/arch/nds32/mm/alignment.c
+++ b/arch/nds32/mm/alignment.c
@@ -19,7 +19,7 @@
#define RA(inst) (((inst) >> 15) & 0x1FUL)
#define RB(inst) (((inst) >> 10) & 0x1FUL)
#define SV(inst) (((inst) >> 8) & 0x3UL)
-#define IMM(inst) (((inst) >> 0) & 0x3FFFUL)
+#define IMM(inst) (((inst) >> 0) & 0x7FFFUL)
#define RA3(inst) (((inst) >> 3) & 0x7UL)
#define RT3(inst) (((inst) >> 6) & 0x7UL)
@@ -28,6 +28,9 @@
#define RA5(inst) (((inst) >> 0) & 0x1FUL)
#define RT4(inst) (((inst) >> 5) & 0xFUL)
+#define GET_IMMSVAL(imm_value) \
+ (((imm_value >> 14) & 0x1) ? (imm_value - 0x8000) : imm_value)
+
#define __get8_data(val,addr,err) \
__asm__( \
"1: lbi.bi %1, [%2], #1\n" \
@@ -467,7 +470,7 @@ static inline int do_32(unsigned long inst, struct pt_regs *regs)
}
if (imm)
- shift = IMM(inst) * len;
+ shift = GET_IMMSVAL(IMM(inst)) * len;
else
shift = *idx_to_addr(regs, RB(inst)) << SV(inst);
@@ -552,7 +555,7 @@ static struct ctl_table alignment_tbl[3] = {
static struct ctl_table nds32_sysctl_table[2] = {
{
- .procname = "unaligned_acess",
+ .procname = "unaligned_access",
.mode = 0555,
.child = alignment_tbl},
{}
diff --git a/arch/nds32/mm/cacheflush.c b/arch/nds32/mm/cacheflush.c
index 6eb786a..ce8fd34 100644
--- a/arch/nds32/mm/cacheflush.c
+++ b/arch/nds32/mm/cacheflush.c
@@ -147,6 +147,25 @@ void flush_cache_vunmap(unsigned long start, unsigned long end)
cpu_icache_inval_all();
}
+void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
+ struct page *to)
+{
+ cpu_dcache_wbinval_page((unsigned long)vaddr);
+ cpu_icache_inval_page((unsigned long)vaddr);
+ copy_page(vto, vfrom);
+ cpu_dcache_wbinval_page((unsigned long)vto);
+ cpu_icache_inval_page((unsigned long)vto);
+}
+
+void clear_user_page(void *addr, unsigned long vaddr, struct page *page)
+{
+ cpu_dcache_wbinval_page((unsigned long)vaddr);
+ cpu_icache_inval_page((unsigned long)vaddr);
+ clear_page(addr);
+ cpu_dcache_wbinval_page((unsigned long)addr);
+ cpu_icache_inval_page((unsigned long)addr);
+}
+
void copy_user_highpage(struct page *to, struct page *from,
unsigned long vaddr, struct vm_area_struct *vma)
{
@@ -156,11 +175,9 @@ void copy_user_highpage(struct page *to, struct page *from,
pto = page_to_phys(to);
pfrom = page_to_phys(from);
+ local_irq_save(flags);
if (aliasing(vaddr, (unsigned long)kfrom))
cpu_dcache_wb_page((unsigned long)kfrom);
- if (aliasing(vaddr, (unsigned long)kto))
- cpu_dcache_inval_page((unsigned long)kto);
- local_irq_save(flags);
vto = kremap0(vaddr, pto);
vfrom = kremap1(vaddr, pfrom);
copy_page((void *)vto, (void *)vfrom);
@@ -198,21 +215,25 @@ void flush_dcache_page(struct page *page)
if (mapping && !mapping_mapped(mapping))
set_bit(PG_dcache_dirty, &page->flags);
else {
- int i, pc;
- unsigned long vto, kaddr, flags;
+ unsigned long kaddr, flags;
+
kaddr = (unsigned long)page_address(page);
- cpu_dcache_wbinval_page(kaddr);
- pc = CACHE_SET(DCACHE) * CACHE_LINE_SIZE(DCACHE) / PAGE_SIZE;
local_irq_save(flags);
- for (i = 0; i < pc; i++) {
- vto =
- kremap0(kaddr + i * PAGE_SIZE, page_to_phys(page));
- cpu_dcache_wbinval_page(vto);
- kunmap01(vto);
+ cpu_dcache_wbinval_page(kaddr);
+ if (mapping) {
+ unsigned long vaddr, kto;
+
+ vaddr = page->index << PAGE_SHIFT;
+ if (aliasing(vaddr, kaddr)) {
+ kto = kremap0(vaddr, page_to_phys(page));
+ cpu_dcache_wbinval_page(kto);
+ kunmap01(kto);
+ }
}
local_irq_restore(flags);
}
}
+EXPORT_SYMBOL(flush_dcache_page);
void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
unsigned long vaddr, void *dst, void *src, int len)
@@ -251,7 +272,7 @@ void copy_from_user_page(struct vm_area_struct *vma, struct page *page,
void flush_anon_page(struct vm_area_struct *vma,
struct page *page, unsigned long vaddr)
{
- unsigned long flags;
+ unsigned long kaddr, flags, ktmp;
if (!PageAnon(page))
return;
@@ -261,7 +282,12 @@ void flush_anon_page(struct vm_area_struct *vma,
local_irq_save(flags);
if (vma->vm_flags & VM_EXEC)
cpu_icache_inval_page(vaddr & PAGE_MASK);
- cpu_dcache_wbinval_page((unsigned long)page_address(page));
+ kaddr = (unsigned long)page_address(page);
+ if (aliasing(vaddr, kaddr)) {
+ ktmp = kremap0(vaddr, page_to_phys(page));
+ cpu_dcache_wbinval_page(ktmp);
+ kunmap01(ktmp);
+ }
local_irq_restore(flags);
}
@@ -272,6 +298,25 @@ void flush_kernel_dcache_page(struct page *page)
cpu_dcache_wbinval_page((unsigned long)page_address(page));
local_irq_restore(flags);
}
+EXPORT_SYMBOL(flush_kernel_dcache_page);
+
+void flush_kernel_vmap_range(void *addr, int size)
+{
+ unsigned long flags;
+ local_irq_save(flags);
+ cpu_dcache_wb_range((unsigned long)addr, (unsigned long)addr + size);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(flush_kernel_vmap_range);
+
+void invalidate_kernel_vmap_range(void *addr, int size)
+{
+ unsigned long flags;
+ local_irq_save(flags);
+ cpu_dcache_inval_range((unsigned long)addr, (unsigned long)addr + size);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(invalidate_kernel_vmap_range);
void flush_icache_range(unsigned long start, unsigned long end)
{
@@ -283,6 +328,7 @@ void flush_icache_range(unsigned long start, unsigned long end)
cpu_cache_wbinval_range(start, end, 1);
local_irq_restore(flags);
}
+EXPORT_SYMBOL(flush_icache_range);
void flush_icache_page(struct vm_area_struct *vma, struct page *page)
{
diff --git a/arch/nds32/mm/fault.c b/arch/nds32/mm/fault.c
index 3a246fb..9bdb7c3 100644
--- a/arch/nds32/mm/fault.c
+++ b/arch/nds32/mm/fault.c
@@ -72,7 +72,7 @@ void do_page_fault(unsigned long entry, unsigned long addr,
struct task_struct *tsk;
struct mm_struct *mm;
struct vm_area_struct *vma;
- siginfo_t info;
+ int si_code;
int fault;
unsigned int mask = VM_READ | VM_WRITE | VM_EXEC;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -80,7 +80,7 @@ void do_page_fault(unsigned long entry, unsigned long addr,
error_code = error_code & (ITYPE_mskINST | ITYPE_mskETYPE);
tsk = current;
mm = tsk->mm;
- info.si_code = SEGV_MAPERR;
+ si_code = SEGV_MAPERR;
/*
* We fault-in kernel-space virtual memory on-demand. The
* 'reference' page table is init_mm.pgd.
@@ -161,7 +161,7 @@ void do_page_fault(unsigned long entry, unsigned long addr,
*/
good_area:
- info.si_code = SEGV_ACCERR;
+ si_code = SEGV_ACCERR;
/* first do some preliminary protection checks */
if (entry == ENTRY_PTE_NOT_PRESENT) {
@@ -266,11 +266,7 @@ void do_page_fault(unsigned long entry, unsigned long addr,
tsk->thread.address = addr;
tsk->thread.error_code = error_code;
tsk->thread.trap_no = entry;
- info.si_signo = SIGSEGV;
- info.si_errno = 0;
- /* info.si_code has been set above */
- info.si_addr = (void *)addr;
- force_sig_info(SIGSEGV, &info, tsk);
+ force_sig_fault(SIGSEGV, si_code, (void __user *)addr, tsk);
return;
}
@@ -339,11 +335,7 @@ void do_page_fault(unsigned long entry, unsigned long addr,
tsk->thread.address = addr;
tsk->thread.error_code = error_code;
tsk->thread.trap_no = entry;
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_ADRERR;
- info.si_addr = (void *)addr;
- force_sig_info(SIGBUS, &info, tsk);
+ force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)addr, tsk);
return;
diff --git a/arch/nds32/mm/init.c b/arch/nds32/mm/init.c
index 93ee016..c713d2a 100644
--- a/arch/nds32/mm/init.c
+++ b/arch/nds32/mm/init.c
@@ -30,6 +30,7 @@ extern unsigned long phys_initrd_size;
* zero-initialized data and COW.
*/
struct page *empty_zero_page;
+EXPORT_SYMBOL(empty_zero_page);
static void __init zone_sizes_init(void)
{
diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild
index d232da2..64ed3d6 100644
--- a/arch/nios2/include/asm/Kbuild
+++ b/arch/nios2/include/asm/Kbuild
@@ -4,6 +4,7 @@
generic-y += bug.h
generic-y += bugs.h
generic-y += cmpxchg.h
+generic-y += compat.h
generic-y += current.h
generic-y += device.h
generic-y += div64.h
diff --git a/arch/nios2/kernel/traps.c b/arch/nios2/kernel/traps.c
index 8184e7d..3bc3cd2 100644
--- a/arch/nios2/kernel/traps.c
+++ b/arch/nios2/kernel/traps.c
@@ -26,13 +26,7 @@ static DEFINE_SPINLOCK(die_lock);
static void _send_sig(int signo, int code, unsigned long addr)
{
- siginfo_t info;
-
- info.si_signo = signo;
- info.si_errno = 0;
- info.si_code = code;
- info.si_addr = (void __user *) addr;
- force_sig_info(signo, &info, current);
+ force_sig_fault(signo, code, (void __user *) addr, current);
}
void die(const char *str, struct pt_regs *regs, long err)
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index f05c722..65964d3 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -2,6 +2,7 @@
generic-y += bug.h
generic-y += bugs.h
generic-y += checksum.h
+generic-y += compat.h
generic-y += current.h
generic-y += device.h
generic-y += div64.h
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index a945f00..ec7fd45 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -247,14 +247,3 @@ const struct dma_map_ops or1k_dma_map_ops = {
.sync_single_for_device = or1k_sync_single_for_device,
};
EXPORT_SYMBOL(or1k_dma_map_ops);
-
-/* Number of entries preallocated for DMA-API debugging */
-#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-
-static int __init dma_init(void)
-{
- dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
-
- return 0;
-}
-fs_initcall(dma_init);
diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c
index 113c175fe..fac246e 100644
--- a/arch/openrisc/kernel/traps.c
+++ b/arch/openrisc/kernel/traps.c
@@ -250,27 +250,16 @@ void __init trap_init(void)
asmlinkage void do_trap(struct pt_regs *regs, unsigned long address)
{
- siginfo_t info;
- memset(&info, 0, sizeof(info));
- info.si_signo = SIGTRAP;
- info.si_code = TRAP_TRACE;
- info.si_addr = (void *)address;
- force_sig_info(SIGTRAP, &info, current);
+ force_sig_fault(SIGTRAP, TRAP_TRACE, (void __user *)address, current);
regs->pc += 4;
}
asmlinkage void do_unaligned_access(struct pt_regs *regs, unsigned long address)
{
- siginfo_t info;
-
if (user_mode(regs)) {
/* Send a SIGBUS */
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_ADRALN;
- info.si_addr = (void __user *)address;
- force_sig_info(SIGBUS, &info, current);
+ force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)address, current);
} else {
printk("KERNEL: Unaligned Access 0x%.8lx\n", address);
show_registers(regs);
@@ -281,15 +270,9 @@ asmlinkage void do_unaligned_access(struct pt_regs *regs, unsigned long address)
asmlinkage void do_bus_fault(struct pt_regs *regs, unsigned long address)
{
- siginfo_t info;
-
if (user_mode(regs)) {
/* Send a SIGBUS */
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_ADRERR;
- info.si_addr = (void *)address;
- force_sig_info(SIGBUS, &info, current);
+ force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address, current);
} else { /* Kernel mode */
printk("KERNEL: Bus error (SIGBUS) 0x%.8lx\n", address);
show_registers(regs);
@@ -464,7 +447,6 @@ static inline void simulate_swa(struct pt_regs *regs, unsigned long address,
asmlinkage void do_illegal_instruction(struct pt_regs *regs,
unsigned long address)
{
- siginfo_t info;
unsigned int op;
unsigned int insn = *((unsigned int *)address);
@@ -485,11 +467,7 @@ asmlinkage void do_illegal_instruction(struct pt_regs *regs,
if (user_mode(regs)) {
/* Send a SIGILL */
- info.si_signo = SIGILL;
- info.si_errno = 0;
- info.si_code = ILL_ILLOPC;
- info.si_addr = (void *)address;
- force_sig_info(SIGBUS, &info, current);
+ force_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)address, current);
} else { /* Kernel mode */
printk("KERNEL: Illegal instruction (SIGILL) 0x%.8lx\n",
address);
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index d0021df..9f011d1 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -52,7 +52,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
struct task_struct *tsk;
struct mm_struct *mm;
struct vm_area_struct *vma;
- siginfo_t info;
+ int si_code;
int fault;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -97,7 +97,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
}
mm = tsk->mm;
- info.si_code = SEGV_MAPERR;
+ si_code = SEGV_MAPERR;
/*
* If we're in an interrupt or have no user
@@ -139,7 +139,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
*/
good_area:
- info.si_code = SEGV_ACCERR;
+ si_code = SEGV_ACCERR;
/* first do some preliminary protection checks */
@@ -213,11 +213,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
/* User mode accesses just cause a SIGSEGV */
if (user_mode(regs)) {
- info.si_signo = SIGSEGV;
- info.si_errno = 0;
- /* info.si_code has been set above */
- info.si_addr = (void *)address;
- force_sig_info(SIGSEGV, &info, tsk);
+ force_sig_fault(SIGSEGV, si_code, (void __user *)address, tsk);
return;
}
@@ -282,11 +278,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
* Send a sigbus, regardless of whether we were in kernel
* or user mode.
*/
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_ADRERR;
- info.si_addr = (void *)address;
- force_sig_info(SIGBUS, &info, tsk);
+ force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address, tsk);
/* Kernel mode? Handle exceptions or die */
if (!user_mode(regs))
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index fc5a574..4d8f64d 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -51,6 +51,8 @@
select GENERIC_CLOCKEVENTS
select ARCH_NO_COHERENT_DMA_MMAP
select CPU_NO_EFFICIENT_FFS
+ select NEED_DMA_MAP_STATE
+ select NEED_SG_DMA_LENGTH
help
The PA-RISC microprocessor is designed by Hewlett-Packard and used
@@ -111,12 +113,6 @@
config STACKTRACE_SUPPORT
def_bool y
-config NEED_DMA_MAP_STATE
- def_bool y
-
-config NEED_SG_DMA_LENGTH
- def_bool y
-
config ISA_DMA_API
bool
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index e2364ff..34ac503 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -123,6 +123,9 @@
PHONY += bzImage $(BOOT_TARGETS) $(INSTALL_TARGETS)
+# Default kernel to build
+all: bzImage
+
zImage: vmlinuz
Image: vmlinux
diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h
index 57b8b2a..ab8a547 100644
--- a/arch/parisc/include/asm/compat.h
+++ b/arch/parisc/include/asm/compat.h
@@ -13,7 +13,6 @@
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
-typedef s32 compat_time_t;
typedef s32 compat_clock_t;
typedef s32 compat_pid_t;
typedef u32 __compat_uid_t;
@@ -40,16 +39,6 @@ typedef u32 compat_ulong_t;
typedef u64 compat_u64;
typedef u32 compat_uptr_t;
-struct compat_timespec {
- compat_time_t tv_sec;
- s32 tv_nsec;
-};
-
-struct compat_timeval {
- compat_time_t tv_sec;
- s32 tv_usec;
-};
-
struct compat_stat {
compat_dev_t st_dev; /* dev_t is 32 bits on parisc */
compat_ino_t st_ino; /* 32 bits */
@@ -149,10 +138,10 @@ struct compat_ipc64_perm {
struct compat_semid64_ds {
struct compat_ipc64_perm sem_perm;
- unsigned int __unused1;
- compat_time_t sem_otime;
- unsigned int __unused2;
- compat_time_t sem_ctime;
+ unsigned int sem_otime_high;
+ unsigned int sem_otime;
+ unsigned int sem_ctime_high;
+ unsigned int sem_ctime;
compat_ulong_t sem_nsems;
compat_ulong_t __unused3;
compat_ulong_t __unused4;
@@ -160,12 +149,12 @@ struct compat_semid64_ds {
struct compat_msqid64_ds {
struct compat_ipc64_perm msg_perm;
- unsigned int __unused1;
- compat_time_t msg_stime;
- unsigned int __unused2;
- compat_time_t msg_rtime;
- unsigned int __unused3;
- compat_time_t msg_ctime;
+ unsigned int msg_stime_high;
+ unsigned int msg_stime;
+ unsigned int msg_rtime_high;
+ unsigned int msg_rtime;
+ unsigned int msg_ctime_high;
+ unsigned int msg_ctime;
compat_ulong_t msg_cbytes;
compat_ulong_t msg_qnum;
compat_ulong_t msg_qbytes;
@@ -177,12 +166,12 @@ struct compat_msqid64_ds {
struct compat_shmid64_ds {
struct compat_ipc64_perm shm_perm;
- unsigned int __unused1;
- compat_time_t shm_atime;
- unsigned int __unused2;
- compat_time_t shm_dtime;
- unsigned int __unused3;
- compat_time_t shm_ctime;
+ unsigned int shm_atime_high;
+ unsigned int shm_atime;
+ unsigned int shm_dtime_high;
+ unsigned int shm_dtime;
+ unsigned int shm_ctime_high;
+ unsigned int shm_ctime;
unsigned int __unused4;
compat_size_t shm_segsz;
compat_pid_t shm_cpid;
diff --git a/arch/parisc/include/asm/hardirq.h b/arch/parisc/include/asm/hardirq.h
index 0778151..1a1235a 100644
--- a/arch/parisc/include/asm/hardirq.h
+++ b/arch/parisc/include/asm/hardirq.h
@@ -34,14 +34,6 @@ DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
#define __IRQ_STAT(cpu, member) (irq_stat[cpu].member)
#define inc_irq_stat(member) this_cpu_inc(irq_stat.member)
#define __inc_irq_stat(member) __this_cpu_inc(irq_stat.member)
-#define local_softirq_pending() this_cpu_read(irq_stat.__softirq_pending)
-
-#define __ARCH_SET_SOFTIRQ_PENDING
-
-#define set_softirq_pending(x) \
- this_cpu_write(irq_stat.__softirq_pending, (x))
-#define or_softirq_pending(x) this_cpu_or(irq_stat.__softirq_pending, (x))
-
#define ack_bad_irq(irq) WARN(1, "unexpected IRQ trap at vector %02x\n", irq)
#endif /* _PARISC_HARDIRQ_H */
diff --git a/arch/parisc/include/asm/pci.h b/arch/parisc/include/asm/pci.h
index 96b7dee..3328fd1 100644
--- a/arch/parisc/include/asm/pci.h
+++ b/arch/parisc/include/asm/pci.h
@@ -88,29 +88,6 @@ struct pci_hba_data {
#endif /* !CONFIG_64BIT */
/*
- * If the PCI device's view of memory is the same as the CPU's view of memory,
- * PCI_DMA_BUS_IS_PHYS is true. The networking and block device layers use
- * this boolean for bounce buffer decisions.
- */
-#ifdef CONFIG_PA20
-/* All PA-2.0 machines have an IOMMU. */
-#define PCI_DMA_BUS_IS_PHYS 0
-#define parisc_has_iommu() do { } while (0)
-#else
-
-#if defined(CONFIG_IOMMU_CCIO) || defined(CONFIG_IOMMU_SBA)
-extern int parisc_bus_is_phys; /* in arch/parisc/kernel/setup.c */
-#define PCI_DMA_BUS_IS_PHYS parisc_bus_is_phys
-#define parisc_has_iommu() do { parisc_bus_is_phys = 0; } while (0)
-#else
-#define PCI_DMA_BUS_IS_PHYS 1
-#define parisc_has_iommu() do { } while (0)
-#endif
-
-#endif /* !CONFIG_PA20 */
-
-
-/*
** Most PCI devices (eg Tulip, NCR720) also export the same registers
** to both MMIO and I/O port space. Due to poor performance of I/O Port
** access under HP PCI bus adapters, strongly recommend the use of MMIO
diff --git a/arch/parisc/include/uapi/asm/msgbuf.h b/arch/parisc/include/uapi/asm/msgbuf.h
index b48b810..6a2e9ab 100644
--- a/arch/parisc/include/uapi/asm/msgbuf.h
+++ b/arch/parisc/include/uapi/asm/msgbuf.h
@@ -10,31 +10,30 @@
* between kernel and user space.
*
* Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
* - 2 miscellaneous 32-bit values
*/
struct msqid64_ds {
struct ipc64_perm msg_perm;
-#if __BITS_PER_LONG != 64
- unsigned int __pad1;
-#endif
+#if __BITS_PER_LONG == 64
__kernel_time_t msg_stime; /* last msgsnd time */
-#if __BITS_PER_LONG != 64
- unsigned int __pad2;
-#endif
__kernel_time_t msg_rtime; /* last msgrcv time */
-#if __BITS_PER_LONG != 64
- unsigned int __pad3;
-#endif
__kernel_time_t msg_ctime; /* last change time */
- unsigned long msg_cbytes; /* current number of bytes on queue */
- unsigned long msg_qnum; /* number of messages in queue */
- unsigned long msg_qbytes; /* max number of bytes on queue */
- __kernel_pid_t msg_lspid; /* pid of last msgsnd */
- __kernel_pid_t msg_lrpid; /* last receive pid */
- unsigned long __unused1;
- unsigned long __unused2;
+#else
+ unsigned long msg_stime_high;
+ unsigned long msg_stime; /* last msgsnd time */
+ unsigned long msg_rtime_high;
+ unsigned long msg_rtime; /* last msgrcv time */
+ unsigned long msg_ctime_high;
+ unsigned long msg_ctime; /* last change time */
+#endif
+ unsigned long msg_cbytes; /* current number of bytes on queue */
+ unsigned long msg_qnum; /* number of messages in queue */
+ unsigned long msg_qbytes; /* max number of bytes on queue */
+ __kernel_pid_t msg_lspid; /* pid of last msgsnd */
+ __kernel_pid_t msg_lrpid; /* last receive pid */
+ unsigned long __unused1;
+ unsigned long __unused2;
};
#endif /* _PARISC_MSGBUF_H */
diff --git a/arch/parisc/include/uapi/asm/sembuf.h b/arch/parisc/include/uapi/asm/sembuf.h
index 746c5d8..3c31163 100644
--- a/arch/parisc/include/uapi/asm/sembuf.h
+++ b/arch/parisc/include/uapi/asm/sembuf.h
@@ -10,21 +10,21 @@
* between kernel and user space.
*
* Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
* - 2 miscellaneous 32-bit values
*/
struct semid64_ds {
struct ipc64_perm sem_perm; /* permissions .. see ipc.h */
-#if __BITS_PER_LONG != 64
- unsigned int __pad1;
-#endif
+#if __BITS_PER_LONG == 64
__kernel_time_t sem_otime; /* last semop time */
-#if __BITS_PER_LONG != 64
- unsigned int __pad2;
-#endif
__kernel_time_t sem_ctime; /* last change time */
- unsigned long sem_nsems; /* no. of semaphores in array */
+#else
+ unsigned long sem_otime_high;
+ unsigned long sem_otime; /* last semop time */
+ unsigned long sem_ctime_high;
+ unsigned long sem_ctime; /* last change time */
+#endif
+ unsigned long sem_nsems; /* no. of semaphores in array */
unsigned long __unused1;
unsigned long __unused2;
};
diff --git a/arch/parisc/include/uapi/asm/shmbuf.h b/arch/parisc/include/uapi/asm/shmbuf.h
index cd4dbce..c89b3dd 100644
--- a/arch/parisc/include/uapi/asm/shmbuf.h
+++ b/arch/parisc/include/uapi/asm/shmbuf.h
@@ -10,25 +10,22 @@
* between kernel and user space.
*
* Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
* - 2 miscellaneous 32-bit values
*/
struct shmid64_ds {
struct ipc64_perm shm_perm; /* operation perms */
-#if __BITS_PER_LONG != 64
- unsigned int __pad1;
-#endif
+#if __BITS_PER_LONG == 64
__kernel_time_t shm_atime; /* last attach time */
-#if __BITS_PER_LONG != 64
- unsigned int __pad2;
-#endif
__kernel_time_t shm_dtime; /* last detach time */
-#if __BITS_PER_LONG != 64
- unsigned int __pad3;
-#endif
__kernel_time_t shm_ctime; /* last change time */
-#if __BITS_PER_LONG != 64
+#else
+ unsigned long shm_atime_high;
+ unsigned long shm_atime; /* last attach time */
+ unsigned long shm_dtime_high;
+ unsigned long shm_dtime; /* last detach time */
+ unsigned long shm_ctime_high;
+ unsigned long shm_ctime; /* last change time */
unsigned int __pad4;
#endif
__kernel_size_t shm_segsz; /* size of segment (bytes) */
diff --git a/arch/parisc/kernel/Makefile b/arch/parisc/kernel/Makefile
index eafd06a..e5de34d0 100644
--- a/arch/parisc/kernel/Makefile
+++ b/arch/parisc/kernel/Makefile
@@ -23,7 +23,7 @@
obj-$(CONFIG_PA11) += pci-dma.o
obj-$(CONFIG_PCI) += pci.o
obj-$(CONFIG_MODULES) += module.o
-obj-$(CONFIG_64BIT) += binfmt_elf32.o sys_parisc32.o signal32.o
+obj-$(CONFIG_64BIT) += sys_parisc32.o signal32.o
obj-$(CONFIG_STACKTRACE)+= stacktrace.o
obj-$(CONFIG_AUDIT) += audit.o
obj64-$(CONFIG_AUDIT) += compat_audit.o
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index 3b8507f..e0e1c97 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -268,7 +268,7 @@ static struct parisc_device *find_device_by_addr(unsigned long hpa)
* Walks up the device tree looking for a device of the specified type.
* If it finds it, it returns it. If not, it returns NULL.
*/
-const struct parisc_device * __init
+const struct parisc_device *
find_pa_parent_type(const struct parisc_device *padev, int type)
{
const struct device *dev = &padev->dev;
@@ -448,7 +448,8 @@ static int match_by_id(struct device * dev, void * data)
* Checks all the children of @parent for a matching @id. If none
* found, it allocates a new device and returns it.
*/
-static struct parisc_device * alloc_tree_node(struct device *parent, char id)
+static struct parisc_device * __init alloc_tree_node(
+ struct device *parent, char id)
{
struct match_id_data d = {
.id = id,
@@ -825,8 +826,8 @@ static void walk_lower_bus(struct parisc_device *dev)
* devices which are not physically connected (such as extra serial &
* keyboard ports). This problem is not yet solved.
*/
-static void walk_native_bus(unsigned long io_io_low, unsigned long io_io_high,
- struct device *parent)
+static void __init walk_native_bus(unsigned long io_io_low,
+ unsigned long io_io_high, struct device *parent)
{
int i, devices_found = 0;
unsigned long hpa = io_io_low;
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index 91bc0ca..6df07ce 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -367,19 +367,6 @@ static int proc_pcxl_dma_show(struct seq_file *m, void *v)
return 0;
}
-static int proc_pcxl_dma_open(struct inode *inode, struct file *file)
-{
- return single_open(file, proc_pcxl_dma_show, NULL);
-}
-
-static const struct file_operations proc_pcxl_dma_ops = {
- .owner = THIS_MODULE,
- .open = proc_pcxl_dma_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __init
pcxl_dma_init(void)
{
@@ -397,8 +384,8 @@ pcxl_dma_init(void)
"pcxl_dma_init: Unable to create gsc /proc dir entry\n");
else {
struct proc_dir_entry* ent;
- ent = proc_create("pcxl_dma", 0, proc_gsc_root,
- &proc_pcxl_dma_ops);
+ ent = proc_create_single("pcxl_dma", 0, proc_gsc_root,
+ proc_pcxl_dma_show);
if (!ent)
printk(KERN_WARNING
"pci-dma.c: Unable to create pcxl_dma /proc entry.\n");
diff --git a/arch/parisc/kernel/pci.c b/arch/parisc/kernel/pci.c
index 13ee356..ae684ac 100644
--- a/arch/parisc/kernel/pci.c
+++ b/arch/parisc/kernel/pci.c
@@ -174,7 +174,7 @@ void pcibios_set_master(struct pci_dev *dev)
* pcibios_init_bridge() initializes cache line and default latency
* for pci controllers and pci-pci bridges
*/
-void __init pcibios_init_bridge(struct pci_dev *dev)
+void __ref pcibios_init_bridge(struct pci_dev *dev)
{
unsigned short bridge_ctl, bridge_ctl_new;
diff --git a/arch/parisc/kernel/pdc_chassis.c b/arch/parisc/kernel/pdc_chassis.c
index 3e04242..28e0748 100644
--- a/arch/parisc/kernel/pdc_chassis.c
+++ b/arch/parisc/kernel/pdc_chassis.c
@@ -266,18 +266,6 @@ static int pdc_chassis_warn_show(struct seq_file *m, void *v)
return 0;
}
-static int pdc_chassis_warn_open(struct inode *inode, struct file *file)
-{
- return single_open(file, pdc_chassis_warn_show, NULL);
-}
-
-static const struct file_operations pdc_chassis_warn_fops = {
- .open = pdc_chassis_warn_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __init pdc_chassis_create_procfs(void)
{
unsigned long test;
@@ -292,7 +280,7 @@ static int __init pdc_chassis_create_procfs(void)
printk(KERN_INFO "Enabling PDC chassis warnings support v%s\n",
PDC_CHASSIS_VER);
- proc_create("chassis", 0400, NULL, &pdc_chassis_warn_fops);
+ proc_create_single("chassis", 0400, NULL, pdc_chassis_warn_show);
return 0;
}
diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c
index 1a2be6e..7aa1d4d 100644
--- a/arch/parisc/kernel/ptrace.c
+++ b/arch/parisc/kernel/ptrace.c
@@ -76,8 +76,6 @@ void user_enable_single_step(struct task_struct *task)
set_tsk_thread_flag(task, TIF_SINGLESTEP);
if (pa_psw(task)->n) {
- struct siginfo si;
-
/* Nullified, just crank over the queue. */
task_regs(task)->iaoq[0] = task_regs(task)->iaoq[1];
task_regs(task)->iasq[0] = task_regs(task)->iasq[1];
@@ -90,11 +88,9 @@ void user_enable_single_step(struct task_struct *task)
ptrace_disable(task);
/* Don't wake up the task, but let the
parent know something happened. */
- si.si_code = TRAP_TRACE;
- si.si_addr = (void __user *) (task_regs(task)->iaoq[0] & ~3);
- si.si_signo = SIGTRAP;
- si.si_errno = 0;
- force_sig_info(SIGTRAP, &si, task);
+ force_sig_fault(SIGTRAP, TRAP_TRACE,
+ (void __user *) (task_regs(task)->iaoq[0] & ~3),
+ task);
/* notify_parent(task, SIGCHLD); */
return;
}
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index 0e9675f..8d3a7b8 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -58,11 +58,6 @@ struct proc_dir_entry * proc_runway_root __read_mostly = NULL;
struct proc_dir_entry * proc_gsc_root __read_mostly = NULL;
struct proc_dir_entry * proc_mckinley_root __read_mostly = NULL;
-#if !defined(CONFIG_PA20) && (defined(CONFIG_IOMMU_CCIO) || defined(CONFIG_IOMMU_SBA))
-int parisc_bus_is_phys __read_mostly = 1; /* Assume no IOMMU is present */
-EXPORT_SYMBOL(parisc_bus_is_phys);
-#endif
-
void __init setup_cmdline(char **cmdline_p)
{
extern unsigned int boot_args[];
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 4065b5e..5e26dbe 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -423,8 +423,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
}
#ifdef CONFIG_PROC_FS
-int __init
-setup_profiling_timer(unsigned int multiplier)
+int setup_profiling_timer(unsigned int multiplier)
{
return -EINVAL;
}
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index c383040..a1e772f 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -205,7 +205,7 @@ static int __init rtc_init(void)
device_initcall(rtc_init);
#endif
-void read_persistent_clock(struct timespec *ts)
+void read_persistent_clock64(struct timespec64 *ts)
{
static struct pdc_tod tod_data;
if (pdc_tod_read(&tod_data) == 0) {
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 68e671a..4309ad3 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -297,13 +297,8 @@ void die_if_kernel(char *str, struct pt_regs *regs, long err)
#define GDB_BREAK_INSN 0x10004
static void handle_gdb_break(struct pt_regs *regs, int wot)
{
- struct siginfo si;
-
- si.si_signo = SIGTRAP;
- si.si_errno = 0;
- si.si_code = wot;
- si.si_addr = (void __user *) (regs->iaoq[0] & ~3);
- force_sig_info(SIGTRAP, &si, current);
+ force_sig_fault(SIGTRAP, wot,
+ (void __user *) (regs->iaoq[0] & ~3), current);
}
static void handle_break(struct pt_regs *regs)
@@ -487,7 +482,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
{
unsigned long fault_address = 0;
unsigned long fault_space = 0;
- struct siginfo si;
+ int si_code;
if (code == 1)
pdc_console_restart(); /* switch back to pdc if HPMC */
@@ -571,7 +566,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
case 8:
/* Illegal instruction trap */
die_if_kernel("Illegal instruction", regs, code);
- si.si_code = ILL_ILLOPC;
+ si_code = ILL_ILLOPC;
goto give_sigill;
case 9:
@@ -582,7 +577,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
case 10:
/* Privileged operation trap */
die_if_kernel("Privileged operation", regs, code);
- si.si_code = ILL_PRVOPC;
+ si_code = ILL_PRVOPC;
goto give_sigill;
case 11:
@@ -605,20 +600,16 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
}
die_if_kernel("Privileged register usage", regs, code);
- si.si_code = ILL_PRVREG;
+ si_code = ILL_PRVREG;
give_sigill:
- si.si_signo = SIGILL;
- si.si_errno = 0;
- si.si_addr = (void __user *) regs->iaoq[0];
- force_sig_info(SIGILL, &si, current);
+ force_sig_fault(SIGILL, si_code,
+ (void __user *) regs->iaoq[0], current);
return;
case 12:
/* Overflow Trap, let the userland signal handler do the cleanup */
- si.si_signo = SIGFPE;
- si.si_code = FPE_INTOVF;
- si.si_addr = (void __user *) regs->iaoq[0];
- force_sig_info(SIGFPE, &si, current);
+ force_sig_fault(SIGFPE, FPE_INTOVF,
+ (void __user *) regs->iaoq[0], current);
return;
case 13:
@@ -626,13 +617,11 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
The condition succeeds in an instruction which traps
on condition */
if(user_mode(regs)){
- si.si_signo = SIGFPE;
/* Let userspace app figure it out from the insn pointed
* to by si_addr.
*/
- si.si_code = FPE_CONDTRAP;
- si.si_addr = (void __user *) regs->iaoq[0];
- force_sig_info(SIGFPE, &si, current);
+ force_sig_fault(SIGFPE, FPE_CONDTRAP,
+ (void __user *) regs->iaoq[0], current);
return;
}
/* The kernel doesn't want to handle condition codes */
@@ -741,14 +730,10 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
return;
die_if_kernel("Protection id trap", regs, code);
- si.si_code = SEGV_MAPERR;
- si.si_signo = SIGSEGV;
- si.si_errno = 0;
- if (code == 7)
- si.si_addr = (void __user *) regs->iaoq[0];
- else
- si.si_addr = (void __user *) regs->ior;
- force_sig_info(SIGSEGV, &si, current);
+ force_sig_fault(SIGSEGV, SEGV_MAPERR,
+ (code == 7)?
+ ((void __user *) regs->iaoq[0]) :
+ ((void __user *) regs->ior), current);
return;
case 28:
@@ -762,11 +747,8 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
"handle_interruption() pid=%d command='%s'\n",
task_pid_nr(current), current->comm);
/* SIGBUS, for lack of a better one. */
- si.si_signo = SIGBUS;
- si.si_code = BUS_OBJERR;
- si.si_errno = 0;
- si.si_addr = (void __user *) regs->ior;
- force_sig_info(SIGBUS, &si, current);
+ force_sig_fault(SIGBUS, BUS_OBJERR,
+ (void __user *)regs->ior, current);
return;
}
pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC);
@@ -781,11 +763,8 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
"User fault %d on space 0x%08lx, pid=%d command='%s'\n",
code, fault_space,
task_pid_nr(current), current->comm);
- si.si_signo = SIGSEGV;
- si.si_errno = 0;
- si.si_code = SEGV_MAPERR;
- si.si_addr = (void __user *) regs->ior;
- force_sig_info(SIGSEGV, &si, current);
+ force_sig_fault(SIGSEGV, SEGV_MAPERR,
+ (void __user *)regs->ior, current);
return;
}
}
@@ -837,6 +816,17 @@ void __init initialize_ivt(const void *iva)
if (pdc_instr(&instr) == PDC_OK)
ivap[0] = instr;
+ /*
+ * Rules for the checksum of the HPMC handler:
+ * 1. The IVA does not point to PDC/PDH space (ie: the OS has installed
+ * its own IVA).
+ * 2. The word at IVA + 32 is nonzero.
+ * 3. If Length (IVA + 60) is not zero, then Length (IVA + 60) and
+ * Address (IVA + 56) are word-aligned.
+ * 4. The checksum of the 8 words starting at IVA + 32 plus the sum of
+ * the Length/4 words starting at Address is zero.
+ */
+
/* Compute Checksum for HPMC handler */
length = os_hpmc_size;
ivap[7] = length;
diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index e36f7b7..932bfc0 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -452,7 +452,6 @@ void handle_unaligned(struct pt_regs *regs)
unsigned long newbase = R1(regs->iir)?regs->gr[R1(regs->iir)]:0;
int modify = 0;
int ret = ERR_NOTHANDLED;
- struct siginfo si;
register int flop=0; /* true if this is a flop */
__inc_irq_stat(irq_unaligned_count);
@@ -690,21 +689,15 @@ void handle_unaligned(struct pt_regs *regs)
if (ret == ERR_PAGEFAULT)
{
- si.si_signo = SIGSEGV;
- si.si_errno = 0;
- si.si_code = SEGV_MAPERR;
- si.si_addr = (void __user *)regs->ior;
- force_sig_info(SIGSEGV, &si, current);
+ force_sig_fault(SIGSEGV, SEGV_MAPERR,
+ (void __user *)regs->ior, current);
}
else
{
force_sigbus:
/* couldn't handle it ... */
- si.si_signo = SIGBUS;
- si.si_errno = 0;
- si.si_code = BUS_ADRALN;
- si.si_addr = (void __user *)regs->ior;
- force_sig_info(SIGBUS, &si, current);
+ force_sig_fault(SIGBUS, BUS_ADRALN,
+ (void __user *)regs->ior, current);
}
return;
diff --git a/arch/parisc/math-emu/driver.c b/arch/parisc/math-emu/driver.c
index 2fb59d2..0590e05 100644
--- a/arch/parisc/math-emu/driver.c
+++ b/arch/parisc/math-emu/driver.c
@@ -81,7 +81,6 @@ int
handle_fpe(struct pt_regs *regs)
{
extern void printbinary(unsigned long x, int nbits);
- struct siginfo si;
unsigned int orig_sw, sw;
int signalcode;
/* need an intermediate copy of float regs because FPU emulation
@@ -117,11 +116,8 @@ handle_fpe(struct pt_regs *regs)
memcpy(regs->fr, frcopy, sizeof regs->fr);
if (signalcode != 0) {
- si.si_signo = signalcode >> 24;
- si.si_errno = 0;
- si.si_code = signalcode & 0xffffff;
- si.si_addr = (void __user *) regs->iaoq[0];
- force_sig_info(si.si_signo, &si, current);
+ force_sig_fault(signalcode >> 24, signalcode & 0xffffff,
+ (void __user *) regs->iaoq[0], current);
return -1;
}
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index e247edb..a801179 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -353,23 +353,22 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
up_read(&mm->mmap_sem);
if (user_mode(regs)) {
- struct siginfo si;
- unsigned int lsb = 0;
+ int signo, si_code;
switch (code) {
case 15: /* Data TLB miss fault/Data page fault */
/* send SIGSEGV when outside of vma */
if (!vma ||
address < vma->vm_start || address >= vma->vm_end) {
- si.si_signo = SIGSEGV;
- si.si_code = SEGV_MAPERR;
+ signo = SIGSEGV;
+ si_code = SEGV_MAPERR;
break;
}
/* send SIGSEGV for wrong permissions */
if ((vma->vm_flags & acc_type) != acc_type) {
- si.si_signo = SIGSEGV;
- si.si_code = SEGV_ACCERR;
+ signo = SIGSEGV;
+ si_code = SEGV_ACCERR;
break;
}
@@ -377,43 +376,40 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
/* fall through */
case 17: /* NA data TLB miss / page fault */
case 18: /* Unaligned access - PCXS only */
- si.si_signo = SIGBUS;
- si.si_code = (code == 18) ? BUS_ADRALN : BUS_ADRERR;
+ signo = SIGBUS;
+ si_code = (code == 18) ? BUS_ADRALN : BUS_ADRERR;
break;
case 16: /* Non-access instruction TLB miss fault */
case 26: /* PCXL: Data memory access rights trap */
default:
- si.si_signo = SIGSEGV;
- si.si_code = (code == 26) ? SEGV_ACCERR : SEGV_MAPERR;
+ signo = SIGSEGV;
+ si_code = (code == 26) ? SEGV_ACCERR : SEGV_MAPERR;
break;
}
-
#ifdef CONFIG_MEMORY_FAILURE
if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
+ unsigned int lsb = 0;
printk(KERN_ERR
"MCE: Killing %s:%d due to hardware memory corruption fault at %08lx\n",
tsk->comm, tsk->pid, address);
- si.si_signo = SIGBUS;
- si.si_code = BUS_MCEERR_AR;
+ /*
+ * Either small page or large page may be poisoned.
+ * In other words, VM_FAULT_HWPOISON_LARGE and
+ * VM_FAULT_HWPOISON are mutually exclusive.
+ */
+ if (fault & VM_FAULT_HWPOISON_LARGE)
+ lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
+ else if (fault & VM_FAULT_HWPOISON)
+ lsb = PAGE_SHIFT;
+
+ force_sig_mceerr(BUS_MCEERR_AR, (void __user *) address,
+ lsb, current);
+ return;
}
#endif
+ show_signal_msg(regs, code, address, tsk, vma);
- /*
- * Either small page or large page may be poisoned.
- * In other words, VM_FAULT_HWPOISON_LARGE and
- * VM_FAULT_HWPOISON are mutually exclusive.
- */
- if (fault & VM_FAULT_HWPOISON_LARGE)
- lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
- else if (fault & VM_FAULT_HWPOISON)
- lsb = PAGE_SHIFT;
- else
- show_signal_msg(regs, code, address, tsk, vma);
- si.si_addr_lsb = lsb;
-
- si.si_errno = 0;
- si.si_addr = (void __user *) address;
- force_sig_info(si.si_signo, &si, current);
+ force_sig_fault(signo, si_code, (void __user *) address, current);
return;
}
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index cab32ee..2607d2d 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -516,7 +516,7 @@ static void __init map_pages(unsigned long start_vaddr,
}
}
-void free_initmem(void)
+void __ref free_initmem(void)
{
unsigned long init_begin = (unsigned long)__init_begin;
unsigned long init_end = (unsigned long)__init_end;
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index c32a181..f674006 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -13,12 +13,6 @@
bool
default y if PPC64
-config ARCH_PHYS_ADDR_T_64BIT
- def_bool PPC64 || PHYS_64BIT
-
-config ARCH_DMA_ADDR_T_64BIT
- def_bool ARCH_PHYS_ADDR_T_64BIT
-
config MMU
bool
default y
@@ -187,7 +181,6 @@
select HAVE_CONTEXT_TRACKING if PPC64
select HAVE_DEBUG_KMEMLEAK
select HAVE_DEBUG_STACKOVERFLOW
- select HAVE_DMA_API_DEBUG
select HAVE_DYNAMIC_FTRACE
select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL
select HAVE_EBPF_JIT if PPC64
@@ -223,9 +216,11 @@
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_VIRT_CPU_ACCOUNTING
select HAVE_IRQ_TIME_ACCOUNTING
+ select IOMMU_HELPER if PPC64
select IRQ_DOMAIN
select IRQ_FORCED_THREADING
select MODULES_USE_ELF_RELA
+ select NEED_SG_DMA_LENGTH
select NO_BOOTMEM
select OF
select OF_EARLY_FLATTREE
@@ -478,19 +473,6 @@
depends on PPC64 && CPU_LITTLE_ENDIAN
def_bool !DISABLE_MPROFILE_KERNEL
-config IOMMU_HELPER
- def_bool PPC64
-
-config SWIOTLB
- bool "SWIOTLB support"
- default n
- select IOMMU_HELPER
- ---help---
- Support for IO bounce buffering for systems without an IOMMU.
- This allows us to DMA to the full physical address space on
- platforms where the size of a physical address is larger
- than the bus address. Not all platforms support this.
-
config HOTPLUG_CPU
bool "Support for enabling/disabling CPUs"
depends on SMP && (PPC_PSERIES || \
@@ -883,7 +865,7 @@
page-based protections, but without requiring modification of the
page tables when an application changes protection domains.
- For details, see Documentation/vm/protection-keys.txt
+ For details, see Documentation/vm/protection-keys.rst
If unsure, say y.
@@ -913,9 +895,6 @@
config NEED_DMA_MAP_STATE
def_bool (PPC64 || NOT_COHERENT_CACHE)
-config NEED_SG_DMA_LENGTH
- def_bool y
-
config GENERIC_ISA_DMA
bool
depends on ISA_DMA_API
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 62168e1..85c8af2 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -17,7 +17,6 @@
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
-typedef s32 compat_time_t;
typedef s32 compat_clock_t;
typedef s32 compat_pid_t;
typedef u32 __compat_uid_t;
@@ -45,16 +44,6 @@ typedef u32 compat_ulong_t;
typedef u64 compat_u64;
typedef u32 compat_uptr_t;
-struct compat_timespec {
- compat_time_t tv_sec;
- s32 tv_nsec;
-};
-
-struct compat_timeval {
- compat_time_t tv_sec;
- s32 tv_usec;
-};
-
struct compat_stat {
compat_dev_t st_dev;
compat_ino_t st_ino;
@@ -173,10 +162,10 @@ struct compat_ipc64_perm {
struct compat_semid64_ds {
struct compat_ipc64_perm sem_perm;
- unsigned int __unused1;
- compat_time_t sem_otime;
- unsigned int __unused2;
- compat_time_t sem_ctime;
+ unsigned int sem_otime_high;
+ unsigned int sem_otime;
+ unsigned int sem_ctime_high;
+ unsigned int sem_ctime;
compat_ulong_t sem_nsems;
compat_ulong_t __unused3;
compat_ulong_t __unused4;
@@ -184,12 +173,12 @@ struct compat_semid64_ds {
struct compat_msqid64_ds {
struct compat_ipc64_perm msg_perm;
- unsigned int __unused1;
- compat_time_t msg_stime;
- unsigned int __unused2;
- compat_time_t msg_rtime;
- unsigned int __unused3;
- compat_time_t msg_ctime;
+ unsigned int msg_stime_high;
+ unsigned int msg_stime;
+ unsigned int msg_rtime_high;
+ unsigned int msg_rtime;
+ unsigned int msg_ctime_high;
+ unsigned int msg_ctime;
compat_ulong_t msg_cbytes;
compat_ulong_t msg_qnum;
compat_ulong_t msg_qbytes;
@@ -201,12 +190,12 @@ struct compat_msqid64_ds {
struct compat_shmid64_ds {
struct compat_ipc64_perm shm_perm;
- unsigned int __unused1;
- compat_time_t shm_atime;
- unsigned int __unused2;
- compat_time_t shm_dtime;
- unsigned int __unused3;
- compat_time_t shm_ctime;
+ unsigned int shm_atime_high;
+ unsigned int shm_atime;
+ unsigned int shm_dtime_high;
+ unsigned int shm_dtime;
+ unsigned int shm_ctime_high;
+ unsigned int shm_ctime;
unsigned int __unused4;
compat_size_t shm_segsz;
compat_pid_t shm_cpid;
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 471b227..c40b438 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -74,6 +74,27 @@
*/
#define EX_R3 EX_DAR
+#define STF_ENTRY_BARRIER_SLOT \
+ STF_ENTRY_BARRIER_FIXUP_SECTION; \
+ nop; \
+ nop; \
+ nop
+
+#define STF_EXIT_BARRIER_SLOT \
+ STF_EXIT_BARRIER_FIXUP_SECTION; \
+ nop; \
+ nop; \
+ nop; \
+ nop; \
+ nop; \
+ nop
+
+/*
+ * r10 must be free to use, r13 must be paca
+ */
+#define INTERRUPT_TO_KERNEL \
+ STF_ENTRY_BARRIER_SLOT
+
/*
* Macros for annotating the expected destination of (h)rfid
*
@@ -90,16 +111,19 @@
rfid
#define RFI_TO_USER \
+ STF_EXIT_BARRIER_SLOT; \
RFI_FLUSH_SLOT; \
rfid; \
b rfi_flush_fallback
#define RFI_TO_USER_OR_KERNEL \
+ STF_EXIT_BARRIER_SLOT; \
RFI_FLUSH_SLOT; \
rfid; \
b rfi_flush_fallback
#define RFI_TO_GUEST \
+ STF_EXIT_BARRIER_SLOT; \
RFI_FLUSH_SLOT; \
rfid; \
b rfi_flush_fallback
@@ -108,21 +132,25 @@
hrfid
#define HRFI_TO_USER \
+ STF_EXIT_BARRIER_SLOT; \
RFI_FLUSH_SLOT; \
hrfid; \
b hrfi_flush_fallback
#define HRFI_TO_USER_OR_KERNEL \
+ STF_EXIT_BARRIER_SLOT; \
RFI_FLUSH_SLOT; \
hrfid; \
b hrfi_flush_fallback
#define HRFI_TO_GUEST \
+ STF_EXIT_BARRIER_SLOT; \
RFI_FLUSH_SLOT; \
hrfid; \
b hrfi_flush_fallback
#define HRFI_TO_UNKNOWN \
+ STF_EXIT_BARRIER_SLOT; \
RFI_FLUSH_SLOT; \
hrfid; \
b hrfi_flush_fallback
@@ -254,6 +282,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
#define __EXCEPTION_PROLOG_1_PRE(area) \
OPT_SAVE_REG_TO_PACA(area+EX_PPR, r9, CPU_FTR_HAS_PPR); \
OPT_SAVE_REG_TO_PACA(area+EX_CFAR, r10, CPU_FTR_CFAR); \
+ INTERRUPT_TO_KERNEL; \
SAVE_CTR(r10, area); \
mfcr r9;
diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index 1e82eb3..a9b64df 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -187,6 +187,22 @@ label##3: \
FTR_ENTRY_OFFSET label##1b-label##3b; \
.popsection;
+#define STF_ENTRY_BARRIER_FIXUP_SECTION \
+953: \
+ .pushsection __stf_entry_barrier_fixup,"a"; \
+ .align 2; \
+954: \
+ FTR_ENTRY_OFFSET 953b-954b; \
+ .popsection;
+
+#define STF_EXIT_BARRIER_FIXUP_SECTION \
+955: \
+ .pushsection __stf_exit_barrier_fixup,"a"; \
+ .align 2; \
+956: \
+ FTR_ENTRY_OFFSET 955b-956b; \
+ .popsection;
+
#define RFI_FLUSH_FIXUP_SECTION \
951: \
.pushsection __rfi_flush_fixup,"a"; \
@@ -199,6 +215,9 @@ label##3: \
#ifndef __ASSEMBLY__
#include <linux/types.h>
+extern long stf_barrier_fallback;
+extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup;
+extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup;
extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup;
void apply_feature_fixups(void);
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index 9abddde..b2dabd0 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -69,17 +69,30 @@ struct dyn_arch_ftrace {
#endif
#if defined(CONFIG_FTRACE_SYSCALLS) && !defined(__ASSEMBLY__)
-#ifdef PPC64_ELF_ABI_v1
+/*
+ * Some syscall entry functions on powerpc start with "ppc_" (fork and clone,
+ * for instance) or ppc32_/ppc64_. We should also match the sys_ variant with
+ * those.
+ */
#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+#ifdef PPC64_ELF_ABI_v1
static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
{
- /*
- * Compare the symbol name with the system call name. Skip the .sys or .SyS
- * prefix from the symbol name and the sys prefix from the system call name and
- * just match the rest. This is only needed on ppc64 since symbol names on
- * 32bit do not start with a period so the generic function will work.
- */
- return !strcmp(sym + 4, name + 3);
+ /* We need to skip past the initial dot, and the __se_sys alias */
+ return !strcmp(sym + 1, name) ||
+ (!strncmp(sym, ".__se_sys", 9) && !strcmp(sym + 6, name)) ||
+ (!strncmp(sym, ".ppc_", 5) && !strcmp(sym + 5, name + 4)) ||
+ (!strncmp(sym, ".ppc32_", 7) && !strcmp(sym + 7, name + 4)) ||
+ (!strncmp(sym, ".ppc64_", 7) && !strcmp(sym + 7, name + 4));
+}
+#else
+static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
+{
+ return !strcmp(sym, name) ||
+ (!strncmp(sym, "__se_sys", 8) && !strcmp(sym + 5, name)) ||
+ (!strncmp(sym, "ppc_", 4) && !strcmp(sym + 4, name + 4)) ||
+ (!strncmp(sym, "ppc32_", 6) && !strcmp(sym + 6, name + 4)) ||
+ (!strncmp(sym, "ppc64_", 6) && !strcmp(sym + 6, name + 4));
}
#endif
#endif /* CONFIG_FTRACE_SYSCALLS && !__ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h
index 5986d47..383f628 100644
--- a/arch/powerpc/include/asm/hardirq.h
+++ b/arch/powerpc/include/asm/hardirq.h
@@ -25,15 +25,8 @@ typedef struct {
DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
#define __ARCH_IRQ_STAT
-
-#define local_softirq_pending() __this_cpu_read(irq_stat.__softirq_pending)
-
-#define __ARCH_SET_SOFTIRQ_PENDING
#define __ARCH_IRQ_EXIT_IRQS_DISABLED
-#define set_softirq_pending(x) __this_cpu_write(irq_stat.__softirq_pending, (x))
-#define or_softirq_pending(x) __this_cpu_or(irq_stat.__softirq_pending, (x))
-
static inline void ack_bad_irq(unsigned int irq)
{
printk(KERN_CRIT "unexpected IRQ trap at vector %02x\n", irq);
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 4c02a73..e7377b7 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -96,6 +96,7 @@ struct kvmppc_vcore {
struct kvm_vcpu *runner;
struct kvm *kvm;
u64 tb_offset; /* guest timebase - host timebase */
+ u64 tb_offset_applied; /* timebase offset currently in force */
ulong lpcr;
u32 arch_compat;
ulong pcr;
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 4185f1c..3f109a3 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -165,7 +165,6 @@ struct paca_struct {
u64 saved_msr; /* MSR saved here by enter_rtas */
u16 trap_save; /* Used when bad stack is encountered */
u8 irq_soft_mask; /* mask for irq soft masking */
- u8 soft_enabled; /* irq soft-enable flag */
u8 irq_happened; /* irq happened while soft-disabled */
u8 io_sync; /* writel() needs spin_unlock sync */
u8 irq_work_pending; /* IRQ_WORK interrupt while soft-disable */
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 401c62a..2af9ded 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -92,24 +92,6 @@ extern int pci_mmap_legacy_page_range(struct pci_bus *bus,
#define HAVE_PCI_LEGACY 1
-#ifdef CONFIG_PPC64
-
-/* The PCI address space does not equal the physical memory address
- * space (we have an IOMMU). The IDE and SCSI device layers use
- * this boolean for bounce buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS (0)
-
-#else /* 32-bit */
-
-/* The PCI address space does equal the physical memory
- * address space (no IOMMU). The IDE and SCSI device layers use
- * this boolean for bounce buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS (1)
-
-#endif /* CONFIG_PPC64 */
-
extern void pcibios_claim_one_bus(struct pci_bus *b);
extern void pcibios_finish_adding_to_bus(struct pci_bus *bus);
diff --git a/arch/powerpc/include/asm/powernv.h b/arch/powerpc/include/asm/powernv.h
index d1c2d2e6..2f3ff7a 100644
--- a/arch/powerpc/include/asm/powernv.h
+++ b/arch/powerpc/include/asm/powernv.h
@@ -15,7 +15,7 @@
extern void powernv_set_nmmu_ptcr(unsigned long ptcr);
extern struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
unsigned long flags,
- struct npu_context *(*cb)(struct npu_context *, void *),
+ void (*cb)(struct npu_context *, void *),
void *priv);
extern void pnv_npu2_destroy_context(struct npu_context *context,
struct pci_dev *gpdev);
diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h
index fa4d2e1..44989b2 100644
--- a/arch/powerpc/include/asm/security_features.h
+++ b/arch/powerpc/include/asm/security_features.h
@@ -12,6 +12,17 @@
extern unsigned long powerpc_security_features;
extern bool rfi_flush;
+/* These are bit flags */
+enum stf_barrier_type {
+ STF_BARRIER_NONE = 0x1,
+ STF_BARRIER_FALLBACK = 0x2,
+ STF_BARRIER_EIEIO = 0x4,
+ STF_BARRIER_SYNC_ORI = 0x8,
+};
+
+void setup_stf_barrier(void);
+void do_stf_barrier_fixups(enum stf_barrier_type types);
+
static inline void security_ftr_set(unsigned long feature)
{
powerpc_security_features |= feature;
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 9f42164..16b0778 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -91,6 +91,7 @@ extern int start_topology_update(void);
extern int stop_topology_update(void);
extern int prrn_is_enabled(void);
extern int find_and_online_cpu_nid(int cpu);
+extern int timed_topology_update(int nsecs);
#else
static inline int start_topology_update(void)
{
@@ -108,16 +109,12 @@ static inline int find_and_online_cpu_nid(int cpu)
{
return 0;
}
+static inline int timed_topology_update(int nsecs)
+{
+ return 0;
+}
#endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
-#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_NEED_MULTIPLE_NODES)
-#if defined(CONFIG_PPC_SPLPAR)
-extern int timed_topology_update(int nsecs);
-#else
-#define timed_topology_update(nsecs)
-#endif /* CONFIG_PPC_SPLPAR */
-#endif /* CONFIG_HOTPLUG_CPU || CONFIG_NEED_MULTIPLE_NODES */
-
#include <asm-generic/topology.h>
#ifdef CONFIG_SMP
diff --git a/arch/powerpc/include/uapi/asm/msgbuf.h b/arch/powerpc/include/uapi/asm/msgbuf.h
index 65beb09..2b1b377 100644
--- a/arch/powerpc/include/uapi/asm/msgbuf.h
+++ b/arch/powerpc/include/uapi/asm/msgbuf.h
@@ -10,18 +10,18 @@
struct msqid64_ds {
struct ipc64_perm msg_perm;
-#ifndef __powerpc64__
- unsigned int __unused1;
-#endif
+#ifdef __powerpc64__
__kernel_time_t msg_stime; /* last msgsnd time */
-#ifndef __powerpc64__
- unsigned int __unused2;
-#endif
__kernel_time_t msg_rtime; /* last msgrcv time */
-#ifndef __powerpc64__
- unsigned int __unused3;
-#endif
__kernel_time_t msg_ctime; /* last change time */
+#else
+ unsigned long msg_stime_high;
+ unsigned long msg_stime; /* last msgsnd time */
+ unsigned long msg_rtime_high;
+ unsigned long msg_rtime; /* last msgrcv time */
+ unsigned long msg_ctime_high;
+ unsigned long msg_ctime; /* last change time */
+#endif
unsigned long msg_cbytes; /* current number of bytes on queue */
unsigned long msg_qnum; /* number of messages in queue */
unsigned long msg_qbytes; /* max number of bytes on queue */
diff --git a/arch/powerpc/include/uapi/asm/sembuf.h b/arch/powerpc/include/uapi/asm/sembuf.h
index 8f393d6..3f60946 100644
--- a/arch/powerpc/include/uapi/asm/sembuf.h
+++ b/arch/powerpc/include/uapi/asm/sembuf.h
@@ -15,20 +15,20 @@
* between kernel and user space.
*
* Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
+ * - 2 miscellaneous 32/64-bit values
*/
struct semid64_ds {
struct ipc64_perm sem_perm; /* permissions .. see ipc.h */
#ifndef __powerpc64__
- unsigned long __unused1;
-#endif
+ unsigned long sem_otime_high;
+ unsigned long sem_otime; /* last semop time */
+ unsigned long sem_ctime_high;
+ unsigned long sem_ctime; /* last change time */
+#else
__kernel_time_t sem_otime; /* last semop time */
-#ifndef __powerpc64__
- unsigned long __unused2;
-#endif
__kernel_time_t sem_ctime; /* last change time */
+#endif
unsigned long sem_nsems; /* no. of semaphores in array */
unsigned long __unused3;
unsigned long __unused4;
diff --git a/arch/powerpc/include/uapi/asm/shmbuf.h b/arch/powerpc/include/uapi/asm/shmbuf.h
index deb1c3e..b591c4d 100644
--- a/arch/powerpc/include/uapi/asm/shmbuf.h
+++ b/arch/powerpc/include/uapi/asm/shmbuf.h
@@ -16,25 +16,22 @@
* between kernel and user space.
*
* Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
* - 2 miscellaneous 32-bit values
*/
struct shmid64_ds {
struct ipc64_perm shm_perm; /* operation perms */
-#ifndef __powerpc64__
- unsigned long __unused1;
-#endif
+#ifdef __powerpc64__
__kernel_time_t shm_atime; /* last attach time */
-#ifndef __powerpc64__
- unsigned long __unused2;
-#endif
__kernel_time_t shm_dtime; /* last detach time */
-#ifndef __powerpc64__
- unsigned long __unused3;
-#endif
__kernel_time_t shm_ctime; /* last change time */
-#ifndef __powerpc64__
+#else
+ unsigned long shm_atime_high;
+ unsigned long shm_atime; /* last attach time */
+ unsigned long shm_dtime_high;
+ unsigned long shm_dtime; /* last detach time */
+ unsigned long shm_ctime_high;
+ unsigned long shm_ctime; /* last change time */
unsigned long __unused4;
#endif
size_t shm_segsz; /* size of segment (bytes) */
diff --git a/arch/powerpc/include/uapi/asm/siginfo.h b/arch/powerpc/include/uapi/asm/siginfo.h
index 9f14245..1d51d9b 100644
--- a/arch/powerpc/include/uapi/asm/siginfo.h
+++ b/arch/powerpc/include/uapi/asm/siginfo.h
@@ -15,19 +15,4 @@
#include <asm-generic/siginfo.h>
-/*
- * SIGFPE si_codes
- */
-#ifdef __KERNEL__
-#define FPE_FIXME 0 /* Broken dup of SI_USER */
-#endif /* __KERNEL__ */
-
-/*
- * SIGTRAP si_codes
- */
-#ifdef __KERNEL__
-#define TRAP_FIXME 0 /* Broken dup of SI_USER */
-#endif /* __KERNEL__ */
-
-
#endif /* _ASM_POWERPC_SIGINFO_H */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 6bee65f..8817c5a 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -13,6 +13,7 @@
* 2 of the License, or (at your option) any later version.
*/
+#include <linux/compat.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
@@ -42,7 +43,6 @@
#include <asm/paca.h>
#include <asm/lppaca.h>
#include <asm/cache.h>
-#include <asm/compat.h>
#include <asm/mmu.h>
#include <asm/hvcall.h>
#include <asm/xics.h>
@@ -562,6 +562,7 @@ int main(void)
OFFSET(VCORE_NAPPING_THREADS, kvmppc_vcore, napping_threads);
OFFSET(VCORE_KVM, kvmppc_vcore, kvm);
OFFSET(VCORE_TB_OFFSET, kvmppc_vcore, tb_offset);
+ OFFSET(VCORE_TB_OFFSET_APPL, kvmppc_vcore, tb_offset_applied);
OFFSET(VCORE_LPCR, kvmppc_vcore, lpcr);
OFFSET(VCORE_PCR, kvmppc_vcore, pcr);
OFFSET(VCORE_DPDES, kvmppc_vcore, dpdes);
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index 3f30c99..458b928 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -28,6 +28,7 @@
beqlr
li r0,0
mtspr SPRN_LPID,r0
+ mtspr SPRN_PCR,r0
mfspr r3,SPRN_LPCR
li r4,(LPCR_LPES1 >> LPCR_LPES_SH)
bl __init_LPCR_ISA206
@@ -41,6 +42,7 @@
beqlr
li r0,0
mtspr SPRN_LPID,r0
+ mtspr SPRN_PCR,r0
mfspr r3,SPRN_LPCR
li r4,(LPCR_LPES1 >> LPCR_LPES_SH)
bl __init_LPCR_ISA206
@@ -57,6 +59,7 @@
beqlr
li r0,0
mtspr SPRN_LPID,r0
+ mtspr SPRN_PCR,r0
mfspr r3,SPRN_LPCR
ori r3, r3, LPCR_PECEDH
li r4,0 /* LPES = 0 */
@@ -78,6 +81,7 @@
beqlr
li r0,0
mtspr SPRN_LPID,r0
+ mtspr SPRN_PCR,r0
mfspr r3,SPRN_LPCR
ori r3, r3, LPCR_PECEDH
li r4,0 /* LPES = 0 */
@@ -99,6 +103,7 @@
mtspr SPRN_PSSCR,r0
mtspr SPRN_LPID,r0
mtspr SPRN_PID,r0
+ mtspr SPRN_PCR,r0
mfspr r3,SPRN_LPCR
LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC)
or r3, r3, r4
@@ -123,6 +128,7 @@
mtspr SPRN_PSSCR,r0
mtspr SPRN_LPID,r0
mtspr SPRN_PID,r0
+ mtspr SPRN_PCR,r0
mfspr r3,SPRN_LPCR
LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC)
or r3, r3, r4
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index da20569..138157de 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -309,8 +309,6 @@ int dma_set_coherent_mask(struct device *dev, u64 mask)
}
EXPORT_SYMBOL(dma_set_coherent_mask);
-#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-
int dma_set_mask(struct device *dev, u64 dma_mask)
{
if (ppc_md.dma_set_mask)
@@ -361,7 +359,6 @@ EXPORT_SYMBOL_GPL(dma_get_required_mask);
static int __init dma_init(void)
{
- dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
#ifdef CONFIG_PCI
dma_debug_add_bus(&pci_bus_type);
#endif
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 8ab51f6..c904477 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -101,6 +101,7 @@ static void __restore_cpu_cpufeatures(void)
if (hv_mode) {
mtspr(SPRN_LPID, 0);
mtspr(SPRN_HFSCR, system_registers.hfscr);
+ mtspr(SPRN_PCR, 0);
}
mtspr(SPRN_FSCR, system_registers.fscr);
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index bc640e4..90bb39b 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1775,18 +1775,6 @@ static int proc_eeh_show(struct seq_file *m, void *v)
return 0;
}
-static int proc_eeh_open(struct inode *inode, struct file *file)
-{
- return single_open(file, proc_eeh_show, NULL);
-}
-
-static const struct file_operations proc_eeh_operations = {
- .open = proc_eeh_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
#ifdef CONFIG_DEBUG_FS
static int eeh_enable_dbgfs_set(void *data, u64 val)
{
@@ -1828,7 +1816,7 @@ DEFINE_SIMPLE_ATTRIBUTE(eeh_freeze_dbgfs_ops, eeh_freeze_dbgfs_get,
static int __init eeh_init_proc(void)
{
if (machine_is(pseries) || machine_is(powernv)) {
- proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations);
+ proc_create_single("powerpc/eeh", 0, NULL, proc_eeh_show);
#ifdef CONFIG_DEBUG_FS
debugfs_create_file("eeh_enable", 0600,
powerpc_debugfs_root, NULL,
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 2d4956e..ee5a67d 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -807,7 +807,8 @@ static void eeh_restore_bridge_bars(struct eeh_dev *edev)
eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]);
/* PCI Command: 0x4 */
- eeh_ops->write_config(pdn, PCI_COMMAND, 4, edev->config_space[1]);
+ eeh_ops->write_config(pdn, PCI_COMMAND, 4, edev->config_space[1] |
+ PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER);
/* Check the PCIe link is ready */
eeh_bridge_check_link(edev);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index ae6a849..f283958 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -885,7 +885,7 @@
#endif
-EXC_REAL_MASKABLE(decrementer, 0x900, 0x80, IRQS_DISABLED)
+EXC_REAL_OOL_MASKABLE(decrementer, 0x900, 0x80, IRQS_DISABLED)
EXC_VIRT_MASKABLE(decrementer, 0x4900, 0x80, 0x900, IRQS_DISABLED)
TRAMP_KVM(PACA_EXGEN, 0x900)
EXC_COMMON_ASYNC(decrementer_common, 0x900, timer_interrupt)
@@ -961,6 +961,7 @@
mtctr r13; \
GET_PACA(r13); \
std r10,PACA_EXGEN+EX_R10(r13); \
+ INTERRUPT_TO_KERNEL; \
KVMTEST_PR(0xc00); /* uses r10, branch to do_kvm_0xc00_system_call */ \
HMT_MEDIUM; \
mfctr r9;
@@ -969,7 +970,8 @@
#define SYSCALL_KVMTEST \
HMT_MEDIUM; \
mr r9,r13; \
- GET_PACA(r13);
+ GET_PACA(r13); \
+ INTERRUPT_TO_KERNEL;
#endif
#define LOAD_SYSCALL_HANDLER(reg) \
@@ -1507,6 +1509,19 @@
b .; \
MASKED_DEC_HANDLER(_H)
+TRAMP_REAL_BEGIN(stf_barrier_fallback)
+ std r9,PACA_EXRFI+EX_R9(r13)
+ std r10,PACA_EXRFI+EX_R10(r13)
+ sync
+ ld r9,PACA_EXRFI+EX_R9(r13)
+ ld r10,PACA_EXRFI+EX_R10(r13)
+ ori 31,31,0
+ .rept 14
+ b 1f
+1:
+ .endr
+ blr
+
TRAMP_REAL_BEGIN(rfi_flush_fallback)
SET_SCRATCH0(r13);
GET_PACA(r13);
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 79d0054..e734f6e 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -553,12 +553,12 @@
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
lbz r0,HSTATE_HWTHREAD_STATE(r13)
cmpwi r0,KVM_HWTHREAD_IN_KERNEL
- beq 1f
+ beq 0f
li r0,KVM_HWTHREAD_IN_KERNEL
stb r0,HSTATE_HWTHREAD_STATE(r13)
/* Order setting hwthread_state vs. testing hwthread_req */
sync
- lbz r0,HSTATE_HWTHREAD_REQ(r13)
+0: lbz r0,HSTATE_HWTHREAD_REQ(r13)
cmpwi r0,0
beq 1f
b kvm_start_guest
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index fe6fc63..38c5b47 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -441,7 +441,6 @@ static int mce_handle_ierror(struct pt_regs *regs,
if (pfn != ULONG_MAX) {
*phys_addr =
(pfn << PAGE_SHIFT);
- handled = 1;
}
}
}
@@ -532,9 +531,7 @@ static int mce_handle_derror(struct pt_regs *regs,
* kernel/exception-64s.h
*/
if (get_paca()->in_mce < MAX_MCE_DEPTH)
- if (!mce_find_instr_ea_and_pfn(regs, addr,
- phys_addr))
- handled = 1;
+ mce_find_instr_ea_and_pfn(regs, addr, phys_addr);
}
found = 1;
}
@@ -572,7 +569,7 @@ static long mce_handle_error(struct pt_regs *regs,
const struct mce_ierror_table itable[])
{
struct mce_error_info mce_err = { 0 };
- uint64_t addr, phys_addr;
+ uint64_t addr, phys_addr = ULONG_MAX;
uint64_t srr1 = regs->msr;
long handled;
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 1237f13..26ea979 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -632,6 +632,7 @@ void do_break (struct pt_regs *regs, unsigned long address,
hw_breakpoint_disable();
/* Deliver the signal to userspace */
+ clear_siginfo(&info);
info.si_signo = SIGTRAP;
info.si_errno = 0;
info.si_code = TRAP_HWBKPT;
diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c
index fb070d8..d49063d 100644
--- a/arch/powerpc/kernel/rtas-proc.c
+++ b/arch/powerpc/kernel/rtas-proc.c
@@ -154,18 +154,6 @@ static ssize_t ppc_rtas_tone_volume_write(struct file *file,
static int ppc_rtas_tone_volume_show(struct seq_file *m, void *v);
static int ppc_rtas_rmo_buf_show(struct seq_file *m, void *v);
-static int sensors_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ppc_rtas_sensors_show, NULL);
-}
-
-static const struct file_operations ppc_rtas_sensors_operations = {
- .open = sensors_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int poweron_open(struct inode *inode, struct file *file)
{
return single_open(file, ppc_rtas_poweron_show, NULL);
@@ -231,18 +219,6 @@ static const struct file_operations ppc_rtas_tone_volume_operations = {
.release = single_release,
};
-static int rmo_buf_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ppc_rtas_rmo_buf_show, NULL);
-}
-
-static const struct file_operations ppc_rtas_rmo_buf_ops = {
- .open = rmo_buf_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int ppc_rtas_find_all_sensors(void);
static void ppc_rtas_process_sensor(struct seq_file *m,
struct individual_sensor *s, int state, int error, const char *loc);
@@ -267,14 +243,14 @@ static int __init proc_rtas_init(void)
&ppc_rtas_clock_operations);
proc_create("powerpc/rtas/poweron", 0644, NULL,
&ppc_rtas_poweron_operations);
- proc_create("powerpc/rtas/sensors", 0444, NULL,
- &ppc_rtas_sensors_operations);
+ proc_create_single("powerpc/rtas/sensors", 0444, NULL,
+ ppc_rtas_sensors_show);
proc_create("powerpc/rtas/frequency", 0644, NULL,
&ppc_rtas_tone_freq_operations);
proc_create("powerpc/rtas/volume", 0644, NULL,
&ppc_rtas_tone_volume_operations);
- proc_create("powerpc/rtas/rmo_buffer", 0400, NULL,
- &ppc_rtas_rmo_buf_ops);
+ proc_create_single("powerpc/rtas/rmo_buffer", 0400, NULL,
+ ppc_rtas_rmo_buf_show);
return 0;
}
diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c
index bab5a27..b98a722 100644
--- a/arch/powerpc/kernel/security.c
+++ b/arch/powerpc/kernel/security.c
@@ -8,6 +8,7 @@
#include <linux/device.h>
#include <linux/seq_buf.h>
+#include <asm/debugfs.h>
#include <asm/security_features.h>
@@ -86,3 +87,151 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c
return s.len;
}
+
+/*
+ * Store-forwarding barrier support.
+ */
+
+static enum stf_barrier_type stf_enabled_flush_types;
+static bool no_stf_barrier;
+bool stf_barrier;
+
+static int __init handle_no_stf_barrier(char *p)
+{
+ pr_info("stf-barrier: disabled on command line.");
+ no_stf_barrier = true;
+ return 0;
+}
+
+early_param("no_stf_barrier", handle_no_stf_barrier);
+
+/* This is the generic flag used by other architectures */
+static int __init handle_ssbd(char *p)
+{
+ if (!p || strncmp(p, "auto", 5) == 0 || strncmp(p, "on", 2) == 0 ) {
+ /* Until firmware tells us, we have the barrier with auto */
+ return 0;
+ } else if (strncmp(p, "off", 3) == 0) {
+ handle_no_stf_barrier(NULL);
+ return 0;
+ } else
+ return 1;
+
+ return 0;
+}
+early_param("spec_store_bypass_disable", handle_ssbd);
+
+/* This is the generic flag used by other architectures */
+static int __init handle_no_ssbd(char *p)
+{
+ handle_no_stf_barrier(NULL);
+ return 0;
+}
+early_param("nospec_store_bypass_disable", handle_no_ssbd);
+
+static void stf_barrier_enable(bool enable)
+{
+ if (enable)
+ do_stf_barrier_fixups(stf_enabled_flush_types);
+ else
+ do_stf_barrier_fixups(STF_BARRIER_NONE);
+
+ stf_barrier = enable;
+}
+
+void setup_stf_barrier(void)
+{
+ enum stf_barrier_type type;
+ bool enable, hv;
+
+ hv = cpu_has_feature(CPU_FTR_HVMODE);
+
+ /* Default to fallback in case fw-features are not available */
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ type = STF_BARRIER_EIEIO;
+ else if (cpu_has_feature(CPU_FTR_ARCH_207S))
+ type = STF_BARRIER_SYNC_ORI;
+ else if (cpu_has_feature(CPU_FTR_ARCH_206))
+ type = STF_BARRIER_FALLBACK;
+ else
+ type = STF_BARRIER_NONE;
+
+ enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+ (security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR) ||
+ (security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV) && hv));
+
+ if (type == STF_BARRIER_FALLBACK) {
+ pr_info("stf-barrier: fallback barrier available\n");
+ } else if (type == STF_BARRIER_SYNC_ORI) {
+ pr_info("stf-barrier: hwsync barrier available\n");
+ } else if (type == STF_BARRIER_EIEIO) {
+ pr_info("stf-barrier: eieio barrier available\n");
+ }
+
+ stf_enabled_flush_types = type;
+
+ if (!no_stf_barrier)
+ stf_barrier_enable(enable);
+}
+
+ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ if (stf_barrier && stf_enabled_flush_types != STF_BARRIER_NONE) {
+ const char *type;
+ switch (stf_enabled_flush_types) {
+ case STF_BARRIER_EIEIO:
+ type = "eieio";
+ break;
+ case STF_BARRIER_SYNC_ORI:
+ type = "hwsync";
+ break;
+ case STF_BARRIER_FALLBACK:
+ type = "fallback";
+ break;
+ default:
+ type = "unknown";
+ }
+ return sprintf(buf, "Mitigation: Kernel entry/exit barrier (%s)\n", type);
+ }
+
+ if (!security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV) &&
+ !security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR))
+ return sprintf(buf, "Not affected\n");
+
+ return sprintf(buf, "Vulnerable\n");
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int stf_barrier_set(void *data, u64 val)
+{
+ bool enable;
+
+ if (val == 1)
+ enable = true;
+ else if (val == 0)
+ enable = false;
+ else
+ return -EINVAL;
+
+ /* Only do anything if we're changing state */
+ if (enable != stf_barrier)
+ stf_barrier_enable(enable);
+
+ return 0;
+}
+
+static int stf_barrier_get(void *data, u64 *val)
+{
+ *val = stf_barrier ? 1 : 0;
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_stf_barrier, stf_barrier_get, stf_barrier_set, "%llu\n");
+
+static __init int stf_barrier_debugfs_init(void)
+{
+ debugfs_create_file("stf_barrier", 0600, powerpc_debugfs_root, NULL, &fops_stf_barrier);
+ return 0;
+}
+device_initcall(stf_barrier_debugfs_init);
+#endif /* CONFIG_DEBUG_FS */
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 44c30dd..b78f142 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -890,6 +890,17 @@ static void __ref init_fallback_flush(void)
return;
l1d_size = ppc64_caches.l1d.size;
+
+ /*
+ * If there is no d-cache-size property in the device tree, l1d_size
+ * could be zero. That leads to the loop in the asm wrapping around to
+ * 2^64-1, and then walking off the end of the fallback area and
+ * eventually causing a page fault which is fatal. Just default to
+ * something vaguely sane.
+ */
+ if (!l1d_size)
+ l1d_size = (64 * 1024);
+
limit = min(ppc64_bolted_size(), ppc64_rma_size);
/*
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index e16ec7b..9ca7148 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -566,10 +566,35 @@ void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
#endif
#ifdef CONFIG_NMI_IPI
-static void stop_this_cpu(struct pt_regs *regs)
-#else
+static void nmi_stop_this_cpu(struct pt_regs *regs)
+{
+ /*
+ * This is a special case because it never returns, so the NMI IPI
+ * handling would never mark it as done, which makes any later
+ * smp_send_nmi_ipi() call spin forever. Mark it done now.
+ *
+ * IRQs are already hard disabled by the smp_handle_nmi_ipi.
+ */
+ nmi_ipi_lock();
+ nmi_ipi_busy_count--;
+ nmi_ipi_unlock();
+
+ /* Remove this CPU */
+ set_cpu_online(smp_processor_id(), false);
+
+ spin_begin();
+ while (1)
+ spin_cpu_relax();
+}
+
+void smp_send_stop(void)
+{
+ smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, nmi_stop_this_cpu, 1000000);
+}
+
+#else /* CONFIG_NMI_IPI */
+
static void stop_this_cpu(void *dummy)
-#endif
{
/* Remove this CPU */
set_cpu_online(smp_processor_id(), false);
@@ -582,12 +607,22 @@ static void stop_this_cpu(void *dummy)
void smp_send_stop(void)
{
-#ifdef CONFIG_NMI_IPI
- smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, stop_this_cpu, 1000000);
-#else
+ static bool stopped = false;
+
+ /*
+ * Prevent waiting on csd lock from a previous smp_send_stop.
+ * This is racy, but in general callers try to do the right
+ * thing and only fire off one smp_send_stop (e.g., see
+ * kernel/panic.c)
+ */
+ if (stopped)
+ return;
+
+ stopped = true;
+
smp_call_function(stop_this_cpu, NULL, 0);
-#endif
}
+#endif /* CONFIG_NMI_IPI */
struct thread_info *current_set[NR_CPUS];
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 0904492..0e17dcb 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -296,7 +296,6 @@ NOKPROBE_SYMBOL(die);
void user_single_step_siginfo(struct task_struct *tsk,
struct pt_regs *regs, siginfo_t *info)
{
- memset(info, 0, sizeof(*info));
info->si_signo = SIGTRAP;
info->si_code = TRAP_TRACE;
info->si_addr = (void __user *)regs->nip;
@@ -334,7 +333,7 @@ void _exception_pkey(int signr, struct pt_regs *regs, int code,
*/
thread_pkey_regs_save(¤t->thread);
- memset(&info, 0, sizeof(info));
+ clear_siginfo(&info);
info.si_signo = signr;
info.si_code = code;
info.si_addr = (void __user *) addr;
@@ -970,7 +969,7 @@ void unknown_exception(struct pt_regs *regs)
printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
regs->nip, regs->msr, regs->trap);
- _exception(SIGTRAP, regs, TRAP_FIXME, 0);
+ _exception(SIGTRAP, regs, TRAP_UNK, 0);
exception_exit(prev_state);
}
@@ -992,7 +991,7 @@ void instruction_breakpoint_exception(struct pt_regs *regs)
void RunModeException(struct pt_regs *regs)
{
- _exception(SIGTRAP, regs, TRAP_FIXME, 0);
+ _exception(SIGTRAP, regs, TRAP_UNK, 0);
}
void single_step_exception(struct pt_regs *regs)
@@ -1032,7 +1031,7 @@ static void emulate_single_step(struct pt_regs *regs)
static inline int __parse_fpscr(unsigned long fpscr)
{
- int ret = FPE_FIXME;
+ int ret = FPE_FLTUNK;
/* Invalid operation */
if ((fpscr & FPSCR_VE) && (fpscr & FPSCR_VX))
@@ -1973,7 +1972,7 @@ void SPEFloatingPointException(struct pt_regs *regs)
extern int do_spe_mathemu(struct pt_regs *regs);
unsigned long spefscr;
int fpexc_mode;
- int code = FPE_FIXME;
+ int code = FPE_FLTUNK;
int err;
flush_spe_to_thread(current);
@@ -2042,7 +2041,7 @@ void SPEFloatingPointRoundException(struct pt_regs *regs)
printk(KERN_ERR "unrecognized spe instruction "
"in %s at %lx\n", current->comm, regs->nip);
} else {
- _exception(SIGFPE, regs, FPE_FIXME, regs->nip);
+ _exception(SIGFPE, regs, FPE_FLTUNK, regs->nip);
return;
}
}
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index c8af90f..b8d8267 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -134,6 +134,20 @@
#ifdef CONFIG_PPC64
. = ALIGN(8);
+ __stf_entry_barrier_fixup : AT(ADDR(__stf_entry_barrier_fixup) - LOAD_OFFSET) {
+ __start___stf_entry_barrier_fixup = .;
+ *(__stf_entry_barrier_fixup)
+ __stop___stf_entry_barrier_fixup = .;
+ }
+
+ . = ALIGN(8);
+ __stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) {
+ __start___stf_exit_barrier_fixup = .;
+ *(__stf_exit_barrier_fixup)
+ __stop___stf_exit_barrier_fixup = .;
+ }
+
+ . = ALIGN(8);
__rfi_flush_fixup : AT(ADDR(__rfi_flush_fixup) - LOAD_OFFSET) {
__start___rfi_flush_fixup = .;
*(__rfi_flush_fixup)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index a57eafe..361f42c 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -162,7 +162,7 @@ static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG))
asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1)
: : "r" (addr), "r" (kvm->arch.lpid) : "memory");
- asm volatile("ptesync": : :"memory");
+ asm volatile("eieio ; tlbsync ; ptesync": : :"memory");
}
static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned long addr)
@@ -173,7 +173,7 @@ static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned long addr)
/* RIC=1 PRS=0 R=1 IS=2 */
asm volatile(PPC_TLBIE_5(%0, %1, 1, 0, 1)
: : "r" (rb), "r" (kvm->arch.lpid) : "memory");
- asm volatile("ptesync": : :"memory");
+ asm volatile("eieio ; tlbsync ; ptesync": : :"memory");
}
unsigned long kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep,
@@ -584,7 +584,7 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
if (ptep && pte_present(*ptep)) {
- old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT, 0,
+ old = kvmppc_radix_update_pte(kvm, ptep, ~0UL, 0,
gpa, shift);
kvmppc_radix_tlbie_page(kvm, gpa, shift);
if ((old & _PAGE_DIRTY) && memslot->dirty_bitmap) {
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 4d07fca..9963f65 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2441,6 +2441,7 @@ static void init_vcore_to_run(struct kvmppc_vcore *vc)
vc->in_guest = 0;
vc->napping_threads = 0;
vc->conferring_threads = 0;
+ vc->tb_offset_applied = 0;
}
static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index bd63fa8..07ca1b2 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -692,6 +692,7 @@
22: ld r8,VCORE_TB_OFFSET(r5)
cmpdi r8,0
beq 37f
+ std r8, VCORE_TB_OFFSET_APPL(r5)
mftb r6 /* current host timebase */
add r8,r8,r6
mtspr SPRN_TBU40,r8 /* update upper 40 bits */
@@ -940,18 +941,6 @@
ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
8:
- /*
- * Set the decrementer to the guest decrementer.
- */
- ld r8,VCPU_DEC_EXPIRES(r4)
- /* r8 is a host timebase value here, convert to guest TB */
- ld r5,HSTATE_KVM_VCORE(r13)
- ld r6,VCORE_TB_OFFSET(r5)
- add r8,r8,r6
- mftb r7
- subf r3,r7,r8
- mtspr SPRN_DEC,r3
-
ld r5, VCPU_SPRG0(r4)
ld r6, VCPU_SPRG1(r4)
ld r7, VCPU_SPRG2(r4)
@@ -1005,6 +994,18 @@
mtspr SPRN_LPCR,r8
isync
+ /*
+ * Set the decrementer to the guest decrementer.
+ */
+ ld r8,VCPU_DEC_EXPIRES(r4)
+ /* r8 is a host timebase value here, convert to guest TB */
+ ld r5,HSTATE_KVM_VCORE(r13)
+ ld r6,VCORE_TB_OFFSET_APPL(r5)
+ add r8,r8,r6
+ mftb r7
+ subf r3,r7,r8
+ mtspr SPRN_DEC,r3
+
/* Check if HDEC expires soon */
mfspr r3, SPRN_HDEC
EXTEND_HDEC(r3)
@@ -1597,8 +1598,27 @@
guest_bypass:
stw r12, STACK_SLOT_TRAP(r1)
- mr r3, r12
+
+ /* Save DEC */
+ /* Do this before kvmhv_commence_exit so we know TB is guest TB */
+ ld r3, HSTATE_KVM_VCORE(r13)
+ mfspr r5,SPRN_DEC
+ mftb r6
+ /* On P9, if the guest has large decr enabled, don't sign extend */
+BEGIN_FTR_SECTION
+ ld r4, VCORE_LPCR(r3)
+ andis. r4, r4, LPCR_LD@h
+ bne 16f
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+ extsw r5,r5
+16: add r5,r5,r6
+ /* r5 is a guest timebase value here, convert to host TB */
+ ld r4,VCORE_TB_OFFSET_APPL(r3)
+ subf r5,r4,r5
+ std r5,VCPU_DEC_EXPIRES(r9)
+
/* Increment exit count, poke other threads to exit */
+ mr r3, r12
bl kvmhv_commence_exit
nop
ld r9, HSTATE_KVM_VCPU(r13)
@@ -1639,23 +1659,6 @@
mtspr SPRN_PURR,r3
mtspr SPRN_SPURR,r4
- /* Save DEC */
- ld r3, HSTATE_KVM_VCORE(r13)
- mfspr r5,SPRN_DEC
- mftb r6
- /* On P9, if the guest has large decr enabled, don't sign extend */
-BEGIN_FTR_SECTION
- ld r4, VCORE_LPCR(r3)
- andis. r4, r4, LPCR_LD@h
- bne 16f
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
- extsw r5,r5
-16: add r5,r5,r6
- /* r5 is a guest timebase value here, convert to host TB */
- ld r4,VCORE_TB_OFFSET(r3)
- subf r5,r4,r5
- std r5,VCPU_DEC_EXPIRES(r9)
-
BEGIN_FTR_SECTION
b 8f
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
@@ -1905,6 +1908,14 @@
cmpwi cr2, r0, 0
beq cr2, 4f
+ /*
+ * Radix: do eieio; tlbsync; ptesync sequence in case we
+ * interrupted the guest between a tlbie and a ptesync.
+ */
+ eieio
+ tlbsync
+ ptesync
+
/* Radix: Handle the case where the guest used an illegal PID */
LOAD_REG_ADDR(r4, mmu_base_pid)
lwz r3, VCPU_GUEST_PID(r9)
@@ -2017,9 +2028,11 @@
27:
/* Subtract timebase offset from timebase */
- ld r8,VCORE_TB_OFFSET(r5)
+ ld r8, VCORE_TB_OFFSET_APPL(r5)
cmpdi r8,0
beq 17f
+ li r0, 0
+ std r0, VCORE_TB_OFFSET_APPL(r5)
mftb r6 /* current guest timebase */
subf r8,r8,r6
mtspr SPRN_TBU40,r8 /* update upper 40 bits */
@@ -2700,7 +2713,7 @@
add r3, r3, r5
ld r4, HSTATE_KVM_VCPU(r13)
ld r5, HSTATE_KVM_VCORE(r13)
- ld r6, VCORE_TB_OFFSET(r5)
+ ld r6, VCORE_TB_OFFSET_APPL(r5)
subf r3, r6, r3 /* convert to host TB value */
std r3, VCPU_DEC_EXPIRES(r4)
@@ -2799,7 +2812,7 @@
/* Restore guest decrementer */
ld r3, VCPU_DEC_EXPIRES(r4)
ld r5, HSTATE_KVM_VCORE(r13)
- ld r6, VCORE_TB_OFFSET(r5)
+ ld r6, VCORE_TB_OFFSET_APPL(r5)
add r3, r3, r6 /* convert host TB to guest TB value */
mftb r7
subf r3, r7, r3
@@ -3606,12 +3619,9 @@
*/
kvmhv_start_timing:
ld r5, HSTATE_KVM_VCORE(r13)
- lbz r6, VCORE_IN_GUEST(r5)
- cmpwi r6, 0
- beq 5f /* if in guest, need to */
- ld r6, VCORE_TB_OFFSET(r5) /* subtract timebase offset */
-5: mftb r5
- subf r5, r6, r5
+ ld r6, VCORE_TB_OFFSET_APPL(r5)
+ mftb r5
+ subf r5, r6, r5 /* subtract current timebase offset */
std r3, VCPU_CUR_ACTIVITY(r4)
std r5, VCPU_ACTIVITY_START(r4)
blr
@@ -3622,15 +3632,12 @@
*/
kvmhv_accumulate_time:
ld r5, HSTATE_KVM_VCORE(r13)
- lbz r8, VCORE_IN_GUEST(r5)
- cmpwi r8, 0
- beq 4f /* if in guest, need to */
- ld r8, VCORE_TB_OFFSET(r5) /* subtract timebase offset */
-4: ld r5, VCPU_CUR_ACTIVITY(r4)
+ ld r8, VCORE_TB_OFFSET_APPL(r5)
+ ld r5, VCPU_CUR_ACTIVITY(r4)
ld r6, VCPU_ACTIVITY_START(r4)
std r3, VCPU_CUR_ACTIVITY(r4)
mftb r7
- subf r7, r8, r7
+ subf r7, r8, r7 /* subtract current timebase offset */
std r7, VCPU_ACTIVITY_START(r4)
cmpdi r5, 0
beqlr
diff --git a/arch/powerpc/kvm/book3s_xive_template.c b/arch/powerpc/kvm/book3s_xive_template.c
index c7a5dea..99c3620 100644
--- a/arch/powerpc/kvm/book3s_xive_template.c
+++ b/arch/powerpc/kvm/book3s_xive_template.c
@@ -11,6 +11,9 @@
#define XGLUE(a,b) a##b
#define GLUE(a,b) XGLUE(a,b)
+/* Dummy interrupt used when taking interrupts out of a queue in H_CPPR */
+#define XICS_DUMMY 1
+
static void GLUE(X_PFX,ack_pending)(struct kvmppc_xive_vcpu *xc)
{
u8 cppr;
@@ -205,6 +208,10 @@ static u32 GLUE(X_PFX,scan_interrupts)(struct kvmppc_xive_vcpu *xc,
goto skip_ipi;
}
+ /* If it's the dummy interrupt, continue searching */
+ if (hirq == XICS_DUMMY)
+ goto skip_ipi;
+
/* If fetching, update queue pointers */
if (scan_type == scan_fetch) {
q->idx = idx;
@@ -385,9 +392,76 @@ static void GLUE(X_PFX,push_pending_to_hw)(struct kvmppc_xive_vcpu *xc)
__x_writeb(prio, __x_tima + TM_SPC_SET_OS_PENDING);
}
+static void GLUE(X_PFX,scan_for_rerouted_irqs)(struct kvmppc_xive *xive,
+ struct kvmppc_xive_vcpu *xc)
+{
+ unsigned int prio;
+
+ /* For each priority that is now masked */
+ for (prio = xc->cppr; prio < KVMPPC_XIVE_Q_COUNT; prio++) {
+ struct xive_q *q = &xc->queues[prio];
+ struct kvmppc_xive_irq_state *state;
+ struct kvmppc_xive_src_block *sb;
+ u32 idx, toggle, entry, irq, hw_num;
+ struct xive_irq_data *xd;
+ __be32 *qpage;
+ u16 src;
+
+ idx = q->idx;
+ toggle = q->toggle;
+ qpage = READ_ONCE(q->qpage);
+ if (!qpage)
+ continue;
+
+ /* For each interrupt in the queue */
+ for (;;) {
+ entry = be32_to_cpup(qpage + idx);
+
+ /* No more ? */
+ if ((entry >> 31) == toggle)
+ break;
+ irq = entry & 0x7fffffff;
+
+ /* Skip dummies and IPIs */
+ if (irq == XICS_DUMMY || irq == XICS_IPI)
+ goto next;
+ sb = kvmppc_xive_find_source(xive, irq, &src);
+ if (!sb)
+ goto next;
+ state = &sb->irq_state[src];
+
+ /* Has it been rerouted ? */
+ if (xc->server_num == state->act_server)
+ goto next;
+
+ /*
+ * Allright, it *has* been re-routed, kill it from
+ * the queue.
+ */
+ qpage[idx] = cpu_to_be32((entry & 0x80000000) | XICS_DUMMY);
+
+ /* Find the HW interrupt */
+ kvmppc_xive_select_irq(state, &hw_num, &xd);
+
+ /* If it's not an LSI, set PQ to 11 the EOI will force a resend */
+ if (!(xd->flags & XIVE_IRQ_FLAG_LSI))
+ GLUE(X_PFX,esb_load)(xd, XIVE_ESB_SET_PQ_11);
+
+ /* EOI the source */
+ GLUE(X_PFX,source_eoi)(hw_num, xd);
+
+ next:
+ idx = (idx + 1) & q->msk;
+ if (idx == 0)
+ toggle ^= 1;
+ }
+ }
+}
+
X_STATIC int GLUE(X_PFX,h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr)
{
struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct kvmppc_xive *xive = vcpu->kvm->arch.xive;
u8 old_cppr;
pr_devel("H_CPPR(cppr=%ld)\n", cppr);
@@ -407,14 +481,34 @@ X_STATIC int GLUE(X_PFX,h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr)
*/
smp_mb();
- /*
- * We are masking less, we need to look for pending things
- * to deliver and set VP pending bits accordingly to trigger
- * a new interrupt otherwise we might miss MFRR changes for
- * which we have optimized out sending an IPI signal.
- */
- if (cppr > old_cppr)
+ if (cppr > old_cppr) {
+ /*
+ * We are masking less, we need to look for pending things
+ * to deliver and set VP pending bits accordingly to trigger
+ * a new interrupt otherwise we might miss MFRR changes for
+ * which we have optimized out sending an IPI signal.
+ */
GLUE(X_PFX,push_pending_to_hw)(xc);
+ } else {
+ /*
+ * We are masking more, we need to check the queue for any
+ * interrupt that has been routed to another CPU, take
+ * it out (replace it with the dummy) and retrigger it.
+ *
+ * This is necessary since those interrupts may otherwise
+ * never be processed, at least not until this CPU restores
+ * its CPPR.
+ *
+ * This is in theory racy vs. HW adding new interrupts to
+ * the queue. In practice this works because the interesting
+ * cases are when the guest has done a set_xive() to move the
+ * interrupt away, which flushes the xive, followed by the
+ * target CPU doing a H_CPPR. So any new interrupt coming into
+ * the queue must still be routed to us and isn't a source
+ * of concern.
+ */
+ GLUE(X_PFX,scan_for_rerouted_irqs)(xive, xc);
+ }
/* Apply new CPPR */
xc->hw_cppr = cppr;
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 6038e2e..876d4f2 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -305,6 +305,13 @@ void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu)
kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_FP_UNAVAIL);
}
+#ifdef CONFIG_ALTIVEC
+void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu)
+{
+ kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_ALTIVEC_UNAVAIL);
+}
+#endif
+
void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu)
{
kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DECREMENTER);
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 35f80ab..e1bcdc3 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -23,6 +23,7 @@
#include <asm/page.h>
#include <asm/sections.h>
#include <asm/setup.h>
+#include <asm/security_features.h>
#include <asm/firmware.h>
struct fixup_entry {
@@ -55,7 +56,7 @@ static int patch_alt_instruction(unsigned int *src, unsigned int *dest,
unsigned int *target = (unsigned int *)branch_target(src);
/* Branch within the section doesn't need translating */
- if (target < alt_start || target >= alt_end) {
+ if (target < alt_start || target > alt_end) {
instr = translate_branch(dest, src);
if (!instr)
return 1;
@@ -117,6 +118,120 @@ void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end)
}
#ifdef CONFIG_PPC_BOOK3S_64
+void do_stf_entry_barrier_fixups(enum stf_barrier_type types)
+{
+ unsigned int instrs[3], *dest;
+ long *start, *end;
+ int i;
+
+ start = PTRRELOC(&__start___stf_entry_barrier_fixup),
+ end = PTRRELOC(&__stop___stf_entry_barrier_fixup);
+
+ instrs[0] = 0x60000000; /* nop */
+ instrs[1] = 0x60000000; /* nop */
+ instrs[2] = 0x60000000; /* nop */
+
+ i = 0;
+ if (types & STF_BARRIER_FALLBACK) {
+ instrs[i++] = 0x7d4802a6; /* mflr r10 */
+ instrs[i++] = 0x60000000; /* branch patched below */
+ instrs[i++] = 0x7d4803a6; /* mtlr r10 */
+ } else if (types & STF_BARRIER_EIEIO) {
+ instrs[i++] = 0x7e0006ac; /* eieio + bit 6 hint */
+ } else if (types & STF_BARRIER_SYNC_ORI) {
+ instrs[i++] = 0x7c0004ac; /* hwsync */
+ instrs[i++] = 0xe94d0000; /* ld r10,0(r13) */
+ instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+ }
+
+ for (i = 0; start < end; start++, i++) {
+ dest = (void *)start + *start;
+
+ pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+ patch_instruction(dest, instrs[0]);
+
+ if (types & STF_BARRIER_FALLBACK)
+ patch_branch(dest + 1, (unsigned long)&stf_barrier_fallback,
+ BRANCH_SET_LINK);
+ else
+ patch_instruction(dest + 1, instrs[1]);
+
+ patch_instruction(dest + 2, instrs[2]);
+ }
+
+ printk(KERN_DEBUG "stf-barrier: patched %d entry locations (%s barrier)\n", i,
+ (types == STF_BARRIER_NONE) ? "no" :
+ (types == STF_BARRIER_FALLBACK) ? "fallback" :
+ (types == STF_BARRIER_EIEIO) ? "eieio" :
+ (types == (STF_BARRIER_SYNC_ORI)) ? "hwsync"
+ : "unknown");
+}
+
+void do_stf_exit_barrier_fixups(enum stf_barrier_type types)
+{
+ unsigned int instrs[6], *dest;
+ long *start, *end;
+ int i;
+
+ start = PTRRELOC(&__start___stf_exit_barrier_fixup),
+ end = PTRRELOC(&__stop___stf_exit_barrier_fixup);
+
+ instrs[0] = 0x60000000; /* nop */
+ instrs[1] = 0x60000000; /* nop */
+ instrs[2] = 0x60000000; /* nop */
+ instrs[3] = 0x60000000; /* nop */
+ instrs[4] = 0x60000000; /* nop */
+ instrs[5] = 0x60000000; /* nop */
+
+ i = 0;
+ if (types & STF_BARRIER_FALLBACK || types & STF_BARRIER_SYNC_ORI) {
+ if (cpu_has_feature(CPU_FTR_HVMODE)) {
+ instrs[i++] = 0x7db14ba6; /* mtspr 0x131, r13 (HSPRG1) */
+ instrs[i++] = 0x7db04aa6; /* mfspr r13, 0x130 (HSPRG0) */
+ } else {
+ instrs[i++] = 0x7db243a6; /* mtsprg 2,r13 */
+ instrs[i++] = 0x7db142a6; /* mfsprg r13,1 */
+ }
+ instrs[i++] = 0x7c0004ac; /* hwsync */
+ instrs[i++] = 0xe9ad0000; /* ld r13,0(r13) */
+ instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+ if (cpu_has_feature(CPU_FTR_HVMODE)) {
+ instrs[i++] = 0x7db14aa6; /* mfspr r13, 0x131 (HSPRG1) */
+ } else {
+ instrs[i++] = 0x7db242a6; /* mfsprg r13,2 */
+ }
+ } else if (types & STF_BARRIER_EIEIO) {
+ instrs[i++] = 0x7e0006ac; /* eieio + bit 6 hint */
+ }
+
+ for (i = 0; start < end; start++, i++) {
+ dest = (void *)start + *start;
+
+ pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+ patch_instruction(dest, instrs[0]);
+ patch_instruction(dest + 1, instrs[1]);
+ patch_instruction(dest + 2, instrs[2]);
+ patch_instruction(dest + 3, instrs[3]);
+ patch_instruction(dest + 4, instrs[4]);
+ patch_instruction(dest + 5, instrs[5]);
+ }
+ printk(KERN_DEBUG "stf-barrier: patched %d exit locations (%s barrier)\n", i,
+ (types == STF_BARRIER_NONE) ? "no" :
+ (types == STF_BARRIER_FALLBACK) ? "fallback" :
+ (types == STF_BARRIER_EIEIO) ? "eieio" :
+ (types == (STF_BARRIER_SYNC_ORI)) ? "hwsync"
+ : "unknown");
+}
+
+
+void do_stf_barrier_fixups(enum stf_barrier_type types)
+{
+ do_stf_entry_barrier_fixups(types);
+ do_stf_exit_barrier_fixups(types);
+}
+
void do_rfi_flush_fixups(enum l1d_flush_type types)
{
unsigned int instrs[3], *dest;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index c01d627..ef268d5 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -168,6 +168,7 @@ static int do_sigbus(struct pt_regs *regs, unsigned long address,
return SIGBUS;
current->thread.trap_nr = BUS_ADRERR;
+ clear_siginfo(&info);
info.si_signo = SIGBUS;
info.si_errno = 0;
info.si_code = BUS_ADRERR;
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 737f8a4..c3c39b0 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -133,6 +133,7 @@ int __meminit arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *
start, start + size, rc);
return -EFAULT;
}
+ flush_inval_dcache_range(start, start + size);
return __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
}
@@ -159,6 +160,7 @@ int __meminit arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap
/* Remove htab bolted mappings for this section of memory */
start = (unsigned long)__va(start);
+ flush_inval_dcache_range(start, start + size);
ret = remove_section_mapping(start, start + size);
/* Ensure all vmalloc mappings are flushed in case they also
diff --git a/arch/powerpc/oprofile/backtrace.c b/arch/powerpc/oprofile/backtrace.c
index ecc66d5..ad054dd 100644
--- a/arch/powerpc/oprofile/backtrace.c
+++ b/arch/powerpc/oprofile/backtrace.c
@@ -7,6 +7,7 @@
* 2 of the License, or (at your option) any later version.
**/
+#include <linux/compat_time.h>
#include <linux/oprofile.h>
#include <linux/sched.h>
#include <asm/processor.h>
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 67d3125..84b58ab 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -222,6 +222,7 @@
config PHYS_64BIT
bool 'Large physical address support' if E500 || PPC_86xx
depends on (44x || E500 || PPC_86xx) && !PPC_83xx && !PPC_82xx
+ select PHYS_ADDR_T_64BIT
---help---
This option enables kernel support for larger than 32-bit physical
addresses. This feature may not be available on all cores.
diff --git a/arch/powerpc/platforms/cell/spufs/fault.c b/arch/powerpc/platforms/cell/spufs/fault.c
index 870c0a8..1e002e9 100644
--- a/arch/powerpc/platforms/cell/spufs/fault.c
+++ b/arch/powerpc/platforms/cell/spufs/fault.c
@@ -44,7 +44,7 @@ static void spufs_handle_event(struct spu_context *ctx,
return;
}
- memset(&info, 0, sizeof(info));
+ clear_siginfo(&info);
switch (type) {
case SPE_EVENT_INVALID_DMA:
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 9033c81..c9ef3c5 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -1093,20 +1093,8 @@ static int show_spu_loadavg(struct seq_file *s, void *private)
LOAD_INT(c), LOAD_FRAC(c),
count_active_contexts(),
atomic_read(&nr_spu_contexts),
- idr_get_cursor(&task_active_pid_ns(current)->idr));
+ idr_get_cursor(&task_active_pid_ns(current)->idr) - 1);
return 0;
-}
-
-static int spu_loadavg_open(struct inode *inode, struct file *file)
-{
- return single_open(file, show_spu_loadavg, NULL);
-}
-
-static const struct file_operations spu_loadavg_fops = {
- .open = spu_loadavg_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
};
int __init spu_sched_init(void)
@@ -1135,7 +1123,7 @@ int __init spu_sched_init(void)
mod_timer(&spuloadavg_timer, 0);
- entry = proc_create("spu_loadavg", 0, NULL, &spu_loadavg_fops);
+ entry = proc_create_single("spu_loadavg", 0, NULL, show_spu_loadavg);
if (!entry)
goto out_stop_kthread;
diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index de470ca..fc222a0 100644
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -82,19 +82,6 @@ static const struct file_operations memtrace_fops = {
.open = simple_open,
};
-static void flush_memory_region(u64 base, u64 size)
-{
- unsigned long line_size = ppc64_caches.l1d.size;
- u64 end = base + size;
- u64 addr;
-
- base = round_down(base, line_size);
- end = round_up(end, line_size);
-
- for (addr = base; addr < end; addr += line_size)
- asm volatile("dcbf 0,%0" : "=r" (addr) :: "memory");
-}
-
static int check_memblock_online(struct memory_block *mem, void *arg)
{
if (mem->state != MEM_ONLINE)
@@ -132,10 +119,6 @@ static bool memtrace_offline_pages(u32 nid, u64 start_pfn, u64 nr_pages)
walk_memory_range(start_pfn, end_pfn, (void *)MEM_OFFLINE,
change_memblock_state);
- /* RCU grace period? */
- flush_memory_region((u64)__va(start_pfn << PAGE_SHIFT),
- nr_pages << PAGE_SHIFT);
-
lock_device_hotplug();
remove_memory(nid, start_pfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT);
unlock_device_hotplug();
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index 69a4f9e..525e966 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -34,6 +34,19 @@
#define npu_to_phb(x) container_of(x, struct pnv_phb, npu)
/*
+ * spinlock to protect initialisation of an npu_context for a particular
+ * mm_struct.
+ */
+static DEFINE_SPINLOCK(npu_context_lock);
+
+/*
+ * When an address shootdown range exceeds this threshold we invalidate the
+ * entire TLB on the GPU for the given PID rather than each specific address in
+ * the range.
+ */
+#define ATSD_THRESHOLD (2*1024*1024)
+
+/*
* Other types of TCE cache invalidation are not functional in the
* hardware.
*/
@@ -401,7 +414,7 @@ struct npu_context {
bool nmmu_flush;
/* Callback to stop translation requests on a given GPU */
- struct npu_context *(*release_cb)(struct npu_context *, void *);
+ void (*release_cb)(struct npu_context *context, void *priv);
/*
* Private pointer passed to the above callback for usage by
@@ -671,11 +684,19 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
struct npu_context *npu_context = mn_to_npu_context(mn);
unsigned long address;
- for (address = start; address < end; address += PAGE_SIZE)
- mmio_invalidate(npu_context, 1, address, false);
+ if (end - start > ATSD_THRESHOLD) {
+ /*
+ * Just invalidate the entire PID if the address range is too
+ * large.
+ */
+ mmio_invalidate(npu_context, 0, 0, true);
+ } else {
+ for (address = start; address < end; address += PAGE_SIZE)
+ mmio_invalidate(npu_context, 1, address, false);
- /* Do the flush only on the final addess == end */
- mmio_invalidate(npu_context, 1, address, true);
+ /* Do the flush only on the final addess == end */
+ mmio_invalidate(npu_context, 1, address, true);
+ }
}
static const struct mmu_notifier_ops nv_nmmu_notifier_ops = {
@@ -696,11 +717,12 @@ static const struct mmu_notifier_ops nv_nmmu_notifier_ops = {
* Returns an error if there no contexts are currently available or a
* npu_context which should be passed to pnv_npu2_handle_fault().
*
- * mmap_sem must be held in write mode.
+ * mmap_sem must be held in write mode and must not be called from interrupt
+ * context.
*/
struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
unsigned long flags,
- struct npu_context *(*cb)(struct npu_context *, void *),
+ void (*cb)(struct npu_context *, void *),
void *priv)
{
int rc;
@@ -743,7 +765,9 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
/*
* Setup the NPU context table for a particular GPU. These need to be
* per-GPU as we need the tables to filter ATSDs when there are no
- * active contexts on a particular GPU.
+ * active contexts on a particular GPU. It is safe for these to be
+ * called concurrently with destroy as the OPAL call takes appropriate
+ * locks and refcounts on init/destroy.
*/
rc = opal_npu_init_context(nphb->opal_id, mm->context.id, flags,
PCI_DEVID(gpdev->bus->number, gpdev->devfn));
@@ -754,8 +778,29 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
* We store the npu pci device so we can more easily get at the
* associated npus.
*/
+ spin_lock(&npu_context_lock);
npu_context = mm->context.npu_context;
+ if (npu_context) {
+ if (npu_context->release_cb != cb ||
+ npu_context->priv != priv) {
+ spin_unlock(&npu_context_lock);
+ opal_npu_destroy_context(nphb->opal_id, mm->context.id,
+ PCI_DEVID(gpdev->bus->number,
+ gpdev->devfn));
+ return ERR_PTR(-EINVAL);
+ }
+
+ WARN_ON(!kref_get_unless_zero(&npu_context->kref));
+ }
+ spin_unlock(&npu_context_lock);
+
if (!npu_context) {
+ /*
+ * We can set up these fields without holding the
+ * npu_context_lock as the npu_context hasn't been returned to
+ * the caller meaning it can't be destroyed. Parallel allocation
+ * is protected against by mmap_sem.
+ */
rc = -ENOMEM;
npu_context = kzalloc(sizeof(struct npu_context), GFP_KERNEL);
if (npu_context) {
@@ -774,8 +819,6 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
}
mm->context.npu_context = npu_context;
- } else {
- WARN_ON(!kref_get_unless_zero(&npu_context->kref));
}
npu_context->release_cb = cb;
@@ -814,15 +857,16 @@ static void pnv_npu2_release_context(struct kref *kref)
mm_context_remove_copro(npu_context->mm);
npu_context->mm->context.npu_context = NULL;
- mmu_notifier_unregister(&npu_context->mn,
- npu_context->mm);
-
- kfree(npu_context);
}
+/*
+ * Destroy a context on the given GPU. May free the npu_context if it is no
+ * longer active on any GPUs. Must not be called from interrupt context.
+ */
void pnv_npu2_destroy_context(struct npu_context *npu_context,
struct pci_dev *gpdev)
{
+ int removed;
struct pnv_phb *nphb;
struct npu *npu;
struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0);
@@ -844,7 +888,21 @@ void pnv_npu2_destroy_context(struct npu_context *npu_context,
WRITE_ONCE(npu_context->npdev[npu->index][nvlink_index], NULL);
opal_npu_destroy_context(nphb->opal_id, npu_context->mm->context.id,
PCI_DEVID(gpdev->bus->number, gpdev->devfn));
- kref_put(&npu_context->kref, pnv_npu2_release_context);
+ spin_lock(&npu_context_lock);
+ removed = kref_put(&npu_context->kref, pnv_npu2_release_context);
+ spin_unlock(&npu_context_lock);
+
+ /*
+ * We need to do this outside of pnv_npu2_release_context so that it is
+ * outside the spinlock as mmu_notifier_destroy uses SRCU.
+ */
+ if (removed) {
+ mmu_notifier_unregister(&npu_context->mn,
+ npu_context->mm);
+
+ kfree(npu_context);
+ }
+
}
EXPORT_SYMBOL(pnv_npu2_destroy_context);
diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c
index 1bceb95..5584247 100644
--- a/arch/powerpc/platforms/powernv/opal-nvram.c
+++ b/arch/powerpc/platforms/powernv/opal-nvram.c
@@ -44,6 +44,10 @@ static ssize_t opal_nvram_read(char *buf, size_t count, loff_t *index)
return count;
}
+/*
+ * This can be called in the panic path with interrupts off, so use
+ * mdelay in that case.
+ */
static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index)
{
s64 rc = OPAL_BUSY;
@@ -58,10 +62,16 @@ static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index)
while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
rc = opal_write_nvram(__pa(buf), count, off);
if (rc == OPAL_BUSY_EVENT) {
- msleep(OPAL_BUSY_DELAY_MS);
+ if (in_interrupt() || irqs_disabled())
+ mdelay(OPAL_BUSY_DELAY_MS);
+ else
+ msleep(OPAL_BUSY_DELAY_MS);
opal_poll_events(NULL);
} else if (rc == OPAL_BUSY) {
- msleep(OPAL_BUSY_DELAY_MS);
+ if (in_interrupt() || irqs_disabled())
+ mdelay(OPAL_BUSY_DELAY_MS);
+ else
+ msleep(OPAL_BUSY_DELAY_MS);
}
}
diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c
index f886886..aa2a513 100644
--- a/arch/powerpc/platforms/powernv/opal-rtc.c
+++ b/arch/powerpc/platforms/powernv/opal-rtc.c
@@ -48,10 +48,12 @@ unsigned long __init opal_get_boot_time(void)
while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
- if (rc == OPAL_BUSY_EVENT)
+ if (rc == OPAL_BUSY_EVENT) {
+ mdelay(OPAL_BUSY_DELAY_MS);
opal_poll_events(NULL);
- else if (rc == OPAL_BUSY)
- mdelay(10);
+ } else if (rc == OPAL_BUSY) {
+ mdelay(OPAL_BUSY_DELAY_MS);
+ }
}
if (rc != OPAL_SUCCESS)
return 0;
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index ef8c9ce..a6648ec 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -131,6 +131,7 @@ static void __init pnv_setup_arch(void)
set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
pnv_setup_rfi_flush();
+ setup_stf_barrier();
/* Initialize SMP */
pnv_smp_init();
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index b55ad42..fdb32e0 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -710,6 +710,7 @@ static void __init pSeries_setup_arch(void)
fwnmi_init();
pseries_setup_rfi_flush();
+ setup_stf_barrier();
/* By default, only probe PCI (can be overridden by rtas_pci) */
pci_add_flags(PCI_PROBE_ONLY);
diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index d22aeb0..b48454b 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -389,6 +389,10 @@ static void xive_native_setup_cpu(unsigned int cpu, struct xive_cpu *xc)
if (xive_pool_vps == XIVE_INVALID_VP)
return;
+ /* Check if pool VP already active, if it is, pull it */
+ if (in_be32(xive_tima + TM_QW2_HV_POOL + TM_WORD2) & TM_QW2W2_VP)
+ in_be64(xive_tima + TM_SPC_PULL_POOL_CTX);
+
/* Enable the pool VP */
vp = xive_pool_vps + cpu;
pr_debug("CPU %d setting up pool VP 0x%x\n", cpu, vp);
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 23d8acc..274bc06 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -3,14 +3,23 @@
# see Documentation/kbuild/kconfig-language.txt.
#
+config 64BIT
+ bool
+
+config 32BIT
+ bool
+
config RISCV
def_bool y
+ # even on 32-bit, physical (and DMA) addresses are > 32-bits
+ select PHYS_ADDR_T_64BIT
select OF
select OF_EARLY_FLATTREE
select OF_IRQ
select ARCH_WANT_FRAME_POINTERS
select CLONE_BACKWARDS
select COMMON_CLK
+ select DMA_DIRECT_OPS
select GENERIC_CLOCKEVENTS
select GENERIC_CPU_DEVICES
select GENERIC_IRQ_SHOW
@@ -21,7 +30,6 @@
select GENERIC_ATOMIC64 if !64BIT || !RISCV_ISA_A
select HAVE_MEMBLOCK
select HAVE_MEMBLOCK_NODE_MAP
- select HAVE_DMA_API_DEBUG
select HAVE_DMA_CONTIGUOUS
select HAVE_GENERIC_DMA_COHERENT
select IRQ_DOMAIN
@@ -38,16 +46,9 @@
config MMU
def_bool y
-# even on 32-bit, physical (and DMA) addresses are > 32-bits
-config ARCH_PHYS_ADDR_T_64BIT
- def_bool y
-
config ZONE_DMA32
bool
- default y
-
-config ARCH_DMA_ADDR_T_64BIT
- def_bool y
+ default y if 64BIT
config PAGE_OFFSET
hex
@@ -89,9 +90,6 @@
config HAVE_KPROBES
def_bool n
-config DMA_DIRECT_OPS
- def_bool y
-
menu "Platform type"
choice
@@ -103,7 +101,6 @@
config ARCH_RV32I
bool "RV32I"
- select CPU_SUPPORTS_32BIT_KERNEL
select 32BIT
select GENERIC_ASHLDI3
select GENERIC_ASHRDI3
@@ -111,13 +108,13 @@
config ARCH_RV64I
bool "RV64I"
- select CPU_SUPPORTS_64BIT_KERNEL
select 64BIT
select HAVE_FUNCTION_TRACER
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_DYNAMIC_FTRACE
select HAVE_DYNAMIC_FTRACE_WITH_REGS
+ select SWIOTLB
endchoice
@@ -173,11 +170,6 @@
depends on SMP
default "8"
-config CPU_SUPPORTS_32BIT_KERNEL
- bool
-config CPU_SUPPORTS_64BIT_KERNEL
- bool
-
choice
prompt "CPU Tuning"
default TUNE_GENERIC
@@ -204,24 +196,6 @@
menu "Kernel type"
-choice
- prompt "Kernel code model"
- default 64BIT
-
-config 32BIT
- bool "32-bit kernel"
- depends on CPU_SUPPORTS_32BIT_KERNEL
- help
- Select this option to build a 32-bit kernel.
-
-config 64BIT
- bool "64-bit kernel"
- depends on CPU_SUPPORTS_64BIT_KERNEL
- help
- Select this option to build a 64-bit kernel.
-
-endchoice
-
source "mm/Kconfig"
source "kernel/Kconfig.preempt"
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
index 1e5fd28..4286a5f 100644
--- a/arch/riscv/include/asm/Kbuild
+++ b/arch/riscv/include/asm/Kbuild
@@ -15,7 +15,6 @@
generic-y += futex.h
generic-y += hardirq.h
generic-y += hash.h
-generic-y += handle_irq.h
generic-y += hw_irq.h
generic-y += ioctl.h
generic-y += ioctls.h
diff --git a/arch/riscv/include/asm/dma-mapping.h b/arch/riscv/include/asm/dma-mapping.h
new file mode 100644
index 0000000..8facc1c
--- /dev/null
+++ b/arch/riscv/include/asm/dma-mapping.h
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _RISCV_ASM_DMA_MAPPING_H
+#define _RISCV_ASM_DMA_MAPPING_H 1
+
+#ifdef CONFIG_SWIOTLB
+#include <linux/swiotlb.h>
+static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
+{
+ return &swiotlb_dma_ops;
+}
+#else
+#include <asm-generic/dma-mapping.h>
+#endif /* CONFIG_SWIOTLB */
+
+#endif /* _RISCV_ASM_DMA_MAPPING_H */
diff --git a/arch/riscv/include/asm/pci.h b/arch/riscv/include/asm/pci.h
index 0f2fc9e..b3638c5 100644
--- a/arch/riscv/include/asm/pci.h
+++ b/arch/riscv/include/asm/pci.h
@@ -26,9 +26,6 @@
/* RISC-V shim does not initialize PCI bus */
#define pcibios_assign_all_busses() 1
-/* We do not have an IOMMU */
-#define PCI_DMA_BUS_IS_PHYS 1
-
extern int isa_dma_bridge_buggy;
#ifdef CONFIG_PCI
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index c11f40c..ee44a48f 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -29,6 +29,7 @@
#include <linux/of_fdt.h>
#include <linux/of_platform.h>
#include <linux/sched/task.h>
+#include <linux/swiotlb.h>
#include <asm/setup.h>
#include <asm/sections.h>
@@ -206,6 +207,7 @@ void __init setup_arch(char **cmdline_p)
setup_bootmem();
paging_init();
unflatten_device_tree();
+ swiotlb_init(1);
#ifdef CONFIG_SMP
setup_smp();
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 93132cb..b99d9dd 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -63,18 +63,6 @@ void die(struct pt_regs *regs, const char *str)
do_exit(SIGSEGV);
}
-static inline void do_trap_siginfo(int signo, int code,
- unsigned long addr, struct task_struct *tsk)
-{
- siginfo_t info;
-
- info.si_signo = signo;
- info.si_errno = 0;
- info.si_code = code;
- info.si_addr = (void __user *)addr;
- force_sig_info(signo, &info, tsk);
-}
-
void do_trap(struct pt_regs *regs, int signo, int code,
unsigned long addr, struct task_struct *tsk)
{
@@ -87,7 +75,7 @@ void do_trap(struct pt_regs *regs, int signo, int code,
show_regs(regs);
}
- do_trap_siginfo(signo, code, addr, tsk);
+ force_sig_fault(signo, code, (void __user *)addr, tsk);
}
static void do_trap_error(struct pt_regs *regs, int signo, int code,
@@ -149,7 +137,7 @@ asmlinkage void do_trap_break(struct pt_regs *regs)
}
#endif /* CONFIG_GENERIC_BUG */
- do_trap_siginfo(SIGTRAP, TRAP_BRKPT, regs->sepc, current);
+ force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)(regs->sepc), current);
regs->sepc += 0x4;
}
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 324568d..f6561b7 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -52,7 +52,7 @@
# Add -lgcc so rv32 gets static muldi3 and lshrdi3 definitions.
# Make sure only to export the intended __vdso_xxx symbol offsets.
quiet_cmd_vdsold = VDSOLD $@
- cmd_vdsold = $(CC) $(KCFLAGS) -nostdlib $(SYSCFLAGS_$(@F)) \
+ cmd_vdsold = $(CC) $(KCFLAGS) $(call cc-option, -no-pie) -nostdlib $(SYSCFLAGS_$(@F)) \
-Wl,-T,$(filter-out FORCE,$^) -o $@.tmp -lgcc && \
$(CROSS_COMPILE)objcopy \
$(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@
diff --git a/arch/s390/Kbuild b/arch/s390/Kbuild
index 9fdff3f..e63940b 100644
--- a/arch/s390/Kbuild
+++ b/arch/s390/Kbuild
@@ -8,3 +8,4 @@
obj-y += net/
obj-$(CONFIG_PCI) += pci/
obj-$(CONFIG_NUMA) += numa/
+obj-$(CONFIG_ARCH_HAS_KEXEC_PURGATORY) += purgatory/
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 32a0d5b..b7deee7 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -35,9 +35,6 @@
config GENERIC_BUG_RELATIVE_POINTERS
def_bool y
-config ARCH_DMA_ADDR_T_64BIT
- def_bool y
-
config GENERIC_LOCKBREAK
def_bool y if SMP && PREEMPT
@@ -47,10 +44,6 @@
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
def_bool y
-config KEXEC
- def_bool y
- select KEXEC_CORE
-
config AUDIT_ARCH
def_bool y
@@ -137,7 +130,6 @@
select HAVE_CMPXCHG_LOCAL
select HAVE_COPY_THREAD_TLS
select HAVE_DEBUG_KMEMLEAK
- select HAVE_DMA_API_DEBUG
select HAVE_DMA_CONTIGUOUS
select DMA_DIRECT_OPS
select HAVE_DYNAMIC_FTRACE
@@ -290,12 +282,12 @@
older machines.
config MARCH_Z14
- bool "IBM z14"
+ bool "IBM z14 ZR1 and z14"
select HAVE_MARCH_Z14_FEATURES
help
- Select this to enable optimizations for IBM z14 (3906 series).
- The kernel will be slightly faster but will not work on older
- machines.
+ Select this to enable optimizations for IBM z14 ZR1 and z14 (3907
+ and 3906 series). The kernel will be slightly faster but will not
+ work on older machines.
endchoice
@@ -525,6 +517,26 @@
source kernel/Kconfig.hz
+config KEXEC
+ def_bool y
+ select KEXEC_CORE
+
+config KEXEC_FILE
+ bool "kexec file based system call"
+ select KEXEC_CORE
+ select BUILD_BIN2C
+ depends on CRYPTO
+ depends on CRYPTO_SHA256
+ depends on CRYPTO_SHA256_S390
+ help
+ Enable the kexec file based system call. In contrast to the normal
+ kexec system call this system call takes file descriptors for the
+ kernel and initramfs as arguments.
+
+config ARCH_HAS_KEXEC_PURGATORY
+ def_bool y
+ depends on KEXEC_FILE
+
config ARCH_RANDOM
def_bool y
prompt "s390 architectural random number generation API"
@@ -693,7 +705,11 @@
menuconfig PCI
bool "PCI support"
select PCI_MSI
+ select IOMMU_HELPER
select IOMMU_SUPPORT
+ select NEED_DMA_MAP_STATE
+ select NEED_SG_DMA_LENGTH
+
help
Enable PCI support.
@@ -717,15 +733,6 @@
config HAS_IOMEM
def_bool PCI
-config IOMMU_HELPER
- def_bool PCI
-
-config NEED_SG_DMA_LENGTH
- def_bool PCI
-
-config NEED_DMA_MAP_STATE
- def_bool PCI
-
config CHSC_SCH
def_tristate m
prompt "Support for CHSC subchannels"
@@ -831,6 +838,10 @@
source "drivers/Kconfig"
+config HAVE_PNETID
+ tristate
+ default (SMC || CCWGROUP)
+
source "fs/Kconfig"
source "arch/s390/Kconfig.debug"
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index da9dad3..d1fa37f 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -3,12 +3,6 @@
# Makefile for the linux s390-specific parts of the memory manager.
#
-COMPILE_VERSION := __linux_compile_version_id__`hostname | \
- tr -c '[0-9A-Za-z]' '_'`__`date | \
- tr -c '[0-9A-Za-z]' '_'`_t
-
-ccflags-y := -DCOMPILE_VERSION=$(COMPILE_VERSION) -gstabs -I.
-
targets := image
targets += bzImage
subdir- := compressed
diff --git a/arch/s390/boot/compressed/.gitignore b/arch/s390/boot/compressed/.gitignore
index ae06b9b..2088cc1 100644
--- a/arch/s390/boot/compressed/.gitignore
+++ b/arch/s390/boot/compressed/.gitignore
@@ -1,3 +1,4 @@
sizes.h
vmlinux
vmlinux.lds
+vmlinux.bin.full
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/debug_defconfig
similarity index 96%
rename from arch/s390/configs/default_defconfig
rename to arch/s390/configs/debug_defconfig
index 5af8458..941d8cc 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -24,13 +24,13 @@
CONFIG_CGROUP_DEVICE=y
CONFIG_CGROUP_CPUACCT=y
CONFIG_CGROUP_PERF=y
-CONFIG_CHECKPOINT_RESTORE=y
CONFIG_NAMESPACES=y
CONFIG_USER_NS=y
CONFIG_SCHED_AUTOGROUP=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_EXPERT=y
# CONFIG_SYSFS_SYSCALL is not set
+CONFIG_CHECKPOINT_RESTORE=y
CONFIG_BPF_SYSCALL=y
CONFIG_USERFAULTFD=y
# CONFIG_COMPAT_BRK is not set
@@ -59,10 +59,11 @@
CONFIG_DEFAULT_DEADLINE=y
CONFIG_LIVEPATCH=y
CONFIG_TUNE_ZEC12=y
-CONFIG_NR_CPUS=256
+CONFIG_NR_CPUS=512
CONFIG_NUMA=y
CONFIG_PREEMPT=y
CONFIG_HZ_100=y
+CONFIG_KEXEC_FILE=y
CONFIG_MEMORY_HOTPLUG=y
CONFIG_MEMORY_HOTREMOVE=y
CONFIG_KSM=y
@@ -260,9 +261,9 @@
CONFIG_IP_VS_FTP=m
CONFIG_IP_VS_PE_SIP=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
+CONFIG_NF_TABLES_IPV4=y
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_IP_NF_IPTABLES=m
CONFIG_IP_NF_MATCH_AH=m
@@ -283,7 +284,7 @@
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
+CONFIG_NF_TABLES_IPV6=y
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
@@ -304,8 +305,7 @@
CONFIG_IP6_NF_SECURITY=m
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
-CONFIG_NF_TABLES_BRIDGE=m
-CONFIG_NET_SCTPPROBE=m
+CONFIG_NF_TABLES_BRIDGE=y
CONFIG_RDS=m
CONFIG_RDS_RDMA=m
CONFIG_RDS_TCP=m
@@ -364,11 +364,11 @@
CONFIG_NET_ACT_SKBEDIT=m
CONFIG_NET_ACT_CSUM=m
CONFIG_DNS_RESOLVER=y
+CONFIG_OPENVSWITCH=m
CONFIG_NETLINK_DIAG=m
CONFIG_CGROUP_NET_PRIO=y
CONFIG_BPF_JIT=y
CONFIG_NET_PKTGEN=m
-CONFIG_NET_TCPPROBE=m
CONFIG_DEVTMPFS=y
CONFIG_DMA_CMA=y
CONFIG_CMA_SIZE_MBYTES=0
@@ -380,9 +380,9 @@
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_SIZE=32768
-CONFIG_BLK_DEV_RAM_DAX=y
CONFIG_VIRTIO_BLK=y
CONFIG_BLK_DEV_RBD=m
+CONFIG_BLK_DEV_NVME=m
CONFIG_ENCLOSURE_SERVICES=m
CONFIG_GENWQE=m
CONFIG_RAID_ATTRS=m
@@ -461,6 +461,7 @@
CONFIG_PPPOL2TP=m
CONFIG_PPP_ASYNC=m
CONFIG_PPP_SYNC_TTY=m
+CONFIG_INPUT_EVDEV=y
# CONFIG_INPUT_KEYBOARD is not set
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
@@ -474,6 +475,9 @@
CONFIG_WATCHDOG_NOWAYOUT=y
CONFIG_SOFT_WATCHDOG=m
CONFIG_DIAG288_WATCHDOG=m
+CONFIG_DRM=y
+CONFIG_DRM_VIRTIO_GPU=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
# CONFIG_HID is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_INFINIBAND=m
@@ -482,7 +486,9 @@
CONFIG_MLX5_INFINIBAND=m
CONFIG_VFIO=m
CONFIG_VFIO_PCI=m
+CONFIG_VIRTIO_PCI=m
CONFIG_VIRTIO_BALLOON=m
+CONFIG_VIRTIO_INPUT=y
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
@@ -598,7 +604,6 @@
CONFIG_WQ_WATCHDOG=y
CONFIG_PANIC_ON_OOPS=y
CONFIG_DEBUG_TIMEKEEPING=y
-CONFIG_DEBUG_WW_MUTEX_SLOWPATH=y
CONFIG_PROVE_LOCKING=y
CONFIG_LOCK_STAT=y
CONFIG_DEBUG_LOCKDEP=y
@@ -641,6 +646,8 @@
CONFIG_TEST_BPF=m
CONFIG_BUG_ON_DATA_CORRUPTION=y
CONFIG_S390_PTDUMP=y
+CONFIG_PERSISTENT_KEYRINGS=y
+CONFIG_BIG_KEYS=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_SECURITY=y
CONFIG_SECURITY_NETWORK=y
@@ -649,17 +656,20 @@
CONFIG_SECURITY_SELINUX_BOOTPARAM=y
CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0
CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_INTEGRITY_SIGNATURE=y
+CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
CONFIG_IMA=y
+CONFIG_IMA_DEFAULT_HASH_SHA256=y
+CONFIG_IMA_WRITE_POLICY=y
CONFIG_IMA_APPRAISE=y
-CONFIG_CRYPTO_RSA=m
CONFIG_CRYPTO_DH=m
CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_USER=m
+# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
CONFIG_CRYPTO_PCRYPT=m
CONFIG_CRYPTO_CRYPTD=m
CONFIG_CRYPTO_MCRYPTD=m
CONFIG_CRYPTO_TEST=m
-CONFIG_CRYPTO_GCM=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
@@ -707,9 +717,8 @@
CONFIG_CRYPTO_AES_S390=m
CONFIG_CRYPTO_GHASH_S390=m
CONFIG_CRYPTO_CRC32_S390=y
-CONFIG_ASYMMETRIC_KEY_TYPE=y
-CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
-CONFIG_X509_CERTIFICATE_PARSER=m
+CONFIG_PKCS7_MESSAGE_PARSER=y
+CONFIG_SYSTEM_TRUSTED_KEYRING=y
CONFIG_CRC7=m
CONFIG_CRC8=m
CONFIG_RANDOM32_SELFTEST=y
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
deleted file mode 100644
index d52eafe..0000000
--- a/arch/s390/configs/gcov_defconfig
+++ /dev/null
@@ -1,661 +0,0 @@
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_AUDIT=y
-CONFIG_NO_HZ_IDLE=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_BSD_PROCESS_ACCT_V3=y
-CONFIG_TASKSTATS=y
-CONFIG_TASK_DELAY_ACCT=y
-CONFIG_TASK_XACCT=y
-CONFIG_TASK_IO_ACCOUNTING=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_NUMA_BALANCING=y
-# CONFIG_NUMA_BALANCING_DEFAULT_ENABLED is not set
-CONFIG_MEMCG=y
-CONFIG_MEMCG_SWAP=y
-CONFIG_BLK_CGROUP=y
-CONFIG_CFS_BANDWIDTH=y
-CONFIG_RT_GROUP_SCHED=y
-CONFIG_CGROUP_PIDS=y
-CONFIG_CGROUP_FREEZER=y
-CONFIG_CGROUP_HUGETLB=y
-CONFIG_CPUSETS=y
-CONFIG_CGROUP_DEVICE=y
-CONFIG_CGROUP_CPUACCT=y
-CONFIG_CGROUP_PERF=y
-CONFIG_CHECKPOINT_RESTORE=y
-CONFIG_NAMESPACES=y
-CONFIG_USER_NS=y
-CONFIG_SCHED_AUTOGROUP=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-# CONFIG_SYSFS_SYSCALL is not set
-CONFIG_BPF_SYSCALL=y
-CONFIG_USERFAULTFD=y
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_KPROBES=y
-CONFIG_JUMP_LABEL=y
-CONFIG_GCOV_KERNEL=y
-CONFIG_GCOV_PROFILE_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_FORCE_LOAD=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-CONFIG_MODULE_SRCVERSION_ALL=y
-CONFIG_BLK_DEV_INTEGRITY=y
-CONFIG_BLK_DEV_THROTTLING=y
-CONFIG_BLK_WBT=y
-CONFIG_BLK_WBT_SQ=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_IBM_PARTITION=y
-CONFIG_BSD_DISKLABEL=y
-CONFIG_MINIX_SUBPARTITION=y
-CONFIG_SOLARIS_X86_PARTITION=y
-CONFIG_UNIXWARE_DISKLABEL=y
-CONFIG_CFQ_GROUP_IOSCHED=y
-CONFIG_DEFAULT_DEADLINE=y
-CONFIG_LIVEPATCH=y
-CONFIG_TUNE_ZEC12=y
-CONFIG_NR_CPUS=512
-CONFIG_NUMA=y
-CONFIG_HZ_100=y
-CONFIG_MEMORY_HOTPLUG=y
-CONFIG_MEMORY_HOTREMOVE=y
-CONFIG_KSM=y
-CONFIG_TRANSPARENT_HUGEPAGE=y
-CONFIG_CLEANCACHE=y
-CONFIG_FRONTSWAP=y
-CONFIG_MEM_SOFT_DIRTY=y
-CONFIG_ZSWAP=y
-CONFIG_ZBUD=m
-CONFIG_ZSMALLOC=m
-CONFIG_ZSMALLOC_STAT=y
-CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
-CONFIG_IDLE_PAGE_TRACKING=y
-CONFIG_PCI=y
-CONFIG_HOTPLUG_PCI=y
-CONFIG_HOTPLUG_PCI_S390=y
-CONFIG_CHSC_SCH=y
-CONFIG_CRASH_DUMP=y
-CONFIG_BINFMT_MISC=m
-CONFIG_HIBERNATION=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_PACKET_DIAG=m
-CONFIG_UNIX=y
-CONFIG_UNIX_DIAG=m
-CONFIG_XFRM_USER=m
-CONFIG_NET_KEY=m
-CONFIG_SMC=m
-CONFIG_SMC_DIAG=m
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_MULTIPLE_TABLES=y
-CONFIG_IP_ROUTE_MULTIPATH=y
-CONFIG_IP_ROUTE_VERBOSE=y
-CONFIG_NET_IPIP=m
-CONFIG_NET_IPGRE_DEMUX=m
-CONFIG_NET_IPGRE=m
-CONFIG_NET_IPGRE_BROADCAST=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_MROUTE_MULTIPLE_TABLES=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_IP_PIMSM_V2=y
-CONFIG_SYN_COOKIES=y
-CONFIG_NET_IPVTI=m
-CONFIG_INET_AH=m
-CONFIG_INET_ESP=m
-CONFIG_INET_IPCOMP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
-CONFIG_INET_DIAG=m
-CONFIG_INET_UDP_DIAG=m
-CONFIG_TCP_CONG_ADVANCED=y
-CONFIG_TCP_CONG_HSTCP=m
-CONFIG_TCP_CONG_HYBLA=m
-CONFIG_TCP_CONG_SCALABLE=m
-CONFIG_TCP_CONG_LP=m
-CONFIG_TCP_CONG_VENO=m
-CONFIG_TCP_CONG_YEAH=m
-CONFIG_TCP_CONG_ILLINOIS=m
-CONFIG_IPV6_ROUTER_PREF=y
-CONFIG_INET6_AH=m
-CONFIG_INET6_ESP=m
-CONFIG_INET6_IPCOMP=m
-CONFIG_IPV6_MIP6=m
-CONFIG_INET6_XFRM_MODE_TRANSPORT=m
-CONFIG_INET6_XFRM_MODE_TUNNEL=m
-CONFIG_INET6_XFRM_MODE_BEET=m
-CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
-CONFIG_IPV6_VTI=m
-CONFIG_IPV6_SIT=m
-CONFIG_IPV6_GRE=m
-CONFIG_IPV6_MULTIPLE_TABLES=y
-CONFIG_IPV6_SUBTREES=y
-CONFIG_NETFILTER=y
-CONFIG_NF_CONNTRACK=m
-CONFIG_NF_CONNTRACK_SECMARK=y
-CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CONNTRACK_TIMEOUT=y
-CONFIG_NF_CONNTRACK_TIMESTAMP=y
-CONFIG_NF_CONNTRACK_AMANDA=m
-CONFIG_NF_CONNTRACK_FTP=m
-CONFIG_NF_CONNTRACK_H323=m
-CONFIG_NF_CONNTRACK_IRC=m
-CONFIG_NF_CONNTRACK_NETBIOS_NS=m
-CONFIG_NF_CONNTRACK_SNMP=m
-CONFIG_NF_CONNTRACK_PPTP=m
-CONFIG_NF_CONNTRACK_SANE=m
-CONFIG_NF_CONNTRACK_SIP=m
-CONFIG_NF_CONNTRACK_TFTP=m
-CONFIG_NF_CT_NETLINK=m
-CONFIG_NF_CT_NETLINK_TIMEOUT=m
-CONFIG_NF_TABLES=m
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_CT=m
-CONFIG_NFT_COUNTER=m
-CONFIG_NFT_LOG=m
-CONFIG_NFT_LIMIT=m
-CONFIG_NFT_NAT=m
-CONFIG_NFT_COMPAT=m
-CONFIG_NFT_HASH=m
-CONFIG_NETFILTER_XT_SET=m
-CONFIG_NETFILTER_XT_TARGET_AUDIT=m
-CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
-CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
-CONFIG_NETFILTER_XT_TARGET_CONNMARK=m
-CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m
-CONFIG_NETFILTER_XT_TARGET_CT=m
-CONFIG_NETFILTER_XT_TARGET_DSCP=m
-CONFIG_NETFILTER_XT_TARGET_HMARK=m
-CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m
-CONFIG_NETFILTER_XT_TARGET_LOG=m
-CONFIG_NETFILTER_XT_TARGET_MARK=m
-CONFIG_NETFILTER_XT_TARGET_NFLOG=m
-CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_TEE=m
-CONFIG_NETFILTER_XT_TARGET_TPROXY=m
-CONFIG_NETFILTER_XT_TARGET_TRACE=m
-CONFIG_NETFILTER_XT_TARGET_SECMARK=m
-CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
-CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
-CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m
-CONFIG_NETFILTER_XT_MATCH_BPF=m
-CONFIG_NETFILTER_XT_MATCH_CLUSTER=m
-CONFIG_NETFILTER_XT_MATCH_COMMENT=m
-CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
-CONFIG_NETFILTER_XT_MATCH_CONNLABEL=m
-CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
-CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
-CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
-CONFIG_NETFILTER_XT_MATCH_CPU=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
-CONFIG_NETFILTER_XT_MATCH_DEVGROUP=m
-CONFIG_NETFILTER_XT_MATCH_DSCP=m
-CONFIG_NETFILTER_XT_MATCH_ESP=m
-CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
-CONFIG_NETFILTER_XT_MATCH_HELPER=m
-CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
-CONFIG_NETFILTER_XT_MATCH_IPVS=m
-CONFIG_NETFILTER_XT_MATCH_LENGTH=m
-CONFIG_NETFILTER_XT_MATCH_LIMIT=m
-CONFIG_NETFILTER_XT_MATCH_MAC=m
-CONFIG_NETFILTER_XT_MATCH_MARK=m
-CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m
-CONFIG_NETFILTER_XT_MATCH_NFACCT=m
-CONFIG_NETFILTER_XT_MATCH_OSF=m
-CONFIG_NETFILTER_XT_MATCH_OWNER=m
-CONFIG_NETFILTER_XT_MATCH_POLICY=m
-CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m
-CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m
-CONFIG_NETFILTER_XT_MATCH_QUOTA=m
-CONFIG_NETFILTER_XT_MATCH_RATEEST=m
-CONFIG_NETFILTER_XT_MATCH_REALM=m
-CONFIG_NETFILTER_XT_MATCH_RECENT=m
-CONFIG_NETFILTER_XT_MATCH_STATE=m
-CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
-CONFIG_NETFILTER_XT_MATCH_STRING=m
-CONFIG_NETFILTER_XT_MATCH_TCPMSS=m
-CONFIG_NETFILTER_XT_MATCH_TIME=m
-CONFIG_NETFILTER_XT_MATCH_U32=m
-CONFIG_IP_SET=m
-CONFIG_IP_SET_BITMAP_IP=m
-CONFIG_IP_SET_BITMAP_IPMAC=m
-CONFIG_IP_SET_BITMAP_PORT=m
-CONFIG_IP_SET_HASH_IP=m
-CONFIG_IP_SET_HASH_IPPORT=m
-CONFIG_IP_SET_HASH_IPPORTIP=m
-CONFIG_IP_SET_HASH_IPPORTNET=m
-CONFIG_IP_SET_HASH_NETPORTNET=m
-CONFIG_IP_SET_HASH_NET=m
-CONFIG_IP_SET_HASH_NETNET=m
-CONFIG_IP_SET_HASH_NETPORT=m
-CONFIG_IP_SET_HASH_NETIFACE=m
-CONFIG_IP_SET_LIST_SET=m
-CONFIG_IP_VS=m
-CONFIG_IP_VS_PROTO_TCP=y
-CONFIG_IP_VS_PROTO_UDP=y
-CONFIG_IP_VS_PROTO_ESP=y
-CONFIG_IP_VS_PROTO_AH=y
-CONFIG_IP_VS_RR=m
-CONFIG_IP_VS_WRR=m
-CONFIG_IP_VS_LC=m
-CONFIG_IP_VS_WLC=m
-CONFIG_IP_VS_LBLC=m
-CONFIG_IP_VS_LBLCR=m
-CONFIG_IP_VS_DH=m
-CONFIG_IP_VS_SH=m
-CONFIG_IP_VS_SED=m
-CONFIG_IP_VS_NQ=m
-CONFIG_IP_VS_FTP=m
-CONFIG_IP_VS_PE_SIP=m
-CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_CHAIN_ROUTE_IPV4=m
-CONFIG_NF_TABLES_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_IP_NF_IPTABLES=m
-CONFIG_IP_NF_MATCH_AH=m
-CONFIG_IP_NF_MATCH_ECN=m
-CONFIG_IP_NF_MATCH_RPFILTER=m
-CONFIG_IP_NF_MATCH_TTL=m
-CONFIG_IP_NF_FILTER=m
-CONFIG_IP_NF_TARGET_REJECT=m
-CONFIG_IP_NF_NAT=m
-CONFIG_IP_NF_TARGET_MASQUERADE=m
-CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
-CONFIG_IP_NF_TARGET_ECN=m
-CONFIG_IP_NF_TARGET_TTL=m
-CONFIG_IP_NF_RAW=m
-CONFIG_IP_NF_SECURITY=m
-CONFIG_IP_NF_ARPTABLES=m
-CONFIG_IP_NF_ARPFILTER=m
-CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
-CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_IP6_NF_IPTABLES=m
-CONFIG_IP6_NF_MATCH_AH=m
-CONFIG_IP6_NF_MATCH_EUI64=m
-CONFIG_IP6_NF_MATCH_FRAG=m
-CONFIG_IP6_NF_MATCH_OPTS=m
-CONFIG_IP6_NF_MATCH_HL=m
-CONFIG_IP6_NF_MATCH_IPV6HEADER=m
-CONFIG_IP6_NF_MATCH_MH=m
-CONFIG_IP6_NF_MATCH_RPFILTER=m
-CONFIG_IP6_NF_MATCH_RT=m
-CONFIG_IP6_NF_TARGET_HL=m
-CONFIG_IP6_NF_FILTER=m
-CONFIG_IP6_NF_TARGET_REJECT=m
-CONFIG_IP6_NF_MANGLE=m
-CONFIG_IP6_NF_RAW=m
-CONFIG_IP6_NF_SECURITY=m
-CONFIG_IP6_NF_NAT=m
-CONFIG_IP6_NF_TARGET_MASQUERADE=m
-CONFIG_NF_TABLES_BRIDGE=m
-CONFIG_NET_SCTPPROBE=m
-CONFIG_RDS=m
-CONFIG_RDS_RDMA=m
-CONFIG_RDS_TCP=m
-CONFIG_L2TP=m
-CONFIG_L2TP_DEBUGFS=m
-CONFIG_L2TP_V3=y
-CONFIG_L2TP_IP=m
-CONFIG_L2TP_ETH=m
-CONFIG_BRIDGE=m
-CONFIG_VLAN_8021Q=m
-CONFIG_VLAN_8021Q_GVRP=y
-CONFIG_NET_SCHED=y
-CONFIG_NET_SCH_CBQ=m
-CONFIG_NET_SCH_HTB=m
-CONFIG_NET_SCH_HFSC=m
-CONFIG_NET_SCH_PRIO=m
-CONFIG_NET_SCH_MULTIQ=m
-CONFIG_NET_SCH_RED=m
-CONFIG_NET_SCH_SFB=m
-CONFIG_NET_SCH_SFQ=m
-CONFIG_NET_SCH_TEQL=m
-CONFIG_NET_SCH_TBF=m
-CONFIG_NET_SCH_GRED=m
-CONFIG_NET_SCH_DSMARK=m
-CONFIG_NET_SCH_NETEM=m
-CONFIG_NET_SCH_DRR=m
-CONFIG_NET_SCH_MQPRIO=m
-CONFIG_NET_SCH_CHOKE=m
-CONFIG_NET_SCH_QFQ=m
-CONFIG_NET_SCH_CODEL=m
-CONFIG_NET_SCH_FQ_CODEL=m
-CONFIG_NET_SCH_INGRESS=m
-CONFIG_NET_SCH_PLUG=m
-CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
-CONFIG_NET_CLS_ROUTE4=m
-CONFIG_NET_CLS_FW=m
-CONFIG_NET_CLS_U32=m
-CONFIG_CLS_U32_PERF=y
-CONFIG_CLS_U32_MARK=y
-CONFIG_NET_CLS_RSVP=m
-CONFIG_NET_CLS_RSVP6=m
-CONFIG_NET_CLS_FLOW=m
-CONFIG_NET_CLS_CGROUP=y
-CONFIG_NET_CLS_BPF=m
-CONFIG_NET_CLS_ACT=y
-CONFIG_NET_ACT_POLICE=m
-CONFIG_NET_ACT_GACT=m
-CONFIG_GACT_PROB=y
-CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
-CONFIG_NET_ACT_NAT=m
-CONFIG_NET_ACT_PEDIT=m
-CONFIG_NET_ACT_SIMP=m
-CONFIG_NET_ACT_SKBEDIT=m
-CONFIG_NET_ACT_CSUM=m
-CONFIG_DNS_RESOLVER=y
-CONFIG_NETLINK_DIAG=m
-CONFIG_CGROUP_NET_PRIO=y
-CONFIG_BPF_JIT=y
-CONFIG_NET_PKTGEN=m
-CONFIG_NET_TCPPROBE=m
-CONFIG_DEVTMPFS=y
-CONFIG_DMA_CMA=y
-CONFIG_CMA_SIZE_MBYTES=0
-CONFIG_CONNECTOR=y
-CONFIG_ZRAM=m
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
-CONFIG_BLK_DEV_DRBD=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=32768
-CONFIG_BLK_DEV_RAM_DAX=y
-CONFIG_VIRTIO_BLK=y
-CONFIG_ENCLOSURE_SERVICES=m
-CONFIG_GENWQE=m
-CONFIG_RAID_ATTRS=m
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_ST=m
-CONFIG_CHR_DEV_OSST=m
-CONFIG_BLK_DEV_SR=m
-CONFIG_CHR_DEV_SG=y
-CONFIG_CHR_DEV_SCH=m
-CONFIG_SCSI_ENCLOSURE=m
-CONFIG_SCSI_CONSTANTS=y
-CONFIG_SCSI_LOGGING=y
-CONFIG_SCSI_SPI_ATTRS=m
-CONFIG_SCSI_FC_ATTRS=y
-CONFIG_SCSI_SAS_LIBSAS=m
-CONFIG_SCSI_SRP_ATTRS=m
-CONFIG_ISCSI_TCP=m
-CONFIG_SCSI_DEBUG=m
-CONFIG_ZFCP=y
-CONFIG_SCSI_VIRTIO=m
-CONFIG_SCSI_DH=y
-CONFIG_SCSI_DH_RDAC=m
-CONFIG_SCSI_DH_HP_SW=m
-CONFIG_SCSI_DH_EMC=m
-CONFIG_SCSI_DH_ALUA=m
-CONFIG_SCSI_OSD_INITIATOR=m
-CONFIG_SCSI_OSD_ULD=m
-CONFIG_MD=y
-CONFIG_BLK_DEV_MD=y
-CONFIG_MD_LINEAR=m
-CONFIG_MD_MULTIPATH=m
-CONFIG_MD_FAULTY=m
-CONFIG_BLK_DEV_DM=m
-CONFIG_DM_CRYPT=m
-CONFIG_DM_SNAPSHOT=m
-CONFIG_DM_THIN_PROVISIONING=m
-CONFIG_DM_MIRROR=m
-CONFIG_DM_LOG_USERSPACE=m
-CONFIG_DM_RAID=m
-CONFIG_DM_ZERO=m
-CONFIG_DM_MULTIPATH=m
-CONFIG_DM_MULTIPATH_QL=m
-CONFIG_DM_MULTIPATH_ST=m
-CONFIG_DM_DELAY=m
-CONFIG_DM_UEVENT=y
-CONFIG_DM_FLAKEY=m
-CONFIG_DM_VERITY=m
-CONFIG_DM_SWITCH=m
-CONFIG_NETDEVICES=y
-CONFIG_BONDING=m
-CONFIG_DUMMY=m
-CONFIG_EQUALIZER=m
-CONFIG_IFB=m
-CONFIG_MACVLAN=m
-CONFIG_MACVTAP=m
-CONFIG_VXLAN=m
-CONFIG_TUN=m
-CONFIG_VETH=m
-CONFIG_VIRTIO_NET=m
-CONFIG_NLMON=m
-# CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_VENDOR_CHELSIO is not set
-# CONFIG_NET_VENDOR_INTEL is not set
-# CONFIG_NET_VENDOR_MARVELL is not set
-CONFIG_MLX4_EN=m
-CONFIG_MLX5_CORE=m
-CONFIG_MLX5_CORE_EN=y
-# CONFIG_NET_VENDOR_NATSEMI is not set
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_MPPE=m
-CONFIG_PPPOE=m
-CONFIG_PPTP=m
-CONFIG_PPPOL2TP=m
-CONFIG_PPP_ASYNC=m
-CONFIG_PPP_SYNC_TTY=m
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_SERIO is not set
-CONFIG_LEGACY_PTY_COUNT=0
-CONFIG_HW_RANDOM_VIRTIO=m
-CONFIG_RAW_DRIVER=m
-CONFIG_HANGCHECK_TIMER=m
-CONFIG_TN3270_FS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_WATCHDOG_NOWAYOUT=y
-CONFIG_SOFT_WATCHDOG=m
-CONFIG_DIAG288_WATCHDOG=m
-# CONFIG_HID is not set
-# CONFIG_USB_SUPPORT is not set
-CONFIG_INFINIBAND=m
-CONFIG_INFINIBAND_USER_ACCESS=m
-CONFIG_MLX4_INFINIBAND=m
-CONFIG_MLX5_INFINIBAND=m
-CONFIG_VFIO=m
-CONFIG_VFIO_PCI=m
-CONFIG_VIRTIO_BALLOON=m
-CONFIG_EXT4_FS=y
-CONFIG_EXT4_FS_POSIX_ACL=y
-CONFIG_EXT4_FS_SECURITY=y
-CONFIG_EXT4_ENCRYPTION=y
-CONFIG_JBD2_DEBUG=y
-CONFIG_JFS_FS=m
-CONFIG_JFS_POSIX_ACL=y
-CONFIG_JFS_SECURITY=y
-CONFIG_JFS_STATISTICS=y
-CONFIG_XFS_FS=y
-CONFIG_XFS_QUOTA=y
-CONFIG_XFS_POSIX_ACL=y
-CONFIG_XFS_RT=y
-CONFIG_GFS2_FS=m
-CONFIG_GFS2_FS_LOCKING_DLM=y
-CONFIG_OCFS2_FS=m
-CONFIG_BTRFS_FS=y
-CONFIG_BTRFS_FS_POSIX_ACL=y
-CONFIG_NILFS2_FS=m
-CONFIG_FS_DAX=y
-CONFIG_EXPORTFS_BLOCK_OPS=y
-CONFIG_FANOTIFY=y
-CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
-CONFIG_QUOTA_NETLINK_INTERFACE=y
-CONFIG_QFMT_V1=m
-CONFIG_QFMT_V2=m
-CONFIG_AUTOFS4_FS=m
-CONFIG_FUSE_FS=y
-CONFIG_CUSE=m
-CONFIG_OVERLAY_FS=m
-CONFIG_OVERLAY_FS_REDIRECT_DIR=y
-CONFIG_FSCACHE=m
-CONFIG_CACHEFILES=m
-CONFIG_ISO9660_FS=y
-CONFIG_JOLIET=y
-CONFIG_ZISOFS=y
-CONFIG_UDF_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_NTFS_FS=m
-CONFIG_NTFS_RW=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_TMPFS_POSIX_ACL=y
-CONFIG_HUGETLBFS=y
-CONFIG_CONFIGFS_FS=m
-CONFIG_ECRYPT_FS=m
-CONFIG_CRAMFS=m
-CONFIG_SQUASHFS=m
-CONFIG_SQUASHFS_XATTR=y
-CONFIG_SQUASHFS_LZO=y
-CONFIG_SQUASHFS_XZ=y
-CONFIG_ROMFS_FS=m
-CONFIG_NFS_FS=m
-CONFIG_NFS_V3_ACL=y
-CONFIG_NFS_V4=m
-CONFIG_NFS_SWAP=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V3_ACL=y
-CONFIG_NFSD_V4=y
-CONFIG_NFSD_V4_SECURITY_LABEL=y
-CONFIG_CIFS=m
-CONFIG_CIFS_STATS=y
-CONFIG_CIFS_STATS2=y
-CONFIG_CIFS_WEAK_PW_HASH=y
-CONFIG_CIFS_UPCALL=y
-CONFIG_CIFS_XATTR=y
-CONFIG_CIFS_POSIX=y
-# CONFIG_CIFS_DEBUG is not set
-CONFIG_CIFS_DFS_UPCALL=y
-CONFIG_NLS_DEFAULT="utf8"
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ASCII=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_ISO8859_15=m
-CONFIG_NLS_UTF8=m
-CONFIG_DLM=m
-CONFIG_PRINTK_TIME=y
-CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_INFO_DWARF4=y
-CONFIG_GDB_SCRIPTS=y
-# CONFIG_ENABLE_MUST_CHECK is not set
-CONFIG_FRAME_WARN=1024
-CONFIG_UNUSED_SYMBOLS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_MEMORY_INIT=y
-CONFIG_PANIC_ON_OOPS=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_RCU_CPU_STALL_TIMEOUT=60
-CONFIG_LATENCYTOP=y
-CONFIG_SCHED_TRACER=y
-CONFIG_FTRACE_SYSCALLS=y
-CONFIG_STACK_TRACER=y
-CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_FUNCTION_PROFILER=y
-CONFIG_HIST_TRIGGERS=y
-CONFIG_LKDTM=m
-CONFIG_PERCPU_TEST=m
-CONFIG_ATOMIC64_SELFTEST=y
-CONFIG_TEST_BPF=m
-CONFIG_BUG_ON_DATA_CORRUPTION=y
-CONFIG_S390_PTDUMP=y
-CONFIG_PERSISTENT_KEYRINGS=y
-CONFIG_BIG_KEYS=y
-CONFIG_ENCRYPTED_KEYS=m
-CONFIG_SECURITY=y
-CONFIG_SECURITY_NETWORK=y
-CONFIG_SECURITY_SELINUX=y
-CONFIG_SECURITY_SELINUX_BOOTPARAM=y
-CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0
-CONFIG_SECURITY_SELINUX_DISABLE=y
-CONFIG_INTEGRITY_SIGNATURE=y
-CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
-CONFIG_IMA=y
-CONFIG_IMA_WRITE_POLICY=y
-CONFIG_IMA_APPRAISE=y
-CONFIG_CRYPTO_DH=m
-CONFIG_CRYPTO_ECDH=m
-CONFIG_CRYPTO_USER=m
-# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
-CONFIG_CRYPTO_PCRYPT=m
-CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_MCRYPTD=m
-CONFIG_CRYPTO_TEST=m
-CONFIG_CRYPTO_CHACHA20POLY1305=m
-CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_KEYWRAP=m
-CONFIG_CRYPTO_XCBC=m
-CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_CRC32=m
-CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
-CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
-CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
-CONFIG_CRYPTO_WP512=m
-CONFIG_CRYPTO_AES_TI=m
-CONFIG_CRYPTO_ANUBIS=m
-CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAMELLIA=m
-CONFIG_CRYPTO_CAST5=m
-CONFIG_CRYPTO_CAST6=m
-CONFIG_CRYPTO_FCRYPT=m
-CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
-CONFIG_CRYPTO_SEED=m
-CONFIG_CRYPTO_SERPENT=m
-CONFIG_CRYPTO_TEA=m
-CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_842=m
-CONFIG_CRYPTO_LZ4=m
-CONFIG_CRYPTO_LZ4HC=m
-CONFIG_CRYPTO_ANSI_CPRNG=m
-CONFIG_CRYPTO_USER_API_HASH=m
-CONFIG_CRYPTO_USER_API_SKCIPHER=m
-CONFIG_CRYPTO_USER_API_RNG=m
-CONFIG_CRYPTO_USER_API_AEAD=m
-CONFIG_ZCRYPT=m
-CONFIG_PKEY=m
-CONFIG_CRYPTO_PAES_S390=m
-CONFIG_CRYPTO_SHA1_S390=m
-CONFIG_CRYPTO_SHA256_S390=m
-CONFIG_CRYPTO_SHA512_S390=m
-CONFIG_CRYPTO_DES_S390=m
-CONFIG_CRYPTO_AES_S390=m
-CONFIG_CRYPTO_GHASH_S390=m
-CONFIG_CRYPTO_CRC32_S390=y
-CONFIG_CRC7=m
-CONFIG_CRC8=m
-CONFIG_CORDIC=m
-CONFIG_CMM=m
-CONFIG_APPLDATA_BASE=y
-CONFIG_KVM=m
-CONFIG_KVM_S390_UCONTROL=y
-CONFIG_VHOST_NET=m
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 20ed149..eb6f75f2 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -25,13 +25,13 @@
CONFIG_CGROUP_DEVICE=y
CONFIG_CGROUP_CPUACCT=y
CONFIG_CGROUP_PERF=y
-CONFIG_CHECKPOINT_RESTORE=y
CONFIG_NAMESPACES=y
CONFIG_USER_NS=y
CONFIG_SCHED_AUTOGROUP=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_EXPERT=y
# CONFIG_SYSFS_SYSCALL is not set
+CONFIG_CHECKPOINT_RESTORE=y
CONFIG_BPF_SYSCALL=y
CONFIG_USERFAULTFD=y
# CONFIG_COMPAT_BRK is not set
@@ -45,6 +45,8 @@
CONFIG_MODULE_FORCE_UNLOAD=y
CONFIG_MODVERSIONS=y
CONFIG_MODULE_SRCVERSION_ALL=y
+CONFIG_MODULE_SIG=y
+CONFIG_MODULE_SIG_SHA256=y
CONFIG_BLK_DEV_INTEGRITY=y
CONFIG_BLK_DEV_THROTTLING=y
CONFIG_BLK_WBT=y
@@ -62,6 +64,7 @@
CONFIG_NR_CPUS=512
CONFIG_NUMA=y
CONFIG_HZ_100=y
+CONFIG_KEXEC_FILE=y
CONFIG_MEMORY_HOTPLUG=y
CONFIG_MEMORY_HOTREMOVE=y
CONFIG_KSM=y
@@ -256,9 +259,9 @@
CONFIG_IP_VS_FTP=m
CONFIG_IP_VS_PE_SIP=m
CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
+CONFIG_NF_TABLES_IPV4=y
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
-CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_TABLES_ARP=y
CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_IP_NF_IPTABLES=m
CONFIG_IP_NF_MATCH_AH=m
@@ -279,7 +282,7 @@
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
+CONFIG_NF_TABLES_IPV6=y
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
@@ -300,8 +303,7 @@
CONFIG_IP6_NF_SECURITY=m
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
-CONFIG_NF_TABLES_BRIDGE=m
-CONFIG_NET_SCTPPROBE=m
+CONFIG_NF_TABLES_BRIDGE=y
CONFIG_RDS=m
CONFIG_RDS_RDMA=m
CONFIG_RDS_TCP=m
@@ -359,11 +361,11 @@
CONFIG_NET_ACT_SKBEDIT=m
CONFIG_NET_ACT_CSUM=m
CONFIG_DNS_RESOLVER=y
+CONFIG_OPENVSWITCH=m
CONFIG_NETLINK_DIAG=m
CONFIG_CGROUP_NET_PRIO=y
CONFIG_BPF_JIT=y
CONFIG_NET_PKTGEN=m
-CONFIG_NET_TCPPROBE=m
CONFIG_DEVTMPFS=y
CONFIG_DMA_CMA=y
CONFIG_CMA_SIZE_MBYTES=0
@@ -375,8 +377,9 @@
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_SIZE=32768
-CONFIG_BLK_DEV_RAM_DAX=y
CONFIG_VIRTIO_BLK=y
+CONFIG_BLK_DEV_RBD=m
+CONFIG_BLK_DEV_NVME=m
CONFIG_ENCLOSURE_SERVICES=m
CONFIG_GENWQE=m
CONFIG_RAID_ATTRS=m
@@ -455,6 +458,7 @@
CONFIG_PPPOL2TP=m
CONFIG_PPP_ASYNC=m
CONFIG_PPP_SYNC_TTY=m
+CONFIG_INPUT_EVDEV=y
# CONFIG_INPUT_KEYBOARD is not set
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
@@ -468,6 +472,9 @@
CONFIG_WATCHDOG_NOWAYOUT=y
CONFIG_SOFT_WATCHDOG=m
CONFIG_DIAG288_WATCHDOG=m
+CONFIG_DRM=y
+CONFIG_DRM_VIRTIO_GPU=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
# CONFIG_HID is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_INFINIBAND=m
@@ -476,7 +483,9 @@
CONFIG_MLX5_INFINIBAND=m
CONFIG_VFIO=m
CONFIG_VFIO_PCI=m
+CONFIG_VIRTIO_PCI=m
CONFIG_VIRTIO_BALLOON=m
+CONFIG_VIRTIO_INPUT=y
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
@@ -507,7 +516,6 @@
CONFIG_FUSE_FS=y
CONFIG_CUSE=m
CONFIG_OVERLAY_FS=m
-CONFIG_OVERLAY_FS_REDIRECT_DIR=y
CONFIG_FSCACHE=m
CONFIG_CACHEFILES=m
CONFIG_ISO9660_FS=y
@@ -592,8 +600,10 @@
CONFIG_INTEGRITY_SIGNATURE=y
CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
CONFIG_IMA=y
+CONFIG_IMA_DEFAULT_HASH_SHA256=y
CONFIG_IMA_WRITE_POLICY=y
CONFIG_IMA_APPRAISE=y
+CONFIG_CRYPTO_FIPS=y
CONFIG_CRYPTO_DH=m
CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_USER=m
diff --git a/arch/s390/crypto/arch_random.c b/arch/s390/crypto/arch_random.c
index 8720e92..dd95cdbd 100644
--- a/arch/s390/crypto/arch_random.c
+++ b/arch/s390/crypto/arch_random.c
@@ -2,14 +2,37 @@
/*
* s390 arch random implementation.
*
- * Copyright IBM Corp. 2017
- * Author(s): Harald Freudenberger <freude@de.ibm.com>
+ * Copyright IBM Corp. 2017, 2018
+ * Author(s): Harald Freudenberger
+ *
+ * The s390_arch_random_generate() function may be called from random.c
+ * in interrupt context. So this implementation does the best to be very
+ * fast. There is a buffer of random data which is asynchronously checked
+ * and filled by a workqueue thread.
+ * If there are enough bytes in the buffer the s390_arch_random_generate()
+ * just delivers these bytes. Otherwise false is returned until the
+ * worker thread refills the buffer.
+ * The worker fills the rng buffer by pulling fresh entropy from the
+ * high quality (but slow) true hardware random generator. This entropy
+ * is then spread over the buffer with an pseudo random generator PRNG.
+ * As the arch_get_random_seed_long() fetches 8 bytes and the calling
+ * function add_interrupt_randomness() counts this as 1 bit entropy the
+ * distribution needs to make sure there is in fact 1 bit entropy contained
+ * in 8 bytes of the buffer. The current values pull 32 byte entropy
+ * and scatter this into a 2048 byte buffer. So 8 byte in the buffer
+ * will contain 1 bit of entropy.
+ * The worker thread is rescheduled based on the charge level of the
+ * buffer but at least with 500 ms delay to avoid too much CPU consumption.
+ * So the max. amount of rng data delivered via arch_get_random_seed is
+ * limited to 4k bytes per second.
*/
#include <linux/kernel.h>
#include <linux/atomic.h>
#include <linux/random.h>
+#include <linux/slab.h>
#include <linux/static_key.h>
+#include <linux/workqueue.h>
#include <asm/cpacf.h>
DEFINE_STATIC_KEY_FALSE(s390_arch_random_available);
@@ -17,11 +40,83 @@ DEFINE_STATIC_KEY_FALSE(s390_arch_random_available);
atomic64_t s390_arch_random_counter = ATOMIC64_INIT(0);
EXPORT_SYMBOL(s390_arch_random_counter);
+#define ARCH_REFILL_TICKS (HZ/2)
+#define ARCH_PRNG_SEED_SIZE 32
+#define ARCH_RNG_BUF_SIZE 2048
+
+static DEFINE_SPINLOCK(arch_rng_lock);
+static u8 *arch_rng_buf;
+static unsigned int arch_rng_buf_idx;
+
+static void arch_rng_refill_buffer(struct work_struct *);
+static DECLARE_DELAYED_WORK(arch_rng_work, arch_rng_refill_buffer);
+
+bool s390_arch_random_generate(u8 *buf, unsigned int nbytes)
+{
+ /* lock rng buffer */
+ if (!spin_trylock(&arch_rng_lock))
+ return false;
+
+ /* try to resolve the requested amount of bytes from the buffer */
+ arch_rng_buf_idx -= nbytes;
+ if (arch_rng_buf_idx < ARCH_RNG_BUF_SIZE) {
+ memcpy(buf, arch_rng_buf + arch_rng_buf_idx, nbytes);
+ atomic64_add(nbytes, &s390_arch_random_counter);
+ spin_unlock(&arch_rng_lock);
+ return true;
+ }
+
+ /* not enough bytes in rng buffer, refill is done asynchronously */
+ spin_unlock(&arch_rng_lock);
+
+ return false;
+}
+EXPORT_SYMBOL(s390_arch_random_generate);
+
+static void arch_rng_refill_buffer(struct work_struct *unused)
+{
+ unsigned int delay = ARCH_REFILL_TICKS;
+
+ spin_lock(&arch_rng_lock);
+ if (arch_rng_buf_idx > ARCH_RNG_BUF_SIZE) {
+ /* buffer is exhausted and needs refill */
+ u8 seed[ARCH_PRNG_SEED_SIZE];
+ u8 prng_wa[240];
+ /* fetch ARCH_PRNG_SEED_SIZE bytes of entropy */
+ cpacf_trng(NULL, 0, seed, sizeof(seed));
+ /* blow this entropy up to ARCH_RNG_BUF_SIZE with PRNG */
+ memset(prng_wa, 0, sizeof(prng_wa));
+ cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED,
+ &prng_wa, NULL, 0, seed, sizeof(seed));
+ cpacf_prno(CPACF_PRNO_SHA512_DRNG_GEN,
+ &prng_wa, arch_rng_buf, ARCH_RNG_BUF_SIZE, NULL, 0);
+ arch_rng_buf_idx = ARCH_RNG_BUF_SIZE;
+ }
+ delay += (ARCH_REFILL_TICKS * arch_rng_buf_idx) / ARCH_RNG_BUF_SIZE;
+ spin_unlock(&arch_rng_lock);
+
+ /* kick next check */
+ queue_delayed_work(system_long_wq, &arch_rng_work, delay);
+}
+
static int __init s390_arch_random_init(void)
{
- /* check if subfunction CPACF_PRNO_TRNG is available */
- if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG))
+ /* all the needed PRNO subfunctions available ? */
+ if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG) &&
+ cpacf_query_func(CPACF_PRNO, CPACF_PRNO_SHA512_DRNG_GEN)) {
+
+ /* alloc arch random working buffer */
+ arch_rng_buf = kmalloc(ARCH_RNG_BUF_SIZE, GFP_KERNEL);
+ if (!arch_rng_buf)
+ return -ENOMEM;
+
+ /* kick worker queue job to fill the random buffer */
+ queue_delayed_work(system_long_wq,
+ &arch_rng_work, ARCH_REFILL_TICKS);
+
+ /* enable arch random to the outside world */
static_branch_enable(&s390_arch_random_available);
+ }
return 0;
}
diff --git a/arch/s390/crypto/crc32be-vx.S b/arch/s390/crypto/crc32be-vx.S
index e8077f0..2bf01ba 100644
--- a/arch/s390/crypto/crc32be-vx.S
+++ b/arch/s390/crypto/crc32be-vx.S
@@ -13,6 +13,7 @@
*/
#include <linux/linkage.h>
+#include <asm/nospec-insn.h>
#include <asm/vx-insn.h>
/* Vector register range containing CRC-32 constants */
@@ -67,6 +68,8 @@
.previous
+ GEN_BR_THUNK %r14
+
.text
/*
* The CRC-32 function(s) use these calling conventions:
@@ -203,6 +206,6 @@
.Ldone:
VLGVF %r2,%v2,3
- br %r14
+ BR_EX %r14
.previous
diff --git a/arch/s390/crypto/crc32le-vx.S b/arch/s390/crypto/crc32le-vx.S
index d8c67a58..7d6f568 100644
--- a/arch/s390/crypto/crc32le-vx.S
+++ b/arch/s390/crypto/crc32le-vx.S
@@ -14,6 +14,7 @@
*/
#include <linux/linkage.h>
+#include <asm/nospec-insn.h>
#include <asm/vx-insn.h>
/* Vector register range containing CRC-32 constants */
@@ -76,6 +77,7 @@
.previous
+ GEN_BR_THUNK %r14
.text
@@ -264,6 +266,6 @@
.Ldone:
VLGVF %r2,%v2,2
- br %r14
+ BR_EX %r14
.previous
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 46a3178..f40600e 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -8,6 +8,7 @@
CONFIG_TASK_DELAY_ACCT=y
CONFIG_TASK_XACCT=y
CONFIG_TASK_IO_ACCOUNTING=y
+# CONFIG_CPU_ISOLATION is not set
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_CGROUPS=y
@@ -23,12 +24,12 @@
CONFIG_CGROUP_DEVICE=y
CONFIG_CGROUP_CPUACCT=y
CONFIG_CGROUP_PERF=y
-CONFIG_CHECKPOINT_RESTORE=y
CONFIG_NAMESPACES=y
CONFIG_USER_NS=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_EXPERT=y
# CONFIG_SYSFS_SYSCALL is not set
+CONFIG_CHECKPOINT_RESTORE=y
CONFIG_BPF_SYSCALL=y
CONFIG_USERFAULTFD=y
# CONFIG_COMPAT_BRK is not set
@@ -47,6 +48,7 @@
CONFIG_NR_CPUS=256
CONFIG_NUMA=y
CONFIG_HZ_100=y
+CONFIG_KEXEC_FILE=y
CONFIG_MEMORY_HOTPLUG=y
CONFIG_MEMORY_HOTREMOVE=y
CONFIG_KSM=y
@@ -129,10 +131,13 @@
CONFIG_TUN=m
CONFIG_VIRTIO_NET=y
# CONFIG_NET_VENDOR_ALACRITECH is not set
+# CONFIG_NET_VENDOR_CORTINA is not set
# CONFIG_NET_VENDOR_SOLARFLARE is not set
+# CONFIG_NET_VENDOR_SOCIONEXT is not set
# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_INPUT is not set
# CONFIG_SERIO is not set
+# CONFIG_VT is not set
CONFIG_DEVKMEM=y
CONFIG_RAW_DRIVER=m
CONFIG_VIRTIO_BALLOON=y
@@ -177,13 +182,15 @@
CONFIG_STACK_TRACER=y
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_FUNCTION_PROFILER=y
-CONFIG_KPROBES_SANITY_TEST=y
+# CONFIG_RUNTIME_TESTING_MENU is not set
CONFIG_S390_PTDUMP=y
CONFIG_CRYPTO_CRYPTD=m
+CONFIG_CRYPTO_AUTHENC=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_CCM=m
CONFIG_CRYPTO_GCM=m
CONFIG_CRYPTO_CBC=y
+CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_CTS=m
CONFIG_CRYPTO_LRW=m
CONFIG_CRYPTO_PCBC=m
@@ -213,6 +220,8 @@
CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SPECK=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_DEFLATE=m
diff --git a/arch/s390/hypfs/hypfs_sprp.c b/arch/s390/hypfs/hypfs_sprp.c
index ae0ed8dd..5d85a03 100644
--- a/arch/s390/hypfs/hypfs_sprp.c
+++ b/arch/s390/hypfs/hypfs_sprp.c
@@ -13,7 +13,6 @@
#include <linux/string.h>
#include <linux/types.h>
#include <linux/uaccess.h>
-#include <asm/compat.h>
#include <asm/diag.h>
#include <asm/sclp.h>
#include "hypfs.h"
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 43bbe63..06b513d 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -320,7 +320,7 @@ static void hypfs_kill_super(struct super_block *sb)
if (sb->s_root)
hypfs_delete_tree(sb->s_root);
- if (sb_info->update_file)
+ if (sb_info && sb_info->update_file)
hypfs_remove(sb_info->update_file);
kfree(sb->s_fs_info);
sb->s_fs_info = NULL;
diff --git a/arch/s390/include/asm/archrandom.h b/arch/s390/include/asm/archrandom.h
index 09aed10..c67b82d 100644
--- a/arch/s390/include/asm/archrandom.h
+++ b/arch/s390/include/asm/archrandom.h
@@ -15,16 +15,11 @@
#include <linux/static_key.h>
#include <linux/atomic.h>
-#include <asm/cpacf.h>
DECLARE_STATIC_KEY_FALSE(s390_arch_random_available);
extern atomic64_t s390_arch_random_counter;
-static void s390_arch_random_generate(u8 *buf, unsigned int nbytes)
-{
- cpacf_trng(NULL, 0, buf, nbytes);
- atomic64_add(nbytes, &s390_arch_random_counter);
-}
+bool s390_arch_random_generate(u8 *buf, unsigned int nbytes);
static inline bool arch_has_random(void)
{
@@ -51,8 +46,7 @@ static inline bool arch_get_random_int(unsigned int *v)
static inline bool arch_get_random_seed_long(unsigned long *v)
{
if (static_branch_likely(&s390_arch_random_available)) {
- s390_arch_random_generate((u8 *)v, sizeof(*v));
- return true;
+ return s390_arch_random_generate((u8 *)v, sizeof(*v));
}
return false;
}
@@ -60,8 +54,7 @@ static inline bool arch_get_random_seed_long(unsigned long *v)
static inline bool arch_get_random_seed_int(unsigned int *v)
{
if (static_branch_likely(&s390_arch_random_available)) {
- s390_arch_random_generate((u8 *)v, sizeof(*v));
- return true;
+ return s390_arch_random_generate((u8 *)v, sizeof(*v));
}
return false;
}
diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h
index 20bce13..a29dd43 100644
--- a/arch/s390/include/asm/ccwdev.h
+++ b/arch/s390/include/asm/ccwdev.h
@@ -231,4 +231,5 @@ int ccw_device_siosl(struct ccw_device *);
extern void ccw_device_get_schid(struct ccw_device *, struct subchannel_id *);
struct channel_path_desc_fmt0 *ccw_device_get_chp_desc(struct ccw_device *, int);
+u8 *ccw_device_get_util_str(struct ccw_device *cdev, int chp_idx);
#endif /* _S390_CCWDEV_H_ */
diff --git a/arch/s390/include/asm/ccwgroup.h b/arch/s390/include/asm/ccwgroup.h
index 99aa817..860cab7 100644
--- a/arch/s390/include/asm/ccwgroup.h
+++ b/arch/s390/include/asm/ccwgroup.h
@@ -73,4 +73,14 @@ extern void ccwgroup_remove_ccwdev(struct ccw_device *cdev);
#define to_ccwgroupdev(x) container_of((x), struct ccwgroup_device, dev)
#define to_ccwgroupdrv(x) container_of((x), struct ccwgroup_driver, driver)
+
+#if IS_ENABLED(CONFIG_CCWGROUP)
+bool dev_is_ccwgroup(struct device *dev);
+#else /* CONFIG_CCWGROUP */
+static inline bool dev_is_ccwgroup(struct device *dev)
+{
+ return false;
+}
+#endif /* CONFIG_CCWGROUP */
+
#endif
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 9830fb6..97db2fb 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -53,7 +53,6 @@
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
-typedef s32 compat_time_t;
typedef s32 compat_clock_t;
typedef s32 compat_pid_t;
typedef u16 __compat_uid_t;
@@ -97,16 +96,6 @@ typedef struct {
u32 gprs_high[NUM_GPRS];
} s390_compat_regs_high;
-struct compat_timespec {
- compat_time_t tv_sec;
- s32 tv_nsec;
-};
-
-struct compat_timeval {
- compat_time_t tv_sec;
- s32 tv_usec;
-};
-
struct compat_stat {
compat_dev_t st_dev;
u16 __pad1;
@@ -243,10 +232,10 @@ struct compat_ipc64_perm {
struct compat_semid64_ds {
struct compat_ipc64_perm sem_perm;
- compat_time_t sem_otime;
- compat_ulong_t __pad1;
- compat_time_t sem_ctime;
- compat_ulong_t __pad2;
+ compat_ulong_t sem_otime;
+ compat_ulong_t sem_otime_high;
+ compat_ulong_t sem_ctime;
+ compat_ulong_t sem_ctime_high;
compat_ulong_t sem_nsems;
compat_ulong_t __unused1;
compat_ulong_t __unused2;
@@ -254,12 +243,12 @@ struct compat_semid64_ds {
struct compat_msqid64_ds {
struct compat_ipc64_perm msg_perm;
- compat_time_t msg_stime;
- compat_ulong_t __pad1;
- compat_time_t msg_rtime;
- compat_ulong_t __pad2;
- compat_time_t msg_ctime;
- compat_ulong_t __pad3;
+ compat_ulong_t msg_stime;
+ compat_ulong_t msg_stime_high;
+ compat_ulong_t msg_rtime;
+ compat_ulong_t msg_rtime_high;
+ compat_ulong_t msg_ctime;
+ compat_ulong_t msg_ctime_high;
compat_ulong_t msg_cbytes;
compat_ulong_t msg_qnum;
compat_ulong_t msg_qbytes;
@@ -272,12 +261,12 @@ struct compat_msqid64_ds {
struct compat_shmid64_ds {
struct compat_ipc64_perm shm_perm;
compat_size_t shm_segsz;
- compat_time_t shm_atime;
- compat_ulong_t __pad1;
- compat_time_t shm_dtime;
- compat_ulong_t __pad2;
- compat_time_t shm_ctime;
- compat_ulong_t __pad3;
+ compat_ulong_t shm_atime;
+ compat_ulong_t shm_atime_high;
+ compat_ulong_t shm_dtime;
+ compat_ulong_t shm_dtime_high;
+ compat_ulong_t shm_ctime;
+ compat_ulong_t shm_ctime_high;
compat_pid_t shm_cpid;
compat_pid_t shm_lpid;
compat_ulong_t shm_nattch;
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index f58d17e..de023a9 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -113,7 +113,7 @@ struct hws_basic_entry {
struct hws_diag_entry {
unsigned int def:16; /* 0-15 Data Entry Format */
- unsigned int R:14; /* 16-19 and 20-30 reserved */
+ unsigned int R:15; /* 16-19 and 20-30 reserved */
unsigned int I:1; /* 31 entry valid or invalid */
u8 data[]; /* Machine-dependent sample data */
} __packed;
@@ -129,7 +129,9 @@ struct hws_trailer_entry {
unsigned int f:1; /* 0 - Block Full Indicator */
unsigned int a:1; /* 1 - Alert request control */
unsigned int t:1; /* 2 - Timestamp format */
- unsigned long long:61; /* 3 - 63: Reserved */
+ unsigned int :29; /* 3 - 31: Reserved */
+ unsigned int bsdes:16; /* 32-47: size of basic SDE */
+ unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */
};
unsigned long long flags; /* 0 - 63: All indicators */
};
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 1a61b1b..7d22a47 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -125,8 +125,9 @@
* ELF register definitions..
*/
+#include <linux/compat.h>
+
#include <asm/ptrace.h>
-#include <asm/compat.h>
#include <asm/syscall.h>
#include <asm/user.h>
@@ -136,7 +137,6 @@ typedef s390_regs elf_gregset_t;
typedef s390_fp_regs compat_elf_fpregset_t;
typedef s390_compat_regs compat_elf_gregset_t;
-#include <linux/compat.h>
#include <linux/sched/mm.h> /* for task_struct */
#include <asm/mmu_context.h>
diff --git a/arch/s390/include/asm/hardirq.h b/arch/s390/include/asm/hardirq.h
index a296c6ac..dfbc3c6c0 100644
--- a/arch/s390/include/asm/hardirq.h
+++ b/arch/s390/include/asm/hardirq.h
@@ -14,6 +14,8 @@
#include <asm/lowcore.h>
#define local_softirq_pending() (S390_lowcore.softirq_pending)
+#define set_softirq_pending(x) (S390_lowcore.softirq_pending = (x))
+#define or_softirq_pending(x) (S390_lowcore.softirq_pending |= (x))
#define __ARCH_IRQ_STAT
#define __ARCH_HAS_DO_SOFTIRQ
diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h
index 1d708a4..825dd0f 100644
--- a/arch/s390/include/asm/kexec.h
+++ b/arch/s390/include/asm/kexec.h
@@ -46,4 +46,27 @@
static inline void crash_setup_regs(struct pt_regs *newregs,
struct pt_regs *oldregs) { }
+struct kimage;
+struct s390_load_data {
+ /* Pointer to the kernel buffer. Used to register cmdline etc.. */
+ void *kernel_buf;
+
+ /* Total size of loaded segments in memory. Used as an offset. */
+ size_t memsz;
+
+ /* Load address of initrd. Used to register INITRD_START in kernel. */
+ unsigned long initrd_load_addr;
+};
+
+int kexec_file_add_purgatory(struct kimage *image,
+ struct s390_load_data *data);
+int kexec_file_add_initrd(struct kimage *image,
+ struct s390_load_data *data,
+ char *initrd, unsigned long initrd_len);
+int *kexec_file_update_kernel(struct kimage *iamge,
+ struct s390_load_data *data);
+
+extern const struct kexec_file_ops s390_kexec_image_ops;
+extern const struct kexec_file_ops s390_kexec_elf_ops;
+
#endif /*_S390_KEXEC_H */
diff --git a/arch/s390/include/asm/nospec-insn.h b/arch/s390/include/asm/nospec-insn.h
new file mode 100644
index 0000000..a01f811
--- /dev/null
+++ b/arch/s390/include/asm/nospec-insn.h
@@ -0,0 +1,196 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_NOSPEC_ASM_H
+#define _ASM_S390_NOSPEC_ASM_H
+
+#include <asm/alternative-asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/dwarf.h>
+
+#ifdef __ASSEMBLY__
+
+#ifdef CONFIG_EXPOLINE
+
+_LC_BR_R1 = __LC_BR_R1
+
+/*
+ * The expoline macros are used to create thunks in the same format
+ * as gcc generates them. The 'comdat' section flag makes sure that
+ * the various thunks are merged into a single copy.
+ */
+ .macro __THUNK_PROLOG_NAME name
+ .pushsection .text.\name,"axG",@progbits,\name,comdat
+ .globl \name
+ .hidden \name
+ .type \name,@function
+\name:
+ CFI_STARTPROC
+ .endm
+
+ .macro __THUNK_EPILOG
+ CFI_ENDPROC
+ .popsection
+ .endm
+
+ .macro __THUNK_PROLOG_BR r1,r2
+ __THUNK_PROLOG_NAME __s390x_indirect_jump_r\r2\()use_r\r1
+ .endm
+
+ .macro __THUNK_PROLOG_BC d0,r1,r2
+ __THUNK_PROLOG_NAME __s390x_indirect_branch_\d0\()_\r2\()use_\r1
+ .endm
+
+ .macro __THUNK_BR r1,r2
+ jg __s390x_indirect_jump_r\r2\()use_r\r1
+ .endm
+
+ .macro __THUNK_BC d0,r1,r2
+ jg __s390x_indirect_branch_\d0\()_\r2\()use_\r1
+ .endm
+
+ .macro __THUNK_BRASL r1,r2,r3
+ brasl \r1,__s390x_indirect_jump_r\r3\()use_r\r2
+ .endm
+
+ .macro __DECODE_RR expand,reg,ruse
+ .set __decode_fail,1
+ .irp r1,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+ .ifc \reg,%r\r1
+ .irp r2,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+ .ifc \ruse,%r\r2
+ \expand \r1,\r2
+ .set __decode_fail,0
+ .endif
+ .endr
+ .endif
+ .endr
+ .if __decode_fail == 1
+ .error "__DECODE_RR failed"
+ .endif
+ .endm
+
+ .macro __DECODE_RRR expand,rsave,rtarget,ruse
+ .set __decode_fail,1
+ .irp r1,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+ .ifc \rsave,%r\r1
+ .irp r2,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+ .ifc \rtarget,%r\r2
+ .irp r3,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+ .ifc \ruse,%r\r3
+ \expand \r1,\r2,\r3
+ .set __decode_fail,0
+ .endif
+ .endr
+ .endif
+ .endr
+ .endif
+ .endr
+ .if __decode_fail == 1
+ .error "__DECODE_RRR failed"
+ .endif
+ .endm
+
+ .macro __DECODE_DRR expand,disp,reg,ruse
+ .set __decode_fail,1
+ .irp r1,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+ .ifc \reg,%r\r1
+ .irp r2,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
+ .ifc \ruse,%r\r2
+ \expand \disp,\r1,\r2
+ .set __decode_fail,0
+ .endif
+ .endr
+ .endif
+ .endr
+ .if __decode_fail == 1
+ .error "__DECODE_DRR failed"
+ .endif
+ .endm
+
+ .macro __THUNK_EX_BR reg,ruse
+ # Be very careful when adding instructions to this macro!
+ # The ALTERNATIVE replacement code has a .+10 which targets
+ # the "br \reg" after the code has been patched.
+#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
+ exrl 0,555f
+ j .
+#else
+ .ifc \reg,%r1
+ ALTERNATIVE "ex %r0,_LC_BR_R1", ".insn ril,0xc60000000000,0,.+10", 35
+ j .
+ .else
+ larl \ruse,555f
+ ex 0,0(\ruse)
+ j .
+ .endif
+#endif
+555: br \reg
+ .endm
+
+ .macro __THUNK_EX_BC disp,reg,ruse
+#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
+ exrl 0,556f
+ j .
+#else
+ larl \ruse,556f
+ ex 0,0(\ruse)
+ j .
+#endif
+556: b \disp(\reg)
+ .endm
+
+ .macro GEN_BR_THUNK reg,ruse=%r1
+ __DECODE_RR __THUNK_PROLOG_BR,\reg,\ruse
+ __THUNK_EX_BR \reg,\ruse
+ __THUNK_EPILOG
+ .endm
+
+ .macro GEN_B_THUNK disp,reg,ruse=%r1
+ __DECODE_DRR __THUNK_PROLOG_BC,\disp,\reg,\ruse
+ __THUNK_EX_BC \disp,\reg,\ruse
+ __THUNK_EPILOG
+ .endm
+
+ .macro BR_EX reg,ruse=%r1
+557: __DECODE_RR __THUNK_BR,\reg,\ruse
+ .pushsection .s390_indirect_branches,"a",@progbits
+ .long 557b-.
+ .popsection
+ .endm
+
+ .macro B_EX disp,reg,ruse=%r1
+558: __DECODE_DRR __THUNK_BC,\disp,\reg,\ruse
+ .pushsection .s390_indirect_branches,"a",@progbits
+ .long 558b-.
+ .popsection
+ .endm
+
+ .macro BASR_EX rsave,rtarget,ruse=%r1
+559: __DECODE_RRR __THUNK_BRASL,\rsave,\rtarget,\ruse
+ .pushsection .s390_indirect_branches,"a",@progbits
+ .long 559b-.
+ .popsection
+ .endm
+
+#else
+ .macro GEN_BR_THUNK reg,ruse=%r1
+ .endm
+
+ .macro GEN_B_THUNK disp,reg,ruse=%r1
+ .endm
+
+ .macro BR_EX reg,ruse=%r1
+ br \reg
+ .endm
+
+ .macro B_EX disp,reg,ruse=%r1
+ b \disp(\reg)
+ .endm
+
+ .macro BASR_EX rsave,rtarget,ruse=%r1
+ basr \rsave,\rtarget
+ .endm
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_S390_NOSPEC_ASM_H */
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 12fe359..94f8db4 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -2,8 +2,6 @@
#ifndef __ASM_S390_PCI_H
#define __ASM_S390_PCI_H
-/* must be set before including asm-generic/pci.h */
-#define PCI_DMA_BUS_IS_PHYS (0)
/* must be set before including pci_clp.h */
#define PCI_BAR_COUNT 6
diff --git a/arch/s390/include/asm/pnet.h b/arch/s390/include/asm/pnet.h
new file mode 100644
index 0000000..6e27858
--- /dev/null
+++ b/arch/s390/include/asm/pnet.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * IBM System z PNET ID Support
+ *
+ * Copyright IBM Corp. 2018
+ */
+
+#ifndef _ASM_S390_PNET_H
+#define _ASM_S390_PNET_H
+
+#include <linux/device.h>
+#include <linux/types.h>
+
+#define PNETIDS_LEN 64 /* Total utility string length in bytes
+ * to cover up to 4 PNETIDs of 16 bytes
+ * for up to 4 device ports
+ */
+#define MAX_PNETID_LEN 16 /* Max.length of a single port PNETID */
+#define MAX_PNETID_PORTS (PNETIDS_LEN / MAX_PNETID_LEN)
+ /* Max. # of ports with a PNETID */
+
+int pnet_id_by_dev_port(struct device *dev, unsigned short port, u8 *pnetid);
+#endif /* _ASM_S390_PNET_H */
diff --git a/arch/s390/include/asm/purgatory.h b/arch/s390/include/asm/purgatory.h
new file mode 100644
index 0000000..6090670
--- /dev/null
+++ b/arch/s390/include/asm/purgatory.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright IBM Corp. 2018
+ *
+ * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com>
+ */
+
+#ifndef _S390_PURGATORY_H_
+#define _S390_PURGATORY_H_
+#ifndef __ASSEMBLY__
+
+#include <linux/purgatory.h>
+
+int verify_sha256_digest(void);
+
+extern u64 kernel_entry;
+extern u64 kernel_type;
+
+extern u64 crash_start;
+extern u64 crash_size;
+
+#endif /* __ASSEMBLY__ */
+#endif /* _S390_PURGATORY_H_ */
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 124154f..9c30ebe 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* S390 version
- * Copyright IBM Corp. 1999, 2010
+ * Copyright IBM Corp. 1999, 2017
*/
#ifndef _ASM_S390_SETUP_H
#define _ASM_S390_SETUP_H
@@ -37,17 +37,31 @@
#define LPP_MAGIC _BITUL(31)
#define LPP_PID_MASK _AC(0xffffffff, UL)
+/* Offsets to entry points in kernel/head.S */
+
+#define STARTUP_NORMAL_OFFSET 0x10000
+#define STARTUP_KDUMP_OFFSET 0x10010
+
+/* Offsets to parameters in kernel/head.S */
+
+#define IPL_DEVICE_OFFSET 0x10400
+#define INITRD_START_OFFSET 0x10408
+#define INITRD_SIZE_OFFSET 0x10410
+#define OLDMEM_BASE_OFFSET 0x10418
+#define OLDMEM_SIZE_OFFSET 0x10420
+#define COMMAND_LINE_OFFSET 0x10480
+
#ifndef __ASSEMBLY__
#include <asm/lowcore.h>
#include <asm/types.h>
-#define IPL_DEVICE (*(unsigned long *) (0x10400))
-#define INITRD_START (*(unsigned long *) (0x10408))
-#define INITRD_SIZE (*(unsigned long *) (0x10410))
-#define OLDMEM_BASE (*(unsigned long *) (0x10418))
-#define OLDMEM_SIZE (*(unsigned long *) (0x10420))
-#define COMMAND_LINE ((char *) (0x10480))
+#define IPL_DEVICE (*(unsigned long *) (IPL_DEVICE_OFFSET))
+#define INITRD_START (*(unsigned long *) (INITRD_START_OFFSET))
+#define INITRD_SIZE (*(unsigned long *) (INITRD_SIZE_OFFSET))
+#define OLDMEM_BASE (*(unsigned long *) (OLDMEM_BASE_OFFSET))
+#define OLDMEM_SIZE (*(unsigned long *) (OLDMEM_SIZE_OFFSET))
+#define COMMAND_LINE ((char *) (COMMAND_LINE_OFFSET))
extern int memory_end_set;
extern unsigned long memory_end;
@@ -121,12 +135,12 @@ extern void (*_machine_power_off)(void);
#else /* __ASSEMBLY__ */
-#define IPL_DEVICE 0x10400
-#define INITRD_START 0x10408
-#define INITRD_SIZE 0x10410
-#define OLDMEM_BASE 0x10418
-#define OLDMEM_SIZE 0x10420
-#define COMMAND_LINE 0x10480
+#define IPL_DEVICE (IPL_DEVICE_OFFSET)
+#define INITRD_START (INITRD_START_OFFSET)
+#define INITRD_SIZE (INITRD_SIZE_OFFSET)
+#define OLDMEM_BASE (OLDMEM_BASE_OFFSET)
+#define OLDMEM_SIZE (OLDMEM_SIZE_OFFSET)
+#define COMMAND_LINE (COMMAND_LINE_OFFSET)
#endif /* __ASSEMBLY__ */
#endif /* _ASM_S390_SETUP_H */
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 83ba575..3c883c3 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -45,6 +45,9 @@ struct thread_info {
void arch_release_task_struct(struct task_struct *tsk);
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
+void arch_setup_new_exec(void);
+#define arch_setup_new_exec arch_setup_new_exec
+
#endif
/*
diff --git a/arch/s390/include/uapi/asm/Kbuild b/arch/s390/include/uapi/asm/Kbuild
index faef3f7..e364873 100644
--- a/arch/s390/include/uapi/asm/Kbuild
+++ b/arch/s390/include/uapi/asm/Kbuild
@@ -9,9 +9,12 @@
generic-y += fcntl.h
generic-y += ioctl.h
generic-y += mman.h
+generic-y += msgbuf.h
generic-y += param.h
generic-y += poll.h
generic-y += resource.h
+generic-y += sembuf.h
+generic-y += shmbuf.h
generic-y += sockios.h
generic-y += swab.h
generic-y += termbits.h
diff --git a/arch/s390/include/uapi/asm/msgbuf.h b/arch/s390/include/uapi/asm/msgbuf.h
deleted file mode 100644
index 604f847..0000000
--- a/arch/s390/include/uapi/asm/msgbuf.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _S390_MSGBUF_H
-#define _S390_MSGBUF_H
-
-/*
- * The msqid64_ds structure for S/390 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct msqid64_ds {
- struct ipc64_perm msg_perm;
- __kernel_time_t msg_stime; /* last msgsnd time */
-#ifndef __s390x__
- unsigned long __unused1;
-#endif /* ! __s390x__ */
- __kernel_time_t msg_rtime; /* last msgrcv time */
-#ifndef __s390x__
- unsigned long __unused2;
-#endif /* ! __s390x__ */
- __kernel_time_t msg_ctime; /* last change time */
-#ifndef __s390x__
- unsigned long __unused3;
-#endif /* ! __s390x__ */
- unsigned long msg_cbytes; /* current number of bytes on queue */
- unsigned long msg_qnum; /* number of messages in queue */
- unsigned long msg_qbytes; /* max number of bytes on queue */
- __kernel_pid_t msg_lspid; /* pid of last msgsnd */
- __kernel_pid_t msg_lrpid; /* last receive pid */
- unsigned long __unused4;
- unsigned long __unused5;
-};
-
-#endif /* _S390_MSGBUF_H */
diff --git a/arch/s390/include/uapi/asm/sembuf.h b/arch/s390/include/uapi/asm/sembuf.h
deleted file mode 100644
index 3e91769..0000000
--- a/arch/s390/include/uapi/asm/sembuf.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _S390_SEMBUF_H
-#define _S390_SEMBUF_H
-
-/*
- * The semid64_ds structure for S/390 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem (for !__s390x__)
- * - 2 miscellaneous 32-bit values
- */
-
-struct semid64_ds {
- struct ipc64_perm sem_perm; /* permissions .. see ipc.h */
- __kernel_time_t sem_otime; /* last semop time */
-#ifndef __s390x__
- unsigned long __unused1;
-#endif /* ! __s390x__ */
- __kernel_time_t sem_ctime; /* last change time */
-#ifndef __s390x__
- unsigned long __unused2;
-#endif /* ! __s390x__ */
- unsigned long sem_nsems; /* no. of semaphores in array */
- unsigned long __unused3;
- unsigned long __unused4;
-};
-
-#endif /* _S390_SEMBUF_H */
diff --git a/arch/s390/include/uapi/asm/shmbuf.h b/arch/s390/include/uapi/asm/shmbuf.h
deleted file mode 100644
index 9cdce8d..0000000
--- a/arch/s390/include/uapi/asm/shmbuf.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _S390_SHMBUF_H
-#define _S390_SHMBUF_H
-
-/*
- * The shmid64_ds structure for S/390 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem (for !__s390x__)
- * - 2 miscellaneous 32-bit values
- */
-
-struct shmid64_ds {
- struct ipc64_perm shm_perm; /* operation perms */
- size_t shm_segsz; /* size of segment (bytes) */
- __kernel_time_t shm_atime; /* last attach time */
-#ifndef __s390x__
- unsigned long __unused1;
-#endif /* ! __s390x__ */
- __kernel_time_t shm_dtime; /* last detach time */
-#ifndef __s390x__
- unsigned long __unused2;
-#endif /* ! __s390x__ */
- __kernel_time_t shm_ctime; /* last change time */
-#ifndef __s390x__
- unsigned long __unused3;
-#endif /* ! __s390x__ */
- __kernel_pid_t shm_cpid; /* pid of creator */
- __kernel_pid_t shm_lpid; /* pid of last operator */
- unsigned long shm_nattch; /* no. of current attaches */
- unsigned long __unused4;
- unsigned long __unused5;
-};
-
-struct shminfo64 {
- unsigned long shmmax;
- unsigned long shmmin;
- unsigned long shmmni;
- unsigned long shmseg;
- unsigned long shmall;
- unsigned long __unused1;
- unsigned long __unused2;
- unsigned long __unused3;
- unsigned long __unused4;
-};
-
-#endif /* _S390_SHMBUF_H */
diff --git a/arch/s390/include/uapi/asm/signal.h b/arch/s390/include/uapi/asm/signal.h
index c57f9d2..9a14a61 100644
--- a/arch/s390/include/uapi/asm/signal.h
+++ b/arch/s390/include/uapi/asm/signal.h
@@ -97,22 +97,31 @@ typedef unsigned long sigset_t;
#include <asm-generic/signal-defs.h>
#ifndef __KERNEL__
-/* Here we must cater to libcs that poke about in kernel headers. */
+/*
+ * There are two system calls in regard to sigaction, sys_rt_sigaction
+ * and sys_sigaction. Internally the kernel uses the struct old_sigaction
+ * for the older sys_sigaction system call, and the kernel version of the
+ * struct sigaction for the newer sys_rt_sigaction.
+ *
+ * The uapi definition for struct sigaction has made a strange distinction
+ * between 31-bit and 64-bit in the past. For 64-bit the uapi structure
+ * looks like the kernel struct sigaction, but for 31-bit it used to
+ * look like the kernel struct old_sigaction. That practically made the
+ * structure unusable for either system call. To get around this problem
+ * the glibc always had its own definitions for the sigaction structures.
+ *
+ * The current struct sigaction uapi definition below is suitable for the
+ * sys_rt_sigaction system call only.
+ */
struct sigaction {
union {
__sighandler_t _sa_handler;
void (*_sa_sigaction)(int, struct siginfo *, void *);
} _u;
-#ifndef __s390x__ /* lovely */
- sigset_t sa_mask;
- unsigned long sa_flags;
- void (*sa_restorer)(void);
-#else /* __s390x__ */
unsigned long sa_flags;
void (*sa_restorer)(void);
sigset_t sa_mask;
-#endif /* __s390x__ */
};
#define sa_handler _u._sa_handler
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index b06a6f7..2fed39b 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -6,22 +6,26 @@
ifdef CONFIG_FUNCTION_TRACER
# Do not trace tracer code
-CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
# Do not trace early setup code
-CFLAGS_REMOVE_als.o = $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_early.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_als.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_early.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_early_nobss.o = $(CC_FLAGS_FTRACE)
endif
-GCOV_PROFILE_als.o := n
-GCOV_PROFILE_early.o := n
+GCOV_PROFILE_als.o := n
+GCOV_PROFILE_early.o := n
+GCOV_PROFILE_early_nobss.o := n
-KCOV_INSTRUMENT_als.o := n
-KCOV_INSTRUMENT_early.o := n
+KCOV_INSTRUMENT_als.o := n
+KCOV_INSTRUMENT_early.o := n
+KCOV_INSTRUMENT_early_nobss.o := n
-UBSAN_SANITIZE_als.o := n
-UBSAN_SANITIZE_early.o := n
+UBSAN_SANITIZE_als.o := n
+UBSAN_SANITIZE_early.o := n
+UBSAN_SANITIZE_early_nobss.o := n
#
# Use -march=z900 for als.c to be able to print an error
@@ -57,7 +61,7 @@
obj-y := traps.o time.o process.o base.o early.o setup.o idle.o vtime.o
obj-y += processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
-obj-y += debug.o irq.o ipl.o dis.o diag.o vdso.o als.o
+obj-y += debug.o irq.o ipl.o dis.o diag.o vdso.o als.o early_nobss.o
obj-y += sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
obj-y += runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o
obj-y += entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o
@@ -65,6 +69,7 @@
extra-y += head.o head64.o vmlinux.lds
+obj-$(CONFIG_SYSFS) += nospec-sysfs.o
CFLAGS_REMOVE_nospec-branch.o += $(CC_FLAGS_EXPOLINE)
obj-$(CONFIG_MODULES) += module.o
@@ -82,6 +87,9 @@
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
obj-$(CONFIG_UPROBES) += uprobes.o
+obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file.o kexec_image.o
+obj-$(CONFIG_KEXEC_FILE) += kexec_elf.o
+
obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_cpum_cf.o perf_cpum_sf.o
obj-$(CONFIG_PERF_EVENTS) += perf_cpum_cf_events.o perf_regs.o
@@ -90,3 +98,6 @@
# vdso
obj-y += vdso64/
obj-$(CONFIG_COMPAT) += vdso32/
+
+chkbss := head.o head64.o als.o early_nobss.o
+include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index cfe2c45..11aea74 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -10,6 +10,7 @@
#include <linux/kbuild.h>
#include <linux/kvm_host.h>
#include <linux/sched.h>
+#include <linux/purgatory.h>
#include <asm/idle.h>
#include <asm/vdso.h>
#include <asm/pgtable.h>
@@ -180,6 +181,7 @@ int main(void)
OFFSET(__LC_MACHINE_FLAGS, lowcore, machine_flags);
OFFSET(__LC_PREEMPT_COUNT, lowcore, preempt_count);
OFFSET(__LC_GMAP, lowcore, gmap);
+ OFFSET(__LC_BR_R1, lowcore, br_r1_trampoline);
/* software defined ABI-relevant lowcore locations 0xe00 - 0xe20 */
OFFSET(__LC_DUMP_REIPL, lowcore, ipib);
/* hardware defined lowcore locations 0x1000 - 0x18ff */
@@ -204,5 +206,9 @@ int main(void)
OFFSET(__GMAP_ASCE, gmap, asce);
OFFSET(__SIE_PROG0C, kvm_s390_sie_block, prog0c);
OFFSET(__SIE_PROG20, kvm_s390_sie_block, prog20);
+ /* kexec_sha_region */
+ OFFSET(__KEXEC_SHA_REGION_START, kexec_sha_region, start);
+ OFFSET(__KEXEC_SHA_REGION_LEN, kexec_sha_region, len);
+ DEFINE(__KEXEC_SHA_REGION_SIZE, sizeof(struct kexec_sha_region));
return 0;
}
diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S
index f6c5600..b65874b 100644
--- a/arch/s390/kernel/base.S
+++ b/arch/s390/kernel/base.S
@@ -9,18 +9,22 @@
#include <linux/linkage.h>
#include <asm/asm-offsets.h>
+#include <asm/nospec-insn.h>
#include <asm/ptrace.h>
#include <asm/sigp.h>
+ GEN_BR_THUNK %r9
+ GEN_BR_THUNK %r14
+
ENTRY(s390_base_mcck_handler)
basr %r13,0
0: lg %r15,__LC_PANIC_STACK # load panic stack
aghi %r15,-STACK_FRAME_OVERHEAD
larl %r1,s390_base_mcck_handler_fn
- lg %r1,0(%r1)
- ltgr %r1,%r1
+ lg %r9,0(%r1)
+ ltgr %r9,%r9
jz 1f
- basr %r14,%r1
+ BASR_EX %r14,%r9
1: la %r1,4095
lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)
lpswe __LC_MCK_OLD_PSW
@@ -37,10 +41,10 @@
basr %r13,0
0: aghi %r15,-STACK_FRAME_OVERHEAD
larl %r1,s390_base_ext_handler_fn
- lg %r1,0(%r1)
- ltgr %r1,%r1
+ lg %r9,0(%r1)
+ ltgr %r9,%r9
jz 1f
- basr %r14,%r1
+ BASR_EX %r14,%r9
1: lmg %r0,%r15,__LC_SAVE_AREA_ASYNC
ni __LC_EXT_OLD_PSW+1,0xfd # clear wait state bit
lpswe __LC_EXT_OLD_PSW
@@ -57,10 +61,10 @@
basr %r13,0
0: aghi %r15,-STACK_FRAME_OVERHEAD
larl %r1,s390_base_pgm_handler_fn
- lg %r1,0(%r1)
- ltgr %r1,%r1
+ lg %r9,0(%r1)
+ ltgr %r9,%r9
jz 1f
- basr %r14,%r1
+ BASR_EX %r14,%r9
lmg %r0,%r15,__LC_SAVE_AREA_SYNC
lpswe __LC_PGM_OLD_PSW
1: lpswe disabled_wait_psw-0b(%r13)
@@ -117,7 +121,7 @@
larl %r4,.Lcontinue_psw # Restore PSW flags
lpswe 0(%r4)
.Lcontinue:
- br %r14
+ BR_EX %r14
.align 16
.Lrestart_psw:
.long 0x00080000,0x80000000 + .Lrestart_part2
diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c
index 11e9d8b..607c5e9 100644
--- a/arch/s390/kernel/compat_wrapper.c
+++ b/arch/s390/kernel/compat_wrapper.c
@@ -182,3 +182,4 @@ COMPAT_SYSCALL_WRAP6(copy_file_range, int, fd_in, loff_t __user *, off_in, int,
COMPAT_SYSCALL_WRAP2(s390_guarded_storage, int, command, struct gs_cb *, gs_cb);
COMPAT_SYSCALL_WRAP5(statx, int, dfd, const char __user *, path, unsigned, flags, unsigned, mask, struct statx __user *, buffer);
COMPAT_SYSCALL_WRAP4(s390_sthyi, unsigned long, code, void __user *, info, u64 __user *, rc, unsigned long, flags);
+COMPAT_SYSCALL_WRAP5(kexec_file_load, int, kernel_fd, int, initrd_fd, unsigned long, cmdline_len, const char __user *, cmdline_ptr, unsigned long, flags)
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 32daa0f..827699e 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -34,32 +34,6 @@
static void __init setup_boot_command_line(void);
/*
- * Get the TOD clock running.
- */
-static void __init reset_tod_clock(void)
-{
- u64 time;
-
- if (store_tod_clock(&time) == 0)
- return;
- /* TOD clock not running. Set the clock to Unix Epoch. */
- if (set_tod_clock(TOD_UNIX_EPOCH) != 0 || store_tod_clock(&time) != 0)
- disabled_wait(0);
-
- memset(tod_clock_base, 0, 16);
- *(__u64 *) &tod_clock_base[1] = TOD_UNIX_EPOCH;
- S390_lowcore.last_update_clock = TOD_UNIX_EPOCH;
-}
-
-/*
- * Clear bss memory
- */
-static noinline __init void clear_bss_section(void)
-{
- memset(__bss_start, 0, __bss_stop - __bss_start);
-}
-
-/*
* Initialize storage key for kernel pages
*/
static noinline __init void init_kernel_storage_key(void)
@@ -310,57 +284,6 @@ static int __init cad_setup(char *str)
}
early_param("cad", cad_setup);
-static __init void memmove_early(void *dst, const void *src, size_t n)
-{
- unsigned long addr;
- long incr;
- psw_t old;
-
- if (!n)
- return;
- incr = 1;
- if (dst > src) {
- incr = -incr;
- dst += n - 1;
- src += n - 1;
- }
- old = S390_lowcore.program_new_psw;
- S390_lowcore.program_new_psw.mask = __extract_psw();
- asm volatile(
- " larl %[addr],1f\n"
- " stg %[addr],%[psw_pgm_addr]\n"
- "0: mvc 0(1,%[dst]),0(%[src])\n"
- " agr %[dst],%[incr]\n"
- " agr %[src],%[incr]\n"
- " brctg %[n],0b\n"
- "1:\n"
- : [addr] "=&d" (addr),
- [psw_pgm_addr] "=Q" (S390_lowcore.program_new_psw.addr),
- [dst] "+&a" (dst), [src] "+&a" (src), [n] "+d" (n)
- : [incr] "d" (incr)
- : "cc", "memory");
- S390_lowcore.program_new_psw = old;
-}
-
-static __init noinline void rescue_initrd(void)
-{
-#ifdef CONFIG_BLK_DEV_INITRD
- unsigned long min_initrd_addr = (unsigned long) _end + (4UL << 20);
- /*
- * Just like in case of IPL from VM reader we make sure there is a
- * gap of 4MB between end of kernel and start of initrd.
- * That way we can also be sure that saving an NSS will succeed,
- * which however only requires different segments.
- */
- if (!INITRD_START || !INITRD_SIZE)
- return;
- if (INITRD_START >= min_initrd_addr)
- return;
- memmove_early((void *) min_initrd_addr, (void *) INITRD_START, INITRD_SIZE);
- INITRD_START = min_initrd_addr;
-#endif
-}
-
/* Set up boot command line */
static void __init append_to_cmdline(size_t (*ipl_data)(char *, size_t))
{
@@ -410,9 +333,6 @@ static void __init setup_boot_command_line(void)
void __init startup_init(void)
{
- reset_tod_clock();
- rescue_initrd();
- clear_bss_section();
time_early_init();
init_kernel_storage_key();
lockdep_off();
diff --git a/arch/s390/kernel/early_nobss.c b/arch/s390/kernel/early_nobss.c
new file mode 100644
index 0000000..2d84fc4
--- /dev/null
+++ b/arch/s390/kernel/early_nobss.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corp. 2007, 2018
+ */
+
+/*
+ * Early setup functions which may not rely on an initialized bss
+ * section. The last thing that is supposed to happen here is
+ * initialization of the bss section.
+ */
+
+#include <linux/processor.h>
+#include <linux/string.h>
+#include <asm/sections.h>
+#include <asm/lowcore.h>
+#include <asm/setup.h>
+#include <asm/timex.h>
+#include "entry.h"
+
+static void __init reset_tod_clock(void)
+{
+ u64 time;
+
+ if (store_tod_clock(&time) == 0)
+ return;
+ /* TOD clock not running. Set the clock to Unix Epoch. */
+ if (set_tod_clock(TOD_UNIX_EPOCH) != 0 || store_tod_clock(&time) != 0)
+ disabled_wait(0);
+
+ memset(tod_clock_base, 0, 16);
+ *(__u64 *) &tod_clock_base[1] = TOD_UNIX_EPOCH;
+ S390_lowcore.last_update_clock = TOD_UNIX_EPOCH;
+}
+
+static void __init rescue_initrd(void)
+{
+ unsigned long min_initrd_addr = (unsigned long) _end + (4UL << 20);
+
+ /*
+ * Just like in case of IPL from VM reader we make sure there is a
+ * gap of 4MB between end of kernel and start of initrd.
+ * That way we can also be sure that saving an NSS will succeed,
+ * which however only requires different segments.
+ */
+ if (!IS_ENABLED(CONFIG_BLK_DEV_INITRD))
+ return;
+ if (!INITRD_START || !INITRD_SIZE)
+ return;
+ if (INITRD_START >= min_initrd_addr)
+ return;
+ memmove((void *) min_initrd_addr, (void *) INITRD_START, INITRD_SIZE);
+ INITRD_START = min_initrd_addr;
+}
+
+static void __init clear_bss_section(void)
+{
+ memset(__bss_start, 0, __bss_stop - __bss_start);
+}
+
+void __init startup_init_nobss(void)
+{
+ reset_tod_clock();
+ rescue_initrd();
+ clear_bss_section();
+}
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 3f22f13..f03402e 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -28,6 +28,7 @@
#include <asm/setup.h>
#include <asm/nmi.h>
#include <asm/export.h>
+#include <asm/nospec-insn.h>
__PT_R0 = __PT_GPRS
__PT_R1 = __PT_GPRS + 8
@@ -183,67 +184,9 @@
"jnz .+8; .long 0xb2e8d000", 82
.endm
-#ifdef CONFIG_EXPOLINE
-
- .macro GEN_BR_THUNK name,reg,tmp
- .section .text.\name,"axG",@progbits,\name,comdat
- .globl \name
- .hidden \name
- .type \name,@function
-\name:
- CFI_STARTPROC
-#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
- exrl 0,0f
-#else
- larl \tmp,0f
- ex 0,0(\tmp)
-#endif
- j .
-0: br \reg
- CFI_ENDPROC
- .endm
-
- GEN_BR_THUNK __s390x_indirect_jump_r1use_r9,%r9,%r1
- GEN_BR_THUNK __s390x_indirect_jump_r1use_r14,%r14,%r1
- GEN_BR_THUNK __s390x_indirect_jump_r11use_r14,%r14,%r11
-
- .macro BASR_R14_R9
-0: brasl %r14,__s390x_indirect_jump_r1use_r9
- .pushsection .s390_indirect_branches,"a",@progbits
- .long 0b-.
- .popsection
- .endm
-
- .macro BR_R1USE_R14
-0: jg __s390x_indirect_jump_r1use_r14
- .pushsection .s390_indirect_branches,"a",@progbits
- .long 0b-.
- .popsection
- .endm
-
- .macro BR_R11USE_R14
-0: jg __s390x_indirect_jump_r11use_r14
- .pushsection .s390_indirect_branches,"a",@progbits
- .long 0b-.
- .popsection
- .endm
-
-#else /* CONFIG_EXPOLINE */
-
- .macro BASR_R14_R9
- basr %r14,%r9
- .endm
-
- .macro BR_R1USE_R14
- br %r14
- .endm
-
- .macro BR_R11USE_R14
- br %r14
- .endm
-
-#endif /* CONFIG_EXPOLINE */
-
+ GEN_BR_THUNK %r9
+ GEN_BR_THUNK %r14
+ GEN_BR_THUNK %r14,%r11
.section .kprobes.text, "ax"
.Ldummy:
@@ -260,7 +203,7 @@
ENTRY(__bpon)
.globl __bpon
BPON
- BR_R1USE_R14
+ BR_EX %r14
/*
* Scheduler resume function, called by switch_to
@@ -284,7 +227,7 @@
mvc __LC_CURRENT_PID(4,%r0),0(%r3) # store pid of next
lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task
ALTERNATIVE "", ".insn s,0xb2800000,_LPP_OFFSET", 40
- BR_R1USE_R14
+ BR_EX %r14
.L__critical_start:
@@ -351,7 +294,7 @@
xgr %r5,%r5
lmg %r6,%r14,__SF_GPRS(%r15) # restore kernel registers
lg %r2,__SF_SIE_REASON(%r15) # return exit reason code
- BR_R1USE_R14
+ BR_EX %r14
.Lsie_fault:
lghi %r14,-EFAULT
stg %r14,__SF_SIE_REASON(%r15) # set exit reason code
@@ -410,7 +353,7 @@
lgf %r9,0(%r8,%r10) # get system call add.
TSTMSK __TI_flags(%r12),_TIF_TRACE
jnz .Lsysc_tracesys
- BASR_R14_R9 # call sys_xxxx
+ BASR_EX %r14,%r9 # call sys_xxxx
stg %r2,__PT_R2(%r11) # store return value
.Lsysc_return:
@@ -595,7 +538,7 @@
lmg %r3,%r7,__PT_R3(%r11)
stg %r7,STACK_FRAME_OVERHEAD(%r15)
lg %r2,__PT_ORIG_GPR2(%r11)
- BASR_R14_R9 # call sys_xxx
+ BASR_EX %r14,%r9 # call sys_xxx
stg %r2,__PT_R2(%r11) # store return value
.Lsysc_tracenogo:
TSTMSK __TI_flags(%r12),_TIF_TRACE
@@ -619,7 +562,7 @@
lmg %r9,%r10,__PT_R9(%r11) # load gprs
ENTRY(kernel_thread_starter)
la %r2,0(%r10)
- BASR_R14_R9
+ BASR_EX %r14,%r9
j .Lsysc_tracenogo
/*
@@ -701,7 +644,7 @@
je .Lpgm_return
lgf %r9,0(%r10,%r1) # load address of handler routine
lgr %r2,%r11 # pass pointer to pt_regs
- BASR_R14_R9 # branch to interrupt-handler
+ BASR_EX %r14,%r9 # branch to interrupt-handler
.Lpgm_return:
LOCKDEP_SYS_EXIT
tm __PT_PSW+1(%r11),0x01 # returning to user ?
@@ -1019,7 +962,7 @@
stpt __TIMER_IDLE_ENTER(%r2)
.Lpsw_idle_lpsw:
lpswe __SF_EMPTY(%r15)
- BR_R1USE_R14
+ BR_EX %r14
.Lpsw_idle_end:
/*
@@ -1061,7 +1004,7 @@
.Lsave_fpu_regs_done:
oi __LC_CPU_FLAGS+7,_CIF_FPU
.Lsave_fpu_regs_exit:
- BR_R1USE_R14
+ BR_EX %r14
.Lsave_fpu_regs_end:
EXPORT_SYMBOL(save_fpu_regs)
@@ -1107,7 +1050,7 @@
.Lload_fpu_regs_done:
ni __LC_CPU_FLAGS+7,255-_CIF_FPU
.Lload_fpu_regs_exit:
- BR_R1USE_R14
+ BR_EX %r14
.Lload_fpu_regs_end:
.L__critical_end:
@@ -1322,7 +1265,7 @@
jl 0f
clg %r9,BASED(.Lcleanup_table+104) # .Lload_fpu_regs_end
jl .Lcleanup_load_fpu_regs
-0: BR_R11USE_R14
+0: BR_EX %r14
.align 8
.Lcleanup_table:
@@ -1358,7 +1301,7 @@
ni __SIE_PROG0C+3(%r9),0xfe # no longer in SIE
lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
larl %r9,sie_exit # skip forward to sie_exit
- BR_R11USE_R14
+ BR_EX %r14
#endif
.Lcleanup_system_call:
@@ -1412,7 +1355,7 @@
stg %r15,56(%r11) # r15 stack pointer
# set new psw address and exit
larl %r9,.Lsysc_do_svc
- BR_R11USE_R14
+ BR_EX %r14,%r11
.Lcleanup_system_call_insn:
.quad system_call
.quad .Lsysc_stmg
@@ -1424,7 +1367,7 @@
.Lcleanup_sysc_tif:
larl %r9,.Lsysc_tif
- BR_R11USE_R14
+ BR_EX %r14,%r11
.Lcleanup_sysc_restore:
# check if stpt has been executed
@@ -1441,14 +1384,14 @@
mvc 0(64,%r11),__PT_R8(%r9)
lmg %r0,%r7,__PT_R0(%r9)
1: lmg %r8,%r9,__LC_RETURN_PSW
- BR_R11USE_R14
+ BR_EX %r14,%r11
.Lcleanup_sysc_restore_insn:
.quad .Lsysc_exit_timer
.quad .Lsysc_done - 4
.Lcleanup_io_tif:
larl %r9,.Lio_tif
- BR_R11USE_R14
+ BR_EX %r14,%r11
.Lcleanup_io_restore:
# check if stpt has been executed
@@ -1462,7 +1405,7 @@
mvc 0(64,%r11),__PT_R8(%r9)
lmg %r0,%r7,__PT_R0(%r9)
1: lmg %r8,%r9,__LC_RETURN_PSW
- BR_R11USE_R14
+ BR_EX %r14,%r11
.Lcleanup_io_restore_insn:
.quad .Lio_exit_timer
.quad .Lio_done - 4
@@ -1515,17 +1458,17 @@
# prepare return psw
nihh %r8,0xfcfd # clear irq & wait state bits
lg %r9,48(%r11) # return from psw_idle
- BR_R11USE_R14
+ BR_EX %r14,%r11
.Lcleanup_idle_insn:
.quad .Lpsw_idle_lpsw
.Lcleanup_save_fpu_regs:
larl %r9,save_fpu_regs
- BR_R11USE_R14
+ BR_EX %r14,%r11
.Lcleanup_load_fpu_regs:
larl %r9,load_fpu_regs
- BR_R11USE_R14
+ BR_EX %r14,%r11
/*
* Integer constants
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index e87758f..961abfa 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -58,6 +58,7 @@ void do_notify_resume(struct pt_regs *regs);
void __init init_IRQ(void);
void do_IRQ(struct pt_regs *regs, int irq);
void do_restart(void);
+void __init startup_init_nobss(void);
void __init startup_init(void);
void die(struct pt_regs *regs, const char *str);
int setup_profiling_timer(unsigned int multiplier);
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 38a973c..791cb90 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -40,8 +40,12 @@
stg %r15,__LC_KERNEL_STACK # set end of kernel stack
aghi %r15,-160
#
-# Save ipl parameters, clear bss memory, initialize storage key for kernel pages,
-# and create a kernel NSS if the SAVESYS= parm is defined
+# Early setup functions that may not rely on an initialized bss section,
+# like moving the initrd. Returns with an initialized bss section.
+#
+ brasl %r14,startup_init_nobss
+#
+# Early machine initialization and detection functions.
#
brasl %r14,startup_init
lpswe .Lentry-.LPG1(13) # jump to _stext in primary-space,
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 94f2099..3d17c41 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -176,10 +176,9 @@ void do_softirq_own_stack(void)
new -= STACK_FRAME_OVERHEAD;
((struct stack_frame *) new)->back_chain = old;
asm volatile(" la 15,0(%0)\n"
- " basr 14,%2\n"
+ " brasl 14,__do_softirq\n"
" la 15,0(%1)\n"
- : : "a" (new), "a" (old),
- "a" (__do_softirq)
+ : : "a" (new), "a" (old)
: "0", "1", "2", "3", "4", "5", "14",
"cc", "memory" );
} else {
diff --git a/arch/s390/kernel/kexec_elf.c b/arch/s390/kernel/kexec_elf.c
new file mode 100644
index 0000000..5a286b0
--- /dev/null
+++ b/arch/s390/kernel/kexec_elf.c
@@ -0,0 +1,147 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ELF loader for kexec_file_load system call.
+ *
+ * Copyright IBM Corp. 2018
+ *
+ * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/kexec.h>
+#include <asm/setup.h>
+
+static int kexec_file_add_elf_kernel(struct kimage *image,
+ struct s390_load_data *data,
+ char *kernel, unsigned long kernel_len)
+{
+ struct kexec_buf buf;
+ const Elf_Ehdr *ehdr;
+ const Elf_Phdr *phdr;
+ int i, ret;
+
+ ehdr = (Elf_Ehdr *)kernel;
+ buf.image = image;
+
+ phdr = (void *)ehdr + ehdr->e_phoff;
+ for (i = 0; i < ehdr->e_phnum; i++, phdr++) {
+ if (phdr->p_type != PT_LOAD)
+ continue;
+
+ buf.buffer = kernel + phdr->p_offset;
+ buf.bufsz = phdr->p_filesz;
+
+ buf.mem = ALIGN(phdr->p_paddr, phdr->p_align);
+ buf.memsz = phdr->p_memsz;
+
+ if (phdr->p_paddr == 0) {
+ data->kernel_buf = buf.buffer;
+ data->memsz += STARTUP_NORMAL_OFFSET;
+
+ buf.buffer += STARTUP_NORMAL_OFFSET;
+ buf.bufsz -= STARTUP_NORMAL_OFFSET;
+
+ buf.mem += STARTUP_NORMAL_OFFSET;
+ buf.memsz -= STARTUP_NORMAL_OFFSET;
+ }
+
+ if (image->type == KEXEC_TYPE_CRASH)
+ buf.mem += crashk_res.start;
+
+ ret = kexec_add_buffer(&buf);
+ if (ret)
+ return ret;
+
+ data->memsz += buf.memsz;
+ }
+
+ return 0;
+}
+
+static void *s390_elf_load(struct kimage *image,
+ char *kernel, unsigned long kernel_len,
+ char *initrd, unsigned long initrd_len,
+ char *cmdline, unsigned long cmdline_len)
+{
+ struct s390_load_data data = {0};
+ const Elf_Ehdr *ehdr;
+ const Elf_Phdr *phdr;
+ size_t size;
+ int i, ret;
+
+ /* image->fobs->probe already checked for valid ELF magic number. */
+ ehdr = (Elf_Ehdr *)kernel;
+
+ if (ehdr->e_type != ET_EXEC ||
+ ehdr->e_ident[EI_CLASS] != ELFCLASS64 ||
+ !elf_check_arch(ehdr))
+ return ERR_PTR(-EINVAL);
+
+ if (!ehdr->e_phnum || ehdr->e_phentsize != sizeof(Elf_Phdr))
+ return ERR_PTR(-EINVAL);
+
+ size = ehdr->e_ehsize + ehdr->e_phoff;
+ size += ehdr->e_phentsize * ehdr->e_phnum;
+ if (size > kernel_len)
+ return ERR_PTR(-EINVAL);
+
+ phdr = (void *)ehdr + ehdr->e_phoff;
+ size = ALIGN(size, phdr->p_align);
+ for (i = 0; i < ehdr->e_phnum; i++, phdr++) {
+ if (phdr->p_type == PT_INTERP)
+ return ERR_PTR(-EINVAL);
+
+ if (phdr->p_offset > kernel_len)
+ return ERR_PTR(-EINVAL);
+
+ size += ALIGN(phdr->p_filesz, phdr->p_align);
+ }
+
+ if (size > kernel_len)
+ return ERR_PTR(-EINVAL);
+
+ ret = kexec_file_add_elf_kernel(image, &data, kernel, kernel_len);
+ if (ret)
+ return ERR_PTR(ret);
+
+ if (!data.memsz)
+ return ERR_PTR(-EINVAL);
+
+ if (initrd) {
+ ret = kexec_file_add_initrd(image, &data, initrd, initrd_len);
+ if (ret)
+ return ERR_PTR(ret);
+ }
+
+ ret = kexec_file_add_purgatory(image, &data);
+ if (ret)
+ return ERR_PTR(ret);
+
+ return kexec_file_update_kernel(image, &data);
+}
+
+static int s390_elf_probe(const char *buf, unsigned long len)
+{
+ const Elf_Ehdr *ehdr;
+
+ if (len < sizeof(Elf_Ehdr))
+ return -ENOEXEC;
+
+ ehdr = (Elf_Ehdr *)buf;
+
+ /* Only check the ELF magic number here and do proper validity check
+ * in the loader. Any check here that fails would send the erroneous
+ * ELF file to the image loader that does not care what it gets.
+ * (Most likely) causing behavior not intended by the user.
+ */
+ if (memcmp(ehdr->e_ident, ELFMAG, SELFMAG) != 0)
+ return -ENOEXEC;
+
+ return 0;
+}
+
+const struct kexec_file_ops s390_kexec_elf_ops = {
+ .probe = s390_elf_probe,
+ .load = s390_elf_load,
+};
diff --git a/arch/s390/kernel/kexec_image.c b/arch/s390/kernel/kexec_image.c
new file mode 100644
index 0000000..3800852
--- /dev/null
+++ b/arch/s390/kernel/kexec_image.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Image loader for kexec_file_load system call.
+ *
+ * Copyright IBM Corp. 2018
+ *
+ * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/kexec.h>
+#include <asm/setup.h>
+
+static int kexec_file_add_image_kernel(struct kimage *image,
+ struct s390_load_data *data,
+ char *kernel, unsigned long kernel_len)
+{
+ struct kexec_buf buf;
+ int ret;
+
+ buf.image = image;
+
+ buf.buffer = kernel + STARTUP_NORMAL_OFFSET;
+ buf.bufsz = kernel_len - STARTUP_NORMAL_OFFSET;
+
+ buf.mem = STARTUP_NORMAL_OFFSET;
+ if (image->type == KEXEC_TYPE_CRASH)
+ buf.mem += crashk_res.start;
+ buf.memsz = buf.bufsz;
+
+ ret = kexec_add_buffer(&buf);
+
+ data->kernel_buf = kernel;
+ data->memsz += buf.memsz + STARTUP_NORMAL_OFFSET;
+
+ return ret;
+}
+
+static void *s390_image_load(struct kimage *image,
+ char *kernel, unsigned long kernel_len,
+ char *initrd, unsigned long initrd_len,
+ char *cmdline, unsigned long cmdline_len)
+{
+ struct s390_load_data data = {0};
+ int ret;
+
+ ret = kexec_file_add_image_kernel(image, &data, kernel, kernel_len);
+ if (ret)
+ return ERR_PTR(ret);
+
+ if (initrd) {
+ ret = kexec_file_add_initrd(image, &data, initrd, initrd_len);
+ if (ret)
+ return ERR_PTR(ret);
+ }
+
+ ret = kexec_file_add_purgatory(image, &data);
+ if (ret)
+ return ERR_PTR(ret);
+
+ return kexec_file_update_kernel(image, &data);
+}
+
+static int s390_image_probe(const char *buf, unsigned long len)
+{
+ /* Can't reliably tell if an image is valid. Therefore give the
+ * user whatever he wants.
+ */
+ return 0;
+}
+
+const struct kexec_file_ops s390_kexec_image_ops = {
+ .probe = s390_image_probe,
+ .load = s390_image_load,
+};
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
new file mode 100644
index 0000000..f413f57
--- /dev/null
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * s390 code for kexec_file_load system call
+ *
+ * Copyright IBM Corp. 2018
+ *
+ * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com>
+ */
+
+#include <linux/elf.h>
+#include <linux/kexec.h>
+#include <asm/setup.h>
+
+const struct kexec_file_ops * const kexec_file_loaders[] = {
+ &s390_kexec_elf_ops,
+ &s390_kexec_image_ops,
+ NULL,
+};
+
+int *kexec_file_update_kernel(struct kimage *image,
+ struct s390_load_data *data)
+{
+ unsigned long *loc;
+
+ if (image->cmdline_buf_len >= ARCH_COMMAND_LINE_SIZE)
+ return ERR_PTR(-EINVAL);
+
+ if (image->cmdline_buf_len)
+ memcpy(data->kernel_buf + COMMAND_LINE_OFFSET,
+ image->cmdline_buf, image->cmdline_buf_len);
+
+ if (image->type == KEXEC_TYPE_CRASH) {
+ loc = (unsigned long *)(data->kernel_buf + OLDMEM_BASE_OFFSET);
+ *loc = crashk_res.start;
+
+ loc = (unsigned long *)(data->kernel_buf + OLDMEM_SIZE_OFFSET);
+ *loc = crashk_res.end - crashk_res.start + 1;
+ }
+
+ if (image->initrd_buf) {
+ loc = (unsigned long *)(data->kernel_buf + INITRD_START_OFFSET);
+ *loc = data->initrd_load_addr;
+
+ loc = (unsigned long *)(data->kernel_buf + INITRD_SIZE_OFFSET);
+ *loc = image->initrd_buf_len;
+ }
+
+ return NULL;
+}
+
+static int kexec_file_update_purgatory(struct kimage *image)
+{
+ u64 entry, type;
+ int ret;
+
+ if (image->type == KEXEC_TYPE_CRASH) {
+ entry = STARTUP_KDUMP_OFFSET;
+ type = KEXEC_TYPE_CRASH;
+ } else {
+ entry = STARTUP_NORMAL_OFFSET;
+ type = KEXEC_TYPE_DEFAULT;
+ }
+
+ ret = kexec_purgatory_get_set_symbol(image, "kernel_entry", &entry,
+ sizeof(entry), false);
+ if (ret)
+ return ret;
+
+ ret = kexec_purgatory_get_set_symbol(image, "kernel_type", &type,
+ sizeof(type), false);
+ if (ret)
+ return ret;
+
+ if (image->type == KEXEC_TYPE_CRASH) {
+ u64 crash_size;
+
+ ret = kexec_purgatory_get_set_symbol(image, "crash_start",
+ &crashk_res.start,
+ sizeof(crashk_res.start),
+ false);
+ if (ret)
+ return ret;
+
+ crash_size = crashk_res.end - crashk_res.start + 1;
+ ret = kexec_purgatory_get_set_symbol(image, "crash_size",
+ &crash_size,
+ sizeof(crash_size),
+ false);
+ }
+ return ret;
+}
+
+int kexec_file_add_purgatory(struct kimage *image, struct s390_load_data *data)
+{
+ struct kexec_buf buf;
+ int ret;
+
+ buf.image = image;
+
+ data->memsz = ALIGN(data->memsz, PAGE_SIZE);
+ buf.mem = data->memsz;
+ if (image->type == KEXEC_TYPE_CRASH)
+ buf.mem += crashk_res.start;
+
+ ret = kexec_load_purgatory(image, &buf);
+ if (ret)
+ return ret;
+
+ ret = kexec_file_update_purgatory(image);
+ return ret;
+}
+
+int kexec_file_add_initrd(struct kimage *image, struct s390_load_data *data,
+ char *initrd, unsigned long initrd_len)
+{
+ struct kexec_buf buf;
+ int ret;
+
+ buf.image = image;
+
+ buf.buffer = initrd;
+ buf.bufsz = initrd_len;
+
+ data->memsz = ALIGN(data->memsz, PAGE_SIZE);
+ buf.mem = data->memsz;
+ if (image->type == KEXEC_TYPE_CRASH)
+ buf.mem += crashk_res.start;
+ buf.memsz = buf.bufsz;
+
+ data->initrd_load_addr = buf.mem;
+ data->memsz += buf.memsz;
+
+ ret = kexec_add_buffer(&buf);
+ return ret;
+}
+
+/*
+ * The kernel is loaded to a fixed location. Turn off kexec_locate_mem_hole
+ * and provide kbuf->mem by hand.
+ */
+int arch_kexec_walk_mem(struct kexec_buf *kbuf,
+ int (*func)(struct resource *, void *))
+{
+ return 1;
+}
+
+int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
+ Elf_Shdr *section,
+ const Elf_Shdr *relsec,
+ const Elf_Shdr *symtab)
+{
+ Elf_Rela *relas;
+ int i;
+
+ relas = (void *)pi->ehdr + relsec->sh_offset;
+
+ for (i = 0; i < relsec->sh_size / sizeof(*relas); i++) {
+ const Elf_Sym *sym; /* symbol to relocate */
+ unsigned long addr; /* final location after relocation */
+ unsigned long val; /* relocated symbol value */
+ void *loc; /* tmp location to modify */
+
+ sym = (void *)pi->ehdr + symtab->sh_offset;
+ sym += ELF64_R_SYM(relas[i].r_info);
+
+ if (sym->st_shndx == SHN_UNDEF)
+ return -ENOEXEC;
+
+ if (sym->st_shndx == SHN_COMMON)
+ return -ENOEXEC;
+
+ if (sym->st_shndx >= pi->ehdr->e_shnum &&
+ sym->st_shndx != SHN_ABS)
+ return -ENOEXEC;
+
+ loc = pi->purgatory_buf;
+ loc += section->sh_offset;
+ loc += relas[i].r_offset;
+
+ val = sym->st_value;
+ if (sym->st_shndx != SHN_ABS)
+ val += pi->sechdrs[sym->st_shndx].sh_addr;
+ val += relas[i].r_addend;
+
+ addr = section->sh_addr + relas[i].r_offset;
+
+ switch (ELF64_R_TYPE(relas[i].r_info)) {
+ case R_390_8: /* Direct 8 bit. */
+ *(u8 *)loc = val;
+ break;
+ case R_390_12: /* Direct 12 bit. */
+ *(u16 *)loc &= 0xf000;
+ *(u16 *)loc |= val & 0xfff;
+ break;
+ case R_390_16: /* Direct 16 bit. */
+ *(u16 *)loc = val;
+ break;
+ case R_390_20: /* Direct 20 bit. */
+ *(u32 *)loc &= 0xf00000ff;
+ *(u32 *)loc |= (val & 0xfff) << 16; /* DL */
+ *(u32 *)loc |= (val & 0xff000) >> 4; /* DH */
+ break;
+ case R_390_32: /* Direct 32 bit. */
+ *(u32 *)loc = val;
+ break;
+ case R_390_64: /* Direct 64 bit. */
+ *(u64 *)loc = val;
+ break;
+ case R_390_PC16: /* PC relative 16 bit. */
+ *(u16 *)loc = (val - addr);
+ break;
+ case R_390_PC16DBL: /* PC relative 16 bit shifted by 1. */
+ *(u16 *)loc = (val - addr) >> 1;
+ break;
+ case R_390_PC32DBL: /* PC relative 32 bit shifted by 1. */
+ *(u32 *)loc = (val - addr) >> 1;
+ break;
+ case R_390_PC32: /* PC relative 32 bit. */
+ *(u32 *)loc = (val - addr);
+ break;
+ case R_390_PC64: /* PC relative 64 bit. */
+ *(u64 *)loc = (val - addr);
+ break;
+ default:
+ break;
+ }
+ }
+ return 0;
+}
+
+int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
+ unsigned long buf_len)
+{
+ /* A kernel must be at least large enough to contain head.S. During
+ * load memory in head.S will be accessed, e.g. to register the next
+ * command line. If the next kernel were smaller the current kernel
+ * will panic at load.
+ *
+ * 0x11000 = sizeof(head.S)
+ */
+ if (buf_len < 0x11000)
+ return -ENOEXEC;
+
+ return kexec_image_probe_default(image, buf, buf_len);
+}
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index 82df7d8..27110f3 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -9,13 +9,17 @@
#include <linux/linkage.h>
#include <asm/asm-offsets.h>
#include <asm/ftrace.h>
+#include <asm/nospec-insn.h>
#include <asm/ptrace.h>
#include <asm/export.h>
+ GEN_BR_THUNK %r1
+ GEN_BR_THUNK %r14
+
.section .kprobes.text, "ax"
ENTRY(ftrace_stub)
- br %r14
+ BR_EX %r14
#define STACK_FRAME_SIZE (STACK_FRAME_OVERHEAD + __PT_SIZE)
#define STACK_PTREGS (STACK_FRAME_OVERHEAD)
@@ -23,7 +27,7 @@
#define STACK_PTREGS_PSW (STACK_PTREGS + __PT_PSW)
ENTRY(_mcount)
- br %r14
+ BR_EX %r14
EXPORT_SYMBOL(_mcount)
@@ -53,7 +57,7 @@
#endif
lgr %r3,%r14
la %r5,STACK_PTREGS(%r15)
- basr %r14,%r1
+ BASR_EX %r14,%r1
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
# The j instruction gets runtime patched to a nop instruction.
# See ftrace_enable_ftrace_graph_caller.
@@ -68,7 +72,7 @@
#endif
lg %r1,(STACK_PTREGS_PSW+8)(%r15)
lmg %r2,%r15,(STACK_PTREGS_GPRS+2*8)(%r15)
- br %r1
+ BR_EX %r1
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -81,6 +85,6 @@
aghi %r15,STACK_FRAME_OVERHEAD
lgr %r14,%r2
lmg %r2,%r5,32(%r15)
- br %r14
+ BR_EX %r14
#endif
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index 5a83be9..0dc8ac8 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -465,11 +465,11 @@ int module_finalize(const Elf_Ehdr *hdr,
apply_alternatives(aseg, aseg + s->sh_size);
if (IS_ENABLED(CONFIG_EXPOLINE) &&
- (!strcmp(".nospec_call_table", secname)))
+ (!strncmp(".s390_indirect", secname, 14)))
nospec_revert(aseg, aseg + s->sh_size);
if (IS_ENABLED(CONFIG_EXPOLINE) &&
- (!strcmp(".nospec_return_table", secname)))
+ (!strncmp(".s390_return", secname, 12)))
nospec_revert(aseg, aseg + s->sh_size);
}
diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c
index f236ce8..18ae7b9 100644
--- a/arch/s390/kernel/nospec-branch.c
+++ b/arch/s390/kernel/nospec-branch.c
@@ -36,31 +36,13 @@ early_param("nospec", nospec_setup_early);
static int __init nospec_report(void)
{
if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
- pr_info("Spectre V2 mitigation: execute trampolines.\n");
+ pr_info("Spectre V2 mitigation: execute trampolines\n");
if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
- pr_info("Spectre V2 mitigation: limited branch prediction.\n");
+ pr_info("Spectre V2 mitigation: limited branch prediction\n");
return 0;
}
arch_initcall(nospec_report);
-#ifdef CONFIG_SYSFS
-ssize_t cpu_show_spectre_v1(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- return sprintf(buf, "Mitigation: __user pointer sanitization\n");
-}
-
-ssize_t cpu_show_spectre_v2(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
- return sprintf(buf, "Mitigation: execute trampolines\n");
- if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
- return sprintf(buf, "Mitigation: limited branch prediction.\n");
- return sprintf(buf, "Vulnerable\n");
-}
-#endif
-
#ifdef CONFIG_EXPOLINE
int nospec_disable = IS_ENABLED(CONFIG_EXPOLINE_OFF);
@@ -111,7 +93,6 @@ static void __init_or_module __nospec_revert(s32 *start, s32 *end)
s32 *epo;
/* Second part of the instruction replace is always a nop */
- memcpy(insnbuf + 2, (char[]) { 0x47, 0x00, 0x00, 0x00 }, 4);
for (epo = start; epo < end; epo++) {
instr = (u8 *) epo + *epo;
if (instr[0] == 0xc0 && (instr[1] & 0x0f) == 0x04)
@@ -132,18 +113,34 @@ static void __init_or_module __nospec_revert(s32 *start, s32 *end)
br = thunk + (*(int *)(thunk + 2)) * 2;
else
continue;
- if (br[0] != 0x07 || (br[1] & 0xf0) != 0xf0)
+ /* Check for unconditional branch 0x07f? or 0x47f???? */
+ if ((br[0] & 0xbf) != 0x07 || (br[1] & 0xf0) != 0xf0)
continue;
+
+ memcpy(insnbuf + 2, (char[]) { 0x47, 0x00, 0x07, 0x00 }, 4);
switch (type) {
case BRCL_EXPOLINE:
- /* brcl to thunk, replace with br + nop */
insnbuf[0] = br[0];
insnbuf[1] = (instr[1] & 0xf0) | (br[1] & 0x0f);
+ if (br[0] == 0x47) {
+ /* brcl to b, replace with bc + nopr */
+ insnbuf[2] = br[2];
+ insnbuf[3] = br[3];
+ } else {
+ /* brcl to br, replace with bcr + nop */
+ }
break;
case BRASL_EXPOLINE:
- /* brasl to thunk, replace with basr + nop */
- insnbuf[0] = 0x0d;
insnbuf[1] = (instr[1] & 0xf0) | (br[1] & 0x0f);
+ if (br[0] == 0x47) {
+ /* brasl to b, replace with bas + nopr */
+ insnbuf[0] = 0x4d;
+ insnbuf[2] = br[2];
+ insnbuf[3] = br[3];
+ } else {
+ /* brasl to br, replace with basr + nop */
+ insnbuf[0] = 0x0d;
+ }
break;
}
diff --git a/arch/s390/kernel/nospec-sysfs.c b/arch/s390/kernel/nospec-sysfs.c
new file mode 100644
index 0000000..8affad5
--- /dev/null
+++ b/arch/s390/kernel/nospec-sysfs.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/device.h>
+#include <linux/cpu.h>
+#include <asm/facility.h>
+#include <asm/nospec-branch.h>
+
+ssize_t cpu_show_spectre_v1(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+}
+
+ssize_t cpu_show_spectre_v2(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
+ return sprintf(buf, "Mitigation: execute trampolines\n");
+ if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
+ return sprintf(buf, "Mitigation: limited branch prediction\n");
+ return sprintf(buf, "Vulnerable\n");
+}
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
index c5bc3f2..feebb29 100644
--- a/arch/s390/kernel/perf_cpum_cf_events.c
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -123,7 +123,7 @@ CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES_IV, 0x00a1);
CPUMF_EVENT_ATTR(cf_zec12, TX_NC_TABORT, 0x00b1);
CPUMF_EVENT_ATTR(cf_zec12, TX_C_TABORT_NO_SPECIAL, 0x00b2);
CPUMF_EVENT_ATTR(cf_zec12, TX_C_TABORT_SPECIAL, 0x00b3);
-CPUMF_EVENT_ATTR(cf_z13, L1D_WRITES_RO_EXCL, 0x0080);
+CPUMF_EVENT_ATTR(cf_z13, L1D_RO_EXCL_WRITES, 0x0080);
CPUMF_EVENT_ATTR(cf_z13, DTLB1_WRITES, 0x0081);
CPUMF_EVENT_ATTR(cf_z13, DTLB1_MISSES, 0x0082);
CPUMF_EVENT_ATTR(cf_z13, DTLB1_HPAGE_WRITES, 0x0083);
@@ -179,7 +179,7 @@ CPUMF_EVENT_ATTR(cf_z13, TX_C_TABORT_NO_SPECIAL, 0x00db);
CPUMF_EVENT_ATTR(cf_z13, TX_C_TABORT_SPECIAL, 0x00dc);
CPUMF_EVENT_ATTR(cf_z13, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
CPUMF_EVENT_ATTR(cf_z13, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
-CPUMF_EVENT_ATTR(cf_z14, L1D_WRITES_RO_EXCL, 0x0080);
+CPUMF_EVENT_ATTR(cf_z14, L1D_RO_EXCL_WRITES, 0x0080);
CPUMF_EVENT_ATTR(cf_z14, DTLB2_WRITES, 0x0081);
CPUMF_EVENT_ATTR(cf_z14, DTLB2_MISSES, 0x0082);
CPUMF_EVENT_ATTR(cf_z14, DTLB2_HPAGE_WRITES, 0x0083);
@@ -371,7 +371,7 @@ static struct attribute *cpumcf_zec12_pmu_event_attr[] __initdata = {
};
static struct attribute *cpumcf_z13_pmu_event_attr[] __initdata = {
- CPUMF_EVENT_PTR(cf_z13, L1D_WRITES_RO_EXCL),
+ CPUMF_EVENT_PTR(cf_z13, L1D_RO_EXCL_WRITES),
CPUMF_EVENT_PTR(cf_z13, DTLB1_WRITES),
CPUMF_EVENT_PTR(cf_z13, DTLB1_MISSES),
CPUMF_EVENT_PTR(cf_z13, DTLB1_HPAGE_WRITES),
@@ -431,7 +431,7 @@ static struct attribute *cpumcf_z13_pmu_event_attr[] __initdata = {
};
static struct attribute *cpumcf_z14_pmu_event_attr[] __initdata = {
- CPUMF_EVENT_PTR(cf_z14, L1D_WRITES_RO_EXCL),
+ CPUMF_EVENT_PTR(cf_z14, L1D_RO_EXCL_WRITES),
CPUMF_EVENT_PTR(cf_z14, DTLB2_WRITES),
CPUMF_EVENT_PTR(cf_z14, DTLB2_MISSES),
CPUMF_EVENT_PTR(cf_z14, DTLB2_HPAGE_WRITES),
@@ -583,6 +583,7 @@ __init const struct attribute_group **cpumf_cf_event_group(void)
model = cpumcf_z13_pmu_event_attr;
break;
case 0x3906:
+ case 0x3907:
model = cpumcf_z14_pmu_event_attr;
break;
default:
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 1c9ddd7..0292d68 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -753,6 +753,10 @@ static int __hw_perf_event_init(struct perf_event *event)
*/
rate = 0;
if (attr->freq) {
+ if (!attr->sample_freq) {
+ err = -EINVAL;
+ goto out;
+ }
rate = freq_to_sample_rate(&si, attr->sample_freq);
rate = hw_limit_rate(&si, rate);
attr->freq = 0;
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 70576a2..6e758bb 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -29,6 +29,7 @@
#include <linux/random.h>
#include <linux/export.h>
#include <linux/init_task.h>
+#include <asm/cpu_mf.h>
#include <asm/io.h>
#include <asm/processor.h>
#include <asm/vtimer.h>
@@ -48,6 +49,15 @@ void flush_thread(void)
{
}
+void arch_setup_new_exec(void)
+{
+ if (S390_lowcore.current_pid != current->pid) {
+ S390_lowcore.current_pid = current->pid;
+ if (test_facility(40))
+ lpp(&S390_lowcore.lpp);
+ }
+}
+
void arch_release_task_struct(struct task_struct *tsk)
{
runtime_instr_release(tsk);
diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S
index 73cc375..7f14adf 100644
--- a/arch/s390/kernel/reipl.S
+++ b/arch/s390/kernel/reipl.S
@@ -7,8 +7,11 @@
#include <linux/linkage.h>
#include <asm/asm-offsets.h>
+#include <asm/nospec-insn.h>
#include <asm/sigp.h>
+ GEN_BR_THUNK %r9
+
#
# Issue "store status" for the current CPU to its prefix page
# and call passed function afterwards
@@ -67,9 +70,9 @@
st %r4,0(%r1)
st %r5,4(%r1)
stg %r2,8(%r1)
- lgr %r1,%r2
+ lgr %r9,%r2
lgr %r2,%r3
- br %r1
+ BR_EX %r9
.section .bss
.align 8
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index fc3b4aa..d82a9ec 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -821,6 +821,7 @@ static int __init setup_hwcaps(void)
strcpy(elf_platform, "z13");
break;
case 0x3906:
+ case 0x3907:
strcpy(elf_platform, "z14");
break;
}
diff --git a/arch/s390/kernel/swsusp.S b/arch/s390/kernel/swsusp.S
index e991871..a049a7b 100644
--- a/arch/s390/kernel/swsusp.S
+++ b/arch/s390/kernel/swsusp.S
@@ -13,6 +13,7 @@
#include <asm/ptrace.h>
#include <asm/thread_info.h>
#include <asm/asm-offsets.h>
+#include <asm/nospec-insn.h>
#include <asm/sigp.h>
/*
@@ -24,6 +25,8 @@
* (see below) in the resume process.
* This function runs with disabled interrupts.
*/
+ GEN_BR_THUNK %r14
+
.section .text
ENTRY(swsusp_arch_suspend)
stmg %r6,%r15,__SF_GPRS(%r15)
@@ -103,7 +106,7 @@
spx 0x318(%r1)
lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
lghi %r2,0
- br %r14
+ BR_EX %r14
/*
* Restore saved memory image to correct place and restore register context.
@@ -197,11 +200,10 @@
larl %r15,init_thread_union
ahi %r15,1<<(PAGE_SHIFT+THREAD_SIZE_ORDER)
larl %r2,.Lpanic_string
- larl %r3,sclp_early_printk
lghi %r1,0
sam31
sigp %r1,%r0,SIGP_SET_ARCHITECTURE
- basr %r14,%r3
+ brasl %r14,sclp_early_printk
larl %r3,.Ldisabled_wait_31
lpsw 0(%r3)
4:
@@ -267,7 +269,7 @@
/* Return 0 */
lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
lghi %r2,0
- br %r14
+ BR_EX %r14
.section .data..nosave,"aw",@progbits
.align 8
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index b38d484..8b210ea 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -388,3 +388,4 @@
378 common s390_guarded_storage sys_s390_guarded_storage compat_sys_s390_guarded_storage
379 common statx sys_statx compat_sys_statx
380 common s390_sthyi sys_s390_sthyi compat_sys_s390_sthyi
+381 common kexec_file_load sys_kexec_file_load compat_sys_kexec_file_load
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index fc7e04c2..54f5496 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -294,21 +294,9 @@ static int sysinfo_show(struct seq_file *m, void *v)
return 0;
}
-static int sysinfo_open(struct inode *inode, struct file *file)
-{
- return single_open(file, sysinfo_show, NULL);
-}
-
-static const struct file_operations sysinfo_fops = {
- .open = sysinfo_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __init sysinfo_create_proc(void)
{
- proc_create("sysinfo", 0444, NULL, &sysinfo_fops);
+ proc_create_single("sysinfo", 0444, NULL, sysinfo_show);
return 0;
}
device_initcall(sysinfo_create_proc);
@@ -386,18 +374,6 @@ static const struct seq_operations service_level_seq_ops = {
.show = service_level_show
};
-static int service_level_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &service_level_seq_ops);
-}
-
-static const struct file_operations service_level_ops = {
- .open = service_level_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release
-};
-
static void service_level_vm_print(struct seq_file *m,
struct service_level *slr)
{
@@ -420,7 +396,7 @@ static struct service_level service_level_vm = {
static __init int create_proc_service_level(void)
{
- proc_create("service_levels", 0, NULL, &service_level_ops);
+ proc_create_seq("service_levels", 0, NULL, &service_level_seq_ops);
if (MACHINE_IS_VM)
register_service_level(&service_level_vm);
return 0;
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index a5297a2..8003b38 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -44,14 +44,8 @@ int is_valid_bugaddr(unsigned long addr)
void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
{
- siginfo_t info;
-
if (user_mode(regs)) {
- info.si_signo = si_signo;
- info.si_errno = 0;
- info.si_code = si_code;
- info.si_addr = get_trap_ip(regs);
- force_sig_info(si_signo, &info, current);
+ force_sig_fault(si_signo, si_code, get_trap_ip(regs), current);
report_user_fault(regs, si_signo, 0);
} else {
const struct exception_table_entry *fixup;
@@ -80,18 +74,12 @@ NOKPROBE_SYMBOL(do_trap);
void do_per_trap(struct pt_regs *regs)
{
- siginfo_t info;
-
if (notify_die(DIE_SSTEP, "sstep", regs, 0, 0, SIGTRAP) == NOTIFY_STOP)
return;
if (!current->ptrace)
return;
- info.si_signo = SIGTRAP;
- info.si_errno = 0;
- info.si_code = TRAP_HWBKPT;
- info.si_addr =
- (void __force __user *) current->thread.per_event.address;
- force_sig_info(SIGTRAP, &info, current);
+ force_sig_fault(SIGTRAP, TRAP_HWBKPT,
+ (void __force __user *) current->thread.per_event.address, current);
}
NOKPROBE_SYMBOL(do_per_trap);
@@ -165,7 +153,6 @@ void translation_exception(struct pt_regs *regs)
void illegal_op(struct pt_regs *regs)
{
- siginfo_t info;
__u8 opcode[6];
__u16 __user *location;
int is_uprobe_insn = 0;
@@ -177,13 +164,9 @@ void illegal_op(struct pt_regs *regs)
if (get_user(*((__u16 *) opcode), (__u16 __user *) location))
return;
if (*((__u16 *) opcode) == S390_BREAKPOINT_U16) {
- if (current->ptrace) {
- info.si_signo = SIGTRAP;
- info.si_errno = 0;
- info.si_code = TRAP_BRKPT;
- info.si_addr = location;
- force_sig_info(SIGTRAP, &info, current);
- } else
+ if (current->ptrace)
+ force_sig_fault(SIGTRAP, TRAP_BRKPT, location, current);
+ else
signal = SIGILL;
#ifdef CONFIG_UPROBES
} else if (*((__u16 *) opcode) == UPROBE_SWBP_INSN) {
diff --git a/arch/s390/kernel/uprobes.c b/arch/s390/kernel/uprobes.c
index d9d1f51..5007fac 100644
--- a/arch/s390/kernel/uprobes.c
+++ b/arch/s390/kernel/uprobes.c
@@ -150,6 +150,15 @@ unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline,
return orig;
}
+bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx,
+ struct pt_regs *regs)
+{
+ if (ctx == RP_CHECK_CHAIN_CALL)
+ return user_stack_pointer(regs) <= ret->stack;
+ else
+ return user_stack_pointer(regs) < ret->stack;
+}
+
/* Instruction Emulation */
static void adjust_psw_addr(psw_t *psw, unsigned long len)
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 08d12cf..f0414f5 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -82,10 +82,10 @@
. = ALIGN(PAGE_SIZE);
.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
- VMLINUX_SYMBOL(_sinittext) = . ;
+ _sinittext = .;
INIT_TEXT
. = ALIGN(PAGE_SIZE);
- VMLINUX_SYMBOL(_einittext) = . ;
+ _einittext = .;
}
/*
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index ebfa044..a3bce0e 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -26,7 +26,6 @@
#include <asm/gmap.h>
#include <asm/io.h>
#include <asm/ptrace.h>
-#include <asm/compat.h>
#include <asm/sclp.h>
#include "gaccess.h"
#include "kvm-s390.h"
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 8961e39..969882b 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -578,7 +578,7 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
gpa = READ_ONCE(scb_o->itdba) & ~0xffUL;
if (gpa && (scb_s->ecb & ECB_TE)) {
- if (!(gpa & ~0x1fffU)) {
+ if (!(gpa & ~0x1fffUL)) {
rc = set_validity_icpt(scb_s, 0x0080U);
goto unpin;
}
diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile
index 9bfe080..57ab401 100644
--- a/arch/s390/lib/Makefile
+++ b/arch/s390/lib/Makefile
@@ -8,3 +8,6 @@
lib-$(CONFIG_SMP) += spinlock.o
lib-$(CONFIG_KPROBES) += probes.o
lib-$(CONFIG_UPROBES) += probes.o
+
+chkbss := mem.o
+include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S
index 495c9c4..2311f15 100644
--- a/arch/s390/lib/mem.S
+++ b/arch/s390/lib/mem.S
@@ -7,6 +7,9 @@
#include <linux/linkage.h>
#include <asm/export.h>
+#include <asm/nospec-insn.h>
+
+ GEN_BR_THUNK %r14
/*
* void *memmove(void *dest, const void *src, size_t n)
@@ -33,14 +36,14 @@
.Lmemmove_forward_remainder:
larl %r5,.Lmemmove_mvc
ex %r4,0(%r5)
- br %r14
+ BR_EX %r14
.Lmemmove_reverse:
ic %r0,0(%r4,%r3)
stc %r0,0(%r4,%r1)
brctg %r4,.Lmemmove_reverse
ic %r0,0(%r4,%r3)
stc %r0,0(%r4,%r1)
- br %r14
+ BR_EX %r14
.Lmemmove_mvc:
mvc 0(1,%r1),0(%r3)
EXPORT_SYMBOL(memmove)
@@ -77,7 +80,7 @@
.Lmemset_clear_remainder:
larl %r3,.Lmemset_xc
ex %r4,0(%r3)
- br %r14
+ BR_EX %r14
.Lmemset_fill:
cghi %r4,1
lgr %r1,%r2
@@ -95,10 +98,10 @@
stc %r3,0(%r1)
larl %r5,.Lmemset_mvc
ex %r4,0(%r5)
- br %r14
+ BR_EX %r14
.Lmemset_fill_exit:
stc %r3,0(%r1)
- br %r14
+ BR_EX %r14
.Lmemset_xc:
xc 0(1,%r1),0(%r1)
.Lmemset_mvc:
@@ -121,7 +124,7 @@
.Lmemcpy_remainder:
larl %r5,.Lmemcpy_mvc
ex %r4,0(%r5)
- br %r14
+ BR_EX %r14
.Lmemcpy_loop:
mvc 0(256,%r1),0(%r3)
la %r1,256(%r1)
@@ -159,10 +162,10 @@
\insn %r3,0(%r1)
larl %r5,.L__memset_mvc\bits
ex %r4,0(%r5)
- br %r14
+ BR_EX %r14
.L__memset_exit\bits:
\insn %r3,0(%r2)
- br %r14
+ BR_EX %r14
.L__memset_mvc\bits:
mvc \bytes(1,%r1),0(%r1)
.endm
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 93faeca..e074480 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -265,14 +265,10 @@ void report_user_fault(struct pt_regs *regs, long signr, int is_mm_fault)
*/
static noinline void do_sigsegv(struct pt_regs *regs, int si_code)
{
- struct siginfo si;
-
report_user_fault(regs, SIGSEGV, 1);
- si.si_signo = SIGSEGV;
- si.si_errno = 0;
- si.si_code = si_code;
- si.si_addr = (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK);
- force_sig_info(SIGSEGV, &si, current);
+ force_sig_fault(SIGSEGV, si_code,
+ (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK),
+ current);
}
static noinline void do_no_context(struct pt_regs *regs)
@@ -316,18 +312,13 @@ static noinline void do_low_address(struct pt_regs *regs)
static noinline void do_sigbus(struct pt_regs *regs)
{
- struct task_struct *tsk = current;
- struct siginfo si;
-
/*
* Send a sigbus, regardless of whether we were in kernel
* or user mode.
*/
- si.si_signo = SIGBUS;
- si.si_errno = 0;
- si.si_code = BUS_ADRERR;
- si.si_addr = (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK);
- force_sig_info(SIGBUS, &si, tsk);
+ force_sig_fault(SIGBUS, BUS_ADRERR,
+ (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK),
+ current);
}
static noinline int signal_return(struct pt_regs *regs)
diff --git a/arch/s390/net/Makefile b/arch/s390/net/Makefile
index e0d5f24..e2b85ff 100644
--- a/arch/s390/net/Makefile
+++ b/arch/s390/net/Makefile
@@ -3,3 +3,4 @@
# Arch-specific network modules
#
obj-$(CONFIG_BPF_JIT) += bpf_jit.o bpf_jit_comp.o
+obj-$(CONFIG_HAVE_PNETID) += pnet.o
diff --git a/arch/s390/net/bpf_jit.S b/arch/s390/net/bpf_jit.S
index 25bb464..9f79486 100644
--- a/arch/s390/net/bpf_jit.S
+++ b/arch/s390/net/bpf_jit.S
@@ -9,6 +9,7 @@
*/
#include <linux/linkage.h>
+#include <asm/nospec-insn.h>
#include "bpf_jit.h"
/*
@@ -54,7 +55,7 @@
clg %r3,STK_OFF_HLEN(%r15); /* Offset + SIZE > hlen? */ \
jh sk_load_##NAME##_slow; \
LOAD %r14,-SIZE(%r3,%r12); /* Get data from skb */ \
- b OFF_OK(%r6); /* Return */ \
+ B_EX OFF_OK,%r6; /* Return */ \
\
sk_load_##NAME##_slow:; \
lgr %r2,%r7; /* Arg1 = skb pointer */ \
@@ -64,11 +65,14 @@
brasl %r14,skb_copy_bits; /* Get data from skb */ \
LOAD %r14,STK_OFF_TMP(%r15); /* Load from temp bufffer */ \
ltgr %r2,%r2; /* Set cc to (%r2 != 0) */ \
- br %r6; /* Return */
+ BR_EX %r6; /* Return */
sk_load_common(word, 4, llgf) /* r14 = *(u32 *) (skb->data+offset) */
sk_load_common(half, 2, llgh) /* r14 = *(u16 *) (skb->data+offset) */
+ GEN_BR_THUNK %r6
+ GEN_B_THUNK OFF_OK,%r6
+
/*
* Load 1 byte from SKB (optimized version)
*/
@@ -80,7 +84,7 @@
clg %r3,STK_OFF_HLEN(%r15) # Offset >= hlen?
jnl sk_load_byte_slow
llgc %r14,0(%r3,%r12) # Get byte from skb
- b OFF_OK(%r6) # Return OK
+ B_EX OFF_OK,%r6 # Return OK
sk_load_byte_slow:
lgr %r2,%r7 # Arg1 = skb pointer
@@ -90,7 +94,7 @@
brasl %r14,skb_copy_bits # Get data from skb
llgc %r14,STK_OFF_TMP(%r15) # Load result from temp buffer
ltgr %r2,%r2 # Set cc to (%r2 != 0)
- br %r6 # Return cc
+ BR_EX %r6 # Return cc
#define sk_negative_common(NAME, SIZE, LOAD) \
sk_load_##NAME##_slow_neg:; \
@@ -104,7 +108,7 @@
jz bpf_error; \
LOAD %r14,0(%r2); /* Get data from pointer */ \
xr %r3,%r3; /* Set cc to zero */ \
- br %r6; /* Return cc */
+ BR_EX %r6; /* Return cc */
sk_negative_common(word, 4, llgf)
sk_negative_common(half, 2, llgh)
@@ -113,4 +117,4 @@
bpf_error:
# force a return 0 from jit handler
ltgr %r15,%r15 # Set condition code
- br %r6
+ BR_EX %r6
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 78a19c9..dd2bcf0 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -25,6 +25,8 @@
#include <linux/bpf.h>
#include <asm/cacheflush.h>
#include <asm/dis.h>
+#include <asm/facility.h>
+#include <asm/nospec-branch.h>
#include <asm/set_memory.h>
#include "bpf_jit.h"
@@ -41,6 +43,8 @@ struct bpf_jit {
int base_ip; /* Base address for literal pool */
int ret0_ip; /* Address of return 0 */
int exit_ip; /* Address of exit */
+ int r1_thunk_ip; /* Address of expoline thunk for 'br %r1' */
+ int r14_thunk_ip; /* Address of expoline thunk for 'br %r14' */
int tail_call_start; /* Tail call start offset */
int labels[1]; /* Labels for local jumps */
};
@@ -250,6 +254,19 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
REG_SET_SEEN(b2); \
})
+#define EMIT6_PCREL_RILB(op, b, target) \
+({ \
+ int rel = (target - jit->prg) / 2; \
+ _EMIT6(op | reg_high(b) << 16 | rel >> 16, rel & 0xffff); \
+ REG_SET_SEEN(b); \
+})
+
+#define EMIT6_PCREL_RIL(op, target) \
+({ \
+ int rel = (target - jit->prg) / 2; \
+ _EMIT6(op | rel >> 16, rel & 0xffff); \
+})
+
#define _EMIT6_IMM(op, imm) \
({ \
unsigned int __imm = (imm); \
@@ -469,8 +486,45 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
EMIT4(0xb9040000, REG_2, BPF_REG_0);
/* Restore registers */
save_restore_regs(jit, REGS_RESTORE, stack_depth);
+ if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) {
+ jit->r14_thunk_ip = jit->prg;
+ /* Generate __s390_indirect_jump_r14 thunk */
+ if (test_facility(35)) {
+ /* exrl %r0,.+10 */
+ EMIT6_PCREL_RIL(0xc6000000, jit->prg + 10);
+ } else {
+ /* larl %r1,.+14 */
+ EMIT6_PCREL_RILB(0xc0000000, REG_1, jit->prg + 14);
+ /* ex 0,0(%r1) */
+ EMIT4_DISP(0x44000000, REG_0, REG_1, 0);
+ }
+ /* j . */
+ EMIT4_PCREL(0xa7f40000, 0);
+ }
/* br %r14 */
_EMIT2(0x07fe);
+
+ if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable &&
+ (jit->seen & SEEN_FUNC)) {
+ jit->r1_thunk_ip = jit->prg;
+ /* Generate __s390_indirect_jump_r1 thunk */
+ if (test_facility(35)) {
+ /* exrl %r0,.+10 */
+ EMIT6_PCREL_RIL(0xc6000000, jit->prg + 10);
+ /* j . */
+ EMIT4_PCREL(0xa7f40000, 0);
+ /* br %r1 */
+ _EMIT2(0x07f1);
+ } else {
+ /* larl %r1,.+14 */
+ EMIT6_PCREL_RILB(0xc0000000, REG_1, jit->prg + 14);
+ /* ex 0,S390_lowcore.br_r1_tampoline */
+ EMIT4_DISP(0x44000000, REG_0, REG_0,
+ offsetof(struct lowcore, br_r1_trampoline));
+ /* j . */
+ EMIT4_PCREL(0xa7f40000, 0);
+ }
+ }
}
/*
@@ -966,8 +1020,13 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
/* lg %w1,<d(imm)>(%l) */
EMIT6_DISP_LH(0xe3000000, 0x0004, REG_W1, REG_0, REG_L,
EMIT_CONST_U64(func));
- /* basr %r14,%w1 */
- EMIT2(0x0d00, REG_14, REG_W1);
+ if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) {
+ /* brasl %r14,__s390_indirect_jump_r1 */
+ EMIT6_PCREL_RILB(0xc0050000, REG_14, jit->r1_thunk_ip);
+ } else {
+ /* basr %r14,%w1 */
+ EMIT2(0x0d00, REG_14, REG_W1);
+ }
/* lgr %b0,%r2: load return value into %b0 */
EMIT4(0xb9040000, BPF_REG_0, REG_2);
if ((jit->seen & SEEN_SKB) &&
diff --git a/arch/s390/net/pnet.c b/arch/s390/net/pnet.c
new file mode 100644
index 0000000..e22f1b1
--- /dev/null
+++ b/arch/s390/net/pnet.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * IBM System z PNET ID Support
+ *
+ * Copyright IBM Corp. 2018
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/types.h>
+#include <asm/ccwgroup.h>
+#include <asm/ccwdev.h>
+#include <asm/pnet.h>
+
+/*
+ * Get the PNETIDs from a device.
+ * s390 hardware supports the definition of a so-called Physical Network
+ * Identifier (short PNETID) per network device port. These PNETIDs can be
+ * used to identify network devices that are attached to the same physical
+ * network (broadcast domain).
+ *
+ * The device can be
+ * - a ccwgroup device with all bundled subchannels having the same PNETID
+ * - a PCI attached network device
+ *
+ * Returns:
+ * 0: PNETIDs extracted from device.
+ * -ENOMEM: No memory to extract utility string.
+ * -EOPNOTSUPP: Device type without utility string support
+ */
+static int pnet_ids_by_device(struct device *dev, u8 *pnetids)
+{
+ memset(pnetids, 0, PNETIDS_LEN);
+ if (dev_is_ccwgroup(dev)) {
+ struct ccwgroup_device *gdev = to_ccwgroupdev(dev);
+ u8 *util_str;
+
+ util_str = ccw_device_get_util_str(gdev->cdev[0], 0);
+ if (!util_str)
+ return -ENOMEM;
+ memcpy(pnetids, util_str, PNETIDS_LEN);
+ kfree(util_str);
+ return 0;
+ }
+ if (dev_is_pci(dev)) {
+ struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
+
+ memcpy(pnetids, zdev->util_str, sizeof(zdev->util_str));
+ return 0;
+ }
+ return -EOPNOTSUPP;
+}
+
+/*
+ * Extract the pnetid for a device port.
+ *
+ * Return 0 if a pnetid is found and -ENOENT otherwise.
+ */
+int pnet_id_by_dev_port(struct device *dev, unsigned short port, u8 *pnetid)
+{
+ u8 pnetids[MAX_PNETID_PORTS][MAX_PNETID_LEN];
+ static const u8 zero[MAX_PNETID_LEN] = { 0 };
+ int rc = 0;
+
+ if (!dev || port >= MAX_PNETID_PORTS)
+ return -ENOENT;
+
+ if (!pnet_ids_by_device(dev, (u8 *)pnetids) &&
+ memcmp(pnetids[port], zero, MAX_PNETID_LEN))
+ memcpy(pnetid, pnetids[port], MAX_PNETID_LEN);
+ else
+ rc = -ENOENT;
+
+ return rc;
+}
+EXPORT_SYMBOL_GPL(pnet_id_by_dev_port);
+
+MODULE_DESCRIPTION("pnetid determination from utility strings");
+MODULE_LICENSE("GPL");
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index 93cd0f1..19b2d2a 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -19,7 +19,6 @@
#include <linux/uaccess.h>
#include <asm/pci_debug.h>
#include <asm/pci_clp.h>
-#include <asm/compat.h>
#include <asm/clp.h>
#include <uapi/asm/clp.h>
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 2d15d84..d387a0f 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -668,15 +668,6 @@ void zpci_dma_exit(void)
kmem_cache_destroy(dma_region_table_cache);
}
-#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-
-static int __init dma_debug_do_init(void)
-{
- dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
- return 0;
-}
-fs_initcall(dma_debug_do_init);
-
const struct dma_map_ops s390_pci_dma_ops = {
.alloc = s390_dma_alloc,
.free = s390_dma_free,
@@ -685,8 +676,6 @@ const struct dma_map_ops s390_pci_dma_ops = {
.map_page = s390_dma_map_pages,
.unmap_page = s390_dma_unmap_pages,
.mapping_error = s390_mapping_error,
- /* if we support direct DMA this must be conditional */
- .is_phys = 0,
/* dma_supported is unconditionally true without a callback */
};
EXPORT_SYMBOL_GPL(s390_pci_dma_ops);
diff --git a/arch/s390/purgatory/.gitignore b/arch/s390/purgatory/.gitignore
new file mode 100644
index 0000000..e9e66f1
--- /dev/null
+++ b/arch/s390/purgatory/.gitignore
@@ -0,0 +1,2 @@
+kexec-purgatory.c
+purgatory.ro
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
new file mode 100644
index 0000000..1ace023
--- /dev/null
+++ b/arch/s390/purgatory/Makefile
@@ -0,0 +1,37 @@
+# SPDX-License-Identifier: GPL-2.0
+
+OBJECT_FILES_NON_STANDARD := y
+
+purgatory-y := head.o purgatory.o string.o sha256.o mem.o
+
+targets += $(purgatory-y) purgatory.ro kexec-purgatory.c
+PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
+
+$(obj)/sha256.o: $(srctree)/lib/sha256.c
+ $(call if_changed_rule,cc_o_c)
+
+$(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S
+ $(call if_changed_rule,as_o_S)
+
+$(obj)/string.o: $(srctree)/arch/s390/lib/string.c
+ $(call if_changed_rule,cc_o_c)
+
+LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib
+LDFLAGS_purgatory.ro += -z nodefaultlib
+KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes
+KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
+KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
+KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float
+KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
+
+$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
+ $(call if_changed,ld)
+
+CMD_BIN2C = $(objtree)/scripts/basic/bin2c
+quiet_cmd_bin2c = BIN2C $@
+ cmd_bin2c = $(CMD_BIN2C) kexec_purgatory < $< > $@
+
+$(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE
+ $(call if_changed,bin2c)
+
+obj-$(CONFIG_ARCH_HAS_KEXEC_PURGATORY) += kexec-purgatory.o
diff --git a/arch/s390/purgatory/head.S b/arch/s390/purgatory/head.S
new file mode 100644
index 0000000..660c96a
--- /dev/null
+++ b/arch/s390/purgatory/head.S
@@ -0,0 +1,279 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Purgatory setup code
+ *
+ * Copyright IBM Corp. 2018
+ *
+ * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com>
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/page.h>
+#include <asm/sigp.h>
+
+/* The purgatory is the code running between two kernels. It's main purpose
+ * is to verify that the next kernel was not corrupted after load and to
+ * start it.
+ *
+ * If the next kernel is a crash kernel there are some peculiarities to
+ * consider:
+ *
+ * First the purgatory is called twice. Once only to verify the
+ * sha digest. So if the crash kernel got corrupted the old kernel can try
+ * to trigger a stand-alone dumper. And once to actually load the crash kernel.
+ *
+ * Second the purgatory also has to swap the crash memory region with its
+ * destination at address 0. As the purgatory is part of crash memory this
+ * requires some finesse. The tactic here is that the purgatory first copies
+ * itself to the end of the destination and then swaps the rest of the
+ * memory running from there.
+ */
+
+#define bufsz purgatory_end-stack
+
+.macro MEMCPY dst,src,len
+ lgr %r0,\dst
+ lgr %r1,\len
+ lgr %r2,\src
+ lgr %r3,\len
+
+20: mvcle %r0,%r2,0
+ jo 20b
+.endm
+
+.macro MEMSWAP dst,src,buf,len
+10: cghi \len,bufsz
+ jh 11f
+ lgr %r4,\len
+ j 12f
+11: lghi %r4,bufsz
+
+12: MEMCPY \buf,\dst,%r4
+ MEMCPY \dst,\src,%r4
+ MEMCPY \src,\buf,%r4
+
+ agr \dst,%r4
+ agr \src,%r4
+ sgr \len,%r4
+
+ cghi \len,0
+ jh 10b
+.endm
+
+.macro START_NEXT_KERNEL base
+ lg %r4,kernel_entry-\base(%r13)
+ lg %r5,load_psw_mask-\base(%r13)
+ ogr %r4,%r5
+ stg %r4,0(%r0)
+
+ xgr %r0,%r0
+ diag %r0,%r0,0x308
+.endm
+
+.text
+.align PAGE_SIZE
+ENTRY(purgatory_start)
+ /* The purgatory might be called after a diag308 so better set
+ * architecture and addressing mode.
+ */
+ lhi %r1,1
+ sigp %r1,%r0,SIGP_SET_ARCHITECTURE
+ sam64
+
+ larl %r5,gprregs
+ stmg %r6,%r15,0(%r5)
+
+ basr %r13,0
+.base_crash:
+
+ /* Setup stack */
+ larl %r15,purgatory_end
+ aghi %r15,-160
+
+ /* If the next kernel is KEXEC_TYPE_CRASH the purgatory is called
+ * directly with a flag passed in %r2 whether the purgatory shall do
+ * checksum verification only (%r2 = 0 -> verification only).
+ *
+ * Check now and preserve over C function call by storing in
+ * %r10 whith
+ * 1 -> checksum verification only
+ * 0 -> load new kernel
+ */
+ lghi %r10,0
+ lg %r11,kernel_type-.base_crash(%r13)
+ cghi %r11,1 /* KEXEC_TYPE_CRASH */
+ jne .do_checksum_verification
+ cghi %r2,0 /* checksum verification only */
+ jne .do_checksum_verification
+ lghi %r10,1
+
+.do_checksum_verification:
+ brasl %r14,verify_sha256_digest
+
+ cghi %r10,1 /* checksum verification only */
+ je .return_old_kernel
+ cghi %r2,0 /* checksum match */
+ jne .disabled_wait
+
+ /* If the next kernel is a crash kernel the purgatory has to swap
+ * the mem regions first.
+ */
+ cghi %r11,1 /* KEXEC_TYPE_CRASH */
+ je .start_crash_kernel
+
+ /* start normal kernel */
+ START_NEXT_KERNEL .base_crash
+
+.return_old_kernel:
+ lmg %r6,%r15,gprregs-.base_crash(%r13)
+ br %r14
+
+.disabled_wait:
+ lpswe disabled_wait_psw-.base_crash(%r13)
+
+.start_crash_kernel:
+ /* Location of purgatory_start in crash memory */
+ lgr %r8,%r13
+ aghi %r8,-(.base_crash-purgatory_start)
+
+ /* Destination for this code i.e. end of memory to be swapped. */
+ lg %r9,crash_size-.base_crash(%r13)
+ aghi %r9,-(purgatory_end-purgatory_start)
+
+ /* Destination in crash memory, i.e. same as r9 but in crash memory. */
+ lg %r10,crash_start-.base_crash(%r13)
+ agr %r10,%r9
+
+ /* Buffer location (in crash memory) and size. As the purgatory is
+ * behind the point of no return it can re-use the stack as buffer.
+ */
+ lghi %r11,bufsz
+ larl %r12,stack
+
+ MEMCPY %r12,%r9,%r11 /* dst -> (crash) buf */
+ MEMCPY %r9,%r8,%r11 /* self -> dst */
+
+ /* Jump to new location. */
+ lgr %r7,%r9
+ aghi %r7,.jump_to_dst-purgatory_start
+ br %r7
+
+.jump_to_dst:
+ basr %r13,0
+.base_dst:
+
+ /* clear buffer */
+ MEMCPY %r12,%r10,%r11 /* (crash) buf -> (crash) dst */
+
+ /* Load new buffer location after jump */
+ larl %r7,stack
+ aghi %r10,stack-purgatory_start
+ MEMCPY %r10,%r7,%r11 /* (new) buf -> (crash) buf */
+
+ /* Now the code is set up to run from its designated location. Start
+ * swapping the rest of crash memory now.
+ *
+ * The registers will be used as follow:
+ *
+ * %r0-%r4 reserved for macros defined above
+ * %r5-%r6 tmp registers
+ * %r7 pointer to current struct sha region
+ * %r8 index to iterate over all sha regions
+ * %r9 pointer in crash memory
+ * %r10 pointer in old kernel
+ * %r11 total size (still) to be moved
+ * %r12 pointer to buffer
+ */
+ lgr %r12,%r7
+ lgr %r11,%r9
+ lghi %r10,0
+ lg %r9,crash_start-.base_dst(%r13)
+ lghi %r8,16 /* KEXEC_SEGMENTS_MAX */
+ larl %r7,purgatory_sha_regions
+
+ j .loop_first
+
+ /* Loop over all purgatory_sha_regions. */
+.loop_next:
+ aghi %r8,-1
+ cghi %r8,0
+ je .loop_out
+
+ aghi %r7,__KEXEC_SHA_REGION_SIZE
+
+.loop_first:
+ lg %r5,__KEXEC_SHA_REGION_START(%r7)
+ cghi %r5,0
+ je .loop_next
+
+ /* Copy [end last sha region, start current sha region) */
+ /* Note: kexec_sha_region->start points in crash memory */
+ sgr %r5,%r9
+ MEMCPY %r9,%r10,%r5
+
+ agr %r9,%r5
+ agr %r10,%r5
+ sgr %r11,%r5
+
+ /* Swap sha region */
+ lg %r6,__KEXEC_SHA_REGION_LEN(%r7)
+ MEMSWAP %r9,%r10,%r12,%r6
+ sg %r11,__KEXEC_SHA_REGION_LEN(%r7)
+ j .loop_next
+
+.loop_out:
+ /* Copy rest of crash memory */
+ MEMCPY %r9,%r10,%r11
+
+ /* start crash kernel */
+ START_NEXT_KERNEL .base_dst
+
+
+load_psw_mask:
+ .long 0x00080000,0x80000000
+
+ .align 8
+disabled_wait_psw:
+ .quad 0x0002000180000000
+ .quad 0x0000000000000000 + .do_checksum_verification
+
+gprregs:
+ .rept 10
+ .quad 0
+ .endr
+
+purgatory_sha256_digest:
+ .global purgatory_sha256_digest
+ .rept 32 /* SHA256_DIGEST_SIZE */
+ .byte 0
+ .endr
+
+purgatory_sha_regions:
+ .global purgatory_sha_regions
+ .rept 16 * __KEXEC_SHA_REGION_SIZE /* KEXEC_SEGMENTS_MAX */
+ .byte 0
+ .endr
+
+kernel_entry:
+ .global kernel_entry
+ .quad 0
+
+kernel_type:
+ .global kernel_type
+ .quad 0
+
+crash_start:
+ .global crash_start
+ .quad 0
+
+crash_size:
+ .global crash_size
+ .quad 0
+
+ .align PAGE_SIZE
+stack:
+ /* The buffer to move this code must be as big as the code. */
+ .skip stack-purgatory_start
+ .align PAGE_SIZE
+purgatory_end:
diff --git a/arch/s390/purgatory/purgatory.c b/arch/s390/purgatory/purgatory.c
new file mode 100644
index 0000000..4e2beb3
--- /dev/null
+++ b/arch/s390/purgatory/purgatory.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Purgatory code running between two kernels.
+ *
+ * Copyright IBM Corp. 2018
+ *
+ * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com>
+ */
+
+#include <linux/kexec.h>
+#include <linux/sha256.h>
+#include <linux/string.h>
+#include <asm/purgatory.h>
+
+struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX];
+u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE];
+
+u64 kernel_entry;
+u64 kernel_type;
+
+u64 crash_start;
+u64 crash_size;
+
+int verify_sha256_digest(void)
+{
+ struct kexec_sha_region *ptr, *end;
+ u8 digest[SHA256_DIGEST_SIZE];
+ struct sha256_state sctx;
+
+ sha256_init(&sctx);
+ end = purgatory_sha_regions + ARRAY_SIZE(purgatory_sha_regions);
+
+ for (ptr = purgatory_sha_regions; ptr < end; ptr++)
+ sha256_update(&sctx, (uint8_t *)(ptr->start), ptr->len);
+
+ sha256_final(&sctx, digest);
+
+ if (memcmp(digest, purgatory_sha256_digest, sizeof(digest)))
+ return 1;
+
+ return 0;
+}
diff --git a/arch/s390/scripts/Makefile.chkbss b/arch/s390/scripts/Makefile.chkbss
new file mode 100644
index 0000000..d92f2d9
--- /dev/null
+++ b/arch/s390/scripts/Makefile.chkbss
@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0
+
+quiet_cmd_chkbss = CHKBSS $<
+define cmd_chkbss
+ if ! $(OBJDUMP) -j .bss -w -h $< | awk 'END { if ($$3) exit 1 }'; then \
+ echo "error: $< .bss section is not empty" >&2; exit 1; \
+ fi; \
+ touch $@;
+endef
+
+$(obj)/built-in.a: $(patsubst %, $(obj)/%.chkbss, $(chkbss))
+
+%.o.chkbss: %.o
+ $(call cmd,chkbss)
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 97fe293..a97538b 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -9,11 +9,11 @@
select HAVE_IDE if HAS_IOPORT_MAP
select HAVE_MEMBLOCK
select HAVE_MEMBLOCK_NODE_MAP
+ select NO_BOOTMEM
select ARCH_DISCARD_MEMBLOCK
select HAVE_OPROFILE
select HAVE_GENERIC_DMA_COHERENT
select HAVE_ARCH_TRACEHOOK
- select HAVE_DMA_API_DEBUG
select HAVE_PERF_EVENTS
select HAVE_DEBUG_BUGVERBOSE
select ARCH_HAVE_CUSTOM_GPIO_H
@@ -50,6 +50,9 @@
select HAVE_ARCH_AUDITSYSCALL
select HAVE_FUTEX_CMPXCHG if FUTEX
select HAVE_NMI
+ select NEED_DMA_MAP_STATE
+ select NEED_SG_DMA_LENGTH
+
help
The SuperH is a RISC processor targeted for use in embedded systems
and consumer electronics; it was also used in the Sega Dreamcast
@@ -160,12 +163,6 @@
config DMA_NONCOHERENT
def_bool !DMA_COHERENT
-config NEED_DMA_MAP_STATE
- def_bool DMA_NONCOHERENT
-
-config NEED_SG_DMA_LENGTH
- def_bool y
-
config PGTABLE_LEVELS
default 3 if X2TLB
default 2
diff --git a/arch/sh/drivers/dma/dma-api.c b/arch/sh/drivers/dma/dma-api.c
index c0eec08..b05be59 100644
--- a/arch/sh/drivers/dma/dma-api.c
+++ b/arch/sh/drivers/dma/dma-api.c
@@ -339,18 +339,6 @@ static int dma_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int dma_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, dma_proc_show, NULL);
-}
-
-static const struct file_operations dma_proc_fops = {
- .open = dma_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
int register_dmac(struct dma_info *info)
{
unsigned int total_channels, i;
@@ -423,7 +411,7 @@ EXPORT_SYMBOL(unregister_dmac);
static int __init dma_api_init(void)
{
printk(KERN_NOTICE "DMA: Registering DMA API.\n");
- return proc_create("dma", 0, NULL, &dma_proc_fops) ? 0 : -ENOMEM;
+ return proc_create_single("dma", 0, NULL, dma_proc_show) ? 0 : -ENOMEM;
}
subsys_initcall(dma_api_init);
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 1efcce7..46dd82a 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -1,3 +1,4 @@
+generic-y += compat.h
generic-y += current.h
generic-y += delay.h
generic-y += div64.h
diff --git a/arch/sh/include/asm/pci.h b/arch/sh/include/asm/pci.h
index 0033f0d..10a36b1 100644
--- a/arch/sh/include/asm/pci.h
+++ b/arch/sh/include/asm/pci.h
@@ -71,12 +71,6 @@ extern unsigned long PCIBIOS_MIN_IO, PCIBIOS_MIN_MEM;
* SuperH has everything mapped statically like x86.
*/
-/* The PCI address space does equal the physical memory
- * address space. The networking and block device layers use
- * this boolean for bounce buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
-
#ifdef CONFIG_PCI
/*
* None of the SH PCI controllers support MWI, it is always treated as a
diff --git a/arch/sh/kernel/cpu/sh2/probe.c b/arch/sh/kernel/cpu/sh2/probe.c
index 4205f6d..a5bd036 100644
--- a/arch/sh/kernel/cpu/sh2/probe.c
+++ b/arch/sh/kernel/cpu/sh2/probe.c
@@ -43,7 +43,11 @@ void __ref cpu_probe(void)
#endif
#if defined(CONFIG_CPU_J2)
+#if defined(CONFIG_SMP)
unsigned cpu = hard_smp_processor_id();
+#else
+ unsigned cpu = 0;
+#endif
if (cpu == 0) of_scan_flat_dt(scan_cache, NULL);
if (j2_ccr_base) __raw_writel(0x80000303, j2_ccr_base + 4*cpu);
if (cpu != 0) return;
diff --git a/arch/sh/kernel/dma-nommu.c b/arch/sh/kernel/dma-nommu.c
index 178457d..3e3a32f 100644
--- a/arch/sh/kernel/dma-nommu.c
+++ b/arch/sh/kernel/dma-nommu.c
@@ -78,7 +78,6 @@ const struct dma_map_ops nommu_dma_ops = {
.sync_single_for_device = nommu_sync_single_for_device,
.sync_sg_for_device = nommu_sync_sg_for_device,
#endif
- .is_phys = 1,
};
void __init no_iommu_init(void)
diff --git a/arch/sh/kernel/hw_breakpoint.c b/arch/sh/kernel/hw_breakpoint.c
index afe9657..8648ed0 100644
--- a/arch/sh/kernel/hw_breakpoint.c
+++ b/arch/sh/kernel/hw_breakpoint.c
@@ -347,13 +347,8 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
/* Deliver the signal to userspace */
if (!arch_check_bp_in_kernelspace(bp)) {
- siginfo_t info;
-
- info.si_signo = args->signr;
- info.si_errno = notifier_to_errno(rc);
- info.si_code = TRAP_HWBKPT;
-
- force_sig_info(args->signr, &info, current);
+ force_sig_fault(SIGTRAP, TRAP_HWBKPT,
+ (void __user *)NULL, current);
}
rcu_read_unlock();
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index 245dbeb..5717c7c 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -44,7 +44,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
seq_printf(p, "%*s: ", prec, "NMI");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", irq_stat[j].__nmi_count);
+ seq_printf(p, "%10u ", nmi_count(j));
seq_printf(p, " Non-maskable interrupts\n");
seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index d34e998..c286cf5 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -11,7 +11,6 @@
#include <linux/ioport.h>
#include <linux/init.h>
#include <linux/initrd.h>
-#include <linux/bootmem.h>
#include <linux/console.h>
#include <linux/root_dev.h>
#include <linux/utsname.h>
diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c
index b3770bb..60709ad 100644
--- a/arch/sh/kernel/traps_32.c
+++ b/arch/sh/kernel/traps_32.c
@@ -477,7 +477,6 @@ asmlinkage void do_address_error(struct pt_regs *regs,
{
unsigned long error_code = 0;
mm_segment_t oldfs;
- siginfo_t info;
insn_size_t instruction;
int tmp;
@@ -537,11 +536,7 @@ asmlinkage void do_address_error(struct pt_regs *regs,
"access (PC %lx PR %lx)\n", current->comm, regs->pc,
regs->pr);
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = si_code;
- info.si_addr = (void __user *)address;
- force_sig_info(SIGBUS, &info, current);
+ force_sig_fault(SIGBUS, si_code, (void __user *)address, current);
} else {
inc_unaligned_kernel_access();
@@ -598,19 +593,20 @@ int is_dsp_inst(struct pt_regs *regs)
#ifdef CONFIG_CPU_SH2A
asmlinkage void do_divide_error(unsigned long r4)
{
- siginfo_t info;
+ int code;
switch (r4) {
case TRAP_DIVZERO_ERROR:
- info.si_code = FPE_INTDIV;
+ code = FPE_INTDIV;
break;
case TRAP_DIVOVF_ERROR:
- info.si_code = FPE_INTOVF;
+ code = FPE_INTOVF;
break;
+ default:
+ /* Let gcc know unhandled cases don't make it past here */
+ return;
}
-
- info.si_signo = SIGFPE;
- force_sig_info(info.si_signo, &info, current);
+ force_sig_fault(SIGFPE, code, NULL, current);
}
#endif
diff --git a/arch/sh/math-emu/math.c b/arch/sh/math-emu/math.c
index c86f436..a0fa8fc 100644
--- a/arch/sh/math-emu/math.c
+++ b/arch/sh/math-emu/math.c
@@ -507,7 +507,6 @@ static int ieee_fpe_handler(struct pt_regs *regs)
unsigned short insn = *(unsigned short *)regs->pc;
unsigned short finsn;
unsigned long nextpc;
- siginfo_t info;
int nib[4] = {
(insn >> 12) & 0xf,
(insn >> 8) & 0xf,
@@ -560,11 +559,8 @@ static int ieee_fpe_handler(struct pt_regs *regs)
~(FPSCR_CAUSE_MASK | FPSCR_FLAG_MASK);
task_thread_info(tsk)->status |= TS_USEDFPU;
} else {
- info.si_signo = SIGFPE;
- info.si_errno = 0;
- info.si_code = FPE_FLTINV;
- info.si_addr = (void __user *)regs->pc;
- force_sig_info(SIGFPE, &info, tsk);
+ force_sig_fault(SIGFPE, FPE_FLTINV,
+ (void __user *)regs->pc, tsk);
}
regs->pc = nextpc;
diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c
index 8ce9869..fceb2ad 100644
--- a/arch/sh/mm/consistent.c
+++ b/arch/sh/mm/consistent.c
@@ -20,18 +20,9 @@
#include <asm/cacheflush.h>
#include <asm/addrspace.h>
-#define PREALLOC_DMA_DEBUG_ENTRIES 4096
-
const struct dma_map_ops *dma_ops;
EXPORT_SYMBOL(dma_ops);
-static int __init dma_init(void)
-{
- dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
- return 0;
-}
-fs_initcall(dma_init);
-
void *dma_generic_alloc_coherent(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t gfp,
unsigned long attrs)
@@ -59,7 +50,9 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
split_page(pfn_to_page(virt_to_phys(ret) >> PAGE_SHIFT), order);
- *dma_handle = virt_to_phys(ret) - PFN_PHYS(dev->dma_pfn_offset);
+ *dma_handle = virt_to_phys(ret);
+ if (!WARN_ON(!dev))
+ *dma_handle -= PFN_PHYS(dev->dma_pfn_offset);
return ret_nocache;
}
@@ -69,9 +62,12 @@ void dma_generic_free_coherent(struct device *dev, size_t size,
unsigned long attrs)
{
int order = get_order(size);
- unsigned long pfn = (dma_handle >> PAGE_SHIFT) + dev->dma_pfn_offset;
+ unsigned long pfn = dma_handle >> PAGE_SHIFT;
int k;
+ if (!WARN_ON(!dev))
+ pfn += dev->dma_pfn_offset;
+
for (k = 0; k < (1 << order); k++)
__free_pages(pfn_to_page(pfn + k), 0);
@@ -143,7 +139,7 @@ int __init platform_resource_setup_memory(struct platform_device *pdev,
if (!memsize)
return 0;
- buf = dma_alloc_coherent(NULL, memsize, &dma_handle, GFP_KERNEL);
+ buf = dma_alloc_coherent(&pdev->dev, memsize, &dma_handle, GFP_KERNEL);
if (!buf) {
pr_warning("%s: unable to allocate memory\n", name);
return -ENOMEM;
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 6fd1bf7..b8e7bb8 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -42,14 +42,7 @@ static void
force_sig_info_fault(int si_signo, int si_code, unsigned long address,
struct task_struct *tsk)
{
- siginfo_t info;
-
- info.si_signo = si_signo;
- info.si_errno = 0;
- info.si_code = si_code;
- info.si_addr = (void __user *)address;
-
- force_sig_info(si_signo, &info, tsk);
+ force_sig_fault(si_signo, si_code, (void __user *)address, tsk);
}
/*
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index ce0bbaa..4034035 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -211,59 +211,15 @@ void __init allocate_pgdat(unsigned int nid)
NODE_DATA(nid) = __va(phys);
memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
-
- NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
#endif
NODE_DATA(nid)->node_start_pfn = start_pfn;
NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
}
-static void __init bootmem_init_one_node(unsigned int nid)
-{
- unsigned long total_pages, paddr;
- unsigned long end_pfn;
- struct pglist_data *p;
-
- p = NODE_DATA(nid);
-
- /* Nothing to do.. */
- if (!p->node_spanned_pages)
- return;
-
- end_pfn = pgdat_end_pfn(p);
-
- total_pages = bootmem_bootmap_pages(p->node_spanned_pages);
-
- paddr = memblock_alloc(total_pages << PAGE_SHIFT, PAGE_SIZE);
- if (!paddr)
- panic("Can't allocate bootmap for nid[%d]\n", nid);
-
- init_bootmem_node(p, paddr >> PAGE_SHIFT, p->node_start_pfn, end_pfn);
-
- free_bootmem_with_active_regions(nid, end_pfn);
-
- /*
- * XXX Handle initial reservations for the system memory node
- * only for the moment, we'll refactor this later for handling
- * reservations in other nodes.
- */
- if (nid == 0) {
- struct memblock_region *reg;
-
- /* Reserve the sections we're already using. */
- for_each_memblock(reserved, reg) {
- reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
- }
- }
-
- sparse_memory_present_with_active_regions(nid);
-}
-
static void __init do_init_bootmem(void)
{
struct memblock_region *reg;
- int i;
/* Add active regions with valid PFNs. */
for_each_memblock(memory, reg) {
@@ -279,9 +235,12 @@ static void __init do_init_bootmem(void)
plat_mem_setup();
- for_each_online_node(i)
- bootmem_init_one_node(i);
+ for_each_memblock(memory, reg) {
+ int nid = memblock_get_region_node(reg);
+ memory_present(nid, memblock_region_memory_base_pfn(reg),
+ memblock_region_memory_end_pfn(reg));
+ }
sparse_init();
}
@@ -322,7 +281,6 @@ void __init paging_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
unsigned long vaddr, end;
- int nid;
sh_mv.mv_mem_init();
@@ -377,21 +335,7 @@ void __init paging_init(void)
kmap_coherent_init();
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
-
- for_each_online_node(nid) {
- pg_data_t *pgdat = NODE_DATA(nid);
- unsigned long low, start_pfn;
-
- start_pfn = pgdat->bdata->node_min_pfn;
- low = pgdat->bdata->node_low_pfn;
-
- if (max_zone_pfns[ZONE_NORMAL] < low)
- max_zone_pfns[ZONE_NORMAL] = low;
-
- printk("Node %u: start_pfn = 0x%lx, low = 0x%lx\n",
- nid, start_pfn, low);
- }
-
+ max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
free_area_init_nodes(max_zone_pfns);
}
diff --git a/arch/sh/mm/numa.c b/arch/sh/mm/numa.c
index 05713d1..830e8b3 100644
--- a/arch/sh/mm/numa.c
+++ b/arch/sh/mm/numa.c
@@ -8,7 +8,6 @@
* for more details.
*/
#include <linux/module.h>
-#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/mm.h>
#include <linux/numa.h>
@@ -26,9 +25,7 @@ EXPORT_SYMBOL_GPL(node_data);
*/
void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end)
{
- unsigned long bootmap_pages;
unsigned long start_pfn, end_pfn;
- unsigned long bootmem_paddr;
/* Don't allow bogus node assignment */
BUG_ON(nid >= MAX_NUMNODES || nid <= 0);
@@ -48,25 +45,9 @@ void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end)
SMP_CACHE_BYTES, end));
memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
- NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
NODE_DATA(nid)->node_start_pfn = start_pfn;
NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
- /* Node-local bootmap */
- bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
- bootmem_paddr = memblock_alloc_base(bootmap_pages << PAGE_SHIFT,
- PAGE_SIZE, end);
- init_bootmem_node(NODE_DATA(nid), bootmem_paddr >> PAGE_SHIFT,
- start_pfn, end_pfn);
-
- free_bootmem_with_active_regions(nid, end_pfn);
-
- /* Reserve the pgdat and bootmap space with the bootmem allocator */
- reserve_bootmem_node(NODE_DATA(nid), start_pfn << PAGE_SHIFT,
- sizeof(struct pglist_data), BOOTMEM_DEFAULT);
- reserve_bootmem_node(NODE_DATA(nid), bootmem_paddr,
- bootmap_pages << PAGE_SHIFT, BOOTMEM_DEFAULT);
-
/* It's up */
node_set_online(nid);
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 8767e45..435dbc0 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -25,7 +25,6 @@
select RTC_CLASS
select RTC_DRV_M48T59
select RTC_SYSTOHC
- select HAVE_DMA_API_DEBUG
select HAVE_ARCH_JUMP_LABEL if SPARC64
select GENERIC_IRQ_SHOW
select ARCH_WANT_IPC_PARSE_VERSION
@@ -44,6 +43,8 @@
select ARCH_HAS_SG_CHAIN
select CPU_NO_EFFICIENT_FFS
select LOCKDEP_SMALL if LOCKDEP
+ select NEED_DMA_MAP_STATE
+ select NEED_SG_DMA_LENGTH
config SPARC32
def_bool !64BIT
@@ -67,6 +68,7 @@
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_CONTEXT_TRACKING
select HAVE_DEBUG_KMEMLEAK
+ select IOMMU_HELPER
select SPARSE_IRQ
select RTC_DRV_CMOS
select RTC_DRV_BQ4802
@@ -102,14 +104,6 @@
bool
default y if SPARC64
-config ARCH_DMA_ADDR_T_64BIT
- bool
- default y if ARCH_ATU
-
-config IOMMU_HELPER
- bool
- default y if SPARC64
-
config STACKTRACE_SUPPORT
bool
default y if SPARC64
@@ -146,12 +140,6 @@
bool
default y if SPARC32
-config NEED_DMA_MAP_STATE
- def_bool y
-
-config NEED_SG_DMA_LENGTH
- def_bool y
-
config GENERIC_ISA_DMA
bool
default y if SPARC32
diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h
index 615283e..4eb51d2 100644
--- a/arch/sparc/include/asm/compat.h
+++ b/arch/sparc/include/asm/compat.h
@@ -11,7 +11,6 @@
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
-typedef s32 compat_time_t;
typedef s32 compat_clock_t;
typedef s32 compat_pid_t;
typedef u16 __compat_uid_t;
@@ -39,16 +38,6 @@ typedef u32 compat_ulong_t;
typedef u64 compat_u64;
typedef u32 compat_uptr_t;
-struct compat_timespec {
- compat_time_t tv_sec;
- s32 tv_nsec;
-};
-
-struct compat_timeval {
- compat_time_t tv_sec;
- s32 tv_usec;
-};
-
struct compat_stat {
compat_dev_t st_dev;
compat_ino_t st_ino;
@@ -168,6 +157,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr)
return (u32)(unsigned long)uptr;
}
+#ifdef CONFIG_COMPAT
static inline void __user *arch_compat_alloc_user_space(long len)
{
struct pt_regs *regs = current_thread_info()->kregs;
@@ -184,6 +174,7 @@ static inline void __user *arch_compat_alloc_user_space(long len)
return (void __user *) usp;
}
+#endif
struct compat_ipc64_perm {
compat_key_t key;
@@ -201,10 +192,10 @@ struct compat_ipc64_perm {
struct compat_semid64_ds {
struct compat_ipc64_perm sem_perm;
- unsigned int __pad1;
- compat_time_t sem_otime;
- unsigned int __pad2;
- compat_time_t sem_ctime;
+ unsigned int sem_otime_high;
+ unsigned int sem_otime;
+ unsigned int sem_ctime_high;
+ unsigned int sem_ctime;
u32 sem_nsems;
u32 __unused1;
u32 __unused2;
@@ -212,12 +203,12 @@ struct compat_semid64_ds {
struct compat_msqid64_ds {
struct compat_ipc64_perm msg_perm;
- unsigned int __pad1;
- compat_time_t msg_stime;
- unsigned int __pad2;
- compat_time_t msg_rtime;
- unsigned int __pad3;
- compat_time_t msg_ctime;
+ unsigned int msg_stime_high;
+ unsigned int msg_stime;
+ unsigned int msg_rtime_high;
+ unsigned int msg_rtime;
+ unsigned int msg_ctime_high;
+ unsigned int msg_ctime;
unsigned int msg_cbytes;
unsigned int msg_qnum;
unsigned int msg_qbytes;
@@ -229,12 +220,12 @@ struct compat_msqid64_ds {
struct compat_shmid64_ds {
struct compat_ipc64_perm shm_perm;
- unsigned int __pad1;
- compat_time_t shm_atime;
- unsigned int __pad2;
- compat_time_t shm_dtime;
- unsigned int __pad3;
- compat_time_t shm_ctime;
+ unsigned int shm_atime_high;
+ unsigned int shm_atime;
+ unsigned int shm_dtime_high;
+ unsigned int shm_dtime;
+ unsigned int shm_ctime_high;
+ unsigned int shm_ctime;
compat_size_t shm_segsz;
compat_pid_t shm_cpid;
compat_pid_t shm_lpid;
@@ -243,6 +234,7 @@ struct compat_shmid64_ds {
unsigned int __unused2;
};
+#ifdef CONFIG_COMPAT
static inline int is_compat_task(void)
{
return test_thread_flag(TIF_32BIT);
@@ -254,5 +246,6 @@ static inline bool in_compat_syscall(void)
return pt_regs_trap_type(current_pt_regs()) == 0x110;
}
#define in_compat_syscall in_compat_syscall
+#endif
#endif /* _ASM_SPARC64_COMPAT_H */
diff --git a/arch/sparc/include/asm/hardirq_64.h b/arch/sparc/include/asm/hardirq_64.h
index f565402..75b92bf 100644
--- a/arch/sparc/include/asm/hardirq_64.h
+++ b/arch/sparc/include/asm/hardirq_64.h
@@ -10,8 +10,9 @@
#include <asm/cpudata.h>
#define __ARCH_IRQ_STAT
-#define local_softirq_pending() \
- (local_cpu_data().__softirq_pending)
+
+#define local_softirq_pending_ref \
+ __cpu_data.__softirq_pending
void ack_bad_irq(unsigned int irq);
diff --git a/include/linux/iommu-common.h b/arch/sparc/include/asm/iommu-common.h
similarity index 100%
rename from include/linux/iommu-common.h
rename to arch/sparc/include/asm/iommu-common.h
diff --git a/arch/sparc/include/asm/iommu_64.h b/arch/sparc/include/asm/iommu_64.h
index 9ed6b54..0ef6ded 100644
--- a/arch/sparc/include/asm/iommu_64.h
+++ b/arch/sparc/include/asm/iommu_64.h
@@ -17,7 +17,7 @@
#define IOPTE_WRITE 0x0000000000000002UL
#define IOMMU_NUM_CTXS 4096
-#include <linux/iommu-common.h>
+#include <asm/iommu-common.h>
struct iommu_arena {
unsigned long *map;
diff --git a/arch/sparc/include/asm/pci_32.h b/arch/sparc/include/asm/pci_32.h
index 98917e4..cfc0ee9 100644
--- a/arch/sparc/include/asm/pci_32.h
+++ b/arch/sparc/include/asm/pci_32.h
@@ -17,10 +17,6 @@
#define PCI_IRQ_NONE 0xffffffff
-/* Dynamic DMA mapping stuff.
- */
-#define PCI_DMA_BUS_IS_PHYS (0)
-
#endif /* __KERNEL__ */
#ifndef CONFIG_LEON_PCI
diff --git a/arch/sparc/include/asm/pci_64.h b/arch/sparc/include/asm/pci_64.h
index 671274e..fac7781 100644
--- a/arch/sparc/include/asm/pci_64.h
+++ b/arch/sparc/include/asm/pci_64.h
@@ -17,12 +17,6 @@
#define PCI_IRQ_NONE 0xffffffff
-/* The PCI address space does not equal the physical memory
- * address space. The networking and block device layers use
- * this boolean for bounce buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS (0)
-
/* PCI IOMMU mapping bypass support. */
/* PCI 64-bit addressing works for all slots on all controller
diff --git a/arch/sparc/include/uapi/asm/jsflash.h b/arch/sparc/include/uapi/asm/jsflash.h
deleted file mode 100644
index 68c98a5..0000000
--- a/arch/sparc/include/uapi/asm/jsflash.h
+++ /dev/null
@@ -1,40 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * jsflash.h: OS Flash SIMM support for JavaStations.
- *
- * Copyright (C) 1999 Pete Zaitcev
- */
-
-#ifndef _SPARC_JSFLASH_H
-#define _SPARC_JSFLASH_H
-
-#ifndef _SPARC_TYPES_H
-#include <linux/types.h>
-#endif
-
-/*
- * Semantics of the offset is a full address.
- * Hardcode it or get it from probe ioctl.
- *
- * We use full bus address, so that we would be
- * automatically compatible with possible future systems.
- */
-
-#define JSFLASH_IDENT (('F'<<8)|54)
-struct jsflash_ident_arg {
- __u64 off; /* 0x20000000 is included */
- __u32 size;
- char name[32]; /* With trailing zero */
-};
-
-#define JSFLASH_ERASE (('F'<<8)|55)
-/* Put 0 as argument, may be flags or sector number... */
-
-#define JSFLASH_PROGRAM (('F'<<8)|56)
-struct jsflash_program_arg {
- __u64 data; /* char* for sparc and sparc64 */
- __u64 off;
- __u32 size;
-};
-
-#endif /* _SPARC_JSFLASH_H */
diff --git a/arch/sparc/include/uapi/asm/msgbuf.h b/arch/sparc/include/uapi/asm/msgbuf.h
index b601c4f..ffc46c2 100644
--- a/arch/sparc/include/uapi/asm/msgbuf.h
+++ b/arch/sparc/include/uapi/asm/msgbuf.h
@@ -8,25 +8,22 @@
* between kernel and user space.
*
* Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
* - 2 miscellaneous 32-bit values
*/
-
-#if defined(__sparc__) && defined(__arch64__)
-# define PADDING(x)
-#else
-# define PADDING(x) unsigned int x;
-#endif
-
-
struct msqid64_ds {
struct ipc64_perm msg_perm;
- PADDING(__pad1)
+#if defined(__sparc__) && defined(__arch64__)
__kernel_time_t msg_stime; /* last msgsnd time */
- PADDING(__pad2)
__kernel_time_t msg_rtime; /* last msgrcv time */
- PADDING(__pad3)
__kernel_time_t msg_ctime; /* last change time */
+#else
+ unsigned long msg_stime_high;
+ unsigned long msg_stime; /* last msgsnd time */
+ unsigned long msg_rtime_high;
+ unsigned long msg_rtime; /* last msgrcv time */
+ unsigned long msg_ctime_high;
+ unsigned long msg_ctime; /* last change time */
+#endif
unsigned long msg_cbytes; /* current number of bytes on queue */
unsigned long msg_qnum; /* number of messages in queue */
unsigned long msg_qbytes; /* max number of bytes on queue */
@@ -35,5 +32,4 @@ struct msqid64_ds {
unsigned long __unused1;
unsigned long __unused2;
};
-#undef PADDING
#endif /* _SPARC_MSGBUF_H */
diff --git a/arch/sparc/include/uapi/asm/oradax.h b/arch/sparc/include/uapi/asm/oradax.h
index 7229519..4f6676f 100644
--- a/arch/sparc/include/uapi/asm/oradax.h
+++ b/arch/sparc/include/uapi/asm/oradax.h
@@ -3,7 +3,7 @@
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
+ * the Free Software Foundation, either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
diff --git a/arch/sparc/include/uapi/asm/sembuf.h b/arch/sparc/include/uapi/asm/sembuf.h
index f49b0ffa..f3d309c 100644
--- a/arch/sparc/include/uapi/asm/sembuf.h
+++ b/arch/sparc/include/uapi/asm/sembuf.h
@@ -8,25 +8,23 @@
* between kernel and user space.
*
* Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
* - 2 miscellaneous 32-bit values
*/
-#if defined(__sparc__) && defined(__arch64__)
-# define PADDING(x)
-#else
-# define PADDING(x) unsigned int x;
-#endif
struct semid64_ds {
struct ipc64_perm sem_perm; /* permissions .. see ipc.h */
- PADDING(__pad1)
+#if defined(__sparc__) && defined(__arch64__)
__kernel_time_t sem_otime; /* last semop time */
- PADDING(__pad2)
__kernel_time_t sem_ctime; /* last change time */
+#else
+ unsigned long sem_otime_high;
+ unsigned long sem_otime; /* last semop time */
+ unsigned long sem_ctime_high;
+ unsigned long sem_ctime; /* last change time */
+#endif
unsigned long sem_nsems; /* no. of semaphores in array */
unsigned long __unused1;
unsigned long __unused2;
};
-#undef PADDING
#endif /* _SPARC64_SEMBUF_H */
diff --git a/arch/sparc/include/uapi/asm/shmbuf.h b/arch/sparc/include/uapi/asm/shmbuf.h
index 286631d..06618b8 100644
--- a/arch/sparc/include/uapi/asm/shmbuf.h
+++ b/arch/sparc/include/uapi/asm/shmbuf.h
@@ -8,24 +8,23 @@
* between kernel and user space.
*
* Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
* - 2 miscellaneous 32-bit values
*/
-#if defined(__sparc__) && defined(__arch64__)
-# define PADDING(x)
-#else
-# define PADDING(x) unsigned int x;
-#endif
-
struct shmid64_ds {
struct ipc64_perm shm_perm; /* operation perms */
- PADDING(__pad1)
+#if defined(__sparc__) && defined(__arch64__)
__kernel_time_t shm_atime; /* last attach time */
- PADDING(__pad2)
__kernel_time_t shm_dtime; /* last detach time */
- PADDING(__pad3)
__kernel_time_t shm_ctime; /* last change time */
+#else
+ unsigned long shm_atime_high;
+ unsigned long shm_atime; /* last attach time */
+ unsigned long shm_dtime_high;
+ unsigned long shm_dtime; /* last detach time */
+ unsigned long shm_ctime_high;
+ unsigned long shm_ctime; /* last change time */
+#endif
size_t shm_segsz; /* size of segment (bytes) */
__kernel_pid_t shm_cpid; /* pid of creator */
__kernel_pid_t shm_lpid; /* pid of last operator */
@@ -46,6 +45,4 @@ struct shminfo64 {
unsigned long __unused4;
};
-#undef PADDING
-
#endif /* _SPARC_SHMBUF_H */
diff --git a/arch/sparc/include/uapi/asm/siginfo.h b/arch/sparc/include/uapi/asm/siginfo.h
index 896ce44..e704955 100644
--- a/arch/sparc/include/uapi/asm/siginfo.h
+++ b/arch/sparc/include/uapi/asm/siginfo.h
@@ -18,13 +18,6 @@
#define SI_NOINFO 32767 /* no information in siginfo_t */
/*
- * SIGFPE si_codes
- */
-#ifdef __KERNEL__
-#define FPE_FIXME 0 /* Broken dup of SI_USER */
-#endif /* __KERNEL__ */
-
-/*
* SIGEMT si_codes
*/
#define EMT_TAGOVF 1 /* tag overflow */
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index 76cb577..cf86408 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -59,7 +59,7 @@
obj-$(CONFIG_SPARC64) += reboot.o
obj-$(CONFIG_SPARC64) += sysfs.o
-obj-$(CONFIG_SPARC64) += iommu.o
+obj-$(CONFIG_SPARC64) += iommu.o iommu-common.o
obj-$(CONFIG_SPARC64) += central.o
obj-$(CONFIG_SPARC64) += starfire.o
obj-$(CONFIG_SPARC64) += power.o
@@ -74,8 +74,6 @@
obj-$(CONFIG_SPARC64) += nmi.o
obj-$(CONFIG_SPARC64_SMP) += cpumap.o
-obj-y += dma.o
-
obj-$(CONFIG_PCIC_PCI) += pcic.o
obj-$(CONFIG_LEON_PCI) += leon_pci.o
obj-$(CONFIG_SPARC_GRPCI2)+= leon_pci_grpci2.o
diff --git a/arch/sparc/kernel/dma.c b/arch/sparc/kernel/dma.c
deleted file mode 100644
index f73e759..0000000
--- a/arch/sparc/kernel/dma.c
+++ /dev/null
@@ -1,13 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/kernel.h>
-#include <linux/dma-mapping.h>
-#include <linux/dma-debug.h>
-
-#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 15)
-
-static int __init dma_init(void)
-{
- dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
- return 0;
-}
-fs_initcall(dma_init);
diff --git a/lib/iommu-common.c b/arch/sparc/kernel/iommu-common.c
similarity index 97%
rename from lib/iommu-common.c
rename to arch/sparc/kernel/iommu-common.c
index 55b00de..59cb166 100644
--- a/lib/iommu-common.c
+++ b/arch/sparc/kernel/iommu-common.c
@@ -8,9 +8,9 @@
#include <linux/bitmap.h>
#include <linux/bug.h>
#include <linux/iommu-helper.h>
-#include <linux/iommu-common.h>
#include <linux/dma-mapping.h>
#include <linux/hash.h>
+#include <asm/iommu-common.h>
static unsigned long iommu_large_alloc = 15;
@@ -93,7 +93,6 @@ void iommu_tbl_pool_init(struct iommu_map_table *iommu,
p->hint = p->start;
p->end = num_entries;
}
-EXPORT_SYMBOL(iommu_tbl_pool_init);
unsigned long iommu_tbl_range_alloc(struct device *dev,
struct iommu_map_table *iommu,
@@ -224,7 +223,6 @@ unsigned long iommu_tbl_range_alloc(struct device *dev,
return n;
}
-EXPORT_SYMBOL(iommu_tbl_range_alloc);
static struct iommu_pool *get_pool(struct iommu_map_table *tbl,
unsigned long entry)
@@ -264,4 +262,3 @@ void iommu_tbl_range_free(struct iommu_map_table *iommu, u64 dma_addr,
bitmap_clear(iommu->map, entry, npages);
spin_unlock_irqrestore(&(pool->lock), flags);
}
-EXPORT_SYMBOL(iommu_tbl_range_free);
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index b08dc34..40d008b 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -14,7 +14,7 @@
#include <linux/errno.h>
#include <linux/iommu-helper.h>
#include <linux/bitmap.h>
-#include <linux/iommu-common.h>
+#include <asm/iommu-common.h>
#ifdef CONFIG_PCI
#include <linux/pci.h>
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index 3bcef9c..cca9134c 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -678,25 +678,14 @@ static int sparc_io_proc_show(struct seq_file *m, void *v)
return 0;
}
-
-static int sparc_io_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, sparc_io_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations sparc_io_proc_fops = {
- .owner = THIS_MODULE,
- .open = sparc_io_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif /* CONFIG_PROC_FS */
static void register_proc_sparc_ioport(void)
{
#ifdef CONFIG_PROC_FS
- proc_create_data("io_map", 0, NULL, &sparc_io_proc_fops, &sparc_iomap);
- proc_create_data("dvma_map", 0, NULL, &sparc_io_proc_fops, &_sparc_dvma);
+ proc_create_single_data("io_map", 0, NULL, sparc_io_proc_show,
+ &sparc_iomap);
+ proc_create_single_data("dvma_map", 0, NULL, sparc_io_proc_show,
+ &_sparc_dvma);
#endif
}
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index 86b625f..c0fa3ef 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -16,7 +16,7 @@
#include <linux/list.h>
#include <linux/init.h>
#include <linux/bitmap.h>
-#include <linux/iommu-common.h>
+#include <asm/iommu-common.h>
#include <asm/hypervisor.h>
#include <asm/iommu.h>
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 2493672..565d9ac 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -16,7 +16,7 @@
#include <linux/export.h>
#include <linux/log2.h>
#include <linux/of_device.h>
-#include <linux/iommu-common.h>
+#include <asm/iommu-common.h>
#include <asm/iommu.h>
#include <asm/irq.h>
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 454a8af..6c08608 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -518,14 +518,7 @@ void synchronize_user_stack(void)
static void stack_unaligned(unsigned long sp)
{
- siginfo_t info;
-
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_ADRALN;
- info.si_addr = (void __user *) sp;
- info.si_trapno = 0;
- force_sig_info(SIGBUS, &info, current);
+ force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *) sp, 0, current);
}
void fault_in_user_windows(void)
diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c
index e8c3cb6..7f3d9c5 100644
--- a/arch/sparc/kernel/sys_sparc_32.c
+++ b/arch/sparc/kernel/sys_sparc_32.c
@@ -147,17 +147,11 @@ SYSCALL_DEFINE0(nis_syscall)
asmlinkage void
sparc_breakpoint (struct pt_regs *regs)
{
- siginfo_t info;
#ifdef DEBUG_SPARC_BREAKPOINT
printk ("TRAP: Entering kernel PC=%x, nPC=%x\n", regs->pc, regs->npc);
#endif
- info.si_signo = SIGTRAP;
- info.si_errno = 0;
- info.si_code = TRAP_BRKPT;
- info.si_addr = (void __user *)regs->pc;
- info.si_trapno = 0;
- force_sig_info(SIGTRAP, &info, current);
+ force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->pc, 0, current);
#ifdef DEBUG_SPARC_BREAKPOINT
printk ("TRAP: Returning to space: PC=%x nPC=%x\n", regs->pc, regs->npc);
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index 9ef8de6..7e49bbc9 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -502,7 +502,6 @@ SYSCALL_DEFINE0(nis_syscall)
asmlinkage void sparc_breakpoint(struct pt_regs *regs)
{
enum ctx_state prev_state = exception_enter();
- siginfo_t info;
if (test_thread_flag(TIF_32BIT)) {
regs->tpc &= 0xffffffff;
@@ -511,12 +510,7 @@ asmlinkage void sparc_breakpoint(struct pt_regs *regs)
#ifdef DEBUG_SPARC_BREAKPOINT
printk ("TRAP: Entering kernel PC=%lx, nPC=%lx\n", regs->tpc, regs->tnpc);
#endif
- info.si_signo = SIGTRAP;
- info.si_errno = 0;
- info.si_code = TRAP_BRKPT;
- info.si_addr = (void __user *)regs->tpc;
- info.si_trapno = 0;
- force_sig_info(SIGTRAP, &info, current);
+ force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->tpc, 0, current);
#ifdef DEBUG_SPARC_BREAKPOINT
printk ("TRAP: Returning to space: PC=%lx nPC=%lx\n", regs->tpc, regs->tnpc);
#endif
diff --git a/arch/sparc/kernel/traps_32.c b/arch/sparc/kernel/traps_32.c
index b1ed763..bcdfc61 100644
--- a/arch/sparc/kernel/traps_32.c
+++ b/arch/sparc/kernel/traps_32.c
@@ -93,8 +93,6 @@ void __noreturn die_if_kernel(char *str, struct pt_regs *regs)
void do_hw_interrupt(struct pt_regs *regs, unsigned long type)
{
- siginfo_t info;
-
if(type < 0x80) {
/* Sun OS's puke from bad traps, Linux survives! */
printk("Unimplemented Sparc TRAP, type = %02lx\n", type);
@@ -104,19 +102,13 @@ void do_hw_interrupt(struct pt_regs *regs, unsigned long type)
if(regs->psr & PSR_PS)
die_if_kernel("Kernel bad trap", regs);
- info.si_signo = SIGILL;
- info.si_errno = 0;
- info.si_code = ILL_ILLTRP;
- info.si_addr = (void __user *)regs->pc;
- info.si_trapno = type - 0x80;
- force_sig_info(SIGILL, &info, current);
+ force_sig_fault(SIGILL, ILL_ILLTRP,
+ (void __user *)regs->pc, type - 0x80, current);
}
void do_illegal_instruction(struct pt_regs *regs, unsigned long pc, unsigned long npc,
unsigned long psr)
{
- siginfo_t info;
-
if(psr & PSR_PS)
die_if_kernel("Kernel illegal instruction", regs);
#ifdef TRAP_DEBUG
@@ -124,27 +116,15 @@ void do_illegal_instruction(struct pt_regs *regs, unsigned long pc, unsigned lon
regs->pc, *(unsigned long *)regs->pc);
#endif
- info.si_signo = SIGILL;
- info.si_errno = 0;
- info.si_code = ILL_ILLOPC;
- info.si_addr = (void __user *)pc;
- info.si_trapno = 0;
- send_sig_info(SIGILL, &info, current);
+ send_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)pc, 0, current);
}
void do_priv_instruction(struct pt_regs *regs, unsigned long pc, unsigned long npc,
unsigned long psr)
{
- siginfo_t info;
-
if(psr & PSR_PS)
die_if_kernel("Penguin instruction from Penguin mode??!?!", regs);
- info.si_signo = SIGILL;
- info.si_errno = 0;
- info.si_code = ILL_PRVOPC;
- info.si_addr = (void __user *)pc;
- info.si_trapno = 0;
- send_sig_info(SIGILL, &info, current);
+ send_sig_fault(SIGILL, ILL_PRVOPC, (void __user *)pc, 0, current);
}
/* XXX User may want to be allowed to do this. XXX */
@@ -152,8 +132,6 @@ void do_priv_instruction(struct pt_regs *regs, unsigned long pc, unsigned long n
void do_memaccess_unaligned(struct pt_regs *regs, unsigned long pc, unsigned long npc,
unsigned long psr)
{
- siginfo_t info;
-
if(regs->psr & PSR_PS) {
printk("KERNEL MNA at pc %08lx npc %08lx called by %08lx\n", pc, npc,
regs->u_regs[UREG_RETPC]);
@@ -165,12 +143,9 @@ void do_memaccess_unaligned(struct pt_regs *regs, unsigned long pc, unsigned lon
instruction_dump ((unsigned long *) regs->pc);
printk ("do_MNA!\n");
#endif
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_ADRALN;
- info.si_addr = /* FIXME: Should dig out mna address */ (void *)0;
- info.si_trapno = 0;
- send_sig_info(SIGBUS, &info, current);
+ send_sig_fault(SIGBUS, BUS_ADRALN,
+ /* FIXME: Should dig out mna address */ (void *)0,
+ 0, current);
}
static unsigned long init_fsr = 0x0UL;
@@ -226,9 +201,9 @@ void do_fpe_trap(struct pt_regs *regs, unsigned long pc, unsigned long npc,
unsigned long psr)
{
static int calls;
- siginfo_t info;
unsigned long fsr;
int ret = 0;
+ int code;
#ifndef CONFIG_SMP
struct task_struct *fpt = last_task_used_math;
#else
@@ -303,24 +278,20 @@ void do_fpe_trap(struct pt_regs *regs, unsigned long pc, unsigned long npc,
}
fsr = fpt->thread.fsr;
- info.si_signo = SIGFPE;
- info.si_errno = 0;
- info.si_addr = (void __user *)pc;
- info.si_trapno = 0;
- info.si_code = FPE_FIXME;
+ code = FPE_FLTUNK;
if ((fsr & 0x1c000) == (1 << 14)) {
if (fsr & 0x10)
- info.si_code = FPE_FLTINV;
+ code = FPE_FLTINV;
else if (fsr & 0x08)
- info.si_code = FPE_FLTOVF;
+ code = FPE_FLTOVF;
else if (fsr & 0x04)
- info.si_code = FPE_FLTUND;
+ code = FPE_FLTUND;
else if (fsr & 0x02)
- info.si_code = FPE_FLTDIV;
+ code = FPE_FLTDIV;
else if (fsr & 0x01)
- info.si_code = FPE_FLTRES;
+ code = FPE_FLTRES;
}
- send_sig_info(SIGFPE, &info, fpt);
+ send_sig_fault(SIGFPE, code, (void __user *)pc, 0, fpt);
#ifndef CONFIG_SMP
last_task_used_math = NULL;
#endif
@@ -332,16 +303,9 @@ void do_fpe_trap(struct pt_regs *regs, unsigned long pc, unsigned long npc,
void handle_tag_overflow(struct pt_regs *regs, unsigned long pc, unsigned long npc,
unsigned long psr)
{
- siginfo_t info;
-
if(psr & PSR_PS)
die_if_kernel("Penguin overflow trap from kernel mode", regs);
- info.si_signo = SIGEMT;
- info.si_errno = 0;
- info.si_code = EMT_TAGOVF;
- info.si_addr = (void __user *)pc;
- info.si_trapno = 0;
- send_sig_info(SIGEMT, &info, current);
+ send_sig_fault(SIGEMT, EMT_TAGOVF, (void __user *)pc, 0, current);
}
void handle_watchpoint(struct pt_regs *regs, unsigned long pc, unsigned long npc,
@@ -359,61 +323,33 @@ void handle_watchpoint(struct pt_regs *regs, unsigned long pc, unsigned long npc
void handle_reg_access(struct pt_regs *regs, unsigned long pc, unsigned long npc,
unsigned long psr)
{
- siginfo_t info;
-
#ifdef TRAP_DEBUG
printk("Register Access Exception at PC %08lx NPC %08lx PSR %08lx\n",
pc, npc, psr);
#endif
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_OBJERR;
- info.si_addr = (void __user *)pc;
- info.si_trapno = 0;
- force_sig_info(SIGBUS, &info, current);
+ force_sig_fault(SIGBUS, BUS_OBJERR, (void __user *)pc, 0, current);
}
void handle_cp_disabled(struct pt_regs *regs, unsigned long pc, unsigned long npc,
unsigned long psr)
{
- siginfo_t info;
-
- info.si_signo = SIGILL;
- info.si_errno = 0;
- info.si_code = ILL_COPROC;
- info.si_addr = (void __user *)pc;
- info.si_trapno = 0;
- send_sig_info(SIGILL, &info, current);
+ send_sig_fault(SIGILL, ILL_COPROC, (void __user *)pc, 0, current);
}
void handle_cp_exception(struct pt_regs *regs, unsigned long pc, unsigned long npc,
unsigned long psr)
{
- siginfo_t info;
-
#ifdef TRAP_DEBUG
printk("Co-Processor Exception at PC %08lx NPC %08lx PSR %08lx\n",
pc, npc, psr);
#endif
- info.si_signo = SIGILL;
- info.si_errno = 0;
- info.si_code = ILL_COPROC;
- info.si_addr = (void __user *)pc;
- info.si_trapno = 0;
- send_sig_info(SIGILL, &info, current);
+ send_sig_fault(SIGILL, ILL_COPROC, (void __user *)pc, 0, current);
}
void handle_hw_divzero(struct pt_regs *regs, unsigned long pc, unsigned long npc,
unsigned long psr)
{
- siginfo_t info;
-
- info.si_signo = SIGFPE;
- info.si_errno = 0;
- info.si_code = FPE_INTDIV;
- info.si_addr = (void __user *)pc;
- info.si_trapno = 0;
- send_sig_info(SIGFPE, &info, current);
+ send_sig_fault(SIGFPE, FPE_INTDIV, (void __user *)pc, 0, current);
}
#ifdef CONFIG_DEBUG_BUGVERBOSE
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 462a21a..aa624ed 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -87,7 +87,6 @@ static void dump_tl1_traplog(struct tl1_traplog *p)
void bad_trap(struct pt_regs *regs, long lvl)
{
char buffer[36];
- siginfo_t info;
if (notify_die(DIE_TRAP, "bad trap", regs,
0, lvl, SIGTRAP) == NOTIFY_STOP)
@@ -107,12 +106,8 @@ void bad_trap(struct pt_regs *regs, long lvl)
regs->tpc &= 0xffffffff;
regs->tnpc &= 0xffffffff;
}
- info.si_signo = SIGILL;
- info.si_errno = 0;
- info.si_code = ILL_ILLTRP;
- info.si_addr = (void __user *)regs->tpc;
- info.si_trapno = lvl;
- force_sig_info(SIGILL, &info, current);
+ force_sig_fault(SIGILL, ILL_ILLTRP,
+ (void __user *)regs->tpc, lvl, current);
}
void bad_trap_tl1(struct pt_regs *regs, long lvl)
@@ -191,7 +186,6 @@ EXPORT_SYMBOL_GPL(unregister_dimm_printer);
void spitfire_insn_access_exception(struct pt_regs *regs, unsigned long sfsr, unsigned long sfar)
{
enum ctx_state prev_state = exception_enter();
- siginfo_t info;
if (notify_die(DIE_TRAP, "instruction access exception", regs,
0, 0x8, SIGTRAP) == NOTIFY_STOP)
@@ -206,12 +200,8 @@ void spitfire_insn_access_exception(struct pt_regs *regs, unsigned long sfsr, un
regs->tpc &= 0xffffffff;
regs->tnpc &= 0xffffffff;
}
- info.si_signo = SIGSEGV;
- info.si_errno = 0;
- info.si_code = SEGV_MAPERR;
- info.si_addr = (void __user *)regs->tpc;
- info.si_trapno = 0;
- force_sig_info(SIGSEGV, &info, current);
+ force_sig_fault(SIGSEGV, SEGV_MAPERR,
+ (void __user *)regs->tpc, 0, current);
out:
exception_exit(prev_state);
}
@@ -230,7 +220,6 @@ void sun4v_insn_access_exception(struct pt_regs *regs, unsigned long addr, unsig
{
unsigned short type = (type_ctx >> 16);
unsigned short ctx = (type_ctx & 0xffff);
- siginfo_t info;
if (notify_die(DIE_TRAP, "instruction access exception", regs,
0, 0x8, SIGTRAP) == NOTIFY_STOP)
@@ -247,12 +236,7 @@ void sun4v_insn_access_exception(struct pt_regs *regs, unsigned long addr, unsig
regs->tpc &= 0xffffffff;
regs->tnpc &= 0xffffffff;
}
- info.si_signo = SIGSEGV;
- info.si_errno = 0;
- info.si_code = SEGV_MAPERR;
- info.si_addr = (void __user *) addr;
- info.si_trapno = 0;
- force_sig_info(SIGSEGV, &info, current);
+ force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *) addr, 0, current);
}
void sun4v_insn_access_exception_tl1(struct pt_regs *regs, unsigned long addr, unsigned long type_ctx)
@@ -307,7 +291,6 @@ bool is_no_fault_exception(struct pt_regs *regs)
void spitfire_data_access_exception(struct pt_regs *regs, unsigned long sfsr, unsigned long sfar)
{
enum ctx_state prev_state = exception_enter();
- siginfo_t info;
if (notify_die(DIE_TRAP, "data access exception", regs,
0, 0x30, SIGTRAP) == NOTIFY_STOP)
@@ -338,12 +321,7 @@ void spitfire_data_access_exception(struct pt_regs *regs, unsigned long sfsr, un
if (is_no_fault_exception(regs))
return;
- info.si_signo = SIGSEGV;
- info.si_errno = 0;
- info.si_code = SEGV_MAPERR;
- info.si_addr = (void __user *)sfar;
- info.si_trapno = 0;
- force_sig_info(SIGSEGV, &info, current);
+ force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)sfar, 0, current);
out:
exception_exit(prev_state);
}
@@ -559,8 +537,6 @@ static void spitfire_cee_log(unsigned long afsr, unsigned long afar, unsigned lo
static void spitfire_ue_log(unsigned long afsr, unsigned long afar, unsigned long udbh, unsigned long udbl, unsigned long tt, int tl1, struct pt_regs *regs)
{
- siginfo_t info;
-
printk(KERN_WARNING "CPU[%d]: Uncorrectable Error AFSR[%lx] "
"AFAR[%lx] UDBL[%lx] UDBH[%ld] TT[%lx] TL>1[%d]\n",
smp_processor_id(), afsr, afar, udbl, udbh, tt, tl1);
@@ -595,12 +571,7 @@ static void spitfire_ue_log(unsigned long afsr, unsigned long afar, unsigned lon
regs->tpc &= 0xffffffff;
regs->tnpc &= 0xffffffff;
}
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_OBJERR;
- info.si_addr = (void *)0;
- info.si_trapno = 0;
- force_sig_info(SIGBUS, &info, current);
+ force_sig_fault(SIGBUS, BUS_OBJERR, (void *)0, 0, current);
}
void spitfire_access_error(struct pt_regs *regs, unsigned long status_encoded, unsigned long afar)
@@ -2190,7 +2161,6 @@ bool sun4v_nonresum_error_user_handled(struct pt_regs *regs,
if (attrs & SUN4V_ERR_ATTRS_MEMORY) {
unsigned long addr = ent->err_raddr;
- siginfo_t info;
if (addr == ~(u64)0) {
/* This seems highly unlikely to ever occur */
@@ -2211,21 +2181,13 @@ bool sun4v_nonresum_error_user_handled(struct pt_regs *regs,
addr += PAGE_SIZE;
}
}
- info.si_signo = SIGKILL;
- info.si_errno = 0;
- info.si_trapno = 0;
- force_sig_info(info.si_signo, &info, current);
+ force_sig(SIGKILL, current);
return true;
}
if (attrs & SUN4V_ERR_ATTRS_PIO) {
- siginfo_t info;
-
- info.si_signo = SIGBUS;
- info.si_code = BUS_ADRERR;
- info.si_addr = (void __user *)sun4v_get_vaddr(regs);
- force_sig_info(info.si_signo, &info, current);
-
+ force_sig_fault(SIGBUS, BUS_ADRERR,
+ (void __user *)sun4v_get_vaddr(regs), 0, current);
return true;
}
@@ -2362,30 +2324,27 @@ static void do_fpe_common(struct pt_regs *regs)
regs->tnpc += 4;
} else {
unsigned long fsr = current_thread_info()->xfsr[0];
- siginfo_t info;
+ int code;
if (test_thread_flag(TIF_32BIT)) {
regs->tpc &= 0xffffffff;
regs->tnpc &= 0xffffffff;
}
- info.si_signo = SIGFPE;
- info.si_errno = 0;
- info.si_addr = (void __user *)regs->tpc;
- info.si_trapno = 0;
- info.si_code = FPE_FIXME;
+ code = FPE_FLTUNK;
if ((fsr & 0x1c000) == (1 << 14)) {
if (fsr & 0x10)
- info.si_code = FPE_FLTINV;
+ code = FPE_FLTINV;
else if (fsr & 0x08)
- info.si_code = FPE_FLTOVF;
+ code = FPE_FLTOVF;
else if (fsr & 0x04)
- info.si_code = FPE_FLTUND;
+ code = FPE_FLTUND;
else if (fsr & 0x02)
- info.si_code = FPE_FLTDIV;
+ code = FPE_FLTDIV;
else if (fsr & 0x01)
- info.si_code = FPE_FLTRES;
+ code = FPE_FLTRES;
}
- force_sig_info(SIGFPE, &info, current);
+ force_sig_fault(SIGFPE, code,
+ (void __user *)regs->tpc, 0, current);
}
}
@@ -2428,7 +2387,6 @@ void do_fpother(struct pt_regs *regs)
void do_tof(struct pt_regs *regs)
{
enum ctx_state prev_state = exception_enter();
- siginfo_t info;
if (notify_die(DIE_TRAP, "tagged arithmetic overflow", regs,
0, 0x26, SIGEMT) == NOTIFY_STOP)
@@ -2440,12 +2398,8 @@ void do_tof(struct pt_regs *regs)
regs->tpc &= 0xffffffff;
regs->tnpc &= 0xffffffff;
}
- info.si_signo = SIGEMT;
- info.si_errno = 0;
- info.si_code = EMT_TAGOVF;
- info.si_addr = (void __user *)regs->tpc;
- info.si_trapno = 0;
- force_sig_info(SIGEMT, &info, current);
+ force_sig_fault(SIGEMT, EMT_TAGOVF,
+ (void __user *)regs->tpc, 0, current);
out:
exception_exit(prev_state);
}
@@ -2453,7 +2407,6 @@ void do_tof(struct pt_regs *regs)
void do_div0(struct pt_regs *regs)
{
enum ctx_state prev_state = exception_enter();
- siginfo_t info;
if (notify_die(DIE_TRAP, "integer division by zero", regs,
0, 0x28, SIGFPE) == NOTIFY_STOP)
@@ -2465,12 +2418,8 @@ void do_div0(struct pt_regs *regs)
regs->tpc &= 0xffffffff;
regs->tnpc &= 0xffffffff;
}
- info.si_signo = SIGFPE;
- info.si_errno = 0;
- info.si_code = FPE_INTDIV;
- info.si_addr = (void __user *)regs->tpc;
- info.si_trapno = 0;
- force_sig_info(SIGFPE, &info, current);
+ force_sig_fault(SIGFPE, FPE_INTDIV,
+ (void __user *)regs->tpc, 0, current);
out:
exception_exit(prev_state);
}
@@ -2632,7 +2581,6 @@ void do_illegal_instruction(struct pt_regs *regs)
unsigned long pc = regs->tpc;
unsigned long tstate = regs->tstate;
u32 insn;
- siginfo_t info;
if (notify_die(DIE_TRAP, "illegal instruction", regs,
0, 0x10, SIGILL) == NOTIFY_STOP)
@@ -2666,12 +2614,7 @@ void do_illegal_instruction(struct pt_regs *regs)
}
}
}
- info.si_signo = SIGILL;
- info.si_errno = 0;
- info.si_code = ILL_ILLOPC;
- info.si_addr = (void __user *)pc;
- info.si_trapno = 0;
- force_sig_info(SIGILL, &info, current);
+ force_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)pc, 0, current);
out:
exception_exit(prev_state);
}
@@ -2679,7 +2622,6 @@ void do_illegal_instruction(struct pt_regs *regs)
void mem_address_unaligned(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr)
{
enum ctx_state prev_state = exception_enter();
- siginfo_t info;
if (notify_die(DIE_TRAP, "memory address unaligned", regs,
0, 0x34, SIGSEGV) == NOTIFY_STOP)
@@ -2692,20 +2634,13 @@ void mem_address_unaligned(struct pt_regs *regs, unsigned long sfar, unsigned lo
if (is_no_fault_exception(regs))
return;
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_ADRALN;
- info.si_addr = (void __user *)sfar;
- info.si_trapno = 0;
- force_sig_info(SIGBUS, &info, current);
+ force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)sfar, 0, current);
out:
exception_exit(prev_state);
}
void sun4v_do_mna(struct pt_regs *regs, unsigned long addr, unsigned long type_ctx)
{
- siginfo_t info;
-
if (notify_die(DIE_TRAP, "memory address unaligned", regs,
0, 0x34, SIGSEGV) == NOTIFY_STOP)
return;
@@ -2717,12 +2652,7 @@ void sun4v_do_mna(struct pt_regs *regs, unsigned long addr, unsigned long type_c
if (is_no_fault_exception(regs))
return;
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_ADRALN;
- info.si_addr = (void __user *) addr;
- info.si_trapno = 0;
- force_sig_info(SIGBUS, &info, current);
+ force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *) addr, 0, current);
}
/* sun4v_mem_corrupt_detect_precise() - Handle precise exception on an ADI
@@ -2775,7 +2705,6 @@ void sun4v_mem_corrupt_detect_precise(struct pt_regs *regs, unsigned long addr,
void do_privop(struct pt_regs *regs)
{
enum ctx_state prev_state = exception_enter();
- siginfo_t info;
if (notify_die(DIE_TRAP, "privileged operation", regs,
0, 0x11, SIGILL) == NOTIFY_STOP)
@@ -2785,12 +2714,8 @@ void do_privop(struct pt_regs *regs)
regs->tpc &= 0xffffffff;
regs->tnpc &= 0xffffffff;
}
- info.si_signo = SIGILL;
- info.si_errno = 0;
- info.si_code = ILL_PRVOPC;
- info.si_addr = (void __user *)regs->tpc;
- info.si_trapno = 0;
- force_sig_info(SIGILL, &info, current);
+ force_sig_fault(SIGILL, ILL_PRVOPC,
+ (void __user *)regs->tpc, 0, current);
out:
exception_exit(prev_state);
}
diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c
index 7642d7e..64ac8c0 100644
--- a/arch/sparc/kernel/unaligned_32.c
+++ b/arch/sparc/kernel/unaligned_32.c
@@ -311,14 +311,9 @@ static inline int ok_for_user(struct pt_regs *regs, unsigned int insn,
static void user_mna_trap_fault(struct pt_regs *regs, unsigned int insn)
{
- siginfo_t info;
-
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_ADRALN;
- info.si_addr = (void __user *)safe_compute_effective_address(regs, insn);
- info.si_trapno = 0;
- send_sig_info(SIGBUS, &info, current);
+ send_sig_fault(SIGBUS, BUS_ADRALN,
+ (void __user *)safe_compute_effective_address(regs, insn),
+ 0, current);
}
asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn)
diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c
index 1a0fa10..32bae68 100644
--- a/arch/sparc/kernel/vio.c
+++ b/arch/sparc/kernel/vio.c
@@ -403,7 +403,7 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp,
if (err) {
printk(KERN_ERR "VIO: Could not register device %s, err=%d\n",
dev_name(&vdev->dev), err);
- kfree(vdev);
+ put_device(&vdev->dev);
return NULL;
}
if (vdev->dp)
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index a8103a8..9f75b64 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -127,19 +127,11 @@ show_signal_msg(struct pt_regs *regs, int sig, int code,
static void __do_fault_siginfo(int code, int sig, struct pt_regs *regs,
unsigned long addr)
{
- siginfo_t info;
-
- info.si_signo = sig;
- info.si_code = code;
- info.si_errno = 0;
- info.si_addr = (void __user *) addr;
- info.si_trapno = 0;
-
if (unlikely(show_unhandled_signals))
- show_signal_msg(regs, sig, info.si_code,
+ show_signal_msg(regs, sig, code,
addr, current);
- force_sig_info (sig, &info, current);
+ force_sig_fault(sig, code, (void __user *) addr, 0, current);
}
static unsigned long compute_si_addr(struct pt_regs *regs, int text_fault)
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 41363f4..63166fc 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -170,11 +170,7 @@ static void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
int fault_code)
{
unsigned long addr;
- siginfo_t info;
- info.si_code = code;
- info.si_signo = sig;
- info.si_errno = 0;
if (fault_code & FAULT_CODE_ITLB) {
addr = regs->tpc;
} else {
@@ -187,13 +183,11 @@ static void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
else
addr = fault_addr;
}
- info.si_addr = (void __user *) addr;
- info.si_trapno = 0;
if (unlikely(show_unhandled_signals))
show_signal_msg(regs, sig, code, addr, current);
- force_sig_info(sig, &info, current);
+ force_sig_fault(sig, code, (void __user *) addr, 0, current);
}
static unsigned int get_fault_insn(struct pt_regs *regs, unsigned int insn)
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index d4e8c49..dcf5ea2 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -208,19 +208,6 @@ static int fake_ide_media_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int fake_ide_media_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, fake_ide_media_proc_show, NULL);
-}
-
-static const struct file_operations fake_ide_media_proc_fops = {
- .owner = THIS_MODULE,
- .open = fake_ide_media_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static void make_ide_entries(const char *dev_name)
{
struct proc_dir_entry *dir, *ent;
@@ -231,7 +218,8 @@ static void make_ide_entries(const char *dev_name)
dir = proc_mkdir(dev_name, proc_ide);
if(!dir) return;
- ent = proc_create("media", S_IRUGO, dir, &fake_ide_media_proc_fops);
+ ent = proc_create_single("media", S_IRUGO, dir,
+ fake_ide_media_proc_show);
if(!ent) return;
snprintf(name, sizeof(name), "ide0/%s", dev_name);
proc_symlink(dev_name, proc_ide_root, name);
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index bb5a196..b10dde6 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -1,6 +1,7 @@
generic-y += barrier.h
generic-y += bpf_perf_event.h
generic-y += bug.h
+generic-y += compat.h
generic-y += current.h
generic-y += delay.h
generic-y += device.h
diff --git a/arch/um/kernel/ptrace.c b/arch/um/kernel/ptrace.c
index bc2a516..1a1d88a 100644
--- a/arch/um/kernel/ptrace.c
+++ b/arch/um/kernel/ptrace.c
@@ -115,17 +115,10 @@ long arch_ptrace(struct task_struct *child, long request,
static void send_sigtrap(struct task_struct *tsk, struct uml_pt_regs *regs,
int error_code)
{
- struct siginfo info;
-
- memset(&info, 0, sizeof(info));
- info.si_signo = SIGTRAP;
- info.si_code = TRAP_BRKPT;
-
- /* User-mode eip? */
- info.si_addr = UPT_IS_USER(regs) ? (void __user *) UPT_IP(regs) : NULL;
-
/* Send us the fake SIGTRAP */
- force_sig_info(SIGTRAP, &info, tsk);
+ force_sig_fault(SIGTRAP, TRAP_BRKPT,
+ /* User-mode eip? */
+ UPT_IS_USER(regs) ? (void __user *) UPT_IP(regs) : NULL, tsk);
}
/*
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index b2b02df..ec9a42c 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -162,13 +162,9 @@ static void show_segv_info(struct uml_pt_regs *regs)
static void bad_segv(struct faultinfo fi, unsigned long ip)
{
- struct siginfo si;
-
- si.si_signo = SIGSEGV;
- si.si_code = SEGV_ACCERR;
- si.si_addr = (void __user *) FAULT_ADDRESS(fi);
current->thread.arch.faultinfo = fi;
- force_sig_info(SIGSEGV, &si, current);
+ force_sig_fault(SIGSEGV, SEGV_ACCERR, (void __user *) FAULT_ADDRESS(fi),
+ current);
}
void fatal_sigsegv(void)
@@ -214,8 +210,8 @@ void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
struct uml_pt_regs *regs)
{
- struct siginfo si;
jmp_buf *catcher;
+ int si_code;
int err;
int is_write = FAULT_WRITE(fi);
unsigned long address = FAULT_ADDRESS(fi);
@@ -239,7 +235,7 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
if (SEGV_IS_FIXABLE(&fi))
err = handle_page_fault(address, ip, is_write, is_user,
- &si.si_code);
+ &si_code);
else {
err = -EFAULT;
/*
@@ -271,18 +267,14 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
show_segv_info(regs);
if (err == -EACCES) {
- si.si_signo = SIGBUS;
- si.si_errno = 0;
- si.si_code = BUS_ADRERR;
- si.si_addr = (void __user *)address;
current->thread.arch.faultinfo = fi;
- force_sig_info(SIGBUS, &si, current);
+ force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address,
+ current);
} else {
BUG_ON(err != -EFAULT);
- si.si_signo = SIGSEGV;
- si.si_addr = (void __user *) address;
current->thread.arch.faultinfo = fi;
- force_sig_info(SIGSEGV, &si, current);
+ force_sig_fault(SIGSEGV, si_code, (void __user *) address,
+ current);
}
out:
@@ -294,9 +286,7 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs)
{
- struct faultinfo *fi;
- struct siginfo clean_si;
-
+ int code, err;
if (!UPT_IS_USER(regs)) {
if (sig == SIGBUS)
printk(KERN_ERR "Bus error - the host /dev/shm or /tmp "
@@ -306,29 +296,21 @@ void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs)
arch_examine_signal(sig, regs);
- clear_siginfo(&clean_si);
- clean_si.si_signo = si->si_signo;
- clean_si.si_errno = si->si_errno;
- clean_si.si_code = si->si_code;
- switch (sig) {
- case SIGILL:
- case SIGFPE:
- case SIGSEGV:
- case SIGBUS:
- case SIGTRAP:
- fi = UPT_FAULTINFO(regs);
- clean_si.si_addr = (void __user *) FAULT_ADDRESS(*fi);
+ /* Is the signal layout for the signal known?
+ * Signal data must be scrubbed to prevent information leaks.
+ */
+ code = si->si_code;
+ err = si->si_errno;
+ if ((err == 0) && (siginfo_layout(sig, code) == SIL_FAULT)) {
+ struct faultinfo *fi = UPT_FAULTINFO(regs);
current->thread.arch.faultinfo = *fi;
-#ifdef __ARCH_SI_TRAPNO
- clean_si.si_trapno = si->si_trapno;
-#endif
- break;
- default:
- printk(KERN_ERR "Attempted to relay unknown signal %d (si_code = %d)\n",
- sig, si->si_code);
+ force_sig_fault(sig, code, (void __user *)FAULT_ADDRESS(*fi),
+ current);
+ } else {
+ printk(KERN_ERR "Attempted to relay unknown signal %d (si_code = %d) with errno %d\n",
+ sig, code, err);
+ force_sig(sig, current);
}
-
- force_sig_info(sig, &clean_si, current);
}
void bus_handler(int sig, struct siginfo *si, struct uml_pt_regs *regs)
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index 462e59a..03f991e 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -19,6 +19,8 @@
select ARCH_WANT_FRAME_POINTERS
select GENERIC_IOMAP
select MODULES_USE_ELF_REL
+ select NEED_DMA_MAP_STATE
+ select SWIOTLB
help
UniCore-32 is 32-bit Instruction Set Architecture,
including a series of low-power-consumption RISC chip
@@ -61,9 +63,6 @@
config ZONE_DMA
def_bool y
-config NEED_DMA_MAP_STATE
- def_bool y
-
source "init/Kconfig"
source "kernel/Kconfig.freezer"
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index 6f70c76..bfc7abe 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -1,5 +1,6 @@
generic-y += atomic.h
generic-y += bugs.h
+generic-y += compat.h
generic-y += current.h
generic-y += device.h
generic-y += div64.h
diff --git a/arch/unicore32/kernel/fpu-ucf64.c b/arch/unicore32/kernel/fpu-ucf64.c
index 12c8c95..8594b16 100644
--- a/arch/unicore32/kernel/fpu-ucf64.c
+++ b/arch/unicore32/kernel/fpu-ucf64.c
@@ -52,14 +52,14 @@
* Raise a SIGFPE for the current process.
* sicode describes the signal being raised.
*/
-void ucf64_raise_sigfpe(unsigned int sicode, struct pt_regs *regs)
+void ucf64_raise_sigfpe(struct pt_regs *regs)
{
siginfo_t info;
- memset(&info, 0, sizeof(info));
+ clear_siginfo(&info);
info.si_signo = SIGFPE;
- info.si_code = sicode;
+ info.si_code = FPE_FLTUNK;
info.si_addr = (void __user *)(instruction_pointer(regs) - 4);
/*
@@ -94,7 +94,7 @@ void ucf64_exchandler(u32 inst, u32 fpexc, struct pt_regs *regs)
pr_debug("UniCore-F64 FPSCR 0x%08x INST 0x%08x\n",
cff(FPSCR), inst);
- ucf64_raise_sigfpe(0, regs);
+ ucf64_raise_sigfpe(regs);
return;
}
diff --git a/arch/unicore32/mm/Kconfig b/arch/unicore32/mm/Kconfig
index e9154a5..82759b6 100644
--- a/arch/unicore32/mm/Kconfig
+++ b/arch/unicore32/mm/Kconfig
@@ -39,14 +39,3 @@
default y
help
Say Y here to disable the TLB single entry operations.
-
-config SWIOTLB
- def_bool y
- select DMA_DIRECT_OPS
-
-config IOMMU_HELPER
- def_bool SWIOTLB
-
-config NEED_SG_DMA_LENGTH
- def_bool SWIOTLB
-
diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c
index bbefcc4..3814734 100644
--- a/arch/unicore32/mm/fault.c
+++ b/arch/unicore32/mm/fault.c
@@ -125,6 +125,7 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
tsk->thread.address = addr;
tsk->thread.error_code = fsr;
tsk->thread.trap_no = 14;
+ clear_siginfo(&si);
si.si_signo = sig;
si.si_errno = 0;
si.si_code = code;
@@ -472,6 +473,7 @@ asmlinkage void do_DataAbort(unsigned long addr, unsigned int fsr,
printk(KERN_ALERT "Unhandled fault: %s (0x%03x) at 0x%08lx\n",
inf->name, fsr, addr);
+ clear_siginfo(&info);
info.si_signo = inf->sig;
info.si_errno = 0;
info.si_code = inf->code;
@@ -491,6 +493,7 @@ asmlinkage void do_PrefetchAbort(unsigned long addr,
printk(KERN_ALERT "Unhandled prefetch abort: %s (0x%03x) at 0x%08lx\n",
inf->name, ifsr, addr);
+ clear_siginfo(&info);
info.si_signo = inf->sig;
info.si_errno = 0;
info.si_code = inf->code;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 00fcf81..1fe24b6 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -28,6 +28,8 @@
select ARCH_USE_CMPXCHG_LOCKREF
select HAVE_ARCH_SOFT_DIRTY
select MODULES_USE_ELF_RELA
+ select NEED_DMA_MAP_STATE
+ select SWIOTLB
select X86_DEV_DMA_OPS
select ARCH_HAS_SYSCALL_WRAPPER
@@ -52,6 +54,7 @@
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FAST_MULTIPLIER
+ select ARCH_HAS_FILTER_PGPROT
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_HAS_KCOV if X86_64
@@ -59,6 +62,7 @@
select ARCH_HAS_PMEM_API if X86_64
select ARCH_HAS_REFCOUNT
select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64
+ select ARCH_HAS_UACCESS_MCSAFE if X86_64
select ARCH_HAS_SET_MEMORY
select ARCH_HAS_SG_CHAIN
select ARCH_HAS_STRICT_KERNEL_RWX
@@ -133,7 +137,6 @@
select HAVE_C_RECORDMCOUNT
select HAVE_DEBUG_KMEMLEAK
select HAVE_DEBUG_STACKOVERFLOW
- select HAVE_DMA_API_DEBUG
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
select HAVE_DYNAMIC_FTRACE_WITH_REGS
@@ -183,6 +186,7 @@
select HAVE_UNSTABLE_SCHED_CLOCK
select HAVE_USER_RETURN_NOTIFIER
select IRQ_FORCED_THREADING
+ select NEED_SG_DMA_LENGTH
select PCI_LOCKLESS_CONFIG
select PERF_EVENTS
select RTC_LIB
@@ -235,13 +239,6 @@
config SBUS
bool
-config NEED_DMA_MAP_STATE
- def_bool y
- depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG || SWIOTLB
-
-config NEED_SG_DMA_LENGTH
- def_bool y
-
config GENERIC_ISA_DMA
def_bool y
depends on ISA_DMA_API
@@ -273,6 +270,9 @@
config ARCH_HAS_CACHE_LINE_SIZE
def_bool y
+config ARCH_HAS_FILTER_PGPROT
+ def_bool y
+
config HAVE_SETUP_PER_CPU_AREA
def_bool y
@@ -871,6 +871,7 @@
config GART_IOMMU
bool "Old AMD GART IOMMU support"
+ select IOMMU_HELPER
select SWIOTLB
depends on X86_64 && PCI && AMD_NB
---help---
@@ -892,6 +893,7 @@
config CALGARY_IOMMU
bool "IBM Calgary IOMMU support"
+ select IOMMU_HELPER
select SWIOTLB
depends on X86_64 && PCI
---help---
@@ -919,20 +921,6 @@
Calgary anyway, pass 'iommu=calgary' on the kernel command line.
If unsure, say Y.
-# need this always selected by IOMMU for the VIA workaround
-config SWIOTLB
- def_bool y if X86_64
- ---help---
- Support for software bounce buffers used on x86-64 systems
- which don't have a hardware IOMMU. Using this PCI devices
- which can only access 32-bits of memory can be used on systems
- with more than 3 GB of memory.
- If unsure, say Y.
-
-config IOMMU_HELPER
- def_bool y
- depends on CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU
-
config MAXSMP
bool "Enable Maximum number of SMP Processors and NUMA Nodes"
depends on X86_64 && SMP && DEBUG_KERNEL
@@ -1454,6 +1442,7 @@
config X86_PAE
bool "PAE (Physical Address Extension) Support"
depends on X86_32 && !HIGHMEM4G
+ select PHYS_ADDR_T_64BIT
select SWIOTLB
---help---
PAE is required for NX support, and furthermore enables
@@ -1481,14 +1470,6 @@
Say N if unsure.
-config ARCH_PHYS_ADDR_T_64BIT
- def_bool y
- depends on X86_64 || X86_PAE
-
-config ARCH_DMA_ADDR_T_64BIT
- def_bool y
- depends on X86_64 || HIGHMEM64G
-
config X86_DIRECT_GBPAGES
def_bool y
depends on X86_64 && !DEBUG_PAGEALLOC
diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c
index 0cb3257..af6cda0 100644
--- a/arch/x86/boot/compressed/cmdline.c
+++ b/arch/x86/boot/compressed/cmdline.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include "misc.h"
-#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE
+#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE || CONFIG_X86_5LEVEL
static unsigned long fs;
static inline void set_fs(unsigned long seg)
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 47d3eff..a8a8642 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -109,23 +109,34 @@ void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
}
static efi_status_t
-__setup_efi_pci32(efi_pci_io_protocol_32 *pci, struct pci_setup_rom **__rom)
+__setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
{
struct pci_setup_rom *rom = NULL;
efi_status_t status;
unsigned long size;
- uint64_t attributes;
+ uint64_t attributes, romsize;
+ void *romimage;
- status = efi_early->call(pci->attributes, pci,
- EfiPciIoAttributeOperationGet, 0, 0,
- &attributes);
+ status = efi_call_proto(efi_pci_io_protocol, attributes, pci,
+ EfiPciIoAttributeOperationGet, 0, 0,
+ &attributes);
if (status != EFI_SUCCESS)
return status;
- if (!pci->romimage || !pci->romsize)
+ /*
+ * Some firmware images contain EFI function pointers at the place where the
+ * romimage and romsize fields are supposed to be. Typically the EFI
+ * code is mapped at high addresses, translating to an unrealistically
+ * large romsize. The UEFI spec limits the size of option ROMs to 16
+ * MiB so we reject any ROMs over 16 MiB in size to catch this.
+ */
+ romimage = (void *)(unsigned long)efi_table_attr(efi_pci_io_protocol,
+ romimage, pci);
+ romsize = efi_table_attr(efi_pci_io_protocol, romsize, pci);
+ if (!romimage || !romsize || romsize > SZ_16M)
return EFI_INVALID_PARAMETER;
- size = pci->romsize + sizeof(*rom);
+ size = romsize + sizeof(*rom);
status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom);
if (status != EFI_SUCCESS) {
@@ -141,29 +152,32 @@ __setup_efi_pci32(efi_pci_io_protocol_32 *pci, struct pci_setup_rom **__rom)
rom->pcilen = pci->romsize;
*__rom = rom;
- status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
- PCI_VENDOR_ID, 1, &(rom->vendor));
+ status = efi_call_proto(efi_pci_io_protocol, pci.read, pci,
+ EfiPciIoWidthUint16, PCI_VENDOR_ID, 1,
+ &rom->vendor);
if (status != EFI_SUCCESS) {
efi_printk(sys_table, "Failed to read rom->vendor\n");
goto free_struct;
}
- status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
- PCI_DEVICE_ID, 1, &(rom->devid));
+ status = efi_call_proto(efi_pci_io_protocol, pci.read, pci,
+ EfiPciIoWidthUint16, PCI_DEVICE_ID, 1,
+ &rom->devid);
if (status != EFI_SUCCESS) {
efi_printk(sys_table, "Failed to read rom->devid\n");
goto free_struct;
}
- status = efi_early->call(pci->get_location, pci, &(rom->segment),
- &(rom->bus), &(rom->device), &(rom->function));
+ status = efi_call_proto(efi_pci_io_protocol, get_location, pci,
+ &rom->segment, &rom->bus, &rom->device,
+ &rom->function);
if (status != EFI_SUCCESS)
goto free_struct;
- memcpy(rom->romdata, pci->romimage, pci->romsize);
+ memcpy(rom->romdata, romimage, romsize);
return status;
free_struct:
@@ -175,7 +189,7 @@ static void
setup_efi_pci32(struct boot_params *params, void **pci_handle,
unsigned long size)
{
- efi_pci_io_protocol_32 *pci = NULL;
+ efi_pci_io_protocol_t *pci = NULL;
efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
u32 *handles = (u32 *)(unsigned long)pci_handle;
efi_status_t status;
@@ -202,7 +216,7 @@ setup_efi_pci32(struct boot_params *params, void **pci_handle,
if (!pci)
continue;
- status = __setup_efi_pci32(pci, &rom);
+ status = __setup_efi_pci(pci, &rom);
if (status != EFI_SUCCESS)
continue;
@@ -216,73 +230,11 @@ setup_efi_pci32(struct boot_params *params, void **pci_handle,
}
}
-static efi_status_t
-__setup_efi_pci64(efi_pci_io_protocol_64 *pci, struct pci_setup_rom **__rom)
-{
- struct pci_setup_rom *rom;
- efi_status_t status;
- unsigned long size;
- uint64_t attributes;
-
- status = efi_early->call(pci->attributes, pci,
- EfiPciIoAttributeOperationGet, 0,
- &attributes);
- if (status != EFI_SUCCESS)
- return status;
-
- if (!pci->romimage || !pci->romsize)
- return EFI_INVALID_PARAMETER;
-
- size = pci->romsize + sizeof(*rom);
-
- status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom);
- if (status != EFI_SUCCESS) {
- efi_printk(sys_table, "Failed to alloc mem for rom\n");
- return status;
- }
-
- rom->data.type = SETUP_PCI;
- rom->data.len = size - sizeof(struct setup_data);
- rom->data.next = 0;
- rom->pcilen = pci->romsize;
- *__rom = rom;
-
- status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
- PCI_VENDOR_ID, 1, &(rom->vendor));
-
- if (status != EFI_SUCCESS) {
- efi_printk(sys_table, "Failed to read rom->vendor\n");
- goto free_struct;
- }
-
- status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
- PCI_DEVICE_ID, 1, &(rom->devid));
-
- if (status != EFI_SUCCESS) {
- efi_printk(sys_table, "Failed to read rom->devid\n");
- goto free_struct;
- }
-
- status = efi_early->call(pci->get_location, pci, &(rom->segment),
- &(rom->bus), &(rom->device), &(rom->function));
-
- if (status != EFI_SUCCESS)
- goto free_struct;
-
- memcpy(rom->romdata, pci->romimage, pci->romsize);
- return status;
-
-free_struct:
- efi_call_early(free_pool, rom);
- return status;
-
-}
-
static void
setup_efi_pci64(struct boot_params *params, void **pci_handle,
unsigned long size)
{
- efi_pci_io_protocol_64 *pci = NULL;
+ efi_pci_io_protocol_t *pci = NULL;
efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
u64 *handles = (u64 *)(unsigned long)pci_handle;
efi_status_t status;
@@ -309,7 +261,7 @@ setup_efi_pci64(struct boot_params *params, void **pci_handle,
if (!pci)
continue;
- status = __setup_efi_pci64(pci, &rom);
+ status = __setup_efi_pci(pci, &rom);
if (status != EFI_SUCCESS)
continue;
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index fca012b..6403789 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -306,6 +306,25 @@
leaq boot_stack_end(%rbx), %rsp
/*
+ * paging_prepare() and cleanup_trampoline() below can have GOT
+ * references. Adjust the table with address we are running at.
+ *
+ * Zero RAX for adjust_got: the GOT was not adjusted before;
+ * there's no adjustment to undo.
+ */
+ xorq %rax, %rax
+
+ /*
+ * Calculate the address the binary is loaded at and use it as
+ * a GOT adjustment.
+ */
+ call 1f
+1: popq %rdi
+ subq $1b, %rdi
+
+ call adjust_got
+
+ /*
* At this point we are in long mode with 4-level paging enabled,
* but we might want to enable 5-level paging or vice versa.
*
@@ -346,6 +365,7 @@
* this function call.
*/
pushq %rsi
+ movq %rsi, %rdi /* real mode address */
call paging_prepare
popq %rsi
@@ -370,10 +390,14 @@
/*
* cleanup_trampoline() would restore trampoline memory.
*
+ * RDI is address of the page table to use instead of page table
+ * in trampoline memory (if required).
+ *
* RSI holds real mode data and needs to be preserved across
* this function call.
*/
pushq %rsi
+ leaq top_pgtable(%rbx), %rdi
call cleanup_trampoline
popq %rsi
@@ -381,6 +405,21 @@
pushq $0
popfq
+ /*
+ * Previously we've adjusted the GOT with address the binary was
+ * loaded at. Now we need to re-adjust for relocation address.
+ *
+ * Calculate the address the binary is loaded at, so that we can
+ * undo the previous GOT adjustment.
+ */
+ call 1f
+1: popq %rax
+ subq $1b, %rax
+
+ /* The new adjustment is the relocation address */
+ movq %rbx, %rdi
+ call adjust_got
+
/*
* Copy the compressed kernel to the end of our buffer
* where decompression in place becomes safe.
@@ -482,19 +521,6 @@
rep stosq
/*
- * Adjust our own GOT
- */
- leaq _got(%rip), %rdx
- leaq _egot(%rip), %rcx
-1:
- cmpq %rcx, %rdx
- jae 2f
- addq %rbx, (%rdx)
- addq $8, %rdx
- jmp 1b
-2:
-
-/*
* Do the extraction, and jump to the new kernel..
*/
pushq %rsi /* Save the real mode argument */
@@ -512,6 +538,27 @@
*/
jmp *%rax
+/*
+ * Adjust the global offset table
+ *
+ * RAX is the previous adjustment of the table to undo (use 0 if it's the
+ * first time we touch GOT).
+ * RDI is the new adjustment to apply.
+ */
+adjust_got:
+ /* Walk through the GOT adding the address to the entries */
+ leaq _got(%rip), %rdx
+ leaq _egot(%rip), %rcx
+1:
+ cmpq %rcx, %rdx
+ jae 2f
+ subq %rax, (%rdx) /* Undo previous adjustment */
+ addq %rdi, (%rdx) /* Apply the new adjustment */
+ addq $8, %rdx
+ jmp 1b
+2:
+ ret
+
.code32
/*
* This is the 32-bit trampoline that will be copied over to low memory.
@@ -649,3 +696,10 @@
.balign 4096
pgtable:
.fill BOOT_PGT_SIZE, 1, 0
+
+/*
+ * The page table is going to be used instead of page table in the trampoline
+ * memory.
+ */
+top_pgtable:
+ .fill PAGE_SIZE, 1, 0
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index a0a50b9..b87a758 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -47,7 +47,7 @@
#include <linux/decompress/mm.h>
#ifdef CONFIG_X86_5LEVEL
-unsigned int pgtable_l5_enabled __ro_after_init;
+unsigned int __pgtable_l5_enabled;
unsigned int pgdir_shift __ro_after_init = 39;
unsigned int ptrs_per_p4d __ro_after_init = 1;
#endif
@@ -734,7 +734,7 @@ void choose_random_location(unsigned long input,
#ifdef CONFIG_X86_5LEVEL
if (__read_cr4() & X86_CR4_LA57) {
- pgtable_l5_enabled = 1;
+ __pgtable_l5_enabled = 1;
pgdir_shift = 48;
ptrs_per_p4d = 512;
}
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 9e11be4..a423bdb 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -12,10 +12,8 @@
#undef CONFIG_PARAVIRT_SPINLOCKS
#undef CONFIG_KASAN
-#ifdef CONFIG_X86_5LEVEL
-/* cpu_feature_enabled() cannot be used that early */
-#define pgtable_l5_enabled __pgtable_l5_enabled
-#endif
+/* cpu_feature_enabled() cannot be used this early */
+#define USE_EARLY_PGTABLE_L5
#include <linux/linkage.h>
#include <linux/screen_info.h>
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index 32af1cb..8c51075 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -23,14 +23,6 @@ struct paging_config {
static char trampoline_save[TRAMPOLINE_32BIT_SIZE];
/*
- * The page table is going to be used instead of page table in the trampoline
- * memory.
- *
- * It must not be in BSS as BSS is cleared after cleanup_trampoline().
- */
-static char top_pgtable[PAGE_SIZE] __aligned(PAGE_SIZE) __section(.data);
-
-/*
* Trampoline address will be printed by extract_kernel() for debugging
* purposes.
*
@@ -39,16 +31,23 @@ static char top_pgtable[PAGE_SIZE] __aligned(PAGE_SIZE) __section(.data);
*/
unsigned long *trampoline_32bit __section(.data);
-struct paging_config paging_prepare(void)
+extern struct boot_params *boot_params;
+int cmdline_find_option_bool(const char *option);
+
+struct paging_config paging_prepare(void *rmode)
{
struct paging_config paging_config = {};
unsigned long bios_start, ebda_start;
+ /* Initialize boot_params. Required for cmdline_find_option_bool(). */
+ boot_params = rmode;
+
/*
* Check if LA57 is desired and supported.
*
- * There are two parts to the check:
+ * There are several parts to the check:
* - if the kernel supports 5-level paging: CONFIG_X86_5LEVEL=y
+ * - if user asked to disable 5-level paging: no5lvl in cmdline
* - if the machine supports 5-level paging:
* + CPUID leaf 7 is supported
* + the leaf has the feature bit set
@@ -56,6 +55,7 @@ struct paging_config paging_prepare(void)
* That's substitute for boot_cpu_has() in early boot code.
*/
if (IS_ENABLED(CONFIG_X86_5LEVEL) &&
+ !cmdline_find_option_bool("no5lvl") &&
native_cpuid_eax(0) >= 7 &&
(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) {
paging_config.l5_required = 1;
@@ -134,19 +134,19 @@ struct paging_config paging_prepare(void)
return paging_config;
}
-void cleanup_trampoline(void)
+void cleanup_trampoline(void *pgtable)
{
void *trampoline_pgtable;
- trampoline_pgtable = trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET;
+ trampoline_pgtable = trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET / sizeof(unsigned long);
/*
* Move the top level page table out of trampoline memory,
* if it's there.
*/
if ((void *)__native_read_cr3() == trampoline_pgtable) {
- memcpy(top_pgtable, trampoline_pgtable, PAGE_SIZE);
- native_write_cr3((unsigned long)top_pgtable);
+ memcpy(pgtable, trampoline_pgtable, PAGE_SIZE);
+ native_write_cr3((unsigned long)pgtable);
}
/* Restore trampoline memory */
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 9af927e..9de7f1e 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -84,13 +84,13 @@
pushq %rdx /* pt_regs->dx */
pushq %rcx /* pt_regs->cx */
pushq $-ENOSYS /* pt_regs->ax */
- pushq $0 /* pt_regs->r8 = 0 */
+ pushq %r8 /* pt_regs->r8 */
xorl %r8d, %r8d /* nospec r8 */
- pushq $0 /* pt_regs->r9 = 0 */
+ pushq %r9 /* pt_regs->r9 */
xorl %r9d, %r9d /* nospec r9 */
- pushq $0 /* pt_regs->r10 = 0 */
+ pushq %r10 /* pt_regs->r10 */
xorl %r10d, %r10d /* nospec r10 */
- pushq $0 /* pt_regs->r11 = 0 */
+ pushq %r11 /* pt_regs->r11 */
xorl %r11d, %r11d /* nospec r11 */
pushq %rbx /* pt_regs->rbx */
xorl %ebx, %ebx /* nospec rbx */
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index d6b27da..14a2f99 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -396,3 +396,4 @@
382 i386 pkey_free sys_pkey_free __ia32_sys_pkey_free
383 i386 statx sys_statx __ia32_sys_statx
384 i386 arch_prctl sys_arch_prctl __ia32_compat_sys_arch_prctl
+385 i386 io_pgetevents sys_io_pgetevents __ia32_compat_sys_io_pgetevents
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 4dfe426..cd36232 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -341,6 +341,7 @@
330 common pkey_alloc __x64_sys_pkey_alloc
331 common pkey_free __x64_sys_pkey_free
332 common statx __x64_sys_statx
+333 common io_pgetevents __x64_sys_io_pgetevents
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index d998a48..261802b 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -44,14 +44,14 @@
targets += $(vdso_img_cfiles)
targets += $(vdso_img_sodbg) $(vdso_img-y:%=vdso%.so)
-export CPPFLAGS_vdso.lds += -P -C
+CPPFLAGS_vdso.lds += -P -C
VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
-Wl,--no-undefined \
-Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 \
$(DISABLE_LTO)
-$(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE
+$(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE
$(call if_changed,vdso)
HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/$(SUBARCH)/include/uapi
@@ -100,11 +100,8 @@
-Wl,-z,max-page-size=4096 \
-Wl,-z,common-page-size=4096
-# 64-bit objects to re-brand as x32
-vobjs64-for-x32 := $(filter-out $(vobjs-nox32),$(vobjs-y))
-
# x32-rebranded versions
-vobjx32s-y := $(vobjs64-for-x32:.o=-x32.o)
+vobjx32s-y := $(vobjs-y:.o=-x32.o)
# same thing, but in the output directory
vobjx32s := $(foreach F,$(vobjx32s-y),$(obj)/$F)
@@ -122,7 +119,7 @@
$(obj)/%.so: $(obj)/%.so.dbg
$(call if_changed,objcopy)
-$(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE
+$(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE
$(call if_changed,vdso)
CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
diff --git a/arch/x86/entry/vdso/vdso32/vdso-fakesections.c b/arch/x86/entry/vdso/vdso32/vdso-fakesections.c
deleted file mode 100644
index 541468e..0000000
--- a/arch/x86/entry/vdso/vdso32/vdso-fakesections.c
+++ /dev/null
@@ -1 +0,0 @@
-#include "../vdso-fakesections.c"
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 70b7845..7782cdb 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -107,7 +107,7 @@ static bool write_ok_or_segv(unsigned long ptr, size_t size)
thread->cr2 = ptr;
thread->trap_nr = X86_TRAP_PF;
- memset(&info, 0, sizeof(info));
+ clear_siginfo(&info);
info.si_signo = SIGSEGV;
info.si_errno = 0;
info.si_code = SEGV_MAPERR;
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 786fd87..4b98101 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -889,7 +889,7 @@ static void force_ibs_eilvt_setup(void)
if (!ibs_eilvt_valid())
goto out;
- pr_info("IBS: LVT offset %d assigned\n", offset);
+ pr_info("LVT offset %d assigned\n", offset);
return;
out:
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index f5cbbba..981ba5e 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -19,6 +19,7 @@
#include <asm/cpufeature.h>
#include <asm/perf_event.h>
#include <asm/msr.h>
+#include <asm/smp.h>
#define NUM_COUNTERS_NB 4
#define NUM_COUNTERS_L2 4
@@ -399,26 +400,8 @@ static int amd_uncore_cpu_starting(unsigned int cpu)
}
if (amd_uncore_llc) {
- unsigned int apicid = cpu_data(cpu).apicid;
- unsigned int nshared, subleaf, prev_eax = 0;
-
uncore = *per_cpu_ptr(amd_uncore_llc, cpu);
- /*
- * Iterate over Cache Topology Definition leaves until no
- * more cache descriptions are available.
- */
- for (subleaf = 0; subleaf < 5; subleaf++) {
- cpuid_count(0x8000001d, subleaf, &eax, &ebx, &ecx, &edx);
-
- /* EAX[0:4] gives type of cache */
- if (!(eax & 0x1f))
- break;
-
- prev_eax = eax;
- }
- nshared = ((prev_eax >> 14) & 0xfff) + 1;
-
- uncore->id = apicid - (apicid % nshared);
+ uncore->id = per_cpu(cpu_llc_id, cpu);
uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc);
*per_cpu_ptr(amd_uncore_llc, cpu) = uncore;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index a6006e7..6e461fb 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -27,6 +27,7 @@
#include <linux/cpu.h>
#include <linux/bitops.h>
#include <linux/device.h>
+#include <linux/nospec.h>
#include <asm/apic.h>
#include <asm/stacktrace.h>
@@ -304,17 +305,20 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event)
config = attr->config;
- cache_type = (config >> 0) & 0xff;
+ cache_type = (config >> 0) & 0xff;
if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
return -EINVAL;
+ cache_type = array_index_nospec(cache_type, PERF_COUNT_HW_CACHE_MAX);
cache_op = (config >> 8) & 0xff;
if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
return -EINVAL;
+ cache_op = array_index_nospec(cache_op, PERF_COUNT_HW_CACHE_OP_MAX);
cache_result = (config >> 16) & 0xff;
if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
return -EINVAL;
+ cache_result = array_index_nospec(cache_result, PERF_COUNT_HW_CACHE_RESULT_MAX);
val = hw_cache_event_ids[cache_type][cache_op][cache_result];
@@ -421,6 +425,8 @@ int x86_setup_perfctr(struct perf_event *event)
if (attr->config >= x86_pmu.max_events)
return -EINVAL;
+ attr->config = array_index_nospec((unsigned long)attr->config, x86_pmu.max_events);
+
/*
* The generic map:
*/
@@ -2391,7 +2397,7 @@ static unsigned long get_segment_base(unsigned int segment)
#ifdef CONFIG_IA32_EMULATION
-#include <asm/compat.h>
+#include <linux/compat.h>
static inline int
perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *entry)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 607bf56..707b2a9 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3339,7 +3339,8 @@ static void intel_pmu_cpu_starting(int cpu)
cpuc->lbr_sel = NULL;
- flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
+ if (x86_pmu.version > 1)
+ flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
if (!cpuc->shared_regs)
return;
@@ -3502,6 +3503,8 @@ static __initconst const struct x86_pmu core_pmu = {
.cpu_dying = intel_pmu_cpu_dying,
};
+static struct attribute *intel_pmu_attrs[];
+
static __initconst const struct x86_pmu intel_pmu = {
.name = "Intel",
.handle_irq = intel_pmu_handle_irq,
@@ -3533,6 +3536,8 @@ static __initconst const struct x86_pmu intel_pmu = {
.format_attrs = intel_arch3_formats_attr,
.events_sysfs_show = intel_event_sysfs_show,
+ .attrs = intel_pmu_attrs,
+
.cpu_prepare = intel_pmu_cpu_prepare,
.cpu_starting = intel_pmu_cpu_starting,
.cpu_dying = intel_pmu_cpu_dying,
@@ -3911,8 +3916,6 @@ __init int intel_pmu_init(void)
x86_pmu.max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters);
-
- x86_pmu.attrs = intel_pmu_attrs;
/*
* Quirk: v2 perfmon does not report fixed-purpose events, so
* assume at least 3 events, when not running in a hypervisor:
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 9aca448..9f8084f 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -92,6 +92,7 @@
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/perf_event.h>
+#include <linux/nospec.h>
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
#include "../perf_event.h"
@@ -302,6 +303,7 @@ static int cstate_pmu_event_init(struct perf_event *event)
} else if (event->pmu == &cstate_pkg_pmu) {
if (cfg >= PERF_CSTATE_PKG_EVENT_MAX)
return -EINVAL;
+ cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_PKG_EVENT_MAX);
if (!pkg_msr[cfg].attr)
return -EINVAL;
event->hw.event_base = pkg_msr[cfg].msr;
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 3b99394..8d016ce 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1194,7 +1194,7 @@ static int pt_event_addr_filters_validate(struct list_head *filters)
filter->action == PERF_ADDR_FILTER_ACTION_START)
return -EOPNOTSUPP;
- if (!filter->inode) {
+ if (!filter->path.dentry) {
if (!valid_kernel_ip(filter->offset))
return -EINVAL;
@@ -1221,7 +1221,7 @@ static void pt_event_addr_filters_sync(struct perf_event *event)
return;
list_for_each_entry(filter, &head->list, entry) {
- if (filter->inode && !offs[range]) {
+ if (filter->path.dentry && !offs[range]) {
msr_a = msr_b = 0;
} else {
/* apply the offset */
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index a7956fc..15b0737 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -203,7 +203,7 @@ static void uncore_assign_hw_event(struct intel_uncore_box *box,
hwc->idx = idx;
hwc->last_tag = ++box->tags[idx];
- if (hwc->idx == UNCORE_PMC_IDX_FIXED) {
+ if (uncore_pmc_fixed(hwc->idx)) {
hwc->event_base = uncore_fixed_ctr(box);
hwc->config_base = uncore_fixed_ctl(box);
return;
@@ -218,7 +218,9 @@ void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *e
u64 prev_count, new_count, delta;
int shift;
- if (event->hw.idx >= UNCORE_PMC_IDX_FIXED)
+ if (uncore_pmc_freerunning(event->hw.idx))
+ shift = 64 - uncore_freerunning_bits(box, event);
+ else if (uncore_pmc_fixed(event->hw.idx))
shift = 64 - uncore_fixed_ctr_bits(box);
else
shift = 64 - uncore_perf_ctr_bits(box);
@@ -449,15 +451,30 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int
return ret ? -EINVAL : 0;
}
-static void uncore_pmu_event_start(struct perf_event *event, int flags)
+void uncore_pmu_event_start(struct perf_event *event, int flags)
{
struct intel_uncore_box *box = uncore_event_to_box(event);
int idx = event->hw.idx;
- if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+ if (WARN_ON_ONCE(idx == -1 || idx >= UNCORE_PMC_IDX_MAX))
return;
- if (WARN_ON_ONCE(idx == -1 || idx >= UNCORE_PMC_IDX_MAX))
+ /*
+ * Free running counter is read-only and always active.
+ * Use the current counter value as start point.
+ * There is no overflow interrupt for free running counter.
+ * Use hrtimer to periodically poll the counter to avoid overflow.
+ */
+ if (uncore_pmc_freerunning(event->hw.idx)) {
+ list_add_tail(&event->active_entry, &box->active_list);
+ local64_set(&event->hw.prev_count,
+ uncore_read_counter(box, event));
+ if (box->n_active++ == 0)
+ uncore_pmu_start_hrtimer(box);
+ return;
+ }
+
+ if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
return;
event->hw.state = 0;
@@ -474,11 +491,20 @@ static void uncore_pmu_event_start(struct perf_event *event, int flags)
}
}
-static void uncore_pmu_event_stop(struct perf_event *event, int flags)
+void uncore_pmu_event_stop(struct perf_event *event, int flags)
{
struct intel_uncore_box *box = uncore_event_to_box(event);
struct hw_perf_event *hwc = &event->hw;
+ /* Cannot disable free running counter which is read-only */
+ if (uncore_pmc_freerunning(hwc->idx)) {
+ list_del(&event->active_entry);
+ if (--box->n_active == 0)
+ uncore_pmu_cancel_hrtimer(box);
+ uncore_perf_event_update(box, event);
+ return;
+ }
+
if (__test_and_clear_bit(hwc->idx, box->active_mask)) {
uncore_disable_event(box, event);
box->n_active--;
@@ -502,7 +528,7 @@ static void uncore_pmu_event_stop(struct perf_event *event, int flags)
}
}
-static int uncore_pmu_event_add(struct perf_event *event, int flags)
+int uncore_pmu_event_add(struct perf_event *event, int flags)
{
struct intel_uncore_box *box = uncore_event_to_box(event);
struct hw_perf_event *hwc = &event->hw;
@@ -512,6 +538,17 @@ static int uncore_pmu_event_add(struct perf_event *event, int flags)
if (!box)
return -ENODEV;
+ /*
+ * The free funning counter is assigned in event_init().
+ * The free running counter event and free running counter
+ * are 1:1 mapped. It doesn't need to be tracked in event_list.
+ */
+ if (uncore_pmc_freerunning(hwc->idx)) {
+ if (flags & PERF_EF_START)
+ uncore_pmu_event_start(event, 0);
+ return 0;
+ }
+
ret = n = uncore_collect_events(box, event, false);
if (ret < 0)
return ret;
@@ -563,13 +600,21 @@ static int uncore_pmu_event_add(struct perf_event *event, int flags)
return 0;
}
-static void uncore_pmu_event_del(struct perf_event *event, int flags)
+void uncore_pmu_event_del(struct perf_event *event, int flags)
{
struct intel_uncore_box *box = uncore_event_to_box(event);
int i;
uncore_pmu_event_stop(event, PERF_EF_UPDATE);
+ /*
+ * The event for free running counter is not tracked by event_list.
+ * It doesn't need to force event->hw.idx = -1 to reassign the counter.
+ * Because the event and the free running counter are 1:1 mapped.
+ */
+ if (uncore_pmc_freerunning(event->hw.idx))
+ return;
+
for (i = 0; i < box->n_events; i++) {
if (event == box->event_list[i]) {
uncore_put_event_constraint(box, event);
@@ -603,6 +648,10 @@ static int uncore_validate_group(struct intel_uncore_pmu *pmu,
struct intel_uncore_box *fake_box;
int ret = -EINVAL, n;
+ /* The free running counter is always active. */
+ if (uncore_pmc_freerunning(event->hw.idx))
+ return 0;
+
fake_box = uncore_alloc_box(pmu->type, NUMA_NO_NODE);
if (!fake_box)
return -ENOMEM;
@@ -690,6 +739,17 @@ static int uncore_pmu_event_init(struct perf_event *event)
/* fixed counters have event field hardcoded to zero */
hwc->config = 0ULL;
+ } else if (is_freerunning_event(event)) {
+ if (!check_valid_freerunning_event(box, event))
+ return -EINVAL;
+ event->hw.idx = UNCORE_PMC_IDX_FREERUNNING;
+ /*
+ * The free running counter event and free running counter
+ * are always 1:1 mapped.
+ * The free running counter is always active.
+ * Assign the free running counter here.
+ */
+ event->hw.event_base = uncore_freerunning_counter(box, event);
} else {
hwc->config = event->attr.config &
(pmu->type->event_mask | ((u64)pmu->type->event_mask_ext << 32));
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 414dc7e..c9e1e0b 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -12,8 +12,13 @@
#define UNCORE_FIXED_EVENT 0xff
#define UNCORE_PMC_IDX_MAX_GENERIC 8
+#define UNCORE_PMC_IDX_MAX_FIXED 1
+#define UNCORE_PMC_IDX_MAX_FREERUNNING 1
#define UNCORE_PMC_IDX_FIXED UNCORE_PMC_IDX_MAX_GENERIC
-#define UNCORE_PMC_IDX_MAX (UNCORE_PMC_IDX_FIXED + 1)
+#define UNCORE_PMC_IDX_FREERUNNING (UNCORE_PMC_IDX_FIXED + \
+ UNCORE_PMC_IDX_MAX_FIXED)
+#define UNCORE_PMC_IDX_MAX (UNCORE_PMC_IDX_FREERUNNING + \
+ UNCORE_PMC_IDX_MAX_FREERUNNING)
#define UNCORE_PCI_DEV_FULL_DATA(dev, func, type, idx) \
((dev << 24) | (func << 16) | (type << 8) | idx)
@@ -35,6 +40,7 @@ struct intel_uncore_ops;
struct intel_uncore_pmu;
struct intel_uncore_box;
struct uncore_event_desc;
+struct freerunning_counters;
struct intel_uncore_type {
const char *name;
@@ -42,6 +48,7 @@ struct intel_uncore_type {
int num_boxes;
int perf_ctr_bits;
int fixed_ctr_bits;
+ int num_freerunning_types;
unsigned perf_ctr;
unsigned event_ctl;
unsigned event_mask;
@@ -59,6 +66,7 @@ struct intel_uncore_type {
struct intel_uncore_pmu *pmus;
struct intel_uncore_ops *ops;
struct uncore_event_desc *event_descs;
+ struct freerunning_counters *freerunning;
const struct attribute_group *attr_groups[4];
struct pmu *pmu; /* for custom pmu ops */
};
@@ -129,6 +137,14 @@ struct uncore_event_desc {
const char *config;
};
+struct freerunning_counters {
+ unsigned int counter_base;
+ unsigned int counter_offset;
+ unsigned int box_offset;
+ unsigned int num_counters;
+ unsigned int bits;
+};
+
struct pci2phy_map {
struct list_head list;
int segment;
@@ -157,6 +173,16 @@ static ssize_t __uncore_##_var##_show(struct kobject *kobj, \
static struct kobj_attribute format_attr_##_var = \
__ATTR(_name, 0444, __uncore_##_var##_show, NULL)
+static inline bool uncore_pmc_fixed(int idx)
+{
+ return idx == UNCORE_PMC_IDX_FIXED;
+}
+
+static inline bool uncore_pmc_freerunning(int idx)
+{
+ return idx == UNCORE_PMC_IDX_FREERUNNING;
+}
+
static inline unsigned uncore_pci_box_ctl(struct intel_uncore_box *box)
{
return box->pmu->type->box_ctl;
@@ -214,6 +240,60 @@ static inline unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box)
return box->pmu->type->fixed_ctr + uncore_msr_box_offset(box);
}
+
+/*
+ * In the uncore document, there is no event-code assigned to free running
+ * counters. Some events need to be defined to indicate the free running
+ * counters. The events are encoded as event-code + umask-code.
+ *
+ * The event-code for all free running counters is 0xff, which is the same as
+ * the fixed counters.
+ *
+ * The umask-code is used to distinguish a fixed counter and a free running
+ * counter, and different types of free running counters.
+ * - For fixed counters, the umask-code is 0x0X.
+ * X indicates the index of the fixed counter, which starts from 0.
+ * - For free running counters, the umask-code uses the rest of the space.
+ * It would bare the format of 0xXY.
+ * X stands for the type of free running counters, which starts from 1.
+ * Y stands for the index of free running counters of same type, which
+ * starts from 0.
+ *
+ * For example, there are three types of IIO free running counters on Skylake
+ * server, IO CLOCKS counters, BANDWIDTH counters and UTILIZATION counters.
+ * The event-code for all the free running counters is 0xff.
+ * 'ioclk' is the first counter of IO CLOCKS. IO CLOCKS is the first type,
+ * which umask-code starts from 0x10.
+ * So 'ioclk' is encoded as event=0xff,umask=0x10
+ * 'bw_in_port2' is the third counter of BANDWIDTH counters. BANDWIDTH is
+ * the second type, which umask-code starts from 0x20.
+ * So 'bw_in_port2' is encoded as event=0xff,umask=0x22
+ */
+static inline unsigned int uncore_freerunning_idx(u64 config)
+{
+ return ((config >> 8) & 0xf);
+}
+
+#define UNCORE_FREERUNNING_UMASK_START 0x10
+
+static inline unsigned int uncore_freerunning_type(u64 config)
+{
+ return ((((config >> 8) - UNCORE_FREERUNNING_UMASK_START) >> 4) & 0xf);
+}
+
+static inline
+unsigned int uncore_freerunning_counter(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ unsigned int type = uncore_freerunning_type(event->attr.config);
+ unsigned int idx = uncore_freerunning_idx(event->attr.config);
+ struct intel_uncore_pmu *pmu = box->pmu;
+
+ return pmu->type->freerunning[type].counter_base +
+ pmu->type->freerunning[type].counter_offset * idx +
+ pmu->type->freerunning[type].box_offset * pmu->pmu_idx;
+}
+
static inline
unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx)
{
@@ -276,11 +356,52 @@ static inline int uncore_fixed_ctr_bits(struct intel_uncore_box *box)
return box->pmu->type->fixed_ctr_bits;
}
+static inline
+unsigned int uncore_freerunning_bits(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ unsigned int type = uncore_freerunning_type(event->attr.config);
+
+ return box->pmu->type->freerunning[type].bits;
+}
+
+static inline int uncore_num_freerunning(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ unsigned int type = uncore_freerunning_type(event->attr.config);
+
+ return box->pmu->type->freerunning[type].num_counters;
+}
+
+static inline int uncore_num_freerunning_types(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ return box->pmu->type->num_freerunning_types;
+}
+
+static inline bool check_valid_freerunning_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ unsigned int type = uncore_freerunning_type(event->attr.config);
+ unsigned int idx = uncore_freerunning_idx(event->attr.config);
+
+ return (type < uncore_num_freerunning_types(box, event)) &&
+ (idx < uncore_num_freerunning(box, event));
+}
+
static inline int uncore_num_counters(struct intel_uncore_box *box)
{
return box->pmu->type->num_counters;
}
+static inline bool is_freerunning_event(struct perf_event *event)
+{
+ u64 cfg = event->attr.config;
+
+ return ((cfg & UNCORE_FIXED_EVENT) == UNCORE_FIXED_EVENT) &&
+ (((cfg >> 8) & 0xff) >= UNCORE_FREERUNNING_UMASK_START);
+}
+
static inline void uncore_disable_box(struct intel_uncore_box *box)
{
if (box->pmu->type->ops->disable_box)
@@ -346,6 +467,10 @@ struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu
u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event);
void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
+void uncore_pmu_event_start(struct perf_event *event, int flags);
+void uncore_pmu_event_stop(struct perf_event *event, int flags);
+int uncore_pmu_event_add(struct perf_event *event, int flags);
+void uncore_pmu_event_del(struct perf_event *event, int flags);
void uncore_pmu_event_read(struct perf_event *event);
void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event);
struct event_constraint *
diff --git a/arch/x86/events/intel/uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c
index 93e7a83..173e267 100644
--- a/arch/x86/events/intel/uncore_nhmex.c
+++ b/arch/x86/events/intel/uncore_nhmex.c
@@ -246,7 +246,7 @@ static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct p
{
struct hw_perf_event *hwc = &event->hw;
- if (hwc->idx >= UNCORE_PMC_IDX_FIXED)
+ if (hwc->idx == UNCORE_PMC_IDX_FIXED)
wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0);
else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0)
wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index aee5e84..8527c3e 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -285,6 +285,15 @@ static struct uncore_event_desc snb_uncore_imc_events[] = {
#define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE 0x5054
#define SNB_UNCORE_PCI_IMC_CTR_BASE SNB_UNCORE_PCI_IMC_DATA_READS_BASE
+enum perf_snb_uncore_imc_freerunning_types {
+ SNB_PCI_UNCORE_IMC_DATA = 0,
+ SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX,
+};
+
+static struct freerunning_counters snb_uncore_imc_freerunning[] = {
+ [SNB_PCI_UNCORE_IMC_DATA] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, 0x4, 0x0, 2, 32 },
+};
+
static struct attribute *snb_uncore_imc_formats_attr[] = {
&format_attr_event.attr,
NULL,
@@ -341,9 +350,8 @@ static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf
}
/*
- * custom event_init() function because we define our own fixed, free
- * running counters, so we do not want to conflict with generic uncore
- * logic. Also simplifies processing
+ * Keep the custom event_init() function compatible with old event
+ * encoding for free running counters.
*/
static int snb_uncore_imc_event_init(struct perf_event *event)
{
@@ -405,11 +413,11 @@ static int snb_uncore_imc_event_init(struct perf_event *event)
switch (cfg) {
case SNB_UNCORE_PCI_IMC_DATA_READS:
base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE;
- idx = UNCORE_PMC_IDX_FIXED;
+ idx = UNCORE_PMC_IDX_FREERUNNING;
break;
case SNB_UNCORE_PCI_IMC_DATA_WRITES:
base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE;
- idx = UNCORE_PMC_IDX_FIXED + 1;
+ idx = UNCORE_PMC_IDX_FREERUNNING;
break;
default:
return -EINVAL;
@@ -430,75 +438,6 @@ static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_ev
return 0;
}
-static void snb_uncore_imc_event_start(struct perf_event *event, int flags)
-{
- struct intel_uncore_box *box = uncore_event_to_box(event);
- u64 count;
-
- if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
- return;
-
- event->hw.state = 0;
- box->n_active++;
-
- list_add_tail(&event->active_entry, &box->active_list);
-
- count = snb_uncore_imc_read_counter(box, event);
- local64_set(&event->hw.prev_count, count);
-
- if (box->n_active == 1)
- uncore_pmu_start_hrtimer(box);
-}
-
-static void snb_uncore_imc_event_stop(struct perf_event *event, int flags)
-{
- struct intel_uncore_box *box = uncore_event_to_box(event);
- struct hw_perf_event *hwc = &event->hw;
-
- if (!(hwc->state & PERF_HES_STOPPED)) {
- box->n_active--;
-
- WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
- hwc->state |= PERF_HES_STOPPED;
-
- list_del(&event->active_entry);
-
- if (box->n_active == 0)
- uncore_pmu_cancel_hrtimer(box);
- }
-
- if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
- /*
- * Drain the remaining delta count out of a event
- * that we are disabling:
- */
- uncore_perf_event_update(box, event);
- hwc->state |= PERF_HES_UPTODATE;
- }
-}
-
-static int snb_uncore_imc_event_add(struct perf_event *event, int flags)
-{
- struct intel_uncore_box *box = uncore_event_to_box(event);
- struct hw_perf_event *hwc = &event->hw;
-
- if (!box)
- return -ENODEV;
-
- hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
- if (!(flags & PERF_EF_START))
- hwc->state |= PERF_HES_ARCH;
-
- snb_uncore_imc_event_start(event, 0);
-
- return 0;
-}
-
-static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
-{
- snb_uncore_imc_event_stop(event, PERF_EF_UPDATE);
-}
-
int snb_pci2phy_map_init(int devid)
{
struct pci_dev *dev = NULL;
@@ -530,10 +469,10 @@ int snb_pci2phy_map_init(int devid)
static struct pmu snb_uncore_imc_pmu = {
.task_ctx_nr = perf_invalid_context,
.event_init = snb_uncore_imc_event_init,
- .add = snb_uncore_imc_event_add,
- .del = snb_uncore_imc_event_del,
- .start = snb_uncore_imc_event_start,
- .stop = snb_uncore_imc_event_stop,
+ .add = uncore_pmu_event_add,
+ .del = uncore_pmu_event_del,
+ .start = uncore_pmu_event_start,
+ .stop = uncore_pmu_event_stop,
.read = uncore_pmu_event_read,
};
@@ -552,12 +491,10 @@ static struct intel_uncore_type snb_uncore_imc = {
.name = "imc",
.num_counters = 2,
.num_boxes = 1,
- .fixed_ctr_bits = 32,
- .fixed_ctr = SNB_UNCORE_PCI_IMC_CTR_BASE,
+ .num_freerunning_types = SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX,
+ .freerunning = snb_uncore_imc_freerunning,
.event_descs = snb_uncore_imc_events,
.format_group = &snb_uncore_imc_format_group,
- .perf_ctr = SNB_UNCORE_PCI_IMC_DATA_READS_BASE,
- .event_mask = SNB_UNCORE_PCI_IMC_EVENT_MASK,
.ops = &snb_uncore_imc_ops,
.pmu = &snb_uncore_imc_pmu,
};
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index c98b943..87dc026 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3028,10 +3028,27 @@ static struct intel_uncore_type bdx_uncore_cbox = {
.format_group = &hswep_uncore_cbox_format_group,
};
+static struct intel_uncore_type bdx_uncore_sbox = {
+ .name = "sbox",
+ .num_counters = 4,
+ .num_boxes = 4,
+ .perf_ctr_bits = 48,
+ .event_ctl = HSWEP_S0_MSR_PMON_CTL0,
+ .perf_ctr = HSWEP_S0_MSR_PMON_CTR0,
+ .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
+ .box_ctl = HSWEP_S0_MSR_PMON_BOX_CTL,
+ .msr_offset = HSWEP_SBOX_MSR_OFFSET,
+ .ops = &hswep_uncore_sbox_msr_ops,
+ .format_group = &hswep_uncore_sbox_format_group,
+};
+
+#define BDX_MSR_UNCORE_SBOX 3
+
static struct intel_uncore_type *bdx_msr_uncores[] = {
&bdx_uncore_ubox,
&bdx_uncore_cbox,
&hswep_uncore_pcu,
+ &bdx_uncore_sbox,
NULL,
};
@@ -3043,10 +3060,25 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = {
void bdx_uncore_cpu_init(void)
{
+ int pkg = topology_phys_to_logical_pkg(0);
+
if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
uncore_msr_uncores = bdx_msr_uncores;
+ /* BDX-DE doesn't have SBOX */
+ if (boot_cpu_data.x86_model == 86) {
+ uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
+ /* Detect systems with no SBOXes */
+ } else if (uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]) {
+ struct pci_dev *pdev;
+ u32 capid4;
+
+ pdev = uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3];
+ pci_read_config_dword(pdev, 0x94, &capid4);
+ if (((capid4 >> 6) & 0x3) == 0)
+ bdx_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
+ }
hswep_uncore_pcu.constraints = bdx_uncore_pcu_constraints;
}
@@ -3264,6 +3296,11 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = {
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46),
.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2),
},
+ { /* PCU.3 (for Capability registers) */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ HSWEP_PCI_PCU_3),
+ },
{ /* end: all zeroes */ }
};
@@ -3485,6 +3522,87 @@ static struct intel_uncore_type skx_uncore_iio = {
.format_group = &skx_uncore_iio_format_group,
};
+enum perf_uncore_iio_freerunning_type_id {
+ SKX_IIO_MSR_IOCLK = 0,
+ SKX_IIO_MSR_BW = 1,
+ SKX_IIO_MSR_UTIL = 2,
+
+ SKX_IIO_FREERUNNING_TYPE_MAX,
+};
+
+
+static struct freerunning_counters skx_iio_freerunning[] = {
+ [SKX_IIO_MSR_IOCLK] = { 0xa45, 0x1, 0x20, 1, 36 },
+ [SKX_IIO_MSR_BW] = { 0xb00, 0x1, 0x10, 8, 36 },
+ [SKX_IIO_MSR_UTIL] = { 0xb08, 0x1, 0x10, 8, 36 },
+};
+
+static struct uncore_event_desc skx_uncore_iio_freerunning_events[] = {
+ /* Free-Running IO CLOCKS Counter */
+ INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"),
+ /* Free-Running IIO BANDWIDTH Counters */
+ INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port0, "event=0xff,umask=0x24"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port0.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port0.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port1, "event=0xff,umask=0x25"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port1.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port1.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port2, "event=0xff,umask=0x26"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port2.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port2.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port3, "event=0xff,umask=0x27"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port3.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_out_port3.unit, "MiB"),
+ /* Free-running IIO UTILIZATION Counters */
+ INTEL_UNCORE_EVENT_DESC(util_in_port0, "event=0xff,umask=0x30"),
+ INTEL_UNCORE_EVENT_DESC(util_out_port0, "event=0xff,umask=0x31"),
+ INTEL_UNCORE_EVENT_DESC(util_in_port1, "event=0xff,umask=0x32"),
+ INTEL_UNCORE_EVENT_DESC(util_out_port1, "event=0xff,umask=0x33"),
+ INTEL_UNCORE_EVENT_DESC(util_in_port2, "event=0xff,umask=0x34"),
+ INTEL_UNCORE_EVENT_DESC(util_out_port2, "event=0xff,umask=0x35"),
+ INTEL_UNCORE_EVENT_DESC(util_in_port3, "event=0xff,umask=0x36"),
+ INTEL_UNCORE_EVENT_DESC(util_out_port3, "event=0xff,umask=0x37"),
+ { /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops skx_uncore_iio_freerunning_ops = {
+ .read_counter = uncore_msr_read_counter,
+};
+
+static struct attribute *skx_uncore_iio_freerunning_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ NULL,
+};
+
+static const struct attribute_group skx_uncore_iio_freerunning_format_group = {
+ .name = "format",
+ .attrs = skx_uncore_iio_freerunning_formats_attr,
+};
+
+static struct intel_uncore_type skx_uncore_iio_free_running = {
+ .name = "iio_free_running",
+ .num_counters = 17,
+ .num_boxes = 6,
+ .num_freerunning_types = SKX_IIO_FREERUNNING_TYPE_MAX,
+ .freerunning = skx_iio_freerunning,
+ .ops = &skx_uncore_iio_freerunning_ops,
+ .event_descs = skx_uncore_iio_freerunning_events,
+ .format_group = &skx_uncore_iio_freerunning_format_group,
+};
+
static struct attribute *skx_uncore_formats_attr[] = {
&format_attr_event.attr,
&format_attr_umask.attr,
@@ -3558,6 +3676,7 @@ static struct intel_uncore_type *skx_msr_uncores[] = {
&skx_uncore_ubox,
&skx_uncore_chabox,
&skx_uncore_iio,
+ &skx_uncore_iio_free_running,
&skx_uncore_irp,
&skx_uncore_pcu,
NULL,
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index e7edf19..b4771a6 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/perf_event.h>
+#include <linux/nospec.h>
#include <asm/intel-family.h>
enum perf_msr_id {
@@ -158,9 +159,6 @@ static int msr_event_init(struct perf_event *event)
if (event->attr.type != event->pmu->type)
return -ENOENT;
- if (cfg >= PERF_MSR_EVENT_MAX)
- return -EINVAL;
-
/* unsupported modes and filters */
if (event->attr.exclude_user ||
event->attr.exclude_kernel ||
@@ -171,6 +169,11 @@ static int msr_event_init(struct perf_event *event)
event->attr.sample_period) /* no sampling */
return -EINVAL;
+ if (cfg >= PERF_MSR_EVENT_MAX)
+ return -EINVAL;
+
+ cfg = array_index_nospec((unsigned long)cfg, PERF_MSR_EVENT_MAX);
+
if (!msr[cfg].attr)
return -EINVAL;
diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile
index 367a820..b173d40 100644
--- a/arch/x86/hyperv/Makefile
+++ b/arch/x86/hyperv/Makefile
@@ -1 +1,2 @@
-obj-y := hv_init.o mmu.o
+obj-y := hv_init.o mmu.o
+obj-$(CONFIG_X86_64) += hv_apic.o
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
new file mode 100644
index 0000000..f688554
--- /dev/null
+++ b/arch/x86/hyperv/hv_apic.c
@@ -0,0 +1,256 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Hyper-V specific APIC code.
+ *
+ * Copyright (C) 2018, Microsoft, Inc.
+ *
+ * Author : K. Y. Srinivasan <kys@microsoft.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT. See the GNU General Public License for more
+ * details.
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/version.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+#include <linux/clockchips.h>
+#include <linux/hyperv.h>
+#include <linux/slab.h>
+#include <linux/cpuhotplug.h>
+#include <asm/hypervisor.h>
+#include <asm/mshyperv.h>
+#include <asm/apic.h>
+
+static struct apic orig_apic;
+
+static u64 hv_apic_icr_read(void)
+{
+ u64 reg_val;
+
+ rdmsrl(HV_X64_MSR_ICR, reg_val);
+ return reg_val;
+}
+
+static void hv_apic_icr_write(u32 low, u32 id)
+{
+ u64 reg_val;
+
+ reg_val = SET_APIC_DEST_FIELD(id);
+ reg_val = reg_val << 32;
+ reg_val |= low;
+
+ wrmsrl(HV_X64_MSR_ICR, reg_val);
+}
+
+static u32 hv_apic_read(u32 reg)
+{
+ u32 reg_val, hi;
+
+ switch (reg) {
+ case APIC_EOI:
+ rdmsr(HV_X64_MSR_EOI, reg_val, hi);
+ return reg_val;
+ case APIC_TASKPRI:
+ rdmsr(HV_X64_MSR_TPR, reg_val, hi);
+ return reg_val;
+
+ default:
+ return native_apic_mem_read(reg);
+ }
+}
+
+static void hv_apic_write(u32 reg, u32 val)
+{
+ switch (reg) {
+ case APIC_EOI:
+ wrmsr(HV_X64_MSR_EOI, val, 0);
+ break;
+ case APIC_TASKPRI:
+ wrmsr(HV_X64_MSR_TPR, val, 0);
+ break;
+ default:
+ native_apic_mem_write(reg, val);
+ }
+}
+
+static void hv_apic_eoi_write(u32 reg, u32 val)
+{
+ wrmsr(HV_X64_MSR_EOI, val, 0);
+}
+
+/*
+ * IPI implementation on Hyper-V.
+ */
+static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
+{
+ struct ipi_arg_ex **arg;
+ struct ipi_arg_ex *ipi_arg;
+ unsigned long flags;
+ int nr_bank = 0;
+ int ret = 1;
+
+ local_irq_save(flags);
+ arg = (struct ipi_arg_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
+
+ ipi_arg = *arg;
+ if (unlikely(!ipi_arg))
+ goto ipi_mask_ex_done;
+
+ ipi_arg->vector = vector;
+ ipi_arg->reserved = 0;
+ ipi_arg->vp_set.valid_bank_mask = 0;
+
+ if (!cpumask_equal(mask, cpu_present_mask)) {
+ ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+ nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask);
+ }
+ if (!nr_bank)
+ ipi_arg->vp_set.format = HV_GENERIC_SET_ALL;
+
+ ret = hv_do_rep_hypercall(HVCALL_SEND_IPI_EX, 0, nr_bank,
+ ipi_arg, NULL);
+
+ipi_mask_ex_done:
+ local_irq_restore(flags);
+ return ((ret == 0) ? true : false);
+}
+
+static bool __send_ipi_mask(const struct cpumask *mask, int vector)
+{
+ int cur_cpu, vcpu;
+ struct ipi_arg_non_ex **arg;
+ struct ipi_arg_non_ex *ipi_arg;
+ int ret = 1;
+ unsigned long flags;
+
+ if (cpumask_empty(mask))
+ return true;
+
+ if (!hv_hypercall_pg)
+ return false;
+
+ if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
+ return false;
+
+ if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
+ return __send_ipi_mask_ex(mask, vector);
+
+ local_irq_save(flags);
+ arg = (struct ipi_arg_non_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
+
+ ipi_arg = *arg;
+ if (unlikely(!ipi_arg))
+ goto ipi_mask_done;
+
+ ipi_arg->vector = vector;
+ ipi_arg->reserved = 0;
+ ipi_arg->cpu_mask = 0;
+
+ for_each_cpu(cur_cpu, mask) {
+ vcpu = hv_cpu_number_to_vp_number(cur_cpu);
+ /*
+ * This particular version of the IPI hypercall can
+ * only target upto 64 CPUs.
+ */
+ if (vcpu >= 64)
+ goto ipi_mask_done;
+
+ __set_bit(vcpu, (unsigned long *)&ipi_arg->cpu_mask);
+ }
+
+ ret = hv_do_hypercall(HVCALL_SEND_IPI, ipi_arg, NULL);
+
+ipi_mask_done:
+ local_irq_restore(flags);
+ return ((ret == 0) ? true : false);
+}
+
+static bool __send_ipi_one(int cpu, int vector)
+{
+ struct cpumask mask = CPU_MASK_NONE;
+
+ cpumask_set_cpu(cpu, &mask);
+ return __send_ipi_mask(&mask, vector);
+}
+
+static void hv_send_ipi(int cpu, int vector)
+{
+ if (!__send_ipi_one(cpu, vector))
+ orig_apic.send_IPI(cpu, vector);
+}
+
+static void hv_send_ipi_mask(const struct cpumask *mask, int vector)
+{
+ if (!__send_ipi_mask(mask, vector))
+ orig_apic.send_IPI_mask(mask, vector);
+}
+
+static void hv_send_ipi_mask_allbutself(const struct cpumask *mask, int vector)
+{
+ unsigned int this_cpu = smp_processor_id();
+ struct cpumask new_mask;
+ const struct cpumask *local_mask;
+
+ cpumask_copy(&new_mask, mask);
+ cpumask_clear_cpu(this_cpu, &new_mask);
+ local_mask = &new_mask;
+ if (!__send_ipi_mask(local_mask, vector))
+ orig_apic.send_IPI_mask_allbutself(mask, vector);
+}
+
+static void hv_send_ipi_allbutself(int vector)
+{
+ hv_send_ipi_mask_allbutself(cpu_online_mask, vector);
+}
+
+static void hv_send_ipi_all(int vector)
+{
+ if (!__send_ipi_mask(cpu_online_mask, vector))
+ orig_apic.send_IPI_all(vector);
+}
+
+static void hv_send_ipi_self(int vector)
+{
+ if (!__send_ipi_one(smp_processor_id(), vector))
+ orig_apic.send_IPI_self(vector);
+}
+
+void __init hv_apic_init(void)
+{
+ if (ms_hyperv.hints & HV_X64_CLUSTER_IPI_RECOMMENDED) {
+ if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
+ pr_info("Hyper-V: Using ext hypercalls for IPI\n");
+ else
+ pr_info("Hyper-V: Using IPI hypercalls\n");
+ /*
+ * Set the IPI entry points.
+ */
+ orig_apic = *apic;
+
+ apic->send_IPI = hv_send_ipi;
+ apic->send_IPI_mask = hv_send_ipi_mask;
+ apic->send_IPI_mask_allbutself = hv_send_ipi_mask_allbutself;
+ apic->send_IPI_allbutself = hv_send_ipi_allbutself;
+ apic->send_IPI_all = hv_send_ipi_all;
+ apic->send_IPI_self = hv_send_ipi_self;
+ }
+
+ if (ms_hyperv.hints & HV_X64_APIC_ACCESS_RECOMMENDED) {
+ pr_info("Hyper-V: Using MSR based APIC access\n");
+ apic_set_eoi_write(hv_apic_eoi_write);
+ apic->read = hv_apic_read;
+ apic->write = hv_apic_write;
+ apic->icr_write = hv_apic_icr_write;
+ apic->icr_read = hv_apic_icr_read;
+ }
+}
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index cfecc22..4c431e1c 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -91,12 +91,19 @@ EXPORT_SYMBOL_GPL(hv_vp_index);
struct hv_vp_assist_page **hv_vp_assist_page;
EXPORT_SYMBOL_GPL(hv_vp_assist_page);
+void __percpu **hyperv_pcpu_input_arg;
+EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg);
+
u32 hv_max_vp_index;
static int hv_cpu_init(unsigned int cpu)
{
u64 msr_vp_index;
struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()];
+ void **input_arg;
+
+ input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
+ *input_arg = page_address(alloc_page(GFP_KERNEL));
hv_get_vp_index(msr_vp_index);
@@ -217,6 +224,16 @@ static int hv_cpu_die(unsigned int cpu)
{
struct hv_reenlightenment_control re_ctrl;
unsigned int new_cpu;
+ unsigned long flags;
+ void **input_arg;
+ void *input_pg = NULL;
+
+ local_irq_save(flags);
+ input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
+ input_pg = *input_arg;
+ *input_arg = NULL;
+ local_irq_restore(flags);
+ free_page((unsigned long)input_pg);
if (hv_vp_assist_page && hv_vp_assist_page[cpu])
wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, 0);
@@ -242,8 +259,9 @@ static int hv_cpu_die(unsigned int cpu)
*
* 1. Setup the hypercall page.
* 2. Register Hyper-V specific clocksource.
+ * 3. Setup Hyper-V specific APIC entry points.
*/
-void hyperv_init(void)
+void __init hyperv_init(void)
{
u64 guest_id, required_msrs;
union hv_x64_msr_hypercall_contents hypercall_msr;
@@ -259,6 +277,16 @@ void hyperv_init(void)
if ((ms_hyperv.features & required_msrs) != required_msrs)
return;
+ /*
+ * Allocate the per-CPU state for the hypercall input arg.
+ * If this allocation fails, we will not be able to setup
+ * (per-CPU) hypercall input page and thus this failure is
+ * fatal on Hyper-V.
+ */
+ hyperv_pcpu_input_arg = alloc_percpu(void *);
+
+ BUG_ON(hyperv_pcpu_input_arg == NULL);
+
/* Allocate percpu VP index */
hv_vp_index = kmalloc_array(num_possible_cpus(), sizeof(*hv_vp_index),
GFP_KERNEL);
@@ -296,7 +324,7 @@ void hyperv_init(void)
hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
- hyper_alloc_mmu();
+ hv_apic_init();
/*
* Register Hyper-V specific clocksource.
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index 56c9eba..5f053d7 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -25,20 +25,13 @@ struct hv_flush_pcpu {
struct hv_flush_pcpu_ex {
u64 address_space;
u64 flags;
- struct {
- u64 format;
- u64 valid_bank_mask;
- u64 bank_contents[];
- } hv_vp_set;
+ struct hv_vpset hv_vp_set;
u64 gva_list[];
};
/* Each gva in gva_list encodes up to 4096 pages to flush */
#define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE)
-static struct hv_flush_pcpu __percpu **pcpu_flush;
-
-static struct hv_flush_pcpu_ex __percpu **pcpu_flush_ex;
/*
* Fills in gva_list starting from offset. Returns the number of items added.
@@ -70,41 +63,6 @@ static inline int fill_gva_list(u64 gva_list[], int offset,
return gva_n - offset;
}
-/* Return the number of banks in the resulting vp_set */
-static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush,
- const struct cpumask *cpus)
-{
- int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1;
-
- /* valid_bank_mask can represent up to 64 banks */
- if (hv_max_vp_index / 64 >= 64)
- return 0;
-
- /*
- * Clear all banks up to the maximum possible bank as hv_flush_pcpu_ex
- * structs are not cleared between calls, we risk flushing unneeded
- * vCPUs otherwise.
- */
- for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++)
- flush->hv_vp_set.bank_contents[vcpu_bank] = 0;
-
- /*
- * Some banks may end up being empty but this is acceptable.
- */
- for_each_cpu(cpu, cpus) {
- vcpu = hv_cpu_number_to_vp_number(cpu);
- vcpu_bank = vcpu / 64;
- vcpu_offset = vcpu % 64;
- __set_bit(vcpu_offset, (unsigned long *)
- &flush->hv_vp_set.bank_contents[vcpu_bank]);
- if (vcpu_bank >= nr_bank)
- nr_bank = vcpu_bank + 1;
- }
- flush->hv_vp_set.valid_bank_mask = GENMASK_ULL(nr_bank - 1, 0);
-
- return nr_bank;
-}
-
static void hyperv_flush_tlb_others(const struct cpumask *cpus,
const struct flush_tlb_info *info)
{
@@ -116,7 +74,7 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
trace_hyperv_mmu_flush_tlb_others(cpus, info);
- if (!pcpu_flush || !hv_hypercall_pg)
+ if (!hv_hypercall_pg)
goto do_native;
if (cpumask_empty(cpus))
@@ -124,10 +82,8 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
local_irq_save(flags);
- flush_pcpu = this_cpu_ptr(pcpu_flush);
-
- if (unlikely(!*flush_pcpu))
- *flush_pcpu = page_address(alloc_page(GFP_ATOMIC));
+ flush_pcpu = (struct hv_flush_pcpu **)
+ this_cpu_ptr(hyperv_pcpu_input_arg);
flush = *flush_pcpu;
@@ -203,7 +159,7 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
trace_hyperv_mmu_flush_tlb_others(cpus, info);
- if (!pcpu_flush_ex || !hv_hypercall_pg)
+ if (!hv_hypercall_pg)
goto do_native;
if (cpumask_empty(cpus))
@@ -211,10 +167,8 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
local_irq_save(flags);
- flush_pcpu = this_cpu_ptr(pcpu_flush_ex);
-
- if (unlikely(!*flush_pcpu))
- *flush_pcpu = page_address(alloc_page(GFP_ATOMIC));
+ flush_pcpu = (struct hv_flush_pcpu_ex **)
+ this_cpu_ptr(hyperv_pcpu_input_arg);
flush = *flush_pcpu;
@@ -239,8 +193,8 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
flush->hv_vp_set.valid_bank_mask = 0;
if (!cpumask_equal(cpus, cpu_present_mask)) {
- flush->hv_vp_set.format = HV_GENERIC_SET_SPARCE_4K;
- nr_bank = cpumask_to_vp_set(flush, cpus);
+ flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+ nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus);
}
if (!nr_bank) {
@@ -296,14 +250,3 @@ void hyperv_setup_mmu_ops(void)
pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others_ex;
}
}
-
-void hyper_alloc_mmu(void)
-{
- if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED))
- return;
-
- if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
- pcpu_flush = alloc_percpu(struct hv_flush_pcpu *);
- else
- pcpu_flush_ex = alloc_percpu(struct hv_flush_pcpu_ex *);
-}
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 386a690..219faae 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -136,7 +136,6 @@
#endif
#ifndef __ASSEMBLY__
-#ifndef __BPF__
/*
* This output constraint should be used for any inline asm which has a "call"
* instruction. Otherwise the asm may be inserted before the frame pointer
@@ -146,6 +145,5 @@
register unsigned long current_stack_pointer asm(_ASM_SP);
#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
#endif
-#endif
#endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/cacheinfo.h b/arch/x86/include/asm/cacheinfo.h
new file mode 100644
index 0000000..e958e28
--- /dev/null
+++ b/arch/x86/include/asm/cacheinfo.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_CACHEINFO_H
+#define _ASM_X86_CACHEINFO_H
+
+void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id);
+
+#endif /* _ASM_X86_CACHEINFO_H */
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index e1c8dab..fb97cf7 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -17,7 +17,6 @@
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
-typedef s32 compat_time_t;
typedef s32 compat_clock_t;
typedef s32 compat_pid_t;
typedef u16 __compat_uid_t;
@@ -46,16 +45,6 @@ typedef u32 compat_u32;
typedef u64 __attribute__((aligned(4))) compat_u64;
typedef u32 compat_uptr_t;
-struct compat_timespec {
- compat_time_t tv_sec;
- s32 tv_nsec;
-};
-
-struct compat_timeval {
- compat_time_t tv_sec;
- s32 tv_usec;
-};
-
struct compat_stat {
compat_dev_t st_dev;
u16 __pad1;
@@ -145,10 +134,10 @@ struct compat_ipc64_perm {
struct compat_semid64_ds {
struct compat_ipc64_perm sem_perm;
- compat_time_t sem_otime;
- compat_ulong_t __unused1;
- compat_time_t sem_ctime;
- compat_ulong_t __unused2;
+ compat_ulong_t sem_otime;
+ compat_ulong_t sem_otime_high;
+ compat_ulong_t sem_ctime;
+ compat_ulong_t sem_ctime_high;
compat_ulong_t sem_nsems;
compat_ulong_t __unused3;
compat_ulong_t __unused4;
@@ -156,12 +145,12 @@ struct compat_semid64_ds {
struct compat_msqid64_ds {
struct compat_ipc64_perm msg_perm;
- compat_time_t msg_stime;
- compat_ulong_t __unused1;
- compat_time_t msg_rtime;
- compat_ulong_t __unused2;
- compat_time_t msg_ctime;
- compat_ulong_t __unused3;
+ compat_ulong_t msg_stime;
+ compat_ulong_t msg_stime_high;
+ compat_ulong_t msg_rtime;
+ compat_ulong_t msg_rtime_high;
+ compat_ulong_t msg_ctime;
+ compat_ulong_t msg_ctime_high;
compat_ulong_t msg_cbytes;
compat_ulong_t msg_qnum;
compat_ulong_t msg_qbytes;
@@ -174,12 +163,12 @@ struct compat_msqid64_ds {
struct compat_shmid64_ds {
struct compat_ipc64_perm shm_perm;
compat_size_t shm_segsz;
- compat_time_t shm_atime;
- compat_ulong_t __unused1;
- compat_time_t shm_dtime;
- compat_ulong_t __unused2;
- compat_time_t shm_ctime;
- compat_ulong_t __unused3;
+ compat_ulong_t shm_atime;
+ compat_ulong_t shm_atime_high;
+ compat_ulong_t shm_dtime;
+ compat_ulong_t shm_dtime_high;
+ compat_ulong_t shm_ctime;
+ compat_ulong_t shm_ctime_high;
compat_pid_t shm_cpid;
compat_pid_t shm_lpid;
compat_ulong_t shm_nattch;
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index b27da96..aced6c9 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -140,6 +140,20 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
+#if defined(__clang__) && !defined(CC_HAVE_ASM_GOTO)
+
+/*
+ * Workaround for the sake of BPF compilation which utilizes kernel
+ * headers, but clang does not support ASM GOTO and fails the build.
+ */
+#ifndef __BPF_TRACING__
+#warning "Compiler lacks ASM_GOTO support. Add -D __BPF_TRACING__ to your compiler arguments"
+#endif
+
+#define static_cpu_has(bit) boot_cpu_has(bit)
+
+#else
+
/*
* Static testing of CPU features. Used the same as boot_cpu_has().
* These will statically patch the target code for additional
@@ -195,6 +209,7 @@ static __always_inline __pure bool _static_cpu_has(u16 bit)
boot_cpu_has(bit) : \
_static_cpu_has(bit) \
)
+#endif
#define cpu_has_bug(c, bit) cpu_has(c, (bit))
#define set_cpu_bug(c, bit) set_cpu_cap(c, (bit))
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index d554c11..fb00a2f 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -198,7 +198,6 @@
#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */
#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */
#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
-
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */
@@ -207,13 +206,19 @@
#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
#define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */
-
+#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
+#define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */
#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */
#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */
#define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */
-
#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */
+#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */
+#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* "" AMD SSBD implementation via LS_CFG MSR */
+#define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
@@ -274,9 +279,10 @@
#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
#define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */
#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */
-#define X86_FEATURE_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */
-#define X86_FEATURE_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */
-#define X86_FEATURE_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */
+#define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */
+#define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */
/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */
@@ -320,6 +326,7 @@
#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */
#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */
+#define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */
/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */
@@ -333,6 +340,7 @@
#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */
#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
+#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */
/*
* BUG word(s)
@@ -362,5 +370,6 @@
#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
+#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 89ce4bf..ce4d176 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -30,10 +30,7 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
return dma_ops;
}
-int arch_dma_supported(struct device *dev, u64 mask);
-#define arch_dma_supported arch_dma_supported
-
-bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp);
+bool arch_dma_alloc_attrs(struct device **dev);
#define arch_dma_alloc_attrs arch_dma_alloc_attrs
#endif
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 09ad885..c18ed65 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -46,10 +46,24 @@ int ftrace_int3_handler(struct pt_regs *regs);
#endif /* CONFIG_FUNCTION_TRACER */
-#if !defined(__ASSEMBLY__) && !defined(COMPILE_OFFSETS)
+#ifndef __ASSEMBLY__
+
+#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
+{
+ /*
+ * Compare the symbol name with the system call name. Skip the
+ * "__x64_sys", "__ia32_sys" or simple "sys" prefix.
+ */
+ return !strcmp(sym + 3, name + 3) ||
+ (!strncmp(sym, "__x64_", 6) && !strcmp(sym + 9, name + 3)) ||
+ (!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3));
+}
+
+#ifndef COMPILE_OFFSETS
#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_IA32_EMULATION)
-#include <asm/compat.h>
+#include <linux/compat.h>
/*
* Because ia32 syscalls do not map to x86_64 syscall numbers
@@ -67,6 +81,7 @@ static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs)
return false;
}
#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_IA32_EMULATION */
-#endif /* !__ASSEMBLY__ && !COMPILE_OFFSETS */
+#endif /* !COMPILE_OFFSETS */
+#endif /* !__ASSEMBLY__ */
#endif /* _ASM_X86_FTRACE_H */
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 5ea2afd..740a428a 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -50,14 +50,6 @@ DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
#define inc_irq_stat(member) this_cpu_inc(irq_stat.member)
-#define local_softirq_pending() this_cpu_read(irq_stat.__softirq_pending)
-
-#define __ARCH_SET_SOFTIRQ_PENDING
-
-#define set_softirq_pending(x) \
- this_cpu_write(irq_stat.__softirq_pending, (x))
-#define or_softirq_pending(x) this_cpu_or(irq_stat.__softirq_pending, (x))
-
extern void ack_bad_irq(unsigned int irq);
extern u64 arch_irq_stat_cpu(unsigned int cpu);
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 416cb0e..3bfa92c 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -164,6 +164,11 @@
*/
#define HV_X64_DEPRECATING_AEOI_RECOMMENDED (1 << 9)
+/*
+ * Recommend using cluster IPI hypercalls.
+ */
+#define HV_X64_CLUSTER_IPI_RECOMMENDED (1 << 10)
+
/* Recommend using the newer ExProcessorMasks interface */
#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED (1 << 11)
@@ -329,12 +334,17 @@ struct hv_tsc_emulation_status {
#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK \
(~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1))
+#define HV_IPI_LOW_VECTOR 0x10
+#define HV_IPI_HIGH_VECTOR 0xff
+
/* Declare the various hypercall operations. */
#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE 0x0002
#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST 0x0003
#define HVCALL_NOTIFY_LONG_SPIN_WAIT 0x0008
+#define HVCALL_SEND_IPI 0x000b
#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX 0x0013
#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX 0x0014
+#define HVCALL_SEND_IPI_EX 0x0015
#define HVCALL_POST_MESSAGE 0x005c
#define HVCALL_SIGNAL_EVENT 0x005d
@@ -360,7 +370,7 @@ struct hv_tsc_emulation_status {
#define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT BIT(3)
enum HV_GENERIC_SET_FORMAT {
- HV_GENERIC_SET_SPARCE_4K,
+ HV_GENERIC_SET_SPARSE_4K,
HV_GENERIC_SET_ALL,
};
@@ -706,4 +716,22 @@ struct hv_enlightened_vmcs {
#define HV_STIMER_AUTOENABLE (1ULL << 3)
#define HV_STIMER_SINT(config) (__u8)(((config) >> 16) & 0x0F)
+struct ipi_arg_non_ex {
+ u32 vector;
+ u32 reserved;
+ u64 cpu_mask;
+};
+
+struct hv_vpset {
+ u64 format;
+ u64 valid_bank_mask;
+ u64 bank_contents[];
+};
+
+struct ipi_arg_ex {
+ u32 vector;
+ u32 reserved;
+ struct hv_vpset vp_set;
+};
+
#endif
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index b3e32b0..c2c01f8 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -208,4 +208,22 @@ static inline int insn_offset_immediate(struct insn *insn)
return insn_offset_displacement(insn) + insn->displacement.nbytes;
}
+#define POP_SS_OPCODE 0x1f
+#define MOV_SREG_OPCODE 0x8e
+
+/*
+ * Intel SDM Vol.3A 6.8.3 states;
+ * "Any single-step trap that would be delivered following the MOV to SS
+ * instruction or POP to SS instruction (because EFLAGS.TF is 1) is
+ * suppressed."
+ * This function returns true if @insn is MOV SS or POP SS. On these
+ * instructions, single stepping is suppressed.
+ */
+static inline int insn_masking_exception(struct insn *insn)
+{
+ return insn->opcode.bytes[0] == POP_SS_OPCODE ||
+ (insn->opcode.bytes[0] == MOV_SREG_OPCODE &&
+ X86_MODRM_REG(insn->modrm.bytes[0]) == 2);
+}
+
#endif /* _ASM_X86_INSN_H */
diff --git a/arch/x86/include/asm/intel_mid_vrtc.h b/arch/x86/include/asm/intel_mid_vrtc.h
index 3555501..0b44b1a 100644
--- a/arch/x86/include/asm/intel_mid_vrtc.h
+++ b/arch/x86/include/asm/intel_mid_vrtc.h
@@ -4,7 +4,7 @@
extern unsigned char vrtc_cmos_read(unsigned char reg);
extern void vrtc_cmos_write(unsigned char val, unsigned char reg);
-extern void vrtc_get_time(struct timespec *now);
-extern int vrtc_set_mmss(const struct timespec *now);
+extern void vrtc_get_time(struct timespec64 *now);
+extern int vrtc_set_mmss(const struct timespec64 *now);
#endif
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index f6e5b93..6de6484 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -94,10 +94,10 @@ build_mmio_write(__writel, "l", unsigned int, "r", )
#ifdef CONFIG_X86_64
-build_mmio_read(readq, "q", unsigned long, "=r", :"memory")
-build_mmio_read(__readq, "q", unsigned long, "=r", )
-build_mmio_write(writeq, "q", unsigned long, "r", :"memory")
-build_mmio_write(__writeq, "q", unsigned long, "r", )
+build_mmio_read(readq, "q", u64, "=r", :"memory")
+build_mmio_read(__readq, "q", u64, "=r", )
+build_mmio_write(writeq, "q", u64, "r", :"memory")
+build_mmio_write(__writeq, "q", u64, "r", )
#define readq_relaxed(a) __readq(a)
#define writeq_relaxed(v, a) __writeq(v, a)
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 404c5fd..548d90b 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -34,11 +34,6 @@
* (0x80 is the syscall vector, 0x30-0x3f are for ISA)
*/
#define FIRST_EXTERNAL_VECTOR 0x20
-/*
- * We start allocating at 0x21 to spread out vectors evenly between
- * priority levels. (0x80 is the syscall vector)
- */
-#define VECTOR_OFFSET_START 1
/*
* Reserve the lowest usable vector (and hence lowest priority) 0x20 for
@@ -119,8 +114,6 @@
#define FIRST_SYSTEM_VECTOR NR_VECTORS
#endif
-#define FPU_IRQ 13
-
/*
* Size the maximum number of interrupts.
*
diff --git a/arch/x86/include/asm/jailhouse_para.h b/arch/x86/include/asm/jailhouse_para.h
index b885a96..a34897a 100644
--- a/arch/x86/include/asm/jailhouse_para.h
+++ b/arch/x86/include/asm/jailhouse_para.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL2.0 */
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Jailhouse paravirt detection
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 949c977..f4b2588 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -924,7 +924,7 @@ struct kvm_x86_ops {
int (*hardware_setup)(void); /* __init */
void (*hardware_unsetup)(void); /* __exit */
bool (*cpu_has_accelerated_tpr)(void);
- bool (*cpu_has_high_real_mode_segbase)(void);
+ bool (*has_emulated_msr)(int index);
void (*cpuid_update)(struct kvm_vcpu *vcpu);
struct kvm *(*vm_alloc)(void);
@@ -1013,6 +1013,7 @@ struct kvm_x86_ops {
bool (*has_wbinvd_exit)(void);
+ u64 (*read_l1_tsc_offset)(struct kvm_vcpu *vcpu);
void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);
diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h
index 1775a32..9719800 100644
--- a/arch/x86/include/asm/mc146818rtc.h
+++ b/arch/x86/include/asm/mc146818rtc.h
@@ -95,8 +95,8 @@ static inline unsigned char current_lock_cmos_reg(void)
unsigned char rtc_cmos_read(unsigned char addr);
void rtc_cmos_write(unsigned char val, unsigned char addr);
-extern int mach_set_rtc_mmss(const struct timespec *now);
-extern void mach_get_cmos_time(struct timespec *now);
+extern int mach_set_rtc_mmss(const struct timespec64 *now);
+extern void mach_get_cmos_time(struct timespec64 *now);
#define RTC_IRQ 8
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 57e3785..cf9911b 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -193,7 +193,7 @@ static inline int init_new_context(struct task_struct *tsk,
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
if (cpu_feature_enabled(X86_FEATURE_OSPKE)) {
- /* pkey 0 is the default and always allocated */
+ /* pkey 0 is the default and allocated implicitly */
mm->context.pkey_allocation_map = 0x1;
/* -1 means unallocated or invalid */
mm->context.execute_only_pkey = -1;
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index b90e796..9971921 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -122,6 +122,7 @@ static inline void hv_disable_stimer0_percpu_irq(int irq) {}
#if IS_ENABLED(CONFIG_HYPERV)
extern struct clocksource *hyperv_cs;
extern void *hv_hypercall_pg;
+extern void __percpu **hyperv_pcpu_input_arg;
static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
{
@@ -258,9 +259,41 @@ static inline int hv_cpu_number_to_vp_number(int cpu_number)
return hv_vp_index[cpu_number];
}
-void hyperv_init(void);
+static inline int cpumask_to_vpset(struct hv_vpset *vpset,
+ const struct cpumask *cpus)
+{
+ int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1;
+
+ /* valid_bank_mask can represent up to 64 banks */
+ if (hv_max_vp_index / 64 >= 64)
+ return 0;
+
+ /*
+ * Clear all banks up to the maximum possible bank as hv_flush_pcpu_ex
+ * structs are not cleared between calls, we risk flushing unneeded
+ * vCPUs otherwise.
+ */
+ for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++)
+ vpset->bank_contents[vcpu_bank] = 0;
+
+ /*
+ * Some banks may end up being empty but this is acceptable.
+ */
+ for_each_cpu(cpu, cpus) {
+ vcpu = hv_cpu_number_to_vp_number(cpu);
+ vcpu_bank = vcpu / 64;
+ vcpu_offset = vcpu % 64;
+ __set_bit(vcpu_offset, (unsigned long *)
+ &vpset->bank_contents[vcpu_bank]);
+ if (vcpu_bank >= nr_bank)
+ nr_bank = vcpu_bank + 1;
+ }
+ vpset->valid_bank_mask = GENMASK_ULL(nr_bank - 1, 0);
+ return nr_bank;
+}
+
+void __init hyperv_init(void);
void hyperv_setup_mmu_ops(void);
-void hyper_alloc_mmu(void);
void hyperv_report_panic(struct pt_regs *regs, long err);
bool hv_is_hyperv_initialized(void);
void hyperv_cleanup(void);
@@ -269,6 +302,13 @@ void hyperv_reenlightenment_intr(struct pt_regs *regs);
void set_hv_tscchange_cb(void (*cb)(void));
void clear_hv_tscchange_cb(void);
void hyperv_stop_tsc_emulation(void);
+
+#ifdef CONFIG_X86_64
+void hv_apic_init(void);
+#else
+static inline void hv_apic_init(void) {}
+#endif
+
#else /* CONFIG_HYPERV */
static inline void hyperv_init(void) {}
static inline bool hv_is_hyperv_initialized(void) { return false; }
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 53d5b1b..68b2c31 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -42,6 +42,8 @@
#define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */
#define SPEC_CTRL_IBRS (1 << 0) /* Indirect Branch Restricted Speculation */
#define SPEC_CTRL_STIBP (1 << 1) /* Single Thread Indirect Branch Predictors */
+#define SPEC_CTRL_SSBD_SHIFT 2 /* Speculative Store Bypass Disable bit */
+#define SPEC_CTRL_SSBD (1 << SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */
#define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */
#define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */
@@ -60,14 +62,19 @@
#define NHM_C3_AUTO_DEMOTE (1UL << 25)
#define NHM_C1_AUTO_DEMOTE (1UL << 26)
#define ATM_LNC_C6_AUTO_DEMOTE (1UL << 25)
-#define SNB_C1_AUTO_UNDEMOTE (1UL << 27)
-#define SNB_C3_AUTO_UNDEMOTE (1UL << 28)
+#define SNB_C3_AUTO_UNDEMOTE (1UL << 27)
+#define SNB_C1_AUTO_UNDEMOTE (1UL << 28)
#define MSR_MTRRcap 0x000000fe
#define MSR_IA32_ARCH_CAPABILITIES 0x0000010a
#define ARCH_CAP_RDCL_NO (1 << 0) /* Not susceptible to Meltdown */
#define ARCH_CAP_IBRS_ALL (1 << 1) /* Enhanced IBRS support */
+#define ARCH_CAP_SSB_NO (1 << 4) /*
+ * Not susceptible to Speculative Store Bypass
+ * attack, so no Speculative Store Bypass
+ * control required.
+ */
#define MSR_IA32_BBL_CR_CTL 0x00000119
#define MSR_IA32_BBL_CR_CTL3 0x0000011e
@@ -340,6 +347,8 @@
#define MSR_AMD64_SEV_ENABLED_BIT 0
#define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
+#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f
+
/* Fam 17h MSRs */
#define MSR_F17H_IRPERF 0xc00000e9
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index f928ad9..8b38df9 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -217,6 +217,14 @@ enum spectre_v2_mitigation {
SPECTRE_V2_IBRS,
};
+/* The Speculative Store Bypass disable variants */
+enum ssb_mitigation {
+ SPEC_STORE_BYPASS_NONE,
+ SPEC_STORE_BYPASS_DISABLE,
+ SPEC_STORE_BYPASS_PRCTL,
+ SPEC_STORE_BYPASS_SECCOMP,
+};
+
extern char __indirect_thunk_start[];
extern char __indirect_thunk_end[];
@@ -241,22 +249,27 @@ static inline void vmexit_fill_RSB(void)
#endif
}
-#define alternative_msr_write(_msr, _val, _feature) \
- asm volatile(ALTERNATIVE("", \
- "movl %[msr], %%ecx\n\t" \
- "movl %[val], %%eax\n\t" \
- "movl $0, %%edx\n\t" \
- "wrmsr", \
- _feature) \
- : : [msr] "i" (_msr), [val] "i" (_val) \
- : "eax", "ecx", "edx", "memory")
+static __always_inline
+void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
+{
+ asm volatile(ALTERNATIVE("", "wrmsr", %c[feature])
+ : : "c" (msr),
+ "a" ((u32)val),
+ "d" ((u32)(val >> 32)),
+ [feature] "i" (feature)
+ : "memory");
+}
static inline void indirect_branch_prediction_barrier(void)
{
- alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB,
- X86_FEATURE_USE_IBPB);
+ u64 val = PRED_CMD_IBPB;
+
+ alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB);
}
+/* The Intel SPEC CTRL MSR base value cache */
+extern u64 x86_spec_ctrl_base;
+
/*
* With retpoline, we must use IBRS to restrict branch prediction
* before calling into firmware.
@@ -265,14 +278,18 @@ static inline void indirect_branch_prediction_barrier(void)
*/
#define firmware_restrict_branch_speculation_start() \
do { \
+ u64 val = x86_spec_ctrl_base | SPEC_CTRL_IBRS; \
+ \
preempt_disable(); \
- alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS, \
+ alternative_msr_write(MSR_IA32_SPEC_CTRL, val, \
X86_FEATURE_USE_IBRS_FW); \
} while (0)
#define firmware_restrict_branch_speculation_end() \
do { \
- alternative_msr_write(MSR_IA32_SPEC_CTRL, 0, \
+ u64 val = x86_spec_ctrl_base; \
+ \
+ alternative_msr_write(MSR_IA32_SPEC_CTRL, val, \
X86_FEATURE_USE_IBRS_FW); \
preempt_enable(); \
} while (0)
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 2c5a966..6afac38 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -53,7 +53,7 @@
#define __PHYSICAL_MASK_SHIFT 52
#ifdef CONFIG_X86_5LEVEL
-#define __VIRTUAL_MASK_SHIFT (pgtable_l5_enabled ? 56 : 47)
+#define __VIRTUAL_MASK_SHIFT (pgtable_l5_enabled() ? 56 : 47)
#else
#define __VIRTUAL_MASK_SHIFT 47
#endif
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 9be2bf1..d49bbf4 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -574,14 +574,14 @@ static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
}
#define set_pgd(pgdp, pgdval) do { \
- if (pgtable_l5_enabled) \
+ if (pgtable_l5_enabled()) \
__set_pgd(pgdp, pgdval); \
else \
set_p4d((p4d_t *)(pgdp), (p4d_t) { (pgdval).pgd }); \
} while (0)
#define pgd_clear(pgdp) do { \
- if (pgtable_l5_enabled) \
+ if (pgtable_l5_enabled()) \
set_pgd(pgdp, __pgd(0)); \
} while (0)
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index d32175e..6629636 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -117,9 +117,6 @@ void native_restore_msi_irqs(struct pci_dev *dev);
#define native_setup_msi_irqs NULL
#define native_teardown_msi_irq NULL
#endif
-
-#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
-
#endif /* __KERNEL__ */
#ifdef CONFIG_X86_64
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index 263c142..ada6410 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -167,7 +167,7 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
#if CONFIG_PGTABLE_LEVELS > 4
static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d)
{
- if (!pgtable_l5_enabled)
+ if (!pgtable_l5_enabled())
return;
paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT);
set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d)));
@@ -193,7 +193,7 @@ extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d);
static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
unsigned long address)
{
- if (pgtable_l5_enabled)
+ if (pgtable_l5_enabled())
___p4d_free_tlb(tlb, p4d);
}
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 5f49b4f..99ecde2 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -65,7 +65,7 @@ extern pmdval_t early_pmd_flags;
#ifndef __PAGETABLE_P4D_FOLDED
#define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd)
-#define pgd_clear(pgd) (pgtable_l5_enabled ? native_pgd_clear(pgd) : 0)
+#define pgd_clear(pgd) (pgtable_l5_enabled() ? native_pgd_clear(pgd) : 0)
#endif
#ifndef set_p4d
@@ -601,6 +601,11 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
#define canon_pgprot(p) __pgprot(massage_pgprot(p))
+static inline pgprot_t arch_filter_pgprot(pgprot_t prot)
+{
+ return canon_pgprot(prot);
+}
+
static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
enum page_cache_mode pcm,
enum page_cache_mode new_pcm)
@@ -876,7 +881,7 @@ static inline unsigned long p4d_index(unsigned long address)
#if CONFIG_PGTABLE_LEVELS > 4
static inline int pgd_present(pgd_t pgd)
{
- if (!pgtable_l5_enabled)
+ if (!pgtable_l5_enabled())
return 1;
return pgd_flags(pgd) & _PAGE_PRESENT;
}
@@ -893,9 +898,9 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd)
#define pgd_page(pgd) pfn_to_page(pgd_pfn(pgd))
/* to find an entry in a page-table-directory. */
-static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+static __always_inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
{
- if (!pgtable_l5_enabled)
+ if (!pgtable_l5_enabled())
return (p4d_t *)pgd;
return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address);
}
@@ -904,7 +909,7 @@ static inline int pgd_bad(pgd_t pgd)
{
unsigned long ignore_flags = _PAGE_USER;
- if (!pgtable_l5_enabled)
+ if (!pgtable_l5_enabled())
return 0;
if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
@@ -915,7 +920,7 @@ static inline int pgd_bad(pgd_t pgd)
static inline int pgd_none(pgd_t pgd)
{
- if (!pgtable_l5_enabled)
+ if (!pgtable_l5_enabled())
return 0;
/*
* There is no need to do a workaround for the KNL stray
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index e3225e8..d9a001a 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -15,7 +15,7 @@
# include <asm/pgtable-2level_types.h>
#endif
-#define pgtable_l5_enabled 0
+#define pgtable_l5_enabled() 0
#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
#define PGDIR_MASK (~(PGDIR_SIZE - 1))
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 877bc27..3c5385f 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -220,7 +220,7 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
{
pgd_t pgd;
- if (pgtable_l5_enabled || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) {
+ if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) {
*p4dp = p4d;
return;
}
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index d5c21a3..054765a 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -22,12 +22,23 @@ typedef struct { pteval_t pte; } pte_t;
#ifdef CONFIG_X86_5LEVEL
extern unsigned int __pgtable_l5_enabled;
-#ifndef pgtable_l5_enabled
-#define pgtable_l5_enabled cpu_feature_enabled(X86_FEATURE_LA57)
-#endif
+
+#ifdef USE_EARLY_PGTABLE_L5
+/*
+ * cpu_feature_enabled() is not available in early boot code.
+ * Use variable instead.
+ */
+static inline bool pgtable_l5_enabled(void)
+{
+ return __pgtable_l5_enabled;
+}
#else
-#define pgtable_l5_enabled 0
-#endif
+#define pgtable_l5_enabled() cpu_feature_enabled(X86_FEATURE_LA57)
+#endif /* USE_EARLY_PGTABLE_L5 */
+
+#else
+#define pgtable_l5_enabled() 0
+#endif /* CONFIG_X86_5LEVEL */
extern unsigned int pgdir_shift;
extern unsigned int ptrs_per_p4d;
@@ -102,21 +113,21 @@ extern unsigned int ptrs_per_p4d;
#define LDT_PGD_ENTRY_L4 -3UL
#define LDT_PGD_ENTRY_L5 -112UL
-#define LDT_PGD_ENTRY (pgtable_l5_enabled ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4)
+#define LDT_PGD_ENTRY (pgtable_l5_enabled() ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4)
#define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT)
-#define __VMALLOC_BASE_L4 0xffffc90000000000
-#define __VMALLOC_BASE_L5 0xffa0000000000000
+#define __VMALLOC_BASE_L4 0xffffc90000000000UL
+#define __VMALLOC_BASE_L5 0xffa0000000000000UL
#define VMALLOC_SIZE_TB_L4 32UL
#define VMALLOC_SIZE_TB_L5 12800UL
-#define __VMEMMAP_BASE_L4 0xffffea0000000000
-#define __VMEMMAP_BASE_L5 0xffd4000000000000
+#define __VMEMMAP_BASE_L4 0xffffea0000000000UL
+#define __VMEMMAP_BASE_L5 0xffd4000000000000UL
#ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
# define VMALLOC_START vmalloc_base
-# define VMALLOC_SIZE_TB (pgtable_l5_enabled ? VMALLOC_SIZE_TB_L5 : VMALLOC_SIZE_TB_L4)
+# define VMALLOC_SIZE_TB (pgtable_l5_enabled() ? VMALLOC_SIZE_TB_L5 : VMALLOC_SIZE_TB_L4)
# define VMEMMAP_START vmemmap_base
#else
# define VMALLOC_START __VMALLOC_BASE_L4
diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h
index a0ba1ff..851c04b 100644
--- a/arch/x86/include/asm/pkeys.h
+++ b/arch/x86/include/asm/pkeys.h
@@ -2,6 +2,8 @@
#ifndef _ASM_X86_PKEYS_H
#define _ASM_X86_PKEYS_H
+#define ARCH_DEFAULT_PKEY 0
+
#define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1)
extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
@@ -15,7 +17,7 @@ extern int __execute_only_pkey(struct mm_struct *mm);
static inline int execute_only_pkey(struct mm_struct *mm)
{
if (!boot_cpu_has(X86_FEATURE_OSPKE))
- return 0;
+ return ARCH_DEFAULT_PKEY;
return __execute_only_pkey(mm);
}
@@ -49,13 +51,21 @@ bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey)
{
/*
* "Allocated" pkeys are those that have been returned
- * from pkey_alloc(). pkey 0 is special, and never
- * returned from pkey_alloc().
+ * from pkey_alloc() or pkey 0 which is allocated
+ * implicitly when the mm is created.
*/
- if (pkey <= 0)
+ if (pkey < 0)
return false;
if (pkey >= arch_max_pkey())
return false;
+ /*
+ * The exec-only pkey is set in the allocation map, but
+ * is not available to any of the user interfaces like
+ * mprotect_pkey().
+ */
+ if (pkey == mm->context.execute_only_pkey)
+ return false;
+
return mm_pkey_allocation_map(mm) & (1U << pkey);
}
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 4fa4206..e28add6 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -186,15 +186,6 @@ extern void identify_boot_cpu(void);
extern void identify_secondary_cpu(struct cpuinfo_x86 *);
extern void print_cpu_info(struct cpuinfo_x86 *);
void print_cpu_msr(struct cpuinfo_x86 *);
-extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
-extern u32 get_scattered_cpuid_leaf(unsigned int level,
- unsigned int sub_leaf,
- enum cpuid_regs_idx reg);
-extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
-extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
-
-extern void detect_extended_topology(struct cpuinfo_x86 *c);
-extern void detect_ht(struct cpuinfo_x86 *c);
#ifdef CONFIG_X86_32
extern int have_cpuid_p(void);
@@ -749,13 +740,11 @@ enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT,
extern void enable_sep_cpu(void);
extern int sysenter_setup(void);
-extern void early_trap_init(void);
void early_trap_pf_init(void);
/* Defined in head.S */
extern struct desc_ptr early_gdt_descr;
-extern void cpu_set_gdt(int);
extern void switch_to_new_gdt(int);
extern void load_direct_gdt(int);
extern void load_fixmap_gdt(int);
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index a7471dc..b603368 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -12,7 +12,7 @@ void pvclock_set_flags(u8 flags);
unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src);
void pvclock_read_wallclock(struct pvclock_wall_clock *wall,
struct pvclock_vcpu_time_info *vcpu,
- struct timespec *ts);
+ struct timespec64 *ts);
void pvclock_resume(void);
void pvclock_touch_watchdogs(void);
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index 5e16b5d..3e70bed 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -7,6 +7,14 @@
#include <asm-generic/qspinlock_types.h>
#include <asm/paravirt.h>
+#define _Q_PENDING_LOOPS (1 << 9)
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __pv_init_lock_hash(void);
+extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock);
+
#define queued_spin_unlock queued_spin_unlock
/**
* queued_spin_unlock - release a queued spinlock
@@ -16,15 +24,9 @@
*/
static inline void native_queued_spin_unlock(struct qspinlock *lock)
{
- smp_store_release((u8 *)lock, 0);
+ smp_store_release(&lock->locked, 0);
}
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
-extern void __pv_init_lock_hash(void);
-extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
-extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock);
-
static inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
{
pv_queued_spin_lock_slowpath(lock, val);
@@ -40,11 +42,6 @@ static inline bool vcpu_is_preempted(long cpu)
{
return pv_vcpu_is_preempted(cpu);
}
-#else
-static inline void queued_spin_unlock(struct qspinlock *lock)
-{
- native_queued_spin_unlock(lock);
-}
#endif
#ifdef CONFIG_PARAVIRT
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index 923307e..9ef5ee03 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -22,8 +22,7 @@ PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath);
*
* void __pv_queued_spin_unlock(struct qspinlock *lock)
* {
- * struct __qspinlock *l = (void *)lock;
- * u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0);
+ * u8 lockval = cmpxchg(&lock->locked, _Q_LOCKED_VAL, 0);
*
* if (likely(lockval == _Q_LOCKED_VAL))
* return;
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index f75bff8..547c4fe 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -171,7 +171,6 @@ static inline int wbinvd_on_all_cpus(void)
wbinvd();
return 0;
}
-#define smp_num_siblings 1
#endif /* CONFIG_SMP */
extern unsigned disabled_cpus;
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 4617a2b..1992187 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -27,8 +27,8 @@
# endif
#else /* CONFIG_X86_32 */
# define SECTION_SIZE_BITS 27 /* matt - 128 is convenient right now */
-# define MAX_PHYSADDR_BITS (pgtable_l5_enabled ? 52 : 44)
-# define MAX_PHYSMEM_BITS (pgtable_l5_enabled ? 52 : 46)
+# define MAX_PHYSADDR_BITS (pgtable_l5_enabled() ? 52 : 44)
+# define MAX_PHYSMEM_BITS (pgtable_l5_enabled() ? 52 : 46)
#endif
#endif /* CONFIG_SPARSEMEM */
diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
new file mode 100644
index 0000000..ae7c2c5
--- /dev/null
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_SPECCTRL_H_
+#define _ASM_X86_SPECCTRL_H_
+
+#include <linux/thread_info.h>
+#include <asm/nospec-branch.h>
+
+/*
+ * On VMENTER we must preserve whatever view of the SPEC_CTRL MSR
+ * the guest has, while on VMEXIT we restore the host view. This
+ * would be easier if SPEC_CTRL were architecturally maskable or
+ * shadowable for guests but this is not (currently) the case.
+ * Takes the guest view of SPEC_CTRL MSR as a parameter and also
+ * the guest's version of VIRT_SPEC_CTRL, if emulated.
+ */
+extern void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool guest);
+
+/**
+ * x86_spec_ctrl_set_guest - Set speculation control registers for the guest
+ * @guest_spec_ctrl: The guest content of MSR_SPEC_CTRL
+ * @guest_virt_spec_ctrl: The guest controlled bits of MSR_VIRT_SPEC_CTRL
+ * (may get translated to MSR_AMD64_LS_CFG bits)
+ *
+ * Avoids writing to the MSR if the content/bits are the same
+ */
+static inline
+void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl)
+{
+ x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, true);
+}
+
+/**
+ * x86_spec_ctrl_restore_host - Restore host speculation control registers
+ * @guest_spec_ctrl: The guest content of MSR_SPEC_CTRL
+ * @guest_virt_spec_ctrl: The guest controlled bits of MSR_VIRT_SPEC_CTRL
+ * (may get translated to MSR_AMD64_LS_CFG bits)
+ *
+ * Avoids writing to the MSR if the content/bits are the same
+ */
+static inline
+void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl)
+{
+ x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, false);
+}
+
+/* AMD specific Speculative Store Bypass MSR data */
+extern u64 x86_amd_ls_cfg_base;
+extern u64 x86_amd_ls_cfg_ssbd_mask;
+
+static inline u64 ssbd_tif_to_spec_ctrl(u64 tifn)
+{
+ BUILD_BUG_ON(TIF_SSBD < SPEC_CTRL_SSBD_SHIFT);
+ return (tifn & _TIF_SSBD) >> (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT);
+}
+
+static inline unsigned long ssbd_spec_ctrl_to_tif(u64 spec_ctrl)
+{
+ BUILD_BUG_ON(TIF_SSBD < SPEC_CTRL_SSBD_SHIFT);
+ return (spec_ctrl & SPEC_CTRL_SSBD) << (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT);
+}
+
+static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn)
+{
+ return (tifn & _TIF_SSBD) ? x86_amd_ls_cfg_ssbd_mask : 0ULL;
+}
+
+#ifdef CONFIG_SMP
+extern void speculative_store_bypass_ht_init(void);
+#else
+static inline void speculative_store_bypass_ht_init(void) { }
+#endif
+
+extern void speculative_store_bypass_update(unsigned long tif);
+
+static inline void speculative_store_bypass_update_current(void)
+{
+ speculative_store_bypass_update(current_thread_info()->flags);
+}
+
+#endif
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 133d942..b6dc698 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -111,4 +111,6 @@ static inline unsigned long caller_frame_pointer(void)
return (unsigned long)frame;
}
+void show_opcodes(u8 *rip, const char *loglvl);
+void show_ip(struct pt_regs *regs, const char *loglvl);
#endif /* _ASM_X86_STACKTRACE_H */
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 533f74c..d33f92b 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -116,7 +116,8 @@ int strcmp(const char *cs, const char *ct);
#endif
#define __HAVE_ARCH_MEMCPY_MCSAFE 1
-__must_check int memcpy_mcsafe_unrolled(void *dst, const void *src, size_t cnt);
+__must_check unsigned long __memcpy_mcsafe(void *dst, const void *src,
+ size_t cnt);
DECLARE_STATIC_KEY_FALSE(mcsafe_key);
/**
@@ -131,14 +132,15 @@ DECLARE_STATIC_KEY_FALSE(mcsafe_key);
* actually do machine check recovery. Everyone else can just
* use memcpy().
*
- * Return 0 for success, -EFAULT for fail
+ * Return 0 for success, or number of bytes not copied if there was an
+ * exception.
*/
-static __always_inline __must_check int
+static __always_inline __must_check unsigned long
memcpy_mcsafe(void *dst, const void *src, size_t cnt)
{
#ifdef CONFIG_X86_MCE
if (static_branch_unlikely(&mcsafe_key))
- return memcpy_mcsafe_unrolled(dst, src, cnt);
+ return __memcpy_mcsafe(dst, src, cnt);
else
#endif
memcpy(dst, src, cnt);
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index a5d9521..2ff2a30 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -79,6 +79,7 @@ struct thread_info {
#define TIF_SIGPENDING 2 /* signal pending */
#define TIF_NEED_RESCHED 3 /* rescheduling necessary */
#define TIF_SINGLESTEP 4 /* reenable singlestep on user return*/
+#define TIF_SSBD 5 /* Reduced data speculation */
#define TIF_SYSCALL_EMU 6 /* syscall emulation active */
#define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */
#define TIF_SECCOMP 8 /* secure computing */
@@ -105,6 +106,7 @@ struct thread_info {
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP)
+#define _TIF_SSBD (1 << TIF_SSBD)
#define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU)
#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
#define _TIF_SECCOMP (1 << TIF_SECCOMP)
@@ -144,7 +146,7 @@ struct thread_info {
/* flags to check in __switch_to() */
#define _TIF_WORK_CTXSW \
- (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP)
+ (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP|_TIF_SSBD)
#define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW)
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 62546b3..62acb61 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -47,6 +47,17 @@ copy_user_generic(void *to, const void *from, unsigned len)
}
static __always_inline __must_check unsigned long
+copy_to_user_mcsafe(void *to, const void *from, unsigned len)
+{
+ unsigned long ret;
+
+ __uaccess_begin();
+ ret = memcpy_mcsafe(to, from, len);
+ __uaccess_end();
+ return ret;
+}
+
+static __always_inline __must_check unsigned long
raw_copy_from_user(void *dst, const void __user *src, unsigned long size)
{
int ret = 0;
@@ -194,4 +205,7 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
unsigned long
copy_user_handle_tail(char *to, char *from, unsigned len);
+unsigned long
+mcsafe_handle_tail(char *to, char *from, unsigned len);
+
#endif /* _ASM_X86_UACCESS_64_H */
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index ce8b4da..2d27236 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -170,7 +170,7 @@ struct x86_cpuinit_ops {
void (*fixup_cpu_id)(struct cpuinfo_x86 *c, int node);
};
-struct timespec;
+struct timespec64;
/**
* struct x86_legacy_devices - legacy x86 devices
@@ -264,8 +264,8 @@ struct x86_hyper_runtime {
struct x86_platform_ops {
unsigned long (*calibrate_cpu)(void);
unsigned long (*calibrate_tsc)(void);
- void (*get_wallclock)(struct timespec *ts);
- int (*set_wallclock)(const struct timespec *ts);
+ void (*get_wallclock)(struct timespec64 *ts);
+ int (*set_wallclock)(const struct timespec64 *ts);
void (*iommu_shutdown)(void);
bool (*is_untracked_pat_range)(u64 start, u64 end);
void (*nmi_init)(void);
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 4c851eb..0ede697 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -29,7 +29,7 @@
#define KVM_FEATURE_PV_TLB_FLUSH 9
#define KVM_FEATURE_ASYNC_PF_VMEXIT 10
-#define KVM_HINTS_DEDICATED 0
+#define KVM_HINTS_REALTIME 0
/* The last 8 bits are used to indicate how to interpret the flags field
* in pvclock structure. If no bits are set, all flags are ignored.
diff --git a/arch/x86/include/uapi/asm/msgbuf.h b/arch/x86/include/uapi/asm/msgbuf.h
index 809134c..90ab9a7 100644
--- a/arch/x86/include/uapi/asm/msgbuf.h
+++ b/arch/x86/include/uapi/asm/msgbuf.h
@@ -1 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_X64_MSGBUF_H
+#define __ASM_X64_MSGBUF_H
+
+#if !defined(__x86_64__) || !defined(__ILP32__)
#include <asm-generic/msgbuf.h>
+#else
+/*
+ * The msqid64_ds structure for x86 architecture with x32 ABI.
+ *
+ * On x86-32 and x86-64 we can just use the generic definition, but
+ * x32 uses the same binary layout as x86_64, which is differnet
+ * from other 32-bit architectures.
+ */
+
+struct msqid64_ds {
+ struct ipc64_perm msg_perm;
+ __kernel_time_t msg_stime; /* last msgsnd time */
+ __kernel_time_t msg_rtime; /* last msgrcv time */
+ __kernel_time_t msg_ctime; /* last change time */
+ __kernel_ulong_t msg_cbytes; /* current number of bytes on queue */
+ __kernel_ulong_t msg_qnum; /* number of messages in queue */
+ __kernel_ulong_t msg_qbytes; /* max number of bytes on queue */
+ __kernel_pid_t msg_lspid; /* pid of last msgsnd */
+ __kernel_pid_t msg_lrpid; /* last receive pid */
+ __kernel_ulong_t __unused4;
+ __kernel_ulong_t __unused5;
+};
+
+#endif
+
+#endif /* __ASM_GENERIC_MSGBUF_H */
diff --git a/arch/x86/include/uapi/asm/sembuf.h b/arch/x86/include/uapi/asm/sembuf.h
index cabd747..89de6cd 100644
--- a/arch/x86/include/uapi/asm/sembuf.h
+++ b/arch/x86/include/uapi/asm/sembuf.h
@@ -8,15 +8,24 @@
* between kernel and user space.
*
* Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
* - 2 miscellaneous 32-bit values
+ *
+ * x86_64 and x32 incorrectly added padding here, so the structures
+ * are still incompatible with the padding on x86.
*/
struct semid64_ds {
struct ipc64_perm sem_perm; /* permissions .. see ipc.h */
+#ifdef __i386__
+ unsigned long sem_otime; /* last semop time */
+ unsigned long sem_otime_high;
+ unsigned long sem_ctime; /* last change time */
+ unsigned long sem_ctime_high;
+#else
__kernel_time_t sem_otime; /* last semop time */
__kernel_ulong_t __unused1;
__kernel_time_t sem_ctime; /* last change time */
__kernel_ulong_t __unused2;
+#endif
__kernel_ulong_t sem_nsems; /* no. of semaphores in array */
__kernel_ulong_t __unused3;
__kernel_ulong_t __unused4;
diff --git a/arch/x86/include/uapi/asm/shmbuf.h b/arch/x86/include/uapi/asm/shmbuf.h
index 83c05fc..644421f 100644
--- a/arch/x86/include/uapi/asm/shmbuf.h
+++ b/arch/x86/include/uapi/asm/shmbuf.h
@@ -1 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_X86_SHMBUF_H
+#define __ASM_X86_SHMBUF_H
+
+#if !defined(__x86_64__) || !defined(__ILP32__)
#include <asm-generic/shmbuf.h>
+#else
+/*
+ * The shmid64_ds structure for x86 architecture with x32 ABI.
+ *
+ * On x86-32 and x86-64 we can just use the generic definition, but
+ * x32 uses the same binary layout as x86_64, which is differnet
+ * from other 32-bit architectures.
+ */
+
+struct shmid64_ds {
+ struct ipc64_perm shm_perm; /* operation perms */
+ size_t shm_segsz; /* size of segment (bytes) */
+ __kernel_time_t shm_atime; /* last attach time */
+ __kernel_time_t shm_dtime; /* last detach time */
+ __kernel_time_t shm_ctime; /* last change time */
+ __kernel_pid_t shm_cpid; /* pid of creator */
+ __kernel_pid_t shm_lpid; /* pid of last operator */
+ __kernel_ulong_t shm_nattch; /* no. of current attaches */
+ __kernel_ulong_t __unused4;
+ __kernel_ulong_t __unused5;
+};
+
+struct shminfo64 {
+ __kernel_ulong_t shmmax;
+ __kernel_ulong_t shmmin;
+ __kernel_ulong_t shmmni;
+ __kernel_ulong_t shmseg;
+ __kernel_ulong_t shmall;
+ __kernel_ulong_t __unused1;
+ __kernel_ulong_t __unused2;
+ __kernel_ulong_t __unused3;
+ __kernel_ulong_t __unused4;
+};
+
+#endif
+
+#endif /* __ASM_X86_SHMBUF_H */
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index dde444f..3b20607 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -215,6 +215,10 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
apic_id = processor->local_apic_id;
enabled = processor->lapic_flags & ACPI_MADT_ENABLED;
+ /* Ignore invalid ID */
+ if (apic_id == 0xffffffff)
+ return 0;
+
/*
* We need to register disabled CPU as well to permit
* counting disabled CPUs. This allows us to size
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index c88e0b1..b481b95 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -14,8 +14,11 @@
#include <asm/amd_nb.h>
#define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450
+#define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0
#define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463
#define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464
+#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb
+#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec
/* Protect the PCI config register pairs used for SMN and DF indirect access. */
static DEFINE_MUTEX(smn_mutex);
@@ -24,6 +27,7 @@ static u32 *flush_words;
static const struct pci_device_id amd_root_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) },
{}
};
@@ -39,6 +43,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
{}
};
@@ -51,6 +56,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
{}
};
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 8b04234..7685444 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -116,6 +116,7 @@ static void init_x2apic_ldr(void)
goto update;
}
cmsk = cluster_hotplug_mask;
+ cmsk->clusterid = cluster;
cluster_hotplug_mask = NULL;
update:
this_cpu_write(cluster_masks, cmsk);
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index dfcbe69..5d0de79 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -1715,19 +1715,6 @@ static int proc_apm_show(struct seq_file *m, void *v)
return 0;
}
-static int proc_apm_open(struct inode *inode, struct file *file)
-{
- return single_open(file, proc_apm_show, NULL);
-}
-
-static const struct file_operations apm_file_ops = {
- .owner = THIS_MODULE,
- .open = proc_apm_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int apm(void *unused)
{
unsigned short bx;
@@ -2360,7 +2347,7 @@ static int __init apm_init(void)
set_desc_base(&gdt[APM_DS >> 3],
(unsigned long)__va((unsigned long)apm_info.bios.dseg << 4));
- proc_create("apm", 0, NULL, &apm_file_ops);
+ proc_create_single("apm", 0, NULL, proc_apm_show);
kapmd_task = kthread_create(apm, NULL, "kapmd");
if (IS_ERR(kapmd_task)) {
@@ -2446,7 +2433,7 @@ MODULE_PARM_DESC(idle_threshold,
"System idle percentage above which to make APM BIOS idle calls");
module_param(idle_period, int, 0444);
MODULE_PARM_DESC(idle_period,
- "Period (in sec/100) over which to caculate the idle percentage");
+ "Period (in sec/100) over which to calculate the idle percentage");
module_param(smp, bool, 0444);
MODULE_PARM_DESC(smp,
"Set this to enable APM use on an SMP platform. Use with caution on older systems");
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index a66229f..7a40196 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -17,7 +17,7 @@
nostackp := $(call cc-option, -fno-stack-protector)
CFLAGS_common.o := $(nostackp)
-obj-y := intel_cacheinfo.o scattered.o topology.o
+obj-y := cacheinfo.o scattered.o topology.o
obj-y += common.o
obj-y += rdrand.o
obj-y += match.o
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 12bc0a1..082d787 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -9,7 +9,9 @@
#include <linux/random.h>
#include <asm/processor.h>
#include <asm/apic.h>
+#include <asm/cacheinfo.h>
#include <asm/cpu.h>
+#include <asm/spec-ctrl.h>
#include <asm/smp.h>
#include <asm/pci-direct.h>
#include <asm/delay.h>
@@ -297,7 +299,6 @@ static int nearby_node(int apicid)
}
#endif
-#ifdef CONFIG_SMP
/*
* Fix up cpu_core_id for pre-F17h systems to be in the
* [0 .. cores_per_node - 1] range. Not really needed but
@@ -327,6 +328,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
/* get information required for multi-node processors */
if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+ int err;
u32 eax, ebx, ecx, edx;
cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
@@ -345,21 +347,15 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
}
/*
- * We may have multiple LLCs if L3 caches exist, so check if we
- * have an L3 cache by looking at the L3 cache CPUID leaf.
+ * In case leaf B is available, use it to derive
+ * topology information.
*/
- if (cpuid_edx(0x80000006)) {
- if (c->x86 == 0x17) {
- /*
- * LLC is at the core complex level.
- * Core complex id is ApicId[3].
- */
- per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
- } else {
- /* LLC is at the node level. */
- per_cpu(cpu_llc_id, cpu) = node_id;
- }
- }
+ err = detect_extended_topology(c);
+ if (!err)
+ c->x86_coreid_bits = get_count_order(c->x86_max_cores);
+
+ cacheinfo_amd_init_llc_id(c, cpu, node_id);
+
} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
u64 value;
@@ -375,7 +371,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
legacy_fixup_core_id(c);
}
}
-#endif
/*
* On a AMD dual core setup the lower bits of the APIC id distinguish the cores.
@@ -383,7 +378,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
*/
static void amd_detect_cmp(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_SMP
unsigned bits;
int cpu = smp_processor_id();
@@ -394,17 +388,11 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
c->phys_proc_id = c->initial_apicid >> bits;
/* use socket ID also for last level cache */
per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
- amd_get_topology(c);
-#endif
}
u16 amd_get_nb_id(int cpu)
{
- u16 id = 0;
-#ifdef CONFIG_SMP
- id = per_cpu(cpu_llc_id, cpu);
-#endif
- return id;
+ return per_cpu(cpu_llc_id, cpu);
}
EXPORT_SYMBOL_GPL(amd_get_nb_id);
@@ -554,6 +542,26 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
rdmsrl(MSR_FAM10H_NODE_ID, value);
nodes_per_socket = ((value >> 3) & 7) + 1;
}
+
+ if (c->x86 >= 0x15 && c->x86 <= 0x17) {
+ unsigned int bit;
+
+ switch (c->x86) {
+ case 0x15: bit = 54; break;
+ case 0x16: bit = 33; break;
+ case 0x17: bit = 10; break;
+ default: return;
+ }
+ /*
+ * Try to cache the base value so further operations can
+ * avoid RMW. If that faults, do not enable SSBD.
+ */
+ if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
+ setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD);
+ setup_force_cpu_cap(X86_FEATURE_SSBD);
+ x86_amd_ls_cfg_ssbd_mask = 1ULL << bit;
+ }
+ }
}
static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
@@ -791,6 +799,7 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
static void init_amd_zn(struct cpuinfo_x86 *c)
{
+ set_cpu_cap(c, X86_FEATURE_ZEN);
/*
* Fix erratum 1076: CPB feature bit not being set in CPUID. It affects
* all up to and including B1.
@@ -842,6 +851,7 @@ static void init_amd(struct cpuinfo_x86 *c)
/* Multi core CPU? */
if (c->extended_cpuid_level >= 0x80000008) {
amd_detect_cmp(c);
+ amd_get_topology(c);
srat_detect_node(c);
}
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index bfca937..7416fc2 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -12,8 +12,10 @@
#include <linux/utsname.h>
#include <linux/cpu.h>
#include <linux/module.h>
+#include <linux/nospec.h>
+#include <linux/prctl.h>
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
#include <asm/cmdline.h>
#include <asm/bugs.h>
#include <asm/processor.h>
@@ -27,6 +29,27 @@
#include <asm/intel-family.h>
static void __init spectre_v2_select_mitigation(void);
+static void __init ssb_select_mitigation(void);
+
+/*
+ * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any
+ * writes to SPEC_CTRL contain whatever reserved bits have been set.
+ */
+u64 __ro_after_init x86_spec_ctrl_base;
+EXPORT_SYMBOL_GPL(x86_spec_ctrl_base);
+
+/*
+ * The vendor and possibly platform specific bits which can be modified in
+ * x86_spec_ctrl_base.
+ */
+static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS;
+
+/*
+ * AMD specific MSR info for Speculative Store Bypass control.
+ * x86_amd_ls_cfg_ssbd_mask is initialized in identify_boot_cpu().
+ */
+u64 __ro_after_init x86_amd_ls_cfg_base;
+u64 __ro_after_init x86_amd_ls_cfg_ssbd_mask;
void __init check_bugs(void)
{
@@ -37,9 +60,27 @@ void __init check_bugs(void)
print_cpu_info(&boot_cpu_data);
}
+ /*
+ * Read the SPEC_CTRL MSR to account for reserved bits which may
+ * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD
+ * init code as it is not enumerated and depends on the family.
+ */
+ if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
+ rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+
+ /* Allow STIBP in MSR_SPEC_CTRL if supported */
+ if (boot_cpu_has(X86_FEATURE_STIBP))
+ x86_spec_ctrl_mask |= SPEC_CTRL_STIBP;
+
/* Select the proper spectre mitigation before patching alternatives */
spectre_v2_select_mitigation();
+ /*
+ * Select proper mitigation for any exposure to the Speculative Store
+ * Bypass vulnerability.
+ */
+ ssb_select_mitigation();
+
#ifdef CONFIG_X86_32
/*
* Check whether we are able to run this kernel safely on SMP.
@@ -93,7 +134,76 @@ static const char *spectre_v2_strings[] = {
#undef pr_fmt
#define pr_fmt(fmt) "Spectre V2 : " fmt
-static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE;
+static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
+ SPECTRE_V2_NONE;
+
+void
+x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
+{
+ u64 msrval, guestval, hostval = x86_spec_ctrl_base;
+ struct thread_info *ti = current_thread_info();
+
+ /* Is MSR_SPEC_CTRL implemented ? */
+ if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) {
+ /*
+ * Restrict guest_spec_ctrl to supported values. Clear the
+ * modifiable bits in the host base value and or the
+ * modifiable bits from the guest value.
+ */
+ guestval = hostval & ~x86_spec_ctrl_mask;
+ guestval |= guest_spec_ctrl & x86_spec_ctrl_mask;
+
+ /* SSBD controlled in MSR_SPEC_CTRL */
+ if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD))
+ hostval |= ssbd_tif_to_spec_ctrl(ti->flags);
+
+ if (hostval != guestval) {
+ msrval = setguest ? guestval : hostval;
+ wrmsrl(MSR_IA32_SPEC_CTRL, msrval);
+ }
+ }
+
+ /*
+ * If SSBD is not handled in MSR_SPEC_CTRL on AMD, update
+ * MSR_AMD64_L2_CFG or MSR_VIRT_SPEC_CTRL if supported.
+ */
+ if (!static_cpu_has(X86_FEATURE_LS_CFG_SSBD) &&
+ !static_cpu_has(X86_FEATURE_VIRT_SSBD))
+ return;
+
+ /*
+ * If the host has SSBD mitigation enabled, force it in the host's
+ * virtual MSR value. If its not permanently enabled, evaluate
+ * current's TIF_SSBD thread flag.
+ */
+ if (static_cpu_has(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE))
+ hostval = SPEC_CTRL_SSBD;
+ else
+ hostval = ssbd_tif_to_spec_ctrl(ti->flags);
+
+ /* Sanitize the guest value */
+ guestval = guest_virt_spec_ctrl & SPEC_CTRL_SSBD;
+
+ if (hostval != guestval) {
+ unsigned long tif;
+
+ tif = setguest ? ssbd_spec_ctrl_to_tif(guestval) :
+ ssbd_spec_ctrl_to_tif(hostval);
+
+ speculative_store_bypass_update(tif);
+ }
+}
+EXPORT_SYMBOL_GPL(x86_virt_spec_ctrl);
+
+static void x86_amd_ssb_disable(void)
+{
+ u64 msrval = x86_amd_ls_cfg_base | x86_amd_ls_cfg_ssbd_mask;
+
+ if (boot_cpu_has(X86_FEATURE_VIRT_SSBD))
+ wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, SPEC_CTRL_SSBD);
+ else if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD))
+ wrmsrl(MSR_AMD64_LS_CFG, msrval);
+}
#ifdef RETPOLINE
static bool spectre_v2_bad_module;
@@ -312,32 +422,289 @@ static void __init spectre_v2_select_mitigation(void)
}
#undef pr_fmt
+#define pr_fmt(fmt) "Speculative Store Bypass: " fmt
+
+static enum ssb_mitigation ssb_mode __ro_after_init = SPEC_STORE_BYPASS_NONE;
+
+/* The kernel command line selection */
+enum ssb_mitigation_cmd {
+ SPEC_STORE_BYPASS_CMD_NONE,
+ SPEC_STORE_BYPASS_CMD_AUTO,
+ SPEC_STORE_BYPASS_CMD_ON,
+ SPEC_STORE_BYPASS_CMD_PRCTL,
+ SPEC_STORE_BYPASS_CMD_SECCOMP,
+};
+
+static const char *ssb_strings[] = {
+ [SPEC_STORE_BYPASS_NONE] = "Vulnerable",
+ [SPEC_STORE_BYPASS_DISABLE] = "Mitigation: Speculative Store Bypass disabled",
+ [SPEC_STORE_BYPASS_PRCTL] = "Mitigation: Speculative Store Bypass disabled via prctl",
+ [SPEC_STORE_BYPASS_SECCOMP] = "Mitigation: Speculative Store Bypass disabled via prctl and seccomp",
+};
+
+static const struct {
+ const char *option;
+ enum ssb_mitigation_cmd cmd;
+} ssb_mitigation_options[] = {
+ { "auto", SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */
+ { "on", SPEC_STORE_BYPASS_CMD_ON }, /* Disable Speculative Store Bypass */
+ { "off", SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */
+ { "prctl", SPEC_STORE_BYPASS_CMD_PRCTL }, /* Disable Speculative Store Bypass via prctl */
+ { "seccomp", SPEC_STORE_BYPASS_CMD_SECCOMP }, /* Disable Speculative Store Bypass via prctl and seccomp */
+};
+
+static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void)
+{
+ enum ssb_mitigation_cmd cmd = SPEC_STORE_BYPASS_CMD_AUTO;
+ char arg[20];
+ int ret, i;
+
+ if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) {
+ return SPEC_STORE_BYPASS_CMD_NONE;
+ } else {
+ ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable",
+ arg, sizeof(arg));
+ if (ret < 0)
+ return SPEC_STORE_BYPASS_CMD_AUTO;
+
+ for (i = 0; i < ARRAY_SIZE(ssb_mitigation_options); i++) {
+ if (!match_option(arg, ret, ssb_mitigation_options[i].option))
+ continue;
+
+ cmd = ssb_mitigation_options[i].cmd;
+ break;
+ }
+
+ if (i >= ARRAY_SIZE(ssb_mitigation_options)) {
+ pr_err("unknown option (%s). Switching to AUTO select\n", arg);
+ return SPEC_STORE_BYPASS_CMD_AUTO;
+ }
+ }
+
+ return cmd;
+}
+
+static enum ssb_mitigation __init __ssb_select_mitigation(void)
+{
+ enum ssb_mitigation mode = SPEC_STORE_BYPASS_NONE;
+ enum ssb_mitigation_cmd cmd;
+
+ if (!boot_cpu_has(X86_FEATURE_SSBD))
+ return mode;
+
+ cmd = ssb_parse_cmdline();
+ if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS) &&
+ (cmd == SPEC_STORE_BYPASS_CMD_NONE ||
+ cmd == SPEC_STORE_BYPASS_CMD_AUTO))
+ return mode;
+
+ switch (cmd) {
+ case SPEC_STORE_BYPASS_CMD_AUTO:
+ case SPEC_STORE_BYPASS_CMD_SECCOMP:
+ /*
+ * Choose prctl+seccomp as the default mode if seccomp is
+ * enabled.
+ */
+ if (IS_ENABLED(CONFIG_SECCOMP))
+ mode = SPEC_STORE_BYPASS_SECCOMP;
+ else
+ mode = SPEC_STORE_BYPASS_PRCTL;
+ break;
+ case SPEC_STORE_BYPASS_CMD_ON:
+ mode = SPEC_STORE_BYPASS_DISABLE;
+ break;
+ case SPEC_STORE_BYPASS_CMD_PRCTL:
+ mode = SPEC_STORE_BYPASS_PRCTL;
+ break;
+ case SPEC_STORE_BYPASS_CMD_NONE:
+ break;
+ }
+
+ /*
+ * We have three CPU feature flags that are in play here:
+ * - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible.
+ * - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass
+ * - X86_FEATURE_SPEC_STORE_BYPASS_DISABLE - engage the mitigation
+ */
+ if (mode == SPEC_STORE_BYPASS_DISABLE) {
+ setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE);
+ /*
+ * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD uses
+ * a completely different MSR and bit dependent on family.
+ */
+ switch (boot_cpu_data.x86_vendor) {
+ case X86_VENDOR_INTEL:
+ x86_spec_ctrl_base |= SPEC_CTRL_SSBD;
+ x86_spec_ctrl_mask |= SPEC_CTRL_SSBD;
+ wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+ break;
+ case X86_VENDOR_AMD:
+ x86_amd_ssb_disable();
+ break;
+ }
+ }
+
+ return mode;
+}
+
+static void ssb_select_mitigation(void)
+{
+ ssb_mode = __ssb_select_mitigation();
+
+ if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+ pr_info("%s\n", ssb_strings[ssb_mode]);
+}
+
+#undef pr_fmt
+#define pr_fmt(fmt) "Speculation prctl: " fmt
+
+static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
+{
+ bool update;
+
+ if (ssb_mode != SPEC_STORE_BYPASS_PRCTL &&
+ ssb_mode != SPEC_STORE_BYPASS_SECCOMP)
+ return -ENXIO;
+
+ switch (ctrl) {
+ case PR_SPEC_ENABLE:
+ /* If speculation is force disabled, enable is not allowed */
+ if (task_spec_ssb_force_disable(task))
+ return -EPERM;
+ task_clear_spec_ssb_disable(task);
+ update = test_and_clear_tsk_thread_flag(task, TIF_SSBD);
+ break;
+ case PR_SPEC_DISABLE:
+ task_set_spec_ssb_disable(task);
+ update = !test_and_set_tsk_thread_flag(task, TIF_SSBD);
+ break;
+ case PR_SPEC_FORCE_DISABLE:
+ task_set_spec_ssb_disable(task);
+ task_set_spec_ssb_force_disable(task);
+ update = !test_and_set_tsk_thread_flag(task, TIF_SSBD);
+ break;
+ default:
+ return -ERANGE;
+ }
+
+ /*
+ * If being set on non-current task, delay setting the CPU
+ * mitigation until it is next scheduled.
+ */
+ if (task == current && update)
+ speculative_store_bypass_update_current();
+
+ return 0;
+}
+
+int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
+ unsigned long ctrl)
+{
+ switch (which) {
+ case PR_SPEC_STORE_BYPASS:
+ return ssb_prctl_set(task, ctrl);
+ default:
+ return -ENODEV;
+ }
+}
+
+#ifdef CONFIG_SECCOMP
+void arch_seccomp_spec_mitigate(struct task_struct *task)
+{
+ if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP)
+ ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE);
+}
+#endif
+
+static int ssb_prctl_get(struct task_struct *task)
+{
+ switch (ssb_mode) {
+ case SPEC_STORE_BYPASS_DISABLE:
+ return PR_SPEC_DISABLE;
+ case SPEC_STORE_BYPASS_SECCOMP:
+ case SPEC_STORE_BYPASS_PRCTL:
+ if (task_spec_ssb_force_disable(task))
+ return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
+ if (task_spec_ssb_disable(task))
+ return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
+ return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
+ default:
+ if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+ return PR_SPEC_ENABLE;
+ return PR_SPEC_NOT_AFFECTED;
+ }
+}
+
+int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
+{
+ switch (which) {
+ case PR_SPEC_STORE_BYPASS:
+ return ssb_prctl_get(task);
+ default:
+ return -ENODEV;
+ }
+}
+
+void x86_spec_ctrl_setup_ap(void)
+{
+ if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
+ wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+
+ if (ssb_mode == SPEC_STORE_BYPASS_DISABLE)
+ x86_amd_ssb_disable();
+}
#ifdef CONFIG_SYSFS
+
+static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
+ char *buf, unsigned int bug)
+{
+ if (!boot_cpu_has_bug(bug))
+ return sprintf(buf, "Not affected\n");
+
+ switch (bug) {
+ case X86_BUG_CPU_MELTDOWN:
+ if (boot_cpu_has(X86_FEATURE_PTI))
+ return sprintf(buf, "Mitigation: PTI\n");
+
+ break;
+
+ case X86_BUG_SPECTRE_V1:
+ return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+
+ case X86_BUG_SPECTRE_V2:
+ return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+ boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
+ boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
+ spectre_v2_module_string());
+
+ case X86_BUG_SPEC_STORE_BYPASS:
+ return sprintf(buf, "%s\n", ssb_strings[ssb_mode]);
+
+ default:
+ break;
+ }
+
+ return sprintf(buf, "Vulnerable\n");
+}
+
ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
{
- if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
- return sprintf(buf, "Not affected\n");
- if (boot_cpu_has(X86_FEATURE_PTI))
- return sprintf(buf, "Mitigation: PTI\n");
- return sprintf(buf, "Vulnerable\n");
+ return cpu_show_common(dev, attr, buf, X86_BUG_CPU_MELTDOWN);
}
ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf)
{
- if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
- return sprintf(buf, "Not affected\n");
- return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+ return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V1);
}
ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf)
{
- if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
- return sprintf(buf, "Not affected\n");
+ return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V2);
+}
- return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
- boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
- boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
- spectre_v2_module_string());
+ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS);
}
#endif
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
similarity index 95%
rename from arch/x86/kernel/cpu/intel_cacheinfo.c
rename to arch/x86/kernel/cpu/cacheinfo.c
index 54d04d5..38354c6 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -20,6 +20,8 @@
#include <asm/amd_nb.h>
#include <asm/smp.h>
+#include "cpu.h"
+
#define LVL_1_INST 1
#define LVL_1_DATA 2
#define LVL_2 3
@@ -637,6 +639,45 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c)
return i;
}
+void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
+{
+ /*
+ * We may have multiple LLCs if L3 caches exist, so check if we
+ * have an L3 cache by looking at the L3 cache CPUID leaf.
+ */
+ if (!cpuid_edx(0x80000006))
+ return;
+
+ if (c->x86 < 0x17) {
+ /* LLC is at the node level. */
+ per_cpu(cpu_llc_id, cpu) = node_id;
+ } else if (c->x86 == 0x17 &&
+ c->x86_model >= 0 && c->x86_model <= 0x1F) {
+ /*
+ * LLC is at the core complex level.
+ * Core complex ID is ApicId[3] for these processors.
+ */
+ per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
+ } else {
+ /*
+ * LLC ID is calculated from the number of threads sharing the
+ * cache.
+ * */
+ u32 eax, ebx, ecx, edx, num_sharing_cache = 0;
+ u32 llc_index = find_num_cache_leaves(c) - 1;
+
+ cpuid_count(0x8000001d, llc_index, &eax, &ebx, &ecx, &edx);
+ if (eax)
+ num_sharing_cache = ((eax >> 14) & 0xfff) + 1;
+
+ if (num_sharing_cache) {
+ int bits = get_count_order(num_sharing_cache) - 1;
+
+ per_cpu(cpu_llc_id, cpu) = c->apicid >> bits;
+ }
+ }
+}
+
void init_amd_cacheinfo(struct cpuinfo_x86 *c)
{
@@ -650,7 +691,7 @@ void init_amd_cacheinfo(struct cpuinfo_x86 *c)
}
}
-unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
+void init_intel_cacheinfo(struct cpuinfo_x86 *c)
{
/* Cache sizes */
unsigned int trace = 0, l1i = 0, l1d = 0, l2 = 0, l3 = 0;
@@ -802,7 +843,8 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));
- return l2;
+ if (!l2)
+ cpu_detect_cache_sizes(c);
}
static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index e5ec0f1..14433ff 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -18,6 +18,13 @@
#define RNG_ENABLED (1 << 3)
#define RNG_ENABLE (1 << 6) /* MSR_VIA_RNG */
+#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW 0x00200000
+#define X86_VMX_FEATURE_PROC_CTLS_VNMI 0x00400000
+#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS 0x80000000
+#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001
+#define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002
+#define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020
+
static void init_c3(struct cpuinfo_x86 *c)
{
u32 lo, hi;
@@ -112,6 +119,31 @@ static void early_init_centaur(struct cpuinfo_x86 *c)
}
}
+static void centaur_detect_vmx_virtcap(struct cpuinfo_x86 *c)
+{
+ u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2;
+
+ rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high);
+ msr_ctl = vmx_msr_high | vmx_msr_low;
+
+ if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)
+ set_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
+ if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI)
+ set_cpu_cap(c, X86_FEATURE_VNMI);
+ if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) {
+ rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
+ vmx_msr_low, vmx_msr_high);
+ msr_ctl2 = vmx_msr_high | vmx_msr_low;
+ if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) &&
+ (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW))
+ set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
+ if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT)
+ set_cpu_cap(c, X86_FEATURE_EPT);
+ if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID)
+ set_cpu_cap(c, X86_FEATURE_VPID);
+ }
+}
+
static void init_centaur(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_32
@@ -128,6 +160,24 @@ static void init_centaur(struct cpuinfo_x86 *c)
clear_cpu_cap(c, 0*32+31);
#endif
early_init_centaur(c);
+ init_intel_cacheinfo(c);
+ detect_num_cpu_cores(c);
+#ifdef CONFIG_X86_32
+ detect_ht(c);
+#endif
+
+ if (c->cpuid_level > 9) {
+ unsigned int eax = cpuid_eax(10);
+
+ /*
+ * Check for version and the number of counters
+ * Version(eax[7:0]) can't be 0;
+ * Counters(eax[15:8]) should be greater than 1;
+ */
+ if ((eax & 0xff) && (((eax >> 8) & 0xff) > 1))
+ set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
+ }
+
switch (c->x86) {
#ifdef CONFIG_X86_32
case 5:
@@ -199,6 +249,9 @@ static void init_centaur(struct cpuinfo_x86 *c)
#ifdef CONFIG_X86_64
set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
#endif
+
+ if (cpu_has(c, X86_FEATURE_VMX))
+ centaur_detect_vmx_virtcap(c);
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8a5b185..95c8e50 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -66,6 +66,13 @@ cpumask_var_t cpu_callin_mask;
/* representing cpus for which sibling maps can be computed */
cpumask_var_t cpu_sibling_setup_mask;
+/* Number of siblings per CPU package */
+int smp_num_siblings = 1;
+EXPORT_SYMBOL(smp_num_siblings);
+
+/* Last level cache ID of each logical CPU */
+DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID;
+
/* correctly size the local cpu masks */
void __init setup_cpu_local_masks(void)
{
@@ -577,6 +584,19 @@ static void get_model_name(struct cpuinfo_x86 *c)
*(s + 1) = '\0';
}
+void detect_num_cpu_cores(struct cpuinfo_x86 *c)
+{
+ unsigned int eax, ebx, ecx, edx;
+
+ c->x86_max_cores = 1;
+ if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4)
+ return;
+
+ cpuid_count(4, 0, &eax, &ebx, &ecx, &edx);
+ if (eax & 0x1f)
+ c->x86_max_cores = (eax >> 26) + 1;
+}
+
void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
{
unsigned int n, dummy, ebx, ecx, edx, l2size;
@@ -757,17 +777,32 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
* and they also have a different bit for STIBP support. Also,
* a hypervisor might have set the individual AMD bits even on
* Intel CPUs, for finer-grained selection of what's available.
- *
- * We use the AMD bits in 0x8000_0008 EBX as the generic hardware
- * features, which are visible in /proc/cpuinfo and used by the
- * kernel. So set those accordingly from the Intel bits.
*/
if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) {
set_cpu_cap(c, X86_FEATURE_IBRS);
set_cpu_cap(c, X86_FEATURE_IBPB);
+ set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
}
+
if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
set_cpu_cap(c, X86_FEATURE_STIBP);
+
+ if (cpu_has(c, X86_FEATURE_SPEC_CTRL_SSBD) ||
+ cpu_has(c, X86_FEATURE_VIRT_SSBD))
+ set_cpu_cap(c, X86_FEATURE_SSBD);
+
+ if (cpu_has(c, X86_FEATURE_AMD_IBRS)) {
+ set_cpu_cap(c, X86_FEATURE_IBRS);
+ set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
+ }
+
+ if (cpu_has(c, X86_FEATURE_AMD_IBPB))
+ set_cpu_cap(c, X86_FEATURE_IBPB);
+
+ if (cpu_has(c, X86_FEATURE_AMD_STIBP)) {
+ set_cpu_cap(c, X86_FEATURE_STIBP);
+ set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL);
+ }
}
void get_cpu_cap(struct cpuinfo_x86 *c)
@@ -848,6 +883,11 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
c->x86_power = edx;
}
+ if (c->extended_cpuid_level >= 0x80000008) {
+ cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
+ c->x86_capability[CPUID_8000_0008_EBX] = ebx;
+ }
+
if (c->extended_cpuid_level >= 0x8000000a)
c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
@@ -871,7 +911,6 @@ static void get_cpu_address_sizes(struct cpuinfo_x86 *c)
c->x86_virt_bits = (eax >> 8) & 0xff;
c->x86_phys_bits = eax & 0xff;
- c->x86_capability[CPUID_8000_0008_EBX] = ebx;
}
#ifdef CONFIG_X86_32
else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
@@ -923,21 +962,47 @@ static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
{}
};
-static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c)
+/* Only list CPUs which speculate but are non susceptible to SSB */
+static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_CORE_YONAH },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM },
+ { X86_VENDOR_AMD, 0x12, },
+ { X86_VENDOR_AMD, 0x11, },
+ { X86_VENDOR_AMD, 0x10, },
+ { X86_VENDOR_AMD, 0xf, },
+ {}
+};
+
+static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
{
u64 ia32_cap = 0;
- if (x86_match_cpu(cpu_no_meltdown))
- return false;
+ if (x86_match_cpu(cpu_no_speculation))
+ return;
+
+ setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
+ setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
+ if (!x86_match_cpu(cpu_no_spec_store_bypass) &&
+ !(ia32_cap & ARCH_CAP_SSB_NO))
+ setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
+
+ if (x86_match_cpu(cpu_no_meltdown))
+ return;
+
/* Rogue Data Cache Load? No! */
if (ia32_cap & ARCH_CAP_RDCL_NO)
- return false;
+ return;
- return true;
+ setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
}
/*
@@ -988,12 +1053,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
- if (!x86_match_cpu(cpu_no_speculation)) {
- if (cpu_vulnerable_to_meltdown(c))
- setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
- setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
- setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
- }
+ cpu_set_bug_bits(c);
fpu__init_system(c);
@@ -1004,6 +1064,21 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
*/
setup_clear_cpu_cap(X86_FEATURE_PCID);
#endif
+
+ /*
+ * Later in the boot process pgtable_l5_enabled() relies on
+ * cpu_feature_enabled(X86_FEATURE_LA57). If 5-level paging is not
+ * enabled by this point we need to clear the feature bit to avoid
+ * false-positives at the later stage.
+ *
+ * pgtable_l5_enabled() can be false here for several reasons:
+ * - 5-level paging is disabled compile-time;
+ * - it's 32-bit kernel;
+ * - machine doesn't support 5-level paging;
+ * - user specified 'no5lvl' in kernel command line.
+ */
+ if (!pgtable_l5_enabled())
+ setup_clear_cpu_cap(X86_FEATURE_LA57);
}
void __init early_cpu_init(void)
@@ -1355,6 +1430,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
#endif
mtrr_ap_init();
validate_apic_and_package_id(c);
+ x86_spec_ctrl_setup_ap();
}
static __init int setup_noclflush(char *arg)
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index e806b11..38216f6 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -47,7 +47,19 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[],
extern void get_cpu_cap(struct cpuinfo_x86 *c);
extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
+extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
+extern u32 get_scattered_cpuid_leaf(unsigned int level,
+ unsigned int sub_leaf,
+ enum cpuid_regs_idx reg);
+extern void init_intel_cacheinfo(struct cpuinfo_x86 *c);
+extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
+
+extern void detect_num_cpu_cores(struct cpuinfo_x86 *c);
+extern int detect_extended_topology(struct cpuinfo_x86 *c);
+extern void detect_ht(struct cpuinfo_x86 *c);
unsigned int aperfmperf_get_khz(int cpu);
+extern void x86_spec_ctrl_setup_ap(void);
+
#endif /* ARCH_X86_CPU_H */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b9693b8..eb75564 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -188,7 +188,10 @@ static void early_init_intel(struct cpuinfo_x86 *c)
setup_clear_cpu_cap(X86_FEATURE_IBPB);
setup_clear_cpu_cap(X86_FEATURE_STIBP);
setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL);
+ setup_clear_cpu_cap(X86_FEATURE_MSR_SPEC_CTRL);
setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP);
+ setup_clear_cpu_cap(X86_FEATURE_SSBD);
+ setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL_SSBD);
}
/*
@@ -453,24 +456,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
#endif
}
-/*
- * find out the number of processor cores on the die
- */
-static int intel_num_cpu_cores(struct cpuinfo_x86 *c)
-{
- unsigned int eax, ebx, ecx, edx;
-
- if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4)
- return 1;
-
- /* Intel has a non-standard dependency on %ecx for this CPUID level. */
- cpuid_count(4, 0, &eax, &ebx, &ecx, &edx);
- if (eax & 0x1f)
- return (eax >> 26) + 1;
- else
- return 1;
-}
-
static void detect_vmx_virtcap(struct cpuinfo_x86 *c)
{
/* Intel VMX MSR indicated features */
@@ -653,8 +638,6 @@ static void init_intel_misc_features(struct cpuinfo_x86 *c)
static void init_intel(struct cpuinfo_x86 *c)
{
- unsigned int l2 = 0;
-
early_init_intel(c);
intel_workarounds(c);
@@ -671,19 +654,13 @@ static void init_intel(struct cpuinfo_x86 *c)
* let's use the legacy cpuid vector 0x1 and 0x4 for topology
* detection.
*/
- c->x86_max_cores = intel_num_cpu_cores(c);
+ detect_num_cpu_cores(c);
#ifdef CONFIG_X86_32
detect_ht(c);
#endif
}
- l2 = init_intel_cacheinfo(c);
-
- /* Detect legacy cache sizes if init_intel_cacheinfo did not */
- if (l2 == 0) {
- cpu_detect_cache_sizes(c);
- l2 = c->x86_cache_size;
- }
+ init_intel_cacheinfo(c);
if (c->cpuid_level > 9) {
unsigned eax = cpuid_eax(10);
@@ -696,7 +673,8 @@ static void init_intel(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
if (boot_cpu_has(X86_FEATURE_DS)) {
- unsigned int l1;
+ unsigned int l1, l2;
+
rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
if (!(l1 & (1<<11)))
set_cpu_cap(c, X86_FEATURE_BTS);
@@ -724,6 +702,7 @@ static void init_intel(struct cpuinfo_x86 *c)
* Dixon is NOT a Celeron.
*/
if (c->x86 == 6) {
+ unsigned int l2 = c->x86_cache_size;
char *p = NULL;
switch (c->x86_model) {
@@ -835,6 +814,9 @@ static const struct _tlb_table intel_tlb_table[] = {
{ 0x5d, TLB_DATA_4K_4M, 256, " TLB_DATA 4 KByte and 4 MByte pages" },
{ 0x61, TLB_INST_4K, 48, " TLB_INST 4 KByte pages, full associative" },
{ 0x63, TLB_DATA_1G, 4, " TLB_DATA 1 GByte pages, 4-way set associative" },
+ { 0x6b, TLB_DATA_4K, 256, " TLB_DATA 4 KByte pages, 8-way associative" },
+ { 0x6c, TLB_DATA_2M_4M, 128, " TLB_DATA 2 MByte or 4 MByte pages, 8-way associative" },
+ { 0x6d, TLB_DATA_1G, 16, " TLB_DATA 1 GByte pages, fully associative" },
{ 0x76, TLB_INST_2M_4M, 8, " TLB_INST 2-MByte or 4-MByte pages, fully associative" },
{ 0xb0, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 4-way set associative" },
{ 0xb1, TLB_INST_2M_4M, 4, " TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" },
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 589b948..24bfa63e 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -33,8 +33,8 @@
#include <asm/intel_rdt_sched.h>
#include "intel_rdt.h"
-#define MAX_MBA_BW 100u
#define MBA_IS_LINEAR 0x4
+#define MBA_MAX_MBPS U32_MAX
/* Mutex to protect rdtgroup access. */
DEFINE_MUTEX(rdtgroup_mutex);
@@ -178,7 +178,7 @@ struct rdt_resource rdt_resources_all[] = {
.msr_update = mba_wrmsr,
.cache_level = 3,
.parse_ctrlval = parse_bw,
- .format_str = "%d=%*d",
+ .format_str = "%d=%*u",
.fflags = RFTYPE_RES_MB,
},
};
@@ -230,6 +230,14 @@ static inline void cache_alloc_hsw_probe(void)
rdt_alloc_capable = true;
}
+bool is_mba_sc(struct rdt_resource *r)
+{
+ if (!r)
+ return rdt_resources_all[RDT_RESOURCE_MBA].membw.mba_sc;
+
+ return r->membw.mba_sc;
+}
+
/*
* rdt_get_mb_table() - get a mapping of bandwidth(b/w) percentage values
* exposed to user interface and the h/w understandable delay values.
@@ -341,7 +349,7 @@ static int get_cache_id(int cpu, int level)
* that can be written to QOS_MSRs.
* There are currently no SKUs which support non linear delay values.
*/
-static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
+u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
{
if (r->membw.delay_linear)
return MAX_MBA_BW - bw;
@@ -431,25 +439,40 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
return NULL;
}
+void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm)
+{
+ int i;
+
+ /*
+ * Initialize the Control MSRs to having no control.
+ * For Cache Allocation: Set all bits in cbm
+ * For Memory Allocation: Set b/w requested to 100%
+ * and the bandwidth in MBps to U32_MAX
+ */
+ for (i = 0; i < r->num_closid; i++, dc++, dm++) {
+ *dc = r->default_ctrl;
+ *dm = MBA_MAX_MBPS;
+ }
+}
+
static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
{
struct msr_param m;
- u32 *dc;
- int i;
+ u32 *dc, *dm;
dc = kmalloc_array(r->num_closid, sizeof(*d->ctrl_val), GFP_KERNEL);
if (!dc)
return -ENOMEM;
- d->ctrl_val = dc;
+ dm = kmalloc_array(r->num_closid, sizeof(*d->mbps_val), GFP_KERNEL);
+ if (!dm) {
+ kfree(dc);
+ return -ENOMEM;
+ }
- /*
- * Initialize the Control MSRs to having no control.
- * For Cache Allocation: Set all bits in cbm
- * For Memory Allocation: Set b/w requested to 100
- */
- for (i = 0; i < r->num_closid; i++, dc++)
- *dc = r->default_ctrl;
+ d->ctrl_val = dc;
+ d->mbps_val = dm;
+ setup_default_ctrlval(r, dc, dm);
m.low = 0;
m.high = r->num_closid;
@@ -588,6 +611,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
}
kfree(d->ctrl_val);
+ kfree(d->mbps_val);
kfree(d->rmid_busy_llc);
kfree(d->mbm_total);
kfree(d->mbm_local);
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 3fd7a70..3975282 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -28,6 +28,7 @@
#define MBM_CNTR_WIDTH 24
#define MBM_OVERFLOW_INTERVAL 1000
+#define MAX_MBA_BW 100u
#define RMID_VAL_ERROR BIT_ULL(63)
#define RMID_VAL_UNAVAIL BIT_ULL(62)
@@ -180,10 +181,20 @@ struct rftype {
* struct mbm_state - status for each MBM counter in each domain
* @chunks: Total data moved (multiply by rdt_group.mon_scale to get bytes)
* @prev_msr Value of IA32_QM_CTR for this RMID last time we read it
+ * @chunks_bw Total local data moved. Used for bandwidth calculation
+ * @prev_bw_msr:Value of previous IA32_QM_CTR for bandwidth counting
+ * @prev_bw The most recent bandwidth in MBps
+ * @delta_bw Difference between the current and previous bandwidth
+ * @delta_comp Indicates whether to compute the delta_bw
*/
struct mbm_state {
u64 chunks;
u64 prev_msr;
+ u64 chunks_bw;
+ u64 prev_bw_msr;
+ u32 prev_bw;
+ u32 delta_bw;
+ bool delta_comp;
};
/**
@@ -202,6 +213,7 @@ struct mbm_state {
* @cqm_work_cpu:
* worker cpu for CQM h/w counters
* @ctrl_val: array of cache or mem ctrl values (indexed by CLOSID)
+ * @mbps_val: When mba_sc is enabled, this holds the bandwidth in MBps
* @new_ctrl: new ctrl value to be loaded
* @have_new_ctrl: did user provide new_ctrl for this domain
*/
@@ -217,6 +229,7 @@ struct rdt_domain {
int mbm_work_cpu;
int cqm_work_cpu;
u32 *ctrl_val;
+ u32 *mbps_val;
u32 new_ctrl;
bool have_new_ctrl;
};
@@ -259,6 +272,7 @@ struct rdt_cache {
* @min_bw: Minimum memory bandwidth percentage user can request
* @bw_gran: Granularity at which the memory bandwidth is allocated
* @delay_linear: True if memory B/W delay is in linear scale
+ * @mba_sc: True if MBA software controller(mba_sc) is enabled
* @mb_map: Mapping of memory B/W percentage to memory B/W delay
*/
struct rdt_membw {
@@ -266,6 +280,7 @@ struct rdt_membw {
u32 min_bw;
u32 bw_gran;
u32 delay_linear;
+ bool mba_sc;
u32 *mb_map;
};
@@ -445,6 +460,9 @@ void mon_event_read(struct rmid_read *rr, struct rdt_domain *d,
void mbm_setup_overflow_handler(struct rdt_domain *dom,
unsigned long delay_ms);
void mbm_handle_overflow(struct work_struct *work);
+bool is_mba_sc(struct rdt_resource *r);
+void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm);
+u32 delay_bw_map(unsigned long bw, struct rdt_resource *r);
void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms);
void cqm_handle_limbo(struct work_struct *work);
bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index 23e1d5c..116d57b 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -53,7 +53,8 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
return false;
}
- if (bw < r->membw.min_bw || bw > r->default_ctrl) {
+ if ((bw < r->membw.min_bw || bw > r->default_ctrl) &&
+ !is_mba_sc(r)) {
rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw,
r->membw.min_bw, r->default_ctrl);
return false;
@@ -179,6 +180,8 @@ static int update_domains(struct rdt_resource *r, int closid)
struct msr_param msr_param;
cpumask_var_t cpu_mask;
struct rdt_domain *d;
+ bool mba_sc;
+ u32 *dc;
int cpu;
if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
@@ -188,13 +191,20 @@ static int update_domains(struct rdt_resource *r, int closid)
msr_param.high = msr_param.low + 1;
msr_param.res = r;
+ mba_sc = is_mba_sc(r);
list_for_each_entry(d, &r->domains, list) {
- if (d->have_new_ctrl && d->new_ctrl != d->ctrl_val[closid]) {
+ dc = !mba_sc ? d->ctrl_val : d->mbps_val;
+ if (d->have_new_ctrl && d->new_ctrl != dc[closid]) {
cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
- d->ctrl_val[closid] = d->new_ctrl;
+ dc[closid] = d->new_ctrl;
}
}
- if (cpumask_empty(cpu_mask))
+
+ /*
+ * Avoid writing the control msr with control values when
+ * MBA software controller is enabled
+ */
+ if (cpumask_empty(cpu_mask) || mba_sc)
goto done;
cpu = get_cpu();
/* Update CBM on this cpu if it's in cpu_mask. */
@@ -282,13 +292,17 @@ static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid)
{
struct rdt_domain *dom;
bool sep = false;
+ u32 ctrl_val;
seq_printf(s, "%*s:", max_name_width, r->name);
list_for_each_entry(dom, &r->domains, list) {
if (sep)
seq_puts(s, ";");
+
+ ctrl_val = (!is_mba_sc(r) ? dom->ctrl_val[closid] :
+ dom->mbps_val[closid]);
seq_printf(s, r->format_str, dom->id, max_data_width,
- dom->ctrl_val[closid]);
+ ctrl_val);
sep = true;
}
seq_puts(s, "\n");
diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/intel_rdt_monitor.c
index 681450e..b0f3aed 100644
--- a/arch/x86/kernel/cpu/intel_rdt_monitor.c
+++ b/arch/x86/kernel/cpu/intel_rdt_monitor.c
@@ -225,10 +225,18 @@ void free_rmid(u32 rmid)
list_add_tail(&entry->list, &rmid_free_lru);
}
+static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr)
+{
+ u64 shift = 64 - MBM_CNTR_WIDTH, chunks;
+
+ chunks = (cur_msr << shift) - (prev_msr << shift);
+ return chunks >>= shift;
+}
+
static int __mon_event_count(u32 rmid, struct rmid_read *rr)
{
- u64 chunks, shift, tval;
struct mbm_state *m;
+ u64 chunks, tval;
tval = __rmid_read(rmid, rr->evtid);
if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) {
@@ -254,14 +262,12 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
}
if (rr->first) {
- m->prev_msr = tval;
- m->chunks = 0;
+ memset(m, 0, sizeof(struct mbm_state));
+ m->prev_bw_msr = m->prev_msr = tval;
return 0;
}
- shift = 64 - MBM_CNTR_WIDTH;
- chunks = (tval << shift) - (m->prev_msr << shift);
- chunks >>= shift;
+ chunks = mbm_overflow_count(m->prev_msr, tval);
m->chunks += chunks;
m->prev_msr = tval;
@@ -270,6 +276,32 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
}
/*
+ * Supporting function to calculate the memory bandwidth
+ * and delta bandwidth in MBps.
+ */
+static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
+{
+ struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3];
+ struct mbm_state *m = &rr->d->mbm_local[rmid];
+ u64 tval, cur_bw, chunks;
+
+ tval = __rmid_read(rmid, rr->evtid);
+ if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL))
+ return;
+
+ chunks = mbm_overflow_count(m->prev_bw_msr, tval);
+ m->chunks_bw += chunks;
+ m->chunks = m->chunks_bw;
+ cur_bw = (chunks * r->mon_scale) >> 20;
+
+ if (m->delta_comp)
+ m->delta_bw = abs(cur_bw - m->prev_bw);
+ m->delta_comp = false;
+ m->prev_bw = cur_bw;
+ m->prev_bw_msr = tval;
+}
+
+/*
* This is called via IPI to read the CQM/MBM counters
* on a domain.
*/
@@ -297,6 +329,118 @@ void mon_event_count(void *info)
}
}
+/*
+ * Feedback loop for MBA software controller (mba_sc)
+ *
+ * mba_sc is a feedback loop where we periodically read MBM counters and
+ * adjust the bandwidth percentage values via the IA32_MBA_THRTL_MSRs so
+ * that:
+ *
+ * current bandwdith(cur_bw) < user specified bandwidth(user_bw)
+ *
+ * This uses the MBM counters to measure the bandwidth and MBA throttle
+ * MSRs to control the bandwidth for a particular rdtgrp. It builds on the
+ * fact that resctrl rdtgroups have both monitoring and control.
+ *
+ * The frequency of the checks is 1s and we just tag along the MBM overflow
+ * timer. Having 1s interval makes the calculation of bandwidth simpler.
+ *
+ * Although MBA's goal is to restrict the bandwidth to a maximum, there may
+ * be a need to increase the bandwidth to avoid uncecessarily restricting
+ * the L2 <-> L3 traffic.
+ *
+ * Since MBA controls the L2 external bandwidth where as MBM measures the
+ * L3 external bandwidth the following sequence could lead to such a
+ * situation.
+ *
+ * Consider an rdtgroup which had high L3 <-> memory traffic in initial
+ * phases -> mba_sc kicks in and reduced bandwidth percentage values -> but
+ * after some time rdtgroup has mostly L2 <-> L3 traffic.
+ *
+ * In this case we may restrict the rdtgroup's L2 <-> L3 traffic as its
+ * throttle MSRs already have low percentage values. To avoid
+ * unnecessarily restricting such rdtgroups, we also increase the bandwidth.
+ */
+static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
+{
+ u32 closid, rmid, cur_msr, cur_msr_val, new_msr_val;
+ struct mbm_state *pmbm_data, *cmbm_data;
+ u32 cur_bw, delta_bw, user_bw;
+ struct rdt_resource *r_mba;
+ struct rdt_domain *dom_mba;
+ struct list_head *head;
+ struct rdtgroup *entry;
+
+ r_mba = &rdt_resources_all[RDT_RESOURCE_MBA];
+ closid = rgrp->closid;
+ rmid = rgrp->mon.rmid;
+ pmbm_data = &dom_mbm->mbm_local[rmid];
+
+ dom_mba = get_domain_from_cpu(smp_processor_id(), r_mba);
+ if (!dom_mba) {
+ pr_warn_once("Failure to get domain for MBA update\n");
+ return;
+ }
+
+ cur_bw = pmbm_data->prev_bw;
+ user_bw = dom_mba->mbps_val[closid];
+ delta_bw = pmbm_data->delta_bw;
+ cur_msr_val = dom_mba->ctrl_val[closid];
+
+ /*
+ * For Ctrl groups read data from child monitor groups.
+ */
+ head = &rgrp->mon.crdtgrp_list;
+ list_for_each_entry(entry, head, mon.crdtgrp_list) {
+ cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
+ cur_bw += cmbm_data->prev_bw;
+ delta_bw += cmbm_data->delta_bw;
+ }
+
+ /*
+ * Scale up/down the bandwidth linearly for the ctrl group. The
+ * bandwidth step is the bandwidth granularity specified by the
+ * hardware.
+ *
+ * The delta_bw is used when increasing the bandwidth so that we
+ * dont alternately increase and decrease the control values
+ * continuously.
+ *
+ * For ex: consider cur_bw = 90MBps, user_bw = 100MBps and if
+ * bandwidth step is 20MBps(> user_bw - cur_bw), we would keep
+ * switching between 90 and 110 continuously if we only check
+ * cur_bw < user_bw.
+ */
+ if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) {
+ new_msr_val = cur_msr_val - r_mba->membw.bw_gran;
+ } else if (cur_msr_val < MAX_MBA_BW &&
+ (user_bw > (cur_bw + delta_bw))) {
+ new_msr_val = cur_msr_val + r_mba->membw.bw_gran;
+ } else {
+ return;
+ }
+
+ cur_msr = r_mba->msr_base + closid;
+ wrmsrl(cur_msr, delay_bw_map(new_msr_val, r_mba));
+ dom_mba->ctrl_val[closid] = new_msr_val;
+
+ /*
+ * Delta values are updated dynamically package wise for each
+ * rdtgrp everytime the throttle MSR changes value.
+ *
+ * This is because (1)the increase in bandwidth is not perfectly
+ * linear and only "approximately" linear even when the hardware
+ * says it is linear.(2)Also since MBA is a core specific
+ * mechanism, the delta values vary based on number of cores used
+ * by the rdtgrp.
+ */
+ pmbm_data->delta_comp = true;
+ list_for_each_entry(entry, head, mon.crdtgrp_list) {
+ cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
+ cmbm_data->delta_comp = true;
+ }
+}
+
static void mbm_update(struct rdt_domain *d, int rmid)
{
struct rmid_read rr;
@@ -314,7 +458,16 @@ static void mbm_update(struct rdt_domain *d, int rmid)
}
if (is_mbm_local_enabled()) {
rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
- __mon_event_count(rmid, &rr);
+
+ /*
+ * Call the MBA software controller only for the
+ * control groups and when user has enabled
+ * the software controller explicitly.
+ */
+ if (!is_mba_sc(NULL))
+ __mon_event_count(rmid, &rr);
+ else
+ mbm_bw_count(rmid, &rr);
}
}
@@ -385,6 +538,9 @@ void mbm_handle_overflow(struct work_struct *work)
head = &prgrp->mon.crdtgrp_list;
list_for_each_entry(crgrp, head, mon.crdtgrp_list)
mbm_update(d, crgrp->mon.rmid);
+
+ if (is_mba_sc(NULL))
+ update_mba_bw(prgrp, d);
}
schedule_delayed_work_on(cpu, &d->mbm_over, delay);
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index fca759d..749856a 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -1005,6 +1005,11 @@ static void l2_qos_cfg_update(void *arg)
wrmsrl(IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
}
+static inline bool is_mba_linear(void)
+{
+ return rdt_resources_all[RDT_RESOURCE_MBA].membw.delay_linear;
+}
+
static int set_cache_qos_cfg(int level, bool enable)
{
void (*update)(void *arg);
@@ -1041,6 +1046,28 @@ static int set_cache_qos_cfg(int level, bool enable)
return 0;
}
+/*
+ * Enable or disable the MBA software controller
+ * which helps user specify bandwidth in MBps.
+ * MBA software controller is supported only if
+ * MBM is supported and MBA is in linear scale.
+ */
+static int set_mba_sc(bool mba_sc)
+{
+ struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA];
+ struct rdt_domain *d;
+
+ if (!is_mbm_enabled() || !is_mba_linear() ||
+ mba_sc == is_mba_sc(r))
+ return -EINVAL;
+
+ r->membw.mba_sc = mba_sc;
+ list_for_each_entry(d, &r->domains, list)
+ setup_default_ctrlval(r, d->ctrl_val, d->mbps_val);
+
+ return 0;
+}
+
static int cdp_enable(int level, int data_type, int code_type)
{
struct rdt_resource *r_ldata = &rdt_resources_all[data_type];
@@ -1123,6 +1150,10 @@ static int parse_rdtgroupfs_options(char *data)
ret = cdpl2_enable();
if (ret)
goto out;
+ } else if (!strcmp(token, "mba_MBps")) {
+ ret = set_mba_sc(true);
+ if (ret)
+ goto out;
} else {
ret = -EINVAL;
goto out;
@@ -1445,6 +1476,8 @@ static void rdt_kill_sb(struct super_block *sb)
cpus_read_lock();
mutex_lock(&rdtgroup_mutex);
+ set_mba_sc(false);
+
/*Put everything back to default values. */
for_each_alloc_enabled_rdt_resource(r)
reset_all_ctrls(r);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 475cb4f..c805a06 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -48,7 +48,7 @@ static struct dentry *dfs_inj;
static u8 n_banks;
-#define MAX_FLAG_OPT_SIZE 3
+#define MAX_FLAG_OPT_SIZE 4
#define NBCFG 0x44
enum injection_type {
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 42cf288..cd76380 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1727,6 +1727,21 @@ static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c)
}
}
+static void mce_centaur_feature_init(struct cpuinfo_x86 *c)
+{
+ struct mca_config *cfg = &mca_cfg;
+
+ /*
+ * All newer Centaur CPUs support MCE broadcasting. Enable
+ * synchronization with a one second timeout.
+ */
+ if ((c->x86 == 6 && c->x86_model == 0xf && c->x86_stepping >= 0xe) ||
+ c->x86 > 6) {
+ if (cfg->monarch_timeout < 0)
+ cfg->monarch_timeout = USEC_PER_SEC;
+ }
+}
+
static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
{
switch (c->x86_vendor) {
@@ -1739,6 +1754,9 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
mce_amd_feature_init(c);
break;
}
+ case X86_VENDOR_CENTAUR:
+ mce_centaur_feature_init(c);
+ break;
default:
break;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index f7666ee..f591b01 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -94,6 +94,11 @@ static struct smca_bank_name smca_names[] = {
[SMCA_SMU] = { "smu", "System Management Unit" },
};
+static u32 smca_bank_addrs[MAX_NR_BANKS][NR_BLOCKS] __ro_after_init =
+{
+ [0 ... MAX_NR_BANKS - 1] = { [0 ... NR_BLOCKS - 1] = -1 }
+};
+
const char *smca_get_name(enum smca_bank_types t)
{
if (t >= N_SMCA_BANK_TYPES)
@@ -431,8 +436,7 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
wrmsr(MSR_CU_DEF_ERR, low, high);
}
-static u32 smca_get_block_address(unsigned int cpu, unsigned int bank,
- unsigned int block)
+static u32 smca_get_block_address(unsigned int bank, unsigned int block)
{
u32 low, high;
u32 addr = 0;
@@ -443,24 +447,30 @@ static u32 smca_get_block_address(unsigned int cpu, unsigned int bank,
if (!block)
return MSR_AMD64_SMCA_MCx_MISC(bank);
+ /* Check our cache first: */
+ if (smca_bank_addrs[bank][block] != -1)
+ return smca_bank_addrs[bank][block];
+
/*
* For SMCA enabled processors, BLKPTR field of the first MISC register
* (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4).
*/
- if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
- return addr;
+ if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
+ goto out;
if (!(low & MCI_CONFIG_MCAX))
- return addr;
+ goto out;
- if (!rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
+ if (!rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
(low & MASK_BLKPTR_LO))
- return MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
+ addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
+out:
+ smca_bank_addrs[bank][block] = addr;
return addr;
}
-static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 high,
+static u32 get_block_address(u32 current_addr, u32 low, u32 high,
unsigned int bank, unsigned int block)
{
u32 addr = 0, offset = 0;
@@ -468,20 +478,8 @@ static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 hi
if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS))
return addr;
- /* Get address from already initialized block. */
- if (per_cpu(threshold_banks, cpu)) {
- struct threshold_bank *bankp = per_cpu(threshold_banks, cpu)[bank];
-
- if (bankp && bankp->blocks) {
- struct threshold_block *blockp = &bankp->blocks[block];
-
- if (blockp)
- return blockp->address;
- }
- }
-
if (mce_flags.smca)
- return smca_get_block_address(cpu, bank, block);
+ return smca_get_block_address(bank, block);
/* Fall back to method we used for older processors: */
switch (block) {
@@ -559,7 +557,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
smca_configure(bank, cpu);
for (block = 0; block < NR_BLOCKS; ++block) {
- address = get_block_address(cpu, address, low, high, bank, block);
+ address = get_block_address(address, low, high, bank, block);
if (!address)
break;
@@ -1176,7 +1174,7 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
if (err)
goto out_free;
recurse:
- address = get_block_address(cpu, address, low, high, bank, ++block);
+ address = get_block_address(address, low, high, bank, ++block);
if (!address)
return 0;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 10c4fc2..77e2013 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -564,14 +564,12 @@ static int __reload_late(void *info)
apply_microcode_local(&err);
spin_unlock(&update_lock);
+ /* siblings return UCODE_OK because their engine got updated already */
if (err > UCODE_NFOUND) {
pr_warn("Error reloading microcode on CPU %d\n", cpu);
- return -1;
- /* siblings return UCODE_OK because their engine got updated already */
+ ret = -1;
} else if (err == UCODE_UPDATED || err == UCODE_OK) {
ret = 1;
- } else {
- return ret;
}
/*
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 32b8e57..1c2cfa0 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -485,7 +485,6 @@ static void show_saved_mc(void)
*/
static void save_mc_for_early(u8 *mc, unsigned int size)
{
-#ifdef CONFIG_HOTPLUG_CPU
/* Synchronization during CPU hotplug. */
static DEFINE_MUTEX(x86_cpu_microcode_mutex);
@@ -495,7 +494,6 @@ static void save_mc_for_early(u8 *mc, unsigned int size)
show_saved_mc();
mutex_unlock(&x86_cpu_microcode_mutex);
-#endif
}
static bool load_builtin_intel_microcode(struct cpio_data *cp)
diff --git a/arch/x86/kernel/cpu/mtrr/Makefile b/arch/x86/kernel/cpu/mtrr/Makefile
index ad9e5ed..2ad9107 100644
--- a/arch/x86/kernel/cpu/mtrr/Makefile
+++ b/arch/x86/kernel/cpu/mtrr/Makefile
@@ -1,3 +1,3 @@
-obj-y := main.o if.o generic.o cleanup.o
+obj-y := mtrr.o if.o generic.o cleanup.o
obj-$(CONFIG_X86_32) += amd.o cyrix.o centaur.o
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/mtrr.c
similarity index 95%
rename from arch/x86/kernel/cpu/mtrr/main.c
rename to arch/x86/kernel/cpu/mtrr/mtrr.c
index 7468de4..9a19c80 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.c
@@ -46,6 +46,7 @@
#include <linux/pci.h>
#include <linux/smp.h>
#include <linux/syscore_ops.h>
+#include <linux/rcupdate.h>
#include <asm/cpufeature.h>
#include <asm/e820/api.h>
@@ -100,7 +101,7 @@ static int have_wrcomb(void)
if (dev->vendor == PCI_VENDOR_ID_SERVERWORKS &&
dev->device == PCI_DEVICE_ID_SERVERWORKS_LE &&
dev->revision <= 5) {
- pr_info("mtrr: Serverworks LE rev < 6 detected. Write-combining disabled.\n");
+ pr_info("Serverworks LE rev < 6 detected. Write-combining disabled.\n");
pci_dev_put(dev);
return 0;
}
@@ -110,7 +111,7 @@ static int have_wrcomb(void)
*/
if (dev->vendor == PCI_VENDOR_ID_INTEL &&
dev->device == PCI_DEVICE_ID_INTEL_82451NX) {
- pr_info("mtrr: Intel 450NX MMC detected. Write-combining disabled.\n");
+ pr_info("Intel 450NX MMC detected. Write-combining disabled.\n");
pci_dev_put(dev);
return 0;
}
@@ -312,24 +313,24 @@ int mtrr_add_page(unsigned long base, unsigned long size,
return error;
if (type >= MTRR_NUM_TYPES) {
- pr_warn("mtrr: type: %u invalid\n", type);
+ pr_warn("type: %u invalid\n", type);
return -EINVAL;
}
/* If the type is WC, check that this processor supports it */
if ((type == MTRR_TYPE_WRCOMB) && !have_wrcomb()) {
- pr_warn("mtrr: your processor doesn't support write-combining\n");
+ pr_warn("your processor doesn't support write-combining\n");
return -ENOSYS;
}
if (!size) {
- pr_warn("mtrr: zero sized request\n");
+ pr_warn("zero sized request\n");
return -EINVAL;
}
if ((base | (base + size - 1)) >>
(boot_cpu_data.x86_phys_bits - PAGE_SHIFT)) {
- pr_warn("mtrr: base or size exceeds the MTRR width\n");
+ pr_warn("base or size exceeds the MTRR width\n");
return -EINVAL;
}
@@ -360,8 +361,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
} else if (types_compatible(type, ltype))
continue;
}
- pr_warn("mtrr: 0x%lx000,0x%lx000 overlaps existing"
- " 0x%lx000,0x%lx000\n", base, size, lbase,
+ pr_warn("0x%lx000,0x%lx000 overlaps existing 0x%lx000,0x%lx000\n", base, size, lbase,
lsize);
goto out;
}
@@ -369,7 +369,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
if (ltype != type) {
if (types_compatible(type, ltype))
continue;
- pr_warn("mtrr: type mismatch for %lx000,%lx000 old: %s new: %s\n",
+ pr_warn("type mismatch for %lx000,%lx000 old: %s new: %s\n",
base, size, mtrr_attrib_to_str(ltype),
mtrr_attrib_to_str(type));
goto out;
@@ -395,7 +395,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
}
}
} else {
- pr_info("mtrr: no more MTRRs available\n");
+ pr_info("no more MTRRs available\n");
}
error = i;
out:
@@ -407,8 +407,8 @@ int mtrr_add_page(unsigned long base, unsigned long size,
static int mtrr_check(unsigned long base, unsigned long size)
{
if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) {
- pr_warn("mtrr: size and base must be multiples of 4 kiB\n");
- pr_debug("mtrr: size: 0x%lx base: 0x%lx\n", size, base);
+ pr_warn("size and base must be multiples of 4 kiB\n");
+ pr_debug("size: 0x%lx base: 0x%lx\n", size, base);
dump_stack();
return -1;
}
@@ -499,22 +499,22 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
}
}
if (reg < 0) {
- pr_debug("mtrr: no MTRR for %lx000,%lx000 found\n",
+ pr_debug("no MTRR for %lx000,%lx000 found\n",
base, size);
goto out;
}
}
if (reg >= max) {
- pr_warn("mtrr: register: %d too big\n", reg);
+ pr_warn("register: %d too big\n", reg);
goto out;
}
mtrr_if->get(reg, &lbase, &lsize, <ype);
if (lsize < 1) {
- pr_warn("mtrr: MTRR %d not used\n", reg);
+ pr_warn("MTRR %d not used\n", reg);
goto out;
}
if (mtrr_usage_table[reg] < 1) {
- pr_warn("mtrr: reg: %d has count=0\n", reg);
+ pr_warn("reg: %d has count=0\n", reg);
goto out;
}
if (--mtrr_usage_table[reg] < 1)
@@ -775,7 +775,7 @@ void __init mtrr_bp_init(void)
}
if (!mtrr_enabled()) {
- pr_info("MTRR: Disabled\n");
+ pr_info("Disabled\n");
/*
* PAT initialization relies on MTRR's rendezvous handler.
@@ -793,6 +793,9 @@ void mtrr_ap_init(void)
if (!use_intel() || mtrr_aps_delayed_init)
return;
+
+ rcu_cpu_starting(smp_processor_id());
+
/*
* Ideally we should hold mtrr_mutex here to avoid mtrr entries
* changed, but this routine will be called in cpu boot time,
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index b099024..81c0afb 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -27,7 +27,7 @@
* exists, use it for populating initial_apicid and cpu topology
* detection.
*/
-void detect_extended_topology(struct cpuinfo_x86 *c)
+int detect_extended_topology(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
unsigned int eax, ebx, ecx, edx, sub_index;
@@ -36,7 +36,7 @@ void detect_extended_topology(struct cpuinfo_x86 *c)
static bool printed;
if (c->cpuid_level < 0xb)
- return;
+ return -1;
cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
@@ -44,7 +44,7 @@ void detect_extended_topology(struct cpuinfo_x86 *c)
* check if the cpuid leaf 0xb is actually implemented.
*/
if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
- return;
+ return -1;
set_cpu_cap(c, X86_FEATURE_XTOPOLOGY);
@@ -95,6 +95,6 @@ void detect_extended_topology(struct cpuinfo_x86 *c)
c->cpu_core_id);
printed = 1;
}
- return;
#endif
+ return 0;
}
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 18fa9d7..666a284 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -22,11 +22,14 @@
#include <asm/stacktrace.h>
#include <asm/unwind.h>
+#define OPCODE_BUFSIZE 64
+
int panic_on_unrecovered_nmi;
int panic_on_io_nmi;
-static unsigned int code_bytes = 64;
static int die_counter;
+static struct pt_regs exec_summary_regs;
+
bool in_task_stack(unsigned long *stack, struct task_struct *task,
struct stack_info *info)
{
@@ -69,9 +72,62 @@ static void printk_stack_address(unsigned long address, int reliable,
printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address);
}
+/*
+ * There are a couple of reasons for the 2/3rd prologue, courtesy of Linus:
+ *
+ * In case where we don't have the exact kernel image (which, if we did, we can
+ * simply disassemble and navigate to the RIP), the purpose of the bigger
+ * prologue is to have more context and to be able to correlate the code from
+ * the different toolchains better.
+ *
+ * In addition, it helps in recreating the register allocation of the failing
+ * kernel and thus make sense of the register dump.
+ *
+ * What is more, the additional complication of a variable length insn arch like
+ * x86 warrants having longer byte sequence before rIP so that the disassembler
+ * can "sync" up properly and find instruction boundaries when decoding the
+ * opcode bytes.
+ *
+ * Thus, the 2/3rds prologue and 64 byte OPCODE_BUFSIZE is just a random
+ * guesstimate in attempt to achieve all of the above.
+ */
+void show_opcodes(u8 *rip, const char *loglvl)
+{
+ unsigned int code_prologue = OPCODE_BUFSIZE * 2 / 3;
+ u8 opcodes[OPCODE_BUFSIZE];
+ u8 *ip;
+ int i;
+
+ printk("%sCode: ", loglvl);
+
+ ip = (u8 *)rip - code_prologue;
+ if (probe_kernel_read(opcodes, ip, OPCODE_BUFSIZE)) {
+ pr_cont("Bad RIP value.\n");
+ return;
+ }
+
+ for (i = 0; i < OPCODE_BUFSIZE; i++, ip++) {
+ if (ip == rip)
+ pr_cont("<%02x> ", opcodes[i]);
+ else
+ pr_cont("%02x ", opcodes[i]);
+ }
+ pr_cont("\n");
+}
+
+void show_ip(struct pt_regs *regs, const char *loglvl)
+{
+#ifdef CONFIG_X86_32
+ printk("%sEIP: %pS\n", loglvl, (void *)regs->ip);
+#else
+ printk("%sRIP: %04x:%pS\n", loglvl, (int)regs->cs, (void *)regs->ip);
+#endif
+ show_opcodes((u8 *)regs->ip, loglvl);
+}
+
void show_iret_regs(struct pt_regs *regs)
{
- printk(KERN_DEFAULT "RIP: %04x:%pS\n", (int)regs->cs, (void *)regs->ip);
+ show_ip(regs, KERN_DEFAULT);
printk(KERN_DEFAULT "RSP: %04x:%016lx EFLAGS: %08lx", (int)regs->ss,
regs->sp, regs->flags);
}
@@ -267,7 +323,6 @@ unsigned long oops_begin(void)
bust_spinlocks(1);
return flags;
}
-EXPORT_SYMBOL_GPL(oops_begin);
NOKPROBE_SYMBOL(oops_begin);
void __noreturn rewind_stack_do_exit(int signr);
@@ -287,6 +342,9 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
raw_local_irq_restore(flags);
oops_exit();
+ /* Executive summary in case the oops scrolled away */
+ __show_regs(&exec_summary_regs, true);
+
if (!signr)
return;
if (in_interrupt())
@@ -305,10 +363,10 @@ NOKPROBE_SYMBOL(oops_end);
int __die(const char *str, struct pt_regs *regs, long err)
{
-#ifdef CONFIG_X86_32
- unsigned short ss;
- unsigned long sp;
-#endif
+ /* Save the regs of the first oops for the executive summary later. */
+ if (!die_counter)
+ exec_summary_regs = *regs;
+
printk(KERN_DEFAULT
"%s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff, ++die_counter,
IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "",
@@ -318,26 +376,13 @@ int __die(const char *str, struct pt_regs *regs, long err)
IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION) ?
(boot_cpu_has(X86_FEATURE_PTI) ? " PTI" : " NOPTI") : "");
+ show_regs(regs);
+ print_modules();
+
if (notify_die(DIE_OOPS, str, regs, err,
current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
return 1;
- print_modules();
- show_regs(regs);
-#ifdef CONFIG_X86_32
- if (user_mode(regs)) {
- sp = regs->sp;
- ss = regs->ss;
- } else {
- sp = kernel_stack_pointer(regs);
- savesegment(ss, ss);
- }
- printk(KERN_EMERG "EIP: %pS SS:ESP: %04x:%08lx\n",
- (void *)regs->ip, ss, sp);
-#else
- /* Executive summary in case the oops scrolled away */
- printk(KERN_ALERT "RIP: %pS RSP: %016lx\n", (void *)regs->ip, regs->sp);
-#endif
return 0;
}
NOKPROBE_SYMBOL(__die);
@@ -356,30 +401,9 @@ void die(const char *str, struct pt_regs *regs, long err)
oops_end(flags, regs, sig);
}
-static int __init code_bytes_setup(char *s)
-{
- ssize_t ret;
- unsigned long val;
-
- if (!s)
- return -EINVAL;
-
- ret = kstrtoul(s, 0, &val);
- if (ret)
- return ret;
-
- code_bytes = val;
- if (code_bytes > 8192)
- code_bytes = 8192;
-
- return 1;
-}
-__setup("code_bytes=", code_bytes_setup);
-
void show_regs(struct pt_regs *regs)
{
bool all = true;
- int i;
show_regs_print_info(KERN_DEFAULT);
@@ -389,36 +413,8 @@ void show_regs(struct pt_regs *regs)
__show_regs(regs, all);
/*
- * When in-kernel, we also print out the stack and code at the
- * time of the fault..
+ * When in-kernel, we also print out the stack at the time of the fault..
*/
- if (!user_mode(regs)) {
- unsigned int code_prologue = code_bytes * 43 / 64;
- unsigned int code_len = code_bytes;
- unsigned char c;
- u8 *ip;
-
+ if (!user_mode(regs))
show_trace_log_lvl(current, regs, NULL, KERN_DEFAULT);
-
- printk(KERN_DEFAULT "Code: ");
-
- ip = (u8 *)regs->ip - code_prologue;
- if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) {
- /* try starting at IP */
- ip = (u8 *)regs->ip;
- code_len = code_len - code_prologue + 1;
- }
- for (i = 0; i < code_len; i++, ip++) {
- if (ip < (u8 *)PAGE_OFFSET ||
- probe_kernel_address(ip, c)) {
- pr_cont(" Bad RIP value.");
- break;
- }
- if (ip == (u8 *)regs->ip)
- pr_cont("<%02x> ", c);
- else
- pr_cont("%02x ", c);
- }
- }
- pr_cont("\n");
}
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 6a2cb14..d1f25c8 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -155,7 +155,8 @@ static void __init __e820__range_add(struct e820_table *table, u64 start, u64 si
int x = table->nr_entries;
if (x >= ARRAY_SIZE(table->entries)) {
- pr_err("e820: too many entries; ignoring [mem %#010llx-%#010llx]\n", start, start + size - 1);
+ pr_err("too many entries; ignoring [mem %#010llx-%#010llx]\n",
+ start, start + size - 1);
return;
}
@@ -190,9 +191,10 @@ void __init e820__print_table(char *who)
int i;
for (i = 0; i < e820_table->nr_entries; i++) {
- pr_info("%s: [mem %#018Lx-%#018Lx] ", who,
- e820_table->entries[i].addr,
- e820_table->entries[i].addr + e820_table->entries[i].size - 1);
+ pr_info("%s: [mem %#018Lx-%#018Lx] ",
+ who,
+ e820_table->entries[i].addr,
+ e820_table->entries[i].addr + e820_table->entries[i].size - 1);
e820_print_type(e820_table->entries[i].type);
pr_cont("\n");
@@ -574,7 +576,7 @@ void __init e820__update_table_print(void)
if (e820__update_table(e820_table))
return;
- pr_info("e820: modified physical RAM map:\n");
+ pr_info("modified physical RAM map:\n");
e820__print_table("modified");
}
@@ -636,9 +638,8 @@ __init void e820__setup_pci_gap(void)
if (!found) {
#ifdef CONFIG_X86_64
gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024;
- pr_err(
- "e820: Cannot find an available gap in the 32-bit address range\n"
- "e820: PCI devices with unassigned 32-bit BARs may not work!\n");
+ pr_err("Cannot find an available gap in the 32-bit address range\n");
+ pr_err("PCI devices with unassigned 32-bit BARs may not work!\n");
#else
gapstart = 0x10000000;
#endif
@@ -649,7 +650,8 @@ __init void e820__setup_pci_gap(void)
*/
pci_mem_start = gapstart;
- pr_info("e820: [mem %#010lx-%#010lx] available for PCI devices\n", gapstart, gapstart + gapsize - 1);
+ pr_info("[mem %#010lx-%#010lx] available for PCI devices\n",
+ gapstart, gapstart + gapsize - 1);
}
/*
@@ -711,7 +713,7 @@ void __init e820__memory_setup_extended(u64 phys_addr, u32 data_len)
memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware));
early_memunmap(sdata, data_len);
- pr_info("e820: extended physical RAM map:\n");
+ pr_info("extended physical RAM map:\n");
e820__print_table("extended");
}
@@ -780,7 +782,7 @@ u64 __init e820__memblock_alloc_reserved(u64 size, u64 align)
addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
if (addr) {
e820__range_update_kexec(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED);
- pr_info("e820: update e820_table_kexec for e820__memblock_alloc_reserved()\n");
+ pr_info("update e820_table_kexec for e820__memblock_alloc_reserved()\n");
e820__update_table_kexec();
}
@@ -830,8 +832,8 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, enum e820_type
if (last_pfn > max_arch_pfn)
last_pfn = max_arch_pfn;
- pr_info("e820: last_pfn = %#lx max_arch_pfn = %#lx\n",
- last_pfn, max_arch_pfn);
+ pr_info("last_pfn = %#lx max_arch_pfn = %#lx\n",
+ last_pfn, max_arch_pfn);
return last_pfn;
}
@@ -1005,7 +1007,7 @@ void __init e820__finish_early_params(void)
if (e820__update_table(e820_table) < 0)
early_panic("Invalid user supplied memory map");
- pr_info("e820: user-defined physical RAM map:\n");
+ pr_info("user-defined physical RAM map:\n");
e820__print_table("user");
}
}
@@ -1238,7 +1240,7 @@ void __init e820__memory_setup(void)
memcpy(e820_table_kexec, e820_table, sizeof(*e820_table_kexec));
memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware));
- pr_info("e820: BIOS-provided physical RAM map:\n");
+ pr_info("BIOS-provided physical RAM map:\n");
e820__print_table(who);
}
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index bae0d32..da5d8ac 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -28,8 +28,6 @@
#include <asm/irq_remapping.h>
#include <asm/early_ioremap.h>
-#define dev_err(msg) pr_err("pci 0000:%02x:%02x.%d: %s", bus, slot, func, msg)
-
static void __init fix_hypertransport_config(int num, int slot, int func)
{
u32 htcfg;
@@ -617,7 +615,8 @@ static void __init apple_airport_reset(int bus, int slot, int func)
pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL);
if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) {
- dev_err("Cannot power up Apple AirPort card\n");
+ pr_err("pci 0000:%02x:%02x.%d: Cannot power up Apple AirPort card\n",
+ bus, slot, func);
return;
}
}
@@ -628,7 +627,8 @@ static void __init apple_airport_reset(int bus, int slot, int func)
mmio = early_ioremap(addr, BCM4331_MMIO_SIZE);
if (!mmio) {
- dev_err("Cannot iomap Apple AirPort card\n");
+ pr_err("pci 0000:%02x:%02x.%d: Cannot iomap Apple AirPort card\n",
+ bus, slot, func);
return;
}
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 0c408f8..a21d6ac 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -6,6 +6,10 @@
*/
#define DISABLE_BRANCH_PROFILING
+
+/* cpu_feature_enabled() cannot be used this early */
+#define USE_EARLY_PGTABLE_L5
+
#include <linux/init.h>
#include <linux/linkage.h>
#include <linux/types.h>
@@ -32,11 +36,6 @@
#include <asm/microcode.h>
#include <asm/kasan.h>
-#ifdef CONFIG_X86_5LEVEL
-#undef pgtable_l5_enabled
-#define pgtable_l5_enabled __pgtable_l5_enabled
-#endif
-
/*
* Manage page tables very early on.
*/
@@ -45,8 +44,7 @@ static unsigned int __initdata next_early_pgt;
pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
#ifdef CONFIG_X86_5LEVEL
-unsigned int __pgtable_l5_enabled __ro_after_init;
-EXPORT_SYMBOL(__pgtable_l5_enabled);
+unsigned int __pgtable_l5_enabled __initdata;
unsigned int pgdir_shift __ro_after_init = 39;
EXPORT_SYMBOL(pgdir_shift);
unsigned int ptrs_per_p4d __ro_after_init = 1;
@@ -82,13 +80,14 @@ static unsigned int __head *fixup_int(void *ptr, unsigned long physaddr)
static bool __head check_la57_support(unsigned long physaddr)
{
- if (native_cpuid_eax(0) < 7)
+ /*
+ * 5-level paging is detected and enabled at kernel decomression
+ * stage. Only check if it has been enabled there.
+ */
+ if (!(native_read_cr4() & X86_CR4_LA57))
return false;
- if (!(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31))))
- return false;
-
- *fixup_int(&pgtable_l5_enabled, physaddr) = 1;
+ *fixup_int(&__pgtable_l5_enabled, physaddr) = 1;
*fixup_int(&pgdir_shift, physaddr) = 48;
*fixup_int(&ptrs_per_p4d, physaddr) = 512;
*fixup_long(&page_offset_base, physaddr) = __PAGE_OFFSET_BASE_L5;
@@ -104,6 +103,12 @@ static bool __head check_la57_support(unsigned long physaddr)
}
#endif
+/* Code in __startup_64() can be relocated during execution, but the compiler
+ * doesn't have to generate PC-relative relocations when accessing globals from
+ * that function. Clang actually does not generate them, which leads to
+ * boot-time crashes. To work around this problem, every global pointer must
+ * be adjusted using fixup_pointer().
+ */
unsigned long __head __startup_64(unsigned long physaddr,
struct boot_params *bp)
{
@@ -113,6 +118,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
p4dval_t *p4d;
pudval_t *pud;
pmdval_t *pmd, pmd_entry;
+ pteval_t *mask_ptr;
bool la57;
int i;
unsigned int *next_pgt_ptr;
@@ -196,7 +202,8 @@ unsigned long __head __startup_64(unsigned long physaddr,
pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
/* Filter out unsupported __PAGE_KERNEL_* bits: */
- pmd_entry &= __supported_pte_mask;
+ mask_ptr = fixup_pointer(&__supported_pte_mask, physaddr);
+ pmd_entry &= *mask_ptr;
pmd_entry += sme_get_me_mask();
pmd_entry += physaddr;
@@ -273,7 +280,7 @@ int __init __early_make_pgtable(unsigned long address, pmdval_t pmd)
* critical -- __PAGE_OFFSET would point us back into the dynamic
* range and we might end up looping forever...
*/
- if (!pgtable_l5_enabled)
+ if (!pgtable_l5_enabled())
p4d_p = pgd_p;
else if (pgd)
p4d_p = (p4dval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base);
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 8ce4212..b6be34e 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -975,8 +975,7 @@ int __init hpet_enable(void)
cfg &= ~(HPET_CFG_ENABLE | HPET_CFG_LEGACY);
hpet_writel(cfg, HPET_CFG);
if (cfg)
- pr_warn("HPET: Unrecognized bits %#x set in global cfg\n",
- cfg);
+ pr_warn("Unrecognized bits %#x set in global cfg\n", cfg);
for (i = 0; i <= last; ++i) {
cfg = hpet_readl(HPET_Tn_CFG(i));
@@ -988,7 +987,7 @@ int __init hpet_enable(void)
| HPET_TN_64BIT_CAP | HPET_TN_32BIT | HPET_TN_ROUTE
| HPET_TN_FSB | HPET_TN_FSB_CAP);
if (cfg)
- pr_warn("HPET: Unrecognized bits %#x set in cfg#%u\n",
+ pr_warn("Unrecognized bits %#x set in cfg#%u\n",
cfg, i);
}
hpet_print_config();
diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
index fa183a1..108c48d 100644
--- a/arch/x86/kernel/jailhouse.c
+++ b/arch/x86/kernel/jailhouse.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL2.0
+// SPDX-License-Identifier: GPL-2.0
/*
* Jailhouse paravirt_ops implementation
*
@@ -37,7 +37,7 @@ static uint32_t __init jailhouse_detect(void)
return jailhouse_cpuid_base();
}
-static void jailhouse_get_wallclock(struct timespec *now)
+static void jailhouse_get_wallclock(struct timespec64 *now)
{
memset(now, 0, sizeof(*now));
}
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 3182908..7326078 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -398,11 +398,10 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
* little bit simple
*/
efi_map_sz = efi_get_runtime_map_size();
- efi_map_sz = ALIGN(efi_map_sz, 16);
params_cmdline_sz = sizeof(struct boot_params) + cmdline_len +
MAX_ELFCOREHDR_STR_LEN;
params_cmdline_sz = ALIGN(params_cmdline_sz, 16);
- kbuf.bufsz = params_cmdline_sz + efi_map_sz +
+ kbuf.bufsz = params_cmdline_sz + ALIGN(efi_map_sz, 16) +
sizeof(struct setup_data) +
sizeof(struct efi_setup_data);
@@ -410,7 +409,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
if (!params)
return ERR_PTR(-ENOMEM);
efi_map_offset = params_cmdline_sz;
- efi_setup_data_offset = efi_map_offset + efi_map_sz;
+ efi_setup_data_offset = efi_map_offset + ALIGN(efi_map_sz, 16);
/* Copy setup header onto bootparams. Documentation/x86/boot.txt */
setup_header_size = 0x0202 + kernel[0x0201] - setup_hdr_offset;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 0715f82..6f4d423 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -370,6 +370,10 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
return 0;
+ /* We should not singlestep on the exception masking instructions */
+ if (insn_masking_exception(insn))
+ return 0;
+
#ifdef CONFIG_X86_64
/* Only x86_64 has RIP relative instructions */
if (insn_rip_relative(insn)) {
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 7867417..5b2300b 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -457,7 +457,7 @@ static void __init sev_map_percpu_data(void)
static void __init kvm_smp_prepare_cpus(unsigned int max_cpus)
{
native_smp_prepare_cpus(max_cpus);
- if (kvm_para_has_hint(KVM_HINTS_DEDICATED))
+ if (kvm_para_has_hint(KVM_HINTS_REALTIME))
static_branch_disable(&virt_spin_lock_key);
}
@@ -553,7 +553,7 @@ static void __init kvm_guest_init(void)
}
if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
- !kvm_para_has_hint(KVM_HINTS_DEDICATED) &&
+ !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
kvm_para_has_feature(KVM_FEATURE_STEAL_TIME))
pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
@@ -649,7 +649,7 @@ static __init int kvm_setup_pv_tlb_flush(void)
int cpu;
if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
- !kvm_para_has_hint(KVM_HINTS_DEDICATED) &&
+ !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
for_each_possible_cpu(cpu) {
zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
@@ -745,7 +745,7 @@ void __init kvm_spinlock_init(void)
if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
return;
- if (kvm_para_has_hint(KVM_HINTS_DEDICATED))
+ if (kvm_para_has_hint(KVM_HINTS_REALTIME))
return;
__pv_init_lock_hash();
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 8b26c9e..bf8d1eb 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -53,7 +53,7 @@ static struct pvclock_wall_clock *wall_clock;
* have elapsed since the hypervisor wrote the data. So we try to account for
* that with system time
*/
-static void kvm_get_wallclock(struct timespec *now)
+static void kvm_get_wallclock(struct timespec64 *now)
{
struct pvclock_vcpu_time_info *vcpu_time;
int low, high;
@@ -72,7 +72,7 @@ static void kvm_get_wallclock(struct timespec *now)
put_cpu();
}
-static int kvm_set_wallclock(const struct timespec *now)
+static int kvm_set_wallclock(const struct timespec64 *now)
{
return -ENODEV;
}
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index d41d896..c9b1402 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -166,7 +166,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
*/
pte_prot = __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL);
/* Filter out unsuppored __PAGE_KERNEL* bits: */
- pgprot_val(pte_prot) |= __supported_pte_mask;
+ pgprot_val(pte_prot) &= __supported_pte_mask;
pte = pfn_pte(pfn, pte_prot);
set_pte_at(mm, va, ptep, pte);
pte_unmap_unlock(ptep, ptl);
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 60cdec6..d1ab07e 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -57,12 +57,17 @@ static void load_segments(void)
static void machine_kexec_free_page_tables(struct kimage *image)
{
free_page((unsigned long)image->arch.pgd);
+ image->arch.pgd = NULL;
#ifdef CONFIG_X86_PAE
free_page((unsigned long)image->arch.pmd0);
+ image->arch.pmd0 = NULL;
free_page((unsigned long)image->arch.pmd1);
+ image->arch.pmd1 = NULL;
#endif
free_page((unsigned long)image->arch.pte0);
+ image->arch.pte0 = NULL;
free_page((unsigned long)image->arch.pte1);
+ image->arch.pte1 = NULL;
}
static int machine_kexec_alloc_page_tables(struct kimage *image)
@@ -79,7 +84,6 @@ static int machine_kexec_alloc_page_tables(struct kimage *image)
!image->arch.pmd0 || !image->arch.pmd1 ||
#endif
!image->arch.pte0 || !image->arch.pte1) {
- machine_kexec_free_page_tables(image);
return -ENOMEM;
}
return 0;
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index a5e55d8..4c8acdf 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -39,9 +39,13 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
static void free_transition_pgtable(struct kimage *image)
{
free_page((unsigned long)image->arch.p4d);
+ image->arch.p4d = NULL;
free_page((unsigned long)image->arch.pud);
+ image->arch.pud = NULL;
free_page((unsigned long)image->arch.pmd);
+ image->arch.pmd = NULL;
free_page((unsigned long)image->arch.pte);
+ image->arch.pte = NULL;
}
static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
@@ -91,7 +95,6 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC_NOENC));
return 0;
err:
- free_transition_pgtable(image);
return result;
}
@@ -351,7 +354,8 @@ void arch_crash_save_vmcoreinfo(void)
{
VMCOREINFO_NUMBER(phys_base);
VMCOREINFO_SYMBOL(init_top_pgt);
- VMCOREINFO_NUMBER(pgtable_l5_enabled);
+ vmcoreinfo_append_str("NUMBER(pgtable_l5_enabled)=%d\n",
+ pgtable_l5_enabled());
#ifdef CONFIG_NUMA
VMCOREINFO_SYMBOL(node_data);
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 77625b6..ab5d9dd 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -15,13 +15,11 @@
#include <asm/x86_init.h>
#include <asm/iommu_table.h>
-static int forbid_dac __read_mostly;
+static bool disable_dac_quirk __read_mostly;
const struct dma_map_ops *dma_ops = &dma_direct_ops;
EXPORT_SYMBOL(dma_ops);
-static int iommu_sac_force __read_mostly;
-
#ifdef CONFIG_IOMMU_DEBUG
int panic_on_overflow __read_mostly = 1;
int force_iommu __read_mostly = 1;
@@ -55,9 +53,6 @@ struct device x86_dma_fallback_dev = {
};
EXPORT_SYMBOL(x86_dma_fallback_dev);
-/* Number of entries preallocated for DMA-API debugging */
-#define PREALLOC_DMA_DEBUG_ENTRIES 65536
-
void __init pci_iommu_alloc(void)
{
struct iommu_table_entry *p;
@@ -76,7 +71,7 @@ void __init pci_iommu_alloc(void)
}
}
-bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp)
+bool arch_dma_alloc_attrs(struct device **dev)
{
if (!*dev)
*dev = &x86_dma_fallback_dev;
@@ -125,13 +120,13 @@ static __init int iommu_setup(char *p)
if (!strncmp(p, "nomerge", 7))
iommu_merge = 0;
if (!strncmp(p, "forcesac", 8))
- iommu_sac_force = 1;
+ pr_warn("forcesac option ignored.\n");
if (!strncmp(p, "allowdac", 8))
- forbid_dac = 0;
+ pr_warn("allowdac option ignored.\n");
if (!strncmp(p, "nodac", 5))
- forbid_dac = 1;
+ pr_warn("nodac option ignored.\n");
if (!strncmp(p, "usedac", 6)) {
- forbid_dac = -1;
+ disable_dac_quirk = true;
return 1;
}
#ifdef CONFIG_SWIOTLB
@@ -156,40 +151,9 @@ static __init int iommu_setup(char *p)
}
early_param("iommu", iommu_setup);
-int arch_dma_supported(struct device *dev, u64 mask)
-{
-#ifdef CONFIG_PCI
- if (mask > 0xffffffff && forbid_dac > 0) {
- dev_info(dev, "PCI: Disallowing DAC for device\n");
- return 0;
- }
-#endif
-
- /* Tell the device to use SAC when IOMMU force is on. This
- allows the driver to use cheaper accesses in some cases.
-
- Problem with this is that if we overflow the IOMMU area and
- return DAC as fallback address the device may not handle it
- correctly.
-
- As a special case some controllers have a 39bit address
- mode that is as efficient as 32bit (aic79xx). Don't force
- SAC for these. Assume all masks <= 40 bits are of this
- type. Normally this doesn't make any difference, but gives
- more gentle handling of IOMMU overflow. */
- if (iommu_sac_force && (mask >= DMA_BIT_MASK(40))) {
- dev_info(dev, "Force SAC with mask %Lx\n", mask);
- return 0;
- }
-
- return 1;
-}
-EXPORT_SYMBOL(arch_dma_supported);
-
static int __init pci_iommu_init(void)
{
struct iommu_table_entry *p;
- dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
#ifdef CONFIG_PCI
dma_debug_add_bus(&pci_bus_type);
@@ -209,11 +173,17 @@ rootfs_initcall(pci_iommu_init);
#ifdef CONFIG_PCI
/* Many VIA bridges seem to corrupt data for DAC. Disable it here */
+static int via_no_dac_cb(struct pci_dev *pdev, void *data)
+{
+ pdev->dev.dma_32bit_limit = true;
+ return 0;
+}
+
static void via_no_dac(struct pci_dev *dev)
{
- if (forbid_dac == 0) {
+ if (!disable_dac_quirk) {
dev_info(&dev->dev, "disabling DAC on VIA PCI bridge\n");
- forbid_dac = 1;
+ pci_walk_bus(dev->subordinate, via_no_dac_cb, NULL);
}
}
DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID,
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
deleted file mode 100644
index ac7ea3a..0000000
--- a/arch/x86/kernel/pci-nommu.c
+++ /dev/null
@@ -1,90 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Fallback functions when the main IOMMU code is not compiled in. This
- code is roughly equivalent to i386. */
-#include <linux/dma-direct.h>
-#include <linux/scatterlist.h>
-#include <linux/string.h>
-#include <linux/gfp.h>
-#include <linux/pci.h>
-#include <linux/mm.h>
-
-#include <asm/processor.h>
-#include <asm/iommu.h>
-#include <asm/dma.h>
-
-#define NOMMU_MAPPING_ERROR 0
-
-static int
-check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size)
-{
- if (hwdev && !dma_capable(hwdev, bus, size)) {
- if (*hwdev->dma_mask >= DMA_BIT_MASK(32))
- printk(KERN_ERR
- "nommu_%s: overflow %Lx+%zu of device mask %Lx\n",
- name, (long long)bus, size,
- (long long)*hwdev->dma_mask);
- return 0;
- }
- return 1;
-}
-
-static dma_addr_t nommu_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- unsigned long attrs)
-{
- dma_addr_t bus = phys_to_dma(dev, page_to_phys(page)) + offset;
- WARN_ON(size == 0);
- if (!check_addr("map_single", dev, bus, size))
- return NOMMU_MAPPING_ERROR;
- return bus;
-}
-
-/* Map a set of buffers described by scatterlist in streaming
- * mode for DMA. This is the scatter-gather version of the
- * above pci_map_single interface. Here the scatter gather list
- * elements are each tagged with the appropriate dma address
- * and length. They are obtained via sg_dma_{address,length}(SG).
- *
- * NOTE: An implementation may be able to use a smaller number of
- * DMA address/length pairs than there are SG table elements.
- * (for example via virtual mapping capabilities)
- * The routine returns the number of addr/length pairs actually
- * used, at most nents.
- *
- * Device ownership issues as mentioned above for pci_map_single are
- * the same here.
- */
-static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
- int nents, enum dma_data_direction dir,
- unsigned long attrs)
-{
- struct scatterlist *s;
- int i;
-
- WARN_ON(nents == 0 || sg[0].length == 0);
-
- for_each_sg(sg, s, nents, i) {
- BUG_ON(!sg_page(s));
- s->dma_address = sg_phys(s);
- if (!check_addr("map_sg", hwdev, s->dma_address, s->length))
- return 0;
- s->dma_length = s->length;
- }
- return nents;
-}
-
-static int nommu_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
- return dma_addr == NOMMU_MAPPING_ERROR;
-}
-
-const struct dma_map_ops nommu_dma_ops = {
- .alloc = dma_generic_alloc_coherent,
- .free = dma_generic_free_coherent,
- .map_sg = nommu_map_sg,
- .map_page = nommu_map_page,
- .is_phys = 1,
- .mapping_error = nommu_mapping_error,
- .dma_supported = x86_dma_supported,
-};
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index e47b2db..c06c4c1 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -151,17 +151,19 @@ void perf_get_regs_user(struct perf_regs *regs_user,
regs_user_copy->sp = user_regs->sp;
regs_user_copy->cs = user_regs->cs;
regs_user_copy->ss = user_regs->ss;
-
/*
- * Most system calls don't save these registers, don't report them.
+ * Store user space frame-pointer value on sample
+ * to facilitate stack unwinding for cases when
+ * user space executable code has such support
+ * enabled at compile time:
*/
+ regs_user_copy->bp = user_regs->bp;
+
regs_user_copy->bx = -1;
- regs_user_copy->bp = -1;
regs_user_copy->r12 = -1;
regs_user_copy->r13 = -1;
regs_user_copy->r14 = -1;
regs_user_copy->r15 = -1;
-
/*
* For this to be at all useful, we need a reasonable guess for
* the ABI. Be careful: we're in NMI context, and we're
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 03408b9..30ca2d1 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -38,6 +38,7 @@
#include <asm/switch_to.h>
#include <asm/desc.h>
#include <asm/prctl.h>
+#include <asm/spec-ctrl.h>
/*
* per-CPU TSS segments. Threads are completely 'soft' on Linux,
@@ -278,6 +279,148 @@ static inline void switch_to_bitmap(struct tss_struct *tss,
}
}
+#ifdef CONFIG_SMP
+
+struct ssb_state {
+ struct ssb_state *shared_state;
+ raw_spinlock_t lock;
+ unsigned int disable_state;
+ unsigned long local_state;
+};
+
+#define LSTATE_SSB 0
+
+static DEFINE_PER_CPU(struct ssb_state, ssb_state);
+
+void speculative_store_bypass_ht_init(void)
+{
+ struct ssb_state *st = this_cpu_ptr(&ssb_state);
+ unsigned int this_cpu = smp_processor_id();
+ unsigned int cpu;
+
+ st->local_state = 0;
+
+ /*
+ * Shared state setup happens once on the first bringup
+ * of the CPU. It's not destroyed on CPU hotunplug.
+ */
+ if (st->shared_state)
+ return;
+
+ raw_spin_lock_init(&st->lock);
+
+ /*
+ * Go over HT siblings and check whether one of them has set up the
+ * shared state pointer already.
+ */
+ for_each_cpu(cpu, topology_sibling_cpumask(this_cpu)) {
+ if (cpu == this_cpu)
+ continue;
+
+ if (!per_cpu(ssb_state, cpu).shared_state)
+ continue;
+
+ /* Link it to the state of the sibling: */
+ st->shared_state = per_cpu(ssb_state, cpu).shared_state;
+ return;
+ }
+
+ /*
+ * First HT sibling to come up on the core. Link shared state of
+ * the first HT sibling to itself. The siblings on the same core
+ * which come up later will see the shared state pointer and link
+ * themself to the state of this CPU.
+ */
+ st->shared_state = st;
+}
+
+/*
+ * Logic is: First HT sibling enables SSBD for both siblings in the core
+ * and last sibling to disable it, disables it for the whole core. This how
+ * MSR_SPEC_CTRL works in "hardware":
+ *
+ * CORE_SPEC_CTRL = THREAD0_SPEC_CTRL | THREAD1_SPEC_CTRL
+ */
+static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
+{
+ struct ssb_state *st = this_cpu_ptr(&ssb_state);
+ u64 msr = x86_amd_ls_cfg_base;
+
+ if (!static_cpu_has(X86_FEATURE_ZEN)) {
+ msr |= ssbd_tif_to_amd_ls_cfg(tifn);
+ wrmsrl(MSR_AMD64_LS_CFG, msr);
+ return;
+ }
+
+ if (tifn & _TIF_SSBD) {
+ /*
+ * Since this can race with prctl(), block reentry on the
+ * same CPU.
+ */
+ if (__test_and_set_bit(LSTATE_SSB, &st->local_state))
+ return;
+
+ msr |= x86_amd_ls_cfg_ssbd_mask;
+
+ raw_spin_lock(&st->shared_state->lock);
+ /* First sibling enables SSBD: */
+ if (!st->shared_state->disable_state)
+ wrmsrl(MSR_AMD64_LS_CFG, msr);
+ st->shared_state->disable_state++;
+ raw_spin_unlock(&st->shared_state->lock);
+ } else {
+ if (!__test_and_clear_bit(LSTATE_SSB, &st->local_state))
+ return;
+
+ raw_spin_lock(&st->shared_state->lock);
+ st->shared_state->disable_state--;
+ if (!st->shared_state->disable_state)
+ wrmsrl(MSR_AMD64_LS_CFG, msr);
+ raw_spin_unlock(&st->shared_state->lock);
+ }
+}
+#else
+static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
+{
+ u64 msr = x86_amd_ls_cfg_base | ssbd_tif_to_amd_ls_cfg(tifn);
+
+ wrmsrl(MSR_AMD64_LS_CFG, msr);
+}
+#endif
+
+static __always_inline void amd_set_ssb_virt_state(unsigned long tifn)
+{
+ /*
+ * SSBD has the same definition in SPEC_CTRL and VIRT_SPEC_CTRL,
+ * so ssbd_tif_to_spec_ctrl() just works.
+ */
+ wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, ssbd_tif_to_spec_ctrl(tifn));
+}
+
+static __always_inline void intel_set_ssb_state(unsigned long tifn)
+{
+ u64 msr = x86_spec_ctrl_base | ssbd_tif_to_spec_ctrl(tifn);
+
+ wrmsrl(MSR_IA32_SPEC_CTRL, msr);
+}
+
+static __always_inline void __speculative_store_bypass_update(unsigned long tifn)
+{
+ if (static_cpu_has(X86_FEATURE_VIRT_SSBD))
+ amd_set_ssb_virt_state(tifn);
+ else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD))
+ amd_set_core_ssb_state(tifn);
+ else
+ intel_set_ssb_state(tifn);
+}
+
+void speculative_store_bypass_update(unsigned long tif)
+{
+ preempt_disable();
+ __speculative_store_bypass_update(tif);
+ preempt_enable();
+}
+
void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
struct tss_struct *tss)
{
@@ -309,6 +452,9 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
if ((tifp ^ tifn) & _TIF_NOCPUID)
set_cpuid_faulting(!!(tifn & _TIF_NOCPUID));
+
+ if ((tifp ^ tifn) & _TIF_SSBD)
+ __speculative_store_bypass_update(tifn);
}
/*
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 5224c60..0ae659d 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -76,16 +76,14 @@ void __show_regs(struct pt_regs *regs, int all)
savesegment(gs, gs);
}
- printk(KERN_DEFAULT "EIP: %pS\n", (void *)regs->ip);
- printk(KERN_DEFAULT "EFLAGS: %08lx CPU: %d\n", regs->flags,
- raw_smp_processor_id());
+ show_ip(regs, KERN_DEFAULT);
printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
regs->ax, regs->bx, regs->cx, regs->dx);
printk(KERN_DEFAULT "ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n",
regs->si, regs->di, regs->bp, sp);
- printk(KERN_DEFAULT " DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n",
- (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss);
+ printk(KERN_DEFAULT "DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x EFLAGS: %08lx\n",
+ (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss, regs->flags);
if (!all)
return;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 4b100fe..12bb445 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -542,6 +542,7 @@ void set_personality_64bit(void)
clear_thread_flag(TIF_X32);
/* Pretend that this comes from a 64bit execve */
task_pt_regs(current)->orig_ax = __NR_execve;
+ current_thread_info()->status &= ~TS_COMPAT;
/* Ensure the corresponding mm is not marked. */
if (current->mm)
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index ed5c4cd..e2ee403 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1377,7 +1377,6 @@ static void fill_sigtrap_info(struct task_struct *tsk,
tsk->thread.trap_nr = X86_TRAP_DB;
tsk->thread.error_code = error_code;
- memset(info, 0, sizeof(*info));
info->si_signo = SIGTRAP;
info->si_code = si_code;
info->si_addr = user_mode(regs) ? (void __user *)regs->ip : NULL;
@@ -1395,6 +1394,7 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
{
struct siginfo info;
+ clear_siginfo(&info);
fill_sigtrap_info(tsk, regs, error_code, si_code, &info);
/* Send us the fake SIGTRAP */
force_sig_info(SIGTRAP, &info, tsk);
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 761f6af..637982e 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -123,28 +123,35 @@ u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
struct pvclock_vcpu_time_info *vcpu_time,
- struct timespec *ts)
+ struct timespec64 *ts)
{
u32 version;
u64 delta;
- struct timespec now;
+ struct timespec64 now;
/* get wallclock at system boot */
do {
version = wall_clock->version;
rmb(); /* fetch version before time */
+ /*
+ * Note: wall_clock->sec is a u32 value, so it can
+ * only store dates between 1970 and 2106. To allow
+ * times beyond that, we need to create a new hypercall
+ * interface with an extended pvclock_wall_clock structure
+ * like ARM has.
+ */
now.tv_sec = wall_clock->sec;
now.tv_nsec = wall_clock->nsec;
rmb(); /* fetch time before checking version */
} while ((wall_clock->version & 1) || (version != wall_clock->version));
delta = pvclock_clocksource_read(vcpu_time); /* time since system boot */
- delta += now.tv_sec * (u64)NSEC_PER_SEC + now.tv_nsec;
+ delta += now.tv_sec * NSEC_PER_SEC + now.tv_nsec;
now.tv_nsec = do_div(delta, NSEC_PER_SEC);
now.tv_sec = delta;
- set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
+ set_normalized_timespec64(ts, now.tv_sec, now.tv_nsec);
}
void pvclock_set_pvti_cpu0_va(struct pvclock_vsyscall_time_info *pvti)
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index f7b82ed..586f718 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -39,7 +39,7 @@ EXPORT_SYMBOL(rtc_lock);
* jump to the next second precisely 500 ms later. Check the Motorola
* MC146818A or Dallas DS12887 data sheet for details.
*/
-int mach_set_rtc_mmss(const struct timespec *now)
+int mach_set_rtc_mmss(const struct timespec64 *now)
{
unsigned long long nowtime = now->tv_sec;
struct rtc_time tm;
@@ -60,7 +60,7 @@ int mach_set_rtc_mmss(const struct timespec *now)
return retval;
}
-void mach_get_cmos_time(struct timespec *now)
+void mach_get_cmos_time(struct timespec64 *now)
{
unsigned int status, year, mon, day, hour, min, sec, century = 0;
unsigned long flags;
@@ -118,7 +118,7 @@ void mach_get_cmos_time(struct timespec *now)
} else
year += CMOS_YEARS_OFFS;
- now->tv_sec = mktime(year, mon, day, hour, min, sec);
+ now->tv_sec = mktime64(year, mon, day, hour, min, sec);
now->tv_nsec = 0;
}
@@ -145,13 +145,13 @@ void rtc_cmos_write(unsigned char val, unsigned char addr)
}
EXPORT_SYMBOL(rtc_cmos_write);
-int update_persistent_clock(struct timespec now)
+int update_persistent_clock64(struct timespec64 now)
{
return x86_platform.set_wallclock(&now);
}
/* not static: needed by APM */
-void read_persistent_clock(struct timespec *ts)
+void read_persistent_clock64(struct timespec64 *ts)
{
x86_platform.get_wallclock(ts);
}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 6285697..5c623df 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -50,6 +50,7 @@
#include <linux/init_ohci1394_dma.h>
#include <linux/kvm_para.h>
#include <linux/dma-contiguous.h>
+#include <xen/xen.h>
#include <linux/errno.h>
#include <linux/kernel.h>
@@ -534,6 +535,11 @@ static void __init reserve_crashkernel(void)
high = true;
}
+ if (xen_pv_domain()) {
+ pr_info("Ignoring crashkernel for a Xen PV domain\n");
+ return;
+ }
+
/* 0 means: find the address automatically */
if (crash_base <= 0) {
/*
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index 14c057f..9ccbf05 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -29,7 +29,7 @@ static inline void signal_compat_build_tests(void)
BUILD_BUG_ON(NSIGFPE != 15);
BUILD_BUG_ON(NSIGSEGV != 7);
BUILD_BUG_ON(NSIGBUS != 5);
- BUILD_BUG_ON(NSIGTRAP != 4);
+ BUILD_BUG_ON(NSIGTRAP != 5);
BUILD_BUG_ON(NSIGCHLD != 6);
BUILD_BUG_ON(NSIGSYS != 1);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index ff99e2b..c2f7d1d 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -77,13 +77,9 @@
#include <asm/i8259.h>
#include <asm/misc.h>
#include <asm/qspinlock.h>
-
-/* Number of siblings per CPU package */
-int smp_num_siblings = 1;
-EXPORT_SYMBOL(smp_num_siblings);
-
-/* Last level cache ID of each logical CPU */
-DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID;
+#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
+#include <asm/spec-ctrl.h>
/* representing HT siblings of each logical CPU */
DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
@@ -242,6 +238,8 @@ static void notrace start_secondary(void *unused)
*/
check_tsc_sync_target();
+ speculative_store_bypass_ht_init();
+
/*
* Lock vector_lock, set CPU online and bring the vector
* allocator online. Online must be set with vector_lock held
@@ -390,15 +388,47 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
return false;
}
+/*
+ * Define snc_cpu[] for SNC (Sub-NUMA Cluster) CPUs.
+ *
+ * These are Intel CPUs that enumerate an LLC that is shared by
+ * multiple NUMA nodes. The LLC on these systems is shared for
+ * off-package data access but private to the NUMA node (half
+ * of the package) for on-package access.
+ *
+ * CPUID (the source of the information about the LLC) can only
+ * enumerate the cache as being shared *or* unshared, but not
+ * this particular configuration. The CPU in this case enumerates
+ * the cache to be shared across the entire package (spanning both
+ * NUMA nodes).
+ */
+
+static const struct x86_cpu_id snc_cpu[] = {
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_X },
+ {}
+};
+
static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
{
int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
- if (per_cpu(cpu_llc_id, cpu1) != BAD_APICID &&
- per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2))
- return topology_sane(c, o, "llc");
+ /* Do not match if we do not have a valid APICID for cpu: */
+ if (per_cpu(cpu_llc_id, cpu1) == BAD_APICID)
+ return false;
- return false;
+ /* Do not match if LLC id does not match: */
+ if (per_cpu(cpu_llc_id, cpu1) != per_cpu(cpu_llc_id, cpu2))
+ return false;
+
+ /*
+ * Allow the SNC topology without warning. Return of false
+ * means 'c' does not share the LLC of 'o'. This will be
+ * reflected to userspace.
+ */
+ if (!topology_same_node(c, o) && x86_match_cpu(snc_cpu))
+ return false;
+
+ return topology_sane(c, o, "llc");
}
/*
@@ -456,7 +486,8 @@ static struct sched_domain_topology_level x86_topology[] = {
/*
* Set if a package/die has multiple NUMA nodes inside.
- * AMD Magny-Cours and Intel Cluster-on-Die have this.
+ * AMD Magny-Cours, Intel Cluster-on-Die, and Intel
+ * Sub-NUMA Clustering have this.
*/
static bool x86_has_numa_in_package;
@@ -1257,6 +1288,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
set_mtrr_aps_delayed_init();
smp_quirk_init_udelay();
+
+ speculative_store_bypass_ht_init();
}
void arch_enable_nonboot_cpus_begin(void)
@@ -1536,6 +1569,8 @@ static inline void mwait_play_dead(void)
void *mwait_ptr;
int i;
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+ return;
if (!this_cpu_has(X86_FEATURE_MWAIT))
return;
if (!this_cpu_has(X86_FEATURE_CLFLUSH))
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index a3f15ed..6a78d4b 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -1,4 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
+#include <linux/compat.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
@@ -19,7 +20,6 @@
#include <linux/elf.h>
#include <asm/elf.h>
-#include <asm/compat.h>
#include <asm/ia32.h>
#include <asm/syscalls.h>
#include <asm/mpx.h>
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 03f3d76..a535dd6 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -299,6 +299,7 @@ static void do_error_trap(struct pt_regs *regs, long error_code, char *str,
if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) !=
NOTIFY_STOP) {
cond_local_irq_enable(regs);
+ clear_siginfo(&info);
do_trap(trapnr, signr, str, regs, error_code,
fill_trap_info(regs, signr, trapnr, &info));
}
@@ -854,6 +855,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
task->thread.trap_nr = trapnr;
task->thread.error_code = error_code;
+ clear_siginfo(&info);
info.si_signo = SIGFPE;
info.si_errno = 0;
info.si_addr = (void __user *)uprobe_get_trap_addr(regs);
@@ -929,6 +931,7 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
local_irq_enable();
+ clear_siginfo(&info);
info.si_signo = SIGILL;
info.si_errno = 0;
info.si_code = ILL_BADSTK;
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index ef32297..74392d9 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -317,7 +317,7 @@ static unsigned long calc_hpet_ref(u64 deltatsc, u64 hpet1, u64 hpet2)
hpet2 -= hpet1;
tmp = ((u64)hpet2 * hpet_readl(HPET_PERIOD));
do_div(tmp, 1000000);
- do_div(deltatsc, tmp);
+ deltatsc = div64_u64(deltatsc, tmp);
return (unsigned long) deltatsc;
}
@@ -1067,6 +1067,7 @@ static struct clocksource clocksource_tsc_early = {
.resume = tsc_resume,
.mark_unstable = tsc_cs_mark_unstable,
.tick_stable = tsc_cs_tick_stable,
+ .list = LIST_HEAD_INIT(clocksource_tsc_early.list),
};
/*
@@ -1086,6 +1087,7 @@ static struct clocksource clocksource_tsc = {
.resume = tsc_resume,
.mark_unstable = tsc_cs_mark_unstable,
.tick_stable = tsc_cs_tick_stable,
+ .list = LIST_HEAD_INIT(clocksource_tsc.list),
};
void mark_tsc_unstable(char *reason)
@@ -1098,13 +1100,9 @@ void mark_tsc_unstable(char *reason)
clear_sched_clock_stable();
disable_sched_clock_irqtime();
pr_info("Marking TSC unstable due to %s\n", reason);
- /* Change only the rating, when not registered */
- if (clocksource_tsc.mult) {
- clocksource_mark_unstable(&clocksource_tsc);
- } else {
- clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE;
- clocksource_tsc.rating = 0;
- }
+
+ clocksource_mark_unstable(&clocksource_tsc_early);
+ clocksource_mark_unstable(&clocksource_tsc);
}
EXPORT_SYMBOL_GPL(mark_tsc_unstable);
@@ -1244,7 +1242,7 @@ static void tsc_refine_calibration_work(struct work_struct *work)
/* Don't bother refining TSC on unstable systems */
if (tsc_unstable)
- return;
+ goto unreg;
/*
* Since the work is started early in boot, we may be
@@ -1297,11 +1295,12 @@ static void tsc_refine_calibration_work(struct work_struct *work)
out:
if (tsc_unstable)
- return;
+ goto unreg;
if (boot_cpu_has(X86_FEATURE_ART))
art_related_clocksource = &clocksource_tsc;
clocksource_register_khz(&clocksource_tsc, tsc_khz);
+unreg:
clocksource_unregister(&clocksource_tsc_early);
}
@@ -1311,8 +1310,8 @@ static int __init init_tsc_clocksource(void)
if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz)
return 0;
- if (check_tsc_unstable())
- return 0;
+ if (tsc_unstable)
+ goto unreg;
if (tsc_clocksource_reliable)
clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
@@ -1328,6 +1327,7 @@ static int __init init_tsc_clocksource(void)
if (boot_cpu_has(X86_FEATURE_ART))
art_related_clocksource = &clocksource_tsc;
clocksource_register_khz(&clocksource_tsc, tsc_khz);
+unreg:
clocksource_unregister(&clocksource_tsc_early);
return 0;
}
diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c
index f44ce0f..ff20b35 100644
--- a/arch/x86/kernel/umip.c
+++ b/arch/x86/kernel/umip.c
@@ -278,6 +278,7 @@ static void force_sig_info_umip_fault(void __user *addr, struct pt_regs *regs)
tsk->thread.error_code = X86_PF_USER | X86_PF_WRITE;
tsk->thread.trap_nr = X86_TRAP_PF;
+ clear_siginfo(&info);
info.si_signo = SIGSEGV;
info.si_errno = 0;
info.si_code = SEGV_MAPERR;
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 85c7ef2..58d8d80 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -299,6 +299,10 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
if (is_prefix_bad(insn))
return -ENOTSUPP;
+ /* We should not singlestep on the exception masking instructions */
+ if (insn_masking_exception(insn))
+ return -ENOTSUPP;
+
if (x86_64)
good_insns = good_insns_64;
else
@@ -1079,8 +1083,8 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs
return orig_ret_vaddr;
if (nleft != rasize) {
- pr_err("uprobe: return address clobbered: pid=%d, %%sp=%#lx, "
- "%%ip=%#lx\n", current->pid, regs->sp, regs->ip);
+ pr_err("return address clobbered: pid=%d, %%sp=%#lx, %%ip=%#lx\n",
+ current->pid, regs->sp, regs->ip);
force_sig_info(SIGSEGV, SEND_SIG_FORCED, current);
}
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 795f3a8..5e1458f 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -117,11 +117,11 @@
#ifdef CONFIG_X86_64
. = ALIGN(PAGE_SIZE);
- VMLINUX_SYMBOL(__entry_trampoline_start) = .;
+ __entry_trampoline_start = .;
_entry_trampoline = .;
*(.entry_trampoline)
. = ALIGN(PAGE_SIZE);
- VMLINUX_SYMBOL(__entry_trampoline_end) = .;
+ __entry_trampoline_end = .;
ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big");
#endif
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 82055b9..92bf2f2 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -379,7 +379,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
/* cpuid 0x80000008.ebx */
const u32 kvm_cpuid_8000_0008_ebx_x86_features =
- F(IBPB) | F(IBRS);
+ F(AMD_IBPB) | F(AMD_IBRS) | F(VIRT_SSBD);
/* cpuid 0xC0000001.edx */
const u32 kvm_cpuid_C000_0001_edx_x86_features =
@@ -408,7 +408,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
/* cpuid 7.0.edx*/
const u32 kvm_cpuid_7_0_edx_x86_features =
F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) |
- F(ARCH_CAPABILITIES);
+ F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES);
/* all calls to cpuid_count() should be made on the same cpu */
get_cpu();
@@ -495,6 +495,11 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
entry->ecx &= ~F(PKU);
entry->edx &= kvm_cpuid_7_0_edx_x86_features;
cpuid_mask(&entry->edx, CPUID_7_EDX);
+ /*
+ * We emulate ARCH_CAPABILITIES in software even
+ * if the host doesn't support it.
+ */
+ entry->edx |= F(ARCH_CAPABILITIES);
} else {
entry->ebx = 0;
entry->ecx = 0;
@@ -647,13 +652,20 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
g_phys_as = phys_as;
entry->eax = g_phys_as | (virt_as << 8);
entry->edx = 0;
- /* IBRS and IBPB aren't necessarily present in hardware cpuid */
- if (boot_cpu_has(X86_FEATURE_IBPB))
- entry->ebx |= F(IBPB);
- if (boot_cpu_has(X86_FEATURE_IBRS))
- entry->ebx |= F(IBRS);
+ /*
+ * IBRS, IBPB and VIRT_SSBD aren't necessarily present in
+ * hardware cpuid
+ */
+ if (boot_cpu_has(X86_FEATURE_AMD_IBPB))
+ entry->ebx |= F(AMD_IBPB);
+ if (boot_cpu_has(X86_FEATURE_AMD_IBRS))
+ entry->ebx |= F(AMD_IBRS);
+ if (boot_cpu_has(X86_FEATURE_VIRT_SSBD))
+ entry->ebx |= F(VIRT_SSBD);
entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features;
cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX);
+ if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD))
+ entry->ebx |= F(VIRT_SSBD);
break;
}
case 0x80000019:
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 98618e3..46ff64d 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1260,12 +1260,16 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
}
}
+static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result)
+{
+ kvm_hv_hypercall_set_result(vcpu, result);
+ ++vcpu->stat.hypercalls;
+ return kvm_skip_emulated_instruction(vcpu);
+}
+
static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
{
- struct kvm_run *run = vcpu->run;
-
- kvm_hv_hypercall_set_result(vcpu, run->hyperv.u.hcall.result);
- return 1;
+ return kvm_hv_hypercall_complete(vcpu, vcpu->run->hyperv.u.hcall.result);
}
static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param)
@@ -1296,8 +1300,10 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param)
if (param & ~KVM_HYPERV_CONN_ID_MASK)
return HV_STATUS_INVALID_HYPERCALL_INPUT;
- /* conn_to_evt is protected by vcpu->kvm->srcu */
+ /* the eventfd is protected by vcpu->kvm->srcu, but conn_to_evt isn't */
+ rcu_read_lock();
eventfd = idr_find(&vcpu->kvm->arch.hyperv.conn_to_evt, param);
+ rcu_read_unlock();
if (!eventfd)
return HV_STATUS_INVALID_PORT_ID;
@@ -1348,7 +1354,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
/* Hypercall continuation is not supported yet */
if (rep_cnt || rep_idx) {
ret = HV_STATUS_INVALID_HYPERCALL_CODE;
- goto set_result;
+ goto out;
}
switch (code) {
@@ -1379,9 +1385,8 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
break;
}
-set_result:
- kvm_hv_hypercall_set_result(vcpu, ret);
- return 1;
+out:
+ return kvm_hv_hypercall_complete(vcpu, ret);
}
void kvm_hv_init_vm(struct kvm *kvm)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 70dcb55..3773c46 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1463,23 +1463,6 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic)
local_irq_restore(flags);
}
-static void start_sw_period(struct kvm_lapic *apic)
-{
- if (!apic->lapic_timer.period)
- return;
-
- if (apic_lvtt_oneshot(apic) &&
- ktime_after(ktime_get(),
- apic->lapic_timer.target_expiration)) {
- apic_timer_expired(apic);
- return;
- }
-
- hrtimer_start(&apic->lapic_timer.timer,
- apic->lapic_timer.target_expiration,
- HRTIMER_MODE_ABS_PINNED);
-}
-
static void update_target_expiration(struct kvm_lapic *apic, uint32_t old_divisor)
{
ktime_t now, remaining;
@@ -1539,11 +1522,43 @@ static bool set_target_expiration(struct kvm_lapic *apic)
static void advance_periodic_target_expiration(struct kvm_lapic *apic)
{
- apic->lapic_timer.tscdeadline +=
- nsec_to_cycles(apic->vcpu, apic->lapic_timer.period);
+ ktime_t now = ktime_get();
+ u64 tscl = rdtsc();
+ ktime_t delta;
+
+ /*
+ * Synchronize both deadlines to the same time source or
+ * differences in the periods (caused by differences in the
+ * underlying clocks or numerical approximation errors) will
+ * cause the two to drift apart over time as the errors
+ * accumulate.
+ */
apic->lapic_timer.target_expiration =
ktime_add_ns(apic->lapic_timer.target_expiration,
apic->lapic_timer.period);
+ delta = ktime_sub(apic->lapic_timer.target_expiration, now);
+ apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) +
+ nsec_to_cycles(apic->vcpu, delta);
+}
+
+static void start_sw_period(struct kvm_lapic *apic)
+{
+ if (!apic->lapic_timer.period)
+ return;
+
+ if (ktime_after(ktime_get(),
+ apic->lapic_timer.target_expiration)) {
+ apic_timer_expired(apic);
+
+ if (apic_lvtt_oneshot(apic))
+ return;
+
+ advance_periodic_target_expiration(apic);
+ }
+
+ hrtimer_start(&apic->lapic_timer.timer,
+ apic->lapic_timer.target_expiration,
+ HRTIMER_MODE_ABS_PINNED);
}
bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 8494dba..d634f033 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3007,6 +3007,7 @@ static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *
{
siginfo_t info;
+ clear_siginfo(&info);
info.si_signo = SIGBUS;
info.si_errno = 0;
info.si_code = BUS_MCEERR_AR;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index b58787d..26110c2 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -49,7 +49,7 @@
#include <asm/debugreg.h>
#include <asm/kvm_para.h>
#include <asm/irq_remapping.h>
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
#include <asm/virtext.h>
#include "trace.h"
@@ -213,6 +213,12 @@ struct vcpu_svm {
} host;
u64 spec_ctrl;
+ /*
+ * Contains guest-controlled bits of VIRT_SPEC_CTRL, which will be
+ * translated into the appropriate L2_CFG bits on the host to
+ * perform speculative control.
+ */
+ u64 virt_spec_ctrl;
u32 *msrpm;
@@ -1423,12 +1429,23 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type)
seg->base = 0;
}
+static u64 svm_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ if (is_guest_mode(vcpu))
+ return svm->nested.hsave->control.tsc_offset;
+
+ return vcpu->arch.tsc_offset;
+}
+
static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
{
struct vcpu_svm *svm = to_svm(vcpu);
u64 g_tsc_offset = 0;
if (is_guest_mode(vcpu)) {
+ /* Write L1's TSC offset. */
g_tsc_offset = svm->vmcb->control.tsc_offset -
svm->nested.hsave->control.tsc_offset;
svm->nested.hsave->control.tsc_offset = offset;
@@ -2049,6 +2066,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
vcpu->arch.microcode_version = 0x01000065;
svm->spec_ctrl = 0;
+ svm->virt_spec_ctrl = 0;
if (!init_event) {
svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
@@ -3322,6 +3340,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
/* Restore the original control entries */
copy_vmcb_control_area(vmcb, hsave);
+ svm->vcpu.arch.tsc_offset = svm->vmcb->control.tsc_offset;
kvm_clear_exception_queue(&svm->vcpu);
kvm_clear_interrupt_queue(&svm->vcpu);
@@ -3482,10 +3501,12 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
/* We don't want to see VMMCALLs from a nested guest */
clr_intercept(svm, INTERCEPT_VMMCALL);
+ svm->vcpu.arch.tsc_offset += nested_vmcb->control.tsc_offset;
+ svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset;
+
svm->vmcb->control.virt_ext = nested_vmcb->control.virt_ext;
svm->vmcb->control.int_vector = nested_vmcb->control.int_vector;
svm->vmcb->control.int_state = nested_vmcb->control.int_state;
- svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset;
svm->vmcb->control.event_inj = nested_vmcb->control.event_inj;
svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err;
@@ -4035,12 +4056,6 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
struct vcpu_svm *svm = to_svm(vcpu);
switch (msr_info->index) {
- case MSR_IA32_TSC: {
- msr_info->data = svm->vmcb->control.tsc_offset +
- kvm_scale_tsc(vcpu, rdtsc());
-
- break;
- }
case MSR_STAR:
msr_info->data = svm->vmcb->save.star;
break;
@@ -4100,11 +4115,18 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
case MSR_IA32_SPEC_CTRL:
if (!msr_info->host_initiated &&
- !guest_cpuid_has(vcpu, X86_FEATURE_IBRS))
+ !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS))
return 1;
msr_info->data = svm->spec_ctrl;
break;
+ case MSR_AMD64_VIRT_SPEC_CTRL:
+ if (!msr_info->host_initiated &&
+ !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD))
+ return 1;
+
+ msr_info->data = svm->virt_spec_ctrl;
+ break;
case MSR_F15H_IC_CFG: {
int family, model;
@@ -4193,12 +4215,9 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
svm->vmcb->save.g_pat = data;
mark_dirty(svm->vmcb, VMCB_NPT);
break;
- case MSR_IA32_TSC:
- kvm_write_tsc(vcpu, msr);
- break;
case MSR_IA32_SPEC_CTRL:
if (!msr->host_initiated &&
- !guest_cpuid_has(vcpu, X86_FEATURE_IBRS))
+ !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS))
return 1;
/* The STIBP bit doesn't fault even if it's not advertised */
@@ -4225,7 +4244,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
break;
case MSR_IA32_PRED_CMD:
if (!msr->host_initiated &&
- !guest_cpuid_has(vcpu, X86_FEATURE_IBPB))
+ !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB))
return 1;
if (data & ~PRED_CMD_IBPB)
@@ -4239,6 +4258,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
break;
set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
break;
+ case MSR_AMD64_VIRT_SPEC_CTRL:
+ if (!msr->host_initiated &&
+ !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD))
+ return 1;
+
+ if (data & ~SPEC_CTRL_SSBD)
+ return 1;
+
+ svm->virt_spec_ctrl = data;
+ break;
case MSR_STAR:
svm->vmcb->save.star = data;
break;
@@ -5265,9 +5294,8 @@ static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
}
if (!ret && svm) {
- trace_kvm_pi_irte_update(svm->vcpu.vcpu_id,
- host_irq, e->gsi,
- vcpu_info.vector,
+ trace_kvm_pi_irte_update(host_irq, svm->vcpu.vcpu_id,
+ e->gsi, vcpu_info.vector,
vcpu_info.pi_desc_addr, set);
}
@@ -5553,8 +5581,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
* is no need to worry about the conditional branch over the wrmsr
* being speculatively taken.
*/
- if (svm->spec_ctrl)
- native_wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl);
+ x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl);
asm volatile (
"push %%" _ASM_BP "; \n\t"
@@ -5648,6 +5675,18 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
#endif
);
+ /* Eliminate branch target predictions from guest mode */
+ vmexit_fill_RSB();
+
+#ifdef CONFIG_X86_64
+ wrmsrl(MSR_GS_BASE, svm->host.gs_base);
+#else
+ loadsegment(fs, svm->host.fs);
+#ifndef CONFIG_X86_32_LAZY_GS
+ loadsegment(gs, svm->host.gs);
+#endif
+#endif
+
/*
* We do not use IBRS in the kernel. If this vCPU has used the
* SPEC_CTRL MSR it may have left it on; save the value and
@@ -5666,20 +5705,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
- if (svm->spec_ctrl)
- native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);
-
- /* Eliminate branch target predictions from guest mode */
- vmexit_fill_RSB();
-
-#ifdef CONFIG_X86_64
- wrmsrl(MSR_GS_BASE, svm->host.gs_base);
-#else
- loadsegment(fs, svm->host.fs);
-#ifndef CONFIG_X86_32_LAZY_GS
- loadsegment(gs, svm->host.gs);
-#endif
-#endif
+ x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl);
reload_tss(vcpu);
@@ -5782,7 +5808,7 @@ static bool svm_cpu_has_accelerated_tpr(void)
return false;
}
-static bool svm_has_high_real_mode_segbase(void)
+static bool svm_has_emulated_msr(int index)
{
return true;
}
@@ -7008,7 +7034,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
.hardware_enable = svm_hardware_enable,
.hardware_disable = svm_hardware_disable,
.cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr,
- .cpu_has_high_real_mode_segbase = svm_has_high_real_mode_segbase,
+ .has_emulated_msr = svm_has_emulated_msr,
.vcpu_create = svm_create_vcpu,
.vcpu_free = svm_free_vcpu,
@@ -7102,6 +7128,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
.has_wbinvd_exit = svm_has_wbinvd_exit,
+ .read_l1_tsc_offset = svm_read_l1_tsc_offset,
.write_tsc_offset = svm_write_tsc_offset,
.set_tdp_cr3 = set_tdp_cr3,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index aafcc98..40aa292 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -51,7 +51,7 @@
#include <asm/apic.h>
#include <asm/irq_remapping.h>
#include <asm/mmu_context.h>
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
#include <asm/mshyperv.h>
#include "trace.h"
@@ -1494,6 +1494,12 @@ static inline bool cpu_has_vmx_vmfunc(void)
SECONDARY_EXEC_ENABLE_VMFUNC;
}
+static bool vmx_umip_emulated(void)
+{
+ return vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_DESC;
+}
+
static inline bool report_flexpriority(void)
{
return flexpriority_enabled;
@@ -2880,18 +2886,15 @@ static void setup_msrs(struct vcpu_vmx *vmx)
vmx_update_msr_bitmap(&vmx->vcpu);
}
-/*
- * reads and returns guest's timestamp counter "register"
- * guest_tsc = (host_tsc * tsc multiplier) >> 48 + tsc_offset
- * -- Intel TSC Scaling for Virtualization White Paper, sec 1.3
- */
-static u64 guest_read_tsc(struct kvm_vcpu *vcpu)
+static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
{
- u64 host_tsc, tsc_offset;
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
- host_tsc = rdtsc();
- tsc_offset = vmcs_read64(TSC_OFFSET);
- return kvm_scale_tsc(vcpu, host_tsc) + tsc_offset;
+ if (is_guest_mode(vcpu) &&
+ (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING))
+ return vcpu->arch.tsc_offset - vmcs12->tsc_offset;
+
+ return vcpu->arch.tsc_offset;
}
/*
@@ -3524,12 +3527,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
#endif
case MSR_EFER:
return kvm_get_msr_common(vcpu, msr_info);
- case MSR_IA32_TSC:
- msr_info->data = guest_read_tsc(vcpu);
- break;
case MSR_IA32_SPEC_CTRL:
if (!msr_info->host_initiated &&
- !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) &&
!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
return 1;
@@ -3646,17 +3645,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
return 1;
vmcs_write64(GUEST_BNDCFGS, data);
break;
- case MSR_IA32_TSC:
- kvm_write_tsc(vcpu, msr_info);
- break;
case MSR_IA32_SPEC_CTRL:
if (!msr_info->host_initiated &&
- !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) &&
!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
return 1;
/* The STIBP bit doesn't fault even if it's not advertised */
- if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP))
+ if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD))
return 1;
vmx->spec_ctrl = data;
@@ -3682,7 +3677,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
case MSR_IA32_PRED_CMD:
if (!msr_info->host_initiated &&
- !guest_cpuid_has(vcpu, X86_FEATURE_IBPB) &&
!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
return 1;
@@ -4553,12 +4547,6 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
__vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid, invalidate_gpa);
}
-static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu)
-{
- if (enable_ept)
- vmx_flush_tlb(vcpu, true);
-}
-
static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
{
ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
@@ -4776,14 +4764,16 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
else
hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON;
- if ((cr4 & X86_CR4_UMIP) && !boot_cpu_has(X86_FEATURE_UMIP)) {
- vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
- SECONDARY_EXEC_DESC);
- hw_cr4 &= ~X86_CR4_UMIP;
- } else if (!is_guest_mode(vcpu) ||
- !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC))
- vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+ if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) {
+ if (cr4 & X86_CR4_UMIP) {
+ vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
SECONDARY_EXEC_DESC);
+ hw_cr4 &= ~X86_CR4_UMIP;
+ } else if (!is_guest_mode(vcpu) ||
+ !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC))
+ vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+ SECONDARY_EXEC_DESC);
+ }
if (cr4 & X86_CR4_VMXE) {
/*
@@ -9287,7 +9277,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
} else {
sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
- vmx_flush_tlb_ept_only(vcpu);
+ vmx_flush_tlb(vcpu, true);
}
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
@@ -9315,7 +9305,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
!nested_cpu_has2(get_vmcs12(&vmx->vcpu),
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
vmcs_write64(APIC_ACCESS_ADDR, hpa);
- vmx_flush_tlb_ept_only(vcpu);
+ vmx_flush_tlb(vcpu, true);
}
}
@@ -9495,9 +9485,21 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
}
STACK_FRAME_NON_STANDARD(vmx_handle_external_intr);
-static bool vmx_has_high_real_mode_segbase(void)
+static bool vmx_has_emulated_msr(int index)
{
- return enable_unrestricted_guest || emulate_invalid_guest_state;
+ switch (index) {
+ case MSR_IA32_SMBASE:
+ /*
+ * We cannot do SMM unless we can run the guest in big
+ * real mode.
+ */
+ return enable_unrestricted_guest || emulate_invalid_guest_state;
+ case MSR_AMD64_VIRT_SPEC_CTRL:
+ /* This is AMD only. */
+ return false;
+ default:
+ return true;
+ }
}
static bool vmx_mpx_supported(void)
@@ -9512,12 +9514,6 @@ static bool vmx_xsaves_supported(void)
SECONDARY_EXEC_XSAVES;
}
-static bool vmx_umip_emulated(void)
-{
- return vmcs_config.cpu_based_2nd_exec_ctrl &
- SECONDARY_EXEC_DESC;
-}
-
static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
{
u32 exit_intr_info;
@@ -9735,8 +9731,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
* is no need to worry about the conditional branch over the wrmsr
* being speculatively taken.
*/
- if (vmx->spec_ctrl)
- native_wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
+ x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
vmx->__launched = vmx->loaded_vmcs->launched;
@@ -9884,8 +9879,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
- if (vmx->spec_ctrl)
- native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+ x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
/* Eliminate branch target predictions from guest mode */
vmexit_fill_RSB();
@@ -10608,6 +10602,16 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
return true;
}
+static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12)
+{
+ if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
+ !page_address_valid(vcpu, vmcs12->apic_access_addr))
+ return -EINVAL;
+ else
+ return 0;
+}
+
static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
@@ -11176,11 +11180,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
}
- if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
- vmcs_write64(TSC_OFFSET,
- vcpu->arch.tsc_offset + vmcs12->tsc_offset);
- else
- vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+ vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+
if (kvm_has_tsc_control)
decache_tsc_multiplier(vmx);
@@ -11222,7 +11223,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
}
} else if (nested_cpu_has2(vmcs12,
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
- vmx_flush_tlb_ept_only(vcpu);
+ vmx_flush_tlb(vcpu, true);
}
/*
@@ -11299,6 +11300,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12))
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+ if (nested_vmx_check_apic_access_controls(vcpu, vmcs12))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
if (nested_vmx_check_tpr_shadow_controls(vcpu, vmcs12))
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
@@ -11420,6 +11424,7 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
u32 msr_entry_idx;
u32 exit_qual;
+ int r;
enter_guest_mode(vcpu);
@@ -11429,26 +11434,21 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);
vmx_segment_cache_clear(vmx);
- if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) {
- leave_guest_mode(vcpu);
- vmx_switch_vmcs(vcpu, &vmx->vmcs01);
- nested_vmx_entry_failure(vcpu, vmcs12,
- EXIT_REASON_INVALID_STATE, exit_qual);
- return 1;
- }
+ if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+ vcpu->arch.tsc_offset += vmcs12->tsc_offset;
+
+ r = EXIT_REASON_INVALID_STATE;
+ if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual))
+ goto fail;
nested_get_vmcs12_pages(vcpu, vmcs12);
+ r = EXIT_REASON_MSR_LOAD_FAIL;
msr_entry_idx = nested_vmx_load_msr(vcpu,
vmcs12->vm_entry_msr_load_addr,
vmcs12->vm_entry_msr_load_count);
- if (msr_entry_idx) {
- leave_guest_mode(vcpu);
- vmx_switch_vmcs(vcpu, &vmx->vmcs01);
- nested_vmx_entry_failure(vcpu, vmcs12,
- EXIT_REASON_MSR_LOAD_FAIL, msr_entry_idx);
- return 1;
- }
+ if (msr_entry_idx)
+ goto fail;
/*
* Note no nested_vmx_succeed or nested_vmx_fail here. At this point
@@ -11457,6 +11457,14 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
* the success flag) when L2 exits (see nested_vmx_vmexit()).
*/
return 0;
+
+fail:
+ if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+ vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
+ leave_guest_mode(vcpu);
+ vmx_switch_vmcs(vcpu, &vmx->vmcs01);
+ nested_vmx_entry_failure(vcpu, vmcs12, r, exit_qual);
+ return 1;
}
/*
@@ -12028,6 +12036,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
leave_guest_mode(vcpu);
+ if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+ vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
+
if (likely(!vmx->fail)) {
if (exit_reason == -1)
sync_vmcs12(vcpu, vmcs12);
@@ -12065,7 +12076,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
} else if (!nested_cpu_has_ept(vmcs12) &&
nested_cpu_has2(vmcs12,
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
- vmx_flush_tlb_ept_only(vcpu);
+ vmx_flush_tlb(vcpu, true);
}
/* This is needed for same reason as it was needed in prepare_vmcs02 */
@@ -12224,10 +12235,16 @@ static inline int u64_shl_div_u64(u64 a, unsigned int shift,
static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- u64 tscl = rdtsc();
- u64 guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
- u64 delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
+ struct vcpu_vmx *vmx;
+ u64 tscl, guest_tscl, delta_tsc;
+
+ if (kvm_mwait_in_guest(vcpu->kvm))
+ return -EOPNOTSUPP;
+
+ vmx = to_vmx(vcpu);
+ tscl = rdtsc();
+ guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
+ delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
/* Convert to host delta tsc if tsc scaling is enabled */
if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio &&
@@ -12533,7 +12550,7 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
vcpu_info.vector = irq.vector;
- trace_kvm_pi_irte_update(vcpu->vcpu_id, host_irq, e->gsi,
+ trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
vcpu_info.vector, vcpu_info.pi_desc_addr, set);
if (set)
@@ -12622,7 +12639,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.hardware_enable = hardware_enable,
.hardware_disable = hardware_disable,
.cpu_has_accelerated_tpr = report_flexpriority,
- .cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase,
+ .has_emulated_msr = vmx_has_emulated_msr,
.vm_init = vmx_vm_init,
.vm_alloc = vmx_vm_alloc,
@@ -12712,6 +12729,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
+ .read_l1_tsc_offset = vmx_read_l1_tsc_offset,
.write_tsc_offset = vmx_write_tsc_offset,
.set_tdp_cr3 = vmx_set_cr3,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b2ff74b..71e7cda 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -114,7 +114,7 @@ module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);
static bool __read_mostly report_ignored_msrs = true;
module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR);
-unsigned int min_timer_period_us = 500;
+unsigned int min_timer_period_us = 200;
module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
static bool __read_mostly kvmclock_periodic_sync = true;
@@ -843,7 +843,10 @@ EXPORT_SYMBOL_GPL(kvm_set_cr4);
int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
#ifdef CONFIG_X86_64
- cr3 &= ~CR3_PCID_INVD;
+ bool pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE);
+
+ if (pcid_enabled)
+ cr3 &= ~CR3_PCID_INVD;
#endif
if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) {
@@ -1058,6 +1061,7 @@ static u32 emulated_msrs[] = {
MSR_SMI_COUNT,
MSR_PLATFORM_INFO,
MSR_MISC_FEATURES_ENABLES,
+ MSR_AMD64_VIRT_SPEC_CTRL,
};
static unsigned num_emulated_msrs;
@@ -1490,7 +1494,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset)
{
- u64 curr_offset = vcpu->arch.tsc_offset;
+ u64 curr_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu);
vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset;
}
@@ -1532,7 +1536,9 @@ static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
{
- return vcpu->arch.tsc_offset + kvm_scale_tsc(vcpu, host_tsc);
+ u64 tsc_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu);
+
+ return tsc_offset + kvm_scale_tsc(vcpu, host_tsc);
}
EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);
@@ -2362,6 +2368,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
return 1;
vcpu->arch.smbase = data;
break;
+ case MSR_IA32_TSC:
+ kvm_write_tsc(vcpu, msr_info);
+ break;
case MSR_SMI_COUNT:
if (!msr_info->host_initiated)
return 1;
@@ -2605,6 +2614,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
case MSR_IA32_UCODE_REV:
msr_info->data = vcpu->arch.microcode_version;
break;
+ case MSR_IA32_TSC:
+ msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset;
+ break;
case MSR_MTRRcap:
case 0x200 ... 0x2ff:
return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data);
@@ -2819,7 +2831,8 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs,
static inline bool kvm_can_mwait_in_guest(void)
{
return boot_cpu_has(X86_FEATURE_MWAIT) &&
- !boot_cpu_has_bug(X86_BUG_MONITOR);
+ !boot_cpu_has_bug(X86_BUG_MONITOR) &&
+ boot_cpu_has(X86_FEATURE_ARAT);
}
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
@@ -2894,7 +2907,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
* fringe case that is not enabled except via specific settings
* of the module parameters.
*/
- r = kvm_x86_ops->cpu_has_high_real_mode_segbase();
+ r = kvm_x86_ops->has_emulated_msr(MSR_IA32_SMBASE);
break;
case KVM_CAP_VAPIC:
r = !kvm_x86_ops->cpu_has_accelerated_tpr();
@@ -4594,14 +4607,8 @@ static void kvm_init_msr_list(void)
num_msrs_to_save = j;
for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) {
- switch (emulated_msrs[i]) {
- case MSR_IA32_SMBASE:
- if (!kvm_x86_ops->cpu_has_high_real_mode_segbase())
- continue;
- break;
- default:
- break;
- }
+ if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i]))
+ continue;
if (j < i)
emulated_msrs[j] = emulated_msrs[i];
@@ -6662,9 +6669,7 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu)
int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
{
unsigned long nr, a0, a1, a2, a3, ret;
- int op_64_bit, r;
-
- r = kvm_skip_emulated_instruction(vcpu);
+ int op_64_bit;
if (kvm_hv_hypercall_enabled(vcpu->kvm))
return kvm_hv_hypercall(vcpu);
@@ -6712,8 +6717,9 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
if (!op_64_bit)
ret = (u32)ret;
kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
+
++vcpu->stat.hypercalls;
- return r;
+ return kvm_skip_emulated_instruction(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);
@@ -7970,6 +7976,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
{
struct msr_data apic_base_msr;
int mmu_reset_needed = 0;
+ int cpuid_update_needed = 0;
int pending_vec, max_bits, idx;
struct desc_ptr dt;
int ret = -EINVAL;
@@ -8008,8 +8015,10 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
vcpu->arch.cr0 = sregs->cr0;
mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
+ cpuid_update_needed |= ((kvm_read_cr4(vcpu) ^ sregs->cr4) &
+ (X86_CR4_OSXSAVE | X86_CR4_PKE));
kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
- if (sregs->cr4 & (X86_CR4_OSXSAVE | X86_CR4_PKE))
+ if (cpuid_update_needed)
kvm_update_cpuid(vcpu);
idx = srcu_read_lock(&vcpu->kvm->srcu);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 7d35ce6..c9492f7 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -302,13 +302,6 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
__rem; \
})
-#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0)
-#define KVM_X86_DISABLE_EXITS_HTL (1 << 1)
-#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2)
-#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \
- KVM_X86_DISABLE_EXITS_HTL | \
- KVM_X86_DISABLE_EXITS_PAUSE)
-
static inline bool kvm_mwait_in_guest(struct kvm *kvm)
{
return kvm->arch.mwait_in_guest;
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 9a53a06..c3b527a 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -184,11 +184,11 @@
#ifndef CONFIG_UML
/*
- * memcpy_mcsafe_unrolled - memory copy with machine check exception handling
+ * __memcpy_mcsafe - memory copy with machine check exception handling
* Note that we only catch machine checks when reading the source addresses.
* Writes to target are posted and don't generate machine checks.
*/
-ENTRY(memcpy_mcsafe_unrolled)
+ENTRY(__memcpy_mcsafe)
cmpl $8, %edx
/* Less than 8 bytes? Go to byte copy loop */
jb .L_no_whole_words
@@ -204,58 +204,29 @@
subl $8, %ecx
negl %ecx
subl %ecx, %edx
-.L_copy_leading_bytes:
+.L_read_leading_bytes:
movb (%rsi), %al
+.L_write_leading_bytes:
movb %al, (%rdi)
incq %rsi
incq %rdi
decl %ecx
- jnz .L_copy_leading_bytes
+ jnz .L_read_leading_bytes
.L_8byte_aligned:
- /* Figure out how many whole cache lines (64-bytes) to copy */
- movl %edx, %ecx
- andl $63, %edx
- shrl $6, %ecx
- jz .L_no_whole_cache_lines
-
- /* Loop copying whole cache lines */
-.L_cache_w0: movq (%rsi), %r8
-.L_cache_w1: movq 1*8(%rsi), %r9
-.L_cache_w2: movq 2*8(%rsi), %r10
-.L_cache_w3: movq 3*8(%rsi), %r11
- movq %r8, (%rdi)
- movq %r9, 1*8(%rdi)
- movq %r10, 2*8(%rdi)
- movq %r11, 3*8(%rdi)
-.L_cache_w4: movq 4*8(%rsi), %r8
-.L_cache_w5: movq 5*8(%rsi), %r9
-.L_cache_w6: movq 6*8(%rsi), %r10
-.L_cache_w7: movq 7*8(%rsi), %r11
- movq %r8, 4*8(%rdi)
- movq %r9, 5*8(%rdi)
- movq %r10, 6*8(%rdi)
- movq %r11, 7*8(%rdi)
- leaq 64(%rsi), %rsi
- leaq 64(%rdi), %rdi
- decl %ecx
- jnz .L_cache_w0
-
- /* Are there any trailing 8-byte words? */
-.L_no_whole_cache_lines:
movl %edx, %ecx
andl $7, %edx
shrl $3, %ecx
jz .L_no_whole_words
- /* Copy trailing words */
-.L_copy_trailing_words:
+.L_read_words:
movq (%rsi), %r8
- mov %r8, (%rdi)
- leaq 8(%rsi), %rsi
- leaq 8(%rdi), %rdi
+.L_write_words:
+ movq %r8, (%rdi)
+ addq $8, %rsi
+ addq $8, %rdi
decl %ecx
- jnz .L_copy_trailing_words
+ jnz .L_read_words
/* Any trailing bytes? */
.L_no_whole_words:
@@ -264,38 +235,53 @@
/* Copy trailing bytes */
movl %edx, %ecx
-.L_copy_trailing_bytes:
+.L_read_trailing_bytes:
movb (%rsi), %al
+.L_write_trailing_bytes:
movb %al, (%rdi)
incq %rsi
incq %rdi
decl %ecx
- jnz .L_copy_trailing_bytes
+ jnz .L_read_trailing_bytes
/* Copy successful. Return zero */
.L_done_memcpy_trap:
xorq %rax, %rax
ret
-ENDPROC(memcpy_mcsafe_unrolled)
-EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled)
+ENDPROC(__memcpy_mcsafe)
+EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
.section .fixup, "ax"
- /* Return -EFAULT for any failure */
-.L_memcpy_mcsafe_fail:
- mov $-EFAULT, %rax
+ /*
+ * Return number of bytes not copied for any failure. Note that
+ * there is no "tail" handling since the source buffer is 8-byte
+ * aligned and poison is cacheline aligned.
+ */
+.E_read_words:
+ shll $3, %ecx
+.E_leading_bytes:
+ addl %edx, %ecx
+.E_trailing_bytes:
+ mov %ecx, %eax
ret
+ /*
+ * For write fault handling, given the destination is unaligned,
+ * we handle faults on multi-byte writes with a byte-by-byte
+ * copy up to the write-protected page.
+ */
+.E_write_words:
+ shll $3, %ecx
+ addl %edx, %ecx
+ movl %ecx, %edx
+ jmp mcsafe_handle_tail
+
.previous
- _ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail)
+ _ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes)
+ _ASM_EXTABLE_FAULT(.L_read_words, .E_read_words)
+ _ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes)
+ _ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes)
+ _ASM_EXTABLE(.L_write_words, .E_write_words)
+ _ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes)
#endif
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 75d3776..9c5606d 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -23,13 +23,13 @@ unsigned long __clear_user(void __user *addr, unsigned long size)
asm volatile(
" testq %[size8],%[size8]\n"
" jz 4f\n"
- "0: movq %[zero],(%[dst])\n"
- " addq %[eight],%[dst]\n"
+ "0: movq $0,(%[dst])\n"
+ " addq $8,%[dst]\n"
" decl %%ecx ; jnz 0b\n"
"4: movq %[size1],%%rcx\n"
" testl %%ecx,%%ecx\n"
" jz 2f\n"
- "1: movb %b[zero],(%[dst])\n"
+ "1: movb $0,(%[dst])\n"
" incq %[dst]\n"
" decl %%ecx ; jnz 1b\n"
"2:\n"
@@ -40,8 +40,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size)
_ASM_EXTABLE(0b,3b)
_ASM_EXTABLE(1b,2b)
: [size8] "=&c"(size), [dst] "=&D" (__d0)
- : [size1] "r"(size & 7), "[size8]" (size / 8), "[dst]"(addr),
- [zero] "r" (0UL), [eight] "r" (8UL));
+ : [size1] "r"(size & 7), "[size8]" (size / 8), "[dst]"(addr));
clac();
return size;
}
@@ -75,6 +74,27 @@ copy_user_handle_tail(char *to, char *from, unsigned len)
return len;
}
+/*
+ * Similar to copy_user_handle_tail, probe for the write fault point,
+ * but reuse __memcpy_mcsafe in case a new read error is encountered.
+ * clac() is handled in _copy_to_iter_mcsafe().
+ */
+__visible unsigned long
+mcsafe_handle_tail(char *to, char *from, unsigned len)
+{
+ for (; len; --len, to++, from++) {
+ /*
+ * Call the assembly routine back directly since
+ * memcpy_mcsafe() may silently fallback to memcpy.
+ */
+ unsigned long rem = __memcpy_mcsafe(to, from, 1);
+
+ if (rem)
+ break;
+ }
+ return len;
+}
+
#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
/**
* clean_cache_range - write back a cache range with CLWB
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 62a7e9f..2f3c919 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -18,6 +18,7 @@
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
+#include <linux/highmem.h>
#include <asm/pgtable.h>
@@ -334,16 +335,16 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr,
pgprotval_t eff_in, unsigned long P)
{
int i;
- pte_t *start;
+ pte_t *pte;
pgprotval_t prot, eff;
- start = (pte_t *)pmd_page_vaddr(addr);
for (i = 0; i < PTRS_PER_PTE; i++) {
- prot = pte_flags(*start);
- eff = effective_prot(eff_in, prot);
st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT);
+ pte = pte_offset_map(&addr, st->current_address);
+ prot = pte_flags(*pte);
+ eff = effective_prot(eff_in, prot);
note_page(m, st, __pgprot(prot), eff, 5);
- start++;
+ pte_unmap(pte);
}
}
#ifdef CONFIG_KASAN
@@ -359,7 +360,7 @@ static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st,
void *pt)
{
if (__pa(pt) == __pa(kasan_zero_pmd) ||
- (pgtable_l5_enabled && __pa(pt) == __pa(kasan_zero_p4d)) ||
+ (pgtable_l5_enabled() && __pa(pt) == __pa(kasan_zero_p4d)) ||
__pa(pt) == __pa(kasan_zero_pud)) {
pgprotval_t prot = pte_flags(kasan_zero_pte[0]);
note_page(m, st, __pgprot(prot), 0, 5);
@@ -475,8 +476,8 @@ static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
}
}
-#define pgd_large(a) (pgtable_l5_enabled ? pgd_large(a) : p4d_large(__p4d(pgd_val(a))))
-#define pgd_none(a) (pgtable_l5_enabled ? pgd_none(a) : p4d_none(__p4d(pgd_val(a))))
+#define pgd_large(a) (pgtable_l5_enabled() ? pgd_large(a) : p4d_large(__p4d(pgd_val(a))))
+#define pgd_none(a) (pgtable_l5_enabled() ? pgd_none(a) : p4d_none(__p4d(pgd_val(a))))
static inline bool is_hypervisor_range(int idx)
{
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 73bd8c9..9a84a0d 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -209,6 +209,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address,
unsigned lsb = 0;
siginfo_t info;
+ clear_siginfo(&info);
info.si_signo = si_signo;
info.si_errno = 0;
info.si_code = si_code;
@@ -439,7 +440,7 @@ static noinline int vmalloc_fault(unsigned long address)
if (pgd_none(*pgd_k))
return -1;
- if (pgtable_l5_enabled) {
+ if (pgtable_l5_enabled()) {
if (pgd_none(*pgd)) {
set_pgd(pgd, *pgd_k);
arch_flush_lazy_mmu_mode();
@@ -454,7 +455,7 @@ static noinline int vmalloc_fault(unsigned long address)
if (p4d_none(*p4d_k))
return -1;
- if (p4d_none(*p4d) && !pgtable_l5_enabled) {
+ if (p4d_none(*p4d) && !pgtable_l5_enabled()) {
set_p4d(p4d, *p4d_k);
arch_flush_lazy_mmu_mode();
} else {
@@ -828,6 +829,8 @@ static inline void
show_signal_msg(struct pt_regs *regs, unsigned long error_code,
unsigned long address, struct task_struct *tsk)
{
+ const char *loglvl = task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG;
+
if (!unhandled_signal(tsk, SIGSEGV))
return;
@@ -835,13 +838,14 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
return;
printk("%s%s[%d]: segfault at %lx ip %px sp %px error %lx",
- task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
- tsk->comm, task_pid_nr(tsk), address,
+ loglvl, tsk->comm, task_pid_nr(tsk), address,
(void *)regs->ip, (void *)regs->sp, error_code);
print_vma_addr(KERN_CONT " in ", regs->ip);
printk(KERN_CONT "\n");
+
+ show_opcodes((u8 *)regs->ip, loglvl);
}
static void
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index a2f0c7e..fe7a125 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -123,7 +123,7 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
result = ident_p4d_init(info, p4d, addr, next);
if (result)
return result;
- if (pgtable_l5_enabled) {
+ if (pgtable_l5_enabled()) {
set_pgd(pgd, __pgd(__pa(p4d) | info->kernpg_flag));
} else {
/*
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 0a40060..17383f9 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -180,7 +180,7 @@ static void sync_global_pgds_l4(unsigned long start, unsigned long end)
*/
void sync_global_pgds(unsigned long start, unsigned long end)
{
- if (pgtable_l5_enabled)
+ if (pgtable_l5_enabled())
sync_global_pgds_l5(start, end);
else
sync_global_pgds_l4(start, end);
@@ -643,7 +643,7 @@ phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end,
unsigned long vaddr = (unsigned long)__va(paddr);
int i = p4d_index(vaddr);
- if (!pgtable_l5_enabled)
+ if (!pgtable_l5_enabled())
return phys_pud_init((pud_t *) p4d_page, paddr, paddr_end, page_size_mask);
for (; i < PTRS_PER_P4D; i++, paddr = paddr_next) {
@@ -723,7 +723,7 @@ kernel_physical_mapping_init(unsigned long paddr_start,
page_size_mask);
spin_lock(&init_mm.page_table_lock);
- if (pgtable_l5_enabled)
+ if (pgtable_l5_enabled())
pgd_populate(&init_mm, pgd, p4d);
else
p4d_populate(&init_mm, p4d_offset(pgd, vaddr), (pud_t *) p4d);
@@ -1100,7 +1100,7 @@ remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end,
* 5-level case we should free them. This code will have to change
* to adapt for boot-time switching between 4 and 5 level page tables.
*/
- if (pgtable_l5_enabled)
+ if (pgtable_l5_enabled())
free_pud_table(pud_base, p4d);
}
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 980dbeb..e3e7752 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -2,10 +2,8 @@
#define DISABLE_BRANCH_PROFILING
#define pr_fmt(fmt) "kasan: " fmt
-#ifdef CONFIG_X86_5LEVEL
-/* Too early to use cpu_feature_enabled() */
-#define pgtable_l5_enabled __pgtable_l5_enabled
-#endif
+/* cpu_feature_enabled() cannot be used this early */
+#define USE_EARLY_PGTABLE_L5
#include <linux/bootmem.h>
#include <linux/kasan.h>
@@ -182,7 +180,7 @@ static void __init clear_pgds(unsigned long start,
* With folded p4d, pgd_clear() is nop, use p4d_clear()
* instead.
*/
- if (pgtable_l5_enabled)
+ if (pgtable_l5_enabled())
pgd_clear(pgd);
else
p4d_clear(p4d_offset(pgd, start));
@@ -197,7 +195,7 @@ static inline p4d_t *early_p4d_offset(pgd_t *pgd, unsigned long addr)
{
unsigned long p4d;
- if (!pgtable_l5_enabled)
+ if (!pgtable_l5_enabled())
return (p4d_t *)pgd;
p4d = __pa_nodebug(pgd_val(*pgd)) & PTE_PFN_MASK;
@@ -284,7 +282,7 @@ void __init kasan_early_init(void)
for (i = 0; i < PTRS_PER_PUD; i++)
kasan_zero_pud[i] = __pud(pud_val);
- for (i = 0; pgtable_l5_enabled && i < PTRS_PER_P4D; i++)
+ for (i = 0; pgtable_l5_enabled() && i < PTRS_PER_P4D; i++)
kasan_zero_p4d[i] = __p4d(p4d_val);
kasan_map_early_shadow(early_top_pgt);
@@ -315,7 +313,7 @@ void __init kasan_init(void)
* bunch of things like kernel code, modules, EFI mapping, etc.
* We need to take extra steps to not overwrite them.
*/
- if (pgtable_l5_enabled) {
+ if (pgtable_l5_enabled()) {
void *ptr;
ptr = (void *)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_END));
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 615cc03..61db77b 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -78,7 +78,7 @@ void __init kernel_randomize_memory(void)
struct rnd_state rand_state;
unsigned long remain_entropy;
- vaddr_start = pgtable_l5_enabled ? __PAGE_OFFSET_BASE_L5 : __PAGE_OFFSET_BASE_L4;
+ vaddr_start = pgtable_l5_enabled() ? __PAGE_OFFSET_BASE_L5 : __PAGE_OFFSET_BASE_L4;
vaddr = vaddr_start;
/*
@@ -124,7 +124,7 @@ void __init kernel_randomize_memory(void)
*/
entropy = remain_entropy / (ARRAY_SIZE(kaslr_regions) - i);
prandom_bytes_state(&rand_state, &rand, sizeof(rand));
- if (pgtable_l5_enabled)
+ if (pgtable_l5_enabled())
entropy = (rand % (entropy + 1)) & P4D_MASK;
else
entropy = (rand % (entropy + 1)) & PUD_MASK;
@@ -136,7 +136,7 @@ void __init kernel_randomize_memory(void)
* randomization alignment.
*/
vaddr += get_padding(&kaslr_regions[i]);
- if (pgtable_l5_enabled)
+ if (pgtable_l5_enabled())
vaddr = round_up(vaddr + 1, P4D_SIZE);
else
vaddr = round_up(vaddr + 1, PUD_SIZE);
@@ -212,7 +212,7 @@ void __meminit init_trampoline(void)
return;
}
- if (pgtable_l5_enabled)
+ if (pgtable_l5_enabled())
init_trampoline_p4d();
else
init_trampoline_pud();
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 25504d5..fa15085 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -136,13 +136,13 @@ static int __init numa_add_memblk_to(int nid, u64 start, u64 end,
/* whine about and ignore invalid blks */
if (start > end || nid < 0 || nid >= MAX_NUMNODES) {
- pr_warning("NUMA: Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
- nid, start, end - 1);
+ pr_warn("Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
+ nid, start, end - 1);
return 0;
}
if (mi->nr_blks >= NR_NODE_MEMBLKS) {
- pr_err("NUMA: too many memblk ranges\n");
+ pr_err("too many memblk ranges\n");
return -EINVAL;
}
@@ -267,14 +267,14 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
*/
if (bi->end > bj->start && bi->start < bj->end) {
if (bi->nid != bj->nid) {
- pr_err("NUMA: node %d [mem %#010Lx-%#010Lx] overlaps with node %d [mem %#010Lx-%#010Lx]\n",
+ pr_err("node %d [mem %#010Lx-%#010Lx] overlaps with node %d [mem %#010Lx-%#010Lx]\n",
bi->nid, bi->start, bi->end - 1,
bj->nid, bj->start, bj->end - 1);
return -EINVAL;
}
- pr_warning("NUMA: Warning: node %d [mem %#010Lx-%#010Lx] overlaps with itself [mem %#010Lx-%#010Lx]\n",
- bi->nid, bi->start, bi->end - 1,
- bj->start, bj->end - 1);
+ pr_warn("Warning: node %d [mem %#010Lx-%#010Lx] overlaps with itself [mem %#010Lx-%#010Lx]\n",
+ bi->nid, bi->start, bi->end - 1,
+ bj->start, bj->end - 1);
}
/*
@@ -364,7 +364,7 @@ static int __init numa_alloc_distance(void)
phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
size, PAGE_SIZE);
if (!phys) {
- pr_warning("NUMA: Warning: can't allocate distance table!\n");
+ pr_warn("Warning: can't allocate distance table!\n");
/* don't retry until explicitly reset */
numa_distance = (void *)1LU;
return -ENOMEM;
@@ -410,14 +410,14 @@ void __init numa_set_distance(int from, int to, int distance)
if (from >= numa_distance_cnt || to >= numa_distance_cnt ||
from < 0 || to < 0) {
- pr_warn_once("NUMA: Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
- from, to, distance);
+ pr_warn_once("Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
+ from, to, distance);
return;
}
if ((u8)distance != distance ||
(from == to && distance != LOCAL_DISTANCE)) {
- pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
+ pr_warn_once("Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
from, to, distance);
return;
}
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 0f3d50f..3bded76e 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -93,6 +93,18 @@ void arch_report_meminfo(struct seq_file *m)
static inline void split_page_count(int level) { }
#endif
+static inline int
+within(unsigned long addr, unsigned long start, unsigned long end)
+{
+ return addr >= start && addr < end;
+}
+
+static inline int
+within_inclusive(unsigned long addr, unsigned long start, unsigned long end)
+{
+ return addr >= start && addr <= end;
+}
+
#ifdef CONFIG_X86_64
static inline unsigned long highmap_start_pfn(void)
@@ -106,20 +118,25 @@ static inline unsigned long highmap_end_pfn(void)
return __pa_symbol(roundup(_brk_end, PMD_SIZE) - 1) >> PAGE_SHIFT;
}
+static bool __cpa_pfn_in_highmap(unsigned long pfn)
+{
+ /*
+ * Kernel text has an alias mapping at a high address, known
+ * here as "highmap".
+ */
+ return within_inclusive(pfn, highmap_start_pfn(), highmap_end_pfn());
+}
+
+#else
+
+static bool __cpa_pfn_in_highmap(unsigned long pfn)
+{
+ /* There is no highmap on 32-bit */
+ return false;
+}
+
#endif
-static inline int
-within(unsigned long addr, unsigned long start, unsigned long end)
-{
- return addr >= start && addr < end;
-}
-
-static inline int
-within_inclusive(unsigned long addr, unsigned long start, unsigned long end)
-{
- return addr >= start && addr <= end;
-}
-
/*
* Flushing functions
*/
@@ -172,7 +189,7 @@ static void __cpa_flush_all(void *arg)
static void cpa_flush_all(unsigned long cache)
{
- BUG_ON(irqs_disabled());
+ BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
on_each_cpu(__cpa_flush_all, (void *) cache, 1);
}
@@ -236,7 +253,7 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache,
unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */
#endif
- BUG_ON(irqs_disabled());
+ BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
on_each_cpu(__cpa_flush_all, (void *) do_wbinvd, 1);
@@ -1183,6 +1200,10 @@ static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr,
cpa->numpages = 1;
cpa->pfn = __pa(vaddr) >> PAGE_SHIFT;
return 0;
+
+ } else if (__cpa_pfn_in_highmap(cpa->pfn)) {
+ /* Faults in the highmap are OK, so do not warn: */
+ return -EFAULT;
} else {
WARN(1, KERN_WARNING "CPA: called for zero pte. "
"vaddr = %lx cpa->vaddr = %lx\n", vaddr,
@@ -1335,8 +1356,7 @@ static int cpa_process_alias(struct cpa_data *cpa)
* to touch the high mapped kernel as well:
*/
if (!within(vaddr, (unsigned long)_text, _brk_end) &&
- within_inclusive(cpa->pfn, highmap_start_pfn(),
- highmap_end_pfn())) {
+ __cpa_pfn_in_highmap(cpa->pfn)) {
unsigned long temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) +
__START_KERNEL_map - phys_base;
alias_cpa = *cpa;
diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c
index d7bc0eea..6e98e0a 100644
--- a/arch/x86/mm/pkeys.c
+++ b/arch/x86/mm/pkeys.c
@@ -94,26 +94,27 @@ int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey
*/
if (pkey != -1)
return pkey;
- /*
- * Look for a protection-key-drive execute-only mapping
- * which is now being given permissions that are not
- * execute-only. Move it back to the default pkey.
- */
- if (vma_is_pkey_exec_only(vma) &&
- (prot & (PROT_READ|PROT_WRITE))) {
- return 0;
- }
+
/*
* The mapping is execute-only. Go try to get the
* execute-only protection key. If we fail to do that,
* fall through as if we do not have execute-only
- * support.
+ * support in this mm.
*/
if (prot == PROT_EXEC) {
pkey = execute_only_pkey(vma->vm_mm);
if (pkey > 0)
return pkey;
+ } else if (vma_is_pkey_exec_only(vma)) {
+ /*
+ * Protections are *not* PROT_EXEC, but the mapping
+ * is using the exec-only pkey. This mapping was
+ * PROT_EXEC and will no longer be. Move back to
+ * the default pkey.
+ */
+ return ARCH_DEFAULT_PKEY;
}
+
/*
* This is a vanilla, non-pkey mprotect (or we failed to
* setup execute-only), inherit the pkey from the VMA we
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index f1fd52f..4d418e7 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -421,6 +421,16 @@ static inline bool pti_kernel_image_global_ok(void)
if (boot_cpu_has(X86_FEATURE_K8))
return false;
+ /*
+ * RANDSTRUCT derives its hardening benefits from the
+ * attacker's lack of knowledge about the layout of kernel
+ * data structures. Keep the kernel image non-global in
+ * cases where RANDSTRUCT is in use to help keep the layout a
+ * secret.
+ */
+ if (IS_ENABLED(CONFIG_GCC_PLUGIN_RANDSTRUCT))
+ return false;
+
return true;
}
@@ -430,12 +440,24 @@ static inline bool pti_kernel_image_global_ok(void)
*/
void pti_clone_kernel_text(void)
{
+ /*
+ * rodata is part of the kernel image and is normally
+ * readable on the filesystem or on the web. But, do not
+ * clone the areas past rodata, they might contain secrets.
+ */
unsigned long start = PFN_ALIGN(_text);
- unsigned long end = ALIGN((unsigned long)_end, PMD_PAGE_SIZE);
+ unsigned long end = (unsigned long)__end_rodata_hpage_align;
if (!pti_kernel_image_global_ok())
return;
+ pr_debug("mapping partial kernel image into user address space\n");
+
+ /*
+ * Note that this will undo _some_ of the work that
+ * pti_set_kernel_image_nonglobal() did to clear the
+ * global bit.
+ */
pti_clone_pmds(start, end, _PAGE_RW);
}
@@ -458,8 +480,6 @@ void pti_set_kernel_image_nonglobal(void)
if (pti_kernel_image_global_ok())
return;
- pr_debug("set kernel image non-global\n");
-
set_memory_nonglobal(start, (end - start) >> PAGE_SHIFT);
}
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index e055d1a..6eb1f34 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -157,7 +157,7 @@ static void sync_current_stack_to_mm(struct mm_struct *mm)
unsigned long sp = current_stack_pointer;
pgd_t *pgd = pgd_offset(mm, sp);
- if (pgtable_l5_enabled) {
+ if (pgtable_l5_enabled()) {
if (unlikely(pgd_none(*pgd))) {
pgd_t *pgd_ref = pgd_offset_k(sp);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index b7251541..d765ace 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1,4 +1,5 @@
-/* bpf_jit_comp.c : BPF JIT compiler
+/*
+ * bpf_jit_comp.c: BPF JIT compiler
*
* Copyright (C) 2011-2013 Eric Dumazet (eric.dumazet@gmail.com)
* Internal BPF Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
@@ -17,7 +18,7 @@
#include <asm/nospec-branch.h>
/*
- * assembly code in arch/x86/net/bpf_jit.S
+ * Assembly code in arch/x86/net/bpf_jit.S
*/
extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[];
@@ -45,14 +46,15 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
#define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2)
#define EMIT3(b1, b2, b3) EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3)
#define EMIT4(b1, b2, b3, b4) EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4)
+
#define EMIT1_off32(b1, off) \
- do {EMIT1(b1); EMIT(off, 4); } while (0)
+ do { EMIT1(b1); EMIT(off, 4); } while (0)
#define EMIT2_off32(b1, b2, off) \
- do {EMIT2(b1, b2); EMIT(off, 4); } while (0)
+ do { EMIT2(b1, b2); EMIT(off, 4); } while (0)
#define EMIT3_off32(b1, b2, b3, off) \
- do {EMIT3(b1, b2, b3); EMIT(off, 4); } while (0)
+ do { EMIT3(b1, b2, b3); EMIT(off, 4); } while (0)
#define EMIT4_off32(b1, b2, b3, b4, off) \
- do {EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
+ do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
static bool is_imm8(int value)
{
@@ -70,9 +72,10 @@ static bool is_uimm32(u64 value)
}
/* mov dst, src */
-#define EMIT_mov(DST, SRC) \
- do {if (DST != SRC) \
- EMIT3(add_2mod(0x48, DST, SRC), 0x89, add_2reg(0xC0, DST, SRC)); \
+#define EMIT_mov(DST, SRC) \
+ do { \
+ if (DST != SRC) \
+ EMIT3(add_2mod(0x48, DST, SRC), 0x89, add_2reg(0xC0, DST, SRC)); \
} while (0)
static int bpf_size_to_x86_bytes(int bpf_size)
@@ -89,7 +92,8 @@ static int bpf_size_to_x86_bytes(int bpf_size)
return 0;
}
-/* list of x86 cond jumps opcodes (. + s8)
+/*
+ * List of x86 cond jumps opcodes (. + s8)
* Add 0x10 (and an extra 0x0f) to generate far jumps (. + s32)
*/
#define X86_JB 0x72
@@ -106,35 +110,37 @@ static int bpf_size_to_x86_bytes(int bpf_size)
#define CHOOSE_LOAD_FUNC(K, func) \
((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
-/* pick a register outside of BPF range for JIT internal work */
+/* Pick a register outside of BPF range for JIT internal work */
#define AUX_REG (MAX_BPF_JIT_REG + 1)
-/* The following table maps BPF registers to x64 registers.
+/*
+ * The following table maps BPF registers to x86-64 registers.
*
- * x64 register r12 is unused, since if used as base address
+ * x86-64 register R12 is unused, since if used as base address
* register in load/store instructions, it always needs an
* extra byte of encoding and is callee saved.
*
- * r9 caches skb->len - skb->data_len
- * r10 caches skb->data, and used for blinding (if enabled)
+ * R9 caches skb->len - skb->data_len
+ * R10 caches skb->data, and used for blinding (if enabled)
*/
static const int reg2hex[] = {
- [BPF_REG_0] = 0, /* rax */
- [BPF_REG_1] = 7, /* rdi */
- [BPF_REG_2] = 6, /* rsi */
- [BPF_REG_3] = 2, /* rdx */
- [BPF_REG_4] = 1, /* rcx */
- [BPF_REG_5] = 0, /* r8 */
- [BPF_REG_6] = 3, /* rbx callee saved */
- [BPF_REG_7] = 5, /* r13 callee saved */
- [BPF_REG_8] = 6, /* r14 callee saved */
- [BPF_REG_9] = 7, /* r15 callee saved */
- [BPF_REG_FP] = 5, /* rbp readonly */
- [BPF_REG_AX] = 2, /* r10 temp register */
- [AUX_REG] = 3, /* r11 temp register */
+ [BPF_REG_0] = 0, /* RAX */
+ [BPF_REG_1] = 7, /* RDI */
+ [BPF_REG_2] = 6, /* RSI */
+ [BPF_REG_3] = 2, /* RDX */
+ [BPF_REG_4] = 1, /* RCX */
+ [BPF_REG_5] = 0, /* R8 */
+ [BPF_REG_6] = 3, /* RBX callee saved */
+ [BPF_REG_7] = 5, /* R13 callee saved */
+ [BPF_REG_8] = 6, /* R14 callee saved */
+ [BPF_REG_9] = 7, /* R15 callee saved */
+ [BPF_REG_FP] = 5, /* RBP readonly */
+ [BPF_REG_AX] = 2, /* R10 temp register */
+ [AUX_REG] = 3, /* R11 temp register */
};
-/* is_ereg() == true if BPF register 'reg' maps to x64 r8..r15
+/*
+ * is_ereg() == true if BPF register 'reg' maps to x86-64 r8..r15
* which need extra byte of encoding.
* rax,rcx,...,rbp have simpler encoding
*/
@@ -153,7 +159,7 @@ static bool is_axreg(u32 reg)
return reg == BPF_REG_0;
}
-/* add modifiers if 'reg' maps to x64 registers r8..r15 */
+/* Add modifiers if 'reg' maps to x86-64 registers R8..R15 */
static u8 add_1mod(u8 byte, u32 reg)
{
if (is_ereg(reg))
@@ -170,13 +176,13 @@ static u8 add_2mod(u8 byte, u32 r1, u32 r2)
return byte;
}
-/* encode 'dst_reg' register into x64 opcode 'byte' */
+/* Encode 'dst_reg' register into x86-64 opcode 'byte' */
static u8 add_1reg(u8 byte, u32 dst_reg)
{
return byte + reg2hex[dst_reg];
}
-/* encode 'dst_reg' and 'src_reg' registers into x64 opcode 'byte' */
+/* Encode 'dst_reg' and 'src_reg' registers into x86-64 opcode 'byte' */
static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg)
{
return byte + reg2hex[dst_reg] + (reg2hex[src_reg] << 3);
@@ -184,27 +190,28 @@ static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg)
static void jit_fill_hole(void *area, unsigned int size)
{
- /* fill whole space with int3 instructions */
+ /* Fill whole space with INT3 instructions */
memset(area, 0xcc, size);
}
struct jit_context {
- int cleanup_addr; /* epilogue code offset */
+ int cleanup_addr; /* Epilogue code offset */
bool seen_ld_abs;
bool seen_ax_reg;
};
-/* maximum number of bytes emitted while JITing one eBPF insn */
+/* Maximum number of bytes emitted while JITing one eBPF insn */
#define BPF_MAX_INSN_SIZE 128
#define BPF_INSN_SAFETY 64
#define AUX_STACK_SPACE \
- (32 /* space for rbx, r13, r14, r15 */ + \
- 8 /* space for skb_copy_bits() buffer */)
+ (32 /* Space for RBX, R13, R14, R15 */ + \
+ 8 /* Space for skb_copy_bits() buffer */)
#define PROLOGUE_SIZE 37
-/* emit x64 prologue code for BPF program and check it's size.
+/*
+ * Emit x86-64 prologue code for BPF program and check its size.
* bpf_tail_call helper will skip it while jumping into another program
*/
static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
@@ -212,8 +219,11 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
u8 *prog = *pprog;
int cnt = 0;
- EMIT1(0x55); /* push rbp */
- EMIT3(0x48, 0x89, 0xE5); /* mov rbp,rsp */
+ /* push rbp */
+ EMIT1(0x55);
+
+ /* mov rbp,rsp */
+ EMIT3(0x48, 0x89, 0xE5);
/* sub rsp, rounded_stack_depth + AUX_STACK_SPACE */
EMIT3_off32(0x48, 0x81, 0xEC,
@@ -222,14 +232,15 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
/* sub rbp, AUX_STACK_SPACE */
EMIT4(0x48, 0x83, 0xED, AUX_STACK_SPACE);
- /* all classic BPF filters use R6(rbx) save it */
+ /* All classic BPF filters use R6(rbx) save it */
/* mov qword ptr [rbp+0],rbx */
EMIT4(0x48, 0x89, 0x5D, 0);
- /* bpf_convert_filter() maps classic BPF register X to R7 and uses R8
- * as temporary, so all tcpdump filters need to spill/fill R7(r13) and
- * R8(r14). R9(r15) spill could be made conditional, but there is only
+ /*
+ * bpf_convert_filter() maps classic BPF register X to R7 and uses R8
+ * as temporary, so all tcpdump filters need to spill/fill R7(R13) and
+ * R8(R14). R9(R15) spill could be made conditional, but there is only
* one 'bpf_error' return path out of helper functions inside bpf_jit.S
* The overhead of extra spill is negligible for any filter other
* than synthetic ones. Therefore not worth adding complexity.
@@ -243,9 +254,10 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
EMIT4(0x4C, 0x89, 0x7D, 24);
if (!ebpf_from_cbpf) {
- /* Clear the tail call counter (tail_call_cnt): for eBPF tail
+ /*
+ * Clear the tail call counter (tail_call_cnt): for eBPF tail
* calls we need to reset the counter to 0. It's done in two
- * instructions, resetting rax register to 0, and moving it
+ * instructions, resetting RAX register to 0, and moving it
* to the counter location.
*/
@@ -260,7 +272,9 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
*pprog = prog;
}
-/* generate the following code:
+/*
+ * Generate the following code:
+ *
* ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ...
* if (index >= array->map.max_entries)
* goto out;
@@ -278,23 +292,26 @@ static void emit_bpf_tail_call(u8 **pprog)
int label1, label2, label3;
int cnt = 0;
- /* rdi - pointer to ctx
+ /*
+ * rdi - pointer to ctx
* rsi - pointer to bpf_array
* rdx - index in bpf_array
*/
- /* if (index >= array->map.max_entries)
- * goto out;
+ /*
+ * if (index >= array->map.max_entries)
+ * goto out;
*/
EMIT2(0x89, 0xD2); /* mov edx, edx */
EMIT3(0x39, 0x56, /* cmp dword ptr [rsi + 16], edx */
offsetof(struct bpf_array, map.max_entries));
-#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* number of bytes to jump */
+#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* Number of bytes to jump */
EMIT2(X86_JBE, OFFSET1); /* jbe out */
label1 = cnt;
- /* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
- * goto out;
+ /*
+ * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
+ * goto out;
*/
EMIT2_off32(0x8B, 0x85, 36); /* mov eax, dword ptr [rbp + 36] */
EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */
@@ -308,8 +325,9 @@ static void emit_bpf_tail_call(u8 **pprog)
EMIT4_off32(0x48, 0x8B, 0x84, 0xD6, /* mov rax, [rsi + rdx * 8 + offsetof(...)] */
offsetof(struct bpf_array, ptrs));
- /* if (prog == NULL)
- * goto out;
+ /*
+ * if (prog == NULL)
+ * goto out;
*/
EMIT3(0x48, 0x85, 0xC0); /* test rax,rax */
#define OFFSET3 (8 + RETPOLINE_RAX_BPF_JIT_SIZE)
@@ -321,7 +339,8 @@ static void emit_bpf_tail_call(u8 **pprog)
offsetof(struct bpf_prog, bpf_func));
EMIT4(0x48, 0x83, 0xC0, PROLOGUE_SIZE); /* add rax, prologue_size */
- /* now we're ready to jump into next BPF program
+ /*
+ * Wow we're ready to jump into next BPF program
* rdi == ctx (1st arg)
* rax == prog->bpf_func + prologue_size
*/
@@ -340,7 +359,8 @@ static void emit_load_skb_data_hlen(u8 **pprog)
u8 *prog = *pprog;
int cnt = 0;
- /* r9d = skb->len - skb->data_len (headlen)
+ /*
+ * r9d = skb->len - skb->data_len (headlen)
* r10 = skb->data
*/
/* mov %r9d, off32(%rdi) */
@@ -361,7 +381,8 @@ static void emit_mov_imm32(u8 **pprog, bool sign_propagate,
u8 b1, b2, b3;
int cnt = 0;
- /* optimization: if imm32 is positive, use 'mov %eax, imm32'
+ /*
+ * Optimization: if imm32 is positive, use 'mov %eax, imm32'
* (which zero-extends imm32) to save 2 bytes.
*/
if (sign_propagate && (s32)imm32 < 0) {
@@ -373,7 +394,8 @@ static void emit_mov_imm32(u8 **pprog, bool sign_propagate,
goto done;
}
- /* optimization: if imm32 is zero, use 'xor %eax, %eax'
+ /*
+ * Optimization: if imm32 is zero, use 'xor %eax, %eax'
* to save 3 bytes.
*/
if (imm32 == 0) {
@@ -400,7 +422,8 @@ static void emit_mov_imm64(u8 **pprog, u32 dst_reg,
int cnt = 0;
if (is_uimm32(((u64)imm32_hi << 32) | (u32)imm32_lo)) {
- /* For emitting plain u32, where sign bit must not be
+ /*
+ * For emitting plain u32, where sign bit must not be
* propagated LLVM tends to load imm64 over mov32
* directly, so save couple of bytes by just doing
* 'mov %eax, imm32' instead.
@@ -525,7 +548,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
else if (is_ereg(dst_reg))
EMIT1(add_1mod(0x40, dst_reg));
- /* b3 holds 'normal' opcode, b2 short form only valid
+ /*
+ * b3 holds 'normal' opcode, b2 short form only valid
* in case dst is eax/rax.
*/
switch (BPF_OP(insn->code)) {
@@ -593,7 +617,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
/* mov rax, dst_reg */
EMIT_mov(BPF_REG_0, dst_reg);
- /* xor edx, edx
+ /*
+ * xor edx, edx
* equivalent to 'xor rdx, rdx', but one byte less
*/
EMIT2(0x31, 0xd2);
@@ -655,7 +680,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
}
break;
}
- /* shifts */
+ /* Shifts */
case BPF_ALU | BPF_LSH | BPF_K:
case BPF_ALU | BPF_RSH | BPF_K:
case BPF_ALU | BPF_ARSH | BPF_K:
@@ -686,7 +711,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
case BPF_ALU64 | BPF_RSH | BPF_X:
case BPF_ALU64 | BPF_ARSH | BPF_X:
- /* check for bad case when dst_reg == rcx */
+ /* Check for bad case when dst_reg == rcx */
if (dst_reg == BPF_REG_4) {
/* mov r11, dst_reg */
EMIT_mov(AUX_REG, dst_reg);
@@ -724,13 +749,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
case BPF_ALU | BPF_END | BPF_FROM_BE:
switch (imm32) {
case 16:
- /* emit 'ror %ax, 8' to swap lower 2 bytes */
+ /* Emit 'ror %ax, 8' to swap lower 2 bytes */
EMIT1(0x66);
if (is_ereg(dst_reg))
EMIT1(0x41);
EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8);
- /* emit 'movzwl eax, ax' */
+ /* Emit 'movzwl eax, ax' */
if (is_ereg(dst_reg))
EMIT3(0x45, 0x0F, 0xB7);
else
@@ -738,7 +763,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
break;
case 32:
- /* emit 'bswap eax' to swap lower 4 bytes */
+ /* Emit 'bswap eax' to swap lower 4 bytes */
if (is_ereg(dst_reg))
EMIT2(0x41, 0x0F);
else
@@ -746,7 +771,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
EMIT1(add_1reg(0xC8, dst_reg));
break;
case 64:
- /* emit 'bswap rax' to swap 8 bytes */
+ /* Emit 'bswap rax' to swap 8 bytes */
EMIT3(add_1mod(0x48, dst_reg), 0x0F,
add_1reg(0xC8, dst_reg));
break;
@@ -756,7 +781,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
case BPF_ALU | BPF_END | BPF_FROM_LE:
switch (imm32) {
case 16:
- /* emit 'movzwl eax, ax' to zero extend 16-bit
+ /*
+ * Emit 'movzwl eax, ax' to zero extend 16-bit
* into 64 bit
*/
if (is_ereg(dst_reg))
@@ -766,7 +792,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
break;
case 32:
- /* emit 'mov eax, eax' to clear upper 32-bits */
+ /* Emit 'mov eax, eax' to clear upper 32-bits */
if (is_ereg(dst_reg))
EMIT1(0x45);
EMIT2(0x89, add_2reg(0xC0, dst_reg, dst_reg));
@@ -809,9 +835,9 @@ st: if (is_imm8(insn->off))
/* STX: *(u8*)(dst_reg + off) = src_reg */
case BPF_STX | BPF_MEM | BPF_B:
- /* emit 'mov byte ptr [rax + off], al' */
+ /* Emit 'mov byte ptr [rax + off], al' */
if (is_ereg(dst_reg) || is_ereg(src_reg) ||
- /* have to add extra byte for x86 SIL, DIL regs */
+ /* We have to add extra byte for x86 SIL, DIL regs */
src_reg == BPF_REG_1 || src_reg == BPF_REG_2)
EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88);
else
@@ -840,25 +866,26 @@ stx: if (is_imm8(insn->off))
/* LDX: dst_reg = *(u8*)(src_reg + off) */
case BPF_LDX | BPF_MEM | BPF_B:
- /* emit 'movzx rax, byte ptr [rax + off]' */
+ /* Emit 'movzx rax, byte ptr [rax + off]' */
EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6);
goto ldx;
case BPF_LDX | BPF_MEM | BPF_H:
- /* emit 'movzx rax, word ptr [rax + off]' */
+ /* Emit 'movzx rax, word ptr [rax + off]' */
EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7);
goto ldx;
case BPF_LDX | BPF_MEM | BPF_W:
- /* emit 'mov eax, dword ptr [rax+0x14]' */
+ /* Emit 'mov eax, dword ptr [rax+0x14]' */
if (is_ereg(dst_reg) || is_ereg(src_reg))
EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B);
else
EMIT1(0x8B);
goto ldx;
case BPF_LDX | BPF_MEM | BPF_DW:
- /* emit 'mov rax, qword ptr [rax+0x14]' */
+ /* Emit 'mov rax, qword ptr [rax+0x14]' */
EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B);
-ldx: /* if insn->off == 0 we can save one extra byte, but
- * special case of x86 r13 which always needs an offset
+ldx: /*
+ * If insn->off == 0 we can save one extra byte, but
+ * special case of x86 R13 which always needs an offset
* is not worth the hassle
*/
if (is_imm8(insn->off))
@@ -870,7 +897,7 @@ stx: if (is_imm8(insn->off))
/* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */
case BPF_STX | BPF_XADD | BPF_W:
- /* emit 'lock add dword ptr [rax + off], eax' */
+ /* Emit 'lock add dword ptr [rax + off], eax' */
if (is_ereg(dst_reg) || is_ereg(src_reg))
EMIT3(0xF0, add_2mod(0x40, dst_reg, src_reg), 0x01);
else
@@ -897,14 +924,15 @@ xadd: if (is_imm8(insn->off))
} else {
EMIT2(0x41, 0x52); /* push %r10 */
EMIT2(0x41, 0x51); /* push %r9 */
- /* need to adjust jmp offset, since
+ /*
+ * We need to adjust jmp offset, since
* pop %r9, pop %r10 take 4 bytes after call insn
*/
jmp_offset += 4;
}
}
if (!imm32 || !is_simm32(jmp_offset)) {
- pr_err("unsupported bpf func %d addr %p image %p\n",
+ pr_err("unsupported BPF func %d addr %p image %p\n",
imm32, func, image);
return -EINVAL;
}
@@ -970,7 +998,7 @@ xadd: if (is_imm8(insn->off))
else
EMIT2_off32(0x81, add_1reg(0xF8, dst_reg), imm32);
-emit_cond_jmp: /* convert BPF opcode to x86 */
+emit_cond_jmp: /* Convert BPF opcode to x86 */
switch (BPF_OP(insn->code)) {
case BPF_JEQ:
jmp_cond = X86_JE;
@@ -996,22 +1024,22 @@ xadd: if (is_imm8(insn->off))
jmp_cond = X86_JBE;
break;
case BPF_JSGT:
- /* signed '>', GT in x86 */
+ /* Signed '>', GT in x86 */
jmp_cond = X86_JG;
break;
case BPF_JSLT:
- /* signed '<', LT in x86 */
+ /* Signed '<', LT in x86 */
jmp_cond = X86_JL;
break;
case BPF_JSGE:
- /* signed '>=', GE in x86 */
+ /* Signed '>=', GE in x86 */
jmp_cond = X86_JGE;
break;
case BPF_JSLE:
- /* signed '<=', LE in x86 */
+ /* Signed '<=', LE in x86 */
jmp_cond = X86_JLE;
break;
- default: /* to silence gcc warning */
+ default: /* to silence GCC warning */
return -EFAULT;
}
jmp_offset = addrs[i + insn->off] - addrs[i];
@@ -1027,9 +1055,19 @@ xadd: if (is_imm8(insn->off))
break;
case BPF_JMP | BPF_JA:
- jmp_offset = addrs[i + insn->off] - addrs[i];
+ if (insn->off == -1)
+ /* -1 jmp instructions will always jump
+ * backwards two bytes. Explicitly handling
+ * this case avoids wasting too many passes
+ * when there are long sequences of replaced
+ * dead code.
+ */
+ jmp_offset = -2;
+ else
+ jmp_offset = addrs[i + insn->off] - addrs[i];
+
if (!jmp_offset)
- /* optimize out nop jumps */
+ /* Optimize out nop jumps */
break;
emit_jmp:
if (is_imm8(jmp_offset)) {
@@ -1051,7 +1089,7 @@ xadd: if (is_imm8(insn->off))
ctx->seen_ld_abs = seen_ld_abs = true;
jmp_offset = func - (image + addrs[i]);
if (!func || !is_simm32(jmp_offset)) {
- pr_err("unsupported bpf func %d addr %p image %p\n",
+ pr_err("unsupported BPF func %d addr %p image %p\n",
imm32, func, image);
return -EINVAL;
}
@@ -1070,7 +1108,8 @@ xadd: if (is_imm8(insn->off))
EMIT2_off32(0x81, 0xC6, imm32);
}
}
- /* skb pointer is in R6 (%rbx), it will be copied into
+ /*
+ * skb pointer is in R6 (%rbx), it will be copied into
* %rdi if skb_copy_bits() call is necessary.
* sk_load_* helpers also use %r10 and %r9d.
* See bpf_jit.S
@@ -1101,7 +1140,7 @@ xadd: if (is_imm8(insn->off))
goto emit_jmp;
}
seen_exit = true;
- /* update cleanup_addr */
+ /* Update cleanup_addr */
ctx->cleanup_addr = proglen;
/* mov rbx, qword ptr [rbp+0] */
EMIT4(0x48, 0x8B, 0x5D, 0);
@@ -1119,10 +1158,11 @@ xadd: if (is_imm8(insn->off))
break;
default:
- /* By design x64 JIT should support all BPF instructions
+ /*
+ * By design x86-64 JIT should support all BPF instructions.
* This error will be seen if new instruction was added
- * to interpreter, but not to JIT
- * or if there is junk in bpf_prog
+ * to the interpreter, but not to the JIT, or if there is
+ * junk in bpf_prog.
*/
pr_err("bpf_jit: unknown opcode %02x\n", insn->code);
return -EINVAL;
@@ -1174,7 +1214,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
return orig_prog;
tmp = bpf_jit_blind_constants(prog);
- /* If blinding was requested and we failed during blinding,
+ /*
+ * If blinding was requested and we failed during blinding,
* we must fall back to the interpreter.
*/
if (IS_ERR(tmp))
@@ -1208,8 +1249,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
goto out_addrs;
}
- /* Before first pass, make a rough estimation of addrs[]
- * each bpf instruction is translated to less than 64 bytes
+ /*
+ * Before first pass, make a rough estimation of addrs[]
+ * each BPF instruction is translated to less than 64 bytes
*/
for (proglen = 0, i = 0; i < prog->len; i++) {
proglen += 64;
@@ -1218,14 +1260,16 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
ctx.cleanup_addr = proglen;
skip_init_addrs:
- /* JITed image shrinks with every pass and the loop iterates
- * until the image stops shrinking. Very large bpf programs
+ /*
+ * JITed image shrinks with every pass and the loop iterates
+ * until the image stops shrinking. Very large BPF programs
* may converge on the last pass. In such case do one more
- * pass to emit the final image
+ * pass to emit the final image.
*/
for (pass = 0; pass < 20 || image; pass++) {
proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
if (proglen <= 0) {
+out_image:
image = NULL;
if (header)
bpf_jit_binary_free(header);
@@ -1236,8 +1280,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
if (proglen != oldproglen) {
pr_err("bpf_jit: proglen=%d != oldproglen=%d\n",
proglen, oldproglen);
- prog = orig_prog;
- goto out_addrs;
+ goto out_image;
}
break;
}
@@ -1273,7 +1316,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
prog = orig_prog;
}
- if (!prog->is_func || extra_pass) {
+ if (!image || !prog->is_func || extra_pass) {
out_addrs:
kfree(addrs);
kfree(jit_data);
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index bed7e7f..e01f7ce 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -225,7 +225,7 @@ int __init efi_alloc_page_tables(void)
pud = pud_alloc(&init_mm, p4d, EFI_VA_END);
if (!pud) {
- if (pgtable_l5_enabled)
+ if (pgtable_l5_enabled())
free_page((unsigned long) pgd_page_vaddr(*pgd));
free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
return -ENOMEM;
diff --git a/arch/x86/platform/intel-mid/intel_mid_vrtc.c b/arch/x86/platform/intel-mid/intel_mid_vrtc.c
index 5802486..a52914a 100644
--- a/arch/x86/platform/intel-mid/intel_mid_vrtc.c
+++ b/arch/x86/platform/intel-mid/intel_mid_vrtc.c
@@ -57,7 +57,7 @@ void vrtc_cmos_write(unsigned char val, unsigned char reg)
}
EXPORT_SYMBOL_GPL(vrtc_cmos_write);
-void vrtc_get_time(struct timespec *now)
+void vrtc_get_time(struct timespec64 *now)
{
u8 sec, min, hour, mday, mon;
unsigned long flags;
@@ -83,18 +83,18 @@ void vrtc_get_time(struct timespec *now)
pr_info("vRTC: sec: %d min: %d hour: %d day: %d "
"mon: %d year: %d\n", sec, min, hour, mday, mon, year);
- now->tv_sec = mktime(year, mon, mday, hour, min, sec);
+ now->tv_sec = mktime64(year, mon, mday, hour, min, sec);
now->tv_nsec = 0;
}
-int vrtc_set_mmss(const struct timespec *now)
+int vrtc_set_mmss(const struct timespec64 *now)
{
unsigned long flags;
struct rtc_time tm;
int year;
int retval = 0;
- rtc_time_to_tm(now->tv_sec, &tm);
+ rtc_time64_to_tm(now->tv_sec, &tm);
if (!rtc_valid_tm(&tm) && tm.tm_year >= 72) {
/*
* tm.year is the number of years since 1900, and the
@@ -110,8 +110,8 @@ int vrtc_set_mmss(const struct timespec *now)
vrtc_cmos_write(tm.tm_sec, RTC_SECONDS);
spin_unlock_irqrestore(&rtc_lock, flags);
} else {
- pr_err("%s: Invalid vRTC value: write of %lx to vRTC failed\n",
- __func__, now->tv_sec);
+ pr_err("%s: Invalid vRTC value: write of %llx to vRTC failed\n",
+ __func__, (s64)now->tv_sec);
retval = -EINVAL;
}
return retval;
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 48b14b5..67ccf64 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -72,7 +72,7 @@ static int set_up_temporary_text_mapping(pgd_t *pgd)
* tables used by the image kernel.
*/
- if (pgtable_l5_enabled) {
+ if (pgtable_l5_enabled()) {
p4d = (p4d_t *)get_safe_page(GFP_ATOMIC);
if (!p4d)
return -ENOMEM;
@@ -98,7 +98,7 @@ static int set_up_temporary_text_mapping(pgd_t *pgd)
set_pgd(pgd + pgd_index(restore_jump_address), new_pgd);
} else {
/* No p4d for 4-level paging: point the pgd to the pud page table */
- pgd_t new_pgd = __pgd(__pa(p4d) | pgprot_val(pgtable_prot));
+ pgd_t new_pgd = __pgd(__pa(pud) | pgprot_val(pgtable_prot));
set_pgd(pgd + pgd_index(restore_jump_address), new_pgd);
}
diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
index 1000335..b2d6967 100644
--- a/arch/x86/um/vdso/Makefile
+++ b/arch/x86/um/vdso/Makefile
@@ -23,14 +23,14 @@
targets += vdso.so vdso.so.dbg vdso.lds $(vobjs-y)
-export CPPFLAGS_vdso.lds += -P -C
+CPPFLAGS_vdso.lds += -P -C
VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
-Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
$(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so
-$(obj)/vdso.so.dbg: $(src)/vdso.lds $(vobjs) FORCE
+$(obj)/vdso.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE
$(call if_changed,vdso)
$(obj)/%.so: OBJCOPYFLAGS := -S
diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c
index a18703b..1804b27 100644
--- a/arch/x86/xen/efi.c
+++ b/arch/x86/xen/efi.c
@@ -115,6 +115,61 @@ static efi_system_table_t __init *xen_efi_probe(void)
return &efi_systab_xen;
}
+/*
+ * Determine whether we're in secure boot mode.
+ *
+ * Please keep the logic in sync with
+ * drivers/firmware/efi/libstub/secureboot.c:efi_get_secureboot().
+ */
+static enum efi_secureboot_mode xen_efi_get_secureboot(void)
+{
+ static efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
+ static efi_guid_t shim_guid = EFI_SHIM_LOCK_GUID;
+ efi_status_t status;
+ u8 moksbstate, secboot, setupmode;
+ unsigned long size;
+
+ size = sizeof(secboot);
+ status = efi.get_variable(L"SecureBoot", &efi_variable_guid,
+ NULL, &size, &secboot);
+
+ if (status == EFI_NOT_FOUND)
+ return efi_secureboot_mode_disabled;
+
+ if (status != EFI_SUCCESS)
+ goto out_efi_err;
+
+ size = sizeof(setupmode);
+ status = efi.get_variable(L"SetupMode", &efi_variable_guid,
+ NULL, &size, &setupmode);
+
+ if (status != EFI_SUCCESS)
+ goto out_efi_err;
+
+ if (secboot == 0 || setupmode == 1)
+ return efi_secureboot_mode_disabled;
+
+ /* See if a user has put the shim into insecure mode. */
+ size = sizeof(moksbstate);
+ status = efi.get_variable(L"MokSBStateRT", &shim_guid,
+ NULL, &size, &moksbstate);
+
+ /* If it fails, we don't care why. Default to secure. */
+ if (status != EFI_SUCCESS)
+ goto secure_boot_enabled;
+
+ if (moksbstate == 1)
+ return efi_secureboot_mode_disabled;
+
+ secure_boot_enabled:
+ pr_info("UEFI Secure Boot is enabled.\n");
+ return efi_secureboot_mode_enabled;
+
+ out_efi_err:
+ pr_err("Could not determine UEFI Secure Boot status.\n");
+ return efi_secureboot_mode_unknown;
+}
+
void __init xen_efi_init(void)
{
efi_system_table_t *efi_systab_xen;
@@ -129,6 +184,8 @@ void __init xen_efi_init(void)
boot_params.efi_info.efi_systab = (__u32)__pa(efi_systab_xen);
boot_params.efi_info.efi_systab_hi = (__u32)(__pa(efi_systab_xen) >> 32);
+ boot_params.secure_boot = xen_efi_get_secureboot();
+
set_bit(EFI_BOOT, &efi.flags);
set_bit(EFI_PARAVIRT, &efi.flags);
set_bit(EFI_64BIT, &efi.flags);
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 8268987..19c1ff5 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -65,6 +65,19 @@ static void __init xen_hvm_init_mem_mapping(void)
{
early_memunmap(HYPERVISOR_shared_info, PAGE_SIZE);
HYPERVISOR_shared_info = __va(PFN_PHYS(shared_info_pfn));
+
+ /*
+ * The virtual address of the shared_info page has changed, so
+ * the vcpu_info pointer for VCPU 0 is now stale.
+ *
+ * The prepare_boot_cpu callback will re-initialize it via
+ * xen_vcpu_setup, but we can't rely on that to be called for
+ * old Xen versions (xen_have_vector_callback == 0).
+ *
+ * It is, in any case, bad to have a stale vcpu_info pointer
+ * so reset it now.
+ */
+ xen_vcpu_info_reset(0);
}
static void __init init_hvm_pv_info(void)
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index c36d23a..357969a 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -421,45 +421,33 @@ static void xen_load_gdt(const struct desc_ptr *dtr)
{
unsigned long va = dtr->address;
unsigned int size = dtr->size + 1;
- unsigned pages = DIV_ROUND_UP(size, PAGE_SIZE);
- unsigned long frames[pages];
- int f;
+ unsigned long pfn, mfn;
+ int level;
+ pte_t *ptep;
+ void *virt;
- /*
- * A GDT can be up to 64k in size, which corresponds to 8192
- * 8-byte entries, or 16 4k pages..
- */
-
- BUG_ON(size > 65536);
+ /* @size should be at most GDT_SIZE which is smaller than PAGE_SIZE. */
+ BUG_ON(size > PAGE_SIZE);
BUG_ON(va & ~PAGE_MASK);
- for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) {
- int level;
- pte_t *ptep;
- unsigned long pfn, mfn;
- void *virt;
+ /*
+ * The GDT is per-cpu and is in the percpu data area.
+ * That can be virtually mapped, so we need to do a
+ * page-walk to get the underlying MFN for the
+ * hypercall. The page can also be in the kernel's
+ * linear range, so we need to RO that mapping too.
+ */
+ ptep = lookup_address(va, &level);
+ BUG_ON(ptep == NULL);
- /*
- * The GDT is per-cpu and is in the percpu data area.
- * That can be virtually mapped, so we need to do a
- * page-walk to get the underlying MFN for the
- * hypercall. The page can also be in the kernel's
- * linear range, so we need to RO that mapping too.
- */
- ptep = lookup_address(va, &level);
- BUG_ON(ptep == NULL);
+ pfn = pte_pfn(*ptep);
+ mfn = pfn_to_mfn(pfn);
+ virt = __va(PFN_PHYS(pfn));
- pfn = pte_pfn(*ptep);
- mfn = pfn_to_mfn(pfn);
- virt = __va(PFN_PHYS(pfn));
+ make_lowmem_page_readonly((void *)va);
+ make_lowmem_page_readonly(virt);
- frames[f] = mfn;
-
- make_lowmem_page_readonly((void *)va);
- make_lowmem_page_readonly(virt);
- }
-
- if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct)))
+ if (HYPERVISOR_set_gdt(&mfn, size / sizeof(struct desc_struct)))
BUG();
}
@@ -470,34 +458,22 @@ static void __init xen_load_gdt_boot(const struct desc_ptr *dtr)
{
unsigned long va = dtr->address;
unsigned int size = dtr->size + 1;
- unsigned pages = DIV_ROUND_UP(size, PAGE_SIZE);
- unsigned long frames[pages];
- int f;
+ unsigned long pfn, mfn;
+ pte_t pte;
- /*
- * A GDT can be up to 64k in size, which corresponds to 8192
- * 8-byte entries, or 16 4k pages..
- */
-
- BUG_ON(size > 65536);
+ /* @size should be at most GDT_SIZE which is smaller than PAGE_SIZE. */
+ BUG_ON(size > PAGE_SIZE);
BUG_ON(va & ~PAGE_MASK);
- for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) {
- pte_t pte;
- unsigned long pfn, mfn;
+ pfn = virt_to_pfn(va);
+ mfn = pfn_to_mfn(pfn);
- pfn = virt_to_pfn(va);
- mfn = pfn_to_mfn(pfn);
+ pte = pfn_pte(pfn, PAGE_KERNEL_RO);
- pte = pfn_pte(pfn, PAGE_KERNEL_RO);
+ if (HYPERVISOR_update_va_mapping((unsigned long)va, pte, 0))
+ BUG();
- if (HYPERVISOR_update_va_mapping((unsigned long)va, pte, 0))
- BUG();
-
- frames[f] = mfn;
- }
-
- if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct)))
+ if (HYPERVISOR_set_gdt(&mfn, size / sizeof(struct desc_struct)))
BUG();
}
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index d33e7db..2d76106 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -42,13 +42,11 @@ xmaddr_t arbitrary_virt_to_machine(void *vaddr)
}
EXPORT_SYMBOL_GPL(arbitrary_virt_to_machine);
-static void xen_flush_tlb_all(void)
+static noinline void xen_flush_tlb_all(void)
{
struct mmuext_op *op;
struct multicall_space mcs;
- trace_xen_mmu_flush_tlb_all(0);
-
preempt_disable();
mcs = xen_mc_entry(sizeof(*op));
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 486c0a3..2c30cab 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1310,13 +1310,11 @@ unsigned long xen_read_cr2_direct(void)
return this_cpu_read(xen_vcpu_info.arch.cr2);
}
-static void xen_flush_tlb(void)
+static noinline void xen_flush_tlb(void)
{
struct mmuext_op *op;
struct multicall_space mcs;
- trace_xen_mmu_flush_tlb(0);
-
preempt_disable();
mcs = xen_mc_entry(sizeof(*op));
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 29163c4..e0f1bcf 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -57,7 +57,7 @@ static u64 xen_clocksource_get_cycles(struct clocksource *cs)
return xen_clocksource_read();
}
-static void xen_read_wallclock(struct timespec *ts)
+static void xen_read_wallclock(struct timespec64 *ts)
{
struct shared_info *s = HYPERVISOR_shared_info;
struct pvclock_wall_clock *wall_clock = &(s->wc);
@@ -68,12 +68,12 @@ static void xen_read_wallclock(struct timespec *ts)
put_cpu_var(xen_vcpu);
}
-static void xen_get_wallclock(struct timespec *now)
+static void xen_get_wallclock(struct timespec64 *now)
{
xen_read_wallclock(now);
}
-static int xen_set_wallclock(const struct timespec *now)
+static int xen_set_wallclock(const struct timespec64 *now)
{
return -ENODEV;
}
@@ -461,7 +461,7 @@ static void __init xen_time_init(void)
{
struct pvclock_vcpu_time_info *pvti;
int cpu = smp_processor_id();
- struct timespec tp;
+ struct timespec64 tp;
/* As Dom0 is never moved, no penalty on using TSC there */
if (xen_initial_domain())
@@ -479,7 +479,7 @@ static void __init xen_time_init(void)
/* Set initial system time with full resolution */
xen_read_wallclock(&tp);
- do_settimeofday(&tp);
+ do_settimeofday64(&tp);
setup_force_cpu_cap(X86_FEATURE_TSC);
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index c921e8b..17df3322 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -19,7 +19,6 @@
select HAVE_ARCH_KASAN if MMU
select HAVE_CC_STACKPROTECTOR
select HAVE_DEBUG_KMEMLEAK
- select HAVE_DMA_API_DEBUG
select HAVE_DMA_CONTIGUOUS
select HAVE_EXIT_THREAD
select HAVE_FUNCTION_TRACER
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 436b203..e5e1e61 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -1,4 +1,5 @@
generic-y += bug.h
+generic-y += compat.h
generic-y += device.h
generic-y += div64.h
generic-y += dma-contiguous.h
diff --git a/arch/xtensa/include/asm/pci.h b/arch/xtensa/include/asm/pci.h
index d5a8215..6ddf0a3 100644
--- a/arch/xtensa/include/asm/pci.h
+++ b/arch/xtensa/include/asm/pci.h
@@ -42,8 +42,6 @@ extern struct pci_controller* pcibios_alloc_controller(void);
* decisions.
*/
-#define PCI_DMA_BUS_IS_PHYS (1)
-
/* Tell PCI code what kind of PCI resource mappings we support */
#define HAVE_PCI_MMAP 1
#define ARCH_GENERIC_PCI_MMAP_RESOURCE 1
diff --git a/arch/xtensa/include/uapi/asm/msgbuf.h b/arch/xtensa/include/uapi/asm/msgbuf.h
index 36e2e10..d6915e9 100644
--- a/arch/xtensa/include/uapi/asm/msgbuf.h
+++ b/arch/xtensa/include/uapi/asm/msgbuf.h
@@ -7,7 +7,6 @@
* between kernel and user space.
*
* Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
* - 2 miscellaneous 32-bit values
*
* This file is subject to the terms and conditions of the GNU General
@@ -21,19 +20,19 @@
struct msqid64_ds {
struct ipc64_perm msg_perm;
#ifdef __XTENSA_EB__
- unsigned int __unused1;
- __kernel_time_t msg_stime; /* last msgsnd time */
- unsigned int __unused2;
- __kernel_time_t msg_rtime; /* last msgrcv time */
- unsigned int __unused3;
- __kernel_time_t msg_ctime; /* last change time */
+ unsigned long msg_stime_high;
+ unsigned long msg_stime; /* last msgsnd time */
+ unsigned long msg_rtime_high;
+ unsigned long msg_rtime; /* last msgrcv time */
+ unsigned long msg_ctime_high;
+ unsigned long msg_ctime; /* last change time */
#elif defined(__XTENSA_EL__)
- __kernel_time_t msg_stime; /* last msgsnd time */
- unsigned int __unused1;
- __kernel_time_t msg_rtime; /* last msgrcv time */
- unsigned int __unused2;
- __kernel_time_t msg_ctime; /* last change time */
- unsigned int __unused3;
+ unsigned long msg_stime; /* last msgsnd time */
+ unsigned long msg_stime_high;
+ unsigned long msg_rtime; /* last msgrcv time */
+ unsigned long msg_rtime_high;
+ unsigned long msg_ctime; /* last change time */
+ unsigned long msg_ctime_high;
#else
# error processor byte order undefined!
#endif
diff --git a/arch/xtensa/include/uapi/asm/sembuf.h b/arch/xtensa/include/uapi/asm/sembuf.h
index f61b633..09f348d 100644
--- a/arch/xtensa/include/uapi/asm/sembuf.h
+++ b/arch/xtensa/include/uapi/asm/sembuf.h
@@ -14,7 +14,6 @@
* between kernel and user space.
*
* Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
* - 2 miscellaneous 32-bit values
*
*/
@@ -27,15 +26,15 @@
struct semid64_ds {
struct ipc64_perm sem_perm; /* permissions .. see ipc.h */
#ifdef __XTENSA_EL__
- __kernel_time_t sem_otime; /* last semop time */
- unsigned long __unused1;
- __kernel_time_t sem_ctime; /* last change time */
- unsigned long __unused2;
+ unsigned long sem_otime; /* last semop time */
+ unsigned long sem_otime_high;
+ unsigned long sem_ctime; /* last change time */
+ unsigned long sem_ctime_high;
#else
- unsigned long __unused1;
- __kernel_time_t sem_otime; /* last semop time */
- unsigned long __unused2;
- __kernel_time_t sem_ctime; /* last change time */
+ unsigned long sem_otime_high;
+ unsigned long sem_otime; /* last semop time */
+ unsigned long sem_ctime_high;
+ unsigned long sem_ctime; /* last change time */
#endif
unsigned long sem_nsems; /* no. of semaphores in array */
unsigned long __unused3;
diff --git a/arch/xtensa/include/uapi/asm/shmbuf.h b/arch/xtensa/include/uapi/asm/shmbuf.h
index 26550bd..554a57a 100644
--- a/arch/xtensa/include/uapi/asm/shmbuf.h
+++ b/arch/xtensa/include/uapi/asm/shmbuf.h
@@ -4,10 +4,10 @@
*
* The shmid64_ds structure for Xtensa architecture.
* Note extra padding because this structure is passed back and forth
- * between kernel and user space.
+ * between kernel and user space, but the padding is on the wrong
+ * side for big-endian xtensa, for historic reasons.
*
* Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
* - 2 miscellaneous 32-bit values
*
* This file is subject to the terms and conditions of the GNU General Public
@@ -20,42 +20,21 @@
#ifndef _XTENSA_SHMBUF_H
#define _XTENSA_SHMBUF_H
-#if defined (__XTENSA_EL__)
struct shmid64_ds {
struct ipc64_perm shm_perm; /* operation perms */
size_t shm_segsz; /* size of segment (bytes) */
- __kernel_time_t shm_atime; /* last attach time */
- unsigned long __unused1;
- __kernel_time_t shm_dtime; /* last detach time */
- unsigned long __unused2;
- __kernel_time_t shm_ctime; /* last change time */
- unsigned long __unused3;
+ unsigned long shm_atime; /* last attach time */
+ unsigned long shm_atime_high;
+ unsigned long shm_dtime; /* last detach time */
+ unsigned long shm_dtime_high;
+ unsigned long shm_ctime; /* last change time */
+ unsigned long shm_ctime_high;
__kernel_pid_t shm_cpid; /* pid of creator */
__kernel_pid_t shm_lpid; /* pid of last operator */
unsigned long shm_nattch; /* no. of current attaches */
unsigned long __unused4;
unsigned long __unused5;
};
-#elif defined (__XTENSA_EB__)
-struct shmid64_ds {
- struct ipc64_perm shm_perm; /* operation perms */
- size_t shm_segsz; /* size of segment (bytes) */
- __kernel_time_t shm_atime; /* last attach time */
- unsigned long __unused1;
- __kernel_time_t shm_dtime; /* last detach time */
- unsigned long __unused2;
- __kernel_time_t shm_ctime; /* last change time */
- unsigned long __unused3;
- __kernel_pid_t shm_cpid; /* pid of creator */
- __kernel_pid_t shm_lpid; /* pid of last operator */
- unsigned long shm_nattch; /* no. of current attaches */
- unsigned long __unused4;
- unsigned long __unused5;
-};
-#else
-# error endian order not defined
-#endif
-
struct shminfo64 {
unsigned long shmmax;
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index 732631c..392b4a8 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -261,12 +261,3 @@ const struct dma_map_ops xtensa_dma_map_ops = {
.mapping_error = xtensa_dma_mapping_error,
};
EXPORT_SYMBOL(xtensa_dma_map_ops);
-
-#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-
-static int __init xtensa_dma_init(void)
-{
- dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
- return 0;
-}
-fs_initcall(xtensa_dma_init);
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index 32c5207..86507fa 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -323,8 +323,6 @@ do_illegal_instruction(struct pt_regs *regs)
void
do_unaligned_user (struct pt_regs *regs)
{
- siginfo_t info;
-
__die_if_kernel("Unhandled unaligned exception in kernel",
regs, SIGKILL);
@@ -334,12 +332,7 @@ do_unaligned_user (struct pt_regs *regs)
"(pid = %d, pc = %#010lx)\n",
regs->excvaddr, current->comm,
task_pid_nr(current), regs->pc);
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_ADRALN;
- info.si_addr = (void *) regs->excvaddr;
- force_sig_info(SIGSEGV, &info, current);
-
+ force_sig_fault(SIGBUS, BUS_ADRALN, (void *) regs->excvaddr, current);
}
#endif
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 8b9b6f4..c111a83 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -39,13 +39,13 @@ void do_page_fault(struct pt_regs *regs)
struct mm_struct *mm = current->mm;
unsigned int exccause = regs->exccause;
unsigned int address = regs->excvaddr;
- siginfo_t info;
+ int code;
int is_write, is_exec;
int fault;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
- info.si_code = SEGV_MAPERR;
+ code = SEGV_MAPERR;
/* We fault-in kernel-space virtual memory on-demand. The
* 'reference' page table is init_mm.pgd.
@@ -91,7 +91,7 @@ void do_page_fault(struct pt_regs *regs)
*/
good_area:
- info.si_code = SEGV_ACCERR;
+ code = SEGV_ACCERR;
if (is_write) {
if (!(vma->vm_flags & VM_WRITE))
@@ -157,11 +157,7 @@ void do_page_fault(struct pt_regs *regs)
if (user_mode(regs)) {
current->thread.bad_vaddr = address;
current->thread.error_code = is_write;
- info.si_signo = SIGSEGV;
- info.si_errno = 0;
- /* info.si_code has been set above */
- info.si_addr = (void *) address;
- force_sig_info(SIGSEGV, &info, current);
+ force_sig_fault(SIGSEGV, code, (void *) address, current);
return;
}
bad_page_fault(regs, address, SIGSEGV);
@@ -186,11 +182,7 @@ void do_page_fault(struct pt_regs *regs)
* or user mode.
*/
current->thread.bad_vaddr = address;
- info.si_code = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_ADRERR;
- info.si_addr = (void *) address;
- force_sig_info(SIGBUS, &info, current);
+ force_sig_fault(SIGBUS, BUS_ADRERR, (void *) address, current);
/* Kernel mode? Handle exceptions or die */
if (!user_mode(regs))
diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c
index 92f567f..af81a62 100644
--- a/arch/xtensa/platforms/iss/console.c
+++ b/arch/xtensa/platforms/iss/console.c
@@ -153,19 +153,6 @@ static int rs_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int rs_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, rs_proc_show, NULL);
-}
-
-static const struct file_operations rs_proc_fops = {
- .owner = THIS_MODULE,
- .open = rs_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static const struct tty_operations serial_ops = {
.open = rs_open,
.close = rs_close,
@@ -176,7 +163,7 @@ static const struct tty_operations serial_ops = {
.chars_in_buffer = rs_chars_in_buffer,
.hangup = rs_hangup,
.wait_until_sent = rs_wait_until_sent,
- .proc_fops = &rs_proc_fops,
+ .proc_show = rs_proc_show,
};
int __init rs_init(void)
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index d819dc7..a9e8633 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -55,13 +55,13 @@ BFQG_FLAG_FNS(empty)
/* This should be called with the scheduler lock held. */
static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
{
- unsigned long long now;
+ u64 now;
if (!bfqg_stats_waiting(stats))
return;
- now = sched_clock();
- if (time_after64(now, stats->start_group_wait_time))
+ now = ktime_get_ns();
+ if (now > stats->start_group_wait_time)
blkg_stat_add(&stats->group_wait_time,
now - stats->start_group_wait_time);
bfqg_stats_clear_waiting(stats);
@@ -77,20 +77,20 @@ static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
return;
if (bfqg == curr_bfqg)
return;
- stats->start_group_wait_time = sched_clock();
+ stats->start_group_wait_time = ktime_get_ns();
bfqg_stats_mark_waiting(stats);
}
/* This should be called with the scheduler lock held. */
static void bfqg_stats_end_empty_time(struct bfqg_stats *stats)
{
- unsigned long long now;
+ u64 now;
if (!bfqg_stats_empty(stats))
return;
- now = sched_clock();
- if (time_after64(now, stats->start_empty_time))
+ now = ktime_get_ns();
+ if (now > stats->start_empty_time)
blkg_stat_add(&stats->empty_time,
now - stats->start_empty_time);
bfqg_stats_clear_empty(stats);
@@ -116,7 +116,7 @@ void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg)
if (bfqg_stats_empty(stats))
return;
- stats->start_empty_time = sched_clock();
+ stats->start_empty_time = ktime_get_ns();
bfqg_stats_mark_empty(stats);
}
@@ -125,9 +125,9 @@ void bfqg_stats_update_idle_time(struct bfq_group *bfqg)
struct bfqg_stats *stats = &bfqg->stats;
if (bfqg_stats_idling(stats)) {
- unsigned long long now = sched_clock();
+ u64 now = ktime_get_ns();
- if (time_after64(now, stats->start_idle_time))
+ if (now > stats->start_idle_time)
blkg_stat_add(&stats->idle_time,
now - stats->start_idle_time);
bfqg_stats_clear_idling(stats);
@@ -138,7 +138,7 @@ void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg)
{
struct bfqg_stats *stats = &bfqg->stats;
- stats->start_idle_time = sched_clock();
+ stats->start_idle_time = ktime_get_ns();
bfqg_stats_mark_idling(stats);
}
@@ -171,18 +171,18 @@ void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op)
blkg_rwstat_add(&bfqg->stats.merged, op, 1);
}
-void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
- uint64_t io_start_time, unsigned int op)
+void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns,
+ u64 io_start_time_ns, unsigned int op)
{
struct bfqg_stats *stats = &bfqg->stats;
- unsigned long long now = sched_clock();
+ u64 now = ktime_get_ns();
- if (time_after64(now, io_start_time))
+ if (now > io_start_time_ns)
blkg_rwstat_add(&stats->service_time, op,
- now - io_start_time);
- if (time_after64(io_start_time, start_time))
+ now - io_start_time_ns);
+ if (io_start_time_ns > start_time_ns)
blkg_rwstat_add(&stats->wait_time, op,
- io_start_time - start_time);
+ io_start_time_ns - start_time_ns);
}
#else /* CONFIG_BFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */
@@ -191,8 +191,8 @@ void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
unsigned int op) { }
void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op) { }
void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op) { }
-void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
- uint64_t io_start_time, unsigned int op) { }
+void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns,
+ u64 io_start_time_ns, unsigned int op) { }
void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { }
void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { }
void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { }
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index f0ecd98..495b9dd 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -49,9 +49,39 @@
*
* In particular, to provide these low-latency guarantees, BFQ
* explicitly privileges the I/O of two classes of time-sensitive
- * applications: interactive and soft real-time. This feature enables
- * BFQ to provide applications in these classes with a very low
- * latency. Finally, BFQ also features additional heuristics for
+ * applications: interactive and soft real-time. In more detail, BFQ
+ * behaves this way if the low_latency parameter is set (default
+ * configuration). This feature enables BFQ to provide applications in
+ * these classes with a very low latency.
+ *
+ * To implement this feature, BFQ constantly tries to detect whether
+ * the I/O requests in a bfq_queue come from an interactive or a soft
+ * real-time application. For brevity, in these cases, the queue is
+ * said to be interactive or soft real-time. In both cases, BFQ
+ * privileges the service of the queue, over that of non-interactive
+ * and non-soft-real-time queues. This privileging is performed,
+ * mainly, by raising the weight of the queue. So, for brevity, we
+ * call just weight-raising periods the time periods during which a
+ * queue is privileged, because deemed interactive or soft real-time.
+ *
+ * The detection of soft real-time queues/applications is described in
+ * detail in the comments on the function
+ * bfq_bfqq_softrt_next_start. On the other hand, the detection of an
+ * interactive queue works as follows: a queue is deemed interactive
+ * if it is constantly non empty only for a limited time interval,
+ * after which it does become empty. The queue may be deemed
+ * interactive again (for a limited time), if it restarts being
+ * constantly non empty, provided that this happens only after the
+ * queue has remained empty for a given minimum idle time.
+ *
+ * By default, BFQ computes automatically the above maximum time
+ * interval, i.e., the time interval after which a constantly
+ * non-empty queue stops being deemed interactive. Since a queue is
+ * weight-raised while it is deemed interactive, this maximum time
+ * interval happens to coincide with the (maximum) duration of the
+ * weight-raising for interactive queues.
+ *
+ * Finally, BFQ also features additional heuristics for
* preserving both a low latency and a high throughput on NCQ-capable,
* rotational or flash-based devices, and to get the job done quickly
* for applications consisting in many I/O-bound processes.
@@ -61,14 +91,14 @@
* all low-latency heuristics for that device, by setting low_latency
* to 0.
*
- * BFQ is described in [1], where also a reference to the initial, more
- * theoretical paper on BFQ can be found. The interested reader can find
- * in the latter paper full details on the main algorithm, as well as
- * formulas of the guarantees and formal proofs of all the properties.
- * With respect to the version of BFQ presented in these papers, this
- * implementation adds a few more heuristics, such as the one that
- * guarantees a low latency to soft real-time applications, and a
- * hierarchical extension based on H-WF2Q+.
+ * BFQ is described in [1], where also a reference to the initial,
+ * more theoretical paper on BFQ can be found. The interested reader
+ * can find in the latter paper full details on the main algorithm, as
+ * well as formulas of the guarantees and formal proofs of all the
+ * properties. With respect to the version of BFQ presented in these
+ * papers, this implementation adds a few more heuristics, such as the
+ * ones that guarantee a low latency to interactive and soft real-time
+ * applications, and a hierarchical extension based on H-WF2Q+.
*
* B-WF2Q+ is based on WF2Q+, which is described in [2], together with
* H-WF2Q+, while the augmented tree used here to implement B-WF2Q+
@@ -218,56 +248,46 @@ static struct kmem_cache *bfq_pool;
#define BFQ_RATE_SHIFT 16
/*
- * By default, BFQ computes the duration of the weight raising for
- * interactive applications automatically, using the following formula:
- * duration = (R / r) * T, where r is the peak rate of the device, and
- * R and T are two reference parameters.
- * In particular, R is the peak rate of the reference device (see
- * below), and T is a reference time: given the systems that are
- * likely to be installed on the reference device according to its
- * speed class, T is about the maximum time needed, under BFQ and
- * while reading two files in parallel, to load typical large
- * applications on these systems (see the comments on
- * max_service_from_wr below, for more details on how T is obtained).
- * In practice, the slower/faster the device at hand is, the more/less
- * it takes to load applications with respect to the reference device.
- * Accordingly, the longer/shorter BFQ grants weight raising to
- * interactive applications.
+ * When configured for computing the duration of the weight-raising
+ * for interactive queues automatically (see the comments at the
+ * beginning of this file), BFQ does it using the following formula:
+ * duration = (ref_rate / r) * ref_wr_duration,
+ * where r is the peak rate of the device, and ref_rate and
+ * ref_wr_duration are two reference parameters. In particular,
+ * ref_rate is the peak rate of the reference storage device (see
+ * below), and ref_wr_duration is about the maximum time needed, with
+ * BFQ and while reading two files in parallel, to load typical large
+ * applications on the reference device (see the comments on
+ * max_service_from_wr below, for more details on how ref_wr_duration
+ * is obtained). In practice, the slower/faster the device at hand
+ * is, the more/less it takes to load applications with respect to the
+ * reference device. Accordingly, the longer/shorter BFQ grants
+ * weight raising to interactive applications.
*
- * BFQ uses four different reference pairs (R, T), depending on:
- * . whether the device is rotational or non-rotational;
- * . whether the device is slow, such as old or portable HDDs, as well as
- * SD cards, or fast, such as newer HDDs and SSDs.
+ * BFQ uses two different reference pairs (ref_rate, ref_wr_duration),
+ * depending on whether the device is rotational or non-rotational.
*
- * The device's speed class is dynamically (re)detected in
- * bfq_update_peak_rate() every time the estimated peak rate is updated.
+ * In the following definitions, ref_rate[0] and ref_wr_duration[0]
+ * are the reference values for a rotational device, whereas
+ * ref_rate[1] and ref_wr_duration[1] are the reference values for a
+ * non-rotational device. The reference rates are not the actual peak
+ * rates of the devices used as a reference, but slightly lower
+ * values. The reason for using slightly lower values is that the
+ * peak-rate estimator tends to yield slightly lower values than the
+ * actual peak rate (it can yield the actual peak rate only if there
+ * is only one process doing I/O, and the process does sequential
+ * I/O).
*
- * In the following definitions, R_slow[0]/R_fast[0] and
- * T_slow[0]/T_fast[0] are the reference values for a slow/fast
- * rotational device, whereas R_slow[1]/R_fast[1] and
- * T_slow[1]/T_fast[1] are the reference values for a slow/fast
- * non-rotational device. Finally, device_speed_thresh are the
- * thresholds used to switch between speed classes. The reference
- * rates are not the actual peak rates of the devices used as a
- * reference, but slightly lower values. The reason for using these
- * slightly lower values is that the peak-rate estimator tends to
- * yield slightly lower values than the actual peak rate (it can yield
- * the actual peak rate only if there is only one process doing I/O,
- * and the process does sequential I/O).
- *
- * Both the reference peak rates and the thresholds are measured in
- * sectors/usec, left-shifted by BFQ_RATE_SHIFT.
+ * The reference peak rates are measured in sectors/usec, left-shifted
+ * by BFQ_RATE_SHIFT.
*/
-static int R_slow[2] = {1000, 10700};
-static int R_fast[2] = {14000, 33000};
+static int ref_rate[2] = {14000, 33000};
/*
- * To improve readability, a conversion function is used to initialize the
- * following arrays, which entails that they can be initialized only in a
- * function.
+ * To improve readability, a conversion function is used to initialize
+ * the following array, which entails that the array can be
+ * initialized only in a function.
*/
-static int T_slow[2];
-static int T_fast[2];
-static int device_speed_thresh[2];
+static int ref_wr_duration[2];
/*
* BFQ uses the above-detailed, time-based weight-raising mechanism to
@@ -487,46 +507,6 @@ static struct request *bfq_choose_req(struct bfq_data *bfqd,
}
/*
- * See the comments on bfq_limit_depth for the purpose of
- * the depths set in the function.
- */
-static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt)
-{
- bfqd->sb_shift = bt->sb.shift;
-
- /*
- * In-word depths if no bfq_queue is being weight-raised:
- * leaving 25% of tags only for sync reads.
- *
- * In next formulas, right-shift the value
- * (1U<<bfqd->sb_shift), instead of computing directly
- * (1U<<(bfqd->sb_shift - something)), to be robust against
- * any possible value of bfqd->sb_shift, without having to
- * limit 'something'.
- */
- /* no more than 50% of tags for async I/O */
- bfqd->word_depths[0][0] = max((1U<<bfqd->sb_shift)>>1, 1U);
- /*
- * no more than 75% of tags for sync writes (25% extra tags
- * w.r.t. async I/O, to prevent async I/O from starving sync
- * writes)
- */
- bfqd->word_depths[0][1] = max(((1U<<bfqd->sb_shift) * 3)>>2, 1U);
-
- /*
- * In-word depths in case some bfq_queue is being weight-
- * raised: leaving ~63% of tags for sync reads. This is the
- * highest percentage for which, in our tests, application
- * start-up times didn't suffer from any regression due to tag
- * shortage.
- */
- /* no more than ~18% of tags for async I/O */
- bfqd->word_depths[1][0] = max(((1U<<bfqd->sb_shift) * 3)>>4, 1U);
- /* no more than ~37% of tags for sync writes (~20% extra tags) */
- bfqd->word_depths[1][1] = max(((1U<<bfqd->sb_shift) * 6)>>4, 1U);
-}
-
-/*
* Async I/O can easily starve sync I/O (both sync reads and sync
* writes), by consuming all tags. Similarly, storms of sync writes,
* such as those that sync(2) may trigger, can starve sync reads.
@@ -535,25 +515,11 @@ static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt)
*/
static void bfq_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
{
- struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
struct bfq_data *bfqd = data->q->elevator->elevator_data;
- struct sbitmap_queue *bt;
if (op_is_sync(op) && !op_is_write(op))
return;
- if (data->flags & BLK_MQ_REQ_RESERVED) {
- if (unlikely(!tags->nr_reserved_tags)) {
- WARN_ON_ONCE(1);
- return;
- }
- bt = &tags->breserved_tags;
- } else
- bt = &tags->bitmap_tags;
-
- if (unlikely(bfqd->sb_shift != bt->sb.shift))
- bfq_update_depths(bfqd, bt);
-
data->shallow_depth =
bfqd->word_depths[!!bfqd->wr_busy_queues][op_is_sync(op)];
@@ -906,26 +872,30 @@ static unsigned int bfq_wr_duration(struct bfq_data *bfqd)
if (bfqd->bfq_wr_max_time > 0)
return bfqd->bfq_wr_max_time;
- dur = bfqd->RT_prod;
+ dur = bfqd->rate_dur_prod;
do_div(dur, bfqd->peak_rate);
/*
- * Limit duration between 3 and 13 seconds. Tests show that
- * higher values than 13 seconds often yield the opposite of
- * the desired result, i.e., worsen responsiveness by letting
- * non-interactive and non-soft-real-time applications
- * preserve weight raising for a too long time interval.
+ * Limit duration between 3 and 25 seconds. The upper limit
+ * has been conservatively set after the following worst case:
+ * on a QEMU/KVM virtual machine
+ * - running in a slow PC
+ * - with a virtual disk stacked on a slow low-end 5400rpm HDD
+ * - serving a heavy I/O workload, such as the sequential reading
+ * of several files
+ * mplayer took 23 seconds to start, if constantly weight-raised.
+ *
+ * As for higher values than that accomodating the above bad
+ * scenario, tests show that higher values would often yield
+ * the opposite of the desired result, i.e., would worsen
+ * responsiveness by allowing non-interactive applications to
+ * preserve weight raising for too long.
*
* On the other end, lower values than 3 seconds make it
* difficult for most interactive tasks to complete their jobs
* before weight-raising finishes.
*/
- if (dur > msecs_to_jiffies(13000))
- dur = msecs_to_jiffies(13000);
- else if (dur < msecs_to_jiffies(3000))
- dur = msecs_to_jiffies(3000);
-
- return dur;
+ return clamp_val(dur, msecs_to_jiffies(3000), msecs_to_jiffies(25000));
}
/* switch back from soft real-time to interactive weight raising */
@@ -1393,15 +1363,6 @@ static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
}
/*
- * Return the farthest future time instant according to jiffies
- * macros.
- */
-static unsigned long bfq_greatest_from_now(void)
-{
- return jiffies + MAX_JIFFY_OFFSET;
-}
-
-/*
* Return the farthest past time instant according to jiffies
* macros.
*/
@@ -1545,7 +1506,8 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
in_burst = bfq_bfqq_in_large_burst(bfqq);
soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
!in_burst &&
- time_is_before_jiffies(bfqq->soft_rt_next_start);
+ time_is_before_jiffies(bfqq->soft_rt_next_start) &&
+ bfqq->dispatched == 0;
*interactive = !in_burst && idle_for_long_time;
wr_or_deserves_wr = bfqd->low_latency &&
(bfqq->wr_coeff > 1 ||
@@ -1858,6 +1820,8 @@ static int bfq_request_merge(struct request_queue *q, struct request **req,
return ELEVATOR_NO_MERGE;
}
+static struct bfq_queue *bfq_init_rq(struct request *rq);
+
static void bfq_request_merged(struct request_queue *q, struct request *req,
enum elv_merge type)
{
@@ -1866,7 +1830,7 @@ static void bfq_request_merged(struct request_queue *q, struct request *req,
blk_rq_pos(req) <
blk_rq_pos(container_of(rb_prev(&req->rb_node),
struct request, rb_node))) {
- struct bfq_queue *bfqq = RQ_BFQQ(req);
+ struct bfq_queue *bfqq = bfq_init_rq(req);
struct bfq_data *bfqd = bfqq->bfqd;
struct request *prev, *next_rq;
@@ -1891,14 +1855,25 @@ static void bfq_request_merged(struct request_queue *q, struct request *req,
}
}
+/*
+ * This function is called to notify the scheduler that the requests
+ * rq and 'next' have been merged, with 'next' going away. BFQ
+ * exploits this hook to address the following issue: if 'next' has a
+ * fifo_time lower that rq, then the fifo_time of rq must be set to
+ * the value of 'next', to not forget the greater age of 'next'.
+ *
+ * NOTE: in this function we assume that rq is in a bfq_queue, basing
+ * on that rq is picked from the hash table q->elevator->hash, which,
+ * in its turn, is filled only with I/O requests present in
+ * bfq_queues, while BFQ is in use for the request queue q. In fact,
+ * the function that fills this hash table (elv_rqhash_add) is called
+ * only by bfq_insert_request.
+ */
static void bfq_requests_merged(struct request_queue *q, struct request *rq,
struct request *next)
{
- struct bfq_queue *bfqq = RQ_BFQQ(rq), *next_bfqq = RQ_BFQQ(next);
-
- if (!RB_EMPTY_NODE(&rq->rb_node))
- goto end;
- spin_lock_irq(&bfqq->bfqd->lock);
+ struct bfq_queue *bfqq = bfq_init_rq(rq),
+ *next_bfqq = bfq_init_rq(next);
/*
* If next and rq belong to the same bfq_queue and next is older
@@ -1920,11 +1895,6 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq,
if (bfqq->next_rq == next)
bfqq->next_rq = rq;
- bfq_remove_request(q, next);
- bfqg_stats_update_io_remove(bfqq_group(bfqq), next->cmd_flags);
-
- spin_unlock_irq(&bfqq->bfqd->lock);
-end:
bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
}
@@ -2506,37 +2476,15 @@ static unsigned long bfq_calc_max_budget(struct bfq_data *bfqd)
/*
* Update parameters related to throughput and responsiveness, as a
* function of the estimated peak rate. See comments on
- * bfq_calc_max_budget(), and on T_slow and T_fast arrays.
+ * bfq_calc_max_budget(), and on the ref_wr_duration array.
*/
static void update_thr_responsiveness_params(struct bfq_data *bfqd)
{
- int dev_type = blk_queue_nonrot(bfqd->queue);
-
- if (bfqd->bfq_user_max_budget == 0)
+ if (bfqd->bfq_user_max_budget == 0) {
bfqd->bfq_max_budget =
bfq_calc_max_budget(bfqd);
-
- if (bfqd->device_speed == BFQ_BFQD_FAST &&
- bfqd->peak_rate < device_speed_thresh[dev_type]) {
- bfqd->device_speed = BFQ_BFQD_SLOW;
- bfqd->RT_prod = R_slow[dev_type] *
- T_slow[dev_type];
- } else if (bfqd->device_speed == BFQ_BFQD_SLOW &&
- bfqd->peak_rate > device_speed_thresh[dev_type]) {
- bfqd->device_speed = BFQ_BFQD_FAST;
- bfqd->RT_prod = R_fast[dev_type] *
- T_fast[dev_type];
+ bfq_log(bfqd, "new max_budget = %d", bfqd->bfq_max_budget);
}
-
- bfq_log(bfqd,
-"dev_type %s dev_speed_class = %s (%llu sects/sec), thresh %llu setcs/sec",
- dev_type == 0 ? "ROT" : "NONROT",
- bfqd->device_speed == BFQ_BFQD_FAST ? "FAST" : "SLOW",
- bfqd->device_speed == BFQ_BFQD_FAST ?
- (USEC_PER_SEC*(u64)R_fast[dev_type])>>BFQ_RATE_SHIFT :
- (USEC_PER_SEC*(u64)R_slow[dev_type])>>BFQ_RATE_SHIFT,
- (USEC_PER_SEC*(u64)device_speed_thresh[dev_type])>>
- BFQ_RATE_SHIFT);
}
static void bfq_reset_rate_computation(struct bfq_data *bfqd,
@@ -3266,23 +3214,6 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
bfq_bfqq_softrt_next_start(bfqd, bfqq);
else {
/*
- * The application is still waiting for the
- * completion of one or more requests:
- * prevent it from possibly being incorrectly
- * deemed as soft real-time by setting its
- * soft_rt_next_start to infinity. In fact,
- * without this assignment, the application
- * would be incorrectly deemed as soft
- * real-time if:
- * 1) it issued a new request before the
- * completion of all its in-flight
- * requests, and
- * 2) at that time, its soft_rt_next_start
- * happened to be in the past.
- */
- bfqq->soft_rt_next_start =
- bfq_greatest_from_now();
- /*
* Schedule an update of soft_rt_next_start to when
* the task may be discovered to be isochronous.
*/
@@ -4540,14 +4471,12 @@ static inline void bfq_update_insert_stats(struct request_queue *q,
unsigned int cmd_flags) {}
#endif
-static void bfq_prepare_request(struct request *rq, struct bio *bio);
-
static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
bool at_head)
{
struct request_queue *q = hctx->queue;
struct bfq_data *bfqd = q->elevator->elevator_data;
- struct bfq_queue *bfqq = RQ_BFQQ(rq);
+ struct bfq_queue *bfqq;
bool idle_timer_disabled = false;
unsigned int cmd_flags;
@@ -4562,24 +4491,13 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
blk_mq_sched_request_inserted(rq);
spin_lock_irq(&bfqd->lock);
+ bfqq = bfq_init_rq(rq);
if (at_head || blk_rq_is_passthrough(rq)) {
if (at_head)
list_add(&rq->queuelist, &bfqd->dispatch);
else
list_add_tail(&rq->queuelist, &bfqd->dispatch);
- } else {
- if (WARN_ON_ONCE(!bfqq)) {
- /*
- * This should never happen. Most likely rq is
- * a requeued regular request, being
- * re-inserted without being first
- * re-prepared. Do a prepare, to avoid
- * failure.
- */
- bfq_prepare_request(rq, rq->bio);
- bfqq = RQ_BFQQ(rq);
- }
-
+ } else { /* bfqq is assumed to be non null here */
idle_timer_disabled = __bfq_insert_request(bfqd, rq);
/*
* Update bfqq, because, if a queue merge has occurred
@@ -4778,8 +4696,8 @@ static void bfq_finish_requeue_request(struct request *rq)
if (rq->rq_flags & RQF_STARTED)
bfqg_stats_update_completion(bfqq_group(bfqq),
- rq_start_time_ns(rq),
- rq_io_start_time_ns(rq),
+ rq->start_time_ns,
+ rq->io_start_time_ns,
rq->cmd_flags);
if (likely(rq->rq_flags & RQF_STARTED)) {
@@ -4922,11 +4840,48 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
}
/*
- * Allocate bfq data structures associated with this request.
+ * Only reset private fields. The actual request preparation will be
+ * performed by bfq_init_rq, when rq is either inserted or merged. See
+ * comments on bfq_init_rq for the reason behind this delayed
+ * preparation.
*/
static void bfq_prepare_request(struct request *rq, struct bio *bio)
{
+ /*
+ * Regardless of whether we have an icq attached, we have to
+ * clear the scheduler pointers, as they might point to
+ * previously allocated bic/bfqq structs.
+ */
+ rq->elv.priv[0] = rq->elv.priv[1] = NULL;
+}
+
+/*
+ * If needed, init rq, allocate bfq data structures associated with
+ * rq, and increment reference counters in the destination bfq_queue
+ * for rq. Return the destination bfq_queue for rq, or NULL is rq is
+ * not associated with any bfq_queue.
+ *
+ * This function is invoked by the functions that perform rq insertion
+ * or merging. One may have expected the above preparation operations
+ * to be performed in bfq_prepare_request, and not delayed to when rq
+ * is inserted or merged. The rationale behind this delayed
+ * preparation is that, after the prepare_request hook is invoked for
+ * rq, rq may still be transformed into a request with no icq, i.e., a
+ * request not associated with any queue. No bfq hook is invoked to
+ * signal this tranformation. As a consequence, should these
+ * preparation operations be performed when the prepare_request hook
+ * is invoked, and should rq be transformed one moment later, bfq
+ * would end up in an inconsistent state, because it would have
+ * incremented some queue counters for an rq destined to
+ * transformation, without any chance to correctly lower these
+ * counters back. In contrast, no transformation can still happen for
+ * rq after rq has been inserted or merged. So, it is safe to execute
+ * these preparation operations when rq is finally inserted or merged.
+ */
+static struct bfq_queue *bfq_init_rq(struct request *rq)
+{
struct request_queue *q = rq->q;
+ struct bio *bio = rq->bio;
struct bfq_data *bfqd = q->elevator->elevator_data;
struct bfq_io_cq *bic;
const int is_sync = rq_is_sync(rq);
@@ -4934,11 +4889,20 @@ static void bfq_prepare_request(struct request *rq, struct bio *bio)
bool new_queue = false;
bool bfqq_already_existing = false, split = false;
- if (!rq->elv.icq)
- return;
- bic = icq_to_bic(rq->elv.icq);
+ if (unlikely(!rq->elv.icq))
+ return NULL;
- spin_lock_irq(&bfqd->lock);
+ /*
+ * Assuming that elv.priv[1] is set only if everything is set
+ * for this rq. This holds true, because this function is
+ * invoked only for insertion or merging, and, after such
+ * events, a request cannot be manipulated any longer before
+ * being removed from bfq.
+ */
+ if (rq->elv.priv[1])
+ return rq->elv.priv[1];
+
+ bic = icq_to_bic(rq->elv.icq);
bfq_check_ioprio_change(bic, bio);
@@ -4998,7 +4962,7 @@ static void bfq_prepare_request(struct request *rq, struct bio *bio)
if (unlikely(bfq_bfqq_just_created(bfqq)))
bfq_handle_burst(bfqd, bfqq);
- spin_unlock_irq(&bfqd->lock);
+ return bfqq;
}
static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
@@ -5097,6 +5061,64 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
__bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq);
}
+/*
+ * See the comments on bfq_limit_depth for the purpose of
+ * the depths set in the function. Return minimum shallow depth we'll use.
+ */
+static unsigned int bfq_update_depths(struct bfq_data *bfqd,
+ struct sbitmap_queue *bt)
+{
+ unsigned int i, j, min_shallow = UINT_MAX;
+
+ /*
+ * In-word depths if no bfq_queue is being weight-raised:
+ * leaving 25% of tags only for sync reads.
+ *
+ * In next formulas, right-shift the value
+ * (1U<<bt->sb.shift), instead of computing directly
+ * (1U<<(bt->sb.shift - something)), to be robust against
+ * any possible value of bt->sb.shift, without having to
+ * limit 'something'.
+ */
+ /* no more than 50% of tags for async I/O */
+ bfqd->word_depths[0][0] = max((1U << bt->sb.shift) >> 1, 1U);
+ /*
+ * no more than 75% of tags for sync writes (25% extra tags
+ * w.r.t. async I/O, to prevent async I/O from starving sync
+ * writes)
+ */
+ bfqd->word_depths[0][1] = max(((1U << bt->sb.shift) * 3) >> 2, 1U);
+
+ /*
+ * In-word depths in case some bfq_queue is being weight-
+ * raised: leaving ~63% of tags for sync reads. This is the
+ * highest percentage for which, in our tests, application
+ * start-up times didn't suffer from any regression due to tag
+ * shortage.
+ */
+ /* no more than ~18% of tags for async I/O */
+ bfqd->word_depths[1][0] = max(((1U << bt->sb.shift) * 3) >> 4, 1U);
+ /* no more than ~37% of tags for sync writes (~20% extra tags) */
+ bfqd->word_depths[1][1] = max(((1U << bt->sb.shift) * 6) >> 4, 1U);
+
+ for (i = 0; i < 2; i++)
+ for (j = 0; j < 2; j++)
+ min_shallow = min(min_shallow, bfqd->word_depths[i][j]);
+
+ return min_shallow;
+}
+
+static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)
+{
+ struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
+ struct blk_mq_tags *tags = hctx->sched_tags;
+ unsigned int min_shallow;
+
+ min_shallow = bfq_update_depths(bfqd, &tags->bitmap_tags);
+ sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, min_shallow);
+ return 0;
+}
+
static void bfq_exit_queue(struct elevator_queue *e)
{
struct bfq_data *bfqd = e->elevator_data;
@@ -5234,14 +5256,12 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
bfqd->wr_busy_queues = 0;
/*
- * Begin by assuming, optimistically, that the device is a
- * high-speed one, and that its peak rate is equal to 2/3 of
- * the highest reference rate.
+ * Begin by assuming, optimistically, that the device peak
+ * rate is equal to 2/3 of the highest reference rate.
*/
- bfqd->RT_prod = R_fast[blk_queue_nonrot(bfqd->queue)] *
- T_fast[blk_queue_nonrot(bfqd->queue)];
- bfqd->peak_rate = R_fast[blk_queue_nonrot(bfqd->queue)] * 2 / 3;
- bfqd->device_speed = BFQ_BFQD_FAST;
+ bfqd->rate_dur_prod = ref_rate[blk_queue_nonrot(bfqd->queue)] *
+ ref_wr_duration[blk_queue_nonrot(bfqd->queue)];
+ bfqd->peak_rate = ref_rate[blk_queue_nonrot(bfqd->queue)] * 2 / 3;
spin_lock_init(&bfqd->lock);
@@ -5518,6 +5538,7 @@ static struct elevator_type iosched_bfq_mq = {
.requests_merged = bfq_requests_merged,
.request_merged = bfq_request_merged,
.has_work = bfq_has_work,
+ .init_hctx = bfq_init_hctx,
.init_sched = bfq_init_queue,
.exit_sched = bfq_exit_queue,
},
@@ -5548,8 +5569,8 @@ static int __init bfq_init(void)
/*
* Times to load large popular applications for the typical
* systems installed on the reference devices (see the
- * comments before the definitions of the next two
- * arrays). Actually, we use slightly slower values, as the
+ * comments before the definition of the next
+ * array). Actually, we use slightly lower values, as the
* estimated peak rate tends to be smaller than the actual
* peak rate. The reason for this last fact is that estimates
* are computed over much shorter time intervals than the long
@@ -5558,25 +5579,8 @@ static int __init bfq_init(void)
* scheduler cannot rely on a peak-rate-evaluation workload to
* be run for a long time.
*/
- T_slow[0] = msecs_to_jiffies(3500); /* actually 4 sec */
- T_slow[1] = msecs_to_jiffies(6000); /* actually 6.5 sec */
- T_fast[0] = msecs_to_jiffies(7000); /* actually 8 sec */
- T_fast[1] = msecs_to_jiffies(2500); /* actually 3 sec */
-
- /*
- * Thresholds that determine the switch between speed classes
- * (see the comments before the definition of the array
- * device_speed_thresh). These thresholds are biased towards
- * transitions to the fast class. This is safer than the
- * opposite bias. In fact, a wrong transition to the slow
- * class results in short weight-raising periods, because the
- * speed of the device then tends to be higher that the
- * reference peak rate. On the opposite end, a wrong
- * transition to the fast class tends to increase
- * weight-raising periods, because of the opposite reason.
- */
- device_speed_thresh[0] = (4 * R_slow[0]) / 3;
- device_speed_thresh[1] = (4 * R_slow[1]) / 3;
+ ref_wr_duration[0] = msecs_to_jiffies(7000); /* actually 8 sec */
+ ref_wr_duration[1] = msecs_to_jiffies(2500); /* actually 3 sec */
ret = elv_register(&iosched_bfq_mq);
if (ret)
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index ae2f3da..0f712e0 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -399,11 +399,6 @@ struct bfq_io_cq {
struct bfq_ttime saved_ttime;
};
-enum bfq_device_speed {
- BFQ_BFQD_FAST,
- BFQ_BFQD_SLOW,
-};
-
/**
* struct bfq_data - per-device data structure.
*
@@ -611,12 +606,11 @@ struct bfq_data {
/* Max service-rate for a soft real-time queue, in sectors/sec */
unsigned int bfq_wr_max_softrt_rate;
/*
- * Cached value of the product R*T, used for computing the
- * maximum duration of weight raising automatically.
+ * Cached value of the product ref_rate*ref_wr_duration, used
+ * for computing the maximum duration of weight raising
+ * automatically.
*/
- u64 RT_prod;
- /* device-speed class for the low-latency heuristic */
- enum bfq_device_speed device_speed;
+ u64 rate_dur_prod;
/* fallback dummy bfqq for extreme OOM conditions */
struct bfq_queue oom_bfqq;
@@ -636,12 +630,6 @@ struct bfq_data {
struct bfq_queue *bio_bfqq;
/*
- * Cached sbitmap shift, used to compute depth limits in
- * bfq_update_depths.
- */
- unsigned int sb_shift;
-
- /*
* Depth limits used in bfq_limit_depth (see comments on the
* function)
*/
@@ -732,9 +720,9 @@ struct bfqg_stats {
/* total time with empty current active q with other requests queued */
struct blkg_stat empty_time;
/* fields after this shouldn't be cleared on stat reset */
- uint64_t start_group_wait_time;
- uint64_t start_idle_time;
- uint64_t start_empty_time;
+ u64 start_group_wait_time;
+ u64 start_idle_time;
+ u64 start_empty_time;
uint16_t flags;
#endif /* CONFIG_BFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */
};
@@ -856,8 +844,8 @@ void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
unsigned int op);
void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op);
void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op);
-void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
- uint64_t io_start_time, unsigned int op);
+void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns,
+ u64 io_start_time_ns, unsigned int op);
void bfqg_stats_update_dequeue(struct bfq_group *bfqg);
void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg);
void bfqg_stats_update_idle_time(struct bfq_group *bfqg);
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 9cfdd6c..add7c7c 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -56,12 +56,12 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
struct bio_set *bs = bio->bi_pool;
unsigned inline_vecs;
- if (!bs || !bs->bio_integrity_pool) {
+ if (!bs || !mempool_initialized(&bs->bio_integrity_pool)) {
bip = kmalloc(sizeof(struct bio_integrity_payload) +
sizeof(struct bio_vec) * nr_vecs, gfp_mask);
inline_vecs = nr_vecs;
} else {
- bip = mempool_alloc(bs->bio_integrity_pool, gfp_mask);
+ bip = mempool_alloc(&bs->bio_integrity_pool, gfp_mask);
inline_vecs = BIP_INLINE_VECS;
}
@@ -74,7 +74,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
unsigned long idx = 0;
bip->bip_vec = bvec_alloc(gfp_mask, nr_vecs, &idx,
- bs->bvec_integrity_pool);
+ &bs->bvec_integrity_pool);
if (!bip->bip_vec)
goto err;
bip->bip_max_vcnt = bvec_nr_vecs(idx);
@@ -90,7 +90,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
return bip;
err:
- mempool_free(bip, bs->bio_integrity_pool);
+ mempool_free(bip, &bs->bio_integrity_pool);
return ERR_PTR(-ENOMEM);
}
EXPORT_SYMBOL(bio_integrity_alloc);
@@ -111,10 +111,10 @@ static void bio_integrity_free(struct bio *bio)
kfree(page_address(bip->bip_vec->bv_page) +
bip->bip_vec->bv_offset);
- if (bs && bs->bio_integrity_pool) {
- bvec_free(bs->bvec_integrity_pool, bip->bip_vec, bip->bip_slab);
+ if (bs && mempool_initialized(&bs->bio_integrity_pool)) {
+ bvec_free(&bs->bvec_integrity_pool, bip->bip_vec, bip->bip_slab);
- mempool_free(bip, bs->bio_integrity_pool);
+ mempool_free(bip, &bs->bio_integrity_pool);
} else {
kfree(bip);
}
@@ -465,16 +465,15 @@ EXPORT_SYMBOL(bio_integrity_clone);
int bioset_integrity_create(struct bio_set *bs, int pool_size)
{
- if (bs->bio_integrity_pool)
+ if (mempool_initialized(&bs->bio_integrity_pool))
return 0;
- bs->bio_integrity_pool = mempool_create_slab_pool(pool_size, bip_slab);
- if (!bs->bio_integrity_pool)
+ if (mempool_init_slab_pool(&bs->bio_integrity_pool,
+ pool_size, bip_slab))
return -1;
- bs->bvec_integrity_pool = biovec_create_pool(pool_size);
- if (!bs->bvec_integrity_pool) {
- mempool_destroy(bs->bio_integrity_pool);
+ if (biovec_init_pool(&bs->bvec_integrity_pool, pool_size)) {
+ mempool_exit(&bs->bio_integrity_pool);
return -1;
}
@@ -484,8 +483,8 @@ EXPORT_SYMBOL(bioset_integrity_create);
void bioset_integrity_free(struct bio_set *bs)
{
- mempool_destroy(bs->bio_integrity_pool);
- mempool_destroy(bs->bvec_integrity_pool);
+ mempool_exit(&bs->bio_integrity_pool);
+ mempool_exit(&bs->bvec_integrity_pool);
}
EXPORT_SYMBOL(bioset_integrity_free);
diff --git a/block/bio.c b/block/bio.c
index 53e0f0a..5f75635 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -53,7 +53,7 @@ static struct biovec_slab bvec_slabs[BVEC_POOL_NR] __read_mostly = {
* fs_bio_set is the bio_set containing bio and iovec memory pools used by
* IO code that does not need private memory pools.
*/
-struct bio_set *fs_bio_set;
+struct bio_set fs_bio_set;
EXPORT_SYMBOL(fs_bio_set);
/*
@@ -254,7 +254,7 @@ static void bio_free(struct bio *bio)
bio_uninit(bio);
if (bs) {
- bvec_free(bs->bvec_pool, bio->bi_io_vec, BVEC_POOL_IDX(bio));
+ bvec_free(&bs->bvec_pool, bio->bi_io_vec, BVEC_POOL_IDX(bio));
/*
* If we have front padding, adjust the bio pointer before freeing
@@ -262,7 +262,7 @@ static void bio_free(struct bio *bio)
p = bio;
p -= bs->front_pad;
- mempool_free(p, bs->bio_pool);
+ mempool_free(p, &bs->bio_pool);
} else {
/* Bio was allocated by bio_kmalloc() */
kfree(bio);
@@ -454,7 +454,8 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs,
inline_vecs = nr_iovecs;
} else {
/* should not use nobvec bioset for nr_iovecs > 0 */
- if (WARN_ON_ONCE(!bs->bvec_pool && nr_iovecs > 0))
+ if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) &&
+ nr_iovecs > 0))
return NULL;
/*
* generic_make_request() converts recursion to iteration; this
@@ -483,11 +484,11 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs,
bs->rescue_workqueue)
gfp_mask &= ~__GFP_DIRECT_RECLAIM;
- p = mempool_alloc(bs->bio_pool, gfp_mask);
+ p = mempool_alloc(&bs->bio_pool, gfp_mask);
if (!p && gfp_mask != saved_gfp) {
punt_bios_to_rescuer(bs);
gfp_mask = saved_gfp;
- p = mempool_alloc(bs->bio_pool, gfp_mask);
+ p = mempool_alloc(&bs->bio_pool, gfp_mask);
}
front_pad = bs->front_pad;
@@ -503,11 +504,11 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs,
if (nr_iovecs > inline_vecs) {
unsigned long idx = 0;
- bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool);
+ bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, &bs->bvec_pool);
if (!bvl && gfp_mask != saved_gfp) {
punt_bios_to_rescuer(bs);
gfp_mask = saved_gfp;
- bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool);
+ bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, &bs->bvec_pool);
}
if (unlikely(!bvl))
@@ -524,25 +525,25 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs,
return bio;
err_free:
- mempool_free(p, bs->bio_pool);
+ mempool_free(p, &bs->bio_pool);
return NULL;
}
EXPORT_SYMBOL(bio_alloc_bioset);
-void zero_fill_bio(struct bio *bio)
+void zero_fill_bio_iter(struct bio *bio, struct bvec_iter start)
{
unsigned long flags;
struct bio_vec bv;
struct bvec_iter iter;
- bio_for_each_segment(bv, bio, iter) {
+ __bio_for_each_segment(bv, bio, iter, start) {
char *data = bvec_kmap_irq(&bv, &flags);
memset(data, 0, bv.bv_len);
flush_dcache_page(bv.bv_page);
bvec_kunmap_irq(data, &flags);
}
}
-EXPORT_SYMBOL(zero_fill_bio);
+EXPORT_SYMBOL(zero_fill_bio_iter);
/**
* bio_put - release a reference to a bio
@@ -773,7 +774,7 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
return 0;
}
- if (bio->bi_vcnt >= bio->bi_max_vecs)
+ if (bio_full(bio))
return 0;
/*
@@ -821,6 +822,65 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
EXPORT_SYMBOL(bio_add_pc_page);
/**
+ * __bio_try_merge_page - try appending data to an existing bvec.
+ * @bio: destination bio
+ * @page: page to add
+ * @len: length of the data to add
+ * @off: offset of the data in @page
+ *
+ * Try to add the data at @page + @off to the last bvec of @bio. This is a
+ * a useful optimisation for file systems with a block size smaller than the
+ * page size.
+ *
+ * Return %true on success or %false on failure.
+ */
+bool __bio_try_merge_page(struct bio *bio, struct page *page,
+ unsigned int len, unsigned int off)
+{
+ if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
+ return false;
+
+ if (bio->bi_vcnt > 0) {
+ struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
+
+ if (page == bv->bv_page && off == bv->bv_offset + bv->bv_len) {
+ bv->bv_len += len;
+ bio->bi_iter.bi_size += len;
+ return true;
+ }
+ }
+ return false;
+}
+EXPORT_SYMBOL_GPL(__bio_try_merge_page);
+
+/**
+ * __bio_add_page - add page to a bio in a new segment
+ * @bio: destination bio
+ * @page: page to add
+ * @len: length of the data to add
+ * @off: offset of the data in @page
+ *
+ * Add the data at @page + @off to @bio as a new bvec. The caller must ensure
+ * that @bio has space for another bvec.
+ */
+void __bio_add_page(struct bio *bio, struct page *page,
+ unsigned int len, unsigned int off)
+{
+ struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt];
+
+ WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED));
+ WARN_ON_ONCE(bio_full(bio));
+
+ bv->bv_page = page;
+ bv->bv_offset = off;
+ bv->bv_len = len;
+
+ bio->bi_iter.bi_size += len;
+ bio->bi_vcnt++;
+}
+EXPORT_SYMBOL_GPL(__bio_add_page);
+
+/**
* bio_add_page - attempt to add page to bio
* @bio: destination bio
* @page: page to add
@@ -833,40 +893,11 @@ EXPORT_SYMBOL(bio_add_pc_page);
int bio_add_page(struct bio *bio, struct page *page,
unsigned int len, unsigned int offset)
{
- struct bio_vec *bv;
-
- /*
- * cloned bio must not modify vec list
- */
- if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
- return 0;
-
- /*
- * For filesystems with a blocksize smaller than the pagesize
- * we will often be called with the same page as last time and
- * a consecutive offset. Optimize this special case.
- */
- if (bio->bi_vcnt > 0) {
- bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
-
- if (page == bv->bv_page &&
- offset == bv->bv_offset + bv->bv_len) {
- bv->bv_len += len;
- goto done;
- }
+ if (!__bio_try_merge_page(bio, page, len, offset)) {
+ if (bio_full(bio))
+ return 0;
+ __bio_add_page(bio, page, len, offset);
}
-
- if (bio->bi_vcnt >= bio->bi_max_vecs)
- return 0;
-
- bv = &bio->bi_io_vec[bio->bi_vcnt];
- bv->bv_page = page;
- bv->bv_len = len;
- bv->bv_offset = offset;
-
- bio->bi_vcnt++;
-done:
- bio->bi_iter.bi_size += len;
return len;
}
EXPORT_SYMBOL(bio_add_page);
@@ -970,27 +1001,68 @@ void bio_advance(struct bio *bio, unsigned bytes)
}
EXPORT_SYMBOL(bio_advance);
+void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
+ struct bio *src, struct bvec_iter *src_iter)
+{
+ struct bio_vec src_bv, dst_bv;
+ void *src_p, *dst_p;
+ unsigned bytes;
+
+ while (src_iter->bi_size && dst_iter->bi_size) {
+ src_bv = bio_iter_iovec(src, *src_iter);
+ dst_bv = bio_iter_iovec(dst, *dst_iter);
+
+ bytes = min(src_bv.bv_len, dst_bv.bv_len);
+
+ src_p = kmap_atomic(src_bv.bv_page);
+ dst_p = kmap_atomic(dst_bv.bv_page);
+
+ memcpy(dst_p + dst_bv.bv_offset,
+ src_p + src_bv.bv_offset,
+ bytes);
+
+ kunmap_atomic(dst_p);
+ kunmap_atomic(src_p);
+
+ flush_dcache_page(dst_bv.bv_page);
+
+ bio_advance_iter(src, src_iter, bytes);
+ bio_advance_iter(dst, dst_iter, bytes);
+ }
+}
+EXPORT_SYMBOL(bio_copy_data_iter);
+
/**
- * bio_copy_data - copy contents of data buffers from one chain of bios to
- * another
- * @src: source bio list
- * @dst: destination bio list
- *
- * If @src and @dst are single bios, bi_next must be NULL - otherwise, treats
- * @src and @dst as linked lists of bios.
+ * bio_copy_data - copy contents of data buffers from one bio to another
+ * @src: source bio
+ * @dst: destination bio
*
* Stops when it reaches the end of either @src or @dst - that is, copies
* min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of bios).
*/
void bio_copy_data(struct bio *dst, struct bio *src)
{
- struct bvec_iter src_iter, dst_iter;
- struct bio_vec src_bv, dst_bv;
- void *src_p, *dst_p;
- unsigned bytes;
+ struct bvec_iter src_iter = src->bi_iter;
+ struct bvec_iter dst_iter = dst->bi_iter;
- src_iter = src->bi_iter;
- dst_iter = dst->bi_iter;
+ bio_copy_data_iter(dst, &dst_iter, src, &src_iter);
+}
+EXPORT_SYMBOL(bio_copy_data);
+
+/**
+ * bio_list_copy_data - copy contents of data buffers from one chain of bios to
+ * another
+ * @src: source bio list
+ * @dst: destination bio list
+ *
+ * Stops when it reaches the end of either the @src list or @dst list - that is,
+ * copies min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of
+ * bios).
+ */
+void bio_list_copy_data(struct bio *dst, struct bio *src)
+{
+ struct bvec_iter src_iter = src->bi_iter;
+ struct bvec_iter dst_iter = dst->bi_iter;
while (1) {
if (!src_iter.bi_size) {
@@ -1009,26 +1081,10 @@ void bio_copy_data(struct bio *dst, struct bio *src)
dst_iter = dst->bi_iter;
}
- src_bv = bio_iter_iovec(src, src_iter);
- dst_bv = bio_iter_iovec(dst, dst_iter);
-
- bytes = min(src_bv.bv_len, dst_bv.bv_len);
-
- src_p = kmap_atomic(src_bv.bv_page);
- dst_p = kmap_atomic(dst_bv.bv_page);
-
- memcpy(dst_p + dst_bv.bv_offset,
- src_p + src_bv.bv_offset,
- bytes);
-
- kunmap_atomic(dst_p);
- kunmap_atomic(src_p);
-
- bio_advance_iter(src, &src_iter, bytes);
- bio_advance_iter(dst, &dst_iter, bytes);
+ bio_copy_data_iter(dst, &dst_iter, src, &src_iter);
}
}
-EXPORT_SYMBOL(bio_copy_data);
+EXPORT_SYMBOL(bio_list_copy_data);
struct bio_map_data {
int is_our_pages;
@@ -1584,6 +1640,7 @@ void bio_set_pages_dirty(struct bio *bio)
set_page_dirty_lock(page);
}
}
+EXPORT_SYMBOL_GPL(bio_set_pages_dirty);
static void bio_release_pages(struct bio *bio)
{
@@ -1667,6 +1724,7 @@ void bio_check_pages_dirty(struct bio *bio)
bio_put(bio);
}
}
+EXPORT_SYMBOL_GPL(bio_check_pages_dirty);
void generic_start_io_acct(struct request_queue *q, int rw,
unsigned long sectors, struct hd_struct *part)
@@ -1749,6 +1807,9 @@ void bio_endio(struct bio *bio)
if (!bio_integrity_endio(bio))
return;
+ if (WARN_ONCE(bio->bi_next, "driver left bi_next not NULL"))
+ bio->bi_next = NULL;
+
/*
* Need to have a real endio function for chained bios, otherwise
* various corner cases will break (like stacking block devices that
@@ -1848,30 +1909,38 @@ EXPORT_SYMBOL_GPL(bio_trim);
* create memory pools for biovec's in a bio_set.
* use the global biovec slabs created for general use.
*/
-mempool_t *biovec_create_pool(int pool_entries)
+int biovec_init_pool(mempool_t *pool, int pool_entries)
{
struct biovec_slab *bp = bvec_slabs + BVEC_POOL_MAX;
- return mempool_create_slab_pool(pool_entries, bp->slab);
+ return mempool_init_slab_pool(pool, pool_entries, bp->slab);
}
-void bioset_free(struct bio_set *bs)
+/*
+ * bioset_exit - exit a bioset initialized with bioset_init()
+ *
+ * May be called on a zeroed but uninitialized bioset (i.e. allocated with
+ * kzalloc()).
+ */
+void bioset_exit(struct bio_set *bs)
{
if (bs->rescue_workqueue)
destroy_workqueue(bs->rescue_workqueue);
+ bs->rescue_workqueue = NULL;
- mempool_destroy(bs->bio_pool);
- mempool_destroy(bs->bvec_pool);
+ mempool_exit(&bs->bio_pool);
+ mempool_exit(&bs->bvec_pool);
bioset_integrity_free(bs);
- bio_put_slab(bs);
-
- kfree(bs);
+ if (bs->bio_slab)
+ bio_put_slab(bs);
+ bs->bio_slab = NULL;
}
-EXPORT_SYMBOL(bioset_free);
+EXPORT_SYMBOL(bioset_exit);
/**
- * bioset_create - Create a bio_set
+ * bioset_init - Initialize a bio_set
+ * @bs: pool to initialize
* @pool_size: Number of bio and bio_vecs to cache in the mempool
* @front_pad: Number of bytes to allocate in front of the returned bio
* @flags: Flags to modify behavior, currently %BIOSET_NEED_BVECS
@@ -1890,16 +1959,12 @@ EXPORT_SYMBOL(bioset_free);
* dispatch queued requests when the mempool runs out of space.
*
*/
-struct bio_set *bioset_create(unsigned int pool_size,
- unsigned int front_pad,
- int flags)
+int bioset_init(struct bio_set *bs,
+ unsigned int pool_size,
+ unsigned int front_pad,
+ int flags)
{
unsigned int back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec);
- struct bio_set *bs;
-
- bs = kzalloc(sizeof(*bs), GFP_KERNEL);
- if (!bs)
- return NULL;
bs->front_pad = front_pad;
@@ -1908,34 +1973,29 @@ struct bio_set *bioset_create(unsigned int pool_size,
INIT_WORK(&bs->rescue_work, bio_alloc_rescue);
bs->bio_slab = bio_find_or_create_slab(front_pad + back_pad);
- if (!bs->bio_slab) {
- kfree(bs);
- return NULL;
- }
+ if (!bs->bio_slab)
+ return -ENOMEM;
- bs->bio_pool = mempool_create_slab_pool(pool_size, bs->bio_slab);
- if (!bs->bio_pool)
+ if (mempool_init_slab_pool(&bs->bio_pool, pool_size, bs->bio_slab))
goto bad;
- if (flags & BIOSET_NEED_BVECS) {
- bs->bvec_pool = biovec_create_pool(pool_size);
- if (!bs->bvec_pool)
- goto bad;
- }
+ if ((flags & BIOSET_NEED_BVECS) &&
+ biovec_init_pool(&bs->bvec_pool, pool_size))
+ goto bad;
if (!(flags & BIOSET_NEED_RESCUER))
- return bs;
+ return 0;
bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0);
if (!bs->rescue_workqueue)
goto bad;
- return bs;
+ return 0;
bad:
- bioset_free(bs);
- return NULL;
+ bioset_exit(bs);
+ return -ENOMEM;
}
-EXPORT_SYMBOL(bioset_create);
+EXPORT_SYMBOL(bioset_init);
#ifdef CONFIG_BLK_CGROUP
@@ -2020,11 +2080,10 @@ static int __init init_bio(void)
bio_integrity_init();
biovec_init_slabs();
- fs_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
- if (!fs_bio_set)
+ if (bioset_init(&fs_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS))
panic("bio: can't allocate bios\n");
- if (bioset_integrity_create(fs_bio_set, BIO_POOL_SIZE))
+ if (bioset_integrity_create(&fs_bio_set, BIO_POOL_SIZE))
panic("bio: can't create integrity pool\n");
return 0;
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 1c16694..eb85cb8 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1177,26 +1177,20 @@ int blkcg_init_queue(struct request_queue *q)
preloaded = !radix_tree_preload(GFP_KERNEL);
- /*
- * Make sure the root blkg exists and count the existing blkgs. As
- * @q is bypassing at this point, blkg_lookup_create() can't be
- * used. Open code insertion.
- */
+ /* Make sure the root blkg exists. */
rcu_read_lock();
spin_lock_irq(q->queue_lock);
blkg = blkg_create(&blkcg_root, q, new_blkg);
+ if (IS_ERR(blkg))
+ goto err_unlock;
+ q->root_blkg = blkg;
+ q->root_rl.blkg = blkg;
spin_unlock_irq(q->queue_lock);
rcu_read_unlock();
if (preloaded)
radix_tree_preload_end();
- if (IS_ERR(blkg))
- return PTR_ERR(blkg);
-
- q->root_blkg = blkg;
- q->root_rl.blkg = blkg;
-
ret = blk_throtl_init(q);
if (ret) {
spin_lock_irq(q->queue_lock);
@@ -1204,6 +1198,13 @@ int blkcg_init_queue(struct request_queue *q)
spin_unlock_irq(q->queue_lock);
}
return ret;
+
+err_unlock:
+ spin_unlock_irq(q->queue_lock);
+ rcu_read_unlock();
+ if (preloaded)
+ radix_tree_preload_end();
+ return PTR_ERR(blkg);
}
/**
@@ -1410,9 +1411,6 @@ void blkcg_deactivate_policy(struct request_queue *q,
__clear_bit(pol->plid, q->blkcg_pols);
list_for_each_entry(blkg, &q->blkg_list, q_node) {
- /* grab blkcg lock too while removing @pd from @blkg */
- spin_lock(&blkg->blkcg->lock);
-
if (blkg->pd[pol->plid]) {
if (!blkg->pd[pol->plid]->offline &&
pol->pd_offline_fn) {
@@ -1422,8 +1420,6 @@ void blkcg_deactivate_policy(struct request_queue *q,
pol->pd_free_fn(blkg->pd[pol->plid]);
blkg->pd[pol->plid] = NULL;
}
-
- spin_unlock(&blkg->blkcg->lock);
}
spin_unlock_irq(q->queue_lock);
diff --git a/block/blk-core.c b/block/blk-core.c
index 806ce24..3f56be1 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -196,11 +196,8 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
RB_CLEAR_NODE(&rq->rb_node);
rq->tag = -1;
rq->internal_tag = -1;
- rq->start_time = jiffies;
- set_start_time_ns(rq);
+ rq->start_time_ns = ktime_get_ns();
rq->part = NULL;
- seqcount_init(&rq->gstate_seq);
- u64_stats_init(&rq->aborted_gstate_sync);
}
EXPORT_SYMBOL(blk_rq_init);
@@ -276,6 +273,10 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
bio_advance(bio, nbytes);
/* don't actually finish bio if it's part of flush sequence */
+ /*
+ * XXX this code looks suspicious - it's not consistent with advancing
+ * req->bio in caller
+ */
if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
bio_endio(bio);
}
@@ -356,7 +357,6 @@ EXPORT_SYMBOL(blk_start_queue_async);
void blk_start_queue(struct request_queue *q)
{
lockdep_assert_held(q->queue_lock);
- WARN_ON(!in_interrupt() && !irqs_disabled());
WARN_ON_ONCE(q->mq_ops);
queue_flag_clear(QUEUE_FLAG_STOPPED, q);
@@ -915,7 +915,6 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
while (true) {
bool success = false;
- int ret;
rcu_read_lock();
if (percpu_ref_tryget_live(&q->q_usage_counter)) {
@@ -947,14 +946,12 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
*/
smp_rmb();
- ret = wait_event_interruptible(q->mq_freeze_wq,
- (atomic_read(&q->mq_freeze_depth) == 0 &&
- (preempt || !blk_queue_preempt_only(q))) ||
- blk_queue_dying(q));
+ wait_event(q->mq_freeze_wq,
+ (atomic_read(&q->mq_freeze_depth) == 0 &&
+ (preempt || !blk_queue_preempt_only(q))) ||
+ blk_queue_dying(q));
if (blk_queue_dying(q))
return -ENODEV;
- if (ret)
- return ret;
}
}
@@ -995,18 +992,24 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id,
spinlock_t *lock)
{
struct request_queue *q;
+ int ret;
q = kmem_cache_alloc_node(blk_requestq_cachep,
gfp_mask | __GFP_ZERO, node_id);
if (!q)
return NULL;
+ INIT_LIST_HEAD(&q->queue_head);
+ q->last_merge = NULL;
+ q->end_sector = 0;
+ q->boundary_rq = NULL;
+
q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask);
if (q->id < 0)
goto fail_q;
- q->bio_split = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
- if (!q->bio_split)
+ ret = bioset_init(&q->bio_split, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+ if (ret)
goto fail_id;
q->backing_dev_info = bdi_alloc_node(gfp_mask, node_id);
@@ -1078,7 +1081,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id,
fail_stats:
bdi_put(q->backing_dev_info);
fail_split:
- bioset_free(q->bio_split);
+ bioset_exit(&q->bio_split);
fail_id:
ida_simple_remove(&blk_queue_ida, q->id);
fail_q:
@@ -1172,16 +1175,8 @@ int blk_init_allocated_queue(struct request_queue *q)
q->sg_reserved_size = INT_MAX;
- /* Protect q->elevator from elevator_change */
- mutex_lock(&q->sysfs_lock);
-
- /* init elevator */
- if (elevator_init(q, NULL)) {
- mutex_unlock(&q->sysfs_lock);
+ if (elevator_init(q))
goto out_exit_flush_rq;
- }
-
- mutex_unlock(&q->sysfs_lock);
return 0;
out_exit_flush_rq:
@@ -1333,6 +1328,7 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
* @op: operation and flags
* @bio: bio to allocate request for (can be %NULL)
* @flags: BLQ_MQ_REQ_* flags
+ * @gfp_mask: allocator flags
*
* Get a free request from @q. This function may fail under memory
* pressure or if @q is dead.
@@ -1342,7 +1338,7 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
* Returns request pointer on success, with @q->queue_lock *not held*.
*/
static struct request *__get_request(struct request_list *rl, unsigned int op,
- struct bio *bio, blk_mq_req_flags_t flags)
+ struct bio *bio, blk_mq_req_flags_t flags, gfp_t gfp_mask)
{
struct request_queue *q = rl->q;
struct request *rq;
@@ -1351,8 +1347,6 @@ static struct request *__get_request(struct request_list *rl, unsigned int op,
struct io_cq *icq = NULL;
const bool is_sync = op_is_sync(op);
int may_queue;
- gfp_t gfp_mask = flags & BLK_MQ_REQ_NOWAIT ? GFP_ATOMIC :
- __GFP_DIRECT_RECLAIM;
req_flags_t rq_flags = RQF_ALLOCED;
lockdep_assert_held(q->queue_lock);
@@ -1516,8 +1510,9 @@ static struct request *__get_request(struct request_list *rl, unsigned int op,
* @op: operation and flags
* @bio: bio to allocate request for (can be %NULL)
* @flags: BLK_MQ_REQ_* flags.
+ * @gfp: allocator flags
*
- * Get a free request from @q. If %__GFP_DIRECT_RECLAIM is set in @gfp_mask,
+ * Get a free request from @q. If %BLK_MQ_REQ_NOWAIT is set in @flags,
* this function keeps retrying under memory pressure and fails iff @q is dead.
*
* Must be called with @q->queue_lock held and,
@@ -1525,7 +1520,7 @@ static struct request *__get_request(struct request_list *rl, unsigned int op,
* Returns request pointer on success, with @q->queue_lock *not held*.
*/
static struct request *get_request(struct request_queue *q, unsigned int op,
- struct bio *bio, blk_mq_req_flags_t flags)
+ struct bio *bio, blk_mq_req_flags_t flags, gfp_t gfp)
{
const bool is_sync = op_is_sync(op);
DEFINE_WAIT(wait);
@@ -1537,7 +1532,7 @@ static struct request *get_request(struct request_queue *q, unsigned int op,
rl = blk_get_rl(q, bio); /* transferred to @rq on success */
retry:
- rq = __get_request(rl, op, bio, flags);
+ rq = __get_request(rl, op, bio, flags, gfp);
if (!IS_ERR(rq))
return rq;
@@ -1578,8 +1573,7 @@ static struct request *blk_old_get_request(struct request_queue *q,
unsigned int op, blk_mq_req_flags_t flags)
{
struct request *rq;
- gfp_t gfp_mask = flags & BLK_MQ_REQ_NOWAIT ? GFP_ATOMIC :
- __GFP_DIRECT_RECLAIM;
+ gfp_t gfp_mask = flags & BLK_MQ_REQ_NOWAIT ? GFP_ATOMIC : GFP_NOIO;
int ret = 0;
WARN_ON_ONCE(q->mq_ops);
@@ -1591,7 +1585,7 @@ static struct request *blk_old_get_request(struct request_queue *q,
if (ret)
return ERR_PTR(ret);
spin_lock_irq(q->queue_lock);
- rq = get_request(q, op, NULL, flags);
+ rq = get_request(q, op, NULL, flags, gfp_mask);
if (IS_ERR(rq)) {
spin_unlock_irq(q->queue_lock);
blk_queue_exit(q);
@@ -1606,13 +1600,13 @@ static struct request *blk_old_get_request(struct request_queue *q,
}
/**
- * blk_get_request_flags - allocate a request
+ * blk_get_request - allocate a request
* @q: request queue to allocate a request for
* @op: operation (REQ_OP_*) and REQ_* flags, e.g. REQ_SYNC.
* @flags: BLK_MQ_REQ_* flags, e.g. BLK_MQ_REQ_NOWAIT.
*/
-struct request *blk_get_request_flags(struct request_queue *q, unsigned int op,
- blk_mq_req_flags_t flags)
+struct request *blk_get_request(struct request_queue *q, unsigned int op,
+ blk_mq_req_flags_t flags)
{
struct request *req;
@@ -1631,14 +1625,6 @@ struct request *blk_get_request_flags(struct request_queue *q, unsigned int op,
return req;
}
-EXPORT_SYMBOL(blk_get_request_flags);
-
-struct request *blk_get_request(struct request_queue *q, unsigned int op,
- gfp_t gfp_mask)
-{
- return blk_get_request_flags(q, op, gfp_mask & __GFP_DIRECT_RECLAIM ?
- 0 : BLK_MQ_REQ_NOWAIT);
-}
EXPORT_SYMBOL(blk_get_request);
/**
@@ -1659,7 +1645,7 @@ void blk_requeue_request(struct request_queue *q, struct request *rq)
blk_delete_timer(rq);
blk_clear_rq_complete(rq);
trace_block_rq_requeue(q, rq);
- wbt_requeue(q->rq_wb, &rq->issue_stat);
+ wbt_requeue(q->rq_wb, rq);
if (rq->rq_flags & RQF_QUEUED)
blk_queue_end_tag(q, rq);
@@ -1766,7 +1752,7 @@ void __blk_put_request(struct request_queue *q, struct request *req)
/* this is a bio leak */
WARN_ON(req->bio != NULL);
- wbt_done(q->rq_wb, &req->issue_stat);
+ wbt_done(q->rq_wb, req);
/*
* Request may not have originated from ll_rw_blk. if not,
@@ -2065,7 +2051,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
* Returns with the queue unlocked.
*/
blk_queue_enter_live(q);
- req = get_request(q, bio->bi_opf, bio, 0);
+ req = get_request(q, bio->bi_opf, bio, 0, GFP_NOIO);
if (IS_ERR(req)) {
blk_queue_exit(q);
__wbt_done(q->rq_wb, wb_acct);
@@ -2077,7 +2063,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
goto out_unlock;
}
- wbt_track(&req->issue_stat, wb_acct);
+ wbt_track(req, wb_acct);
/*
* After dropping the lock and possibly sleeping here, our request
@@ -2391,7 +2377,9 @@ blk_qc_t generic_make_request(struct bio *bio)
if (bio->bi_opf & REQ_NOWAIT)
flags = BLK_MQ_REQ_NOWAIT;
- if (blk_queue_enter(q, flags) < 0) {
+ if (bio_flagged(bio, BIO_QUEUE_ENTERED))
+ blk_queue_enter_live(q);
+ else if (blk_queue_enter(q, flags) < 0) {
if (!blk_queue_dying(q) && (bio->bi_opf & REQ_NOWAIT))
bio_wouldblock_error(bio);
else
@@ -2726,7 +2714,7 @@ void blk_account_io_completion(struct request *req, unsigned int bytes)
}
}
-void blk_account_io_done(struct request *req)
+void blk_account_io_done(struct request *req, u64 now)
{
/*
* Account IO completion. flush_rq isn't accounted as a
@@ -2734,11 +2722,12 @@ void blk_account_io_done(struct request *req)
* containing request is enough.
*/
if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) {
- unsigned long duration = jiffies - req->start_time;
+ unsigned long duration;
const int rw = rq_data_dir(req);
struct hd_struct *part;
int cpu;
+ duration = nsecs_to_jiffies(now - req->start_time_ns);
cpu = part_stat_lock();
part = req->part;
@@ -2969,10 +2958,8 @@ static void blk_dequeue_request(struct request *rq)
* and to it is freed is accounted as io that is in progress at
* the driver side.
*/
- if (blk_account_rq(rq)) {
+ if (blk_account_rq(rq))
q->in_flight[rq_is_sync(rq)]++;
- set_io_start_time_ns(rq);
- }
}
/**
@@ -2991,9 +2978,12 @@ void blk_start_request(struct request *req)
blk_dequeue_request(req);
if (test_bit(QUEUE_FLAG_STATS, &req->q->queue_flags)) {
- blk_stat_set_issue(&req->issue_stat, blk_rq_sectors(req));
+ req->io_start_time_ns = ktime_get_ns();
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+ req->throtl_size = blk_rq_sectors(req);
+#endif
req->rq_flags |= RQF_STATS;
- wbt_issue(req->q->rq_wb, &req->issue_stat);
+ wbt_issue(req->q->rq_wb, req);
}
BUG_ON(blk_rq_is_complete(req));
@@ -3091,8 +3081,10 @@ bool blk_update_request(struct request *req, blk_status_t error,
struct bio *bio = req->bio;
unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
- if (bio_bytes == bio->bi_iter.bi_size)
+ if (bio_bytes == bio->bi_iter.bi_size) {
req->bio = bio->bi_next;
+ bio->bi_next = NULL;
+ }
/* Completion has already been traced */
bio_clear_flag(bio, BIO_TRACE_COMPLETION);
@@ -3189,12 +3181,13 @@ EXPORT_SYMBOL_GPL(blk_unprep_request);
void blk_finish_request(struct request *req, blk_status_t error)
{
struct request_queue *q = req->q;
+ u64 now = ktime_get_ns();
lockdep_assert_held(req->q->queue_lock);
WARN_ON_ONCE(q->mq_ops);
if (req->rq_flags & RQF_STATS)
- blk_stat_add(req);
+ blk_stat_add(req, now);
if (req->rq_flags & RQF_QUEUED)
blk_queue_end_tag(q, req);
@@ -3209,10 +3202,10 @@ void blk_finish_request(struct request *req, blk_status_t error)
if (req->rq_flags & RQF_DONTPREP)
blk_unprep_request(req);
- blk_account_io_done(req);
+ blk_account_io_done(req, now);
if (req->end_io) {
- wbt_done(req->q->rq_wb, &req->issue_stat);
+ wbt_done(req->q->rq_wb, req);
req->end_io(req, error);
} else {
if (blk_bidi_rq(req))
@@ -3518,7 +3511,7 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
struct bio *bio, *bio_src;
if (!bs)
- bs = fs_bio_set;
+ bs = &fs_bio_set;
__rq_for_each_bio(bio_src, rq_src) {
bio = bio_clone_fast(bio_src, gfp_mask, bs);
@@ -3629,7 +3622,7 @@ static void queue_unplugged(struct request_queue *q, unsigned int depth,
blk_run_queue_async(q);
else
__blk_run_queue(q);
- spin_unlock(q->queue_lock);
+ spin_unlock_irq(q->queue_lock);
}
static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule)
@@ -3677,7 +3670,6 @@ EXPORT_SYMBOL(blk_check_plugged);
void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
{
struct request_queue *q;
- unsigned long flags;
struct request *rq;
LIST_HEAD(list);
unsigned int depth;
@@ -3697,11 +3689,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
q = NULL;
depth = 0;
- /*
- * Save and disable interrupts here, to avoid doing it for every
- * queue lock we have to take.
- */
- local_irq_save(flags);
while (!list_empty(&list)) {
rq = list_entry_rq(list.next);
list_del_init(&rq->queuelist);
@@ -3714,7 +3701,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
queue_unplugged(q, depth, from_schedule);
q = rq->q;
depth = 0;
- spin_lock(q->queue_lock);
+ spin_lock_irq(q->queue_lock);
}
/*
@@ -3741,8 +3728,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
*/
if (q)
queue_unplugged(q, depth, from_schedule);
-
- local_irq_restore(flags);
}
void blk_finish_plug(struct blk_plug *plug)
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index feb3057..6121611 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -333,34 +333,34 @@ static ssize_t integrity_device_show(struct blk_integrity *bi, char *page)
}
static struct integrity_sysfs_entry integrity_format_entry = {
- .attr = { .name = "format", .mode = S_IRUGO },
+ .attr = { .name = "format", .mode = 0444 },
.show = integrity_format_show,
};
static struct integrity_sysfs_entry integrity_tag_size_entry = {
- .attr = { .name = "tag_size", .mode = S_IRUGO },
+ .attr = { .name = "tag_size", .mode = 0444 },
.show = integrity_tag_size_show,
};
static struct integrity_sysfs_entry integrity_interval_entry = {
- .attr = { .name = "protection_interval_bytes", .mode = S_IRUGO },
+ .attr = { .name = "protection_interval_bytes", .mode = 0444 },
.show = integrity_interval_show,
};
static struct integrity_sysfs_entry integrity_verify_entry = {
- .attr = { .name = "read_verify", .mode = S_IRUGO | S_IWUSR },
+ .attr = { .name = "read_verify", .mode = 0644 },
.show = integrity_verify_show,
.store = integrity_verify_store,
};
static struct integrity_sysfs_entry integrity_generate_entry = {
- .attr = { .name = "write_generate", .mode = S_IRUGO | S_IWUSR },
+ .attr = { .name = "write_generate", .mode = 0644 },
.show = integrity_generate_show,
.store = integrity_generate_store,
};
static struct integrity_sysfs_entry integrity_device_entry = {
- .attr = { .name = "device_is_integrity_capable", .mode = S_IRUGO },
+ .attr = { .name = "device_is_integrity_capable", .mode = 0444 },
.show = integrity_device_show,
};
diff --git a/block/blk-lib.c b/block/blk-lib.c
index a676084d..8faa70f 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -62,10 +62,16 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
unsigned int req_sects;
sector_t end_sect, tmp;
- /* Make sure bi_size doesn't overflow */
- req_sects = min_t(sector_t, nr_sects, UINT_MAX >> 9);
+ /*
+ * Issue in chunks of the user defined max discard setting,
+ * ensuring that bi_size doesn't overflow
+ */
+ req_sects = min_t(sector_t, nr_sects,
+ q->limits.max_discard_sectors);
+ if (req_sects > UINT_MAX >> 9)
+ req_sects = UINT_MAX >> 9;
- /**
+ /*
* If splitting a request, and the next starting sector would be
* misaligned, stop the discard at the previous aligned sector.
*/
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 782940c..aaec38c 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -188,16 +188,16 @@ void blk_queue_split(struct request_queue *q, struct bio **bio)
switch (bio_op(*bio)) {
case REQ_OP_DISCARD:
case REQ_OP_SECURE_ERASE:
- split = blk_bio_discard_split(q, *bio, q->bio_split, &nsegs);
+ split = blk_bio_discard_split(q, *bio, &q->bio_split, &nsegs);
break;
case REQ_OP_WRITE_ZEROES:
- split = blk_bio_write_zeroes_split(q, *bio, q->bio_split, &nsegs);
+ split = blk_bio_write_zeroes_split(q, *bio, &q->bio_split, &nsegs);
break;
case REQ_OP_WRITE_SAME:
- split = blk_bio_write_same_split(q, *bio, q->bio_split, &nsegs);
+ split = blk_bio_write_same_split(q, *bio, &q->bio_split, &nsegs);
break;
default:
- split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs);
+ split = blk_bio_segment_split(q, *bio, &q->bio_split, &nsegs);
break;
}
@@ -210,6 +210,16 @@ void blk_queue_split(struct request_queue *q, struct bio **bio)
/* there isn't chance to merge the splitted bio */
split->bi_opf |= REQ_NOMERGE;
+ /*
+ * Since we're recursing into make_request here, ensure
+ * that we mark this bio as already having entered the queue.
+ * If not, and the queue is going away, we can get stuck
+ * forever on waiting for the queue reference to drop. But
+ * that will never happen, as we're already holding a
+ * reference to it.
+ */
+ bio_set_flag(*bio, BIO_QUEUE_ENTERED);
+
bio_chain(split, *bio);
trace_block_split(q, split, (*bio)->bi_iter.bi_sector);
generic_make_request(*bio);
@@ -724,13 +734,12 @@ static struct request *attempt_merge(struct request_queue *q,
}
/*
- * At this point we have either done a back merge
- * or front merge. We need the smaller start_time of
- * the merged requests to be the current request
- * for accounting purposes.
+ * At this point we have either done a back merge or front merge. We
+ * need the smaller start_time_ns of the merged requests to be the
+ * current request for accounting purposes.
*/
- if (time_after(req->start_time, next->start_time))
- req->start_time = next->start_time;
+ if (next->start_time_ns < req->start_time_ns)
+ req->start_time_ns = next->start_time_ns;
req->biotail->bi_next = next->bio;
req->biotail = next->biotail;
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 3080e18..ffa6223 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -344,7 +344,6 @@ static const char *const rqf_name[] = {
RQF_NAME(STATS),
RQF_NAME(SPECIAL_PAYLOAD),
RQF_NAME(ZONE_WRITE_LOCKED),
- RQF_NAME(MQ_TIMEOUT_EXPIRED),
RQF_NAME(MQ_POLL_SLEPT),
};
#undef RQF_NAME
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 25c14c5..56c493c 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -268,19 +268,16 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);
/*
- * Reverse check our software queue for entries that we could potentially
- * merge with. Currently includes a hand-wavy stop count of 8, to not spend
- * too much time checking for merges.
+ * Iterate list of requests and see if we can merge this bio with any
+ * of them.
*/
-static bool blk_mq_attempt_merge(struct request_queue *q,
- struct blk_mq_ctx *ctx, struct bio *bio)
+bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
+ struct bio *bio)
{
struct request *rq;
int checked = 8;
- lockdep_assert_held(&ctx->lock);
-
- list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) {
+ list_for_each_entry_reverse(rq, list, queuelist) {
bool merged = false;
if (!checked--)
@@ -305,13 +302,30 @@ static bool blk_mq_attempt_merge(struct request_queue *q,
continue;
}
- if (merged)
- ctx->rq_merged++;
return merged;
}
return false;
}
+EXPORT_SYMBOL_GPL(blk_mq_bio_list_merge);
+
+/*
+ * Reverse check our software queue for entries that we could potentially
+ * merge with. Currently includes a hand-wavy stop count of 8, to not spend
+ * too much time checking for merges.
+ */
+static bool blk_mq_attempt_merge(struct request_queue *q,
+ struct blk_mq_ctx *ctx, struct bio *bio)
+{
+ lockdep_assert_held(&ctx->lock);
+
+ if (blk_mq_bio_list_merge(q, &ctx->rq_list, bio)) {
+ ctx->rq_merged++;
+ return true;
+ }
+
+ return false;
+}
bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
{
@@ -571,6 +585,7 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
if (!e) {
q->elevator = NULL;
+ q->nr_requests = q->tag_set->queue_depth;
return 0;
}
@@ -633,14 +648,3 @@ void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e)
blk_mq_sched_tags_teardown(q);
q->elevator = NULL;
}
-
-int blk_mq_sched_init(struct request_queue *q)
-{
- int ret;
-
- mutex_lock(&q->sysfs_lock);
- ret = elevator_init(q, NULL);
- mutex_unlock(&q->sysfs_lock);
-
- return ret;
-}
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index 1e9c901..0cb8f93 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -33,8 +33,6 @@ int blk_mq_sched_init_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
unsigned int hctx_idx);
-int blk_mq_sched_init(struct request_queue *q);
-
static inline bool
blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
{
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index a54b4b0..aafb442 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -166,15 +166,15 @@ static struct attribute *default_ctx_attrs[] = {
};
static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_tags = {
- .attr = {.name = "nr_tags", .mode = S_IRUGO },
+ .attr = {.name = "nr_tags", .mode = 0444 },
.show = blk_mq_hw_sysfs_nr_tags_show,
};
static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_reserved_tags = {
- .attr = {.name = "nr_reserved_tags", .mode = S_IRUGO },
+ .attr = {.name = "nr_reserved_tags", .mode = 0444 },
.show = blk_mq_hw_sysfs_nr_reserved_tags_show,
};
static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_cpus = {
- .attr = {.name = "cpu_list", .mode = S_IRUGO },
+ .attr = {.name = "cpu_list", .mode = 0444 },
.show = blk_mq_hw_sysfs_cpus_show,
};
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 336dde0..70356a2a 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -134,6 +134,8 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
ws = bt_wait_ptr(bt, data->hctx);
drop_ctx = data->ctx == NULL;
do {
+ struct sbitmap_queue *bt_prev;
+
/*
* We're out of tags on this hardware queue, kick any
* pending IO submits before going to sleep waiting for
@@ -159,6 +161,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
if (data->ctx)
blk_mq_put_ctx(data->ctx);
+ bt_prev = bt;
io_schedule();
data->ctx = blk_mq_get_ctx(data->q);
@@ -170,6 +173,15 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
bt = &tags->bitmap_tags;
finish_wait(&ws->wait, &wait);
+
+ /*
+ * If destination hw queue is changed, fake wake up on
+ * previous queue for compensating the wake up miss, so
+ * other allocations on previous queue won't be starved.
+ */
+ if (bt != bt_prev)
+ sbitmap_queue_wake_up(bt_prev);
+
ws = bt_wait_ptr(bt, data->hctx);
} while (1);
@@ -259,7 +271,7 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
* test and set the bit before assining ->rqs[].
*/
rq = tags->rqs[bitnr];
- if (rq)
+ if (rq && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT)
iter_data->fn(rq, iter_data->data, reserved);
return true;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 0dc9e34..d2de0a7 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -95,18 +95,15 @@ static void blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
{
struct mq_inflight *mi = priv;
- if (blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT) {
- /*
- * index[0] counts the specific partition that was asked
- * for. index[1] counts the ones that are active on the
- * whole device, so increment that if mi->part is indeed
- * a partition, and not a whole device.
- */
- if (rq->part == mi->part)
- mi->inflight[0]++;
- if (mi->part->partno)
- mi->inflight[1]++;
- }
+ /*
+ * index[0] counts the specific partition that was asked for. index[1]
+ * counts the ones that are active on the whole device, so increment
+ * that if mi->part is indeed a partition, and not a whole device.
+ */
+ if (rq->part == mi->part)
+ mi->inflight[0]++;
+ if (mi->part->partno)
+ mi->inflight[1]++;
}
void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
@@ -118,6 +115,25 @@ void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
}
+static void blk_mq_check_inflight_rw(struct blk_mq_hw_ctx *hctx,
+ struct request *rq, void *priv,
+ bool reserved)
+{
+ struct mq_inflight *mi = priv;
+
+ if (rq->part == mi->part)
+ mi->inflight[rq_data_dir(rq)]++;
+}
+
+void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+ unsigned int inflight[2])
+{
+ struct mq_inflight mi = { .part = part, .inflight = inflight, };
+
+ inflight[0] = inflight[1] = 0;
+ blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight_rw, &mi);
+}
+
void blk_freeze_queue_start(struct request_queue *q)
{
int freeze_depth;
@@ -293,7 +309,8 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
RB_CLEAR_NODE(&rq->rb_node);
rq->rq_disk = NULL;
rq->part = NULL;
- rq->start_time = jiffies;
+ rq->start_time_ns = ktime_get_ns();
+ rq->io_start_time_ns = 0;
rq->nr_phys_segments = 0;
#if defined(CONFIG_BLK_DEV_INTEGRITY)
rq->nr_integrity_segments = 0;
@@ -312,11 +329,10 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
#ifdef CONFIG_BLK_CGROUP
rq->rl = NULL;
- set_start_time_ns(rq);
- rq->io_start_time_ns = 0;
#endif
data->ctx->rq_dispatched[op_is_sync(op)]++;
+ refcount_set(&rq->ref, 1);
return rq;
}
@@ -345,9 +361,11 @@ static struct request *blk_mq_get_request(struct request_queue *q,
/*
* Flush requests are special and go directly to the
- * dispatch list.
+ * dispatch list. Don't include reserved tags in the
+ * limiting, as it isn't useful.
*/
- if (!op_is_flush(op) && e->type->ops.mq.limit_depth)
+ if (!op_is_flush(op) && e->type->ops.mq.limit_depth &&
+ !(data->flags & BLK_MQ_REQ_RESERVED))
e->type->ops.mq.limit_depth(op, data);
}
@@ -448,13 +466,27 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
}
EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
+static void __blk_mq_free_request(struct request *rq)
+{
+ struct request_queue *q = rq->q;
+ struct blk_mq_ctx *ctx = rq->mq_ctx;
+ struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+ const int sched_tag = rq->internal_tag;
+
+ if (rq->tag != -1)
+ blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
+ if (sched_tag != -1)
+ blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag);
+ blk_mq_sched_restart(hctx);
+ blk_queue_exit(q);
+}
+
void blk_mq_free_request(struct request *rq)
{
struct request_queue *q = rq->q;
struct elevator_queue *e = q->elevator;
struct blk_mq_ctx *ctx = rq->mq_ctx;
struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
- const int sched_tag = rq->internal_tag;
if (rq->rq_flags & RQF_ELVPRIV) {
if (e && e->type->ops.mq.finish_request)
@@ -472,27 +504,30 @@ void blk_mq_free_request(struct request *rq)
if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
laptop_io_completion(q->backing_dev_info);
- wbt_done(q->rq_wb, &rq->issue_stat);
+ wbt_done(q->rq_wb, rq);
if (blk_rq_rl(rq))
blk_put_rl(blk_rq_rl(rq));
- blk_mq_rq_update_state(rq, MQ_RQ_IDLE);
- if (rq->tag != -1)
- blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
- if (sched_tag != -1)
- blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag);
- blk_mq_sched_restart(hctx);
- blk_queue_exit(q);
+ WRITE_ONCE(rq->state, MQ_RQ_IDLE);
+ if (refcount_dec_and_test(&rq->ref))
+ __blk_mq_free_request(rq);
}
EXPORT_SYMBOL_GPL(blk_mq_free_request);
inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
{
- blk_account_io_done(rq);
+ u64 now = ktime_get_ns();
+
+ if (rq->rq_flags & RQF_STATS) {
+ blk_mq_poll_stats_start(rq->q);
+ blk_stat_add(rq, now);
+ }
+
+ blk_account_io_done(rq, now);
if (rq->end_io) {
- wbt_done(rq->q->rq_wb, &rq->issue_stat);
+ wbt_done(rq->q->rq_wb, rq);
rq->end_io(rq, error);
} else {
if (unlikely(blk_bidi_rq(rq)))
@@ -523,15 +558,12 @@ static void __blk_mq_complete_request(struct request *rq)
bool shared = false;
int cpu;
- WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT);
- blk_mq_rq_update_state(rq, MQ_RQ_COMPLETE);
+ if (cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) !=
+ MQ_RQ_IN_FLIGHT)
+ return;
if (rq->internal_tag != -1)
blk_mq_sched_completed_request(rq);
- if (rq->rq_flags & RQF_STATS) {
- blk_mq_poll_stats_start(rq->q);
- blk_stat_add(rq);
- }
if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) {
rq->q->softirq_done_fn(rq);
@@ -573,36 +605,6 @@ static void hctx_lock(struct blk_mq_hw_ctx *hctx, int *srcu_idx)
*srcu_idx = srcu_read_lock(hctx->srcu);
}
-static void blk_mq_rq_update_aborted_gstate(struct request *rq, u64 gstate)
-{
- unsigned long flags;
-
- /*
- * blk_mq_rq_aborted_gstate() is used from the completion path and
- * can thus be called from irq context. u64_stats_fetch in the
- * middle of update on the same CPU leads to lockup. Disable irq
- * while updating.
- */
- local_irq_save(flags);
- u64_stats_update_begin(&rq->aborted_gstate_sync);
- rq->aborted_gstate = gstate;
- u64_stats_update_end(&rq->aborted_gstate_sync);
- local_irq_restore(flags);
-}
-
-static u64 blk_mq_rq_aborted_gstate(struct request *rq)
-{
- unsigned int start;
- u64 aborted_gstate;
-
- do {
- start = u64_stats_fetch_begin(&rq->aborted_gstate_sync);
- aborted_gstate = rq->aborted_gstate;
- } while (u64_stats_fetch_retry(&rq->aborted_gstate_sync, start));
-
- return aborted_gstate;
-}
-
/**
* blk_mq_complete_request - end I/O on a request
* @rq: the request being processed
@@ -613,28 +615,9 @@ static u64 blk_mq_rq_aborted_gstate(struct request *rq)
**/
void blk_mq_complete_request(struct request *rq)
{
- struct request_queue *q = rq->q;
- struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu);
- int srcu_idx;
-
- if (unlikely(blk_should_fake_timeout(q)))
+ if (unlikely(blk_should_fake_timeout(rq->q)))
return;
-
- /*
- * If @rq->aborted_gstate equals the current instance, timeout is
- * claiming @rq and we lost. This is synchronized through
- * hctx_lock(). See blk_mq_timeout_work() for details.
- *
- * Completion path never blocks and we can directly use RCU here
- * instead of hctx_lock() which can be either RCU or SRCU.
- * However, that would complicate paths which want to synchronize
- * against us. Let stay in sync with the issue path so that
- * hctx_lock() covers both issue and completion paths.
- */
- hctx_lock(hctx, &srcu_idx);
- if (blk_mq_rq_aborted_gstate(rq) != rq->gstate)
- __blk_mq_complete_request(rq);
- hctx_unlock(hctx, srcu_idx);
+ __blk_mq_complete_request(rq);
}
EXPORT_SYMBOL(blk_mq_complete_request);
@@ -653,32 +636,18 @@ void blk_mq_start_request(struct request *rq)
trace_block_rq_issue(q, rq);
if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
- blk_stat_set_issue(&rq->issue_stat, blk_rq_sectors(rq));
+ rq->io_start_time_ns = ktime_get_ns();
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+ rq->throtl_size = blk_rq_sectors(rq);
+#endif
rq->rq_flags |= RQF_STATS;
- wbt_issue(q->rq_wb, &rq->issue_stat);
+ wbt_issue(q->rq_wb, rq);
}
WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE);
- /*
- * Mark @rq in-flight which also advances the generation number,
- * and register for timeout. Protect with a seqcount to allow the
- * timeout path to read both @rq->gstate and @rq->deadline
- * coherently.
- *
- * This is the only place where a request is marked in-flight. If
- * the timeout path reads an in-flight @rq->gstate, the
- * @rq->deadline it reads together under @rq->gstate_seq is
- * guaranteed to be the matching one.
- */
- preempt_disable();
- write_seqcount_begin(&rq->gstate_seq);
-
- blk_mq_rq_update_state(rq, MQ_RQ_IN_FLIGHT);
blk_add_timer(rq);
-
- write_seqcount_end(&rq->gstate_seq);
- preempt_enable();
+ WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT);
if (q->dma_drain_size && blk_rq_bytes(rq)) {
/*
@@ -691,11 +660,6 @@ void blk_mq_start_request(struct request *rq)
}
EXPORT_SYMBOL(blk_mq_start_request);
-/*
- * When we reach here because queue is busy, it's safe to change the state
- * to IDLE without checking @rq->aborted_gstate because we should still be
- * holding the RCU read lock and thus protected against timeout.
- */
static void __blk_mq_requeue_request(struct request *rq)
{
struct request_queue *q = rq->q;
@@ -703,10 +667,10 @@ static void __blk_mq_requeue_request(struct request *rq)
blk_mq_put_driver_tag(rq);
trace_block_rq_requeue(q, rq);
- wbt_requeue(q->rq_wb, &rq->issue_stat);
+ wbt_requeue(q->rq_wb, rq);
- if (blk_mq_rq_state(rq) != MQ_RQ_IDLE) {
- blk_mq_rq_update_state(rq, MQ_RQ_IDLE);
+ if (blk_mq_request_started(rq)) {
+ WRITE_ONCE(rq->state, MQ_RQ_IDLE);
if (q->dma_drain_size && blk_rq_bytes(rq))
rq->nr_phys_segments--;
}
@@ -804,101 +768,79 @@ struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag)
}
EXPORT_SYMBOL(blk_mq_tag_to_rq);
-struct blk_mq_timeout_data {
- unsigned long next;
- unsigned int next_set;
- unsigned int nr_expired;
-};
-
static void blk_mq_rq_timed_out(struct request *req, bool reserved)
{
- const struct blk_mq_ops *ops = req->q->mq_ops;
- enum blk_eh_timer_return ret = BLK_EH_RESET_TIMER;
+ if (req->q->mq_ops->timeout) {
+ enum blk_eh_timer_return ret;
- req->rq_flags |= RQF_MQ_TIMEOUT_EXPIRED;
-
- if (ops->timeout)
- ret = ops->timeout(req, reserved);
-
- switch (ret) {
- case BLK_EH_HANDLED:
- __blk_mq_complete_request(req);
- break;
- case BLK_EH_RESET_TIMER:
- /*
- * As nothing prevents from completion happening while
- * ->aborted_gstate is set, this may lead to ignored
- * completions and further spurious timeouts.
- */
- blk_mq_rq_update_aborted_gstate(req, 0);
- blk_add_timer(req);
- break;
- case BLK_EH_NOT_HANDLED:
- break;
- default:
- printk(KERN_ERR "block: bad eh return: %d\n", ret);
- break;
+ ret = req->q->mq_ops->timeout(req, reserved);
+ if (ret == BLK_EH_DONE)
+ return;
+ WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER);
}
+
+ blk_add_timer(req);
+}
+
+static bool blk_mq_req_expired(struct request *rq, unsigned long *next)
+{
+ unsigned long deadline;
+
+ if (blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT)
+ return false;
+
+ deadline = blk_rq_deadline(rq);
+ if (time_after_eq(jiffies, deadline))
+ return true;
+
+ if (*next == 0)
+ *next = deadline;
+ else if (time_after(*next, deadline))
+ *next = deadline;
+ return false;
}
static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
struct request *rq, void *priv, bool reserved)
{
- struct blk_mq_timeout_data *data = priv;
- unsigned long gstate, deadline;
- int start;
+ unsigned long *next = priv;
- might_sleep();
-
- if (rq->rq_flags & RQF_MQ_TIMEOUT_EXPIRED)
+ /*
+ * Just do a quick check if it is expired before locking the request in
+ * so we're not unnecessarilly synchronizing across CPUs.
+ */
+ if (!blk_mq_req_expired(rq, next))
return;
- /* read coherent snapshots of @rq->state_gen and @rq->deadline */
- while (true) {
- start = read_seqcount_begin(&rq->gstate_seq);
- gstate = READ_ONCE(rq->gstate);
- deadline = blk_rq_deadline(rq);
- if (!read_seqcount_retry(&rq->gstate_seq, start))
- break;
- cond_resched();
- }
-
- /* if in-flight && overdue, mark for abortion */
- if ((gstate & MQ_RQ_STATE_MASK) == MQ_RQ_IN_FLIGHT &&
- time_after_eq(jiffies, deadline)) {
- blk_mq_rq_update_aborted_gstate(rq, gstate);
- data->nr_expired++;
- hctx->nr_expired++;
- } else if (!data->next_set || time_after(data->next, deadline)) {
- data->next = deadline;
- data->next_set = 1;
- }
-}
-
-static void blk_mq_terminate_expired(struct blk_mq_hw_ctx *hctx,
- struct request *rq, void *priv, bool reserved)
-{
/*
- * We marked @rq->aborted_gstate and waited for RCU. If there were
- * completions that we lost to, they would have finished and
- * updated @rq->gstate by now; otherwise, the completion path is
- * now guaranteed to see @rq->aborted_gstate and yield. If
- * @rq->aborted_gstate still matches @rq->gstate, @rq is ours.
+ * We have reason to believe the request may be expired. Take a
+ * reference on the request to lock this request lifetime into its
+ * currently allocated context to prevent it from being reallocated in
+ * the event the completion by-passes this timeout handler.
+ *
+ * If the reference was already released, then the driver beat the
+ * timeout handler to posting a natural completion.
*/
- if (!(rq->rq_flags & RQF_MQ_TIMEOUT_EXPIRED) &&
- READ_ONCE(rq->gstate) == rq->aborted_gstate)
+ if (!refcount_inc_not_zero(&rq->ref))
+ return;
+
+ /*
+ * The request is now locked and cannot be reallocated underneath the
+ * timeout handler's processing. Re-verify this exact request is truly
+ * expired; if it is not expired, then the request was completed and
+ * reallocated as a new request.
+ */
+ if (blk_mq_req_expired(rq, next))
blk_mq_rq_timed_out(rq, reserved);
+ if (refcount_dec_and_test(&rq->ref))
+ __blk_mq_free_request(rq);
}
static void blk_mq_timeout_work(struct work_struct *work)
{
struct request_queue *q =
container_of(work, struct request_queue, timeout_work);
- struct blk_mq_timeout_data data = {
- .next = 0,
- .next_set = 0,
- .nr_expired = 0,
- };
+ unsigned long next = 0;
struct blk_mq_hw_ctx *hctx;
int i;
@@ -918,39 +860,10 @@ static void blk_mq_timeout_work(struct work_struct *work)
if (!percpu_ref_tryget(&q->q_usage_counter))
return;
- /* scan for the expired ones and set their ->aborted_gstate */
- blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &data);
+ blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &next);
- if (data.nr_expired) {
- bool has_rcu = false;
-
- /*
- * Wait till everyone sees ->aborted_gstate. The
- * sequential waits for SRCUs aren't ideal. If this ever
- * becomes a problem, we can add per-hw_ctx rcu_head and
- * wait in parallel.
- */
- queue_for_each_hw_ctx(q, hctx, i) {
- if (!hctx->nr_expired)
- continue;
-
- if (!(hctx->flags & BLK_MQ_F_BLOCKING))
- has_rcu = true;
- else
- synchronize_srcu(hctx->srcu);
-
- hctx->nr_expired = 0;
- }
- if (has_rcu)
- synchronize_rcu();
-
- /* terminate the ones we won */
- blk_mq_queue_tag_busy_iter(q, blk_mq_terminate_expired, NULL);
- }
-
- if (data.next_set) {
- data.next = blk_rq_timeout(round_jiffies_up(data.next));
- mod_timer(&q->timeout, data.next);
+ if (next != 0) {
+ mod_timer(&q->timeout, next);
} else {
/*
* Request timeouts are handled as a forward rolling timer. If
@@ -1013,7 +926,7 @@ static bool dispatch_rq_from_ctx(struct sbitmap *sb, unsigned int bitnr,
struct blk_mq_ctx *ctx = hctx->ctxs[bitnr];
spin_lock(&ctx->lock);
- if (unlikely(!list_empty(&ctx->rq_list))) {
+ if (!list_empty(&ctx->rq_list)) {
dispatch_data->rq = list_entry_rq(ctx->rq_list.next);
list_del_init(&dispatch_data->rq->queuelist);
if (list_empty(&ctx->rq_list))
@@ -1562,7 +1475,7 @@ static void blk_mq_run_work_fn(struct work_struct *work)
* If we are stopped, don't run the queue.
*/
if (test_bit(BLK_MQ_S_STOPPED, &hctx->state))
- clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
+ return;
__blk_mq_run_hw_queue(hctx);
}
@@ -1700,15 +1613,6 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio)
blk_account_io_start(rq, true);
}
-static inline void blk_mq_queue_io(struct blk_mq_hw_ctx *hctx,
- struct blk_mq_ctx *ctx,
- struct request *rq)
-{
- spin_lock(&ctx->lock);
- __blk_mq_insert_request(hctx, rq, false);
- spin_unlock(&ctx->lock);
-}
-
static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq)
{
if (rq->tag != -1)
@@ -1866,7 +1770,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
return BLK_QC_T_NONE;
}
- wbt_track(&rq->issue_stat, wb_acct);
+ wbt_track(rq, wb_acct);
cookie = request_to_qc_t(data.hctx, rq);
@@ -1933,15 +1837,10 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
blk_mq_put_ctx(data.ctx);
blk_mq_bio_to_request(rq, bio);
blk_mq_try_issue_directly(data.hctx, rq, &cookie);
- } else if (q->elevator) {
- blk_mq_put_ctx(data.ctx);
- blk_mq_bio_to_request(rq, bio);
- blk_mq_sched_insert_request(rq, false, true, true);
} else {
blk_mq_put_ctx(data.ctx);
blk_mq_bio_to_request(rq, bio);
- blk_mq_queue_io(data.hctx, data.ctx, rq);
- blk_mq_run_hw_queue(data.hctx, true);
+ blk_mq_sched_insert_request(rq, false, true, true);
}
return cookie;
@@ -2040,8 +1939,7 @@ static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
return ret;
}
- seqcount_init(&rq->gstate_seq);
- u64_stats_init(&rq->aborted_gstate_sync);
+ WRITE_ONCE(rq->state, MQ_RQ_IDLE);
return 0;
}
@@ -2329,7 +2227,7 @@ static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set,
static void blk_mq_map_swqueue(struct request_queue *q)
{
- unsigned int i;
+ unsigned int i, hctx_idx;
struct blk_mq_hw_ctx *hctx;
struct blk_mq_ctx *ctx;
struct blk_mq_tag_set *set = q->tag_set;
@@ -2342,12 +2240,28 @@ static void blk_mq_map_swqueue(struct request_queue *q)
queue_for_each_hw_ctx(q, hctx, i) {
cpumask_clear(hctx->cpumask);
hctx->nr_ctx = 0;
+ hctx->dispatch_from = NULL;
}
/*
* Map software to hardware queues.
+ *
+ * If the cpu isn't present, the cpu is mapped to first hctx.
*/
for_each_possible_cpu(i) {
+ hctx_idx = q->mq_map[i];
+ /* unmapped hw queue can be remapped after CPU topo changed */
+ if (!set->tags[hctx_idx] &&
+ !__blk_mq_alloc_rq_map(set, hctx_idx)) {
+ /*
+ * If tags initialization fail for some hctx,
+ * that hctx won't be brought online. In this
+ * case, remap the current ctx to hctx[0] which
+ * is guaranteed to always have tags allocated
+ */
+ q->mq_map[i] = 0;
+ }
+
ctx = per_cpu_ptr(q->queue_ctx, i);
hctx = blk_mq_map_queue(q, i);
@@ -2359,8 +2273,21 @@ static void blk_mq_map_swqueue(struct request_queue *q)
mutex_unlock(&q->sysfs_lock);
queue_for_each_hw_ctx(q, hctx, i) {
- /* every hctx should get mapped by at least one CPU */
- WARN_ON(!hctx->nr_ctx);
+ /*
+ * If no software queues are mapped to this hardware queue,
+ * disable it and free the request entries.
+ */
+ if (!hctx->nr_ctx) {
+ /* Never unmap queue 0. We need it as a
+ * fallback in case of a new remap fails
+ * allocation
+ */
+ if (i && set->tags[i])
+ blk_mq_free_map_and_requests(set, i);
+
+ hctx->tags = NULL;
+ continue;
+ }
hctx->tags = set->tags[i];
WARN_ON(!hctx->tags);
@@ -2646,7 +2573,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
if (!(set->flags & BLK_MQ_F_NO_SCHED)) {
int ret;
- ret = blk_mq_sched_init(q);
+ ret = elevator_init_mq(q);
if (ret)
return ERR_PTR(ret);
}
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 88c558f..89231e4 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -7,6 +7,9 @@
struct blk_mq_tag_set;
+/**
+ * struct blk_mq_ctx - State for a software queue facing the submitting CPUs
+ */
struct blk_mq_ctx {
struct {
spinlock_t lock;
@@ -27,20 +30,6 @@ struct blk_mq_ctx {
struct kobject kobj;
} ____cacheline_aligned_in_smp;
-/*
- * Bits for request->gstate. The lower two bits carry MQ_RQ_* state value
- * and the upper bits the generation number.
- */
-enum mq_rq_state {
- MQ_RQ_IDLE = 0,
- MQ_RQ_IN_FLIGHT = 1,
- MQ_RQ_COMPLETE = 2,
-
- MQ_RQ_STATE_BITS = 2,
- MQ_RQ_STATE_MASK = (1 << MQ_RQ_STATE_BITS) - 1,
- MQ_RQ_GEN_INC = 1 << MQ_RQ_STATE_BITS,
-};
-
void blk_mq_freeze_queue(struct request_queue *q);
void blk_mq_free_queue(struct request_queue *q);
int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
@@ -104,33 +93,9 @@ void blk_mq_release(struct request_queue *q);
* blk_mq_rq_state() - read the current MQ_RQ_* state of a request
* @rq: target request.
*/
-static inline int blk_mq_rq_state(struct request *rq)
+static inline enum mq_rq_state blk_mq_rq_state(struct request *rq)
{
- return READ_ONCE(rq->gstate) & MQ_RQ_STATE_MASK;
-}
-
-/**
- * blk_mq_rq_update_state() - set the current MQ_RQ_* state of a request
- * @rq: target request.
- * @state: new state to set.
- *
- * Set @rq's state to @state. The caller is responsible for ensuring that
- * there are no other updaters. A request can transition into IN_FLIGHT
- * only from IDLE and doing so increments the generation number.
- */
-static inline void blk_mq_rq_update_state(struct request *rq,
- enum mq_rq_state state)
-{
- u64 old_val = READ_ONCE(rq->gstate);
- u64 new_val = (old_val & ~MQ_RQ_STATE_MASK) | state;
-
- if (state == MQ_RQ_IN_FLIGHT) {
- WARN_ON_ONCE((old_val & MQ_RQ_STATE_MASK) != MQ_RQ_IDLE);
- new_val += MQ_RQ_GEN_INC;
- }
-
- /* avoid exposing interim values */
- WRITE_ONCE(rq->gstate, new_val);
+ return READ_ONCE(rq->state);
}
static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
@@ -185,7 +150,9 @@ static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx)
}
void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
- unsigned int inflight[2]);
+ unsigned int inflight[2]);
+void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+ unsigned int inflight[2]);
static inline void blk_mq_put_dispatch_budget(struct blk_mq_hw_ctx *hctx)
{
diff --git a/block/blk-stat.c b/block/blk-stat.c
index bd365a9..175c143 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -47,19 +47,15 @@ static void __blk_stat_add(struct blk_rq_stat *stat, u64 value)
stat->nr_samples++;
}
-void blk_stat_add(struct request *rq)
+void blk_stat_add(struct request *rq, u64 now)
{
struct request_queue *q = rq->q;
struct blk_stat_callback *cb;
struct blk_rq_stat *stat;
int bucket;
- u64 now, value;
+ u64 value;
- now = __blk_stat_time(ktime_to_ns(ktime_get()));
- if (now < blk_stat_time(&rq->issue_stat))
- return;
-
- value = now - blk_stat_time(&rq->issue_stat);
+ value = (now >= rq->io_start_time_ns) ? now - rq->io_start_time_ns : 0;
blk_throtl_stat_add(rq, value);
diff --git a/block/blk-stat.h b/block/blk-stat.h
index 2dd3634..78399cd 100644
--- a/block/blk-stat.h
+++ b/block/blk-stat.h
@@ -8,21 +8,6 @@
#include <linux/rcupdate.h>
#include <linux/timer.h>
-/*
- * from upper:
- * 3 bits: reserved for other usage
- * 12 bits: size
- * 49 bits: time
- */
-#define BLK_STAT_RES_BITS 3
-#define BLK_STAT_SIZE_BITS 12
-#define BLK_STAT_RES_SHIFT (64 - BLK_STAT_RES_BITS)
-#define BLK_STAT_SIZE_SHIFT (BLK_STAT_RES_SHIFT - BLK_STAT_SIZE_BITS)
-#define BLK_STAT_TIME_MASK ((1ULL << BLK_STAT_SIZE_SHIFT) - 1)
-#define BLK_STAT_SIZE_MASK \
- (((1ULL << BLK_STAT_SIZE_BITS) - 1) << BLK_STAT_SIZE_SHIFT)
-#define BLK_STAT_RES_MASK (~((1ULL << BLK_STAT_RES_SHIFT) - 1))
-
/**
* struct blk_stat_callback - Block statistics callback.
*
@@ -80,35 +65,7 @@ struct blk_stat_callback {
struct blk_queue_stats *blk_alloc_queue_stats(void);
void blk_free_queue_stats(struct blk_queue_stats *);
-void blk_stat_add(struct request *);
-
-static inline u64 __blk_stat_time(u64 time)
-{
- return time & BLK_STAT_TIME_MASK;
-}
-
-static inline u64 blk_stat_time(struct blk_issue_stat *stat)
-{
- return __blk_stat_time(stat->stat);
-}
-
-static inline sector_t blk_capped_size(sector_t size)
-{
- return size & ((1ULL << BLK_STAT_SIZE_BITS) - 1);
-}
-
-static inline sector_t blk_stat_size(struct blk_issue_stat *stat)
-{
- return (stat->stat & BLK_STAT_SIZE_MASK) >> BLK_STAT_SIZE_SHIFT;
-}
-
-static inline void blk_stat_set_issue(struct blk_issue_stat *stat,
- sector_t size)
-{
- stat->stat = (stat->stat & BLK_STAT_RES_MASK) |
- (ktime_to_ns(ktime_get()) & BLK_STAT_TIME_MASK) |
- (((u64)blk_capped_size(size)) << BLK_STAT_SIZE_SHIFT);
-}
+void blk_stat_add(struct request *rq, u64 now);
/* record time/size info in request but not add a callback */
void blk_stat_enable_accounting(struct request_queue *q);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index d00d1b0..94987b1 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -491,188 +491,198 @@ static ssize_t queue_wc_store(struct request_queue *q, const char *page,
return count;
}
+static ssize_t queue_fua_show(struct request_queue *q, char *page)
+{
+ return sprintf(page, "%u\n", test_bit(QUEUE_FLAG_FUA, &q->queue_flags));
+}
+
static ssize_t queue_dax_show(struct request_queue *q, char *page)
{
return queue_var_show(blk_queue_dax(q), page);
}
static struct queue_sysfs_entry queue_requests_entry = {
- .attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
+ .attr = {.name = "nr_requests", .mode = 0644 },
.show = queue_requests_show,
.store = queue_requests_store,
};
static struct queue_sysfs_entry queue_ra_entry = {
- .attr = {.name = "read_ahead_kb", .mode = S_IRUGO | S_IWUSR },
+ .attr = {.name = "read_ahead_kb", .mode = 0644 },
.show = queue_ra_show,
.store = queue_ra_store,
};
static struct queue_sysfs_entry queue_max_sectors_entry = {
- .attr = {.name = "max_sectors_kb", .mode = S_IRUGO | S_IWUSR },
+ .attr = {.name = "max_sectors_kb", .mode = 0644 },
.show = queue_max_sectors_show,
.store = queue_max_sectors_store,
};
static struct queue_sysfs_entry queue_max_hw_sectors_entry = {
- .attr = {.name = "max_hw_sectors_kb", .mode = S_IRUGO },
+ .attr = {.name = "max_hw_sectors_kb", .mode = 0444 },
.show = queue_max_hw_sectors_show,
};
static struct queue_sysfs_entry queue_max_segments_entry = {
- .attr = {.name = "max_segments", .mode = S_IRUGO },
+ .attr = {.name = "max_segments", .mode = 0444 },
.show = queue_max_segments_show,
};
static struct queue_sysfs_entry queue_max_discard_segments_entry = {
- .attr = {.name = "max_discard_segments", .mode = S_IRUGO },
+ .attr = {.name = "max_discard_segments", .mode = 0444 },
.show = queue_max_discard_segments_show,
};
static struct queue_sysfs_entry queue_max_integrity_segments_entry = {
- .attr = {.name = "max_integrity_segments", .mode = S_IRUGO },
+ .attr = {.name = "max_integrity_segments", .mode = 0444 },
.show = queue_max_integrity_segments_show,
};
static struct queue_sysfs_entry queue_max_segment_size_entry = {
- .attr = {.name = "max_segment_size", .mode = S_IRUGO },
+ .attr = {.name = "max_segment_size", .mode = 0444 },
.show = queue_max_segment_size_show,
};
static struct queue_sysfs_entry queue_iosched_entry = {
- .attr = {.name = "scheduler", .mode = S_IRUGO | S_IWUSR },
+ .attr = {.name = "scheduler", .mode = 0644 },
.show = elv_iosched_show,
.store = elv_iosched_store,
};
static struct queue_sysfs_entry queue_hw_sector_size_entry = {
- .attr = {.name = "hw_sector_size", .mode = S_IRUGO },
+ .attr = {.name = "hw_sector_size", .mode = 0444 },
.show = queue_logical_block_size_show,
};
static struct queue_sysfs_entry queue_logical_block_size_entry = {
- .attr = {.name = "logical_block_size", .mode = S_IRUGO },
+ .attr = {.name = "logical_block_size", .mode = 0444 },
.show = queue_logical_block_size_show,
};
static struct queue_sysfs_entry queue_physical_block_size_entry = {
- .attr = {.name = "physical_block_size", .mode = S_IRUGO },
+ .attr = {.name = "physical_block_size", .mode = 0444 },
.show = queue_physical_block_size_show,
};
static struct queue_sysfs_entry queue_chunk_sectors_entry = {
- .attr = {.name = "chunk_sectors", .mode = S_IRUGO },
+ .attr = {.name = "chunk_sectors", .mode = 0444 },
.show = queue_chunk_sectors_show,
};
static struct queue_sysfs_entry queue_io_min_entry = {
- .attr = {.name = "minimum_io_size", .mode = S_IRUGO },
+ .attr = {.name = "minimum_io_size", .mode = 0444 },
.show = queue_io_min_show,
};
static struct queue_sysfs_entry queue_io_opt_entry = {
- .attr = {.name = "optimal_io_size", .mode = S_IRUGO },
+ .attr = {.name = "optimal_io_size", .mode = 0444 },
.show = queue_io_opt_show,
};
static struct queue_sysfs_entry queue_discard_granularity_entry = {
- .attr = {.name = "discard_granularity", .mode = S_IRUGO },
+ .attr = {.name = "discard_granularity", .mode = 0444 },
.show = queue_discard_granularity_show,
};
static struct queue_sysfs_entry queue_discard_max_hw_entry = {
- .attr = {.name = "discard_max_hw_bytes", .mode = S_IRUGO },
+ .attr = {.name = "discard_max_hw_bytes", .mode = 0444 },
.show = queue_discard_max_hw_show,
};
static struct queue_sysfs_entry queue_discard_max_entry = {
- .attr = {.name = "discard_max_bytes", .mode = S_IRUGO | S_IWUSR },
+ .attr = {.name = "discard_max_bytes", .mode = 0644 },
.show = queue_discard_max_show,
.store = queue_discard_max_store,
};
static struct queue_sysfs_entry queue_discard_zeroes_data_entry = {
- .attr = {.name = "discard_zeroes_data", .mode = S_IRUGO },
+ .attr = {.name = "discard_zeroes_data", .mode = 0444 },
.show = queue_discard_zeroes_data_show,
};
static struct queue_sysfs_entry queue_write_same_max_entry = {
- .attr = {.name = "write_same_max_bytes", .mode = S_IRUGO },
+ .attr = {.name = "write_same_max_bytes", .mode = 0444 },
.show = queue_write_same_max_show,
};
static struct queue_sysfs_entry queue_write_zeroes_max_entry = {
- .attr = {.name = "write_zeroes_max_bytes", .mode = S_IRUGO },
+ .attr = {.name = "write_zeroes_max_bytes", .mode = 0444 },
.show = queue_write_zeroes_max_show,
};
static struct queue_sysfs_entry queue_nonrot_entry = {
- .attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR },
+ .attr = {.name = "rotational", .mode = 0644 },
.show = queue_show_nonrot,
.store = queue_store_nonrot,
};
static struct queue_sysfs_entry queue_zoned_entry = {
- .attr = {.name = "zoned", .mode = S_IRUGO },
+ .attr = {.name = "zoned", .mode = 0444 },
.show = queue_zoned_show,
};
static struct queue_sysfs_entry queue_nomerges_entry = {
- .attr = {.name = "nomerges", .mode = S_IRUGO | S_IWUSR },
+ .attr = {.name = "nomerges", .mode = 0644 },
.show = queue_nomerges_show,
.store = queue_nomerges_store,
};
static struct queue_sysfs_entry queue_rq_affinity_entry = {
- .attr = {.name = "rq_affinity", .mode = S_IRUGO | S_IWUSR },
+ .attr = {.name = "rq_affinity", .mode = 0644 },
.show = queue_rq_affinity_show,
.store = queue_rq_affinity_store,
};
static struct queue_sysfs_entry queue_iostats_entry = {
- .attr = {.name = "iostats", .mode = S_IRUGO | S_IWUSR },
+ .attr = {.name = "iostats", .mode = 0644 },
.show = queue_show_iostats,
.store = queue_store_iostats,
};
static struct queue_sysfs_entry queue_random_entry = {
- .attr = {.name = "add_random", .mode = S_IRUGO | S_IWUSR },
+ .attr = {.name = "add_random", .mode = 0644 },
.show = queue_show_random,
.store = queue_store_random,
};
static struct queue_sysfs_entry queue_poll_entry = {
- .attr = {.name = "io_poll", .mode = S_IRUGO | S_IWUSR },
+ .attr = {.name = "io_poll", .mode = 0644 },
.show = queue_poll_show,
.store = queue_poll_store,
};
static struct queue_sysfs_entry queue_poll_delay_entry = {
- .attr = {.name = "io_poll_delay", .mode = S_IRUGO | S_IWUSR },
+ .attr = {.name = "io_poll_delay", .mode = 0644 },
.show = queue_poll_delay_show,
.store = queue_poll_delay_store,
};
static struct queue_sysfs_entry queue_wc_entry = {
- .attr = {.name = "write_cache", .mode = S_IRUGO | S_IWUSR },
+ .attr = {.name = "write_cache", .mode = 0644 },
.show = queue_wc_show,
.store = queue_wc_store,
};
+static struct queue_sysfs_entry queue_fua_entry = {
+ .attr = {.name = "fua", .mode = 0444 },
+ .show = queue_fua_show,
+};
+
static struct queue_sysfs_entry queue_dax_entry = {
- .attr = {.name = "dax", .mode = S_IRUGO },
+ .attr = {.name = "dax", .mode = 0444 },
.show = queue_dax_show,
};
static struct queue_sysfs_entry queue_wb_lat_entry = {
- .attr = {.name = "wbt_lat_usec", .mode = S_IRUGO | S_IWUSR },
+ .attr = {.name = "wbt_lat_usec", .mode = 0644 },
.show = queue_wb_lat_show,
.store = queue_wb_lat_store,
};
#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
static struct queue_sysfs_entry throtl_sample_time_entry = {
- .attr = {.name = "throttle_sample_time", .mode = S_IRUGO | S_IWUSR },
+ .attr = {.name = "throttle_sample_time", .mode = 0644 },
.show = blk_throtl_sample_time_show,
.store = blk_throtl_sample_time_store,
};
@@ -708,6 +718,7 @@ static struct attribute *default_attrs[] = {
&queue_random_entry.attr,
&queue_poll_entry.attr,
&queue_wc_entry.attr,
+ &queue_fua_entry.attr,
&queue_dax_entry.attr,
&queue_wb_lat_entry.attr,
&queue_poll_delay_entry.attr,
@@ -813,8 +824,7 @@ static void __blk_release_queue(struct work_struct *work)
if (q->mq_ops)
blk_mq_debugfs_unregister(q);
- if (q->bio_split)
- bioset_free(q->bio_split);
+ bioset_exit(&q->bio_split);
ida_simple_remove(&blk_queue_ida, q->id);
call_rcu(&q->rcu_head, blk_free_queue_rcu);
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index c5a1316..82282e6 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -36,8 +36,6 @@ static int throtl_quantum = 32;
*/
#define LATENCY_FILTERED_HD (1000L) /* 1ms */
-#define SKIP_LATENCY (((u64)1) << BLK_STAT_RES_SHIFT)
-
static struct blkcg_policy blkcg_policy_throtl;
/* A workqueue to queue throttle related work */
@@ -821,7 +819,7 @@ static bool throtl_slice_used(struct throtl_grp *tg, bool rw)
if (time_in_range(jiffies, tg->slice_start[rw], tg->slice_end[rw]))
return false;
- return 1;
+ return true;
}
/* Trim the used slices and adjust slice start accordingly */
@@ -931,7 +929,7 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
if (wait)
*wait = jiffy_wait;
- return 0;
+ return false;
}
static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
@@ -974,7 +972,7 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
jiffy_wait = jiffy_wait + (jiffy_elapsed_rnd - jiffy_elapsed);
if (wait)
*wait = jiffy_wait;
- return 0;
+ return false;
}
/*
@@ -1024,7 +1022,7 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
tg_with_in_iops_limit(tg, bio, &iops_wait)) {
if (wait)
*wait = 0;
- return 1;
+ return true;
}
max_wait = max(bps_wait, iops_wait);
@@ -1035,7 +1033,7 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
if (time_before(tg->slice_end[rw], jiffies + max_wait))
throtl_extend_slice(tg, rw, jiffies + max_wait);
- return 0;
+ return false;
}
static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
@@ -1209,7 +1207,7 @@ static int throtl_select_dispatch(struct throtl_service_queue *parent_sq)
while (1) {
struct throtl_grp *tg = throtl_rb_first(parent_sq);
- struct throtl_service_queue *sq = &tg->service_queue;
+ struct throtl_service_queue *sq;
if (!tg)
break;
@@ -1221,6 +1219,7 @@ static int throtl_select_dispatch(struct throtl_service_queue *parent_sq)
nr_disp += throtl_dispatch_tg(tg);
+ sq = &tg->service_queue;
if (sq->nr_queued[0] || sq->nr_queued[1])
tg_update_disptime(tg);
@@ -2139,7 +2138,7 @@ static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio)
bio->bi_cg_private = tg;
blkg_get(tg_to_blkg(tg));
}
- blk_stat_set_issue(&bio->bi_issue_stat, bio_sectors(bio));
+ bio_issue_init(&bio->bi_issue, bio_sectors(bio));
#endif
}
@@ -2251,7 +2250,7 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
if (throttled || !td->track_bio_latency)
- bio->bi_issue_stat.stat |= SKIP_LATENCY;
+ bio->bi_issue.value |= BIO_ISSUE_THROTL_SKIP_LATENCY;
#endif
return throttled;
}
@@ -2281,8 +2280,7 @@ void blk_throtl_stat_add(struct request *rq, u64 time_ns)
struct request_queue *q = rq->q;
struct throtl_data *td = q->td;
- throtl_track_latency(td, blk_stat_size(&rq->issue_stat),
- req_op(rq), time_ns >> 10);
+ throtl_track_latency(td, rq->throtl_size, req_op(rq), time_ns >> 10);
}
void blk_throtl_bio_endio(struct bio *bio)
@@ -2302,8 +2300,8 @@ void blk_throtl_bio_endio(struct bio *bio)
finish_time_ns = ktime_get_ns();
tg->last_finish_time = finish_time_ns >> 10;
- start_time = blk_stat_time(&bio->bi_issue_stat) >> 10;
- finish_time = __blk_stat_time(finish_time_ns) >> 10;
+ start_time = bio_issue_time(&bio->bi_issue) >> 10;
+ finish_time = __bio_issue_time(finish_time_ns) >> 10;
if (!start_time || finish_time <= start_time) {
blkg_put(tg_to_blkg(tg));
return;
@@ -2311,16 +2309,15 @@ void blk_throtl_bio_endio(struct bio *bio)
lat = finish_time - start_time;
/* this is only for bio based driver */
- if (!(bio->bi_issue_stat.stat & SKIP_LATENCY))
- throtl_track_latency(tg->td, blk_stat_size(&bio->bi_issue_stat),
- bio_op(bio), lat);
+ if (!(bio->bi_issue.value & BIO_ISSUE_THROTL_SKIP_LATENCY))
+ throtl_track_latency(tg->td, bio_issue_size(&bio->bi_issue),
+ bio_op(bio), lat);
if (tg->latency_target && lat >= tg->td->filtered_latency) {
int bucket;
unsigned int threshold;
- bucket = request_bucket_index(
- blk_stat_size(&bio->bi_issue_stat));
+ bucket = request_bucket_index(bio_issue_size(&bio->bi_issue));
threshold = tg->td->avg_buckets[rw][bucket].latency +
tg->latency_target;
if (lat > threshold)
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 652d4d4..4b8a48d 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -86,14 +86,11 @@ static void blk_rq_timed_out(struct request *req)
if (q->rq_timed_out_fn)
ret = q->rq_timed_out_fn(req);
switch (ret) {
- case BLK_EH_HANDLED:
- __blk_complete_request(req);
- break;
case BLK_EH_RESET_TIMER:
blk_add_timer(req);
blk_clear_rq_complete(req);
break;
- case BLK_EH_NOT_HANDLED:
+ case BLK_EH_DONE:
/*
* LLD handles this for now but in the future
* we can send a request msg to abort the command
@@ -214,7 +211,6 @@ void blk_add_timer(struct request *req)
req->timeout = q->rq_timeout;
blk_rq_set_deadline(req, jiffies + req->timeout);
- req->rq_flags &= ~RQF_MQ_TIMEOUT_EXPIRED;
/*
* Only the non-mq case needs to add the request to a protected list.
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index f92fc84b..4f89b28 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -29,6 +29,26 @@
#define CREATE_TRACE_POINTS
#include <trace/events/wbt.h>
+static inline void wbt_clear_state(struct request *rq)
+{
+ rq->wbt_flags = 0;
+}
+
+static inline enum wbt_flags wbt_flags(struct request *rq)
+{
+ return rq->wbt_flags;
+}
+
+static inline bool wbt_is_tracked(struct request *rq)
+{
+ return rq->wbt_flags & WBT_TRACKED;
+}
+
+static inline bool wbt_is_read(struct request *rq)
+{
+ return rq->wbt_flags & WBT_READ;
+}
+
enum {
/*
* Default setting, we'll scale up (to 75% of QD max) or down (min 1)
@@ -101,9 +121,15 @@ static bool wb_recent_wait(struct rq_wb *rwb)
return time_before(jiffies, wb->dirty_sleep + HZ);
}
-static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb, bool is_kswapd)
+static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb,
+ enum wbt_flags wb_acct)
{
- return &rwb->rq_wait[is_kswapd];
+ if (wb_acct & WBT_KSWAPD)
+ return &rwb->rq_wait[WBT_RWQ_KSWAPD];
+ else if (wb_acct & WBT_DISCARD)
+ return &rwb->rq_wait[WBT_RWQ_DISCARD];
+
+ return &rwb->rq_wait[WBT_RWQ_BG];
}
static void rwb_wake_all(struct rq_wb *rwb)
@@ -126,7 +152,7 @@ void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
if (!(wb_acct & WBT_TRACKED))
return;
- rqw = get_rq_wait(rwb, wb_acct & WBT_KSWAPD);
+ rqw = get_rq_wait(rwb, wb_acct);
inflight = atomic_dec_return(&rqw->inflight);
/*
@@ -139,10 +165,13 @@ void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
}
/*
- * If the device does write back caching, drop further down
- * before we wake people up.
+ * For discards, our limit is always the background. For writes, if
+ * the device does write back caching, drop further down before we
+ * wake people up.
*/
- if (rwb->wc && !wb_recent_wait(rwb))
+ if (wb_acct & WBT_DISCARD)
+ limit = rwb->wb_background;
+ else if (rwb->wc && !wb_recent_wait(rwb))
limit = 0;
else
limit = rwb->wb_normal;
@@ -165,24 +194,24 @@ void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
* Called on completion of a request. Note that it's also called when
* a request is merged, when the request gets freed.
*/
-void wbt_done(struct rq_wb *rwb, struct blk_issue_stat *stat)
+void wbt_done(struct rq_wb *rwb, struct request *rq)
{
if (!rwb)
return;
- if (!wbt_is_tracked(stat)) {
- if (rwb->sync_cookie == stat) {
+ if (!wbt_is_tracked(rq)) {
+ if (rwb->sync_cookie == rq) {
rwb->sync_issue = 0;
rwb->sync_cookie = NULL;
}
- if (wbt_is_read(stat))
+ if (wbt_is_read(rq))
wb_timestamp(rwb, &rwb->last_comp);
} else {
- WARN_ON_ONCE(stat == rwb->sync_cookie);
- __wbt_done(rwb, wbt_stat_to_mask(stat));
+ WARN_ON_ONCE(rq == rwb->sync_cookie);
+ __wbt_done(rwb, wbt_flags(rq));
}
- wbt_clear_state(stat);
+ wbt_clear_state(rq);
}
/*
@@ -479,6 +508,9 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
{
unsigned int limit;
+ if ((rw & REQ_OP_MASK) == REQ_OP_DISCARD)
+ return rwb->wb_background;
+
/*
* At this point we know it's a buffered write. If this is
* kswapd trying to free memory, or REQ_SYNC is set, then
@@ -529,11 +561,12 @@ static inline bool may_queue(struct rq_wb *rwb, struct rq_wait *rqw,
* Block if we will exceed our limit, or if we are currently waiting for
* the timer to kick off queuing again.
*/
-static void __wbt_wait(struct rq_wb *rwb, unsigned long rw, spinlock_t *lock)
+static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct,
+ unsigned long rw, spinlock_t *lock)
__releases(lock)
__acquires(lock)
{
- struct rq_wait *rqw = get_rq_wait(rwb, current_is_kswapd());
+ struct rq_wait *rqw = get_rq_wait(rwb, wb_acct);
DEFINE_WAIT(wait);
if (may_queue(rwb, rqw, &wait, rw))
@@ -559,21 +592,20 @@ static void __wbt_wait(struct rq_wb *rwb, unsigned long rw, spinlock_t *lock)
static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
{
- const int op = bio_op(bio);
-
- /*
- * If not a WRITE, do nothing
- */
- if (op != REQ_OP_WRITE)
+ switch (bio_op(bio)) {
+ case REQ_OP_WRITE:
+ /*
+ * Don't throttle WRITE_ODIRECT
+ */
+ if ((bio->bi_opf & (REQ_SYNC | REQ_IDLE)) ==
+ (REQ_SYNC | REQ_IDLE))
+ return false;
+ /* fallthrough */
+ case REQ_OP_DISCARD:
+ return true;
+ default:
return false;
-
- /*
- * Don't throttle WRITE_ODIRECT
- */
- if ((bio->bi_opf & (REQ_SYNC | REQ_IDLE)) == (REQ_SYNC | REQ_IDLE))
- return false;
-
- return true;
+ }
}
/*
@@ -584,7 +616,7 @@ static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
*/
enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock)
{
- unsigned int ret = 0;
+ enum wbt_flags ret = 0;
if (!rwb_enabled(rwb))
return 0;
@@ -598,41 +630,42 @@ enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock)
return ret;
}
- __wbt_wait(rwb, bio->bi_opf, lock);
+ if (current_is_kswapd())
+ ret |= WBT_KSWAPD;
+ if (bio_op(bio) == REQ_OP_DISCARD)
+ ret |= WBT_DISCARD;
+
+ __wbt_wait(rwb, ret, bio->bi_opf, lock);
if (!blk_stat_is_active(rwb->cb))
rwb_arm_timer(rwb);
- if (current_is_kswapd())
- ret |= WBT_KSWAPD;
-
return ret | WBT_TRACKED;
}
-void wbt_issue(struct rq_wb *rwb, struct blk_issue_stat *stat)
+void wbt_issue(struct rq_wb *rwb, struct request *rq)
{
if (!rwb_enabled(rwb))
return;
/*
- * Track sync issue, in case it takes a long time to complete. Allows
- * us to react quicker, if a sync IO takes a long time to complete.
- * Note that this is just a hint. 'stat' can go away when the
- * request completes, so it's important we never dereference it. We
- * only use the address to compare with, which is why we store the
- * sync_issue time locally.
+ * Track sync issue, in case it takes a long time to complete. Allows us
+ * to react quicker, if a sync IO takes a long time to complete. Note
+ * that this is just a hint. The request can go away when it completes,
+ * so it's important we never dereference it. We only use the address to
+ * compare with, which is why we store the sync_issue time locally.
*/
- if (wbt_is_read(stat) && !rwb->sync_issue) {
- rwb->sync_cookie = stat;
- rwb->sync_issue = blk_stat_time(stat);
+ if (wbt_is_read(rq) && !rwb->sync_issue) {
+ rwb->sync_cookie = rq;
+ rwb->sync_issue = rq->io_start_time_ns;
}
}
-void wbt_requeue(struct rq_wb *rwb, struct blk_issue_stat *stat)
+void wbt_requeue(struct rq_wb *rwb, struct request *rq)
{
if (!rwb_enabled(rwb))
return;
- if (stat == rwb->sync_cookie) {
+ if (rq == rwb->sync_cookie) {
rwb->sync_issue = 0;
rwb->sync_cookie = NULL;
}
@@ -701,7 +734,7 @@ static int wbt_data_dir(const struct request *rq)
if (op == REQ_OP_READ)
return READ;
- else if (op == REQ_OP_WRITE || op == REQ_OP_FLUSH)
+ else if (op_is_write(op))
return WRITE;
/* don't account */
@@ -713,8 +746,6 @@ int wbt_init(struct request_queue *q)
struct rq_wb *rwb;
int i;
- BUILD_BUG_ON(WBT_NR_BITS > BLK_STAT_RES_BITS);
-
rwb = kzalloc(sizeof(*rwb), GFP_KERNEL);
if (!rwb)
return -ENOMEM;
diff --git a/block/blk-wbt.h b/block/blk-wbt.h
index a232c98..300df53 100644
--- a/block/blk-wbt.h
+++ b/block/blk-wbt.h
@@ -14,12 +14,16 @@ enum wbt_flags {
WBT_TRACKED = 1, /* write, tracked for throttling */
WBT_READ = 2, /* read */
WBT_KSWAPD = 4, /* write, from kswapd */
+ WBT_DISCARD = 8, /* discard */
- WBT_NR_BITS = 3, /* number of bits */
+ WBT_NR_BITS = 4, /* number of bits */
};
enum {
- WBT_NUM_RWQ = 2,
+ WBT_RWQ_BG = 0,
+ WBT_RWQ_KSWAPD,
+ WBT_RWQ_DISCARD,
+ WBT_NUM_RWQ,
};
/*
@@ -31,31 +35,6 @@ enum {
WBT_STATE_ON_MANUAL = 2,
};
-static inline void wbt_clear_state(struct blk_issue_stat *stat)
-{
- stat->stat &= ~BLK_STAT_RES_MASK;
-}
-
-static inline enum wbt_flags wbt_stat_to_mask(struct blk_issue_stat *stat)
-{
- return (stat->stat & BLK_STAT_RES_MASK) >> BLK_STAT_RES_SHIFT;
-}
-
-static inline void wbt_track(struct blk_issue_stat *stat, enum wbt_flags wb_acct)
-{
- stat->stat |= ((u64) wb_acct) << BLK_STAT_RES_SHIFT;
-}
-
-static inline bool wbt_is_tracked(struct blk_issue_stat *stat)
-{
- return (stat->stat >> BLK_STAT_RES_SHIFT) & WBT_TRACKED;
-}
-
-static inline bool wbt_is_read(struct blk_issue_stat *stat)
-{
- return (stat->stat >> BLK_STAT_RES_SHIFT) & WBT_READ;
-}
-
struct rq_wait {
wait_queue_head_t wait;
atomic_t inflight;
@@ -84,7 +63,7 @@ struct rq_wb {
struct blk_stat_callback *cb;
- s64 sync_issue;
+ u64 sync_issue;
void *sync_cookie;
unsigned int wc;
@@ -109,14 +88,19 @@ static inline unsigned int wbt_inflight(struct rq_wb *rwb)
#ifdef CONFIG_BLK_WBT
+static inline void wbt_track(struct request *rq, enum wbt_flags flags)
+{
+ rq->wbt_flags |= flags;
+}
+
void __wbt_done(struct rq_wb *, enum wbt_flags);
-void wbt_done(struct rq_wb *, struct blk_issue_stat *);
+void wbt_done(struct rq_wb *, struct request *);
enum wbt_flags wbt_wait(struct rq_wb *, struct bio *, spinlock_t *);
int wbt_init(struct request_queue *);
void wbt_exit(struct request_queue *);
void wbt_update_limits(struct rq_wb *);
-void wbt_requeue(struct rq_wb *, struct blk_issue_stat *);
-void wbt_issue(struct rq_wb *, struct blk_issue_stat *);
+void wbt_requeue(struct rq_wb *, struct request *);
+void wbt_issue(struct rq_wb *, struct request *);
void wbt_disable_default(struct request_queue *);
void wbt_enable_default(struct request_queue *);
@@ -127,10 +111,13 @@ u64 wbt_default_latency_nsec(struct request_queue *);
#else
+static inline void wbt_track(struct request *rq, enum wbt_flags flags)
+{
+}
static inline void __wbt_done(struct rq_wb *rwb, enum wbt_flags flags)
{
}
-static inline void wbt_done(struct rq_wb *rwb, struct blk_issue_stat *stat)
+static inline void wbt_done(struct rq_wb *rwb, struct request *rq)
{
}
static inline enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio,
@@ -148,10 +135,10 @@ static inline void wbt_exit(struct request_queue *q)
static inline void wbt_update_limits(struct rq_wb *rwb)
{
}
-static inline void wbt_requeue(struct rq_wb *rwb, struct blk_issue_stat *stat)
+static inline void wbt_requeue(struct rq_wb *rwb, struct request *rq)
{
}
-static inline void wbt_issue(struct rq_wb *rwb, struct blk_issue_stat *stat)
+static inline void wbt_issue(struct rq_wb *rwb, struct request *rq)
{
}
static inline void wbt_disable_default(struct request_queue *q)
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 08e84ef..3d08dc84 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -328,7 +328,11 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
if (!rep.nr_zones)
return -EINVAL;
- zones = kcalloc(rep.nr_zones, sizeof(struct blk_zone), GFP_KERNEL);
+ if (rep.nr_zones > INT_MAX / sizeof(struct blk_zone))
+ return -ERANGE;
+
+ zones = kvmalloc(rep.nr_zones * sizeof(struct blk_zone),
+ GFP_KERNEL | __GFP_ZERO);
if (!zones)
return -ENOMEM;
@@ -350,7 +354,7 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
}
out:
- kfree(zones);
+ kvfree(zones);
return ret;
}
diff --git a/block/blk.h b/block/blk.h
index b034fd2..8d23aea9 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -186,7 +186,7 @@ unsigned int blk_plug_queued_count(struct request_queue *q);
void blk_account_io_start(struct request *req, bool new_io);
void blk_account_io_completion(struct request *req, unsigned int bytes);
-void blk_account_io_done(struct request *req);
+void blk_account_io_done(struct request *req, u64 now);
/*
* EH timer and IO completion will both attempt to 'grab' the request, make
@@ -231,6 +231,9 @@ static inline void elv_deactivate_rq(struct request_queue *q, struct request *rq
e->type->ops.sq.elevator_deactivate_req_fn(q, rq);
}
+int elevator_init(struct request_queue *);
+int elevator_init_mq(struct request_queue *q);
+void elevator_exit(struct request_queue *, struct elevator_queue *);
int elv_register_queue(struct request_queue *q);
void elv_unregister_queue(struct request_queue *q);
diff --git a/block/bounce.c b/block/bounce.c
index dd0b93f..fd31347 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -28,28 +28,29 @@
#define POOL_SIZE 64
#define ISA_POOL_SIZE 16
-static struct bio_set *bounce_bio_set, *bounce_bio_split;
-static mempool_t *page_pool, *isa_page_pool;
+static struct bio_set bounce_bio_set, bounce_bio_split;
+static mempool_t page_pool, isa_page_pool;
#if defined(CONFIG_HIGHMEM)
static __init int init_emergency_pool(void)
{
+ int ret;
#if defined(CONFIG_HIGHMEM) && !defined(CONFIG_MEMORY_HOTPLUG)
if (max_pfn <= max_low_pfn)
return 0;
#endif
- page_pool = mempool_create_page_pool(POOL_SIZE, 0);
- BUG_ON(!page_pool);
+ ret = mempool_init_page_pool(&page_pool, POOL_SIZE, 0);
+ BUG_ON(ret);
pr_info("pool size: %d pages\n", POOL_SIZE);
- bounce_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
- BUG_ON(!bounce_bio_set);
- if (bioset_integrity_create(bounce_bio_set, BIO_POOL_SIZE))
+ ret = bioset_init(&bounce_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+ BUG_ON(ret);
+ if (bioset_integrity_create(&bounce_bio_set, BIO_POOL_SIZE))
BUG_ON(1);
- bounce_bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
- BUG_ON(!bounce_bio_split);
+ ret = bioset_init(&bounce_bio_split, BIO_POOL_SIZE, 0, 0);
+ BUG_ON(ret);
return 0;
}
@@ -63,14 +64,11 @@ __initcall(init_emergency_pool);
*/
static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
{
- unsigned long flags;
unsigned char *vto;
- local_irq_save(flags);
vto = kmap_atomic(to->bv_page);
memcpy(vto + to->bv_offset, vfrom, to->bv_len);
kunmap_atomic(vto);
- local_irq_restore(flags);
}
#else /* CONFIG_HIGHMEM */
@@ -94,12 +92,14 @@ static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data)
*/
int init_emergency_isa_pool(void)
{
- if (isa_page_pool)
+ int ret;
+
+ if (mempool_initialized(&isa_page_pool))
return 0;
- isa_page_pool = mempool_create(ISA_POOL_SIZE, mempool_alloc_pages_isa,
- mempool_free_pages, (void *) 0);
- BUG_ON(!isa_page_pool);
+ ret = mempool_init(&isa_page_pool, ISA_POOL_SIZE, mempool_alloc_pages_isa,
+ mempool_free_pages, (void *) 0);
+ BUG_ON(ret);
pr_info("isa pool size: %d pages\n", ISA_POOL_SIZE);
return 0;
@@ -166,13 +166,13 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool)
static void bounce_end_io_write(struct bio *bio)
{
- bounce_end_io(bio, page_pool);
+ bounce_end_io(bio, &page_pool);
}
static void bounce_end_io_write_isa(struct bio *bio)
{
- bounce_end_io(bio, isa_page_pool);
+ bounce_end_io(bio, &isa_page_pool);
}
static void __bounce_end_io_read(struct bio *bio, mempool_t *pool)
@@ -187,12 +187,12 @@ static void __bounce_end_io_read(struct bio *bio, mempool_t *pool)
static void bounce_end_io_read(struct bio *bio)
{
- __bounce_end_io_read(bio, page_pool);
+ __bounce_end_io_read(bio, &page_pool);
}
static void bounce_end_io_read_isa(struct bio *bio)
{
- __bounce_end_io_read(bio, isa_page_pool);
+ __bounce_end_io_read(bio, &isa_page_pool);
}
static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
@@ -217,13 +217,13 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
return;
if (!passthrough && sectors < bio_sectors(*bio_orig)) {
- bio = bio_split(*bio_orig, sectors, GFP_NOIO, bounce_bio_split);
+ bio = bio_split(*bio_orig, sectors, GFP_NOIO, &bounce_bio_split);
bio_chain(bio, *bio_orig);
generic_make_request(*bio_orig);
*bio_orig = bio;
}
bio = bio_clone_bioset(*bio_orig, GFP_NOIO, passthrough ? NULL :
- bounce_bio_set);
+ &bounce_bio_set);
bio_for_each_segment_all(to, bio, i) {
struct page *page = to->bv_page;
@@ -250,7 +250,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
bio->bi_flags |= (1 << BIO_BOUNCED);
- if (pool == page_pool) {
+ if (pool == &page_pool) {
bio->bi_end_io = bounce_end_io_write;
if (rw == READ)
bio->bi_end_io = bounce_end_io_read;
@@ -282,10 +282,10 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
if (!(q->bounce_gfp & GFP_DMA)) {
if (q->limits.bounce_pfn >= blk_max_pfn)
return;
- pool = page_pool;
+ pool = &page_pool;
} else {
- BUG_ON(!isa_page_pool);
- pool = isa_page_pool;
+ BUG_ON(!mempool_initialized(&isa_page_pool));
+ pool = &isa_page_pool;
}
/*
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index fc2e5ff..9419def 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -303,11 +303,9 @@ static void bsg_exit_rq(struct request_queue *q, struct request *req)
* @name: device to give bsg device
* @job_fn: bsg job handler
* @dd_job_size: size of LLD data needed for each job
- * @release: @dev release function
*/
struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
- bsg_job_fn *job_fn, int dd_job_size,
- void (*release)(struct device *))
+ bsg_job_fn *job_fn, int dd_job_size)
{
struct request_queue *q;
int ret;
@@ -331,7 +329,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
blk_queue_softirq_done(q, bsg_softirq_done);
blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT);
- ret = bsg_register_queue(q, dev, name, &bsg_transport_ops, release);
+ ret = bsg_register_queue(q, dev, name, &bsg_transport_ops);
if (ret) {
printk(KERN_ERR "%s: bsg interface failed to "
"initialize - register queue\n", dev->kobj.name);
diff --git a/block/bsg.c b/block/bsg.c
index defa06c..132e657 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -226,8 +226,7 @@ bsg_map_hdr(struct request_queue *q, struct sg_io_v4 *hdr, fmode_t mode)
return ERR_PTR(ret);
rq = blk_get_request(q, hdr->dout_xfer_len ?
- REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
- GFP_KERNEL);
+ REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
if (IS_ERR(rq))
return rq;
@@ -249,7 +248,7 @@ bsg_map_hdr(struct request_queue *q, struct sg_io_v4 *hdr, fmode_t mode)
goto out;
}
- next_rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL);
+ next_rq = blk_get_request(q, REQ_OP_SCSI_IN, 0);
if (IS_ERR(next_rq)) {
ret = PTR_ERR(next_rq);
goto out;
@@ -650,18 +649,6 @@ static struct bsg_device *bsg_alloc_device(void)
return bd;
}
-static void bsg_kref_release_function(struct kref *kref)
-{
- struct bsg_class_device *bcd =
- container_of(kref, struct bsg_class_device, ref);
- struct device *parent = bcd->parent;
-
- if (bcd->release)
- bcd->release(bcd->parent);
-
- put_device(parent);
-}
-
static int bsg_put_device(struct bsg_device *bd)
{
int ret = 0, do_free;
@@ -694,7 +681,6 @@ static int bsg_put_device(struct bsg_device *bd)
kfree(bd);
out:
- kref_put(&q->bsg_dev.ref, bsg_kref_release_function);
if (do_free)
blk_put_queue(q);
return ret;
@@ -760,8 +746,6 @@ static struct bsg_device *bsg_get_device(struct inode *inode, struct file *file)
*/
mutex_lock(&bsg_mutex);
bcd = idr_find(&bsg_minor_idr, iminor(inode));
- if (bcd)
- kref_get(&bcd->ref);
mutex_unlock(&bsg_mutex);
if (!bcd)
@@ -772,8 +756,6 @@ static struct bsg_device *bsg_get_device(struct inode *inode, struct file *file)
return bd;
bd = bsg_add_device(inode, bcd->queue, file);
- if (IS_ERR(bd))
- kref_put(&bcd->ref, bsg_kref_release_function);
return bd;
}
@@ -913,25 +895,17 @@ void bsg_unregister_queue(struct request_queue *q)
sysfs_remove_link(&q->kobj, "bsg");
device_unregister(bcd->class_dev);
bcd->class_dev = NULL;
- kref_put(&bcd->ref, bsg_kref_release_function);
mutex_unlock(&bsg_mutex);
}
EXPORT_SYMBOL_GPL(bsg_unregister_queue);
int bsg_register_queue(struct request_queue *q, struct device *parent,
- const char *name, const struct bsg_ops *ops,
- void (*release)(struct device *))
+ const char *name, const struct bsg_ops *ops)
{
struct bsg_class_device *bcd;
dev_t dev;
int ret;
struct device *class_dev = NULL;
- const char *devname;
-
- if (name)
- devname = name;
- else
- devname = dev_name(parent);
/*
* we need a proper transport to send commands, not a stacked device
@@ -955,15 +929,12 @@ int bsg_register_queue(struct request_queue *q, struct device *parent,
bcd->minor = ret;
bcd->queue = q;
- bcd->parent = get_device(parent);
- bcd->release = release;
bcd->ops = ops;
- kref_init(&bcd->ref);
dev = MKDEV(bsg_major, bcd->minor);
- class_dev = device_create(bsg_class, parent, dev, NULL, "%s", devname);
+ class_dev = device_create(bsg_class, parent, dev, NULL, "%s", name);
if (IS_ERR(class_dev)) {
ret = PTR_ERR(class_dev);
- goto put_dev;
+ goto idr_remove;
}
bcd->class_dev = class_dev;
@@ -978,8 +949,7 @@ int bsg_register_queue(struct request_queue *q, struct device *parent,
unregister_class_dev:
device_unregister(class_dev);
-put_dev:
- put_device(parent);
+idr_remove:
idr_remove(&bsg_minor_idr, bcd->minor);
unlock:
mutex_unlock(&bsg_mutex);
@@ -993,7 +963,7 @@ int bsg_scsi_register_queue(struct request_queue *q, struct device *parent)
return -EINVAL;
}
- return bsg_register_queue(q, parent, NULL, &bsg_scsi_ops, NULL);
+ return bsg_register_queue(q, parent, dev_name(parent), &bsg_scsi_ops);
}
EXPORT_SYMBOL_GPL(bsg_scsi_register_queue);
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 9f342ef..82b6c27 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -210,9 +210,9 @@ struct cfqg_stats {
/* total time with empty current active q with other requests queued */
struct blkg_stat empty_time;
/* fields after this shouldn't be cleared on stat reset */
- uint64_t start_group_wait_time;
- uint64_t start_idle_time;
- uint64_t start_empty_time;
+ u64 start_group_wait_time;
+ u64 start_idle_time;
+ u64 start_empty_time;
uint16_t flags;
#endif /* CONFIG_DEBUG_BLK_CGROUP */
#endif /* CONFIG_CFQ_GROUP_IOSCHED */
@@ -491,13 +491,13 @@ CFQG_FLAG_FNS(empty)
/* This should be called with the queue_lock held. */
static void cfqg_stats_update_group_wait_time(struct cfqg_stats *stats)
{
- unsigned long long now;
+ u64 now;
if (!cfqg_stats_waiting(stats))
return;
- now = sched_clock();
- if (time_after64(now, stats->start_group_wait_time))
+ now = ktime_get_ns();
+ if (now > stats->start_group_wait_time)
blkg_stat_add(&stats->group_wait_time,
now - stats->start_group_wait_time);
cfqg_stats_clear_waiting(stats);
@@ -513,20 +513,20 @@ static void cfqg_stats_set_start_group_wait_time(struct cfq_group *cfqg,
return;
if (cfqg == curr_cfqg)
return;
- stats->start_group_wait_time = sched_clock();
+ stats->start_group_wait_time = ktime_get_ns();
cfqg_stats_mark_waiting(stats);
}
/* This should be called with the queue_lock held. */
static void cfqg_stats_end_empty_time(struct cfqg_stats *stats)
{
- unsigned long long now;
+ u64 now;
if (!cfqg_stats_empty(stats))
return;
- now = sched_clock();
- if (time_after64(now, stats->start_empty_time))
+ now = ktime_get_ns();
+ if (now > stats->start_empty_time)
blkg_stat_add(&stats->empty_time,
now - stats->start_empty_time);
cfqg_stats_clear_empty(stats);
@@ -552,7 +552,7 @@ static void cfqg_stats_set_start_empty_time(struct cfq_group *cfqg)
if (cfqg_stats_empty(stats))
return;
- stats->start_empty_time = sched_clock();
+ stats->start_empty_time = ktime_get_ns();
cfqg_stats_mark_empty(stats);
}
@@ -561,9 +561,9 @@ static void cfqg_stats_update_idle_time(struct cfq_group *cfqg)
struct cfqg_stats *stats = &cfqg->stats;
if (cfqg_stats_idling(stats)) {
- unsigned long long now = sched_clock();
+ u64 now = ktime_get_ns();
- if (time_after64(now, stats->start_idle_time))
+ if (now > stats->start_idle_time)
blkg_stat_add(&stats->idle_time,
now - stats->start_idle_time);
cfqg_stats_clear_idling(stats);
@@ -576,7 +576,7 @@ static void cfqg_stats_set_start_idle_time(struct cfq_group *cfqg)
BUG_ON(cfqg_stats_idling(stats));
- stats->start_idle_time = sched_clock();
+ stats->start_idle_time = ktime_get_ns();
cfqg_stats_mark_idling(stats);
}
@@ -701,17 +701,19 @@ static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg,
}
static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
- uint64_t start_time, uint64_t io_start_time,
- unsigned int op)
+ u64 start_time_ns,
+ u64 io_start_time_ns,
+ unsigned int op)
{
struct cfqg_stats *stats = &cfqg->stats;
- unsigned long long now = sched_clock();
+ u64 now = ktime_get_ns();
- if (time_after64(now, io_start_time))
- blkg_rwstat_add(&stats->service_time, op, now - io_start_time);
- if (time_after64(io_start_time, start_time))
+ if (now > io_start_time_ns)
+ blkg_rwstat_add(&stats->service_time, op,
+ now - io_start_time_ns);
+ if (io_start_time_ns > start_time_ns)
blkg_rwstat_add(&stats->wait_time, op,
- io_start_time - start_time);
+ io_start_time_ns - start_time_ns);
}
/* @stats = 0 */
@@ -797,8 +799,9 @@ static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg,
static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg,
unsigned int op) { }
static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
- uint64_t start_time, uint64_t io_start_time,
- unsigned int op) { }
+ u64 start_time_ns,
+ u64 io_start_time_ns,
+ unsigned int op) { }
#endif /* CONFIG_CFQ_GROUP_IOSCHED */
@@ -4225,8 +4228,8 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
cfqd->rq_in_driver--;
cfqq->dispatched--;
(RQ_CFQG(rq))->dispatched--;
- cfqg_stats_update_completion(cfqq->cfqg, rq_start_time_ns(rq),
- rq_io_start_time_ns(rq), rq->cmd_flags);
+ cfqg_stats_update_completion(cfqq->cfqg, rq->start_time_ns,
+ rq->io_start_time_ns, rq->cmd_flags);
cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--;
@@ -4242,16 +4245,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
cfqq_type(cfqq));
st->ttime.last_end_request = now;
- /*
- * We have to do this check in jiffies since start_time is in
- * jiffies and it is not trivial to convert to ns. If
- * cfq_fifo_expire[1] ever comes close to 1 jiffie, this test
- * will become problematic but so far we are fine (the default
- * is 128 ms).
- */
- if (!time_after(rq->start_time +
- nsecs_to_jiffies(cfqd->cfq_fifo_expire[1]),
- jiffies))
+ if (rq->start_time_ns + cfqd->cfq_fifo_expire[1] <= now)
cfqd->last_delayed_sync = now;
}
@@ -4792,7 +4786,7 @@ USEC_STORE_FUNCTION(cfq_target_latency_us_store, &cfqd->cfq_target_latency, 1, U
#undef USEC_STORE_FUNCTION
#define CFQ_ATTR(name) \
- __ATTR(name, S_IRUGO|S_IWUSR, cfq_##name##_show, cfq_##name##_store)
+ __ATTR(name, 0644, cfq_##name##_show, cfq_##name##_store)
static struct elv_fs_entry cfq_attrs[] = {
CFQ_ATTR(quantum),
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index 9de9f15..ef2f1f0 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -512,8 +512,7 @@ STORE_FUNCTION(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX, 0);
#undef STORE_FUNCTION
#define DD_ATTR(name) \
- __ATTR(name, S_IRUGO|S_IWUSR, deadline_##name##_show, \
- deadline_##name##_store)
+ __ATTR(name, 0644, deadline_##name##_show, deadline_##name##_store)
static struct elv_fs_entry deadline_attrs[] = {
DD_ATTR(read_expire),
diff --git a/block/elevator.c b/block/elevator.c
index e87e9b43..fa828b5 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -199,76 +199,46 @@ static void elevator_release(struct kobject *kobj)
kfree(e);
}
-int elevator_init(struct request_queue *q, char *name)
+/*
+ * Use the default elevator specified by config boot param for non-mq devices,
+ * or by config option. Don't try to load modules as we could be running off
+ * async and request_module() isn't allowed from async.
+ */
+int elevator_init(struct request_queue *q)
{
struct elevator_type *e = NULL;
- int err;
+ int err = 0;
/*
* q->sysfs_lock must be held to provide mutual exclusion between
* elevator_switch() and here.
*/
- lockdep_assert_held(&q->sysfs_lock);
-
+ mutex_lock(&q->sysfs_lock);
if (unlikely(q->elevator))
- return 0;
+ goto out_unlock;
- INIT_LIST_HEAD(&q->queue_head);
- q->last_merge = NULL;
- q->end_sector = 0;
- q->boundary_rq = NULL;
-
- if (name) {
- e = elevator_get(q, name, true);
- if (!e)
- return -EINVAL;
- }
-
- /*
- * Use the default elevator specified by config boot param for
- * non-mq devices, or by config option. Don't try to load modules
- * as we could be running off async and request_module() isn't
- * allowed from async.
- */
- if (!e && !q->mq_ops && *chosen_elevator) {
+ if (*chosen_elevator) {
e = elevator_get(q, chosen_elevator, false);
if (!e)
printk(KERN_ERR "I/O scheduler %s not found\n",
chosen_elevator);
}
+ if (!e)
+ e = elevator_get(q, CONFIG_DEFAULT_IOSCHED, false);
if (!e) {
- /*
- * For blk-mq devices, we default to using mq-deadline,
- * if available, for single queue devices. If deadline
- * isn't available OR we have multiple queues, default
- * to "none".
- */
- if (q->mq_ops) {
- if (q->nr_hw_queues == 1)
- e = elevator_get(q, "mq-deadline", false);
- if (!e)
- return 0;
- } else
- e = elevator_get(q, CONFIG_DEFAULT_IOSCHED, false);
-
- if (!e) {
- printk(KERN_ERR
- "Default I/O scheduler not found. " \
- "Using noop.\n");
- e = elevator_get(q, "noop", false);
- }
+ printk(KERN_ERR
+ "Default I/O scheduler not found. Using noop.\n");
+ e = elevator_get(q, "noop", false);
}
- if (e->uses_mq)
- err = blk_mq_init_sched(q, e);
- else
- err = e->ops.sq.elevator_init_fn(q, e);
+ err = e->ops.sq.elevator_init_fn(q, e);
if (err)
elevator_put(e);
+out_unlock:
+ mutex_unlock(&q->sysfs_lock);
return err;
}
-EXPORT_SYMBOL(elevator_init);
void elevator_exit(struct request_queue *q, struct elevator_queue *e)
{
@@ -281,7 +251,6 @@ void elevator_exit(struct request_queue *q, struct elevator_queue *e)
kobject_put(&e->kobj);
}
-EXPORT_SYMBOL(elevator_exit);
static inline void __elv_rqhash_del(struct request *rq)
{
@@ -1005,6 +974,40 @@ static int elevator_switch_mq(struct request_queue *q,
}
/*
+ * For blk-mq devices, we default to using mq-deadline, if available, for single
+ * queue devices. If deadline isn't available OR we have multiple queues,
+ * default to "none".
+ */
+int elevator_init_mq(struct request_queue *q)
+{
+ struct elevator_type *e;
+ int err = 0;
+
+ if (q->nr_hw_queues != 1)
+ return 0;
+
+ /*
+ * q->sysfs_lock must be held to provide mutual exclusion between
+ * elevator_switch() and here.
+ */
+ mutex_lock(&q->sysfs_lock);
+ if (unlikely(q->elevator))
+ goto out_unlock;
+
+ e = elevator_get(q, "mq-deadline", false);
+ if (!e)
+ goto out_unlock;
+
+ err = blk_mq_init_sched(q, e);
+ if (err)
+ elevator_put(e);
+out_unlock:
+ mutex_unlock(&q->sysfs_lock);
+ return err;
+}
+
+
+/*
* switch to new_e io scheduler. be careful not to introduce deadlocks -
* we don't free the old io scheduler, before we have allocated what we
* need for the new one. this way we have a chance of going back to the old
diff --git a/block/genhd.c b/block/genhd.c
index dc7e089..f1543a4 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -82,6 +82,18 @@ void part_in_flight(struct request_queue *q, struct hd_struct *part,
}
}
+void part_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+ unsigned int inflight[2])
+{
+ if (q->mq_ops) {
+ blk_mq_in_flight_rw(q, part, inflight);
+ return;
+ }
+
+ inflight[0] = atomic_read(&part->in_flight[0]);
+ inflight[1] = atomic_read(&part->in_flight[1]);
+}
+
struct hd_struct *__disk_get_part(struct gendisk *disk, int partno)
{
struct disk_part_tbl *ptbl = rcu_dereference(disk->part_tbl);
@@ -1015,18 +1027,6 @@ static const struct seq_operations partitions_op = {
.stop = disk_seqf_stop,
.show = show_partition
};
-
-static int partitions_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &partitions_op);
-}
-
-static const struct file_operations proc_partitions_operations = {
- .open = partitions_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
#endif
@@ -1127,28 +1127,25 @@ static ssize_t disk_discard_alignment_show(struct device *dev,
return sprintf(buf, "%d\n", queue_discard_alignment(disk->queue));
}
-static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL);
-static DEVICE_ATTR(ext_range, S_IRUGO, disk_ext_range_show, NULL);
-static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL);
-static DEVICE_ATTR(hidden, S_IRUGO, disk_hidden_show, NULL);
-static DEVICE_ATTR(ro, S_IRUGO, disk_ro_show, NULL);
-static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
-static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL);
-static DEVICE_ATTR(discard_alignment, S_IRUGO, disk_discard_alignment_show,
- NULL);
-static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL);
-static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
-static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
-static DEVICE_ATTR(badblocks, S_IRUGO | S_IWUSR, disk_badblocks_show,
- disk_badblocks_store);
+static DEVICE_ATTR(range, 0444, disk_range_show, NULL);
+static DEVICE_ATTR(ext_range, 0444, disk_ext_range_show, NULL);
+static DEVICE_ATTR(removable, 0444, disk_removable_show, NULL);
+static DEVICE_ATTR(hidden, 0444, disk_hidden_show, NULL);
+static DEVICE_ATTR(ro, 0444, disk_ro_show, NULL);
+static DEVICE_ATTR(size, 0444, part_size_show, NULL);
+static DEVICE_ATTR(alignment_offset, 0444, disk_alignment_offset_show, NULL);
+static DEVICE_ATTR(discard_alignment, 0444, disk_discard_alignment_show, NULL);
+static DEVICE_ATTR(capability, 0444, disk_capability_show, NULL);
+static DEVICE_ATTR(stat, 0444, part_stat_show, NULL);
+static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL);
+static DEVICE_ATTR(badblocks, 0644, disk_badblocks_show, disk_badblocks_store);
#ifdef CONFIG_FAIL_MAKE_REQUEST
static struct device_attribute dev_attr_fail =
- __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
+ __ATTR(make-it-fail, 0644, part_fail_show, part_fail_store);
#endif
#ifdef CONFIG_FAIL_IO_TIMEOUT
static struct device_attribute dev_attr_fail_timeout =
- __ATTR(io-timeout-fail, S_IRUGO|S_IWUSR, part_timeout_show,
- part_timeout_store);
+ __ATTR(io-timeout-fail, 0644, part_timeout_show, part_timeout_store);
#endif
static struct attribute *disk_attrs[] = {
@@ -1365,22 +1362,10 @@ static const struct seq_operations diskstats_op = {
.show = diskstats_show
};
-static int diskstats_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &diskstats_op);
-}
-
-static const struct file_operations proc_diskstats_operations = {
- .open = diskstats_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static int __init proc_genhd_init(void)
{
- proc_create("diskstats", 0, NULL, &proc_diskstats_operations);
- proc_create("partitions", 0, NULL, &proc_partitions_operations);
+ proc_create_seq("diskstats", 0, NULL, &diskstats_op);
+ proc_create_seq("partitions", 0, NULL, &partitions_op);
return 0;
}
module_init(proc_genhd_init);
@@ -1912,9 +1897,9 @@ static ssize_t disk_events_poll_msecs_store(struct device *dev,
return count;
}
-static const DEVICE_ATTR(events, S_IRUGO, disk_events_show, NULL);
-static const DEVICE_ATTR(events_async, S_IRUGO, disk_events_async_show, NULL);
-static const DEVICE_ATTR(events_poll_msecs, S_IRUGO|S_IWUSR,
+static const DEVICE_ATTR(events, 0444, disk_events_show, NULL);
+static const DEVICE_ATTR(events_async, 0444, disk_events_async_show, NULL);
+static const DEVICE_ATTR(events_poll_msecs, 0644,
disk_events_poll_msecs_show,
disk_events_poll_msecs_store);
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index 0d6d25e3..a1660ba 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -72,6 +72,19 @@ static const unsigned int kyber_batch_size[] = {
[KYBER_OTHER] = 8,
};
+/*
+ * There is a same mapping between ctx & hctx and kcq & khd,
+ * we use request->mq_ctx->index_hw to index the kcq in khd.
+ */
+struct kyber_ctx_queue {
+ /*
+ * Used to ensure operations on rq_list and kcq_map to be an atmoic one.
+ * Also protect the rqs on rq_list when merge.
+ */
+ spinlock_t lock;
+ struct list_head rq_list[KYBER_NUM_DOMAINS];
+} ____cacheline_aligned_in_smp;
+
struct kyber_queue_data {
struct request_queue *q;
@@ -99,6 +112,8 @@ struct kyber_hctx_data {
struct list_head rqs[KYBER_NUM_DOMAINS];
unsigned int cur_domain;
unsigned int batching;
+ struct kyber_ctx_queue *kcqs;
+ struct sbitmap kcq_map[KYBER_NUM_DOMAINS];
wait_queue_entry_t domain_wait[KYBER_NUM_DOMAINS];
struct sbq_wait_state *domain_ws[KYBER_NUM_DOMAINS];
atomic_t wait_index[KYBER_NUM_DOMAINS];
@@ -107,10 +122,8 @@ struct kyber_hctx_data {
static int kyber_domain_wake(wait_queue_entry_t *wait, unsigned mode, int flags,
void *key);
-static int rq_sched_domain(const struct request *rq)
+static unsigned int kyber_sched_domain(unsigned int op)
{
- unsigned int op = rq->cmd_flags;
-
if ((op & REQ_OP_MASK) == REQ_OP_READ)
return KYBER_READ;
else if ((op & REQ_OP_MASK) == REQ_OP_WRITE && op_is_sync(op))
@@ -284,6 +297,11 @@ static unsigned int kyber_sched_tags_shift(struct kyber_queue_data *kqd)
return kqd->q->queue_hw_ctx[0]->sched_tags->bitmap_tags.sb.shift;
}
+static int kyber_bucket_fn(const struct request *rq)
+{
+ return kyber_sched_domain(rq->cmd_flags);
+}
+
static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q)
{
struct kyber_queue_data *kqd;
@@ -297,7 +315,7 @@ static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q)
goto err;
kqd->q = q;
- kqd->cb = blk_stat_alloc_callback(kyber_stat_timer_fn, rq_sched_domain,
+ kqd->cb = blk_stat_alloc_callback(kyber_stat_timer_fn, kyber_bucket_fn,
KYBER_NUM_DOMAINS, kqd);
if (!kqd->cb)
goto err_kqd;
@@ -376,8 +394,18 @@ static void kyber_exit_sched(struct elevator_queue *e)
kfree(kqd);
}
+static void kyber_ctx_queue_init(struct kyber_ctx_queue *kcq)
+{
+ unsigned int i;
+
+ spin_lock_init(&kcq->lock);
+ for (i = 0; i < KYBER_NUM_DOMAINS; i++)
+ INIT_LIST_HEAD(&kcq->rq_list[i]);
+}
+
static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
{
+ struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data;
struct kyber_hctx_data *khd;
int i;
@@ -385,6 +413,24 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
if (!khd)
return -ENOMEM;
+ khd->kcqs = kmalloc_array_node(hctx->nr_ctx,
+ sizeof(struct kyber_ctx_queue),
+ GFP_KERNEL, hctx->numa_node);
+ if (!khd->kcqs)
+ goto err_khd;
+
+ for (i = 0; i < hctx->nr_ctx; i++)
+ kyber_ctx_queue_init(&khd->kcqs[i]);
+
+ for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
+ if (sbitmap_init_node(&khd->kcq_map[i], hctx->nr_ctx,
+ ilog2(8), GFP_KERNEL, hctx->numa_node)) {
+ while (--i >= 0)
+ sbitmap_free(&khd->kcq_map[i]);
+ goto err_kcqs;
+ }
+ }
+
spin_lock_init(&khd->lock);
for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
@@ -400,12 +446,26 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
khd->batching = 0;
hctx->sched_data = khd;
+ sbitmap_queue_min_shallow_depth(&hctx->sched_tags->bitmap_tags,
+ kqd->async_depth);
return 0;
+
+err_kcqs:
+ kfree(khd->kcqs);
+err_khd:
+ kfree(khd);
+ return -ENOMEM;
}
static void kyber_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
{
+ struct kyber_hctx_data *khd = hctx->sched_data;
+ int i;
+
+ for (i = 0; i < KYBER_NUM_DOMAINS; i++)
+ sbitmap_free(&khd->kcq_map[i]);
+ kfree(khd->kcqs);
kfree(hctx->sched_data);
}
@@ -427,7 +487,7 @@ static void rq_clear_domain_token(struct kyber_queue_data *kqd,
nr = rq_get_domain_token(rq);
if (nr != -1) {
- sched_domain = rq_sched_domain(rq);
+ sched_domain = kyber_sched_domain(rq->cmd_flags);
sbitmap_queue_clear(&kqd->domain_tokens[sched_domain], nr,
rq->mq_ctx->cpu);
}
@@ -446,11 +506,51 @@ static void kyber_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
}
}
+static bool kyber_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
+{
+ struct kyber_hctx_data *khd = hctx->sched_data;
+ struct blk_mq_ctx *ctx = blk_mq_get_ctx(hctx->queue);
+ struct kyber_ctx_queue *kcq = &khd->kcqs[ctx->index_hw];
+ unsigned int sched_domain = kyber_sched_domain(bio->bi_opf);
+ struct list_head *rq_list = &kcq->rq_list[sched_domain];
+ bool merged;
+
+ spin_lock(&kcq->lock);
+ merged = blk_mq_bio_list_merge(hctx->queue, rq_list, bio);
+ spin_unlock(&kcq->lock);
+ blk_mq_put_ctx(ctx);
+
+ return merged;
+}
+
static void kyber_prepare_request(struct request *rq, struct bio *bio)
{
rq_set_domain_token(rq, -1);
}
+static void kyber_insert_requests(struct blk_mq_hw_ctx *hctx,
+ struct list_head *rq_list, bool at_head)
+{
+ struct kyber_hctx_data *khd = hctx->sched_data;
+ struct request *rq, *next;
+
+ list_for_each_entry_safe(rq, next, rq_list, queuelist) {
+ unsigned int sched_domain = kyber_sched_domain(rq->cmd_flags);
+ struct kyber_ctx_queue *kcq = &khd->kcqs[rq->mq_ctx->index_hw];
+ struct list_head *head = &kcq->rq_list[sched_domain];
+
+ spin_lock(&kcq->lock);
+ if (at_head)
+ list_move(&rq->queuelist, head);
+ else
+ list_move_tail(&rq->queuelist, head);
+ sbitmap_set_bit(&khd->kcq_map[sched_domain],
+ rq->mq_ctx->index_hw);
+ blk_mq_sched_request_inserted(rq);
+ spin_unlock(&kcq->lock);
+ }
+}
+
static void kyber_finish_request(struct request *rq)
{
struct kyber_queue_data *kqd = rq->q->elevator->elevator_data;
@@ -469,7 +569,7 @@ static void kyber_completed_request(struct request *rq)
* Check if this request met our latency goal. If not, quickly gather
* some statistics and start throttling.
*/
- sched_domain = rq_sched_domain(rq);
+ sched_domain = kyber_sched_domain(rq->cmd_flags);
switch (sched_domain) {
case KYBER_READ:
target = kqd->read_lat_nsec;
@@ -485,29 +585,48 @@ static void kyber_completed_request(struct request *rq)
if (blk_stat_is_active(kqd->cb))
return;
- now = __blk_stat_time(ktime_to_ns(ktime_get()));
- if (now < blk_stat_time(&rq->issue_stat))
+ now = ktime_get_ns();
+ if (now < rq->io_start_time_ns)
return;
- latency = now - blk_stat_time(&rq->issue_stat);
+ latency = now - rq->io_start_time_ns;
if (latency > target)
blk_stat_activate_msecs(kqd->cb, 10);
}
-static void kyber_flush_busy_ctxs(struct kyber_hctx_data *khd,
- struct blk_mq_hw_ctx *hctx)
+struct flush_kcq_data {
+ struct kyber_hctx_data *khd;
+ unsigned int sched_domain;
+ struct list_head *list;
+};
+
+static bool flush_busy_kcq(struct sbitmap *sb, unsigned int bitnr, void *data)
{
- LIST_HEAD(rq_list);
- struct request *rq, *next;
+ struct flush_kcq_data *flush_data = data;
+ struct kyber_ctx_queue *kcq = &flush_data->khd->kcqs[bitnr];
- blk_mq_flush_busy_ctxs(hctx, &rq_list);
- list_for_each_entry_safe(rq, next, &rq_list, queuelist) {
- unsigned int sched_domain;
+ spin_lock(&kcq->lock);
+ list_splice_tail_init(&kcq->rq_list[flush_data->sched_domain],
+ flush_data->list);
+ sbitmap_clear_bit(sb, bitnr);
+ spin_unlock(&kcq->lock);
- sched_domain = rq_sched_domain(rq);
- list_move_tail(&rq->queuelist, &khd->rqs[sched_domain]);
- }
+ return true;
+}
+
+static void kyber_flush_busy_kcqs(struct kyber_hctx_data *khd,
+ unsigned int sched_domain,
+ struct list_head *list)
+{
+ struct flush_kcq_data data = {
+ .khd = khd,
+ .sched_domain = sched_domain,
+ .list = list,
+ };
+
+ sbitmap_for_each_set(&khd->kcq_map[sched_domain],
+ flush_busy_kcq, &data);
}
static int kyber_domain_wake(wait_queue_entry_t *wait, unsigned mode, int flags,
@@ -570,26 +689,23 @@ static int kyber_get_domain_token(struct kyber_queue_data *kqd,
static struct request *
kyber_dispatch_cur_domain(struct kyber_queue_data *kqd,
struct kyber_hctx_data *khd,
- struct blk_mq_hw_ctx *hctx,
- bool *flushed)
+ struct blk_mq_hw_ctx *hctx)
{
struct list_head *rqs;
struct request *rq;
int nr;
rqs = &khd->rqs[khd->cur_domain];
- rq = list_first_entry_or_null(rqs, struct request, queuelist);
/*
- * If there wasn't already a pending request and we haven't flushed the
- * software queues yet, flush the software queues and check again.
+ * If we already have a flushed request, then we just need to get a
+ * token for it. Otherwise, if there are pending requests in the kcqs,
+ * flush the kcqs, but only if we can get a token. If not, we should
+ * leave the requests in the kcqs so that they can be merged. Note that
+ * khd->lock serializes the flushes, so if we observed any bit set in
+ * the kcq_map, we will always get a request.
*/
- if (!rq && !*flushed) {
- kyber_flush_busy_ctxs(khd, hctx);
- *flushed = true;
- rq = list_first_entry_or_null(rqs, struct request, queuelist);
- }
-
+ rq = list_first_entry_or_null(rqs, struct request, queuelist);
if (rq) {
nr = kyber_get_domain_token(kqd, khd, hctx);
if (nr >= 0) {
@@ -598,6 +714,16 @@ kyber_dispatch_cur_domain(struct kyber_queue_data *kqd,
list_del_init(&rq->queuelist);
return rq;
}
+ } else if (sbitmap_any_bit_set(&khd->kcq_map[khd->cur_domain])) {
+ nr = kyber_get_domain_token(kqd, khd, hctx);
+ if (nr >= 0) {
+ kyber_flush_busy_kcqs(khd, khd->cur_domain, rqs);
+ rq = list_first_entry(rqs, struct request, queuelist);
+ khd->batching++;
+ rq_set_domain_token(rq, nr);
+ list_del_init(&rq->queuelist);
+ return rq;
+ }
}
/* There were either no pending requests or no tokens. */
@@ -608,7 +734,6 @@ static struct request *kyber_dispatch_request(struct blk_mq_hw_ctx *hctx)
{
struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data;
struct kyber_hctx_data *khd = hctx->sched_data;
- bool flushed = false;
struct request *rq;
int i;
@@ -619,7 +744,7 @@ static struct request *kyber_dispatch_request(struct blk_mq_hw_ctx *hctx)
* from the batch.
*/
if (khd->batching < kyber_batch_size[khd->cur_domain]) {
- rq = kyber_dispatch_cur_domain(kqd, khd, hctx, &flushed);
+ rq = kyber_dispatch_cur_domain(kqd, khd, hctx);
if (rq)
goto out;
}
@@ -640,7 +765,7 @@ static struct request *kyber_dispatch_request(struct blk_mq_hw_ctx *hctx)
else
khd->cur_domain++;
- rq = kyber_dispatch_cur_domain(kqd, khd, hctx, &flushed);
+ rq = kyber_dispatch_cur_domain(kqd, khd, hctx);
if (rq)
goto out;
}
@@ -657,10 +782,12 @@ static bool kyber_has_work(struct blk_mq_hw_ctx *hctx)
int i;
for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
- if (!list_empty_careful(&khd->rqs[i]))
+ if (!list_empty_careful(&khd->rqs[i]) ||
+ sbitmap_any_bit_set(&khd->kcq_map[i]))
return true;
}
- return sbitmap_any_bit_set(&hctx->ctx_map);
+
+ return false;
}
#define KYBER_LAT_SHOW_STORE(op) \
@@ -831,7 +958,9 @@ static struct elevator_type kyber_sched = {
.init_hctx = kyber_init_hctx,
.exit_hctx = kyber_exit_hctx,
.limit_depth = kyber_limit_depth,
+ .bio_merge = kyber_bio_merge,
.prepare_request = kyber_prepare_request,
+ .insert_requests = kyber_insert_requests,
.finish_request = kyber_finish_request,
.requeue_request = kyber_finish_request,
.completed_request = kyber_completed_request,
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index 8ec0ba9..099a9e05 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -630,8 +630,7 @@ STORE_FUNCTION(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX, 0);
#undef STORE_FUNCTION
#define DD_ATTR(name) \
- __ATTR(name, S_IRUGO|S_IWUSR, deadline_##name##_show, \
- deadline_##name##_store)
+ __ATTR(name, 0644, deadline_##name##_show, deadline_##name##_store)
static struct elv_fs_entry deadline_attrs[] = {
DD_ATTR(read_expire),
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 08dabcd..3dcfd4e 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -145,13 +145,15 @@ ssize_t part_stat_show(struct device *dev,
jiffies_to_msecs(part_stat_read(p, time_in_queue)));
}
-ssize_t part_inflight_show(struct device *dev,
- struct device_attribute *attr, char *buf)
+ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
struct hd_struct *p = dev_to_part(dev);
+ struct request_queue *q = part_to_disk(p)->queue;
+ unsigned int inflight[2];
- return sprintf(buf, "%8u %8u\n", atomic_read(&p->in_flight[0]),
- atomic_read(&p->in_flight[1]));
+ part_in_flight_rw(q, p, inflight);
+ return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]);
}
#ifdef CONFIG_FAIL_MAKE_REQUEST
@@ -177,18 +179,17 @@ ssize_t part_fail_store(struct device *dev,
}
#endif
-static DEVICE_ATTR(partition, S_IRUGO, part_partition_show, NULL);
-static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL);
-static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
-static DEVICE_ATTR(ro, S_IRUGO, part_ro_show, NULL);
-static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL);
-static DEVICE_ATTR(discard_alignment, S_IRUGO, part_discard_alignment_show,
- NULL);
-static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
-static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
+static DEVICE_ATTR(partition, 0444, part_partition_show, NULL);
+static DEVICE_ATTR(start, 0444, part_start_show, NULL);
+static DEVICE_ATTR(size, 0444, part_size_show, NULL);
+static DEVICE_ATTR(ro, 0444, part_ro_show, NULL);
+static DEVICE_ATTR(alignment_offset, 0444, part_alignment_offset_show, NULL);
+static DEVICE_ATTR(discard_alignment, 0444, part_discard_alignment_show, NULL);
+static DEVICE_ATTR(stat, 0444, part_stat_show, NULL);
+static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL);
#ifdef CONFIG_FAIL_MAKE_REQUEST
static struct device_attribute dev_attr_fail =
- __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
+ __ATTR(make-it-fail, 0644, part_fail_show, part_fail_store);
#endif
static struct attribute *part_attrs[] = {
@@ -289,8 +290,7 @@ static ssize_t whole_disk_show(struct device *dev,
{
return 0;
}
-static DEVICE_ATTR(whole_disk, S_IRUSR | S_IRGRP | S_IROTH,
- whole_disk_show, NULL);
+static DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL);
/*
* Must be called either with bd_mutex held, before a disk can be opened or
@@ -516,7 +516,7 @@ int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
if (disk->fops->revalidate_disk)
disk->fops->revalidate_disk(disk);
- check_disk_size_change(disk, bdev);
+ check_disk_size_change(disk, bdev, true);
bdev->bd_invalidated = 0;
if (!get_capacity(disk) || !(state = check_partition(disk, bdev)))
return 0;
@@ -641,7 +641,7 @@ int invalidate_partitions(struct gendisk *disk, struct block_device *bdev)
return res;
set_capacity(disk, 0);
- check_disk_size_change(disk, bdev);
+ check_disk_size_change(disk, bdev, false);
bdev->bd_invalidated = 0;
/* tell userspace that the media / partition table may have changed */
kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 60b471f..533f4ae 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -321,8 +321,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
at_head = 1;
ret = -ENOMEM;
- rq = blk_get_request(q, writing ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
- GFP_KERNEL);
+ rq = blk_get_request(q, writing ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
if (IS_ERR(rq))
return PTR_ERR(rq);
req = scsi_req(rq);
@@ -449,8 +448,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
}
- rq = blk_get_request(q, in_len ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
- __GFP_RECLAIM);
+ rq = blk_get_request(q, in_len ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
if (IS_ERR(rq)) {
err = PTR_ERR(rq);
goto error_free_buffer;
@@ -501,7 +499,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
break;
}
- if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_RECLAIM)) {
+ if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, GFP_NOIO)) {
err = DRIVER_ERROR << 24;
goto error;
}
@@ -538,7 +536,7 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
struct request *rq;
int err;
- rq = blk_get_request(q, REQ_OP_SCSI_OUT, __GFP_RECLAIM);
+ rq = blk_get_request(q, REQ_OP_SCSI_OUT, 0);
if (IS_ERR(rq))
return PTR_ERR(rq);
rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 7846c0c..89ed613 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -347,7 +347,6 @@ static const struct proto_ops alg_proto_ops = {
.sendpage = sock_no_sendpage,
.sendmsg = sock_no_sendmsg,
.recvmsg = sock_no_recvmsg,
- .poll = sock_no_poll,
.bind = alg_bind,
.release = af_alg_release,
@@ -1061,19 +1060,12 @@ void af_alg_async_cb(struct crypto_async_request *_req, int err)
}
EXPORT_SYMBOL_GPL(af_alg_async_cb);
-/**
- * af_alg_poll - poll system call handler
- */
-__poll_t af_alg_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+__poll_t af_alg_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
struct alg_sock *ask = alg_sk(sk);
struct af_alg_ctx *ctx = ask->private;
- __poll_t mask;
-
- sock_poll_wait(file, sk_sleep(sk), wait);
- mask = 0;
+ __poll_t mask = 0;
if (!ctx->more || ctx->used)
mask |= EPOLLIN | EPOLLRDNORM;
@@ -1083,7 +1075,7 @@ __poll_t af_alg_poll(struct file *file, struct socket *sock,
return mask;
}
-EXPORT_SYMBOL_GPL(af_alg_poll);
+EXPORT_SYMBOL_GPL(af_alg_poll_mask);
/**
* af_alg_alloc_areq - allocate struct af_alg_async_req
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index 4b07edd..330cf9f 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -375,7 +375,7 @@ static struct proto_ops algif_aead_ops = {
.sendmsg = aead_sendmsg,
.sendpage = af_alg_sendpage,
.recvmsg = aead_recvmsg,
- .poll = af_alg_poll,
+ .poll_mask = af_alg_poll_mask,
};
static int aead_check_key(struct socket *sock)
@@ -471,7 +471,7 @@ static struct proto_ops algif_aead_ops_nokey = {
.sendmsg = aead_sendmsg_nokey,
.sendpage = aead_sendpage_nokey,
.recvmsg = aead_recvmsg_nokey,
- .poll = af_alg_poll,
+ .poll_mask = af_alg_poll_mask,
};
static void *aead_bind(const char *name, u32 type, u32 mask)
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 6c9b192..bfcf595 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -288,7 +288,6 @@ static struct proto_ops algif_hash_ops = {
.mmap = sock_no_mmap,
.bind = sock_no_bind,
.setsockopt = sock_no_setsockopt,
- .poll = sock_no_poll,
.release = af_alg_release,
.sendmsg = hash_sendmsg,
@@ -396,7 +395,6 @@ static struct proto_ops algif_hash_ops_nokey = {
.mmap = sock_no_mmap,
.bind = sock_no_bind,
.setsockopt = sock_no_setsockopt,
- .poll = sock_no_poll,
.release = af_alg_release,
.sendmsg = hash_sendmsg_nokey,
diff --git a/crypto/algif_rng.c b/crypto/algif_rng.c
index 150c2b6..22df379 100644
--- a/crypto/algif_rng.c
+++ b/crypto/algif_rng.c
@@ -106,7 +106,6 @@ static struct proto_ops algif_rng_ops = {
.bind = sock_no_bind,
.accept = sock_no_accept,
.setsockopt = sock_no_setsockopt,
- .poll = sock_no_poll,
.sendmsg = sock_no_sendmsg,
.sendpage = sock_no_sendpage,
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index c4e885df4..15cf3c5 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -205,7 +205,7 @@ static struct proto_ops algif_skcipher_ops = {
.sendmsg = skcipher_sendmsg,
.sendpage = af_alg_sendpage,
.recvmsg = skcipher_recvmsg,
- .poll = af_alg_poll,
+ .poll_mask = af_alg_poll_mask,
};
static int skcipher_check_key(struct socket *sock)
@@ -301,7 +301,7 @@ static struct proto_ops algif_skcipher_ops_nokey = {
.sendmsg = skcipher_sendmsg_nokey,
.sendpage = skcipher_sendpage_nokey,
.recvmsg = skcipher_recvmsg_nokey,
- .poll = af_alg_poll,
+ .poll_mask = af_alg_poll_mask,
};
static void *skcipher_bind(const char *name, u32 type, u32 mask)
diff --git a/crypto/proc.c b/crypto/proc.c
index 822fcef..f4eb613 100644
--- a/crypto/proc.c
+++ b/crypto/proc.c
@@ -94,21 +94,9 @@ static const struct seq_operations crypto_seq_ops = {
.show = c_show
};
-static int crypto_info_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &crypto_seq_ops);
-}
-
-static const struct file_operations proc_crypto_ops = {
- .open = crypto_info_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release
-};
-
void __init crypto_init_proc(void)
{
- proc_create("crypto", 0, NULL, &proc_crypto_ops);
+ proc_create_seq("crypto", 0, NULL, &crypto_seq_ops);
}
void __exit crypto_exit_proc(void)
diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index 2d8de2f..cdd3136 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -82,11 +82,11 @@ static SIMPLE_DEV_PM_OPS(acpi_ac_pm, NULL, acpi_ac_resume);
#ifdef CONFIG_ACPI_PROCFS_POWER
extern struct proc_dir_entry *acpi_lock_ac_dir(void);
extern void *acpi_unlock_ac_dir(struct proc_dir_entry *acpi_ac_dir);
-static int acpi_ac_open_fs(struct inode *inode, struct file *file);
#endif
static int ac_sleep_before_get_state_ms;
+static int ac_check_pmic = 1;
static struct acpi_driver acpi_ac_driver = {
.name = "ac",
@@ -111,16 +111,6 @@ struct acpi_ac {
#define to_acpi_ac(x) power_supply_get_drvdata(x)
-#ifdef CONFIG_ACPI_PROCFS_POWER
-static const struct file_operations acpi_ac_fops = {
- .owner = THIS_MODULE,
- .open = acpi_ac_open_fs,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-#endif
-
/* --------------------------------------------------------------------------
AC Adapter Management
-------------------------------------------------------------------------- */
@@ -209,11 +199,6 @@ static int acpi_ac_seq_show(struct seq_file *seq, void *offset)
return 0;
}
-static int acpi_ac_open_fs(struct inode *inode, struct file *file)
-{
- return single_open(file, acpi_ac_seq_show, PDE_DATA(inode));
-}
-
static int acpi_ac_add_fs(struct acpi_ac *ac)
{
struct proc_dir_entry *entry = NULL;
@@ -228,9 +213,8 @@ static int acpi_ac_add_fs(struct acpi_ac *ac)
}
/* 'state' [R] */
- entry = proc_create_data(ACPI_AC_FILE_STATE,
- S_IRUGO, acpi_device_dir(ac->device),
- &acpi_ac_fops, ac);
+ entry = proc_create_single_data(ACPI_AC_FILE_STATE, S_IRUGO,
+ acpi_device_dir(ac->device), acpi_ac_seq_show, ac);
if (!entry)
return -ENODEV;
return 0;
@@ -310,21 +294,43 @@ static int acpi_ac_battery_notify(struct notifier_block *nb,
return NOTIFY_OK;
}
-static int thinkpad_e530_quirk(const struct dmi_system_id *d)
+static int __init thinkpad_e530_quirk(const struct dmi_system_id *d)
{
ac_sleep_before_get_state_ms = 1000;
return 0;
}
-static const struct dmi_system_id ac_dmi_table[] = {
+static int __init ac_do_not_check_pmic_quirk(const struct dmi_system_id *d)
+{
+ ac_check_pmic = 0;
+ return 0;
+}
+
+static const struct dmi_system_id ac_dmi_table[] __initconst = {
{
+ /* Thinkpad e530 */
.callback = thinkpad_e530_quirk,
- .ident = "thinkpad e530",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
DMI_MATCH(DMI_PRODUCT_NAME, "32597CG"),
},
},
+ {
+ /* ECS EF20EA */
+ .callback = ac_do_not_check_pmic_quirk,
+ .matches = {
+ DMI_MATCH(DMI_PRODUCT_NAME, "EF20EA"),
+ },
+ },
+ {
+ /* Lenovo Ideapad Miix 320 */
+ .callback = ac_do_not_check_pmic_quirk,
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "80XF"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo MIIX 320-10ICR"),
+ },
+ },
{},
};
@@ -384,7 +390,6 @@ static int acpi_ac_add(struct acpi_device *device)
kfree(ac);
}
- dmi_check_system(ac_dmi_table);
return result;
}
@@ -442,13 +447,17 @@ static int __init acpi_ac_init(void)
if (acpi_disabled)
return -ENODEV;
- for (i = 0; i < ARRAY_SIZE(acpi_ac_blacklist); i++)
- if (acpi_dev_present(acpi_ac_blacklist[i].hid, "1",
- acpi_ac_blacklist[i].hrv)) {
- pr_info(PREFIX "AC: found native %s PMIC, not loading\n",
- acpi_ac_blacklist[i].hid);
- return -ENODEV;
- }
+ dmi_check_system(ac_dmi_table);
+
+ if (ac_check_pmic) {
+ for (i = 0; i < ARRAY_SIZE(acpi_ac_blacklist); i++)
+ if (acpi_dev_present(acpi_ac_blacklist[i].hid, "1",
+ acpi_ac_blacklist[i].hrv)) {
+ pr_info(PREFIX "AC: found native %s PMIC, not loading\n",
+ acpi_ac_blacklist[i].hid);
+ return -ENODEV;
+ }
+ }
#ifdef CONFIG_ACPI_PROCFS_POWER
acpi_ac_dir = acpi_lock_ac_dir();
diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c
index d553b008..2664452 100644
--- a/drivers/acpi/acpi_apd.c
+++ b/drivers/acpi/acpi_apd.c
@@ -11,6 +11,7 @@
*/
#include <linux/clk-provider.h>
+#include <linux/platform_data/clk-st.h>
#include <linux/platform_device.h>
#include <linux/pm_domain.h>
#include <linux/clkdev.h>
@@ -72,6 +73,47 @@ static int acpi_apd_setup(struct apd_private_data *pdata)
}
#ifdef CONFIG_X86_AMD_PLATFORM_DEVICE
+
+static int misc_check_res(struct acpi_resource *ares, void *data)
+{
+ struct resource res;
+
+ return !acpi_dev_resource_memory(ares, &res);
+}
+
+static int st_misc_setup(struct apd_private_data *pdata)
+{
+ struct acpi_device *adev = pdata->adev;
+ struct platform_device *clkdev;
+ struct st_clk_data *clk_data;
+ struct resource_entry *rentry;
+ struct list_head resource_list;
+ int ret;
+
+ clk_data = devm_kzalloc(&adev->dev, sizeof(*clk_data), GFP_KERNEL);
+ if (!clk_data)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&resource_list);
+ ret = acpi_dev_get_resources(adev, &resource_list, misc_check_res,
+ NULL);
+ if (ret < 0)
+ return -ENOENT;
+
+ list_for_each_entry(rentry, &resource_list, node) {
+ clk_data->base = devm_ioremap(&adev->dev, rentry->res->start,
+ resource_size(rentry->res));
+ break;
+ }
+
+ acpi_dev_free_resource_list(&resource_list);
+
+ clkdev = platform_device_register_data(&adev->dev, "clk-st",
+ PLATFORM_DEVID_NONE, clk_data,
+ sizeof(*clk_data));
+ return PTR_ERR_OR_ZERO(clkdev);
+}
+
static const struct apd_device_desc cz_i2c_desc = {
.setup = acpi_apd_setup,
.fixed_clk_rate = 133000000,
@@ -94,6 +136,10 @@ static const struct apd_device_desc cz_uart_desc = {
.fixed_clk_rate = 48000000,
.properties = uart_properties,
};
+
+static const struct apd_device_desc st_misc_desc = {
+ .setup = st_misc_setup,
+};
#endif
#ifdef CONFIG_ARM64
@@ -179,6 +225,7 @@ static const struct acpi_device_id acpi_apd_device_ids[] = {
{ "AMD0020", APD_ADDR(cz_uart_desc) },
{ "AMDI0020", APD_ADDR(cz_uart_desc) },
{ "AMD0030", },
+ { "AMD0040", APD_ADDR(st_misc_desc)},
#endif
#ifdef CONFIG_ARM64
{ "APMC0D0F", APD_ADDR(xgene_i2c_desc) },
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 2bcffec..cb6ac5c 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -69,6 +69,10 @@ ACPI_MODULE_NAME("acpi_lpss");
#define LPSS_SAVE_CTX BIT(4)
#define LPSS_NO_D3_DELAY BIT(5)
+/* Crystal Cove PMIC shares same ACPI ID between different platforms */
+#define BYT_CRC_HRV 2
+#define CHT_CRC_HRV 3
+
struct lpss_private_data;
struct lpss_device_desc {
@@ -162,7 +166,7 @@ static void byt_pwm_setup(struct lpss_private_data *pdata)
if (!adev->pnp.unique_id || strcmp(adev->pnp.unique_id, "1"))
return;
- if (!acpi_dev_present("INT33FD", NULL, -1))
+ if (!acpi_dev_present("INT33FD", NULL, BYT_CRC_HRV))
pwm_add_table(byt_pwm_lookup, ARRAY_SIZE(byt_pwm_lookup));
}
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 76fb969..2f2e737 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -2123,6 +2123,25 @@ static int __init intel_opregion_present(void)
return opregion;
}
+static bool dmi_is_desktop(void)
+{
+ const char *chassis_type;
+
+ chassis_type = dmi_get_system_info(DMI_CHASSIS_TYPE);
+ if (!chassis_type)
+ return false;
+
+ if (!strcmp(chassis_type, "3") || /* 3: Desktop */
+ !strcmp(chassis_type, "4") || /* 4: Low Profile Desktop */
+ !strcmp(chassis_type, "5") || /* 5: Pizza Box */
+ !strcmp(chassis_type, "6") || /* 6: Mini Tower */
+ !strcmp(chassis_type, "7") || /* 7: Tower */
+ !strcmp(chassis_type, "11")) /* 11: Main Server Chassis */
+ return true;
+
+ return false;
+}
+
int acpi_video_register(void)
{
int ret = 0;
@@ -2143,8 +2162,12 @@ int acpi_video_register(void)
* win8 ready (where we also prefer the native backlight driver, so
* normally the acpi_video code should not register there anyways).
*/
- if (only_lcd == -1)
- only_lcd = acpi_osi_is_win8();
+ if (only_lcd == -1) {
+ if (dmi_is_desktop() && acpi_osi_is_win8())
+ only_lcd = true;
+ else
+ only_lcd = false;
+ }
dmi_check_system(video_dmi_table);
diff --git a/drivers/acpi/acpi_watchdog.c b/drivers/acpi/acpi_watchdog.c
index ebb626f..9560030 100644
--- a/drivers/acpi/acpi_watchdog.c
+++ b/drivers/acpi/acpi_watchdog.c
@@ -17,18 +17,77 @@
#include "internal.h"
+#ifdef CONFIG_RTC_MC146818_LIB
+#include <linux/mc146818rtc.h>
+
+/*
+ * There are several systems where the WDAT table is accessing RTC SRAM to
+ * store persistent information. This does not work well with the Linux RTC
+ * driver so on those systems we skip WDAT driver and prefer iTCO_wdt
+ * instead.
+ *
+ * See also https://bugzilla.kernel.org/show_bug.cgi?id=199033.
+ */
+static bool acpi_watchdog_uses_rtc(const struct acpi_table_wdat *wdat)
+{
+ const struct acpi_wdat_entry *entries;
+ int i;
+
+ entries = (struct acpi_wdat_entry *)(wdat + 1);
+ for (i = 0; i < wdat->entries; i++) {
+ const struct acpi_generic_address *gas;
+
+ gas = &entries[i].register_region;
+ if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
+ switch (gas->address) {
+ case RTC_PORT(0):
+ case RTC_PORT(1):
+ case RTC_PORT(2):
+ case RTC_PORT(3):
+ return true;
+ }
+ }
+ }
+
+ return false;
+}
+#else
+static bool acpi_watchdog_uses_rtc(const struct acpi_table_wdat *wdat)
+{
+ return false;
+}
+#endif
+
+static const struct acpi_table_wdat *acpi_watchdog_get_wdat(void)
+{
+ const struct acpi_table_wdat *wdat = NULL;
+ acpi_status status;
+
+ if (acpi_disabled)
+ return NULL;
+
+ status = acpi_get_table(ACPI_SIG_WDAT, 0,
+ (struct acpi_table_header **)&wdat);
+ if (ACPI_FAILURE(status)) {
+ /* It is fine if there is no WDAT */
+ return NULL;
+ }
+
+ if (acpi_watchdog_uses_rtc(wdat)) {
+ pr_info("Skipping WDAT on this system because it uses RTC SRAM\n");
+ return NULL;
+ }
+
+ return wdat;
+}
+
/**
* Returns true if this system should prefer ACPI based watchdog instead of
* the native one (which are typically the same hardware).
*/
bool acpi_has_watchdog(void)
{
- struct acpi_table_header hdr;
-
- if (acpi_disabled)
- return false;
-
- return ACPI_SUCCESS(acpi_get_table_header(ACPI_SIG_WDAT, 0, &hdr));
+ return !!acpi_watchdog_get_wdat();
}
EXPORT_SYMBOL_GPL(acpi_has_watchdog);
@@ -41,12 +100,10 @@ void __init acpi_watchdog_init(void)
struct platform_device *pdev;
struct resource *resources;
size_t nresources = 0;
- acpi_status status;
int i;
- status = acpi_get_table(ACPI_SIG_WDAT, 0,
- (struct acpi_table_header **)&wdat);
- if (ACPI_FAILURE(status)) {
+ wdat = acpi_watchdog_get_wdat();
+ if (!wdat) {
/* It is fine if there is no WDAT */
return;
}
diff --git a/drivers/acpi/acpica/acapps.h b/drivers/acpi/acpica/acapps.h
index a2a8512..5a9c2fe 100644
--- a/drivers/acpi/acpica/acapps.h
+++ b/drivers/acpi/acpica/acapps.h
@@ -143,6 +143,8 @@ acpi_status
fl_split_input_pathname(char *input_path,
char **out_directory_path, char **out_filename);
+char *fl_get_file_basename(char *file_pathname);
+
char *ad_generate_filename(char *prefix, char *table_id);
void
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index 0bc5500..1e62045 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -82,7 +82,7 @@ ACPI_GLOBAL(u8, acpi_gbl_global_lock_pending);
* interrupt level
*/
ACPI_GLOBAL(acpi_spinlock, acpi_gbl_gpe_lock); /* For GPE data structs and registers */
-ACPI_GLOBAL(acpi_spinlock, acpi_gbl_hardware_lock); /* For ACPI H/W except GPE registers */
+ACPI_GLOBAL(acpi_raw_spinlock, acpi_gbl_hardware_lock); /* For ACPI H/W except GPE registers */
ACPI_GLOBAL(acpi_spinlock, acpi_gbl_reference_count_lock);
/* Mutex for _OSI support */
diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h
index 514aaf9..3825df9 100644
--- a/drivers/acpi/acpica/acnamesp.h
+++ b/drivers/acpi/acpica/acnamesp.h
@@ -56,6 +56,10 @@ acpi_status acpi_ns_initialize_objects(void);
acpi_status acpi_ns_initialize_devices(u32 flags);
+acpi_status
+acpi_ns_init_one_package(acpi_handle obj_handle,
+ u32 level, void *context, void **return_value);
+
/*
* nsload - Namespace loading
*/
diff --git a/drivers/acpi/acpica/dbnames.c b/drivers/acpi/acpica/dbnames.c
index 170802c..dc94de9 100644
--- a/drivers/acpi/acpica/dbnames.c
+++ b/drivers/acpi/acpica/dbnames.c
@@ -189,9 +189,15 @@ void acpi_db_dump_namespace(char *start_arg, char *depth_arg)
}
acpi_db_set_output_destination(ACPI_DB_DUPLICATE_OUTPUT);
- acpi_os_printf("ACPI Namespace (from %4.4s (%p) subtree):\n",
- ((struct acpi_namespace_node *)subtree_entry)->name.
- ascii, subtree_entry);
+
+ if (((struct acpi_namespace_node *)subtree_entry)->parent) {
+ acpi_os_printf("ACPI Namespace (from %4.4s (%p) subtree):\n",
+ ((struct acpi_namespace_node *)subtree_entry)->
+ name.ascii, subtree_entry);
+ } else {
+ acpi_os_printf("ACPI Namespace (from %s):\n",
+ ACPI_NAMESPACE_ROOT);
+ }
/* Display the subtree */
diff --git a/drivers/acpi/acpica/dbtest.c b/drivers/acpi/acpica/dbtest.c
index 3892680..8a54624 100644
--- a/drivers/acpi/acpica/dbtest.c
+++ b/drivers/acpi/acpica/dbtest.c
@@ -30,6 +30,8 @@ acpi_db_test_buffer_type(struct acpi_namespace_node *node, u32 bit_length);
static acpi_status
acpi_db_test_string_type(struct acpi_namespace_node *node, u32 byte_length);
+static acpi_status acpi_db_test_package_type(struct acpi_namespace_node *node);
+
static acpi_status
acpi_db_read_from_object(struct acpi_namespace_node *node,
acpi_object_type expected_type,
@@ -273,6 +275,11 @@ acpi_db_test_one_object(acpi_handle obj_handle,
bit_length = byte_length * 8;
break;
+ case ACPI_TYPE_PACKAGE:
+
+ local_type = ACPI_TYPE_PACKAGE;
+ break;
+
case ACPI_TYPE_FIELD_UNIT:
case ACPI_TYPE_BUFFER_FIELD:
case ACPI_TYPE_LOCAL_REGION_FIELD:
@@ -305,6 +312,7 @@ acpi_db_test_one_object(acpi_handle obj_handle,
acpi_os_printf("%14s: %4.4s",
acpi_ut_get_type_name(node->type), node->name.ascii);
+
if (!obj_desc) {
acpi_os_printf(" Ignoring, no attached object\n");
return (AE_OK);
@@ -322,14 +330,13 @@ acpi_db_test_one_object(acpi_handle obj_handle,
case ACPI_ADR_SPACE_SYSTEM_MEMORY:
case ACPI_ADR_SPACE_SYSTEM_IO:
case ACPI_ADR_SPACE_PCI_CONFIG:
- case ACPI_ADR_SPACE_EC:
break;
default:
acpi_os_printf
- (" %s space is not supported [%4.4s]\n",
+ (" %s space is not supported in this command [%4.4s]\n",
acpi_ut_get_region_name(region_obj->region.
space_id),
region_obj->region.node->name.ascii);
@@ -359,6 +366,11 @@ acpi_db_test_one_object(acpi_handle obj_handle,
status = acpi_db_test_buffer_type(node, bit_length);
break;
+ case ACPI_TYPE_PACKAGE:
+
+ status = acpi_db_test_package_type(node);
+ break;
+
default:
acpi_os_printf(" Ignoring, type not implemented (%2.2X)",
@@ -366,6 +378,13 @@ acpi_db_test_one_object(acpi_handle obj_handle,
break;
}
+ /* Exit on error, but don't abort the namespace walk */
+
+ if (ACPI_FAILURE(status)) {
+ status = AE_OK;
+ goto exit;
+ }
+
switch (node->type) {
case ACPI_TYPE_LOCAL_REGION_FIELD:
@@ -373,12 +392,14 @@ acpi_db_test_one_object(acpi_handle obj_handle,
acpi_os_printf(" (%s)",
acpi_ut_get_region_name(region_obj->region.
space_id));
+
break;
default:
break;
}
+exit:
acpi_os_printf("\n");
return (status);
}
@@ -431,7 +452,6 @@ acpi_db_test_integer_type(struct acpi_namespace_node *node, u32 bit_length)
if (temp1->integer.value == value_to_write) {
value_to_write = 0;
}
-
/* Write a new value */
write_value.type = ACPI_TYPE_INTEGER;
@@ -708,6 +728,35 @@ acpi_db_test_string_type(struct acpi_namespace_node *node, u32 byte_length)
/*******************************************************************************
*
+ * FUNCTION: acpi_db_test_package_type
+ *
+ * PARAMETERS: node - Parent NS node for the object
+ *
+ * RETURN: Status
+ *
+ * DESCRIPTION: Test read for a Package object.
+ *
+ ******************************************************************************/
+
+static acpi_status acpi_db_test_package_type(struct acpi_namespace_node *node)
+{
+ union acpi_object *temp1 = NULL;
+ acpi_status status;
+
+ /* Read the original value */
+
+ status = acpi_db_read_from_object(node, ACPI_TYPE_PACKAGE, &temp1);
+ if (ACPI_FAILURE(status)) {
+ return (status);
+ }
+
+ acpi_os_printf(" %8.8X Elements", temp1->package.count);
+ acpi_os_free(temp1);
+ return (status);
+}
+
+/*******************************************************************************
+ *
* FUNCTION: acpi_db_read_from_object
*
* PARAMETERS: node - Parent NS node for the object
@@ -746,8 +795,8 @@ acpi_db_read_from_object(struct acpi_namespace_node *node,
acpi_gbl_method_executing = TRUE;
status = acpi_evaluate_object(read_handle, NULL,
¶m_objects, &return_obj);
- acpi_gbl_method_executing = FALSE;
+ acpi_gbl_method_executing = FALSE;
if (ACPI_FAILURE(status)) {
acpi_os_printf("Could not read from object, %s",
acpi_format_exception(status));
@@ -760,6 +809,7 @@ acpi_db_read_from_object(struct acpi_namespace_node *node,
case ACPI_TYPE_INTEGER:
case ACPI_TYPE_BUFFER:
case ACPI_TYPE_STRING:
+ case ACPI_TYPE_PACKAGE:
/*
* Did we receive the type we wanted? Most important for the
* Integer/Buffer case (when a field is larger than an Integer,
@@ -771,6 +821,7 @@ acpi_db_read_from_object(struct acpi_namespace_node *node,
acpi_ut_get_type_name(expected_type),
acpi_ut_get_type_name(ret_value->type));
+ acpi_os_free(return_obj.pointer);
return (AE_TYPE);
}
diff --git a/drivers/acpi/acpica/dswscope.c b/drivers/acpi/acpica/dswscope.c
index d1422f9..7592176 100644
--- a/drivers/acpi/acpica/dswscope.c
+++ b/drivers/acpi/acpica/dswscope.c
@@ -115,7 +115,7 @@ acpi_ds_scope_stack_push(struct acpi_namespace_node *node,
acpi_ut_get_type_name(old_scope_info->
common.value)));
} else {
- ACPI_DEBUG_PRINT_RAW((ACPI_DB_EXEC, "[\\___] (%s)", "ROOT"));
+ ACPI_DEBUG_PRINT_RAW((ACPI_DB_EXEC, ACPI_NAMESPACE_ROOT));
}
ACPI_DEBUG_PRINT_RAW((ACPI_DB_EXEC,
@@ -166,14 +166,14 @@ acpi_status acpi_ds_scope_stack_pop(struct acpi_walk_state *walk_state)
new_scope_info = walk_state->scope_info;
if (new_scope_info) {
- ACPI_DEBUG_PRINT_RAW((ACPI_DB_EXEC,
- "[%4.4s] (%s)\n",
+ ACPI_DEBUG_PRINT_RAW((ACPI_DB_EXEC, "[%4.4s] (%s)\n",
acpi_ut_get_node_name(new_scope_info->
scope.node),
acpi_ut_get_type_name(new_scope_info->
common.value)));
} else {
- ACPI_DEBUG_PRINT_RAW((ACPI_DB_EXEC, "[\\___] (ROOT)\n"));
+ ACPI_DEBUG_PRINT_RAW((ACPI_DB_EXEC, "%s\n",
+ ACPI_NAMESPACE_ROOT));
}
acpi_ut_delete_generic_state(scope_info);
diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c
index abbd590..e10fec9 100644
--- a/drivers/acpi/acpica/evgpe.c
+++ b/drivers/acpi/acpica/evgpe.c
@@ -634,6 +634,12 @@ acpi_ev_detect_gpe(struct acpi_namespace_node *gpe_device,
flags = acpi_os_acquire_lock(acpi_gbl_gpe_lock);
+ if (!gpe_event_info) {
+ gpe_event_info = acpi_ev_get_gpe_event_info(gpe_device, gpe_number);
+ if (!gpe_event_info)
+ goto error_exit;
+ }
+
/* Get the info block for the entire GPE register */
gpe_register_info = gpe_event_info->register_info;
diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c
index c80e3bdf..b2d5f66 100644
--- a/drivers/acpi/acpica/evxfgpe.c
+++ b/drivers/acpi/acpica/evxfgpe.c
@@ -639,6 +639,28 @@ ACPI_EXPORT_SYMBOL(acpi_get_gpe_status)
/*******************************************************************************
*
+ * FUNCTION: acpi_gispatch_gpe
+ *
+ * PARAMETERS: gpe_device - Parent GPE Device. NULL for GPE0/GPE1
+ * gpe_number - GPE level within the GPE block
+ *
+ * RETURN: None
+ *
+ * DESCRIPTION: Detect and dispatch a General Purpose Event to either a function
+ * (e.g. EC) or method (e.g. _Lxx/_Exx) handler.
+ *
+ ******************************************************************************/
+void acpi_dispatch_gpe(acpi_handle gpe_device, u32 gpe_number)
+{
+ ACPI_FUNCTION_TRACE(acpi_dispatch_gpe);
+
+ acpi_ev_detect_gpe(gpe_device, NULL, gpe_number);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_dispatch_gpe)
+
+/*******************************************************************************
+ *
* FUNCTION: acpi_finish_gpe
*
* PARAMETERS: gpe_device - Namespace node for the GPE Block
diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c
index 99d92cb..f85c6f3 100644
--- a/drivers/acpi/acpica/exconfig.c
+++ b/drivers/acpi/acpica/exconfig.c
@@ -174,6 +174,13 @@ acpi_ex_load_table_op(struct acpi_walk_state *walk_state,
return_ACPI_STATUS(status);
}
+ /* Complete the initialization/resolution of package objects */
+
+ status = acpi_ns_walk_namespace(ACPI_TYPE_PACKAGE, ACPI_ROOT_OBJECT,
+ ACPI_UINT32_MAX, 0,
+ acpi_ns_init_one_package, NULL, NULL,
+ NULL);
+
/* Parameter Data (optional) */
if (parameter_node) {
@@ -430,6 +437,13 @@ acpi_ex_load_op(union acpi_operand_object *obj_desc,
return_ACPI_STATUS(status);
}
+ /* Complete the initialization/resolution of package objects */
+
+ status = acpi_ns_walk_namespace(ACPI_TYPE_PACKAGE, ACPI_ROOT_OBJECT,
+ ACPI_UINT32_MAX, 0,
+ acpi_ns_init_one_package, NULL, NULL,
+ NULL);
+
/* Store the ddb_handle into the Target operand */
status = acpi_ex_store(ddb_handle, target, walk_state);
diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c
index 27a86ad..3de794b 100644
--- a/drivers/acpi/acpica/hwregs.c
+++ b/drivers/acpi/acpica/hwregs.c
@@ -390,14 +390,14 @@ acpi_status acpi_hw_clear_acpi_status(void)
ACPI_BITMASK_ALL_FIXED_STATUS,
ACPI_FORMAT_UINT64(acpi_gbl_xpm1a_status.address)));
- lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock);
+ lock_flags = acpi_os_acquire_raw_lock(acpi_gbl_hardware_lock);
/* Clear the fixed events in PM1 A/B */
status = acpi_hw_register_write(ACPI_REGISTER_PM1_STATUS,
ACPI_BITMASK_ALL_FIXED_STATUS);
- acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags);
+ acpi_os_release_raw_lock(acpi_gbl_hardware_lock, lock_flags);
if (ACPI_FAILURE(status)) {
goto exit;
diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c
index 5d13968..6e39a77 100644
--- a/drivers/acpi/acpica/hwxface.c
+++ b/drivers/acpi/acpica/hwxface.c
@@ -227,7 +227,7 @@ acpi_status acpi_write_bit_register(u32 register_id, u32 value)
return_ACPI_STATUS(AE_BAD_PARAMETER);
}
- lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock);
+ lock_flags = acpi_os_acquire_raw_lock(acpi_gbl_hardware_lock);
/*
* At this point, we know that the parent register is one of the
@@ -288,7 +288,7 @@ acpi_status acpi_write_bit_register(u32 register_id, u32 value)
unlock_and_exit:
- acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags);
+ acpi_os_release_raw_lock(acpi_gbl_hardware_lock, lock_flags);
return_ACPI_STATUS(status);
}
diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c
index 77f2b5f..d77257d 100644
--- a/drivers/acpi/acpica/nsinit.c
+++ b/drivers/acpi/acpica/nsinit.c
@@ -242,6 +242,58 @@ acpi_status acpi_ns_initialize_devices(u32 flags)
/*******************************************************************************
*
+ * FUNCTION: acpi_ns_init_one_package
+ *
+ * PARAMETERS: obj_handle - Node
+ * level - Current nesting level
+ * context - Not used
+ * return_value - Not used
+ *
+ * RETURN: Status
+ *
+ * DESCRIPTION: Callback from acpi_walk_namespace. Invoked for every package
+ * within the namespace. Used during dynamic load of an SSDT.
+ *
+ ******************************************************************************/
+
+acpi_status
+acpi_ns_init_one_package(acpi_handle obj_handle,
+ u32 level, void *context, void **return_value)
+{
+ acpi_status status;
+ union acpi_operand_object *obj_desc;
+ struct acpi_namespace_node *node =
+ (struct acpi_namespace_node *)obj_handle;
+
+ obj_desc = acpi_ns_get_attached_object(node);
+ if (!obj_desc) {
+ return (AE_OK);
+ }
+
+ /* Exit if package is already initialized */
+
+ if (obj_desc->package.flags & AOPOBJ_DATA_VALID) {
+ return (AE_OK);
+ }
+
+ status = acpi_ds_get_package_arguments(obj_desc);
+ if (ACPI_FAILURE(status)) {
+ return (AE_OK);
+ }
+
+ status =
+ acpi_ut_walk_package_tree(obj_desc, NULL,
+ acpi_ds_init_package_element, NULL);
+ if (ACPI_FAILURE(status)) {
+ return (AE_OK);
+ }
+
+ obj_desc->package.flags |= AOPOBJ_DATA_VALID;
+ return (AE_OK);
+}
+
+/*******************************************************************************
+ *
* FUNCTION: acpi_ns_init_one_object
*
* PARAMETERS: obj_handle - Node
@@ -360,27 +412,11 @@ acpi_ns_init_one_object(acpi_handle obj_handle,
case ACPI_TYPE_PACKAGE:
+ /* Complete the initialization/resolution of the package object */
+
info->package_init++;
- status = acpi_ds_get_package_arguments(obj_desc);
- if (ACPI_FAILURE(status)) {
- break;
- }
-
- ACPI_DEBUG_PRINT_RAW((ACPI_DB_PARSE,
- "%s: Completing resolution of Package elements\n",
- ACPI_GET_FUNCTION_NAME));
-
- /*
- * Resolve all named references in package objects (and all
- * sub-packages). This action has been deferred until the entire
- * namespace has been loaded, in order to support external and
- * forward references from individual package elements (05/2017).
- */
- status = acpi_ut_walk_package_tree(obj_desc, NULL,
- acpi_ds_init_package_element,
- NULL);
-
- obj_desc->package.flags |= AOPOBJ_DATA_VALID;
+ status =
+ acpi_ns_init_one_package(obj_handle, level, NULL, NULL);
break;
default:
diff --git a/drivers/acpi/acpica/rsdump.c b/drivers/acpi/acpica/rsdump.c
index b12a0b1..6601e71 100644
--- a/drivers/acpi/acpica/rsdump.c
+++ b/drivers/acpi/acpica/rsdump.c
@@ -539,7 +539,7 @@ static void acpi_rs_out_title(const char *title)
static void acpi_rs_dump_byte_list(u16 length, u8 * data)
{
- u8 i;
+ u16 i;
for (i = 0; i < length; i++) {
acpi_os_printf("%25s%2.2X : %2.2X\n", "Byte", i, data[i]);
diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c
index c5085b7..5f8e7b5 100644
--- a/drivers/acpi/acpica/tbinstal.c
+++ b/drivers/acpi/acpica/tbinstal.c
@@ -88,7 +88,7 @@ acpi_tb_install_table_with_override(struct acpi_table_desc *new_table_desc,
* DESCRIPTION: This function is called to verify and install an ACPI table.
* When this function is called by "Load" or "LoadTable" opcodes,
* or by acpi_load_table() API, the "Reload" parameter is set.
- * After sucessfully returning from this function, table is
+ * After successfully returning from this function, table is
* "INSTALLED" but not "VALIDATED".
*
******************************************************************************/
diff --git a/drivers/acpi/acpica/utbuffer.c b/drivers/acpi/acpica/utbuffer.c
index 148aeb8..fffa6f5 100644
--- a/drivers/acpi/acpica/utbuffer.c
+++ b/drivers/acpi/acpica/utbuffer.c
@@ -53,7 +53,7 @@ void acpi_ut_dump_buffer(u8 *buffer, u32 count, u32 display, u32 base_offset)
/* Print current offset */
- acpi_os_printf("%6.4X: ", (base_offset + i));
+ acpi_os_printf("%8.4X: ", (base_offset + i));
/* Print 16 hex chars */
@@ -219,7 +219,7 @@ acpi_ut_dump_buffer_to_file(ACPI_FILE file,
/* Print current offset */
- fprintf(file, "%6.4X: ", (base_offset + i));
+ fprintf(file, "%8.4X: ", (base_offset + i));
/* Print 16 hex chars */
diff --git a/drivers/acpi/acpica/utmutex.c b/drivers/acpi/acpica/utmutex.c
index d2d93e3..2e465e6 100644
--- a/drivers/acpi/acpica/utmutex.c
+++ b/drivers/acpi/acpica/utmutex.c
@@ -52,7 +52,7 @@ acpi_status acpi_ut_mutex_initialize(void)
return_ACPI_STATUS (status);
}
- status = acpi_os_create_lock (&acpi_gbl_hardware_lock);
+ status = acpi_os_create_raw_lock(&acpi_gbl_hardware_lock);
if (ACPI_FAILURE (status)) {
return_ACPI_STATUS (status);
}
@@ -109,7 +109,7 @@ void acpi_ut_mutex_terminate(void)
/* Delete the spinlocks */
acpi_os_delete_lock(acpi_gbl_gpe_lock);
- acpi_os_delete_lock(acpi_gbl_hardware_lock);
+ acpi_os_delete_raw_lock(acpi_gbl_hardware_lock);
acpi_os_delete_lock(acpi_gbl_reference_count_lock);
/* Delete the reader/writer lock */
diff --git a/drivers/acpi/acpica/utobject.c b/drivers/acpi/acpica/utobject.c
index 5b78fe0..ae6d8cc 100644
--- a/drivers/acpi/acpica/utobject.c
+++ b/drivers/acpi/acpica/utobject.c
@@ -8,6 +8,7 @@
*****************************************************************************/
#include <acpi/acpi.h>
+#include <linux/kmemleak.h>
#include "accommon.h"
#include "acnamesp.h"
@@ -70,6 +71,7 @@ union acpi_operand_object *acpi_ut_create_internal_object_dbg(const char
if (!object) {
return_PTR(NULL);
}
+ kmemleak_not_leak(object);
switch (type) {
case ACPI_TYPE_REGION:
diff --git a/drivers/acpi/acpica/utprint.c b/drivers/acpi/acpica/utprint.c
index 35ffd8d..a98c334 100644
--- a/drivers/acpi/acpica/utprint.c
+++ b/drivers/acpi/acpica/utprint.c
@@ -470,6 +470,7 @@ int vsnprintf(char *string, acpi_size size, const char *format, va_list args)
case 'X':
type |= ACPI_FORMAT_UPPER;
+ /* FALLTHROUGH */
case 'x':
diff --git a/drivers/acpi/acpica/utstring.c b/drivers/acpi/acpica/utstring.c
index bd57a77..5bef0b0 100644
--- a/drivers/acpi/acpica/utstring.c
+++ b/drivers/acpi/acpica/utstring.c
@@ -141,7 +141,7 @@ void acpi_ut_repair_name(char *name)
* Special case for the root node. This can happen if we get an
* error during the execution of module-level code.
*/
- if (ACPI_COMPARE_NAME(name, "\\___")) {
+ if (ACPI_COMPARE_NAME(name, ACPI_ROOT_PATHNAME)) {
return;
}
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index bdb24d6..b0113a5 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -74,6 +74,8 @@ static async_cookie_t async_cookie;
static bool battery_driver_registered;
static int battery_bix_broken_package;
static int battery_notification_delay_ms;
+static int battery_ac_is_broken;
+static int battery_check_pmic = 1;
static unsigned int cache_time = 1000;
module_param(cache_time, uint, 0644);
MODULE_PARM_DESC(cache_time, "cache time in milliseconds");
@@ -81,14 +83,6 @@ MODULE_PARM_DESC(cache_time, "cache time in milliseconds");
#ifdef CONFIG_ACPI_PROCFS_POWER
extern struct proc_dir_entry *acpi_lock_battery_dir(void);
extern void *acpi_unlock_battery_dir(struct proc_dir_entry *acpi_battery_dir);
-
-enum acpi_battery_files {
- info_tag = 0,
- state_tag,
- alarm_tag,
- ACPI_BATTERY_NUMFILES,
-};
-
#endif
static const struct acpi_device_id battery_device_ids[] = {
@@ -215,6 +209,20 @@ static bool acpi_battery_is_degraded(struct acpi_battery *battery)
battery->full_charge_capacity < battery->design_capacity;
}
+static int acpi_battery_handle_discharging(struct acpi_battery *battery)
+{
+ /*
+ * Some devices wrongly report discharging if the battery's charge level
+ * was above the device's start charging threshold atm the AC adapter
+ * was plugged in and the device thus did not start a new charge cycle.
+ */
+ if ((battery_ac_is_broken || power_supply_is_system_supplied()) &&
+ battery->rate_now == 0)
+ return POWER_SUPPLY_STATUS_NOT_CHARGING;
+
+ return POWER_SUPPLY_STATUS_DISCHARGING;
+}
+
static int acpi_battery_get_property(struct power_supply *psy,
enum power_supply_property psp,
union power_supply_propval *val)
@@ -230,7 +238,7 @@ static int acpi_battery_get_property(struct power_supply *psy,
switch (psp) {
case POWER_SUPPLY_PROP_STATUS:
if (battery->state & ACPI_BATTERY_STATE_DISCHARGING)
- val->intval = POWER_SUPPLY_STATUS_DISCHARGING;
+ val->intval = acpi_battery_handle_discharging(battery);
else if (battery->state & ACPI_BATTERY_STATE_CHARGING)
val->intval = POWER_SUPPLY_STATUS_CHARGING;
else if (acpi_battery_is_charged(battery))
@@ -985,9 +993,10 @@ static const char *acpi_battery_units(const struct acpi_battery *battery)
"mA" : "mW";
}
-static int acpi_battery_print_info(struct seq_file *seq, int result)
+static int acpi_battery_info_proc_show(struct seq_file *seq, void *offset)
{
struct acpi_battery *battery = seq->private;
+ int result = acpi_battery_update(battery, false);
if (result)
goto end;
@@ -1041,9 +1050,10 @@ static int acpi_battery_print_info(struct seq_file *seq, int result)
return result;
}
-static int acpi_battery_print_state(struct seq_file *seq, int result)
+static int acpi_battery_state_proc_show(struct seq_file *seq, void *offset)
{
struct acpi_battery *battery = seq->private;
+ int result = acpi_battery_update(battery, false);
if (result)
goto end;
@@ -1088,9 +1098,10 @@ static int acpi_battery_print_state(struct seq_file *seq, int result)
return result;
}
-static int acpi_battery_print_alarm(struct seq_file *seq, int result)
+static int acpi_battery_alarm_proc_show(struct seq_file *seq, void *offset)
{
struct acpi_battery *battery = seq->private;
+ int result = acpi_battery_update(battery, false);
if (result)
goto end;
@@ -1142,82 +1153,22 @@ static ssize_t acpi_battery_write_alarm(struct file *file,
return result;
}
-typedef int(*print_func)(struct seq_file *seq, int result);
-
-static print_func acpi_print_funcs[ACPI_BATTERY_NUMFILES] = {
- acpi_battery_print_info,
- acpi_battery_print_state,
- acpi_battery_print_alarm,
-};
-
-static int acpi_battery_read(int fid, struct seq_file *seq)
+static int acpi_battery_alarm_proc_open(struct inode *inode, struct file *file)
{
- struct acpi_battery *battery = seq->private;
- int result = acpi_battery_update(battery, false);
- return acpi_print_funcs[fid](seq, result);
+ return single_open(file, acpi_battery_alarm_proc_show, PDE_DATA(inode));
}
-#define DECLARE_FILE_FUNCTIONS(_name) \
-static int acpi_battery_read_##_name(struct seq_file *seq, void *offset) \
-{ \
- return acpi_battery_read(_name##_tag, seq); \
-} \
-static int acpi_battery_##_name##_open_fs(struct inode *inode, struct file *file) \
-{ \
- return single_open(file, acpi_battery_read_##_name, PDE_DATA(inode)); \
-}
-
-DECLARE_FILE_FUNCTIONS(info);
-DECLARE_FILE_FUNCTIONS(state);
-DECLARE_FILE_FUNCTIONS(alarm);
-
-#undef DECLARE_FILE_FUNCTIONS
-
-#define FILE_DESCRIPTION_RO(_name) \
- { \
- .name = __stringify(_name), \
- .mode = S_IRUGO, \
- .ops = { \
- .open = acpi_battery_##_name##_open_fs, \
- .read = seq_read, \
- .llseek = seq_lseek, \
- .release = single_release, \
- .owner = THIS_MODULE, \
- }, \
- }
-
-#define FILE_DESCRIPTION_RW(_name) \
- { \
- .name = __stringify(_name), \
- .mode = S_IFREG | S_IRUGO | S_IWUSR, \
- .ops = { \
- .open = acpi_battery_##_name##_open_fs, \
- .read = seq_read, \
- .llseek = seq_lseek, \
- .write = acpi_battery_write_##_name, \
- .release = single_release, \
- .owner = THIS_MODULE, \
- }, \
- }
-
-static const struct battery_file {
- struct file_operations ops;
- umode_t mode;
- const char *name;
-} acpi_battery_file[] = {
- FILE_DESCRIPTION_RO(info),
- FILE_DESCRIPTION_RO(state),
- FILE_DESCRIPTION_RW(alarm),
+static const struct file_operations acpi_battery_alarm_fops = {
+ .owner = THIS_MODULE,
+ .open = acpi_battery_alarm_proc_open,
+ .read = seq_read,
+ .write = acpi_battery_write_alarm,
+ .llseek = seq_lseek,
+ .release = single_release,
};
-#undef FILE_DESCRIPTION_RO
-#undef FILE_DESCRIPTION_RW
-
static int acpi_battery_add_fs(struct acpi_device *device)
{
- struct proc_dir_entry *entry = NULL;
- int i;
-
printk(KERN_WARNING PREFIX "Deprecated procfs I/F for battery is loaded,"
" please retry with CONFIG_ACPI_PROCFS_POWER cleared\n");
if (!acpi_device_dir(device)) {
@@ -1227,28 +1178,24 @@ static int acpi_battery_add_fs(struct acpi_device *device)
return -ENODEV;
}
- for (i = 0; i < ACPI_BATTERY_NUMFILES; ++i) {
- entry = proc_create_data(acpi_battery_file[i].name,
- acpi_battery_file[i].mode,
- acpi_device_dir(device),
- &acpi_battery_file[i].ops,
- acpi_driver_data(device));
- if (!entry)
- return -ENODEV;
- }
+ if (!proc_create_single_data("info", S_IRUGO, acpi_device_dir(device),
+ acpi_battery_info_proc_show, acpi_driver_data(device)))
+ return -ENODEV;
+ if (!proc_create_single_data("state", S_IRUGO, acpi_device_dir(device),
+ acpi_battery_state_proc_show, acpi_driver_data(device)))
+ return -ENODEV;
+ if (!proc_create_data("alarm", S_IFREG | S_IRUGO | S_IWUSR,
+ acpi_device_dir(device), &acpi_battery_alarm_fops,
+ acpi_driver_data(device)))
+ return -ENODEV;
return 0;
}
static void acpi_battery_remove_fs(struct acpi_device *device)
{
- int i;
if (!acpi_device_dir(device))
return;
- for (i = 0; i < ACPI_BATTERY_NUMFILES; ++i)
- remove_proc_entry(acpi_battery_file[i].name,
- acpi_device_dir(device));
-
- remove_proc_entry(acpi_device_bid(device), acpi_battery_dir);
+ remove_proc_subtree(acpi_device_bid(device), acpi_battery_dir);
acpi_device_dir(device) = NULL;
}
@@ -1332,23 +1279,64 @@ battery_notification_delay_quirk(const struct dmi_system_id *d)
return 0;
}
+static int __init
+battery_ac_is_broken_quirk(const struct dmi_system_id *d)
+{
+ battery_ac_is_broken = 1;
+ return 0;
+}
+
+static int __init
+battery_do_not_check_pmic_quirk(const struct dmi_system_id *d)
+{
+ battery_check_pmic = 0;
+ return 0;
+}
+
static const struct dmi_system_id bat_dmi_table[] __initconst = {
{
+ /* NEC LZ750/LS */
.callback = battery_bix_broken_package_quirk,
- .ident = "NEC LZ750/LS",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
DMI_MATCH(DMI_PRODUCT_NAME, "PC-LZ750LS"),
},
},
{
+ /* Acer Aspire V5-573G */
.callback = battery_notification_delay_quirk,
- .ident = "Acer Aspire V5-573G",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
DMI_MATCH(DMI_PRODUCT_NAME, "Aspire V5-573G"),
},
},
+ {
+ /* Point of View mobii wintab p800w */
+ .callback = battery_ac_is_broken_quirk,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
+ DMI_MATCH(DMI_BOARD_NAME, "Aptio CRB"),
+ DMI_MATCH(DMI_BIOS_VERSION, "3BAIR1013"),
+ /* Above matches are too generic, add bios-date match */
+ DMI_MATCH(DMI_BIOS_DATE, "08/22/2014"),
+ },
+ },
+ {
+ /* ECS EF20EA */
+ .callback = battery_do_not_check_pmic_quirk,
+ .matches = {
+ DMI_MATCH(DMI_PRODUCT_NAME, "EF20EA"),
+ },
+ },
+ {
+ /* Lenovo Ideapad Miix 320 */
+ .callback = battery_do_not_check_pmic_quirk,
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "80XF"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo MIIX 320-10ICR"),
+ },
+ },
{},
};
@@ -1488,16 +1476,18 @@ static void __init acpi_battery_init_async(void *unused, async_cookie_t cookie)
unsigned int i;
int result;
- for (i = 0; i < ARRAY_SIZE(acpi_battery_blacklist); i++)
- if (acpi_dev_present(acpi_battery_blacklist[i], "1", -1)) {
- pr_info(PREFIX ACPI_BATTERY_DEVICE_NAME
- ": found native %s PMIC, not loading\n",
- acpi_battery_blacklist[i]);
- return;
- }
-
dmi_check_system(bat_dmi_table);
+ if (battery_check_pmic) {
+ for (i = 0; i < ARRAY_SIZE(acpi_battery_blacklist); i++)
+ if (acpi_dev_present(acpi_battery_blacklist[i], "1", -1)) {
+ pr_info(PREFIX ACPI_BATTERY_DEVICE_NAME
+ ": found native %s PMIC, not loading\n",
+ acpi_battery_blacklist[i]);
+ return;
+ }
+ }
+
#ifdef CONFIG_ACPI_PROCFS_POWER
acpi_battery_dir = acpi_lock_battery_dir();
if (!acpi_battery_dir)
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index e1eee7a..2345a5e 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -263,19 +263,6 @@ static int acpi_button_state_seq_show(struct seq_file *seq, void *offset)
return 0;
}
-static int acpi_button_state_open_fs(struct inode *inode, struct file *file)
-{
- return single_open(file, acpi_button_state_seq_show, PDE_DATA(inode));
-}
-
-static const struct file_operations acpi_button_state_fops = {
- .owner = THIS_MODULE,
- .open = acpi_button_state_open_fs,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int acpi_button_add_fs(struct acpi_device *device)
{
struct acpi_button *button = acpi_driver_data(device);
@@ -311,9 +298,9 @@ static int acpi_button_add_fs(struct acpi_device *device)
}
/* create /proc/acpi/button/lid/LID/state */
- entry = proc_create_data(ACPI_BUTTON_FILE_STATE,
- S_IRUGO, acpi_device_dir(device),
- &acpi_button_state_fops, device);
+ entry = proc_create_single_data(ACPI_BUTTON_FILE_STATE, S_IRUGO,
+ acpi_device_dir(device), acpi_button_state_seq_show,
+ device);
if (!entry) {
ret = -ENODEV;
goto remove_dev_dir;
@@ -635,4 +622,26 @@ module_param_call(lid_init_state,
NULL, 0644);
MODULE_PARM_DESC(lid_init_state, "Behavior for reporting LID initial state");
-module_acpi_driver(acpi_button_driver);
+static int acpi_button_register_driver(struct acpi_driver *driver)
+{
+ /*
+ * Modules such as nouveau.ko and i915.ko have a link time dependency
+ * on acpi_lid_open(), and would therefore not be loadable on ACPI
+ * capable kernels booted in non-ACPI mode if the return value of
+ * acpi_bus_register_driver() is returned from here with ACPI disabled
+ * when this driver is built as a module.
+ */
+ if (acpi_disabled)
+ return 0;
+
+ return acpi_bus_register_driver(driver);
+}
+
+static void acpi_button_unregister_driver(struct acpi_driver *driver)
+{
+ if (!acpi_disabled)
+ acpi_bus_unregister_driver(driver);
+}
+
+module_driver(acpi_button_driver, acpi_button_register_driver,
+ acpi_button_unregister_driver);
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 735c74a..d9ce4b1 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -39,6 +39,7 @@
#include <linux/cpufreq.h>
#include <linux/delay.h>
+#include <linux/iopoll.h>
#include <linux/ktime.h>
#include <linux/rwsem.h>
#include <linux/wait.h>
@@ -49,7 +50,7 @@ struct cppc_pcc_data {
struct mbox_chan *pcc_channel;
void __iomem *pcc_comm_addr;
bool pcc_channel_acquired;
- ktime_t deadline;
+ unsigned int deadline_us;
unsigned int pcc_mpar, pcc_mrtt, pcc_nominal;
bool pending_pcc_write_cmd; /* Any pending/batched PCC write cmds? */
@@ -156,6 +157,9 @@ show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, highest_perf);
show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, lowest_perf);
show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, nominal_perf);
show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, lowest_nonlinear_perf);
+show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, lowest_freq);
+show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, nominal_freq);
+
show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, reference_perf);
show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, wraparound_time);
@@ -183,6 +187,8 @@ static struct attribute *cppc_attrs[] = {
&lowest_perf.attr,
&lowest_nonlinear_perf.attr,
&nominal_perf.attr,
+ &nominal_freq.attr,
+ &lowest_freq.attr,
NULL
};
@@ -193,42 +199,31 @@ static struct kobj_type cppc_ktype = {
static int check_pcc_chan(int pcc_ss_id, bool chk_err_bit)
{
- int ret = -EIO, status = 0;
+ int ret, status;
struct cppc_pcc_data *pcc_ss_data = pcc_data[pcc_ss_id];
struct acpi_pcct_shared_memory __iomem *generic_comm_base =
pcc_ss_data->pcc_comm_addr;
- ktime_t next_deadline = ktime_add(ktime_get(),
- pcc_ss_data->deadline);
if (!pcc_ss_data->platform_owns_pcc)
return 0;
- /* Retry in case the remote processor was too slow to catch up. */
- while (!ktime_after(ktime_get(), next_deadline)) {
- /*
- * Per spec, prior to boot the PCC space wil be initialized by
- * platform and should have set the command completion bit when
- * PCC can be used by OSPM
- */
- status = readw_relaxed(&generic_comm_base->status);
- if (status & PCC_CMD_COMPLETE_MASK) {
- ret = 0;
- if (chk_err_bit && (status & PCC_ERROR_MASK))
- ret = -EIO;
- break;
- }
- /*
- * Reducing the bus traffic in case this loop takes longer than
- * a few retries.
- */
- udelay(3);
+ /*
+ * Poll PCC status register every 3us(delay_us) for maximum of
+ * deadline_us(timeout_us) until PCC command complete bit is set(cond)
+ */
+ ret = readw_relaxed_poll_timeout(&generic_comm_base->status, status,
+ status & PCC_CMD_COMPLETE_MASK, 3,
+ pcc_ss_data->deadline_us);
+
+ if (likely(!ret)) {
+ pcc_ss_data->platform_owns_pcc = false;
+ if (chk_err_bit && (status & PCC_ERROR_MASK))
+ ret = -EIO;
}
- if (likely(!ret))
- pcc_ss_data->platform_owns_pcc = false;
- else
- pr_err("PCC check channel failed for ss: %d. Status=%x\n",
- pcc_ss_id, status);
+ if (unlikely(ret))
+ pr_err("PCC check channel failed for ss: %d. ret=%d\n",
+ pcc_ss_id, ret);
return ret;
}
@@ -580,7 +575,7 @@ static int register_pcc_channel(int pcc_ss_idx)
* So add an arbitrary amount of wait on top of Nominal.
*/
usecs_lat = NUM_RETRIES * cppc_ss->latency;
- pcc_data[pcc_ss_idx]->deadline = ns_to_ktime(usecs_lat * NSEC_PER_USEC);
+ pcc_data[pcc_ss_idx]->deadline_us = usecs_lat;
pcc_data[pcc_ss_idx]->pcc_mrtt = cppc_ss->min_turnaround_time;
pcc_data[pcc_ss_idx]->pcc_mpar = cppc_ss->max_access_rate;
pcc_data[pcc_ss_idx]->pcc_nominal = cppc_ss->latency;
@@ -613,7 +608,6 @@ bool __weak cpc_ffh_supported(void)
return false;
}
-
/**
* pcc_data_alloc() - Allocate the pcc_data memory for pcc subspace
*
@@ -641,6 +635,34 @@ int pcc_data_alloc(int pcc_ss_id)
return 0;
}
+
+/* Check if CPPC revision + num_ent combination is supported */
+static bool is_cppc_supported(int revision, int num_ent)
+{
+ int expected_num_ent;
+
+ switch (revision) {
+ case CPPC_V2_REV:
+ expected_num_ent = CPPC_V2_NUM_ENT;
+ break;
+ case CPPC_V3_REV:
+ expected_num_ent = CPPC_V3_NUM_ENT;
+ break;
+ default:
+ pr_debug("Firmware exports unsupported CPPC revision: %d\n",
+ revision);
+ return false;
+ }
+
+ if (expected_num_ent != num_ent) {
+ pr_debug("Firmware exports %d entries. Expected: %d for CPPC rev:%d\n",
+ num_ent, expected_num_ent, revision);
+ return false;
+ }
+
+ return true;
+}
+
/*
* An example CPC table looks like the following.
*
@@ -731,14 +753,6 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
cpc_obj->type);
goto out_free;
}
-
- /* Only support CPPCv2. Bail otherwise. */
- if (num_ent != CPPC_NUM_ENT) {
- pr_debug("Firmware exports %d entries. Expected: %d\n",
- num_ent, CPPC_NUM_ENT);
- goto out_free;
- }
-
cpc_ptr->num_entries = num_ent;
/* Second entry should be revision. */
@@ -750,12 +764,10 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
cpc_obj->type);
goto out_free;
}
+ cpc_ptr->version = cpc_rev;
- if (cpc_rev != CPPC_REV) {
- pr_debug("Firmware exports revision:%d. Expected:%d\n",
- cpc_rev, CPPC_REV);
+ if (!is_cppc_supported(cpc_rev, num_ent))
goto out_free;
- }
/* Iterate through remaining entries in _CPC */
for (i = 2; i < num_ent; i++) {
@@ -808,6 +820,18 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
}
}
per_cpu(cpu_pcc_subspace_idx, pr->id) = pcc_subspace_id;
+
+ /*
+ * Initialize the remaining cpc_regs as unsupported.
+ * Example: In case FW exposes CPPC v2, the below loop will initialize
+ * LOWEST_FREQ and NOMINAL_FREQ regs as unsupported
+ */
+ for (i = num_ent - 2; i < MAX_CPC_REG_ENT; i++) {
+ cpc_ptr->cpc_regs[i].type = ACPI_TYPE_INTEGER;
+ cpc_ptr->cpc_regs[i].cpc_entry.int_value = 0;
+ }
+
+
/* Store CPU Logical ID */
cpc_ptr->cpu_id = pr->id;
@@ -1037,26 +1061,34 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
{
struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
struct cpc_register_resource *highest_reg, *lowest_reg,
- *lowest_non_linear_reg, *nominal_reg;
- u64 high, low, nom, min_nonlinear;
+ *lowest_non_linear_reg, *nominal_reg,
+ *low_freq_reg = NULL, *nom_freq_reg = NULL;
+ u64 high, low, nom, min_nonlinear, low_f = 0, nom_f = 0;
int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
- struct cppc_pcc_data *pcc_ss_data;
+ struct cppc_pcc_data *pcc_ss_data = NULL;
int ret = 0, regs_in_pcc = 0;
- if (!cpc_desc || pcc_ss_id < 0) {
+ if (!cpc_desc) {
pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
return -ENODEV;
}
- pcc_ss_data = pcc_data[pcc_ss_id];
highest_reg = &cpc_desc->cpc_regs[HIGHEST_PERF];
lowest_reg = &cpc_desc->cpc_regs[LOWEST_PERF];
lowest_non_linear_reg = &cpc_desc->cpc_regs[LOW_NON_LINEAR_PERF];
nominal_reg = &cpc_desc->cpc_regs[NOMINAL_PERF];
+ low_freq_reg = &cpc_desc->cpc_regs[LOWEST_FREQ];
+ nom_freq_reg = &cpc_desc->cpc_regs[NOMINAL_FREQ];
/* Are any of the regs PCC ?*/
if (CPC_IN_PCC(highest_reg) || CPC_IN_PCC(lowest_reg) ||
- CPC_IN_PCC(lowest_non_linear_reg) || CPC_IN_PCC(nominal_reg)) {
+ CPC_IN_PCC(lowest_non_linear_reg) || CPC_IN_PCC(nominal_reg) ||
+ CPC_IN_PCC(low_freq_reg) || CPC_IN_PCC(nom_freq_reg)) {
+ if (pcc_ss_id < 0) {
+ pr_debug("Invalid pcc_ss_id\n");
+ return -ENODEV;
+ }
+ pcc_ss_data = pcc_data[pcc_ss_id];
regs_in_pcc = 1;
down_write(&pcc_ss_data->pcc_lock);
/* Ring doorbell once to update PCC subspace */
@@ -1081,6 +1113,17 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
if (!high || !low || !nom || !min_nonlinear)
ret = -EFAULT;
+ /* Read optional lowest and nominal frequencies if present */
+ if (CPC_SUPPORTED(low_freq_reg))
+ cpc_read(cpunum, low_freq_reg, &low_f);
+
+ if (CPC_SUPPORTED(nom_freq_reg))
+ cpc_read(cpunum, nom_freq_reg, &nom_f);
+
+ perf_caps->lowest_freq = low_f;
+ perf_caps->nominal_freq = nom_f;
+
+
out_err:
if (regs_in_pcc)
up_write(&pcc_ss_data->pcc_lock);
@@ -1101,16 +1144,15 @@ int cppc_get_perf_ctrs(int cpunum, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
struct cpc_register_resource *delivered_reg, *reference_reg,
*ref_perf_reg, *ctr_wrap_reg;
int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
- struct cppc_pcc_data *pcc_ss_data;
+ struct cppc_pcc_data *pcc_ss_data = NULL;
u64 delivered, reference, ref_perf, ctr_wrap_time;
int ret = 0, regs_in_pcc = 0;
- if (!cpc_desc || pcc_ss_id < 0) {
+ if (!cpc_desc) {
pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
return -ENODEV;
}
- pcc_ss_data = pcc_data[pcc_ss_id];
delivered_reg = &cpc_desc->cpc_regs[DELIVERED_CTR];
reference_reg = &cpc_desc->cpc_regs[REFERENCE_CTR];
ref_perf_reg = &cpc_desc->cpc_regs[REFERENCE_PERF];
@@ -1126,6 +1168,11 @@ int cppc_get_perf_ctrs(int cpunum, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
/* Are any of the regs PCC ?*/
if (CPC_IN_PCC(delivered_reg) || CPC_IN_PCC(reference_reg) ||
CPC_IN_PCC(ctr_wrap_reg) || CPC_IN_PCC(ref_perf_reg)) {
+ if (pcc_ss_id < 0) {
+ pr_debug("Invalid pcc_ss_id\n");
+ return -ENODEV;
+ }
+ pcc_ss_data = pcc_data[pcc_ss_id];
down_write(&pcc_ss_data->pcc_lock);
regs_in_pcc = 1;
/* Ring doorbell once to update PCC subspace */
@@ -1176,15 +1223,14 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
struct cpc_register_resource *desired_reg;
int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
- struct cppc_pcc_data *pcc_ss_data;
+ struct cppc_pcc_data *pcc_ss_data = NULL;
int ret = 0;
- if (!cpc_desc || pcc_ss_id < 0) {
+ if (!cpc_desc) {
pr_debug("No CPC descriptor for CPU:%d\n", cpu);
return -ENODEV;
}
- pcc_ss_data = pcc_data[pcc_ss_id];
desired_reg = &cpc_desc->cpc_regs[DESIRED_PERF];
/*
@@ -1195,6 +1241,11 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
* achieve that goal here
*/
if (CPC_IN_PCC(desired_reg)) {
+ if (pcc_ss_id < 0) {
+ pr_debug("Invalid pcc_ss_id\n");
+ return -ENODEV;
+ }
+ pcc_ss_data = pcc_data[pcc_ss_id];
down_read(&pcc_ss_data->pcc_lock); /* BEGIN Phase-I */
if (pcc_ss_data->platform_owns_pcc) {
ret = check_pcc_chan(pcc_ss_id, false);
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 3d96e4d..a7c2673 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -1257,10 +1257,7 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
struct acpi_device *adev = ACPI_COMPANION(dev);
if (!adev)
- return -ENODEV;
-
- if (dev->pm_domain)
- return -EEXIST;
+ return 0;
/*
* Only attach the power domain to the first device if the
@@ -1268,7 +1265,7 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
* management twice.
*/
if (!acpi_device_is_first_physical_node(adev, dev))
- return -EBUSY;
+ return 0;
acpi_add_pm_notifier(adev, dev, acpi_pm_notify_work_func);
dev_pm_domain_set(dev, &acpi_general_pm_domain);
@@ -1278,7 +1275,7 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
}
dev->pm_domain->detach = acpi_dev_pm_detach;
- return 0;
+ return 1;
}
EXPORT_SYMBOL_GPL(acpi_dev_pm_attach);
#endif /* CONFIG_PM */
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 30a5729..bb94cf0 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1034,6 +1034,12 @@ void acpi_ec_unblock_transactions(void)
acpi_ec_start(first_ec, true);
}
+void acpi_ec_dispatch_gpe(void)
+{
+ if (first_ec)
+ acpi_dispatch_gpe(NULL, first_ec->gpe);
+}
+
/* --------------------------------------------------------------------------
Event Management
-------------------------------------------------------------------------- */
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 1d0a501..530a3f6 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -188,6 +188,7 @@ int acpi_ec_ecdt_probe(void);
int acpi_ec_dsdt_probe(void);
void acpi_ec_block_transactions(void);
void acpi_ec_unblock_transactions(void);
+void acpi_ec_dispatch_gpe(void);
int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit,
acpi_handle handle, acpi_ec_query_func func,
void *data);
diff --git a/drivers/acpi/reboot.c b/drivers/acpi/reboot.c
index 71769fd..6fa9c2a 100644
--- a/drivers/acpi/reboot.c
+++ b/drivers/acpi/reboot.c
@@ -8,8 +8,8 @@ void acpi_reboot(void)
{
struct acpi_generic_address *rr;
struct pci_bus *bus0;
- u8 reset_value;
unsigned int devfn;
+ u8 reset_value;
if (acpi_disabled)
return;
@@ -40,7 +40,7 @@ void acpi_reboot(void)
/* Form PCI device/function pair. */
devfn = PCI_DEVFN((rr->address >> 32) & 0xffff,
(rr->address >> 16) & 0xffff);
- printk(KERN_DEBUG "Resetting with ACPI PCI RESET_REG.");
+ printk(KERN_DEBUG "Resetting with ACPI PCI RESET_REG.\n");
/* Write the value that resets us. */
pci_bus_write_config_byte(bus0, devfn,
(rr->address & 0xffff), reset_value);
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index cc234e6..970dd87 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -2166,10 +2166,10 @@ int __init acpi_scan_init(void)
acpi_cmos_rtc_init();
acpi_container_init();
acpi_memory_hotplug_init();
+ acpi_watchdog_init();
acpi_pnp_init();
acpi_int340x_thermal_init();
acpi_amba_init();
- acpi_watchdog_init();
acpi_init_lpit();
acpi_scan_add_handler(&generic_device_handler);
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 99a1a65..5d0486f 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -364,6 +364,19 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = {
DMI_MATCH(DMI_PRODUCT_NAME, "XPS 13 9360"),
},
},
+ /*
+ * ThinkPad X1 Tablet(2016) cannot do suspend-to-idle using
+ * the Low Power S0 Idle firmware interface (see
+ * https://bugzilla.kernel.org/show_bug.cgi?id=199057).
+ */
+ {
+ .callback = init_no_lps0,
+ .ident = "ThinkPad X1 Tablet(2016)",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "20GGA00L00"),
+ },
+ },
{},
};
@@ -976,6 +989,13 @@ static void acpi_s2idle_wake(void)
!irqd_is_wakeup_armed(irq_get_irq_data(acpi_sci_irq))) {
pm_system_cancel_wakeup();
s2idle_wakeup = true;
+ /*
+ * On some platforms with the LPS0 _DSM device noirq resume
+ * takes too much time for EC wakeup events to survive, so look
+ * for them now.
+ */
+ if (lps0_device_handle)
+ acpi_ec_dispatch_gpe();
}
}
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index 849c4fb..4a3410a 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -222,7 +222,7 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header)
* acpi_parse_entries_array - for each proc_num find a suitable subtable
*
* @id: table id (for debugging purposes)
- * @table_size: single entry size
+ * @table_size: size of the root table
* @table_header: where does the table start?
* @proc: array of acpi_subtable_proc struct containing entry id
* and associated handler with it
@@ -233,6 +233,11 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header)
* on it. Assumption is that there's only single handler for particular
* entry id.
*
+ * The table_size is not the size of the complete ACPI table (the length
+ * field in the header struct), but only the size of the root table; i.e.,
+ * the offset from the very first byte of the complete ACPI table, to the
+ * first byte of the very first subtable.
+ *
* On success returns sum of all matching entries for all proc handlers.
* Otherwise, -ENODEV or -EINVAL is returned.
*/
@@ -400,7 +405,7 @@ int __init acpi_table_parse(char *id, acpi_tbl_table_handler handler)
return -ENODEV;
}
-/*
+/*
* The BIOS is supposed to supply a single APIC/MADT,
* but some report two. Provide a knob to use either.
* (don't you wish instance 0 and 1 were not the same?)
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index 594c228..0cf51d5 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -20,6 +20,7 @@
#include <linux/sizes.h>
#include <linux/limits.h>
#include <linux/clk/clk-conf.h>
+#include <linux/platform_device.h>
#include <asm/irq.h>
@@ -69,11 +70,12 @@ static ssize_t driver_override_show(struct device *_dev,
struct device_attribute *attr, char *buf)
{
struct amba_device *dev = to_amba_device(_dev);
+ ssize_t len;
- if (!dev->driver_override)
- return 0;
-
- return sprintf(buf, "%s\n", dev->driver_override);
+ device_lock(_dev);
+ len = sprintf(buf, "%s\n", dev->driver_override);
+ device_unlock(_dev);
+ return len;
}
static ssize_t driver_override_store(struct device *_dev,
@@ -81,9 +83,10 @@ static ssize_t driver_override_store(struct device *_dev,
const char *buf, size_t count)
{
struct amba_device *dev = to_amba_device(_dev);
- char *driver_override, *old = dev->driver_override, *cp;
+ char *driver_override, *old, *cp;
- if (count > PATH_MAX)
+ /* We need to keep extra room for a newline */
+ if (count >= (PAGE_SIZE - 1))
return -EINVAL;
driver_override = kstrndup(buf, count, GFP_KERNEL);
@@ -94,12 +97,15 @@ static ssize_t driver_override_store(struct device *_dev,
if (cp)
*cp = '\0';
+ device_lock(_dev);
+ old = dev->driver_override;
if (strlen(driver_override)) {
dev->driver_override = driver_override;
} else {
kfree(driver_override);
dev->driver_override = NULL;
}
+ device_unlock(_dev);
kfree(old);
@@ -188,14 +194,16 @@ static const struct dev_pm_ops amba_pm = {
/*
* Primecells are part of the Advanced Microcontroller Bus Architecture,
* so we call the bus "amba".
+ * DMA configuration for platform and AMBA bus is same. So here we reuse
+ * platform's DMA config routine.
*/
struct bus_type amba_bustype = {
.name = "amba",
.dev_groups = amba_dev_groups,
.match = amba_match,
.uevent = amba_uevent,
+ .dma_configure = platform_dma_configure,
.pm = &amba_pm,
- .force_dma = true,
};
static int __init amba_init(void)
@@ -243,7 +251,7 @@ static int amba_probe(struct device *dev)
break;
ret = dev_pm_domain_attach(dev, true);
- if (ret == -EPROBE_DEFER)
+ if (ret)
break;
ret = amba_get_enable_pclk(pcdev);
@@ -370,7 +378,7 @@ static int amba_device_try_add(struct amba_device *dev, struct resource *parent)
}
ret = dev_pm_domain_attach(&dev->dev, true);
- if (ret == -EPROBE_DEFER) {
+ if (ret) {
iounmap(tmp);
goto err_release;
}
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 764b63a..e578eee 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -2839,6 +2839,14 @@ static void binder_transaction(struct binder_proc *proc,
else
return_error = BR_DEAD_REPLY;
mutex_unlock(&context->context_mgr_node_lock);
+ if (target_node && target_proc == proc) {
+ binder_user_error("%d:%d got transaction to context manager from process owning it\n",
+ proc->pid, thread->pid);
+ return_error = BR_FAILED_REPLY;
+ return_error_param = -EINVAL;
+ return_error_line = __LINE__;
+ goto err_invalid_target_handle;
+ }
}
if (!target_node) {
/*
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 1ff1779..738fb229 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -334,6 +334,7 @@ static const struct pci_device_id ahci_pci_tbl[] = {
{ PCI_VDEVICE(INTEL, 0x9c07), board_ahci_mobile }, /* Lynx LP RAID */
{ PCI_VDEVICE(INTEL, 0x9c0e), board_ahci_mobile }, /* Lynx LP RAID */
{ PCI_VDEVICE(INTEL, 0x9c0f), board_ahci_mobile }, /* Lynx LP RAID */
+ { PCI_VDEVICE(INTEL, 0x9dd3), board_ahci_mobile }, /* Cannon Lake PCH-LP AHCI */
{ PCI_VDEVICE(INTEL, 0x1f22), board_ahci }, /* Avoton AHCI */
{ PCI_VDEVICE(INTEL, 0x1f23), board_ahci }, /* Avoton AHCI */
{ PCI_VDEVICE(INTEL, 0x1f24), board_ahci }, /* Avoton RAID */
@@ -698,7 +699,7 @@ static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class,
DPRINTK("ENTER\n");
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
rc = sata_link_hardreset(link, sata_ehc_deb_timing(&link->eh_context),
deadline, &online, NULL);
@@ -724,7 +725,7 @@ static int ahci_p5wdh_hardreset(struct ata_link *link, unsigned int *class,
bool online;
int rc;
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
/* clear D2H reception area to properly wait for D2H FIS */
ata_tf_init(link->device, &tf);
@@ -788,7 +789,7 @@ static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class,
DPRINTK("ENTER\n");
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
for (i = 0; i < 2; i++) {
u16 val;
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 4356ef1..824bd39 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -350,7 +350,6 @@ struct ahci_host_priv {
u32 em_msg_type; /* EM message type */
bool got_runtime_pm; /* Did we do pm_runtime_get? */
struct clk *clks[AHCI_MAX_CLKS]; /* Optional */
- struct reset_control *rsts; /* Optional */
struct regulator **target_pwrs; /* Optional */
/*
* If platform uses PHYs. There is a 1:1 relation between the port number and
@@ -366,6 +365,13 @@ struct ahci_host_priv {
* be overridden anytime before the host is activated.
*/
void (*start_engine)(struct ata_port *ap);
+ /*
+ * Optional ahci_stop_engine override, if not set this gets set to the
+ * default ahci_stop_engine during ahci_save_initial_config, this can
+ * be overridden anytime before the host is activated.
+ */
+ int (*stop_engine)(struct ata_port *ap);
+
irqreturn_t (*irq_handler)(int irq, void *dev_instance);
/* only required for per-port MSI(-X) support */
diff --git a/drivers/ata/ahci_mvebu.c b/drivers/ata/ahci_mvebu.c
index de7128d..0045dac 100644
--- a/drivers/ata/ahci_mvebu.c
+++ b/drivers/ata/ahci_mvebu.c
@@ -62,6 +62,60 @@ static void ahci_mvebu_regret_option(struct ahci_host_priv *hpriv)
writel(0x80, hpriv->mmio + AHCI_VENDOR_SPECIFIC_0_DATA);
}
+/**
+ * ahci_mvebu_stop_engine
+ *
+ * @ap: Target ata port
+ *
+ * Errata Ref#226 - SATA Disk HOT swap issue when connected through
+ * Port Multiplier in FIS-based Switching mode.
+ *
+ * To avoid the issue, according to design, the bits[11:8, 0] of
+ * register PxFBS are cleared when Port Command and Status (0x18) bit[0]
+ * changes its value from 1 to 0, i.e. falling edge of Port
+ * Command and Status bit[0] sends PULSE that resets PxFBS
+ * bits[11:8; 0].
+ *
+ * This function is used to override function of "ahci_stop_engine"
+ * from libahci.c by adding the mvebu work around(WA) to save PxFBS
+ * value before the PxCMD ST write of 0, then restore PxFBS value.
+ *
+ * Return: 0 on success; Error code otherwise.
+ */
+int ahci_mvebu_stop_engine(struct ata_port *ap)
+{
+ void __iomem *port_mmio = ahci_port_base(ap);
+ u32 tmp, port_fbs;
+
+ tmp = readl(port_mmio + PORT_CMD);
+
+ /* check if the HBA is idle */
+ if ((tmp & (PORT_CMD_START | PORT_CMD_LIST_ON)) == 0)
+ return 0;
+
+ /* save the port PxFBS register for later restore */
+ port_fbs = readl(port_mmio + PORT_FBS);
+
+ /* setting HBA to idle */
+ tmp &= ~PORT_CMD_START;
+ writel(tmp, port_mmio + PORT_CMD);
+
+ /*
+ * bit #15 PxCMD signal doesn't clear PxFBS,
+ * restore the PxFBS register right after clearing the PxCMD ST,
+ * no need to wait for the PxCMD bit #15.
+ */
+ writel(port_fbs, port_mmio + PORT_FBS);
+
+ /* wait for engine to stop. This could be as long as 500 msec */
+ tmp = ata_wait_register(ap, port_mmio + PORT_CMD,
+ PORT_CMD_LIST_ON, PORT_CMD_LIST_ON, 1, 500);
+ if (tmp & PORT_CMD_LIST_ON)
+ return -EIO;
+
+ return 0;
+}
+
#ifdef CONFIG_PM_SLEEP
static int ahci_mvebu_suspend(struct platform_device *pdev, pm_message_t state)
{
@@ -112,6 +166,8 @@ static int ahci_mvebu_probe(struct platform_device *pdev)
if (rc)
return rc;
+ hpriv->stop_engine = ahci_mvebu_stop_engine;
+
if (of_device_is_compatible(pdev->dev.of_node,
"marvell,armada-380-ahci")) {
dram = mv_mbus_dram_info();
diff --git a/drivers/ata/ahci_qoriq.c b/drivers/ata/ahci_qoriq.c
index 2685f28..cfdef4d 100644
--- a/drivers/ata/ahci_qoriq.c
+++ b/drivers/ata/ahci_qoriq.c
@@ -96,7 +96,7 @@ static int ahci_qoriq_hardreset(struct ata_link *link, unsigned int *class,
DPRINTK("ENTER\n");
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
/*
* There is a errata on ls1021a Rev1.0 and Rev2.0 which is:
diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c
index c2b5941..ad58da7 100644
--- a/drivers/ata/ahci_xgene.c
+++ b/drivers/ata/ahci_xgene.c
@@ -165,7 +165,7 @@ static int xgene_ahci_restart_engine(struct ata_port *ap)
PORT_CMD_ISSUE, 0x0, 1, 100))
return -EBUSY;
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
ahci_start_fis_rx(ap);
/*
@@ -421,7 +421,7 @@ static int xgene_ahci_hardreset(struct ata_link *link, unsigned int *class,
portrxfis_saved = readl(port_mmio + PORT_FIS_ADDR);
portrxfishi_saved = readl(port_mmio + PORT_FIS_ADDR_HI);
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
rc = xgene_ahci_do_hardreset(link, deadline, &online);
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 7adcf3c..e5d9097 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -560,6 +560,9 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv)
if (!hpriv->start_engine)
hpriv->start_engine = ahci_start_engine;
+ if (!hpriv->stop_engine)
+ hpriv->stop_engine = ahci_stop_engine;
+
if (!hpriv->irq_handler)
hpriv->irq_handler = ahci_single_level_irq_intr;
}
@@ -897,9 +900,10 @@ static void ahci_start_port(struct ata_port *ap)
static int ahci_deinit_port(struct ata_port *ap, const char **emsg)
{
int rc;
+ struct ahci_host_priv *hpriv = ap->host->private_data;
/* disable DMA */
- rc = ahci_stop_engine(ap);
+ rc = hpriv->stop_engine(ap);
if (rc) {
*emsg = "failed to stop engine";
return rc;
@@ -1310,7 +1314,7 @@ int ahci_kick_engine(struct ata_port *ap)
int busy, rc;
/* stop engine */
- rc = ahci_stop_engine(ap);
+ rc = hpriv->stop_engine(ap);
if (rc)
goto out_restart;
@@ -1549,7 +1553,7 @@ int ahci_do_hardreset(struct ata_link *link, unsigned int *class,
DPRINTK("ENTER\n");
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
/* clear D2H reception area to properly wait for D2H FIS */
ata_tf_init(link->device, &tf);
@@ -2075,14 +2079,14 @@ void ahci_error_handler(struct ata_port *ap)
if (!(ap->pflags & ATA_PFLAG_FROZEN)) {
/* restart engine */
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
hpriv->start_engine(ap);
}
sata_pmp_error_handler(ap);
if (!ata_dev_enabled(ap->link.device))
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
}
EXPORT_SYMBOL_GPL(ahci_error_handler);
@@ -2129,7 +2133,7 @@ static void ahci_set_aggressive_devslp(struct ata_port *ap, bool sleep)
return;
/* set DITO, MDAT, DETO and enable DevSlp, need to stop engine first */
- rc = ahci_stop_engine(ap);
+ rc = hpriv->stop_engine(ap);
if (rc)
return;
@@ -2189,7 +2193,7 @@ static void ahci_enable_fbs(struct ata_port *ap)
return;
}
- rc = ahci_stop_engine(ap);
+ rc = hpriv->stop_engine(ap);
if (rc)
return;
@@ -2222,7 +2226,7 @@ static void ahci_disable_fbs(struct ata_port *ap)
return;
}
- rc = ahci_stop_engine(ap);
+ rc = hpriv->stop_engine(ap);
if (rc)
return;
diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c
index 46a7624..30cc8f1 100644
--- a/drivers/ata/libahci_platform.c
+++ b/drivers/ata/libahci_platform.c
@@ -25,7 +25,6 @@
#include <linux/phy/phy.h>
#include <linux/pm_runtime.h>
#include <linux/of_platform.h>
-#include <linux/reset.h>
#include "ahci.h"
static void ahci_host_stop(struct ata_host *host);
@@ -196,8 +195,7 @@ EXPORT_SYMBOL_GPL(ahci_platform_disable_regulators);
* following order:
* 1) Regulator
* 2) Clocks (through ahci_platform_enable_clks)
- * 3) Resets
- * 4) Phys
+ * 3) Phys
*
* If resource enabling fails at any point the previous enabled resources
* are disabled in reverse order.
@@ -217,19 +215,12 @@ int ahci_platform_enable_resources(struct ahci_host_priv *hpriv)
if (rc)
goto disable_regulator;
- rc = reset_control_deassert(hpriv->rsts);
+ rc = ahci_platform_enable_phys(hpriv);
if (rc)
goto disable_clks;
- rc = ahci_platform_enable_phys(hpriv);
- if (rc)
- goto disable_resets;
-
return 0;
-disable_resets:
- reset_control_assert(hpriv->rsts);
-
disable_clks:
ahci_platform_disable_clks(hpriv);
@@ -248,15 +239,12 @@ EXPORT_SYMBOL_GPL(ahci_platform_enable_resources);
* following order:
* 1) Phys
* 2) Clocks (through ahci_platform_disable_clks)
- * 3) Resets
- * 4) Regulator
+ * 3) Regulator
*/
void ahci_platform_disable_resources(struct ahci_host_priv *hpriv)
{
ahci_platform_disable_phys(hpriv);
- reset_control_assert(hpriv->rsts);
-
ahci_platform_disable_clks(hpriv);
ahci_platform_disable_regulators(hpriv);
@@ -405,12 +393,6 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev)
hpriv->clks[i] = clk;
}
- hpriv->rsts = devm_reset_control_array_get_optional_shared(dev);
- if (IS_ERR(hpriv->rsts)) {
- rc = PTR_ERR(hpriv->rsts);
- goto err_out;
- }
-
hpriv->nports = child_nodes = of_get_child_count(dev->of_node);
/*
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 8bc71ca..346b163 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4493,6 +4493,10 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
/* https://bugzilla.kernel.org/show_bug.cgi?id=15573 */
{ "C300-CTFDDAC128MAG", "0001", ATA_HORKAGE_NONCQ, },
+ /* Some Sandisk SSDs lock up hard with NCQ enabled. Reported on
+ SD7SN6S256G and SD8SN8U256G */
+ { "SanDisk SD[78]SN*G", NULL, ATA_HORKAGE_NONCQ, },
+
/* devices which puke on READ_NATIVE_MAX */
{ "HDS724040KLSA80", "KFAOA20N", ATA_HORKAGE_BROKEN_HPA, },
{ "WDC WD3200JD-00KLB0", "WD-WCAMR1130137", ATA_HORKAGE_BROKEN_HPA },
@@ -4549,7 +4553,16 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
ATA_HORKAGE_ZERO_AFTER_TRIM |
ATA_HORKAGE_NOLPM, },
+ /* These specific Samsung models/firmware-revs do not handle LPM well */
+ { "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM, },
+ { "SAMSUNG SSD PM830 mSATA *", "CXM13D1Q", ATA_HORKAGE_NOLPM, },
+
+ /* Sandisk devices which are known to not handle LPM well */
+ { "SanDisk SD7UB3Q*G1001", NULL, ATA_HORKAGE_NOLPM, },
+
/* devices that don't properly handle queued TRIM commands */
+ { "Micron_M500IT_*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM |
+ ATA_HORKAGE_ZERO_AFTER_TRIM, },
{ "Micron_M500_*", NULL, ATA_HORKAGE_NO_NCQ_TRIM |
ATA_HORKAGE_ZERO_AFTER_TRIM, },
{ "Crucial_CT*M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM |
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index c016829..a2398e2 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -175,8 +175,8 @@ static void ata_eh_handle_port_resume(struct ata_port *ap)
{ }
#endif /* CONFIG_PM */
-static void __ata_ehi_pushv_desc(struct ata_eh_info *ehi, const char *fmt,
- va_list args)
+static __printf(2, 0) void __ata_ehi_pushv_desc(struct ata_eh_info *ehi,
+ const char *fmt, va_list args)
{
ehi->desc_len += vscnprintf(ehi->desc + ehi->desc_len,
ATA_EH_DESC_LEN - ehi->desc_len,
@@ -500,57 +500,6 @@ void ata_eh_release(struct ata_port *ap)
mutex_unlock(&ap->host->eh_mutex);
}
-/**
- * ata_scsi_timed_out - SCSI layer time out callback
- * @cmd: timed out SCSI command
- *
- * Handles SCSI layer timeout. We race with normal completion of
- * the qc for @cmd. If the qc is already gone, we lose and let
- * the scsi command finish (EH_HANDLED). Otherwise, the qc has
- * timed out and EH should be invoked. Prevent ata_qc_complete()
- * from finishing it by setting EH_SCHEDULED and return
- * EH_NOT_HANDLED.
- *
- * TODO: kill this function once old EH is gone.
- *
- * LOCKING:
- * Called from timer context
- *
- * RETURNS:
- * EH_HANDLED or EH_NOT_HANDLED
- */
-enum blk_eh_timer_return ata_scsi_timed_out(struct scsi_cmnd *cmd)
-{
- struct Scsi_Host *host = cmd->device->host;
- struct ata_port *ap = ata_shost_to_port(host);
- unsigned long flags;
- struct ata_queued_cmd *qc;
- enum blk_eh_timer_return ret;
-
- DPRINTK("ENTER\n");
-
- if (ap->ops->error_handler) {
- ret = BLK_EH_NOT_HANDLED;
- goto out;
- }
-
- ret = BLK_EH_HANDLED;
- spin_lock_irqsave(ap->lock, flags);
- qc = ata_qc_from_tag(ap, ap->link.active_tag);
- if (qc) {
- WARN_ON(qc->scsicmd != cmd);
- qc->flags |= ATA_QCFLAG_EH_SCHEDULED;
- qc->err_mask |= AC_ERR_TIMEOUT;
- ret = BLK_EH_NOT_HANDLED;
- }
- spin_unlock_irqrestore(ap->lock, flags);
-
- out:
- DPRINTK("EXIT, ret=%d\n", ret);
- return ret;
-}
-EXPORT_SYMBOL(ata_scsi_timed_out);
-
static void ata_eh_unload(struct ata_port *ap)
{
struct ata_link *link;
diff --git a/drivers/ata/sata_highbank.c b/drivers/ata/sata_highbank.c
index aafb8cc..e67815b 100644
--- a/drivers/ata/sata_highbank.c
+++ b/drivers/ata/sata_highbank.c
@@ -410,7 +410,7 @@ static int ahci_highbank_hardreset(struct ata_link *link, unsigned int *class,
int rc;
int retry = 100;
- ahci_stop_engine(ap);
+ hpriv->stop_engine(ap);
/* clear D2H reception area to properly wait for D2H FIS */
ata_tf_init(link->device, &tf);
diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c
index 4b1995e..010ca10 100644
--- a/drivers/ata/sata_sil24.c
+++ b/drivers/ata/sata_sil24.c
@@ -285,13 +285,13 @@ static const struct sil24_cerr_info {
[PORT_CERR_INCONSISTENT] = { AC_ERR_HSM, ATA_EH_RESET,
"protocol mismatch" },
[PORT_CERR_DIRECTION] = { AC_ERR_HSM, ATA_EH_RESET,
- "data directon mismatch" },
+ "data direction mismatch" },
[PORT_CERR_UNDERRUN] = { AC_ERR_HSM, ATA_EH_RESET,
"ran out of SGEs while writing" },
[PORT_CERR_OVERRUN] = { AC_ERR_HSM, ATA_EH_RESET,
"ran out of SGEs while reading" },
[PORT_CERR_PKT_PROT] = { AC_ERR_HSM, ATA_EH_RESET,
- "invalid data directon for ATAPI CDB" },
+ "invalid data direction for ATAPI CDB" },
[PORT_CERR_SGT_BOUNDARY] = { AC_ERR_SYSTEM, ATA_EH_RESET,
"SGT not on qword boundary" },
[PORT_CERR_SGT_TGTABRT] = { AC_ERR_HOST_BUS, ATA_EH_RESET,
diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c
index d97c056..4e46dc9 100644
--- a/drivers/atm/firestream.c
+++ b/drivers/atm/firestream.c
@@ -191,7 +191,7 @@ static char *res_strings[] = {
"reserved 37",
"reserved 38",
"reserved 39",
- "reseverd 40",
+ "reserved 40",
"reserved 41",
"reserved 42",
"reserved 43",
diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index 44abb8a..be07660 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -671,7 +671,7 @@ static void ia_tx_poll (IADEV *iadev) {
if ((vcc->pop) && (skb1->len != 0))
{
vcc->pop(vcc, skb1);
- IF_EVENT(printk("Tansmit Done - skb 0x%lx return\n",
+ IF_EVENT(printk("Transmit Done - skb 0x%lx return\n",
(long)skb1);)
}
else
@@ -1665,7 +1665,7 @@ static void tx_intr(struct atm_dev *dev)
status = readl(iadev->seg_reg+SEG_INTR_STATUS_REG);
if (status & TRANSMIT_DONE){
- IF_EVENT(printk("Tansmit Done Intr logic run\n");)
+ IF_EVENT(printk("Transmit Done Intr logic run\n");)
spin_lock_irqsave(&iadev->tx_lock, flags);
ia_tx_poll(iadev);
spin_unlock_irqrestore(&iadev->tx_lock, flags);
diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c
index 1ef67db..a8d2eb0 100644
--- a/drivers/atm/zatm.c
+++ b/drivers/atm/zatm.c
@@ -28,6 +28,7 @@
#include <asm/io.h>
#include <linux/atomic.h>
#include <linux/uaccess.h>
+#include <linux/nospec.h>
#include "uPD98401.h"
#include "uPD98402.h"
@@ -1150,8 +1151,8 @@ static void eprom_get_byte(struct zatm_dev *zatm_dev, unsigned char *byte,
}
-static unsigned char eprom_try_esi(struct atm_dev *dev, unsigned short cmd,
- int offset, int swap)
+static int eprom_try_esi(struct atm_dev *dev, unsigned short cmd, int offset,
+ int swap)
{
unsigned char buf[ZEPROM_SIZE];
struct zatm_dev *zatm_dev;
@@ -1458,6 +1459,8 @@ static int zatm_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg)
return -EFAULT;
if (pool < 0 || pool > ZATM_LAST_POOL)
return -EINVAL;
+ pool = array_index_nospec(pool,
+ ZATM_LAST_POOL + 1);
spin_lock_irqsave(&zatm_dev->lock, flags);
info = zatm_dev->pool_info[pool];
if (cmd == ZATM_GETPOOLZ) {
diff --git a/drivers/base/base.h b/drivers/base/base.h
index d800de6..a75c302 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -161,3 +161,6 @@ extern void device_links_driver_cleanup(struct device *dev);
extern void device_links_no_driver(struct device *dev);
extern bool device_links_busy(struct device *dev);
extern void device_links_unbind_consumers(struct device *dev);
+
+/* device pm support */
+void device_pm_move_to_tail(struct device *dev);
diff --git a/drivers/base/core.c b/drivers/base/core.c
index b610816..ad7b508 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -145,6 +145,26 @@ static int device_reorder_to_tail(struct device *dev, void *not_used)
}
/**
+ * device_pm_move_to_tail - Move set of devices to the end of device lists
+ * @dev: Device to move
+ *
+ * This is a device_reorder_to_tail() wrapper taking the requisite locks.
+ *
+ * It moves the @dev along with all of its children and all of its consumers
+ * to the ends of the device_kset and dpm_list, recursively.
+ */
+void device_pm_move_to_tail(struct device *dev)
+{
+ int idx;
+
+ idx = device_links_read_lock();
+ device_pm_lock();
+ device_reorder_to_tail(dev, NULL);
+ device_pm_unlock();
+ device_links_read_unlock(idx);
+}
+
+/**
* device_link_add - Create a link between two devices.
* @consumer: Consumer end of the link.
* @supplier: Supplier end of the link.
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 2da998b..30cc9c8 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -534,14 +534,22 @@ ssize_t __weak cpu_show_spectre_v2(struct device *dev,
return sprintf(buf, "Not affected\n");
}
+ssize_t __weak cpu_show_spec_store_bypass(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return sprintf(buf, "Not affected\n");
+}
+
static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
+static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL);
static struct attribute *cpu_root_vulnerabilities_attrs[] = {
&dev_attr_meltdown.attr,
&dev_attr_spectre_v1.attr,
&dev_attr_spectre_v2.attr,
+ &dev_attr_spec_store_bypass.attr,
NULL
};
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index c9f5408..a41c91b 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -122,9 +122,7 @@ static void deferred_probe_work_func(struct work_struct *work)
* the list is a good order for suspend but deferred
* probe makes that very unsafe.
*/
- device_pm_lock();
- device_pm_move_last(dev);
- device_pm_unlock();
+ device_pm_move_to_tail(dev);
dev_dbg(dev, "Retrying from deferred list\n");
if (initcall_debug && !initcalls_done)
@@ -582,7 +580,7 @@ int driver_probe_device(struct device_driver *drv, struct device *dev)
pr_debug("bus: '%s': %s: matched device %s with driver %s\n",
drv->bus->name, __func__, dev_name(dev), drv->name);
- pm_runtime_get_suppliers(dev);
+ pm_runtime_resume_suppliers(dev);
if (dev->parent)
pm_runtime_get_sync(dev->parent);
@@ -593,7 +591,6 @@ int driver_probe_device(struct device_driver *drv, struct device *dev)
if (dev->parent)
pm_runtime_put(dev->parent);
- pm_runtime_put_suppliers(dev);
return ret;
}
diff --git a/drivers/base/dma-coherent.c b/drivers/base/dma-coherent.c
index 1e6396b..597d408 100644
--- a/drivers/base/dma-coherent.c
+++ b/drivers/base/dma-coherent.c
@@ -312,8 +312,9 @@ static int __dma_mmap_from_coherent(struct dma_coherent_mem *mem,
* This checks whether the memory was allocated from the per-device
* coherent memory pool and if so, maps that memory to the provided vma.
*
- * Returns 1 if we correctly mapped the memory, or 0 if the caller should
- * proceed with mapping memory from generic pools.
+ * Returns 1 if @vaddr belongs to the device coherent pool and the caller
+ * should return @ret, or 0 if they should proceed with mapping memory from
+ * generic areas.
*/
int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
void *vaddr, size_t size, int *ret)
diff --git a/drivers/base/dma-mapping.c b/drivers/base/dma-mapping.c
index 3b11835..f831a58 100644
--- a/drivers/base/dma-mapping.c
+++ b/drivers/base/dma-mapping.c
@@ -226,7 +226,6 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
#ifndef CONFIG_ARCH_NO_COHERENT_DMA_MMAP
unsigned long user_count = vma_pages(vma);
unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
- unsigned long pfn = page_to_pfn(virt_to_page(cpu_addr));
unsigned long off = vma->vm_pgoff;
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
@@ -234,12 +233,11 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
return ret;
- if (off < count && user_count <= (count - off)) {
+ if (off < count && user_count <= (count - off))
ret = remap_pfn_range(vma, vma->vm_start,
- pfn + off,
+ page_to_pfn(virt_to_page(cpu_addr)) + off,
user_count << PAGE_SHIFT,
vma->vm_page_prot);
- }
#endif /* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */
return ret;
@@ -331,36 +329,13 @@ void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags)
#endif
/*
- * Common configuration to enable DMA API use for a device
+ * enables DMA API use for a device
*/
-#include <linux/pci.h>
-
int dma_configure(struct device *dev)
{
- struct device *bridge = NULL, *dma_dev = dev;
- enum dev_dma_attr attr;
- int ret = 0;
-
- if (dev_is_pci(dev)) {
- bridge = pci_get_host_bridge_device(to_pci_dev(dev));
- dma_dev = bridge;
- if (IS_ENABLED(CONFIG_OF) && dma_dev->parent &&
- dma_dev->parent->of_node)
- dma_dev = dma_dev->parent;
- }
-
- if (dma_dev->of_node) {
- ret = of_dma_configure(dev, dma_dev->of_node);
- } else if (has_acpi_companion(dma_dev)) {
- attr = acpi_get_dma_attr(to_acpi_device_node(dma_dev->fwnode));
- if (attr != DEV_DMA_NOT_SUPPORTED)
- ret = acpi_dma_configure(dev, attr);
- }
-
- if (bridge)
- pci_put_host_bridge_device(bridge);
-
- return ret;
+ if (dev->bus->dma_configure)
+ return dev->bus->dma_configure(dev);
+ return 0;
}
void dma_deconfigure(struct device *dev)
diff --git a/drivers/base/firmware_loader/fallback.c b/drivers/base/firmware_loader/fallback.c
index 31b5015..3583541 100644
--- a/drivers/base/firmware_loader/fallback.c
+++ b/drivers/base/firmware_loader/fallback.c
@@ -537,8 +537,8 @@ fw_create_instance(struct firmware *firmware, const char *fw_name,
}
/**
- * fw_load_sysfs_fallback - load a firmware via the syfs fallback mechanism
- * @fw_sysfs: firmware syfs information for the firmware to load
+ * fw_load_sysfs_fallback - load a firmware via the sysfs fallback mechanism
+ * @fw_sysfs: firmware sysfs information for the firmware to load
* @opt_flags: flags of options, FW_OPT_*
* @timeout: timeout to wait for the load
*
diff --git a/drivers/base/firmware_loader/fallback.h b/drivers/base/firmware_loader/fallback.h
index dfebc64..f825567 100644
--- a/drivers/base/firmware_loader/fallback.h
+++ b/drivers/base/firmware_loader/fallback.h
@@ -6,7 +6,7 @@
#include <linux/device.h>
/**
- * struct firmware_fallback_config - firmware fallback configuratioon settings
+ * struct firmware_fallback_config - firmware fallback configuration settings
*
* Helps describe and fine tune the fallback mechanism.
*
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 7a3a580..a5e821d 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -490,7 +490,8 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
return 0;
}
-int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages)
+int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages,
+ bool check_nid)
{
unsigned long end_pfn = start_pfn + nr_pages;
unsigned long pfn;
@@ -514,7 +515,7 @@ int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages)
mem_blk = find_memory_block_hinted(mem_sect, mem_blk);
- ret = register_mem_sect_under_node(mem_blk, nid, true);
+ ret = register_mem_sect_under_node(mem_blk, nid, check_nid);
if (!err)
err = ret;
diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c
index 8e22073..60d6cc6 100644
--- a/drivers/base/platform-msi.c
+++ b/drivers/base/platform-msi.c
@@ -101,6 +101,9 @@ static void platform_msi_update_chip_ops(struct msi_domain_info *info)
chip->irq_set_affinity = msi_domain_set_affinity;
if (!chip->irq_write_msi_msg)
chip->irq_write_msi_msg = platform_msi_write_msg;
+ if (WARN_ON((info->flags & MSI_FLAG_LEVEL_CAPABLE) &&
+ !(chip->flags & IRQCHIP_SUPPORTS_LEVEL_MSI)))
+ info->flags &= ~MSI_FLAG_LEVEL_CAPABLE;
}
static void platform_msi_free_descs(struct device *dev, int base, int nvec)
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 8075ddc..dff82a3 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -572,17 +572,16 @@ static int platform_drv_probe(struct device *_dev)
return ret;
ret = dev_pm_domain_attach(_dev, true);
- if (ret != -EPROBE_DEFER) {
- if (drv->probe) {
- ret = drv->probe(dev);
- if (ret)
- dev_pm_domain_detach(_dev, true);
- } else {
- /* don't fail if just dev_pm_domain_attach failed */
- ret = 0;
- }
+ if (ret)
+ goto out;
+
+ if (drv->probe) {
+ ret = drv->probe(dev);
+ if (ret)
+ dev_pm_domain_detach(_dev, true);
}
+out:
if (drv->prevent_deferred_probe && ret == -EPROBE_DEFER) {
dev_warn(_dev, "probe deferral not supported\n");
ret = -ENXIO;
@@ -1130,6 +1129,22 @@ int platform_pm_restore(struct device *dev)
#endif /* CONFIG_HIBERNATE_CALLBACKS */
+int platform_dma_configure(struct device *dev)
+{
+ enum dev_dma_attr attr;
+ int ret = 0;
+
+ if (dev->of_node) {
+ ret = of_dma_configure(dev, dev->of_node, true);
+ } else if (has_acpi_companion(dev)) {
+ attr = acpi_get_dma_attr(to_acpi_device_node(dev->fwnode));
+ if (attr != DEV_DMA_NOT_SUPPORTED)
+ ret = acpi_dma_configure(dev, attr);
+ }
+
+ return ret;
+}
+
static const struct dev_pm_ops platform_dev_pm_ops = {
.runtime_suspend = pm_generic_runtime_suspend,
.runtime_resume = pm_generic_runtime_resume,
@@ -1141,8 +1156,8 @@ struct bus_type platform_bus_type = {
.dev_groups = platform_dev_groups,
.match = platform_match,
.uevent = platform_uevent,
+ .dma_configure = platform_dma_configure,
.pm = &platform_dev_pm_ops,
- .force_dma = true,
};
EXPORT_SYMBOL_GPL(platform_bus_type);
diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
index f6a9ad5..7ae62b6 100644
--- a/drivers/base/power/common.c
+++ b/drivers/base/power/common.c
@@ -98,17 +98,21 @@ EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data);
* Callers must ensure proper synchronization of this function with power
* management callbacks.
*
- * Returns 0 on successfully attached PM domain or negative error code.
+ * Returns 0 on successfully attached PM domain, or when it is found that the
+ * device doesn't need a PM domain, else a negative error code.
*/
int dev_pm_domain_attach(struct device *dev, bool power_on)
{
int ret;
+ if (dev->pm_domain)
+ return 0;
+
ret = acpi_dev_pm_attach(dev, power_on);
- if (ret)
+ if (!ret)
ret = genpd_dev_pm_attach(dev);
- return ret;
+ return ret < 0 ? ret : 0;
}
EXPORT_SYMBOL_GPL(dev_pm_domain_attach);
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 1ea0e25..6f403d6 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -10,6 +10,7 @@
#include <linux/kernel.h>
#include <linux/io.h>
#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
#include <linux/pm_runtime.h>
#include <linux/pm_domain.h>
#include <linux/pm_qos.h>
@@ -1315,7 +1316,6 @@ EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweron);
#endif /* CONFIG_PM_SLEEP */
static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev,
- struct generic_pm_domain *genpd,
struct gpd_timing_data *td)
{
struct generic_pm_domain_data *gpd_data;
@@ -1377,24 +1377,19 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
struct gpd_timing_data *td)
{
struct generic_pm_domain_data *gpd_data;
- int ret = 0;
+ int ret;
dev_dbg(dev, "%s()\n", __func__);
if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev))
return -EINVAL;
- gpd_data = genpd_alloc_dev_data(dev, genpd, td);
+ gpd_data = genpd_alloc_dev_data(dev, td);
if (IS_ERR(gpd_data))
return PTR_ERR(gpd_data);
genpd_lock(genpd);
- if (genpd->prepared_count > 0) {
- ret = -EAGAIN;
- goto out;
- }
-
ret = genpd->attach_dev ? genpd->attach_dev(genpd, dev) : 0;
if (ret)
goto out;
@@ -1418,23 +1413,21 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
}
/**
- * __pm_genpd_add_device - Add a device to an I/O PM domain.
+ * pm_genpd_add_device - Add a device to an I/O PM domain.
* @genpd: PM domain to add the device to.
* @dev: Device to be added.
- * @td: Set of PM QoS timing parameters to attach to the device.
*/
-int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
- struct gpd_timing_data *td)
+int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev)
{
int ret;
mutex_lock(&gpd_list_lock);
- ret = genpd_add_device(genpd, dev, td);
+ ret = genpd_add_device(genpd, dev, NULL);
mutex_unlock(&gpd_list_lock);
return ret;
}
-EXPORT_SYMBOL_GPL(__pm_genpd_add_device);
+EXPORT_SYMBOL_GPL(pm_genpd_add_device);
static int genpd_remove_device(struct generic_pm_domain *genpd,
struct device *dev)
@@ -1481,13 +1474,13 @@ static int genpd_remove_device(struct generic_pm_domain *genpd,
/**
* pm_genpd_remove_device - Remove a device from an I/O PM domain.
- * @genpd: PM domain to remove the device from.
* @dev: Device to be removed.
*/
-int pm_genpd_remove_device(struct generic_pm_domain *genpd,
- struct device *dev)
+int pm_genpd_remove_device(struct device *dev)
{
- if (!genpd || genpd != genpd_lookup_dev(dev))
+ struct generic_pm_domain *genpd = genpd_lookup_dev(dev);
+
+ if (!genpd)
return -EINVAL;
return genpd_remove_device(genpd, dev);
@@ -1696,6 +1689,9 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
return ret;
}
+ device_initialize(&genpd->dev);
+ dev_set_name(&genpd->dev, "%s", genpd->name);
+
mutex_lock(&gpd_list_lock);
list_add(&genpd->gpd_list_node, &gpd_list);
mutex_unlock(&gpd_list_lock);
@@ -1892,14 +1888,33 @@ int of_genpd_add_provider_simple(struct device_node *np,
mutex_lock(&gpd_list_lock);
- if (genpd_present(genpd)) {
- ret = genpd_add_provider(np, genpd_xlate_simple, genpd);
- if (!ret) {
- genpd->provider = &np->fwnode;
- genpd->has_provider = true;
+ if (!genpd_present(genpd))
+ goto unlock;
+
+ genpd->dev.of_node = np;
+
+ /* Parse genpd OPP table */
+ if (genpd->set_performance_state) {
+ ret = dev_pm_opp_of_add_table(&genpd->dev);
+ if (ret) {
+ dev_err(&genpd->dev, "Failed to add OPP table: %d\n",
+ ret);
+ goto unlock;
}
}
+ ret = genpd_add_provider(np, genpd_xlate_simple, genpd);
+ if (ret) {
+ if (genpd->set_performance_state)
+ dev_pm_opp_of_remove_table(&genpd->dev);
+
+ goto unlock;
+ }
+
+ genpd->provider = &np->fwnode;
+ genpd->has_provider = true;
+
+unlock:
mutex_unlock(&gpd_list_lock);
return ret;
@@ -1914,6 +1929,7 @@ EXPORT_SYMBOL_GPL(of_genpd_add_provider_simple);
int of_genpd_add_provider_onecell(struct device_node *np,
struct genpd_onecell_data *data)
{
+ struct generic_pm_domain *genpd;
unsigned int i;
int ret = -EINVAL;
@@ -1926,13 +1942,27 @@ int of_genpd_add_provider_onecell(struct device_node *np,
data->xlate = genpd_xlate_onecell;
for (i = 0; i < data->num_domains; i++) {
- if (!data->domains[i])
+ genpd = data->domains[i];
+
+ if (!genpd)
continue;
- if (!genpd_present(data->domains[i]))
+ if (!genpd_present(genpd))
goto error;
- data->domains[i]->provider = &np->fwnode;
- data->domains[i]->has_provider = true;
+ genpd->dev.of_node = np;
+
+ /* Parse genpd OPP table */
+ if (genpd->set_performance_state) {
+ ret = dev_pm_opp_of_add_table_indexed(&genpd->dev, i);
+ if (ret) {
+ dev_err(&genpd->dev, "Failed to add OPP table for index %d: %d\n",
+ i, ret);
+ goto error;
+ }
+ }
+
+ genpd->provider = &np->fwnode;
+ genpd->has_provider = true;
}
ret = genpd_add_provider(np, data->xlate, data);
@@ -1945,10 +1975,16 @@ int of_genpd_add_provider_onecell(struct device_node *np,
error:
while (i--) {
- if (!data->domains[i])
+ genpd = data->domains[i];
+
+ if (!genpd)
continue;
- data->domains[i]->provider = NULL;
- data->domains[i]->has_provider = false;
+
+ genpd->provider = NULL;
+ genpd->has_provider = false;
+
+ if (genpd->set_performance_state)
+ dev_pm_opp_of_remove_table(&genpd->dev);
}
mutex_unlock(&gpd_list_lock);
@@ -1975,10 +2011,17 @@ void of_genpd_del_provider(struct device_node *np)
* provider, set the 'has_provider' to false
* so that the PM domain can be safely removed.
*/
- list_for_each_entry(gpd, &gpd_list, gpd_list_node)
- if (gpd->provider == &np->fwnode)
+ list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
+ if (gpd->provider == &np->fwnode) {
gpd->has_provider = false;
+ if (!gpd->set_performance_state)
+ continue;
+
+ dev_pm_opp_of_remove_table(&gpd->dev);
+ }
+ }
+
list_del(&cp->link);
of_node_put(cp->node);
kfree(cp);
@@ -2185,31 +2228,25 @@ static void genpd_dev_pm_sync(struct device *dev)
* Parse device's OF node to find a PM domain specifier. If such is found,
* attaches the device to retrieved pm_domain ops.
*
- * Both generic and legacy Samsung-specific DT bindings are supported to keep
- * backwards compatibility with existing DTBs.
- *
- * Returns 0 on successfully attached PM domain or negative error code. Note
- * that if a power-domain exists for the device, but it cannot be found or
- * turned on, then return -EPROBE_DEFER to ensure that the device is not
- * probed and to re-try again later.
+ * Returns 1 on successfully attached PM domain, 0 when the device don't need a
+ * PM domain or a negative error code in case of failures. Note that if a
+ * power-domain exists for the device, but it cannot be found or turned on,
+ * then return -EPROBE_DEFER to ensure that the device is not probed and to
+ * re-try again later.
*/
int genpd_dev_pm_attach(struct device *dev)
{
struct of_phandle_args pd_args;
struct generic_pm_domain *pd;
- unsigned int i;
int ret;
if (!dev->of_node)
- return -ENODEV;
-
- if (dev->pm_domain)
- return -EEXIST;
+ return 0;
ret = of_parse_phandle_with_args(dev->of_node, "power-domains",
"#power-domain-cells", 0, &pd_args);
if (ret < 0)
- return ret;
+ return 0;
mutex_lock(&gpd_list_lock);
pd = genpd_get_from_provider(&pd_args);
@@ -2223,21 +2260,14 @@ int genpd_dev_pm_attach(struct device *dev)
dev_dbg(dev, "adding to PM domain %s\n", pd->name);
- for (i = 1; i < GENPD_RETRY_MAX_MS; i <<= 1) {
- ret = genpd_add_device(pd, dev, NULL);
- if (ret != -EAGAIN)
- break;
-
- mdelay(i);
- cond_resched();
- }
+ ret = genpd_add_device(pd, dev, NULL);
mutex_unlock(&gpd_list_lock);
if (ret < 0) {
if (ret != -EPROBE_DEFER)
dev_err(dev, "failed to add to PM domain %s: %d",
pd->name, ret);
- goto out;
+ return ret;
}
dev->pm_domain->detach = genpd_dev_pm_detach;
@@ -2246,8 +2276,11 @@ int genpd_dev_pm_attach(struct device *dev)
genpd_lock(pd);
ret = genpd_power_on(pd, 0);
genpd_unlock(pd);
-out:
- return ret ? -EPROBE_DEFER : 0;
+
+ if (ret)
+ genpd_remove_device(pd, dev);
+
+ return ret ? -EPROBE_DEFER : 1;
}
EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
@@ -2361,6 +2394,55 @@ int of_genpd_parse_idle_states(struct device_node *dn,
}
EXPORT_SYMBOL_GPL(of_genpd_parse_idle_states);
+/**
+ * of_genpd_opp_to_performance_state- Gets performance state of device's
+ * power domain corresponding to a DT node's "required-opps" property.
+ *
+ * @dev: Device for which the performance-state needs to be found.
+ * @opp_node: DT node where the "required-opps" property is present. This can be
+ * the device node itself (if it doesn't have an OPP table) or a node
+ * within the OPP table of a device (if device has an OPP table).
+ * @state: Pointer to return performance state.
+ *
+ * Returns performance state corresponding to the "required-opps" property of
+ * a DT node. This calls platform specific genpd->opp_to_performance_state()
+ * callback to translate power domain OPP to performance state.
+ *
+ * Returns performance state on success and 0 on failure.
+ */
+unsigned int of_genpd_opp_to_performance_state(struct device *dev,
+ struct device_node *opp_node)
+{
+ struct generic_pm_domain *genpd;
+ struct dev_pm_opp *opp;
+ int state = 0;
+
+ genpd = dev_to_genpd(dev);
+ if (IS_ERR(genpd))
+ return 0;
+
+ if (unlikely(!genpd->set_performance_state))
+ return 0;
+
+ genpd_lock(genpd);
+
+ opp = of_dev_pm_opp_find_required_opp(&genpd->dev, opp_node);
+ if (IS_ERR(opp)) {
+ dev_err(dev, "Failed to find required OPP: %ld\n",
+ PTR_ERR(opp));
+ goto unlock;
+ }
+
+ state = genpd->opp_to_performance_state(genpd, opp);
+ dev_pm_opp_put(opp);
+
+unlock:
+ genpd_unlock(genpd);
+
+ return state;
+}
+EXPORT_SYMBOL_GPL(of_genpd_opp_to_performance_state);
+
#endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
@@ -2628,6 +2710,19 @@ static int genpd_devices_show(struct seq_file *s, void *data)
return ret;
}
+static int genpd_perf_state_show(struct seq_file *s, void *data)
+{
+ struct generic_pm_domain *genpd = s->private;
+
+ if (genpd_lock_interruptible(genpd))
+ return -ERESTARTSYS;
+
+ seq_printf(s, "%u\n", genpd->performance_state);
+
+ genpd_unlock(genpd);
+ return 0;
+}
+
#define define_genpd_open_function(name) \
static int genpd_##name##_open(struct inode *inode, struct file *file) \
{ \
@@ -2641,6 +2736,7 @@ define_genpd_open_function(idle_states);
define_genpd_open_function(active_time);
define_genpd_open_function(total_idle_time);
define_genpd_open_function(devices);
+define_genpd_open_function(perf_state);
#define define_genpd_debugfs_fops(name) \
static const struct file_operations genpd_##name##_fops = { \
@@ -2657,6 +2753,7 @@ define_genpd_debugfs_fops(idle_states);
define_genpd_debugfs_fops(active_time);
define_genpd_debugfs_fops(total_idle_time);
define_genpd_debugfs_fops(devices);
+define_genpd_debugfs_fops(perf_state);
static int __init genpd_debug_init(void)
{
@@ -2690,6 +2787,9 @@ static int __init genpd_debug_init(void)
d, genpd, &genpd_total_idle_time_fops);
debugfs_create_file("devices", 0444,
d, genpd, &genpd_devices_fops);
+ if (genpd->set_performance_state)
+ debugfs_create_file("perf_state", 0444,
+ d, genpd, &genpd_perf_state_fops);
}
return 0;
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 02a497e..3f68e29 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -192,34 +192,31 @@ void device_pm_move_last(struct device *dev)
list_move_tail(&dev->power.entry, &dpm_list);
}
-static ktime_t initcall_debug_start(struct device *dev)
+static ktime_t initcall_debug_start(struct device *dev, void *cb)
{
- ktime_t calltime = 0;
+ if (!pm_print_times_enabled)
+ return 0;
- if (pm_print_times_enabled) {
- pr_info("calling %s+ @ %i, parent: %s\n",
- dev_name(dev), task_pid_nr(current),
- dev->parent ? dev_name(dev->parent) : "none");
- calltime = ktime_get();
- }
-
- return calltime;
+ dev_info(dev, "calling %pF @ %i, parent: %s\n", cb,
+ task_pid_nr(current),
+ dev->parent ? dev_name(dev->parent) : "none");
+ return ktime_get();
}
static void initcall_debug_report(struct device *dev, ktime_t calltime,
- int error, pm_message_t state,
- const char *info)
+ void *cb, int error)
{
ktime_t rettime;
s64 nsecs;
+ if (!pm_print_times_enabled)
+ return;
+
rettime = ktime_get();
nsecs = (s64) ktime_to_ns(ktime_sub(rettime, calltime));
- if (pm_print_times_enabled) {
- pr_info("call %s+ returned %d after %Ld usecs\n", dev_name(dev),
- error, (unsigned long long)nsecs >> 10);
- }
+ dev_info(dev, "%pF returned %d after %Ld usecs\n", cb, error,
+ (unsigned long long)nsecs >> 10);
}
/**
@@ -446,7 +443,7 @@ static int dpm_run_callback(pm_callback_t cb, struct device *dev,
if (!cb)
return 0;
- calltime = initcall_debug_start(dev);
+ calltime = initcall_debug_start(dev, cb);
pm_dev_dbg(dev, state, info);
trace_device_pm_callback_start(dev, info, state.event);
@@ -454,7 +451,7 @@ static int dpm_run_callback(pm_callback_t cb, struct device *dev,
trace_device_pm_callback_end(dev, error);
suspend_report_result(cb, error);
- initcall_debug_report(dev, calltime, error, state, info);
+ initcall_debug_report(dev, calltime, cb, error);
return error;
}
@@ -1664,14 +1661,14 @@ static int legacy_suspend(struct device *dev, pm_message_t state,
int error;
ktime_t calltime;
- calltime = initcall_debug_start(dev);
+ calltime = initcall_debug_start(dev, cb);
trace_device_pm_callback_start(dev, info, state.event);
error = cb(dev, state);
trace_device_pm_callback_end(dev, error);
suspend_report_result(cb, error);
- initcall_debug_report(dev, calltime, error, state, info);
+ initcall_debug_report(dev, calltime, cb, error);
return error;
}
@@ -1923,10 +1920,8 @@ static int device_prepare(struct device *dev, pm_message_t state)
dev->power.wakeup_path = false;
- if (dev->power.no_pm_callbacks) {
- ret = 1; /* Let device go direct_complete */
+ if (dev->power.no_pm_callbacks)
goto unlock;
- }
if (dev->pm_domain)
callback = dev->pm_domain->ops.prepare;
@@ -1960,7 +1955,8 @@ static int device_prepare(struct device *dev, pm_message_t state)
*/
spin_lock_irq(&dev->power.lock);
dev->power.direct_complete = state.event == PM_EVENT_SUSPEND &&
- pm_runtime_suspended(dev) && ret > 0 &&
+ ((pm_runtime_suspended(dev) && ret > 0) ||
+ dev->power.no_pm_callbacks) &&
!dev_pm_test_driver_flags(dev, DPM_FLAG_NEVER_SKIP);
spin_unlock_irq(&dev->power.lock);
return 0;
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index 86e67e7..c511def 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -56,14 +56,6 @@ static inline void device_wakeup_detach_irq(struct device *dev)
{
}
-static inline void device_wakeup_arm_wake_irqs(void)
-{
-}
-
-static inline void device_wakeup_disarm_wake_irqs(void)
-{
-}
-
#endif /* CONFIG_PM_SLEEP */
/*
@@ -95,28 +87,6 @@ static inline void pm_runtime_remove(struct device *dev) {}
static inline int dpm_sysfs_add(struct device *dev) { return 0; }
static inline void dpm_sysfs_remove(struct device *dev) {}
-static inline void rpm_sysfs_remove(struct device *dev) {}
-static inline int wakeup_sysfs_add(struct device *dev) { return 0; }
-static inline void wakeup_sysfs_remove(struct device *dev) {}
-static inline int pm_qos_sysfs_add(struct device *dev) { return 0; }
-static inline void pm_qos_sysfs_remove(struct device *dev) {}
-
-static inline void dev_pm_arm_wake_irq(struct wake_irq *wirq)
-{
-}
-
-static inline void dev_pm_disarm_wake_irq(struct wake_irq *wirq)
-{
-}
-
-static inline void dev_pm_enable_wake_irq_check(struct device *dev,
- bool can_change_status)
-{
-}
-
-static inline void dev_pm_disable_wake_irq_check(struct device *dev)
-{
-}
#endif
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 8bef3cb..c6030f1 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1563,37 +1563,16 @@ void pm_runtime_clean_up_links(struct device *dev)
}
/**
- * pm_runtime_get_suppliers - Resume and reference-count supplier devices.
+ * pm_runtime_resume_suppliers - Resume supplier devices.
* @dev: Consumer device.
*/
-void pm_runtime_get_suppliers(struct device *dev)
+void pm_runtime_resume_suppliers(struct device *dev)
{
- struct device_link *link;
int idx;
idx = device_links_read_lock();
- list_for_each_entry_rcu(link, &dev->links.suppliers, c_node)
- if (link->flags & DL_FLAG_PM_RUNTIME)
- pm_runtime_get_sync(link->supplier);
-
- device_links_read_unlock(idx);
-}
-
-/**
- * pm_runtime_put_suppliers - Drop references to supplier devices.
- * @dev: Consumer device.
- */
-void pm_runtime_put_suppliers(struct device *dev)
-{
- struct device_link *link;
- int idx;
-
- idx = device_links_read_lock();
-
- list_for_each_entry_rcu(link, &dev->links.suppliers, c_node)
- if (link->flags & DL_FLAG_PM_RUNTIME)
- pm_runtime_put(link->supplier);
+ rpm_get_suppliers(dev);
device_links_read_unlock(idx);
}
@@ -1607,6 +1586,8 @@ void pm_runtime_new_link(struct device *dev)
void pm_runtime_drop_link(struct device *dev)
{
+ rpm_put_suppliers(dev);
+
spin_lock_irq(&dev->power.lock);
WARN_ON(dev->power.links_count == 0);
dev->power.links_count--;
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index ea01621..5fa1898 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -57,7 +57,7 @@ static void split_counters(unsigned int *cnt, unsigned int *inpr)
/* A preserved old value of the events counter. */
static unsigned int saved_count;
-static DEFINE_SPINLOCK(events_lock);
+static DEFINE_RAW_SPINLOCK(events_lock);
static void pm_wakeup_timer_fn(struct timer_list *t);
@@ -183,11 +183,10 @@ void wakeup_source_add(struct wakeup_source *ws)
spin_lock_init(&ws->lock);
timer_setup(&ws->timer, pm_wakeup_timer_fn, 0);
ws->active = false;
- ws->last_time = ktime_get();
- spin_lock_irqsave(&events_lock, flags);
+ raw_spin_lock_irqsave(&events_lock, flags);
list_add_rcu(&ws->entry, &wakeup_sources);
- spin_unlock_irqrestore(&events_lock, flags);
+ raw_spin_unlock_irqrestore(&events_lock, flags);
}
EXPORT_SYMBOL_GPL(wakeup_source_add);
@@ -202,9 +201,9 @@ void wakeup_source_remove(struct wakeup_source *ws)
if (WARN_ON(!ws))
return;
- spin_lock_irqsave(&events_lock, flags);
+ raw_spin_lock_irqsave(&events_lock, flags);
list_del_rcu(&ws->entry);
- spin_unlock_irqrestore(&events_lock, flags);
+ raw_spin_unlock_irqrestore(&events_lock, flags);
synchronize_srcu(&wakeup_srcu);
}
EXPORT_SYMBOL_GPL(wakeup_source_remove);
@@ -843,7 +842,7 @@ bool pm_wakeup_pending(void)
unsigned long flags;
bool ret = false;
- spin_lock_irqsave(&events_lock, flags);
+ raw_spin_lock_irqsave(&events_lock, flags);
if (events_check_enabled) {
unsigned int cnt, inpr;
@@ -851,10 +850,10 @@ bool pm_wakeup_pending(void)
ret = (cnt != saved_count || inpr > 0);
events_check_enabled = !ret;
}
- spin_unlock_irqrestore(&events_lock, flags);
+ raw_spin_unlock_irqrestore(&events_lock, flags);
if (ret) {
- pr_info("PM: Wakeup pending, aborting suspend\n");
+ pr_debug("PM: Wakeup pending, aborting suspend\n");
pm_print_active_wakeup_sources();
}
@@ -940,13 +939,13 @@ bool pm_save_wakeup_count(unsigned int count)
unsigned long flags;
events_check_enabled = false;
- spin_lock_irqsave(&events_lock, flags);
+ raw_spin_lock_irqsave(&events_lock, flags);
split_counters(&cnt, &inpr);
if (cnt == count && inpr == 0) {
saved_count = count;
events_check_enabled = true;
}
- spin_unlock_irqrestore(&events_lock, flags);
+ raw_spin_unlock_irqrestore(&events_lock, flags);
return events_check_enabled;
}
@@ -1029,32 +1028,75 @@ static int print_wakeup_source_stats(struct seq_file *m,
return 0;
}
-/**
- * wakeup_sources_stats_show - Print wakeup sources statistics information.
- * @m: seq_file to print the statistics into.
- */
-static int wakeup_sources_stats_show(struct seq_file *m, void *unused)
+static void *wakeup_sources_stats_seq_start(struct seq_file *m,
+ loff_t *pos)
{
struct wakeup_source *ws;
- int srcuidx;
+ loff_t n = *pos;
+ int *srcuidx = m->private;
- seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t"
- "expire_count\tactive_since\ttotal_time\tmax_time\t"
- "last_change\tprevent_suspend_time\n");
+ if (n == 0) {
+ seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t"
+ "expire_count\tactive_since\ttotal_time\tmax_time\t"
+ "last_change\tprevent_suspend_time\n");
+ }
- srcuidx = srcu_read_lock(&wakeup_srcu);
- list_for_each_entry_rcu(ws, &wakeup_sources, entry)
- print_wakeup_source_stats(m, ws);
- srcu_read_unlock(&wakeup_srcu, srcuidx);
+ *srcuidx = srcu_read_lock(&wakeup_srcu);
+ list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+ if (n-- <= 0)
+ return ws;
+ }
- print_wakeup_source_stats(m, &deleted_ws);
+ return NULL;
+}
+
+static void *wakeup_sources_stats_seq_next(struct seq_file *m,
+ void *v, loff_t *pos)
+{
+ struct wakeup_source *ws = v;
+ struct wakeup_source *next_ws = NULL;
+
+ ++(*pos);
+
+ list_for_each_entry_continue_rcu(ws, &wakeup_sources, entry) {
+ next_ws = ws;
+ break;
+ }
+
+ return next_ws;
+}
+
+static void wakeup_sources_stats_seq_stop(struct seq_file *m, void *v)
+{
+ int *srcuidx = m->private;
+
+ srcu_read_unlock(&wakeup_srcu, *srcuidx);
+}
+
+/**
+ * wakeup_sources_stats_seq_show - Print wakeup sources statistics information.
+ * @m: seq_file to print the statistics into.
+ * @v: wakeup_source of each iteration
+ */
+static int wakeup_sources_stats_seq_show(struct seq_file *m, void *v)
+{
+ struct wakeup_source *ws = v;
+
+ print_wakeup_source_stats(m, ws);
return 0;
}
+static const struct seq_operations wakeup_sources_stats_seq_ops = {
+ .start = wakeup_sources_stats_seq_start,
+ .next = wakeup_sources_stats_seq_next,
+ .stop = wakeup_sources_stats_seq_stop,
+ .show = wakeup_sources_stats_seq_show,
+};
+
static int wakeup_sources_stats_open(struct inode *inode, struct file *file)
{
- return single_open(file, wakeup_sources_stats_show, NULL);
+ return seq_open_private(file, &wakeup_sources_stats_seq_ops, sizeof(int));
}
static const struct file_operations wakeup_sources_stats_fops = {
@@ -1062,7 +1104,7 @@ static const struct file_operations wakeup_sources_stats_fops = {
.open = wakeup_sources_stats_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .release = seq_release_private,
};
static int __init wakeup_sources_debugfs_init(void)
diff --git a/drivers/base/property.c b/drivers/base/property.c
index 8f205f6..240ab52 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -56,6 +56,72 @@ pset_prop_get(const struct property_set *pset, const char *name)
return NULL;
}
+static const void *property_get_pointer(const struct property_entry *prop)
+{
+ switch (prop->type) {
+ case DEV_PROP_U8:
+ if (prop->is_array)
+ return prop->pointer.u8_data;
+ return &prop->value.u8_data;
+ case DEV_PROP_U16:
+ if (prop->is_array)
+ return prop->pointer.u16_data;
+ return &prop->value.u16_data;
+ case DEV_PROP_U32:
+ if (prop->is_array)
+ return prop->pointer.u32_data;
+ return &prop->value.u32_data;
+ case DEV_PROP_U64:
+ if (prop->is_array)
+ return prop->pointer.u64_data;
+ return &prop->value.u64_data;
+ case DEV_PROP_STRING:
+ if (prop->is_array)
+ return prop->pointer.str;
+ return &prop->value.str;
+ default:
+ return NULL;
+ }
+}
+
+static void property_set_pointer(struct property_entry *prop, const void *pointer)
+{
+ switch (prop->type) {
+ case DEV_PROP_U8:
+ if (prop->is_array)
+ prop->pointer.u8_data = pointer;
+ else
+ prop->value.u8_data = *((u8 *)pointer);
+ break;
+ case DEV_PROP_U16:
+ if (prop->is_array)
+ prop->pointer.u16_data = pointer;
+ else
+ prop->value.u16_data = *((u16 *)pointer);
+ break;
+ case DEV_PROP_U32:
+ if (prop->is_array)
+ prop->pointer.u32_data = pointer;
+ else
+ prop->value.u32_data = *((u32 *)pointer);
+ break;
+ case DEV_PROP_U64:
+ if (prop->is_array)
+ prop->pointer.u64_data = pointer;
+ else
+ prop->value.u64_data = *((u64 *)pointer);
+ break;
+ case DEV_PROP_STRING:
+ if (prop->is_array)
+ prop->pointer.str = pointer;
+ else
+ prop->value.str = pointer;
+ break;
+ default:
+ break;
+ }
+}
+
static const void *pset_prop_find(const struct property_set *pset,
const char *propname, size_t length)
{
@@ -65,10 +131,7 @@ static const void *pset_prop_find(const struct property_set *pset,
prop = pset_prop_get(pset, propname);
if (!prop)
return ERR_PTR(-EINVAL);
- if (prop->is_array)
- pointer = prop->pointer.raw_data;
- else
- pointer = &prop->value.raw_data;
+ pointer = property_get_pointer(prop);
if (!pointer)
return ERR_PTR(-ENODATA);
if (length > prop->length)
@@ -698,16 +761,17 @@ EXPORT_SYMBOL_GPL(fwnode_property_get_reference_args);
static void property_entry_free_data(const struct property_entry *p)
{
+ const void *pointer = property_get_pointer(p);
size_t i, nval;
if (p->is_array) {
- if (p->is_string && p->pointer.str) {
+ if (p->type == DEV_PROP_STRING && p->pointer.str) {
nval = p->length / sizeof(const char *);
for (i = 0; i < nval; i++)
kfree(p->pointer.str[i]);
}
- kfree(p->pointer.raw_data);
- } else if (p->is_string) {
+ kfree(pointer);
+ } else if (p->type == DEV_PROP_STRING) {
kfree(p->value.str);
}
kfree(p->name);
@@ -716,7 +780,7 @@ static void property_entry_free_data(const struct property_entry *p)
static int property_copy_string_array(struct property_entry *dst,
const struct property_entry *src)
{
- char **d;
+ const char **d;
size_t nval = src->length / sizeof(*d);
int i;
@@ -734,40 +798,44 @@ static int property_copy_string_array(struct property_entry *dst,
}
}
- dst->pointer.raw_data = d;
+ dst->pointer.str = d;
return 0;
}
static int property_entry_copy_data(struct property_entry *dst,
const struct property_entry *src)
{
+ const void *pointer = property_get_pointer(src);
+ const void *new;
int error;
if (src->is_array) {
if (!src->length)
return -ENODATA;
- if (src->is_string) {
+ if (src->type == DEV_PROP_STRING) {
error = property_copy_string_array(dst, src);
if (error)
return error;
+ new = dst->pointer.str;
} else {
- dst->pointer.raw_data = kmemdup(src->pointer.raw_data,
- src->length, GFP_KERNEL);
- if (!dst->pointer.raw_data)
+ new = kmemdup(pointer, src->length, GFP_KERNEL);
+ if (!new)
return -ENOMEM;
}
- } else if (src->is_string) {
- dst->value.str = kstrdup(src->value.str, GFP_KERNEL);
- if (!dst->value.str && src->value.str)
+ } else if (src->type == DEV_PROP_STRING) {
+ new = kstrdup(src->value.str, GFP_KERNEL);
+ if (!new && src->value.str)
return -ENOMEM;
} else {
- dst->value.raw_data = src->value.raw_data;
+ new = pointer;
}
dst->length = src->length;
dst->is_array = src->is_array;
- dst->is_string = src->is_string;
+ dst->type = src->type;
+
+ property_set_pointer(dst, new);
dst->name = kstrdup(src->name, GFP_KERNEL);
if (!dst->name)
diff --git a/drivers/base/regmap/regmap-mmio.c b/drivers/base/regmap/regmap-mmio.c
index 5cadfd3..8741fb5 100644
--- a/drivers/base/regmap/regmap-mmio.c
+++ b/drivers/base/regmap/regmap-mmio.c
@@ -206,7 +206,8 @@ static void regmap_mmio_free_context(void *context)
if (!IS_ERR(ctx->clk)) {
clk_unprepare(ctx->clk);
- clk_put(ctx->clk);
+ if (!ctx->attached_clk)
+ clk_put(ctx->clk);
}
kfree(context);
}
diff --git a/drivers/base/regmap/regmap-slimbus.c b/drivers/base/regmap/regmap-slimbus.c
index c90bee8..91d501e 100644
--- a/drivers/base/regmap/regmap-slimbus.c
+++ b/drivers/base/regmap/regmap-slimbus.c
@@ -41,7 +41,7 @@ static struct regmap_bus regmap_slimbus_bus = {
static const struct regmap_bus *regmap_get_slimbus(struct slim_device *slim,
const struct regmap_config *config)
{
- if (config->val_bits == 8 && config->reg_bits == 8)
+ if (config->val_bits == 8 && config->reg_bits == 16)
return ®map_slimbus_bus;
return ERR_PTR(-ENOTSUPP);
diff --git a/drivers/bcma/driver_mips.c b/drivers/bcma/driver_mips.c
index f040aba..27e9686 100644
--- a/drivers/bcma/driver_mips.c
+++ b/drivers/bcma/driver_mips.c
@@ -184,7 +184,7 @@ static void bcma_core_mips_print_irq(struct bcma_device *dev, unsigned int irq)
{
int i;
static const char *irq_name[] = {"2(S)", "3", "4", "5", "6", "D", "I"};
- char interrupts[20];
+ char interrupts[25];
char *ints = interrupts;
for (i = 0; i < ARRAY_SIZE(irq_name); i++)
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index e6986c7..fc1f4ac 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -207,7 +207,7 @@ static void bcma_of_fill_device(struct device *parent,
core->irq = bcma_of_get_irq(parent, core, 0);
- of_dma_configure(&core->dev, node);
+ of_dma_configure(&core->dev, node, false);
}
unsigned int bcma_core_irq(struct bcma_device *core, int num)
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index f781eff..6ca77d6 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -1179,7 +1179,6 @@ static bool DAC960_V1_EnableMemoryMailboxInterface(DAC960_Controller_T
if (pci_set_dma_mask(Controller->PCIDevice, DMA_BIT_MASK(32)))
return DAC960_Failure(Controller, "DMA mask out of range");
- Controller->BounceBufferLimit = DMA_BIT_MASK(32);
if ((hw_type == DAC960_PD_Controller) || (hw_type == DAC960_P_Controller)) {
CommandMailboxesSize = 0;
@@ -1380,11 +1379,8 @@ static bool DAC960_V2_EnableMemoryMailboxInterface(DAC960_Controller_T
dma_addr_t CommandMailboxDMA;
DAC960_V2_CommandStatus_T CommandStatus;
- if (!pci_set_dma_mask(Controller->PCIDevice, DMA_BIT_MASK(64)))
- Controller->BounceBufferLimit = DMA_BIT_MASK(64);
- else if (!pci_set_dma_mask(Controller->PCIDevice, DMA_BIT_MASK(32)))
- Controller->BounceBufferLimit = DMA_BIT_MASK(32);
- else
+ if (pci_set_dma_mask(Controller->PCIDevice, DMA_BIT_MASK(64)) &&
+ pci_set_dma_mask(Controller->PCIDevice, DMA_BIT_MASK(32)))
return DAC960_Failure(Controller, "DMA mask out of range");
/* This is a temporary dma mapping, used only in the scope of this function */
@@ -2540,7 +2536,6 @@ static bool DAC960_RegisterBlockDevice(DAC960_Controller_T *Controller)
continue;
}
Controller->RequestQueue[n] = RequestQueue;
- blk_queue_bounce_limit(RequestQueue, Controller->BounceBufferLimit);
RequestQueue->queuedata = Controller;
blk_queue_max_segments(RequestQueue, Controller->DriverScatterGatherLimit);
blk_queue_max_hw_sectors(RequestQueue, Controller->MaxBlocksPerCommand);
@@ -6451,19 +6446,6 @@ static int dac960_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int dac960_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, dac960_proc_show, NULL);
-}
-
-static const struct file_operations dac960_proc_fops = {
- .owner = THIS_MODULE,
- .open = dac960_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int dac960_initial_status_proc_show(struct seq_file *m, void *v)
{
DAC960_Controller_T *Controller = (DAC960_Controller_T *)m->private;
@@ -6471,19 +6453,6 @@ static int dac960_initial_status_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int dac960_initial_status_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, dac960_initial_status_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations dac960_initial_status_proc_fops = {
- .owner = THIS_MODULE,
- .open = dac960_initial_status_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int dac960_current_status_proc_show(struct seq_file *m, void *v)
{
DAC960_Controller_T *Controller = (DAC960_Controller_T *) m->private;
@@ -6517,19 +6486,6 @@ static int dac960_current_status_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int dac960_current_status_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, dac960_current_status_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations dac960_current_status_proc_fops = {
- .owner = THIS_MODULE,
- .open = dac960_current_status_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int dac960_user_command_proc_show(struct seq_file *m, void *v)
{
DAC960_Controller_T *Controller = (DAC960_Controller_T *)m->private;
@@ -6584,17 +6540,19 @@ static void DAC960_CreateProcEntries(DAC960_Controller_T *Controller)
if (DAC960_ProcDirectoryEntry == NULL) {
DAC960_ProcDirectoryEntry = proc_mkdir("rd", NULL);
- proc_create("status", 0, DAC960_ProcDirectoryEntry,
- &dac960_proc_fops);
+ proc_create_single("status", 0, DAC960_ProcDirectoryEntry,
+ dac960_proc_show);
}
snprintf(Controller->ControllerName, sizeof(Controller->ControllerName),
"c%d", Controller->ControllerNumber);
ControllerProcEntry = proc_mkdir(Controller->ControllerName,
DAC960_ProcDirectoryEntry);
- proc_create_data("initial_status", 0, ControllerProcEntry, &dac960_initial_status_proc_fops, Controller);
- proc_create_data("current_status", 0, ControllerProcEntry, &dac960_current_status_proc_fops, Controller);
- proc_create_data("user_command", S_IWUSR | S_IRUSR, ControllerProcEntry, &dac960_user_command_proc_fops, Controller);
+ proc_create_single_data("initial_status", 0, ControllerProcEntry,
+ dac960_initial_status_proc_show, Controller);
+ proc_create_single_data("current_status", 0, ControllerProcEntry,
+ dac960_current_status_proc_show, Controller);
+ proc_create_data("user_command", 0600, ControllerProcEntry, &dac960_user_command_proc_fops, Controller);
Controller->ControllerProcEntry = ControllerProcEntry;
}
diff --git a/drivers/block/DAC960.h b/drivers/block/DAC960.h
index 21aff47..1439e65 100644
--- a/drivers/block/DAC960.h
+++ b/drivers/block/DAC960.h
@@ -2295,7 +2295,6 @@ typedef struct DAC960_Controller
unsigned short MaxBlocksPerCommand;
unsigned short ControllerScatterGatherLimit;
unsigned short DriverScatterGatherLimit;
- u64 BounceBufferLimit;
unsigned int CombinedStatusBufferLength;
unsigned int InitialStatusLength;
unsigned int CurrentStatusLength;
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index 6797e6c..429ebb8 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -159,14 +159,14 @@ static int aoe_debugfs_open(struct inode *inode, struct file *file)
return single_open(file, aoedisk_debugfs_show, inode->i_private);
}
-static DEVICE_ATTR(state, S_IRUGO, aoedisk_show_state, NULL);
-static DEVICE_ATTR(mac, S_IRUGO, aoedisk_show_mac, NULL);
-static DEVICE_ATTR(netif, S_IRUGO, aoedisk_show_netif, NULL);
+static DEVICE_ATTR(state, 0444, aoedisk_show_state, NULL);
+static DEVICE_ATTR(mac, 0444, aoedisk_show_mac, NULL);
+static DEVICE_ATTR(netif, 0444, aoedisk_show_netif, NULL);
static struct device_attribute dev_attr_firmware_version = {
- .attr = { .name = "firmware-version", .mode = S_IRUGO },
+ .attr = { .name = "firmware-version", .mode = 0444 },
.show = aoedisk_show_fwver,
};
-static DEVICE_ATTR(payload, S_IRUGO, aoedisk_show_payload, NULL);
+static DEVICE_ATTR(payload, 0444, aoedisk_show_payload, NULL);
static struct attribute *aoe_attrs[] = {
&dev_attr_state.attr,
@@ -388,7 +388,6 @@ aoeblk_gdalloc(void *vp)
d->aoemajor, d->aoeminor);
goto err_mempool;
}
- blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
spin_lock_irqsave(&d->lock, flags);
WARN_ON(!(d->flags & DEVFL_GD_NOW));
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 540bb60..096882e 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -1032,8 +1032,9 @@ bvcpy(struct sk_buff *skb, struct bio *bio, struct bvec_iter iter, long cnt)
iter.bi_size = cnt;
__bio_for_each_segment(bv, bio, iter, iter) {
- char *p = page_address(bv.bv_page) + bv.bv_offset;
+ char *p = kmap_atomic(bv.bv_page) + bv.bv_offset;
skb_copy_bits(skb, soff, p, bv.bv_len);
+ kunmap_atomic(p);
soff += bv.bv_len;
}
}
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 66cb0f8..bb97659 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -331,15 +331,15 @@ static const struct block_device_operations brd_fops = {
* And now the modules code and kernel interface.
*/
static int rd_nr = CONFIG_BLK_DEV_RAM_COUNT;
-module_param(rd_nr, int, S_IRUGO);
+module_param(rd_nr, int, 0444);
MODULE_PARM_DESC(rd_nr, "Maximum number of brd devices");
unsigned long rd_size = CONFIG_BLK_DEV_RAM_SIZE;
-module_param(rd_size, ulong, S_IRUGO);
+module_param(rd_size, ulong, 0444);
MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes.");
static int max_part = 1;
-module_param(max_part, int, S_IRUGO);
+module_param(max_part, int, 0444);
MODULE_PARM_DESC(max_part, "Num Minors to reserve between devices");
MODULE_LICENSE("GPL");
@@ -402,6 +402,10 @@ static struct brd_device *brd_alloc(int i)
set_capacity(disk, rd_size * 2);
disk->queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO;
+ /* Tell the block layer that this is not a rotational device */
+ blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
+ blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue);
+
return brd;
out_free_queue:
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index 9f4e6f5..11a85b7 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -977,7 +977,7 @@ static void drbd_bm_endio(struct bio *bio)
bm_page_unlock_io(device, idx);
if (ctx->flags & BM_AIO_COPY_PAGES)
- mempool_free(bio->bi_io_vec[0].bv_page, drbd_md_io_page_pool);
+ mempool_free(bio->bi_io_vec[0].bv_page, &drbd_md_io_page_pool);
bio_put(bio);
@@ -1014,7 +1014,8 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho
bm_set_page_unchanged(b->bm_pages[page_nr]);
if (ctx->flags & BM_AIO_COPY_PAGES) {
- page = mempool_alloc(drbd_md_io_page_pool, __GFP_HIGHMEM|__GFP_RECLAIM);
+ page = mempool_alloc(&drbd_md_io_page_pool,
+ GFP_NOIO | __GFP_HIGHMEM);
copy_highpage(page, b->bm_pages[page_nr]);
bm_store_page_idx(page, page_nr);
} else
diff --git a/drivers/block/drbd/drbd_debugfs.c b/drivers/block/drbd/drbd_debugfs.c
index ab21976..5d5e8d6 100644
--- a/drivers/block/drbd/drbd_debugfs.c
+++ b/drivers/block/drbd/drbd_debugfs.c
@@ -481,9 +481,9 @@ void drbd_debugfs_resource_add(struct drbd_resource *resource)
goto fail;
resource->debugfs_res_connections = dentry;
- dentry = debugfs_create_file("in_flight_summary", S_IRUSR|S_IRGRP,
- resource->debugfs_res, resource,
- &in_flight_summary_fops);
+ dentry = debugfs_create_file("in_flight_summary", 0440,
+ resource->debugfs_res, resource,
+ &in_flight_summary_fops);
if (IS_ERR_OR_NULL(dentry))
goto fail;
resource->debugfs_res_in_flight_summary = dentry;
@@ -645,16 +645,16 @@ void drbd_debugfs_connection_add(struct drbd_connection *connection)
goto fail;
connection->debugfs_conn = dentry;
- dentry = debugfs_create_file("callback_history", S_IRUSR|S_IRGRP,
- connection->debugfs_conn, connection,
- &connection_callback_history_fops);
+ dentry = debugfs_create_file("callback_history", 0440,
+ connection->debugfs_conn, connection,
+ &connection_callback_history_fops);
if (IS_ERR_OR_NULL(dentry))
goto fail;
connection->debugfs_conn_callback_history = dentry;
- dentry = debugfs_create_file("oldest_requests", S_IRUSR|S_IRGRP,
- connection->debugfs_conn, connection,
- &connection_oldest_requests_fops);
+ dentry = debugfs_create_file("oldest_requests", 0440,
+ connection->debugfs_conn, connection,
+ &connection_oldest_requests_fops);
if (IS_ERR_OR_NULL(dentry))
goto fail;
connection->debugfs_conn_oldest_requests = dentry;
@@ -824,7 +824,7 @@ void drbd_debugfs_device_add(struct drbd_device *device)
device->debugfs_minor = dentry;
#define DCF(name) do { \
- dentry = debugfs_create_file(#name, S_IRUSR|S_IRGRP, \
+ dentry = debugfs_create_file(#name, 0440, \
device->debugfs_vol, device, \
&device_ ## name ## _fops); \
if (IS_ERR_OR_NULL(dentry)) \
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 06ecee1..bc4ed2e 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1405,8 +1405,8 @@ extern struct kmem_cache *drbd_request_cache;
extern struct kmem_cache *drbd_ee_cache; /* peer requests */
extern struct kmem_cache *drbd_bm_ext_cache; /* bitmap extents */
extern struct kmem_cache *drbd_al_ext_cache; /* activity log extents */
-extern mempool_t *drbd_request_mempool;
-extern mempool_t *drbd_ee_mempool;
+extern mempool_t drbd_request_mempool;
+extern mempool_t drbd_ee_mempool;
/* drbd's page pool, used to buffer data received from the peer,
* or data requested by the peer.
@@ -1432,16 +1432,16 @@ extern wait_queue_head_t drbd_pp_wait;
* 128 should be plenty, currently we probably can get away with as few as 1.
*/
#define DRBD_MIN_POOL_PAGES 128
-extern mempool_t *drbd_md_io_page_pool;
+extern mempool_t drbd_md_io_page_pool;
/* We also need to make sure we get a bio
* when we need it for housekeeping purposes */
-extern struct bio_set *drbd_md_io_bio_set;
+extern struct bio_set drbd_md_io_bio_set;
/* to allocate from that set */
extern struct bio *bio_alloc_drbd(gfp_t gfp_mask);
/* And a bio_set for cloning */
-extern struct bio_set *drbd_io_bio_set;
+extern struct bio_set drbd_io_bio_set;
extern struct mutex resources_mutex;
@@ -1643,7 +1643,7 @@ void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backin
/* drbd_proc.c */
extern struct proc_dir_entry *drbd_proc;
-extern const struct file_operations drbd_proc_fops;
+int drbd_seq_show(struct seq_file *seq, void *v);
/* drbd_actlog.c */
extern bool drbd_al_begin_io_prepare(struct drbd_device *device, struct drbd_interval *i);
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 185f1ef..7655d61 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -124,11 +124,11 @@ struct kmem_cache *drbd_request_cache;
struct kmem_cache *drbd_ee_cache; /* peer requests */
struct kmem_cache *drbd_bm_ext_cache; /* bitmap extents */
struct kmem_cache *drbd_al_ext_cache; /* activity log extents */
-mempool_t *drbd_request_mempool;
-mempool_t *drbd_ee_mempool;
-mempool_t *drbd_md_io_page_pool;
-struct bio_set *drbd_md_io_bio_set;
-struct bio_set *drbd_io_bio_set;
+mempool_t drbd_request_mempool;
+mempool_t drbd_ee_mempool;
+mempool_t drbd_md_io_page_pool;
+struct bio_set drbd_md_io_bio_set;
+struct bio_set drbd_io_bio_set;
/* I do not use a standard mempool, because:
1) I want to hand out the pre-allocated objects first.
@@ -153,10 +153,10 @@ struct bio *bio_alloc_drbd(gfp_t gfp_mask)
{
struct bio *bio;
- if (!drbd_md_io_bio_set)
+ if (!bioset_initialized(&drbd_md_io_bio_set))
return bio_alloc(gfp_mask, 1);
- bio = bio_alloc_bioset(gfp_mask, 1, drbd_md_io_bio_set);
+ bio = bio_alloc_bioset(gfp_mask, 1, &drbd_md_io_bio_set);
if (!bio)
return NULL;
return bio;
@@ -2097,16 +2097,11 @@ static void drbd_destroy_mempools(void)
/* D_ASSERT(device, atomic_read(&drbd_pp_vacant)==0); */
- if (drbd_io_bio_set)
- bioset_free(drbd_io_bio_set);
- if (drbd_md_io_bio_set)
- bioset_free(drbd_md_io_bio_set);
- if (drbd_md_io_page_pool)
- mempool_destroy(drbd_md_io_page_pool);
- if (drbd_ee_mempool)
- mempool_destroy(drbd_ee_mempool);
- if (drbd_request_mempool)
- mempool_destroy(drbd_request_mempool);
+ bioset_exit(&drbd_io_bio_set);
+ bioset_exit(&drbd_md_io_bio_set);
+ mempool_exit(&drbd_md_io_page_pool);
+ mempool_exit(&drbd_ee_mempool);
+ mempool_exit(&drbd_request_mempool);
if (drbd_ee_cache)
kmem_cache_destroy(drbd_ee_cache);
if (drbd_request_cache)
@@ -2116,11 +2111,6 @@ static void drbd_destroy_mempools(void)
if (drbd_al_ext_cache)
kmem_cache_destroy(drbd_al_ext_cache);
- drbd_io_bio_set = NULL;
- drbd_md_io_bio_set = NULL;
- drbd_md_io_page_pool = NULL;
- drbd_ee_mempool = NULL;
- drbd_request_mempool = NULL;
drbd_ee_cache = NULL;
drbd_request_cache = NULL;
drbd_bm_ext_cache = NULL;
@@ -2133,18 +2123,7 @@ static int drbd_create_mempools(void)
{
struct page *page;
const int number = (DRBD_MAX_BIO_SIZE/PAGE_SIZE) * drbd_minor_count;
- int i;
-
- /* prepare our caches and mempools */
- drbd_request_mempool = NULL;
- drbd_ee_cache = NULL;
- drbd_request_cache = NULL;
- drbd_bm_ext_cache = NULL;
- drbd_al_ext_cache = NULL;
- drbd_pp_pool = NULL;
- drbd_md_io_page_pool = NULL;
- drbd_md_io_bio_set = NULL;
- drbd_io_bio_set = NULL;
+ int i, ret;
/* caches */
drbd_request_cache = kmem_cache_create(
@@ -2168,26 +2147,26 @@ static int drbd_create_mempools(void)
goto Enomem;
/* mempools */
- drbd_io_bio_set = bioset_create(BIO_POOL_SIZE, 0, 0);
- if (drbd_io_bio_set == NULL)
+ ret = bioset_init(&drbd_io_bio_set, BIO_POOL_SIZE, 0, 0);
+ if (ret)
goto Enomem;
- drbd_md_io_bio_set = bioset_create(DRBD_MIN_POOL_PAGES, 0,
- BIOSET_NEED_BVECS);
- if (drbd_md_io_bio_set == NULL)
+ ret = bioset_init(&drbd_md_io_bio_set, DRBD_MIN_POOL_PAGES, 0,
+ BIOSET_NEED_BVECS);
+ if (ret)
goto Enomem;
- drbd_md_io_page_pool = mempool_create_page_pool(DRBD_MIN_POOL_PAGES, 0);
- if (drbd_md_io_page_pool == NULL)
+ ret = mempool_init_page_pool(&drbd_md_io_page_pool, DRBD_MIN_POOL_PAGES, 0);
+ if (ret)
goto Enomem;
- drbd_request_mempool = mempool_create_slab_pool(number,
- drbd_request_cache);
- if (drbd_request_mempool == NULL)
+ ret = mempool_init_slab_pool(&drbd_request_mempool, number,
+ drbd_request_cache);
+ if (ret)
goto Enomem;
- drbd_ee_mempool = mempool_create_slab_pool(number, drbd_ee_cache);
- if (drbd_ee_mempool == NULL)
+ ret = mempool_init_slab_pool(&drbd_ee_mempool, number, drbd_ee_cache);
+ if (ret)
goto Enomem;
/* drbd's page pool */
@@ -3010,7 +2989,7 @@ static int __init drbd_init(void)
goto fail;
err = -ENOMEM;
- drbd_proc = proc_create_data("drbd", S_IFREG | S_IRUGO , NULL, &drbd_proc_fops, NULL);
+ drbd_proc = proc_create_single("drbd", S_IFREG | 0444 , NULL, drbd_seq_show);
if (!drbd_proc) {
pr_err("unable to register proc file\n");
goto fail;
diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c
index 582caeb..74ef292 100644
--- a/drivers/block/drbd/drbd_proc.c
+++ b/drivers/block/drbd/drbd_proc.c
@@ -33,18 +33,7 @@
#include <linux/drbd.h>
#include "drbd_int.h"
-static int drbd_proc_open(struct inode *inode, struct file *file);
-static int drbd_proc_release(struct inode *inode, struct file *file);
-
-
struct proc_dir_entry *drbd_proc;
-const struct file_operations drbd_proc_fops = {
- .owner = THIS_MODULE,
- .open = drbd_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = drbd_proc_release,
-};
static void seq_printf_with_thousands_grouping(struct seq_file *seq, long v)
{
@@ -235,7 +224,7 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se
}
}
-static int drbd_seq_show(struct seq_file *seq, void *v)
+int drbd_seq_show(struct seq_file *seq, void *v)
{
int i, prev_i = -1;
const char *sn;
@@ -345,24 +334,3 @@ static int drbd_seq_show(struct seq_file *seq, void *v)
return 0;
}
-
-static int drbd_proc_open(struct inode *inode, struct file *file)
-{
- int err;
-
- if (try_module_get(THIS_MODULE)) {
- err = single_open(file, drbd_seq_show, NULL);
- if (err)
- module_put(THIS_MODULE);
- return err;
- }
- return -ENODEV;
-}
-
-static int drbd_proc_release(struct inode *inode, struct file *file)
-{
- module_put(THIS_MODULE);
- return single_release(inode, file);
-}
-
-/* PROC FS stuff end */
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index c72dee0..be9450f 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -378,7 +378,7 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto
if (drbd_insert_fault(device, DRBD_FAULT_AL_EE))
return NULL;
- peer_req = mempool_alloc(drbd_ee_mempool, gfp_mask & ~__GFP_HIGHMEM);
+ peer_req = mempool_alloc(&drbd_ee_mempool, gfp_mask & ~__GFP_HIGHMEM);
if (!peer_req) {
if (!(gfp_mask & __GFP_NOWARN))
drbd_err(device, "%s: allocation failed\n", __func__);
@@ -409,7 +409,7 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto
return peer_req;
fail:
- mempool_free(peer_req, drbd_ee_mempool);
+ mempool_free(peer_req, &drbd_ee_mempool);
return NULL;
}
@@ -426,7 +426,7 @@ void __drbd_free_peer_req(struct drbd_device *device, struct drbd_peer_request *
peer_req->flags &= ~EE_CALL_AL_COMPLETE_IO;
drbd_al_complete_io(device, &peer_req->i);
}
- mempool_free(peer_req, drbd_ee_mempool);
+ mempool_free(peer_req, &drbd_ee_mempool);
}
int drbd_free_peer_reqs(struct drbd_device *device, struct list_head *list)
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index a500e73..a47e498 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -55,7 +55,7 @@ static struct drbd_request *drbd_req_new(struct drbd_device *device, struct bio
{
struct drbd_request *req;
- req = mempool_alloc(drbd_request_mempool, GFP_NOIO);
+ req = mempool_alloc(&drbd_request_mempool, GFP_NOIO);
if (!req)
return NULL;
memset(req, 0, sizeof(*req));
@@ -184,7 +184,7 @@ void drbd_req_destroy(struct kref *kref)
}
}
- mempool_free(req, drbd_request_mempool);
+ mempool_free(req, &drbd_request_mempool);
}
static void wake_all_senders(struct drbd_connection *connection)
diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h
index cb97b3b..94c6540 100644
--- a/drivers/block/drbd/drbd_req.h
+++ b/drivers/block/drbd/drbd_req.h
@@ -269,7 +269,7 @@ enum drbd_req_state_bits {
static inline void drbd_req_make_private_bio(struct drbd_request *req, struct bio *bio_src)
{
struct bio *bio;
- bio = bio_clone_fast(bio_src, GFP_NOIO, drbd_io_bio_set);
+ bio = bio_clone_fast(bio_src, GFP_NOIO, &drbd_io_bio_set);
req->private_bio = bio;
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 8ec7235..8871b50 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -4450,7 +4450,7 @@ static ssize_t floppy_cmos_show(struct device *dev,
return sprintf(buf, "%X\n", UDP->cmos);
}
-static DEVICE_ATTR(cmos, S_IRUGO, floppy_cmos_show, NULL);
+static DEVICE_ATTR(cmos, 0444, floppy_cmos_show, NULL);
static struct attribute *floppy_dev_attrs[] = {
&dev_attr_cmos.attr,
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index c9d0449..4838b0d 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -451,25 +451,47 @@ static int lo_req_flush(struct loop_device *lo, struct request *rq)
static void lo_complete_rq(struct request *rq)
{
struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
+ blk_status_t ret = BLK_STS_OK;
- if (unlikely(req_op(cmd->rq) == REQ_OP_READ && cmd->use_aio &&
- cmd->ret >= 0 && cmd->ret < blk_rq_bytes(cmd->rq))) {
- struct bio *bio = cmd->rq->bio;
-
- bio_advance(bio, cmd->ret);
- zero_fill_bio(bio);
+ if (!cmd->use_aio || cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) ||
+ req_op(rq) != REQ_OP_READ) {
+ if (cmd->ret < 0)
+ ret = BLK_STS_IOERR;
+ goto end_io;
}
- blk_mq_end_request(rq, cmd->ret < 0 ? BLK_STS_IOERR : BLK_STS_OK);
+ /*
+ * Short READ - if we got some data, advance our request and
+ * retry it. If we got no data, end the rest with EIO.
+ */
+ if (cmd->ret) {
+ blk_update_request(rq, BLK_STS_OK, cmd->ret);
+ cmd->ret = 0;
+ blk_mq_requeue_request(rq, true);
+ } else {
+ if (cmd->use_aio) {
+ struct bio *bio = rq->bio;
+
+ while (bio) {
+ zero_fill_bio(bio);
+ bio = bio->bi_next;
+ }
+ }
+ ret = BLK_STS_IOERR;
+end_io:
+ blk_mq_end_request(rq, ret);
+ }
}
static void lo_rw_aio_do_completion(struct loop_cmd *cmd)
{
+ struct request *rq = blk_mq_rq_from_pdu(cmd);
+
if (!atomic_dec_and_test(&cmd->ref))
return;
kfree(cmd->bvec);
cmd->bvec = NULL;
- blk_mq_complete_request(cmd->rq);
+ blk_mq_complete_request(rq);
}
static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
@@ -487,7 +509,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
{
struct iov_iter iter;
struct bio_vec *bvec;
- struct request *rq = cmd->rq;
+ struct request *rq = blk_mq_rq_from_pdu(cmd);
struct bio *bio = rq->bio;
struct file *file = lo->lo_backing_file;
unsigned int offset;
@@ -710,7 +732,7 @@ static ssize_t loop_attr_do_show_##_name(struct device *d, \
return loop_attr_show(d, b, loop_attr_##_name##_show); \
} \
static struct device_attribute loop_attr_##_name = \
- __ATTR(_name, S_IRUGO, loop_attr_do_show_##_name, NULL);
+ __ATTR(_name, 0444, loop_attr_do_show_##_name, NULL);
static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf)
{
@@ -787,16 +809,17 @@ static struct attribute_group loop_attribute_group = {
.attrs= loop_attrs,
};
-static int loop_sysfs_init(struct loop_device *lo)
+static void loop_sysfs_init(struct loop_device *lo)
{
- return sysfs_create_group(&disk_to_dev(lo->lo_disk)->kobj,
- &loop_attribute_group);
+ lo->sysfs_inited = !sysfs_create_group(&disk_to_dev(lo->lo_disk)->kobj,
+ &loop_attribute_group);
}
static void loop_sysfs_exit(struct loop_device *lo)
{
- sysfs_remove_group(&disk_to_dev(lo->lo_disk)->kobj,
- &loop_attribute_group);
+ if (lo->sysfs_inited)
+ sysfs_remove_group(&disk_to_dev(lo->lo_disk)->kobj,
+ &loop_attribute_group);
}
static void loop_config_discard(struct loop_device *lo)
@@ -1046,6 +1069,7 @@ static int loop_clr_fd(struct loop_device *lo)
if (bdev) {
bdput(bdev);
invalidate_bdev(bdev);
+ bdev->bd_inode->i_mapping->wb_err = 0;
}
set_capacity(lo->lo_disk, 0);
loop_sysfs_exit(lo);
@@ -1654,9 +1678,9 @@ static const struct block_device_operations lo_fops = {
* And now the modules code and kernel interface.
*/
static int max_loop;
-module_param(max_loop, int, S_IRUGO);
+module_param(max_loop, int, 0444);
MODULE_PARM_DESC(max_loop, "Maximum number of loop devices");
-module_param(max_part, int, S_IRUGO);
+module_param(max_part, int, 0444);
MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device");
MODULE_LICENSE("GPL");
MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR);
@@ -1702,15 +1726,16 @@ EXPORT_SYMBOL(loop_unregister_transfer);
static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
- struct loop_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
- struct loop_device *lo = cmd->rq->q->queuedata;
+ struct request *rq = bd->rq;
+ struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
+ struct loop_device *lo = rq->q->queuedata;
- blk_mq_start_request(bd->rq);
+ blk_mq_start_request(rq);
if (lo->lo_state != Lo_bound)
return BLK_STS_IOERR;
- switch (req_op(cmd->rq)) {
+ switch (req_op(rq)) {
case REQ_OP_FLUSH:
case REQ_OP_DISCARD:
case REQ_OP_WRITE_ZEROES:
@@ -1723,8 +1748,8 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
/* always use the first bio's css */
#ifdef CONFIG_BLK_CGROUP
- if (cmd->use_aio && cmd->rq->bio && cmd->rq->bio->bi_css) {
- cmd->css = cmd->rq->bio->bi_css;
+ if (cmd->use_aio && rq->bio && rq->bio->bi_css) {
+ cmd->css = rq->bio->bi_css;
css_get(cmd->css);
} else
#endif
@@ -1736,8 +1761,9 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
static void loop_handle_cmd(struct loop_cmd *cmd)
{
- const bool write = op_is_write(req_op(cmd->rq));
- struct loop_device *lo = cmd->rq->q->queuedata;
+ struct request *rq = blk_mq_rq_from_pdu(cmd);
+ const bool write = op_is_write(req_op(rq));
+ struct loop_device *lo = rq->q->queuedata;
int ret = 0;
if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) {
@@ -1745,12 +1771,12 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
goto failed;
}
- ret = do_req_filebacked(lo, cmd->rq);
+ ret = do_req_filebacked(lo, rq);
failed:
/* complete non-aio request */
if (!cmd->use_aio || ret) {
cmd->ret = ret ? -EIO : 0;
- blk_mq_complete_request(cmd->rq);
+ blk_mq_complete_request(rq);
}
}
@@ -1767,9 +1793,7 @@ static int loop_init_request(struct blk_mq_tag_set *set, struct request *rq,
{
struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
- cmd->rq = rq;
kthread_init_work(&cmd->work, loop_queue_work);
-
return 0;
}
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index 0f45416..4d42c7a 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -58,6 +58,7 @@ struct loop_device {
struct kthread_worker worker;
struct task_struct *worker_task;
bool use_dio;
+ bool sysfs_inited;
struct request_queue *lo_queue;
struct blk_mq_tag_set tag_set;
@@ -66,7 +67,6 @@ struct loop_device {
struct loop_cmd {
struct kthread_work work;
- struct request *rq;
bool use_aio; /* use AIO interface to handle I/O */
atomic_t ref; /* only for aio */
long ret;
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 769c551..c73626d 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -2285,7 +2285,7 @@ static ssize_t mtip_hw_show_status(struct device *dev,
return size;
}
-static DEVICE_ATTR(status, S_IRUGO, mtip_hw_show_status, NULL);
+static DEVICE_ATTR(status, 0444, mtip_hw_show_status, NULL);
/* debugsfs entries */
@@ -2566,10 +2566,9 @@ static int mtip_hw_debugfs_init(struct driver_data *dd)
return -1;
}
- debugfs_create_file("flags", S_IRUGO, dd->dfs_node, dd,
- &mtip_flags_fops);
- debugfs_create_file("registers", S_IRUGO, dd->dfs_node, dd,
- &mtip_regs_fops);
+ debugfs_create_file("flags", 0444, dd->dfs_node, dd, &mtip_flags_fops);
+ debugfs_create_file("registers", 0444, dd->dfs_node, dd,
+ &mtip_regs_fops);
return 0;
}
@@ -2726,15 +2725,11 @@ static void mtip_softirq_done_fn(struct request *rq)
blk_mq_end_request(rq, cmd->status);
}
-static void mtip_abort_cmd(struct request *req, void *data,
- bool reserved)
+static void mtip_abort_cmd(struct request *req, void *data, bool reserved)
{
struct mtip_cmd *cmd = blk_mq_rq_to_pdu(req);
struct driver_data *dd = data;
- if (!blk_mq_request_started(req))
- return;
-
dbg_printk(MTIP_DRV_NAME " Aborting request, tag = %d\n", req->tag);
clear_bit(req->tag, dd->port->cmds_to_issue);
@@ -2742,14 +2737,10 @@ static void mtip_abort_cmd(struct request *req, void *data,
mtip_softirq_done_fn(req);
}
-static void mtip_queue_cmd(struct request *req, void *data,
- bool reserved)
+static void mtip_queue_cmd(struct request *req, void *data, bool reserved)
{
struct driver_data *dd = data;
- if (!blk_mq_request_started(req))
- return;
-
set_bit(req->tag, dd->port->cmds_to_issue);
blk_abort_request(req);
}
@@ -3720,7 +3711,8 @@ static enum blk_eh_timer_return mtip_cmd_timeout(struct request *req,
struct mtip_cmd *cmd = blk_mq_rq_to_pdu(req);
cmd->status = BLK_STS_TIMEOUT;
- return BLK_EH_HANDLED;
+ blk_mq_complete_request(req);
+ return BLK_EH_DONE;
}
if (test_bit(req->tag, dd->port->cmds_to_issue))
@@ -3862,7 +3854,6 @@ static int mtip_block_initialize(struct driver_data *dd)
blk_queue_max_hw_sectors(dd->queue, 0xffff);
blk_queue_max_segment_size(dd->queue, 0x400000);
blk_queue_io_min(dd->queue, 4096);
- blk_queue_bounce_limit(dd->queue, dd->pdev->dma_mask);
/* Signal trim support */
if (dd->trim_supp == true) {
@@ -4273,7 +4264,7 @@ static int mtip_pci_probe(struct pci_dev *pdev,
if (!dd->isr_workq) {
dev_warn(&pdev->dev, "Can't create wq %d\n", dd->instance);
rv = -ENOMEM;
- goto block_initialize_err;
+ goto setmask_err;
}
memset(cpu_list, 0, sizeof(cpu_list));
@@ -4614,7 +4605,7 @@ static int __init mtip_init(void)
}
if (dfs_parent) {
dfs_device_status = debugfs_create_file("device_status",
- S_IRUGO, dfs_parent, NULL,
+ 0444, dfs_parent, NULL,
&mtip_device_status_fops);
if (IS_ERR_OR_NULL(dfs_device_status)) {
pr_err("Error creating device_status node\n");
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index afbc202..3ed1ef8 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -166,16 +166,19 @@ static ssize_t pid_show(struct device *dev,
}
static const struct device_attribute pid_attr = {
- .attr = { .name = "pid", .mode = S_IRUGO},
+ .attr = { .name = "pid", .mode = 0444},
.show = pid_show,
};
static void nbd_dev_remove(struct nbd_device *nbd)
{
struct gendisk *disk = nbd->disk;
+ struct request_queue *q;
+
if (disk) {
+ q = disk->queue;
del_gendisk(disk);
- blk_cleanup_queue(disk->queue);
+ blk_cleanup_queue(q);
blk_mq_free_tag_set(&nbd->tag_set);
disk->private_data = NULL;
put_disk(disk);
@@ -213,7 +216,15 @@ static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock,
}
if (!nsock->dead) {
kernel_sock_shutdown(nsock->sock, SHUT_RDWR);
- atomic_dec(&nbd->config->live_connections);
+ if (atomic_dec_return(&nbd->config->live_connections) == 0) {
+ if (test_and_clear_bit(NBD_DISCONNECT_REQUESTED,
+ &nbd->config->runtime_flags)) {
+ set_bit(NBD_DISCONNECTED,
+ &nbd->config->runtime_flags);
+ dev_info(nbd_to_dev(nbd),
+ "Disconnected due to user request.\n");
+ }
+ }
}
nsock->dead = true;
nsock->pending = NULL;
@@ -231,9 +242,22 @@ static void nbd_size_clear(struct nbd_device *nbd)
static void nbd_size_update(struct nbd_device *nbd)
{
struct nbd_config *config = nbd->config;
+ struct block_device *bdev = bdget_disk(nbd->disk, 0);
+
+ if (config->flags & NBD_FLAG_SEND_TRIM) {
+ nbd->disk->queue->limits.discard_granularity = config->blksize;
+ blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX);
+ }
blk_queue_logical_block_size(nbd->disk->queue, config->blksize);
blk_queue_physical_block_size(nbd->disk->queue, config->blksize);
set_capacity(nbd->disk, config->bytesize >> 9);
+ if (bdev) {
+ if (bdev->bd_disk)
+ bd_set_size(bdev, config->bytesize);
+ else
+ bdev->bd_invalidated = 1;
+ bdput(bdev);
+ }
kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
}
@@ -243,6 +267,8 @@ static void nbd_size_set(struct nbd_device *nbd, loff_t blocksize,
struct nbd_config *config = nbd->config;
config->blksize = blocksize;
config->bytesize = blocksize * nr_blocks;
+ if (nbd->task_recv != NULL)
+ nbd_size_update(nbd);
}
static void nbd_complete_rq(struct request *req)
@@ -286,13 +312,15 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
if (!refcount_inc_not_zero(&nbd->config_refs)) {
cmd->status = BLK_STS_TIMEOUT;
- return BLK_EH_HANDLED;
+ goto done;
}
config = nbd->config;
if (config->num_connections > 1) {
dev_err_ratelimited(nbd_to_dev(nbd),
- "Connection timed out, retrying\n");
+ "Connection timed out, retrying (%d/%d alive)\n",
+ atomic_read(&config->live_connections),
+ config->num_connections);
/*
* Hooray we have more connections, requeue this IO, the submit
* path will put it on a real connection.
@@ -314,7 +342,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
}
blk_mq_requeue_request(req, true);
nbd_config_put(nbd);
- return BLK_EH_NOT_HANDLED;
+ return BLK_EH_DONE;
}
} else {
dev_err_ratelimited(nbd_to_dev(nbd),
@@ -324,8 +352,9 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
cmd->status = BLK_STS_IOERR;
sock_shutdown(nbd);
nbd_config_put(nbd);
-
- return BLK_EH_HANDLED;
+done:
+ blk_mq_complete_request(req);
+ return BLK_EH_DONE;
}
/*
@@ -647,11 +676,8 @@ static void recv_work(struct work_struct *work)
static void nbd_clear_req(struct request *req, void *data, bool reserved)
{
- struct nbd_cmd *cmd;
+ struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
- if (!blk_mq_request_started(req))
- return;
- cmd = blk_mq_rq_to_pdu(req);
cmd->status = BLK_STS_IOERR;
blk_mq_complete_request(req);
}
@@ -714,10 +740,9 @@ static int wait_for_reconnect(struct nbd_device *nbd)
return 0;
if (test_bit(NBD_DISCONNECTED, &config->runtime_flags))
return 0;
- wait_event_timeout(config->conn_wait,
- atomic_read(&config->live_connections),
- config->dead_conn_timeout);
- return atomic_read(&config->live_connections);
+ return wait_event_timeout(config->conn_wait,
+ atomic_read(&config->live_connections) > 0,
+ config->dead_conn_timeout) > 0;
}
static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
@@ -950,10 +975,6 @@ static void nbd_bdev_reset(struct block_device *bdev)
if (bdev->bd_openers > 1)
return;
bd_set_size(bdev, 0);
- if (max_part > 0) {
- blkdev_reread_part(bdev);
- bdev->bd_invalidated = 1;
- }
}
static void nbd_parse_flags(struct nbd_device *nbd)
@@ -1040,6 +1061,8 @@ static void nbd_config_put(struct nbd_device *nbd)
nbd->config = NULL;
nbd->tag_set.timeout = 0;
+ nbd->disk->queue->limits.discard_granularity = 0;
+ blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX);
blk_queue_flag_clear(QUEUE_FLAG_DISCARD, nbd->disk->queue);
mutex_unlock(&nbd->config_lock);
@@ -1109,7 +1132,6 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b
if (ret)
return ret;
- bd_set_size(bdev, config->bytesize);
if (max_part)
bdev->bd_invalidated = 1;
mutex_unlock(&nbd->config_lock);
@@ -1118,7 +1140,7 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b
if (ret)
sock_shutdown(nbd);
mutex_lock(&nbd->config_lock);
- bd_set_size(bdev, 0);
+ nbd_bdev_reset(bdev);
/* user requested, ignore socket errors */
if (test_bit(NBD_DISCONNECT_REQUESTED, &config->runtime_flags))
ret = 0;
@@ -1269,6 +1291,9 @@ static int nbd_open(struct block_device *bdev, fmode_t mode)
refcount_set(&nbd->config_refs, 1);
refcount_inc(&nbd->refs);
mutex_unlock(&nbd->config_lock);
+ bdev->bd_invalidated = 1;
+ } else if (nbd_disconnected(nbd->config)) {
+ bdev->bd_invalidated = 1;
}
out:
mutex_unlock(&nbd_index_mutex);
@@ -1490,8 +1515,8 @@ static int nbd_dev_add(int index)
*/
blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue);
- disk->queue->limits.discard_granularity = 512;
- blk_queue_max_discard_sectors(disk->queue, UINT_MAX);
+ disk->queue->limits.discard_granularity = 0;
+ blk_queue_max_discard_sectors(disk->queue, 0);
blk_queue_max_segment_size(disk->queue, UINT_MAX);
blk_queue_max_segments(disk->queue, USHRT_MAX);
blk_queue_max_hw_sectors(disk->queue, 65536);
@@ -1755,6 +1780,7 @@ static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info)
}
mutex_lock(&nbd->config_lock);
nbd_disconnect(nbd);
+ nbd_clear_sock(nbd);
mutex_unlock(&nbd->config_lock);
if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
&nbd->config->runtime_flags))
@@ -2093,7 +2119,8 @@ static int __init nbd_init(void)
if (nbds_max > 1UL << (MINORBITS - part_shift))
return -EINVAL;
recv_workqueue = alloc_workqueue("knbd-recv",
- WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
+ WQ_MEM_RECLAIM | WQ_HIGHPRI |
+ WQ_UNBOUND, 0);
if (!recv_workqueue)
return -ENOMEM;
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index a765532..2bdadd7 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -157,23 +157,23 @@ enum {
};
static int g_no_sched;
-module_param_named(no_sched, g_no_sched, int, S_IRUGO);
+module_param_named(no_sched, g_no_sched, int, 0444);
MODULE_PARM_DESC(no_sched, "No io scheduler");
static int g_submit_queues = 1;
-module_param_named(submit_queues, g_submit_queues, int, S_IRUGO);
+module_param_named(submit_queues, g_submit_queues, int, 0444);
MODULE_PARM_DESC(submit_queues, "Number of submission queues");
static int g_home_node = NUMA_NO_NODE;
-module_param_named(home_node, g_home_node, int, S_IRUGO);
+module_param_named(home_node, g_home_node, int, 0444);
MODULE_PARM_DESC(home_node, "Home node for the device");
#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
static char g_timeout_str[80];
-module_param_string(timeout, g_timeout_str, sizeof(g_timeout_str), S_IRUGO);
+module_param_string(timeout, g_timeout_str, sizeof(g_timeout_str), 0444);
static char g_requeue_str[80];
-module_param_string(requeue, g_requeue_str, sizeof(g_requeue_str), S_IRUGO);
+module_param_string(requeue, g_requeue_str, sizeof(g_requeue_str), 0444);
#endif
static int g_queue_mode = NULL_Q_MQ;
@@ -203,27 +203,27 @@ static const struct kernel_param_ops null_queue_mode_param_ops = {
.get = param_get_int,
};
-device_param_cb(queue_mode, &null_queue_mode_param_ops, &g_queue_mode, S_IRUGO);
+device_param_cb(queue_mode, &null_queue_mode_param_ops, &g_queue_mode, 0444);
MODULE_PARM_DESC(queue_mode, "Block interface to use (0=bio,1=rq,2=multiqueue)");
static int g_gb = 250;
-module_param_named(gb, g_gb, int, S_IRUGO);
+module_param_named(gb, g_gb, int, 0444);
MODULE_PARM_DESC(gb, "Size in GB");
static int g_bs = 512;
-module_param_named(bs, g_bs, int, S_IRUGO);
+module_param_named(bs, g_bs, int, 0444);
MODULE_PARM_DESC(bs, "Block size (in bytes)");
static int nr_devices = 1;
-module_param(nr_devices, int, S_IRUGO);
+module_param(nr_devices, int, 0444);
MODULE_PARM_DESC(nr_devices, "Number of devices to register");
static bool g_blocking;
-module_param_named(blocking, g_blocking, bool, S_IRUGO);
+module_param_named(blocking, g_blocking, bool, 0444);
MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device");
static bool shared_tags;
-module_param(shared_tags, bool, S_IRUGO);
+module_param(shared_tags, bool, 0444);
MODULE_PARM_DESC(shared_tags, "Share tag set between devices for blk-mq");
static int g_irqmode = NULL_IRQ_SOFTIRQ;
@@ -239,19 +239,19 @@ static const struct kernel_param_ops null_irqmode_param_ops = {
.get = param_get_int,
};
-device_param_cb(irqmode, &null_irqmode_param_ops, &g_irqmode, S_IRUGO);
+device_param_cb(irqmode, &null_irqmode_param_ops, &g_irqmode, 0444);
MODULE_PARM_DESC(irqmode, "IRQ completion handler. 0-none, 1-softirq, 2-timer");
static unsigned long g_completion_nsec = 10000;
-module_param_named(completion_nsec, g_completion_nsec, ulong, S_IRUGO);
+module_param_named(completion_nsec, g_completion_nsec, ulong, 0444);
MODULE_PARM_DESC(completion_nsec, "Time in ns to complete a request in hardware. Default: 10,000ns");
static int g_hw_queue_depth = 64;
-module_param_named(hw_queue_depth, g_hw_queue_depth, int, S_IRUGO);
+module_param_named(hw_queue_depth, g_hw_queue_depth, int, 0444);
MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: 64");
static bool g_use_per_node_hctx;
-module_param_named(use_per_node_hctx, g_use_per_node_hctx, bool, S_IRUGO);
+module_param_named(use_per_node_hctx, g_use_per_node_hctx, bool, 0444);
MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false");
static struct nullb_device *null_alloc_dev(void);
@@ -1365,7 +1365,8 @@ static blk_qc_t null_queue_bio(struct request_queue *q, struct bio *bio)
static enum blk_eh_timer_return null_rq_timed_out_fn(struct request *rq)
{
pr_info("null: rq %p timed out\n", rq);
- return BLK_EH_HANDLED;
+ blk_mq_complete_request(rq);
+ return BLK_EH_DONE;
}
static int null_rq_prep_fn(struct request_queue *q, struct request *req)
@@ -1427,7 +1428,8 @@ static void null_request_fn(struct request_queue *q)
static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res)
{
pr_info("null: rq %p timed out\n", rq);
- return BLK_EH_HANDLED;
+ blk_mq_complete_request(rq);
+ return BLK_EH_DONE;
}
static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 27a44b9..8961b190 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -740,7 +740,7 @@ static int pd_special_command(struct pd_unit *disk,
{
struct request *rq;
- rq = blk_get_request(disk->gd->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+ rq = blk_get_request(disk->gd->queue, REQ_OP_DRV_IN, 0);
if (IS_ERR(rq))
return PTR_ERR(rq);
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index c61d20c..b3f83cd 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -97,8 +97,8 @@ static int pktdev_major;
static int write_congestion_on = PKT_WRITE_CONGESTION_ON;
static int write_congestion_off = PKT_WRITE_CONGESTION_OFF;
static struct mutex ctl_mutex; /* Serialize open/close/setup/teardown */
-static mempool_t *psd_pool;
-static struct bio_set *pkt_bio_set;
+static mempool_t psd_pool;
+static struct bio_set pkt_bio_set;
static struct class *class_pktcdvd = NULL; /* /sys/class/pktcdvd */
static struct dentry *pkt_debugfs_root = NULL; /* /sys/kernel/debug/pktcdvd */
@@ -478,8 +478,8 @@ static void pkt_debugfs_dev_new(struct pktcdvd_device *pd)
if (!pd->dfs_d_root)
return;
- pd->dfs_f_info = debugfs_create_file("info", S_IRUGO,
- pd->dfs_d_root, pd, &debug_fops);
+ pd->dfs_f_info = debugfs_create_file("info", 0444,
+ pd->dfs_d_root, pd, &debug_fops);
}
static void pkt_debugfs_dev_remove(struct pktcdvd_device *pd)
@@ -631,7 +631,7 @@ static inline struct pkt_rb_node *pkt_rbtree_next(struct pkt_rb_node *node)
static void pkt_rbtree_erase(struct pktcdvd_device *pd, struct pkt_rb_node *node)
{
rb_erase(&node->rb_node, &pd->bio_queue);
- mempool_free(node, pd->rb_pool);
+ mempool_free(node, &pd->rb_pool);
pd->bio_queue_size--;
BUG_ON(pd->bio_queue_size < 0);
}
@@ -704,13 +704,13 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
int ret = 0;
rq = blk_get_request(q, (cgc->data_direction == CGC_DATA_WRITE) ?
- REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, __GFP_RECLAIM);
+ REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
if (IS_ERR(rq))
return PTR_ERR(rq);
if (cgc->buflen) {
ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen,
- __GFP_RECLAIM);
+ GFP_NOIO);
if (ret)
goto out;
}
@@ -1285,7 +1285,7 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
* Fill-in bvec with data from orig_bios.
*/
spin_lock(&pkt->lock);
- bio_copy_data(pkt->w_bio, pkt->orig_bios.head);
+ bio_list_copy_data(pkt->w_bio, pkt->orig_bios.head);
pkt_set_state(pkt, PACKET_WRITE_WAIT_STATE);
spin_unlock(&pkt->lock);
@@ -2303,14 +2303,14 @@ static void pkt_end_io_read_cloned(struct bio *bio)
psd->bio->bi_status = bio->bi_status;
bio_put(bio);
bio_endio(psd->bio);
- mempool_free(psd, psd_pool);
+ mempool_free(psd, &psd_pool);
pkt_bio_finished(pd);
}
static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio)
{
- struct bio *cloned_bio = bio_clone_fast(bio, GFP_NOIO, pkt_bio_set);
- struct packet_stacked_data *psd = mempool_alloc(psd_pool, GFP_NOIO);
+ struct bio *cloned_bio = bio_clone_fast(bio, GFP_NOIO, &pkt_bio_set);
+ struct packet_stacked_data *psd = mempool_alloc(&psd_pool, GFP_NOIO);
psd->pd = pd;
psd->bio = bio;
@@ -2381,7 +2381,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
/*
* No matching packet found. Store the bio in the work queue.
*/
- node = mempool_alloc(pd->rb_pool, GFP_NOIO);
+ node = mempool_alloc(&pd->rb_pool, GFP_NOIO);
node->bio = bio;
spin_lock(&pd->lock);
BUG_ON(pd->bio_queue_size < 0);
@@ -2451,7 +2451,7 @@ static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio)
split = bio_split(bio, last_zone -
bio->bi_iter.bi_sector,
- GFP_NOIO, pkt_bio_set);
+ GFP_NOIO, &pkt_bio_set);
bio_chain(split, bio);
} else {
split = bio;
@@ -2538,18 +2538,6 @@ static int pkt_seq_show(struct seq_file *m, void *p)
return 0;
}
-static int pkt_seq_open(struct inode *inode, struct file *file)
-{
- return single_open(file, pkt_seq_show, PDE_DATA(inode));
-}
-
-static const struct file_operations pkt_proc_fops = {
- .open = pkt_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release
-};
-
static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
{
int i;
@@ -2604,7 +2592,7 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
goto out_mem;
}
- proc_create_data(pd->name, 0, pkt_proc, &pkt_proc_fops, pd);
+ proc_create_single_data(pd->name, 0, pkt_proc, pkt_seq_show, pd);
pkt_dbg(1, pd, "writer mapped to %s\n", bdevname(bdev, b));
return 0;
@@ -2707,9 +2695,9 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
if (!pd)
goto out_mutex;
- pd->rb_pool = mempool_create_kmalloc_pool(PKT_RB_POOL_SIZE,
- sizeof(struct pkt_rb_node));
- if (!pd->rb_pool)
+ ret = mempool_init_kmalloc_pool(&pd->rb_pool, PKT_RB_POOL_SIZE,
+ sizeof(struct pkt_rb_node));
+ if (ret)
goto out_mem;
INIT_LIST_HEAD(&pd->cdrw.pkt_free_list);
@@ -2766,7 +2754,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
out_mem2:
put_disk(disk);
out_mem:
- mempool_destroy(pd->rb_pool);
+ mempool_exit(&pd->rb_pool);
kfree(pd);
out_mutex:
mutex_unlock(&ctl_mutex);
@@ -2817,7 +2805,7 @@ static int pkt_remove_dev(dev_t pkt_dev)
blk_cleanup_queue(pd->disk->queue);
put_disk(pd->disk);
- mempool_destroy(pd->rb_pool);
+ mempool_exit(&pd->rb_pool);
kfree(pd);
/* This is safe: open() is still holding a reference. */
@@ -2914,14 +2902,14 @@ static int __init pkt_init(void)
mutex_init(&ctl_mutex);
- psd_pool = mempool_create_kmalloc_pool(PSD_POOL_SIZE,
- sizeof(struct packet_stacked_data));
- if (!psd_pool)
- return -ENOMEM;
- pkt_bio_set = bioset_create(BIO_POOL_SIZE, 0, 0);
- if (!pkt_bio_set) {
- mempool_destroy(psd_pool);
- return -ENOMEM;
+ ret = mempool_init_kmalloc_pool(&psd_pool, PSD_POOL_SIZE,
+ sizeof(struct packet_stacked_data));
+ if (ret)
+ return ret;
+ ret = bioset_init(&pkt_bio_set, BIO_POOL_SIZE, 0, 0);
+ if (ret) {
+ mempool_exit(&psd_pool);
+ return ret;
}
ret = register_blkdev(pktdev_major, DRIVER_NAME);
@@ -2954,8 +2942,8 @@ static int __init pkt_init(void)
out:
unregister_blkdev(pktdev_major, DRIVER_NAME);
out2:
- mempool_destroy(psd_pool);
- bioset_free(pkt_bio_set);
+ mempool_exit(&psd_pool);
+ bioset_exit(&pkt_bio_set);
return ret;
}
@@ -2968,8 +2956,8 @@ static void __exit pkt_exit(void)
pkt_sysfs_cleanup();
unregister_blkdev(pktdev_major, DRIVER_NAME);
- mempool_destroy(psd_pool);
- bioset_free(pkt_bio_set);
+ mempool_exit(&psd_pool);
+ bioset_exit(&pkt_bio_set);
}
MODULE_DESCRIPTION("Packet writing layer for CD/DVD drives");
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index 075662f..afe1508 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -465,8 +465,6 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
priv->queue = queue;
queue->queuedata = dev;
- blk_queue_bounce_limit(queue, BLK_BOUNCE_HIGH);
-
blk_queue_max_hw_sectors(queue, dev->bounce_size >> 9);
blk_queue_segment_boundary(queue, -1UL);
blk_queue_dma_alignment(queue, dev->blk_size-1);
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index 6a55959..8fa4533 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -521,26 +521,13 @@ static int ps3vram_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int ps3vram_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ps3vram_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations ps3vram_proc_fops = {
- .owner = THIS_MODULE,
- .open = ps3vram_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static void ps3vram_proc_init(struct ps3_system_bus_device *dev)
{
struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
struct proc_dir_entry *pde;
- pde = proc_create_data(DEVICE_NAME, 0444, NULL, &ps3vram_proc_fops,
- priv);
+ pde = proc_create_single_data(DEVICE_NAME, 0444, NULL,
+ ps3vram_proc_show, priv);
if (!pde)
dev_warn(&dev->core, "failed to create /proc entry\n");
}
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 07dc541..af35404 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -424,7 +424,7 @@ static struct workqueue_struct *rbd_wq;
* single-major requires >= 0.75 version of userspace rbd utility.
*/
static bool single_major = true;
-module_param(single_major, bool, S_IRUGO);
+module_param(single_major, bool, 0444);
MODULE_PARM_DESC(single_major, "Use a single major number for all rbd devices (default: true)");
static ssize_t rbd_add(struct bus_type *bus, const char *buf,
@@ -468,11 +468,11 @@ static ssize_t rbd_supported_features_show(struct bus_type *bus, char *buf)
return sprintf(buf, "0x%llx\n", RBD_FEATURES_SUPPORTED);
}
-static BUS_ATTR(add, S_IWUSR, NULL, rbd_add);
-static BUS_ATTR(remove, S_IWUSR, NULL, rbd_remove);
-static BUS_ATTR(add_single_major, S_IWUSR, NULL, rbd_add_single_major);
-static BUS_ATTR(remove_single_major, S_IWUSR, NULL, rbd_remove_single_major);
-static BUS_ATTR(supported_features, S_IRUGO, rbd_supported_features_show, NULL);
+static BUS_ATTR(add, 0200, NULL, rbd_add);
+static BUS_ATTR(remove, 0200, NULL, rbd_remove);
+static BUS_ATTR(add_single_major, 0200, NULL, rbd_add_single_major);
+static BUS_ATTR(remove_single_major, 0200, NULL, rbd_remove_single_major);
+static BUS_ATTR(supported_features, 0444, rbd_supported_features_show, NULL);
static struct attribute *rbd_bus_attrs[] = {
&bus_attr_add.attr,
@@ -732,6 +732,7 @@ static struct rbd_client *rbd_client_find(struct ceph_options *ceph_opts)
*/
enum {
Opt_queue_depth,
+ Opt_lock_timeout,
Opt_last_int,
/* int args above */
Opt_last_string,
@@ -740,11 +741,13 @@ enum {
Opt_read_write,
Opt_lock_on_read,
Opt_exclusive,
+ Opt_notrim,
Opt_err
};
static match_table_t rbd_opts_tokens = {
{Opt_queue_depth, "queue_depth=%d"},
+ {Opt_lock_timeout, "lock_timeout=%d"},
/* int args above */
/* string args above */
{Opt_read_only, "read_only"},
@@ -753,20 +756,25 @@ static match_table_t rbd_opts_tokens = {
{Opt_read_write, "rw"}, /* Alternate spelling */
{Opt_lock_on_read, "lock_on_read"},
{Opt_exclusive, "exclusive"},
+ {Opt_notrim, "notrim"},
{Opt_err, NULL}
};
struct rbd_options {
int queue_depth;
+ unsigned long lock_timeout;
bool read_only;
bool lock_on_read;
bool exclusive;
+ bool trim;
};
#define RBD_QUEUE_DEPTH_DEFAULT BLKDEV_MAX_RQ
+#define RBD_LOCK_TIMEOUT_DEFAULT 0 /* no timeout */
#define RBD_READ_ONLY_DEFAULT false
#define RBD_LOCK_ON_READ_DEFAULT false
#define RBD_EXCLUSIVE_DEFAULT false
+#define RBD_TRIM_DEFAULT true
static int parse_rbd_opts_token(char *c, void *private)
{
@@ -796,6 +804,14 @@ static int parse_rbd_opts_token(char *c, void *private)
}
rbd_opts->queue_depth = intval;
break;
+ case Opt_lock_timeout:
+ /* 0 is "wait forever" (i.e. infinite timeout) */
+ if (intval < 0 || intval > INT_MAX / 1000) {
+ pr_err("lock_timeout out of range\n");
+ return -EINVAL;
+ }
+ rbd_opts->lock_timeout = msecs_to_jiffies(intval * 1000);
+ break;
case Opt_read_only:
rbd_opts->read_only = true;
break;
@@ -808,6 +824,9 @@ static int parse_rbd_opts_token(char *c, void *private)
case Opt_exclusive:
rbd_opts->exclusive = true;
break;
+ case Opt_notrim:
+ rbd_opts->trim = false;
+ break;
default:
/* libceph prints "bad option" msg */
return -EINVAL;
@@ -1392,7 +1411,7 @@ static bool rbd_img_is_write(struct rbd_img_request *img_req)
case OBJ_OP_DISCARD:
return true;
default:
- rbd_assert(0);
+ BUG();
}
}
@@ -2347,7 +2366,9 @@ static int rbd_obj_issue_copyup(struct rbd_obj_request *obj_req, u32 bytes)
osd_req_op_cls_init(obj_req->osd_req, 0, CEPH_OSD_OP_CALL, "rbd",
"copyup");
osd_req_op_cls_request_data_bvecs(obj_req->osd_req, 0,
- obj_req->copyup_bvecs, bytes);
+ obj_req->copyup_bvecs,
+ obj_req->copyup_bvec_count,
+ bytes);
switch (obj_req->img_request->op_type) {
case OBJ_OP_WRITE:
@@ -2466,7 +2487,7 @@ static bool rbd_obj_handle_write(struct rbd_obj_request *obj_req)
}
return false;
default:
- rbd_assert(0);
+ BUG();
}
}
@@ -2494,7 +2515,7 @@ static bool __rbd_obj_handle_request(struct rbd_obj_request *obj_req)
}
return false;
default:
- rbd_assert(0);
+ BUG();
}
}
@@ -3533,9 +3554,22 @@ static int rbd_obj_method_sync(struct rbd_device *rbd_dev,
/*
* lock_rwsem must be held for read
*/
-static void rbd_wait_state_locked(struct rbd_device *rbd_dev)
+static int rbd_wait_state_locked(struct rbd_device *rbd_dev, bool may_acquire)
{
DEFINE_WAIT(wait);
+ unsigned long timeout;
+ int ret = 0;
+
+ if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags))
+ return -EBLACKLISTED;
+
+ if (rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED)
+ return 0;
+
+ if (!may_acquire) {
+ rbd_warn(rbd_dev, "exclusive lock required");
+ return -EROFS;
+ }
do {
/*
@@ -3547,12 +3581,22 @@ static void rbd_wait_state_locked(struct rbd_device *rbd_dev)
prepare_to_wait_exclusive(&rbd_dev->lock_waitq, &wait,
TASK_UNINTERRUPTIBLE);
up_read(&rbd_dev->lock_rwsem);
- schedule();
+ timeout = schedule_timeout(ceph_timeout_jiffies(
+ rbd_dev->opts->lock_timeout));
down_read(&rbd_dev->lock_rwsem);
- } while (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED &&
- !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags));
+ if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
+ ret = -EBLACKLISTED;
+ break;
+ }
+ if (!timeout) {
+ rbd_warn(rbd_dev, "timed out waiting for lock");
+ ret = -ETIMEDOUT;
+ break;
+ }
+ } while (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED);
finish_wait(&rbd_dev->lock_waitq, &wait);
+ return ret;
}
static void rbd_queue_workfn(struct work_struct *work)
@@ -3638,19 +3682,10 @@ static void rbd_queue_workfn(struct work_struct *work)
(op_type != OBJ_OP_READ || rbd_dev->opts->lock_on_read);
if (must_be_locked) {
down_read(&rbd_dev->lock_rwsem);
- if (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED &&
- !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
- if (rbd_dev->opts->exclusive) {
- rbd_warn(rbd_dev, "exclusive lock required");
- result = -EROFS;
- goto err_unlock;
- }
- rbd_wait_state_locked(rbd_dev);
- }
- if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
- result = -EBLACKLISTED;
+ result = rbd_wait_state_locked(rbd_dev,
+ !rbd_dev->opts->exclusive);
+ if (result)
goto err_unlock;
- }
}
img_request = rbd_img_request_create(rbd_dev, op_type, snapc);
@@ -3902,7 +3937,8 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
{
struct gendisk *disk;
struct request_queue *q;
- u64 segment_size;
+ unsigned int objset_bytes =
+ rbd_dev->layout.object_size * rbd_dev->layout.stripe_count;
int err;
/* create gendisk info */
@@ -3942,20 +3978,19 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
/* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */
- /* set io sizes to object size */
- segment_size = rbd_obj_bytes(&rbd_dev->header);
- blk_queue_max_hw_sectors(q, segment_size / SECTOR_SIZE);
+ blk_queue_max_hw_sectors(q, objset_bytes >> SECTOR_SHIFT);
q->limits.max_sectors = queue_max_hw_sectors(q);
blk_queue_max_segments(q, USHRT_MAX);
blk_queue_max_segment_size(q, UINT_MAX);
- blk_queue_io_min(q, segment_size);
- blk_queue_io_opt(q, segment_size);
+ blk_queue_io_min(q, objset_bytes);
+ blk_queue_io_opt(q, objset_bytes);
- /* enable the discard support */
- blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
- q->limits.discard_granularity = segment_size;
- blk_queue_max_discard_sectors(q, segment_size / SECTOR_SIZE);
- blk_queue_max_write_zeroes_sectors(q, segment_size / SECTOR_SIZE);
+ if (rbd_dev->opts->trim) {
+ blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
+ q->limits.discard_granularity = objset_bytes;
+ blk_queue_max_discard_sectors(q, objset_bytes >> SECTOR_SHIFT);
+ blk_queue_max_write_zeroes_sectors(q, objset_bytes >> SECTOR_SHIFT);
+ }
if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
@@ -4169,22 +4204,22 @@ static ssize_t rbd_image_refresh(struct device *dev,
return size;
}
-static DEVICE_ATTR(size, S_IRUGO, rbd_size_show, NULL);
-static DEVICE_ATTR(features, S_IRUGO, rbd_features_show, NULL);
-static DEVICE_ATTR(major, S_IRUGO, rbd_major_show, NULL);
-static DEVICE_ATTR(minor, S_IRUGO, rbd_minor_show, NULL);
-static DEVICE_ATTR(client_addr, S_IRUGO, rbd_client_addr_show, NULL);
-static DEVICE_ATTR(client_id, S_IRUGO, rbd_client_id_show, NULL);
-static DEVICE_ATTR(cluster_fsid, S_IRUGO, rbd_cluster_fsid_show, NULL);
-static DEVICE_ATTR(config_info, S_IRUSR, rbd_config_info_show, NULL);
-static DEVICE_ATTR(pool, S_IRUGO, rbd_pool_show, NULL);
-static DEVICE_ATTR(pool_id, S_IRUGO, rbd_pool_id_show, NULL);
-static DEVICE_ATTR(name, S_IRUGO, rbd_name_show, NULL);
-static DEVICE_ATTR(image_id, S_IRUGO, rbd_image_id_show, NULL);
-static DEVICE_ATTR(refresh, S_IWUSR, NULL, rbd_image_refresh);
-static DEVICE_ATTR(current_snap, S_IRUGO, rbd_snap_show, NULL);
-static DEVICE_ATTR(snap_id, S_IRUGO, rbd_snap_id_show, NULL);
-static DEVICE_ATTR(parent, S_IRUGO, rbd_parent_show, NULL);
+static DEVICE_ATTR(size, 0444, rbd_size_show, NULL);
+static DEVICE_ATTR(features, 0444, rbd_features_show, NULL);
+static DEVICE_ATTR(major, 0444, rbd_major_show, NULL);
+static DEVICE_ATTR(minor, 0444, rbd_minor_show, NULL);
+static DEVICE_ATTR(client_addr, 0444, rbd_client_addr_show, NULL);
+static DEVICE_ATTR(client_id, 0444, rbd_client_id_show, NULL);
+static DEVICE_ATTR(cluster_fsid, 0444, rbd_cluster_fsid_show, NULL);
+static DEVICE_ATTR(config_info, 0400, rbd_config_info_show, NULL);
+static DEVICE_ATTR(pool, 0444, rbd_pool_show, NULL);
+static DEVICE_ATTR(pool_id, 0444, rbd_pool_id_show, NULL);
+static DEVICE_ATTR(name, 0444, rbd_name_show, NULL);
+static DEVICE_ATTR(image_id, 0444, rbd_image_id_show, NULL);
+static DEVICE_ATTR(refresh, 0200, NULL, rbd_image_refresh);
+static DEVICE_ATTR(current_snap, 0444, rbd_snap_show, NULL);
+static DEVICE_ATTR(snap_id, 0444, rbd_snap_id_show, NULL);
+static DEVICE_ATTR(parent, 0444, rbd_parent_show, NULL);
static struct attribute *rbd_attrs[] = {
&dev_attr_size.attr,
@@ -5179,8 +5214,10 @@ static int rbd_add_parse_args(const char *buf,
rbd_opts->read_only = RBD_READ_ONLY_DEFAULT;
rbd_opts->queue_depth = RBD_QUEUE_DEPTH_DEFAULT;
+ rbd_opts->lock_timeout = RBD_LOCK_TIMEOUT_DEFAULT;
rbd_opts->lock_on_read = RBD_LOCK_ON_READ_DEFAULT;
rbd_opts->exclusive = RBD_EXCLUSIVE_DEFAULT;
+ rbd_opts->trim = RBD_TRIM_DEFAULT;
copts = ceph_parse_options(options, mon_addrs,
mon_addrs + mon_addrs_size - 1,
@@ -5216,6 +5253,8 @@ static void rbd_dev_image_unlock(struct rbd_device *rbd_dev)
static int rbd_add_acquire_lock(struct rbd_device *rbd_dev)
{
+ int ret;
+
if (!(rbd_dev->header.features & RBD_FEATURE_EXCLUSIVE_LOCK)) {
rbd_warn(rbd_dev, "exclusive-lock feature is not enabled");
return -EINVAL;
@@ -5223,9 +5262,9 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev)
/* FIXME: "rbd map --exclusive" should be in interruptible */
down_read(&rbd_dev->lock_rwsem);
- rbd_wait_state_locked(rbd_dev);
+ ret = rbd_wait_state_locked(rbd_dev, true);
up_read(&rbd_dev->lock_rwsem);
- if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
+ if (ret) {
rbd_warn(rbd_dev, "failed to acquire exclusive lock");
return -EROFS;
}
diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c
index 34997df..09537be 100644
--- a/drivers/block/rsxx/core.c
+++ b/drivers/block/rsxx/core.c
@@ -247,19 +247,19 @@ static void rsxx_debugfs_dev_new(struct rsxx_cardinfo *card)
if (IS_ERR_OR_NULL(card->debugfs_dir))
goto failed_debugfs_dir;
- debugfs_stats = debugfs_create_file("stats", S_IRUGO,
+ debugfs_stats = debugfs_create_file("stats", 0444,
card->debugfs_dir, card,
&debugfs_stats_fops);
if (IS_ERR_OR_NULL(debugfs_stats))
goto failed_debugfs_stats;
- debugfs_pci_regs = debugfs_create_file("pci_regs", S_IRUGO,
+ debugfs_pci_regs = debugfs_create_file("pci_regs", 0444,
card->debugfs_dir, card,
&debugfs_pci_regs_fops);
if (IS_ERR_OR_NULL(debugfs_pci_regs))
goto failed_debugfs_pci_regs;
- debugfs_cram = debugfs_create_file("cram", S_IRUGO | S_IWUSR,
+ debugfs_cram = debugfs_create_file("cram", 0644,
card->debugfs_dir, card,
&debugfs_cram_fops);
if (IS_ERR_OR_NULL(debugfs_cram))
diff --git a/drivers/block/swim.c b/drivers/block/swim.c
index 64e066e..0e31884 100644
--- a/drivers/block/swim.c
+++ b/drivers/block/swim.c
@@ -110,7 +110,7 @@ struct iwm {
/* Select values for swim_select and swim_readbit */
#define READ_DATA_0 0x074
-#define TWOMEG_DRIVE 0x075
+#define ONEMEG_DRIVE 0x075
#define SINGLE_SIDED 0x076
#define DRIVE_PRESENT 0x077
#define DISK_IN 0x170
@@ -118,9 +118,9 @@ struct iwm {
#define TRACK_ZERO 0x172
#define TACHO 0x173
#define READ_DATA_1 0x174
-#define MFM_MODE 0x175
+#define GCR_MODE 0x175
#define SEEK_COMPLETE 0x176
-#define ONEMEG_MEDIA 0x177
+#define TWOMEG_MEDIA 0x177
/* Bits in handshake register */
@@ -612,7 +612,6 @@ static void setup_medium(struct floppy_state *fs)
struct floppy_struct *g;
fs->disk_in = 1;
fs->write_protected = swim_readbit(base, WRITE_PROT);
- fs->type = swim_readbit(base, ONEMEG_MEDIA);
if (swim_track00(base))
printk(KERN_ERR
@@ -620,6 +619,9 @@ static void setup_medium(struct floppy_state *fs)
swim_track00(base);
+ fs->type = swim_readbit(base, TWOMEG_MEDIA) ?
+ HD_MEDIA : DD_MEDIA;
+ fs->head_number = swim_readbit(base, SINGLE_SIDED) ? 1 : 2;
get_floppy_geometry(fs, 0, &g);
fs->total_secs = g->size;
fs->secpercyl = g->head * g->sect;
@@ -646,7 +648,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
swim_write(base, setup, S_IBM_DRIVE | S_FCLK_DIV2);
udelay(10);
- swim_drive(base, INTERNAL_DRIVE);
+ swim_drive(base, fs->location);
swim_motor(base, ON);
swim_action(base, SETMFM);
if (fs->ejected)
@@ -656,6 +658,8 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
goto out;
}
+ set_capacity(fs->disk, fs->total_secs);
+
if (mode & FMODE_NDELAY)
return 0;
@@ -727,14 +731,9 @@ static int floppy_ioctl(struct block_device *bdev, fmode_t mode,
if (copy_to_user((void __user *) param, (void *) &floppy_type,
sizeof(struct floppy_struct)))
return -EFAULT;
- break;
-
- default:
- printk(KERN_DEBUG "SWIM floppy_ioctl: unknown cmd %d\n",
- cmd);
- return -ENOSYS;
+ return 0;
}
- return 0;
+ return -ENOTTY;
}
static int floppy_getgeo(struct block_device *bdev, struct hd_geometry *geo)
@@ -795,7 +794,7 @@ static struct kobject *floppy_find(dev_t dev, int *part, void *data)
struct swim_priv *swd = data;
int drive = (*part & 3);
- if (drive > swd->floppy_count)
+ if (drive >= swd->floppy_count)
return NULL;
*part = 0;
@@ -813,10 +812,9 @@ static int swim_add_floppy(struct swim_priv *swd, enum drive_location location)
swim_motor(base, OFF);
- if (swim_readbit(base, SINGLE_SIDED))
- fs->head_number = 1;
- else
- fs->head_number = 2;
+ fs->type = HD_MEDIA;
+ fs->head_number = 2;
+
fs->ref_count = 0;
fs->ejected = 1;
@@ -834,10 +832,12 @@ static int swim_floppy_init(struct swim_priv *swd)
/* scan floppy drives */
swim_drive(base, INTERNAL_DRIVE);
- if (swim_readbit(base, DRIVE_PRESENT))
+ if (swim_readbit(base, DRIVE_PRESENT) &&
+ !swim_readbit(base, ONEMEG_DRIVE))
swim_add_floppy(swd, INTERNAL_DRIVE);
swim_drive(base, EXTERNAL_DRIVE);
- if (swim_readbit(base, DRIVE_PRESENT))
+ if (swim_readbit(base, DRIVE_PRESENT) &&
+ !swim_readbit(base, ONEMEG_DRIVE))
swim_add_floppy(swd, EXTERNAL_DRIVE);
/* register floppy drives */
@@ -861,7 +861,6 @@ static int swim_floppy_init(struct swim_priv *swd)
&swd->lock);
if (!swd->unit[drive].disk->queue) {
err = -ENOMEM;
- put_disk(swd->unit[drive].disk);
goto exit_put_disks;
}
blk_queue_bounce_limit(swd->unit[drive].disk->queue,
@@ -911,7 +910,7 @@ static int swim_probe(struct platform_device *dev)
goto out;
}
- swim_base = ioremap(res->start, resource_size(res));
+ swim_base = (struct swim __iomem *)res->start;
if (!swim_base) {
ret = -ENOMEM;
goto out_release_io;
@@ -923,7 +922,7 @@ static int swim_probe(struct platform_device *dev)
if (!get_swim_mode(swim_base)) {
printk(KERN_INFO "SWIM device not found !\n");
ret = -ENODEV;
- goto out_iounmap;
+ goto out_release_io;
}
/* set platform driver data */
@@ -931,7 +930,7 @@ static int swim_probe(struct platform_device *dev)
swd = kzalloc(sizeof(struct swim_priv), GFP_KERNEL);
if (!swd) {
ret = -ENOMEM;
- goto out_iounmap;
+ goto out_release_io;
}
platform_set_drvdata(dev, swd);
@@ -945,8 +944,6 @@ static int swim_probe(struct platform_device *dev)
out_kfree:
kfree(swd);
-out_iounmap:
- iounmap(swim_base);
out_release_io:
release_mem_region(res->start, resource_size(res));
out:
@@ -974,8 +971,6 @@ static int swim_remove(struct platform_device *dev)
for (drive = 0; drive < swd->floppy_count; drive++)
floppy_eject(&swd->unit[drive]);
- iounmap(swd->base);
-
res = platform_get_resource(dev, IORESOURCE_MEM, 0);
if (res)
release_mem_region(res->start, resource_size(res));
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index af51015..469541c 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -148,7 +148,7 @@ struct swim3 {
#define MOTOR_ON 2
#define RELAX 3 /* also eject in progress */
#define READ_DATA_0 4
-#define TWOMEG_DRIVE 5
+#define ONEMEG_DRIVE 5
#define SINGLE_SIDED 6 /* drive or diskette is 4MB type? */
#define DRIVE_PRESENT 7
#define DISK_IN 8
@@ -156,9 +156,9 @@ struct swim3 {
#define TRACK_ZERO 10
#define TACHO 11
#define READ_DATA_1 12
-#define MFM_MODE 13
+#define GCR_MODE 13
#define SEEK_COMPLETE 14
-#define ONEMEG_MEDIA 15
+#define TWOMEG_MEDIA 15
/* Definitions of values used in writing and formatting */
#define DATA_ESCAPE 0x99
diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c
index 08586dc..4d90e5e 100644
--- a/drivers/block/sx8.c
+++ b/drivers/block/sx8.c
@@ -567,7 +567,7 @@ static struct carm_request *carm_get_special(struct carm_host *host)
if (!crq)
return NULL;
- rq = blk_get_request(host->oob_q, REQ_OP_DRV_OUT, GFP_KERNEL);
+ rq = blk_get_request(host->oob_q, REQ_OP_DRV_OUT, 0);
if (IS_ERR(rq)) {
spin_lock_irqsave(&host->lock, flags);
carm_put_request(host, crq);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 4a07593c..23752dc 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -298,7 +298,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
struct request *req;
int err;
- req = blk_get_request(q, REQ_OP_DRV_IN, GFP_KERNEL);
+ req = blk_get_request(q, REQ_OP_DRV_IN, 0);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -371,7 +371,7 @@ static ssize_t virtblk_serial_show(struct device *dev,
return err;
}
-static DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL);
+static DEVICE_ATTR(serial, 0444, virtblk_serial_show, NULL);
/* The queue's logical block size must be set before calling this */
static void virtblk_update_capacity(struct virtio_blk *vblk, bool resize)
@@ -576,10 +576,10 @@ virtblk_cache_type_show(struct device *dev, struct device_attribute *attr,
}
static const struct device_attribute dev_attr_cache_type_ro =
- __ATTR(cache_type, S_IRUGO,
+ __ATTR(cache_type, 0444,
virtblk_cache_type_show, NULL);
static const struct device_attribute dev_attr_cache_type_rw =
- __ATTR(cache_type, S_IRUGO|S_IWUSR,
+ __ATTR(cache_type, 0644,
virtblk_cache_type_show, virtblk_cache_type_store);
static int virtblk_init_request(struct blk_mq_tag_set *set, struct request *rq,
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 987d665..b55b245 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -98,7 +98,7 @@ MODULE_PARM_DESC(max_queues,
* backend, 4KB page granularity is used.
*/
unsigned int xen_blkif_max_ring_order = XENBUS_MAX_RING_GRANT_ORDER;
-module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, S_IRUGO);
+module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, 0444);
MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring");
/*
* The LRU mechanism to clean the lists of persistent grants needs to
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 21c1be1..66412eed 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -367,7 +367,7 @@ int __init xen_blkif_interface_init(void)
out: \
return sprintf(buf, format, result); \
} \
- static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL)
+ static DEVICE_ATTR(name, 0444, show_##name, NULL)
VBD_SHOW_ALLRING(oo_req, "%llu\n");
VBD_SHOW_ALLRING(rd_req, "%llu\n");
@@ -403,7 +403,7 @@ static const struct attribute_group xen_vbdstat_group = {
\
return sprintf(buf, format, ##args); \
} \
- static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL)
+ static DEVICE_ATTR(name, 0444, show_##name, NULL)
VBD_SHOW(physical_device, "%x:%x\n", be->major, be->minor);
VBD_SHOW(mode, "%s\n", be->mode);
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 2a8e781..ae00a82 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -129,13 +129,12 @@ static const struct block_device_operations xlvbd_block_fops;
*/
static unsigned int xen_blkif_max_segments = 32;
-module_param_named(max_indirect_segments, xen_blkif_max_segments, uint,
- S_IRUGO);
+module_param_named(max_indirect_segments, xen_blkif_max_segments, uint, 0444);
MODULE_PARM_DESC(max_indirect_segments,
"Maximum amount of segments in indirect requests (default is 32)");
static unsigned int xen_blkif_max_queues = 4;
-module_param_named(max_queues, xen_blkif_max_queues, uint, S_IRUGO);
+module_param_named(max_queues, xen_blkif_max_queues, uint, 0444);
MODULE_PARM_DESC(max_queues, "Maximum number of hardware queues/rings used per virtual disk");
/*
@@ -143,7 +142,7 @@ MODULE_PARM_DESC(max_queues, "Maximum number of hardware queues/rings used per v
* backend, 4KB page granularity is used.
*/
static unsigned int xen_blkif_max_ring_order;
-module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, S_IRUGO);
+module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, 0444);
MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring");
#define BLK_RING_SIZE(info) \
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index c8c8b0b..b937cc1 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -231,6 +231,7 @@ static const struct usb_device_id blacklist_table[] = {
{ USB_DEVICE(0x0930, 0x0227), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0b05, 0x17d0), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0x0036), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0x3008), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0x311d), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0x311e), .driver_info = BTUSB_ATH3012 },
@@ -263,7 +264,6 @@ static const struct usb_device_id blacklist_table[] = {
{ USB_DEVICE(0x0489, 0xe03c), .driver_info = BTUSB_ATH3012 },
/* QCA ROME chipset */
- { USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_QCA_ROME },
{ USB_DEVICE(0x0cf3, 0xe007), .driver_info = BTUSB_QCA_ROME },
{ USB_DEVICE(0x0cf3, 0xe009), .driver_info = BTUSB_QCA_ROME },
{ USB_DEVICE(0x0cf3, 0xe010), .driver_info = BTUSB_QCA_ROME },
@@ -399,6 +399,13 @@ static const struct dmi_system_id btusb_needs_reset_resume_table[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 3060"),
},
},
+ {
+ /* Dell XPS 9360 (QCA ROME device 0cf3:e300) */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "XPS 13 9360"),
+ },
+ },
{}
};
@@ -2852,6 +2859,12 @@ static int btusb_config_oob_wake(struct hci_dev *hdev)
}
#endif
+static void btusb_check_needs_reset_resume(struct usb_interface *intf)
+{
+ if (dmi_check_system(btusb_needs_reset_resume_table))
+ interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME;
+}
+
static int btusb_probe(struct usb_interface *intf,
const struct usb_device_id *id)
{
@@ -2974,9 +2987,6 @@ static int btusb_probe(struct usb_interface *intf,
hdev->send = btusb_send_frame;
hdev->notify = btusb_notify;
- if (dmi_check_system(btusb_needs_reset_resume_table))
- interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME;
-
#ifdef CONFIG_PM
err = btusb_config_oob_wake(hdev);
if (err)
@@ -3064,6 +3074,7 @@ static int btusb_probe(struct usb_interface *intf,
data->setup_on_usb = btusb_setup_qca;
hdev->set_bdaddr = btusb_set_bdaddr_ath3012;
set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks);
+ btusb_check_needs_reset_resume(intf);
}
#ifdef CONFIG_BT_HCIBTUSB_RTL
diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig
index d1c0b60..6dc177b 100644
--- a/drivers/bus/Kconfig
+++ b/drivers/bus/Kconfig
@@ -33,6 +33,7 @@
bool "Support for ISA I/O space on HiSilicon Hip06/7"
depends on ARM64 && (ARCH_HISI || COMPILE_TEST)
select INDIRECT_PIO
+ select MFD_CORE if ACPI
help
Driver to enable I/O access to devices attached to the Low Pin
Count bus on the HiSilicon Hip06/7 SoC.
diff --git a/drivers/bus/fsl-mc/fsl-mc-msi.c b/drivers/bus/fsl-mc/fsl-mc-msi.c
index ec35e25..8b9c66d 100644
--- a/drivers/bus/fsl-mc/fsl-mc-msi.c
+++ b/drivers/bus/fsl-mc/fsl-mc-msi.c
@@ -163,6 +163,8 @@ struct irq_domain *fsl_mc_msi_create_irq_domain(struct fwnode_handle *fwnode,
{
struct irq_domain *domain;
+ if (WARN_ON((info->flags & MSI_FLAG_LEVEL_CAPABLE)))
+ info->flags &= ~MSI_FLAG_LEVEL_CAPABLE;
if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS)
fsl_mc_msi_update_dom_ops(info);
if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 8327478..9adc8c3 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -2192,7 +2192,7 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
len = nr * CD_FRAMESIZE_RAW;
- rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL);
+ rq = blk_get_request(q, REQ_OP_SCSI_IN, 0);
if (IS_ERR(rq)) {
ret = PTR_ERR(rq);
break;
@@ -2371,7 +2371,7 @@ static int cdrom_ioctl_media_changed(struct cdrom_device_info *cdi,
if (!CDROM_CAN(CDC_SELECT_DISC) || arg == CDSL_CURRENT)
return media_changed(cdi, 1);
- if ((unsigned int)arg >= cdi->capacity)
+ if (arg >= cdi->capacity)
return -EINVAL;
info = kmalloc(sizeof(*info), GFP_KERNEL);
diff --git a/drivers/char/agp/uninorth-agp.c b/drivers/char/agp/uninorth-agp.c
index c381c8e..79d8c84 100644
--- a/drivers/char/agp/uninorth-agp.c
+++ b/drivers/char/agp/uninorth-agp.c
@@ -195,7 +195,7 @@ static int uninorth_insert_memory(struct agp_memory *mem, off_t pg_start, int ty
return 0;
}
-int uninorth_remove_memory(struct agp_memory *mem, off_t pg_start, int type)
+static int uninorth_remove_memory(struct agp_memory *mem, off_t pg_start, int type)
{
size_t i;
u32 *gp;
@@ -470,7 +470,7 @@ static int uninorth_free_gatt_table(struct agp_bridge_data *bridge)
return 0;
}
-void null_cache_flush(void)
+static void null_cache_flush(void)
{
mb();
}
diff --git a/drivers/char/apm-emulation.c b/drivers/char/apm-emulation.c
index a5e2f9e..53436c0 100644
--- a/drivers/char/apm-emulation.c
+++ b/drivers/char/apm-emulation.c
@@ -461,19 +461,6 @@ static int proc_apm_show(struct seq_file *m, void *v)
return 0;
}
-
-static int proc_apm_open(struct inode *inode, struct file *file)
-{
- return single_open(file, proc_apm_show, NULL);
-}
-
-static const struct file_operations apm_proc_fops = {
- .owner = THIS_MODULE,
- .open = proc_apm_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif
static int kapmd(void *arg)
@@ -657,7 +644,7 @@ static int __init apm_init(void)
wake_up_process(kapmd_tsk);
#ifdef CONFIG_PROC_FS
- proc_create("apm", 0, NULL, &apm_proc_fops);
+ proc_create_single("apm", 0, NULL, proc_apm_show);
#endif
ret = misc_register(&apm_device);
diff --git a/drivers/char/ds1620.c b/drivers/char/ds1620.c
index eb53cba..a5ecf6d 100644
--- a/drivers/char/ds1620.c
+++ b/drivers/char/ds1620.c
@@ -345,18 +345,6 @@ static int ds1620_proc_therm_show(struct seq_file *m, void *v)
fan_state[netwinder_get_fan()]);
return 0;
}
-
-static int ds1620_proc_therm_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ds1620_proc_therm_show, NULL);
-}
-
-static const struct file_operations ds1620_proc_therm_fops = {
- .open = ds1620_proc_therm_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif
static const struct file_operations ds1620_fops = {
@@ -404,7 +392,7 @@ static int __init ds1620_init(void)
return ret;
#ifdef THERM_USE_PROC
- if (!proc_create("therm", 0, NULL, &ds1620_proc_therm_fops))
+ if (!proc_create_single("therm", 0, NULL, ds1620_proc_therm_show))
printk(KERN_ERR "therm: unable to register /proc/therm\n");
#endif
diff --git a/drivers/char/efirtc.c b/drivers/char/efirtc.c
index dc62568..d9aab64 100644
--- a/drivers/char/efirtc.c
+++ b/drivers/char/efirtc.c
@@ -358,19 +358,6 @@ static int efi_rtc_proc_show(struct seq_file *m, void *v)
return 0;
}
-
-static int efi_rtc_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, efi_rtc_proc_show, NULL);
-}
-
-static const struct file_operations efi_rtc_proc_fops = {
- .open = efi_rtc_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __init
efi_rtc_init(void)
{
@@ -386,7 +373,7 @@ efi_rtc_init(void)
return ret;
}
- dir = proc_create("driver/efirtc", 0, NULL, &efi_rtc_proc_fops);
+ dir = proc_create_single("driver/efirtc", 0, NULL, efi_rtc_proc_show);
if (dir == NULL) {
printk(KERN_ERR "efirtc: can't create /proc/driver/efirtc.\n");
misc_deregister(&efi_rtc_dev);
diff --git a/drivers/char/misc.c b/drivers/char/misc.c
index 1bb9e7c..53cfe57 100644
--- a/drivers/char/misc.c
+++ b/drivers/char/misc.c
@@ -95,19 +95,6 @@ static const struct seq_operations misc_seq_ops = {
.stop = misc_seq_stop,
.show = misc_seq_show,
};
-
-static int misc_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &misc_seq_ops);
-}
-
-static const struct file_operations misc_proc_fops = {
- .owner = THIS_MODULE,
- .open = misc_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
#endif
static int misc_open(struct inode *inode, struct file *file)
@@ -282,7 +269,7 @@ static int __init misc_init(void)
int err;
struct proc_dir_entry *ret;
- ret = proc_create("misc", 0, NULL, &misc_proc_fops);
+ ret = proc_create_seq("misc", 0, NULL, &misc_seq_ops);
misc_class = class_create(THIS_MODULE, "misc");
err = PTR_ERR(misc_class);
if (IS_ERR(misc_class))
diff --git a/drivers/char/nvram.c b/drivers/char/nvram.c
index 678fa97..25264d6 100644
--- a/drivers/char/nvram.c
+++ b/drivers/char/nvram.c
@@ -389,22 +389,9 @@ static int nvram_proc_read(struct seq_file *seq, void *offset)
return 0;
}
-static int nvram_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, nvram_proc_read, NULL);
-}
-
-static const struct file_operations nvram_proc_fops = {
- .owner = THIS_MODULE,
- .open = nvram_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int nvram_add_proc_fs(void)
{
- if (!proc_create("driver/nvram", 0, NULL, &nvram_proc_fops))
+ if (!proc_create_single("driver/nvram", 0, NULL, nvram_proc_read))
return -ENOMEM;
return 0;
}
diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c
index aa502e9..66b0419 100644
--- a/drivers/char/pcmcia/synclink_cs.c
+++ b/drivers/char/pcmcia/synclink_cs.c
@@ -2616,19 +2616,6 @@ static int mgslpc_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int mgslpc_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, mgslpc_proc_show, NULL);
-}
-
-static const struct file_operations mgslpc_proc_fops = {
- .owner = THIS_MODULE,
- .open = mgslpc_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int rx_alloc_buffers(MGSLPC_INFO *info)
{
/* each buffer has header and data */
@@ -2815,7 +2802,7 @@ static const struct tty_operations mgslpc_ops = {
.tiocmget = tiocmget,
.tiocmset = tiocmset,
.get_icount = mgslpc_get_icount,
- .proc_fops = &mgslpc_proc_fops,
+ .proc_show = mgslpc_proc_show,
};
static int __init synclink_cs_init(void)
diff --git a/drivers/char/random.c b/drivers/char/random.c
index e027e7f..a8fb002 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -261,6 +261,7 @@
#include <linux/ptrace.h>
#include <linux/workqueue.h>
#include <linux/irq.h>
+#include <linux/ratelimit.h>
#include <linux/syscalls.h>
#include <linux/completion.h>
#include <linux/uuid.h>
@@ -401,8 +402,7 @@ static struct poolinfo {
/*
* Static global variables
*/
-static DECLARE_WAIT_QUEUE_HEAD(random_read_wait);
-static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
+static DECLARE_WAIT_QUEUE_HEAD(random_wait);
static struct fasync_struct *fasync;
static DEFINE_SPINLOCK(random_ready_list_lock);
@@ -427,8 +427,9 @@ struct crng_state primary_crng = {
* its value (from 0->1->2).
*/
static int crng_init = 0;
-#define crng_ready() (likely(crng_init > 0))
+#define crng_ready() (likely(crng_init > 1))
static int crng_init_cnt = 0;
+static unsigned long crng_global_init_time = 0;
#define CRNG_INIT_CNT_THRESH (2*CHACHA20_KEY_SIZE)
static void _extract_crng(struct crng_state *crng,
__u32 out[CHACHA20_BLOCK_WORDS]);
@@ -437,6 +438,16 @@ static void _crng_backtrack_protect(struct crng_state *crng,
static void process_random_ready_list(void);
static void _get_random_bytes(void *buf, int nbytes);
+static struct ratelimit_state unseeded_warning =
+ RATELIMIT_STATE_INIT("warn_unseeded_randomness", HZ, 3);
+static struct ratelimit_state urandom_warning =
+ RATELIMIT_STATE_INIT("warn_urandom_randomness", HZ, 3);
+
+static int ratelimit_disable __read_mostly;
+
+module_param_named(ratelimit_disable, ratelimit_disable, int, 0644);
+MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression");
+
/**********************************************************************
*
* OS independent entropy store. Here are the functions which handle
@@ -710,8 +721,8 @@ static void credit_entropy_bits(struct entropy_store *r, int nbits)
/* should we wake readers? */
if (entropy_bits >= random_read_wakeup_bits &&
- wq_has_sleeper(&random_read_wait)) {
- wake_up_interruptible(&random_read_wait);
+ wq_has_sleeper(&random_wait)) {
+ wake_up_interruptible_poll(&random_wait, POLLIN);
kill_fasync(&fasync, SIGIO, POLL_IN);
}
/* If the input pool is getting full, send some
@@ -787,6 +798,43 @@ static void crng_initialize(struct crng_state *crng)
crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1;
}
+#ifdef CONFIG_NUMA
+static void do_numa_crng_init(struct work_struct *work)
+{
+ int i;
+ struct crng_state *crng;
+ struct crng_state **pool;
+
+ pool = kcalloc(nr_node_ids, sizeof(*pool), GFP_KERNEL|__GFP_NOFAIL);
+ for_each_online_node(i) {
+ crng = kmalloc_node(sizeof(struct crng_state),
+ GFP_KERNEL | __GFP_NOFAIL, i);
+ spin_lock_init(&crng->lock);
+ crng_initialize(crng);
+ pool[i] = crng;
+ }
+ mb();
+ if (cmpxchg(&crng_node_pool, NULL, pool)) {
+ for_each_node(i)
+ kfree(pool[i]);
+ kfree(pool);
+ }
+}
+
+static DECLARE_WORK(numa_crng_init_work, do_numa_crng_init);
+
+static void numa_crng_init(void)
+{
+ schedule_work(&numa_crng_init_work);
+}
+#else
+static void numa_crng_init(void) {}
+#endif
+
+/*
+ * crng_fast_load() can be called by code in the interrupt service
+ * path. So we can't afford to dilly-dally.
+ */
static int crng_fast_load(const char *cp, size_t len)
{
unsigned long flags;
@@ -794,7 +842,7 @@ static int crng_fast_load(const char *cp, size_t len)
if (!spin_trylock_irqsave(&primary_crng.lock, flags))
return 0;
- if (crng_ready()) {
+ if (crng_init != 0) {
spin_unlock_irqrestore(&primary_crng.lock, flags);
return 0;
}
@@ -813,6 +861,51 @@ static int crng_fast_load(const char *cp, size_t len)
return 1;
}
+/*
+ * crng_slow_load() is called by add_device_randomness, which has two
+ * attributes. (1) We can't trust the buffer passed to it is
+ * guaranteed to be unpredictable (so it might not have any entropy at
+ * all), and (2) it doesn't have the performance constraints of
+ * crng_fast_load().
+ *
+ * So we do something more comprehensive which is guaranteed to touch
+ * all of the primary_crng's state, and which uses a LFSR with a
+ * period of 255 as part of the mixing algorithm. Finally, we do
+ * *not* advance crng_init_cnt since buffer we may get may be something
+ * like a fixed DMI table (for example), which might very well be
+ * unique to the machine, but is otherwise unvarying.
+ */
+static int crng_slow_load(const char *cp, size_t len)
+{
+ unsigned long flags;
+ static unsigned char lfsr = 1;
+ unsigned char tmp;
+ unsigned i, max = CHACHA20_KEY_SIZE;
+ const char * src_buf = cp;
+ char * dest_buf = (char *) &primary_crng.state[4];
+
+ if (!spin_trylock_irqsave(&primary_crng.lock, flags))
+ return 0;
+ if (crng_init != 0) {
+ spin_unlock_irqrestore(&primary_crng.lock, flags);
+ return 0;
+ }
+ if (len > max)
+ max = len;
+
+ for (i = 0; i < max ; i++) {
+ tmp = lfsr;
+ lfsr >>= 1;
+ if (tmp & 1)
+ lfsr ^= 0xE1;
+ tmp = dest_buf[i % CHACHA20_KEY_SIZE];
+ dest_buf[i % CHACHA20_KEY_SIZE] ^= src_buf[i % len] ^ lfsr;
+ lfsr += (tmp << 3) | (tmp >> 5);
+ }
+ spin_unlock_irqrestore(&primary_crng.lock, flags);
+ return 1;
+}
+
static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
{
unsigned long flags;
@@ -831,7 +924,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
_crng_backtrack_protect(&primary_crng, buf.block,
CHACHA20_KEY_SIZE);
}
- spin_lock_irqsave(&primary_crng.lock, flags);
+ spin_lock_irqsave(&crng->lock, flags);
for (i = 0; i < 8; i++) {
unsigned long rv;
if (!arch_get_random_seed_long(&rv) &&
@@ -841,13 +934,26 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
}
memzero_explicit(&buf, sizeof(buf));
crng->init_time = jiffies;
- spin_unlock_irqrestore(&primary_crng.lock, flags);
+ spin_unlock_irqrestore(&crng->lock, flags);
if (crng == &primary_crng && crng_init < 2) {
invalidate_batched_entropy();
+ numa_crng_init();
crng_init = 2;
process_random_ready_list();
wake_up_interruptible(&crng_init_wait);
pr_notice("random: crng init done\n");
+ if (unseeded_warning.missed) {
+ pr_notice("random: %d get_random_xx warning(s) missed "
+ "due to ratelimiting\n",
+ unseeded_warning.missed);
+ unseeded_warning.missed = 0;
+ }
+ if (urandom_warning.missed) {
+ pr_notice("random: %d urandom warning(s) missed "
+ "due to ratelimiting\n",
+ urandom_warning.missed);
+ urandom_warning.missed = 0;
+ }
}
}
@@ -856,8 +962,9 @@ static void _extract_crng(struct crng_state *crng,
{
unsigned long v, flags;
- if (crng_init > 1 &&
- time_after(jiffies, crng->init_time + CRNG_RESEED_INTERVAL))
+ if (crng_ready() &&
+ (time_after(crng_global_init_time, crng->init_time) ||
+ time_after(jiffies, crng->init_time + CRNG_RESEED_INTERVAL)))
crng_reseed(crng, crng == &primary_crng ? &input_pool : NULL);
spin_lock_irqsave(&crng->lock, flags);
if (arch_get_random_long(&v))
@@ -981,10 +1088,8 @@ void add_device_randomness(const void *buf, unsigned int size)
unsigned long time = random_get_entropy() ^ jiffies;
unsigned long flags;
- if (!crng_ready()) {
- crng_fast_load(buf, size);
- return;
- }
+ if (!crng_ready() && size)
+ crng_slow_load(buf, size);
trace_add_device_randomness(size, _RET_IP_);
spin_lock_irqsave(&input_pool.lock, flags);
@@ -1139,7 +1244,7 @@ void add_interrupt_randomness(int irq, int irq_flags)
fast_mix(fast_pool);
add_interrupt_bench(cycles);
- if (!crng_ready()) {
+ if (unlikely(crng_init == 0)) {
if ((fast_pool->count >= 64) &&
crng_fast_load((char *) fast_pool->pool,
sizeof(fast_pool->pool))) {
@@ -1291,7 +1396,7 @@ static size_t account(struct entropy_store *r, size_t nbytes, int min,
trace_debit_entropy(r->name, 8 * ibytes);
if (ibytes &&
(r->entropy_count >> ENTROPY_SHIFT) < random_write_wakeup_bits) {
- wake_up_interruptible(&random_write_wait);
+ wake_up_interruptible_poll(&random_wait, POLLOUT);
kill_fasync(&fasync, SIGIO, POLL_OUT);
}
@@ -1489,8 +1594,9 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller,
#ifndef CONFIG_WARN_ALL_UNSEEDED_RANDOM
print_once = true;
#endif
- pr_notice("random: %s called from %pS with crng_init=%d\n",
- func_name, caller, crng_init);
+ if (__ratelimit(&unseeded_warning))
+ pr_notice("random: %s called from %pS with crng_init=%d\n",
+ func_name, caller, crng_init);
}
/*
@@ -1680,28 +1786,14 @@ static void init_std_data(struct entropy_store *r)
*/
static int rand_initialize(void)
{
-#ifdef CONFIG_NUMA
- int i;
- struct crng_state *crng;
- struct crng_state **pool;
-#endif
-
init_std_data(&input_pool);
init_std_data(&blocking_pool);
crng_initialize(&primary_crng);
-
-#ifdef CONFIG_NUMA
- pool = kcalloc(nr_node_ids, sizeof(*pool), GFP_KERNEL|__GFP_NOFAIL);
- for_each_online_node(i) {
- crng = kmalloc_node(sizeof(struct crng_state),
- GFP_KERNEL | __GFP_NOFAIL, i);
- spin_lock_init(&crng->lock);
- crng_initialize(crng);
- pool[i] = crng;
+ crng_global_init_time = jiffies;
+ if (ratelimit_disable) {
+ urandom_warning.interval = 0;
+ unseeded_warning.interval = 0;
}
- mb();
- crng_node_pool = pool;
-#endif
return 0;
}
early_initcall(rand_initialize);
@@ -1746,7 +1838,7 @@ _random_read(int nonblock, char __user *buf, size_t nbytes)
if (nonblock)
return -EAGAIN;
- wait_event_interruptible(random_read_wait,
+ wait_event_interruptible(random_wait,
ENTROPY_BITS(&input_pool) >=
random_read_wakeup_bits);
if (signal_pending(current))
@@ -1769,9 +1861,10 @@ urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
if (!crng_ready() && maxwarn > 0) {
maxwarn--;
- printk(KERN_NOTICE "random: %s: uninitialized urandom read "
- "(%zd bytes read)\n",
- current->comm, nbytes);
+ if (__ratelimit(&urandom_warning))
+ printk(KERN_NOTICE "random: %s: uninitialized "
+ "urandom read (%zd bytes read)\n",
+ current->comm, nbytes);
spin_lock_irqsave(&primary_crng.lock, flags);
crng_init_cnt = 0;
spin_unlock_irqrestore(&primary_crng.lock, flags);
@@ -1782,14 +1875,17 @@ urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
return ret;
}
-static __poll_t
-random_poll(struct file *file, poll_table * wait)
+static struct wait_queue_head *
+random_get_poll_head(struct file *file, __poll_t events)
{
- __poll_t mask;
+ return &random_wait;
+}
- poll_wait(file, &random_read_wait, wait);
- poll_wait(file, &random_write_wait, wait);
- mask = 0;
+static __poll_t
+random_poll_mask(struct file *file, __poll_t events)
+{
+ __poll_t mask = 0;
+
if (ENTROPY_BITS(&input_pool) >= random_read_wakeup_bits)
mask |= EPOLLIN | EPOLLRDNORM;
if (ENTROPY_BITS(&input_pool) < random_write_wakeup_bits)
@@ -1875,6 +1971,14 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
input_pool.entropy_count = 0;
blocking_pool.entropy_count = 0;
return 0;
+ case RNDRESEEDCRNG:
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ if (crng_init < 2)
+ return -ENODATA;
+ crng_reseed(&primary_crng, NULL);
+ crng_global_init_time = jiffies - 1;
+ return 0;
default:
return -EINVAL;
}
@@ -1888,7 +1992,8 @@ static int random_fasync(int fd, struct file *filp, int on)
const struct file_operations random_fops = {
.read = random_read,
.write = random_write,
- .poll = random_poll,
+ .get_poll_head = random_get_poll_head,
+ .poll_mask = random_poll_mask,
.unlocked_ioctl = random_ioctl,
.fasync = random_fasync,
.llseek = noop_llseek,
@@ -2212,7 +2317,7 @@ void add_hwgenerator_randomness(const char *buffer, size_t count,
{
struct entropy_store *poolp = &input_pool;
- if (!crng_ready()) {
+ if (unlikely(crng_init == 0)) {
crng_fast_load(buffer, count);
return;
}
@@ -2221,7 +2326,7 @@ void add_hwgenerator_randomness(const char *buffer, size_t count,
* We'll be woken up again once below random_write_wakeup_thresh,
* or when the calling thread is about to terminate.
*/
- wait_event_interruptible(random_write_wait, kthread_should_stop() ||
+ wait_event_interruptible(random_wait, kthread_should_stop() ||
ENTROPY_BITS(&input_pool) <= random_write_wakeup_bits);
mix_pool_bytes(poolp, buffer, count);
credit_entropy_bits(poolp, entropy);
diff --git a/drivers/char/rtc.c b/drivers/char/rtc.c
index 57dc546..94fedee 100644
--- a/drivers/char/rtc.c
+++ b/drivers/char/rtc.c
@@ -171,7 +171,7 @@ static void mask_rtc_irq_bit(unsigned char bit)
#endif
#ifdef CONFIG_PROC_FS
-static int rtc_proc_open(struct inode *inode, struct file *file);
+static int rtc_proc_show(struct seq_file *seq, void *v);
#endif
/*
@@ -832,16 +832,6 @@ static struct miscdevice rtc_dev = {
.fops = &rtc_fops,
};
-#ifdef CONFIG_PROC_FS
-static const struct file_operations rtc_proc_fops = {
- .owner = THIS_MODULE,
- .open = rtc_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-#endif
-
static resource_size_t rtc_size;
static struct resource * __init rtc_request_region(resource_size_t size)
@@ -982,7 +972,7 @@ static int __init rtc_init(void)
}
#ifdef CONFIG_PROC_FS
- ent = proc_create("driver/rtc", 0, NULL, &rtc_proc_fops);
+ ent = proc_create_single("driver/rtc", 0, NULL, rtc_proc_show);
if (!ent)
printk(KERN_WARNING "rtc: Failed to register with procfs.\n");
#endif
@@ -1201,11 +1191,6 @@ static int rtc_proc_show(struct seq_file *seq, void *v)
#undef YN
#undef NY
}
-
-static int rtc_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, rtc_proc_show, NULL);
-}
#endif
static void rtc_get_rtc_time(struct rtc_time *rtc_tm)
diff --git a/drivers/char/toshiba.c b/drivers/char/toshiba.c
index 5488516..802376f 100644
--- a/drivers/char/toshiba.c
+++ b/drivers/char/toshiba.c
@@ -326,19 +326,6 @@ static int proc_toshiba_show(struct seq_file *m, void *v)
key);
return 0;
}
-
-static int proc_toshiba_open(struct inode *inode, struct file *file)
-{
- return single_open(file, proc_toshiba_show, NULL);
-}
-
-static const struct file_operations proc_toshiba_fops = {
- .owner = THIS_MODULE,
- .open = proc_toshiba_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif
@@ -524,7 +511,7 @@ static int __init toshiba_init(void)
{
struct proc_dir_entry *pde;
- pde = proc_create("toshiba", 0, NULL, &proc_toshiba_fops);
+ pde = proc_create_single("toshiba", 0, NULL, proc_toshiba_show);
if (!pde) {
misc_deregister(&tosh_device);
return -ENOMEM;
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 468f061..2108551 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -422,7 +422,7 @@ static void reclaim_dma_bufs(void)
}
}
-static struct port_buffer *alloc_buf(struct virtqueue *vq, size_t buf_size,
+static struct port_buffer *alloc_buf(struct virtio_device *vdev, size_t buf_size,
int pages)
{
struct port_buffer *buf;
@@ -445,16 +445,16 @@ static struct port_buffer *alloc_buf(struct virtqueue *vq, size_t buf_size,
return buf;
}
- if (is_rproc_serial(vq->vdev)) {
+ if (is_rproc_serial(vdev)) {
/*
* Allocate DMA memory from ancestor. When a virtio
* device is created by remoteproc, the DMA memory is
* associated with the grandparent device:
* vdev => rproc => platform-dev.
*/
- if (!vq->vdev->dev.parent || !vq->vdev->dev.parent->parent)
+ if (!vdev->dev.parent || !vdev->dev.parent->parent)
goto free_buf;
- buf->dev = vq->vdev->dev.parent->parent;
+ buf->dev = vdev->dev.parent->parent;
/* Increase device refcnt to avoid freeing it */
get_device(buf->dev);
@@ -838,7 +838,7 @@ static ssize_t port_fops_write(struct file *filp, const char __user *ubuf,
count = min((size_t)(32 * 1024), count);
- buf = alloc_buf(port->out_vq, count, 0);
+ buf = alloc_buf(port->portdev->vdev, count, 0);
if (!buf)
return -ENOMEM;
@@ -957,7 +957,7 @@ static ssize_t port_fops_splice_write(struct pipe_inode_info *pipe,
if (ret < 0)
goto error_out;
- buf = alloc_buf(port->out_vq, 0, pipe->nrbufs);
+ buf = alloc_buf(port->portdev->vdev, 0, pipe->nrbufs);
if (!buf) {
ret = -ENOMEM;
goto error_out;
@@ -1374,7 +1374,7 @@ static unsigned int fill_queue(struct virtqueue *vq, spinlock_t *lock)
nr_added_bufs = 0;
do {
- buf = alloc_buf(vq, PAGE_SIZE, 0);
+ buf = alloc_buf(vq->vdev, PAGE_SIZE, 0);
if (!buf)
break;
@@ -1402,7 +1402,6 @@ static int add_port(struct ports_device *portdev, u32 id)
{
char debugfs_name[16];
struct port *port;
- struct port_buffer *buf;
dev_t devt;
unsigned int nr_added_bufs;
int err;
@@ -1513,8 +1512,6 @@ static int add_port(struct ports_device *portdev, u32 id)
return 0;
free_inbufs:
- while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
- free_buf(buf, true);
free_device:
device_destroy(pdrvdata.class, port->dev->devt);
free_cdev:
@@ -1539,34 +1536,14 @@ static void remove_port(struct kref *kref)
static void remove_port_data(struct port *port)
{
- struct port_buffer *buf;
-
spin_lock_irq(&port->inbuf_lock);
/* Remove unused data this port might have received. */
discard_port_data(port);
spin_unlock_irq(&port->inbuf_lock);
- /* Remove buffers we queued up for the Host to send us data in. */
- do {
- spin_lock_irq(&port->inbuf_lock);
- buf = virtqueue_detach_unused_buf(port->in_vq);
- spin_unlock_irq(&port->inbuf_lock);
- if (buf)
- free_buf(buf, true);
- } while (buf);
-
spin_lock_irq(&port->outvq_lock);
reclaim_consumed_buffers(port);
spin_unlock_irq(&port->outvq_lock);
-
- /* Free pending buffers from the out-queue. */
- do {
- spin_lock_irq(&port->outvq_lock);
- buf = virtqueue_detach_unused_buf(port->out_vq);
- spin_unlock_irq(&port->outvq_lock);
- if (buf)
- free_buf(buf, true);
- } while (buf);
}
/*
@@ -1791,13 +1768,24 @@ static void control_work_handler(struct work_struct *work)
spin_unlock(&portdev->c_ivq_lock);
}
+static void flush_bufs(struct virtqueue *vq, bool can_sleep)
+{
+ struct port_buffer *buf;
+ unsigned int len;
+
+ while ((buf = virtqueue_get_buf(vq, &len)))
+ free_buf(buf, can_sleep);
+}
+
static void out_intr(struct virtqueue *vq)
{
struct port *port;
port = find_port_by_vq(vq->vdev->priv, vq);
- if (!port)
+ if (!port) {
+ flush_bufs(vq, false);
return;
+ }
wake_up_interruptible(&port->waitqueue);
}
@@ -1808,8 +1796,10 @@ static void in_intr(struct virtqueue *vq)
unsigned long flags;
port = find_port_by_vq(vq->vdev->priv, vq);
- if (!port)
+ if (!port) {
+ flush_bufs(vq, false);
return;
+ }
spin_lock_irqsave(&port->inbuf_lock, flags);
port->inbuf = get_inbuf(port);
@@ -1984,24 +1974,54 @@ static const struct file_operations portdev_fops = {
static void remove_vqs(struct ports_device *portdev)
{
+ struct virtqueue *vq;
+
+ virtio_device_for_each_vq(portdev->vdev, vq) {
+ struct port_buffer *buf;
+
+ flush_bufs(vq, true);
+ while ((buf = virtqueue_detach_unused_buf(vq)))
+ free_buf(buf, true);
+ }
portdev->vdev->config->del_vqs(portdev->vdev);
kfree(portdev->in_vqs);
kfree(portdev->out_vqs);
}
-static void remove_controlq_data(struct ports_device *portdev)
+static void virtcons_remove(struct virtio_device *vdev)
{
- struct port_buffer *buf;
- unsigned int len;
+ struct ports_device *portdev;
+ struct port *port, *port2;
- if (!use_multiport(portdev))
- return;
+ portdev = vdev->priv;
- while ((buf = virtqueue_get_buf(portdev->c_ivq, &len)))
- free_buf(buf, true);
+ spin_lock_irq(&pdrvdata_lock);
+ list_del(&portdev->list);
+ spin_unlock_irq(&pdrvdata_lock);
- while ((buf = virtqueue_detach_unused_buf(portdev->c_ivq)))
- free_buf(buf, true);
+ /* Disable interrupts for vqs */
+ vdev->config->reset(vdev);
+ /* Finish up work that's lined up */
+ if (use_multiport(portdev))
+ cancel_work_sync(&portdev->control_work);
+ else
+ cancel_work_sync(&portdev->config_work);
+
+ list_for_each_entry_safe(port, port2, &portdev->ports, list)
+ unplug_port(port);
+
+ unregister_chrdev(portdev->chr_major, "virtio-portsdev");
+
+ /*
+ * When yanking out a device, we immediately lose the
+ * (device-side) queues. So there's no point in keeping the
+ * guest side around till we drop our final reference. This
+ * also means that any ports which are in an open state will
+ * have to just stop using the port, as the vqs are going
+ * away.
+ */
+ remove_vqs(portdev);
+ kfree(portdev);
}
/*
@@ -2070,6 +2090,7 @@ static int virtcons_probe(struct virtio_device *vdev)
spin_lock_init(&portdev->ports_lock);
INIT_LIST_HEAD(&portdev->ports);
+ INIT_LIST_HEAD(&portdev->list);
virtio_device_ready(portdev->vdev);
@@ -2087,8 +2108,15 @@ static int virtcons_probe(struct virtio_device *vdev)
if (!nr_added_bufs) {
dev_err(&vdev->dev,
"Error allocating buffers for control queue\n");
- err = -ENOMEM;
- goto free_vqs;
+ /*
+ * The host might want to notify mgmt sw about device
+ * add failure.
+ */
+ __send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
+ VIRTIO_CONSOLE_DEVICE_READY, 0);
+ /* Device was functional: we need full cleanup. */
+ virtcons_remove(vdev);
+ return -ENOMEM;
}
} else {
/*
@@ -2119,11 +2147,6 @@ static int virtcons_probe(struct virtio_device *vdev)
return 0;
-free_vqs:
- /* The host might want to notify mgmt sw about device add failure */
- __send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
- VIRTIO_CONSOLE_DEVICE_READY, 0);
- remove_vqs(portdev);
free_chrdev:
unregister_chrdev(portdev->chr_major, "virtio-portsdev");
free:
@@ -2132,43 +2155,6 @@ static int virtcons_probe(struct virtio_device *vdev)
return err;
}
-static void virtcons_remove(struct virtio_device *vdev)
-{
- struct ports_device *portdev;
- struct port *port, *port2;
-
- portdev = vdev->priv;
-
- spin_lock_irq(&pdrvdata_lock);
- list_del(&portdev->list);
- spin_unlock_irq(&pdrvdata_lock);
-
- /* Disable interrupts for vqs */
- vdev->config->reset(vdev);
- /* Finish up work that's lined up */
- if (use_multiport(portdev))
- cancel_work_sync(&portdev->control_work);
- else
- cancel_work_sync(&portdev->config_work);
-
- list_for_each_entry_safe(port, port2, &portdev->ports, list)
- unplug_port(port);
-
- unregister_chrdev(portdev->chr_major, "virtio-portsdev");
-
- /*
- * When yanking out a device, we immediately lose the
- * (device-side) queues. So there's no point in keeping the
- * guest side around till we drop our final reference. This
- * also means that any ports which are in an open state will
- * have to just stop using the port, as the vqs are going
- * away.
- */
- remove_controlq_data(portdev);
- remove_vqs(portdev);
- kfree(portdev);
-}
-
static struct virtio_device_id id_table[] = {
{ VIRTIO_ID_CONSOLE, VIRTIO_DEV_ANY_ID },
{ 0 },
@@ -2209,7 +2195,6 @@ static int virtcons_freeze(struct virtio_device *vdev)
*/
if (use_multiport(portdev))
virtqueue_disable_cb(portdev->c_ivq);
- remove_controlq_data(portdev);
list_for_each_entry(port, &portdev->ports, list) {
virtqueue_disable_cb(port->in_vq);
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 41492e9..34968a3 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -266,15 +266,13 @@
Support for stm32mp157 SoC family clocks
config COMMON_CLK_STM32F
- bool "Clock driver for stm32f4 and stm32f7 SoC families"
- depends on MACH_STM32F429 || MACH_STM32F469 || MACH_STM32F746
+ def_bool COMMON_CLK && (MACH_STM32F429 || MACH_STM32F469 || MACH_STM32F746)
help
---help---
Support for stm32f4 and stm32f7 SoC families clocks
config COMMON_CLK_STM32H7
- bool "Clock driver for stm32h7 SoC family"
- depends on MACH_STM32H743
+ def_bool COMMON_CLK && MACH_STM32H743
help
---help---
Support for stm32h7 SoC family clocks
diff --git a/drivers/clk/clk-cs2000-cp.c b/drivers/clk/clk-cs2000-cp.c
index c580197..a2f8c42 100644
--- a/drivers/clk/clk-cs2000-cp.c
+++ b/drivers/clk/clk-cs2000-cp.c
@@ -541,7 +541,7 @@ static int cs2000_probe(struct i2c_client *client,
return ret;
}
-static int cs2000_resume(struct device *dev)
+static int __maybe_unused cs2000_resume(struct device *dev)
{
struct cs2000_priv *priv = dev_get_drvdata(dev);
diff --git a/drivers/clk/clk-mux.c b/drivers/clk/clk-mux.c
index ac4a042..1628b93 100644
--- a/drivers/clk/clk-mux.c
+++ b/drivers/clk/clk-mux.c
@@ -112,10 +112,18 @@ static int clk_mux_set_parent(struct clk_hw *hw, u8 index)
return 0;
}
+static int clk_mux_determine_rate(struct clk_hw *hw,
+ struct clk_rate_request *req)
+{
+ struct clk_mux *mux = to_clk_mux(hw);
+
+ return clk_mux_determine_rate_flags(hw, req, mux->flags);
+}
+
const struct clk_ops clk_mux_ops = {
.get_parent = clk_mux_get_parent,
.set_parent = clk_mux_set_parent,
- .determine_rate = __clk_mux_determine_rate,
+ .determine_rate = clk_mux_determine_rate,
};
EXPORT_SYMBOL_GPL(clk_mux_ops);
diff --git a/drivers/clk/clk-stm32mp1.c b/drivers/clk/clk-stm32mp1.c
index f1d5967..edd3cf4 100644
--- a/drivers/clk/clk-stm32mp1.c
+++ b/drivers/clk/clk-stm32mp1.c
@@ -216,7 +216,7 @@ static const char * const usart1_src[] = {
"pclk5", "pll3_q", "ck_hsi", "ck_csi", "pll4_q", "ck_hse"
};
-const char * const usart234578_src[] = {
+static const char * const usart234578_src[] = {
"pclk1", "pll4_q", "ck_hsi", "ck_csi", "ck_hse"
};
@@ -224,10 +224,6 @@ static const char * const usart6_src[] = {
"pclk2", "pll4_q", "ck_hsi", "ck_csi", "ck_hse"
};
-static const char * const dfsdm_src[] = {
- "pclk2", "ck_mcu"
-};
-
static const char * const fdcan_src[] = {
"ck_hse", "pll3_q", "pll4_q"
};
@@ -316,10 +312,8 @@ struct stm32_clk_mgate {
struct clock_config {
u32 id;
const char *name;
- union {
- const char *parent_name;
- const char * const *parent_names;
- };
+ const char *parent_name;
+ const char * const *parent_names;
int num_parents;
unsigned long flags;
void *cfg;
@@ -469,7 +463,7 @@ static void mp1_gate_clk_disable(struct clk_hw *hw)
}
}
-const struct clk_ops mp1_gate_clk_ops = {
+static const struct clk_ops mp1_gate_clk_ops = {
.enable = mp1_gate_clk_enable,
.disable = mp1_gate_clk_disable,
.is_enabled = clk_gate_is_enabled,
@@ -698,7 +692,7 @@ static void mp1_mgate_clk_disable(struct clk_hw *hw)
mp1_gate_clk_disable(hw);
}
-const struct clk_ops mp1_mgate_clk_ops = {
+static const struct clk_ops mp1_mgate_clk_ops = {
.enable = mp1_mgate_clk_enable,
.disable = mp1_mgate_clk_disable,
.is_enabled = clk_gate_is_enabled,
@@ -732,7 +726,7 @@ static int clk_mmux_set_parent(struct clk_hw *hw, u8 index)
return 0;
}
-const struct clk_ops clk_mmux_ops = {
+static const struct clk_ops clk_mmux_ops = {
.get_parent = clk_mmux_get_parent,
.set_parent = clk_mmux_set_parent,
.determine_rate = __clk_mux_determine_rate,
@@ -1048,10 +1042,10 @@ struct stm32_pll_cfg {
u32 offset;
};
-struct clk_hw *_clk_register_pll(struct device *dev,
- struct clk_hw_onecell_data *clk_data,
- void __iomem *base, spinlock_t *lock,
- const struct clock_config *cfg)
+static struct clk_hw *_clk_register_pll(struct device *dev,
+ struct clk_hw_onecell_data *clk_data,
+ void __iomem *base, spinlock_t *lock,
+ const struct clock_config *cfg)
{
struct stm32_pll_cfg *stm_pll_cfg = cfg->cfg;
@@ -1405,7 +1399,8 @@ enum {
G_USBH,
G_ETHSTP,
G_RTCAPB,
- G_TZC,
+ G_TZC1,
+ G_TZC2,
G_TZPC,
G_IWDG1,
G_BSEC,
@@ -1417,7 +1412,7 @@ enum {
G_LAST
};
-struct stm32_mgate mp1_mgate[G_LAST];
+static struct stm32_mgate mp1_mgate[G_LAST];
#define _K_GATE(_id, _gate_offset, _gate_bit_idx, _gate_flags,\
_mgate, _ops)\
@@ -1440,7 +1435,7 @@ struct stm32_mgate mp1_mgate[G_LAST];
&mp1_mgate[_id], &mp1_mgate_clk_ops)
/* Peripheral gates */
-struct stm32_gate_cfg per_gate_cfg[G_LAST] = {
+static struct stm32_gate_cfg per_gate_cfg[G_LAST] = {
/* Multi gates */
K_GATE(G_MDIO, RCC_APB1ENSETR, 31, 0),
K_MGATE(G_DAC12, RCC_APB1ENSETR, 29, 0),
@@ -1506,7 +1501,8 @@ struct stm32_gate_cfg per_gate_cfg[G_LAST] = {
K_GATE(G_BSEC, RCC_APB5ENSETR, 16, 0),
K_GATE(G_IWDG1, RCC_APB5ENSETR, 15, 0),
K_GATE(G_TZPC, RCC_APB5ENSETR, 13, 0),
- K_GATE(G_TZC, RCC_APB5ENSETR, 12, 0),
+ K_GATE(G_TZC2, RCC_APB5ENSETR, 12, 0),
+ K_GATE(G_TZC1, RCC_APB5ENSETR, 11, 0),
K_GATE(G_RTCAPB, RCC_APB5ENSETR, 8, 0),
K_MGATE(G_USART1, RCC_APB5ENSETR, 4, 0),
K_MGATE(G_I2C6, RCC_APB5ENSETR, 3, 0),
@@ -1600,7 +1596,7 @@ enum {
M_LAST
};
-struct stm32_mmux ker_mux[M_LAST];
+static struct stm32_mmux ker_mux[M_LAST];
#define _K_MUX(_id, _offset, _shift, _width, _mux_flags, _mmux, _ops)\
[_id] = {\
@@ -1623,7 +1619,7 @@ struct stm32_mmux ker_mux[M_LAST];
_K_MUX(_id, _offset, _shift, _width, _mux_flags,\
&ker_mux[_id], &clk_mmux_ops)
-const struct stm32_mux_cfg ker_mux_cfg[M_LAST] = {
+static const struct stm32_mux_cfg ker_mux_cfg[M_LAST] = {
/* Kernel multi mux */
K_MMUX(M_SDMMC12, RCC_SDMMC12CKSELR, 0, 3, 0),
K_MMUX(M_SPI23, RCC_SPI2S23CKSELR, 0, 3, 0),
@@ -1860,7 +1856,8 @@ static const struct clock_config stm32mp1_clock_cfg[] = {
PCLK(USART1, "usart1", "pclk5", 0, G_USART1),
PCLK(RTCAPB, "rtcapb", "pclk5", CLK_IGNORE_UNUSED |
CLK_IS_CRITICAL, G_RTCAPB),
- PCLK(TZC, "tzc", "pclk5", CLK_IGNORE_UNUSED, G_TZC),
+ PCLK(TZC1, "tzc1", "ck_axi", CLK_IGNORE_UNUSED, G_TZC1),
+ PCLK(TZC2, "tzc2", "ck_axi", CLK_IGNORE_UNUSED, G_TZC2),
PCLK(TZPC, "tzpc", "pclk5", CLK_IGNORE_UNUSED, G_TZPC),
PCLK(IWDG1, "iwdg1", "pclk5", 0, G_IWDG1),
PCLK(BSEC, "bsec", "pclk5", CLK_IGNORE_UNUSED, G_BSEC),
@@ -1916,8 +1913,7 @@ static const struct clock_config stm32mp1_clock_cfg[] = {
KCLK(RNG1_K, "rng1_k", rng_src, 0, G_RNG1, M_RNG1),
KCLK(RNG2_K, "rng2_k", rng_src, 0, G_RNG2, M_RNG2),
KCLK(USBPHY_K, "usbphy_k", usbphy_src, 0, G_USBPHY, M_USBPHY),
- KCLK(STGEN_K, "stgen_k", stgen_src, CLK_IGNORE_UNUSED,
- G_STGEN, M_STGEN),
+ KCLK(STGEN_K, "stgen_k", stgen_src, CLK_IS_CRITICAL, G_STGEN, M_STGEN),
KCLK(SPDIF_K, "spdif_k", spdif_src, 0, G_SPDIF, M_SPDIF),
KCLK(SPI1_K, "spi1_k", spi123_src, 0, G_SPI1, M_SPI1),
KCLK(SPI2_K, "spi2_k", spi123_src, 0, G_SPI2, M_SPI23),
@@ -1948,8 +1944,8 @@ static const struct clock_config stm32mp1_clock_cfg[] = {
KCLK(FDCAN_K, "fdcan_k", fdcan_src, 0, G_FDCAN, M_FDCAN),
KCLK(SAI1_K, "sai1_k", sai_src, 0, G_SAI1, M_SAI1),
KCLK(SAI2_K, "sai2_k", sai2_src, 0, G_SAI2, M_SAI2),
- KCLK(SAI3_K, "sai3_k", sai_src, 0, G_SAI2, M_SAI3),
- KCLK(SAI4_K, "sai4_k", sai_src, 0, G_SAI2, M_SAI4),
+ KCLK(SAI3_K, "sai3_k", sai_src, 0, G_SAI3, M_SAI3),
+ KCLK(SAI4_K, "sai4_k", sai_src, 0, G_SAI4, M_SAI4),
KCLK(ADC12_K, "adc12_k", adc12_src, 0, G_ADC12, M_ADC12),
KCLK(DSI_K, "dsi_k", dsi_src, 0, G_DSI, M_DSI),
KCLK(ADFSDM_K, "adfsdm_k", sai_src, 0, G_ADFSDM, M_SAI1),
@@ -1992,10 +1988,6 @@ static const struct clock_config stm32mp1_clock_cfg[] = {
_DIV(RCC_MCO2CFGR, 4, 4, 0, NULL)),
/* Debug clocks */
- FIXED_FACTOR(NO_ID, "ck_axi_div2", "ck_axi", 0, 1, 2),
-
- GATE(DBG, "ck_apb_dbg", "ck_axi_div2", 0, RCC_DBGCFGR, 8, 0),
-
GATE(CK_DBG, "ck_sys_dbg", "ck_axi", 0, RCC_DBGCFGR, 8, 0),
COMPOSITE(CK_TRACE, "ck_trace", ck_trace_src, CLK_OPS_PARENT_ENABLE,
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index ea67ac8..7af555f 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -426,9 +426,9 @@ static bool mux_is_better_rate(unsigned long rate, unsigned long now,
return now <= rate && now > best;
}
-static int
-clk_mux_determine_rate_flags(struct clk_hw *hw, struct clk_rate_request *req,
- unsigned long flags)
+int clk_mux_determine_rate_flags(struct clk_hw *hw,
+ struct clk_rate_request *req,
+ unsigned long flags)
{
struct clk_core *core = hw->core, *parent, *best_parent = NULL;
int i, num_parents, ret;
@@ -488,6 +488,7 @@ clk_mux_determine_rate_flags(struct clk_hw *hw, struct clk_rate_request *req,
return 0;
}
+EXPORT_SYMBOL_GPL(clk_mux_determine_rate_flags);
struct clk *__clk_lookup(const char *name)
{
diff --git a/drivers/clk/imx/clk-imx6ul.c b/drivers/clk/imx/clk-imx6ul.c
index 114ecbb..1232011 100644
--- a/drivers/clk/imx/clk-imx6ul.c
+++ b/drivers/clk/imx/clk-imx6ul.c
@@ -464,7 +464,7 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
clk_set_rate(clks[IMX6UL_CLK_AHB], 99000000);
/* Change periph_pre clock to pll2_bus to adjust AXI rate to 264MHz */
- clk_set_parent(clks[IMX6UL_CLK_PERIPH_CLK2_SEL], clks[IMX6UL_CLK_PLL3_USB_OTG]);
+ clk_set_parent(clks[IMX6UL_CLK_PERIPH_CLK2_SEL], clks[IMX6UL_CLK_OSC]);
clk_set_parent(clks[IMX6UL_CLK_PERIPH], clks[IMX6UL_CLK_PERIPH_CLK2]);
clk_set_parent(clks[IMX6UL_CLK_PERIPH_PRE], clks[IMX6UL_CLK_PLL2_BUS]);
clk_set_parent(clks[IMX6UL_CLK_PERIPH], clks[IMX6UL_CLK_PERIPH_PRE]);
diff --git a/drivers/clk/meson/clk-regmap.c b/drivers/clk/meson/clk-regmap.c
index 3645fdb6..ab7a355 100644
--- a/drivers/clk/meson/clk-regmap.c
+++ b/drivers/clk/meson/clk-regmap.c
@@ -153,10 +153,19 @@ static int clk_regmap_mux_set_parent(struct clk_hw *hw, u8 index)
val << mux->shift);
}
+static int clk_regmap_mux_determine_rate(struct clk_hw *hw,
+ struct clk_rate_request *req)
+{
+ struct clk_regmap *clk = to_clk_regmap(hw);
+ struct clk_regmap_mux_data *mux = clk_get_regmap_mux_data(clk);
+
+ return clk_mux_determine_rate_flags(hw, req, mux->flags);
+}
+
const struct clk_ops clk_regmap_mux_ops = {
.get_parent = clk_regmap_mux_get_parent,
.set_parent = clk_regmap_mux_set_parent,
- .determine_rate = __clk_mux_determine_rate,
+ .determine_rate = clk_regmap_mux_determine_rate,
};
EXPORT_SYMBOL_GPL(clk_regmap_mux_ops);
diff --git a/drivers/clk/meson/gxbb-aoclk.h b/drivers/clk/meson/gxbb-aoclk.h
index 0be7838..badc4c2 100644
--- a/drivers/clk/meson/gxbb-aoclk.h
+++ b/drivers/clk/meson/gxbb-aoclk.h
@@ -17,8 +17,6 @@
#define AO_RTC_ALT_CLK_CNTL0 0x94
#define AO_RTC_ALT_CLK_CNTL1 0x98
-extern const struct clk_ops meson_aoclk_gate_regmap_ops;
-
struct aoclk_cec_32k {
struct clk_hw hw;
struct regmap *regmap;
diff --git a/drivers/clk/meson/meson8b.c b/drivers/clk/meson/meson8b.c
index cc29924..d0524ec 100644
--- a/drivers/clk/meson/meson8b.c
+++ b/drivers/clk/meson/meson8b.c
@@ -253,7 +253,7 @@ static struct clk_fixed_factor meson8b_fclk_div3_div = {
.mult = 1,
.div = 3,
.hw.init = &(struct clk_init_data){
- .name = "fclk_div_div3",
+ .name = "fclk_div3_div",
.ops = &clk_fixed_factor_ops,
.parent_names = (const char *[]){ "fixed_pll" },
.num_parents = 1,
@@ -632,7 +632,8 @@ static struct clk_regmap meson8b_cpu_clk = {
.hw.init = &(struct clk_init_data){
.name = "cpu_clk",
.ops = &clk_regmap_mux_ro_ops,
- .parent_names = (const char *[]){ "xtal", "cpu_out_sel" },
+ .parent_names = (const char *[]){ "xtal",
+ "cpu_scale_out_sel" },
.num_parents = 2,
.flags = (CLK_SET_RATE_PARENT |
CLK_SET_RATE_NO_REPARENT),
diff --git a/drivers/clk/x86/Makefile b/drivers/clk/x86/Makefile
index 1367afb..00303bc 100644
--- a/drivers/clk/x86/Makefile
+++ b/drivers/clk/x86/Makefile
@@ -1,3 +1,4 @@
+obj-$(CONFIG_PMC_ATOM) += clk-pmc-atom.o
+obj-$(CONFIG_X86_AMD_PLATFORM_DEVICE) += clk-st.o
clk-x86-lpss-objs := clk-lpt.o
obj-$(CONFIG_X86_INTEL_LPSS) += clk-x86-lpss.o
-obj-$(CONFIG_PMC_ATOM) += clk-pmc-atom.o
diff --git a/drivers/clk/x86/clk-st.c b/drivers/clk/x86/clk-st.c
new file mode 100644
index 0000000..fb62f39
--- /dev/null
+++ b/drivers/clk/x86/clk-st.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: MIT
+/*
+ * clock framework for AMD Stoney based clocks
+ *
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ */
+
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/platform_data/clk-st.h>
+#include <linux/platform_device.h>
+
+/* Clock Driving Strength 2 register */
+#define CLKDRVSTR2 0x28
+/* Clock Control 1 register */
+#define MISCCLKCNTL1 0x40
+/* Auxiliary clock1 enable bit */
+#define OSCCLKENB 2
+/* 25Mhz auxiliary output clock freq bit */
+#define OSCOUT1CLK25MHZ 16
+
+#define ST_CLK_48M 0
+#define ST_CLK_25M 1
+#define ST_CLK_MUX 2
+#define ST_CLK_GATE 3
+#define ST_MAX_CLKS 4
+
+static const char * const clk_oscout1_parents[] = { "clk48MHz", "clk25MHz" };
+static struct clk_hw *hws[ST_MAX_CLKS];
+
+static int st_clk_probe(struct platform_device *pdev)
+{
+ struct st_clk_data *st_data;
+
+ st_data = dev_get_platdata(&pdev->dev);
+ if (!st_data || !st_data->base)
+ return -EINVAL;
+
+ hws[ST_CLK_48M] = clk_hw_register_fixed_rate(NULL, "clk48MHz", NULL, 0,
+ 48000000);
+ hws[ST_CLK_25M] = clk_hw_register_fixed_rate(NULL, "clk25MHz", NULL, 0,
+ 25000000);
+
+ hws[ST_CLK_MUX] = clk_hw_register_mux(NULL, "oscout1_mux",
+ clk_oscout1_parents, ARRAY_SIZE(clk_oscout1_parents),
+ 0, st_data->base + CLKDRVSTR2, OSCOUT1CLK25MHZ, 3, 0, NULL);
+
+ clk_set_parent(hws[ST_CLK_MUX]->clk, hws[ST_CLK_25M]->clk);
+
+ hws[ST_CLK_GATE] = clk_hw_register_gate(NULL, "oscout1", "oscout1_mux",
+ 0, st_data->base + MISCCLKCNTL1, OSCCLKENB,
+ CLK_GATE_SET_TO_DISABLE, NULL);
+
+ clk_hw_register_clkdev(hws[ST_CLK_GATE], "oscout1", NULL);
+
+ return 0;
+}
+
+static int st_clk_remove(struct platform_device *pdev)
+{
+ int i;
+
+ for (i = 0; i < ST_MAX_CLKS; i++)
+ clk_hw_unregister(hws[i]);
+ return 0;
+}
+
+static struct platform_driver st_clk_driver = {
+ .driver = {
+ .name = "clk-st",
+ .suppress_bind_attrs = true,
+ },
+ .probe = st_clk_probe,
+ .remove = st_clk_remove,
+};
+builtin_platform_driver(st_clk_driver);
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 9ee2888..dec0dd8 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -133,6 +133,14 @@
help
Enables support for the VT8500 driver.
+config NPCM7XX_TIMER
+ bool "NPCM7xx timer driver" if COMPILE_TEST
+ depends on HAS_IOMEM
+ select CLKSRC_MMIO
+ help
+ Enable 24-bit TIMER0 and TIMER1 counters in the NPCM7xx architecture,
+ While TIMER0 serves as clockevent and TIMER1 serves as clocksource.
+
config CADENCE_TTC_TIMER
bool "Cadence TTC timer driver" if COMPILE_TEST
depends on COMMON_CLK
@@ -442,8 +450,10 @@
Support for Mediatek timer driver.
config SPRD_TIMER
- bool "Spreadtrum timer driver" if COMPILE_TEST
+ bool "Spreadtrum timer driver" if EXPERT
depends on HAS_IOMEM
+ depends on (ARCH_SPRD || COMPILE_TEST)
+ default ARCH_SPRD
select TIMER_OF
help
Enables support for the Spreadtrum timer driver.
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index e8e76df..00caf37 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -56,6 +56,7 @@
obj-$(CONFIG_OXNAS_RPS_TIMER) += timer-oxnas-rps.o
obj-$(CONFIG_OWL_TIMER) += owl-timer.o
obj-$(CONFIG_SPRD_TIMER) += timer-sprd.o
+obj-$(CONFIG_NPCM7XX_TIMER) += timer-npcm7xx.o
obj-$(CONFIG_ARC_TIMERS) += arc_timer.o
obj-$(CONFIG_ARM_ARCH_TIMER) += arm_arch_timer.o
diff --git a/drivers/clocksource/arc_timer.c b/drivers/clocksource/arc_timer.c
index 471b428..20da9b1 100644
--- a/drivers/clocksource/arc_timer.c
+++ b/drivers/clocksource/arc_timer.c
@@ -61,6 +61,20 @@ static u64 arc_read_gfrc(struct clocksource *cs)
unsigned long flags;
u32 l, h;
+ /*
+ * From a programming model pov, there seems to be just one instance of
+ * MCIP_CMD/MCIP_READBACK however micro-architecturally there's
+ * an instance PER ARC CORE (not per cluster), and there are dedicated
+ * hardware decode logic (per core) inside ARConnect to handle
+ * simultaneous read/write accesses from cores via those two registers.
+ * So several concurrent commands to ARConnect are OK if they are
+ * trying to access two different sub-components (like GFRC,
+ * inter-core interrupt, etc...). HW also supports simultaneously
+ * accessing GFRC by multiple cores.
+ * That's why it is safe to disable hard interrupts on the local CPU
+ * before access to GFRC instead of taking global MCIP spinlock
+ * defined in arch/arc/kernel/mcip.c
+ */
local_irq_save(flags);
__mcip_cmd(CMD_GFRC_READ_LO, 0);
diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c
index 986b679..54f8a33 100644
--- a/drivers/clocksource/mips-gic-timer.c
+++ b/drivers/clocksource/mips-gic-timer.c
@@ -5,6 +5,9 @@
*
* Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved.
*/
+
+#define pr_fmt(fmt) "mips-gic-timer: " fmt
+
#include <linux/clk.h>
#include <linux/clockchips.h>
#include <linux/cpu.h>
@@ -136,8 +139,7 @@ static int gic_clockevent_init(void)
ret = setup_percpu_irq(gic_timer_irq, &gic_compare_irqaction);
if (ret < 0) {
- pr_err("GIC timer IRQ %d setup failed: %d\n",
- gic_timer_irq, ret);
+ pr_err("IRQ %d setup failed (%d)\n", gic_timer_irq, ret);
return ret;
}
@@ -176,7 +178,7 @@ static int __init __gic_clocksource_init(void)
ret = clocksource_register_hz(&gic_clocksource, gic_frequency);
if (ret < 0)
- pr_warn("GIC: Unable to register clocksource\n");
+ pr_warn("Unable to register clocksource\n");
return ret;
}
@@ -188,7 +190,7 @@ static int __init gic_clocksource_of_init(struct device_node *node)
if (!mips_gic_present() || !node->parent ||
!of_device_is_compatible(node->parent, "mti,gic")) {
- pr_warn("No DT definition for the mips gic driver\n");
+ pr_warn("No DT definition\n");
return -ENXIO;
}
@@ -196,7 +198,7 @@ static int __init gic_clocksource_of_init(struct device_node *node)
if (!IS_ERR(clk)) {
ret = clk_prepare_enable(clk);
if (ret < 0) {
- pr_err("GIC failed to enable clock\n");
+ pr_err("Failed to enable clock\n");
clk_put(clk);
return ret;
}
@@ -204,12 +206,12 @@ static int __init gic_clocksource_of_init(struct device_node *node)
gic_frequency = clk_get_rate(clk);
} else if (of_property_read_u32(node, "clock-frequency",
&gic_frequency)) {
- pr_err("GIC frequency not specified.\n");
+ pr_err("Frequency not specified\n");
return -EINVAL;
}
gic_timer_irq = irq_of_parse_and_map(node, 0);
if (!gic_timer_irq) {
- pr_err("GIC timer IRQ not specified.\n");
+ pr_err("IRQ not specified\n");
return -EINVAL;
}
@@ -220,7 +222,7 @@ static int __init gic_clocksource_of_init(struct device_node *node)
ret = gic_clockevent_init();
if (!ret && !IS_ERR(clk)) {
if (clk_notifier_register(clk, &gic_clk_nb) < 0)
- pr_warn("GIC: Unable to register clock notifier\n");
+ pr_warn("Unable to register clock notifier\n");
}
/* And finally start the counter */
diff --git a/drivers/clocksource/mxs_timer.c b/drivers/clocksource/mxs_timer.c
index a03434e..f6ddae3 100644
--- a/drivers/clocksource/mxs_timer.c
+++ b/drivers/clocksource/mxs_timer.c
@@ -1,24 +1,10 @@
-/*
- * Copyright (C) 2000-2001 Deep Blue Solutions
- * Copyright (C) 2002 Shane Nay (shane@minirl.com)
- * Copyright (C) 2006-2007 Pavel Pisa (ppisa@pikron.com)
- * Copyright (C) 2008 Juergen Beisert (kernel@pengutronix.de)
- * Copyright (C) 2010 Freescale Semiconductor, Inc. All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (C) 2000-2001 Deep Blue Solutions
+// Copyright (C) 2002 Shane Nay (shane@minirl.com)
+// Copyright (C) 2006-2007 Pavel Pisa (ppisa@pikron.com)
+// Copyright (C) 2008 Juergen Beisert (kernel@pengutronix.de)
+// Copyright (C) 2010 Freescale Semiconductor, Inc. All Rights Reserved.
#include <linux/err.h>
#include <linux/interrupt.h>
diff --git a/drivers/clocksource/timer-imx-gpt.c b/drivers/clocksource/timer-imx-gpt.c
index 6ec6d79..165fbbb 100644
--- a/drivers/clocksource/timer-imx-gpt.c
+++ b/drivers/clocksource/timer-imx-gpt.c
@@ -1,25 +1,9 @@
-/*
- * linux/arch/arm/plat-mxc/time.c
- *
- * Copyright (C) 2000-2001 Deep Blue Solutions
- * Copyright (C) 2002 Shane Nay (shane@minirl.com)
- * Copyright (C) 2006-2007 Pavel Pisa (ppisa@pikron.com)
- * Copyright (C) 2008 Juergen Beisert (kernel@pengutronix.de)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (C) 2000-2001 Deep Blue Solutions
+// Copyright (C) 2002 Shane Nay (shane@minirl.com)
+// Copyright (C) 2006-2007 Pavel Pisa (ppisa@pikron.com)
+// Copyright (C) 2008 Juergen Beisert (kernel@pengutronix.de)
#include <linux/interrupt.h>
#include <linux/irq.h>
diff --git a/drivers/clocksource/timer-imx-tpm.c b/drivers/clocksource/timer-imx-tpm.c
index 21bffdc..b7aa2b8 100644
--- a/drivers/clocksource/timer-imx-tpm.c
+++ b/drivers/clocksource/timer-imx-tpm.c
@@ -1,12 +1,7 @@
-/*
- * Copyright 2016 Freescale Semiconductor, Inc.
- * Copyright 2017 NXP
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright 2016 Freescale Semiconductor, Inc.
+// Copyright 2017 NXP
#include <linux/clk.h>
#include <linux/clockchips.h>
@@ -17,9 +12,14 @@
#include <linux/of_irq.h>
#include <linux/sched_clock.h>
+#define TPM_PARAM 0x4
+#define TPM_PARAM_WIDTH_SHIFT 16
+#define TPM_PARAM_WIDTH_MASK (0xff << 16)
#define TPM_SC 0x10
#define TPM_SC_CMOD_INC_PER_CNT (0x1 << 3)
#define TPM_SC_CMOD_DIV_DEFAULT 0x3
+#define TPM_SC_CMOD_DIV_MAX 0x7
+#define TPM_SC_TOF_MASK (0x1 << 7)
#define TPM_CNT 0x14
#define TPM_MOD 0x18
#define TPM_STATUS 0x1c
@@ -29,8 +29,11 @@
#define TPM_C0SC_MODE_SHIFT 2
#define TPM_C0SC_MODE_MASK 0x3c
#define TPM_C0SC_MODE_SW_COMPARE 0x4
+#define TPM_C0SC_CHF_MASK (0x1 << 7)
#define TPM_C0V 0x24
+static int counter_width;
+static int rating;
static void __iomem *timer_base;
static struct clock_event_device clockevent_tpm;
@@ -83,10 +86,11 @@ static int __init tpm_clocksource_init(unsigned long rate)
tpm_delay_timer.freq = rate;
register_current_timer_delay(&tpm_delay_timer);
- sched_clock_register(tpm_read_sched_clock, 32, rate);
+ sched_clock_register(tpm_read_sched_clock, counter_width, rate);
return clocksource_mmio_init(timer_base + TPM_CNT, "imx-tpm",
- rate, 200, 32, clocksource_mmio_readl_up);
+ rate, rating, counter_width,
+ clocksource_mmio_readl_up);
}
static int tpm_set_next_event(unsigned long delta,
@@ -105,7 +109,7 @@ static int tpm_set_next_event(unsigned long delta,
* of writing CNT registers which may cause the min_delta event got
* missed, so we need add a ETIME check here in case it happened.
*/
- return (int)((next - now) <= 0) ? -ETIME : 0;
+ return (int)(next - now) <= 0 ? -ETIME : 0;
}
static int tpm_set_state_oneshot(struct clock_event_device *evt)
@@ -139,7 +143,6 @@ static struct clock_event_device clockevent_tpm = {
.set_state_oneshot = tpm_set_state_oneshot,
.set_next_event = tpm_set_next_event,
.set_state_shutdown = tpm_set_state_shutdown,
- .rating = 200,
};
static int __init tpm_clockevent_init(unsigned long rate, int irq)
@@ -149,10 +152,11 @@ static int __init tpm_clockevent_init(unsigned long rate, int irq)
ret = request_irq(irq, tpm_timer_interrupt, IRQF_TIMER | IRQF_IRQPOLL,
"i.MX7ULP TPM Timer", &clockevent_tpm);
+ clockevent_tpm.rating = rating;
clockevent_tpm.cpumask = cpumask_of(0);
clockevent_tpm.irq = irq;
- clockevents_config_and_register(&clockevent_tpm,
- rate, 300, 0xfffffffe);
+ clockevents_config_and_register(&clockevent_tpm, rate, 300,
+ GENMASK(counter_width - 1, 1));
return ret;
}
@@ -179,7 +183,7 @@ static int __init tpm_timer_init(struct device_node *np)
ipg = of_clk_get_by_name(np, "ipg");
per = of_clk_get_by_name(np, "per");
if (IS_ERR(ipg) || IS_ERR(per)) {
- pr_err("tpm: failed to get igp or per clk\n");
+ pr_err("tpm: failed to get ipg or per clk\n");
ret = -ENODEV;
goto err_clk_get;
}
@@ -197,6 +201,11 @@ static int __init tpm_timer_init(struct device_node *np)
goto err_per_clk_enable;
}
+ counter_width = (readl(timer_base + TPM_PARAM) & TPM_PARAM_WIDTH_MASK)
+ >> TPM_PARAM_WIDTH_SHIFT;
+ /* use rating 200 for 32-bit counter and 150 for 16-bit counter */
+ rating = counter_width == 0x20 ? 200 : 150;
+
/*
* Initialize tpm module to a known state
* 1) Counter disabled
@@ -205,16 +214,25 @@ static int __init tpm_timer_init(struct device_node *np)
* 4) Channel0 disabled
* 5) DMA transfers disabled
*/
+ /* make sure counter is disabled */
writel(0, timer_base + TPM_SC);
+ /* TOF is W1C */
+ writel(TPM_SC_TOF_MASK, timer_base + TPM_SC);
writel(0, timer_base + TPM_CNT);
- writel(0, timer_base + TPM_C0SC);
+ /* CHF is W1C */
+ writel(TPM_C0SC_CHF_MASK, timer_base + TPM_C0SC);
- /* increase per cnt, div 8 by default */
- writel(TPM_SC_CMOD_INC_PER_CNT | TPM_SC_CMOD_DIV_DEFAULT,
+ /*
+ * increase per cnt,
+ * div 8 for 32-bit counter and div 128 for 16-bit counter
+ */
+ writel(TPM_SC_CMOD_INC_PER_CNT |
+ (counter_width == 0x20 ?
+ TPM_SC_CMOD_DIV_DEFAULT : TPM_SC_CMOD_DIV_MAX),
timer_base + TPM_SC);
/* set MOD register to maximum for free running mode */
- writel(0xffffffff, timer_base + TPM_MOD);
+ writel(GENMASK(counter_width - 1, 0), timer_base + TPM_MOD);
rate = clk_get_rate(per) >> 3;
ret = tpm_clocksource_init(rate);
diff --git a/drivers/clocksource/timer-npcm7xx.c b/drivers/clocksource/timer-npcm7xx.c
new file mode 100644
index 0000000..7a9bb55
--- /dev/null
+++ b/drivers/clocksource/timer-npcm7xx.c
@@ -0,0 +1,215 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2014-2018 Nuvoton Technologies tomer.maimon@nuvoton.com
+ * All rights reserved.
+ *
+ * Copyright 2017 Google, Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/err.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/clockchips.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+#include "timer-of.h"
+
+/* Timers registers */
+#define NPCM7XX_REG_TCSR0 0x0 /* Timer 0 Control and Status Register */
+#define NPCM7XX_REG_TICR0 0x8 /* Timer 0 Initial Count Register */
+#define NPCM7XX_REG_TCSR1 0x4 /* Timer 1 Control and Status Register */
+#define NPCM7XX_REG_TICR1 0xc /* Timer 1 Initial Count Register */
+#define NPCM7XX_REG_TDR1 0x14 /* Timer 1 Data Register */
+#define NPCM7XX_REG_TISR 0x18 /* Timer Interrupt Status Register */
+
+/* Timers control */
+#define NPCM7XX_Tx_RESETINT 0x1f
+#define NPCM7XX_Tx_PERIOD BIT(27)
+#define NPCM7XX_Tx_INTEN BIT(29)
+#define NPCM7XX_Tx_COUNTEN BIT(30)
+#define NPCM7XX_Tx_ONESHOT 0x0
+#define NPCM7XX_Tx_OPER GENMASK(3, 27)
+#define NPCM7XX_Tx_MIN_PRESCALE 0x1
+#define NPCM7XX_Tx_TDR_MASK_BITS 24
+#define NPCM7XX_Tx_MAX_CNT 0xFFFFFF
+#define NPCM7XX_T0_CLR_INT 0x1
+#define NPCM7XX_Tx_CLR_CSR 0x0
+
+/* Timers operating mode */
+#define NPCM7XX_START_PERIODIC_Tx (NPCM7XX_Tx_PERIOD | NPCM7XX_Tx_COUNTEN | \
+ NPCM7XX_Tx_INTEN | \
+ NPCM7XX_Tx_MIN_PRESCALE)
+
+#define NPCM7XX_START_ONESHOT_Tx (NPCM7XX_Tx_ONESHOT | NPCM7XX_Tx_COUNTEN | \
+ NPCM7XX_Tx_INTEN | \
+ NPCM7XX_Tx_MIN_PRESCALE)
+
+#define NPCM7XX_START_Tx (NPCM7XX_Tx_COUNTEN | NPCM7XX_Tx_PERIOD | \
+ NPCM7XX_Tx_MIN_PRESCALE)
+
+#define NPCM7XX_DEFAULT_CSR (NPCM7XX_Tx_CLR_CSR | NPCM7XX_Tx_MIN_PRESCALE)
+
+static int npcm7xx_timer_resume(struct clock_event_device *evt)
+{
+ struct timer_of *to = to_timer_of(evt);
+ u32 val;
+
+ val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
+ val |= NPCM7XX_Tx_COUNTEN;
+ writel(val, timer_of_base(to) + NPCM7XX_REG_TCSR0);
+
+ return 0;
+}
+
+static int npcm7xx_timer_shutdown(struct clock_event_device *evt)
+{
+ struct timer_of *to = to_timer_of(evt);
+ u32 val;
+
+ val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
+ val &= ~NPCM7XX_Tx_COUNTEN;
+ writel(val, timer_of_base(to) + NPCM7XX_REG_TCSR0);
+
+ return 0;
+}
+
+static int npcm7xx_timer_oneshot(struct clock_event_device *evt)
+{
+ struct timer_of *to = to_timer_of(evt);
+ u32 val;
+
+ val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
+ val &= ~NPCM7XX_Tx_OPER;
+
+ val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
+ val |= NPCM7XX_START_ONESHOT_Tx;
+ writel(val, timer_of_base(to) + NPCM7XX_REG_TCSR0);
+
+ return 0;
+}
+
+static int npcm7xx_timer_periodic(struct clock_event_device *evt)
+{
+ struct timer_of *to = to_timer_of(evt);
+ u32 val;
+
+ val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
+ val &= ~NPCM7XX_Tx_OPER;
+
+ writel(timer_of_period(to), timer_of_base(to) + NPCM7XX_REG_TICR0);
+ val |= NPCM7XX_START_PERIODIC_Tx;
+
+ writel(val, timer_of_base(to) + NPCM7XX_REG_TCSR0);
+
+ return 0;
+}
+
+static int npcm7xx_clockevent_set_next_event(unsigned long evt,
+ struct clock_event_device *clk)
+{
+ struct timer_of *to = to_timer_of(clk);
+ u32 val;
+
+ writel(evt, timer_of_base(to) + NPCM7XX_REG_TICR0);
+ val = readl(timer_of_base(to) + NPCM7XX_REG_TCSR0);
+ val |= NPCM7XX_START_Tx;
+ writel(val, timer_of_base(to) + NPCM7XX_REG_TCSR0);
+
+ return 0;
+}
+
+static irqreturn_t npcm7xx_timer0_interrupt(int irq, void *dev_id)
+{
+ struct clock_event_device *evt = (struct clock_event_device *)dev_id;
+ struct timer_of *to = to_timer_of(evt);
+
+ writel(NPCM7XX_T0_CLR_INT, timer_of_base(to) + NPCM7XX_REG_TISR);
+
+ evt->event_handler(evt);
+
+ return IRQ_HANDLED;
+}
+
+static struct timer_of npcm7xx_to = {
+ .flags = TIMER_OF_IRQ | TIMER_OF_BASE | TIMER_OF_CLOCK,
+
+ .clkevt = {
+ .name = "npcm7xx-timer0",
+ .features = CLOCK_EVT_FEAT_PERIODIC |
+ CLOCK_EVT_FEAT_ONESHOT,
+ .set_next_event = npcm7xx_clockevent_set_next_event,
+ .set_state_shutdown = npcm7xx_timer_shutdown,
+ .set_state_periodic = npcm7xx_timer_periodic,
+ .set_state_oneshot = npcm7xx_timer_oneshot,
+ .tick_resume = npcm7xx_timer_resume,
+ .rating = 300,
+ },
+
+ .of_irq = {
+ .handler = npcm7xx_timer0_interrupt,
+ .flags = IRQF_TIMER | IRQF_IRQPOLL,
+ },
+};
+
+static void __init npcm7xx_clockevents_init(void)
+{
+ writel(NPCM7XX_DEFAULT_CSR,
+ timer_of_base(&npcm7xx_to) + NPCM7XX_REG_TCSR0);
+
+ writel(NPCM7XX_Tx_RESETINT,
+ timer_of_base(&npcm7xx_to) + NPCM7XX_REG_TISR);
+
+ npcm7xx_to.clkevt.cpumask = cpumask_of(0);
+ clockevents_config_and_register(&npcm7xx_to.clkevt,
+ timer_of_rate(&npcm7xx_to),
+ 0x1, NPCM7XX_Tx_MAX_CNT);
+}
+
+static void __init npcm7xx_clocksource_init(void)
+{
+ u32 val;
+
+ writel(NPCM7XX_DEFAULT_CSR,
+ timer_of_base(&npcm7xx_to) + NPCM7XX_REG_TCSR1);
+ writel(NPCM7XX_Tx_MAX_CNT,
+ timer_of_base(&npcm7xx_to) + NPCM7XX_REG_TICR1);
+
+ val = readl(timer_of_base(&npcm7xx_to) + NPCM7XX_REG_TCSR1);
+ val |= NPCM7XX_START_Tx;
+ writel(val, timer_of_base(&npcm7xx_to) + NPCM7XX_REG_TCSR1);
+
+ clocksource_mmio_init(timer_of_base(&npcm7xx_to) +
+ NPCM7XX_REG_TDR1,
+ "npcm7xx-timer1", timer_of_rate(&npcm7xx_to),
+ 200, (unsigned int)NPCM7XX_Tx_TDR_MASK_BITS,
+ clocksource_mmio_readl_down);
+}
+
+static int __init npcm7xx_timer_init(struct device_node *np)
+{
+ int ret;
+
+ ret = timer_of_init(np, &npcm7xx_to);
+ if (ret)
+ return ret;
+
+ /* Clock input is divided by PRESCALE + 1 before it is fed */
+ /* to the counter */
+ npcm7xx_to.of_clk.rate = npcm7xx_to.of_clk.rate /
+ (NPCM7XX_Tx_MIN_PRESCALE + 1);
+
+ npcm7xx_clocksource_init();
+ npcm7xx_clockevents_init();
+
+ pr_info("Enabling NPCM7xx clocksource timer base: %px, IRQ: %d ",
+ timer_of_base(&npcm7xx_to), timer_of_irq(&npcm7xx_to));
+
+ return 0;
+}
+
+TIMER_OF_DECLARE(npcm7xx, "nuvoton,npcm750-timer", npcm7xx_timer_init);
+
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index 8615594b..e718b8c 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -260,19 +260,6 @@ static int cn_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int cn_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, cn_proc_show, NULL);
-}
-
-static const struct file_operations cn_file_ops = {
- .owner = THIS_MODULE,
- .open = cn_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release
-};
-
static struct cn_dev cdev = {
.input = cn_rx_skb,
};
@@ -297,7 +284,7 @@ static int cn_init(void)
cn_already_initialized = 1;
- proc_create("connector", S_IRUGO, init_net.proc_net, &cn_file_ops);
+ proc_create_single("connector", S_IRUGO, init_net.proc_net, cn_proc_show);
return 0;
}
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 7f56fe5..c7ce928 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -20,7 +20,7 @@
config ARM_ARMADA_37XX_CPUFREQ
tristate "Armada 37xx CPUFreq support"
- depends on ARCH_MVEBU
+ depends on ARCH_MVEBU && CPUFREQ_DT
help
This adds the CPUFreq driver support for Marvell Armada 37xx SoCs.
The Armada 37xx PMU supports 4 frequency and VDD levels.
@@ -71,16 +71,6 @@
Say Y, if you have a Broadcom SoC with AVS support for DFS or DVFS.
-config ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
- bool "Broadcom STB AVS CPUfreq driver sysfs debug capability"
- depends on ARM_BRCMSTB_AVS_CPUFREQ
- help
- Enabling this option turns on debug support via sysfs under
- /sys/kernel/debug/brcmstb-avs-cpufreq. It is possible to read all and
- write some AVS mailbox registers through sysfs entries.
-
- If in doubt, say N.
-
config ARM_EXYNOS5440_CPUFREQ
tristate "SAMSUNG EXYNOS5440"
depends on SOC_EXYNOS5440
@@ -134,6 +124,17 @@
depends on ARCH_OMAP2PLUS
default ARCH_OMAP2PLUS
+config ARM_QCOM_CPUFREQ_KRYO
+ bool "Qualcomm Kryo based CPUFreq"
+ depends on ARM64
+ depends on QCOM_QFPROM
+ depends on QCOM_SMEM
+ select PM_OPP
+ help
+ This adds the CPUFreq driver for Qualcomm Kryo SoC based boards.
+
+ If in doubt, say N.
+
config ARM_S3C_CPUFREQ
bool
help
@@ -274,7 +275,7 @@
default y
config ARM_TEGRA20_CPUFREQ
- bool "Tegra20 CPUFreq support"
+ tristate "Tegra20 CPUFreq support"
depends on ARCH_TEGRA
default y
help
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 8d24ade..fb4a2ec 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -65,6 +65,7 @@
obj-$(CONFIG_ARM_OMAP2PLUS_CPUFREQ) += omap-cpufreq.o
obj-$(CONFIG_ARM_PXA2xx_CPUFREQ) += pxa2xx-cpufreq.o
obj-$(CONFIG_PXA3xx) += pxa3xx-cpufreq.o
+obj-$(CONFIG_ARM_QCOM_CPUFREQ_KRYO) += qcom-cpufreq-kryo.o
obj-$(CONFIG_ARM_S3C2410_CPUFREQ) += s3c2410-cpufreq.o
obj-$(CONFIG_ARM_S3C2412_CPUFREQ) += s3c2412-cpufreq.o
obj-$(CONFIG_ARM_S3C2416_CPUFREQ) += s3c2416-cpufreq.o
diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c
index 72a2975..739da90 100644
--- a/drivers/cpufreq/armada-37xx-cpufreq.c
+++ b/drivers/cpufreq/armada-37xx-cpufreq.c
@@ -23,6 +23,8 @@
#include <linux/regmap.h>
#include <linux/slab.h>
+#include "cpufreq-dt.h"
+
/* Power management in North Bridge register set */
#define ARMADA_37XX_NB_L0L1 0x18
#define ARMADA_37XX_NB_L2L3 0x1C
@@ -56,6 +58,16 @@
*/
#define LOAD_LEVEL_NR 4
+struct armada37xx_cpufreq_state {
+ struct regmap *regmap;
+ u32 nb_l0l1;
+ u32 nb_l2l3;
+ u32 nb_dyn_mod;
+ u32 nb_cpu_load;
+};
+
+static struct armada37xx_cpufreq_state *armada37xx_cpufreq_state;
+
struct armada_37xx_dvfs {
u32 cpu_freq_max;
u8 divider[LOAD_LEVEL_NR];
@@ -136,7 +148,7 @@ static void __init armada37xx_cpufreq_dvfs_setup(struct regmap *base,
clk_set_parent(clk, parent);
}
-static void __init armada37xx_cpufreq_disable_dvfs(struct regmap *base)
+static void armada37xx_cpufreq_disable_dvfs(struct regmap *base)
{
unsigned int reg = ARMADA_37XX_NB_DYN_MOD,
mask = ARMADA_37XX_NB_DFS_EN;
@@ -162,10 +174,47 @@ static void __init armada37xx_cpufreq_enable_dvfs(struct regmap *base)
regmap_update_bits(base, reg, mask, mask);
}
+static int armada37xx_cpufreq_suspend(struct cpufreq_policy *policy)
+{
+ struct armada37xx_cpufreq_state *state = armada37xx_cpufreq_state;
+
+ regmap_read(state->regmap, ARMADA_37XX_NB_L0L1, &state->nb_l0l1);
+ regmap_read(state->regmap, ARMADA_37XX_NB_L2L3, &state->nb_l2l3);
+ regmap_read(state->regmap, ARMADA_37XX_NB_CPU_LOAD,
+ &state->nb_cpu_load);
+ regmap_read(state->regmap, ARMADA_37XX_NB_DYN_MOD, &state->nb_dyn_mod);
+
+ return 0;
+}
+
+static int armada37xx_cpufreq_resume(struct cpufreq_policy *policy)
+{
+ struct armada37xx_cpufreq_state *state = armada37xx_cpufreq_state;
+
+ /* Ensure DVFS is disabled otherwise the following registers are RO */
+ armada37xx_cpufreq_disable_dvfs(state->regmap);
+
+ regmap_write(state->regmap, ARMADA_37XX_NB_L0L1, state->nb_l0l1);
+ regmap_write(state->regmap, ARMADA_37XX_NB_L2L3, state->nb_l2l3);
+ regmap_write(state->regmap, ARMADA_37XX_NB_CPU_LOAD,
+ state->nb_cpu_load);
+
+ /*
+ * NB_DYN_MOD register is the one that actually enable back DVFS if it
+ * was enabled before the suspend operation. This must be done last
+ * otherwise other registers are not writable.
+ */
+ regmap_write(state->regmap, ARMADA_37XX_NB_DYN_MOD, state->nb_dyn_mod);
+
+ return 0;
+}
+
static int __init armada37xx_cpufreq_driver_init(void)
{
+ struct cpufreq_dt_platform_data pdata;
struct armada_37xx_dvfs *dvfs;
struct platform_device *pdev;
+ unsigned long freq;
unsigned int cur_frequency;
struct regmap *nb_pm_base;
struct device *cpu_dev;
@@ -207,33 +256,58 @@ static int __init armada37xx_cpufreq_driver_init(void)
}
dvfs = armada_37xx_cpu_freq_info_get(cur_frequency);
- if (!dvfs)
+ if (!dvfs) {
+ clk_put(clk);
return -EINVAL;
+ }
+
+ armada37xx_cpufreq_state = kmalloc(sizeof(*armada37xx_cpufreq_state),
+ GFP_KERNEL);
+ if (!armada37xx_cpufreq_state) {
+ clk_put(clk);
+ return -ENOMEM;
+ }
+
+ armada37xx_cpufreq_state->regmap = nb_pm_base;
armada37xx_cpufreq_dvfs_setup(nb_pm_base, clk, dvfs->divider);
clk_put(clk);
for (load_lvl = ARMADA_37XX_DVFS_LOAD_0; load_lvl < LOAD_LEVEL_NR;
load_lvl++) {
- unsigned long freq = cur_frequency / dvfs->divider[load_lvl];
+ freq = cur_frequency / dvfs->divider[load_lvl];
ret = dev_pm_opp_add(cpu_dev, freq, 0);
- if (ret) {
- /* clean-up the already added opp before leaving */
- while (load_lvl-- > ARMADA_37XX_DVFS_LOAD_0) {
- freq = cur_frequency / dvfs->divider[load_lvl];
- dev_pm_opp_remove(cpu_dev, freq);
- }
- return ret;
- }
+ if (ret)
+ goto remove_opp;
}
/* Now that everything is setup, enable the DVFS at hardware level */
armada37xx_cpufreq_enable_dvfs(nb_pm_base);
- pdev = platform_device_register_simple("cpufreq-dt", -1, NULL, 0);
+ pdata.suspend = armada37xx_cpufreq_suspend;
+ pdata.resume = armada37xx_cpufreq_resume;
- return PTR_ERR_OR_ZERO(pdev);
+ pdev = platform_device_register_data(NULL, "cpufreq-dt", -1, &pdata,
+ sizeof(pdata));
+ ret = PTR_ERR_OR_ZERO(pdev);
+ if (ret)
+ goto disable_dvfs;
+
+ return 0;
+
+disable_dvfs:
+ armada37xx_cpufreq_disable_dvfs(nb_pm_base);
+remove_opp:
+ /* clean-up the already added opp before leaving */
+ while (load_lvl-- > ARMADA_37XX_DVFS_LOAD_0) {
+ freq = cur_frequency / dvfs->divider[load_lvl];
+ dev_pm_opp_remove(cpu_dev, freq);
+ }
+
+ kfree(armada37xx_cpufreq_state);
+
+ return ret;
}
/* late_initcall, to guarantee the driver is loaded after A37xx clock driver */
late_initcall(armada37xx_cpufreq_driver_init);
diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c
index 6cdac1a..b07559b 100644
--- a/drivers/cpufreq/brcmstb-avs-cpufreq.c
+++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c
@@ -49,13 +49,6 @@
#include <linux/platform_device.h>
#include <linux/semaphore.h>
-#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
-#include <linux/ctype.h>
-#include <linux/debugfs.h>
-#include <linux/slab.h>
-#include <linux/uaccess.h>
-#endif
-
/* Max number of arguments AVS calls take */
#define AVS_MAX_CMD_ARGS 4
/*
@@ -182,88 +175,11 @@ struct private_data {
void __iomem *base;
void __iomem *avs_intr_base;
struct device *dev;
-#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
- struct dentry *debugfs;
-#endif
struct completion done;
struct semaphore sem;
struct pmap pmap;
};
-#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
-
-enum debugfs_format {
- DEBUGFS_NORMAL,
- DEBUGFS_FLOAT,
- DEBUGFS_REV,
-};
-
-struct debugfs_data {
- struct debugfs_entry *entry;
- struct private_data *priv;
-};
-
-struct debugfs_entry {
- char *name;
- u32 offset;
- fmode_t mode;
- enum debugfs_format format;
-};
-
-#define DEBUGFS_ENTRY(name, mode, format) { \
- #name, AVS_MBOX_##name, mode, format \
-}
-
-/*
- * These are used for debugfs only. Otherwise we use AVS_MBOX_PARAM() directly.
- */
-#define AVS_MBOX_PARAM1 AVS_MBOX_PARAM(0)
-#define AVS_MBOX_PARAM2 AVS_MBOX_PARAM(1)
-#define AVS_MBOX_PARAM3 AVS_MBOX_PARAM(2)
-#define AVS_MBOX_PARAM4 AVS_MBOX_PARAM(3)
-
-/*
- * This table stores the name, access permissions and offset for each hardware
- * register and is used to generate debugfs entries.
- */
-static struct debugfs_entry debugfs_entries[] = {
- DEBUGFS_ENTRY(COMMAND, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(STATUS, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(VOLTAGE0, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(TEMP0, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(PV0, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(MV0, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(PARAM1, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(PARAM2, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(PARAM3, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(PARAM4, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(REVISION, 0, DEBUGFS_REV),
- DEBUGFS_ENTRY(PSTATE, 0, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(HEARTBEAT, 0, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(MAGIC, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(SIGMA_HVT, 0, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(SIGMA_SVT, 0, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(VOLTAGE1, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(TEMP1, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(PV1, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(MV1, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(FREQUENCY, 0, DEBUGFS_NORMAL),
-};
-
-static int brcm_avs_target_index(struct cpufreq_policy *, unsigned int);
-
-static char *__strtolower(char *s)
-{
- char *p;
-
- for (p = s; *p; p++)
- *p = tolower(*p);
-
- return s;
-}
-
-#endif /* CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG */
-
static void __iomem *__map_region(const char *name)
{
struct device_node *np;
@@ -516,238 +432,6 @@ brcm_avs_get_freq_table(struct device *dev, struct private_data *priv)
return table;
}
-#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
-
-#define MANT(x) (unsigned int)(abs((x)) / 1000)
-#define FRAC(x) (unsigned int)(abs((x)) - abs((x)) / 1000 * 1000)
-
-static int brcm_avs_debug_show(struct seq_file *s, void *data)
-{
- struct debugfs_data *dbgfs = s->private;
- void __iomem *base;
- u32 val, offset;
-
- if (!dbgfs) {
- seq_puts(s, "No device pointer\n");
- return 0;
- }
-
- base = dbgfs->priv->base;
- offset = dbgfs->entry->offset;
- val = readl(base + offset);
- switch (dbgfs->entry->format) {
- case DEBUGFS_NORMAL:
- seq_printf(s, "%u\n", val);
- break;
- case DEBUGFS_FLOAT:
- seq_printf(s, "%d.%03d\n", MANT(val), FRAC(val));
- break;
- case DEBUGFS_REV:
- seq_printf(s, "%c.%c.%c.%c\n", (val >> 24 & 0xff),
- (val >> 16 & 0xff), (val >> 8 & 0xff),
- val & 0xff);
- break;
- }
- seq_printf(s, "0x%08x\n", val);
-
- return 0;
-}
-
-#undef MANT
-#undef FRAC
-
-static ssize_t brcm_avs_seq_write(struct file *file, const char __user *buf,
- size_t size, loff_t *ppos)
-{
- struct seq_file *s = file->private_data;
- struct debugfs_data *dbgfs = s->private;
- struct private_data *priv = dbgfs->priv;
- void __iomem *base, *avs_intr_base;
- bool use_issue_command = false;
- unsigned long val, offset;
- char str[128];
- int ret;
- char *str_ptr = str;
-
- if (size >= sizeof(str))
- return -E2BIG;
-
- memset(str, 0, sizeof(str));
- ret = copy_from_user(str, buf, size);
- if (ret)
- return ret;
-
- base = priv->base;
- avs_intr_base = priv->avs_intr_base;
- offset = dbgfs->entry->offset;
- /*
- * Special case writing to "command" entry only: if the string starts
- * with a 'c', we use the driver's __issue_avs_command() function.
- * Otherwise, we perform a raw write. This should allow testing of raw
- * access as well as using the higher level function. (Raw access
- * doesn't clear the firmware return status after issuing the command.)
- */
- if (str_ptr[0] == 'c' && offset == AVS_MBOX_COMMAND) {
- use_issue_command = true;
- str_ptr++;
- }
- if (kstrtoul(str_ptr, 0, &val) != 0)
- return -EINVAL;
-
- /*
- * Setting the P-state is a special case. We need to update the CPU
- * frequency we report.
- */
- if (val == AVS_CMD_SET_PSTATE) {
- struct cpufreq_policy *policy;
- unsigned int pstate;
-
- policy = cpufreq_cpu_get(smp_processor_id());
- /* Read back the P-state we are about to set */
- pstate = readl(base + AVS_MBOX_PARAM(0));
- if (use_issue_command) {
- ret = brcm_avs_target_index(policy, pstate);
- return ret ? ret : size;
- }
- policy->cur = policy->freq_table[pstate].frequency;
- }
-
- if (use_issue_command) {
- ret = __issue_avs_command(priv, val, false, NULL);
- } else {
- /* Locking here is not perfect, but is only for debug. */
- ret = down_interruptible(&priv->sem);
- if (ret)
- return ret;
-
- writel(val, base + offset);
- /* We have to wake up the firmware to process a command. */
- if (offset == AVS_MBOX_COMMAND)
- writel(AVS_CPU_L2_INT_MASK,
- avs_intr_base + AVS_CPU_L2_SET0);
- up(&priv->sem);
- }
-
- return ret ? ret : size;
-}
-
-static struct debugfs_entry *__find_debugfs_entry(const char *name)
-{
- int i;
-
- for (i = 0; i < ARRAY_SIZE(debugfs_entries); i++)
- if (strcasecmp(debugfs_entries[i].name, name) == 0)
- return &debugfs_entries[i];
-
- return NULL;
-}
-
-static int brcm_avs_debug_open(struct inode *inode, struct file *file)
-{
- struct debugfs_data *data;
- fmode_t fmode;
- int ret;
-
- /*
- * seq_open(), which is called by single_open(), clears "write" access.
- * We need write access to some files, so we preserve our access mode
- * and restore it.
- */
- fmode = file->f_mode;
- /*
- * Check access permissions even for root. We don't want to be writing
- * to read-only registers. Access for regular users has already been
- * checked by the VFS layer.
- */
- if ((fmode & FMODE_WRITER) && !(inode->i_mode & S_IWUSR))
- return -EACCES;
-
- data = kmalloc(sizeof(*data), GFP_KERNEL);
- if (!data)
- return -ENOMEM;
- /*
- * We use the same file system operations for all our debug files. To
- * produce specific output, we look up the file name upon opening a
- * debugfs entry and map it to a memory offset. This offset is then used
- * in the generic "show" function to read a specific register.
- */
- data->entry = __find_debugfs_entry(file->f_path.dentry->d_iname);
- data->priv = inode->i_private;
-
- ret = single_open(file, brcm_avs_debug_show, data);
- if (ret)
- kfree(data);
- file->f_mode = fmode;
-
- return ret;
-}
-
-static int brcm_avs_debug_release(struct inode *inode, struct file *file)
-{
- struct seq_file *seq_priv = file->private_data;
- struct debugfs_data *data = seq_priv->private;
-
- kfree(data);
- return single_release(inode, file);
-}
-
-static const struct file_operations brcm_avs_debug_ops = {
- .open = brcm_avs_debug_open,
- .read = seq_read,
- .write = brcm_avs_seq_write,
- .llseek = seq_lseek,
- .release = brcm_avs_debug_release,
-};
-
-static void brcm_avs_cpufreq_debug_init(struct platform_device *pdev)
-{
- struct private_data *priv = platform_get_drvdata(pdev);
- struct dentry *dir;
- int i;
-
- if (!priv)
- return;
-
- dir = debugfs_create_dir(BRCM_AVS_CPUFREQ_NAME, NULL);
- if (IS_ERR_OR_NULL(dir))
- return;
- priv->debugfs = dir;
-
- for (i = 0; i < ARRAY_SIZE(debugfs_entries); i++) {
- /*
- * The DEBUGFS_ENTRY macro generates uppercase strings. We
- * convert them to lowercase before creating the debugfs
- * entries.
- */
- char *entry = __strtolower(debugfs_entries[i].name);
- fmode_t mode = debugfs_entries[i].mode;
-
- if (!debugfs_create_file(entry, S_IFREG | S_IRUGO | mode,
- dir, priv, &brcm_avs_debug_ops)) {
- priv->debugfs = NULL;
- debugfs_remove_recursive(dir);
- break;
- }
- }
-}
-
-static void brcm_avs_cpufreq_debug_exit(struct platform_device *pdev)
-{
- struct private_data *priv = platform_get_drvdata(pdev);
-
- if (priv && priv->debugfs) {
- debugfs_remove_recursive(priv->debugfs);
- priv->debugfs = NULL;
- }
-}
-
-#else
-
-static void brcm_avs_cpufreq_debug_init(struct platform_device *pdev) {}
-static void brcm_avs_cpufreq_debug_exit(struct platform_device *pdev) {}
-
-#endif /* CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG */
-
/*
* To ensure the right firmware is running we need to
* - check the MAGIC matches what we expect
@@ -1016,11 +700,8 @@ static int brcm_avs_cpufreq_probe(struct platform_device *pdev)
return ret;
brcm_avs_driver.driver_data = pdev;
- ret = cpufreq_register_driver(&brcm_avs_driver);
- if (!ret)
- brcm_avs_cpufreq_debug_init(pdev);
- return ret;
+ return cpufreq_register_driver(&brcm_avs_driver);
}
static int brcm_avs_cpufreq_remove(struct platform_device *pdev)
@@ -1032,8 +713,6 @@ static int brcm_avs_cpufreq_remove(struct platform_device *pdev)
if (ret)
return ret;
- brcm_avs_cpufreq_debug_exit(pdev);
-
priv = platform_get_drvdata(pdev);
iounmap(priv->base);
iounmap(priv->avs_intr_base);
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index bc5fc16..3464580 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -42,9 +42,6 @@
*/
static struct cppc_cpudata **all_cpu_data;
-/* Capture the max KHz from DMI */
-static u64 cppc_dmi_max_khz;
-
/* Callback function used to retrieve the max frequency from DMI */
static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
{
@@ -75,6 +72,64 @@ static u64 cppc_get_dmi_max_khz(void)
return (1000 * mhz);
}
+/*
+ * If CPPC lowest_freq and nominal_freq registers are exposed then we can
+ * use them to convert perf to freq and vice versa
+ *
+ * If the perf/freq point lies between Nominal and Lowest, we can treat
+ * (Low perf, Low freq) and (Nom Perf, Nom freq) as 2D co-ordinates of a line
+ * and extrapolate the rest
+ * For perf/freq > Nominal, we use the ratio perf:freq at Nominal for conversion
+ */
+static unsigned int cppc_cpufreq_perf_to_khz(struct cppc_cpudata *cpu,
+ unsigned int perf)
+{
+ static u64 max_khz;
+ struct cppc_perf_caps *caps = &cpu->perf_caps;
+ u64 mul, div;
+
+ if (caps->lowest_freq && caps->nominal_freq) {
+ if (perf >= caps->nominal_perf) {
+ mul = caps->nominal_freq;
+ div = caps->nominal_perf;
+ } else {
+ mul = caps->nominal_freq - caps->lowest_freq;
+ div = caps->nominal_perf - caps->lowest_perf;
+ }
+ } else {
+ if (!max_khz)
+ max_khz = cppc_get_dmi_max_khz();
+ mul = max_khz;
+ div = cpu->perf_caps.highest_perf;
+ }
+ return (u64)perf * mul / div;
+}
+
+static unsigned int cppc_cpufreq_khz_to_perf(struct cppc_cpudata *cpu,
+ unsigned int freq)
+{
+ static u64 max_khz;
+ struct cppc_perf_caps *caps = &cpu->perf_caps;
+ u64 mul, div;
+
+ if (caps->lowest_freq && caps->nominal_freq) {
+ if (freq >= caps->nominal_freq) {
+ mul = caps->nominal_perf;
+ div = caps->nominal_freq;
+ } else {
+ mul = caps->lowest_perf;
+ div = caps->lowest_freq;
+ }
+ } else {
+ if (!max_khz)
+ max_khz = cppc_get_dmi_max_khz();
+ mul = cpu->perf_caps.highest_perf;
+ div = max_khz;
+ }
+
+ return (u64)freq * mul / div;
+}
+
static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
unsigned int target_freq,
unsigned int relation)
@@ -86,7 +141,7 @@ static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
cpu = all_cpu_data[policy->cpu];
- desired_perf = (u64)target_freq * cpu->perf_caps.highest_perf / cppc_dmi_max_khz;
+ desired_perf = cppc_cpufreq_khz_to_perf(cpu, target_freq);
/* Return if it is exactly the same perf */
if (desired_perf == cpu->perf_ctrls.desired_perf)
return ret;
@@ -126,6 +181,49 @@ static void cppc_cpufreq_stop_cpu(struct cpufreq_policy *policy)
cpu->perf_caps.lowest_perf, cpu_num, ret);
}
+/*
+ * The PCC subspace describes the rate at which platform can accept commands
+ * on the shared PCC channel (including READs which do not count towards freq
+ * trasition requests), so ideally we need to use the PCC values as a fallback
+ * if we don't have a platform specific transition_delay_us
+ */
+#ifdef CONFIG_ARM64
+#include <asm/cputype.h>
+
+static unsigned int cppc_cpufreq_get_transition_delay_us(int cpu)
+{
+ unsigned long implementor = read_cpuid_implementor();
+ unsigned long part_num = read_cpuid_part_number();
+ unsigned int delay_us = 0;
+
+ switch (implementor) {
+ case ARM_CPU_IMP_QCOM:
+ switch (part_num) {
+ case QCOM_CPU_PART_FALKOR_V1:
+ case QCOM_CPU_PART_FALKOR:
+ delay_us = 10000;
+ break;
+ default:
+ delay_us = cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
+ break;
+ }
+ break;
+ default:
+ delay_us = cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
+ break;
+ }
+
+ return delay_us;
+}
+
+#else
+
+static unsigned int cppc_cpufreq_get_transition_delay_us(int cpu)
+{
+ return cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
+}
+#endif
+
static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
{
struct cppc_cpudata *cpu;
@@ -143,27 +241,26 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
return ret;
}
- cppc_dmi_max_khz = cppc_get_dmi_max_khz();
+ /* Convert the lowest and nominal freq from MHz to KHz */
+ cpu->perf_caps.lowest_freq *= 1000;
+ cpu->perf_caps.nominal_freq *= 1000;
/*
* Set min to lowest nonlinear perf to avoid any efficiency penalty (see
* Section 8.4.7.1.1.5 of ACPI 6.1 spec)
*/
- policy->min = cpu->perf_caps.lowest_nonlinear_perf * cppc_dmi_max_khz /
- cpu->perf_caps.highest_perf;
- policy->max = cppc_dmi_max_khz;
+ policy->min = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.lowest_nonlinear_perf);
+ policy->max = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.highest_perf);
/*
* Set cpuinfo.min_freq to Lowest to make the full range of performance
* available if userspace wants to use any perf between lowest & lowest
* nonlinear perf
*/
- policy->cpuinfo.min_freq = cpu->perf_caps.lowest_perf * cppc_dmi_max_khz /
- cpu->perf_caps.highest_perf;
- policy->cpuinfo.max_freq = cppc_dmi_max_khz;
+ policy->cpuinfo.min_freq = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.lowest_perf);
+ policy->cpuinfo.max_freq = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.highest_perf);
- policy->transition_delay_us = cppc_get_transition_latency(cpu_num) /
- NSEC_PER_USEC;
+ policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu_num);
policy->shared_type = cpu->shared_type;
if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) {
@@ -187,7 +284,8 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
cpu->cur_policy = policy;
/* Set policy->cur to max now. The governors will adjust later. */
- policy->cur = cppc_dmi_max_khz;
+ policy->cur = cppc_cpufreq_perf_to_khz(cpu,
+ cpu->perf_caps.highest_perf);
cpu->perf_ctrls.desired_perf = cpu->perf_caps.highest_perf;
ret = cppc_set_perf(cpu_num, &cpu->perf_ctrls);
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 3b585e4..fe14c57 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -66,8 +66,6 @@ static const struct of_device_id whitelist[] __initconst = {
{ .compatible = "renesas,r8a7792", },
{ .compatible = "renesas,r8a7793", },
{ .compatible = "renesas,r8a7794", },
- { .compatible = "renesas,r8a7795", },
- { .compatible = "renesas,r8a7796", },
{ .compatible = "renesas,sh73a0", },
{ .compatible = "rockchip,rk2928", },
@@ -118,6 +116,9 @@ static const struct of_device_id blacklist[] __initconst = {
{ .compatible = "nvidia,tegra124", },
+ { .compatible = "qcom,apq8096", },
+ { .compatible = "qcom,msm8996", },
+
{ .compatible = "st,stih407", },
{ .compatible = "st,stih410", },
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 190ea0d..0a9ebf0 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -346,8 +346,14 @@ static int dt_cpufreq_probe(struct platform_device *pdev)
if (ret)
return ret;
- if (data && data->have_governor_per_policy)
- dt_cpufreq_driver.flags |= CPUFREQ_HAVE_GOVERNOR_PER_POLICY;
+ if (data) {
+ if (data->have_governor_per_policy)
+ dt_cpufreq_driver.flags |= CPUFREQ_HAVE_GOVERNOR_PER_POLICY;
+
+ dt_cpufreq_driver.resume = data->resume;
+ if (data->suspend)
+ dt_cpufreq_driver.suspend = data->suspend;
+ }
ret = cpufreq_register_driver(&dt_cpufreq_driver);
if (ret)
diff --git a/drivers/cpufreq/cpufreq-dt.h b/drivers/cpufreq/cpufreq-dt.h
index 54d774e..d5aeea1 100644
--- a/drivers/cpufreq/cpufreq-dt.h
+++ b/drivers/cpufreq/cpufreq-dt.h
@@ -12,8 +12,13 @@
#include <linux/types.h>
+struct cpufreq_policy;
+
struct cpufreq_dt_platform_data {
bool have_governor_per_policy;
+
+ int (*suspend)(struct cpufreq_policy *policy);
+ int (*resume)(struct cpufreq_policy *policy);
};
#endif /* __CPUFREQ_DT_H__ */
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 075d18f..b0dfd32 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -89,16 +89,7 @@ static void cpufreq_governor_limits(struct cpufreq_policy *policy);
* The mutex locks both lists.
*/
static BLOCKING_NOTIFIER_HEAD(cpufreq_policy_notifier_list);
-static struct srcu_notifier_head cpufreq_transition_notifier_list;
-
-static bool init_cpufreq_transition_notifier_list_called;
-static int __init init_cpufreq_transition_notifier_list(void)
-{
- srcu_init_notifier_head(&cpufreq_transition_notifier_list);
- init_cpufreq_transition_notifier_list_called = true;
- return 0;
-}
-pure_initcall(init_cpufreq_transition_notifier_list);
+SRCU_NOTIFIER_HEAD_STATIC(cpufreq_transition_notifier_list);
static int off __read_mostly;
static int cpufreq_disabled(void)
@@ -300,8 +291,19 @@ static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci)
#endif
}
-static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
- struct cpufreq_freqs *freqs, unsigned int state)
+/**
+ * cpufreq_notify_transition - Notify frequency transition and adjust_jiffies.
+ * @policy: cpufreq policy to enable fast frequency switching for.
+ * @freqs: contain details of the frequency update.
+ * @state: set to CPUFREQ_PRECHANGE or CPUFREQ_POSTCHANGE.
+ *
+ * This function calls the transition notifiers and the "adjust_jiffies"
+ * function. It is called twice on all CPU frequency changes that have
+ * external effects.
+ */
+static void cpufreq_notify_transition(struct cpufreq_policy *policy,
+ struct cpufreq_freqs *freqs,
+ unsigned int state)
{
BUG_ON(irqs_disabled());
@@ -313,52 +315,42 @@ static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
state, freqs->new);
switch (state) {
-
case CPUFREQ_PRECHANGE:
- /* detect if the driver reported a value as "old frequency"
+ /*
+ * Detect if the driver reported a value as "old frequency"
* which is not equal to what the cpufreq core thinks is
* "old frequency".
*/
if (!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) {
- if ((policy) && (policy->cpu == freqs->cpu) &&
- (policy->cur) && (policy->cur != freqs->old)) {
+ if (policy->cur && (policy->cur != freqs->old)) {
pr_debug("Warning: CPU frequency is %u, cpufreq assumed %u kHz\n",
freqs->old, policy->cur);
freqs->old = policy->cur;
}
}
- srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
- CPUFREQ_PRECHANGE, freqs);
+
+ for_each_cpu(freqs->cpu, policy->cpus) {
+ srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
+ CPUFREQ_PRECHANGE, freqs);
+ }
+
adjust_jiffies(CPUFREQ_PRECHANGE, freqs);
break;
case CPUFREQ_POSTCHANGE:
adjust_jiffies(CPUFREQ_POSTCHANGE, freqs);
- pr_debug("FREQ: %lu - CPU: %lu\n",
- (unsigned long)freqs->new, (unsigned long)freqs->cpu);
- trace_cpu_frequency(freqs->new, freqs->cpu);
- cpufreq_stats_record_transition(policy, freqs->new);
- srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
- CPUFREQ_POSTCHANGE, freqs);
- if (likely(policy) && likely(policy->cpu == freqs->cpu))
- policy->cur = freqs->new;
- break;
- }
-}
+ pr_debug("FREQ: %u - CPUs: %*pbl\n", freqs->new,
+ cpumask_pr_args(policy->cpus));
-/**
- * cpufreq_notify_transition - call notifier chain and adjust_jiffies
- * on frequency transition.
- *
- * This function calls the transition notifiers and the "adjust_jiffies"
- * function. It is called twice on all CPU frequency changes that have
- * external effects.
- */
-static void cpufreq_notify_transition(struct cpufreq_policy *policy,
- struct cpufreq_freqs *freqs, unsigned int state)
-{
- for_each_cpu(freqs->cpu, policy->cpus)
- __cpufreq_notify_transition(policy, freqs, state);
+ for_each_cpu(freqs->cpu, policy->cpus) {
+ trace_cpu_frequency(freqs->new, freqs->cpu);
+ srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
+ CPUFREQ_POSTCHANGE, freqs);
+ }
+
+ cpufreq_stats_record_transition(policy, freqs->new);
+ policy->cur = freqs->new;
+ }
}
/* Do post notifications when there are chances that transition has failed */
@@ -696,6 +688,8 @@ static ssize_t store_##file_name \
struct cpufreq_policy new_policy; \
\
memcpy(&new_policy, policy, sizeof(*policy)); \
+ new_policy.min = policy->user_policy.min; \
+ new_policy.max = policy->user_policy.max; \
\
ret = sscanf(buf, "%u", &new_policy.object); \
if (ret != 1) \
@@ -1764,8 +1758,6 @@ int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list)
if (cpufreq_disabled())
return -EINVAL;
- WARN_ON(!init_cpufreq_transition_notifier_list_called);
-
switch (list) {
case CPUFREQ_TRANSITION_NOTIFIER:
mutex_lock(&cpufreq_fast_switch_lock);
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index ca38229..871bf9c 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -278,7 +278,7 @@ static void dbs_update_util_handler(struct update_util_data *data, u64 time,
struct policy_dbs_info *policy_dbs = cdbs->policy_dbs;
u64 delta_ns, lst;
- if (!cpufreq_can_do_remote_dvfs(policy_dbs->policy))
+ if (!cpufreq_this_cpu_can_update(policy_dbs->policy))
return;
/*
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 17e566af..08960a5 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1939,13 +1939,51 @@ static int intel_cpufreq_verify_policy(struct cpufreq_policy *policy)
return 0;
}
+/* Use of trace in passive mode:
+ *
+ * In passive mode the trace core_busy field (also known as the
+ * performance field, and lablelled as such on the graphs; also known as
+ * core_avg_perf) is not needed and so is re-assigned to indicate if the
+ * driver call was via the normal or fast switch path. Various graphs
+ * output from the intel_pstate_tracer.py utility that include core_busy
+ * (or performance or core_avg_perf) have a fixed y-axis from 0 to 100%,
+ * so we use 10 to indicate the the normal path through the driver, and
+ * 90 to indicate the fast switch path through the driver.
+ * The scaled_busy field is not used, and is set to 0.
+ */
+
+#define INTEL_PSTATE_TRACE_TARGET 10
+#define INTEL_PSTATE_TRACE_FAST_SWITCH 90
+
+static void intel_cpufreq_trace(struct cpudata *cpu, unsigned int trace_type, int old_pstate)
+{
+ struct sample *sample;
+
+ if (!trace_pstate_sample_enabled())
+ return;
+
+ if (!intel_pstate_sample(cpu, ktime_get()))
+ return;
+
+ sample = &cpu->sample;
+ trace_pstate_sample(trace_type,
+ 0,
+ old_pstate,
+ cpu->pstate.current_pstate,
+ sample->mperf,
+ sample->aperf,
+ sample->tsc,
+ get_avg_frequency(cpu),
+ fp_toint(cpu->iowait_boost * 100));
+}
+
static int intel_cpufreq_target(struct cpufreq_policy *policy,
unsigned int target_freq,
unsigned int relation)
{
struct cpudata *cpu = all_cpu_data[policy->cpu];
struct cpufreq_freqs freqs;
- int target_pstate;
+ int target_pstate, old_pstate;
update_turbo_state();
@@ -1965,12 +2003,14 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy,
break;
}
target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
+ old_pstate = cpu->pstate.current_pstate;
if (target_pstate != cpu->pstate.current_pstate) {
cpu->pstate.current_pstate = target_pstate;
wrmsrl_on_cpu(policy->cpu, MSR_IA32_PERF_CTL,
pstate_funcs.get_val(cpu, target_pstate));
}
freqs.new = target_pstate * cpu->pstate.scaling;
+ intel_cpufreq_trace(cpu, INTEL_PSTATE_TRACE_TARGET, old_pstate);
cpufreq_freq_transition_end(policy, &freqs, false);
return 0;
@@ -1980,13 +2020,15 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy,
unsigned int target_freq)
{
struct cpudata *cpu = all_cpu_data[policy->cpu];
- int target_pstate;
+ int target_pstate, old_pstate;
update_turbo_state();
target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling);
target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
+ old_pstate = cpu->pstate.current_pstate;
intel_pstate_update_pstate(cpu, target_pstate);
+ intel_cpufreq_trace(cpu, INTEL_PSTATE_TRACE_FAST_SWITCH, old_pstate);
return target_pstate * cpu->pstate.scaling;
}
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 0591874..54edaec 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -679,6 +679,16 @@ void gpstate_timer_handler(struct timer_list *t)
if (!spin_trylock(&gpstates->gpstate_lock))
return;
+ /*
+ * If the timer has migrated to the different cpu then bring
+ * it back to one of the policy->cpus
+ */
+ if (!cpumask_test_cpu(raw_smp_processor_id(), policy->cpus)) {
+ gpstates->timer.expires = jiffies + msecs_to_jiffies(1);
+ add_timer_on(&gpstates->timer, cpumask_first(policy->cpus));
+ spin_unlock(&gpstates->gpstate_lock);
+ return;
+ }
/*
* If PMCR was last updated was using fast_swtich then
@@ -718,10 +728,8 @@ void gpstate_timer_handler(struct timer_list *t)
if (gpstate_idx != gpstates->last_lpstate_idx)
queue_gpstate_timer(gpstates);
+ set_pstate(&freq_data);
spin_unlock(&gpstates->gpstate_lock);
-
- /* Timer may get migrated to a different cpu on cpu hot unplug */
- smp_call_function_any(policy->cpus, set_pstate, &freq_data, 1);
}
/*
diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c
new file mode 100644
index 0000000..d049fe4
--- /dev/null
+++ b/drivers/cpufreq/qcom-cpufreq-kryo.c
@@ -0,0 +1,212 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ */
+
+/*
+ * In Certain QCOM SoCs like apq8096 and msm8996 that have KRYO processors,
+ * the CPU frequency subset and voltage value of each OPP varies
+ * based on the silicon variant in use. Qualcomm Process Voltage Scaling Tables
+ * defines the voltage and frequency value based on the msm-id in SMEM
+ * and speedbin blown in the efuse combination.
+ * The qcom-cpufreq-kryo driver reads the msm-id and efuse value from the SoC
+ * to provide the OPP framework with required information.
+ * This is used to determine the voltage and frequency value for each OPP of
+ * operating-points-v2 table when it is parsed by the OPP framework.
+ */
+
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/nvmem-consumer.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/slab.h>
+#include <linux/soc/qcom/smem.h>
+
+#define MSM_ID_SMEM 137
+
+enum _msm_id {
+ MSM8996V3 = 0xF6ul,
+ APQ8096V3 = 0x123ul,
+ MSM8996SG = 0x131ul,
+ APQ8096SG = 0x138ul,
+};
+
+enum _msm8996_version {
+ MSM8996_V3,
+ MSM8996_SG,
+ NUM_OF_MSM8996_VERSIONS,
+};
+
+static enum _msm8996_version __init qcom_cpufreq_kryo_get_msm_id(void)
+{
+ size_t len;
+ u32 *msm_id;
+ enum _msm8996_version version;
+
+ msm_id = qcom_smem_get(QCOM_SMEM_HOST_ANY, MSM_ID_SMEM, &len);
+ if (IS_ERR(msm_id))
+ return NUM_OF_MSM8996_VERSIONS;
+
+ /* The first 4 bytes are format, next to them is the actual msm-id */
+ msm_id++;
+
+ switch ((enum _msm_id)*msm_id) {
+ case MSM8996V3:
+ case APQ8096V3:
+ version = MSM8996_V3;
+ break;
+ case MSM8996SG:
+ case APQ8096SG:
+ version = MSM8996_SG;
+ break;
+ default:
+ version = NUM_OF_MSM8996_VERSIONS;
+ }
+
+ return version;
+}
+
+static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
+{
+ struct opp_table *opp_tables[NR_CPUS] = {0};
+ struct platform_device *cpufreq_dt_pdev;
+ enum _msm8996_version msm8996_version;
+ struct nvmem_cell *speedbin_nvmem;
+ struct device_node *np;
+ struct device *cpu_dev;
+ unsigned cpu;
+ u8 *speedbin;
+ u32 versions;
+ size_t len;
+ int ret;
+
+ cpu_dev = get_cpu_device(0);
+ if (NULL == cpu_dev)
+ ret = -ENODEV;
+
+ msm8996_version = qcom_cpufreq_kryo_get_msm_id();
+ if (NUM_OF_MSM8996_VERSIONS == msm8996_version) {
+ dev_err(cpu_dev, "Not Snapdragon 820/821!");
+ return -ENODEV;
+ }
+
+ np = dev_pm_opp_of_get_opp_desc_node(cpu_dev);
+ if (IS_ERR(np))
+ return PTR_ERR(np);
+
+ ret = of_device_is_compatible(np, "operating-points-v2-kryo-cpu");
+ if (!ret) {
+ of_node_put(np);
+ return -ENOENT;
+ }
+
+ speedbin_nvmem = of_nvmem_cell_get(np, NULL);
+ of_node_put(np);
+ if (IS_ERR(speedbin_nvmem)) {
+ dev_err(cpu_dev, "Could not get nvmem cell: %ld\n",
+ PTR_ERR(speedbin_nvmem));
+ return PTR_ERR(speedbin_nvmem);
+ }
+
+ speedbin = nvmem_cell_read(speedbin_nvmem, &len);
+ nvmem_cell_put(speedbin_nvmem);
+
+ switch (msm8996_version) {
+ case MSM8996_V3:
+ versions = 1 << (unsigned int)(*speedbin);
+ break;
+ case MSM8996_SG:
+ versions = 1 << ((unsigned int)(*speedbin) + 4);
+ break;
+ default:
+ BUG();
+ break;
+ }
+
+ for_each_possible_cpu(cpu) {
+ cpu_dev = get_cpu_device(cpu);
+ if (NULL == cpu_dev) {
+ ret = -ENODEV;
+ goto free_opp;
+ }
+
+ opp_tables[cpu] = dev_pm_opp_set_supported_hw(cpu_dev,
+ &versions, 1);
+ if (IS_ERR(opp_tables[cpu])) {
+ ret = PTR_ERR(opp_tables[cpu]);
+ dev_err(cpu_dev, "Failed to set supported hardware\n");
+ goto free_opp;
+ }
+ }
+
+ cpufreq_dt_pdev = platform_device_register_simple("cpufreq-dt", -1,
+ NULL, 0);
+ if (!IS_ERR(cpufreq_dt_pdev))
+ return 0;
+
+ ret = PTR_ERR(cpufreq_dt_pdev);
+ dev_err(cpu_dev, "Failed to register platform device\n");
+
+free_opp:
+ for_each_possible_cpu(cpu) {
+ if (IS_ERR_OR_NULL(opp_tables[cpu]))
+ break;
+ dev_pm_opp_put_supported_hw(opp_tables[cpu]);
+ }
+
+ return ret;
+}
+
+static struct platform_driver qcom_cpufreq_kryo_driver = {
+ .probe = qcom_cpufreq_kryo_probe,
+ .driver = {
+ .name = "qcom-cpufreq-kryo",
+ },
+};
+
+static const struct of_device_id qcom_cpufreq_kryo_match_list[] __initconst = {
+ { .compatible = "qcom,apq8096", },
+ { .compatible = "qcom,msm8996", },
+};
+
+/*
+ * Since the driver depends on smem and nvmem drivers, which may
+ * return EPROBE_DEFER, all the real activity is done in the probe,
+ * which may be defered as well. The init here is only registering
+ * the driver and the platform device.
+ */
+static int __init qcom_cpufreq_kryo_init(void)
+{
+ struct device_node *np = of_find_node_by_path("/");
+ const struct of_device_id *match;
+ int ret;
+
+ if (!np)
+ return -ENODEV;
+
+ match = of_match_node(qcom_cpufreq_kryo_match_list, np);
+ of_node_put(np);
+ if (!match)
+ return -ENODEV;
+
+ ret = platform_driver_register(&qcom_cpufreq_kryo_driver);
+ if (unlikely(ret < 0))
+ return ret;
+
+ ret = PTR_ERR_OR_ZERO(platform_device_register_simple(
+ "qcom-cpufreq-kryo", -1, NULL, 0));
+ if (0 == ret)
+ return 0;
+
+ platform_driver_unregister(&qcom_cpufreq_kryo_driver);
+ return ret;
+}
+module_init(qcom_cpufreq_kryo_init);
+
+MODULE_DESCRIPTION("Qualcomm Technologies, Inc. Kryo CPUfreq driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/cpufreq/s3c2440-cpufreq.c b/drivers/cpufreq/s3c2440-cpufreq.c
index d0d75b6..d2f67b7 100644
--- a/drivers/cpufreq/s3c2440-cpufreq.c
+++ b/drivers/cpufreq/s3c2440-cpufreq.c
@@ -143,7 +143,7 @@ static void s3c2440_cpufreq_setdivs(struct s3c_cpufreq_config *cfg)
{
unsigned long clkdiv, camdiv;
- s3c_freq_dbg("%s: divsiors: h=%d, p=%d\n", __func__,
+ s3c_freq_dbg("%s: divisors: h=%d, p=%d\n", __func__,
cfg->divs.h_divisor, cfg->divs.p_divisor);
clkdiv = __raw_readl(S3C2410_CLKDIVN);
diff --git a/drivers/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c
index e3a9962..cabb6f4 100644
--- a/drivers/cpufreq/speedstep-lib.c
+++ b/drivers/cpufreq/speedstep-lib.c
@@ -252,7 +252,7 @@ EXPORT_SYMBOL_GPL(speedstep_get_frequency);
*********************************************************************/
/* Keep in sync with the x86_cpu_id tables in the different modules */
-unsigned int speedstep_detect_processor(void)
+enum speedstep_processor speedstep_detect_processor(void)
{
struct cpuinfo_x86 *c = &cpu_data(0);
u32 ebx, msr_lo, msr_hi;
diff --git a/drivers/cpufreq/tegra20-cpufreq.c b/drivers/cpufreq/tegra20-cpufreq.c
index 2bd6284..05f57dc 100644
--- a/drivers/cpufreq/tegra20-cpufreq.c
+++ b/drivers/cpufreq/tegra20-cpufreq.c
@@ -16,16 +16,13 @@
*
*/
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/sched.h>
-#include <linux/cpufreq.h>
-#include <linux/delay.h>
-#include <linux/init.h>
-#include <linux/err.h>
#include <linux/clk.h>
-#include <linux/io.h>
+#include <linux/cpufreq.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/types.h>
static struct cpufreq_frequency_table freq_table[] = {
{ .frequency = 216000 },
@@ -39,25 +36,27 @@ static struct cpufreq_frequency_table freq_table[] = {
{ .frequency = CPUFREQ_TABLE_END },
};
-#define NUM_CPUS 2
-
-static struct clk *cpu_clk;
-static struct clk *pll_x_clk;
-static struct clk *pll_p_clk;
-static struct clk *emc_clk;
-static bool pll_x_prepared;
+struct tegra20_cpufreq {
+ struct device *dev;
+ struct cpufreq_driver driver;
+ struct clk *cpu_clk;
+ struct clk *pll_x_clk;
+ struct clk *pll_p_clk;
+ bool pll_x_prepared;
+};
static unsigned int tegra_get_intermediate(struct cpufreq_policy *policy,
unsigned int index)
{
- unsigned int ifreq = clk_get_rate(pll_p_clk) / 1000;
+ struct tegra20_cpufreq *cpufreq = cpufreq_get_driver_data();
+ unsigned int ifreq = clk_get_rate(cpufreq->pll_p_clk) / 1000;
/*
* Don't switch to intermediate freq if:
* - we are already at it, i.e. policy->cur == ifreq
* - index corresponds to ifreq
*/
- if ((freq_table[index].frequency == ifreq) || (policy->cur == ifreq))
+ if (freq_table[index].frequency == ifreq || policy->cur == ifreq)
return 0;
return ifreq;
@@ -66,6 +65,7 @@ static unsigned int tegra_get_intermediate(struct cpufreq_policy *policy,
static int tegra_target_intermediate(struct cpufreq_policy *policy,
unsigned int index)
{
+ struct tegra20_cpufreq *cpufreq = cpufreq_get_driver_data();
int ret;
/*
@@ -78,47 +78,37 @@ static int tegra_target_intermediate(struct cpufreq_policy *policy,
* Also, we wouldn't be using pll_x anymore and must not take extra
* reference to it, as it can be disabled now to save some power.
*/
- clk_prepare_enable(pll_x_clk);
+ clk_prepare_enable(cpufreq->pll_x_clk);
- ret = clk_set_parent(cpu_clk, pll_p_clk);
+ ret = clk_set_parent(cpufreq->cpu_clk, cpufreq->pll_p_clk);
if (ret)
- clk_disable_unprepare(pll_x_clk);
+ clk_disable_unprepare(cpufreq->pll_x_clk);
else
- pll_x_prepared = true;
+ cpufreq->pll_x_prepared = true;
return ret;
}
static int tegra_target(struct cpufreq_policy *policy, unsigned int index)
{
+ struct tegra20_cpufreq *cpufreq = cpufreq_get_driver_data();
unsigned long rate = freq_table[index].frequency;
- unsigned int ifreq = clk_get_rate(pll_p_clk) / 1000;
- int ret = 0;
-
- /*
- * Vote on memory bus frequency based on cpu frequency
- * This sets the minimum frequency, display or avp may request higher
- */
- if (rate >= 816000)
- clk_set_rate(emc_clk, 600000000); /* cpu 816 MHz, emc max */
- else if (rate >= 456000)
- clk_set_rate(emc_clk, 300000000); /* cpu 456 MHz, emc 150Mhz */
- else
- clk_set_rate(emc_clk, 100000000); /* emc 50Mhz */
+ unsigned int ifreq = clk_get_rate(cpufreq->pll_p_clk) / 1000;
+ int ret;
/*
* target freq == pll_p, don't need to take extra reference to pll_x_clk
* as it isn't used anymore.
*/
if (rate == ifreq)
- return clk_set_parent(cpu_clk, pll_p_clk);
+ return clk_set_parent(cpufreq->cpu_clk, cpufreq->pll_p_clk);
- ret = clk_set_rate(pll_x_clk, rate * 1000);
+ ret = clk_set_rate(cpufreq->pll_x_clk, rate * 1000);
/* Restore to earlier frequency on error, i.e. pll_x */
if (ret)
- pr_err("Failed to change pll_x to %lu\n", rate);
+ dev_err(cpufreq->dev, "Failed to change pll_x to %lu\n", rate);
- ret = clk_set_parent(cpu_clk, pll_x_clk);
+ ret = clk_set_parent(cpufreq->cpu_clk, cpufreq->pll_x_clk);
/* This shouldn't fail while changing or restoring */
WARN_ON(ret);
@@ -126,9 +116,9 @@ static int tegra_target(struct cpufreq_policy *policy, unsigned int index)
* Drop count to pll_x clock only if we switched to intermediate freq
* earlier while transitioning to a target frequency.
*/
- if (pll_x_prepared) {
- clk_disable_unprepare(pll_x_clk);
- pll_x_prepared = false;
+ if (cpufreq->pll_x_prepared) {
+ clk_disable_unprepare(cpufreq->pll_x_clk);
+ cpufreq->pll_x_prepared = false;
}
return ret;
@@ -136,81 +126,111 @@ static int tegra_target(struct cpufreq_policy *policy, unsigned int index)
static int tegra_cpu_init(struct cpufreq_policy *policy)
{
+ struct tegra20_cpufreq *cpufreq = cpufreq_get_driver_data();
int ret;
- if (policy->cpu >= NUM_CPUS)
- return -EINVAL;
-
- clk_prepare_enable(emc_clk);
- clk_prepare_enable(cpu_clk);
+ clk_prepare_enable(cpufreq->cpu_clk);
/* FIXME: what's the actual transition time? */
ret = cpufreq_generic_init(policy, freq_table, 300 * 1000);
if (ret) {
- clk_disable_unprepare(cpu_clk);
- clk_disable_unprepare(emc_clk);
+ clk_disable_unprepare(cpufreq->cpu_clk);
return ret;
}
- policy->clk = cpu_clk;
+ policy->clk = cpufreq->cpu_clk;
policy->suspend_freq = freq_table[0].frequency;
return 0;
}
static int tegra_cpu_exit(struct cpufreq_policy *policy)
{
- clk_disable_unprepare(cpu_clk);
- clk_disable_unprepare(emc_clk);
+ struct tegra20_cpufreq *cpufreq = cpufreq_get_driver_data();
+
+ clk_disable_unprepare(cpufreq->cpu_clk);
return 0;
}
-static struct cpufreq_driver tegra_cpufreq_driver = {
- .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK,
- .verify = cpufreq_generic_frequency_table_verify,
- .get_intermediate = tegra_get_intermediate,
- .target_intermediate = tegra_target_intermediate,
- .target_index = tegra_target,
- .get = cpufreq_generic_get,
- .init = tegra_cpu_init,
- .exit = tegra_cpu_exit,
- .name = "tegra",
- .attr = cpufreq_generic_attr,
- .suspend = cpufreq_generic_suspend,
-};
-
-static int __init tegra_cpufreq_init(void)
+static int tegra20_cpufreq_probe(struct platform_device *pdev)
{
- cpu_clk = clk_get_sys(NULL, "cclk");
- if (IS_ERR(cpu_clk))
- return PTR_ERR(cpu_clk);
+ struct tegra20_cpufreq *cpufreq;
+ int err;
- pll_x_clk = clk_get_sys(NULL, "pll_x");
- if (IS_ERR(pll_x_clk))
- return PTR_ERR(pll_x_clk);
+ cpufreq = devm_kzalloc(&pdev->dev, sizeof(*cpufreq), GFP_KERNEL);
+ if (!cpufreq)
+ return -ENOMEM;
- pll_p_clk = clk_get_sys(NULL, "pll_p");
- if (IS_ERR(pll_p_clk))
- return PTR_ERR(pll_p_clk);
+ cpufreq->cpu_clk = clk_get_sys(NULL, "cclk");
+ if (IS_ERR(cpufreq->cpu_clk))
+ return PTR_ERR(cpufreq->cpu_clk);
- emc_clk = clk_get_sys("cpu", "emc");
- if (IS_ERR(emc_clk)) {
- clk_put(cpu_clk);
- return PTR_ERR(emc_clk);
+ cpufreq->pll_x_clk = clk_get_sys(NULL, "pll_x");
+ if (IS_ERR(cpufreq->pll_x_clk)) {
+ err = PTR_ERR(cpufreq->pll_x_clk);
+ goto put_cpu;
}
- return cpufreq_register_driver(&tegra_cpufreq_driver);
+ cpufreq->pll_p_clk = clk_get_sys(NULL, "pll_p");
+ if (IS_ERR(cpufreq->pll_p_clk)) {
+ err = PTR_ERR(cpufreq->pll_p_clk);
+ goto put_pll_x;
+ }
+
+ cpufreq->dev = &pdev->dev;
+ cpufreq->driver.get = cpufreq_generic_get;
+ cpufreq->driver.attr = cpufreq_generic_attr;
+ cpufreq->driver.init = tegra_cpu_init;
+ cpufreq->driver.exit = tegra_cpu_exit;
+ cpufreq->driver.flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK;
+ cpufreq->driver.verify = cpufreq_generic_frequency_table_verify;
+ cpufreq->driver.suspend = cpufreq_generic_suspend;
+ cpufreq->driver.driver_data = cpufreq;
+ cpufreq->driver.target_index = tegra_target;
+ cpufreq->driver.get_intermediate = tegra_get_intermediate;
+ cpufreq->driver.target_intermediate = tegra_target_intermediate;
+ snprintf(cpufreq->driver.name, CPUFREQ_NAME_LEN, "tegra");
+
+ err = cpufreq_register_driver(&cpufreq->driver);
+ if (err)
+ goto put_pll_p;
+
+ platform_set_drvdata(pdev, cpufreq);
+
+ return 0;
+
+put_pll_p:
+ clk_put(cpufreq->pll_p_clk);
+put_pll_x:
+ clk_put(cpufreq->pll_x_clk);
+put_cpu:
+ clk_put(cpufreq->cpu_clk);
+
+ return err;
}
-static void __exit tegra_cpufreq_exit(void)
+static int tegra20_cpufreq_remove(struct platform_device *pdev)
{
- cpufreq_unregister_driver(&tegra_cpufreq_driver);
- clk_put(emc_clk);
- clk_put(cpu_clk);
+ struct tegra20_cpufreq *cpufreq = platform_get_drvdata(pdev);
+
+ cpufreq_unregister_driver(&cpufreq->driver);
+
+ clk_put(cpufreq->pll_p_clk);
+ clk_put(cpufreq->pll_x_clk);
+ clk_put(cpufreq->cpu_clk);
+
+ return 0;
}
+static struct platform_driver tegra20_cpufreq_driver = {
+ .probe = tegra20_cpufreq_probe,
+ .remove = tegra20_cpufreq_remove,
+ .driver = {
+ .name = "tegra20-cpufreq",
+ },
+};
+module_platform_driver(tegra20_cpufreq_driver);
+MODULE_ALIAS("platform:tegra20-cpufreq");
MODULE_AUTHOR("Colin Cross <ccross@android.com>");
-MODULE_DESCRIPTION("cpufreq driver for Nvidia Tegra2");
+MODULE_DESCRIPTION("NVIDIA Tegra20 cpufreq driver");
MODULE_LICENSE("GPL");
-module_init(tegra_cpufreq_init);
-module_exit(tegra_cpufreq_exit);
diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c
index 5d359af..9fed1b82 100644
--- a/drivers/cpuidle/governor.c
+++ b/drivers/cpuidle/governor.c
@@ -8,8 +8,10 @@
* This code is licenced under the GPL.
*/
-#include <linux/mutex.h>
+#include <linux/cpu.h>
#include <linux/cpuidle.h>
+#include <linux/mutex.h>
+#include <linux/pm_qos.h>
#include "cpuidle.h"
@@ -93,3 +95,16 @@ int cpuidle_register_governor(struct cpuidle_governor *gov)
return ret;
}
+
+/**
+ * cpuidle_governor_latency_req - Compute a latency constraint for CPU
+ * @cpu: Target CPU
+ */
+int cpuidle_governor_latency_req(unsigned int cpu)
+{
+ int global_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
+ struct device *device = get_cpu_device(cpu);
+ int device_req = dev_pm_qos_raw_read_value(device);
+
+ return device_req < global_req ? device_req : global_req;
+}
diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c
index b24883f..704880a 100644
--- a/drivers/cpuidle/governors/ladder.c
+++ b/drivers/cpuidle/governors/ladder.c
@@ -14,10 +14,8 @@
#include <linux/kernel.h>
#include <linux/cpuidle.h>
-#include <linux/pm_qos.h>
#include <linux/jiffies.h>
#include <linux/tick.h>
-#include <linux/cpu.h>
#include <asm/io.h>
#include <linux/uaccess.h>
@@ -69,16 +67,10 @@ static int ladder_select_state(struct cpuidle_driver *drv,
struct cpuidle_device *dev, bool *dummy)
{
struct ladder_device *ldev = this_cpu_ptr(&ladder_devices);
- struct device *device = get_cpu_device(dev->cpu);
struct ladder_device_state *last_state;
int last_residency, last_idx = ldev->last_state_idx;
int first_idx = drv->states[0].flags & CPUIDLE_FLAG_POLLING ? 1 : 0;
- int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
- int resume_latency = dev_pm_qos_raw_read_value(device);
-
- if (resume_latency < latency_req &&
- resume_latency != PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
- latency_req = resume_latency;
+ int latency_req = cpuidle_governor_latency_req(dev->cpu);
/* Special case when user has set very strict latency requirement */
if (unlikely(latency_req == 0)) {
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 1bfe03c..1aef60d1 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -12,7 +12,6 @@
#include <linux/kernel.h>
#include <linux/cpuidle.h>
-#include <linux/pm_qos.h>
#include <linux/time.h>
#include <linux/ktime.h>
#include <linux/hrtimer.h>
@@ -21,7 +20,6 @@
#include <linux/sched/loadavg.h>
#include <linux/sched/stat.h>
#include <linux/math64.h>
-#include <linux/cpu.h>
/*
* Please note when changing the tuning values:
@@ -286,15 +284,13 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
bool *stop_tick)
{
struct menu_device *data = this_cpu_ptr(&menu_devices);
- struct device *device = get_cpu_device(dev->cpu);
- int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
+ int latency_req = cpuidle_governor_latency_req(dev->cpu);
int i;
int first_idx;
int idx;
unsigned int interactivity_req;
unsigned int expected_interval;
unsigned long nr_iowaiters, cpu_load;
- int resume_latency = dev_pm_qos_raw_read_value(device);
ktime_t delta_next;
if (data->needs_update) {
@@ -302,10 +298,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
data->needs_update = 0;
}
- if (resume_latency < latency_req &&
- resume_latency != PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
- latency_req = resume_latency;
-
/* Special case when user has set very strict latency requirement */
if (unlikely(latency_req == 0)) {
*stop_tick = false;
diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 46ab2d0..4e86f86 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -153,8 +153,8 @@ static int eip197_load_firmwares(struct safexcel_crypto_priv *priv)
EIP197_PE_ICE_SCRATCH_CTRL_CHANGE_ACCESS;
writel(val, EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_CTRL);
- memset(EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_RAM, 0,
- EIP197_NUM_OF_SCRATCH_BLOCKS * sizeof(u32));
+ memset_io(EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_RAM, 0,
+ EIP197_NUM_OF_SCRATCH_BLOCKS * sizeof(u32));
eip197_write_firmware(priv, fw[FW_IFPP], EIP197_PE_ICE_FPP_CTRL,
EIP197_PE_ICE_RAM_CTRL_FPP_PROG_EN);
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index be86064..aff2c15 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -19,6 +19,7 @@
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/mm.h>
+#include <linux/mman.h>
#include "dax-private.h"
#include "dax.h"
@@ -540,6 +541,7 @@ static const struct file_operations dax_fops = {
.release = dax_release,
.get_unmapped_area = dax_get_unmapped_area,
.mmap = dax_mmap,
+ .mmap_supported_flags = MAP_SYNC,
};
static void dev_dax_release(struct device *dev)
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 2b2332b..1d7bd96 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -74,42 +74,42 @@ EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
/**
* __bdev_dax_supported() - Check if the device supports dax for filesystem
- * @sb: The superblock of the device
+ * @bdev: block device to check
* @blocksize: The block size of the device
*
* This is a library function for filesystems to check if the block device
* can be mounted with dax option.
*
- * Return: negative errno if unsupported, 0 if supported.
+ * Return: true if supported, false if unsupported
*/
-int __bdev_dax_supported(struct super_block *sb, int blocksize)
+bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
{
- struct block_device *bdev = sb->s_bdev;
struct dax_device *dax_dev;
pgoff_t pgoff;
int err, id;
void *kaddr;
pfn_t pfn;
long len;
+ char buf[BDEVNAME_SIZE];
if (blocksize != PAGE_SIZE) {
- pr_debug("VFS (%s): error: unsupported blocksize for dax\n",
- sb->s_id);
- return -EINVAL;
+ pr_debug("%s: error: unsupported blocksize for dax\n",
+ bdevname(bdev, buf));
+ return false;
}
err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
if (err) {
- pr_debug("VFS (%s): error: unaligned partition for dax\n",
- sb->s_id);
- return err;
+ pr_debug("%s: error: unaligned partition for dax\n",
+ bdevname(bdev, buf));
+ return false;
}
dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
if (!dax_dev) {
- pr_debug("VFS (%s): error: device does not support dax\n",
- sb->s_id);
- return -EOPNOTSUPP;
+ pr_debug("%s: error: device does not support dax\n",
+ bdevname(bdev, buf));
+ return false;
}
id = dax_read_lock();
@@ -119,9 +119,9 @@ int __bdev_dax_supported(struct super_block *sb, int blocksize)
put_dax(dax_dev);
if (len < 1) {
- pr_debug("VFS (%s): error: dax access failed (%ld)\n",
- sb->s_id, len);
- return len < 0 ? len : -EIO;
+ pr_debug("%s: error: dax access failed (%ld)\n",
+ bdevname(bdev, buf), len);
+ return false;
}
if (IS_ENABLED(CONFIG_FS_DAX_LIMITED) && pfn_t_special(pfn)) {
@@ -137,12 +137,12 @@ int __bdev_dax_supported(struct super_block *sb, int blocksize)
} else if (pfn_t_devmap(pfn)) {
/* pass */;
} else {
- pr_debug("VFS (%s): error: dax support not enabled\n",
- sb->s_id);
- return -EOPNOTSUPP;
+ pr_debug("%s: error: dax support not enabled\n",
+ bdevname(bdev, buf));
+ return false;
}
- return 0;
+ return true;
}
EXPORT_SYMBOL_GPL(__bdev_dax_supported);
#endif
diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c
index d29275b..4a828c1 100644
--- a/drivers/dma/qcom/bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -524,6 +524,14 @@ static int bam_alloc_chan(struct dma_chan *chan)
return 0;
}
+static int bam_pm_runtime_get_sync(struct device *dev)
+{
+ if (pm_runtime_enabled(dev))
+ return pm_runtime_get_sync(dev);
+
+ return 0;
+}
+
/**
* bam_free_chan - Frees dma resources associated with specific channel
* @chan: specified channel
@@ -539,7 +547,7 @@ static void bam_free_chan(struct dma_chan *chan)
unsigned long flags;
int ret;
- ret = pm_runtime_get_sync(bdev->dev);
+ ret = bam_pm_runtime_get_sync(bdev->dev);
if (ret < 0)
return;
@@ -720,7 +728,7 @@ static int bam_pause(struct dma_chan *chan)
unsigned long flag;
int ret;
- ret = pm_runtime_get_sync(bdev->dev);
+ ret = bam_pm_runtime_get_sync(bdev->dev);
if (ret < 0)
return ret;
@@ -746,7 +754,7 @@ static int bam_resume(struct dma_chan *chan)
unsigned long flag;
int ret;
- ret = pm_runtime_get_sync(bdev->dev);
+ ret = bam_pm_runtime_get_sync(bdev->dev);
if (ret < 0)
return ret;
@@ -852,7 +860,7 @@ static irqreturn_t bam_dma_irq(int irq, void *data)
if (srcs & P_IRQ)
tasklet_schedule(&bdev->task);
- ret = pm_runtime_get_sync(bdev->dev);
+ ret = bam_pm_runtime_get_sync(bdev->dev);
if (ret < 0)
return ret;
@@ -969,7 +977,7 @@ static void bam_start_dma(struct bam_chan *bchan)
if (!vd)
return;
- ret = pm_runtime_get_sync(bdev->dev);
+ ret = bam_pm_runtime_get_sync(bdev->dev);
if (ret < 0)
return;
diff --git a/drivers/dma/qcom/hidma_mgmt.c b/drivers/dma/qcom/hidma_mgmt.c
index 000c7019..d64edeb 100644
--- a/drivers/dma/qcom/hidma_mgmt.c
+++ b/drivers/dma/qcom/hidma_mgmt.c
@@ -398,7 +398,7 @@ static int __init hidma_mgmt_of_populate_channels(struct device_node *np)
}
of_node_get(child);
new_pdev->dev.of_node = child;
- of_dma_configure(&new_pdev->dev, child);
+ of_dma_configure(&new_pdev->dev, child, true);
/*
* It is assumed that calling of_msi_configure is safe on
* platforms with or without MSI support.
diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c
index e6f1782..2b90606 100644
--- a/drivers/firmware/arm_scmi/clock.c
+++ b/drivers/firmware/arm_scmi/clock.c
@@ -284,7 +284,7 @@ scmi_clock_info_get(const struct scmi_handle *handle, u32 clk_id)
struct clock_info *ci = handle->clk_priv;
struct scmi_clock_info *clk = ci->clk + clk_id;
- if (!clk->name || !clk->name[0])
+ if (!clk->name[0])
return NULL;
return clk;
diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c
index 14b1471..2455be8 100644
--- a/drivers/firmware/arm_scmi/driver.c
+++ b/drivers/firmware/arm_scmi/driver.c
@@ -778,6 +778,7 @@ scmi_create_protocol_device(struct device_node *np, struct scmi_info *info,
if (scmi_mbox_chan_setup(info, &sdev->dev, prot_id)) {
dev_err(&sdev->dev, "failed to setup transport\n");
scmi_device_destroy(sdev);
+ return;
}
/* setup handle now as the transport is ready */
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 3098410..781a4a3 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -174,6 +174,11 @@
depends on UEFI_CPER && ( ARM || ARM64 )
default y
+config UEFI_CPER_X86
+ bool
+ depends on UEFI_CPER && X86
+ default y
+
config EFI_DEV_PATH_PARSER
bool
depends on ACPI
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index cb80537..5f9f503 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -31,3 +31,4 @@
obj-$(CONFIG_ARM64) += $(arm-obj-y)
obj-$(CONFIG_EFI_CAPSULE_LOADER) += capsule-loader.o
obj-$(CONFIG_UEFI_CPER_ARM) += cper-arm.o
+obj-$(CONFIG_UEFI_CPER_X86) += cper-x86.o
diff --git a/drivers/firmware/efi/apple-properties.c b/drivers/firmware/efi/apple-properties.c
index adaa9a37..60a9571 100644
--- a/drivers/firmware/efi/apple-properties.c
+++ b/drivers/firmware/efi/apple-properties.c
@@ -13,6 +13,9 @@
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Note, all properties are considered as u8 arrays.
+ * To get a value of any of them the caller must use device_property_read_u8_array().
*/
#define pr_fmt(fmt) "apple-properties: " fmt
@@ -96,12 +99,13 @@ static void __init unmarshal_key_value_pairs(struct dev_header *dev_header,
entry[i].name = key;
entry[i].length = val_len - sizeof(val_len);
entry[i].is_array = !!entry[i].length;
- entry[i].pointer.raw_data = ptr + key_len + sizeof(val_len);
+ entry[i].type = DEV_PROP_U8;
+ entry[i].pointer.u8_data = ptr + key_len + sizeof(val_len);
if (dump_properties) {
dev_info(dev, "property: %s\n", entry[i].name);
print_hex_dump(KERN_INFO, pr_fmt(), DUMP_PREFIX_OFFSET,
- 16, 1, entry[i].pointer.raw_data,
+ 16, 1, entry[i].pointer.u8_data,
entry[i].length, true);
}
diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c
index e456f46..9668898 100644
--- a/drivers/firmware/efi/capsule-loader.c
+++ b/drivers/firmware/efi/capsule-loader.c
@@ -134,10 +134,16 @@ static ssize_t efi_capsule_submit_update(struct capsule_info *cap_info)
/* Indicate capsule binary uploading is done */
cap_info->index = NO_FURTHER_WRITE_ACTION;
- pr_info("Successfully upload capsule file with reboot type '%s'\n",
- !cap_info->reset_type ? "RESET_COLD" :
- cap_info->reset_type == 1 ? "RESET_WARM" :
- "RESET_SHUTDOWN");
+
+ if (cap_info->header.flags & EFI_CAPSULE_PERSIST_ACROSS_RESET) {
+ pr_info("Successfully uploaded capsule file with reboot type '%s'\n",
+ !cap_info->reset_type ? "RESET_COLD" :
+ cap_info->reset_type == 1 ? "RESET_WARM" :
+ "RESET_SHUTDOWN");
+ } else {
+ pr_info("Successfully processed capsule file\n");
+ }
+
return 0;
}
diff --git a/drivers/firmware/efi/cper-arm.c b/drivers/firmware/efi/cper-arm.c
index 698e5c8..5028113 100644
--- a/drivers/firmware/efi/cper-arm.c
+++ b/drivers/firmware/efi/cper-arm.c
@@ -30,8 +30,6 @@
#include <acpi/ghes.h>
#include <ras/ras_event.h>
-#define INDENT_SP " "
-
static const char * const arm_reg_ctx_strs[] = {
"AArch32 general purpose registers",
"AArch32 EL1 context registers",
@@ -283,7 +281,7 @@ void cper_print_proc_arm(const char *pfx,
pfx, proc->psci_state);
}
- snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
+ snprintf(newpfx, sizeof(newpfx), "%s ", pfx);
err_info = (struct cper_arm_err_info *)(proc + 1);
for (i = 0; i < proc->err_info_num; i++) {
@@ -310,7 +308,7 @@ void cper_print_proc_arm(const char *pfx,
if (err_info->validation_bits & CPER_ARM_INFO_VALID_ERR_INFO) {
printk("%serror_info: 0x%016llx\n", newpfx,
err_info->error_info);
- snprintf(infopfx, sizeof(infopfx), "%s%s", newpfx, INDENT_SP);
+ snprintf(infopfx, sizeof(infopfx), "%s ", newpfx);
cper_print_arm_err_info(infopfx, err_info->type,
err_info->error_info);
}
diff --git a/drivers/firmware/efi/cper-x86.c b/drivers/firmware/efi/cper-x86.c
new file mode 100644
index 0000000..2531de4
--- /dev/null
+++ b/drivers/firmware/efi/cper-x86.c
@@ -0,0 +1,356 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018, Advanced Micro Devices, Inc.
+
+#include <linux/cper.h>
+
+/*
+ * We don't need a "CPER_IA" prefix since these are all locally defined.
+ * This will save us a lot of line space.
+ */
+#define VALID_LAPIC_ID BIT_ULL(0)
+#define VALID_CPUID_INFO BIT_ULL(1)
+#define VALID_PROC_ERR_INFO_NUM(bits) (((bits) & GENMASK_ULL(7, 2)) >> 2)
+#define VALID_PROC_CXT_INFO_NUM(bits) (((bits) & GENMASK_ULL(13, 8)) >> 8)
+
+#define INFO_ERR_STRUCT_TYPE_CACHE \
+ GUID_INIT(0xA55701F5, 0xE3EF, 0x43DE, 0xAC, 0x72, 0x24, 0x9B, \
+ 0x57, 0x3F, 0xAD, 0x2C)
+#define INFO_ERR_STRUCT_TYPE_TLB \
+ GUID_INIT(0xFC06B535, 0x5E1F, 0x4562, 0x9F, 0x25, 0x0A, 0x3B, \
+ 0x9A, 0xDB, 0x63, 0xC3)
+#define INFO_ERR_STRUCT_TYPE_BUS \
+ GUID_INIT(0x1CF3F8B3, 0xC5B1, 0x49a2, 0xAA, 0x59, 0x5E, 0xEF, \
+ 0x92, 0xFF, 0xA6, 0x3C)
+#define INFO_ERR_STRUCT_TYPE_MS \
+ GUID_INIT(0x48AB7F57, 0xDC34, 0x4f6c, 0xA7, 0xD3, 0xB0, 0xB5, \
+ 0xB0, 0xA7, 0x43, 0x14)
+
+#define INFO_VALID_CHECK_INFO BIT_ULL(0)
+#define INFO_VALID_TARGET_ID BIT_ULL(1)
+#define INFO_VALID_REQUESTOR_ID BIT_ULL(2)
+#define INFO_VALID_RESPONDER_ID BIT_ULL(3)
+#define INFO_VALID_IP BIT_ULL(4)
+
+#define CHECK_VALID_TRANS_TYPE BIT_ULL(0)
+#define CHECK_VALID_OPERATION BIT_ULL(1)
+#define CHECK_VALID_LEVEL BIT_ULL(2)
+#define CHECK_VALID_PCC BIT_ULL(3)
+#define CHECK_VALID_UNCORRECTED BIT_ULL(4)
+#define CHECK_VALID_PRECISE_IP BIT_ULL(5)
+#define CHECK_VALID_RESTARTABLE_IP BIT_ULL(6)
+#define CHECK_VALID_OVERFLOW BIT_ULL(7)
+
+#define CHECK_VALID_BUS_PART_TYPE BIT_ULL(8)
+#define CHECK_VALID_BUS_TIME_OUT BIT_ULL(9)
+#define CHECK_VALID_BUS_ADDR_SPACE BIT_ULL(10)
+
+#define CHECK_VALID_BITS(check) (((check) & GENMASK_ULL(15, 0)))
+#define CHECK_TRANS_TYPE(check) (((check) & GENMASK_ULL(17, 16)) >> 16)
+#define CHECK_OPERATION(check) (((check) & GENMASK_ULL(21, 18)) >> 18)
+#define CHECK_LEVEL(check) (((check) & GENMASK_ULL(24, 22)) >> 22)
+#define CHECK_PCC BIT_ULL(25)
+#define CHECK_UNCORRECTED BIT_ULL(26)
+#define CHECK_PRECISE_IP BIT_ULL(27)
+#define CHECK_RESTARTABLE_IP BIT_ULL(28)
+#define CHECK_OVERFLOW BIT_ULL(29)
+
+#define CHECK_BUS_PART_TYPE(check) (((check) & GENMASK_ULL(31, 30)) >> 30)
+#define CHECK_BUS_TIME_OUT BIT_ULL(32)
+#define CHECK_BUS_ADDR_SPACE(check) (((check) & GENMASK_ULL(34, 33)) >> 33)
+
+#define CHECK_VALID_MS_ERR_TYPE BIT_ULL(0)
+#define CHECK_VALID_MS_PCC BIT_ULL(1)
+#define CHECK_VALID_MS_UNCORRECTED BIT_ULL(2)
+#define CHECK_VALID_MS_PRECISE_IP BIT_ULL(3)
+#define CHECK_VALID_MS_RESTARTABLE_IP BIT_ULL(4)
+#define CHECK_VALID_MS_OVERFLOW BIT_ULL(5)
+
+#define CHECK_MS_ERR_TYPE(check) (((check) & GENMASK_ULL(18, 16)) >> 16)
+#define CHECK_MS_PCC BIT_ULL(19)
+#define CHECK_MS_UNCORRECTED BIT_ULL(20)
+#define CHECK_MS_PRECISE_IP BIT_ULL(21)
+#define CHECK_MS_RESTARTABLE_IP BIT_ULL(22)
+#define CHECK_MS_OVERFLOW BIT_ULL(23)
+
+#define CTX_TYPE_MSR 1
+#define CTX_TYPE_MMREG 7
+
+enum err_types {
+ ERR_TYPE_CACHE = 0,
+ ERR_TYPE_TLB,
+ ERR_TYPE_BUS,
+ ERR_TYPE_MS,
+ N_ERR_TYPES
+};
+
+static enum err_types cper_get_err_type(const guid_t *err_type)
+{
+ if (guid_equal(err_type, &INFO_ERR_STRUCT_TYPE_CACHE))
+ return ERR_TYPE_CACHE;
+ else if (guid_equal(err_type, &INFO_ERR_STRUCT_TYPE_TLB))
+ return ERR_TYPE_TLB;
+ else if (guid_equal(err_type, &INFO_ERR_STRUCT_TYPE_BUS))
+ return ERR_TYPE_BUS;
+ else if (guid_equal(err_type, &INFO_ERR_STRUCT_TYPE_MS))
+ return ERR_TYPE_MS;
+ else
+ return N_ERR_TYPES;
+}
+
+static const char * const ia_check_trans_type_strs[] = {
+ "Instruction",
+ "Data Access",
+ "Generic",
+};
+
+static const char * const ia_check_op_strs[] = {
+ "generic error",
+ "generic read",
+ "generic write",
+ "data read",
+ "data write",
+ "instruction fetch",
+ "prefetch",
+ "eviction",
+ "snoop",
+};
+
+static const char * const ia_check_bus_part_type_strs[] = {
+ "Local Processor originated request",
+ "Local Processor responded to request",
+ "Local Processor observed",
+ "Generic",
+};
+
+static const char * const ia_check_bus_addr_space_strs[] = {
+ "Memory Access",
+ "Reserved",
+ "I/O",
+ "Other Transaction",
+};
+
+static const char * const ia_check_ms_error_type_strs[] = {
+ "No Error",
+ "Unclassified",
+ "Microcode ROM Parity Error",
+ "External Error",
+ "FRC Error",
+ "Internal Unclassified",
+};
+
+static const char * const ia_reg_ctx_strs[] = {
+ "Unclassified Data",
+ "MSR Registers (Machine Check and other MSRs)",
+ "32-bit Mode Execution Context",
+ "64-bit Mode Execution Context",
+ "FXSAVE Context",
+ "32-bit Mode Debug Registers (DR0-DR7)",
+ "64-bit Mode Debug Registers (DR0-DR7)",
+ "Memory Mapped Registers",
+};
+
+static inline void print_bool(char *str, const char *pfx, u64 check, u64 bit)
+{
+ printk("%s%s: %s\n", pfx, str, (check & bit) ? "true" : "false");
+}
+
+static void print_err_info_ms(const char *pfx, u16 validation_bits, u64 check)
+{
+ if (validation_bits & CHECK_VALID_MS_ERR_TYPE) {
+ u8 err_type = CHECK_MS_ERR_TYPE(check);
+
+ printk("%sError Type: %u, %s\n", pfx, err_type,
+ err_type < ARRAY_SIZE(ia_check_ms_error_type_strs) ?
+ ia_check_ms_error_type_strs[err_type] : "unknown");
+ }
+
+ if (validation_bits & CHECK_VALID_MS_PCC)
+ print_bool("Processor Context Corrupt", pfx, check, CHECK_MS_PCC);
+
+ if (validation_bits & CHECK_VALID_MS_UNCORRECTED)
+ print_bool("Uncorrected", pfx, check, CHECK_MS_UNCORRECTED);
+
+ if (validation_bits & CHECK_VALID_MS_PRECISE_IP)
+ print_bool("Precise IP", pfx, check, CHECK_MS_PRECISE_IP);
+
+ if (validation_bits & CHECK_VALID_MS_RESTARTABLE_IP)
+ print_bool("Restartable IP", pfx, check, CHECK_MS_RESTARTABLE_IP);
+
+ if (validation_bits & CHECK_VALID_MS_OVERFLOW)
+ print_bool("Overflow", pfx, check, CHECK_MS_OVERFLOW);
+}
+
+static void print_err_info(const char *pfx, u8 err_type, u64 check)
+{
+ u16 validation_bits = CHECK_VALID_BITS(check);
+
+ /*
+ * The MS Check structure varies a lot from the others, so use a
+ * separate function for decoding.
+ */
+ if (err_type == ERR_TYPE_MS)
+ return print_err_info_ms(pfx, validation_bits, check);
+
+ if (validation_bits & CHECK_VALID_TRANS_TYPE) {
+ u8 trans_type = CHECK_TRANS_TYPE(check);
+
+ printk("%sTransaction Type: %u, %s\n", pfx, trans_type,
+ trans_type < ARRAY_SIZE(ia_check_trans_type_strs) ?
+ ia_check_trans_type_strs[trans_type] : "unknown");
+ }
+
+ if (validation_bits & CHECK_VALID_OPERATION) {
+ u8 op = CHECK_OPERATION(check);
+
+ /*
+ * CACHE has more operation types than TLB or BUS, though the
+ * name and the order are the same.
+ */
+ u8 max_ops = (err_type == ERR_TYPE_CACHE) ? 9 : 7;
+
+ printk("%sOperation: %u, %s\n", pfx, op,
+ op < max_ops ? ia_check_op_strs[op] : "unknown");
+ }
+
+ if (validation_bits & CHECK_VALID_LEVEL)
+ printk("%sLevel: %llu\n", pfx, CHECK_LEVEL(check));
+
+ if (validation_bits & CHECK_VALID_PCC)
+ print_bool("Processor Context Corrupt", pfx, check, CHECK_PCC);
+
+ if (validation_bits & CHECK_VALID_UNCORRECTED)
+ print_bool("Uncorrected", pfx, check, CHECK_UNCORRECTED);
+
+ if (validation_bits & CHECK_VALID_PRECISE_IP)
+ print_bool("Precise IP", pfx, check, CHECK_PRECISE_IP);
+
+ if (validation_bits & CHECK_VALID_RESTARTABLE_IP)
+ print_bool("Restartable IP", pfx, check, CHECK_RESTARTABLE_IP);
+
+ if (validation_bits & CHECK_VALID_OVERFLOW)
+ print_bool("Overflow", pfx, check, CHECK_OVERFLOW);
+
+ if (err_type != ERR_TYPE_BUS)
+ return;
+
+ if (validation_bits & CHECK_VALID_BUS_PART_TYPE) {
+ u8 part_type = CHECK_BUS_PART_TYPE(check);
+
+ printk("%sParticipation Type: %u, %s\n", pfx, part_type,
+ part_type < ARRAY_SIZE(ia_check_bus_part_type_strs) ?
+ ia_check_bus_part_type_strs[part_type] : "unknown");
+ }
+
+ if (validation_bits & CHECK_VALID_BUS_TIME_OUT)
+ print_bool("Time Out", pfx, check, CHECK_BUS_TIME_OUT);
+
+ if (validation_bits & CHECK_VALID_BUS_ADDR_SPACE) {
+ u8 addr_space = CHECK_BUS_ADDR_SPACE(check);
+
+ printk("%sAddress Space: %u, %s\n", pfx, addr_space,
+ addr_space < ARRAY_SIZE(ia_check_bus_addr_space_strs) ?
+ ia_check_bus_addr_space_strs[addr_space] : "unknown");
+ }
+}
+
+void cper_print_proc_ia(const char *pfx, const struct cper_sec_proc_ia *proc)
+{
+ int i;
+ struct cper_ia_err_info *err_info;
+ struct cper_ia_proc_ctx *ctx_info;
+ char newpfx[64], infopfx[64];
+ u8 err_type;
+
+ if (proc->validation_bits & VALID_LAPIC_ID)
+ printk("%sLocal APIC_ID: 0x%llx\n", pfx, proc->lapic_id);
+
+ if (proc->validation_bits & VALID_CPUID_INFO) {
+ printk("%sCPUID Info:\n", pfx);
+ print_hex_dump(pfx, "", DUMP_PREFIX_OFFSET, 16, 4, proc->cpuid,
+ sizeof(proc->cpuid), 0);
+ }
+
+ snprintf(newpfx, sizeof(newpfx), "%s ", pfx);
+
+ err_info = (struct cper_ia_err_info *)(proc + 1);
+ for (i = 0; i < VALID_PROC_ERR_INFO_NUM(proc->validation_bits); i++) {
+ printk("%sError Information Structure %d:\n", pfx, i);
+
+ err_type = cper_get_err_type(&err_info->err_type);
+ printk("%sError Structure Type: %s\n", newpfx,
+ err_type < ARRAY_SIZE(cper_proc_error_type_strs) ?
+ cper_proc_error_type_strs[err_type] : "unknown");
+
+ if (err_type >= N_ERR_TYPES) {
+ printk("%sError Structure Type: %pUl\n", newpfx,
+ &err_info->err_type);
+ }
+
+ if (err_info->validation_bits & INFO_VALID_CHECK_INFO) {
+ printk("%sCheck Information: 0x%016llx\n", newpfx,
+ err_info->check_info);
+
+ if (err_type < N_ERR_TYPES) {
+ snprintf(infopfx, sizeof(infopfx), "%s ",
+ newpfx);
+
+ print_err_info(infopfx, err_type,
+ err_info->check_info);
+ }
+ }
+
+ if (err_info->validation_bits & INFO_VALID_TARGET_ID) {
+ printk("%sTarget Identifier: 0x%016llx\n",
+ newpfx, err_info->target_id);
+ }
+
+ if (err_info->validation_bits & INFO_VALID_REQUESTOR_ID) {
+ printk("%sRequestor Identifier: 0x%016llx\n",
+ newpfx, err_info->requestor_id);
+ }
+
+ if (err_info->validation_bits & INFO_VALID_RESPONDER_ID) {
+ printk("%sResponder Identifier: 0x%016llx\n",
+ newpfx, err_info->responder_id);
+ }
+
+ if (err_info->validation_bits & INFO_VALID_IP) {
+ printk("%sInstruction Pointer: 0x%016llx\n",
+ newpfx, err_info->ip);
+ }
+
+ err_info++;
+ }
+
+ ctx_info = (struct cper_ia_proc_ctx *)err_info;
+ for (i = 0; i < VALID_PROC_CXT_INFO_NUM(proc->validation_bits); i++) {
+ int size = sizeof(*ctx_info) + ctx_info->reg_arr_size;
+ int groupsize = 4;
+
+ printk("%sContext Information Structure %d:\n", pfx, i);
+
+ printk("%sRegister Context Type: %s\n", newpfx,
+ ctx_info->reg_ctx_type < ARRAY_SIZE(ia_reg_ctx_strs) ?
+ ia_reg_ctx_strs[ctx_info->reg_ctx_type] : "unknown");
+
+ printk("%sRegister Array Size: 0x%04x\n", newpfx,
+ ctx_info->reg_arr_size);
+
+ if (ctx_info->reg_ctx_type == CTX_TYPE_MSR) {
+ groupsize = 8; /* MSRs are 8 bytes wide. */
+ printk("%sMSR Address: 0x%08x\n", newpfx,
+ ctx_info->msr_addr);
+ }
+
+ if (ctx_info->reg_ctx_type == CTX_TYPE_MMREG) {
+ printk("%sMM Register Address: 0x%016llx\n", newpfx,
+ ctx_info->mm_reg_addr);
+ }
+
+ printk("%sRegister Array:\n", newpfx);
+ print_hex_dump(newpfx, "", DUMP_PREFIX_OFFSET, 16, groupsize,
+ (ctx_info + 1), ctx_info->reg_arr_size, 0);
+
+ ctx_info = (struct cper_ia_proc_ctx *)((long)ctx_info + size);
+ }
+}
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index c165933..3bf0dca 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -37,8 +37,6 @@
#include <acpi/ghes.h>
#include <ras/ras_event.h>
-#define INDENT_SP " "
-
static char rcd_decode_str[CPER_REC_LEN];
/*
@@ -433,7 +431,7 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata
if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
printk("%s""fru_text: %.20s\n", pfx, gdata->fru_text);
- snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
+ snprintf(newpfx, sizeof(newpfx), "%s ", pfx);
if (guid_equal(sec_type, &CPER_SEC_PROC_GENERIC)) {
struct cper_sec_proc_generic *proc_err = acpi_hest_get_payload(gdata);
@@ -470,6 +468,16 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata
else
goto err_section_too_small;
#endif
+#if defined(CONFIG_UEFI_CPER_X86)
+ } else if (guid_equal(sec_type, &CPER_SEC_PROC_IA)) {
+ struct cper_sec_proc_ia *ia_err = acpi_hest_get_payload(gdata);
+
+ printk("%ssection_type: IA32/X64 processor error\n", newpfx);
+ if (gdata->error_data_length >= sizeof(*ia_err))
+ cper_print_proc_ia(newpfx, ia_err);
+ else
+ goto err_section_too_small;
+#endif
} else {
const void *err = acpi_hest_get_payload(gdata);
@@ -500,7 +508,7 @@ void cper_estatus_print(const char *pfx,
"It has been corrected by h/w "
"and requires no further action");
printk("%s""event severity: %s\n", pfx, cper_severity_str(severity));
- snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
+ snprintf(newpfx, sizeof(newpfx), "%s ", pfx);
apei_estatus_for_each_section(estatus, gdata) {
cper_estatus_print_section(newpfx, gdata, sec_no);
diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c
index b9bd827..1b4d465 100644
--- a/drivers/firmware/efi/libstub/arm64-stub.c
+++ b/drivers/firmware/efi/libstub/arm64-stub.c
@@ -98,6 +98,16 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table_arg,
(phys_seed >> 32) & mask : TEXT_OFFSET;
/*
+ * With CONFIG_RANDOMIZE_TEXT_OFFSET=y, TEXT_OFFSET may not
+ * be a multiple of EFI_KIMG_ALIGN, and we must ensure that
+ * we preserve the misalignment of 'offset' relative to
+ * EFI_KIMG_ALIGN so that statically allocated objects whose
+ * alignment exceeds PAGE_SIZE appear correctly aligned in
+ * memory.
+ */
+ offset |= TEXT_OFFSET % EFI_KIMG_ALIGN;
+
+ /*
* If KASLR is enabled, and we have some randomness available,
* locate the kernel at a randomized offset in physical memory.
*/
diff --git a/drivers/firmware/efi/libstub/secureboot.c b/drivers/firmware/efi/libstub/secureboot.c
index 8f07eb4..72d9dfb 100644
--- a/drivers/firmware/efi/libstub/secureboot.c
+++ b/drivers/firmware/efi/libstub/secureboot.c
@@ -30,6 +30,9 @@ static const efi_char16_t shim_MokSBState_name[] = L"MokSBState";
/*
* Determine whether we're in secure boot mode.
+ *
+ * Please keep the logic in sync with
+ * arch/x86/xen/efi.c:xen_efi_get_secureboot().
*/
enum efi_secureboot_mode efi_get_secureboot(efi_system_table_t *sys_table_arg)
{
diff --git a/drivers/firmware/efi/libstub/tpm.c b/drivers/firmware/efi/libstub/tpm.c
index 9d08cea..caa37a6 100644
--- a/drivers/firmware/efi/libstub/tpm.c
+++ b/drivers/firmware/efi/libstub/tpm.c
@@ -59,7 +59,7 @@ void efi_enable_reset_attack_mitigation(efi_system_table_t *sys_table_arg)
#endif
-void efi_retrieve_tpm2_eventlog_1_2(efi_system_table_t *sys_table_arg)
+static void efi_retrieve_tpm2_eventlog_1_2(efi_system_table_t *sys_table_arg)
{
efi_guid_t tcg2_guid = EFI_TCG2_PROTOCOL_GUID;
efi_guid_t linux_eventlog_guid = LINUX_EFI_TPM_EVENT_LOG_GUID;
diff --git a/drivers/firmware/qcom_scm-32.c b/drivers/firmware/qcom_scm-32.c
index dfbd894..4e24e59 100644
--- a/drivers/firmware/qcom_scm-32.c
+++ b/drivers/firmware/qcom_scm-32.c
@@ -147,7 +147,7 @@ static u32 smc(u32 cmd_addr)
"smc #0 @ switch to secure world\n"
: "=r" (r0)
: "r" (r0), "r" (r1), "r" (r2)
- : "r3");
+ : "r3", "r12");
} while (r0 == QCOM_SCM_INTERRUPTED);
return r0;
@@ -263,7 +263,7 @@ static s32 qcom_scm_call_atomic1(u32 svc, u32 cmd, u32 arg1)
"smc #0 @ switch to secure world\n"
: "=r" (r0)
: "r" (r0), "r" (r1), "r" (r2)
- : "r3");
+ : "r3", "r12");
return r0;
}
@@ -298,7 +298,7 @@ static s32 qcom_scm_call_atomic2(u32 svc, u32 cmd, u32 arg1, u32 arg2)
"smc #0 @ switch to secure world\n"
: "=r" (r0)
: "r" (r0), "r" (r1), "r" (r2), "r" (r3)
- );
+ : "r12");
return r0;
}
@@ -328,7 +328,7 @@ u32 qcom_scm_get_version(void)
"smc #0 @ switch to secure world\n"
: "=r" (r0), "=r" (r1)
: "r" (r0), "r" (r1)
- : "r2", "r3");
+ : "r2", "r3", "r12");
} while (r0 == QCOM_SCM_INTERRUPTED);
version = r1;
diff --git a/drivers/fpga/altera-ps-spi.c b/drivers/fpga/altera-ps-spi.c
index 14f14ef..06d212a 100644
--- a/drivers/fpga/altera-ps-spi.c
+++ b/drivers/fpga/altera-ps-spi.c
@@ -249,7 +249,7 @@ static int altera_ps_probe(struct spi_device *spi)
conf->data = of_id->data;
conf->spi = spi;
- conf->config = devm_gpiod_get(&spi->dev, "nconfig", GPIOD_OUT_HIGH);
+ conf->config = devm_gpiod_get(&spi->dev, "nconfig", GPIOD_OUT_LOW);
if (IS_ERR(conf->config)) {
dev_err(&spi->dev, "Failed to get config gpio: %ld\n",
PTR_ERR(conf->config));
diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c
index 77e4855..6f693b7 100644
--- a/drivers/gpio/gpio-aspeed.c
+++ b/drivers/gpio/gpio-aspeed.c
@@ -384,7 +384,7 @@ static void aspeed_gpio_irq_set_mask(struct irq_data *d, bool set)
if (set)
reg |= bit;
else
- reg &= bit;
+ reg &= ~bit;
iowrite32(reg, addr);
spin_unlock_irqrestore(&gpio->lock, flags);
diff --git a/drivers/gpio/gpio-pci-idio-16.c b/drivers/gpio/gpio-pci-idio-16.c
index 1948724..25d16b2 100644
--- a/drivers/gpio/gpio-pci-idio-16.c
+++ b/drivers/gpio/gpio-pci-idio-16.c
@@ -116,9 +116,9 @@ static int idio_16_gpio_get_multiple(struct gpio_chip *chip,
unsigned long word_mask;
const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0);
unsigned long port_state;
- u8 __iomem ports[] = {
- idio16gpio->reg->out0_7, idio16gpio->reg->out8_15,
- idio16gpio->reg->in0_7, idio16gpio->reg->in8_15,
+ void __iomem *ports[] = {
+ &idio16gpio->reg->out0_7, &idio16gpio->reg->out8_15,
+ &idio16gpio->reg->in0_7, &idio16gpio->reg->in8_15,
};
/* clear bits array to a clean slate */
@@ -143,7 +143,7 @@ static int idio_16_gpio_get_multiple(struct gpio_chip *chip,
}
/* read bits from current gpio port */
- port_state = ioread8(ports + i);
+ port_state = ioread8(ports[i]);
/* store acquired bits at respective bits array offset */
bits[word_index] |= port_state << word_offset;
diff --git a/drivers/gpio/gpio-pcie-idio-24.c b/drivers/gpio/gpio-pcie-idio-24.c
index 835607e..f953541 100644
--- a/drivers/gpio/gpio-pcie-idio-24.c
+++ b/drivers/gpio/gpio-pcie-idio-24.c
@@ -206,10 +206,10 @@ static int idio_24_gpio_get_multiple(struct gpio_chip *chip,
unsigned long word_mask;
const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0);
unsigned long port_state;
- u8 __iomem ports[] = {
- idio24gpio->reg->out0_7, idio24gpio->reg->out8_15,
- idio24gpio->reg->out16_23, idio24gpio->reg->in0_7,
- idio24gpio->reg->in8_15, idio24gpio->reg->in16_23,
+ void __iomem *ports[] = {
+ &idio24gpio->reg->out0_7, &idio24gpio->reg->out8_15,
+ &idio24gpio->reg->out16_23, &idio24gpio->reg->in0_7,
+ &idio24gpio->reg->in8_15, &idio24gpio->reg->in16_23,
};
const unsigned long out_mode_mask = BIT(1);
@@ -217,7 +217,7 @@ static int idio_24_gpio_get_multiple(struct gpio_chip *chip,
bitmap_zero(bits, chip->ngpio);
/* get bits are evaluated a gpio port register at a time */
- for (i = 0; i < ARRAY_SIZE(ports); i++) {
+ for (i = 0; i < ARRAY_SIZE(ports) + 1; i++) {
/* gpio offset in bits array */
bits_offset = i * gpio_reg_size;
@@ -236,7 +236,7 @@ static int idio_24_gpio_get_multiple(struct gpio_chip *chip,
/* read bits from current gpio port (port 6 is TTL GPIO) */
if (i < 6)
- port_state = ioread8(ports + i);
+ port_state = ioread8(ports[i]);
else if (ioread8(&idio24gpio->reg->ctl) & out_mode_mask)
port_state = ioread8(&idio24gpio->reg->ttl_out0_7);
else
@@ -301,9 +301,9 @@ static void idio_24_gpio_set_multiple(struct gpio_chip *chip,
const unsigned long port_mask = GENMASK(gpio_reg_size, 0);
unsigned long flags;
unsigned int out_state;
- u8 __iomem ports[] = {
- idio24gpio->reg->out0_7, idio24gpio->reg->out8_15,
- idio24gpio->reg->out16_23
+ void __iomem *ports[] = {
+ &idio24gpio->reg->out0_7, &idio24gpio->reg->out8_15,
+ &idio24gpio->reg->out16_23
};
const unsigned long out_mode_mask = BIT(1);
const unsigned int ttl_offset = 48;
@@ -327,9 +327,9 @@ static void idio_24_gpio_set_multiple(struct gpio_chip *chip,
raw_spin_lock_irqsave(&idio24gpio->lock, flags);
/* process output lines */
- out_state = ioread8(ports + i) & ~gpio_mask;
+ out_state = ioread8(ports[i]) & ~gpio_mask;
out_state |= (*bits >> bits_offset) & gpio_mask;
- iowrite8(out_state, ports + i);
+ iowrite8(out_state, ports[i]);
raw_spin_unlock_irqrestore(&idio24gpio->lock, flags);
}
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 43aeb07..d8ccb50 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -497,7 +497,7 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
struct gpiohandle_request handlereq;
struct linehandle_state *lh;
struct file *file;
- int fd, i, ret;
+ int fd, i, count = 0, ret;
u32 lflags;
if (copy_from_user(&handlereq, ip, sizeof(handlereq)))
@@ -558,6 +558,7 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
if (ret)
goto out_free_descs;
lh->descs[i] = desc;
+ count = i;
if (lflags & GPIOHANDLE_REQUEST_ACTIVE_LOW)
set_bit(FLAG_ACTIVE_LOW, &desc->flags);
@@ -628,7 +629,7 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
out_put_unused_fd:
put_unused_fd(fd);
out_free_descs:
- for (; i >= 0; i--)
+ for (i = 0; i < count; i++)
gpiod_free(lh->descs[i]);
kfree(lh->label);
out_free_lh:
@@ -902,7 +903,7 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip)
desc = &gdev->descs[offset];
ret = gpiod_request(desc, le->label);
if (ret)
- goto out_free_desc;
+ goto out_free_label;
le->desc = desc;
le->eflags = eflags;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index a29362f..1255804 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -513,7 +513,7 @@ static int acp_hw_fini(void *handle)
if (adev->acp.acp_genpd) {
for (i = 0; i < ACP_DEVS ; i++) {
dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i);
- ret = pm_genpd_remove_device(&adev->acp.acp_genpd->gpd, dev);
+ ret = pm_genpd_remove_device(dev);
/* If removal fails, dont giveup and try rest */
if (ret)
dev_err(dev, "remove dev from genpd failed\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 09d35051..3fabf9f9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -419,9 +419,11 @@ int amdgpu_ctx_wait_prev_fence(struct amdgpu_ctx *ctx, unsigned ring_id)
if (other) {
signed long r;
- r = dma_fence_wait_timeout(other, false, MAX_SCHEDULE_TIMEOUT);
+ r = dma_fence_wait(other, true);
if (r < 0) {
- DRM_ERROR("Error (%ld) waiting for fence!\n", r);
+ if (r != -ERESTARTSYS)
+ DRM_ERROR("Error (%ld) waiting for fence!\n", r);
+
return r;
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index b0e591e..e14263f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -1459,10 +1459,11 @@ static const u32 sgpr_init_compute_shader[] =
static const u32 vgpr_init_regs[] =
{
mmCOMPUTE_STATIC_THREAD_MGMT_SE0, 0xffffffff,
- mmCOMPUTE_RESOURCE_LIMITS, 0,
+ mmCOMPUTE_RESOURCE_LIMITS, 0x1000000, /* CU_GROUP_COUNT=1 */
mmCOMPUTE_NUM_THREAD_X, 256*4,
mmCOMPUTE_NUM_THREAD_Y, 1,
mmCOMPUTE_NUM_THREAD_Z, 1,
+ mmCOMPUTE_PGM_RSRC1, 0x100004f, /* VGPRS=15 (64 logical VGPRs), SGPRS=1 (16 SGPRs), BULKY=1 */
mmCOMPUTE_PGM_RSRC2, 20,
mmCOMPUTE_USER_DATA_0, 0xedcedc00,
mmCOMPUTE_USER_DATA_1, 0xedcedc01,
@@ -1479,10 +1480,11 @@ static const u32 vgpr_init_regs[] =
static const u32 sgpr1_init_regs[] =
{
mmCOMPUTE_STATIC_THREAD_MGMT_SE0, 0x0f,
- mmCOMPUTE_RESOURCE_LIMITS, 0x1000000,
+ mmCOMPUTE_RESOURCE_LIMITS, 0x1000000, /* CU_GROUP_COUNT=1 */
mmCOMPUTE_NUM_THREAD_X, 256*5,
mmCOMPUTE_NUM_THREAD_Y, 1,
mmCOMPUTE_NUM_THREAD_Z, 1,
+ mmCOMPUTE_PGM_RSRC1, 0x240, /* SGPRS=9 (80 GPRS) */
mmCOMPUTE_PGM_RSRC2, 20,
mmCOMPUTE_USER_DATA_0, 0xedcedc00,
mmCOMPUTE_USER_DATA_1, 0xedcedc01,
@@ -1503,6 +1505,7 @@ static const u32 sgpr2_init_regs[] =
mmCOMPUTE_NUM_THREAD_X, 256*5,
mmCOMPUTE_NUM_THREAD_Y, 1,
mmCOMPUTE_NUM_THREAD_Z, 1,
+ mmCOMPUTE_PGM_RSRC1, 0x240, /* SGPRS=9 (80 GPRS) */
mmCOMPUTE_PGM_RSRC2, 20,
mmCOMPUTE_USER_DATA_0, 0xedcedc00,
mmCOMPUTE_USER_DATA_1, 0xedcedc01,
diff --git a/drivers/gpu/drm/amd/amdkfd/Kconfig b/drivers/gpu/drm/amd/amdkfd/Kconfig
index ed2f06c..3858820 100644
--- a/drivers/gpu/drm/amd/amdkfd/Kconfig
+++ b/drivers/gpu/drm/amd/amdkfd/Kconfig
@@ -6,5 +6,6 @@
tristate "HSA kernel driver for AMD GPU devices"
depends on DRM_AMDGPU && X86_64
imply AMD_IOMMU_V2
+ select MMU_NOTIFIER
help
Enable this if you want to use HSA features on AMD GPU devices.
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index cd679cf..59808a3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -749,12 +749,13 @@ static int kfd_ioctl_get_clock_counters(struct file *filep,
struct timespec64 time;
dev = kfd_device_by_id(args->gpu_id);
- if (dev == NULL)
- return -EINVAL;
-
- /* Reading GPU clock counter from KGD */
- args->gpu_clock_counter =
- dev->kfd2kgd->get_gpu_clock_counter(dev->kgd);
+ if (dev)
+ /* Reading GPU clock counter from KGD */
+ args->gpu_clock_counter =
+ dev->kfd2kgd->get_gpu_clock_counter(dev->kgd);
+ else
+ /* Node without GPU resource */
+ args->gpu_clock_counter = 0;
/* No access to rdtsc. Using raw monotonic time */
getrawmonotonic64(&time);
@@ -1147,7 +1148,7 @@ static int kfd_ioctl_acquire_vm(struct file *filep, struct kfd_process *p,
return ret;
}
-bool kfd_dev_is_large_bar(struct kfd_dev *dev)
+static bool kfd_dev_is_large_bar(struct kfd_dev *dev)
{
struct kfd_local_mem_info mem_info;
@@ -1421,7 +1422,7 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
pdd = kfd_get_process_device_data(dev, p);
if (!pdd) {
- err = PTR_ERR(pdd);
+ err = -EINVAL;
goto bind_process_to_device_failed;
}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 4e2f379..2757944 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -4555,8 +4555,9 @@ static int dm_update_crtcs_state(struct dc *dc,
for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
struct amdgpu_crtc *acrtc = NULL;
struct amdgpu_dm_connector *aconnector = NULL;
- struct drm_connector_state *new_con_state = NULL;
- struct dm_connector_state *dm_conn_state = NULL;
+ struct drm_connector_state *drm_new_conn_state = NULL, *drm_old_conn_state = NULL;
+ struct dm_connector_state *dm_new_conn_state = NULL, *dm_old_conn_state = NULL;
+ struct drm_plane_state *new_plane_state = NULL;
new_stream = NULL;
@@ -4564,24 +4565,35 @@ static int dm_update_crtcs_state(struct dc *dc,
dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
acrtc = to_amdgpu_crtc(crtc);
+ new_plane_state = drm_atomic_get_new_plane_state(state, new_crtc_state->crtc->primary);
+
+ if (new_crtc_state->enable && new_plane_state && !new_plane_state->fb) {
+ ret = -EINVAL;
+ goto fail;
+ }
+
aconnector = amdgpu_dm_find_first_crtc_matching_connector(state, crtc);
/* TODO This hack should go away */
if (aconnector && enable) {
// Make sure fake sink is created in plug-in scenario
- new_con_state = drm_atomic_get_connector_state(state,
+ drm_new_conn_state = drm_atomic_get_new_connector_state(state,
&aconnector->base);
+ drm_old_conn_state = drm_atomic_get_old_connector_state(state,
+ &aconnector->base);
- if (IS_ERR(new_con_state)) {
- ret = PTR_ERR_OR_ZERO(new_con_state);
+
+ if (IS_ERR(drm_new_conn_state)) {
+ ret = PTR_ERR_OR_ZERO(drm_new_conn_state);
break;
}
- dm_conn_state = to_dm_connector_state(new_con_state);
+ dm_new_conn_state = to_dm_connector_state(drm_new_conn_state);
+ dm_old_conn_state = to_dm_connector_state(drm_old_conn_state);
new_stream = create_stream_for_sink(aconnector,
&new_crtc_state->mode,
- dm_conn_state);
+ dm_new_conn_state);
/*
* we can have no stream on ACTION_SET if a display
@@ -4687,20 +4699,30 @@ static int dm_update_crtcs_state(struct dc *dc,
* We want to do dc stream updates that do not require a
* full modeset below.
*/
- if (!enable || !aconnector || modereset_required(new_crtc_state))
+ if (!(enable && aconnector && new_crtc_state->enable &&
+ new_crtc_state->active))
continue;
/*
* Given above conditions, the dc state cannot be NULL because:
- * 1. We're attempting to enable a CRTC. Which has a...
- * 2. Valid connector attached, and
- * 3. User does not want to reset it (disable or mark inactive,
- * which can happen on a CRTC that's already disabled).
- * => It currently exists.
+ * 1. We're in the process of enabling CRTCs (just been added
+ * to the dc context, or already is on the context)
+ * 2. Has a valid connector attached, and
+ * 3. Is currently active and enabled.
+ * => The dc stream state currently exists.
*/
BUG_ON(dm_new_crtc_state->stream == NULL);
- /* Color managment settings */
- if (dm_new_crtc_state->base.color_mgmt_changed) {
+ /* Scaling or underscan settings */
+ if (is_scaling_state_different(dm_old_conn_state, dm_new_conn_state))
+ update_stream_scaling_settings(
+ &new_crtc_state->mode, dm_new_conn_state, dm_new_crtc_state->stream);
+
+ /*
+ * Color management settings. We also update color properties
+ * when a modeset is needed, to ensure it gets reprogrammed.
+ */
+ if (dm_new_crtc_state->base.color_mgmt_changed ||
+ drm_atomic_crtc_needs_modeset(new_crtc_state)) {
ret = amdgpu_dm_set_regamma_lut(dm_new_crtc_state);
if (ret)
goto fail;
@@ -4760,7 +4782,7 @@ static int dm_update_planes_state(struct dc *dc,
if (!dm_old_crtc_state->stream)
continue;
- DRM_DEBUG_DRIVER("Disabling DRM plane: %d on DRM crtc %d\n",
+ DRM_DEBUG_ATOMIC("Disabling DRM plane: %d on DRM crtc %d\n",
plane->base.id, old_plane_crtc->base.id);
if (!dc_remove_plane_from_context(
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
index f6cb502..25f064c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
@@ -138,13 +138,6 @@ int amdgpu_dm_set_regamma_lut(struct dm_crtc_state *crtc)
lut = (struct drm_color_lut *)blob->data;
lut_size = blob->length / sizeof(struct drm_color_lut);
- if (__is_lut_linear(lut, lut_size)) {
- /* Set to bypass if lut is set to linear */
- stream->out_transfer_func->type = TF_TYPE_BYPASS;
- stream->out_transfer_func->tf = TRANSFER_FUNCTION_LINEAR;
- return 0;
- }
-
gamma = dc_create_gamma();
if (!gamma)
return -ENOMEM;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index 490017d..4be21bf 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -329,14 +329,15 @@ void amdgpu_dm_irq_fini(struct amdgpu_device *adev)
{
int src;
struct irq_list_head *lh;
+ unsigned long irq_table_flags;
DRM_DEBUG_KMS("DM_IRQ: releasing resources.\n");
-
for (src = 0; src < DAL_IRQ_SOURCES_NUMBER; src++) {
-
+ DM_IRQ_TABLE_LOCK(adev, irq_table_flags);
/* The handler was removed from the table,
* it means it is safe to flush all the 'work'
* (because no code can schedule a new one). */
lh = &adev->dm.irq_handler_list_low_tab[src];
+ DM_IRQ_TABLE_UNLOCK(adev, irq_table_flags);
flush_work(&lh->work);
}
}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 8291d74..4304d9e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -83,21 +83,22 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
enum i2c_mot_mode mot = (msg->request & DP_AUX_I2C_MOT) ?
I2C_MOT_TRUE : I2C_MOT_FALSE;
enum ddc_result res;
- ssize_t read_bytes;
+ uint32_t read_bytes = msg->size;
if (WARN_ON(msg->size > 16))
return -E2BIG;
switch (msg->request & ~DP_AUX_I2C_MOT) {
case DP_AUX_NATIVE_READ:
- read_bytes = dal_ddc_service_read_dpcd_data(
+ res = dal_ddc_service_read_dpcd_data(
TO_DM_AUX(aux)->ddc_service,
false,
I2C_MOT_UNDEF,
msg->address,
msg->buffer,
- msg->size);
- return read_bytes;
+ msg->size,
+ &read_bytes);
+ break;
case DP_AUX_NATIVE_WRITE:
res = dal_ddc_service_write_dpcd_data(
TO_DM_AUX(aux)->ddc_service,
@@ -108,14 +109,15 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
msg->size);
break;
case DP_AUX_I2C_READ:
- read_bytes = dal_ddc_service_read_dpcd_data(
+ res = dal_ddc_service_read_dpcd_data(
TO_DM_AUX(aux)->ddc_service,
true,
mot,
msg->address,
msg->buffer,
- msg->size);
- return read_bytes;
+ msg->size,
+ &read_bytes);
+ break;
case DP_AUX_I2C_WRITE:
res = dal_ddc_service_write_dpcd_data(
TO_DM_AUX(aux)->ddc_service,
@@ -137,7 +139,9 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
r == DDC_RESULT_SUCESSFULL);
#endif
- return msg->size;
+ if (res != DDC_RESULT_SUCESSFULL)
+ return -EIO;
+ return read_bytes;
}
static enum drm_connector_status
@@ -161,6 +165,11 @@ dm_dp_mst_connector_destroy(struct drm_connector *connector)
struct amdgpu_dm_connector *amdgpu_dm_connector = to_amdgpu_dm_connector(connector);
struct amdgpu_encoder *amdgpu_encoder = amdgpu_dm_connector->mst_encoder;
+ if (amdgpu_dm_connector->edid) {
+ kfree(amdgpu_dm_connector->edid);
+ amdgpu_dm_connector->edid = NULL;
+ }
+
drm_encoder_cleanup(&amdgpu_encoder->base);
kfree(amdgpu_encoder);
drm_connector_cleanup(connector);
@@ -181,28 +190,22 @@ static const struct drm_connector_funcs dm_dp_mst_connector_funcs = {
void dm_dp_mst_dc_sink_create(struct drm_connector *connector)
{
struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
- struct edid *edid;
struct dc_sink *dc_sink;
struct dc_sink_init_data init_params = {
.link = aconnector->dc_link,
.sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST };
+ /* FIXME none of this is safe. we shouldn't touch aconnector here in
+ * atomic_check
+ */
+
/*
* TODO: Need to further figure out why ddc.algo is NULL while MST port exists
*/
if (!aconnector->port || !aconnector->port->aux.ddc.algo)
return;
- edid = drm_dp_mst_get_edid(connector, &aconnector->mst_port->mst_mgr, aconnector->port);
-
- if (!edid) {
- drm_mode_connector_update_edid_property(
- &aconnector->base,
- NULL);
- return;
- }
-
- aconnector->edid = edid;
+ ASSERT(aconnector->edid);
dc_sink = dc_link_add_remote_sink(
aconnector->dc_link,
@@ -215,9 +218,6 @@ void dm_dp_mst_dc_sink_create(struct drm_connector *connector)
amdgpu_dm_add_sink_to_freesync_module(
connector, aconnector->edid);
-
- drm_mode_connector_update_edid_property(
- &aconnector->base, aconnector->edid);
}
static int dm_dp_mst_get_modes(struct drm_connector *connector)
@@ -230,10 +230,6 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector)
if (!aconnector->edid) {
struct edid *edid;
- struct dc_sink *dc_sink;
- struct dc_sink_init_data init_params = {
- .link = aconnector->dc_link,
- .sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST };
edid = drm_dp_mst_get_edid(connector, &aconnector->mst_port->mst_mgr, aconnector->port);
if (!edid) {
@@ -244,11 +240,17 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector)
}
aconnector->edid = edid;
+ }
+ if (!aconnector->dc_sink) {
+ struct dc_sink *dc_sink;
+ struct dc_sink_init_data init_params = {
+ .link = aconnector->dc_link,
+ .sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST };
dc_sink = dc_link_add_remote_sink(
aconnector->dc_link,
- (uint8_t *)edid,
- (edid->extensions + 1) * EDID_LENGTH,
+ (uint8_t *)aconnector->edid,
+ (aconnector->edid->extensions + 1) * EDID_LENGTH,
&init_params);
dc_sink->priv = aconnector;
@@ -256,12 +258,12 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector)
if (aconnector->dc_sink)
amdgpu_dm_add_sink_to_freesync_module(
- connector, edid);
-
- drm_mode_connector_update_edid_property(
- &aconnector->base, edid);
+ connector, aconnector->edid);
}
+ drm_mode_connector_update_edid_property(
+ &aconnector->base, aconnector->edid);
+
ret = drm_add_edid_modes(connector, aconnector->edid);
return ret;
@@ -424,14 +426,6 @@ static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
dc_sink_release(aconnector->dc_sink);
aconnector->dc_sink = NULL;
}
- if (aconnector->edid) {
- kfree(aconnector->edid);
- aconnector->edid = NULL;
- }
-
- drm_mode_connector_update_edid_property(
- &aconnector->base,
- NULL);
aconnector->mst_connected = false;
}
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index 985fe8c..10a5807 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -70,6 +70,10 @@ static enum bp_result get_firmware_info_v3_1(
struct bios_parser *bp,
struct dc_firmware_info *info);
+static enum bp_result get_firmware_info_v3_2(
+ struct bios_parser *bp,
+ struct dc_firmware_info *info);
+
static struct atom_hpd_int_record *get_hpd_record(struct bios_parser *bp,
struct atom_display_object_path_v2 *object);
@@ -1321,9 +1325,11 @@ static enum bp_result bios_parser_get_firmware_info(
case 3:
switch (revision.minor) {
case 1:
- case 2:
result = get_firmware_info_v3_1(bp, info);
break;
+ case 2:
+ result = get_firmware_info_v3_2(bp, info);
+ break;
default:
break;
}
@@ -1383,6 +1389,84 @@ static enum bp_result get_firmware_info_v3_1(
return BP_RESULT_OK;
}
+static enum bp_result get_firmware_info_v3_2(
+ struct bios_parser *bp,
+ struct dc_firmware_info *info)
+{
+ struct atom_firmware_info_v3_2 *firmware_info;
+ struct atom_display_controller_info_v4_1 *dce_info = NULL;
+ struct atom_common_table_header *header;
+ struct atom_data_revision revision;
+ struct atom_smu_info_v3_2 *smu_info_v3_2 = NULL;
+ struct atom_smu_info_v3_3 *smu_info_v3_3 = NULL;
+
+ if (!info)
+ return BP_RESULT_BADINPUT;
+
+ firmware_info = GET_IMAGE(struct atom_firmware_info_v3_2,
+ DATA_TABLES(firmwareinfo));
+
+ dce_info = GET_IMAGE(struct atom_display_controller_info_v4_1,
+ DATA_TABLES(dce_info));
+
+ if (!firmware_info || !dce_info)
+ return BP_RESULT_BADBIOSTABLE;
+
+ memset(info, 0, sizeof(*info));
+
+ header = GET_IMAGE(struct atom_common_table_header,
+ DATA_TABLES(smu_info));
+ get_atom_data_table_revision(header, &revision);
+
+ if (revision.minor == 2) {
+ /* Vega12 */
+ smu_info_v3_2 = GET_IMAGE(struct atom_smu_info_v3_2,
+ DATA_TABLES(smu_info));
+
+ if (!smu_info_v3_2)
+ return BP_RESULT_BADBIOSTABLE;
+
+ info->default_engine_clk = smu_info_v3_2->bootup_dcefclk_10khz * 10;
+ } else if (revision.minor == 3) {
+ /* Vega20 */
+ smu_info_v3_3 = GET_IMAGE(struct atom_smu_info_v3_3,
+ DATA_TABLES(smu_info));
+
+ if (!smu_info_v3_3)
+ return BP_RESULT_BADBIOSTABLE;
+
+ info->default_engine_clk = smu_info_v3_3->bootup_dcefclk_10khz * 10;
+ }
+
+ // We need to convert from 10KHz units into KHz units.
+ info->default_memory_clk = firmware_info->bootup_mclk_in10khz * 10;
+
+ /* 27MHz for Vega10 & Vega12; 100MHz for Vega20 */
+ info->pll_info.crystal_frequency = dce_info->dce_refclk_10khz * 10;
+ /* Hardcode frequency if BIOS gives no DCE Ref Clk */
+ if (info->pll_info.crystal_frequency == 0) {
+ if (revision.minor == 2)
+ info->pll_info.crystal_frequency = 27000;
+ else if (revision.minor == 3)
+ info->pll_info.crystal_frequency = 100000;
+ }
+ /*dp_phy_ref_clk is not correct for atom_display_controller_info_v4_2, but we don't use it*/
+ info->dp_phy_ref_clk = dce_info->dpphy_refclk_10khz * 10;
+ info->i2c_engine_ref_clk = dce_info->i2c_engine_refclk_10khz * 10;
+
+ /* Get GPU PLL VCO Clock */
+ if (bp->cmd_tbl.get_smu_clock_info != NULL) {
+ if (revision.minor == 2)
+ info->smu_gpu_pll_output_freq =
+ bp->cmd_tbl.get_smu_clock_info(bp, SMU9_SYSPLL0_ID) * 10;
+ else if (revision.minor == 3)
+ info->smu_gpu_pll_output_freq =
+ bp->cmd_tbl.get_smu_clock_info(bp, SMU11_SYSPLL3_0_ID) * 10;
+ }
+
+ return BP_RESULT_OK;
+}
+
static enum bp_result bios_parser_get_encoder_cap_info(
struct dc_bios *dcb,
struct graphics_object_id object_id,
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
index 49c2fac..ae48d60 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
@@ -629,13 +629,14 @@ bool dal_ddc_service_query_ddc_data(
return ret;
}
-ssize_t dal_ddc_service_read_dpcd_data(
+enum ddc_result dal_ddc_service_read_dpcd_data(
struct ddc_service *ddc,
bool i2c,
enum i2c_mot_mode mot,
uint32_t address,
uint8_t *data,
- uint32_t len)
+ uint32_t len,
+ uint32_t *read)
{
struct aux_payload read_payload = {
.i2c_over_aux = i2c,
@@ -652,6 +653,8 @@ ssize_t dal_ddc_service_read_dpcd_data(
.mot = mot
};
+ *read = 0;
+
if (len > DEFAULT_AUX_MAX_DATA_SIZE) {
BREAK_TO_DEBUGGER();
return DDC_RESULT_FAILED_INVALID_OPERATION;
@@ -661,7 +664,8 @@ ssize_t dal_ddc_service_read_dpcd_data(
ddc->ctx->i2caux,
ddc->ddc_pin,
&command)) {
- return (ssize_t)command.payloads->length;
+ *read = command.payloads->length;
+ return DDC_RESULT_SUCESSFULL;
}
return DDC_RESULT_FAILED_OPERATION;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
index ade5b8e..132eef3 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
@@ -66,8 +66,8 @@ struct dc_plane_state *dc_create_plane_state(struct dc *dc)
{
struct dc *core_dc = dc;
- struct dc_plane_state *plane_state = kzalloc(sizeof(*plane_state),
- GFP_KERNEL);
+ struct dc_plane_state *plane_state = kvzalloc(sizeof(*plane_state),
+ GFP_KERNEL);
if (NULL == plane_state)
return NULL;
@@ -120,7 +120,7 @@ static void dc_plane_state_free(struct kref *kref)
{
struct dc_plane_state *plane_state = container_of(kref, struct dc_plane_state, refcount);
destruct(plane_state);
- kfree(plane_state);
+ kvfree(plane_state);
}
void dc_plane_state_release(struct dc_plane_state *plane_state)
@@ -136,7 +136,7 @@ void dc_gamma_retain(struct dc_gamma *gamma)
static void dc_gamma_free(struct kref *kref)
{
struct dc_gamma *gamma = container_of(kref, struct dc_gamma, refcount);
- kfree(gamma);
+ kvfree(gamma);
}
void dc_gamma_release(struct dc_gamma **gamma)
@@ -147,7 +147,7 @@ void dc_gamma_release(struct dc_gamma **gamma)
struct dc_gamma *dc_create_gamma(void)
{
- struct dc_gamma *gamma = kzalloc(sizeof(*gamma), GFP_KERNEL);
+ struct dc_gamma *gamma = kvzalloc(sizeof(*gamma), GFP_KERNEL);
if (gamma == NULL)
goto alloc_fail;
@@ -167,7 +167,7 @@ void dc_transfer_func_retain(struct dc_transfer_func *tf)
static void dc_transfer_func_free(struct kref *kref)
{
struct dc_transfer_func *tf = container_of(kref, struct dc_transfer_func, refcount);
- kfree(tf);
+ kvfree(tf);
}
void dc_transfer_func_release(struct dc_transfer_func *tf)
@@ -177,7 +177,7 @@ void dc_transfer_func_release(struct dc_transfer_func *tf)
struct dc_transfer_func *dc_create_transfer_func(void)
{
- struct dc_transfer_func *tf = kzalloc(sizeof(*tf), GFP_KERNEL);
+ struct dc_transfer_func *tf = kvzalloc(sizeof(*tf), GFP_KERNEL);
if (tf == NULL)
goto alloc_fail;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
index 090b7a8..30b3a08 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
@@ -102,13 +102,14 @@ bool dal_ddc_service_query_ddc_data(
uint8_t *read_buf,
uint32_t read_size);
-ssize_t dal_ddc_service_read_dpcd_data(
+enum ddc_result dal_ddc_service_read_dpcd_data(
struct ddc_service *ddc,
bool i2c,
enum i2c_mot_mode mot,
uint32_t address,
uint8_t *data,
- uint32_t len);
+ uint32_t len,
+ uint32_t *read);
enum ddc_result dal_ddc_service_write_dpcd_data(
struct ddc_service *ddc,
diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
index 9831cb5..9b0a04f 100644
--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -113,9 +113,14 @@
#define AI_GREENLAND_P_A0 1
#define AI_GREENLAND_P_A1 2
+#define AI_UNKNOWN 0xFF
-#define ASICREV_IS_GREENLAND_M(eChipRev) (eChipRev < AI_UNKNOWN)
-#define ASICREV_IS_GREENLAND_P(eChipRev) (eChipRev < AI_UNKNOWN)
+#define AI_VEGA12_P_A0 20
+#define ASICREV_IS_GREENLAND_M(eChipRev) (eChipRev < AI_VEGA12_P_A0)
+#define ASICREV_IS_GREENLAND_P(eChipRev) (eChipRev < AI_VEGA12_P_A0)
+
+#define ASICREV_IS_VEGA12_P(eChipRev) ((eChipRev >= AI_VEGA12_P_A0) && (eChipRev < AI_UNKNOWN))
+#define ASICREV_IS_VEGA12_p(eChipRev) ((eChipRev >= AI_VEGA12_P_A0) && (eChipRev < AI_UNKNOWN))
/* DCN1_0 */
#define INTERNAL_REV_RAVEN_A0 0x00 /* First spin of Raven */
diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
index e7e374f..b3747a0 100644
--- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
+++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
@@ -1093,19 +1093,19 @@ bool mod_color_calculate_regamma_params(struct dc_transfer_func *output_tf,
output_tf->type = TF_TYPE_DISTRIBUTED_POINTS;
- rgb_user = kzalloc(sizeof(*rgb_user) * (ramp->num_entries + _EXTRA_POINTS),
- GFP_KERNEL);
+ rgb_user = kvzalloc(sizeof(*rgb_user) * (ramp->num_entries + _EXTRA_POINTS),
+ GFP_KERNEL);
if (!rgb_user)
goto rgb_user_alloc_fail;
- rgb_regamma = kzalloc(sizeof(*rgb_regamma) * (MAX_HW_POINTS + _EXTRA_POINTS),
- GFP_KERNEL);
+ rgb_regamma = kvzalloc(sizeof(*rgb_regamma) * (MAX_HW_POINTS + _EXTRA_POINTS),
+ GFP_KERNEL);
if (!rgb_regamma)
goto rgb_regamma_alloc_fail;
- axix_x = kzalloc(sizeof(*axix_x) * (ramp->num_entries + 3),
- GFP_KERNEL);
+ axix_x = kvzalloc(sizeof(*axix_x) * (ramp->num_entries + 3),
+ GFP_KERNEL);
if (!axix_x)
goto axix_x_alloc_fail;
- coeff = kzalloc(sizeof(*coeff) * (MAX_HW_POINTS + _EXTRA_POINTS), GFP_KERNEL);
+ coeff = kvzalloc(sizeof(*coeff) * (MAX_HW_POINTS + _EXTRA_POINTS), GFP_KERNEL);
if (!coeff)
goto coeff_alloc_fail;
@@ -1157,13 +1157,13 @@ bool mod_color_calculate_regamma_params(struct dc_transfer_func *output_tf,
ret = true;
- kfree(coeff);
+ kvfree(coeff);
coeff_alloc_fail:
- kfree(axix_x);
+ kvfree(axix_x);
axix_x_alloc_fail:
- kfree(rgb_regamma);
+ kvfree(rgb_regamma);
rgb_regamma_alloc_fail:
- kfree(rgb_user);
+ kvfree(rgb_user);
rgb_user_alloc_fail:
return ret;
}
@@ -1192,19 +1192,19 @@ bool mod_color_calculate_degamma_params(struct dc_transfer_func *input_tf,
input_tf->type = TF_TYPE_DISTRIBUTED_POINTS;
- rgb_user = kzalloc(sizeof(*rgb_user) * (ramp->num_entries + _EXTRA_POINTS),
- GFP_KERNEL);
+ rgb_user = kvzalloc(sizeof(*rgb_user) * (ramp->num_entries + _EXTRA_POINTS),
+ GFP_KERNEL);
if (!rgb_user)
goto rgb_user_alloc_fail;
- curve = kzalloc(sizeof(*curve) * (MAX_HW_POINTS + _EXTRA_POINTS),
- GFP_KERNEL);
+ curve = kvzalloc(sizeof(*curve) * (MAX_HW_POINTS + _EXTRA_POINTS),
+ GFP_KERNEL);
if (!curve)
goto curve_alloc_fail;
- axix_x = kzalloc(sizeof(*axix_x) * (ramp->num_entries + _EXTRA_POINTS),
- GFP_KERNEL);
+ axix_x = kvzalloc(sizeof(*axix_x) * (ramp->num_entries + _EXTRA_POINTS),
+ GFP_KERNEL);
if (!axix_x)
goto axix_x_alloc_fail;
- coeff = kzalloc(sizeof(*coeff) * (MAX_HW_POINTS + _EXTRA_POINTS), GFP_KERNEL);
+ coeff = kvzalloc(sizeof(*coeff) * (MAX_HW_POINTS + _EXTRA_POINTS), GFP_KERNEL);
if (!coeff)
goto coeff_alloc_fail;
@@ -1246,13 +1246,13 @@ bool mod_color_calculate_degamma_params(struct dc_transfer_func *input_tf,
ret = true;
- kfree(coeff);
+ kvfree(coeff);
coeff_alloc_fail:
- kfree(axix_x);
+ kvfree(axix_x);
axix_x_alloc_fail:
- kfree(curve);
+ kvfree(curve);
curve_alloc_fail:
- kfree(rgb_user);
+ kvfree(rgb_user);
rgb_user_alloc_fail:
return ret;
@@ -1281,8 +1281,9 @@ bool mod_color_calculate_curve(enum dc_transfer_func_predefined trans,
}
ret = true;
} else if (trans == TRANSFER_FUNCTION_PQ) {
- rgb_regamma = kzalloc(sizeof(*rgb_regamma) * (MAX_HW_POINTS +
- _EXTRA_POINTS), GFP_KERNEL);
+ rgb_regamma = kvzalloc(sizeof(*rgb_regamma) *
+ (MAX_HW_POINTS + _EXTRA_POINTS),
+ GFP_KERNEL);
if (!rgb_regamma)
goto rgb_regamma_alloc_fail;
points->end_exponent = 7;
@@ -1302,11 +1303,12 @@ bool mod_color_calculate_curve(enum dc_transfer_func_predefined trans,
}
ret = true;
- kfree(rgb_regamma);
+ kvfree(rgb_regamma);
} else if (trans == TRANSFER_FUNCTION_SRGB ||
trans == TRANSFER_FUNCTION_BT709) {
- rgb_regamma = kzalloc(sizeof(*rgb_regamma) * (MAX_HW_POINTS +
- _EXTRA_POINTS), GFP_KERNEL);
+ rgb_regamma = kvzalloc(sizeof(*rgb_regamma) *
+ (MAX_HW_POINTS + _EXTRA_POINTS),
+ GFP_KERNEL);
if (!rgb_regamma)
goto rgb_regamma_alloc_fail;
points->end_exponent = 0;
@@ -1324,7 +1326,7 @@ bool mod_color_calculate_curve(enum dc_transfer_func_predefined trans,
}
ret = true;
- kfree(rgb_regamma);
+ kvfree(rgb_regamma);
}
rgb_regamma_alloc_fail:
return ret;
@@ -1348,8 +1350,9 @@ bool mod_color_calculate_degamma_curve(enum dc_transfer_func_predefined trans,
}
ret = true;
} else if (trans == TRANSFER_FUNCTION_PQ) {
- rgb_degamma = kzalloc(sizeof(*rgb_degamma) * (MAX_HW_POINTS +
- _EXTRA_POINTS), GFP_KERNEL);
+ rgb_degamma = kvzalloc(sizeof(*rgb_degamma) *
+ (MAX_HW_POINTS + _EXTRA_POINTS),
+ GFP_KERNEL);
if (!rgb_degamma)
goto rgb_degamma_alloc_fail;
@@ -1364,11 +1367,12 @@ bool mod_color_calculate_degamma_curve(enum dc_transfer_func_predefined trans,
}
ret = true;
- kfree(rgb_degamma);
+ kvfree(rgb_degamma);
} else if (trans == TRANSFER_FUNCTION_SRGB ||
trans == TRANSFER_FUNCTION_BT709) {
- rgb_degamma = kzalloc(sizeof(*rgb_degamma) * (MAX_HW_POINTS +
- _EXTRA_POINTS), GFP_KERNEL);
+ rgb_degamma = kvzalloc(sizeof(*rgb_degamma) *
+ (MAX_HW_POINTS + _EXTRA_POINTS),
+ GFP_KERNEL);
if (!rgb_degamma)
goto rgb_degamma_alloc_fail;
@@ -1382,7 +1386,7 @@ bool mod_color_calculate_degamma_curve(enum dc_transfer_func_predefined trans,
}
ret = true;
- kfree(rgb_degamma);
+ kvfree(rgb_degamma);
}
points->end_exponent = 0;
points->x_point_at_y1_red = 1;
diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index 0f5ad54..de177ce 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -501,6 +501,32 @@ enum atom_cooling_solution_id{
LIQUID_COOLING = 0x01
};
+struct atom_firmware_info_v3_2 {
+ struct atom_common_table_header table_header;
+ uint32_t firmware_revision;
+ uint32_t bootup_sclk_in10khz;
+ uint32_t bootup_mclk_in10khz;
+ uint32_t firmware_capability; // enum atombios_firmware_capability
+ uint32_t main_call_parser_entry; /* direct address of main parser call in VBIOS binary. */
+ uint32_t bios_scratch_reg_startaddr; // 1st bios scratch register dword address
+ uint16_t bootup_vddc_mv;
+ uint16_t bootup_vddci_mv;
+ uint16_t bootup_mvddc_mv;
+ uint16_t bootup_vddgfx_mv;
+ uint8_t mem_module_id;
+ uint8_t coolingsolution_id; /*0: Air cooling; 1: Liquid cooling ... */
+ uint8_t reserved1[2];
+ uint32_t mc_baseaddr_high;
+ uint32_t mc_baseaddr_low;
+ uint8_t board_i2c_feature_id; // enum of atom_board_i2c_feature_id_def
+ uint8_t board_i2c_feature_gpio_id; // i2c id find in gpio_lut data table gpio_id
+ uint8_t board_i2c_feature_slave_addr;
+ uint8_t reserved3;
+ uint16_t bootup_mvddq_mv;
+ uint16_t bootup_mvpp_mv;
+ uint32_t zfbstartaddrin16mb;
+ uint32_t reserved2[3];
+};
/*
***************************************************************************
@@ -1169,7 +1195,29 @@ struct atom_gfx_info_v2_2
uint32_t rlc_gpu_timer_refclk;
};
-
+struct atom_gfx_info_v2_3 {
+ struct atom_common_table_header table_header;
+ uint8_t gfxip_min_ver;
+ uint8_t gfxip_max_ver;
+ uint8_t max_shader_engines;
+ uint8_t max_tile_pipes;
+ uint8_t max_cu_per_sh;
+ uint8_t max_sh_per_se;
+ uint8_t max_backends_per_se;
+ uint8_t max_texture_channel_caches;
+ uint32_t regaddr_cp_dma_src_addr;
+ uint32_t regaddr_cp_dma_src_addr_hi;
+ uint32_t regaddr_cp_dma_dst_addr;
+ uint32_t regaddr_cp_dma_dst_addr_hi;
+ uint32_t regaddr_cp_dma_command;
+ uint32_t regaddr_cp_status;
+ uint32_t regaddr_rlc_gpu_clock_32;
+ uint32_t rlc_gpu_timer_refclk;
+ uint8_t active_cu_per_sh;
+ uint8_t active_rb_per_se;
+ uint16_t gcgoldenoffset;
+ uint32_t rm21_sram_vmin_value;
+};
/*
***************************************************************************
@@ -1198,6 +1246,76 @@ struct atom_smu_info_v3_1
uint8_t fw_ctf_polarity; // GPIO polarity for CTF
};
+struct atom_smu_info_v3_2 {
+ struct atom_common_table_header table_header;
+ uint8_t smuip_min_ver;
+ uint8_t smuip_max_ver;
+ uint8_t smu_rsd1;
+ uint8_t gpuclk_ss_mode;
+ uint16_t sclk_ss_percentage;
+ uint16_t sclk_ss_rate_10hz;
+ uint16_t gpuclk_ss_percentage; // in unit of 0.001%
+ uint16_t gpuclk_ss_rate_10hz;
+ uint32_t core_refclk_10khz;
+ uint8_t ac_dc_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for AC/DC switching, =0xff means invalid
+ uint8_t ac_dc_polarity; // GPIO polarity for AC/DC switching
+ uint8_t vr0hot_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for VR0 HOT event, =0xff means invalid
+ uint8_t vr0hot_polarity; // GPIO polarity for VR0 HOT event
+ uint8_t vr1hot_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for VR1 HOT event , =0xff means invalid
+ uint8_t vr1hot_polarity; // GPIO polarity for VR1 HOT event
+ uint8_t fw_ctf_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for CTF, =0xff means invalid
+ uint8_t fw_ctf_polarity; // GPIO polarity for CTF
+ uint8_t pcc_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for PCC, =0xff means invalid
+ uint8_t pcc_gpio_polarity; // GPIO polarity for CTF
+ uint16_t smugoldenoffset;
+ uint32_t gpupll_vco_freq_10khz;
+ uint32_t bootup_smnclk_10khz;
+ uint32_t bootup_socclk_10khz;
+ uint32_t bootup_mp0clk_10khz;
+ uint32_t bootup_mp1clk_10khz;
+ uint32_t bootup_lclk_10khz;
+ uint32_t bootup_dcefclk_10khz;
+ uint32_t ctf_threshold_override_value;
+ uint32_t reserved[5];
+};
+
+struct atom_smu_info_v3_3 {
+ struct atom_common_table_header table_header;
+ uint8_t smuip_min_ver;
+ uint8_t smuip_max_ver;
+ uint8_t smu_rsd1;
+ uint8_t gpuclk_ss_mode;
+ uint16_t sclk_ss_percentage;
+ uint16_t sclk_ss_rate_10hz;
+ uint16_t gpuclk_ss_percentage; // in unit of 0.001%
+ uint16_t gpuclk_ss_rate_10hz;
+ uint32_t core_refclk_10khz;
+ uint8_t ac_dc_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for AC/DC switching, =0xff means invalid
+ uint8_t ac_dc_polarity; // GPIO polarity for AC/DC switching
+ uint8_t vr0hot_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for VR0 HOT event, =0xff means invalid
+ uint8_t vr0hot_polarity; // GPIO polarity for VR0 HOT event
+ uint8_t vr1hot_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for VR1 HOT event , =0xff means invalid
+ uint8_t vr1hot_polarity; // GPIO polarity for VR1 HOT event
+ uint8_t fw_ctf_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for CTF, =0xff means invalid
+ uint8_t fw_ctf_polarity; // GPIO polarity for CTF
+ uint8_t pcc_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for PCC, =0xff means invalid
+ uint8_t pcc_gpio_polarity; // GPIO polarity for CTF
+ uint16_t smugoldenoffset;
+ uint32_t gpupll_vco_freq_10khz;
+ uint32_t bootup_smnclk_10khz;
+ uint32_t bootup_socclk_10khz;
+ uint32_t bootup_mp0clk_10khz;
+ uint32_t bootup_mp1clk_10khz;
+ uint32_t bootup_lclk_10khz;
+ uint32_t bootup_dcefclk_10khz;
+ uint32_t ctf_threshold_override_value;
+ uint32_t syspll3_0_vco_freq_10khz;
+ uint32_t syspll3_1_vco_freq_10khz;
+ uint32_t bootup_fclk_10khz;
+ uint32_t bootup_waflclk_10khz;
+ uint32_t reserved[3];
+};
+
/*
***************************************************************************
Data Table smc_dpm_info structure
@@ -1283,7 +1401,6 @@ struct atom_smc_dpm_info_v4_1
uint32_t boardreserved[10];
};
-
/*
***************************************************************************
Data Table asic_profiling_info structure
@@ -1864,6 +1981,55 @@ enum atom_smu9_syspll0_clock_id
SMU9_SYSPLL0_DISPCLK_ID = 11, // DISPCLK
};
+enum atom_smu11_syspll_id {
+ SMU11_SYSPLL0_ID = 0,
+ SMU11_SYSPLL1_0_ID = 1,
+ SMU11_SYSPLL1_1_ID = 2,
+ SMU11_SYSPLL1_2_ID = 3,
+ SMU11_SYSPLL2_ID = 4,
+ SMU11_SYSPLL3_0_ID = 5,
+ SMU11_SYSPLL3_1_ID = 6,
+};
+
+
+enum atom_smu11_syspll0_clock_id {
+ SMU11_SYSPLL0_SOCCLK_ID = 0, // SOCCLK
+ SMU11_SYSPLL0_MP0CLK_ID = 1, // MP0CLK
+ SMU11_SYSPLL0_DCLK_ID = 2, // DCLK
+ SMU11_SYSPLL0_VCLK_ID = 3, // VCLK
+ SMU11_SYSPLL0_ECLK_ID = 4, // ECLK
+ SMU11_SYSPLL0_DCEFCLK_ID = 5, // DCEFCLK
+};
+
+
+enum atom_smu11_syspll1_0_clock_id {
+ SMU11_SYSPLL1_0_UCLKA_ID = 0, // UCLK_a
+};
+
+enum atom_smu11_syspll1_1_clock_id {
+ SMU11_SYSPLL1_0_UCLKB_ID = 0, // UCLK_b
+};
+
+enum atom_smu11_syspll1_2_clock_id {
+ SMU11_SYSPLL1_0_FCLK_ID = 0, // FCLK
+};
+
+enum atom_smu11_syspll2_clock_id {
+ SMU11_SYSPLL2_GFXCLK_ID = 0, // GFXCLK
+};
+
+enum atom_smu11_syspll3_0_clock_id {
+ SMU11_SYSPLL3_0_WAFCLK_ID = 0, // WAFCLK
+ SMU11_SYSPLL3_0_DISPCLK_ID = 1, // DISPCLK
+ SMU11_SYSPLL3_0_DPREFCLK_ID = 2, // DPREFCLK
+};
+
+enum atom_smu11_syspll3_1_clock_id {
+ SMU11_SYSPLL3_1_MP1CLK_ID = 0, // MP1CLK
+ SMU11_SYSPLL3_1_SMNCLK_ID = 1, // SMNCLK
+ SMU11_SYSPLL3_1_LCLK_ID = 2, // LCLK
+};
+
struct atom_get_smu_clock_info_output_parameters_v3_1
{
union {
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index add9067..18b5b2f 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -79,12 +79,13 @@
#define PCIE_BUS_CLK 10000
#define TCLK (PCIE_BUS_CLK / 10)
-static const struct profile_mode_setting smu7_profiling[5] =
+static const struct profile_mode_setting smu7_profiling[6] =
{{1, 0, 100, 30, 1, 0, 100, 10},
{1, 10, 0, 30, 0, 0, 0, 0},
{0, 0, 0, 0, 1, 10, 16, 31},
{1, 0, 11, 50, 1, 0, 100, 10},
{1, 0, 5, 30, 0, 0, 0, 0},
+ {0, 0, 0, 0, 0, 0, 0, 0},
};
/** Values for the CG_THERMAL_CTRL::DPM_EVENT_SRC field. */
@@ -4743,23 +4744,27 @@ static void smu7_check_dpm_table_updated(struct pp_hwmgr *hwmgr)
for (i=0; i < dep_table->count; i++) {
if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
- data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC;
- break;
+ data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_MCLK;
+ return;
}
}
- if (i == dep_table->count)
+ if (i == dep_table->count && data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_VDDC) {
data->need_update_smu7_dpm_table &= ~DPMTABLE_OD_UPDATE_VDDC;
+ data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_MCLK;
+ }
dep_table = table_info->vdd_dep_on_sclk;
odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dependency_on_sclk);
for (i=0; i < dep_table->count; i++) {
if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
- data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC;
- break;
+ data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_SCLK;
+ return;
}
}
- if (i == dep_table->count)
+ if (i == dep_table->count && data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_VDDC) {
data->need_update_smu7_dpm_table &= ~DPMTABLE_OD_UPDATE_VDDC;
+ data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_SCLK;
+ }
}
static int smu7_odn_edit_dpm_table(struct pp_hwmgr *hwmgr,
@@ -4860,6 +4865,17 @@ static int smu7_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
len = sizeof(smu7_profiling) / sizeof(struct profile_mode_setting);
for (i = 0; i < len; i++) {
+ if (i == hwmgr->power_profile_mode) {
+ size += sprintf(buf + size, "%3d %14s %s: %8d %16d %16d %16d %16d %16d\n",
+ i, profile_name[i], "*",
+ data->current_profile_setting.sclk_up_hyst,
+ data->current_profile_setting.sclk_down_hyst,
+ data->current_profile_setting.sclk_activity,
+ data->current_profile_setting.mclk_up_hyst,
+ data->current_profile_setting.mclk_down_hyst,
+ data->current_profile_setting.mclk_activity);
+ continue;
+ }
if (smu7_profiling[i].bupdate_sclk)
size += sprintf(buf + size, "%3d %16s: %8d %16d %16d ",
i, profile_name[i], smu7_profiling[i].sclk_up_hyst,
@@ -4879,24 +4895,6 @@ static int smu7_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
"-", "-", "-");
}
- size += sprintf(buf + size, "%3d %16s: %8d %16d %16d %16d %16d %16d\n",
- i, profile_name[i],
- data->custom_profile_setting.sclk_up_hyst,
- data->custom_profile_setting.sclk_down_hyst,
- data->custom_profile_setting.sclk_activity,
- data->custom_profile_setting.mclk_up_hyst,
- data->custom_profile_setting.mclk_down_hyst,
- data->custom_profile_setting.mclk_activity);
-
- size += sprintf(buf + size, "%3s %16s: %8d %16d %16d %16d %16d %16d\n",
- "*", "CURRENT",
- data->current_profile_setting.sclk_up_hyst,
- data->current_profile_setting.sclk_down_hyst,
- data->current_profile_setting.sclk_activity,
- data->current_profile_setting.mclk_up_hyst,
- data->current_profile_setting.mclk_down_hyst,
- data->current_profile_setting.mclk_activity);
-
return size;
}
@@ -4935,16 +4933,16 @@ static int smu7_set_power_profile_mode(struct pp_hwmgr *hwmgr, long *input, uint
if (size < 8)
return -EINVAL;
- data->custom_profile_setting.bupdate_sclk = input[0];
- data->custom_profile_setting.sclk_up_hyst = input[1];
- data->custom_profile_setting.sclk_down_hyst = input[2];
- data->custom_profile_setting.sclk_activity = input[3];
- data->custom_profile_setting.bupdate_mclk = input[4];
- data->custom_profile_setting.mclk_up_hyst = input[5];
- data->custom_profile_setting.mclk_down_hyst = input[6];
- data->custom_profile_setting.mclk_activity = input[7];
- if (!smum_update_dpm_settings(hwmgr, &data->custom_profile_setting)) {
- memcpy(&data->current_profile_setting, &data->custom_profile_setting, sizeof(struct profile_mode_setting));
+ tmp.bupdate_sclk = input[0];
+ tmp.sclk_up_hyst = input[1];
+ tmp.sclk_down_hyst = input[2];
+ tmp.sclk_activity = input[3];
+ tmp.bupdate_mclk = input[4];
+ tmp.mclk_up_hyst = input[5];
+ tmp.mclk_down_hyst = input[6];
+ tmp.mclk_activity = input[7];
+ if (!smum_update_dpm_settings(hwmgr, &tmp)) {
+ memcpy(&data->current_profile_setting, &tmp, sizeof(struct profile_mode_setting));
hwmgr->power_profile_mode = mode;
}
break;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h
index f40179c..b8d0bb3 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h
@@ -325,7 +325,6 @@ struct smu7_hwmgr {
uint16_t mem_latency_high;
uint16_t mem_latency_low;
uint32_t vr_config;
- struct profile_mode_setting custom_profile_setting;
struct profile_mode_setting current_profile_setting;
};
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c
index 03bc745..d9e92e3 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c
@@ -852,12 +852,10 @@ int smu7_set_power_limit(struct pp_hwmgr *hwmgr, uint32_t n)
{
struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
- n = (n & 0xff) << 8;
-
if (data->power_containment_features &
POWERCONTAINMENT_FEATURE_PkgPwrLimit)
return smum_send_msg_to_smc_with_parameter(hwmgr,
- PPSMC_MSG_PkgPwrSetLimit, n);
+ PPSMC_MSG_PkgPwrSetLimit, n<<8);
return 0;
}
diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h b/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
index fb696e3..2f8a3b9 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
@@ -412,8 +412,10 @@ typedef struct {
QuadraticInt_t ReservedEquation2;
QuadraticInt_t ReservedEquation3;
+ uint16_t MinVoltageUlvGfx;
+ uint16_t MinVoltageUlvSoc;
- uint32_t Reserved[15];
+ uint32_t Reserved[14];
diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig
index 3aa65bd..684ac62 100644
--- a/drivers/gpu/drm/bridge/Kconfig
+++ b/drivers/gpu/drm/bridge/Kconfig
@@ -74,6 +74,7 @@
tristate "Silicon Image SII8620 HDMI/MHL bridge"
depends on OF && RC_CORE
select DRM_KMS_HELPER
+ imply EXTCON
help
Silicon Image SII8620 HDMI/MHL bridge chip driver.
diff --git a/drivers/gpu/drm/bridge/dumb-vga-dac.c b/drivers/gpu/drm/bridge/dumb-vga-dac.c
index 498d594..9837c8d 100644
--- a/drivers/gpu/drm/bridge/dumb-vga-dac.c
+++ b/drivers/gpu/drm/bridge/dumb-vga-dac.c
@@ -56,7 +56,9 @@ static int dumb_vga_get_modes(struct drm_connector *connector)
}
drm_mode_connector_update_edid_property(connector, edid);
- return drm_add_edid_modes(connector, edid);
+ ret = drm_add_edid_modes(connector, edid);
+ kfree(edid);
+ return ret;
fallback:
/*
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
index ec8d0006..3c136f2b 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
@@ -2077,7 +2077,7 @@ static irqreturn_t dw_hdmi_hardirq(int irq, void *dev_id)
return ret;
}
-void __dw_hdmi_setup_rx_sense(struct dw_hdmi *hdmi, bool hpd, bool rx_sense)
+void dw_hdmi_setup_rx_sense(struct dw_hdmi *hdmi, bool hpd, bool rx_sense)
{
mutex_lock(&hdmi->mutex);
@@ -2103,13 +2103,6 @@ void __dw_hdmi_setup_rx_sense(struct dw_hdmi *hdmi, bool hpd, bool rx_sense)
}
mutex_unlock(&hdmi->mutex);
}
-
-void dw_hdmi_setup_rx_sense(struct device *dev, bool hpd, bool rx_sense)
-{
- struct dw_hdmi *hdmi = dev_get_drvdata(dev);
-
- __dw_hdmi_setup_rx_sense(hdmi, hpd, rx_sense);
-}
EXPORT_SYMBOL_GPL(dw_hdmi_setup_rx_sense);
static irqreturn_t dw_hdmi_irq(int irq, void *dev_id)
@@ -2145,9 +2138,9 @@ static irqreturn_t dw_hdmi_irq(int irq, void *dev_id)
*/
if (intr_stat &
(HDMI_IH_PHY_STAT0_RX_SENSE | HDMI_IH_PHY_STAT0_HPD)) {
- __dw_hdmi_setup_rx_sense(hdmi,
- phy_stat & HDMI_PHY_HPD,
- phy_stat & HDMI_PHY_RX_SENSE);
+ dw_hdmi_setup_rx_sense(hdmi,
+ phy_stat & HDMI_PHY_HPD,
+ phy_stat & HDMI_PHY_RX_SENSE);
if ((phy_stat & (HDMI_PHY_RX_SENSE | HDMI_PHY_HPD)) == 0)
cec_notifier_set_phys_addr(hdmi->cec_notifier,
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 7d25c42..c825c76 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -155,6 +155,8 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state)
state->connectors[i].state);
state->connectors[i].ptr = NULL;
state->connectors[i].state = NULL;
+ state->connectors[i].old_state = NULL;
+ state->connectors[i].new_state = NULL;
drm_connector_put(connector);
}
@@ -169,6 +171,8 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state)
state->crtcs[i].ptr = NULL;
state->crtcs[i].state = NULL;
+ state->crtcs[i].old_state = NULL;
+ state->crtcs[i].new_state = NULL;
}
for (i = 0; i < config->num_total_plane; i++) {
@@ -181,6 +185,8 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state)
state->planes[i].state);
state->planes[i].ptr = NULL;
state->planes[i].state = NULL;
+ state->planes[i].old_state = NULL;
+ state->planes[i].new_state = NULL;
}
for (i = 0; i < state->num_private_objs; i++) {
@@ -190,6 +196,8 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state)
state->private_objs[i].state);
state->private_objs[i].ptr = NULL;
state->private_objs[i].state = NULL;
+ state->private_objs[i].old_state = NULL;
+ state->private_objs[i].new_state = NULL;
}
state->num_private_objs = 0;
diff --git a/drivers/gpu/drm/drm_dp_dual_mode_helper.c b/drivers/gpu/drm/drm_dp_dual_mode_helper.c
index 02a5092..e7f4fe2 100644
--- a/drivers/gpu/drm/drm_dp_dual_mode_helper.c
+++ b/drivers/gpu/drm/drm_dp_dual_mode_helper.c
@@ -350,19 +350,44 @@ int drm_dp_dual_mode_set_tmds_output(enum drm_dp_dual_mode_type type,
{
uint8_t tmds_oen = enable ? 0 : DP_DUAL_MODE_TMDS_DISABLE;
ssize_t ret;
+ int retry;
if (type < DRM_DP_DUAL_MODE_TYPE2_DVI)
return 0;
- ret = drm_dp_dual_mode_write(adapter, DP_DUAL_MODE_TMDS_OEN,
- &tmds_oen, sizeof(tmds_oen));
- if (ret) {
- DRM_DEBUG_KMS("Failed to %s TMDS output buffers\n",
- enable ? "enable" : "disable");
- return ret;
+ /*
+ * LSPCON adapters in low-power state may ignore the first write, so
+ * read back and verify the written value a few times.
+ */
+ for (retry = 0; retry < 3; retry++) {
+ uint8_t tmp;
+
+ ret = drm_dp_dual_mode_write(adapter, DP_DUAL_MODE_TMDS_OEN,
+ &tmds_oen, sizeof(tmds_oen));
+ if (ret) {
+ DRM_DEBUG_KMS("Failed to %s TMDS output buffers (%d attempts)\n",
+ enable ? "enable" : "disable",
+ retry + 1);
+ return ret;
+ }
+
+ ret = drm_dp_dual_mode_read(adapter, DP_DUAL_MODE_TMDS_OEN,
+ &tmp, sizeof(tmp));
+ if (ret) {
+ DRM_DEBUG_KMS("I2C read failed during TMDS output buffer %s (%d attempts)\n",
+ enable ? "enabling" : "disabling",
+ retry + 1);
+ return ret;
+ }
+
+ if (tmp == tmds_oen)
+ return 0;
}
- return 0;
+ DRM_DEBUG_KMS("I2C write value mismatch during TMDS output buffer %s\n",
+ enable ? "enabling" : "disabling");
+
+ return -EIO;
}
EXPORT_SYMBOL(drm_dp_dual_mode_set_tmds_output);
diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index ffe14ec..70ae1f2 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -1145,6 +1145,7 @@ int drm_dp_psr_setup_time(const u8 psr_cap[EDP_PSR_RECEIVER_CAP_SIZE])
static const u16 psr_setup_time_us[] = {
PSR_SETUP_TIME(330),
PSR_SETUP_TIME(275),
+ PSR_SETUP_TIME(220),
PSR_SETUP_TIME(165),
PSR_SETUP_TIME(110),
PSR_SETUP_TIME(55),
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index a1b9338..c2c21d8 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -716,7 +716,7 @@ static void remove_compat_control_link(struct drm_device *dev)
if (!minor)
return;
- name = kasprintf(GFP_KERNEL, "controlD%d", minor->index);
+ name = kasprintf(GFP_KERNEL, "controlD%d", minor->index + 64);
if (!name)
return;
diff --git a/drivers/gpu/drm/drm_dumb_buffers.c b/drivers/gpu/drm/drm_dumb_buffers.c
index 39ac15c..9e2ae02 100644
--- a/drivers/gpu/drm/drm_dumb_buffers.c
+++ b/drivers/gpu/drm/drm_dumb_buffers.c
@@ -65,12 +65,13 @@ int drm_mode_create_dumb_ioctl(struct drm_device *dev,
return -EINVAL;
/* overflow checks for 32bit size calculations */
- /* NOTE: DIV_ROUND_UP() can overflow */
+ if (args->bpp > U32_MAX - 8)
+ return -EINVAL;
cpp = DIV_ROUND_UP(args->bpp, 8);
- if (!cpp || cpp > 0xffffffffU / args->width)
+ if (cpp > U32_MAX / args->width)
return -EINVAL;
stride = cpp * args->width;
- if (args->height > 0xffffffffU / stride)
+ if (args->height > U32_MAX / stride)
return -EINVAL;
/* test for wrap-around */
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 134069f..39f1db4a 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -4451,6 +4451,7 @@ drm_reset_display_info(struct drm_connector *connector)
info->max_tmds_clock = 0;
info->dvi_dual = false;
info->has_hdmi_infoframe = false;
+ memset(&info->hdmi, 0, sizeof(info->hdmi));
info->non_desktop = 0;
}
@@ -4462,17 +4463,11 @@ u32 drm_add_display_info(struct drm_connector *connector, const struct edid *edi
u32 quirks = edid_get_quirks(edid);
+ drm_reset_display_info(connector);
+
info->width_mm = edid->width_cm * 10;
info->height_mm = edid->height_cm * 10;
- /* driver figures it out in this case */
- info->bpc = 0;
- info->color_formats = 0;
- info->cea_rev = 0;
- info->max_tmds_clock = 0;
- info->dvi_dual = false;
- info->has_hdmi_infoframe = false;
-
info->non_desktop = !!(quirks & EDID_QUIRK_NON_DESKTOP);
DRM_DEBUG_KMS("non_desktop set to %d\n", info->non_desktop);
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index e394799..6d9b945 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -212,6 +212,7 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor)
return -ENOMEM;
filp->private_data = priv;
+ filp->f_mode |= FMODE_UNSIGNED_OFFSET;
priv->filp = filp;
priv->pid = get_pid(task_pid(current));
priv->minor = minor;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c
index 0faaf82..f0e7917 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fb.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c
@@ -18,6 +18,7 @@
#include <drm/drm_fb_helper.h>
#include <drm/drm_atomic.h>
#include <drm/drm_atomic_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
#include <uapi/drm/exynos_drm.h>
#include "exynos_drm_drv.h"
@@ -26,20 +27,6 @@
#include "exynos_drm_iommu.h"
#include "exynos_drm_crtc.h"
-#define to_exynos_fb(x) container_of(x, struct exynos_drm_fb, fb)
-
-/*
- * exynos specific framebuffer structure.
- *
- * @fb: drm framebuffer obejct.
- * @exynos_gem: array of exynos specific gem object containing a gem object.
- */
-struct exynos_drm_fb {
- struct drm_framebuffer fb;
- struct exynos_drm_gem *exynos_gem[MAX_FB_BUFFER];
- dma_addr_t dma_addr[MAX_FB_BUFFER];
-};
-
static int check_fb_gem_memory_type(struct drm_device *drm_dev,
struct exynos_drm_gem *exynos_gem)
{
@@ -66,40 +53,9 @@ static int check_fb_gem_memory_type(struct drm_device *drm_dev,
return 0;
}
-static void exynos_drm_fb_destroy(struct drm_framebuffer *fb)
-{
- struct exynos_drm_fb *exynos_fb = to_exynos_fb(fb);
- unsigned int i;
-
- drm_framebuffer_cleanup(fb);
-
- for (i = 0; i < ARRAY_SIZE(exynos_fb->exynos_gem); i++) {
- struct drm_gem_object *obj;
-
- if (exynos_fb->exynos_gem[i] == NULL)
- continue;
-
- obj = &exynos_fb->exynos_gem[i]->base;
- drm_gem_object_unreference_unlocked(obj);
- }
-
- kfree(exynos_fb);
- exynos_fb = NULL;
-}
-
-static int exynos_drm_fb_create_handle(struct drm_framebuffer *fb,
- struct drm_file *file_priv,
- unsigned int *handle)
-{
- struct exynos_drm_fb *exynos_fb = to_exynos_fb(fb);
-
- return drm_gem_handle_create(file_priv,
- &exynos_fb->exynos_gem[0]->base, handle);
-}
-
static const struct drm_framebuffer_funcs exynos_drm_fb_funcs = {
- .destroy = exynos_drm_fb_destroy,
- .create_handle = exynos_drm_fb_create_handle,
+ .destroy = drm_gem_fb_destroy,
+ .create_handle = drm_gem_fb_create_handle,
};
struct drm_framebuffer *
@@ -108,12 +64,12 @@ exynos_drm_framebuffer_init(struct drm_device *dev,
struct exynos_drm_gem **exynos_gem,
int count)
{
- struct exynos_drm_fb *exynos_fb;
+ struct drm_framebuffer *fb;
int i;
int ret;
- exynos_fb = kzalloc(sizeof(*exynos_fb), GFP_KERNEL);
- if (!exynos_fb)
+ fb = kzalloc(sizeof(*fb), GFP_KERNEL);
+ if (!fb)
return ERR_PTR(-ENOMEM);
for (i = 0; i < count; i++) {
@@ -121,23 +77,21 @@ exynos_drm_framebuffer_init(struct drm_device *dev,
if (ret < 0)
goto err;
- exynos_fb->exynos_gem[i] = exynos_gem[i];
- exynos_fb->dma_addr[i] = exynos_gem[i]->dma_addr
- + mode_cmd->offsets[i];
+ fb->obj[i] = &exynos_gem[i]->base;
}
- drm_helper_mode_fill_fb_struct(dev, &exynos_fb->fb, mode_cmd);
+ drm_helper_mode_fill_fb_struct(dev, fb, mode_cmd);
- ret = drm_framebuffer_init(dev, &exynos_fb->fb, &exynos_drm_fb_funcs);
+ ret = drm_framebuffer_init(dev, fb, &exynos_drm_fb_funcs);
if (ret < 0) {
DRM_ERROR("failed to initialize framebuffer\n");
goto err;
}
- return &exynos_fb->fb;
+ return fb;
err:
- kfree(exynos_fb);
+ kfree(fb);
return ERR_PTR(ret);
}
@@ -191,12 +145,13 @@ exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
dma_addr_t exynos_drm_fb_dma_addr(struct drm_framebuffer *fb, int index)
{
- struct exynos_drm_fb *exynos_fb = to_exynos_fb(fb);
+ struct exynos_drm_gem *exynos_gem;
if (WARN_ON_ONCE(index >= MAX_FB_BUFFER))
return 0;
- return exynos_fb->dma_addr[index];
+ exynos_gem = to_exynos_gem(fb->obj[index]);
+ return exynos_gem->dma_addr + fb->offsets[index];
}
static struct drm_mode_config_helper_funcs exynos_drm_mode_config_helpers = {
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index abd84cb..09c4bc0 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -954,8 +954,6 @@ static int hdmi_create_connector(struct drm_encoder *encoder)
drm_mode_connector_attach_encoder(connector, encoder);
if (hdata->bridge) {
- encoder->bridge = hdata->bridge;
- hdata->bridge->encoder = encoder;
ret = drm_bridge_attach(encoder, hdata->bridge, NULL);
if (ret)
DRM_ERROR("Failed to attach bridge\n");
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index 257299e..272c79f 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -473,7 +473,7 @@ static void vp_video_buffer(struct mixer_context *ctx,
chroma_addr[1] = chroma_addr[0] + 0x40;
} else {
luma_addr[1] = luma_addr[0] + fb->pitches[0];
- chroma_addr[1] = chroma_addr[0] + fb->pitches[0];
+ chroma_addr[1] = chroma_addr[0] + fb->pitches[1];
}
} else {
luma_addr[1] = 0;
@@ -482,6 +482,7 @@ static void vp_video_buffer(struct mixer_context *ctx,
spin_lock_irqsave(&ctx->reg_slock, flags);
+ vp_reg_write(ctx, VP_SHADOW_UPDATE, 1);
/* interlace or progressive scan mode */
val = (test_bit(MXR_BIT_INTERLACE, &ctx->flags) ? ~0 : 0);
vp_reg_writemask(ctx, VP_MODE, val, VP_MODE_LINE_SKIP);
@@ -495,21 +496,23 @@ static void vp_video_buffer(struct mixer_context *ctx,
vp_reg_write(ctx, VP_IMG_SIZE_Y, VP_IMG_HSIZE(fb->pitches[0]) |
VP_IMG_VSIZE(fb->height));
/* chroma plane for NV12/NV21 is half the height of the luma plane */
- vp_reg_write(ctx, VP_IMG_SIZE_C, VP_IMG_HSIZE(fb->pitches[0]) |
+ vp_reg_write(ctx, VP_IMG_SIZE_C, VP_IMG_HSIZE(fb->pitches[1]) |
VP_IMG_VSIZE(fb->height / 2));
vp_reg_write(ctx, VP_SRC_WIDTH, state->src.w);
- vp_reg_write(ctx, VP_SRC_HEIGHT, state->src.h);
vp_reg_write(ctx, VP_SRC_H_POSITION,
VP_SRC_H_POSITION_VAL(state->src.x));
- vp_reg_write(ctx, VP_SRC_V_POSITION, state->src.y);
-
vp_reg_write(ctx, VP_DST_WIDTH, state->crtc.w);
vp_reg_write(ctx, VP_DST_H_POSITION, state->crtc.x);
+
if (test_bit(MXR_BIT_INTERLACE, &ctx->flags)) {
+ vp_reg_write(ctx, VP_SRC_HEIGHT, state->src.h / 2);
+ vp_reg_write(ctx, VP_SRC_V_POSITION, state->src.y / 2);
vp_reg_write(ctx, VP_DST_HEIGHT, state->crtc.h / 2);
vp_reg_write(ctx, VP_DST_V_POSITION, state->crtc.y / 2);
} else {
+ vp_reg_write(ctx, VP_SRC_HEIGHT, state->src.h);
+ vp_reg_write(ctx, VP_SRC_V_POSITION, state->src.y);
vp_reg_write(ctx, VP_DST_HEIGHT, state->crtc.h);
vp_reg_write(ctx, VP_DST_V_POSITION, state->crtc.y);
}
@@ -699,6 +702,15 @@ static irqreturn_t mixer_irq_handler(int irq, void *arg)
/* interlace scan need to check shadow register */
if (test_bit(MXR_BIT_INTERLACE, &ctx->flags)) {
+ if (test_bit(MXR_BIT_VP_ENABLED, &ctx->flags) &&
+ vp_reg_read(ctx, VP_SHADOW_UPDATE))
+ goto out;
+
+ base = mixer_reg_read(ctx, MXR_CFG);
+ shadow = mixer_reg_read(ctx, MXR_CFG_S);
+ if (base != shadow)
+ goto out;
+
base = mixer_reg_read(ctx, MXR_GRAPHIC_BASE(0));
shadow = mixer_reg_read(ctx, MXR_GRAPHIC_BASE_S(0));
if (base != shadow)
diff --git a/drivers/gpu/drm/exynos/regs-mixer.h b/drivers/gpu/drm/exynos/regs-mixer.h
index c311f57..189cfa2 100644
--- a/drivers/gpu/drm/exynos/regs-mixer.h
+++ b/drivers/gpu/drm/exynos/regs-mixer.h
@@ -47,6 +47,7 @@
#define MXR_MO 0x0304
#define MXR_RESOLUTION 0x0310
+#define MXR_CFG_S 0x2004
#define MXR_GRAPHIC0_BASE_S 0x2024
#define MXR_GRAPHIC1_BASE_S 0x2044
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index db6b94d..d85939b 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -1080,6 +1080,7 @@ static int cmd_handler_mi_user_interrupt(struct parser_exec_state *s)
{
set_bit(cmd_interrupt_events[s->ring_id].mi_user_interrupt,
s->workload->pending_events);
+ patch_value(s, cmd_ptr(s, 0), MI_NOOP);
return 0;
}
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index dd96ffc..6d8180e 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -169,6 +169,8 @@ static u8 dpcd_fix_data[DPCD_HEADER_SIZE] = {
static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
{
struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
+ int pipe;
+
vgpu_vreg_t(vgpu, SDEISR) &= ~(SDE_PORTB_HOTPLUG_CPT |
SDE_PORTC_HOTPLUG_CPT |
SDE_PORTD_HOTPLUG_CPT);
@@ -267,6 +269,14 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
if (IS_BROADWELL(dev_priv))
vgpu_vreg_t(vgpu, PCH_ADPA) &= ~ADPA_CRT_HOTPLUG_MONITOR_MASK;
+ /* Disable Primary/Sprite/Cursor plane */
+ for_each_pipe(dev_priv, pipe) {
+ vgpu_vreg_t(vgpu, DSPCNTR(pipe)) &= ~DISPLAY_PLANE_ENABLE;
+ vgpu_vreg_t(vgpu, SPRCTL(pipe)) &= ~SPRITE_ENABLE;
+ vgpu_vreg_t(vgpu, CURCNTR(pipe)) &= ~CURSOR_MODE;
+ vgpu_vreg_t(vgpu, CURCNTR(pipe)) |= CURSOR_MODE_DISABLE;
+ }
+
vgpu_vreg_t(vgpu, PIPECONF(PIPE_A)) |= PIPECONF_ENABLE;
}
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index b555eb2..6f4f8e9 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -323,6 +323,7 @@ static void update_fb_info(struct vfio_device_gfx_plane_info *gvt_dmabuf,
struct intel_vgpu_fb_info *fb_info)
{
gvt_dmabuf->drm_format = fb_info->drm_format;
+ gvt_dmabuf->drm_format_mod = fb_info->drm_format_mod;
gvt_dmabuf->width = fb_info->width;
gvt_dmabuf->height = fb_info->height;
gvt_dmabuf->stride = fb_info->stride;
diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.c b/drivers/gpu/drm/i915/gvt/fb_decoder.c
index 6b50fe7..1c12068 100644
--- a/drivers/gpu/drm/i915/gvt/fb_decoder.c
+++ b/drivers/gpu/drm/i915/gvt/fb_decoder.c
@@ -245,16 +245,13 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu,
plane->hw_format = fmt;
plane->base = vgpu_vreg_t(vgpu, DSPSURF(pipe)) & I915_GTT_PAGE_MASK;
- if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) {
- gvt_vgpu_err("invalid gma address: %lx\n",
- (unsigned long)plane->base);
+ if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0))
return -EINVAL;
- }
plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base);
if (plane->base_gpa == INTEL_GVT_INVALID_ADDR) {
- gvt_vgpu_err("invalid gma address: %lx\n",
- (unsigned long)plane->base);
+ gvt_vgpu_err("Translate primary plane gma 0x%x to gpa fail\n",
+ plane->base);
return -EINVAL;
}
@@ -371,16 +368,13 @@ int intel_vgpu_decode_cursor_plane(struct intel_vgpu *vgpu,
alpha_plane, alpha_force);
plane->base = vgpu_vreg_t(vgpu, CURBASE(pipe)) & I915_GTT_PAGE_MASK;
- if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) {
- gvt_vgpu_err("invalid gma address: %lx\n",
- (unsigned long)plane->base);
+ if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0))
return -EINVAL;
- }
plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base);
if (plane->base_gpa == INTEL_GVT_INVALID_ADDR) {
- gvt_vgpu_err("invalid gma address: %lx\n",
- (unsigned long)plane->base);
+ gvt_vgpu_err("Translate cursor plane gma 0x%x to gpa fail\n",
+ plane->base);
return -EINVAL;
}
@@ -476,16 +470,13 @@ int intel_vgpu_decode_sprite_plane(struct intel_vgpu *vgpu,
plane->drm_format = drm_format;
plane->base = vgpu_vreg_t(vgpu, SPRSURF(pipe)) & I915_GTT_PAGE_MASK;
- if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) {
- gvt_vgpu_err("invalid gma address: %lx\n",
- (unsigned long)plane->base);
+ if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0))
return -EINVAL;
- }
plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base);
if (plane->base_gpa == INTEL_GVT_INVALID_ADDR) {
- gvt_vgpu_err("invalid gma address: %lx\n",
- (unsigned long)plane->base);
+ gvt_vgpu_err("Translate sprite plane gma 0x%x to gpa fail\n",
+ plane->base);
return -EINVAL;
}
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index d292812..78e55aa 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -530,6 +530,16 @@ static void ggtt_set_guest_entry(struct intel_vgpu_mm *mm,
false, 0, mm->vgpu);
}
+static void ggtt_get_host_entry(struct intel_vgpu_mm *mm,
+ struct intel_gvt_gtt_entry *entry, unsigned long index)
+{
+ struct intel_gvt_gtt_pte_ops *pte_ops = mm->vgpu->gvt->gtt.pte_ops;
+
+ GEM_BUG_ON(mm->type != INTEL_GVT_MM_GGTT);
+
+ pte_ops->get_entry(NULL, entry, index, false, 0, mm->vgpu);
+}
+
static void ggtt_set_host_entry(struct intel_vgpu_mm *mm,
struct intel_gvt_gtt_entry *entry, unsigned long index)
{
@@ -1818,6 +1828,18 @@ int intel_vgpu_emulate_ggtt_mmio_read(struct intel_vgpu *vgpu, unsigned int off,
return ret;
}
+static void ggtt_invalidate_pte(struct intel_vgpu *vgpu,
+ struct intel_gvt_gtt_entry *entry)
+{
+ struct intel_gvt_gtt_pte_ops *pte_ops = vgpu->gvt->gtt.pte_ops;
+ unsigned long pfn;
+
+ pfn = pte_ops->get_pfn(entry);
+ if (pfn != vgpu->gvt->gtt.scratch_mfn)
+ intel_gvt_hypervisor_dma_unmap_guest_page(vgpu,
+ pfn << PAGE_SHIFT);
+}
+
static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
void *p_data, unsigned int bytes)
{
@@ -1844,10 +1866,10 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
memcpy((void *)&e.val64 + (off & (info->gtt_entry_size - 1)), p_data,
bytes);
- m = e;
if (ops->test_present(&e)) {
gfn = ops->get_pfn(&e);
+ m = e;
/* one PTE update may be issued in multiple writes and the
* first write may not construct a valid gfn
@@ -1868,8 +1890,12 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
ops->set_pfn(&m, gvt->gtt.scratch_mfn);
} else
ops->set_pfn(&m, dma_addr >> PAGE_SHIFT);
- } else
+ } else {
+ ggtt_get_host_entry(ggtt_mm, &m, g_gtt_index);
+ ggtt_invalidate_pte(vgpu, &m);
ops->set_pfn(&m, gvt->gtt.scratch_mfn);
+ ops->clear_present(&m);
+ }
out:
ggtt_set_host_entry(ggtt_mm, &m, g_gtt_index);
@@ -2030,7 +2056,7 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu)
return PTR_ERR(gtt->ggtt_mm);
}
- intel_vgpu_reset_ggtt(vgpu);
+ intel_vgpu_reset_ggtt(vgpu, false);
return create_scratch_page_tree(vgpu);
}
@@ -2315,17 +2341,19 @@ void intel_vgpu_invalidate_ppgtt(struct intel_vgpu *vgpu)
/**
* intel_vgpu_reset_ggtt - reset the GGTT entry
* @vgpu: a vGPU
+ * @invalidate_old: invalidate old entries
*
* This function is called at the vGPU create stage
* to reset all the GGTT entries.
*
*/
-void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu)
+void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old)
{
struct intel_gvt *gvt = vgpu->gvt;
struct drm_i915_private *dev_priv = gvt->dev_priv;
struct intel_gvt_gtt_pte_ops *pte_ops = vgpu->gvt->gtt.pte_ops;
struct intel_gvt_gtt_entry entry = {.type = GTT_TYPE_GGTT_PTE};
+ struct intel_gvt_gtt_entry old_entry;
u32 index;
u32 num_entries;
@@ -2334,13 +2362,23 @@ void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu)
index = vgpu_aperture_gmadr_base(vgpu) >> PAGE_SHIFT;
num_entries = vgpu_aperture_sz(vgpu) >> PAGE_SHIFT;
- while (num_entries--)
+ while (num_entries--) {
+ if (invalidate_old) {
+ ggtt_get_host_entry(vgpu->gtt.ggtt_mm, &old_entry, index);
+ ggtt_invalidate_pte(vgpu, &old_entry);
+ }
ggtt_set_host_entry(vgpu->gtt.ggtt_mm, &entry, index++);
+ }
index = vgpu_hidden_gmadr_base(vgpu) >> PAGE_SHIFT;
num_entries = vgpu_hidden_sz(vgpu) >> PAGE_SHIFT;
- while (num_entries--)
+ while (num_entries--) {
+ if (invalidate_old) {
+ ggtt_get_host_entry(vgpu->gtt.ggtt_mm, &old_entry, index);
+ ggtt_invalidate_pte(vgpu, &old_entry);
+ }
ggtt_set_host_entry(vgpu->gtt.ggtt_mm, &entry, index++);
+ }
ggtt_invalidate(dev_priv);
}
@@ -2360,5 +2398,5 @@ void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu)
* removing the shadow pages.
*/
intel_vgpu_destroy_all_ppgtt_mm(vgpu);
- intel_vgpu_reset_ggtt(vgpu);
+ intel_vgpu_reset_ggtt(vgpu, true);
}
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index a8b369c..3792f2b 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -193,7 +193,7 @@ struct intel_vgpu_gtt {
extern int intel_vgpu_init_gtt(struct intel_vgpu *vgpu);
extern void intel_vgpu_clean_gtt(struct intel_vgpu *vgpu);
-void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu);
+void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old);
void intel_vgpu_invalidate_ppgtt(struct intel_vgpu *vgpu);
extern int intel_gvt_init_gtt(struct intel_gvt *gvt);
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 8c5d5d0..a33c1c3e 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1150,6 +1150,7 @@ static int handle_g2v_notification(struct intel_vgpu *vgpu, int notification)
switch (notification) {
case VGT_G2V_PPGTT_L3_PAGE_TABLE_CREATE:
root_entry_type = GTT_TYPE_PPGTT_ROOT_L3_ENTRY;
+ /* fall through */
case VGT_G2V_PPGTT_L4_PAGE_TABLE_CREATE:
mm = intel_vgpu_get_ppgtt_mm(vgpu, root_entry_type, pdps);
return PTR_ERR_OR_ZERO(mm);
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index c16a4924..1466d87 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -1301,7 +1301,7 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd,
}
- return 0;
+ return -ENOTTY;
}
static ssize_t
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 84ca369..3b4daaf 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1105,30 +1105,32 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
ret = i915_ggtt_probe_hw(dev_priv);
if (ret)
- return ret;
+ goto err_perf;
- /* WARNING: Apparently we must kick fbdev drivers before vgacon,
- * otherwise the vga fbdev driver falls over. */
+ /*
+ * WARNING: Apparently we must kick fbdev drivers before vgacon,
+ * otherwise the vga fbdev driver falls over.
+ */
ret = i915_kick_out_firmware_fb(dev_priv);
if (ret) {
DRM_ERROR("failed to remove conflicting framebuffer drivers\n");
- goto out_ggtt;
+ goto err_ggtt;
}
ret = i915_kick_out_vgacon(dev_priv);
if (ret) {
DRM_ERROR("failed to remove conflicting VGA console\n");
- goto out_ggtt;
+ goto err_ggtt;
}
ret = i915_ggtt_init_hw(dev_priv);
if (ret)
- return ret;
+ goto err_ggtt;
ret = i915_ggtt_enable_hw(dev_priv);
if (ret) {
DRM_ERROR("failed to enable GGTT\n");
- goto out_ggtt;
+ goto err_ggtt;
}
pci_set_master(pdev);
@@ -1139,7 +1141,7 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
if (ret) {
DRM_ERROR("failed to set DMA mask\n");
- goto out_ggtt;
+ goto err_ggtt;
}
}
@@ -1157,7 +1159,7 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
if (ret) {
DRM_ERROR("failed to set DMA mask\n");
- goto out_ggtt;
+ goto err_ggtt;
}
}
@@ -1190,13 +1192,14 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
ret = intel_gvt_init(dev_priv);
if (ret)
- goto out_ggtt;
+ goto err_ggtt;
return 0;
-out_ggtt:
+err_ggtt:
i915_ggtt_cleanup_hw(dev_priv);
-
+err_perf:
+ i915_perf_fini(dev_priv);
return ret;
}
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 8c170db..0414228 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -728,7 +728,7 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb)
err = radix_tree_insert(handles_vma, handle, vma);
if (unlikely(err)) {
- kfree(lut);
+ kmem_cache_free(eb->i915->luts, lut);
goto err_obj;
}
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index d596a83..854bd51 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -778,6 +778,9 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
I915_USERPTR_UNSYNCHRONIZED))
return -EINVAL;
+ if (!args->user_size)
+ return -EINVAL;
+
if (offset_in_page(args->user_ptr | args->user_size))
return -EINVAL;
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index d8feb90..f0519e3 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -473,20 +473,37 @@ static u64 get_rc6(struct drm_i915_private *i915)
spin_lock_irqsave(&i915->pmu.lock, flags);
spin_lock(&kdev->power.lock);
- if (!i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur)
- i915->pmu.suspended_jiffies_last =
- kdev->power.suspended_jiffies;
+ /*
+ * After the above branch intel_runtime_pm_get_if_in_use failed
+ * to get the runtime PM reference we cannot assume we are in
+ * runtime suspend since we can either: a) race with coming out
+ * of it before we took the power.lock, or b) there are other
+ * states than suspended which can bring us here.
+ *
+ * We need to double-check that we are indeed currently runtime
+ * suspended and if not we cannot do better than report the last
+ * known RC6 value.
+ */
+ if (kdev->power.runtime_status == RPM_SUSPENDED) {
+ if (!i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur)
+ i915->pmu.suspended_jiffies_last =
+ kdev->power.suspended_jiffies;
- val = kdev->power.suspended_jiffies -
- i915->pmu.suspended_jiffies_last;
- val += jiffies - kdev->power.accounting_timestamp;
+ val = kdev->power.suspended_jiffies -
+ i915->pmu.suspended_jiffies_last;
+ val += jiffies - kdev->power.accounting_timestamp;
+
+ val = jiffies_to_nsecs(val);
+ val += i915->pmu.sample[__I915_SAMPLE_RC6].cur;
+
+ i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur = val;
+ } else if (i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur) {
+ val = i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur;
+ } else {
+ val = i915->pmu.sample[__I915_SAMPLE_RC6].cur;
+ }
spin_unlock(&kdev->power.lock);
-
- val = jiffies_to_nsecs(val);
- val += i915->pmu.sample[__I915_SAMPLE_RC6].cur;
- i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur = val;
-
spin_unlock_irqrestore(&i915->pmu.lock, flags);
}
diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index 3ace929..3f502ee 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -4,6 +4,8 @@
* Copyright © 2018 Intel Corporation
*/
+#include <linux/nospec.h>
+
#include "i915_drv.h"
#include "i915_query.h"
#include <uapi/drm/i915_drm.h>
@@ -100,7 +102,7 @@ int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
for (i = 0; i < args->num_items; i++, user_item_ptr++) {
struct drm_i915_query_item item;
- u64 func_idx;
+ unsigned long func_idx;
int ret;
if (copy_from_user(&item, user_item_ptr, sizeof(item)))
@@ -109,12 +111,17 @@ int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
if (item.query_id == 0)
return -EINVAL;
+ if (overflows_type(item.query_id - 1, unsigned long))
+ return -EINVAL;
+
func_idx = item.query_id - 1;
- if (func_idx < ARRAY_SIZE(i915_query_funcs))
+ ret = -EINVAL;
+ if (func_idx < ARRAY_SIZE(i915_query_funcs)) {
+ func_idx = array_index_nospec(func_idx,
+ ARRAY_SIZE(i915_query_funcs));
ret = i915_query_funcs[func_idx](dev_priv, &item);
- else
- ret = -EINVAL;
+ }
/* Only write the length back to userspace if they differ. */
if (ret != item.length && put_user(ret, &user_item_ptr->length))
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index e6a8c0e..8a69a92 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7326,6 +7326,9 @@ enum {
#define SLICE_ECO_CHICKEN0 _MMIO(0x7308)
#define PIXEL_MASK_CAMMING_DISABLE (1 << 14)
+#define GEN9_WM_CHICKEN3 _MMIO(0x5588)
+#define GEN9_FACTOR_IN_CLR_VAL_HIZ (1 << 9)
+
/* WaCatErrorRejectionIssue */
#define GEN7_SQ_CHICKEN_MBCUNIT_CONFIG _MMIO(0x9030)
#define GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB (1<<11)
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 709d6ca..3ea566f 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -729,7 +729,7 @@ static void i915_audio_component_codec_wake_override(struct device *kdev,
struct drm_i915_private *dev_priv = kdev_to_i915(kdev);
u32 tmp;
- if (!IS_GEN9_BC(dev_priv))
+ if (!IS_GEN9(dev_priv))
return;
i915_audio_component_get_power(kdev);
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index c5c7530..447b721 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -1256,7 +1256,6 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
return;
aux_channel = child->aux_channel;
- ddc_pin = child->ddc_pin;
is_dvi = child->device_type & DEVICE_TYPE_TMDS_DVI_SIGNALING;
is_dp = child->device_type & DEVICE_TYPE_DISPLAYPORT_OUTPUT;
@@ -1303,9 +1302,15 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
DRM_DEBUG_KMS("Port %c is internal DP\n", port_name(port));
if (is_dvi) {
- info->alternate_ddc_pin = map_ddc_pin(dev_priv, ddc_pin);
-
- sanitize_ddc_pin(dev_priv, port);
+ ddc_pin = map_ddc_pin(dev_priv, child->ddc_pin);
+ if (intel_gmbus_is_valid_pin(dev_priv, ddc_pin)) {
+ info->alternate_ddc_pin = ddc_pin;
+ sanitize_ddc_pin(dev_priv, port);
+ } else {
+ DRM_DEBUG_KMS("Port %c has invalid DDC pin %d, "
+ "sticking to defaults\n",
+ port_name(port), ddc_pin);
+ }
}
if (is_dp) {
diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c
index fc8b2c6..704ddb4 100644
--- a/drivers/gpu/drm/i915/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/intel_cdclk.c
@@ -2140,10 +2140,22 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state)
}
}
- /* According to BSpec, "The CD clock frequency must be at least twice
+ /*
+ * According to BSpec, "The CD clock frequency must be at least twice
* the frequency of the Azalia BCLK." and BCLK is 96 MHz by default.
+ *
+ * FIXME: Check the actual, not default, BCLK being used.
+ *
+ * FIXME: This does not depend on ->has_audio because the higher CDCLK
+ * is required for audio probe, also when there are no audio capable
+ * displays connected at probe time. This leads to unnecessarily high
+ * CDCLK when audio is not required.
+ *
+ * FIXME: This limit is only applied when there are displays connected
+ * at probe time. If we probe without displays, we'll still end up using
+ * the platform minimum CDCLK, failing audio probe.
*/
- if (crtc_state->has_audio && INTEL_GEN(dev_priv) >= 9)
+ if (INTEL_GEN(dev_priv) >= 9)
min_cdclk = max(2 * 96000, min_cdclk);
/*
@@ -2290,9 +2302,44 @@ static int bdw_modeset_calc_cdclk(struct drm_atomic_state *state)
return 0;
}
+static int skl_dpll0_vco(struct intel_atomic_state *intel_state)
+{
+ struct drm_i915_private *dev_priv = to_i915(intel_state->base.dev);
+ struct intel_crtc *crtc;
+ struct intel_crtc_state *crtc_state;
+ int vco, i;
+
+ vco = intel_state->cdclk.logical.vco;
+ if (!vco)
+ vco = dev_priv->skl_preferred_vco_freq;
+
+ for_each_new_intel_crtc_in_state(intel_state, crtc, crtc_state, i) {
+ if (!crtc_state->base.enable)
+ continue;
+
+ if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP))
+ continue;
+
+ /*
+ * DPLL0 VCO may need to be adjusted to get the correct
+ * clock for eDP. This will affect cdclk as well.
+ */
+ switch (crtc_state->port_clock / 2) {
+ case 108000:
+ case 216000:
+ vco = 8640000;
+ break;
+ default:
+ vco = 8100000;
+ break;
+ }
+ }
+
+ return vco;
+}
+
static int skl_modeset_calc_cdclk(struct drm_atomic_state *state)
{
- struct drm_i915_private *dev_priv = to_i915(state->dev);
struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
int min_cdclk, cdclk, vco;
@@ -2300,9 +2347,7 @@ static int skl_modeset_calc_cdclk(struct drm_atomic_state *state)
if (min_cdclk < 0)
return min_cdclk;
- vco = intel_state->cdclk.logical.vco;
- if (!vco)
- vco = dev_priv->skl_preferred_vco_freq;
+ vco = skl_dpll0_vco(intel_state);
/*
* FIXME should also account for plane ratio
diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c
index 41e6c75..f9550ea 100644
--- a/drivers/gpu/drm/i915/intel_csr.c
+++ b/drivers/gpu/drm/i915/intel_csr.c
@@ -35,6 +35,7 @@
*/
#define I915_CSR_GLK "i915/glk_dmc_ver1_04.bin"
+MODULE_FIRMWARE(I915_CSR_GLK);
#define GLK_CSR_VERSION_REQUIRED CSR_VERSION(1, 4)
#define I915_CSR_CNL "i915/cnl_dmc_ver1_07.bin"
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 3b48fd2..56004ff 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -15178,6 +15178,8 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
memset(&crtc->base.mode, 0, sizeof(crtc->base.mode));
if (crtc_state->base.active) {
intel_mode_from_pipe_config(&crtc->base.mode, crtc_state);
+ crtc->base.mode.hdisplay = crtc_state->pipe_src_w;
+ crtc->base.mode.vdisplay = crtc_state->pipe_src_h;
intel_mode_from_pipe_config(&crtc_state->base.adjusted_mode, crtc_state);
WARN_ON(drm_atomic_set_mode_for_crtc(crtc->base.state, &crtc->base.mode));
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 9a4a51e..b7b4cfd 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1881,26 +1881,6 @@ intel_dp_compute_config(struct intel_encoder *encoder,
reduce_m_n);
}
- /*
- * DPLL0 VCO may need to be adjusted to get the correct
- * clock for eDP. This will affect cdclk as well.
- */
- if (intel_dp_is_edp(intel_dp) && IS_GEN9_BC(dev_priv)) {
- int vco;
-
- switch (pipe_config->port_clock / 2) {
- case 108000:
- case 216000:
- vco = 8640000;
- break;
- default:
- vco = 8100000;
- break;
- }
-
- to_intel_atomic_state(pipe_config->base.state)->cdclk.logical.vco = vco;
- }
-
if (!HAS_DDI(dev_priv))
intel_dp_set_clock(encoder, pipe_config);
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index d436858..a80fbad 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -49,12 +49,12 @@
* check the condition before the timeout.
*/
#define __wait_for(OP, COND, US, Wmin, Wmax) ({ \
- unsigned long timeout__ = jiffies + usecs_to_jiffies(US) + 1; \
+ const ktime_t end__ = ktime_add_ns(ktime_get_raw(), 1000ll * (US)); \
long wait__ = (Wmin); /* recommended min for usleep is 10 us */ \
int ret__; \
might_sleep(); \
for (;;) { \
- bool expired__ = time_after(jiffies, timeout__); \
+ const bool expired__ = ktime_after(ktime_get_raw(), end__); \
OP; \
if (COND) { \
ret__ = 0; \
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 4ba139c..f7c2582 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1149,6 +1149,10 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine)
WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_GPGPU_LEVEL_MASK,
GEN9_PREEMPT_GPGPU_COMMAND_LEVEL);
+ /* WaClearHIZ_WM_CHICKEN3:bxt,glk */
+ if (IS_GEN9_LP(dev_priv))
+ WA_SET_BIT_MASKED(GEN9_WM_CHICKEN3, GEN9_FACTOR_IN_CLR_VAL_HIZ);
+
/* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt,glk,cfl */
ret = wa_ring_whitelist_reg(engine, GEN9_CTX_PREEMPT_REG);
if (ret)
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index 6f12adc..6467a5c 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -806,7 +806,7 @@ void intel_fbdev_output_poll_changed(struct drm_device *dev)
return;
intel_fbdev_sync(ifbdev);
- if (ifbdev->vma)
+ if (ifbdev->vma || ifbdev->helper.deferred_setup)
drm_fb_helper_hotplug_event(&ifbdev->helper);
}
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 697af5a..8704f7f 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -577,6 +577,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
* know the next preemption status we see corresponds
* to this ELSP update.
*/
+ GEM_BUG_ON(!execlists_is_active(execlists,
+ EXECLISTS_ACTIVE_USER));
GEM_BUG_ON(!port_count(&port[0]));
if (port_count(&port[0]) > 1)
goto unlock;
@@ -738,6 +740,8 @@ execlists_cancel_port_requests(struct intel_engine_execlists * const execlists)
memset(port, 0, sizeof(*port));
port++;
}
+
+ execlists_clear_active(execlists, EXECLISTS_ACTIVE_USER);
}
static void execlists_cancel_requests(struct intel_engine_cs *engine)
@@ -880,6 +884,7 @@ static void execlists_submission_tasklet(unsigned long data)
head = execlists->csb_head;
tail = READ_ONCE(buf[write_idx]);
+ rmb(); /* Hopefully paired with a wmb() in HW */
}
GEM_TRACE("%s cs-irq head=%d [%d%s], tail=%d [%d%s]\n",
engine->name,
@@ -1001,6 +1006,11 @@ static void execlists_submission_tasklet(unsigned long data)
if (fw)
intel_uncore_forcewake_put(dev_priv, execlists->fw_domains);
+
+ /* If the engine is now idle, so should be the flag; and vice versa. */
+ GEM_BUG_ON(execlists_is_active(&engine->execlists,
+ EXECLISTS_ACTIVE_USER) ==
+ !port_isset(engine->execlists.port));
}
static void queue_request(struct intel_engine_cs *engine,
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index d35d2d5..e125d16 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -326,7 +326,8 @@ static void intel_enable_lvds(struct intel_encoder *encoder,
I915_WRITE(PP_CONTROL(0), I915_READ(PP_CONTROL(0)) | PANEL_POWER_ON);
POSTING_READ(lvds_encoder->reg);
- if (intel_wait_for_register(dev_priv, PP_STATUS(0), PP_ON, PP_ON, 1000))
+
+ if (intel_wait_for_register(dev_priv, PP_STATUS(0), PP_ON, PP_ON, 5000))
DRM_ERROR("timed out waiting for panel to power on\n");
intel_panel_enable_backlight(pipe_config, conn_state);
@@ -573,6 +574,36 @@ static int intel_lid_notify(struct notifier_block *nb, unsigned long val,
return NOTIFY_OK;
}
+static int
+intel_lvds_connector_register(struct drm_connector *connector)
+{
+ struct intel_lvds_connector *lvds = to_lvds_connector(connector);
+ int ret;
+
+ ret = intel_connector_register(connector);
+ if (ret)
+ return ret;
+
+ lvds->lid_notifier.notifier_call = intel_lid_notify;
+ if (acpi_lid_notifier_register(&lvds->lid_notifier)) {
+ DRM_DEBUG_KMS("lid notifier registration failed\n");
+ lvds->lid_notifier.notifier_call = NULL;
+ }
+
+ return 0;
+}
+
+static void
+intel_lvds_connector_unregister(struct drm_connector *connector)
+{
+ struct intel_lvds_connector *lvds = to_lvds_connector(connector);
+
+ if (lvds->lid_notifier.notifier_call)
+ acpi_lid_notifier_unregister(&lvds->lid_notifier);
+
+ intel_connector_unregister(connector);
+}
+
/**
* intel_lvds_destroy - unregister and free LVDS structures
* @connector: connector to free
@@ -585,9 +616,6 @@ static void intel_lvds_destroy(struct drm_connector *connector)
struct intel_lvds_connector *lvds_connector =
to_lvds_connector(connector);
- if (lvds_connector->lid_notifier.notifier_call)
- acpi_lid_notifier_unregister(&lvds_connector->lid_notifier);
-
if (!IS_ERR_OR_NULL(lvds_connector->base.edid))
kfree(lvds_connector->base.edid);
@@ -608,8 +636,8 @@ static const struct drm_connector_funcs intel_lvds_connector_funcs = {
.fill_modes = drm_helper_probe_single_connector_modes,
.atomic_get_property = intel_digital_connector_atomic_get_property,
.atomic_set_property = intel_digital_connector_atomic_set_property,
- .late_register = intel_connector_register,
- .early_unregister = intel_connector_unregister,
+ .late_register = intel_lvds_connector_register,
+ .early_unregister = intel_lvds_connector_unregister,
.destroy = intel_lvds_destroy,
.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
.atomic_duplicate_state = intel_digital_connector_duplicate_state,
@@ -826,6 +854,14 @@ static const struct dmi_system_id intel_no_lvds[] = {
DMI_EXACT_MATCH(DMI_BOARD_NAME, "D525MW"),
},
},
+ {
+ .callback = intel_no_lvds_dmi_callback,
+ .ident = "Radiant P845",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Radiant Systems Inc"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "P845"),
+ },
+ },
{ } /* terminating entry */
};
@@ -1149,12 +1185,6 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
lvds_encoder->a3_power = lvds & LVDS_A3_POWER_MASK;
- lvds_connector->lid_notifier.notifier_call = intel_lid_notify;
- if (acpi_lid_notifier_register(&lvds_connector->lid_notifier)) {
- DRM_DEBUG_KMS("lid notifier registration failed\n");
- lvds_connector->lid_notifier.notifier_call = NULL;
- }
-
return;
failed:
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 53ea564..66de4b2 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -641,19 +641,18 @@ void skl_enable_dc6(struct drm_i915_private *dev_priv)
DRM_DEBUG_KMS("Enabling DC6\n");
- gen9_set_dc_state(dev_priv, DC_STATE_EN_UPTO_DC6);
+ /* Wa Display #1183: skl,kbl,cfl */
+ if (IS_GEN9_BC(dev_priv))
+ I915_WRITE(GEN8_CHICKEN_DCPR_1, I915_READ(GEN8_CHICKEN_DCPR_1) |
+ SKL_SELECT_ALTERNATE_DC_EXIT);
+ gen9_set_dc_state(dev_priv, DC_STATE_EN_UPTO_DC6);
}
void skl_disable_dc6(struct drm_i915_private *dev_priv)
{
DRM_DEBUG_KMS("Disabling DC6\n");
- /* Wa Display #1183: skl,kbl,cfl */
- if (IS_GEN9_BC(dev_priv))
- I915_WRITE(GEN8_CHICKEN_DCPR_1, I915_READ(GEN8_CHICKEN_DCPR_1) |
- SKL_SELECT_ALTERNATE_DC_EXIT);
-
gen9_set_dc_state(dev_priv, DC_STATE_DISABLE);
}
diff --git a/drivers/gpu/drm/meson/meson_dw_hdmi.c b/drivers/gpu/drm/meson/meson_dw_hdmi.c
index a393095..c9ad456 100644
--- a/drivers/gpu/drm/meson/meson_dw_hdmi.c
+++ b/drivers/gpu/drm/meson/meson_dw_hdmi.c
@@ -529,7 +529,7 @@ static irqreturn_t dw_hdmi_top_thread_irq(int irq, void *dev_id)
if (stat & HDMITX_TOP_INTR_HPD_RISE)
hpd_connected = true;
- dw_hdmi_setup_rx_sense(dw_hdmi->dev, hpd_connected,
+ dw_hdmi_setup_rx_sense(dw_hdmi->hdmi, hpd_connected,
hpd_connected);
drm_helper_hpd_irq_event(dw_hdmi->encoder.dev);
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c
index 6e5e1aa..b001699 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c
@@ -351,6 +351,7 @@ static void mdp4_crtc_atomic_flush(struct drm_crtc *crtc,
spin_lock_irqsave(&dev->event_lock, flags);
mdp4_crtc->event = crtc->state->event;
+ crtc->state->event = NULL;
spin_unlock_irqrestore(&dev->event_lock, flags);
blend_setup(crtc);
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index 9893e43..76b9608 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -708,6 +708,7 @@ static void mdp5_crtc_atomic_flush(struct drm_crtc *crtc,
spin_lock_irqsave(&dev->event_lock, flags);
mdp5_crtc->event = crtc->state->event;
+ crtc->state->event = NULL;
spin_unlock_irqrestore(&dev->event_lock, flags);
/*
diff --git a/drivers/gpu/drm/msm/disp/mdp_format.c b/drivers/gpu/drm/msm/disp/mdp_format.c
index b4a8aa4..005760b 100644
--- a/drivers/gpu/drm/msm/disp/mdp_format.c
+++ b/drivers/gpu/drm/msm/disp/mdp_format.c
@@ -171,7 +171,8 @@ uint32_t mdp_get_formats(uint32_t *pixel_formats, uint32_t max_formats,
return i;
}
-const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format)
+const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format,
+ uint64_t modifier)
{
int i;
for (i = 0; i < ARRAY_SIZE(formats); i++) {
diff --git a/drivers/gpu/drm/msm/disp/mdp_kms.h b/drivers/gpu/drm/msm/disp/mdp_kms.h
index 1185487..4fa8dbe 100644
--- a/drivers/gpu/drm/msm/disp/mdp_kms.h
+++ b/drivers/gpu/drm/msm/disp/mdp_kms.h
@@ -98,7 +98,7 @@ struct mdp_format {
#define MDP_FORMAT_IS_YUV(mdp_format) ((mdp_format)->is_yuv)
uint32_t mdp_get_formats(uint32_t *formats, uint32_t max_formats, bool rgb_only);
-const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format);
+const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format, uint64_t modifier);
/* MDP capabilities */
#define MDP_CAP_SMP BIT(0) /* Shared Memory Pool */
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 7a03a94..8baba30 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -173,6 +173,7 @@ struct msm_dsi_host {
bool registered;
bool power_on;
+ bool enabled;
int irq;
};
@@ -775,7 +776,7 @@ static inline enum dsi_cmd_dst_format dsi_get_cmd_fmt(
switch (mipi_fmt) {
case MIPI_DSI_FMT_RGB888: return CMD_DST_FORMAT_RGB888;
case MIPI_DSI_FMT_RGB666_PACKED:
- case MIPI_DSI_FMT_RGB666: return VID_DST_FORMAT_RGB666;
+ case MIPI_DSI_FMT_RGB666: return CMD_DST_FORMAT_RGB666;
case MIPI_DSI_FMT_RGB565: return CMD_DST_FORMAT_RGB565;
default: return CMD_DST_FORMAT_RGB888;
}
@@ -986,13 +987,19 @@ static void dsi_set_tx_power_mode(int mode, struct msm_dsi_host *msm_host)
static void dsi_wait4video_done(struct msm_dsi_host *msm_host)
{
+ u32 ret = 0;
+ struct device *dev = &msm_host->pdev->dev;
+
dsi_intr_ctrl(msm_host, DSI_IRQ_MASK_VIDEO_DONE, 1);
reinit_completion(&msm_host->video_comp);
- wait_for_completion_timeout(&msm_host->video_comp,
+ ret = wait_for_completion_timeout(&msm_host->video_comp,
msecs_to_jiffies(70));
+ if (ret <= 0)
+ dev_err(dev, "wait for video done timed out\n");
+
dsi_intr_ctrl(msm_host, DSI_IRQ_MASK_VIDEO_DONE, 0);
}
@@ -1001,7 +1008,7 @@ static void dsi_wait4video_eng_busy(struct msm_dsi_host *msm_host)
if (!(msm_host->mode_flags & MIPI_DSI_MODE_VIDEO))
return;
- if (msm_host->power_on) {
+ if (msm_host->power_on && msm_host->enabled) {
dsi_wait4video_done(msm_host);
/* delay 4 ms to skip BLLP */
usleep_range(2000, 4000);
@@ -2203,7 +2210,7 @@ int msm_dsi_host_enable(struct mipi_dsi_host *host)
* pm_runtime_put_autosuspend(&msm_host->pdev->dev);
* }
*/
-
+ msm_host->enabled = true;
return 0;
}
@@ -2211,6 +2218,7 @@ int msm_dsi_host_disable(struct mipi_dsi_host *host)
{
struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+ msm_host->enabled = false;
dsi_op_mode_config(msm_host,
!!(msm_host->mode_flags & MIPI_DSI_MODE_VIDEO), false);
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index 8e9d5c2..9a9fa0c 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -265,6 +265,115 @@ int msm_dsi_dphy_timing_calc_v2(struct msm_dsi_dphy_timing *timing,
return 0;
}
+int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing,
+ struct msm_dsi_phy_clk_request *clk_req)
+{
+ const unsigned long bit_rate = clk_req->bitclk_rate;
+ const unsigned long esc_rate = clk_req->escclk_rate;
+ s32 ui, ui_x8, lpx;
+ s32 tmax, tmin;
+ s32 pcnt0 = 50;
+ s32 pcnt1 = 50;
+ s32 pcnt2 = 10;
+ s32 pcnt3 = 30;
+ s32 pcnt4 = 10;
+ s32 pcnt5 = 2;
+ s32 coeff = 1000; /* Precision, should avoid overflow */
+ s32 hb_en, hb_en_ckln;
+ s32 temp;
+
+ if (!bit_rate || !esc_rate)
+ return -EINVAL;
+
+ timing->hs_halfbyte_en = 0;
+ hb_en = 0;
+ timing->hs_halfbyte_en_ckln = 0;
+ hb_en_ckln = 0;
+
+ ui = mult_frac(NSEC_PER_MSEC, coeff, bit_rate / 1000);
+ ui_x8 = ui << 3;
+ lpx = mult_frac(NSEC_PER_MSEC, coeff, esc_rate / 1000);
+
+ temp = S_DIV_ROUND_UP(38 * coeff, ui_x8);
+ tmin = max_t(s32, temp, 0);
+ temp = (95 * coeff) / ui_x8;
+ tmax = max_t(s32, temp, 0);
+ timing->clk_prepare = linear_inter(tmax, tmin, pcnt0, 0, false);
+
+ temp = 300 * coeff - (timing->clk_prepare << 3) * ui;
+ tmin = S_DIV_ROUND_UP(temp, ui_x8) - 1;
+ tmax = (tmin > 255) ? 511 : 255;
+ timing->clk_zero = linear_inter(tmax, tmin, pcnt5, 0, false);
+
+ tmin = DIV_ROUND_UP(60 * coeff + 3 * ui, ui_x8);
+ temp = 105 * coeff + 12 * ui - 20 * coeff;
+ tmax = (temp + 3 * ui) / ui_x8;
+ timing->clk_trail = linear_inter(tmax, tmin, pcnt3, 0, false);
+
+ temp = S_DIV_ROUND_UP(40 * coeff + 4 * ui, ui_x8);
+ tmin = max_t(s32, temp, 0);
+ temp = (85 * coeff + 6 * ui) / ui_x8;
+ tmax = max_t(s32, temp, 0);
+ timing->hs_prepare = linear_inter(tmax, tmin, pcnt1, 0, false);
+
+ temp = 145 * coeff + 10 * ui - (timing->hs_prepare << 3) * ui;
+ tmin = S_DIV_ROUND_UP(temp, ui_x8) - 1;
+ tmax = 255;
+ timing->hs_zero = linear_inter(tmax, tmin, pcnt4, 0, false);
+
+ tmin = DIV_ROUND_UP(60 * coeff + 4 * ui, ui_x8) - 1;
+ temp = 105 * coeff + 12 * ui - 20 * coeff;
+ tmax = (temp / ui_x8) - 1;
+ timing->hs_trail = linear_inter(tmax, tmin, pcnt3, 0, false);
+
+ temp = 50 * coeff + ((hb_en << 2) - 8) * ui;
+ timing->hs_rqst = S_DIV_ROUND_UP(temp, ui_x8);
+
+ tmin = DIV_ROUND_UP(100 * coeff, ui_x8) - 1;
+ tmax = 255;
+ timing->hs_exit = linear_inter(tmax, tmin, pcnt2, 0, false);
+
+ temp = 50 * coeff + ((hb_en_ckln << 2) - 8) * ui;
+ timing->hs_rqst_ckln = S_DIV_ROUND_UP(temp, ui_x8);
+
+ temp = 60 * coeff + 52 * ui - 43 * ui;
+ tmin = DIV_ROUND_UP(temp, ui_x8) - 1;
+ tmax = 63;
+ timing->shared_timings.clk_post =
+ linear_inter(tmax, tmin, pcnt2, 0, false);
+
+ temp = 8 * ui + (timing->clk_prepare << 3) * ui;
+ temp += (((timing->clk_zero + 3) << 3) + 11) * ui;
+ temp += hb_en_ckln ? (((timing->hs_rqst_ckln << 3) + 4) * ui) :
+ (((timing->hs_rqst_ckln << 3) + 8) * ui);
+ tmin = S_DIV_ROUND_UP(temp, ui_x8) - 1;
+ tmax = 63;
+ if (tmin > tmax) {
+ temp = linear_inter(tmax << 1, tmin, pcnt2, 0, false);
+ timing->shared_timings.clk_pre = temp >> 1;
+ timing->shared_timings.clk_pre_inc_by_2 = 1;
+ } else {
+ timing->shared_timings.clk_pre =
+ linear_inter(tmax, tmin, pcnt2, 0, false);
+ timing->shared_timings.clk_pre_inc_by_2 = 0;
+ }
+
+ timing->ta_go = 3;
+ timing->ta_sure = 0;
+ timing->ta_get = 4;
+
+ DBG("%d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d, %d",
+ timing->shared_timings.clk_pre, timing->shared_timings.clk_post,
+ timing->shared_timings.clk_pre_inc_by_2, timing->clk_zero,
+ timing->clk_trail, timing->clk_prepare, timing->hs_exit,
+ timing->hs_zero, timing->hs_prepare, timing->hs_trail,
+ timing->hs_rqst, timing->hs_rqst_ckln, timing->hs_halfbyte_en,
+ timing->hs_halfbyte_en_ckln, timing->hs_prep_dly,
+ timing->hs_prep_dly_ckln);
+
+ return 0;
+}
+
void msm_dsi_phy_set_src_pll(struct msm_dsi_phy *phy, int pll_id, u32 reg,
u32 bit_mask)
{
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
index c56268c..a24ab80 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
@@ -101,6 +101,8 @@ int msm_dsi_dphy_timing_calc(struct msm_dsi_dphy_timing *timing,
struct msm_dsi_phy_clk_request *clk_req);
int msm_dsi_dphy_timing_calc_v2(struct msm_dsi_dphy_timing *timing,
struct msm_dsi_phy_clk_request *clk_req);
+int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing,
+ struct msm_dsi_phy_clk_request *clk_req);
void msm_dsi_phy_set_src_pll(struct msm_dsi_phy *phy, int pll_id, u32 reg,
u32 bit_mask);
int msm_dsi_phy_init_common(struct msm_dsi_phy *phy);
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
index 0af951a..b3fffc8 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
@@ -79,34 +79,6 @@ static void dsi_phy_hw_v3_0_lane_settings(struct msm_dsi_phy *phy)
dsi_phy_write(lane_base + REG_DSI_10nm_PHY_LN_TX_DCTRL(3), 0x04);
}
-static int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing,
- struct msm_dsi_phy_clk_request *clk_req)
-{
- /*
- * TODO: These params need to be computed, they're currently hardcoded
- * for a 1440x2560@60Hz panel with a byteclk of 100.618 Mhz, and a
- * default escape clock of 19.2 Mhz.
- */
-
- timing->hs_halfbyte_en = 0;
- timing->clk_zero = 0x1c;
- timing->clk_prepare = 0x07;
- timing->clk_trail = 0x07;
- timing->hs_exit = 0x23;
- timing->hs_zero = 0x21;
- timing->hs_prepare = 0x07;
- timing->hs_trail = 0x07;
- timing->hs_rqst = 0x05;
- timing->ta_sure = 0x00;
- timing->ta_go = 0x03;
- timing->ta_get = 0x04;
-
- timing->shared_timings.clk_pre = 0x2d;
- timing->shared_timings.clk_post = 0x0d;
-
- return 0;
-}
-
static int dsi_10nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
struct msm_dsi_phy_clk_request *clk_req)
{
diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c
index 0e0c872..7a16242 100644
--- a/drivers/gpu/drm/msm/msm_fb.c
+++ b/drivers/gpu/drm/msm/msm_fb.c
@@ -183,7 +183,8 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
hsub = drm_format_horz_chroma_subsampling(mode_cmd->pixel_format);
vsub = drm_format_vert_chroma_subsampling(mode_cmd->pixel_format);
- format = kms->funcs->get_format(kms, mode_cmd->pixel_format);
+ format = kms->funcs->get_format(kms, mode_cmd->pixel_format,
+ mode_cmd->modifier[0]);
if (!format) {
dev_err(dev->dev, "unsupported pixel format: %4.4s\n",
(char *)&mode_cmd->pixel_format);
diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c
index c178563..456622b 100644
--- a/drivers/gpu/drm/msm/msm_fbdev.c
+++ b/drivers/gpu/drm/msm/msm_fbdev.c
@@ -92,8 +92,7 @@ static int msm_fbdev_create(struct drm_fb_helper *helper,
if (IS_ERR(fb)) {
dev_err(dev->dev, "failed to allocate fb\n");
- ret = PTR_ERR(fb);
- goto fail;
+ return PTR_ERR(fb);
}
bo = msm_framebuffer_bo(fb, 0);
@@ -151,13 +150,7 @@ static int msm_fbdev_create(struct drm_fb_helper *helper,
fail_unlock:
mutex_unlock(&dev->struct_mutex);
-fail:
-
- if (ret) {
- if (fb)
- drm_framebuffer_remove(fb);
- }
-
+ drm_framebuffer_remove(fb);
return ret;
}
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 9519647..f583bb4 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -132,17 +132,19 @@ static void put_pages(struct drm_gem_object *obj)
struct msm_gem_object *msm_obj = to_msm_bo(obj);
if (msm_obj->pages) {
- /* For non-cached buffers, ensure the new pages are clean
- * because display controller, GPU, etc. are not coherent:
- */
- if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED))
- dma_unmap_sg(obj->dev->dev, msm_obj->sgt->sgl,
- msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+ if (msm_obj->sgt) {
+ /* For non-cached buffers, ensure the new
+ * pages are clean because display controller,
+ * GPU, etc. are not coherent:
+ */
+ if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED))
+ dma_unmap_sg(obj->dev->dev, msm_obj->sgt->sgl,
+ msm_obj->sgt->nents,
+ DMA_BIDIRECTIONAL);
- if (msm_obj->sgt)
sg_free_table(msm_obj->sgt);
-
- kfree(msm_obj->sgt);
+ kfree(msm_obj->sgt);
+ }
if (use_pages(obj))
drm_gem_put_pages(obj, msm_obj->pages, true, false);
diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h
index 17d5824..aaa329d 100644
--- a/drivers/gpu/drm/msm/msm_kms.h
+++ b/drivers/gpu/drm/msm/msm_kms.h
@@ -48,8 +48,11 @@ struct msm_kms_funcs {
/* functions to wait for atomic commit completed on each CRTC */
void (*wait_for_crtc_commit_done)(struct msm_kms *kms,
struct drm_crtc *crtc);
+ /* get msm_format w/ optional format modifiers from drm_mode_fb_cmd2 */
+ const struct msm_format *(*get_format)(struct msm_kms *kms,
+ const uint32_t format,
+ const uint64_t modifiers);
/* misc: */
- const struct msm_format *(*get_format)(struct msm_kms *kms, uint32_t format);
long (*round_pixclk)(struct msm_kms *kms, unsigned long rate,
struct drm_encoder *encoder);
int (*set_split_display)(struct msm_kms *kms,
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 6f402c4..ab61c03 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -214,7 +214,6 @@ nouveau_bo_new(struct nouveau_cli *cli, u64 size, int align,
INIT_LIST_HEAD(&nvbo->entry);
INIT_LIST_HEAD(&nvbo->vma_list);
nvbo->bo.bdev = &drm->ttm.bdev;
- nvbo->cli = cli;
/* This is confusing, and doesn't actually mean we want an uncached
* mapping, but is what NOUVEAU_GEM_DOMAIN_COHERENT gets translated
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.h b/drivers/gpu/drm/nouveau/nouveau_bo.h
index be8e00b..73c4844 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.h
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.h
@@ -26,8 +26,6 @@ struct nouveau_bo {
struct list_head vma_list;
- struct nouveau_cli *cli;
-
unsigned contig:1;
unsigned page:5;
unsigned kind:8;
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index dff51a0..8c093ca 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -63,7 +63,7 @@ nouveau_vram_manager_new(struct ttm_mem_type_manager *man,
struct ttm_mem_reg *reg)
{
struct nouveau_bo *nvbo = nouveau_bo(bo);
- struct nouveau_drm *drm = nvbo->cli->drm;
+ struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
struct nouveau_mem *mem;
int ret;
@@ -103,7 +103,7 @@ nouveau_gart_manager_new(struct ttm_mem_type_manager *man,
struct ttm_mem_reg *reg)
{
struct nouveau_bo *nvbo = nouveau_bo(bo);
- struct nouveau_drm *drm = nvbo->cli->drm;
+ struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
struct nouveau_mem *mem;
int ret;
@@ -131,7 +131,7 @@ nv04_gart_manager_new(struct ttm_mem_type_manager *man,
struct ttm_mem_reg *reg)
{
struct nouveau_bo *nvbo = nouveau_bo(bo);
- struct nouveau_drm *drm = nvbo->cli->drm;
+ struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
struct nouveau_mem *mem;
int ret;
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index 8bd739c..2b3ccd8 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -3264,10 +3264,11 @@ nv50_mstm_destroy_connector(struct drm_dp_mst_topology_mgr *mgr,
drm_connector_unregister(&mstc->connector);
- drm_modeset_lock_all(drm->dev);
drm_fb_helper_remove_one_connector(&drm->fbcon->helper, &mstc->connector);
+
+ drm_modeset_lock(&drm->dev->mode_config.connection_mutex, NULL);
mstc->port = NULL;
- drm_modeset_unlock_all(drm->dev);
+ drm_modeset_unlock(&drm->dev->mode_config.connection_mutex);
drm_connector_unreference(&mstc->connector);
}
@@ -3277,9 +3278,7 @@ nv50_mstm_register_connector(struct drm_connector *connector)
{
struct nouveau_drm *drm = nouveau_drm(connector->dev);
- drm_modeset_lock_all(drm->dev);
drm_fb_helper_add_one_connector(&drm->fbcon->helper, connector);
- drm_modeset_unlock_all(drm->dev);
drm_connector_register(connector);
}
diff --git a/drivers/gpu/drm/omapdrm/dss/dispc.c b/drivers/gpu/drm/omapdrm/dss/dispc.c
index 5e2e65e..7f3ac6b 100644
--- a/drivers/gpu/drm/omapdrm/dss/dispc.c
+++ b/drivers/gpu/drm/omapdrm/dss/dispc.c
@@ -828,6 +828,12 @@ static void dispc_ovl_set_scale_coef(struct dispc_device *dispc,
h_coef = dispc_ovl_get_scale_coef(fir_hinc, true);
v_coef = dispc_ovl_get_scale_coef(fir_vinc, five_taps);
+ if (!h_coef || !v_coef) {
+ dev_err(&dispc->pdev->dev, "%s: failed to find scale coefs\n",
+ __func__);
+ return;
+ }
+
for (i = 0; i < 8; i++) {
u32 h, hv;
@@ -2342,7 +2348,7 @@ static int dispc_ovl_calc_scaling_24xx(struct dispc_device *dispc,
}
if (in_width > maxsinglelinewidth) {
- DSSERR("Cannot scale max input width exceeded");
+ DSSERR("Cannot scale max input width exceeded\n");
return -EINVAL;
}
return 0;
@@ -2424,13 +2430,13 @@ static int dispc_ovl_calc_scaling_34xx(struct dispc_device *dispc,
}
if (in_width > (maxsinglelinewidth * 2)) {
- DSSERR("Cannot setup scaling");
- DSSERR("width exceeds maximum width possible");
+ DSSERR("Cannot setup scaling\n");
+ DSSERR("width exceeds maximum width possible\n");
return -EINVAL;
}
if (in_width > maxsinglelinewidth && *five_taps) {
- DSSERR("cannot setup scaling with five taps");
+ DSSERR("cannot setup scaling with five taps\n");
return -EINVAL;
}
return 0;
@@ -2472,7 +2478,7 @@ static int dispc_ovl_calc_scaling_44xx(struct dispc_device *dispc,
in_width > maxsinglelinewidth && ++*decim_x);
if (in_width > maxsinglelinewidth) {
- DSSERR("Cannot scale width exceeds max line width");
+ DSSERR("Cannot scale width exceeds max line width\n");
return -EINVAL;
}
@@ -2490,7 +2496,7 @@ static int dispc_ovl_calc_scaling_44xx(struct dispc_device *dispc,
* bandwidth. Despite what theory says this appears to
* be true also for 16-bit color formats.
*/
- DSSERR("Not enough bandwidth, too much downscaling (x-decimation factor %d > 4)", *decim_x);
+ DSSERR("Not enough bandwidth, too much downscaling (x-decimation factor %d > 4)\n", *decim_x);
return -EINVAL;
}
@@ -4633,7 +4639,7 @@ static int dispc_errata_i734_wa_init(struct dispc_device *dispc)
i734_buf.size, &i734_buf.paddr,
GFP_KERNEL);
if (!i734_buf.vaddr) {
- dev_err(&dispc->pdev->dev, "%s: dma_alloc_writecombine failed",
+ dev_err(&dispc->pdev->dev, "%s: dma_alloc_writecombine failed\n",
__func__);
return -ENOMEM;
}
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4.c b/drivers/gpu/drm/omapdrm/dss/hdmi4.c
index 97c8886..5879f45 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi4.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi4.c
@@ -679,7 +679,7 @@ static int hdmi_audio_config(struct device *dev,
struct omap_dss_audio *dss_audio)
{
struct omap_hdmi *hd = dev_get_drvdata(dev);
- int ret;
+ int ret = 0;
mutex_lock(&hd->lock);
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c b/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c
index 35ed2ad..813ba42 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c
@@ -922,8 +922,13 @@ int hdmi4_core_init(struct platform_device *pdev, struct hdmi_core_data *core)
{
const struct hdmi4_features *features;
struct resource *res;
+ const struct soc_device_attribute *soc;
- features = soc_device_match(hdmi4_soc_devices)->data;
+ soc = soc_device_match(hdmi4_soc_devices);
+ if (!soc)
+ return -ENODEV;
+
+ features = soc->data;
core->cts_swmode = features->cts_swmode;
core->audio_use_mclk = features->audio_use_mclk;
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi5.c b/drivers/gpu/drm/omapdrm/dss/hdmi5.c
index d28da9a..ae1a001 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi5.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi5.c
@@ -671,7 +671,7 @@ static int hdmi_audio_config(struct device *dev,
struct omap_dss_audio *dss_audio)
{
struct omap_hdmi *hd = dev_get_drvdata(dev);
- int ret;
+ int ret = 0;
mutex_lock(&hd->lock);
diff --git a/drivers/gpu/drm/omapdrm/dss/sdi.c b/drivers/gpu/drm/omapdrm/dss/sdi.c
index 68a40ae..1e2c931 100644
--- a/drivers/gpu/drm/omapdrm/dss/sdi.c
+++ b/drivers/gpu/drm/omapdrm/dss/sdi.c
@@ -82,7 +82,7 @@ static int sdi_calc_clock_div(struct sdi_device *sdi, unsigned long pclk,
struct dispc_clock_info *dispc_cinfo)
{
int i;
- struct sdi_clk_calc_ctx ctx = { .sdi = sdi };
+ struct sdi_clk_calc_ctx ctx;
/*
* DSS fclk gives us very few possibilities, so finding a good pixel
@@ -95,6 +95,9 @@ static int sdi_calc_clock_div(struct sdi_device *sdi, unsigned long pclk,
bool ok;
memset(&ctx, 0, sizeof(ctx));
+
+ ctx.sdi = sdi;
+
if (pclk > 1000 * i * i * i)
ctx.pck_min = max(pclk - 1000 * i * i * i, 0lu);
else
diff --git a/drivers/gpu/drm/omapdrm/omap_connector.c b/drivers/gpu/drm/omapdrm/omap_connector.c
index a0d7b1d..5cde26a 100644
--- a/drivers/gpu/drm/omapdrm/omap_connector.c
+++ b/drivers/gpu/drm/omapdrm/omap_connector.c
@@ -121,6 +121,9 @@ static int omap_connector_get_modes(struct drm_connector *connector)
if (dssdrv->read_edid) {
void *edid = kzalloc(MAX_EDID, GFP_KERNEL);
+ if (!edid)
+ return 0;
+
if ((dssdrv->read_edid(dssdev, edid, MAX_EDID) > 0) &&
drm_edid_is_valid(edid)) {
drm_mode_connector_update_edid_property(
@@ -139,6 +142,9 @@ static int omap_connector_get_modes(struct drm_connector *connector)
struct drm_display_mode *mode = drm_mode_create(dev);
struct videomode vm = {0};
+ if (!mode)
+ return 0;
+
dssdrv->get_timings(dssdev, &vm);
drm_display_mode_from_videomode(&vm, mode);
@@ -200,6 +206,10 @@ static int omap_connector_mode_valid(struct drm_connector *connector,
if (!r) {
/* check if vrefresh is still valid */
new_mode = drm_mode_duplicate(dev, mode);
+
+ if (!new_mode)
+ return MODE_BAD;
+
new_mode->clock = vm.pixelclock / 1000;
new_mode->vrefresh = 0;
if (mode->vrefresh == drm_mode_vrefresh(new_mode))
diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
index f9fa1c9..401c02e 100644
--- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
+++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
@@ -401,12 +401,16 @@ int tiler_unpin(struct tiler_block *block)
struct tiler_block *tiler_reserve_2d(enum tiler_fmt fmt, u16 w,
u16 h, u16 align)
{
- struct tiler_block *block = kzalloc(sizeof(*block), GFP_KERNEL);
+ struct tiler_block *block;
u32 min_align = 128;
int ret;
unsigned long flags;
u32 slot_bytes;
+ block = kzalloc(sizeof(*block), GFP_KERNEL);
+ if (!block)
+ return ERR_PTR(-ENOMEM);
+
BUG_ON(!validfmt(fmt));
/* convert width/height to slots */
diff --git a/drivers/gpu/drm/omapdrm/tcm-sita.c b/drivers/gpu/drm/omapdrm/tcm-sita.c
index d7f7bc9..817be3c 100644
--- a/drivers/gpu/drm/omapdrm/tcm-sita.c
+++ b/drivers/gpu/drm/omapdrm/tcm-sita.c
@@ -90,7 +90,7 @@ static int l2r_t2b(u16 w, u16 h, u16 a, s16 offset,
{
int i;
unsigned long index;
- bool area_free;
+ bool area_free = false;
unsigned long slots_per_band = PAGE_SIZE / slot_bytes;
unsigned long bit_offset = (offset > 0) ? offset / slot_bytes : 0;
unsigned long curr_bit = bit_offset;
diff --git a/drivers/gpu/drm/qxl/qxl_cmd.c b/drivers/gpu/drm/qxl/qxl_cmd.c
index c0fb52c..01665b9 100644
--- a/drivers/gpu/drm/qxl/qxl_cmd.c
+++ b/drivers/gpu/drm/qxl/qxl_cmd.c
@@ -179,10 +179,9 @@ qxl_push_command_ring_release(struct qxl_device *qdev, struct qxl_release *relea
uint32_t type, bool interruptible)
{
struct qxl_command cmd;
- struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head);
cmd.type = type;
- cmd.data = qxl_bo_physical_address(qdev, to_qxl_bo(entry->tv.bo), release->release_offset);
+ cmd.data = qxl_bo_physical_address(qdev, release->release_bo, release->release_offset);
return qxl_ring_push(qdev->command_ring, &cmd, interruptible);
}
@@ -192,10 +191,9 @@ qxl_push_cursor_ring_release(struct qxl_device *qdev, struct qxl_release *releas
uint32_t type, bool interruptible)
{
struct qxl_command cmd;
- struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head);
cmd.type = type;
- cmd.data = qxl_bo_physical_address(qdev, to_qxl_bo(entry->tv.bo), release->release_offset);
+ cmd.data = qxl_bo_physical_address(qdev, release->release_bo, release->release_offset);
return qxl_ring_push(qdev->cursor_ring, &cmd, interruptible);
}
diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h
index 00a1a66..864b456 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.h
+++ b/drivers/gpu/drm/qxl/qxl_drv.h
@@ -167,6 +167,7 @@ struct qxl_release {
int id;
int type;
+ struct qxl_bo *release_bo;
uint32_t release_offset;
uint32_t surface_release_id;
struct ww_acquire_ctx ticket;
diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c
index e238a1a..6cc9f33 100644
--- a/drivers/gpu/drm/qxl/qxl_ioctl.c
+++ b/drivers/gpu/drm/qxl/qxl_ioctl.c
@@ -182,9 +182,9 @@ static int qxl_process_single_command(struct qxl_device *qdev,
goto out_free_reloc;
/* TODO copy slow path code from i915 */
- fb_cmd = qxl_bo_kmap_atomic_page(qdev, cmd_bo, (release->release_offset & PAGE_SIZE));
+ fb_cmd = qxl_bo_kmap_atomic_page(qdev, cmd_bo, (release->release_offset & PAGE_MASK));
unwritten = __copy_from_user_inatomic_nocache
- (fb_cmd + sizeof(union qxl_release_info) + (release->release_offset & ~PAGE_SIZE),
+ (fb_cmd + sizeof(union qxl_release_info) + (release->release_offset & ~PAGE_MASK),
u64_to_user_ptr(cmd->command), cmd->command_size);
{
diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index 5d84a66..7cb2145 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -173,6 +173,7 @@ qxl_release_free_list(struct qxl_release *release)
list_del(&entry->tv.head);
kfree(entry);
}
+ release->release_bo = NULL;
}
void
@@ -296,7 +297,6 @@ int qxl_alloc_surface_release_reserved(struct qxl_device *qdev,
{
if (surface_cmd_type == QXL_SURFACE_CMD_DESTROY && create_rel) {
int idr_ret;
- struct qxl_bo_list *entry = list_first_entry(&create_rel->bos, struct qxl_bo_list, tv.head);
struct qxl_bo *bo;
union qxl_release_info *info;
@@ -304,8 +304,9 @@ int qxl_alloc_surface_release_reserved(struct qxl_device *qdev,
idr_ret = qxl_release_alloc(qdev, QXL_RELEASE_SURFACE_CMD, release);
if (idr_ret < 0)
return idr_ret;
- bo = to_qxl_bo(entry->tv.bo);
+ bo = create_rel->release_bo;
+ (*release)->release_bo = bo;
(*release)->release_offset = create_rel->release_offset + 64;
qxl_release_list_add(*release, bo);
@@ -365,6 +366,7 @@ int qxl_alloc_release_reserved(struct qxl_device *qdev, unsigned long size,
bo = qxl_bo_ref(qdev->current_release_bo[cur_idx]);
+ (*release)->release_bo = bo;
(*release)->release_offset = qdev->current_release_bo_offset[cur_idx] * release_size_per_bo[cur_idx];
qdev->current_release_bo_offset[cur_idx]++;
@@ -408,13 +410,12 @@ union qxl_release_info *qxl_release_map(struct qxl_device *qdev,
{
void *ptr;
union qxl_release_info *info;
- struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head);
- struct qxl_bo *bo = to_qxl_bo(entry->tv.bo);
+ struct qxl_bo *bo = release->release_bo;
- ptr = qxl_bo_kmap_atomic_page(qdev, bo, release->release_offset & PAGE_SIZE);
+ ptr = qxl_bo_kmap_atomic_page(qdev, bo, release->release_offset & PAGE_MASK);
if (!ptr)
return NULL;
- info = ptr + (release->release_offset & ~PAGE_SIZE);
+ info = ptr + (release->release_offset & ~PAGE_MASK);
return info;
}
@@ -422,11 +423,10 @@ void qxl_release_unmap(struct qxl_device *qdev,
struct qxl_release *release,
union qxl_release_info *info)
{
- struct qxl_bo_list *entry = list_first_entry(&release->bos, struct qxl_bo_list, tv.head);
- struct qxl_bo *bo = to_qxl_bo(entry->tv.bo);
+ struct qxl_bo *bo = release->release_bo;
void *ptr;
- ptr = ((void *)info) - (release->release_offset & ~PAGE_SIZE);
+ ptr = ((void *)info) - (release->release_offset & ~PAGE_MASK);
qxl_bo_kunmap_atomic_page(qdev, bo, ptr);
}
diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c
index 3d2d3bb..155ad84 100644
--- a/drivers/gpu/drm/rcar-du/rcar_lvds.c
+++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c
@@ -88,6 +88,9 @@ static int rcar_lvds_connector_atomic_check(struct drm_connector *connector,
const struct drm_display_mode *panel_mode;
struct drm_crtc_state *crtc_state;
+ if (!state->crtc)
+ return 0;
+
if (list_empty(&connector->modes)) {
dev_dbg(lvds->dev, "connector: empty modes list\n");
return -EINVAL;
diff --git a/drivers/gpu/drm/sun4i/sun4i_lvds.c b/drivers/gpu/drm/sun4i/sun4i_lvds.c
index bffff4c..be3f14d 100644
--- a/drivers/gpu/drm/sun4i/sun4i_lvds.c
+++ b/drivers/gpu/drm/sun4i/sun4i_lvds.c
@@ -94,64 +94,9 @@ static void sun4i_lvds_encoder_disable(struct drm_encoder *encoder)
}
}
-static enum drm_mode_status sun4i_lvds_encoder_mode_valid(struct drm_encoder *crtc,
- const struct drm_display_mode *mode)
-{
- struct sun4i_lvds *lvds = drm_encoder_to_sun4i_lvds(crtc);
- struct sun4i_tcon *tcon = lvds->tcon;
- u32 hsync = mode->hsync_end - mode->hsync_start;
- u32 vsync = mode->vsync_end - mode->vsync_start;
- unsigned long rate = mode->clock * 1000;
- long rounded_rate;
-
- DRM_DEBUG_DRIVER("Validating modes...\n");
-
- if (hsync < 1)
- return MODE_HSYNC_NARROW;
-
- if (hsync > 0x3ff)
- return MODE_HSYNC_WIDE;
-
- if ((mode->hdisplay < 1) || (mode->htotal < 1))
- return MODE_H_ILLEGAL;
-
- if ((mode->hdisplay > 0x7ff) || (mode->htotal > 0xfff))
- return MODE_BAD_HVALUE;
-
- DRM_DEBUG_DRIVER("Horizontal parameters OK\n");
-
- if (vsync < 1)
- return MODE_VSYNC_NARROW;
-
- if (vsync > 0x3ff)
- return MODE_VSYNC_WIDE;
-
- if ((mode->vdisplay < 1) || (mode->vtotal < 1))
- return MODE_V_ILLEGAL;
-
- if ((mode->vdisplay > 0x7ff) || (mode->vtotal > 0xfff))
- return MODE_BAD_VVALUE;
-
- DRM_DEBUG_DRIVER("Vertical parameters OK\n");
-
- tcon->dclk_min_div = 7;
- tcon->dclk_max_div = 7;
- rounded_rate = clk_round_rate(tcon->dclk, rate);
- if (rounded_rate < rate)
- return MODE_CLOCK_LOW;
-
- if (rounded_rate > rate)
- return MODE_CLOCK_HIGH;
-
- DRM_DEBUG_DRIVER("Clock rate OK\n");
-
- return MODE_OK;
-}
-
static const struct drm_encoder_helper_funcs sun4i_lvds_enc_helper_funcs = {
.disable = sun4i_lvds_encoder_disable,
.enable = sun4i_lvds_encoder_enable,
- .mode_valid = sun4i_lvds_encoder_mode_valid,
};
static const struct drm_encoder_funcs sun4i_lvds_enc_funcs = {
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index f0481b7..06c94e3 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -910,7 +910,8 @@ static int ttm_get_pages(struct page **pages, unsigned npages, int flags,
while (npages >= HPAGE_PMD_NR) {
gfp_t huge_flags = gfp_flags;
- huge_flags |= GFP_TRANSHUGE;
+ huge_flags |= GFP_TRANSHUGE_LIGHT | __GFP_NORETRY |
+ __GFP_KSWAPD_RECLAIM;
huge_flags &= ~__GFP_MOVABLE;
huge_flags &= ~__GFP_COMP;
p = alloc_pages(huge_flags, HPAGE_PMD_ORDER);
@@ -1027,11 +1028,15 @@ int ttm_page_alloc_init(struct ttm_mem_global *glob, unsigned max_pages)
GFP_USER | GFP_DMA32, "uc dma", 0);
ttm_page_pool_init_locked(&_manager->wc_pool_huge,
- GFP_TRANSHUGE & ~(__GFP_MOVABLE | __GFP_COMP),
+ (GFP_TRANSHUGE_LIGHT | __GFP_NORETRY |
+ __GFP_KSWAPD_RECLAIM) &
+ ~(__GFP_MOVABLE | __GFP_COMP),
"wc huge", order);
ttm_page_pool_init_locked(&_manager->uc_pool_huge,
- GFP_TRANSHUGE & ~(__GFP_MOVABLE | __GFP_COMP)
+ (GFP_TRANSHUGE_LIGHT | __GFP_NORETRY |
+ __GFP_KSWAPD_RECLAIM) &
+ ~(__GFP_MOVABLE | __GFP_COMP)
, "uc huge", order);
_manager->options.max_size = max_pages;
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index 8a25d19..f63d99c 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -910,7 +910,8 @@ static gfp_t ttm_dma_pool_gfp_flags(struct ttm_dma_tt *ttm_dma, bool huge)
gfp_flags |= __GFP_ZERO;
if (huge) {
- gfp_flags |= GFP_TRANSHUGE;
+ gfp_flags |= GFP_TRANSHUGE_LIGHT | __GFP_NORETRY |
+ __GFP_KSWAPD_RECLAIM;
gfp_flags &= ~__GFP_MOVABLE;
gfp_flags &= ~__GFP_COMP;
}
diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index 2decc8e..add9cc9 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -195,6 +195,7 @@ static void vc4_bo_destroy(struct vc4_bo *bo)
vc4_bo_set_label(obj, -1);
if (bo->validated_shader) {
+ kfree(bo->validated_shader->uniform_addr_offsets);
kfree(bo->validated_shader->texture_samples);
kfree(bo->validated_shader);
bo->validated_shader = NULL;
@@ -591,6 +592,7 @@ void vc4_free_object(struct drm_gem_object *gem_bo)
}
if (bo->validated_shader) {
+ kfree(bo->validated_shader->uniform_addr_offsets);
kfree(bo->validated_shader->texture_samples);
kfree(bo->validated_shader);
bo->validated_shader = NULL;
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index bf466748..c61dff5 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -760,6 +760,7 @@ static irqreturn_t vc4_crtc_irq_handler(int irq, void *data)
struct vc4_async_flip_state {
struct drm_crtc *crtc;
struct drm_framebuffer *fb;
+ struct drm_framebuffer *old_fb;
struct drm_pending_vblank_event *event;
struct vc4_seqno_cb cb;
@@ -789,6 +790,23 @@ vc4_async_page_flip_complete(struct vc4_seqno_cb *cb)
drm_crtc_vblank_put(crtc);
drm_framebuffer_put(flip_state->fb);
+
+ /* Decrement the BO usecnt in order to keep the inc/dec calls balanced
+ * when the planes are updated through the async update path.
+ * FIXME: we should move to generic async-page-flip when it's
+ * available, so that we can get rid of this hand-made cleanup_fb()
+ * logic.
+ */
+ if (flip_state->old_fb) {
+ struct drm_gem_cma_object *cma_bo;
+ struct vc4_bo *bo;
+
+ cma_bo = drm_fb_cma_get_gem_obj(flip_state->old_fb, 0);
+ bo = to_vc4_bo(&cma_bo->base);
+ vc4_bo_dec_usecnt(bo);
+ drm_framebuffer_put(flip_state->old_fb);
+ }
+
kfree(flip_state);
up(&vc4->async_modeset);
@@ -813,9 +831,22 @@ static int vc4_async_page_flip(struct drm_crtc *crtc,
struct drm_gem_cma_object *cma_bo = drm_fb_cma_get_gem_obj(fb, 0);
struct vc4_bo *bo = to_vc4_bo(&cma_bo->base);
+ /* Increment the BO usecnt here, so that we never end up with an
+ * unbalanced number of vc4_bo_{dec,inc}_usecnt() calls when the
+ * plane is later updated through the non-async path.
+ * FIXME: we should move to generic async-page-flip when it's
+ * available, so that we can get rid of this hand-made prepare_fb()
+ * logic.
+ */
+ ret = vc4_bo_inc_usecnt(bo);
+ if (ret)
+ return ret;
+
flip_state = kzalloc(sizeof(*flip_state), GFP_KERNEL);
- if (!flip_state)
+ if (!flip_state) {
+ vc4_bo_dec_usecnt(bo);
return -ENOMEM;
+ }
drm_framebuffer_get(fb);
flip_state->fb = fb;
@@ -826,10 +857,23 @@ static int vc4_async_page_flip(struct drm_crtc *crtc,
ret = down_interruptible(&vc4->async_modeset);
if (ret) {
drm_framebuffer_put(fb);
+ vc4_bo_dec_usecnt(bo);
kfree(flip_state);
return ret;
}
+ /* Save the current FB before it's replaced by the new one in
+ * drm_atomic_set_fb_for_plane(). We'll need the old FB in
+ * vc4_async_page_flip_complete() to decrement the BO usecnt and keep
+ * it consistent.
+ * FIXME: we should move to generic async-page-flip when it's
+ * available, so that we can get rid of this hand-made cleanup_fb()
+ * logic.
+ */
+ flip_state->old_fb = plane->state->fb;
+ if (flip_state->old_fb)
+ drm_framebuffer_get(flip_state->old_fb);
+
WARN_ON(drm_crtc_vblank_get(crtc) != 0);
/* Immediately update the plane's legacy fb pointer, so that later
diff --git a/drivers/gpu/drm/vc4/vc4_dpi.c b/drivers/gpu/drm/vc4/vc4_dpi.c
index 72c9dbd..f185812 100644
--- a/drivers/gpu/drm/vc4/vc4_dpi.c
+++ b/drivers/gpu/drm/vc4/vc4_dpi.c
@@ -96,7 +96,6 @@ struct vc4_dpi {
struct platform_device *pdev;
struct drm_encoder *encoder;
- struct drm_connector *connector;
void __iomem *regs;
@@ -164,14 +163,31 @@ static void vc4_dpi_encoder_disable(struct drm_encoder *encoder)
static void vc4_dpi_encoder_enable(struct drm_encoder *encoder)
{
+ struct drm_device *dev = encoder->dev;
struct drm_display_mode *mode = &encoder->crtc->mode;
struct vc4_dpi_encoder *vc4_encoder = to_vc4_dpi_encoder(encoder);
struct vc4_dpi *dpi = vc4_encoder->dpi;
+ struct drm_connector_list_iter conn_iter;
+ struct drm_connector *connector = NULL, *connector_scan;
u32 dpi_c = DPI_ENABLE | DPI_OUTPUT_ENABLE_MODE;
int ret;
- if (dpi->connector->display_info.num_bus_formats) {
- u32 bus_format = dpi->connector->display_info.bus_formats[0];
+ /* Look up the connector attached to DPI so we can get the
+ * bus_format. Ideally the bridge would tell us the
+ * bus_format we want, but it doesn't yet, so assume that it's
+ * uniform throughout the bridge chain.
+ */
+ drm_connector_list_iter_begin(dev, &conn_iter);
+ drm_for_each_connector_iter(connector_scan, &conn_iter) {
+ if (connector_scan->encoder == encoder) {
+ connector = connector_scan;
+ break;
+ }
+ }
+ drm_connector_list_iter_end(&conn_iter);
+
+ if (connector && connector->display_info.num_bus_formats) {
+ u32 bus_format = connector->display_info.bus_formats[0];
switch (bus_format) {
case MEDIA_BUS_FMT_RGB888_1X24:
@@ -199,6 +215,9 @@ static void vc4_dpi_encoder_enable(struct drm_encoder *encoder)
DRM_ERROR("Unknown media bus format %d\n", bus_format);
break;
}
+ } else {
+ /* Default to 24bit if no connector found. */
+ dpi_c |= VC4_SET_FIELD(DPI_FORMAT_24BIT_888_RGB, DPI_FORMAT);
}
if (mode->flags & DRM_MODE_FLAG_NHSYNC)
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 94b99c9..7c95ed5 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -130,6 +130,7 @@ static void vc4_close(struct drm_device *dev, struct drm_file *file)
struct vc4_file *vc4file = file->driver_priv;
vc4_perfmon_close_file(vc4file);
+ kfree(vc4file);
}
static const struct vm_operations_struct vc4_vm_ops = {
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index ce39390..13dcaad 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -503,7 +503,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
* the scl fields here.
*/
if (num_planes == 1) {
- scl0 = vc4_get_scl_field(state, 1);
+ scl0 = vc4_get_scl_field(state, 0);
scl1 = scl0;
} else {
scl0 = vc4_get_scl_field(state, 1);
diff --git a/drivers/gpu/drm/vc4/vc4_validate_shaders.c b/drivers/gpu/drm/vc4/vc4_validate_shaders.c
index d3f15bf..7cf82b0 100644
--- a/drivers/gpu/drm/vc4/vc4_validate_shaders.c
+++ b/drivers/gpu/drm/vc4/vc4_validate_shaders.c
@@ -942,6 +942,7 @@ vc4_validate_shader(struct drm_gem_cma_object *shader_obj)
fail:
kfree(validation_state.branch_targets);
if (validated_shader) {
+ kfree(validated_shader->uniform_addr_offsets);
kfree(validated_shader->texture_samples);
kfree(validated_shader);
}
diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c
index 48e4f1d..020070d 100644
--- a/drivers/gpu/drm/virtio/virtgpu_vq.c
+++ b/drivers/gpu/drm/virtio/virtgpu_vq.c
@@ -293,7 +293,7 @@ static int virtio_gpu_queue_ctrl_buffer_locked(struct virtio_gpu_device *vgdev,
ret = virtqueue_add_sgs(vq, sgs, outcnt, incnt, vbuf, GFP_ATOMIC);
if (ret == -ENOSPC) {
spin_unlock(&vgdev->ctrlq.qlock);
- wait_event(vgdev->ctrlq.ack_queue, vq->num_free);
+ wait_event(vgdev->ctrlq.ack_queue, vq->num_free >= outcnt + incnt);
spin_lock(&vgdev->ctrlq.qlock);
goto retry;
} else {
@@ -368,7 +368,7 @@ static int virtio_gpu_queue_cursor(struct virtio_gpu_device *vgdev,
ret = virtqueue_add_sgs(vq, sgs, outcnt, 0, vbuf, GFP_ATOMIC);
if (ret == -ENOSPC) {
spin_unlock(&vgdev->cursorq.qlock);
- wait_event(vgdev->cursorq.ack_queue, vq->num_free);
+ wait_event(vgdev->cursorq.ack_queue, vq->num_free >= outcnt);
spin_lock(&vgdev->cursorq.qlock);
goto retry;
} else {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 70e1a88..8b770a8 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -1278,8 +1278,6 @@ static void vmw_master_drop(struct drm_device *dev,
dev_priv->active_master = &dev_priv->fbdev_master;
ttm_lock_set_kill(&dev_priv->fbdev_master.lock, false, SIGTERM);
ttm_vt_unlock(&dev_priv->fbdev_master.lock);
-
- vmw_fb_refresh(dev_priv);
}
/**
@@ -1483,7 +1481,6 @@ static int vmw_pm_freeze(struct device *kdev)
vmw_kms_resume(dev);
if (dev_priv->enable_fb)
vmw_fb_on(dev_priv);
- vmw_fb_refresh(dev_priv);
return -EBUSY;
}
@@ -1523,8 +1520,6 @@ static int vmw_pm_restore(struct device *kdev)
if (dev_priv->enable_fb)
vmw_fb_on(dev_priv);
- vmw_fb_refresh(dev_priv);
-
return 0;
}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index f34f368..5fcbe16 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -910,7 +910,6 @@ int vmw_fb_init(struct vmw_private *vmw_priv);
int vmw_fb_close(struct vmw_private *dev_priv);
int vmw_fb_off(struct vmw_private *vmw_priv);
int vmw_fb_on(struct vmw_private *vmw_priv);
-void vmw_fb_refresh(struct vmw_private *vmw_priv);
/**
* Kernel modesetting - vmwgfx_kms.c
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index 2582ffd..54e30036 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -441,11 +441,11 @@ static int vmwgfx_set_config_internal(struct drm_mode_set *set)
struct drm_crtc *crtc = set->crtc;
struct drm_framebuffer *fb;
struct drm_crtc *tmp;
- struct drm_modeset_acquire_ctx *ctx;
struct drm_device *dev = set->crtc->dev;
+ struct drm_modeset_acquire_ctx ctx;
int ret;
- ctx = dev->mode_config.acquire_ctx;
+ drm_modeset_acquire_init(&ctx, 0);
restart:
/*
@@ -458,7 +458,7 @@ static int vmwgfx_set_config_internal(struct drm_mode_set *set)
fb = set->fb;
- ret = crtc->funcs->set_config(set, ctx);
+ ret = crtc->funcs->set_config(set, &ctx);
if (ret == 0) {
crtc->primary->crtc = crtc;
crtc->primary->fb = fb;
@@ -473,20 +473,13 @@ static int vmwgfx_set_config_internal(struct drm_mode_set *set)
}
if (ret == -EDEADLK) {
- dev->mode_config.acquire_ctx = NULL;
-
-retry_locking:
- drm_modeset_backoff(ctx);
-
- ret = drm_modeset_lock_all_ctx(dev, ctx);
- if (ret)
- goto retry_locking;
-
- dev->mode_config.acquire_ctx = ctx;
-
+ drm_modeset_backoff(&ctx);
goto restart;
}
+ drm_modeset_drop_locks(&ctx);
+ drm_modeset_acquire_fini(&ctx);
+
return ret;
}
@@ -624,7 +617,6 @@ static int vmw_fb_set_par(struct fb_info *info)
}
mutex_lock(&par->bo_mutex);
- drm_modeset_lock_all(vmw_priv->dev);
ret = vmw_fb_kms_framebuffer(info);
if (ret)
goto out_unlock;
@@ -657,7 +649,6 @@ static int vmw_fb_set_par(struct fb_info *info)
drm_mode_destroy(vmw_priv->dev, old_mode);
par->set_mode = mode;
- drm_modeset_unlock_all(vmw_priv->dev);
mutex_unlock(&par->bo_mutex);
return ret;
@@ -713,18 +704,14 @@ int vmw_fb_init(struct vmw_private *vmw_priv)
par->max_width = fb_width;
par->max_height = fb_height;
- drm_modeset_lock_all(vmw_priv->dev);
ret = vmw_kms_fbdev_init_data(vmw_priv, 0, par->max_width,
par->max_height, &par->con,
&par->crtc, &init_mode);
- if (ret) {
- drm_modeset_unlock_all(vmw_priv->dev);
+ if (ret)
goto err_kms;
- }
info->var.xres = init_mode->hdisplay;
info->var.yres = init_mode->vdisplay;
- drm_modeset_unlock_all(vmw_priv->dev);
/*
* Create buffers and alloc memory
@@ -832,7 +819,9 @@ int vmw_fb_close(struct vmw_private *vmw_priv)
cancel_delayed_work_sync(&par->local_work);
unregister_framebuffer(info);
+ mutex_lock(&par->bo_mutex);
(void) vmw_fb_kms_detach(par, true, true);
+ mutex_unlock(&par->bo_mutex);
vfree(par->vmalloc);
framebuffer_release(info);
@@ -877,21 +866,13 @@ int vmw_fb_on(struct vmw_private *vmw_priv)
spin_lock_irqsave(&par->dirty.lock, flags);
par->dirty.active = true;
spin_unlock_irqrestore(&par->dirty.lock, flags);
-
+
+ /*
+ * Need to reschedule a dirty update, because otherwise that's
+ * only done in dirty_mark() if the previous coalesced
+ * dirty region was empty.
+ */
+ schedule_delayed_work(&par->local_work, 0);
+
return 0;
}
-
-/**
- * vmw_fb_refresh - Refresh fb display
- *
- * @vmw_priv: Pointer to device private
- *
- * Call into kms to show the fbdev display(s).
- */
-void vmw_fb_refresh(struct vmw_private *vmw_priv)
-{
- if (!vmw_priv->fb_info)
- return;
-
- vmw_fb_set_par(vmw_priv->fb_info);
-}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index f11601b..96fd7a0 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -2595,6 +2595,7 @@ void vmw_kms_helper_resource_finish(struct vmw_validation_ctx *ctx,
vmw_kms_helper_buffer_finish(res->dev_priv, NULL, ctx->buf,
out_fence, NULL);
+ vmw_dmabuf_unreference(&ctx->buf);
vmw_resource_unreserve(res, false, NULL, 0);
mutex_unlock(&res->dev_priv->cmdbuf_mutex);
}
@@ -2680,7 +2681,9 @@ int vmw_kms_fbdev_init_data(struct vmw_private *dev_priv,
struct vmw_display_unit *du;
struct drm_display_mode *mode;
int i = 0;
+ int ret = 0;
+ mutex_lock(&dev_priv->dev->mode_config.mutex);
list_for_each_entry(con, &dev_priv->dev->mode_config.connector_list,
head) {
if (i == unit)
@@ -2691,7 +2694,8 @@ int vmw_kms_fbdev_init_data(struct vmw_private *dev_priv,
if (i != unit) {
DRM_ERROR("Could not find initial display unit.\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out_unlock;
}
if (list_empty(&con->modes))
@@ -2699,7 +2703,8 @@ int vmw_kms_fbdev_init_data(struct vmw_private *dev_priv,
if (list_empty(&con->modes)) {
DRM_ERROR("Could not find initial display mode.\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out_unlock;
}
du = vmw_connector_to_du(con);
@@ -2720,7 +2725,10 @@ int vmw_kms_fbdev_init_data(struct vmw_private *dev_priv,
head);
}
- return 0;
+ out_unlock:
+ mutex_unlock(&dev_priv->dev->mode_config.mutex);
+
+ return ret;
}
/**
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index cdff992..21d746b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -329,8 +329,6 @@ int vmw_host_get_guestinfo(const char *guest_info_param,
struct rpc_channel channel;
char *msg, *reply = NULL;
size_t reply_len = 0;
- int ret = 0;
-
if (!vmw_msg_enabled)
return -ENODEV;
@@ -344,15 +342,14 @@ int vmw_host_get_guestinfo(const char *guest_info_param,
return -ENOMEM;
}
- if (vmw_open_channel(&channel, RPCI_PROTOCOL_NUM) ||
- vmw_send_msg(&channel, msg) ||
- vmw_recv_msg(&channel, (void *) &reply, &reply_len) ||
- vmw_close_channel(&channel)) {
- DRM_ERROR("Failed to get %s", guest_info_param);
+ if (vmw_open_channel(&channel, RPCI_PROTOCOL_NUM))
+ goto out_open;
- ret = -EINVAL;
- }
+ if (vmw_send_msg(&channel, msg) ||
+ vmw_recv_msg(&channel, (void *) &reply, &reply_len))
+ goto out_msg;
+ vmw_close_channel(&channel);
if (buffer && reply && reply_len > 0) {
/* Remove reply code, which are the first 2 characters of
* the reply
@@ -369,7 +366,17 @@ int vmw_host_get_guestinfo(const char *guest_info_param,
kfree(reply);
kfree(msg);
- return ret;
+ return 0;
+
+out_msg:
+ vmw_close_channel(&channel);
+ kfree(reply);
+out_open:
+ *length = 0;
+ kfree(msg);
+ DRM_ERROR("Failed to get %s", guest_info_param);
+
+ return -EINVAL;
}
@@ -400,15 +407,22 @@ int vmw_host_log(const char *log)
return -ENOMEM;
}
- if (vmw_open_channel(&channel, RPCI_PROTOCOL_NUM) ||
- vmw_send_msg(&channel, msg) ||
- vmw_close_channel(&channel)) {
- DRM_ERROR("Failed to send log\n");
+ if (vmw_open_channel(&channel, RPCI_PROTOCOL_NUM))
+ goto out_open;
- ret = -EINVAL;
- }
+ if (vmw_send_msg(&channel, msg))
+ goto out_msg;
+ vmw_close_channel(&channel);
kfree(msg);
- return ret;
+ return 0;
+
+out_msg:
+ vmw_close_channel(&channel);
+out_open:
+ kfree(msg);
+ DRM_ERROR("Failed to send log\n");
+
+ return -EINVAL;
}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h
index 557a033..8545488 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h
@@ -135,17 +135,24 @@
#else
-/* In the 32-bit version of this macro, we use "m" because there is no
- * more register left for bp
+/*
+ * In the 32-bit version of this macro, we store bp in a memory location
+ * because we've ran out of registers.
+ * Now we can't reference that memory location while we've modified
+ * %esp or %ebp, so we first push it on the stack, just before we push
+ * %ebp, and then when we need it we read it from the stack where we
+ * just pushed it.
*/
#define VMW_PORT_HB_OUT(cmd, in_ecx, in_si, in_di, \
port_num, magic, bp, \
eax, ebx, ecx, edx, si, di) \
({ \
- asm volatile ("push %%ebp;" \
- "mov %12, %%ebp;" \
+ asm volatile ("push %12;" \
+ "push %%ebp;" \
+ "mov 0x04(%%esp), %%ebp;" \
"rep outsb;" \
- "pop %%ebp;" : \
+ "pop %%ebp;" \
+ "add $0x04, %%esp;" : \
"=a"(eax), \
"=b"(ebx), \
"=c"(ecx), \
@@ -167,10 +174,12 @@
port_num, magic, bp, \
eax, ebx, ecx, edx, si, di) \
({ \
- asm volatile ("push %%ebp;" \
- "mov %12, %%ebp;" \
+ asm volatile ("push %12;" \
+ "push %%ebp;" \
+ "mov 0x04(%%esp), %%ebp;" \
"rep insb;" \
- "pop %%ebp" : \
+ "pop %%ebp;" \
+ "add $0x04, %%esp;" : \
"=a"(eax), \
"=b"(ebx), \
"=c"(ecx), \
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
index 648f812..3d667e9 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
@@ -482,6 +482,8 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
return ret;
}
+ vps->dmabuf_size = size;
+
/*
* TTM already thinks the buffer is pinned, but make sure the
* pin_count is upped.
diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
index 88a3558..815bdb4 100644
--- a/drivers/gpu/host1x/bus.c
+++ b/drivers/gpu/host1x/bus.c
@@ -314,6 +314,11 @@ static int host1x_device_match(struct device *dev, struct device_driver *drv)
return strcmp(dev_name(dev), drv->name) == 0;
}
+static int host1x_dma_configure(struct device *dev)
+{
+ return of_dma_configure(dev, dev->of_node, true);
+}
+
static const struct dev_pm_ops host1x_device_pm_ops = {
.suspend = pm_generic_suspend,
.resume = pm_generic_resume,
@@ -326,8 +331,8 @@ static const struct dev_pm_ops host1x_device_pm_ops = {
struct bus_type host1x_bus_type = {
.name = "host1x",
.match = host1x_device_match,
+ .dma_configure = host1x_dma_configure,
.pm = &host1x_device_pm_ops,
- .force_dma = true,
};
static void __host1x_device_del(struct host1x_device *device)
@@ -416,7 +421,7 @@ static int host1x_device_add(struct host1x *host1x,
device->dev.bus = &host1x_bus_type;
device->dev.parent = host1x->dev;
- of_dma_configure(&device->dev, host1x->dev->of_node);
+ of_dma_configure(&device->dev, host1x->dev->of_node, true);
err = host1x_device_parse_dt(device, driver);
if (err < 0) {
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 60252fd..0000434 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -462,10 +462,11 @@
select NEW_LEDS
select LEDS_CLASS
---help---
- Support for Lenovo devices that are not fully compliant with HID standard.
+ Support for IBM/Lenovo devices that are not fully compliant with HID standard.
- Say Y if you want support for the non-compliant features of the Lenovo
- Thinkpad standalone keyboards, e.g:
+ Say Y if you want support for horizontal scrolling of the IBM/Lenovo
+ Scrollpoint mice or the non-compliant features of the Lenovo Thinkpad
+ standalone keyboards, e.g:
- ThinkPad USB Keyboard with TrackPoint (supports extra LEDs and trackpoint
configuration)
- ThinkPad Compact Bluetooth Keyboard with TrackPoint (supports Fn keys)
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 5a3a7ea..46f5ecd 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -525,6 +525,9 @@
#define I2C_VENDOR_ID_HANTICK 0x0911
#define I2C_PRODUCT_ID_HANTICK_5288 0x5288
+#define I2C_VENDOR_ID_RAYD 0x2386
+#define I2C_PRODUCT_ID_RAYD_3118 0x3118
+
#define USB_VENDOR_ID_HANWANG 0x0b57
#define USB_DEVICE_ID_HANWANG_TABLET_FIRST 0x5000
#define USB_DEVICE_ID_HANWANG_TABLET_LAST 0x8fff
@@ -549,6 +552,13 @@
#define USB_VENDOR_ID_HUION 0x256c
#define USB_DEVICE_ID_HUION_TABLET 0x006e
+#define USB_VENDOR_ID_IBM 0x04b3
+#define USB_DEVICE_ID_IBM_SCROLLPOINT_III 0x3100
+#define USB_DEVICE_ID_IBM_SCROLLPOINT_PRO 0x3103
+#define USB_DEVICE_ID_IBM_SCROLLPOINT_OPTICAL 0x3105
+#define USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL 0x3108
+#define USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL_PRO 0x3109
+
#define USB_VENDOR_ID_IDEACOM 0x1cb6
#define USB_DEVICE_ID_IDEACOM_IDC6650 0x6650
#define USB_DEVICE_ID_IDEACOM_IDC6651 0x6651
@@ -681,6 +691,7 @@
#define USB_DEVICE_ID_LENOVO_TPKBD 0x6009
#define USB_DEVICE_ID_LENOVO_CUSBKBD 0x6047
#define USB_DEVICE_ID_LENOVO_CBTKBD 0x6048
+#define USB_DEVICE_ID_LENOVO_SCROLLPOINT_OPTICAL 0x6049
#define USB_DEVICE_ID_LENOVO_TPPRODOCK 0x6067
#define USB_DEVICE_ID_LENOVO_X1_COVER 0x6085
#define USB_DEVICE_ID_LENOVO_X1_TAB 0x60a3
@@ -961,6 +972,7 @@
#define USB_DEVICE_ID_SIS817_TOUCH 0x0817
#define USB_DEVICE_ID_SIS_TS 0x1013
#define USB_DEVICE_ID_SIS1030_TOUCH 0x1030
+#define USB_DEVICE_ID_SIS10FB_TOUCH 0x10fb
#define USB_VENDOR_ID_SKYCABLE 0x1223
#define USB_DEVICE_ID_SKYCABLE_WIRELESS_PRESENTER 0x3F07
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 6836a85..930652c 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -387,7 +387,8 @@ static int hidinput_get_battery_property(struct power_supply *psy,
break;
case POWER_SUPPLY_PROP_CAPACITY:
- if (dev->battery_report_type == HID_FEATURE_REPORT) {
+ if (dev->battery_status != HID_BATTERY_REPORTED &&
+ !dev->battery_avoid_query) {
value = hidinput_query_battery_capacity(dev);
if (value < 0)
return value;
@@ -403,17 +404,17 @@ static int hidinput_get_battery_property(struct power_supply *psy,
break;
case POWER_SUPPLY_PROP_STATUS:
- if (!dev->battery_reported &&
- dev->battery_report_type == HID_FEATURE_REPORT) {
+ if (dev->battery_status != HID_BATTERY_REPORTED &&
+ !dev->battery_avoid_query) {
value = hidinput_query_battery_capacity(dev);
if (value < 0)
return value;
dev->battery_capacity = value;
- dev->battery_reported = true;
+ dev->battery_status = HID_BATTERY_QUERIED;
}
- if (!dev->battery_reported)
+ if (dev->battery_status == HID_BATTERY_UNKNOWN)
val->intval = POWER_SUPPLY_STATUS_UNKNOWN;
else if (dev->battery_capacity == 100)
val->intval = POWER_SUPPLY_STATUS_FULL;
@@ -486,6 +487,14 @@ static int hidinput_setup_battery(struct hid_device *dev, unsigned report_type,
dev->battery_report_type = report_type;
dev->battery_report_id = field->report->id;
+ /*
+ * Stylus is normally not connected to the device and thus we
+ * can't query the device and get meaningful battery strength.
+ * We have to wait for the device to report it on its own.
+ */
+ dev->battery_avoid_query = report_type == HID_INPUT_REPORT &&
+ field->physical == HID_DG_STYLUS;
+
dev->battery = power_supply_register(&dev->dev, psy_desc, &psy_cfg);
if (IS_ERR(dev->battery)) {
error = PTR_ERR(dev->battery);
@@ -530,9 +539,10 @@ static void hidinput_update_battery(struct hid_device *dev, int value)
capacity = hidinput_scale_battery_capacity(dev, value);
- if (!dev->battery_reported || capacity != dev->battery_capacity) {
+ if (dev->battery_status != HID_BATTERY_REPORTED ||
+ capacity != dev->battery_capacity) {
dev->battery_capacity = capacity;
- dev->battery_reported = true;
+ dev->battery_status = HID_BATTERY_REPORTED;
power_supply_changed(dev->battery);
}
}
diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c
index 1ac4ff4..643b6eb 100644
--- a/drivers/hid/hid-lenovo.c
+++ b/drivers/hid/hid-lenovo.c
@@ -6,6 +6,17 @@
*
* Copyright (c) 2012 Bernhard Seibold
* Copyright (c) 2014 Jamie Lentin <jm@lentin.co.uk>
+ *
+ * Linux IBM/Lenovo Scrollpoint mouse driver:
+ * - IBM Scrollpoint III
+ * - IBM Scrollpoint Pro
+ * - IBM Scrollpoint Optical
+ * - IBM Scrollpoint Optical 800dpi
+ * - IBM Scrollpoint Optical 800dpi Pro
+ * - Lenovo Scrollpoint Optical
+ *
+ * Copyright (c) 2012 Peter De Wachter <pdewacht@gmail.com>
+ * Copyright (c) 2018 Peter Ganzhorn <peter.ganzhorn@gmail.com>
*/
/*
@@ -160,6 +171,17 @@ static int lenovo_input_mapping_cptkbd(struct hid_device *hdev,
return 0;
}
+static int lenovo_input_mapping_scrollpoint(struct hid_device *hdev,
+ struct hid_input *hi, struct hid_field *field,
+ struct hid_usage *usage, unsigned long **bit, int *max)
+{
+ if (usage->hid == HID_GD_Z) {
+ hid_map_usage(hi, usage, bit, max, EV_REL, REL_HWHEEL);
+ return 1;
+ }
+ return 0;
+}
+
static int lenovo_input_mapping(struct hid_device *hdev,
struct hid_input *hi, struct hid_field *field,
struct hid_usage *usage, unsigned long **bit, int *max)
@@ -172,6 +194,14 @@ static int lenovo_input_mapping(struct hid_device *hdev,
case USB_DEVICE_ID_LENOVO_CBTKBD:
return lenovo_input_mapping_cptkbd(hdev, hi, field,
usage, bit, max);
+ case USB_DEVICE_ID_IBM_SCROLLPOINT_III:
+ case USB_DEVICE_ID_IBM_SCROLLPOINT_PRO:
+ case USB_DEVICE_ID_IBM_SCROLLPOINT_OPTICAL:
+ case USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL:
+ case USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL_PRO:
+ case USB_DEVICE_ID_LENOVO_SCROLLPOINT_OPTICAL:
+ return lenovo_input_mapping_scrollpoint(hdev, hi, field,
+ usage, bit, max);
default:
return 0;
}
@@ -883,6 +913,12 @@ static const struct hid_device_id lenovo_devices[] = {
{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CUSBKBD) },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CBTKBD) },
{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPPRODOCK) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_III) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_PRO) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_OPTICAL) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL_PRO) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_SCROLLPOINT_OPTICAL) },
{ }
};
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index fbfcc80..b39844a 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -192,6 +192,11 @@ static ssize_t hidraw_get_report(struct file *file, char __user *buffer, size_t
int ret = 0, len;
unsigned char report_number;
+ if (!hidraw_table[minor] || !hidraw_table[minor]->exist) {
+ ret = -ENODEV;
+ goto out;
+ }
+
dev = hidraw_table[minor]->hid;
if (!dev->ll_driver->raw_request) {
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index 97689e9..cc33622 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -47,6 +47,7 @@
/* quirks to control the device */
#define I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV BIT(0)
#define I2C_HID_QUIRK_NO_IRQ_AFTER_RESET BIT(1)
+#define I2C_HID_QUIRK_RESEND_REPORT_DESCR BIT(2)
/* flags */
#define I2C_HID_STARTED 0
@@ -171,6 +172,10 @@ static const struct i2c_hid_quirks {
I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV },
{ I2C_VENDOR_ID_HANTICK, I2C_PRODUCT_ID_HANTICK_5288,
I2C_HID_QUIRK_NO_IRQ_AFTER_RESET },
+ { I2C_VENDOR_ID_RAYD, I2C_PRODUCT_ID_RAYD_3118,
+ I2C_HID_QUIRK_RESEND_REPORT_DESCR },
+ { USB_VENDOR_ID_SIS_TOUCH, USB_DEVICE_ID_SIS10FB_TOUCH,
+ I2C_HID_QUIRK_RESEND_REPORT_DESCR },
{ 0, 0 }
};
@@ -1220,6 +1225,16 @@ static int i2c_hid_resume(struct device *dev)
if (ret)
return ret;
+ /* RAYDIUM device (2386:3118) need to re-send report descr cmd
+ * after resume, after this it will be back normal.
+ * otherwise it issues too many incomplete reports.
+ */
+ if (ihid->quirks & I2C_HID_QUIRK_RESEND_REPORT_DESCR) {
+ ret = i2c_hid_command(client, &hid_report_descr_cmd, NULL, 0);
+ if (ret)
+ return ret;
+ }
+
if (hid->driver && hid->driver->reset_resume) {
ret = hid->driver->reset_resume(hid);
return ret;
diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c
index 157b44a..acc2536 100644
--- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c
+++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c
@@ -77,21 +77,21 @@ static void process_recv(struct ishtp_cl *hid_ishtp_cl, void *recv_buf,
struct ishtp_cl_data *client_data = hid_ishtp_cl->client_data;
int curr_hid_dev = client_data->cur_hid_dev;
- if (data_len < sizeof(struct hostif_msg_hdr)) {
- dev_err(&client_data->cl_device->dev,
- "[hid-ish]: error, received %u which is less than data header %u\n",
- (unsigned int)data_len,
- (unsigned int)sizeof(struct hostif_msg_hdr));
- ++client_data->bad_recv_cnt;
- ish_hw_reset(hid_ishtp_cl->dev);
- return;
- }
-
payload = recv_buf + sizeof(struct hostif_msg_hdr);
total_len = data_len;
cur_pos = 0;
do {
+ if (cur_pos + sizeof(struct hostif_msg) > total_len) {
+ dev_err(&client_data->cl_device->dev,
+ "[hid-ish]: error, received %u which is less than data header %u\n",
+ (unsigned int)data_len,
+ (unsigned int)sizeof(struct hostif_msg_hdr));
+ ++client_data->bad_recv_cnt;
+ ish_hw_reset(hid_ishtp_cl->dev);
+ break;
+ }
+
recv_msg = (struct hostif_msg *)(recv_buf + cur_pos);
payload_len = recv_msg->hdr.size;
@@ -412,9 +412,7 @@ void hid_ishtp_get_report(struct hid_device *hid, int report_id,
{
struct ishtp_hid_data *hid_data = hid->driver_data;
struct ishtp_cl_data *client_data = hid_data->client_data;
- static unsigned char buf[10];
- unsigned int len;
- struct hostif_msg_to_sensor *msg = (struct hostif_msg_to_sensor *)buf;
+ struct hostif_msg_to_sensor msg = {};
int rv;
int i;
@@ -426,14 +424,11 @@ void hid_ishtp_get_report(struct hid_device *hid, int report_id,
return;
}
- len = sizeof(struct hostif_msg_to_sensor);
-
- memset(msg, 0, sizeof(struct hostif_msg_to_sensor));
- msg->hdr.command = (report_type == HID_FEATURE_REPORT) ?
+ msg.hdr.command = (report_type == HID_FEATURE_REPORT) ?
HOSTIF_GET_FEATURE_REPORT : HOSTIF_GET_INPUT_REPORT;
for (i = 0; i < client_data->num_hid_devices; ++i) {
if (hid == client_data->hid_sensor_hubs[i]) {
- msg->hdr.device_id =
+ msg.hdr.device_id =
client_data->hid_devices[i].dev_id;
break;
}
@@ -442,8 +437,9 @@ void hid_ishtp_get_report(struct hid_device *hid, int report_id,
if (i == client_data->num_hid_devices)
return;
- msg->report_id = report_id;
- rv = ishtp_cl_send(client_data->hid_ishtp_cl, buf, len);
+ msg.report_id = report_id;
+ rv = ishtp_cl_send(client_data->hid_ishtp_cl, (uint8_t *)&msg,
+ sizeof(msg));
if (rv)
hid_ishtp_trace(client_data, "%s hid %p send failed\n",
__func__, hid);
diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c
index f272cdd..2623a56 100644
--- a/drivers/hid/intel-ish-hid/ishtp/bus.c
+++ b/drivers/hid/intel-ish-hid/ishtp/bus.c
@@ -418,7 +418,7 @@ static struct ishtp_cl_device *ishtp_bus_add_device(struct ishtp_device *dev,
list_del(&device->device_link);
spin_unlock_irqrestore(&dev->device_list_lock, flags);
dev_err(dev->devc, "Failed to register ISHTP client device\n");
- kfree(device);
+ put_device(&device->dev);
return NULL;
}
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index b54ef1f..ee7a37e 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -1213,8 +1213,10 @@ static int __wacom_devm_sysfs_create_group(struct wacom *wacom,
devres->root = root;
error = sysfs_create_group(devres->root, group);
- if (error)
+ if (error) {
+ devres_free(devres);
return error;
+ }
devres_add(&wacom->hdev->dev, devres);
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 6da16a8..5f947ec 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -689,6 +689,45 @@ static int wacom_intuos_get_tool_type(int tool_id)
return tool_type;
}
+static void wacom_exit_report(struct wacom_wac *wacom)
+{
+ struct input_dev *input = wacom->pen_input;
+ struct wacom_features *features = &wacom->features;
+ unsigned char *data = wacom->data;
+ int idx = (features->type == INTUOS) ? (data[1] & 0x01) : 0;
+
+ /*
+ * Reset all states otherwise we lose the initial states
+ * when in-prox next time
+ */
+ input_report_abs(input, ABS_X, 0);
+ input_report_abs(input, ABS_Y, 0);
+ input_report_abs(input, ABS_DISTANCE, 0);
+ input_report_abs(input, ABS_TILT_X, 0);
+ input_report_abs(input, ABS_TILT_Y, 0);
+ if (wacom->tool[idx] >= BTN_TOOL_MOUSE) {
+ input_report_key(input, BTN_LEFT, 0);
+ input_report_key(input, BTN_MIDDLE, 0);
+ input_report_key(input, BTN_RIGHT, 0);
+ input_report_key(input, BTN_SIDE, 0);
+ input_report_key(input, BTN_EXTRA, 0);
+ input_report_abs(input, ABS_THROTTLE, 0);
+ input_report_abs(input, ABS_RZ, 0);
+ } else {
+ input_report_abs(input, ABS_PRESSURE, 0);
+ input_report_key(input, BTN_STYLUS, 0);
+ input_report_key(input, BTN_STYLUS2, 0);
+ input_report_key(input, BTN_TOUCH, 0);
+ input_report_abs(input, ABS_WHEEL, 0);
+ if (features->type >= INTUOS3S)
+ input_report_abs(input, ABS_Z, 0);
+ }
+ input_report_key(input, wacom->tool[idx], 0);
+ input_report_abs(input, ABS_MISC, 0); /* reset tool id */
+ input_event(input, EV_MSC, MSC_SERIAL, wacom->serial[idx]);
+ wacom->id[idx] = 0;
+}
+
static int wacom_intuos_inout(struct wacom_wac *wacom)
{
struct wacom_features *features = &wacom->features;
@@ -741,36 +780,7 @@ static int wacom_intuos_inout(struct wacom_wac *wacom)
if (!wacom->id[idx])
return 1;
- /*
- * Reset all states otherwise we lose the initial states
- * when in-prox next time
- */
- input_report_abs(input, ABS_X, 0);
- input_report_abs(input, ABS_Y, 0);
- input_report_abs(input, ABS_DISTANCE, 0);
- input_report_abs(input, ABS_TILT_X, 0);
- input_report_abs(input, ABS_TILT_Y, 0);
- if (wacom->tool[idx] >= BTN_TOOL_MOUSE) {
- input_report_key(input, BTN_LEFT, 0);
- input_report_key(input, BTN_MIDDLE, 0);
- input_report_key(input, BTN_RIGHT, 0);
- input_report_key(input, BTN_SIDE, 0);
- input_report_key(input, BTN_EXTRA, 0);
- input_report_abs(input, ABS_THROTTLE, 0);
- input_report_abs(input, ABS_RZ, 0);
- } else {
- input_report_abs(input, ABS_PRESSURE, 0);
- input_report_key(input, BTN_STYLUS, 0);
- input_report_key(input, BTN_STYLUS2, 0);
- input_report_key(input, BTN_TOUCH, 0);
- input_report_abs(input, ABS_WHEEL, 0);
- if (features->type >= INTUOS3S)
- input_report_abs(input, ABS_Z, 0);
- }
- input_report_key(input, wacom->tool[idx], 0);
- input_report_abs(input, ABS_MISC, 0); /* reset tool id */
- input_event(input, EV_MSC, MSC_SERIAL, wacom->serial[idx]);
- wacom->id[idx] = 0;
+ wacom_exit_report(wacom);
return 2;
}
@@ -1235,6 +1245,12 @@ static void wacom_intuos_pro2_bt_pen(struct wacom_wac *wacom)
if (!valid)
continue;
+ if (!prox) {
+ wacom->shared->stylus_in_proximity = false;
+ wacom_exit_report(wacom);
+ input_sync(pen_input);
+ return;
+ }
if (range) {
input_report_abs(pen_input, ABS_X, get_unaligned_le16(&frame[1]));
input_report_abs(pen_input, ABS_Y, get_unaligned_le16(&frame[3]));
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index f249a44..f10840a 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -272,7 +272,7 @@
config SENSORS_K10TEMP
tristate "AMD Family 10h+ temperature sensor"
- depends on X86 && PCI
+ depends on X86 && PCI && AMD_NB
help
If you say yes here you get support for the temperature
sensor(s) inside your CPU. Supported are later revisions of
@@ -717,15 +717,12 @@
be called ltc2945.
config SENSORS_LTC2990
- tristate "Linear Technology LTC2990 (current monitoring mode only)"
+ tristate "Linear Technology LTC2990"
depends on I2C
help
If you say yes here you get support for Linear Technology LTC2990
I2C System Monitor. The LTC2990 supports a combination of voltage,
- current and temperature monitoring, but in addition to the Vcc supply
- voltage and chip temperature, this driver currently only supports
- reading two currents by measuring two differential voltages across
- series resistors.
+ current and temperature monitoring.
This driver can also be built as a module. If so, the module will
be called ltc2990.
diff --git a/drivers/hwmon/asus_atk0110.c b/drivers/hwmon/asus_atk0110.c
index 975c43d..a6636fe 100644
--- a/drivers/hwmon/asus_atk0110.c
+++ b/drivers/hwmon/asus_atk0110.c
@@ -125,6 +125,8 @@ struct atk_data {
int temperature_count;
int fan_count;
struct list_head sensor_list;
+ struct attribute_group attr_group;
+ const struct attribute_group *attr_groups[2];
struct {
struct dentry *root;
@@ -188,7 +190,6 @@ static int atk_add(struct acpi_device *device);
static int atk_remove(struct acpi_device *device);
static void atk_print_sensor(struct atk_data *data, union acpi_object *obj);
static int atk_read_value(struct atk_sensor_data *sensor, u64 *value);
-static void atk_free_sensors(struct atk_data *data);
static struct acpi_driver atk_driver = {
.name = ATK_HID,
@@ -262,14 +263,6 @@ static ssize_t atk_limit2_show(struct device *dev,
return sprintf(buf, "%lld\n", value);
}
-static ssize_t atk_name_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- return sprintf(buf, "atk0110\n");
-}
-static struct device_attribute atk_name_attr =
- __ATTR(name, 0444, atk_name_show, NULL);
-
static void atk_init_attribute(struct device_attribute *attr, char *name,
sysfs_show_func show)
{
@@ -912,15 +905,13 @@ static int atk_add_sensor(struct atk_data *data, union acpi_object *obj)
limit1 = atk_get_pack_member(data, obj, HWMON_PACK_LIMIT1);
limit2 = atk_get_pack_member(data, obj, HWMON_PACK_LIMIT2);
- sensor = kzalloc(sizeof(*sensor), GFP_KERNEL);
+ sensor = devm_kzalloc(dev, sizeof(*sensor), GFP_KERNEL);
if (!sensor)
return -ENOMEM;
- sensor->acpi_name = kstrdup(name->string.pointer, GFP_KERNEL);
- if (!sensor->acpi_name) {
- err = -ENOMEM;
- goto out;
- }
+ sensor->acpi_name = devm_kstrdup(dev, name->string.pointer, GFP_KERNEL);
+ if (!sensor->acpi_name)
+ return -ENOMEM;
INIT_LIST_HEAD(&sensor->list);
sensor->type = type;
@@ -961,9 +952,6 @@ static int atk_add_sensor(struct atk_data *data, union acpi_object *obj)
(*num)++;
return 1;
-out:
- kfree(sensor);
- return err;
}
static int atk_enumerate_old_hwmon(struct atk_data *data)
@@ -1004,8 +992,7 @@ static int atk_enumerate_old_hwmon(struct atk_data *data)
dev_warn(dev, METHOD_OLD_ENUM_TMP ": ACPI exception: %s\n",
acpi_format_exception(status));
- ret = -ENODEV;
- goto cleanup;
+ return -ENODEV;
}
pack = buf.pointer;
@@ -1026,8 +1013,7 @@ static int atk_enumerate_old_hwmon(struct atk_data *data)
dev_warn(dev, METHOD_OLD_ENUM_FAN ": ACPI exception: %s\n",
acpi_format_exception(status));
- ret = -ENODEV;
- goto cleanup;
+ return -ENODEV;
}
pack = buf.pointer;
@@ -1041,9 +1027,6 @@ static int atk_enumerate_old_hwmon(struct atk_data *data)
ACPI_FREE(buf.pointer);
return count;
-cleanup:
- atk_free_sensors(data);
- return ret;
}
static int atk_ec_present(struct atk_data *data)
@@ -1193,76 +1176,44 @@ static int atk_enumerate_new_hwmon(struct atk_data *data)
return err;
}
-static int atk_create_files(struct atk_data *data)
+static int atk_init_attribute_groups(struct atk_data *data)
{
+ struct device *dev = &data->acpi_dev->dev;
struct atk_sensor_data *s;
- int err;
+ struct attribute **attrs;
+ int i = 0;
+ int len = (data->voltage_count + data->temperature_count
+ + data->fan_count) * 4 + 1;
+
+ attrs = devm_kcalloc(dev, len, sizeof(struct attribute *), GFP_KERNEL);
+ if (!attrs)
+ return -ENOMEM;
list_for_each_entry(s, &data->sensor_list, list) {
- err = device_create_file(data->hwmon_dev, &s->input_attr);
- if (err)
- return err;
- err = device_create_file(data->hwmon_dev, &s->label_attr);
- if (err)
- return err;
- err = device_create_file(data->hwmon_dev, &s->limit1_attr);
- if (err)
- return err;
- err = device_create_file(data->hwmon_dev, &s->limit2_attr);
- if (err)
- return err;
+ attrs[i++] = &s->input_attr.attr;
+ attrs[i++] = &s->label_attr.attr;
+ attrs[i++] = &s->limit1_attr.attr;
+ attrs[i++] = &s->limit2_attr.attr;
}
- err = device_create_file(data->hwmon_dev, &atk_name_attr);
+ data->attr_group.attrs = attrs;
+ data->attr_groups[0] = &data->attr_group;
- return err;
-}
-
-static void atk_remove_files(struct atk_data *data)
-{
- struct atk_sensor_data *s;
-
- list_for_each_entry(s, &data->sensor_list, list) {
- device_remove_file(data->hwmon_dev, &s->input_attr);
- device_remove_file(data->hwmon_dev, &s->label_attr);
- device_remove_file(data->hwmon_dev, &s->limit1_attr);
- device_remove_file(data->hwmon_dev, &s->limit2_attr);
- }
- device_remove_file(data->hwmon_dev, &atk_name_attr);
-}
-
-static void atk_free_sensors(struct atk_data *data)
-{
- struct list_head *head = &data->sensor_list;
- struct atk_sensor_data *s, *tmp;
-
- list_for_each_entry_safe(s, tmp, head, list) {
- kfree(s->acpi_name);
- kfree(s);
- }
+ return 0;
}
static int atk_register_hwmon(struct atk_data *data)
{
struct device *dev = &data->acpi_dev->dev;
- int err;
dev_dbg(dev, "registering hwmon device\n");
- data->hwmon_dev = hwmon_device_register(dev);
+ data->hwmon_dev = hwmon_device_register_with_groups(dev, "atk0110",
+ data,
+ data->attr_groups);
if (IS_ERR(data->hwmon_dev))
return PTR_ERR(data->hwmon_dev);
- dev_dbg(dev, "populating sysfs directory\n");
- err = atk_create_files(data);
- if (err)
- goto remove;
-
return 0;
-remove:
- /* Cleanup the registered files */
- atk_remove_files(data);
- hwmon_device_unregister(data->hwmon_dev);
- return err;
}
static int atk_probe_if(struct atk_data *data)
@@ -1350,7 +1301,7 @@ static int atk_add(struct acpi_device *device)
dev_dbg(&device->dev, "adding...\n");
- data = kzalloc(sizeof(*data), GFP_KERNEL);
+ data = devm_kzalloc(&device->dev, sizeof(*data), GFP_KERNEL);
if (!data)
return -ENOMEM;
@@ -1397,20 +1348,20 @@ static int atk_add(struct acpi_device *device)
goto out;
}
+ err = atk_init_attribute_groups(data);
+ if (err)
+ goto out;
err = atk_register_hwmon(data);
if (err)
- goto cleanup;
+ goto out;
atk_debugfs_init(data);
device->driver_data = data;
return 0;
-cleanup:
- atk_free_sensors(data);
out:
if (data->disable_ec)
atk_ec_ctl(data, 0);
- kfree(data);
return err;
}
@@ -1423,8 +1374,6 @@ static int atk_remove(struct acpi_device *device)
atk_debugfs_cleanup(data);
- atk_remove_files(data);
- atk_free_sensors(data);
hwmon_device_unregister(data->hwmon_dev);
if (data->disable_ec) {
@@ -1432,8 +1381,6 @@ static int atk_remove(struct acpi_device *device)
dev_err(&device->dev, "Failed to disable EC\n");
}
- kfree(data);
-
return 0;
}
diff --git a/drivers/hwmon/fschmd.c b/drivers/hwmon/fschmd.c
index 5e78229..22d3a84 100644
--- a/drivers/hwmon/fschmd.c
+++ b/drivers/hwmon/fschmd.c
@@ -105,7 +105,7 @@ static const u8 FSCHMD_REG_VOLT[7][6] = {
static const int FSCHMD_NO_VOLT_SENSORS[7] = { 3, 3, 3, 3, 3, 3, 6 };
/*
- * minimum pwm at which the fan is driven (pwm can by increased depending on
+ * minimum pwm at which the fan is driven (pwm can be increased depending on
* the temp. Notice that for the scy some fans share there minimum speed.
* Also notice that with the scy the sensor order is different than with the
* other chips, this order was in the 2.4 driver and kept for consistency.
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index 32083e4..e88c019 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -698,6 +698,9 @@ hwmon_device_register_with_info(struct device *dev, const char *name,
if (chip && (!chip->ops || !chip->ops->is_visible || !chip->info))
return ERR_PTR(-EINVAL);
+ if (chip && !dev)
+ return ERR_PTR(-EINVAL);
+
return __hwmon_device_register(dev, name, drvdata, chip, extra_groups);
}
EXPORT_SYMBOL_GPL(hwmon_device_register_with_info);
diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index 051a72e..17c6460 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -23,6 +23,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/pci.h>
+#include <asm/amd_nb.h>
#include <asm/processor.h>
MODULE_DESCRIPTION("AMD Family 10h+ CPU core temperature monitor");
@@ -36,10 +37,18 @@ MODULE_PARM_DESC(force, "force loading on processors with erratum 319");
/* Provide lock for writing to NB_SMU_IND_ADDR */
static DEFINE_MUTEX(nb_smu_ind_mutex);
+#ifndef PCI_DEVICE_ID_AMD_15H_M70H_NB_F3
+#define PCI_DEVICE_ID_AMD_15H_M70H_NB_F3 0x15b3
+#endif
+
#ifndef PCI_DEVICE_ID_AMD_17H_DF_F3
#define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463
#endif
+#ifndef PCI_DEVICE_ID_AMD_17H_M10H_DF_F3
+#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb
+#endif
+
/* CPUID function 0x80000001, ebx */
#define CPUID_PKGTYPE_MASK 0xf0000000
#define CPUID_PKGTYPE_F 0x00000000
@@ -59,10 +68,12 @@ static DEFINE_MUTEX(nb_smu_ind_mutex);
#define NB_CAP_HTC 0x00000400
/*
- * For F15h M60h, functionality of REG_REPORTED_TEMPERATURE
- * has been moved to D0F0xBC_xD820_0CA4 [Reported Temperature
- * Control]
+ * For F15h M60h and M70h, REG_HARDWARE_THERMAL_CONTROL
+ * and REG_REPORTED_TEMPERATURE have been moved to
+ * D0F0xBC_xD820_0C64 [Hardware Temperature Control]
+ * D0F0xBC_xD820_0CA4 [Reported Temperature Control]
*/
+#define F15H_M60H_HARDWARE_TEMP_CTRL_OFFSET 0xd8200c64
#define F15H_M60H_REPORTED_TEMP_CTRL_OFFSET 0xd8200ca4
/* F17h M01h Access througn SMN */
@@ -70,8 +81,11 @@ static DEFINE_MUTEX(nb_smu_ind_mutex);
struct k10temp_data {
struct pci_dev *pdev;
+ void (*read_htcreg)(struct pci_dev *pdev, u32 *regval);
void (*read_tempreg)(struct pci_dev *pdev, u32 *regval);
int temp_offset;
+ u32 temp_adjust_mask;
+ bool show_tdie;
};
struct tctl_offset {
@@ -84,6 +98,7 @@ static const struct tctl_offset tctl_offset_table[] = {
{ 0x17, "AMD Ryzen 5 1600X", 20000 },
{ 0x17, "AMD Ryzen 7 1700X", 20000 },
{ 0x17, "AMD Ryzen 7 1800X", 20000 },
+ { 0x17, "AMD Ryzen 7 2700X", 10000 },
{ 0x17, "AMD Ryzen Threadripper 1950X", 27000 },
{ 0x17, "AMD Ryzen Threadripper 1920X", 27000 },
{ 0x17, "AMD Ryzen Threadripper 1900X", 27000 },
@@ -92,6 +107,11 @@ static const struct tctl_offset tctl_offset_table[] = {
{ 0x17, "AMD Ryzen Threadripper 1910", 10000 },
};
+static void read_htcreg_pci(struct pci_dev *pdev, u32 *regval)
+{
+ pci_read_config_dword(pdev, REG_HARDWARE_THERMAL_CONTROL, regval);
+}
+
static void read_tempreg_pci(struct pci_dev *pdev, u32 *regval)
{
pci_read_config_dword(pdev, REG_REPORTED_TEMPERATURE, regval);
@@ -108,6 +128,12 @@ static void amd_nb_index_read(struct pci_dev *pdev, unsigned int devfn,
mutex_unlock(&nb_smu_ind_mutex);
}
+static void read_htcreg_nb_f15(struct pci_dev *pdev, u32 *regval)
+{
+ amd_nb_index_read(pdev, PCI_DEVFN(0, 0), 0xb8,
+ F15H_M60H_HARDWARE_TEMP_CTRL_OFFSET, regval);
+}
+
static void read_tempreg_nb_f15(struct pci_dev *pdev, u32 *regval)
{
amd_nb_index_read(pdev, PCI_DEVFN(0, 0), 0xb8,
@@ -116,19 +142,28 @@ static void read_tempreg_nb_f15(struct pci_dev *pdev, u32 *regval)
static void read_tempreg_nb_f17(struct pci_dev *pdev, u32 *regval)
{
- amd_nb_index_read(pdev, PCI_DEVFN(0, 0), 0x60,
- F17H_M01H_REPORTED_TEMP_CTRL_OFFSET, regval);
+ amd_smn_read(amd_pci_dev_to_node_id(pdev),
+ F17H_M01H_REPORTED_TEMP_CTRL_OFFSET, regval);
+}
+
+static unsigned int get_raw_temp(struct k10temp_data *data)
+{
+ unsigned int temp;
+ u32 regval;
+
+ data->read_tempreg(data->pdev, ®val);
+ temp = (regval >> 21) * 125;
+ if (regval & data->temp_adjust_mask)
+ temp -= 49000;
+ return temp;
}
static ssize_t temp1_input_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct k10temp_data *data = dev_get_drvdata(dev);
- u32 regval;
- unsigned int temp;
+ unsigned int temp = get_raw_temp(data);
- data->read_tempreg(data->pdev, ®val);
- temp = (regval >> 21) * 125;
if (temp > data->temp_offset)
temp -= data->temp_offset;
else
@@ -137,6 +172,23 @@ static ssize_t temp1_input_show(struct device *dev,
return sprintf(buf, "%u\n", temp);
}
+static ssize_t temp2_input_show(struct device *dev,
+ struct device_attribute *devattr, char *buf)
+{
+ struct k10temp_data *data = dev_get_drvdata(dev);
+ unsigned int temp = get_raw_temp(data);
+
+ return sprintf(buf, "%u\n", temp);
+}
+
+static ssize_t temp_label_show(struct device *dev,
+ struct device_attribute *devattr, char *buf)
+{
+ struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+
+ return sprintf(buf, "%s\n", attr->index ? "Tctl" : "Tdie");
+}
+
static ssize_t temp1_max_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -152,8 +204,7 @@ static ssize_t show_temp_crit(struct device *dev,
u32 regval;
int value;
- pci_read_config_dword(data->pdev,
- REG_HARDWARE_THERMAL_CONTROL, ®val);
+ data->read_htcreg(data->pdev, ®val);
value = ((regval >> 16) & 0x7f) * 500 + 52000;
if (show_hyst)
value -= ((regval >> 24) & 0xf) * 500;
@@ -165,22 +216,39 @@ static DEVICE_ATTR_RO(temp1_max);
static SENSOR_DEVICE_ATTR(temp1_crit, S_IRUGO, show_temp_crit, NULL, 0);
static SENSOR_DEVICE_ATTR(temp1_crit_hyst, S_IRUGO, show_temp_crit, NULL, 1);
+static SENSOR_DEVICE_ATTR(temp1_label, 0444, temp_label_show, NULL, 0);
+static DEVICE_ATTR_RO(temp2_input);
+static SENSOR_DEVICE_ATTR(temp2_label, 0444, temp_label_show, NULL, 1);
+
static umode_t k10temp_is_visible(struct kobject *kobj,
struct attribute *attr, int index)
{
struct device *dev = container_of(kobj, struct device, kobj);
struct k10temp_data *data = dev_get_drvdata(dev);
struct pci_dev *pdev = data->pdev;
+ u32 reg;
- if (index >= 2) {
- u32 reg_caps, reg_htc;
+ switch (index) {
+ case 0 ... 1: /* temp1_input, temp1_max */
+ default:
+ break;
+ case 2 ... 3: /* temp1_crit, temp1_crit_hyst */
+ if (!data->read_htcreg)
+ return 0;
pci_read_config_dword(pdev, REG_NORTHBRIDGE_CAPABILITIES,
- ®_caps);
- pci_read_config_dword(pdev, REG_HARDWARE_THERMAL_CONTROL,
- ®_htc);
- if (!(reg_caps & NB_CAP_HTC) || !(reg_htc & HTC_ENABLE))
+ ®);
+ if (!(reg & NB_CAP_HTC))
return 0;
+
+ data->read_htcreg(data->pdev, ®);
+ if (!(reg & HTC_ENABLE))
+ return 0;
+ break;
+ case 4 ... 6: /* temp1_label, temp2_input, temp2_label */
+ if (!data->show_tdie)
+ return 0;
+ break;
}
return attr->mode;
}
@@ -190,6 +258,9 @@ static struct attribute *k10temp_attrs[] = {
&dev_attr_temp1_max.attr,
&sensor_dev_attr_temp1_crit.dev_attr.attr,
&sensor_dev_attr_temp1_crit_hyst.dev_attr.attr,
+ &sensor_dev_attr_temp1_label.dev_attr.attr,
+ &dev_attr_temp2_input.attr,
+ &sensor_dev_attr_temp2_label.dev_attr.attr,
NULL
};
@@ -259,12 +330,17 @@ static int k10temp_probe(struct pci_dev *pdev,
data->pdev = pdev;
if (boot_cpu_data.x86 == 0x15 && (boot_cpu_data.x86_model == 0x60 ||
- boot_cpu_data.x86_model == 0x70))
+ boot_cpu_data.x86_model == 0x70)) {
+ data->read_htcreg = read_htcreg_nb_f15;
data->read_tempreg = read_tempreg_nb_f15;
- else if (boot_cpu_data.x86 == 0x17)
+ } else if (boot_cpu_data.x86 == 0x17) {
+ data->temp_adjust_mask = 0x80000;
data->read_tempreg = read_tempreg_nb_f17;
- else
+ data->show_tdie = true;
+ } else {
+ data->read_htcreg = read_htcreg_pci;
data->read_tempreg = read_tempreg_pci;
+ }
for (i = 0; i < ARRAY_SIZE(tctl_offset_table); i++) {
const struct tctl_offset *entry = &tctl_offset_table[i];
@@ -289,9 +365,11 @@ static const struct pci_device_id k10temp_id_table[] = {
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) },
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) },
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M60H_NB_F3) },
+ { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M70H_NB_F3) },
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) },
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) },
+ { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) },
{}
};
MODULE_DEVICE_TABLE(pci, k10temp_id_table);
diff --git a/drivers/hwmon/ltc2990.c b/drivers/hwmon/ltc2990.c
index 8f8fe05..2aefdc5 100644
--- a/drivers/hwmon/ltc2990.c
+++ b/drivers/hwmon/ltc2990.c
@@ -5,18 +5,16 @@
* Author: Mike Looijmans <mike.looijmans@topic.nl>
*
* License: GPLv2
- *
- * This driver assumes the chip is wired as a dual current monitor, and
- * reports the voltage drop across two series resistors. It also reports
- * the chip's internal temperature and Vcc power supply voltage.
*/
+#include <linux/bitops.h>
#include <linux/err.h>
#include <linux/hwmon.h>
#include <linux/hwmon-sysfs.h>
#include <linux/i2c.h>
#include <linux/kernel.h>
#include <linux/module.h>
+#include <linux/of.h>
#define LTC2990_STATUS 0x00
#define LTC2990_CONTROL 0x01
@@ -28,45 +26,108 @@
#define LTC2990_V4_MSB 0x0C
#define LTC2990_VCC_MSB 0x0E
-#define LTC2990_CONTROL_KELVIN BIT(7)
-#define LTC2990_CONTROL_SINGLE BIT(6)
-#define LTC2990_CONTROL_MEASURE_ALL (0x3 << 3)
-#define LTC2990_CONTROL_MODE_CURRENT 0x06
-#define LTC2990_CONTROL_MODE_VOLTAGE 0x07
+#define LTC2990_IN0 BIT(0)
+#define LTC2990_IN1 BIT(1)
+#define LTC2990_IN2 BIT(2)
+#define LTC2990_IN3 BIT(3)
+#define LTC2990_IN4 BIT(4)
+#define LTC2990_CURR1 BIT(5)
+#define LTC2990_CURR2 BIT(6)
+#define LTC2990_TEMP1 BIT(7)
+#define LTC2990_TEMP2 BIT(8)
+#define LTC2990_TEMP3 BIT(9)
+#define LTC2990_NONE 0
+#define LTC2990_ALL GENMASK(9, 0)
-/* convert raw register value to sign-extended integer in 16-bit range */
-static int ltc2990_voltage_to_int(int raw)
-{
- if (raw & BIT(14))
- return -(0x4000 - (raw & 0x3FFF)) << 2;
- else
- return (raw & 0x3FFF) << 2;
-}
+#define LTC2990_MODE0_SHIFT 0
+#define LTC2990_MODE0_MASK GENMASK(2, 0)
+#define LTC2990_MODE1_SHIFT 3
+#define LTC2990_MODE1_MASK GENMASK(1, 0)
+
+/* Enabled measurements for mode bits 2..0 */
+static const int ltc2990_attrs_ena_0[] = {
+ LTC2990_IN1 | LTC2990_IN2 | LTC2990_TEMP3,
+ LTC2990_CURR1 | LTC2990_TEMP3,
+ LTC2990_CURR1 | LTC2990_IN3 | LTC2990_IN4,
+ LTC2990_TEMP2 | LTC2990_IN3 | LTC2990_IN4,
+ LTC2990_TEMP2 | LTC2990_CURR2,
+ LTC2990_TEMP2 | LTC2990_TEMP3,
+ LTC2990_CURR1 | LTC2990_CURR2,
+ LTC2990_IN1 | LTC2990_IN2 | LTC2990_IN3 | LTC2990_IN4
+};
+
+/* Enabled measurements for mode bits 4..3 */
+static const int ltc2990_attrs_ena_1[] = {
+ LTC2990_NONE,
+ LTC2990_TEMP2 | LTC2990_IN1 | LTC2990_CURR1,
+ LTC2990_TEMP3 | LTC2990_IN3 | LTC2990_CURR2,
+ LTC2990_ALL
+};
+
+struct ltc2990_data {
+ struct i2c_client *i2c;
+ u32 mode[2];
+};
/* Return the converted value from the given register in uV or mC */
-static int ltc2990_get_value(struct i2c_client *i2c, u8 reg, int *result)
+static int ltc2990_get_value(struct i2c_client *i2c, int index, int *result)
{
int val;
+ u8 reg;
+
+ switch (index) {
+ case LTC2990_IN0:
+ reg = LTC2990_VCC_MSB;
+ break;
+ case LTC2990_IN1:
+ case LTC2990_CURR1:
+ case LTC2990_TEMP2:
+ reg = LTC2990_V1_MSB;
+ break;
+ case LTC2990_IN2:
+ reg = LTC2990_V2_MSB;
+ break;
+ case LTC2990_IN3:
+ case LTC2990_CURR2:
+ case LTC2990_TEMP3:
+ reg = LTC2990_V3_MSB;
+ break;
+ case LTC2990_IN4:
+ reg = LTC2990_V4_MSB;
+ break;
+ case LTC2990_TEMP1:
+ reg = LTC2990_TINT_MSB;
+ break;
+ default:
+ return -EINVAL;
+ }
val = i2c_smbus_read_word_swapped(i2c, reg);
if (unlikely(val < 0))
return val;
- switch (reg) {
- case LTC2990_TINT_MSB:
- /* internal temp, 0.0625 degrees/LSB, 13-bit */
- val = (val & 0x1FFF) << 3;
- *result = (val * 1000) >> 7;
+ switch (index) {
+ case LTC2990_TEMP1:
+ case LTC2990_TEMP2:
+ case LTC2990_TEMP3:
+ /* temp, 0.0625 degrees/LSB */
+ *result = sign_extend32(val, 12) * 1000 / 16;
break;
- case LTC2990_V1_MSB:
- case LTC2990_V3_MSB:
- /* Vx-Vy, 19.42uV/LSB. Depends on mode. */
- *result = ltc2990_voltage_to_int(val) * 1942 / (4 * 100);
+ case LTC2990_CURR1:
+ case LTC2990_CURR2:
+ /* Vx-Vy, 19.42uV/LSB */
+ *result = sign_extend32(val, 14) * 1942 / 100;
break;
- case LTC2990_VCC_MSB:
- /* Vcc, 305.18μV/LSB, 2.5V offset */
- *result = (ltc2990_voltage_to_int(val) * 30518 /
- (4 * 100 * 1000)) + 2500;
+ case LTC2990_IN0:
+ /* Vcc, 305.18uV/LSB, 2.5V offset */
+ *result = sign_extend32(val, 14) * 30518 / (100 * 1000) + 2500;
+ break;
+ case LTC2990_IN1:
+ case LTC2990_IN2:
+ case LTC2990_IN3:
+ case LTC2990_IN4:
+ /* Vx, 305.18uV/LSB */
+ *result = sign_extend32(val, 14) * 30518 / (100 * 1000);
break;
default:
return -EINVAL; /* won't happen, keep compiler happy */
@@ -79,48 +140,117 @@ static ssize_t ltc2990_show_value(struct device *dev,
struct device_attribute *da, char *buf)
{
struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
+ struct ltc2990_data *data = dev_get_drvdata(dev);
int value;
int ret;
- ret = ltc2990_get_value(dev_get_drvdata(dev), attr->index, &value);
+ ret = ltc2990_get_value(data->i2c, attr->index, &value);
if (unlikely(ret < 0))
return ret;
return snprintf(buf, PAGE_SIZE, "%d\n", value);
}
+static umode_t ltc2990_attrs_visible(struct kobject *kobj,
+ struct attribute *a, int n)
+{
+ struct device *dev = container_of(kobj, struct device, kobj);
+ struct ltc2990_data *data = dev_get_drvdata(dev);
+ struct device_attribute *da =
+ container_of(a, struct device_attribute, attr);
+ struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
+
+ int attrs_mask = LTC2990_IN0 | LTC2990_TEMP1 |
+ (ltc2990_attrs_ena_0[data->mode[0]] &
+ ltc2990_attrs_ena_1[data->mode[1]]);
+
+ if (attr->index & attrs_mask)
+ return a->mode;
+
+ return 0;
+}
+
static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, ltc2990_show_value, NULL,
- LTC2990_TINT_MSB);
+ LTC2990_TEMP1);
+static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO, ltc2990_show_value, NULL,
+ LTC2990_TEMP2);
+static SENSOR_DEVICE_ATTR(temp3_input, S_IRUGO, ltc2990_show_value, NULL,
+ LTC2990_TEMP3);
static SENSOR_DEVICE_ATTR(curr1_input, S_IRUGO, ltc2990_show_value, NULL,
- LTC2990_V1_MSB);
+ LTC2990_CURR1);
static SENSOR_DEVICE_ATTR(curr2_input, S_IRUGO, ltc2990_show_value, NULL,
- LTC2990_V3_MSB);
+ LTC2990_CURR2);
static SENSOR_DEVICE_ATTR(in0_input, S_IRUGO, ltc2990_show_value, NULL,
- LTC2990_VCC_MSB);
+ LTC2990_IN0);
+static SENSOR_DEVICE_ATTR(in1_input, S_IRUGO, ltc2990_show_value, NULL,
+ LTC2990_IN1);
+static SENSOR_DEVICE_ATTR(in2_input, S_IRUGO, ltc2990_show_value, NULL,
+ LTC2990_IN2);
+static SENSOR_DEVICE_ATTR(in3_input, S_IRUGO, ltc2990_show_value, NULL,
+ LTC2990_IN3);
+static SENSOR_DEVICE_ATTR(in4_input, S_IRUGO, ltc2990_show_value, NULL,
+ LTC2990_IN4);
static struct attribute *ltc2990_attrs[] = {
&sensor_dev_attr_temp1_input.dev_attr.attr,
+ &sensor_dev_attr_temp2_input.dev_attr.attr,
+ &sensor_dev_attr_temp3_input.dev_attr.attr,
&sensor_dev_attr_curr1_input.dev_attr.attr,
&sensor_dev_attr_curr2_input.dev_attr.attr,
&sensor_dev_attr_in0_input.dev_attr.attr,
+ &sensor_dev_attr_in1_input.dev_attr.attr,
+ &sensor_dev_attr_in2_input.dev_attr.attr,
+ &sensor_dev_attr_in3_input.dev_attr.attr,
+ &sensor_dev_attr_in4_input.dev_attr.attr,
NULL,
};
-ATTRIBUTE_GROUPS(ltc2990);
+
+static const struct attribute_group ltc2990_group = {
+ .attrs = ltc2990_attrs,
+ .is_visible = ltc2990_attrs_visible,
+};
+__ATTRIBUTE_GROUPS(ltc2990);
static int ltc2990_i2c_probe(struct i2c_client *i2c,
const struct i2c_device_id *id)
{
int ret;
struct device *hwmon_dev;
+ struct ltc2990_data *data;
+ struct device_node *of_node = i2c->dev.of_node;
if (!i2c_check_functionality(i2c->adapter, I2C_FUNC_SMBUS_BYTE_DATA |
I2C_FUNC_SMBUS_WORD_DATA))
return -ENODEV;
- /* Setup continuous mode, current monitor */
+ data = devm_kzalloc(&i2c->dev, sizeof(struct ltc2990_data), GFP_KERNEL);
+ if (unlikely(!data))
+ return -ENOMEM;
+
+ data->i2c = i2c;
+
+ if (of_node) {
+ ret = of_property_read_u32_array(of_node, "lltc,meas-mode",
+ data->mode, 2);
+ if (ret < 0)
+ return ret;
+
+ if (data->mode[0] & ~LTC2990_MODE0_MASK ||
+ data->mode[1] & ~LTC2990_MODE1_MASK)
+ return -EINVAL;
+ } else {
+ ret = i2c_smbus_read_byte_data(i2c, LTC2990_CONTROL);
+ if (ret < 0)
+ return ret;
+
+ data->mode[0] = ret >> LTC2990_MODE0_SHIFT & LTC2990_MODE0_MASK;
+ data->mode[1] = ret >> LTC2990_MODE1_SHIFT & LTC2990_MODE1_MASK;
+ }
+
+ /* Setup continuous mode */
ret = i2c_smbus_write_byte_data(i2c, LTC2990_CONTROL,
- LTC2990_CONTROL_MEASURE_ALL |
- LTC2990_CONTROL_MODE_CURRENT);
+ data->mode[0] << LTC2990_MODE0_SHIFT |
+ data->mode[1] << LTC2990_MODE1_SHIFT);
if (ret < 0) {
dev_err(&i2c->dev, "Error: Failed to set control mode.\n");
return ret;
@@ -134,7 +264,7 @@ static int ltc2990_i2c_probe(struct i2c_client *i2c,
hwmon_dev = devm_hwmon_device_register_with_groups(&i2c->dev,
i2c->name,
- i2c,
+ data,
ltc2990_groups);
return PTR_ERR_OR_ZERO(hwmon_dev);
diff --git a/drivers/hwmon/mc13783-adc.c b/drivers/hwmon/mc13783-adc.c
index 960a1db..67860ad 100644
--- a/drivers/hwmon/mc13783-adc.c
+++ b/drivers/hwmon/mc13783-adc.c
@@ -63,6 +63,10 @@ static int mc13783_adc_read(struct device *dev,
if (ret)
return ret;
+ /* ADIN7 subchannels */
+ if (channel >= 16)
+ channel = 7;
+
channel &= 0x7;
*val = (sample[channel % 4] >> (channel > 3 ? 14 : 2)) & 0x3ff;
@@ -111,6 +115,57 @@ static ssize_t mc13783_adc_read_gp(struct device *dev,
return sprintf(buf, "%u\n", val);
}
+static ssize_t mc13783_adc_read_uid(struct device *dev,
+ struct device_attribute *devattr, char *buf)
+{
+ unsigned int val;
+ struct platform_device *pdev = to_platform_device(dev);
+ kernel_ulong_t driver_data = platform_get_device_id(pdev)->driver_data;
+ int ret = mc13783_adc_read(dev, devattr, &val);
+
+ if (ret)
+ return ret;
+
+ if (driver_data & MC13783_ADC_BPDIV2)
+ /* MC13892 have 1/2 divider, input range is [0, 4.800V] */
+ val = DIV_ROUND_CLOSEST(val * 4800, 1024);
+ else
+ /* MC13783 have 0.9 divider, input range is [0, 2.555V] */
+ val = DIV_ROUND_CLOSEST(val * 2555, 1024);
+
+ return sprintf(buf, "%u\n", val);
+}
+
+static ssize_t mc13783_adc_read_temp(struct device *dev,
+ struct device_attribute *devattr, char *buf)
+{
+ unsigned int val;
+ struct platform_device *pdev = to_platform_device(dev);
+ kernel_ulong_t driver_data = platform_get_device_id(pdev)->driver_data;
+ int ret = mc13783_adc_read(dev, devattr, &val);
+
+ if (ret)
+ return ret;
+
+ if (driver_data & MC13783_ADC_BPDIV2) {
+ /*
+ * MC13892:
+ * Die Temperature Read Out Code at 25C 680
+ * Temperature change per LSB +0.4244C
+ */
+ ret = DIV_ROUND_CLOSEST(-2635920 + val * 4244, 10);
+ } else {
+ /*
+ * MC13783:
+ * Die Temperature Read Out Code at 25C 282
+ * Temperature change per LSB -1.14C
+ */
+ ret = 346480 - 1140 * val;
+ }
+
+ return sprintf(buf, "%d\n", ret);
+}
+
static DEVICE_ATTR_RO(name);
static SENSOR_DEVICE_ATTR(in2_input, S_IRUGO, mc13783_adc_read_bp, NULL, 2);
static SENSOR_DEVICE_ATTR(in5_input, S_IRUGO, mc13783_adc_read_gp, NULL, 5);
@@ -124,6 +179,9 @@ static SENSOR_DEVICE_ATTR(in12_input, S_IRUGO, mc13783_adc_read_gp, NULL, 12);
static SENSOR_DEVICE_ATTR(in13_input, S_IRUGO, mc13783_adc_read_gp, NULL, 13);
static SENSOR_DEVICE_ATTR(in14_input, S_IRUGO, mc13783_adc_read_gp, NULL, 14);
static SENSOR_DEVICE_ATTR(in15_input, S_IRUGO, mc13783_adc_read_gp, NULL, 15);
+static SENSOR_DEVICE_ATTR(in16_input, S_IRUGO, mc13783_adc_read_uid, NULL, 16);
+static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO,
+ mc13783_adc_read_temp, NULL, 17);
static struct attribute *mc13783_attr_base[] = {
&dev_attr_name.attr,
@@ -131,6 +189,8 @@ static struct attribute *mc13783_attr_base[] = {
&sensor_dev_attr_in5_input.dev_attr.attr,
&sensor_dev_attr_in6_input.dev_attr.attr,
&sensor_dev_attr_in7_input.dev_attr.attr,
+ &sensor_dev_attr_in16_input.dev_attr.attr,
+ &sensor_dev_attr_temp1_input.dev_attr.attr,
NULL
};
diff --git a/drivers/hwmon/nct6683.c b/drivers/hwmon/nct6683.c
index 8b0bc4f..b0bc77b 100644
--- a/drivers/hwmon/nct6683.c
+++ b/drivers/hwmon/nct6683.c
@@ -1380,8 +1380,8 @@ static int __init nct6683_find(int sioaddr, struct nct6683_sio_data *sio_data)
/* Activate logical device if needed */
val = superio_inb(sioaddr, SIO_REG_ENABLE);
if (!(val & 0x01)) {
- pr_err("EC is disabled\n");
- goto fail;
+ pr_warn("Forcibly enabling EC access. Data may be unusable.\n");
+ superio_outb(sioaddr, SIO_REG_ENABLE, val | 0x01);
}
superio_exit(sioaddr);
diff --git a/drivers/hwmon/scmi-hwmon.c b/drivers/hwmon/scmi-hwmon.c
index 363bf56..91976b6 100644
--- a/drivers/hwmon/scmi-hwmon.c
+++ b/drivers/hwmon/scmi-hwmon.c
@@ -170,7 +170,10 @@ static int scmi_hwmon_probe(struct scmi_device *sdev)
scmi_chip_info.info = ptr_scmi_ci;
chip_info = &scmi_chip_info;
- for (type = 0; type < hwmon_max && nr_count[type]; type++) {
+ for (type = 0; type < hwmon_max; type++) {
+ if (!nr_count[type])
+ continue;
+
scmi_hwmon_add_chan_info(scmi_hwmon_chan, dev, nr_count[type],
type, hwmon_attributes[type]);
*ptr_scmi_ci++ = scmi_hwmon_chan++;
diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index ede3883..634f580 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -733,8 +733,8 @@ static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks)
/* Reset the page to write-back before releasing */
set_memory_wb((unsigned long)win->block[i].bdesc, 1);
#endif
- dma_free_coherent(msc_dev(msc), size, win->block[i].bdesc,
- win->block[i].addr);
+ dma_free_coherent(msc_dev(msc)->parent->parent, size,
+ win->block[i].bdesc, win->block[i].addr);
}
kfree(win);
@@ -769,7 +769,7 @@ static void msc_buffer_win_free(struct msc *msc, struct msc_window *win)
/* Reset the page to write-back before releasing */
set_memory_wb((unsigned long)win->block[i].bdesc, 1);
#endif
- dma_free_coherent(msc_dev(win->msc), PAGE_SIZE,
+ dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE,
win->block[i].bdesc, win->block[i].addr);
}
diff --git a/drivers/hwtracing/stm/core.c b/drivers/hwtracing/stm/core.c
index 05386b7..10bcb5d 100644
--- a/drivers/hwtracing/stm/core.c
+++ b/drivers/hwtracing/stm/core.c
@@ -19,6 +19,7 @@
#include <linux/stm.h>
#include <linux/fs.h>
#include <linux/mm.h>
+#include <linux/vmalloc.h>
#include "stm.h"
#include <uapi/linux/stm.h>
@@ -674,7 +675,7 @@ static void stm_device_release(struct device *dev)
{
struct stm_device *stm = to_stm_device(dev);
- kfree(stm);
+ vfree(stm);
}
int stm_register_device(struct device *parent, struct stm_data *stm_data,
@@ -691,7 +692,7 @@ int stm_register_device(struct device *parent, struct stm_data *stm_data,
return -EINVAL;
nmasters = stm_data->sw_end - stm_data->sw_start + 1;
- stm = kzalloc(sizeof(*stm) + nmasters * sizeof(void *), GFP_KERNEL);
+ stm = vzalloc(sizeof(*stm) + nmasters * sizeof(void *));
if (!stm)
return -ENOMEM;
@@ -744,7 +745,7 @@ int stm_register_device(struct device *parent, struct stm_data *stm_data,
/* matches device_initialize() above */
put_device(&stm->dev);
err_free:
- kfree(stm);
+ vfree(stm);
return err;
}
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index c4865b0..8d21b98 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -707,7 +707,6 @@
config I2C_MT65XX
tristate "MediaTek I2C adapter"
depends on ARCH_MEDIATEK || COMPILE_TEST
- depends on HAS_DMA
help
This selects the MediaTek(R) Integrated Inter Circuit bus driver
for MT65xx and MT81xx.
@@ -885,7 +884,6 @@
config I2C_SH_MOBILE
tristate "SuperH Mobile I2C Controller"
- depends on HAS_DMA
depends on ARCH_SHMOBILE || ARCH_RENESAS || COMPILE_TEST
help
If you say yes to this option, support will be included for the
@@ -1098,7 +1096,6 @@
config I2C_RCAR
tristate "Renesas R-Car I2C Controller"
- depends on HAS_DMA
depends on ARCH_RENESAS || COMPILE_TEST
select I2C_SLAVE
help
diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c
index fd36c39..0cdba29 100644
--- a/drivers/i2c/busses/i2c-designware-master.c
+++ b/drivers/i2c/busses/i2c-designware-master.c
@@ -209,7 +209,10 @@ static void i2c_dw_xfer_init(struct dw_i2c_dev *dev)
i2c_dw_disable_int(dev);
/* Enable the adapter */
- __i2c_dw_enable_and_wait(dev, true);
+ __i2c_dw_enable(dev, true);
+
+ /* Dummy read to avoid the register getting stuck on Bay Trail */
+ dw_readl(dev, DW_IC_ENABLE_STATUS);
/* Clear and enable interrupts */
dw_readl(dev, DW_IC_CLR_INTR);
diff --git a/drivers/i2c/busses/i2c-ocores.c b/drivers/i2c/busses/i2c-ocores.c
index 8c42ca7..45ae3c0 100644
--- a/drivers/i2c/busses/i2c-ocores.c
+++ b/drivers/i2c/busses/i2c-ocores.c
@@ -1,6 +1,6 @@
/*
* i2c-ocores.c: I2C bus driver for OpenCores I2C controller
- * (http://www.opencores.org/projects.cgi/web/i2c/overview).
+ * (https://opencores.org/project/i2c/overview)
*
* Peter Korsgaard <jacmet@sunsite.dk>
*
diff --git a/drivers/i2c/busses/i2c-pmcmsp.c b/drivers/i2c/busses/i2c-pmcmsp.c
index 2aa0e83..dae8ac6 100644
--- a/drivers/i2c/busses/i2c-pmcmsp.c
+++ b/drivers/i2c/busses/i2c-pmcmsp.c
@@ -564,10 +564,10 @@ static int pmcmsptwi_master_xfer(struct i2c_adapter *adap,
* TODO: We could potentially loop and retry in the case
* of MSP_TWI_XFER_TIMEOUT.
*/
- return -1;
+ return -EIO;
}
- return 0;
+ return num;
}
static u32 pmcmsptwi_i2c_func(struct i2c_adapter *adapter)
diff --git a/drivers/i2c/busses/i2c-sprd.c b/drivers/i2c/busses/i2c-sprd.c
index 25fcc3c..4053259 100644
--- a/drivers/i2c/busses/i2c-sprd.c
+++ b/drivers/i2c/busses/i2c-sprd.c
@@ -86,6 +86,7 @@ struct sprd_i2c {
u32 count;
int irq;
int err;
+ bool is_suspended;
};
static void sprd_i2c_set_count(struct sprd_i2c *i2c_dev, u32 count)
@@ -283,6 +284,9 @@ static int sprd_i2c_master_xfer(struct i2c_adapter *i2c_adap,
struct sprd_i2c *i2c_dev = i2c_adap->algo_data;
int im, ret;
+ if (i2c_dev->is_suspended)
+ return -EBUSY;
+
ret = pm_runtime_get_sync(i2c_dev->dev);
if (ret < 0)
return ret;
@@ -364,13 +368,12 @@ static irqreturn_t sprd_i2c_isr_thread(int irq, void *dev_id)
struct sprd_i2c *i2c_dev = dev_id;
struct i2c_msg *msg = i2c_dev->msg;
bool ack = !(readl(i2c_dev->base + I2C_STATUS) & I2C_RX_ACK);
- u32 i2c_count = readl(i2c_dev->base + I2C_COUNT);
u32 i2c_tran;
if (msg->flags & I2C_M_RD)
i2c_tran = i2c_dev->count >= I2C_FIFO_FULL_THLD;
else
- i2c_tran = i2c_count;
+ i2c_tran = i2c_dev->count;
/*
* If we got one ACK from slave when writing data, and we did not
@@ -408,14 +411,13 @@ static irqreturn_t sprd_i2c_isr(int irq, void *dev_id)
{
struct sprd_i2c *i2c_dev = dev_id;
struct i2c_msg *msg = i2c_dev->msg;
- u32 i2c_count = readl(i2c_dev->base + I2C_COUNT);
bool ack = !(readl(i2c_dev->base + I2C_STATUS) & I2C_RX_ACK);
u32 i2c_tran;
if (msg->flags & I2C_M_RD)
i2c_tran = i2c_dev->count >= I2C_FIFO_FULL_THLD;
else
- i2c_tran = i2c_count;
+ i2c_tran = i2c_dev->count;
/*
* If we did not get one ACK from slave when writing data, then we
@@ -586,11 +588,23 @@ static int sprd_i2c_remove(struct platform_device *pdev)
static int __maybe_unused sprd_i2c_suspend_noirq(struct device *pdev)
{
+ struct sprd_i2c *i2c_dev = dev_get_drvdata(pdev);
+
+ i2c_lock_adapter(&i2c_dev->adap);
+ i2c_dev->is_suspended = true;
+ i2c_unlock_adapter(&i2c_dev->adap);
+
return pm_runtime_force_suspend(pdev);
}
static int __maybe_unused sprd_i2c_resume_noirq(struct device *pdev)
{
+ struct sprd_i2c *i2c_dev = dev_get_drvdata(pdev);
+
+ i2c_lock_adapter(&i2c_dev->adap);
+ i2c_dev->is_suspended = false;
+ i2c_unlock_adapter(&i2c_dev->adap);
+
return pm_runtime_force_resume(pdev);
}
diff --git a/drivers/i2c/busses/i2c-viperboard.c b/drivers/i2c/busses/i2c-viperboard.c
index e4be86b..7235c73 100644
--- a/drivers/i2c/busses/i2c-viperboard.c
+++ b/drivers/i2c/busses/i2c-viperboard.c
@@ -337,7 +337,7 @@ static int vprbrd_i2c_xfer(struct i2c_adapter *i2c, struct i2c_msg *msgs,
}
mutex_unlock(&vb->lock);
}
- return 0;
+ return num;
error:
mutex_unlock(&vb->lock);
return error;
diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c
index a9126b3..7c3b474 100644
--- a/drivers/i2c/i2c-core-acpi.c
+++ b/drivers/i2c/i2c-core-acpi.c
@@ -445,10 +445,17 @@ static int acpi_gsb_i2c_read_bytes(struct i2c_client *client,
msgs[1].buf = buffer;
ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs));
- if (ret < 0)
- dev_err(&client->adapter->dev, "i2c read failed\n");
- else
+ if (ret < 0) {
+ /* Getting a NACK is unfortunately normal with some DSTDs */
+ if (ret == -EREMOTEIO)
+ dev_dbg(&client->adapter->dev, "i2c read %d bytes from client@%#x starting at reg %#x failed, error: %d\n",
+ data_len, client->addr, cmd, ret);
+ else
+ dev_err(&client->adapter->dev, "i2c read %d bytes from client@%#x starting at reg %#x failed, error: %d\n",
+ data_len, client->addr, cmd, ret);
+ } else {
memcpy(data, buffer, data_len);
+ }
kfree(buffer);
return ret;
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 1ba40bb..a17f46a 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -363,7 +363,7 @@ static int i2c_device_probe(struct device *dev)
goto err_clear_wakeup_irq;
status = dev_pm_domain_attach(&client->dev, true);
- if (status == -EPROBE_DEFER)
+ if (status)
goto err_clear_wakeup_irq;
/*
diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c
index 036a03f..1667b6e 100644
--- a/drivers/i2c/i2c-dev.c
+++ b/drivers/i2c/i2c-dev.c
@@ -280,7 +280,7 @@ static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client,
*/
if (msgs[i].flags & I2C_M_RECV_LEN) {
if (!(msgs[i].flags & I2C_M_RD) ||
- msgs[i].buf[0] < 1 ||
+ msgs[i].len < 1 || msgs[i].buf[0] < 1 ||
msgs[i].len < msgs[i].buf[0] +
I2C_SMBUS_BLOCK_MAX) {
res = -EINVAL;
diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c
index 0e6bc63..8b2b72b 100644
--- a/drivers/ide/ide-atapi.c
+++ b/drivers/ide/ide-atapi.c
@@ -92,7 +92,7 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk,
struct request *rq;
int error;
- rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+ rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, 0);
ide_req(rq)->type = ATA_PRIV_MISC;
rq->special = (char *)pc;
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 5a8e8e3..5f17838 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -437,7 +437,7 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
bool delay = false;
rq = blk_get_request(drive->queue,
- write ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, __GFP_RECLAIM);
+ write ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
memcpy(scsi_req(rq)->cmd, cmd, BLK_MAX_CDB);
ide_req(rq)->type = ATA_PRIV_PC;
rq->rq_flags |= rq_flags;
@@ -1426,21 +1426,8 @@ static int idecd_capacity_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int idecd_capacity_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, idecd_capacity_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations idecd_capacity_proc_fops = {
- .owner = THIS_MODULE,
- .open = idecd_capacity_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static ide_proc_entry_t idecd_proc[] = {
- { "capacity", S_IFREG|S_IRUGO, &idecd_capacity_proc_fops },
+ { "capacity", S_IFREG|S_IRUGO, idecd_capacity_proc_show },
{}
};
diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c
index 2acca12..b132240 100644
--- a/drivers/ide/ide-cd_ioctl.c
+++ b/drivers/ide/ide-cd_ioctl.c
@@ -304,7 +304,7 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
struct request *rq;
int ret;
- rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+ rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, 0);
ide_req(rq)->type = ATA_PRIV_MISC;
rq->rq_flags = RQF_QUIET;
blk_execute_rq(drive->queue, cd->disk, rq, 0);
diff --git a/drivers/ide/ide-devsets.c b/drivers/ide/ide-devsets.c
index 4e20747..f4f8afd 100644
--- a/drivers/ide/ide-devsets.c
+++ b/drivers/ide/ide-devsets.c
@@ -166,7 +166,7 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting,
if (!(setting->flags & DS_SYNC))
return setting->set(drive, arg);
- rq = blk_get_request(q, REQ_OP_DRV_IN, __GFP_RECLAIM);
+ rq = blk_get_request(q, REQ_OP_DRV_IN, 0);
ide_req(rq)->type = ATA_PRIV_MISC;
scsi_req(rq)->cmd_len = 5;
scsi_req(rq)->cmd[0] = REQ_DEVSET_EXEC;
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index f1a7c58..e3b4e65 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -478,7 +478,7 @@ static int set_multcount(ide_drive_t *drive, int arg)
if (drive->special_flags & IDE_SFLAG_SET_MULTMODE)
return -EBUSY;
- rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+ rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, 0);
ide_req(rq)->type = ATA_PRIV_TASKFILE;
drive->mult_req = arg;
diff --git a/drivers/ide/ide-disk_proc.c b/drivers/ide/ide-disk_proc.c
index 82a36ce..95d239b 100644
--- a/drivers/ide/ide-disk_proc.c
+++ b/drivers/ide/ide-disk_proc.c
@@ -52,19 +52,6 @@ static int idedisk_cache_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int idedisk_cache_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, idedisk_cache_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations idedisk_cache_proc_fops = {
- .owner = THIS_MODULE,
- .open = idedisk_cache_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int idedisk_capacity_proc_show(struct seq_file *m, void *v)
{
ide_drive_t*drive = (ide_drive_t *)m->private;
@@ -73,19 +60,6 @@ static int idedisk_capacity_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int idedisk_capacity_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, idedisk_capacity_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations idedisk_capacity_proc_fops = {
- .owner = THIS_MODULE,
- .open = idedisk_capacity_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __idedisk_proc_show(struct seq_file *m, ide_drive_t *drive, u8 sub_cmd)
{
u8 *buf;
@@ -114,43 +88,17 @@ static int idedisk_sv_proc_show(struct seq_file *m, void *v)
return __idedisk_proc_show(m, m->private, ATA_SMART_READ_VALUES);
}
-static int idedisk_sv_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, idedisk_sv_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations idedisk_sv_proc_fops = {
- .owner = THIS_MODULE,
- .open = idedisk_sv_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int idedisk_st_proc_show(struct seq_file *m, void *v)
{
return __idedisk_proc_show(m, m->private, ATA_SMART_READ_THRESHOLDS);
}
-static int idedisk_st_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, idedisk_st_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations idedisk_st_proc_fops = {
- .owner = THIS_MODULE,
- .open = idedisk_st_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
ide_proc_entry_t ide_disk_proc[] = {
- { "cache", S_IFREG|S_IRUGO, &idedisk_cache_proc_fops },
- { "capacity", S_IFREG|S_IRUGO, &idedisk_capacity_proc_fops },
- { "geometry", S_IFREG|S_IRUGO, &ide_geometry_proc_fops },
- { "smart_values", S_IFREG|S_IRUSR, &idedisk_sv_proc_fops },
- { "smart_thresholds", S_IFREG|S_IRUSR, &idedisk_st_proc_fops },
+ { "cache", S_IFREG|S_IRUGO, idedisk_cache_proc_show },
+ { "capacity", S_IFREG|S_IRUGO, idedisk_capacity_proc_show },
+ { "geometry", S_IFREG|S_IRUGO, ide_geometry_proc_show },
+ { "smart_values", S_IFREG|S_IRUSR, idedisk_sv_proc_show },
+ { "smart_thresholds", S_IFREG|S_IRUSR, idedisk_st_proc_show },
{}
};
diff --git a/drivers/ide/ide-dma.c b/drivers/ide/ide-dma.c
index 54d4d78..6f34465 100644
--- a/drivers/ide/ide-dma.c
+++ b/drivers/ide/ide-dma.c
@@ -180,7 +180,6 @@ EXPORT_SYMBOL_GPL(ide_dma_unmap_sg);
void ide_dma_off_quietly(ide_drive_t *drive)
{
drive->dev_flags &= ~IDE_DFLAG_USING_DMA;
- ide_toggle_bounce(drive, 0);
drive->hwif->dma_ops->dma_host_set(drive, 0);
}
@@ -211,7 +210,6 @@ EXPORT_SYMBOL(ide_dma_off);
void ide_dma_on(ide_drive_t *drive)
{
drive->dev_flags |= IDE_DFLAG_USING_DMA;
- ide_toggle_bounce(drive, 1);
drive->hwif->dma_ops->dma_host_set(drive, 1);
}
diff --git a/drivers/ide/ide-floppy_proc.c b/drivers/ide/ide-floppy_proc.c
index 471457e..7f697ddb 100644
--- a/drivers/ide/ide-floppy_proc.c
+++ b/drivers/ide/ide-floppy_proc.c
@@ -14,22 +14,9 @@ static int idefloppy_capacity_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int idefloppy_capacity_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, idefloppy_capacity_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations idefloppy_capacity_proc_fops = {
- .owner = THIS_MODULE,
- .open = idefloppy_capacity_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
ide_proc_entry_t ide_floppy_proc[] = {
- { "capacity", S_IFREG|S_IRUGO, &idefloppy_capacity_proc_fops },
- { "geometry", S_IFREG|S_IRUGO, &ide_geometry_proc_fops },
+ { "capacity", S_IFREG|S_IRUGO, idefloppy_capacity_proc_show },
+ { "geometry", S_IFREG|S_IRUGO, ide_geometry_proc_show },
{}
};
diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c
index 3661abb..af5119a 100644
--- a/drivers/ide/ide-ioctls.c
+++ b/drivers/ide/ide-ioctls.c
@@ -125,7 +125,7 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg)
if (NULL == (void *) arg) {
struct request *rq;
- rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+ rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, 0);
ide_req(rq)->type = ATA_PRIV_TASKFILE;
blk_execute_rq(drive->queue, NULL, rq, 0);
err = scsi_req(rq)->result ? -EIO : 0;
@@ -222,7 +222,7 @@ static int generic_drive_reset(ide_drive_t *drive)
struct request *rq;
int ret = 0;
- rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+ rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, 0);
ide_req(rq)->type = ATA_PRIV_MISC;
scsi_req(rq)->cmd_len = 1;
scsi_req(rq)->cmd[0] = REQ_DRIVE_RESET;
diff --git a/drivers/ide/ide-lib.c b/drivers/ide/ide-lib.c
index e1180fa..78cb79e 100644
--- a/drivers/ide/ide-lib.c
+++ b/drivers/ide/ide-lib.c
@@ -6,32 +6,6 @@
#include <linux/ide.h>
#include <linux/bitops.h>
-/**
- * ide_toggle_bounce - handle bounce buffering
- * @drive: drive to update
- * @on: on/off boolean
- *
- * Enable or disable bounce buffering for the device. Drives move
- * between PIO and DMA and that changes the rules we need.
- */
-
-void ide_toggle_bounce(ide_drive_t *drive, int on)
-{
- u64 addr = BLK_BOUNCE_HIGH; /* dma64_addr_t */
-
- if (!PCI_DMA_BUS_IS_PHYS) {
- addr = BLK_BOUNCE_ANY;
- } else if (on && drive->media == ide_disk) {
- struct device *dev = drive->hwif->dev;
-
- if (dev && dev->dma_mask)
- addr = *dev->dma_mask;
- }
-
- if (drive->queue)
- blk_queue_bounce_limit(drive->queue, addr);
-}
-
u64 ide_get_lba_addr(struct ide_cmd *cmd, int lba48)
{
struct ide_taskfile *tf = &cmd->tf;
diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c
index 6465bcc..622f0ed 100644
--- a/drivers/ide/ide-park.c
+++ b/drivers/ide/ide-park.c
@@ -32,7 +32,7 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
}
spin_unlock_irq(&hwif->lock);
- rq = blk_get_request(q, REQ_OP_DRV_IN, __GFP_RECLAIM);
+ rq = blk_get_request(q, REQ_OP_DRV_IN, 0);
scsi_req(rq)->cmd[0] = REQ_PARK_HEADS;
scsi_req(rq)->cmd_len = 1;
ide_req(rq)->type = ATA_PRIV_MISC;
@@ -47,7 +47,7 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
* Make sure that *some* command is sent to the drive after the
* timeout has expired, so power management will be reenabled.
*/
- rq = blk_get_request(q, REQ_OP_DRV_IN, GFP_NOWAIT);
+ rq = blk_get_request(q, REQ_OP_DRV_IN, BLK_MQ_REQ_NOWAIT);
if (IS_ERR(rq))
goto out;
diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c
index ad8a125..59217aa 100644
--- a/drivers/ide/ide-pm.c
+++ b/drivers/ide/ide-pm.c
@@ -19,7 +19,7 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
}
memset(&rqpm, 0, sizeof(rqpm));
- rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+ rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, 0);
ide_req(rq)->type = ATA_PRIV_PM_SUSPEND;
rq->special = &rqpm;
rqpm.pm_step = IDE_PM_START_SUSPEND;
@@ -90,8 +90,7 @@ int generic_ide_resume(struct device *dev)
}
memset(&rqpm, 0, sizeof(rqpm));
- rq = blk_get_request_flags(drive->queue, REQ_OP_DRV_IN,
- BLK_MQ_REQ_PREEMPT);
+ rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, BLK_MQ_REQ_PREEMPT);
ide_req(rq)->type = ATA_PRIV_PM_RESUME;
rq->special = &rqpm;
rqpm.pm_step = IDE_PM_START_RESUME;
diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c
index 2019e66e..56d7bc2 100644
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -796,8 +796,7 @@ static int ide_init_queue(ide_drive_t *drive)
* This will be fixed once we teach pci_map_sg() about our boundary
* requirements, hopefully soon. *FIXME*
*/
- if (!PCI_DMA_BUS_IS_PHYS)
- max_sg_entries >>= 1;
+ max_sg_entries >>= 1;
#endif /* CONFIG_PCI */
blk_queue_max_segments(q, max_sg_entries);
@@ -805,9 +804,6 @@ static int ide_init_queue(ide_drive_t *drive)
/* assign drive queue */
drive->queue = q;
- /* needs drive->queue to be set */
- ide_toggle_bounce(drive, 1);
-
return 0;
}
diff --git a/drivers/ide/ide-proc.c b/drivers/ide/ide-proc.c
index 863db44..45c9974 100644
--- a/drivers/ide/ide-proc.c
+++ b/drivers/ide/ide-proc.c
@@ -56,19 +56,6 @@ static int ide_imodel_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int ide_imodel_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ide_imodel_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations ide_imodel_proc_fops = {
- .owner = THIS_MODULE,
- .open = ide_imodel_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int ide_mate_proc_show(struct seq_file *m, void *v)
{
ide_hwif_t *hwif = (ide_hwif_t *) m->private;
@@ -80,19 +67,6 @@ static int ide_mate_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int ide_mate_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ide_mate_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations ide_mate_proc_fops = {
- .owner = THIS_MODULE,
- .open = ide_mate_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int ide_channel_proc_show(struct seq_file *m, void *v)
{
ide_hwif_t *hwif = (ide_hwif_t *) m->private;
@@ -101,19 +75,6 @@ static int ide_channel_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int ide_channel_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ide_channel_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations ide_channel_proc_fops = {
- .owner = THIS_MODULE,
- .open = ide_channel_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int ide_identify_proc_show(struct seq_file *m, void *v)
{
ide_drive_t *drive = (ide_drive_t *)m->private;
@@ -141,19 +102,6 @@ static int ide_identify_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int ide_identify_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ide_identify_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations ide_identify_proc_fops = {
- .owner = THIS_MODULE,
- .open = ide_identify_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/**
* ide_find_setting - find a specific setting
* @st: setting table pointer
@@ -441,27 +389,14 @@ static const struct file_operations ide_settings_proc_fops = {
.write = ide_settings_proc_write,
};
-static int ide_capacity_proc_show(struct seq_file *m, void *v)
+int ide_capacity_proc_show(struct seq_file *m, void *v)
{
seq_printf(m, "%llu\n", (long long)0x7fffffff);
return 0;
}
+EXPORT_SYMBOL_GPL(ide_capacity_proc_show);
-static int ide_capacity_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ide_capacity_proc_show, NULL);
-}
-
-const struct file_operations ide_capacity_proc_fops = {
- .owner = THIS_MODULE,
- .open = ide_capacity_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-EXPORT_SYMBOL_GPL(ide_capacity_proc_fops);
-
-static int ide_geometry_proc_show(struct seq_file *m, void *v)
+int ide_geometry_proc_show(struct seq_file *m, void *v)
{
ide_drive_t *drive = (ide_drive_t *) m->private;
@@ -471,20 +406,7 @@ static int ide_geometry_proc_show(struct seq_file *m, void *v)
drive->bios_cyl, drive->bios_head, drive->bios_sect);
return 0;
}
-
-static int ide_geometry_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ide_geometry_proc_show, PDE_DATA(inode));
-}
-
-const struct file_operations ide_geometry_proc_fops = {
- .owner = THIS_MODULE,
- .open = ide_geometry_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-EXPORT_SYMBOL(ide_geometry_proc_fops);
+EXPORT_SYMBOL(ide_geometry_proc_show);
static int ide_dmodel_proc_show(struct seq_file *seq, void *v)
{
@@ -495,19 +417,6 @@ static int ide_dmodel_proc_show(struct seq_file *seq, void *v)
return 0;
}
-static int ide_dmodel_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ide_dmodel_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations ide_dmodel_proc_fops = {
- .owner = THIS_MODULE,
- .open = ide_dmodel_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int ide_driver_proc_show(struct seq_file *m, void *v)
{
ide_drive_t *drive = (ide_drive_t *)m->private;
@@ -523,65 +432,6 @@ static int ide_driver_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int ide_driver_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ide_driver_proc_show, PDE_DATA(inode));
-}
-
-static int ide_replace_subdriver(ide_drive_t *drive, const char *driver)
-{
- struct device *dev = &drive->gendev;
- int ret = 1;
- int err;
-
- device_release_driver(dev);
- /* FIXME: device can still be in use by previous driver */
- strlcpy(drive->driver_req, driver, sizeof(drive->driver_req));
- err = device_attach(dev);
- if (err < 0)
- printk(KERN_WARNING "IDE: %s: device_attach error: %d\n",
- __func__, err);
- drive->driver_req[0] = 0;
- if (dev->driver == NULL) {
- err = device_attach(dev);
- if (err < 0)
- printk(KERN_WARNING
- "IDE: %s: device_attach(2) error: %d\n",
- __func__, err);
- }
- if (dev->driver && !strcmp(dev->driver->name, driver))
- ret = 0;
-
- return ret;
-}
-
-static ssize_t ide_driver_proc_write(struct file *file, const char __user *buffer,
- size_t count, loff_t *pos)
-{
- ide_drive_t *drive = PDE_DATA(file_inode(file));
- char name[32];
-
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
- if (count > 31)
- count = 31;
- if (copy_from_user(name, buffer, count))
- return -EFAULT;
- name[count] = '\0';
- if (ide_replace_subdriver(drive, name))
- return -EINVAL;
- return count;
-}
-
-static const struct file_operations ide_driver_proc_fops = {
- .owner = THIS_MODULE,
- .open = ide_driver_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
- .write = ide_driver_proc_write,
-};
-
static int ide_media_proc_show(struct seq_file *m, void *v)
{
ide_drive_t *drive = (ide_drive_t *) m->private;
@@ -613,11 +463,10 @@ static const struct file_operations ide_media_proc_fops = {
};
static ide_proc_entry_t generic_drive_entries[] = {
- { "driver", S_IFREG|S_IRUGO, &ide_driver_proc_fops },
- { "identify", S_IFREG|S_IRUSR, &ide_identify_proc_fops},
- { "media", S_IFREG|S_IRUGO, &ide_media_proc_fops },
- { "model", S_IFREG|S_IRUGO, &ide_dmodel_proc_fops },
- { "settings", S_IFREG|S_IRUSR|S_IWUSR, &ide_settings_proc_fops},
+ { "driver", S_IFREG|S_IRUGO, ide_driver_proc_show },
+ { "identify", S_IFREG|S_IRUSR, ide_identify_proc_show },
+ { "media", S_IFREG|S_IRUGO, ide_media_proc_show },
+ { "model", S_IFREG|S_IRUGO, ide_dmodel_proc_show },
{}
};
@@ -628,7 +477,7 @@ static void ide_add_proc_entries(struct proc_dir_entry *dir, ide_proc_entry_t *p
if (!dir || !p)
return;
while (p->name != NULL) {
- ent = proc_create_data(p->name, p->mode, dir, p->proc_fops, data);
+ ent = proc_create_single_data(p->name, p->mode, dir, p->show, data);
if (!ent) return;
p++;
}
@@ -693,8 +542,12 @@ void ide_proc_port_register_devices(ide_hwif_t *hwif)
continue;
drive->proc = proc_mkdir(drive->name, parent);
- if (drive->proc)
+ if (drive->proc) {
ide_add_proc_entries(drive->proc, generic_drive_entries, drive);
+ proc_create_data("setting", S_IFREG|S_IRUSR|S_IWUSR,
+ drive->proc, &ide_settings_proc_fops,
+ drive);
+ }
sprintf(name, "ide%d/%s", (drive->name[2]-'a')/2, drive->name);
ent = proc_symlink(drive->name, proc_ide_root, name);
if (!ent) return;
@@ -704,6 +557,7 @@ void ide_proc_port_register_devices(ide_hwif_t *hwif)
void ide_proc_unregister_device(ide_drive_t *drive)
{
if (drive->proc) {
+ remove_proc_entry("settings", drive->proc);
ide_remove_proc_entries(drive->proc, generic_drive_entries);
remove_proc_entry(drive->name, proc_ide_root);
remove_proc_entry(drive->name, drive->hwif->proc);
@@ -712,9 +566,9 @@ void ide_proc_unregister_device(ide_drive_t *drive)
}
static ide_proc_entry_t hwif_entries[] = {
- { "channel", S_IFREG|S_IRUGO, &ide_channel_proc_fops },
- { "mate", S_IFREG|S_IRUGO, &ide_mate_proc_fops },
- { "model", S_IFREG|S_IRUGO, &ide_imodel_proc_fops },
+ { "channel", S_IFREG|S_IRUGO, ide_channel_proc_show },
+ { "mate", S_IFREG|S_IRUGO, ide_mate_proc_show },
+ { "model", S_IFREG|S_IRUGO, ide_imodel_proc_show },
{}
};
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index fd57e8c..aee7b46 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -854,7 +854,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
BUG_ON(cmd != REQ_IDETAPE_READ && cmd != REQ_IDETAPE_WRITE);
BUG_ON(size < 0 || size % tape->blk_size);
- rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+ rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, 0);
ide_req(rq)->type = ATA_PRIV_MISC;
scsi_req(rq)->cmd[13] = cmd;
rq->rq_disk = tape->disk;
@@ -862,7 +862,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
if (size) {
ret = blk_rq_map_kern(drive->queue, rq, tape->buf, size,
- __GFP_RECLAIM);
+ GFP_NOIO);
if (ret)
goto out_put;
}
@@ -1847,22 +1847,9 @@ static int idetape_name_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int idetape_name_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, idetape_name_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations idetape_name_proc_fops = {
- .owner = THIS_MODULE,
- .open = idetape_name_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static ide_proc_entry_t idetape_proc[] = {
- { "capacity", S_IFREG|S_IRUGO, &ide_capacity_proc_fops },
- { "name", S_IFREG|S_IRUGO, &idetape_name_proc_fops },
+ { "capacity", S_IFREG|S_IRUGO, ide_capacity_proc_show },
+ { "name", S_IFREG|S_IRUGO, idetape_name_proc_show },
{}
};
diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c
index abe0822..c034cd9 100644
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -431,7 +431,7 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf,
rq = blk_get_request(drive->queue,
(cmd->tf_flags & IDE_TFLAG_WRITE) ?
- REQ_OP_DRV_OUT : REQ_OP_DRV_IN, __GFP_RECLAIM);
+ REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
ide_req(rq)->type = ATA_PRIV_TASKFILE;
/*
@@ -442,7 +442,7 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf,
*/
if (nsect) {
error = blk_rq_map_kern(drive->queue, rq, buf,
- nsect * SECTOR_SIZE, __GFP_RECLAIM);
+ nsect * SECTOR_SIZE, GFP_NOIO);
if (error)
goto put_req;
}
diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 15606f2..9da7907 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -158,6 +158,7 @@
depends on ARCH_AT91 || COMPILE_TEST
depends on HAS_IOMEM
depends on HAS_DMA
+ select IIO_BUFFER
select IIO_TRIGGERED_BUFFER
help
Say yes here to build support for Atmel SAMA5D2 ADC which is
diff --git a/drivers/iio/adc/ad7793.c b/drivers/iio/adc/ad7793.c
index 801afb6..d4bbe5b 100644
--- a/drivers/iio/adc/ad7793.c
+++ b/drivers/iio/adc/ad7793.c
@@ -348,55 +348,6 @@ static const u16 ad7793_sample_freq_avail[16] = {0, 470, 242, 123, 62, 50, 39,
static const u16 ad7797_sample_freq_avail[16] = {0, 0, 0, 123, 62, 50, 0,
33, 0, 17, 16, 12, 10, 8, 6, 4};
-static ssize_t ad7793_read_frequency(struct device *dev,
- struct device_attribute *attr,
- char *buf)
-{
- struct iio_dev *indio_dev = dev_to_iio_dev(dev);
- struct ad7793_state *st = iio_priv(indio_dev);
-
- return sprintf(buf, "%d\n",
- st->chip_info->sample_freq_avail[AD7793_MODE_RATE(st->mode)]);
-}
-
-static ssize_t ad7793_write_frequency(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t len)
-{
- struct iio_dev *indio_dev = dev_to_iio_dev(dev);
- struct ad7793_state *st = iio_priv(indio_dev);
- long lval;
- int i, ret;
-
- ret = kstrtol(buf, 10, &lval);
- if (ret)
- return ret;
-
- if (lval == 0)
- return -EINVAL;
-
- for (i = 0; i < 16; i++)
- if (lval == st->chip_info->sample_freq_avail[i])
- break;
- if (i == 16)
- return -EINVAL;
-
- ret = iio_device_claim_direct_mode(indio_dev);
- if (ret)
- return ret;
- st->mode &= ~AD7793_MODE_RATE(-1);
- st->mode |= AD7793_MODE_RATE(i);
- ad_sd_write_reg(&st->sd, AD7793_REG_MODE, sizeof(st->mode), st->mode);
- iio_device_release_direct_mode(indio_dev);
-
- return len;
-}
-
-static IIO_DEV_ATTR_SAMP_FREQ(S_IWUSR | S_IRUGO,
- ad7793_read_frequency,
- ad7793_write_frequency);
-
static IIO_CONST_ATTR_SAMP_FREQ_AVAIL(
"470 242 123 62 50 39 33 19 17 16 12 10 8 6 4");
@@ -424,7 +375,6 @@ static IIO_DEVICE_ATTR_NAMED(in_m_in_scale_available,
ad7793_show_scale_available, NULL, 0);
static struct attribute *ad7793_attributes[] = {
- &iio_dev_attr_sampling_frequency.dev_attr.attr,
&iio_const_attr_sampling_frequency_available.dev_attr.attr,
&iio_dev_attr_in_m_in_scale_available.dev_attr.attr,
NULL
@@ -435,7 +385,6 @@ static const struct attribute_group ad7793_attribute_group = {
};
static struct attribute *ad7797_attributes[] = {
- &iio_dev_attr_sampling_frequency.dev_attr.attr,
&iio_const_attr_sampling_frequency_available_ad7797.dev_attr.attr,
NULL
};
@@ -505,6 +454,10 @@ static int ad7793_read_raw(struct iio_dev *indio_dev,
*val -= offset;
}
return IIO_VAL_INT;
+ case IIO_CHAN_INFO_SAMP_FREQ:
+ *val = st->chip_info
+ ->sample_freq_avail[AD7793_MODE_RATE(st->mode)];
+ return IIO_VAL_INT;
}
return -EINVAL;
}
@@ -542,6 +495,26 @@ static int ad7793_write_raw(struct iio_dev *indio_dev,
break;
}
break;
+ case IIO_CHAN_INFO_SAMP_FREQ:
+ if (!val) {
+ ret = -EINVAL;
+ break;
+ }
+
+ for (i = 0; i < 16; i++)
+ if (val == st->chip_info->sample_freq_avail[i])
+ break;
+
+ if (i == 16) {
+ ret = -EINVAL;
+ break;
+ }
+
+ st->mode &= ~AD7793_MODE_RATE(-1);
+ st->mode |= AD7793_MODE_RATE(i);
+ ad_sd_write_reg(&st->sd, AD7793_REG_MODE, sizeof(st->mode),
+ st->mode);
+ break;
default:
ret = -EINVAL;
}
diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c
index 4eff835..8729d65 100644
--- a/drivers/iio/adc/at91-sama5d2_adc.c
+++ b/drivers/iio/adc/at91-sama5d2_adc.c
@@ -333,6 +333,27 @@ static const struct iio_chan_spec at91_adc_channels[] = {
+ AT91_SAMA5D2_DIFF_CHAN_CNT + 1),
};
+static int at91_adc_chan_xlate(struct iio_dev *indio_dev, int chan)
+{
+ int i;
+
+ for (i = 0; i < indio_dev->num_channels; i++) {
+ if (indio_dev->channels[i].scan_index == chan)
+ return i;
+ }
+ return -EINVAL;
+}
+
+static inline struct iio_chan_spec const *
+at91_adc_chan_get(struct iio_dev *indio_dev, int chan)
+{
+ int index = at91_adc_chan_xlate(indio_dev, chan);
+
+ if (index < 0)
+ return NULL;
+ return indio_dev->channels + index;
+}
+
static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state)
{
struct iio_dev *indio = iio_trigger_get_drvdata(trig);
@@ -350,8 +371,10 @@ static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state)
at91_adc_writel(st, AT91_SAMA5D2_TRGR, status);
for_each_set_bit(bit, indio->active_scan_mask, indio->num_channels) {
- struct iio_chan_spec const *chan = indio->channels + bit;
+ struct iio_chan_spec const *chan = at91_adc_chan_get(indio, bit);
+ if (!chan)
+ continue;
if (state) {
at91_adc_writel(st, AT91_SAMA5D2_CHER,
BIT(chan->channel));
@@ -448,7 +471,11 @@ static int at91_adc_dma_start(struct iio_dev *indio_dev)
for_each_set_bit(bit, indio_dev->active_scan_mask,
indio_dev->num_channels) {
- struct iio_chan_spec const *chan = indio_dev->channels + bit;
+ struct iio_chan_spec const *chan =
+ at91_adc_chan_get(indio_dev, bit);
+
+ if (!chan)
+ continue;
st->dma_st.rx_buf_sz += chan->scan_type.storagebits / 8;
}
@@ -526,8 +553,11 @@ static int at91_adc_buffer_predisable(struct iio_dev *indio_dev)
*/
for_each_set_bit(bit, indio_dev->active_scan_mask,
indio_dev->num_channels) {
- struct iio_chan_spec const *chan = indio_dev->channels + bit;
+ struct iio_chan_spec const *chan =
+ at91_adc_chan_get(indio_dev, bit);
+ if (!chan)
+ continue;
if (st->dma_st.dma_chan)
at91_adc_readl(st, chan->address);
}
@@ -587,8 +617,11 @@ static void at91_adc_trigger_handler_nodma(struct iio_dev *indio_dev,
for_each_set_bit(bit, indio_dev->active_scan_mask,
indio_dev->num_channels) {
- struct iio_chan_spec const *chan = indio_dev->channels + bit;
+ struct iio_chan_spec const *chan =
+ at91_adc_chan_get(indio_dev, bit);
+ if (!chan)
+ continue;
st->buffer[i] = at91_adc_readl(st, chan->address);
i++;
}
diff --git a/drivers/iio/adc/stm32-dfsdm-adc.c b/drivers/iio/adc/stm32-dfsdm-adc.c
index 01422d1..b28a716 100644
--- a/drivers/iio/adc/stm32-dfsdm-adc.c
+++ b/drivers/iio/adc/stm32-dfsdm-adc.c
@@ -144,6 +144,7 @@ static int stm32_dfsdm_set_osrs(struct stm32_dfsdm_filter *fl,
* Leave as soon as if exact resolution if reached.
* Otherwise the higher resolution below 32 bits is kept.
*/
+ fl->res = 0;
for (fosr = 1; fosr <= DFSDM_MAX_FL_OVERSAMPLING; fosr++) {
for (iosr = 1; iosr <= DFSDM_MAX_INT_OVERSAMPLING; iosr++) {
if (fast)
@@ -193,7 +194,7 @@ static int stm32_dfsdm_set_osrs(struct stm32_dfsdm_filter *fl,
}
}
- if (!fl->fosr)
+ if (!fl->res)
return -EINVAL;
return 0;
@@ -770,7 +771,7 @@ static int stm32_dfsdm_write_raw(struct iio_dev *indio_dev,
struct stm32_dfsdm_adc *adc = iio_priv(indio_dev);
struct stm32_dfsdm_filter *fl = &adc->dfsdm->fl_list[adc->fl_id];
struct stm32_dfsdm_channel *ch = &adc->dfsdm->ch_list[chan->channel];
- unsigned int spi_freq = adc->spi_freq;
+ unsigned int spi_freq;
int ret = -EINVAL;
switch (mask) {
@@ -784,8 +785,18 @@ static int stm32_dfsdm_write_raw(struct iio_dev *indio_dev,
case IIO_CHAN_INFO_SAMP_FREQ:
if (!val)
return -EINVAL;
- if (ch->src != DFSDM_CHANNEL_SPI_CLOCK_EXTERNAL)
+
+ switch (ch->src) {
+ case DFSDM_CHANNEL_SPI_CLOCK_INTERNAL:
spi_freq = adc->dfsdm->spi_master_freq;
+ break;
+ case DFSDM_CHANNEL_SPI_CLOCK_INTERNAL_DIV2_FALLING:
+ case DFSDM_CHANNEL_SPI_CLOCK_INTERNAL_DIV2_RISING:
+ spi_freq = adc->dfsdm->spi_master_freq / 2;
+ break;
+ default:
+ spi_freq = adc->spi_freq;
+ }
if (spi_freq % val)
dev_warn(&indio_dev->dev,
diff --git a/drivers/iio/buffer/industrialio-buffer-dma.c b/drivers/iio/buffer/industrialio-buffer-dma.c
index 05e0c35..b32bf57 100644
--- a/drivers/iio/buffer/industrialio-buffer-dma.c
+++ b/drivers/iio/buffer/industrialio-buffer-dma.c
@@ -587,7 +587,7 @@ EXPORT_SYMBOL_GPL(iio_dma_buffer_set_bytes_per_datum);
* Should be used as the set_length callback for iio_buffer_access_ops
* struct for DMA buffers.
*/
-int iio_dma_buffer_set_length(struct iio_buffer *buffer, int length)
+int iio_dma_buffer_set_length(struct iio_buffer *buffer, unsigned int length)
{
/* Avoid an invalid state */
if (length < 2)
diff --git a/drivers/iio/buffer/kfifo_buf.c b/drivers/iio/buffer/kfifo_buf.c
index 047fe75..70c302a 100644
--- a/drivers/iio/buffer/kfifo_buf.c
+++ b/drivers/iio/buffer/kfifo_buf.c
@@ -22,11 +22,18 @@ struct iio_kfifo {
#define iio_to_kfifo(r) container_of(r, struct iio_kfifo, buffer)
static inline int __iio_allocate_kfifo(struct iio_kfifo *buf,
- int bytes_per_datum, int length)
+ size_t bytes_per_datum, unsigned int length)
{
if ((length == 0) || (bytes_per_datum == 0))
return -EINVAL;
+ /*
+ * Make sure we don't overflow an unsigned int after kfifo rounds up to
+ * the next power of 2.
+ */
+ if (roundup_pow_of_two(length) > UINT_MAX / bytes_per_datum)
+ return -EINVAL;
+
return __kfifo_alloc((struct __kfifo *)&buf->kf, length,
bytes_per_datum, GFP_KERNEL);
}
@@ -67,7 +74,7 @@ static int iio_set_bytes_per_datum_kfifo(struct iio_buffer *r, size_t bpd)
return 0;
}
-static int iio_set_length_kfifo(struct iio_buffer *r, int length)
+static int iio_set_length_kfifo(struct iio_buffer *r, unsigned int length)
{
/* Avoid an invalid state */
if (length < 2)
diff --git a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
index cfb6588..4905a99 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
@@ -178,14 +178,14 @@ int hid_sensor_power_state(struct hid_sensor_common *st, bool state)
#ifdef CONFIG_PM
int ret;
- atomic_set(&st->user_requested_state, state);
-
if (atomic_add_unless(&st->runtime_pm_enable, 1, 1))
pm_runtime_enable(&st->pdev->dev);
- if (state)
+ if (state) {
+ atomic_inc(&st->user_requested_state);
ret = pm_runtime_get_sync(&st->pdev->dev);
- else {
+ } else {
+ atomic_dec(&st->user_requested_state);
pm_runtime_mark_last_busy(&st->pdev->dev);
pm_runtime_use_autosuspend(&st->pdev->dev);
ret = pm_runtime_put_autosuspend(&st->pdev->dev);
diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index ee270e0..2a972ed6 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -61,9 +61,12 @@
pages on demand instead.
config INFINIBAND_ADDR_TRANS
- bool
+ bool "RDMA/CM"
depends on INFINIBAND
default y
+ ---help---
+ Support for RDMA communication manager (CM).
+ This allows for a generic connection abstraction over RDMA.
config INFINIBAND_ADDR_TRANS_CONFIGFS
bool
diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index e337b08..ecc55e9 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -291,14 +291,18 @@ static int find_gid(struct ib_gid_table *table, const union ib_gid *gid,
* so lookup free slot only if requested.
*/
if (pempty && empty < 0) {
- if (data->props & GID_TABLE_ENTRY_INVALID) {
- /* Found an invalid (free) entry; allocate it */
- if (data->props & GID_TABLE_ENTRY_DEFAULT) {
- if (default_gid)
- empty = curr_index;
- } else {
- empty = curr_index;
- }
+ if (data->props & GID_TABLE_ENTRY_INVALID &&
+ (default_gid ==
+ !!(data->props & GID_TABLE_ENTRY_DEFAULT))) {
+ /*
+ * Found an invalid (free) entry; allocate it.
+ * If default GID is requested, then our
+ * found slot must be one of the DEFAULT
+ * reserved slots or we fail.
+ * This ensures that only DEFAULT reserved
+ * slots are used for default property GIDs.
+ */
+ empty = curr_index;
}
}
@@ -420,8 +424,10 @@ int ib_cache_gid_add(struct ib_device *ib_dev, u8 port,
return ret;
}
-int ib_cache_gid_del(struct ib_device *ib_dev, u8 port,
- union ib_gid *gid, struct ib_gid_attr *attr)
+static int
+_ib_cache_gid_del(struct ib_device *ib_dev, u8 port,
+ union ib_gid *gid, struct ib_gid_attr *attr,
+ unsigned long mask, bool default_gid)
{
struct ib_gid_table *table;
int ret = 0;
@@ -431,11 +437,7 @@ int ib_cache_gid_del(struct ib_device *ib_dev, u8 port,
mutex_lock(&table->lock);
- ix = find_gid(table, gid, attr, false,
- GID_ATTR_FIND_MASK_GID |
- GID_ATTR_FIND_MASK_GID_TYPE |
- GID_ATTR_FIND_MASK_NETDEV,
- NULL);
+ ix = find_gid(table, gid, attr, default_gid, mask, NULL);
if (ix < 0) {
ret = -EINVAL;
goto out_unlock;
@@ -452,6 +454,17 @@ int ib_cache_gid_del(struct ib_device *ib_dev, u8 port,
return ret;
}
+int ib_cache_gid_del(struct ib_device *ib_dev, u8 port,
+ union ib_gid *gid, struct ib_gid_attr *attr)
+{
+ unsigned long mask = GID_ATTR_FIND_MASK_GID |
+ GID_ATTR_FIND_MASK_GID_TYPE |
+ GID_ATTR_FIND_MASK_DEFAULT |
+ GID_ATTR_FIND_MASK_NETDEV;
+
+ return _ib_cache_gid_del(ib_dev, port, gid, attr, mask, false);
+}
+
int ib_cache_gid_del_all_netdev_gids(struct ib_device *ib_dev, u8 port,
struct net_device *ndev)
{
@@ -489,7 +502,7 @@ static int __ib_cache_gid_get(struct ib_device *ib_dev, u8 port, int index,
return -EINVAL;
if (table->data_vec[index].props & GID_TABLE_ENTRY_INVALID)
- return -EAGAIN;
+ return -EINVAL;
memcpy(gid, &table->data_vec[index].gid, sizeof(*gid));
if (attr) {
@@ -728,7 +741,7 @@ void ib_cache_gid_set_default_gid(struct ib_device *ib_dev, u8 port,
unsigned long gid_type_mask,
enum ib_cache_gid_default_mode mode)
{
- union ib_gid gid;
+ union ib_gid gid = { };
struct ib_gid_attr gid_attr;
struct ib_gid_table *table;
unsigned int gid_type;
@@ -736,7 +749,9 @@ void ib_cache_gid_set_default_gid(struct ib_device *ib_dev, u8 port,
table = ib_dev->cache.ports[port - rdma_start_port(ib_dev)].gid;
- make_default_gid(ndev, &gid);
+ mask = GID_ATTR_FIND_MASK_GID_TYPE |
+ GID_ATTR_FIND_MASK_DEFAULT |
+ GID_ATTR_FIND_MASK_NETDEV;
memset(&gid_attr, 0, sizeof(gid_attr));
gid_attr.ndev = ndev;
@@ -747,12 +762,12 @@ void ib_cache_gid_set_default_gid(struct ib_device *ib_dev, u8 port,
gid_attr.gid_type = gid_type;
if (mode == IB_CACHE_GID_DEFAULT_MODE_SET) {
- mask = GID_ATTR_FIND_MASK_GID_TYPE |
- GID_ATTR_FIND_MASK_DEFAULT;
+ make_default_gid(ndev, &gid);
__ib_cache_gid_add(ib_dev, port, &gid,
&gid_attr, mask, true);
} else if (mode == IB_CACHE_GID_DEFAULT_MODE_DELETE) {
- ib_cache_gid_del(ib_dev, port, &gid, &gid_attr);
+ _ib_cache_gid_del(ib_dev, port, &gid,
+ &gid_attr, mask, true);
}
}
}
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 51a6410..a693fcd 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -382,6 +382,8 @@ struct cma_hdr {
#define CMA_VERSION 0x00
struct cma_req_info {
+ struct sockaddr_storage listen_addr_storage;
+ struct sockaddr_storage src_addr_storage;
struct ib_device *device;
int port;
union ib_gid local_gid;
@@ -866,7 +868,6 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv,
{
struct ib_qp_attr qp_attr;
int qp_attr_mask, ret;
- union ib_gid sgid;
mutex_lock(&id_priv->qp_mutex);
if (!id_priv->id.qp) {
@@ -889,12 +890,6 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv,
if (ret)
goto out;
- ret = ib_query_gid(id_priv->id.device, id_priv->id.port_num,
- rdma_ah_read_grh(&qp_attr.ah_attr)->sgid_index,
- &sgid, NULL);
- if (ret)
- goto out;
-
BUG_ON(id_priv->cma_dev->device != id_priv->id.device);
if (conn_param)
@@ -1340,11 +1335,11 @@ static bool validate_net_dev(struct net_device *net_dev,
}
static struct net_device *cma_get_net_dev(struct ib_cm_event *ib_event,
- const struct cma_req_info *req)
+ struct cma_req_info *req)
{
- struct sockaddr_storage listen_addr_storage, src_addr_storage;
- struct sockaddr *listen_addr = (struct sockaddr *)&listen_addr_storage,
- *src_addr = (struct sockaddr *)&src_addr_storage;
+ struct sockaddr *listen_addr =
+ (struct sockaddr *)&req->listen_addr_storage;
+ struct sockaddr *src_addr = (struct sockaddr *)&req->src_addr_storage;
struct net_device *net_dev;
const union ib_gid *gid = req->has_gid ? &req->local_gid : NULL;
int err;
@@ -1359,11 +1354,6 @@ static struct net_device *cma_get_net_dev(struct ib_cm_event *ib_event,
if (!net_dev)
return ERR_PTR(-ENODEV);
- if (!validate_net_dev(net_dev, listen_addr, src_addr)) {
- dev_put(net_dev);
- return ERR_PTR(-EHOSTUNREACH);
- }
-
return net_dev;
}
@@ -1490,15 +1480,51 @@ static struct rdma_id_private *cma_id_from_event(struct ib_cm_id *cm_id,
}
}
+ /*
+ * Net namespace might be getting deleted while route lookup,
+ * cm_id lookup is in progress. Therefore, perform netdevice
+ * validation, cm_id lookup under rcu lock.
+ * RCU lock along with netdevice state check, synchronizes with
+ * netdevice migrating to different net namespace and also avoids
+ * case where net namespace doesn't get deleted while lookup is in
+ * progress.
+ * If the device state is not IFF_UP, its properties such as ifindex
+ * and nd_net cannot be trusted to remain valid without rcu lock.
+ * net/core/dev.c change_net_namespace() ensures to synchronize with
+ * ongoing operations on net device after device is closed using
+ * synchronize_net().
+ */
+ rcu_read_lock();
+ if (*net_dev) {
+ /*
+ * If netdevice is down, it is likely that it is administratively
+ * down or it might be migrating to different namespace.
+ * In that case avoid further processing, as the net namespace
+ * or ifindex may change.
+ */
+ if (((*net_dev)->flags & IFF_UP) == 0) {
+ id_priv = ERR_PTR(-EHOSTUNREACH);
+ goto err;
+ }
+
+ if (!validate_net_dev(*net_dev,
+ (struct sockaddr *)&req.listen_addr_storage,
+ (struct sockaddr *)&req.src_addr_storage)) {
+ id_priv = ERR_PTR(-EHOSTUNREACH);
+ goto err;
+ }
+ }
+
bind_list = cma_ps_find(*net_dev ? dev_net(*net_dev) : &init_net,
rdma_ps_from_service_id(req.service_id),
cma_port_from_service_id(req.service_id));
id_priv = cma_find_listener(bind_list, cm_id, ib_event, &req, *net_dev);
+err:
+ rcu_read_unlock();
if (IS_ERR(id_priv) && *net_dev) {
dev_put(*net_dev);
*net_dev = NULL;
}
-
return id_priv;
}
diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c
index 9821ae9..da12da1 100644
--- a/drivers/infiniband/core/iwpm_util.c
+++ b/drivers/infiniband/core/iwpm_util.c
@@ -114,7 +114,7 @@ int iwpm_create_mapinfo(struct sockaddr_storage *local_sockaddr,
struct sockaddr_storage *mapped_sockaddr,
u8 nl_client)
{
- struct hlist_head *hash_bucket_head;
+ struct hlist_head *hash_bucket_head = NULL;
struct iwpm_mapping_info *map_info;
unsigned long flags;
int ret = -EINVAL;
@@ -142,6 +142,9 @@ int iwpm_create_mapinfo(struct sockaddr_storage *local_sockaddr,
}
}
spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
+
+ if (!hash_bucket_head)
+ kfree(map_info);
return ret;
}
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index c50596f..b28452a 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -59,7 +59,7 @@ module_param_named(recv_queue_size, mad_recvq_size, int, 0444);
MODULE_PARM_DESC(recv_queue_size, "Size of receive queue in number of work requests");
static struct list_head ib_mad_port_list;
-static u32 ib_mad_client_id = 0;
+static atomic_t ib_mad_client_id = ATOMIC_INIT(0);
/* Port list lock */
static DEFINE_SPINLOCK(ib_mad_port_list_lock);
@@ -377,7 +377,7 @@ struct ib_mad_agent *ib_register_mad_agent(struct ib_device *device,
}
spin_lock_irqsave(&port_priv->reg_lock, flags);
- mad_agent_priv->agent.hi_tid = ++ib_mad_client_id;
+ mad_agent_priv->agent.hi_tid = atomic_inc_return(&ib_mad_client_id);
/*
* Make sure MAD registration (if supplied)
diff --git a/drivers/infiniband/core/roce_gid_mgmt.c b/drivers/infiniband/core/roce_gid_mgmt.c
index cc29663..c0e4fd5 100644
--- a/drivers/infiniband/core/roce_gid_mgmt.c
+++ b/drivers/infiniband/core/roce_gid_mgmt.c
@@ -255,6 +255,7 @@ static void bond_delete_netdev_default_gids(struct ib_device *ib_dev,
struct net_device *rdma_ndev)
{
struct net_device *real_dev = rdma_vlan_dev_real_dev(event_ndev);
+ unsigned long gid_type_mask;
if (!rdma_ndev)
return;
@@ -264,21 +265,22 @@ static void bond_delete_netdev_default_gids(struct ib_device *ib_dev,
rcu_read_lock();
- if (rdma_is_upper_dev_rcu(rdma_ndev, event_ndev) &&
- is_eth_active_slave_of_bonding_rcu(rdma_ndev, real_dev) ==
- BONDING_SLAVE_STATE_INACTIVE) {
- unsigned long gid_type_mask;
-
+ if (((rdma_ndev != event_ndev &&
+ !rdma_is_upper_dev_rcu(rdma_ndev, event_ndev)) ||
+ is_eth_active_slave_of_bonding_rcu(rdma_ndev, real_dev)
+ ==
+ BONDING_SLAVE_STATE_INACTIVE)) {
rcu_read_unlock();
-
- gid_type_mask = roce_gid_type_mask_support(ib_dev, port);
-
- ib_cache_gid_set_default_gid(ib_dev, port, rdma_ndev,
- gid_type_mask,
- IB_CACHE_GID_DEFAULT_MODE_DELETE);
- } else {
- rcu_read_unlock();
+ return;
}
+
+ rcu_read_unlock();
+
+ gid_type_mask = roce_gid_type_mask_support(ib_dev, port);
+
+ ib_cache_gid_set_default_gid(ib_dev, port, rdma_ndev,
+ gid_type_mask,
+ IB_CACHE_GID_DEFAULT_MODE_DELETE);
}
static void enum_netdev_ipv4_ips(struct ib_device *ib_dev,
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 7432948..eab43b1 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -159,6 +159,23 @@ static void ucma_put_ctx(struct ucma_context *ctx)
complete(&ctx->comp);
}
+/*
+ * Same as ucm_get_ctx but requires that ->cm_id->device is valid, eg that the
+ * CM_ID is bound.
+ */
+static struct ucma_context *ucma_get_ctx_dev(struct ucma_file *file, int id)
+{
+ struct ucma_context *ctx = ucma_get_ctx(file, id);
+
+ if (IS_ERR(ctx))
+ return ctx;
+ if (!ctx->cm_id->device) {
+ ucma_put_ctx(ctx);
+ return ERR_PTR(-EINVAL);
+ }
+ return ctx;
+}
+
static void ucma_close_event_id(struct work_struct *work)
{
struct ucma_event *uevent_close = container_of(work, struct ucma_event, close_work);
@@ -683,7 +700,7 @@ static ssize_t ucma_resolve_ip(struct ucma_file *file,
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
- if (!rdma_addr_size_in6(&cmd.src_addr) ||
+ if ((cmd.src_addr.sin6_family && !rdma_addr_size_in6(&cmd.src_addr)) ||
!rdma_addr_size_in6(&cmd.dst_addr))
return -EINVAL;
@@ -734,7 +751,7 @@ static ssize_t ucma_resolve_route(struct ucma_file *file,
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
- ctx = ucma_get_ctx(file, cmd.id);
+ ctx = ucma_get_ctx_dev(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
@@ -1050,7 +1067,7 @@ static ssize_t ucma_connect(struct ucma_file *file, const char __user *inbuf,
if (!cmd.conn_param.valid)
return -EINVAL;
- ctx = ucma_get_ctx(file, cmd.id);
+ ctx = ucma_get_ctx_dev(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
@@ -1092,7 +1109,7 @@ static ssize_t ucma_accept(struct ucma_file *file, const char __user *inbuf,
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
- ctx = ucma_get_ctx(file, cmd.id);
+ ctx = ucma_get_ctx_dev(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
@@ -1120,7 +1137,7 @@ static ssize_t ucma_reject(struct ucma_file *file, const char __user *inbuf,
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
- ctx = ucma_get_ctx(file, cmd.id);
+ ctx = ucma_get_ctx_dev(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
@@ -1139,7 +1156,7 @@ static ssize_t ucma_disconnect(struct ucma_file *file, const char __user *inbuf,
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
- ctx = ucma_get_ctx(file, cmd.id);
+ ctx = ucma_get_ctx_dev(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
@@ -1167,15 +1184,10 @@ static ssize_t ucma_init_qp_attr(struct ucma_file *file,
if (cmd.qp_state > IB_QPS_ERR)
return -EINVAL;
- ctx = ucma_get_ctx(file, cmd.id);
+ ctx = ucma_get_ctx_dev(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
- if (!ctx->cm_id->device) {
- ret = -EINVAL;
- goto out;
- }
-
resp.qp_attr_mask = 0;
memset(&qp_attr, 0, sizeof qp_attr);
qp_attr.qp_state = cmd.qp_state;
@@ -1316,13 +1328,13 @@ static ssize_t ucma_set_option(struct ucma_file *file, const char __user *inbuf,
if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
return -EFAULT;
+ if (unlikely(cmd.optlen > KMALLOC_MAX_SIZE))
+ return -EINVAL;
+
ctx = ucma_get_ctx(file, cmd.id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
- if (unlikely(cmd.optlen > KMALLOC_MAX_SIZE))
- return -EINVAL;
-
optval = memdup_user(u64_to_user_ptr(cmd.optval),
cmd.optlen);
if (IS_ERR(optval)) {
@@ -1384,7 +1396,7 @@ static ssize_t ucma_process_join(struct ucma_file *file,
else
return -EINVAL;
- ctx = ucma_get_ctx(file, cmd->id);
+ ctx = ucma_get_ctx_dev(file, cmd->id);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 9a4e899..2b6c9b5 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -119,7 +119,6 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
umem->length = size;
umem->address = addr;
umem->page_shift = PAGE_SHIFT;
- umem->pid = get_task_pid(current, PIDTYPE_PID);
/*
* We ask for writable memory if any of the following
* access flags are set. "Local write" and "remote write"
@@ -132,7 +131,6 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND));
if (access & IB_ACCESS_ON_DEMAND) {
- put_pid(umem->pid);
ret = ib_umem_odp_get(context, umem, access);
if (ret) {
kfree(umem);
@@ -148,7 +146,6 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
page_list = (struct page **) __get_free_page(GFP_KERNEL);
if (!page_list) {
- put_pid(umem->pid);
kfree(umem);
return ERR_PTR(-ENOMEM);
}
@@ -231,7 +228,6 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
if (ret < 0) {
if (need_release)
__ib_umem_release(context->device, umem, 0);
- put_pid(umem->pid);
kfree(umem);
} else
current->mm->pinned_vm = locked;
@@ -274,8 +270,7 @@ void ib_umem_release(struct ib_umem *umem)
__ib_umem_release(umem->context->device, umem, 1);
- task = get_pid_task(umem->pid, PIDTYPE_PID);
- put_pid(umem->pid);
+ task = get_pid_task(umem->context->tgid, PIDTYPE_PID);
if (!task)
goto out;
mm = get_task_mm(task);
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 13cb5e4..21a887c9 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -691,6 +691,7 @@ ssize_t ib_uverbs_reg_mr(struct ib_uverbs_file *file,
mr->device = pd->device;
mr->pd = pd;
+ mr->dm = NULL;
mr->uobject = uobj;
atomic_inc(&pd->usecnt);
mr->res.type = RDMA_RESTRACK_MR;
@@ -765,6 +766,11 @@ ssize_t ib_uverbs_rereg_mr(struct ib_uverbs_file *file,
mr = uobj->object;
+ if (mr->dm) {
+ ret = -EINVAL;
+ goto put_uobjs;
+ }
+
if (cmd.flags & IB_MR_REREG_ACCESS) {
ret = ib_check_mr_access(cmd.access_flags);
if (ret)
diff --git a/drivers/infiniband/core/uverbs_ioctl.c b/drivers/infiniband/core/uverbs_ioctl.c
index 8c93970..8d32c4a 100644
--- a/drivers/infiniband/core/uverbs_ioctl.c
+++ b/drivers/infiniband/core/uverbs_ioctl.c
@@ -234,6 +234,15 @@ static int uverbs_validate_kernel_mandatory(const struct uverbs_method_spec *met
return -EINVAL;
}
+ for (; i < method_spec->num_buckets; i++) {
+ struct uverbs_attr_spec_hash *attr_spec_bucket =
+ method_spec->attr_buckets[i];
+
+ if (!bitmap_empty(attr_spec_bucket->mandatory_attrs_bitmask,
+ attr_spec_bucket->num_attrs))
+ return -EINVAL;
+ }
+
return 0;
}
diff --git a/drivers/infiniband/core/uverbs_std_types_flow_action.c b/drivers/infiniband/core/uverbs_std_types_flow_action.c
index cbcec3da..b4f016d 100644
--- a/drivers/infiniband/core/uverbs_std_types_flow_action.c
+++ b/drivers/infiniband/core/uverbs_std_types_flow_action.c
@@ -363,28 +363,28 @@ static int UVERBS_HANDLER(UVERBS_METHOD_FLOW_ACTION_ESP_MODIFY)(struct ib_device
static const struct uverbs_attr_spec uverbs_flow_action_esp_keymat[] = {
[IB_UVERBS_FLOW_ACTION_ESP_KEYMAT_AES_GCM] = {
- .ptr = {
+ { .ptr = {
.type = UVERBS_ATTR_TYPE_PTR_IN,
UVERBS_ATTR_TYPE(struct ib_uverbs_flow_action_esp_keymat_aes_gcm),
.flags = UVERBS_ATTR_SPEC_F_MIN_SZ_OR_ZERO,
- },
+ } },
},
};
static const struct uverbs_attr_spec uverbs_flow_action_esp_replay[] = {
[IB_UVERBS_FLOW_ACTION_ESP_REPLAY_NONE] = {
- .ptr = {
+ { .ptr = {
.type = UVERBS_ATTR_TYPE_PTR_IN,
/* No need to specify any data */
.len = 0,
- }
+ } }
},
[IB_UVERBS_FLOW_ACTION_ESP_REPLAY_BMP] = {
- .ptr = {
+ { .ptr = {
.type = UVERBS_ATTR_TYPE_PTR_IN,
UVERBS_ATTR_STRUCT(struct ib_uverbs_flow_action_esp_replay_bmp, size),
.flags = UVERBS_ATTR_SPEC_F_MIN_SZ_OR_ZERO,
- }
+ } }
},
};
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 7eff3ae..6ddfb1fa 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1656,6 +1656,7 @@ struct ib_mr *ib_alloc_mr(struct ib_pd *pd,
if (!IS_ERR(mr)) {
mr->device = pd->device;
mr->pd = pd;
+ mr->dm = NULL;
mr->uobject = NULL;
atomic_inc(&pd->usecnt);
mr->need_inval = false;
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index f6c739e..20b9f31 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -185,12 +185,65 @@ static void bnxt_re_shutdown(void *p)
bnxt_re_ib_unreg(rdev, false);
}
+static void bnxt_re_stop_irq(void *handle)
+{
+ struct bnxt_re_dev *rdev = (struct bnxt_re_dev *)handle;
+ struct bnxt_qplib_rcfw *rcfw = &rdev->rcfw;
+ struct bnxt_qplib_nq *nq;
+ int indx;
+
+ for (indx = BNXT_RE_NQ_IDX; indx < rdev->num_msix; indx++) {
+ nq = &rdev->nq[indx - 1];
+ bnxt_qplib_nq_stop_irq(nq, false);
+ }
+
+ bnxt_qplib_rcfw_stop_irq(rcfw, false);
+}
+
+static void bnxt_re_start_irq(void *handle, struct bnxt_msix_entry *ent)
+{
+ struct bnxt_re_dev *rdev = (struct bnxt_re_dev *)handle;
+ struct bnxt_msix_entry *msix_ent = rdev->msix_entries;
+ struct bnxt_qplib_rcfw *rcfw = &rdev->rcfw;
+ struct bnxt_qplib_nq *nq;
+ int indx, rc;
+
+ if (!ent) {
+ /* Not setting the f/w timeout bit in rcfw.
+ * During the driver unload the first command
+ * to f/w will timeout and that will set the
+ * timeout bit.
+ */
+ dev_err(rdev_to_dev(rdev), "Failed to re-start IRQs\n");
+ return;
+ }
+
+ /* Vectors may change after restart, so update with new vectors
+ * in device sctructure.
+ */
+ for (indx = 0; indx < rdev->num_msix; indx++)
+ rdev->msix_entries[indx].vector = ent[indx].vector;
+
+ bnxt_qplib_rcfw_start_irq(rcfw, msix_ent[BNXT_RE_AEQ_IDX].vector,
+ false);
+ for (indx = BNXT_RE_NQ_IDX ; indx < rdev->num_msix; indx++) {
+ nq = &rdev->nq[indx - 1];
+ rc = bnxt_qplib_nq_start_irq(nq, indx - 1,
+ msix_ent[indx].vector, false);
+ if (rc)
+ dev_warn(rdev_to_dev(rdev),
+ "Failed to reinit NQ index %d\n", indx - 1);
+ }
+}
+
static struct bnxt_ulp_ops bnxt_re_ulp_ops = {
.ulp_async_notifier = NULL,
.ulp_stop = bnxt_re_stop,
.ulp_start = bnxt_re_start,
.ulp_sriov_config = bnxt_re_sriov_config,
- .ulp_shutdown = bnxt_re_shutdown
+ .ulp_shutdown = bnxt_re_shutdown,
+ .ulp_irq_stop = bnxt_re_stop_irq,
+ .ulp_irq_restart = bnxt_re_start_irq
};
/* RoCE -> Net driver */
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index 3a78fab..50d8f1f 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -336,22 +336,32 @@ static irqreturn_t bnxt_qplib_nq_irq(int irq, void *dev_instance)
return IRQ_HANDLED;
}
+void bnxt_qplib_nq_stop_irq(struct bnxt_qplib_nq *nq, bool kill)
+{
+ tasklet_disable(&nq->worker);
+ /* Mask h/w interrupt */
+ NQ_DB(nq->bar_reg_iomem, nq->hwq.cons, nq->hwq.max_elements);
+ /* Sync with last running IRQ handler */
+ synchronize_irq(nq->vector);
+ if (kill)
+ tasklet_kill(&nq->worker);
+ if (nq->requested) {
+ irq_set_affinity_hint(nq->vector, NULL);
+ free_irq(nq->vector, nq);
+ nq->requested = false;
+ }
+}
+
void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq)
{
if (nq->cqn_wq) {
destroy_workqueue(nq->cqn_wq);
nq->cqn_wq = NULL;
}
- /* Make sure the HW is stopped! */
- synchronize_irq(nq->vector);
- tasklet_disable(&nq->worker);
- tasklet_kill(&nq->worker);
- if (nq->requested) {
- irq_set_affinity_hint(nq->vector, NULL);
- free_irq(nq->vector, nq);
- nq->requested = false;
- }
+ /* Make sure the HW is stopped! */
+ bnxt_qplib_nq_stop_irq(nq, true);
+
if (nq->bar_reg_iomem)
iounmap(nq->bar_reg_iomem);
nq->bar_reg_iomem = NULL;
@@ -361,6 +371,40 @@ void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq)
nq->vector = 0;
}
+int bnxt_qplib_nq_start_irq(struct bnxt_qplib_nq *nq, int nq_indx,
+ int msix_vector, bool need_init)
+{
+ int rc;
+
+ if (nq->requested)
+ return -EFAULT;
+
+ nq->vector = msix_vector;
+ if (need_init)
+ tasklet_init(&nq->worker, bnxt_qplib_service_nq,
+ (unsigned long)nq);
+ else
+ tasklet_enable(&nq->worker);
+
+ snprintf(nq->name, sizeof(nq->name), "bnxt_qplib_nq-%d", nq_indx);
+ rc = request_irq(nq->vector, bnxt_qplib_nq_irq, 0, nq->name, nq);
+ if (rc)
+ return rc;
+
+ cpumask_clear(&nq->mask);
+ cpumask_set_cpu(nq_indx, &nq->mask);
+ rc = irq_set_affinity_hint(nq->vector, &nq->mask);
+ if (rc) {
+ dev_warn(&nq->pdev->dev,
+ "QPLIB: set affinity failed; vector: %d nq_idx: %d\n",
+ nq->vector, nq_indx);
+ }
+ nq->requested = true;
+ NQ_DB_REARM(nq->bar_reg_iomem, nq->hwq.cons, nq->hwq.max_elements);
+
+ return rc;
+}
+
int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
int nq_idx, int msix_vector, int bar_reg_offset,
int (*cqn_handler)(struct bnxt_qplib_nq *nq,
@@ -372,41 +416,17 @@ int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
resource_size_t nq_base;
int rc = -1;
- nq->pdev = pdev;
- nq->vector = msix_vector;
if (cqn_handler)
nq->cqn_handler = cqn_handler;
if (srqn_handler)
nq->srqn_handler = srqn_handler;
- tasklet_init(&nq->worker, bnxt_qplib_service_nq, (unsigned long)nq);
-
/* Have a task to schedule CQ notifiers in post send case */
nq->cqn_wq = create_singlethread_workqueue("bnxt_qplib_nq");
if (!nq->cqn_wq)
- goto fail;
+ return -ENOMEM;
- nq->requested = false;
- memset(nq->name, 0, 32);
- sprintf(nq->name, "bnxt_qplib_nq-%d", nq_idx);
- rc = request_irq(nq->vector, bnxt_qplib_nq_irq, 0, nq->name, nq);
- if (rc) {
- dev_err(&nq->pdev->dev,
- "Failed to request IRQ for NQ: %#x", rc);
- goto fail;
- }
-
- cpumask_clear(&nq->mask);
- cpumask_set_cpu(nq_idx, &nq->mask);
- rc = irq_set_affinity_hint(nq->vector, &nq->mask);
- if (rc) {
- dev_warn(&nq->pdev->dev,
- "QPLIB: set affinity failed; vector: %d nq_idx: %d\n",
- nq->vector, nq_idx);
- }
-
- nq->requested = true;
nq->bar_reg = NQ_CONS_PCI_BAR_REGION;
nq->bar_reg_off = bar_reg_offset;
nq_base = pci_resource_start(pdev, nq->bar_reg);
@@ -419,7 +439,13 @@ int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
rc = -ENOMEM;
goto fail;
}
- NQ_DB_REARM(nq->bar_reg_iomem, nq->hwq.cons, nq->hwq.max_elements);
+
+ rc = bnxt_qplib_nq_start_irq(nq, nq_idx, msix_vector, true);
+ if (rc) {
+ dev_err(&nq->pdev->dev,
+ "QPLIB: Failed to request irq for nq-idx %d", nq_idx);
+ goto fail;
+ }
return 0;
fail:
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h
index ade9f13..72352ca 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h
@@ -467,7 +467,10 @@ struct bnxt_qplib_nq_work {
struct bnxt_qplib_cq *cq;
};
+void bnxt_qplib_nq_stop_irq(struct bnxt_qplib_nq *nq, bool kill);
void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq);
+int bnxt_qplib_nq_start_irq(struct bnxt_qplib_nq *nq, int nq_indx,
+ int msix_vector, bool need_init);
int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
int nq_idx, int msix_vector, int bar_reg_offset,
int (*cqn_handler)(struct bnxt_qplib_nq *nq,
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
index 80027a4..2852d35 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -582,19 +582,29 @@ int bnxt_qplib_alloc_rcfw_channel(struct pci_dev *pdev,
return -ENOMEM;
}
-void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw)
+void bnxt_qplib_rcfw_stop_irq(struct bnxt_qplib_rcfw *rcfw, bool kill)
{
- unsigned long indx;
-
- /* Make sure the HW channel is stopped! */
- synchronize_irq(rcfw->vector);
tasklet_disable(&rcfw->worker);
- tasklet_kill(&rcfw->worker);
+ /* Mask h/w interrupts */
+ CREQ_DB(rcfw->creq_bar_reg_iomem, rcfw->creq.cons,
+ rcfw->creq.max_elements);
+ /* Sync with last running IRQ-handler */
+ synchronize_irq(rcfw->vector);
+ if (kill)
+ tasklet_kill(&rcfw->worker);
if (rcfw->requested) {
free_irq(rcfw->vector, rcfw);
rcfw->requested = false;
}
+}
+
+void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw)
+{
+ unsigned long indx;
+
+ bnxt_qplib_rcfw_stop_irq(rcfw, true);
+
if (rcfw->cmdq_bar_reg_iomem)
iounmap(rcfw->cmdq_bar_reg_iomem);
rcfw->cmdq_bar_reg_iomem = NULL;
@@ -614,6 +624,31 @@ void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw)
rcfw->vector = 0;
}
+int bnxt_qplib_rcfw_start_irq(struct bnxt_qplib_rcfw *rcfw, int msix_vector,
+ bool need_init)
+{
+ int rc;
+
+ if (rcfw->requested)
+ return -EFAULT;
+
+ rcfw->vector = msix_vector;
+ if (need_init)
+ tasklet_init(&rcfw->worker,
+ bnxt_qplib_service_creq, (unsigned long)rcfw);
+ else
+ tasklet_enable(&rcfw->worker);
+ rc = request_irq(rcfw->vector, bnxt_qplib_creq_irq, 0,
+ "bnxt_qplib_creq", rcfw);
+ if (rc)
+ return rc;
+ rcfw->requested = true;
+ CREQ_DB_REARM(rcfw->creq_bar_reg_iomem, rcfw->creq.cons,
+ rcfw->creq.max_elements);
+
+ return 0;
+}
+
int bnxt_qplib_enable_rcfw_channel(struct pci_dev *pdev,
struct bnxt_qplib_rcfw *rcfw,
int msix_vector,
@@ -675,27 +710,17 @@ int bnxt_qplib_enable_rcfw_channel(struct pci_dev *pdev,
rcfw->creq_qp_event_processed = 0;
rcfw->creq_func_event_processed = 0;
- rcfw->vector = msix_vector;
if (aeq_handler)
rcfw->aeq_handler = aeq_handler;
+ init_waitqueue_head(&rcfw->waitq);
- tasklet_init(&rcfw->worker, bnxt_qplib_service_creq,
- (unsigned long)rcfw);
-
- rcfw->requested = false;
- rc = request_irq(rcfw->vector, bnxt_qplib_creq_irq, 0,
- "bnxt_qplib_creq", rcfw);
+ rc = bnxt_qplib_rcfw_start_irq(rcfw, msix_vector, true);
if (rc) {
dev_err(&rcfw->pdev->dev,
"QPLIB: Failed to request IRQ for CREQ rc = 0x%x", rc);
bnxt_qplib_disable_rcfw_channel(rcfw);
return rc;
}
- rcfw->requested = true;
-
- init_waitqueue_head(&rcfw->waitq);
-
- CREQ_DB_REARM(rcfw->creq_bar_reg_iomem, 0, rcfw->creq.max_elements);
init.cmdq_pbl = cpu_to_le64(rcfw->cmdq.pbl[PBL_LVL_0].pg_map_arr[0]);
init.cmdq_size_cmdq_lvl = cpu_to_le16(
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
index c7cce2e..46416df 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
@@ -195,7 +195,10 @@ struct bnxt_qplib_rcfw {
void bnxt_qplib_free_rcfw_channel(struct bnxt_qplib_rcfw *rcfw);
int bnxt_qplib_alloc_rcfw_channel(struct pci_dev *pdev,
struct bnxt_qplib_rcfw *rcfw, int qp_tbl_sz);
+void bnxt_qplib_rcfw_stop_irq(struct bnxt_qplib_rcfw *rcfw, bool kill);
void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw);
+int bnxt_qplib_rcfw_start_irq(struct bnxt_qplib_rcfw *rcfw, int msix_vector,
+ bool need_init);
int bnxt_qplib_enable_rcfw_channel(struct pci_dev *pdev,
struct bnxt_qplib_rcfw *rcfw,
int msix_vector,
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index 6f2b261..2be2e1a 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -315,7 +315,7 @@ static void advance_oldest_read(struct t4_wq *wq)
* Deal with out-of-order and/or completions that complete
* prior unsignalled WRs.
*/
-void c4iw_flush_hw_cq(struct c4iw_cq *chp)
+void c4iw_flush_hw_cq(struct c4iw_cq *chp, struct c4iw_qp *flush_qhp)
{
struct t4_cqe *hw_cqe, *swcqe, read_cqe;
struct c4iw_qp *qhp;
@@ -339,6 +339,13 @@ void c4iw_flush_hw_cq(struct c4iw_cq *chp)
if (qhp == NULL)
goto next_cqe;
+ if (flush_qhp != qhp) {
+ spin_lock(&qhp->lock);
+
+ if (qhp->wq.flushed == 1)
+ goto next_cqe;
+ }
+
if (CQE_OPCODE(hw_cqe) == FW_RI_TERMINATE)
goto next_cqe;
@@ -390,6 +397,8 @@ void c4iw_flush_hw_cq(struct c4iw_cq *chp)
next_cqe:
t4_hwcq_consume(&chp->cq);
ret = t4_next_hw_cqe(&chp->cq, &hw_cqe);
+ if (qhp && flush_qhp != qhp)
+ spin_unlock(&qhp->lock);
}
}
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index feeb8ee..44161ca 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -875,6 +875,11 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
rdev->status_page->db_off = 0;
+ init_completion(&rdev->rqt_compl);
+ init_completion(&rdev->pbl_compl);
+ kref_init(&rdev->rqt_kref);
+ kref_init(&rdev->pbl_kref);
+
return 0;
err_free_status_page_and_wr_log:
if (c4iw_wr_log && rdev->wr_log)
@@ -893,13 +898,15 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
static void c4iw_rdev_close(struct c4iw_rdev *rdev)
{
- destroy_workqueue(rdev->free_workq);
kfree(rdev->wr_log);
c4iw_release_dev_ucontext(rdev, &rdev->uctx);
free_page((unsigned long)rdev->status_page);
c4iw_pblpool_destroy(rdev);
c4iw_rqtpool_destroy(rdev);
+ wait_for_completion(&rdev->pbl_compl);
+ wait_for_completion(&rdev->rqt_compl);
c4iw_ocqp_pool_destroy(rdev);
+ destroy_workqueue(rdev->free_workq);
c4iw_destroy_resource(&rdev->resource);
}
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index cc92900..8310277 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -185,6 +185,10 @@ struct c4iw_rdev {
struct wr_log_entry *wr_log;
int wr_log_size;
struct workqueue_struct *free_workq;
+ struct completion rqt_compl;
+ struct completion pbl_compl;
+ struct kref rqt_kref;
+ struct kref pbl_kref;
};
static inline int c4iw_fatal_error(struct c4iw_rdev *rdev)
@@ -1049,7 +1053,7 @@ u32 c4iw_pblpool_alloc(struct c4iw_rdev *rdev, int size);
void c4iw_pblpool_free(struct c4iw_rdev *rdev, u32 addr, int size);
u32 c4iw_ocqp_pool_alloc(struct c4iw_rdev *rdev, int size);
void c4iw_ocqp_pool_free(struct c4iw_rdev *rdev, u32 addr, int size);
-void c4iw_flush_hw_cq(struct c4iw_cq *chp);
+void c4iw_flush_hw_cq(struct c4iw_cq *chp, struct c4iw_qp *flush_qhp);
void c4iw_count_rcqes(struct t4_cq *cq, struct t4_wq *wq, int *count);
int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp);
int c4iw_flush_rq(struct t4_wq *wq, struct t4_cq *cq, int count);
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index e90f2fd..1445918 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -489,10 +489,10 @@ struct ib_mr *c4iw_get_dma_mr(struct ib_pd *pd, int acc)
err_dereg_mem:
dereg_mem(&rhp->rdev, mhp->attr.stag, mhp->attr.pbl_size,
mhp->attr.pbl_addr, mhp->dereg_skb, mhp->wr_waitp);
-err_free_wr_wait:
- c4iw_put_wr_wait(mhp->wr_waitp);
err_free_skb:
kfree_skb(mhp->dereg_skb);
+err_free_wr_wait:
+ c4iw_put_wr_wait(mhp->wr_waitp);
err_free_mhp:
kfree(mhp);
return ERR_PTR(ret);
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index de77b60..ae167b6 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -1343,12 +1343,12 @@ static void __flush_qp(struct c4iw_qp *qhp, struct c4iw_cq *rchp,
qhp->wq.flushed = 1;
t4_set_wq_in_error(&qhp->wq);
- c4iw_flush_hw_cq(rchp);
+ c4iw_flush_hw_cq(rchp, qhp);
c4iw_count_rcqes(&rchp->cq, &qhp->wq, &count);
rq_flushed = c4iw_flush_rq(&qhp->wq, &rchp->cq, count);
if (schp != rchp)
- c4iw_flush_hw_cq(schp);
+ c4iw_flush_hw_cq(schp, qhp);
sq_flushed = c4iw_flush_sq(qhp);
spin_unlock(&qhp->lock);
diff --git a/drivers/infiniband/hw/cxgb4/resource.c b/drivers/infiniband/hw/cxgb4/resource.c
index 3cf2599..0ef25ae 100644
--- a/drivers/infiniband/hw/cxgb4/resource.c
+++ b/drivers/infiniband/hw/cxgb4/resource.c
@@ -260,12 +260,22 @@ u32 c4iw_pblpool_alloc(struct c4iw_rdev *rdev, int size)
rdev->stats.pbl.cur += roundup(size, 1 << MIN_PBL_SHIFT);
if (rdev->stats.pbl.cur > rdev->stats.pbl.max)
rdev->stats.pbl.max = rdev->stats.pbl.cur;
+ kref_get(&rdev->pbl_kref);
} else
rdev->stats.pbl.fail++;
mutex_unlock(&rdev->stats.lock);
return (u32)addr;
}
+static void destroy_pblpool(struct kref *kref)
+{
+ struct c4iw_rdev *rdev;
+
+ rdev = container_of(kref, struct c4iw_rdev, pbl_kref);
+ gen_pool_destroy(rdev->pbl_pool);
+ complete(&rdev->pbl_compl);
+}
+
void c4iw_pblpool_free(struct c4iw_rdev *rdev, u32 addr, int size)
{
pr_debug("addr 0x%x size %d\n", addr, size);
@@ -273,6 +283,7 @@ void c4iw_pblpool_free(struct c4iw_rdev *rdev, u32 addr, int size)
rdev->stats.pbl.cur -= roundup(size, 1 << MIN_PBL_SHIFT);
mutex_unlock(&rdev->stats.lock);
gen_pool_free(rdev->pbl_pool, (unsigned long)addr, size);
+ kref_put(&rdev->pbl_kref, destroy_pblpool);
}
int c4iw_pblpool_create(struct c4iw_rdev *rdev)
@@ -310,7 +321,7 @@ int c4iw_pblpool_create(struct c4iw_rdev *rdev)
void c4iw_pblpool_destroy(struct c4iw_rdev *rdev)
{
- gen_pool_destroy(rdev->pbl_pool);
+ kref_put(&rdev->pbl_kref, destroy_pblpool);
}
/*
@@ -331,12 +342,22 @@ u32 c4iw_rqtpool_alloc(struct c4iw_rdev *rdev, int size)
rdev->stats.rqt.cur += roundup(size << 6, 1 << MIN_RQT_SHIFT);
if (rdev->stats.rqt.cur > rdev->stats.rqt.max)
rdev->stats.rqt.max = rdev->stats.rqt.cur;
+ kref_get(&rdev->rqt_kref);
} else
rdev->stats.rqt.fail++;
mutex_unlock(&rdev->stats.lock);
return (u32)addr;
}
+static void destroy_rqtpool(struct kref *kref)
+{
+ struct c4iw_rdev *rdev;
+
+ rdev = container_of(kref, struct c4iw_rdev, rqt_kref);
+ gen_pool_destroy(rdev->rqt_pool);
+ complete(&rdev->rqt_compl);
+}
+
void c4iw_rqtpool_free(struct c4iw_rdev *rdev, u32 addr, int size)
{
pr_debug("addr 0x%x size %d\n", addr, size << 6);
@@ -344,6 +365,7 @@ void c4iw_rqtpool_free(struct c4iw_rdev *rdev, u32 addr, int size)
rdev->stats.rqt.cur -= roundup(size << 6, 1 << MIN_RQT_SHIFT);
mutex_unlock(&rdev->stats.lock);
gen_pool_free(rdev->rqt_pool, (unsigned long)addr, size << 6);
+ kref_put(&rdev->rqt_kref, destroy_rqtpool);
}
int c4iw_rqtpool_create(struct c4iw_rdev *rdev)
@@ -380,7 +402,7 @@ int c4iw_rqtpool_create(struct c4iw_rdev *rdev)
void c4iw_rqtpool_destroy(struct c4iw_rdev *rdev)
{
- gen_pool_destroy(rdev->rqt_pool);
+ kref_put(&rdev->rqt_kref, destroy_rqtpool);
}
/*
diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index a97055d..b5fab55 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -412,7 +412,6 @@ static void hfi1_cleanup_sdma_notifier(struct hfi1_msix_entry *msix)
static int get_irq_affinity(struct hfi1_devdata *dd,
struct hfi1_msix_entry *msix)
{
- int ret;
cpumask_var_t diff;
struct hfi1_affinity_node *entry;
struct cpu_mask_set *set = NULL;
@@ -424,10 +423,6 @@ static int get_irq_affinity(struct hfi1_devdata *dd,
extra[0] = '\0';
cpumask_clear(&msix->mask);
- ret = zalloc_cpumask_var(&diff, GFP_KERNEL);
- if (!ret)
- return -ENOMEM;
-
entry = node_affinity_lookup(dd->node);
switch (msix->type) {
@@ -458,6 +453,9 @@ static int get_irq_affinity(struct hfi1_devdata *dd,
* finds its CPU here.
*/
if (cpu == -1 && set) {
+ if (!zalloc_cpumask_var(&diff, GFP_KERNEL))
+ return -ENOMEM;
+
if (cpumask_equal(&set->mask, &set->used)) {
/*
* We've used up all the CPUs, bump up the generation
@@ -469,6 +467,8 @@ static int get_irq_affinity(struct hfi1_devdata *dd,
cpumask_andnot(diff, &set->mask, &set->used);
cpu = cpumask_first(diff);
cpumask_set_cpu(cpu, &set->used);
+
+ free_cpumask_var(diff);
}
cpumask_set_cpu(cpu, &msix->mask);
@@ -482,7 +482,6 @@ static int get_irq_affinity(struct hfi1_devdata *dd,
hfi1_setup_sdma_notifier(msix);
}
- free_cpumask_var(diff);
return 0;
}
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index e6a60fa..e6bdd0c 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -5944,6 +5944,7 @@ static void is_sendctxt_err_int(struct hfi1_devdata *dd,
u64 status;
u32 sw_index;
int i = 0;
+ unsigned long irq_flags;
sw_index = dd->hw_to_sw[hw_context];
if (sw_index >= dd->num_send_contexts) {
@@ -5953,10 +5954,12 @@ static void is_sendctxt_err_int(struct hfi1_devdata *dd,
return;
}
sci = &dd->send_contexts[sw_index];
+ spin_lock_irqsave(&dd->sc_lock, irq_flags);
sc = sci->sc;
if (!sc) {
dd_dev_err(dd, "%s: context %u(%u): no sc?\n", __func__,
sw_index, hw_context);
+ spin_unlock_irqrestore(&dd->sc_lock, irq_flags);
return;
}
@@ -5978,6 +5981,7 @@ static void is_sendctxt_err_int(struct hfi1_devdata *dd,
*/
if (sc->type != SC_USER)
queue_work(dd->pport->hfi1_wq, &sc->halt_work);
+ spin_unlock_irqrestore(&dd->sc_lock, irq_flags);
/*
* Update the counters for the corresponding status bits.
diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c
index 46d1475..bd837a0 100644
--- a/drivers/infiniband/hw/hfi1/driver.c
+++ b/drivers/infiniband/hw/hfi1/driver.c
@@ -433,31 +433,43 @@ void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt,
bool do_cnp)
{
struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+ struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
struct ib_other_headers *ohdr = pkt->ohdr;
struct ib_grh *grh = pkt->grh;
u32 rqpn = 0, bth1;
- u16 pkey, rlid, dlid = ib_get_dlid(pkt->hdr);
+ u16 pkey;
+ u32 rlid, slid, dlid = 0;
u8 hdr_type, sc, svc_type;
bool is_mcast = false;
+ /* can be called from prescan */
if (pkt->etype == RHF_RCV_TYPE_BYPASS) {
is_mcast = hfi1_is_16B_mcast(dlid);
pkey = hfi1_16B_get_pkey(pkt->hdr);
sc = hfi1_16B_get_sc(pkt->hdr);
+ dlid = hfi1_16B_get_dlid(pkt->hdr);
+ slid = hfi1_16B_get_slid(pkt->hdr);
hdr_type = HFI1_PKT_TYPE_16B;
} else {
is_mcast = (dlid > be16_to_cpu(IB_MULTICAST_LID_BASE)) &&
(dlid != be16_to_cpu(IB_LID_PERMISSIVE));
pkey = ib_bth_get_pkey(ohdr);
sc = hfi1_9B_get_sc5(pkt->hdr, pkt->rhf);
+ dlid = ib_get_dlid(pkt->hdr);
+ slid = ib_get_slid(pkt->hdr);
hdr_type = HFI1_PKT_TYPE_9B;
}
switch (qp->ibqp.qp_type) {
+ case IB_QPT_UD:
+ dlid = ppd->lid;
+ rlid = slid;
+ rqpn = ib_get_sqpn(pkt->ohdr);
+ svc_type = IB_CC_SVCTYPE_UD;
+ break;
case IB_QPT_SMI:
case IB_QPT_GSI:
- case IB_QPT_UD:
- rlid = ib_get_slid(pkt->hdr);
+ rlid = slid;
rqpn = ib_get_sqpn(pkt->ohdr);
svc_type = IB_CC_SVCTYPE_UD;
break;
@@ -482,7 +494,6 @@ void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt,
dlid, rlid, sc, grh);
if (!is_mcast && (bth1 & IB_BECN_SMASK)) {
- struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
u32 lqpn = bth1 & RVT_QPN_MASK;
u8 sl = ibp->sc_to_sl[sc];
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 32c4826..cac2c62 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1537,13 +1537,13 @@ void set_link_ipg(struct hfi1_pportdata *ppd);
void process_becn(struct hfi1_pportdata *ppd, u8 sl, u32 rlid, u32 lqpn,
u32 rqpn, u8 svc_type);
void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn,
- u32 pkey, u32 slid, u32 dlid, u8 sc5,
+ u16 pkey, u32 slid, u32 dlid, u8 sc5,
const struct ib_grh *old_grh);
void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
- u32 remote_qpn, u32 pkey, u32 slid, u32 dlid,
+ u32 remote_qpn, u16 pkey, u32 slid, u32 dlid,
u8 sc5, const struct ib_grh *old_grh);
typedef void (*hfi1_handle_cnp)(struct hfi1_ibport *ibp, struct rvt_qp *qp,
- u32 remote_qpn, u32 pkey, u32 slid, u32 dlid,
+ u32 remote_qpn, u16 pkey, u32 slid, u32 dlid,
u8 sc5, const struct ib_grh *old_grh);
#define PKEY_CHECK_INVALID -1
@@ -2437,7 +2437,7 @@ static inline void hfi1_make_16b_hdr(struct hfi1_16b_header *hdr,
((slid >> OPA_16B_SLID_SHIFT) << OPA_16B_SLID_HIGH_SHIFT);
lrh2 = (lrh2 & ~OPA_16B_DLID_MASK) |
((dlid >> OPA_16B_DLID_SHIFT) << OPA_16B_DLID_HIGH_SHIFT);
- lrh2 = (lrh2 & ~OPA_16B_PKEY_MASK) | (pkey << OPA_16B_PKEY_SHIFT);
+ lrh2 = (lrh2 & ~OPA_16B_PKEY_MASK) | ((u32)pkey << OPA_16B_PKEY_SHIFT);
lrh2 = (lrh2 & ~OPA_16B_L4_MASK) | l4;
hdr->lrh[0] = lrh0;
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 33eba23..6309edf 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -88,9 +88,9 @@
* pio buffers per ctxt, etc.) Zero means use one user context per CPU.
*/
int num_user_contexts = -1;
-module_param_named(num_user_contexts, num_user_contexts, uint, S_IRUGO);
+module_param_named(num_user_contexts, num_user_contexts, int, 0444);
MODULE_PARM_DESC(
- num_user_contexts, "Set max number of user contexts to use");
+ num_user_contexts, "Set max number of user contexts to use (default: -1 will use the real (non-HT) CPU count)");
uint krcvqs[RXE_NUM_DATA_VL];
int krcvqsset;
@@ -1209,30 +1209,49 @@ static void finalize_asic_data(struct hfi1_devdata *dd,
kfree(ad);
}
-static void __hfi1_free_devdata(struct kobject *kobj)
+/**
+ * hfi1_clean_devdata - cleans up per-unit data structure
+ * @dd: pointer to a valid devdata structure
+ *
+ * It cleans up all data structures set up by
+ * by hfi1_alloc_devdata().
+ */
+static void hfi1_clean_devdata(struct hfi1_devdata *dd)
{
- struct hfi1_devdata *dd =
- container_of(kobj, struct hfi1_devdata, kobj);
struct hfi1_asic_data *ad;
unsigned long flags;
spin_lock_irqsave(&hfi1_devs_lock, flags);
- idr_remove(&hfi1_unit_table, dd->unit);
- list_del(&dd->list);
+ if (!list_empty(&dd->list)) {
+ idr_remove(&hfi1_unit_table, dd->unit);
+ list_del_init(&dd->list);
+ }
ad = release_asic_data(dd);
spin_unlock_irqrestore(&hfi1_devs_lock, flags);
- if (ad)
- finalize_asic_data(dd, ad);
+
+ finalize_asic_data(dd, ad);
free_platform_config(dd);
rcu_barrier(); /* wait for rcu callbacks to complete */
free_percpu(dd->int_counter);
free_percpu(dd->rcv_limit);
free_percpu(dd->send_schedule);
free_percpu(dd->tx_opstats);
+ dd->int_counter = NULL;
+ dd->rcv_limit = NULL;
+ dd->send_schedule = NULL;
+ dd->tx_opstats = NULL;
sdma_clean(dd, dd->num_sdma);
rvt_dealloc_device(&dd->verbs_dev.rdi);
}
+static void __hfi1_free_devdata(struct kobject *kobj)
+{
+ struct hfi1_devdata *dd =
+ container_of(kobj, struct hfi1_devdata, kobj);
+
+ hfi1_clean_devdata(dd);
+}
+
static struct kobj_type hfi1_devdata_type = {
.release = __hfi1_free_devdata,
};
@@ -1265,6 +1284,8 @@ struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, size_t extra)
return ERR_PTR(-ENOMEM);
dd->num_pports = nports;
dd->pport = (struct hfi1_pportdata *)(dd + 1);
+ dd->pcidev = pdev;
+ pci_set_drvdata(pdev, dd);
INIT_LIST_HEAD(&dd->list);
idr_preload(GFP_KERNEL);
@@ -1331,9 +1352,7 @@ struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, size_t extra)
return dd;
bail:
- if (!list_empty(&dd->list))
- list_del_init(&dd->list);
- rvt_dealloc_device(&dd->verbs_dev.rdi);
+ hfi1_clean_devdata(dd);
return ERR_PTR(ret);
}
diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 83d66e8..c1c9829 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -163,9 +163,6 @@ int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev)
resource_size_t addr;
int ret = 0;
- dd->pcidev = pdev;
- pci_set_drvdata(pdev, dd);
-
addr = pci_resource_start(pdev, 0);
len = pci_resource_len(pdev, 0);
diff --git a/drivers/infiniband/hw/hfi1/platform.c b/drivers/infiniband/hw/hfi1/platform.c
index d486355..cbf7faa 100644
--- a/drivers/infiniband/hw/hfi1/platform.c
+++ b/drivers/infiniband/hw/hfi1/platform.c
@@ -199,6 +199,7 @@ void free_platform_config(struct hfi1_devdata *dd)
{
/* Release memory allocated for eprom or fallback file read. */
kfree(dd->platform_config.data);
+ dd->platform_config.data = NULL;
}
void get_port_type(struct hfi1_pportdata *ppd)
diff --git a/drivers/infiniband/hw/hfi1/qsfp.c b/drivers/infiniband/hw/hfi1/qsfp.c
index 1869f63..b596699 100644
--- a/drivers/infiniband/hw/hfi1/qsfp.c
+++ b/drivers/infiniband/hw/hfi1/qsfp.c
@@ -204,6 +204,8 @@ static void clean_i2c_bus(struct hfi1_i2c_bus *bus)
void clean_up_i2c(struct hfi1_devdata *dd, struct hfi1_asic_data *ad)
{
+ if (!ad)
+ return;
clean_i2c_bus(ad->i2c_bus0);
ad->i2c_bus0 = NULL;
clean_i2c_bus(ad->i2c_bus1);
diff --git a/drivers/infiniband/hw/hfi1/ruc.c b/drivers/infiniband/hw/hfi1/ruc.c
index 3daa94b..c0071ca 100644
--- a/drivers/infiniband/hw/hfi1/ruc.c
+++ b/drivers/infiniband/hw/hfi1/ruc.c
@@ -733,6 +733,20 @@ static inline void hfi1_make_ruc_bth(struct rvt_qp *qp,
ohdr->bth[2] = cpu_to_be32(bth2);
}
+/**
+ * hfi1_make_ruc_header_16B - build a 16B header
+ * @qp: the queue pair
+ * @ohdr: a pointer to the destination header memory
+ * @bth0: bth0 passed in from the RC/UC builder
+ * @bth2: bth2 passed in from the RC/UC builder
+ * @middle: non zero implies indicates ahg "could" be used
+ * @ps: the current packet state
+ *
+ * This routine may disarm ahg under these situations:
+ * - packet needs a GRH
+ * - BECN needed
+ * - migration state not IB_MIG_MIGRATED
+ */
static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
struct ib_other_headers *ohdr,
u32 bth0, u32 bth2, int middle,
@@ -777,6 +791,12 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
else
middle = 0;
+ if (qp->s_flags & RVT_S_ECN) {
+ qp->s_flags &= ~RVT_S_ECN;
+ /* we recently received a FECN, so return a BECN */
+ becn = true;
+ middle = 0;
+ }
if (middle)
build_ahg(qp, bth2);
else
@@ -784,11 +804,6 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
bth0 |= pkey;
bth0 |= extra_bytes << 20;
- if (qp->s_flags & RVT_S_ECN) {
- qp->s_flags &= ~RVT_S_ECN;
- /* we recently received a FECN, so return a BECN */
- becn = true;
- }
hfi1_make_ruc_bth(qp, ohdr, bth0, bth1, bth2);
if (!ppd->lid)
@@ -806,6 +821,20 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
pkey, becn, 0, l4, priv->s_sc);
}
+/**
+ * hfi1_make_ruc_header_9B - build a 9B header
+ * @qp: the queue pair
+ * @ohdr: a pointer to the destination header memory
+ * @bth0: bth0 passed in from the RC/UC builder
+ * @bth2: bth2 passed in from the RC/UC builder
+ * @middle: non zero implies indicates ahg "could" be used
+ * @ps: the current packet state
+ *
+ * This routine may disarm ahg under these situations:
+ * - packet needs a GRH
+ * - BECN needed
+ * - migration state not IB_MIG_MIGRATED
+ */
static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp,
struct ib_other_headers *ohdr,
u32 bth0, u32 bth2, int middle,
@@ -839,6 +868,12 @@ static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp,
else
middle = 0;
+ if (qp->s_flags & RVT_S_ECN) {
+ qp->s_flags &= ~RVT_S_ECN;
+ /* we recently received a FECN, so return a BECN */
+ bth1 |= (IB_BECN_MASK << IB_BECN_SHIFT);
+ middle = 0;
+ }
if (middle)
build_ahg(qp, bth2);
else
@@ -846,11 +881,6 @@ static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp,
bth0 |= pkey;
bth0 |= extra_bytes << 20;
- if (qp->s_flags & RVT_S_ECN) {
- qp->s_flags &= ~RVT_S_ECN;
- /* we recently received a FECN, so return a BECN */
- bth1 |= (IB_BECN_MASK << IB_BECN_SHIFT);
- }
hfi1_make_ruc_bth(qp, ohdr, bth0, bth1, bth2);
hfi1_make_ib_hdr(&ps->s_txreq->phdr.hdr.ibh,
lrh0,
diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c
index bcf3b0b..69c17a5 100644
--- a/drivers/infiniband/hw/hfi1/ud.c
+++ b/drivers/infiniband/hw/hfi1/ud.c
@@ -628,7 +628,7 @@ int hfi1_lookup_pkey_idx(struct hfi1_ibport *ibp, u16 pkey)
}
void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
- u32 remote_qpn, u32 pkey, u32 slid, u32 dlid,
+ u32 remote_qpn, u16 pkey, u32 slid, u32 dlid,
u8 sc5, const struct ib_grh *old_grh)
{
u64 pbc, pbc_flags = 0;
@@ -687,7 +687,7 @@ void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
}
void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn,
- u32 pkey, u32 slid, u32 dlid, u8 sc5,
+ u16 pkey, u32 slid, u32 dlid, u8 sc5,
const struct ib_grh *old_grh)
{
u64 pbc, pbc_flags = 0;
diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c
index 14734d0..3a485f5 100644
--- a/drivers/infiniband/hw/hns/hns_roce_cq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_cq.c
@@ -377,6 +377,7 @@ struct ib_cq *hns_roce_ib_create_cq(struct ib_device *ib_dev,
hr_cq->set_ci_db = hr_cq->db.db_record;
*hr_cq->set_ci_db = 0;
+ hr_cq->db_en = 1;
}
/* Init mmt table and write buff address to mtt table */
diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c
index 0eeabfb..63b5b3e 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hem.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hem.c
@@ -912,7 +912,7 @@ int hns_roce_init_hem_table(struct hns_roce_dev *hr_dev,
obj_per_chunk = buf_chunk_size / obj_size;
num_hem = (nobj + obj_per_chunk - 1) / obj_per_chunk;
bt_chunk_num = bt_chunk_size / 8;
- if (table->type >= HEM_TYPE_MTT)
+ if (type >= HEM_TYPE_MTT)
num_bt_l0 = bt_chunk_num;
table->hem = kcalloc(num_hem, sizeof(*table->hem),
@@ -920,7 +920,7 @@ int hns_roce_init_hem_table(struct hns_roce_dev *hr_dev,
if (!table->hem)
goto err_kcalloc_hem_buf;
- if (check_whether_bt_num_3(table->type, hop_num)) {
+ if (check_whether_bt_num_3(type, hop_num)) {
unsigned long num_bt_l1;
num_bt_l1 = (num_hem + bt_chunk_num - 1) /
@@ -939,8 +939,8 @@ int hns_roce_init_hem_table(struct hns_roce_dev *hr_dev,
goto err_kcalloc_l1_dma;
}
- if (check_whether_bt_num_2(table->type, hop_num) ||
- check_whether_bt_num_3(table->type, hop_num)) {
+ if (check_whether_bt_num_2(type, hop_num) ||
+ check_whether_bt_num_3(type, hop_num)) {
table->bt_l0 = kcalloc(num_bt_l0, sizeof(*table->bt_l0),
GFP_KERNEL);
if (!table->bt_l0)
@@ -1039,14 +1039,14 @@ void hns_roce_cleanup_hem_table(struct hns_roce_dev *hr_dev,
void hns_roce_cleanup_hem(struct hns_roce_dev *hr_dev)
{
hns_roce_cleanup_hem_table(hr_dev, &hr_dev->cq_table.table);
- hns_roce_cleanup_hem_table(hr_dev, &hr_dev->qp_table.irrl_table);
if (hr_dev->caps.trrl_entry_sz)
hns_roce_cleanup_hem_table(hr_dev,
&hr_dev->qp_table.trrl_table);
+ hns_roce_cleanup_hem_table(hr_dev, &hr_dev->qp_table.irrl_table);
hns_roce_cleanup_hem_table(hr_dev, &hr_dev->qp_table.qp_table);
hns_roce_cleanup_hem_table(hr_dev, &hr_dev->mr_table.mtpt_table);
- hns_roce_cleanup_hem_table(hr_dev, &hr_dev->mr_table.mtt_table);
if (hns_roce_check_whether_mhop(hr_dev, HEM_TYPE_CQE))
hns_roce_cleanup_hem_table(hr_dev,
&hr_dev->mr_table.mtt_cqe_table);
+ hns_roce_cleanup_hem_table(hr_dev, &hr_dev->mr_table.mtt_table);
}
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
index 47e1b6a..8013d69 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
@@ -722,6 +722,7 @@ static int hns_roce_v1_rsv_lp_qp(struct hns_roce_dev *hr_dev)
free_mr->mr_free_pd = to_hr_pd(pd);
free_mr->mr_free_pd->ibpd.device = &hr_dev->ib_dev;
free_mr->mr_free_pd->ibpd.uobject = NULL;
+ free_mr->mr_free_pd->ibpd.__internal_mr = NULL;
atomic_set(&free_mr->mr_free_pd->ibpd.usecnt, 0);
attr.qp_access_flags = IB_ACCESS_REMOTE_WRITE;
@@ -1036,7 +1037,7 @@ static void hns_roce_v1_mr_free_work_fn(struct work_struct *work)
do {
ret = hns_roce_v1_poll_cq(&mr_free_cq->ib_cq, ne, wc);
- if (ret < 0) {
+ if (ret < 0 && hr_qp) {
dev_err(dev,
"(qp:0x%lx) starts, Poll cqe failed(%d) for mr 0x%x free! Remain %d cqe\n",
hr_qp->qpn, ret, hr_mr->key, ne);
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index 8b84ab7..1f0965bb 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -71,6 +71,11 @@ static int set_rwqe_data_seg(struct ib_qp *ibqp, struct ib_send_wr *wr,
return -EINVAL;
}
+ if (wr->opcode == IB_WR_RDMA_READ) {
+ dev_err(hr_dev->dev, "Not support inline data!\n");
+ return -EINVAL;
+ }
+
for (i = 0; i < wr->num_sge; i++) {
memcpy(wqe, ((void *)wr->sg_list[i].addr),
wr->sg_list[i].length);
@@ -137,8 +142,8 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
unsigned long flags;
unsigned int ind;
void *wqe = NULL;
- u32 tmp_len = 0;
bool loopback;
+ u32 tmp_len;
int ret = 0;
u8 *smac;
int nreq;
@@ -148,7 +153,7 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
ibqp->qp_type != IB_QPT_GSI &&
ibqp->qp_type != IB_QPT_UD)) {
dev_err(dev, "Not supported QP(0x%x)type!\n", ibqp->qp_type);
- *bad_wr = NULL;
+ *bad_wr = wr;
return -EOPNOTSUPP;
}
@@ -182,7 +187,9 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
qp->sq.wrid[(qp->sq.head + nreq) & (qp->sq.wqe_cnt - 1)] =
wr->wr_id;
- owner_bit = ~(qp->sq.head >> ilog2(qp->sq.wqe_cnt)) & 0x1;
+ owner_bit =
+ ~(((qp->sq.head + nreq) >> ilog2(qp->sq.wqe_cnt)) & 0x1);
+ tmp_len = 0;
/* Corresponding to the QP type, wqe process separately */
if (ibqp->qp_type == IB_QPT_GSI) {
@@ -456,6 +463,7 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
} else {
dev_err(dev, "Illegal qp_type(0x%x)\n", ibqp->qp_type);
spin_unlock_irqrestore(&qp->sq.lock, flags);
+ *bad_wr = wr;
return -EOPNOTSUPP;
}
}
@@ -540,16 +548,20 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
}
if (i < hr_qp->rq.max_gs) {
- dseg[i].lkey = cpu_to_le32(HNS_ROCE_INVALID_LKEY);
- dseg[i].addr = 0;
+ dseg->lkey = cpu_to_le32(HNS_ROCE_INVALID_LKEY);
+ dseg->addr = 0;
}
/* rq support inline data */
- sge_list = hr_qp->rq_inl_buf.wqe_list[ind].sg_list;
- hr_qp->rq_inl_buf.wqe_list[ind].sge_cnt = (u32)wr->num_sge;
- for (i = 0; i < wr->num_sge; i++) {
- sge_list[i].addr = (void *)(u64)wr->sg_list[i].addr;
- sge_list[i].len = wr->sg_list[i].length;
+ if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_RQ_INLINE) {
+ sge_list = hr_qp->rq_inl_buf.wqe_list[ind].sg_list;
+ hr_qp->rq_inl_buf.wqe_list[ind].sge_cnt =
+ (u32)wr->num_sge;
+ for (i = 0; i < wr->num_sge; i++) {
+ sge_list[i].addr =
+ (void *)(u64)wr->sg_list[i].addr;
+ sge_list[i].len = wr->sg_list[i].length;
+ }
}
hr_qp->rq.wrid[ind] = wr->wr_id;
@@ -606,6 +618,8 @@ static void hns_roce_free_cmq_desc(struct hns_roce_dev *hr_dev,
dma_unmap_single(hr_dev->dev, ring->desc_dma_addr,
ring->desc_num * sizeof(struct hns_roce_cmq_desc),
DMA_BIDIRECTIONAL);
+
+ ring->desc_dma_addr = 0;
kfree(ring->desc);
}
@@ -1074,6 +1088,7 @@ static int hns_roce_v2_profile(struct hns_roce_dev *hr_dev)
if (ret) {
dev_err(hr_dev->dev, "Configure global param fail, ret = %d.\n",
ret);
+ return ret;
}
/* Get pf resource owned by every pf */
@@ -1365,6 +1380,8 @@ static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr,
roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_PA_S,
mr->type == MR_TYPE_MR ? 0 : 1);
+ roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_INNER_PA_VLD_S,
+ 1);
mpt_entry->byte_12_mw_pa = cpu_to_le32(mpt_entry->byte_12_mw_pa);
mpt_entry->len_l = cpu_to_le32(lower_32_bits(mr->size));
@@ -2162,6 +2179,7 @@ static void modify_qp_reset_to_init(struct ib_qp *ibqp,
struct hns_roce_v2_qp_context *context,
struct hns_roce_v2_qp_context *qpc_mask)
{
+ struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
/*
@@ -2274,7 +2292,8 @@ static void modify_qp_reset_to_init(struct ib_qp *ibqp,
context->rq_db_record_addr = hr_qp->rdb.dma >> 32;
qpc_mask->rq_db_record_addr = 0;
- roce_set_bit(context->byte_76_srqn_op_en, V2_QPC_BYTE_76_RQIE_S, 1);
+ roce_set_bit(context->byte_76_srqn_op_en, V2_QPC_BYTE_76_RQIE_S,
+ (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_RQ_INLINE) ? 1 : 0);
roce_set_bit(qpc_mask->byte_76_srqn_op_en, V2_QPC_BYTE_76_RQIE_S, 0);
roce_set_field(context->byte_80_rnr_rx_cqn, V2_QPC_BYTE_80_RX_CQN_M,
@@ -2592,10 +2611,12 @@ static void modify_qp_init_to_init(struct ib_qp *ibqp,
roce_set_field(qpc_mask->byte_4_sqpn_tst, V2_QPC_BYTE_4_SQPN_M,
V2_QPC_BYTE_4_SQPN_S, 0);
- roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
- V2_QPC_BYTE_56_DQPN_S, hr_qp->qpn);
- roce_set_field(qpc_mask->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
- V2_QPC_BYTE_56_DQPN_S, 0);
+ if (attr_mask & IB_QP_DEST_QPN) {
+ roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
+ V2_QPC_BYTE_56_DQPN_S, hr_qp->qpn);
+ roce_set_field(qpc_mask->byte_56_dqpn_err,
+ V2_QPC_BYTE_56_DQPN_M, V2_QPC_BYTE_56_DQPN_S, 0);
+ }
roce_set_field(context->byte_168_irrl_idx,
V2_QPC_BYTE_168_SQ_SHIFT_BAK_M,
V2_QPC_BYTE_168_SQ_SHIFT_BAK_S,
@@ -2650,8 +2671,7 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp,
return -EINVAL;
}
- if ((attr_mask & IB_QP_ALT_PATH) || (attr_mask & IB_QP_ACCESS_FLAGS) ||
- (attr_mask & IB_QP_PKEY_INDEX) || (attr_mask & IB_QP_QKEY)) {
+ if (attr_mask & IB_QP_ALT_PATH) {
dev_err(dev, "INIT2RTR attr_mask (0x%x) error\n", attr_mask);
return -EINVAL;
}
@@ -2800,10 +2820,12 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp,
V2_QPC_BYTE_140_RR_MAX_S, 0);
}
- roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
- V2_QPC_BYTE_56_DQPN_S, attr->dest_qp_num);
- roce_set_field(qpc_mask->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
- V2_QPC_BYTE_56_DQPN_S, 0);
+ if (attr_mask & IB_QP_DEST_QPN) {
+ roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_DQPN_M,
+ V2_QPC_BYTE_56_DQPN_S, attr->dest_qp_num);
+ roce_set_field(qpc_mask->byte_56_dqpn_err,
+ V2_QPC_BYTE_56_DQPN_M, V2_QPC_BYTE_56_DQPN_S, 0);
+ }
/* Configure GID index */
port_num = rdma_ah_get_port_num(&attr->ah_attr);
@@ -2845,7 +2867,7 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp,
if (ibqp->qp_type == IB_QPT_GSI || ibqp->qp_type == IB_QPT_UD)
roce_set_field(context->byte_24_mtu_tc, V2_QPC_BYTE_24_MTU_M,
V2_QPC_BYTE_24_MTU_S, IB_MTU_4096);
- else
+ else if (attr_mask & IB_QP_PATH_MTU)
roce_set_field(context->byte_24_mtu_tc, V2_QPC_BYTE_24_MTU_M,
V2_QPC_BYTE_24_MTU_S, attr->path_mtu);
@@ -2922,11 +2944,9 @@ static int modify_qp_rtr_to_rts(struct ib_qp *ibqp,
return -EINVAL;
}
- /* If exist optional param, return error */
- if ((attr_mask & IB_QP_ALT_PATH) || (attr_mask & IB_QP_ACCESS_FLAGS) ||
- (attr_mask & IB_QP_QKEY) || (attr_mask & IB_QP_PATH_MIG_STATE) ||
- (attr_mask & IB_QP_CUR_STATE) ||
- (attr_mask & IB_QP_MIN_RNR_TIMER)) {
+ /* Not support alternate path and path migration */
+ if ((attr_mask & IB_QP_ALT_PATH) ||
+ (attr_mask & IB_QP_PATH_MIG_STATE)) {
dev_err(dev, "RTR2RTS attr_mask (0x%x)error\n", attr_mask);
return -EINVAL;
}
@@ -3161,7 +3181,8 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp,
(cur_state == IB_QPS_RTR && new_state == IB_QPS_ERR) ||
(cur_state == IB_QPS_RTS && new_state == IB_QPS_ERR) ||
(cur_state == IB_QPS_SQD && new_state == IB_QPS_ERR) ||
- (cur_state == IB_QPS_SQE && new_state == IB_QPS_ERR)) {
+ (cur_state == IB_QPS_SQE && new_state == IB_QPS_ERR) ||
+ (cur_state == IB_QPS_ERR && new_state == IB_QPS_ERR)) {
/* Nothing */
;
} else {
@@ -4478,7 +4499,7 @@ static int hns_roce_v2_create_eq(struct hns_roce_dev *hr_dev,
ret = hns_roce_cmd_mbox(hr_dev, mailbox->dma, 0, eq->eqn, 0,
eq_cmd, HNS_ROCE_CMD_TIMEOUT_MSECS);
if (ret) {
- dev_err(dev, "[mailbox cmd] creat eqc failed.\n");
+ dev_err(dev, "[mailbox cmd] create eqc failed.\n");
goto err_cmd_mbox;
}
@@ -4694,6 +4715,8 @@ static const struct pci_device_id hns_roce_hw_v2_pci_tbl[] = {
{0, }
};
+MODULE_DEVICE_TABLE(pci, hns_roce_hw_v2_pci_tbl);
+
static int hns_roce_hw_v2_get_cfg(struct hns_roce_dev *hr_dev,
struct hnae3_handle *handle)
{
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index 9d48bc0..96fb6a9 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -199,7 +199,7 @@ static int hns_roce_query_device(struct ib_device *ib_dev,
memset(props, 0, sizeof(*props));
- props->sys_image_guid = cpu_to_be32(hr_dev->sys_image_guid);
+ props->sys_image_guid = cpu_to_be64(hr_dev->sys_image_guid);
props->max_mr_size = (u64)(~(0ULL));
props->page_size_cap = hr_dev->caps.page_size_cap;
props->vendor_id = hr_dev->vendor_id;
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index e289a92..baaf906 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -620,7 +620,7 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev,
to_hr_ucontext(ib_pd->uobject->context),
ucmd.db_addr, &hr_qp->rdb);
if (ret) {
- dev_err(dev, "rp record doorbell map failed!\n");
+ dev_err(dev, "rq record doorbell map failed!\n");
goto err_mtt;
}
}
@@ -660,6 +660,7 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev,
goto err_rq_sge_list;
}
*hr_qp->rdb.db_record = 0;
+ hr_qp->rdb_en = 1;
}
/* Allocate QP buf */
@@ -955,7 +956,14 @@ int hns_roce_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
}
if (cur_state == new_state && cur_state == IB_QPS_RESET) {
- ret = 0;
+ if (hr_dev->caps.min_wqes) {
+ ret = -EPERM;
+ dev_err(dev, "cur_state=%d new_state=%d\n", cur_state,
+ new_state);
+ } else {
+ ret = 0;
+ }
+
goto out;
}
diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h
index d5d8c1b..2f2b442 100644
--- a/drivers/infiniband/hw/i40iw/i40iw.h
+++ b/drivers/infiniband/hw/i40iw/i40iw.h
@@ -207,6 +207,7 @@ struct i40iw_msix_vector {
u32 irq;
u32 cpu_affinity;
u32 ceq_id;
+ cpumask_t mask;
};
struct l2params_work {
diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c
index 4cfa8f4..f7c6fd9 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_cm.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c
@@ -2093,7 +2093,7 @@ static int i40iw_addr_resolve_neigh_ipv6(struct i40iw_device *iwdev,
if (netif_is_bond_slave(netdev))
netdev = netdev_master_upper_dev_get(netdev);
- neigh = dst_neigh_lookup(dst, &dst_addr);
+ neigh = dst_neigh_lookup(dst, dst_addr.sin6_addr.in6_u.u6_addr32);
rcu_read_lock();
if (neigh) {
diff --git a/drivers/infiniband/hw/i40iw/i40iw_hw.c b/drivers/infiniband/hw/i40iw/i40iw_hw.c
index 6139836..c9f62ca 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_hw.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_hw.c
@@ -331,7 +331,7 @@ void i40iw_process_aeq(struct i40iw_device *iwdev)
switch (info->ae_id) {
case I40IW_AE_LLP_FIN_RECEIVED:
if (qp->term_flags)
- continue;
+ break;
if (atomic_inc_return(&iwqp->close_timer_started) == 1) {
iwqp->hw_tcp_state = I40IW_TCP_STATE_CLOSE_WAIT;
if ((iwqp->hw_tcp_state == I40IW_TCP_STATE_CLOSE_WAIT) &&
@@ -360,7 +360,7 @@ void i40iw_process_aeq(struct i40iw_device *iwdev)
break;
case I40IW_AE_LLP_CONNECTION_RESET:
if (atomic_read(&iwqp->close_timer_started))
- continue;
+ break;
i40iw_cm_disconn(iwqp);
break;
case I40IW_AE_QP_SUSPEND_COMPLETE:
diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c
index 9cd0d3e..05001e6 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_main.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_main.c
@@ -687,7 +687,6 @@ static enum i40iw_status_code i40iw_configure_ceq_vector(struct i40iw_device *iw
struct i40iw_msix_vector *msix_vec)
{
enum i40iw_status_code status;
- cpumask_t mask;
if (iwdev->msix_shared && !ceq_id) {
tasklet_init(&iwdev->dpc_tasklet, i40iw_dpc, (unsigned long)iwdev);
@@ -697,9 +696,9 @@ static enum i40iw_status_code i40iw_configure_ceq_vector(struct i40iw_device *iw
status = request_irq(msix_vec->irq, i40iw_ceq_handler, 0, "CEQ", iwceq);
}
- cpumask_clear(&mask);
- cpumask_set_cpu(msix_vec->cpu_affinity, &mask);
- irq_set_affinity_hint(msix_vec->irq, &mask);
+ cpumask_clear(&msix_vec->mask);
+ cpumask_set_cpu(msix_vec->cpu_affinity, &msix_vec->mask);
+ irq_set_affinity_hint(msix_vec->irq, &msix_vec->mask);
if (status) {
i40iw_pr_err("ceq irq config fail\n");
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 40e4f5a..68679ad 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -394,6 +394,7 @@ static struct i40iw_pbl *i40iw_get_pbl(unsigned long va,
list_for_each_entry(iwpbl, pbl_list, list) {
if (iwpbl->user_base == va) {
+ iwpbl->on_list = false;
list_del(&iwpbl->list);
return iwpbl;
}
@@ -614,6 +615,7 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd,
return ERR_PTR(-ENOMEM);
iwqp = (struct i40iw_qp *)mem;
+ iwqp->allocated_buffer = mem;
qp = &iwqp->sc_qp;
qp->back_qp = (void *)iwqp;
qp->push_idx = I40IW_INVALID_PUSH_PAGE_INDEX;
@@ -642,7 +644,6 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd,
goto error;
}
- iwqp->allocated_buffer = mem;
iwqp->iwdev = iwdev;
iwqp->iwpd = iwpd;
iwqp->ibqp.qp_num = qp_num;
@@ -1898,6 +1899,7 @@ static struct ib_mr *i40iw_reg_user_mr(struct ib_pd *pd,
goto error;
spin_lock_irqsave(&ucontext->qp_reg_mem_list_lock, flags);
list_add_tail(&iwpbl->list, &ucontext->qp_reg_mem_list);
+ iwpbl->on_list = true;
spin_unlock_irqrestore(&ucontext->qp_reg_mem_list_lock, flags);
break;
case IW_MEMREG_TYPE_CQ:
@@ -1908,6 +1910,7 @@ static struct ib_mr *i40iw_reg_user_mr(struct ib_pd *pd,
spin_lock_irqsave(&ucontext->cq_reg_mem_list_lock, flags);
list_add_tail(&iwpbl->list, &ucontext->cq_reg_mem_list);
+ iwpbl->on_list = true;
spin_unlock_irqrestore(&ucontext->cq_reg_mem_list_lock, flags);
break;
case IW_MEMREG_TYPE_MEM:
@@ -2045,14 +2048,18 @@ static void i40iw_del_memlist(struct i40iw_mr *iwmr,
switch (iwmr->type) {
case IW_MEMREG_TYPE_CQ:
spin_lock_irqsave(&ucontext->cq_reg_mem_list_lock, flags);
- if (!list_empty(&ucontext->cq_reg_mem_list))
+ if (iwpbl->on_list) {
+ iwpbl->on_list = false;
list_del(&iwpbl->list);
+ }
spin_unlock_irqrestore(&ucontext->cq_reg_mem_list_lock, flags);
break;
case IW_MEMREG_TYPE_QP:
spin_lock_irqsave(&ucontext->qp_reg_mem_list_lock, flags);
- if (!list_empty(&ucontext->qp_reg_mem_list))
+ if (iwpbl->on_list) {
+ iwpbl->on_list = false;
list_del(&iwpbl->list);
+ }
spin_unlock_irqrestore(&ucontext->qp_reg_mem_list_lock, flags);
break;
default:
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.h b/drivers/infiniband/hw/i40iw/i40iw_verbs.h
index 9067443..76cf173 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.h
@@ -78,6 +78,7 @@ struct i40iw_pbl {
};
bool pbl_allocated;
+ bool on_list;
u64 user_base;
struct i40iw_pble_alloc pble_alloc;
struct i40iw_mr *iwmr;
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index 17f4f15..61d8b06 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -346,7 +346,7 @@ int mlx4_ib_umem_calc_optimal_mtt_size(struct ib_umem *umem, u64 start_va,
/* Add to the first block the misalignment that it suffers from. */
total_len += (first_block_start & ((1ULL << block_shift) - 1ULL));
last_block_end = current_block_start + current_block_len;
- last_block_aligned_end = round_up(last_block_end, 1 << block_shift);
+ last_block_aligned_end = round_up(last_block_end, 1ULL << block_shift);
total_len += (last_block_aligned_end - last_block_end);
if (total_len & ((1ULL << block_shift) - 1ULL))
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 50af891..199648a 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -673,7 +673,8 @@ static int set_qp_rss(struct mlx4_ib_dev *dev, struct mlx4_ib_rss *rss_ctx,
MLX4_IB_RX_HASH_SRC_PORT_TCP |
MLX4_IB_RX_HASH_DST_PORT_TCP |
MLX4_IB_RX_HASH_SRC_PORT_UDP |
- MLX4_IB_RX_HASH_DST_PORT_UDP)) {
+ MLX4_IB_RX_HASH_DST_PORT_UDP |
+ MLX4_IB_RX_HASH_INNER)) {
pr_debug("RX Hash fields_mask has unsupported mask (0x%llx)\n",
ucmd->rx_hash_fields_mask);
return (-EOPNOTSUPP);
diff --git a/drivers/infiniband/hw/mlx5/Kconfig b/drivers/infiniband/hw/mlx5/Kconfig
index bce263b..fb4d77b 100644
--- a/drivers/infiniband/hw/mlx5/Kconfig
+++ b/drivers/infiniband/hw/mlx5/Kconfig
@@ -1,6 +1,7 @@
config MLX5_INFINIBAND
tristate "Mellanox Connect-IB HCA support"
depends on NETDEVICES && ETHERNET && PCI && MLX5_CORE
+ depends on INFINIBAND_USER_ACCESS || INFINIBAND_USER_ACCESS=n
---help---
This driver provides low-level InfiniBand support for
Mellanox Connect-IB PCI Express host channel adapters (HCAs).
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index daa919e..69716a7 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -52,7 +52,6 @@
#include <linux/mlx5/port.h>
#include <linux/mlx5/vport.h>
#include <linux/mlx5/fs.h>
-#include <linux/mlx5/fs_helpers.h>
#include <linux/list.h>
#include <rdma/ib_smi.h>
#include <rdma/ib_umem.h>
@@ -180,7 +179,7 @@ static int mlx5_netdev_event(struct notifier_block *this,
if (rep_ndev == ndev)
roce->netdev = (event == NETDEV_UNREGISTER) ?
NULL : ndev;
- } else if (ndev->dev.parent == &ibdev->mdev->pdev->dev) {
+ } else if (ndev->dev.parent == &mdev->pdev->dev) {
roce->netdev = (event == NETDEV_UNREGISTER) ?
NULL : ndev;
}
@@ -2417,7 +2416,7 @@ static void set_proto(void *outer_c, void *outer_v, u8 mask, u8 val)
MLX5_SET(fte_match_set_lyr_2_4, outer_v, ip_protocol, val);
}
-static void set_flow_label(void *misc_c, void *misc_v, u8 mask, u8 val,
+static void set_flow_label(void *misc_c, void *misc_v, u32 mask, u32 val,
bool inner)
{
if (inner) {
@@ -4757,7 +4756,7 @@ mlx5_ib_get_vector_affinity(struct ib_device *ibdev, int comp_vector)
{
struct mlx5_ib_dev *dev = to_mdev(ibdev);
- return mlx5_get_vector_affinity(dev->mdev, comp_vector);
+ return mlx5_get_vector_affinity_hint(dev->mdev, comp_vector);
}
/* The mlx5_ib_multiport_mutex should be held when calling this function */
@@ -5427,9 +5426,7 @@ static void mlx5_ib_stage_cong_debugfs_cleanup(struct mlx5_ib_dev *dev)
static int mlx5_ib_stage_uar_init(struct mlx5_ib_dev *dev)
{
dev->mdev->priv.uar = mlx5_get_uars_page(dev->mdev);
- if (!dev->mdev->priv.uar)
- return -ENOMEM;
- return 0;
+ return PTR_ERR_OR_ZERO(dev->mdev->priv.uar);
}
static void mlx5_ib_stage_uar_cleanup(struct mlx5_ib_dev *dev)
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 1520a2f..90a9c46 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -866,25 +866,28 @@ static int mr_umem_get(struct ib_pd *pd, u64 start, u64 length,
int *order)
{
struct mlx5_ib_dev *dev = to_mdev(pd->device);
+ struct ib_umem *u;
int err;
- *umem = ib_umem_get(pd->uobject->context, start, length,
- access_flags, 0);
- err = PTR_ERR_OR_ZERO(*umem);
+ *umem = NULL;
+
+ u = ib_umem_get(pd->uobject->context, start, length, access_flags, 0);
+ err = PTR_ERR_OR_ZERO(u);
if (err) {
- *umem = NULL;
- mlx5_ib_err(dev, "umem get failed (%d)\n", err);
+ mlx5_ib_dbg(dev, "umem get failed (%d)\n", err);
return err;
}
- mlx5_ib_cont_pages(*umem, start, MLX5_MKEY_PAGE_SHIFT_MASK, npages,
+ mlx5_ib_cont_pages(u, start, MLX5_MKEY_PAGE_SHIFT_MASK, npages,
page_shift, ncont, order);
if (!*npages) {
mlx5_ib_warn(dev, "avoid zero region\n");
- ib_umem_release(*umem);
+ ib_umem_release(u);
return -EINVAL;
}
+ *umem = u;
+
mlx5_ib_dbg(dev, "npages %d, ncont %d, order %d, page_shift %d\n",
*npages, *ncont, *order, *page_shift);
@@ -1458,13 +1461,12 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
int access_flags = flags & IB_MR_REREG_ACCESS ?
new_access_flags :
mr->access_flags;
- u64 addr = (flags & IB_MR_REREG_TRANS) ? virt_addr : mr->umem->address;
- u64 len = (flags & IB_MR_REREG_TRANS) ? length : mr->umem->length;
int page_shift = 0;
int upd_flags = 0;
int npages = 0;
int ncont = 0;
int order = 0;
+ u64 addr, len;
int err;
mlx5_ib_dbg(dev, "start 0x%llx, virt_addr 0x%llx, length 0x%llx, access_flags 0x%x\n",
@@ -1472,6 +1474,17 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
atomic_sub(mr->npages, &dev->mdev->priv.reg_pages);
+ if (!mr->umem)
+ return -EINVAL;
+
+ if (flags & IB_MR_REREG_TRANS) {
+ addr = virt_addr;
+ len = length;
+ } else {
+ addr = mr->umem->address;
+ len = mr->umem->length;
+ }
+
if (flags != IB_MR_REREG_PD) {
/*
* Replace umem. This needs to be done whether or not UMR is
@@ -1479,6 +1492,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
*/
flags |= IB_MR_REREG_TRANS;
ib_umem_release(mr->umem);
+ mr->umem = NULL;
err = mr_umem_get(pd, addr, len, access_flags, &mr->umem,
&npages, &page_shift, &ncont, &order);
if (err)
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 7ed4b70..2193dc1 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -259,7 +259,11 @@ static int set_rq_size(struct mlx5_ib_dev *dev, struct ib_qp_cap *cap,
} else {
if (ucmd) {
qp->rq.wqe_cnt = ucmd->rq_wqe_count;
+ if (ucmd->rq_wqe_shift > BITS_PER_BYTE * sizeof(ucmd->rq_wqe_shift))
+ return -EINVAL;
qp->rq.wqe_shift = ucmd->rq_wqe_shift;
+ if ((1 << qp->rq.wqe_shift) / sizeof(struct mlx5_wqe_data_seg) < qp->wq_sig)
+ return -EINVAL;
qp->rq.max_gs = (1 << qp->rq.wqe_shift) / sizeof(struct mlx5_wqe_data_seg) - qp->wq_sig;
qp->rq.max_post = qp->rq.wqe_cnt;
} else {
@@ -480,11 +484,6 @@ static int qp_has_rq(struct ib_qp_init_attr *attr)
return 1;
}
-static int first_med_bfreg(void)
-{
- return 1;
-}
-
enum {
/* this is the first blue flame register in the array of bfregs assigned
* to a processes. Since we do not use it for blue flame but rather
@@ -510,6 +509,12 @@ static int num_med_bfreg(struct mlx5_ib_dev *dev,
return n >= 0 ? n : 0;
}
+static int first_med_bfreg(struct mlx5_ib_dev *dev,
+ struct mlx5_bfreg_info *bfregi)
+{
+ return num_med_bfreg(dev, bfregi) ? 1 : -ENOMEM;
+}
+
static int first_hi_bfreg(struct mlx5_ib_dev *dev,
struct mlx5_bfreg_info *bfregi)
{
@@ -537,10 +542,13 @@ static int alloc_high_class_bfreg(struct mlx5_ib_dev *dev,
static int alloc_med_class_bfreg(struct mlx5_ib_dev *dev,
struct mlx5_bfreg_info *bfregi)
{
- int minidx = first_med_bfreg();
+ int minidx = first_med_bfreg(dev, bfregi);
int i;
- for (i = first_med_bfreg(); i < first_hi_bfreg(dev, bfregi); i++) {
+ if (minidx < 0)
+ return minidx;
+
+ for (i = minidx; i < first_hi_bfreg(dev, bfregi); i++) {
if (bfregi->count[i] < bfregi->count[minidx])
minidx = i;
if (!bfregi->count[minidx])
@@ -2451,18 +2459,18 @@ enum {
static int ib_rate_to_mlx5(struct mlx5_ib_dev *dev, u8 rate)
{
- if (rate == IB_RATE_PORT_CURRENT) {
+ if (rate == IB_RATE_PORT_CURRENT)
return 0;
- } else if (rate < IB_RATE_2_5_GBPS || rate > IB_RATE_300_GBPS) {
- return -EINVAL;
- } else {
- while (rate != IB_RATE_2_5_GBPS &&
- !(1 << (rate + MLX5_STAT_RATE_OFFSET) &
- MLX5_CAP_GEN(dev->mdev, stat_rate_support)))
- --rate;
- }
- return rate + MLX5_STAT_RATE_OFFSET;
+ if (rate < IB_RATE_2_5_GBPS || rate > IB_RATE_300_GBPS)
+ return -EINVAL;
+
+ while (rate != IB_RATE_PORT_CURRENT &&
+ !(1 << (rate + MLX5_STAT_RATE_OFFSET) &
+ MLX5_CAP_GEN(dev->mdev, stat_rate_support)))
+ --rate;
+
+ return rate ? rate + MLX5_STAT_RATE_OFFSET : rate;
}
static int modify_raw_packet_eth_prio(struct mlx5_core_dev *dev,
diff --git a/drivers/infiniband/hw/nes/nes_nic.c b/drivers/infiniband/hw/nes/nes_nic.c
index 0a75164..007d5e8 100644
--- a/drivers/infiniband/hw/nes/nes_nic.c
+++ b/drivers/infiniband/hw/nes/nes_nic.c
@@ -461,7 +461,7 @@ static bool nes_nic_send(struct sk_buff *skb, struct net_device *netdev)
/**
* nes_netdev_start_xmit
*/
-static int nes_netdev_start_xmit(struct sk_buff *skb, struct net_device *netdev)
+static netdev_tx_t nes_netdev_start_xmit(struct sk_buff *skb, struct net_device *netdev)
{
struct nes_vnic *nesvnic = netdev_priv(netdev);
struct nes_device *nesdev = nesvnic->nesdev;
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 7d3763b..3f9afc0 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -401,49 +401,47 @@ int qedr_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
{
struct qedr_ucontext *ucontext = get_qedr_ucontext(context);
struct qedr_dev *dev = get_qedr_dev(context->device);
- unsigned long vm_page = vma->vm_pgoff << PAGE_SHIFT;
- u64 unmapped_db = dev->db_phys_addr;
+ unsigned long phys_addr = vma->vm_pgoff << PAGE_SHIFT;
unsigned long len = (vma->vm_end - vma->vm_start);
- int rc = 0;
- bool found;
+ unsigned long dpi_start;
+
+ dpi_start = dev->db_phys_addr + (ucontext->dpi * ucontext->dpi_size);
DP_DEBUG(dev, QEDR_MSG_INIT,
- "qedr_mmap called vm_page=0x%lx vm_pgoff=0x%lx unmapped_db=0x%llx db_size=%x, len=%lx\n",
- vm_page, vma->vm_pgoff, unmapped_db, dev->db_size, len);
- if (vma->vm_start & (PAGE_SIZE - 1)) {
- DP_ERR(dev, "Vma_start not page aligned = %ld\n",
- vma->vm_start);
+ "mmap invoked with vm_start=0x%pK, vm_end=0x%pK,vm_pgoff=0x%pK; dpi_start=0x%pK dpi_size=0x%x\n",
+ (void *)vma->vm_start, (void *)vma->vm_end,
+ (void *)vma->vm_pgoff, (void *)dpi_start, ucontext->dpi_size);
+
+ if ((vma->vm_start & (PAGE_SIZE - 1)) || (len & (PAGE_SIZE - 1))) {
+ DP_ERR(dev,
+ "failed mmap, adrresses must be page aligned: start=0x%pK, end=0x%pK\n",
+ (void *)vma->vm_start, (void *)vma->vm_end);
return -EINVAL;
}
- found = qedr_search_mmap(ucontext, vm_page, len);
- if (!found) {
- DP_ERR(dev, "Vma_pgoff not found in mapped array = %ld\n",
+ if (!qedr_search_mmap(ucontext, phys_addr, len)) {
+ DP_ERR(dev, "failed mmap, vm_pgoff=0x%lx is not authorized\n",
vma->vm_pgoff);
return -EINVAL;
}
- DP_DEBUG(dev, QEDR_MSG_INIT, "Mapping doorbell bar\n");
-
- if ((vm_page >= unmapped_db) && (vm_page <= (unmapped_db +
- dev->db_size))) {
- DP_DEBUG(dev, QEDR_MSG_INIT, "Mapping doorbell bar\n");
- if (vma->vm_flags & VM_READ) {
- DP_ERR(dev, "Trying to map doorbell bar for read\n");
- return -EPERM;
- }
-
- vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
-
- rc = io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
- PAGE_SIZE, vma->vm_page_prot);
- } else {
- DP_DEBUG(dev, QEDR_MSG_INIT, "Mapping chains\n");
- rc = remap_pfn_range(vma, vma->vm_start,
- vma->vm_pgoff, len, vma->vm_page_prot);
+ if (phys_addr < dpi_start ||
+ ((phys_addr + len) > (dpi_start + ucontext->dpi_size))) {
+ DP_ERR(dev,
+ "failed mmap, pages are outside of dpi; page address=0x%pK, dpi_start=0x%pK, dpi_size=0x%x\n",
+ (void *)phys_addr, (void *)dpi_start,
+ ucontext->dpi_size);
+ return -EINVAL;
}
- DP_DEBUG(dev, QEDR_MSG_INIT, "qedr_mmap return code: %d\n", rc);
- return rc;
+
+ if (vma->vm_flags & VM_READ) {
+ DP_ERR(dev, "failed mmap, cannot map doorbell bar for read\n");
+ return -EINVAL;
+ }
+
+ vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+ return io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, len,
+ vma->vm_page_prot);
}
struct ib_pd *qedr_alloc_pd(struct ib_device *ibdev,
diff --git a/drivers/infiniband/sw/rxe/rxe_opcode.c b/drivers/infiniband/sw/rxe/rxe_opcode.c
index 61927c1..4cf1106 100644
--- a/drivers/infiniband/sw/rxe/rxe_opcode.c
+++ b/drivers/infiniband/sw/rxe/rxe_opcode.c
@@ -390,7 +390,7 @@ struct rxe_opcode_info rxe_opcode[RXE_NUM_OPCODE] = {
.name = "IB_OPCODE_RC_SEND_ONLY_INV",
.mask = RXE_IETH_MASK | RXE_PAYLOAD_MASK | RXE_REQ_MASK
| RXE_COMP_MASK | RXE_RWR_MASK | RXE_SEND_MASK
- | RXE_END_MASK,
+ | RXE_END_MASK | RXE_START_MASK,
.length = RXE_BTH_BYTES + RXE_IETH_BYTES,
.offset = {
[RXE_BTH] = 0,
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index 7bdaf71..7851999 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -728,7 +728,6 @@ int rxe_requester(void *arg)
rollback_state(wqe, qp, &rollback_wqe, rollback_psn);
if (ret == -EAGAIN) {
- kfree_skb(skb);
rxe_run_task(&qp->req.task, 1);
goto exit;
}
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index a65c996..955ff3b 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -742,7 +742,6 @@ static enum resp_states read_reply(struct rxe_qp *qp,
err = rxe_xmit_packet(rxe, qp, &ack_pkt, skb);
if (err) {
pr_err("Failed sending RDMA reply.\n");
- kfree_skb(skb);
return RESPST_ERR_RNR;
}
@@ -954,10 +953,8 @@ static int send_ack(struct rxe_qp *qp, struct rxe_pkt_info *pkt,
}
err = rxe_xmit_packet(rxe, qp, &ack_pkt, skb);
- if (err) {
+ if (err)
pr_err_ratelimited("Failed sending ack\n");
- kfree_skb(skb);
- }
err1:
return err;
@@ -1141,7 +1138,6 @@ static enum resp_states duplicate_request(struct rxe_qp *qp,
if (rc) {
pr_err("Failed resending result. This flow is not handled - skb ignored\n");
rxe_drop_ref(qp);
- kfree_skb(skb_copy);
rc = RESPST_CLEANUP;
goto out;
}
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 2cb52fd..73a00a1 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -761,7 +761,6 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, struct ib_send_wr *wr,
unsigned int mask;
unsigned int length = 0;
int i;
- int must_sched;
while (wr) {
mask = wr_opcode_mask(wr->opcode, qp);
@@ -791,14 +790,7 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, struct ib_send_wr *wr,
wr = wr->next;
}
- /*
- * Must sched in case of GSI QP because ib_send_mad() hold irq lock,
- * and the requester call ip_local_out_sk() that takes spin_lock_bh.
- */
- must_sched = (qp_type(qp) == IB_QPT_GSI) ||
- (queue_count(qp->sq.queue) > 1);
-
- rxe_run_task(&qp->req.task, must_sched);
+ rxe_run_task(&qp->req.task, 1);
if (unlikely(qp->req.state == QP_STATE_ERROR))
rxe_run_task(&qp->comp.task, 1);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 161ba8c..cf291f9 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1094,7 +1094,7 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
spin_unlock_irqrestore(&priv->lock, flags);
}
-static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ipoib_dev_priv *priv = ipoib_priv(dev);
struct rdma_netdev *rn = netdev_priv(dev);
diff --git a/drivers/infiniband/ulp/srp/Kconfig b/drivers/infiniband/ulp/srp/Kconfig
index c74ee96..99db8fe 100644
--- a/drivers/infiniband/ulp/srp/Kconfig
+++ b/drivers/infiniband/ulp/srp/Kconfig
@@ -1,6 +1,6 @@
config INFINIBAND_SRP
tristate "InfiniBand SCSI RDMA Protocol"
- depends on SCSI
+ depends on SCSI && INFINIBAND_ADDR_TRANS
select SCSI_SRP_ATTRS
---help---
Support for the SCSI RDMA Protocol over InfiniBand. This
diff --git a/drivers/infiniband/ulp/srpt/Kconfig b/drivers/infiniband/ulp/srpt/Kconfig
index 31ee83d..fb8b718 100644
--- a/drivers/infiniband/ulp/srpt/Kconfig
+++ b/drivers/infiniband/ulp/srpt/Kconfig
@@ -1,6 +1,6 @@
config INFINIBAND_SRPT
tristate "InfiniBand SCSI RDMA Protocol target support"
- depends on INFINIBAND && TARGET_CORE
+ depends on INFINIBAND && INFINIBAND_ADDR_TRANS && TARGET_CORE
---help---
Support for the SCSI RDMA Protocol (SRP) Target driver. The
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index 46115a3..c81c79d 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -31,6 +31,7 @@
enum evdev_clock_type {
EV_CLK_REAL = 0,
EV_CLK_MONO,
+ EV_CLK_BOOT,
EV_CLK_MAX
};
@@ -197,10 +198,12 @@ static int evdev_set_clk_type(struct evdev_client *client, unsigned int clkid)
case CLOCK_REALTIME:
clk_type = EV_CLK_REAL;
break;
- case CLOCK_BOOTTIME:
case CLOCK_MONOTONIC:
clk_type = EV_CLK_MONO;
break;
+ case CLOCK_BOOTTIME:
+ clk_type = EV_CLK_BOOT;
+ break;
default:
return -EINVAL;
}
@@ -311,6 +314,8 @@ static void evdev_events(struct input_handle *handle,
ev_time[EV_CLK_MONO] = ktime_get();
ev_time[EV_CLK_REAL] = ktime_mono_to_real(ev_time[EV_CLK_MONO]);
+ ev_time[EV_CLK_BOOT] = ktime_mono_to_any(ev_time[EV_CLK_MONO],
+ TK_OFFS_BOOT);
rcu_read_lock();
diff --git a/drivers/input/input-leds.c b/drivers/input/input-leds.c
index 766bf26..5f04b2d 100644
--- a/drivers/input/input-leds.c
+++ b/drivers/input/input-leds.c
@@ -88,6 +88,7 @@ static int input_leds_connect(struct input_handler *handler,
const struct input_device_id *id)
{
struct input_leds *leds;
+ struct input_led *led;
unsigned int num_leds;
unsigned int led_code;
int led_no;
@@ -119,14 +120,13 @@ static int input_leds_connect(struct input_handler *handler,
led_no = 0;
for_each_set_bit(led_code, dev->ledbit, LED_CNT) {
- struct input_led *led = &leds->leds[led_no];
-
- led->handle = &leds->handle;
- led->code = led_code;
-
if (!input_led_info[led_code].name)
continue;
+ led = &leds->leds[led_no];
+ led->handle = &leds->handle;
+ led->code = led_code;
+
led->cdev.name = kasprintf(GFP_KERNEL, "%s::%s",
dev_name(&dev->dev),
input_led_info[led_code].name);
diff --git a/drivers/input/misc/hp_sdc_rtc.c b/drivers/input/misc/hp_sdc_rtc.c
index 49b34de0..47eb8ca 100644
--- a/drivers/input/misc/hp_sdc_rtc.c
+++ b/drivers/input/misc/hp_sdc_rtc.c
@@ -509,18 +509,6 @@ static int hp_sdc_rtc_proc_show(struct seq_file *m, void *v)
#undef NY
}
-static int hp_sdc_rtc_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, hp_sdc_rtc_proc_show, NULL);
-}
-
-static const struct file_operations hp_sdc_rtc_proc_fops = {
- .open = hp_sdc_rtc_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int hp_sdc_rtc_ioctl(struct file *file,
unsigned int cmd, unsigned long arg)
{
@@ -713,7 +701,7 @@ static int __init hp_sdc_rtc_init(void)
if (misc_register(&hp_sdc_rtc_dev) != 0)
printk(KERN_INFO "Could not register misc. dev for i8042 rtc\n");
- proc_create("driver/rtc", 0, NULL, &hp_sdc_rtc_proc_fops);
+ proc_create_single("driver/rtc", 0, NULL, hp_sdc_rtc_proc_show);
printk(KERN_INFO "HP i8042 SDC + MSM-58321 RTC support loaded "
"(RTC v " RTC_VERSION ")\n");
diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index 0a67f23..38f9501 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -583,7 +583,7 @@ static void alps_process_trackstick_packet_v3(struct psmouse *psmouse)
x = (s8)(((packet[0] & 0x20) << 2) | (packet[1] & 0x7f));
y = (s8)(((packet[0] & 0x10) << 3) | (packet[2] & 0x7f));
- z = packet[4] & 0x7c;
+ z = packet[4] & 0x7f;
/*
* The x and y values tend to be quite large, and when used
diff --git a/drivers/input/mouse/elan_i2c_smbus.c b/drivers/input/mouse/elan_i2c_smbus.c
index 29f9952..cfcb325 100644
--- a/drivers/input/mouse/elan_i2c_smbus.c
+++ b/drivers/input/mouse/elan_i2c_smbus.c
@@ -130,7 +130,7 @@ static int elan_smbus_get_baseline_data(struct i2c_client *client,
bool max_baseline, u8 *value)
{
int error;
- u8 val[3];
+ u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
error = i2c_smbus_read_block_data(client,
max_baseline ?
@@ -149,7 +149,7 @@ static int elan_smbus_get_version(struct i2c_client *client,
bool iap, u8 *version)
{
int error;
- u8 val[3];
+ u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
error = i2c_smbus_read_block_data(client,
iap ? ETP_SMBUS_IAP_VERSION_CMD :
@@ -170,7 +170,7 @@ static int elan_smbus_get_sm_version(struct i2c_client *client,
u8 *clickpad)
{
int error;
- u8 val[3];
+ u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
error = i2c_smbus_read_block_data(client,
ETP_SMBUS_SM_VERSION_CMD, val);
@@ -188,7 +188,7 @@ static int elan_smbus_get_sm_version(struct i2c_client *client,
static int elan_smbus_get_product_id(struct i2c_client *client, u16 *id)
{
int error;
- u8 val[3];
+ u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
error = i2c_smbus_read_block_data(client,
ETP_SMBUS_UNIQUEID_CMD, val);
@@ -205,7 +205,7 @@ static int elan_smbus_get_checksum(struct i2c_client *client,
bool iap, u16 *csum)
{
int error;
- u8 val[3];
+ u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
error = i2c_smbus_read_block_data(client,
iap ? ETP_SMBUS_FW_CHECKSUM_CMD :
@@ -226,7 +226,7 @@ static int elan_smbus_get_max(struct i2c_client *client,
{
int ret;
int error;
- u8 val[3];
+ u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
ret = i2c_smbus_read_block_data(client, ETP_SMBUS_RANGE_CMD, val);
if (ret != 3) {
@@ -246,7 +246,7 @@ static int elan_smbus_get_resolution(struct i2c_client *client,
{
int ret;
int error;
- u8 val[3];
+ u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
ret = i2c_smbus_read_block_data(client, ETP_SMBUS_RESOLUTION_CMD, val);
if (ret != 3) {
@@ -267,7 +267,7 @@ static int elan_smbus_get_num_traces(struct i2c_client *client,
{
int ret;
int error;
- u8 val[3];
+ u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
ret = i2c_smbus_read_block_data(client, ETP_SMBUS_XY_TRACENUM_CMD, val);
if (ret != 3) {
@@ -294,7 +294,7 @@ static int elan_smbus_iap_get_mode(struct i2c_client *client,
{
int error;
u16 constant;
- u8 val[3];
+ u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
error = i2c_smbus_read_block_data(client, ETP_SMBUS_IAP_CTRL_CMD, val);
if (error < 0) {
@@ -345,7 +345,7 @@ static int elan_smbus_prepare_fw_update(struct i2c_client *client)
int len;
int error;
enum tp_mode mode;
- u8 val[3];
+ u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
u8 cmd[4] = {0x0F, 0x78, 0x00, 0x06};
u16 password;
@@ -419,7 +419,7 @@ static int elan_smbus_write_fw_block(struct i2c_client *client,
struct device *dev = &client->dev;
int error;
u16 result;
- u8 val[3];
+ u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
/*
* Due to the limitation of smbus protocol limiting
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 60f2c46..a9591d2 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -172,6 +172,12 @@ static const char * const smbus_pnp_ids[] = {
"LEN0048", /* X1 Carbon 3 */
"LEN0046", /* X250 */
"LEN004a", /* W541 */
+ "LEN0071", /* T480 */
+ "LEN0072", /* X1 Carbon Gen 5 (2017) - Elan/ALPS trackpoint */
+ "LEN0073", /* X1 Carbon G5 (Elantech) */
+ "LEN0092", /* X1 Carbon 6 */
+ "LEN0096", /* X280 */
+ "LEN0097", /* X280 -> ALPS trackpoint */
"LEN200f", /* T450s */
NULL
};
diff --git a/drivers/input/rmi4/rmi_spi.c b/drivers/input/rmi4/rmi_spi.c
index 76edbf2..082defc 100644
--- a/drivers/input/rmi4/rmi_spi.c
+++ b/drivers/input/rmi4/rmi_spi.c
@@ -147,8 +147,11 @@ static int rmi_spi_xfer(struct rmi_spi_xport *rmi_spi,
if (len > RMI_SPI_XFER_SIZE_LIMIT)
return -EINVAL;
- if (rmi_spi->xfer_buf_size < len)
- rmi_spi_manage_pools(rmi_spi, len);
+ if (rmi_spi->xfer_buf_size < len) {
+ ret = rmi_spi_manage_pools(rmi_spi, len);
+ if (ret < 0)
+ return ret;
+ }
if (addr == 0)
/*
diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig
index 4f15496..3e613af 100644
--- a/drivers/input/touchscreen/Kconfig
+++ b/drivers/input/touchscreen/Kconfig
@@ -362,7 +362,7 @@
If unsure, say N.
- To compile this driver as a moudle, choose M here : the
+ To compile this driver as a module, choose M here : the
module will be called hideep_ts.
config TOUCHSCREEN_ILI210X
diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c
index 5d9699f..0919472 100644
--- a/drivers/input/touchscreen/atmel_mxt_ts.c
+++ b/drivers/input/touchscreen/atmel_mxt_ts.c
@@ -280,7 +280,8 @@ struct mxt_data {
struct input_dev *input_dev;
char phys[64]; /* device physical location */
struct mxt_object *object_table;
- struct mxt_info info;
+ struct mxt_info *info;
+ void *raw_info_block;
unsigned int irq;
unsigned int max_x;
unsigned int max_y;
@@ -460,12 +461,13 @@ static int mxt_lookup_bootloader_address(struct mxt_data *data, bool retry)
{
u8 appmode = data->client->addr;
u8 bootloader;
+ u8 family_id = data->info ? data->info->family_id : 0;
switch (appmode) {
case 0x4a:
case 0x4b:
/* Chips after 1664S use different scheme */
- if (retry || data->info.family_id >= 0xa2) {
+ if (retry || family_id >= 0xa2) {
bootloader = appmode - 0x24;
break;
}
@@ -692,7 +694,7 @@ mxt_get_object(struct mxt_data *data, u8 type)
struct mxt_object *object;
int i;
- for (i = 0; i < data->info.object_num; i++) {
+ for (i = 0; i < data->info->object_num; i++) {
object = data->object_table + i;
if (object->type == type)
return object;
@@ -1462,12 +1464,12 @@ static int mxt_update_cfg(struct mxt_data *data, const struct firmware *cfg)
data_pos += offset;
}
- if (cfg_info.family_id != data->info.family_id) {
+ if (cfg_info.family_id != data->info->family_id) {
dev_err(dev, "Family ID mismatch!\n");
return -EINVAL;
}
- if (cfg_info.variant_id != data->info.variant_id) {
+ if (cfg_info.variant_id != data->info->variant_id) {
dev_err(dev, "Variant ID mismatch!\n");
return -EINVAL;
}
@@ -1512,7 +1514,7 @@ static int mxt_update_cfg(struct mxt_data *data, const struct firmware *cfg)
/* Malloc memory to store configuration */
cfg_start_ofs = MXT_OBJECT_START +
- data->info.object_num * sizeof(struct mxt_object) +
+ data->info->object_num * sizeof(struct mxt_object) +
MXT_INFO_CHECKSUM_SIZE;
config_mem_size = data->mem_size - cfg_start_ofs;
config_mem = kzalloc(config_mem_size, GFP_KERNEL);
@@ -1563,20 +1565,6 @@ static int mxt_update_cfg(struct mxt_data *data, const struct firmware *cfg)
return ret;
}
-static int mxt_get_info(struct mxt_data *data)
-{
- struct i2c_client *client = data->client;
- struct mxt_info *info = &data->info;
- int error;
-
- /* Read 7-byte info block starting at address 0 */
- error = __mxt_read_reg(client, 0, sizeof(*info), info);
- if (error)
- return error;
-
- return 0;
-}
-
static void mxt_free_input_device(struct mxt_data *data)
{
if (data->input_dev) {
@@ -1591,9 +1579,10 @@ static void mxt_free_object_table(struct mxt_data *data)
video_unregister_device(&data->dbg.vdev);
v4l2_device_unregister(&data->dbg.v4l2);
#endif
-
- kfree(data->object_table);
data->object_table = NULL;
+ data->info = NULL;
+ kfree(data->raw_info_block);
+ data->raw_info_block = NULL;
kfree(data->msg_buf);
data->msg_buf = NULL;
data->T5_address = 0;
@@ -1609,34 +1598,18 @@ static void mxt_free_object_table(struct mxt_data *data)
data->max_reportid = 0;
}
-static int mxt_get_object_table(struct mxt_data *data)
+static int mxt_parse_object_table(struct mxt_data *data,
+ struct mxt_object *object_table)
{
struct i2c_client *client = data->client;
- size_t table_size;
- struct mxt_object *object_table;
- int error;
int i;
u8 reportid;
u16 end_address;
- table_size = data->info.object_num * sizeof(struct mxt_object);
- object_table = kzalloc(table_size, GFP_KERNEL);
- if (!object_table) {
- dev_err(&data->client->dev, "Failed to allocate memory\n");
- return -ENOMEM;
- }
-
- error = __mxt_read_reg(client, MXT_OBJECT_START, table_size,
- object_table);
- if (error) {
- kfree(object_table);
- return error;
- }
-
/* Valid Report IDs start counting from 1 */
reportid = 1;
data->mem_size = 0;
- for (i = 0; i < data->info.object_num; i++) {
+ for (i = 0; i < data->info->object_num; i++) {
struct mxt_object *object = object_table + i;
u8 min_id, max_id;
@@ -1660,8 +1633,8 @@ static int mxt_get_object_table(struct mxt_data *data)
switch (object->type) {
case MXT_GEN_MESSAGE_T5:
- if (data->info.family_id == 0x80 &&
- data->info.version < 0x20) {
+ if (data->info->family_id == 0x80 &&
+ data->info->version < 0x20) {
/*
* On mXT224 firmware versions prior to V2.0
* read and discard unused CRC byte otherwise
@@ -1716,24 +1689,102 @@ static int mxt_get_object_table(struct mxt_data *data)
/* If T44 exists, T5 position has to be directly after */
if (data->T44_address && (data->T5_address != data->T44_address + 1)) {
dev_err(&client->dev, "Invalid T44 position\n");
- error = -EINVAL;
- goto free_object_table;
+ return -EINVAL;
}
data->msg_buf = kcalloc(data->max_reportid,
data->T5_msg_size, GFP_KERNEL);
- if (!data->msg_buf) {
- dev_err(&client->dev, "Failed to allocate message buffer\n");
+ if (!data->msg_buf)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int mxt_read_info_block(struct mxt_data *data)
+{
+ struct i2c_client *client = data->client;
+ int error;
+ size_t size;
+ void *id_buf, *buf;
+ uint8_t num_objects;
+ u32 calculated_crc;
+ u8 *crc_ptr;
+
+ /* If info block already allocated, free it */
+ if (data->raw_info_block)
+ mxt_free_object_table(data);
+
+ /* Read 7-byte ID information block starting at address 0 */
+ size = sizeof(struct mxt_info);
+ id_buf = kzalloc(size, GFP_KERNEL);
+ if (!id_buf)
+ return -ENOMEM;
+
+ error = __mxt_read_reg(client, 0, size, id_buf);
+ if (error)
+ goto err_free_mem;
+
+ /* Resize buffer to give space for rest of info block */
+ num_objects = ((struct mxt_info *)id_buf)->object_num;
+ size += (num_objects * sizeof(struct mxt_object))
+ + MXT_INFO_CHECKSUM_SIZE;
+
+ buf = krealloc(id_buf, size, GFP_KERNEL);
+ if (!buf) {
error = -ENOMEM;
- goto free_object_table;
+ goto err_free_mem;
+ }
+ id_buf = buf;
+
+ /* Read rest of info block */
+ error = __mxt_read_reg(client, MXT_OBJECT_START,
+ size - MXT_OBJECT_START,
+ id_buf + MXT_OBJECT_START);
+ if (error)
+ goto err_free_mem;
+
+ /* Extract & calculate checksum */
+ crc_ptr = id_buf + size - MXT_INFO_CHECKSUM_SIZE;
+ data->info_crc = crc_ptr[0] | (crc_ptr[1] << 8) | (crc_ptr[2] << 16);
+
+ calculated_crc = mxt_calculate_crc(id_buf, 0,
+ size - MXT_INFO_CHECKSUM_SIZE);
+
+ /*
+ * CRC mismatch can be caused by data corruption due to I2C comms
+ * issue or else device is not using Object Based Protocol (eg i2c-hid)
+ */
+ if ((data->info_crc == 0) || (data->info_crc != calculated_crc)) {
+ dev_err(&client->dev,
+ "Info Block CRC error calculated=0x%06X read=0x%06X\n",
+ calculated_crc, data->info_crc);
+ error = -EIO;
+ goto err_free_mem;
}
- data->object_table = object_table;
+ data->raw_info_block = id_buf;
+ data->info = (struct mxt_info *)id_buf;
+
+ dev_info(&client->dev,
+ "Family: %u Variant: %u Firmware V%u.%u.%02X Objects: %u\n",
+ data->info->family_id, data->info->variant_id,
+ data->info->version >> 4, data->info->version & 0xf,
+ data->info->build, data->info->object_num);
+
+ /* Parse object table information */
+ error = mxt_parse_object_table(data, id_buf + MXT_OBJECT_START);
+ if (error) {
+ dev_err(&client->dev, "Error %d parsing object table\n", error);
+ mxt_free_object_table(data);
+ goto err_free_mem;
+ }
+
+ data->object_table = (struct mxt_object *)(id_buf + MXT_OBJECT_START);
return 0;
-free_object_table:
- mxt_free_object_table(data);
+err_free_mem:
+ kfree(id_buf);
return error;
}
@@ -2046,7 +2097,7 @@ static int mxt_initialize(struct mxt_data *data)
int error;
while (1) {
- error = mxt_get_info(data);
+ error = mxt_read_info_block(data);
if (!error)
break;
@@ -2077,16 +2128,9 @@ static int mxt_initialize(struct mxt_data *data)
msleep(MXT_FW_RESET_TIME);
}
- /* Get object table information */
- error = mxt_get_object_table(data);
- if (error) {
- dev_err(&client->dev, "Error %d reading object table\n", error);
- return error;
- }
-
error = mxt_acquire_irq(data);
if (error)
- goto err_free_object_table;
+ return error;
error = request_firmware_nowait(THIS_MODULE, true, MXT_CFG_NAME,
&client->dev, GFP_KERNEL, data,
@@ -2094,14 +2138,10 @@ static int mxt_initialize(struct mxt_data *data)
if (error) {
dev_err(&client->dev, "Failed to invoke firmware loader: %d\n",
error);
- goto err_free_object_table;
+ return error;
}
return 0;
-
-err_free_object_table:
- mxt_free_object_table(data);
- return error;
}
static int mxt_set_t7_power_cfg(struct mxt_data *data, u8 sleep)
@@ -2162,7 +2202,7 @@ static int mxt_init_t7_power_cfg(struct mxt_data *data)
static u16 mxt_get_debug_value(struct mxt_data *data, unsigned int x,
unsigned int y)
{
- struct mxt_info *info = &data->info;
+ struct mxt_info *info = data->info;
struct mxt_dbg *dbg = &data->dbg;
unsigned int ofs, page;
unsigned int col = 0;
@@ -2490,7 +2530,7 @@ static const struct video_device mxt_video_device = {
static void mxt_debug_init(struct mxt_data *data)
{
- struct mxt_info *info = &data->info;
+ struct mxt_info *info = data->info;
struct mxt_dbg *dbg = &data->dbg;
struct mxt_object *object;
int error;
@@ -2576,7 +2616,6 @@ static int mxt_configure_objects(struct mxt_data *data,
const struct firmware *cfg)
{
struct device *dev = &data->client->dev;
- struct mxt_info *info = &data->info;
int error;
error = mxt_init_t7_power_cfg(data);
@@ -2601,11 +2640,6 @@ static int mxt_configure_objects(struct mxt_data *data,
mxt_debug_init(data);
- dev_info(dev,
- "Family: %u Variant: %u Firmware V%u.%u.%02X Objects: %u\n",
- info->family_id, info->variant_id, info->version >> 4,
- info->version & 0xf, info->build, info->object_num);
-
return 0;
}
@@ -2614,7 +2648,7 @@ static ssize_t mxt_fw_version_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct mxt_data *data = dev_get_drvdata(dev);
- struct mxt_info *info = &data->info;
+ struct mxt_info *info = data->info;
return scnprintf(buf, PAGE_SIZE, "%u.%u.%02X\n",
info->version >> 4, info->version & 0xf, info->build);
}
@@ -2624,7 +2658,7 @@ static ssize_t mxt_hw_version_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct mxt_data *data = dev_get_drvdata(dev);
- struct mxt_info *info = &data->info;
+ struct mxt_info *info = data->info;
return scnprintf(buf, PAGE_SIZE, "%u.%u\n",
info->family_id, info->variant_id);
}
@@ -2663,7 +2697,7 @@ static ssize_t mxt_object_show(struct device *dev,
return -ENOMEM;
error = 0;
- for (i = 0; i < data->info.object_num; i++) {
+ for (i = 0; i < data->info->object_num; i++) {
object = data->object_table + i;
if (!mxt_object_readable(object->type))
@@ -3035,6 +3069,15 @@ static const struct dmi_system_id mxt_dmi_table[] = {
.driver_data = samus_platform_data,
},
{
+ /* Samsung Chromebook Pro */
+ .ident = "Samsung Chromebook Pro",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Google"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Caroline"),
+ },
+ .driver_data = samus_platform_data,
+ },
+ {
/* Other Google Chromebooks */
.ident = "Chromebook",
.matches = {
@@ -3254,6 +3297,11 @@ static SIMPLE_DEV_PM_OPS(mxt_pm_ops, mxt_suspend, mxt_resume);
static const struct of_device_id mxt_of_match[] = {
{ .compatible = "atmel,maxtouch", },
+ /* Compatibles listed below are deprecated */
+ { .compatible = "atmel,qt602240_ts", },
+ { .compatible = "atmel,atmel_mxt_ts", },
+ { .compatible = "atmel,atmel_mxt_tp", },
+ { .compatible = "atmel,mXT224", },
{},
};
MODULE_DEVICE_TABLE(of, mxt_of_match);
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index df171cb..5b714a0 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -146,6 +146,7 @@
select DMA_DIRECT_OPS
select IOMMU_API
select IOMMU_IOVA
+ select NEED_DMA_MAP_STATE
select DMAR_TABLE
help
DMA remapping (DMAR) devices support enables independent address
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 2a99f0f..8fb8c73 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -83,7 +83,6 @@
static DEFINE_SPINLOCK(amd_iommu_devtable_lock);
static DEFINE_SPINLOCK(pd_bitmap_lock);
-static DEFINE_SPINLOCK(iommu_table_lock);
/* List of all available dev_data structures */
static LLIST_HEAD(dev_data_list);
@@ -3562,6 +3561,7 @@ EXPORT_SYMBOL(amd_iommu_device_info);
*****************************************************************************/
static struct irq_chip amd_ir_chip;
+static DEFINE_SPINLOCK(iommu_table_lock);
static void set_dte_irq_entry(u16 devid, struct irq_remap_table *table)
{
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index f05f3cf..ddcbbdb 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -167,40 +167,16 @@ EXPORT_SYMBOL(iommu_put_dma_cookie);
* @list: Reserved region list from iommu_get_resv_regions()
*
* IOMMU drivers can use this to implement their .get_resv_regions callback
- * for general non-IOMMU-specific reservations. Currently, this covers host
- * bridge windows for PCI devices and GICv3 ITS region reservation on ACPI
- * based ARM platforms that may require HW MSI reservation.
+ * for general non-IOMMU-specific reservations. Currently, this covers GICv3
+ * ITS region reservation on ACPI based ARM platforms that may require HW MSI
+ * reservation.
*/
void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list)
{
- struct pci_host_bridge *bridge;
- struct resource_entry *window;
- if (!is_of_node(dev->iommu_fwspec->iommu_fwnode) &&
- iort_iommu_msi_get_resv_regions(dev, list) < 0)
- return;
+ if (!is_of_node(dev->iommu_fwspec->iommu_fwnode))
+ iort_iommu_msi_get_resv_regions(dev, list);
- if (!dev_is_pci(dev))
- return;
-
- bridge = pci_find_host_bridge(to_pci_dev(dev)->bus);
- resource_list_for_each_entry(window, &bridge->windows) {
- struct iommu_resv_region *region;
- phys_addr_t start;
- size_t length;
-
- if (resource_type(window->res) != IORESOURCE_MEM)
- continue;
-
- start = window->res->start - window->offset;
- length = window->res->end - window->res->start + 1;
- region = iommu_alloc_resv_region(start, length, 0,
- IOMMU_RESV_RESERVED);
- if (!region)
- return;
-
- list_add_tail(®ion->list, list);
- }
}
EXPORT_SYMBOL(iommu_dma_get_resv_regions);
@@ -229,6 +205,23 @@ static int cookie_init_hw_msi_region(struct iommu_dma_cookie *cookie,
return 0;
}
+static void iova_reserve_pci_windows(struct pci_dev *dev,
+ struct iova_domain *iovad)
+{
+ struct pci_host_bridge *bridge = pci_find_host_bridge(dev->bus);
+ struct resource_entry *window;
+ unsigned long lo, hi;
+
+ resource_list_for_each_entry(window, &bridge->windows) {
+ if (resource_type(window->res) != IORESOURCE_MEM)
+ continue;
+
+ lo = iova_pfn(iovad, window->res->start - window->offset);
+ hi = iova_pfn(iovad, window->res->end - window->offset);
+ reserve_iova(iovad, lo, hi);
+ }
+}
+
static int iova_reserve_iommu_regions(struct device *dev,
struct iommu_domain *domain)
{
@@ -238,6 +231,9 @@ static int iova_reserve_iommu_regions(struct device *dev,
LIST_HEAD(resv_regions);
int ret = 0;
+ if (dev_is_pci(dev))
+ iova_reserve_pci_windows(to_pci_dev(dev), iovad);
+
iommu_get_resv_regions(dev, &resv_regions);
list_for_each_entry(region, &resv_regions, list) {
unsigned long lo, hi;
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index accf5838..460bed4 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -1345,7 +1345,7 @@ void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 qdep,
struct qi_desc desc;
if (mask) {
- BUG_ON(addr & ((1 << (VTD_PAGE_SHIFT + mask)) - 1));
+ WARN_ON_ONCE(addr & ((1ULL << (VTD_PAGE_SHIFT + mask)) - 1));
addr |= (1ULL << (VTD_PAGE_SHIFT + mask - 1)) - 1;
desc.high = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
} else
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 66f69af..3062a15 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -1136,7 +1136,7 @@ static void intel_ir_reconfigure_irte(struct irq_data *irqd, bool force)
irte->dest_id = IRTE_DEST(cfg->dest_apicid);
/* Update the hardware only if the interrupt is in remapped mode. */
- if (!force || ir_data->irq_2_iommu.mode == IRQ_REMAPPING)
+ if (force || ir_data->irq_2_iommu.mode == IRQ_REMAPPING)
modify_irte(&ir_data->irq_2_iommu, irte);
}
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index 5fc8656..0468acf 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -1098,7 +1098,7 @@ static int rk_iommu_of_xlate(struct device *dev,
data->iommu = platform_get_drvdata(iommu_dev);
dev->archdata.iommu = data;
- of_dev_put(iommu_dev);
+ platform_device_put(iommu_dev);
return 0;
}
@@ -1175,8 +1175,15 @@ static int rk_iommu_probe(struct platform_device *pdev)
for (i = 0; i < iommu->num_clocks; ++i)
iommu->clocks[i].id = rk_iommu_clocks[i];
+ /*
+ * iommu clocks should be present for all new devices and devicetrees
+ * but there are older devicetrees without clocks out in the wild.
+ * So clocks as optional for the time being.
+ */
err = devm_clk_bulk_get(iommu->dev, iommu->num_clocks, iommu->clocks);
- if (err)
+ if (err == -ENOENT)
+ iommu->num_clocks = 0;
+ else if (err)
return err;
err = clk_bulk_prepare(iommu->num_clocks, iommu->clocks);
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 5ed465a..15f268f 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -27,7 +27,7 @@
obj-$(CONFIG_ARM_GIC_PM) += irq-gic-pm.o
obj-$(CONFIG_ARCH_REALVIEW) += irq-gic-realview.o
obj-$(CONFIG_ARM_GIC_V2M) += irq-gic-v2m.o
-obj-$(CONFIG_ARM_GIC_V3) += irq-gic-v3.o irq-gic-common.o
+obj-$(CONFIG_ARM_GIC_V3) += irq-gic-v3.o irq-gic-v3-mbi.o irq-gic-common.o
obj-$(CONFIG_ARM_GIC_V3_ITS) += irq-gic-v3-its.o irq-gic-v3-its-platform-msi.o irq-gic-v4.o
obj-$(CONFIG_ARM_GIC_V3_ITS_PCI) += irq-gic-v3-its-pci-msi.o
obj-$(CONFIG_ARM_GIC_V3_ITS_FSL_MC) += irq-gic-v3-its-fsl-mc-msi.o
diff --git a/drivers/irqchip/irq-gic-v3-mbi.c b/drivers/irqchip/irq-gic-v3-mbi.c
new file mode 100644
index 0000000..ad70e7c
--- /dev/null
+++ b/drivers/irqchip/irq-gic-v3-mbi.c
@@ -0,0 +1,331 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#define pr_fmt(fmt) "GICv3: " fmt
+
+#include <linux/dma-iommu.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/msi.h>
+#include <linux/of_address.h>
+#include <linux/of_pci.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include <linux/irqchip/arm-gic-v3.h>
+
+struct mbi_range {
+ u32 spi_start;
+ u32 nr_spis;
+ unsigned long *bm;
+};
+
+static struct mutex mbi_lock;
+static phys_addr_t mbi_phys_base;
+static struct mbi_range *mbi_ranges;
+static unsigned int mbi_range_nr;
+
+static struct irq_chip mbi_irq_chip = {
+ .name = "MBI",
+ .irq_mask = irq_chip_mask_parent,
+ .irq_unmask = irq_chip_unmask_parent,
+ .irq_eoi = irq_chip_eoi_parent,
+ .irq_set_type = irq_chip_set_type_parent,
+ .irq_set_affinity = irq_chip_set_affinity_parent,
+};
+
+static int mbi_irq_gic_domain_alloc(struct irq_domain *domain,
+ unsigned int virq,
+ irq_hw_number_t hwirq)
+{
+ struct irq_fwspec fwspec;
+ struct irq_data *d;
+ int err;
+
+ /*
+ * Using ACPI? There is no MBI support in the spec, you
+ * shouldn't even be here.
+ */
+ if (!is_of_node(domain->parent->fwnode))
+ return -EINVAL;
+
+ /*
+ * Let's default to edge. This is consistent with traditional
+ * MSIs, and systems requiring level signaling will just
+ * enforce the trigger on their own.
+ */
+ fwspec.fwnode = domain->parent->fwnode;
+ fwspec.param_count = 3;
+ fwspec.param[0] = 0;
+ fwspec.param[1] = hwirq - 32;
+ fwspec.param[2] = IRQ_TYPE_EDGE_RISING;
+
+ err = irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec);
+ if (err)
+ return err;
+
+ d = irq_domain_get_irq_data(domain->parent, virq);
+ return d->chip->irq_set_type(d, IRQ_TYPE_EDGE_RISING);
+}
+
+static void mbi_free_msi(struct mbi_range *mbi, unsigned int hwirq,
+ int nr_irqs)
+{
+ mutex_lock(&mbi_lock);
+ bitmap_release_region(mbi->bm, hwirq - mbi->spi_start,
+ get_count_order(nr_irqs));
+ mutex_unlock(&mbi_lock);
+}
+
+static int mbi_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *args)
+{
+ struct mbi_range *mbi = NULL;
+ int hwirq, offset, i, err = 0;
+
+ mutex_lock(&mbi_lock);
+ for (i = 0; i < mbi_range_nr; i++) {
+ offset = bitmap_find_free_region(mbi_ranges[i].bm,
+ mbi_ranges[i].nr_spis,
+ get_count_order(nr_irqs));
+ if (offset >= 0) {
+ mbi = &mbi_ranges[i];
+ break;
+ }
+ }
+ mutex_unlock(&mbi_lock);
+
+ if (!mbi)
+ return -ENOSPC;
+
+ hwirq = mbi->spi_start + offset;
+
+ for (i = 0; i < nr_irqs; i++) {
+ err = mbi_irq_gic_domain_alloc(domain, virq + i, hwirq + i);
+ if (err)
+ goto fail;
+
+ irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i,
+ &mbi_irq_chip, mbi);
+ }
+
+ return 0;
+
+fail:
+ irq_domain_free_irqs_parent(domain, virq, nr_irqs);
+ mbi_free_msi(mbi, hwirq, nr_irqs);
+ return err;
+}
+
+static void mbi_irq_domain_free(struct irq_domain *domain,
+ unsigned int virq, unsigned int nr_irqs)
+{
+ struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+ struct mbi_range *mbi = irq_data_get_irq_chip_data(d);
+
+ mbi_free_msi(mbi, d->hwirq, nr_irqs);
+ irq_domain_free_irqs_parent(domain, virq, nr_irqs);
+}
+
+static const struct irq_domain_ops mbi_domain_ops = {
+ .alloc = mbi_irq_domain_alloc,
+ .free = mbi_irq_domain_free,
+};
+
+static void mbi_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+ msg[0].address_hi = upper_32_bits(mbi_phys_base + GICD_SETSPI_NSR);
+ msg[0].address_lo = lower_32_bits(mbi_phys_base + GICD_SETSPI_NSR);
+ msg[0].data = data->parent_data->hwirq;
+
+ iommu_dma_map_msi_msg(data->irq, msg);
+}
+
+#ifdef CONFIG_PCI_MSI
+/* PCI-specific irqchip */
+static void mbi_mask_msi_irq(struct irq_data *d)
+{
+ pci_msi_mask_irq(d);
+ irq_chip_mask_parent(d);
+}
+
+static void mbi_unmask_msi_irq(struct irq_data *d)
+{
+ pci_msi_unmask_irq(d);
+ irq_chip_unmask_parent(d);
+}
+
+static struct irq_chip mbi_msi_irq_chip = {
+ .name = "MSI",
+ .irq_mask = mbi_mask_msi_irq,
+ .irq_unmask = mbi_unmask_msi_irq,
+ .irq_eoi = irq_chip_eoi_parent,
+ .irq_compose_msi_msg = mbi_compose_msi_msg,
+ .irq_write_msi_msg = pci_msi_domain_write_msg,
+};
+
+static struct msi_domain_info mbi_msi_domain_info = {
+ .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+ MSI_FLAG_PCI_MSIX | MSI_FLAG_MULTI_PCI_MSI),
+ .chip = &mbi_msi_irq_chip,
+};
+
+static int mbi_allocate_pci_domain(struct irq_domain *nexus_domain,
+ struct irq_domain **pci_domain)
+{
+ *pci_domain = pci_msi_create_irq_domain(nexus_domain->parent->fwnode,
+ &mbi_msi_domain_info,
+ nexus_domain);
+ if (!*pci_domain)
+ return -ENOMEM;
+
+ return 0;
+}
+#else
+static int mbi_allocate_pci_domain(struct irq_domain *nexus_domain,
+ struct irq_domain **pci_domain)
+{
+ *pci_domain = NULL;
+ return 0;
+}
+#endif
+
+static void mbi_compose_mbi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+ mbi_compose_msi_msg(data, msg);
+
+ msg[1].address_hi = upper_32_bits(mbi_phys_base + GICD_CLRSPI_NSR);
+ msg[1].address_lo = lower_32_bits(mbi_phys_base + GICD_CLRSPI_NSR);
+ msg[1].data = data->parent_data->hwirq;
+
+ iommu_dma_map_msi_msg(data->irq, &msg[1]);
+}
+
+/* Platform-MSI specific irqchip */
+static struct irq_chip mbi_pmsi_irq_chip = {
+ .name = "pMSI",
+ .irq_set_type = irq_chip_set_type_parent,
+ .irq_compose_msi_msg = mbi_compose_mbi_msg,
+ .flags = IRQCHIP_SUPPORTS_LEVEL_MSI,
+};
+
+static struct msi_domain_ops mbi_pmsi_ops = {
+};
+
+static struct msi_domain_info mbi_pmsi_domain_info = {
+ .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+ MSI_FLAG_LEVEL_CAPABLE),
+ .ops = &mbi_pmsi_ops,
+ .chip = &mbi_pmsi_irq_chip,
+};
+
+static int mbi_allocate_domains(struct irq_domain *parent)
+{
+ struct irq_domain *nexus_domain, *pci_domain, *plat_domain;
+ int err;
+
+ nexus_domain = irq_domain_create_tree(parent->fwnode,
+ &mbi_domain_ops, NULL);
+ if (!nexus_domain)
+ return -ENOMEM;
+
+ irq_domain_update_bus_token(nexus_domain, DOMAIN_BUS_NEXUS);
+ nexus_domain->parent = parent;
+
+ err = mbi_allocate_pci_domain(nexus_domain, &pci_domain);
+
+ plat_domain = platform_msi_create_irq_domain(parent->fwnode,
+ &mbi_pmsi_domain_info,
+ nexus_domain);
+
+ if (err || !plat_domain) {
+ if (plat_domain)
+ irq_domain_remove(plat_domain);
+ if (pci_domain)
+ irq_domain_remove(pci_domain);
+ irq_domain_remove(nexus_domain);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+int __init mbi_init(struct fwnode_handle *fwnode, struct irq_domain *parent)
+{
+ struct device_node *np;
+ const __be32 *reg;
+ int ret, n;
+
+ np = to_of_node(fwnode);
+
+ if (!of_property_read_bool(np, "msi-controller"))
+ return 0;
+
+ n = of_property_count_elems_of_size(np, "mbi-ranges", sizeof(u32));
+ if (n <= 0 || n % 2)
+ return -EINVAL;
+
+ mbi_range_nr = n / 2;
+ mbi_ranges = kcalloc(mbi_range_nr, sizeof(*mbi_ranges), GFP_KERNEL);
+ if (!mbi_ranges)
+ return -ENOMEM;
+
+ for (n = 0; n < mbi_range_nr; n++) {
+ ret = of_property_read_u32_index(np, "mbi-ranges", n * 2,
+ &mbi_ranges[n].spi_start);
+ if (ret)
+ goto err_free_mbi;
+ ret = of_property_read_u32_index(np, "mbi-ranges", n * 2 + 1,
+ &mbi_ranges[n].nr_spis);
+ if (ret)
+ goto err_free_mbi;
+
+ mbi_ranges[n].bm = kcalloc(BITS_TO_LONGS(mbi_ranges[n].nr_spis),
+ sizeof(long), GFP_KERNEL);
+ if (!mbi_ranges[n].bm) {
+ ret = -ENOMEM;
+ goto err_free_mbi;
+ }
+ pr_info("MBI range [%d:%d]\n", mbi_ranges[n].spi_start,
+ mbi_ranges[n].spi_start + mbi_ranges[n].nr_spis - 1);
+ }
+
+ reg = of_get_property(np, "mbi-alias", NULL);
+ if (reg) {
+ mbi_phys_base = of_translate_address(np, reg);
+ if (mbi_phys_base == OF_BAD_ADDR) {
+ ret = -ENXIO;
+ goto err_free_mbi;
+ }
+ } else {
+ struct resource res;
+
+ if (of_address_to_resource(np, 0, &res)) {
+ ret = -ENXIO;
+ goto err_free_mbi;
+ }
+
+ mbi_phys_base = res.start;
+ }
+
+ pr_info("Using MBI frame %pa\n", &mbi_phys_base);
+
+ ret = mbi_allocate_domains(parent);
+ if (ret)
+ goto err_free_mbi;
+
+ return 0;
+
+err_free_mbi:
+ if (mbi_ranges) {
+ for (n = 0; n < mbi_range_nr; n++)
+ kfree(mbi_ranges[n].bm);
+ kfree(mbi_ranges);
+ }
+
+ return ret;
+}
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index e5d1014..5a67ec0 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -1099,6 +1099,7 @@ static int __init gic_init_bases(void __iomem *dist_base,
gic_data.domain = irq_domain_create_tree(handle, &gic_irq_domain_ops,
&gic_data);
+ irq_domain_update_bus_token(gic_data.domain, DOMAIN_BUS_WIRED);
gic_data.rdists.rdist = alloc_percpu(typeof(*gic_data.rdists.rdist));
gic_data.rdists.has_vlpis = true;
gic_data.rdists.has_direct_lpi = true;
@@ -1112,6 +1113,12 @@ static int __init gic_init_bases(void __iomem *dist_base,
pr_info("Distributor has %sRange Selector support\n",
gic_data.has_rss ? "" : "no ");
+ if (typer & GICD_TYPER_MBIS) {
+ err = mbi_init(handle, gic_data.domain);
+ if (err)
+ pr_err("Failed to initialize MBIs\n");
+ }
+
set_handle_irq(gic_handle_irq);
gic_update_vlpi_properties();
diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c
index a59bdbc..7b531fd 100644
--- a/drivers/irqchip/irq-meson-gpio.c
+++ b/drivers/irqchip/irq-meson-gpio.c
@@ -63,11 +63,16 @@ static const struct meson_gpio_irq_params gxl_params = {
.nr_hwirq = 110,
};
+static const struct meson_gpio_irq_params axg_params = {
+ .nr_hwirq = 100,
+};
+
static const struct of_device_id meson_irq_gpio_matches[] = {
{ .compatible = "amlogic,meson8-gpio-intc", .data = &meson8_params },
{ .compatible = "amlogic,meson8b-gpio-intc", .data = &meson8b_params },
{ .compatible = "amlogic,meson-gxbb-gpio-intc", .data = &gxbb_params },
{ .compatible = "amlogic,meson-gxl-gpio-intc", .data = &gxl_params },
+ { .compatible = "amlogic,meson-axg-gpio-intc", .data = &axg_params },
{ }
};
diff --git a/drivers/irqchip/irq-mvebu-gicp.c b/drivers/irqchip/irq-mvebu-gicp.c
index 17a4a7b..4e17f70 100644
--- a/drivers/irqchip/irq-mvebu-gicp.c
+++ b/drivers/irqchip/irq-mvebu-gicp.c
@@ -19,8 +19,6 @@
#include <dt-bindings/interrupt-controller/arm-gic.h>
-#include "irq-mvebu-gicp.h"
-
#define GICP_SETSPI_NSR_OFFSET 0x0
#define GICP_CLRSPI_NSR_OFFSET 0x8
@@ -55,34 +53,18 @@ static int gicp_idx_to_spi(struct mvebu_gicp *gicp, int idx)
return -EINVAL;
}
-int mvebu_gicp_get_doorbells(struct device_node *dn, phys_addr_t *setspi,
- phys_addr_t *clrspi)
-{
- struct platform_device *pdev;
- struct mvebu_gicp *gicp;
-
- pdev = of_find_device_by_node(dn);
- if (!pdev)
- return -ENODEV;
-
- gicp = platform_get_drvdata(pdev);
- if (!gicp)
- return -ENODEV;
-
- *setspi = gicp->res->start + GICP_SETSPI_NSR_OFFSET;
- *clrspi = gicp->res->start + GICP_CLRSPI_NSR_OFFSET;
-
- return 0;
-}
-
static void gicp_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
{
struct mvebu_gicp *gicp = data->chip_data;
phys_addr_t setspi = gicp->res->start + GICP_SETSPI_NSR_OFFSET;
+ phys_addr_t clrspi = gicp->res->start + GICP_CLRSPI_NSR_OFFSET;
- msg->data = data->hwirq;
- msg->address_lo = lower_32_bits(setspi);
- msg->address_hi = upper_32_bits(setspi);
+ msg[0].data = data->hwirq;
+ msg[0].address_lo = lower_32_bits(setspi);
+ msg[0].address_hi = upper_32_bits(setspi);
+ msg[1].data = data->hwirq;
+ msg[1].address_lo = lower_32_bits(clrspi);
+ msg[1].address_hi = upper_32_bits(clrspi);
}
static struct irq_chip gicp_irq_chip = {
@@ -170,13 +152,15 @@ static const struct irq_domain_ops gicp_domain_ops = {
static struct irq_chip gicp_msi_irq_chip = {
.name = "GICP",
.irq_set_type = irq_chip_set_type_parent,
+ .flags = IRQCHIP_SUPPORTS_LEVEL_MSI,
};
static struct msi_domain_ops gicp_msi_ops = {
};
static struct msi_domain_info gicp_msi_domain_info = {
- .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS),
+ .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+ MSI_FLAG_LEVEL_CAPABLE),
.ops = &gicp_msi_ops,
.chip = &gicp_msi_irq_chip,
};
diff --git a/drivers/irqchip/irq-mvebu-gicp.h b/drivers/irqchip/irq-mvebu-gicp.h
deleted file mode 100644
index eaa12fb..0000000
--- a/drivers/irqchip/irq-mvebu-gicp.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __MVEBU_GICP_H__
-#define __MVEBU_GICP_H__
-
-#include <linux/types.h>
-
-struct device_node;
-
-int mvebu_gicp_get_doorbells(struct device_node *dn, phys_addr_t *setspi,
- phys_addr_t *clrspi);
-
-#endif /* __MVEBU_GICP_H__ */
diff --git a/drivers/irqchip/irq-mvebu-icu.c b/drivers/irqchip/irq-mvebu-icu.c
index e18c48d..1306333 100644
--- a/drivers/irqchip/irq-mvebu-icu.c
+++ b/drivers/irqchip/irq-mvebu-icu.c
@@ -21,8 +21,6 @@
#include <dt-bindings/interrupt-controller/mvebu-icu.h>
-#include "irq-mvebu-gicp.h"
-
/* ICU registers */
#define ICU_SETSPI_NSR_AL 0x10
#define ICU_SETSPI_NSR_AH 0x14
@@ -43,6 +41,7 @@ struct mvebu_icu {
void __iomem *base;
struct irq_domain *domain;
struct device *dev;
+ atomic_t initialized;
};
struct mvebu_icu_irq_data {
@@ -51,6 +50,18 @@ struct mvebu_icu_irq_data {
unsigned int type;
};
+static void mvebu_icu_init(struct mvebu_icu *icu, struct msi_msg *msg)
+{
+ if (atomic_cmpxchg(&icu->initialized, false, true))
+ return;
+
+ /* Set Clear/Set ICU SPI message address in AP */
+ writel_relaxed(msg[0].address_hi, icu->base + ICU_SETSPI_NSR_AH);
+ writel_relaxed(msg[0].address_lo, icu->base + ICU_SETSPI_NSR_AL);
+ writel_relaxed(msg[1].address_hi, icu->base + ICU_CLRSPI_NSR_AH);
+ writel_relaxed(msg[1].address_lo, icu->base + ICU_CLRSPI_NSR_AL);
+}
+
static void mvebu_icu_write_msg(struct msi_desc *desc, struct msi_msg *msg)
{
struct irq_data *d = irq_get_irq_data(desc->irq);
@@ -59,6 +70,8 @@ static void mvebu_icu_write_msg(struct msi_desc *desc, struct msi_msg *msg)
unsigned int icu_int;
if (msg->address_lo || msg->address_hi) {
+ /* One off initialization */
+ mvebu_icu_init(icu, msg);
/* Configure the ICU with irq number & type */
icu_int = msg->data | ICU_INT_ENABLE;
if (icu_irqd->type & IRQ_TYPE_EDGE_RISING)
@@ -197,9 +210,7 @@ static int mvebu_icu_probe(struct platform_device *pdev)
struct device_node *node = pdev->dev.of_node;
struct device_node *gicp_dn;
struct resource *res;
- phys_addr_t setspi, clrspi;
- u32 i, icu_int;
- int ret;
+ int i;
icu = devm_kzalloc(&pdev->dev, sizeof(struct mvebu_icu),
GFP_KERNEL);
@@ -242,22 +253,12 @@ static int mvebu_icu_probe(struct platform_device *pdev)
if (!gicp_dn)
return -ENODEV;
- ret = mvebu_gicp_get_doorbells(gicp_dn, &setspi, &clrspi);
- if (ret)
- return ret;
-
- /* Set Clear/Set ICU SPI message address in AP */
- writel_relaxed(upper_32_bits(setspi), icu->base + ICU_SETSPI_NSR_AH);
- writel_relaxed(lower_32_bits(setspi), icu->base + ICU_SETSPI_NSR_AL);
- writel_relaxed(upper_32_bits(clrspi), icu->base + ICU_CLRSPI_NSR_AH);
- writel_relaxed(lower_32_bits(clrspi), icu->base + ICU_CLRSPI_NSR_AL);
-
/*
* Clean all ICU interrupts with type SPI_NSR, required to
* avoid unpredictable SPI assignments done by firmware.
*/
for (i = 0 ; i < ICU_MAX_IRQS ; i++) {
- icu_int = readl(icu->base + ICU_INT_CFG(i));
+ u32 icu_int = readl_relaxed(icu->base + ICU_INT_CFG(i));
if ((icu_int >> ICU_GROUP_SHIFT) == ICU_GRP_NSR)
writel_relaxed(0x0, icu->base + ICU_INT_CFG(i));
}
diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c
index 36f0fbe..5089c1e 100644
--- a/drivers/irqchip/irq-stm32-exti.c
+++ b/drivers/irqchip/irq-stm32-exti.c
@@ -14,6 +14,9 @@
#include <linux/irqdomain.h>
#include <linux/of_address.h>
#include <linux/of_irq.h>
+#include <linux/syscore_ops.h>
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
#define IRQS_PER_BANK 32
@@ -23,29 +26,69 @@ struct stm32_exti_bank {
u32 rtsr_ofst;
u32 ftsr_ofst;
u32 swier_ofst;
- u32 pr_ofst;
+ u32 rpr_ofst;
+ u32 fpr_ofst;
};
+#define UNDEF_REG ~0
+
+struct stm32_desc_irq {
+ u32 exti;
+ u32 irq_parent;
+};
+
+struct stm32_exti_drv_data {
+ const struct stm32_exti_bank **exti_banks;
+ const struct stm32_desc_irq *desc_irqs;
+ u32 bank_nr;
+ u32 irq_nr;
+};
+
+struct stm32_exti_chip_data {
+ struct stm32_exti_host_data *host_data;
+ const struct stm32_exti_bank *reg_bank;
+ struct raw_spinlock rlock;
+ u32 wake_active;
+ u32 mask_cache;
+ u32 rtsr_cache;
+ u32 ftsr_cache;
+};
+
+struct stm32_exti_host_data {
+ void __iomem *base;
+ struct stm32_exti_chip_data *chips_data;
+ const struct stm32_exti_drv_data *drv_data;
+};
+
+static struct stm32_exti_host_data *stm32_host_data;
+
static const struct stm32_exti_bank stm32f4xx_exti_b1 = {
.imr_ofst = 0x00,
.emr_ofst = 0x04,
.rtsr_ofst = 0x08,
.ftsr_ofst = 0x0C,
.swier_ofst = 0x10,
- .pr_ofst = 0x14,
+ .rpr_ofst = 0x14,
+ .fpr_ofst = UNDEF_REG,
};
static const struct stm32_exti_bank *stm32f4xx_exti_banks[] = {
&stm32f4xx_exti_b1,
};
+static const struct stm32_exti_drv_data stm32f4xx_drv_data = {
+ .exti_banks = stm32f4xx_exti_banks,
+ .bank_nr = ARRAY_SIZE(stm32f4xx_exti_banks),
+};
+
static const struct stm32_exti_bank stm32h7xx_exti_b1 = {
.imr_ofst = 0x80,
.emr_ofst = 0x84,
.rtsr_ofst = 0x00,
.ftsr_ofst = 0x04,
.swier_ofst = 0x08,
- .pr_ofst = 0x88,
+ .rpr_ofst = 0x88,
+ .fpr_ofst = UNDEF_REG,
};
static const struct stm32_exti_bank stm32h7xx_exti_b2 = {
@@ -54,7 +97,8 @@ static const struct stm32_exti_bank stm32h7xx_exti_b2 = {
.rtsr_ofst = 0x20,
.ftsr_ofst = 0x24,
.swier_ofst = 0x28,
- .pr_ofst = 0x98,
+ .rpr_ofst = 0x98,
+ .fpr_ofst = UNDEF_REG,
};
static const struct stm32_exti_bank stm32h7xx_exti_b3 = {
@@ -63,7 +107,8 @@ static const struct stm32_exti_bank stm32h7xx_exti_b3 = {
.rtsr_ofst = 0x40,
.ftsr_ofst = 0x44,
.swier_ofst = 0x48,
- .pr_ofst = 0xA8,
+ .rpr_ofst = 0xA8,
+ .fpr_ofst = UNDEF_REG,
};
static const struct stm32_exti_bank *stm32h7xx_exti_banks[] = {
@@ -72,18 +117,105 @@ static const struct stm32_exti_bank *stm32h7xx_exti_banks[] = {
&stm32h7xx_exti_b3,
};
-static unsigned long stm32_exti_pending(struct irq_chip_generic *gc)
-{
- const struct stm32_exti_bank *stm32_bank = gc->private;
+static const struct stm32_exti_drv_data stm32h7xx_drv_data = {
+ .exti_banks = stm32h7xx_exti_banks,
+ .bank_nr = ARRAY_SIZE(stm32h7xx_exti_banks),
+};
- return irq_reg_readl(gc, stm32_bank->pr_ofst);
+static const struct stm32_exti_bank stm32mp1_exti_b1 = {
+ .imr_ofst = 0x80,
+ .emr_ofst = 0x84,
+ .rtsr_ofst = 0x00,
+ .ftsr_ofst = 0x04,
+ .swier_ofst = 0x08,
+ .rpr_ofst = 0x0C,
+ .fpr_ofst = 0x10,
+};
+
+static const struct stm32_exti_bank stm32mp1_exti_b2 = {
+ .imr_ofst = 0x90,
+ .emr_ofst = 0x94,
+ .rtsr_ofst = 0x20,
+ .ftsr_ofst = 0x24,
+ .swier_ofst = 0x28,
+ .rpr_ofst = 0x2C,
+ .fpr_ofst = 0x30,
+};
+
+static const struct stm32_exti_bank stm32mp1_exti_b3 = {
+ .imr_ofst = 0xA0,
+ .emr_ofst = 0xA4,
+ .rtsr_ofst = 0x40,
+ .ftsr_ofst = 0x44,
+ .swier_ofst = 0x48,
+ .rpr_ofst = 0x4C,
+ .fpr_ofst = 0x50,
+};
+
+static const struct stm32_exti_bank *stm32mp1_exti_banks[] = {
+ &stm32mp1_exti_b1,
+ &stm32mp1_exti_b2,
+ &stm32mp1_exti_b3,
+};
+
+static const struct stm32_desc_irq stm32mp1_desc_irq[] = {
+ { .exti = 1, .irq_parent = 7 },
+ { .exti = 2, .irq_parent = 8 },
+ { .exti = 3, .irq_parent = 9 },
+ { .exti = 4, .irq_parent = 10 },
+ { .exti = 5, .irq_parent = 23 },
+ { .exti = 6, .irq_parent = 64 },
+ { .exti = 7, .irq_parent = 65 },
+ { .exti = 8, .irq_parent = 66 },
+ { .exti = 9, .irq_parent = 67 },
+ { .exti = 10, .irq_parent = 40 },
+ { .exti = 11, .irq_parent = 42 },
+ { .exti = 12, .irq_parent = 76 },
+ { .exti = 13, .irq_parent = 77 },
+ { .exti = 14, .irq_parent = 121 },
+ { .exti = 15, .irq_parent = 127 },
+ { .exti = 16, .irq_parent = 1 },
+ { .exti = 65, .irq_parent = 144 },
+ { .exti = 68, .irq_parent = 143 },
+ { .exti = 73, .irq_parent = 129 },
+};
+
+static const struct stm32_exti_drv_data stm32mp1_drv_data = {
+ .exti_banks = stm32mp1_exti_banks,
+ .bank_nr = ARRAY_SIZE(stm32mp1_exti_banks),
+ .desc_irqs = stm32mp1_desc_irq,
+ .irq_nr = ARRAY_SIZE(stm32mp1_desc_irq),
+};
+
+static int stm32_exti_to_irq(const struct stm32_exti_drv_data *drv_data,
+ irq_hw_number_t hwirq)
+{
+ const struct stm32_desc_irq *desc_irq;
+ int i;
+
+ if (!drv_data->desc_irqs)
+ return -EINVAL;
+
+ for (i = 0; i < drv_data->irq_nr; i++) {
+ desc_irq = &drv_data->desc_irqs[i];
+ if (desc_irq->exti == hwirq)
+ return desc_irq->irq_parent;
+ }
+
+ return -EINVAL;
}
-static void stm32_exti_irq_ack(struct irq_chip_generic *gc, u32 mask)
+static unsigned long stm32_exti_pending(struct irq_chip_generic *gc)
{
- const struct stm32_exti_bank *stm32_bank = gc->private;
+ struct stm32_exti_chip_data *chip_data = gc->private;
+ const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+ unsigned long pending;
- irq_reg_writel(gc, mask, stm32_bank->pr_ofst);
+ pending = irq_reg_readl(gc, stm32_bank->rpr_ofst);
+ if (stm32_bank->fpr_ofst != UNDEF_REG)
+ pending |= irq_reg_readl(gc, stm32_bank->fpr_ofst);
+
+ return pending;
}
static void stm32_irq_handler(struct irq_desc *desc)
@@ -92,7 +224,6 @@ static void stm32_irq_handler(struct irq_desc *desc)
struct irq_chip *chip = irq_desc_get_chip(desc);
unsigned int virq, nbanks = domain->gc->num_chips;
struct irq_chip_generic *gc;
- const struct stm32_exti_bank *stm32_bank;
unsigned long pending;
int n, i, irq_base = 0;
@@ -100,13 +231,11 @@ static void stm32_irq_handler(struct irq_desc *desc)
for (i = 0; i < nbanks; i++, irq_base += IRQS_PER_BANK) {
gc = irq_get_domain_generic_chip(domain, irq_base);
- stm32_bank = gc->private;
while ((pending = stm32_exti_pending(gc))) {
for_each_set_bit(n, &pending, IRQS_PER_BANK) {
virq = irq_find_mapping(domain, irq_base + n);
generic_handle_irq(virq);
- stm32_exti_irq_ack(gc, BIT(n));
}
}
}
@@ -114,34 +243,48 @@ static void stm32_irq_handler(struct irq_desc *desc)
chained_irq_exit(chip, desc);
}
-static int stm32_irq_set_type(struct irq_data *data, unsigned int type)
+static int stm32_exti_set_type(struct irq_data *d,
+ unsigned int type, u32 *rtsr, u32 *ftsr)
{
- struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
- const struct stm32_exti_bank *stm32_bank = gc->private;
- int pin = data->hwirq % IRQS_PER_BANK;
+ u32 mask = BIT(d->hwirq % IRQS_PER_BANK);
+
+ switch (type) {
+ case IRQ_TYPE_EDGE_RISING:
+ *rtsr |= mask;
+ *ftsr &= ~mask;
+ break;
+ case IRQ_TYPE_EDGE_FALLING:
+ *rtsr &= ~mask;
+ *ftsr |= mask;
+ break;
+ case IRQ_TYPE_EDGE_BOTH:
+ *rtsr |= mask;
+ *ftsr |= mask;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int stm32_irq_set_type(struct irq_data *d, unsigned int type)
+{
+ struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+ struct stm32_exti_chip_data *chip_data = gc->private;
+ const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
u32 rtsr, ftsr;
+ int err;
irq_gc_lock(gc);
rtsr = irq_reg_readl(gc, stm32_bank->rtsr_ofst);
ftsr = irq_reg_readl(gc, stm32_bank->ftsr_ofst);
- switch (type) {
- case IRQ_TYPE_EDGE_RISING:
- rtsr |= BIT(pin);
- ftsr &= ~BIT(pin);
- break;
- case IRQ_TYPE_EDGE_FALLING:
- rtsr &= ~BIT(pin);
- ftsr |= BIT(pin);
- break;
- case IRQ_TYPE_EDGE_BOTH:
- rtsr |= BIT(pin);
- ftsr |= BIT(pin);
- break;
- default:
+ err = stm32_exti_set_type(d, type, &rtsr, &ftsr);
+ if (err) {
irq_gc_unlock(gc);
- return -EINVAL;
+ return err;
}
irq_reg_writel(gc, rtsr, stm32_bank->rtsr_ofst);
@@ -152,40 +295,59 @@ static int stm32_irq_set_type(struct irq_data *data, unsigned int type)
return 0;
}
-static int stm32_irq_set_wake(struct irq_data *data, unsigned int on)
+static void stm32_chip_suspend(struct stm32_exti_chip_data *chip_data,
+ u32 wake_active)
{
- struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
- const struct stm32_exti_bank *stm32_bank = gc->private;
- int pin = data->hwirq % IRQS_PER_BANK;
- u32 imr;
+ const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+ void __iomem *base = chip_data->host_data->base;
+
+ /* save rtsr, ftsr registers */
+ chip_data->rtsr_cache = readl_relaxed(base + stm32_bank->rtsr_ofst);
+ chip_data->ftsr_cache = readl_relaxed(base + stm32_bank->ftsr_ofst);
+
+ writel_relaxed(wake_active, base + stm32_bank->imr_ofst);
+}
+
+static void stm32_chip_resume(struct stm32_exti_chip_data *chip_data,
+ u32 mask_cache)
+{
+ const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+ void __iomem *base = chip_data->host_data->base;
+
+ /* restore rtsr, ftsr, registers */
+ writel_relaxed(chip_data->rtsr_cache, base + stm32_bank->rtsr_ofst);
+ writel_relaxed(chip_data->ftsr_cache, base + stm32_bank->ftsr_ofst);
+
+ writel_relaxed(mask_cache, base + stm32_bank->imr_ofst);
+}
+
+static void stm32_irq_suspend(struct irq_chip_generic *gc)
+{
+ struct stm32_exti_chip_data *chip_data = gc->private;
irq_gc_lock(gc);
-
- imr = irq_reg_readl(gc, stm32_bank->imr_ofst);
- if (on)
- imr |= BIT(pin);
- else
- imr &= ~BIT(pin);
- irq_reg_writel(gc, imr, stm32_bank->imr_ofst);
-
+ stm32_chip_suspend(chip_data, gc->wake_active);
irq_gc_unlock(gc);
+}
- return 0;
+static void stm32_irq_resume(struct irq_chip_generic *gc)
+{
+ struct stm32_exti_chip_data *chip_data = gc->private;
+
+ irq_gc_lock(gc);
+ stm32_chip_resume(chip_data, gc->mask_cache);
+ irq_gc_unlock(gc);
}
static int stm32_exti_alloc(struct irq_domain *d, unsigned int virq,
unsigned int nr_irqs, void *data)
{
- struct irq_chip_generic *gc;
struct irq_fwspec *fwspec = data;
irq_hw_number_t hwirq;
hwirq = fwspec->param[0];
- gc = irq_get_domain_generic_chip(d, hwirq);
irq_map_generic_chip(d, virq, hwirq);
- irq_domain_set_info(d, virq, hwirq, &gc->chip_types->chip, gc,
- handle_simple_irq, NULL, NULL);
return 0;
}
@@ -198,30 +360,318 @@ static void stm32_exti_free(struct irq_domain *d, unsigned int virq,
irq_domain_reset_irq_data(data);
}
-struct irq_domain_ops irq_exti_domain_ops = {
+static const struct irq_domain_ops irq_exti_domain_ops = {
.map = irq_map_generic_chip,
- .xlate = irq_domain_xlate_onetwocell,
.alloc = stm32_exti_alloc,
.free = stm32_exti_free,
};
-static int
-__init stm32_exti_init(const struct stm32_exti_bank **stm32_exti_banks,
- int bank_nr, struct device_node *node)
+static void stm32_irq_ack(struct irq_data *d)
{
- unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
- int nr_irqs, nr_exti, ret, i;
- struct irq_chip_generic *gc;
- struct irq_domain *domain;
- void *base;
+ struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+ struct stm32_exti_chip_data *chip_data = gc->private;
+ const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
- base = of_iomap(node, 0);
- if (!base) {
- pr_err("%pOF: Unable to map registers\n", node);
- return -ENOMEM;
+ irq_gc_lock(gc);
+
+ irq_reg_writel(gc, d->mask, stm32_bank->rpr_ofst);
+ if (stm32_bank->fpr_ofst != UNDEF_REG)
+ irq_reg_writel(gc, d->mask, stm32_bank->fpr_ofst);
+
+ irq_gc_unlock(gc);
+}
+
+static inline u32 stm32_exti_set_bit(struct irq_data *d, u32 reg)
+{
+ struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d);
+ void __iomem *base = chip_data->host_data->base;
+ u32 val;
+
+ val = readl_relaxed(base + reg);
+ val |= BIT(d->hwirq % IRQS_PER_BANK);
+ writel_relaxed(val, base + reg);
+
+ return val;
+}
+
+static inline u32 stm32_exti_clr_bit(struct irq_data *d, u32 reg)
+{
+ struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d);
+ void __iomem *base = chip_data->host_data->base;
+ u32 val;
+
+ val = readl_relaxed(base + reg);
+ val &= ~BIT(d->hwirq % IRQS_PER_BANK);
+ writel_relaxed(val, base + reg);
+
+ return val;
+}
+
+static void stm32_exti_h_eoi(struct irq_data *d)
+{
+ struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d);
+ const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+
+ raw_spin_lock(&chip_data->rlock);
+
+ stm32_exti_set_bit(d, stm32_bank->rpr_ofst);
+ if (stm32_bank->fpr_ofst != UNDEF_REG)
+ stm32_exti_set_bit(d, stm32_bank->fpr_ofst);
+
+ raw_spin_unlock(&chip_data->rlock);
+
+ if (d->parent_data->chip)
+ irq_chip_eoi_parent(d);
+}
+
+static void stm32_exti_h_mask(struct irq_data *d)
+{
+ struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d);
+ const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+
+ raw_spin_lock(&chip_data->rlock);
+ chip_data->mask_cache = stm32_exti_clr_bit(d, stm32_bank->imr_ofst);
+ raw_spin_unlock(&chip_data->rlock);
+
+ if (d->parent_data->chip)
+ irq_chip_mask_parent(d);
+}
+
+static void stm32_exti_h_unmask(struct irq_data *d)
+{
+ struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d);
+ const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+
+ raw_spin_lock(&chip_data->rlock);
+ chip_data->mask_cache = stm32_exti_set_bit(d, stm32_bank->imr_ofst);
+ raw_spin_unlock(&chip_data->rlock);
+
+ if (d->parent_data->chip)
+ irq_chip_unmask_parent(d);
+}
+
+static int stm32_exti_h_set_type(struct irq_data *d, unsigned int type)
+{
+ struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d);
+ const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+ void __iomem *base = chip_data->host_data->base;
+ u32 rtsr, ftsr;
+ int err;
+
+ raw_spin_lock(&chip_data->rlock);
+ rtsr = readl_relaxed(base + stm32_bank->rtsr_ofst);
+ ftsr = readl_relaxed(base + stm32_bank->ftsr_ofst);
+
+ err = stm32_exti_set_type(d, type, &rtsr, &ftsr);
+ if (err) {
+ raw_spin_unlock(&chip_data->rlock);
+ return err;
}
- domain = irq_domain_add_linear(node, bank_nr * IRQS_PER_BANK,
+ writel_relaxed(rtsr, base + stm32_bank->rtsr_ofst);
+ writel_relaxed(ftsr, base + stm32_bank->ftsr_ofst);
+ raw_spin_unlock(&chip_data->rlock);
+
+ return 0;
+}
+
+static int stm32_exti_h_set_wake(struct irq_data *d, unsigned int on)
+{
+ struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d);
+ u32 mask = BIT(d->hwirq % IRQS_PER_BANK);
+
+ raw_spin_lock(&chip_data->rlock);
+
+ if (on)
+ chip_data->wake_active |= mask;
+ else
+ chip_data->wake_active &= ~mask;
+
+ raw_spin_unlock(&chip_data->rlock);
+
+ return 0;
+}
+
+static int stm32_exti_h_set_affinity(struct irq_data *d,
+ const struct cpumask *dest, bool force)
+{
+ if (d->parent_data->chip)
+ return irq_chip_set_affinity_parent(d, dest, force);
+
+ return -EINVAL;
+}
+
+#ifdef CONFIG_PM
+static int stm32_exti_h_suspend(void)
+{
+ struct stm32_exti_chip_data *chip_data;
+ int i;
+
+ for (i = 0; i < stm32_host_data->drv_data->bank_nr; i++) {
+ chip_data = &stm32_host_data->chips_data[i];
+ raw_spin_lock(&chip_data->rlock);
+ stm32_chip_suspend(chip_data, chip_data->wake_active);
+ raw_spin_unlock(&chip_data->rlock);
+ }
+
+ return 0;
+}
+
+static void stm32_exti_h_resume(void)
+{
+ struct stm32_exti_chip_data *chip_data;
+ int i;
+
+ for (i = 0; i < stm32_host_data->drv_data->bank_nr; i++) {
+ chip_data = &stm32_host_data->chips_data[i];
+ raw_spin_lock(&chip_data->rlock);
+ stm32_chip_resume(chip_data, chip_data->mask_cache);
+ raw_spin_unlock(&chip_data->rlock);
+ }
+}
+
+static struct syscore_ops stm32_exti_h_syscore_ops = {
+ .suspend = stm32_exti_h_suspend,
+ .resume = stm32_exti_h_resume,
+};
+
+static void stm32_exti_h_syscore_init(void)
+{
+ register_syscore_ops(&stm32_exti_h_syscore_ops);
+}
+#else
+static inline void stm32_exti_h_syscore_init(void) {}
+#endif
+
+static struct irq_chip stm32_exti_h_chip = {
+ .name = "stm32-exti-h",
+ .irq_eoi = stm32_exti_h_eoi,
+ .irq_mask = stm32_exti_h_mask,
+ .irq_unmask = stm32_exti_h_unmask,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
+ .irq_set_type = stm32_exti_h_set_type,
+ .irq_set_wake = stm32_exti_h_set_wake,
+ .flags = IRQCHIP_MASK_ON_SUSPEND,
+#ifdef CONFIG_SMP
+ .irq_set_affinity = stm32_exti_h_set_affinity,
+#endif
+};
+
+static int stm32_exti_h_domain_alloc(struct irq_domain *dm,
+ unsigned int virq,
+ unsigned int nr_irqs, void *data)
+{
+ struct stm32_exti_host_data *host_data = dm->host_data;
+ struct stm32_exti_chip_data *chip_data;
+ struct irq_fwspec *fwspec = data;
+ struct irq_fwspec p_fwspec;
+ irq_hw_number_t hwirq;
+ int p_irq, bank;
+
+ hwirq = fwspec->param[0];
+ bank = hwirq / IRQS_PER_BANK;
+ chip_data = &host_data->chips_data[bank];
+
+ irq_domain_set_hwirq_and_chip(dm, virq, hwirq,
+ &stm32_exti_h_chip, chip_data);
+
+ p_irq = stm32_exti_to_irq(host_data->drv_data, hwirq);
+ if (p_irq >= 0) {
+ p_fwspec.fwnode = dm->parent->fwnode;
+ p_fwspec.param_count = 3;
+ p_fwspec.param[0] = GIC_SPI;
+ p_fwspec.param[1] = p_irq;
+ p_fwspec.param[2] = IRQ_TYPE_LEVEL_HIGH;
+
+ return irq_domain_alloc_irqs_parent(dm, virq, 1, &p_fwspec);
+ }
+
+ return 0;
+}
+
+static struct
+stm32_exti_host_data *stm32_exti_host_init(const struct stm32_exti_drv_data *dd,
+ struct device_node *node)
+{
+ struct stm32_exti_host_data *host_data;
+
+ host_data = kzalloc(sizeof(*host_data), GFP_KERNEL);
+ if (!host_data)
+ return NULL;
+
+ host_data->drv_data = dd;
+ host_data->chips_data = kcalloc(dd->bank_nr,
+ sizeof(struct stm32_exti_chip_data),
+ GFP_KERNEL);
+ if (!host_data->chips_data)
+ return NULL;
+
+ host_data->base = of_iomap(node, 0);
+ if (!host_data->base) {
+ pr_err("%pOF: Unable to map registers\n", node);
+ return NULL;
+ }
+
+ stm32_host_data = host_data;
+
+ return host_data;
+}
+
+static struct
+stm32_exti_chip_data *stm32_exti_chip_init(struct stm32_exti_host_data *h_data,
+ u32 bank_idx,
+ struct device_node *node)
+{
+ const struct stm32_exti_bank *stm32_bank;
+ struct stm32_exti_chip_data *chip_data;
+ void __iomem *base = h_data->base;
+ u32 irqs_mask;
+
+ stm32_bank = h_data->drv_data->exti_banks[bank_idx];
+ chip_data = &h_data->chips_data[bank_idx];
+ chip_data->host_data = h_data;
+ chip_data->reg_bank = stm32_bank;
+
+ raw_spin_lock_init(&chip_data->rlock);
+
+ /* Determine number of irqs supported */
+ writel_relaxed(~0UL, base + stm32_bank->rtsr_ofst);
+ irqs_mask = readl_relaxed(base + stm32_bank->rtsr_ofst);
+
+ /*
+ * This IP has no reset, so after hot reboot we should
+ * clear registers to avoid residue
+ */
+ writel_relaxed(0, base + stm32_bank->imr_ofst);
+ writel_relaxed(0, base + stm32_bank->emr_ofst);
+ writel_relaxed(0, base + stm32_bank->rtsr_ofst);
+ writel_relaxed(0, base + stm32_bank->ftsr_ofst);
+ writel_relaxed(~0UL, base + stm32_bank->rpr_ofst);
+ if (stm32_bank->fpr_ofst != UNDEF_REG)
+ writel_relaxed(~0UL, base + stm32_bank->fpr_ofst);
+
+ pr_info("%s: bank%d, External IRQs available:%#x\n",
+ node->full_name, bank_idx, irqs_mask);
+
+ return chip_data;
+}
+
+static int __init stm32_exti_init(const struct stm32_exti_drv_data *drv_data,
+ struct device_node *node)
+{
+ struct stm32_exti_host_data *host_data;
+ unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
+ int nr_irqs, ret, i;
+ struct irq_chip_generic *gc;
+ struct irq_domain *domain;
+
+ host_data = stm32_exti_host_init(drv_data, node);
+ if (!host_data) {
+ ret = -ENOMEM;
+ goto out_free_mem;
+ }
+
+ domain = irq_domain_add_linear(node, drv_data->bank_nr * IRQS_PER_BANK,
&irq_exti_domain_ops, NULL);
if (!domain) {
pr_err("%s: Could not register interrupt domain.\n",
@@ -234,44 +684,32 @@ __init stm32_exti_init(const struct stm32_exti_bank **stm32_exti_banks,
handle_edge_irq, clr, 0, 0);
if (ret) {
pr_err("%pOF: Could not allocate generic interrupt chip.\n",
- node);
+ node);
goto out_free_domain;
}
- for (i = 0; i < bank_nr; i++) {
- const struct stm32_exti_bank *stm32_bank = stm32_exti_banks[i];
- u32 irqs_mask;
+ for (i = 0; i < drv_data->bank_nr; i++) {
+ const struct stm32_exti_bank *stm32_bank;
+ struct stm32_exti_chip_data *chip_data;
+
+ stm32_bank = drv_data->exti_banks[i];
+ chip_data = stm32_exti_chip_init(host_data, i, node);
gc = irq_get_domain_generic_chip(domain, i * IRQS_PER_BANK);
- gc->reg_base = base;
+ gc->reg_base = host_data->base;
gc->chip_types->type = IRQ_TYPE_EDGE_BOTH;
- gc->chip_types->chip.irq_ack = irq_gc_ack_set_bit;
+ gc->chip_types->chip.irq_ack = stm32_irq_ack;
gc->chip_types->chip.irq_mask = irq_gc_mask_clr_bit;
gc->chip_types->chip.irq_unmask = irq_gc_mask_set_bit;
gc->chip_types->chip.irq_set_type = stm32_irq_set_type;
- gc->chip_types->chip.irq_set_wake = stm32_irq_set_wake;
- gc->chip_types->regs.ack = stm32_bank->pr_ofst;
+ gc->chip_types->chip.irq_set_wake = irq_gc_set_wake;
+ gc->suspend = stm32_irq_suspend;
+ gc->resume = stm32_irq_resume;
+ gc->wake_enabled = IRQ_MSK(IRQS_PER_BANK);
+
gc->chip_types->regs.mask = stm32_bank->imr_ofst;
- gc->private = (void *)stm32_bank;
-
- /* Determine number of irqs supported */
- writel_relaxed(~0UL, base + stm32_bank->rtsr_ofst);
- irqs_mask = readl_relaxed(base + stm32_bank->rtsr_ofst);
- nr_exti = fls(readl_relaxed(base + stm32_bank->rtsr_ofst));
-
- /*
- * This IP has no reset, so after hot reboot we should
- * clear registers to avoid residue
- */
- writel_relaxed(0, base + stm32_bank->imr_ofst);
- writel_relaxed(0, base + stm32_bank->emr_ofst);
- writel_relaxed(0, base + stm32_bank->rtsr_ofst);
- writel_relaxed(0, base + stm32_bank->ftsr_ofst);
- writel_relaxed(~0UL, base + stm32_bank->pr_ofst);
-
- pr_info("%s: bank%d, External IRQs available:%#x\n",
- node->full_name, i, irqs_mask);
+ gc->private = (void *)chip_data;
}
nr_irqs = of_irq_count(node);
@@ -287,15 +725,69 @@ __init stm32_exti_init(const struct stm32_exti_bank **stm32_exti_banks,
out_free_domain:
irq_domain_remove(domain);
out_unmap:
- iounmap(base);
+ iounmap(host_data->base);
+out_free_mem:
+ kfree(host_data->chips_data);
+ kfree(host_data);
+ return ret;
+}
+
+static const struct irq_domain_ops stm32_exti_h_domain_ops = {
+ .alloc = stm32_exti_h_domain_alloc,
+ .free = irq_domain_free_irqs_common,
+};
+
+static int
+__init stm32_exti_hierarchy_init(const struct stm32_exti_drv_data *drv_data,
+ struct device_node *node,
+ struct device_node *parent)
+{
+ struct irq_domain *parent_domain, *domain;
+ struct stm32_exti_host_data *host_data;
+ int ret, i;
+
+ parent_domain = irq_find_host(parent);
+ if (!parent_domain) {
+ pr_err("interrupt-parent not found\n");
+ return -EINVAL;
+ }
+
+ host_data = stm32_exti_host_init(drv_data, node);
+ if (!host_data) {
+ ret = -ENOMEM;
+ goto out_free_mem;
+ }
+
+ for (i = 0; i < drv_data->bank_nr; i++)
+ stm32_exti_chip_init(host_data, i, node);
+
+ domain = irq_domain_add_hierarchy(parent_domain, 0,
+ drv_data->bank_nr * IRQS_PER_BANK,
+ node, &stm32_exti_h_domain_ops,
+ host_data);
+
+ if (!domain) {
+ pr_err("%s: Could not register exti domain.\n", node->name);
+ ret = -ENOMEM;
+ goto out_unmap;
+ }
+
+ stm32_exti_h_syscore_init();
+
+ return 0;
+
+out_unmap:
+ iounmap(host_data->base);
+out_free_mem:
+ kfree(host_data->chips_data);
+ kfree(host_data);
return ret;
}
static int __init stm32f4_exti_of_init(struct device_node *np,
struct device_node *parent)
{
- return stm32_exti_init(stm32f4xx_exti_banks,
- ARRAY_SIZE(stm32f4xx_exti_banks), np);
+ return stm32_exti_init(&stm32f4xx_drv_data, np);
}
IRQCHIP_DECLARE(stm32f4_exti, "st,stm32-exti", stm32f4_exti_of_init);
@@ -303,8 +795,15 @@ IRQCHIP_DECLARE(stm32f4_exti, "st,stm32-exti", stm32f4_exti_of_init);
static int __init stm32h7_exti_of_init(struct device_node *np,
struct device_node *parent)
{
- return stm32_exti_init(stm32h7xx_exti_banks,
- ARRAY_SIZE(stm32h7xx_exti_banks), np);
+ return stm32_exti_init(&stm32h7xx_drv_data, np);
}
IRQCHIP_DECLARE(stm32h7_exti, "st,stm32h7-exti", stm32h7_exti_of_init);
+
+static int __init stm32mp1_exti_of_init(struct device_node *np,
+ struct device_node *parent)
+{
+ return stm32_exti_hierarchy_init(&stm32mp1_drv_data, np, parent);
+}
+
+IRQCHIP_DECLARE(stm32mp1_exti, "st,stm32mp1-exti", stm32mp1_exti_of_init);
diff --git a/drivers/irqchip/qcom-irq-combiner.c b/drivers/irqchip/qcom-irq-combiner.c
index f312659..7f0c0be 100644
--- a/drivers/irqchip/qcom-irq-combiner.c
+++ b/drivers/irqchip/qcom-irq-combiner.c
@@ -1,4 +1,4 @@
-/* Copyright (c) 2015-2016, The Linux Foundation. All rights reserved.
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 and
@@ -68,7 +68,7 @@ static void combiner_handle_irq(struct irq_desc *desc)
bit = readl_relaxed(combiner->regs[reg].addr);
status = bit & combiner->regs[reg].enabled;
- if (!status)
+ if (bit && !status)
pr_warn_ratelimited("Unexpected IRQ on CPU%d: (%08x %08lx %p)\n",
smp_processor_id(), bit,
combiner->regs[reg].enabled,
diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c
index 19cd937..baa1ee2 100644
--- a/drivers/isdn/capi/capi.c
+++ b/drivers/isdn/capi/capi.c
@@ -1340,19 +1340,6 @@ static int capi20_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int capi20_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, capi20_proc_show, NULL);
-}
-
-static const struct file_operations capi20_proc_fops = {
- .owner = THIS_MODULE,
- .open = capi20_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/*
* /proc/capi/capi20ncci:
* applid ncci
@@ -1373,23 +1360,10 @@ static int capi20ncci_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int capi20ncci_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, capi20ncci_proc_show, NULL);
-}
-
-static const struct file_operations capi20ncci_proc_fops = {
- .owner = THIS_MODULE,
- .open = capi20ncci_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static void __init proc_init(void)
{
- proc_create("capi/capi20", 0, NULL, &capi20_proc_fops);
- proc_create("capi/capi20ncci", 0, NULL, &capi20ncci_proc_fops);
+ proc_create_single("capi/capi20", 0, NULL, capi20_proc_show);
+ proc_create_single("capi/capi20ncci", 0, NULL, capi20ncci_proc_show);
}
static void __exit proc_exit(void)
diff --git a/drivers/isdn/capi/capidrv.c b/drivers/isdn/capi/capidrv.c
index 49fef08..7ac5179 100644
--- a/drivers/isdn/capi/capidrv.c
+++ b/drivers/isdn/capi/capidrv.c
@@ -2460,22 +2460,9 @@ static int capidrv_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int capidrv_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, capidrv_proc_show, NULL);
-}
-
-static const struct file_operations capidrv_proc_fops = {
- .owner = THIS_MODULE,
- .open = capidrv_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static void __init proc_init(void)
{
- proc_create("capi/capidrv", 0, NULL, &capidrv_proc_fops);
+ proc_create_single("capi/capidrv", 0, NULL, capidrv_proc_show);
}
static void __exit proc_exit(void)
diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c
index 46c189a..0ff517d 100644
--- a/drivers/isdn/capi/kcapi.c
+++ b/drivers/isdn/capi/kcapi.c
@@ -534,7 +534,8 @@ int attach_capi_ctr(struct capi_ctr *ctr)
init_waitqueue_head(&ctr->state_wait_queue);
sprintf(ctr->procfn, "capi/controllers/%d", ctr->cnr);
- ctr->procent = proc_create_data(ctr->procfn, 0, NULL, ctr->proc_fops, ctr);
+ ctr->procent = proc_create_single_data(ctr->procfn, 0, NULL,
+ ctr->proc_show, ctr);
ncontrollers++;
diff --git a/drivers/isdn/capi/kcapi_proc.c b/drivers/isdn/capi/kcapi_proc.c
index 68db3c5..c94bd12 100644
--- a/drivers/isdn/capi/kcapi_proc.c
+++ b/drivers/isdn/capi/kcapi_proc.c
@@ -108,32 +108,6 @@ static const struct seq_operations seq_contrstats_ops = {
.show = contrstats_show,
};
-static int seq_controller_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &seq_controller_ops);
-}
-
-static int seq_contrstats_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &seq_contrstats_ops);
-}
-
-static const struct file_operations proc_controller_ops = {
- .owner = THIS_MODULE,
- .open = seq_controller_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-static const struct file_operations proc_contrstats_ops = {
- .owner = THIS_MODULE,
- .open = seq_contrstats_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
// /proc/capi/applications:
// applid l3cnt dblkcnt dblklen #ncci recvqueuelen
// /proc/capi/applstats:
@@ -216,34 +190,6 @@ static const struct seq_operations seq_applstats_ops = {
.show = applstats_show,
};
-static int
-seq_applications_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &seq_applications_ops);
-}
-
-static int
-seq_applstats_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &seq_applstats_ops);
-}
-
-static const struct file_operations proc_applications_ops = {
- .owner = THIS_MODULE,
- .open = seq_applications_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-static const struct file_operations proc_applstats_ops = {
- .owner = THIS_MODULE,
- .open = seq_applstats_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
// ---------------------------------------------------------------------------
static void *capi_driver_start(struct seq_file *seq, loff_t *pos)
@@ -279,22 +225,6 @@ static const struct seq_operations seq_capi_driver_ops = {
.show = capi_driver_show,
};
-static int
-seq_capi_driver_open(struct inode *inode, struct file *file)
-{
- int err;
- err = seq_open(file, &seq_capi_driver_ops);
- return err;
-}
-
-static const struct file_operations proc_driver_ops = {
- .owner = THIS_MODULE,
- .open = seq_capi_driver_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
// ---------------------------------------------------------------------------
void __init
@@ -302,11 +232,11 @@ kcapi_proc_init(void)
{
proc_mkdir("capi", NULL);
proc_mkdir("capi/controllers", NULL);
- proc_create("capi/controller", 0, NULL, &proc_controller_ops);
- proc_create("capi/contrstats", 0, NULL, &proc_contrstats_ops);
- proc_create("capi/applications", 0, NULL, &proc_applications_ops);
- proc_create("capi/applstats", 0, NULL, &proc_applstats_ops);
- proc_create("capi/driver", 0, NULL, &proc_driver_ops);
+ proc_create_seq("capi/controller", 0, NULL, &seq_controller_ops);
+ proc_create_seq("capi/contrstats", 0, NULL, &seq_contrstats_ops);
+ proc_create_seq("capi/applications", 0, NULL, &seq_applications_ops);
+ proc_create_seq("capi/applstats", 0, NULL, &seq_applstats_ops);
+ proc_create_seq("capi/driver", 0, NULL, &seq_capi_driver_ops);
}
void __exit
diff --git a/drivers/isdn/gigaset/capi.c b/drivers/isdn/gigaset/capi.c
index ccec777..56748af 100644
--- a/drivers/isdn/gigaset/capi.c
+++ b/drivers/isdn/gigaset/capi.c
@@ -2437,19 +2437,6 @@ static int gigaset_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int gigaset_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, gigaset_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations gigaset_proc_fops = {
- .owner = THIS_MODULE,
- .open = gigaset_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/**
* gigaset_isdn_regdev() - register device to LL
* @cs: device descriptor structure.
@@ -2479,7 +2466,7 @@ int gigaset_isdn_regdev(struct cardstate *cs, const char *isdnid)
iif->ctr.release_appl = gigaset_release_appl;
iif->ctr.send_message = gigaset_send_message;
iif->ctr.procinfo = gigaset_procinfo;
- iif->ctr.proc_fops = &gigaset_proc_fops;
+ iif->ctr.proc_show = gigaset_proc_show,
INIT_LIST_HEAD(&iif->appls);
skb_queue_head_init(&iif->sendqueue);
atomic_set(&iif->sendqlen, 0);
diff --git a/drivers/isdn/hardware/avm/avmcard.h b/drivers/isdn/hardware/avm/avmcard.h
index c95712d..cdfa89c 100644
--- a/drivers/isdn/hardware/avm/avmcard.h
+++ b/drivers/isdn/hardware/avm/avmcard.h
@@ -556,7 +556,7 @@ u16 b1_send_message(struct capi_ctr *ctrl, struct sk_buff *skb);
void b1_parse_version(avmctrl_info *card);
irqreturn_t b1_interrupt(int interrupt, void *devptr);
-extern const struct file_operations b1ctl_proc_fops;
+int b1_proc_show(struct seq_file *m, void *v);
avmcard_dmainfo *avmcard_dma_alloc(char *name, struct pci_dev *,
long rsize, long ssize);
@@ -576,6 +576,6 @@ void b1dma_register_appl(struct capi_ctr *ctrl,
capi_register_params *rp);
void b1dma_release_appl(struct capi_ctr *ctrl, u16 appl);
u16 b1dma_send_message(struct capi_ctr *ctrl, struct sk_buff *skb);
-extern const struct file_operations b1dmactl_proc_fops;
+int b1dma_proc_show(struct seq_file *m, void *v);
#endif /* _AVMCARD_H_ */
diff --git a/drivers/isdn/hardware/avm/b1.c b/drivers/isdn/hardware/avm/b1.c
index b1833d0..5ee5489 100644
--- a/drivers/isdn/hardware/avm/b1.c
+++ b/drivers/isdn/hardware/avm/b1.c
@@ -637,7 +637,7 @@ irqreturn_t b1_interrupt(int interrupt, void *devptr)
}
/* ------------------------------------------------------------- */
-static int b1ctl_proc_show(struct seq_file *m, void *v)
+int b1_proc_show(struct seq_file *m, void *v)
{
struct capi_ctr *ctrl = m->private;
avmctrl_info *cinfo = (avmctrl_info *)(ctrl->driverdata);
@@ -699,20 +699,7 @@ static int b1ctl_proc_show(struct seq_file *m, void *v)
return 0;
}
-
-static int b1ctl_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, b1ctl_proc_show, PDE_DATA(inode));
-}
-
-const struct file_operations b1ctl_proc_fops = {
- .owner = THIS_MODULE,
- .open = b1ctl_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-EXPORT_SYMBOL(b1ctl_proc_fops);
+EXPORT_SYMBOL(b1_proc_show);
/* ------------------------------------------------------------- */
diff --git a/drivers/isdn/hardware/avm/b1dma.c b/drivers/isdn/hardware/avm/b1dma.c
index 9538a9e..6a3dc99 100644
--- a/drivers/isdn/hardware/avm/b1dma.c
+++ b/drivers/isdn/hardware/avm/b1dma.c
@@ -858,7 +858,7 @@ u16 b1dma_send_message(struct capi_ctr *ctrl, struct sk_buff *skb)
/* ------------------------------------------------------------- */
-static int b1dmactl_proc_show(struct seq_file *m, void *v)
+int b1dma_proc_show(struct seq_file *m, void *v)
{
struct capi_ctr *ctrl = m->private;
avmctrl_info *cinfo = (avmctrl_info *)(ctrl->driverdata);
@@ -941,20 +941,7 @@ static int b1dmactl_proc_show(struct seq_file *m, void *v)
return 0;
}
-
-static int b1dmactl_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, b1dmactl_proc_show, PDE_DATA(inode));
-}
-
-const struct file_operations b1dmactl_proc_fops = {
- .owner = THIS_MODULE,
- .open = b1dmactl_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-EXPORT_SYMBOL(b1dmactl_proc_fops);
+EXPORT_SYMBOL(b1dma_proc_show);
/* ------------------------------------------------------------- */
diff --git a/drivers/isdn/hardware/avm/b1isa.c b/drivers/isdn/hardware/avm/b1isa.c
index 54e871a..cdfea72 100644
--- a/drivers/isdn/hardware/avm/b1isa.c
+++ b/drivers/isdn/hardware/avm/b1isa.c
@@ -121,7 +121,7 @@ static int b1isa_probe(struct pci_dev *pdev)
cinfo->capi_ctrl.load_firmware = b1_load_firmware;
cinfo->capi_ctrl.reset_ctr = b1_reset_ctr;
cinfo->capi_ctrl.procinfo = b1isa_procinfo;
- cinfo->capi_ctrl.proc_fops = &b1ctl_proc_fops;
+ cinfo->capi_ctrl.proc_show = b1_proc_show;
strcpy(cinfo->capi_ctrl.name, card->name);
retval = attach_capi_ctr(&cinfo->capi_ctrl);
diff --git a/drivers/isdn/hardware/avm/b1pci.c b/drivers/isdn/hardware/avm/b1pci.c
index ac4863c..b76b57a 100644
--- a/drivers/isdn/hardware/avm/b1pci.c
+++ b/drivers/isdn/hardware/avm/b1pci.c
@@ -112,7 +112,7 @@ static int b1pci_probe(struct capicardparams *p, struct pci_dev *pdev)
cinfo->capi_ctrl.load_firmware = b1_load_firmware;
cinfo->capi_ctrl.reset_ctr = b1_reset_ctr;
cinfo->capi_ctrl.procinfo = b1pci_procinfo;
- cinfo->capi_ctrl.proc_fops = &b1ctl_proc_fops;
+ cinfo->capi_ctrl.proc_show = b1_proc_show;
strcpy(cinfo->capi_ctrl.name, card->name);
cinfo->capi_ctrl.owner = THIS_MODULE;
@@ -251,7 +251,7 @@ static int b1pciv4_probe(struct capicardparams *p, struct pci_dev *pdev)
cinfo->capi_ctrl.load_firmware = b1dma_load_firmware;
cinfo->capi_ctrl.reset_ctr = b1dma_reset_ctr;
cinfo->capi_ctrl.procinfo = b1pciv4_procinfo;
- cinfo->capi_ctrl.proc_fops = &b1dmactl_proc_fops;
+ cinfo->capi_ctrl.proc_show = b1dma_proc_show;
strcpy(cinfo->capi_ctrl.name, card->name);
retval = attach_capi_ctr(&cinfo->capi_ctrl);
diff --git a/drivers/isdn/hardware/avm/b1pcmcia.c b/drivers/isdn/hardware/avm/b1pcmcia.c
index 6b0d19d..3aca16e 100644
--- a/drivers/isdn/hardware/avm/b1pcmcia.c
+++ b/drivers/isdn/hardware/avm/b1pcmcia.c
@@ -108,7 +108,7 @@ static int b1pcmcia_add_card(unsigned int port, unsigned irq,
cinfo->capi_ctrl.load_firmware = b1_load_firmware;
cinfo->capi_ctrl.reset_ctr = b1_reset_ctr;
cinfo->capi_ctrl.procinfo = b1pcmcia_procinfo;
- cinfo->capi_ctrl.proc_fops = &b1ctl_proc_fops;
+ cinfo->capi_ctrl.proc_show = b1_proc_show;
strcpy(cinfo->capi_ctrl.name, card->name);
retval = attach_capi_ctr(&cinfo->capi_ctrl);
diff --git a/drivers/isdn/hardware/avm/c4.c b/drivers/isdn/hardware/avm/c4.c
index 034caba..ac72cd2 100644
--- a/drivers/isdn/hardware/avm/c4.c
+++ b/drivers/isdn/hardware/avm/c4.c
@@ -1127,19 +1127,6 @@ static int c4_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int c4_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, c4_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations c4_proc_fops = {
- .owner = THIS_MODULE,
- .open = c4_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/* ------------------------------------------------------------- */
static int c4_add_card(struct capicardparams *p, struct pci_dev *dev,
@@ -1211,7 +1198,7 @@ static int c4_add_card(struct capicardparams *p, struct pci_dev *dev,
cinfo->capi_ctrl.load_firmware = c4_load_firmware;
cinfo->capi_ctrl.reset_ctr = c4_reset_ctr;
cinfo->capi_ctrl.procinfo = c4_procinfo;
- cinfo->capi_ctrl.proc_fops = &c4_proc_fops;
+ cinfo->capi_ctrl.proc_show = c4_proc_show;
strcpy(cinfo->capi_ctrl.name, card->name);
retval = attach_capi_ctr(&cinfo->capi_ctrl);
diff --git a/drivers/isdn/hardware/avm/t1isa.c b/drivers/isdn/hardware/avm/t1isa.c
index 9f80d20..2153619 100644
--- a/drivers/isdn/hardware/avm/t1isa.c
+++ b/drivers/isdn/hardware/avm/t1isa.c
@@ -430,7 +430,7 @@ static int t1isa_probe(struct pci_dev *pdev, int cardnr)
cinfo->capi_ctrl.load_firmware = t1isa_load_firmware;
cinfo->capi_ctrl.reset_ctr = t1isa_reset_ctr;
cinfo->capi_ctrl.procinfo = t1isa_procinfo;
- cinfo->capi_ctrl.proc_fops = &b1ctl_proc_fops;
+ cinfo->capi_ctrl.proc_show = b1_proc_show;
strcpy(cinfo->capi_ctrl.name, card->name);
retval = attach_capi_ctr(&cinfo->capi_ctrl);
diff --git a/drivers/isdn/hardware/avm/t1pci.c b/drivers/isdn/hardware/avm/t1pci.c
index 2180b16..f5ed1d5 100644
--- a/drivers/isdn/hardware/avm/t1pci.c
+++ b/drivers/isdn/hardware/avm/t1pci.c
@@ -119,7 +119,7 @@ static int t1pci_add_card(struct capicardparams *p, struct pci_dev *pdev)
cinfo->capi_ctrl.load_firmware = b1dma_load_firmware;
cinfo->capi_ctrl.reset_ctr = b1dma_reset_ctr;
cinfo->capi_ctrl.procinfo = t1pci_procinfo;
- cinfo->capi_ctrl.proc_fops = &b1dmactl_proc_fops;
+ cinfo->capi_ctrl.proc_show = b1dma_proc_show;
strcpy(cinfo->capi_ctrl.name, card->name);
retval = attach_capi_ctr(&cinfo->capi_ctrl);
diff --git a/drivers/isdn/hardware/eicon/capimain.c b/drivers/isdn/hardware/eicon/capimain.c
index be36d82..f9244dc 100644
--- a/drivers/isdn/hardware/eicon/capimain.c
+++ b/drivers/isdn/hardware/eicon/capimain.c
@@ -90,19 +90,6 @@ static int diva_ctl_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int diva_ctl_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, diva_ctl_proc_show, NULL);
-}
-
-static const struct file_operations diva_ctl_proc_fops = {
- .owner = THIS_MODULE,
- .open = diva_ctl_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/*
* set additional os settings in capi_ctr struct
*/
@@ -111,7 +98,7 @@ void diva_os_set_controller_struct(struct capi_ctr *ctrl)
ctrl->driver_name = DRIVERLNAME;
ctrl->load_firmware = NULL;
ctrl->reset_ctr = NULL;
- ctrl->proc_fops = &diva_ctl_proc_fops;
+ ctrl->proc_show = diva_ctl_proc_show;
ctrl->owner = THIS_MODULE;
}
diff --git a/drivers/isdn/hardware/eicon/diva.c b/drivers/isdn/hardware/eicon/diva.c
index 944a7f3..1b25d8b 100644
--- a/drivers/isdn/hardware/eicon/diva.c
+++ b/drivers/isdn/hardware/eicon/diva.c
@@ -388,10 +388,10 @@ void divasa_xdi_driver_unload(void)
** Receive and process command from user mode utility
*/
void *diva_xdi_open_adapter(void *os_handle, const void __user *src,
- int length,
+ int length, void *mptr,
divas_xdi_copy_from_user_fn_t cp_fn)
{
- diva_xdi_um_cfg_cmd_t msg;
+ diva_xdi_um_cfg_cmd_t *msg = (diva_xdi_um_cfg_cmd_t *)mptr;
diva_os_xdi_adapter_t *a = NULL;
diva_os_spin_lock_magic_t old_irql;
struct list_head *tmp;
@@ -401,21 +401,21 @@ void *diva_xdi_open_adapter(void *os_handle, const void __user *src,
length, sizeof(diva_xdi_um_cfg_cmd_t)))
return NULL;
}
- if ((*cp_fn) (os_handle, &msg, src, sizeof(msg)) <= 0) {
+ if ((*cp_fn) (os_handle, msg, src, sizeof(*msg)) <= 0) {
DBG_ERR(("A: A(?) open, write error"))
return NULL;
}
diva_os_enter_spin_lock(&adapter_lock, &old_irql, "open_adapter");
list_for_each(tmp, &adapter_queue) {
a = list_entry(tmp, diva_os_xdi_adapter_t, link);
- if (a->controller == (int)msg.adapter)
+ if (a->controller == (int)msg->adapter)
break;
a = NULL;
}
diva_os_leave_spin_lock(&adapter_lock, &old_irql, "open_adapter");
if (!a) {
- DBG_ERR(("A: A(%d) open, adapter not found", msg.adapter))
+ DBG_ERR(("A: A(%d) open, adapter not found", msg->adapter))
}
return (a);
@@ -437,8 +437,10 @@ void diva_xdi_close_adapter(void *adapter, void *os_handle)
int
diva_xdi_write(void *adapter, void *os_handle, const void __user *src,
- int length, divas_xdi_copy_from_user_fn_t cp_fn)
+ int length, void *mptr,
+ divas_xdi_copy_from_user_fn_t cp_fn)
{
+ diva_xdi_um_cfg_cmd_t *msg = (diva_xdi_um_cfg_cmd_t *)mptr;
diva_os_xdi_adapter_t *a = (diva_os_xdi_adapter_t *) adapter;
void *data;
@@ -459,7 +461,13 @@ diva_xdi_write(void *adapter, void *os_handle, const void __user *src,
return (-2);
}
- length = (*cp_fn) (os_handle, data, src, length);
+ if (msg) {
+ *(diva_xdi_um_cfg_cmd_t *)data = *msg;
+ length = (*cp_fn) (os_handle, (char *)data + sizeof(*msg),
+ src + sizeof(*msg), length - sizeof(*msg));
+ } else {
+ length = (*cp_fn) (os_handle, data, src, length);
+ }
if (length > 0) {
if ((*(a->interface.cmd_proc))
(a, (diva_xdi_um_cfg_cmd_t *) data, length)) {
diff --git a/drivers/isdn/hardware/eicon/diva.h b/drivers/isdn/hardware/eicon/diva.h
index b067032..1ad7665 100644
--- a/drivers/isdn/hardware/eicon/diva.h
+++ b/drivers/isdn/hardware/eicon/diva.h
@@ -20,10 +20,11 @@ int diva_xdi_read(void *adapter, void *os_handle, void __user *dst,
int max_length, divas_xdi_copy_to_user_fn_t cp_fn);
int diva_xdi_write(void *adapter, void *os_handle, const void __user *src,
- int length, divas_xdi_copy_from_user_fn_t cp_fn);
+ int length, void *msg,
+ divas_xdi_copy_from_user_fn_t cp_fn);
void *diva_xdi_open_adapter(void *os_handle, const void __user *src,
- int length,
+ int length, void *msg,
divas_xdi_copy_from_user_fn_t cp_fn);
void diva_xdi_close_adapter(void *adapter, void *os_handle);
diff --git a/drivers/isdn/hardware/eicon/diva_didd.c b/drivers/isdn/hardware/eicon/diva_didd.c
index fab6ccf..60e7925 100644
--- a/drivers/isdn/hardware/eicon/diva_didd.c
+++ b/drivers/isdn/hardware/eicon/diva_didd.c
@@ -78,26 +78,13 @@ static int divadidd_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int divadidd_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, divadidd_proc_show, NULL);
-}
-
-static const struct file_operations divadidd_proc_fops = {
- .owner = THIS_MODULE,
- .open = divadidd_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __init create_proc(void)
{
proc_net_eicon = proc_mkdir("eicon", init_net.proc_net);
if (proc_net_eicon) {
- proc_didd = proc_create(DRIVERLNAME, S_IRUGO, proc_net_eicon,
- &divadidd_proc_fops);
+ proc_didd = proc_create_single(DRIVERLNAME, S_IRUGO,
+ proc_net_eicon, divadidd_proc_show);
return (1);
}
return (0);
diff --git a/drivers/isdn/hardware/eicon/divasi.c b/drivers/isdn/hardware/eicon/divasi.c
index 525518c..e7081e0 100644
--- a/drivers/isdn/hardware/eicon/divasi.c
+++ b/drivers/isdn/hardware/eicon/divasi.c
@@ -101,23 +101,10 @@ static int um_idi_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int um_idi_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, um_idi_proc_show, NULL);
-}
-
-static const struct file_operations um_idi_proc_fops = {
- .owner = THIS_MODULE,
- .open = um_idi_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __init create_um_idi_proc(void)
{
- um_idi_proc_entry = proc_create(DRIVERLNAME, S_IRUGO, proc_net_eicon,
- &um_idi_proc_fops);
+ um_idi_proc_entry = proc_create_single(DRIVERLNAME, S_IRUGO,
+ proc_net_eicon, um_idi_proc_show);
if (!um_idi_proc_entry)
return (0);
return (1);
diff --git a/drivers/isdn/hardware/eicon/divasmain.c b/drivers/isdn/hardware/eicon/divasmain.c
index b9980e8..b6a3950 100644
--- a/drivers/isdn/hardware/eicon/divasmain.c
+++ b/drivers/isdn/hardware/eicon/divasmain.c
@@ -591,19 +591,22 @@ static int divas_release(struct inode *inode, struct file *file)
static ssize_t divas_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
+ diva_xdi_um_cfg_cmd_t msg;
int ret = -EINVAL;
if (!file->private_data) {
file->private_data = diva_xdi_open_adapter(file, buf,
- count,
+ count, &msg,
xdi_copy_from_user);
- }
- if (!file->private_data) {
- return (-ENODEV);
+ if (!file->private_data)
+ return (-ENODEV);
+ ret = diva_xdi_write(file->private_data, file,
+ buf, count, &msg, xdi_copy_from_user);
+ } else {
+ ret = diva_xdi_write(file->private_data, file,
+ buf, count, NULL, xdi_copy_from_user);
}
- ret = diva_xdi_write(file->private_data, file,
- buf, count, xdi_copy_from_user);
switch (ret) {
case -1: /* Message should be removed from rx mailbox first */
ret = -EBUSY;
@@ -622,11 +625,12 @@ static ssize_t divas_write(struct file *file, const char __user *buf,
static ssize_t divas_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
+ diva_xdi_um_cfg_cmd_t msg;
int ret = -EINVAL;
if (!file->private_data) {
file->private_data = diva_xdi_open_adapter(file, buf,
- count,
+ count, &msg,
xdi_copy_from_user);
}
if (!file->private_data) {
diff --git a/drivers/isdn/hysdn/hycapi.c b/drivers/isdn/hysdn/hycapi.c
index eac0f51..a2c15cd 100644
--- a/drivers/isdn/hysdn/hycapi.c
+++ b/drivers/isdn/hysdn/hycapi.c
@@ -467,19 +467,6 @@ static int hycapi_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int hycapi_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, hycapi_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations hycapi_proc_fops = {
- .owner = THIS_MODULE,
- .open = hycapi_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/**************************************************************
hycapi_load_firmware
@@ -774,7 +761,7 @@ hycapi_capi_create(hysdn_card *card)
ctrl->load_firmware = hycapi_load_firmware;
ctrl->reset_ctr = hycapi_reset_ctr;
ctrl->procinfo = hycapi_procinfo;
- ctrl->proc_fops = &hycapi_proc_fops;
+ ctrl->proc_show = hycapi_proc_show;
strcpy(ctrl->name, cinfo->cardname);
ctrl->owner = THIS_MODULE;
diff --git a/drivers/isdn/mISDN/dsp_hwec.c b/drivers/isdn/mISDN/dsp_hwec.c
index a6e8707..5336bbd 100644
--- a/drivers/isdn/mISDN/dsp_hwec.c
+++ b/drivers/isdn/mISDN/dsp_hwec.c
@@ -68,12 +68,12 @@ void dsp_hwec_enable(struct dsp *dsp, const char *arg)
goto _do;
{
- char _dup[len + 1];
char *dup, *tok, *name, *val;
int tmp;
- strcpy(_dup, arg);
- dup = _dup;
+ dup = kstrdup(arg, GFP_ATOMIC);
+ if (!dup)
+ return;
while ((tok = strsep(&dup, ","))) {
if (!strlen(tok))
@@ -89,6 +89,8 @@ void dsp_hwec_enable(struct dsp *dsp, const char *arg)
deftaps = tmp;
}
}
+
+ kfree(dup);
}
_do:
diff --git a/drivers/isdn/mISDN/l1oip_core.c b/drivers/isdn/mISDN/l1oip_core.c
index 21d50e4..b05022f 100644
--- a/drivers/isdn/mISDN/l1oip_core.c
+++ b/drivers/isdn/mISDN/l1oip_core.c
@@ -279,7 +279,7 @@ l1oip_socket_send(struct l1oip *hc, u8 localcodec, u8 channel, u32 chanmask,
u16 timebase, u8 *buf, int len)
{
u8 *p;
- u8 frame[len + 32];
+ u8 frame[MAX_DFRAME_LEN_L1 + 32];
struct socket *socket = NULL;
if (debug & DEBUG_L1OIP_MSG)
@@ -902,7 +902,11 @@ handle_dmsg(struct mISDNchannel *ch, struct sk_buff *skb)
p = skb->data;
l = skb->len;
while (l) {
- ll = (l < L1OIP_MAX_PERFRAME) ? l : L1OIP_MAX_PERFRAME;
+ /*
+ * This is technically bounded by L1OIP_MAX_PERFRAME but
+ * MAX_DFRAME_LEN_L1 < L1OIP_MAX_PERFRAME
+ */
+ ll = (l < MAX_DFRAME_LEN_L1) ? l : MAX_DFRAME_LEN_L1;
l1oip_socket_send(hc, 0, dch->slot, 0,
hc->chan[dch->slot].tx_counter++, p, ll);
p += ll;
@@ -1140,7 +1144,11 @@ handle_bmsg(struct mISDNchannel *ch, struct sk_buff *skb)
p = skb->data;
l = skb->len;
while (l) {
- ll = (l < L1OIP_MAX_PERFRAME) ? l : L1OIP_MAX_PERFRAME;
+ /*
+ * This is technically bounded by L1OIP_MAX_PERFRAME but
+ * MAX_DFRAME_LEN_L1 < L1OIP_MAX_PERFRAME
+ */
+ ll = (l < MAX_DFRAME_LEN_L1) ? l : MAX_DFRAME_LEN_L1;
l1oip_socket_send(hc, hc->codec, bch->slot, 0,
hc->chan[bch->slot].tx_counter, p, ll);
hc->chan[bch->slot].tx_counter += ll;
diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index 1f8f489..98f90aa 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -588,7 +588,7 @@ static const struct proto_ops data_sock_ops = {
.getname = data_sock_getname,
.sendmsg = mISDN_sock_sendmsg,
.recvmsg = mISDN_sock_recvmsg,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = data_sock_setsockopt,
@@ -745,7 +745,6 @@ static const struct proto_ops base_sock_ops = {
.getname = sock_no_getname,
.sendmsg = sock_no_sendmsg,
.recvmsg = sock_no_recvmsg,
- .poll = sock_no_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index 63171cd..60aa7bc 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -431,7 +431,7 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
return 0;
err_sysfs:
if (tt->exit)
- tt->exit(targetdata);
+ tt->exit(targetdata, true);
err_init:
blk_cleanup_queue(tqueue);
tdisk->queue = NULL;
@@ -446,7 +446,7 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
return ret;
}
-static void __nvm_remove_target(struct nvm_target *t)
+static void __nvm_remove_target(struct nvm_target *t, bool graceful)
{
struct nvm_tgt_type *tt = t->type;
struct gendisk *tdisk = t->disk;
@@ -459,7 +459,7 @@ static void __nvm_remove_target(struct nvm_target *t)
tt->sysfs_exit(tdisk);
if (tt->exit)
- tt->exit(tdisk->private_data);
+ tt->exit(tdisk->private_data, graceful);
nvm_remove_tgt_dev(t->dev, 1);
put_disk(tdisk);
@@ -489,7 +489,7 @@ static int nvm_remove_tgt(struct nvm_dev *dev, struct nvm_ioctl_remove *remove)
mutex_unlock(&dev->mlock);
return 1;
}
- __nvm_remove_target(t);
+ __nvm_remove_target(t, true);
mutex_unlock(&dev->mlock);
return 0;
@@ -963,7 +963,7 @@ void nvm_unregister(struct nvm_dev *dev)
list_for_each_entry_safe(t, tmp, &dev->targets, list) {
if (t->dev->parent != dev)
continue;
- __nvm_remove_target(t);
+ __nvm_remove_target(t, false);
}
mutex_unlock(&dev->mlock);
diff --git a/drivers/lightnvm/pblk-cache.c b/drivers/lightnvm/pblk-cache.c
index 29a2311..b1c6d7e 100644
--- a/drivers/lightnvm/pblk-cache.c
+++ b/drivers/lightnvm/pblk-cache.c
@@ -44,13 +44,15 @@ int pblk_write_to_cache(struct pblk *pblk, struct bio *bio, unsigned long flags)
goto out;
}
- if (unlikely(!bio_has_data(bio)))
- goto out;
-
pblk_ppa_set_empty(&w_ctx.ppa);
w_ctx.flags = flags;
- if (bio->bi_opf & REQ_PREFLUSH)
+ if (bio->bi_opf & REQ_PREFLUSH) {
w_ctx.flags |= PBLK_FLUSH_ENTRY;
+ pblk_write_kick(pblk);
+ }
+
+ if (unlikely(!bio_has_data(bio)))
+ goto out;
for (i = 0; i < nr_entries; i++) {
void *data = bio_data(bio);
diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index 94d5d97..ed9cc97 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -40,7 +40,7 @@ static void pblk_line_mark_bb(struct work_struct *work)
}
kfree(ppa);
- mempool_free(line_ws, pblk->gen_ws_pool);
+ mempool_free(line_ws, &pblk->gen_ws_pool);
}
static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
@@ -102,7 +102,7 @@ static void pblk_end_io_erase(struct nvm_rq *rqd)
struct pblk *pblk = rqd->private;
__pblk_end_io_erase(pblk, rqd);
- mempool_free(rqd, pblk->e_rq_pool);
+ mempool_free(rqd, &pblk->e_rq_pool);
}
/*
@@ -237,15 +237,15 @@ struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int type)
switch (type) {
case PBLK_WRITE:
case PBLK_WRITE_INT:
- pool = pblk->w_rq_pool;
+ pool = &pblk->w_rq_pool;
rq_size = pblk_w_rq_size;
break;
case PBLK_READ:
- pool = pblk->r_rq_pool;
+ pool = &pblk->r_rq_pool;
rq_size = pblk_g_rq_size;
break;
default:
- pool = pblk->e_rq_pool;
+ pool = &pblk->e_rq_pool;
rq_size = pblk_g_rq_size;
}
@@ -265,20 +265,22 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type)
case PBLK_WRITE:
kfree(((struct pblk_c_ctx *)nvm_rq_to_pdu(rqd))->lun_bitmap);
case PBLK_WRITE_INT:
- pool = pblk->w_rq_pool;
+ pool = &pblk->w_rq_pool;
break;
case PBLK_READ:
- pool = pblk->r_rq_pool;
+ pool = &pblk->r_rq_pool;
break;
case PBLK_ERASE:
- pool = pblk->e_rq_pool;
+ pool = &pblk->e_rq_pool;
break;
default:
pr_err("pblk: trying to free unknown rqd type\n");
return;
}
- nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
+ if (rqd->meta_list)
+ nvm_dev_dma_free(dev->parent, rqd->meta_list,
+ rqd->dma_meta_list);
mempool_free(rqd, pool);
}
@@ -292,7 +294,7 @@ void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off,
for (i = off; i < nr_pages + off; i++) {
bv = bio->bi_io_vec[i];
- mempool_free(bv.bv_page, pblk->page_bio_pool);
+ mempool_free(bv.bv_page, &pblk->page_bio_pool);
}
}
@@ -304,23 +306,23 @@ int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
int i, ret;
for (i = 0; i < nr_pages; i++) {
- page = mempool_alloc(pblk->page_bio_pool, flags);
+ page = mempool_alloc(&pblk->page_bio_pool, flags);
ret = bio_add_pc_page(q, bio, page, PBLK_EXPOSED_PAGE_SIZE, 0);
if (ret != PBLK_EXPOSED_PAGE_SIZE) {
pr_err("pblk: could not add page to bio\n");
- mempool_free(page, pblk->page_bio_pool);
+ mempool_free(page, &pblk->page_bio_pool);
goto err;
}
}
return 0;
err:
- pblk_bio_free_pages(pblk, bio, 0, i - 1);
+ pblk_bio_free_pages(pblk, bio, (bio->bi_vcnt - i), i);
return -1;
}
-static void pblk_write_kick(struct pblk *pblk)
+void pblk_write_kick(struct pblk *pblk)
{
wake_up_process(pblk->writer_ts);
mod_timer(&pblk->wtimer, jiffies + msecs_to_jiffies(1000));
@@ -342,13 +344,6 @@ void pblk_write_should_kick(struct pblk *pblk)
pblk_write_kick(pblk);
}
-void pblk_end_io_sync(struct nvm_rq *rqd)
-{
- struct completion *waiting = rqd->private;
-
- complete(waiting);
-}
-
static void pblk_wait_for_meta(struct pblk *pblk)
{
do {
@@ -380,7 +375,13 @@ struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
lockdep_assert_held(&line->lock);
- if (!vsc) {
+ if (line->w_err_gc->has_write_err) {
+ if (line->gc_group != PBLK_LINEGC_WERR) {
+ line->gc_group = PBLK_LINEGC_WERR;
+ move_list = &l_mg->gc_werr_list;
+ pblk_rl_werr_line_in(&pblk->rl);
+ }
+ } else if (!vsc) {
if (line->gc_group != PBLK_LINEGC_FULL) {
line->gc_group = PBLK_LINEGC_FULL;
move_list = &l_mg->gc_full_list;
@@ -467,16 +468,13 @@ int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd)
{
struct nvm_tgt_dev *dev = pblk->dev;
-#ifdef CONFIG_NVM_DEBUG
- int ret;
-
- ret = pblk_check_io(pblk, rqd);
- if (ret)
- return ret;
-#endif
-
atomic_inc(&pblk->inflight_io);
+#ifdef CONFIG_NVM_DEBUG
+ if (pblk_check_io(pblk, rqd))
+ return NVM_IO_ERR;
+#endif
+
return nvm_submit_io(dev, rqd);
}
@@ -484,16 +482,13 @@ int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd)
{
struct nvm_tgt_dev *dev = pblk->dev;
-#ifdef CONFIG_NVM_DEBUG
- int ret;
-
- ret = pblk_check_io(pblk, rqd);
- if (ret)
- return ret;
-#endif
-
atomic_inc(&pblk->inflight_io);
+#ifdef CONFIG_NVM_DEBUG
+ if (pblk_check_io(pblk, rqd))
+ return NVM_IO_ERR;
+#endif
+
return nvm_submit_io_sync(dev, rqd);
}
@@ -856,9 +851,10 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
atomic_dec(&pblk->inflight_io);
if (rqd.error) {
- if (dir == PBLK_WRITE)
+ if (dir == PBLK_WRITE) {
pblk_log_write_err(pblk, &rqd);
- else if (dir == PBLK_READ)
+ ret = 1;
+ } else if (dir == PBLK_READ)
pblk_log_read_err(pblk, &rqd);
}
@@ -1071,6 +1067,25 @@ static int pblk_line_init_metadata(struct pblk *pblk, struct pblk_line *line,
return 1;
}
+static int pblk_line_alloc_bitmaps(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+
+ line->map_bitmap = kzalloc(lm->sec_bitmap_len, GFP_KERNEL);
+ if (!line->map_bitmap)
+ return -ENOMEM;
+
+ /* will be initialized using bb info from map_bitmap */
+ line->invalid_bitmap = kmalloc(lm->sec_bitmap_len, GFP_KERNEL);
+ if (!line->invalid_bitmap) {
+ kfree(line->map_bitmap);
+ line->map_bitmap = NULL;
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
/* For now lines are always assumed full lines. Thus, smeta former and current
* lun bitmaps are omitted.
*/
@@ -1108,7 +1123,7 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
if (init && pblk_line_submit_smeta_io(pblk, line, off, PBLK_WRITE)) {
pr_debug("pblk: line smeta I/O failed. Retry\n");
- return 1;
+ return 0;
}
bitmap_copy(line->invalid_bitmap, line->map_bitmap, lm->sec_per_line);
@@ -1174,19 +1189,9 @@ static int pblk_prepare_new_line(struct pblk *pblk, struct pblk_line *line)
static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line)
{
struct pblk_line_meta *lm = &pblk->lm;
+ int blk_in_line = atomic_read(&line->blk_in_line);
int blk_to_erase;
- line->map_bitmap = kzalloc(lm->sec_bitmap_len, GFP_ATOMIC);
- if (!line->map_bitmap)
- return -ENOMEM;
-
- /* will be initialized using bb info from map_bitmap */
- line->invalid_bitmap = kmalloc(lm->sec_bitmap_len, GFP_ATOMIC);
- if (!line->invalid_bitmap) {
- kfree(line->map_bitmap);
- return -ENOMEM;
- }
-
/* Bad blocks do not need to be erased */
bitmap_copy(line->erase_bitmap, line->blk_bitmap, lm->blk_per_line);
@@ -1199,16 +1204,19 @@ static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line)
blk_to_erase = pblk_prepare_new_line(pblk, line);
line->state = PBLK_LINESTATE_FREE;
} else {
- blk_to_erase = atomic_read(&line->blk_in_line);
+ blk_to_erase = blk_in_line;
+ }
+
+ if (blk_in_line < lm->min_blk_line) {
+ spin_unlock(&line->lock);
+ return -EAGAIN;
}
if (line->state != PBLK_LINESTATE_FREE) {
- kfree(line->map_bitmap);
- kfree(line->invalid_bitmap);
- spin_unlock(&line->lock);
WARN(1, "pblk: corrupted line %d, state %d\n",
line->id, line->state);
- return -EAGAIN;
+ spin_unlock(&line->lock);
+ return -EINTR;
}
line->state = PBLK_LINESTATE_OPEN;
@@ -1241,13 +1249,16 @@ int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line)
}
spin_unlock(&l_mg->free_lock);
- pblk_rl_free_lines_dec(&pblk->rl, line, true);
+ ret = pblk_line_alloc_bitmaps(pblk, line);
+ if (ret)
+ return ret;
if (!pblk_line_init_bb(pblk, line, 0)) {
list_add(&line->list, &l_mg->free_list);
return -EINTR;
}
+ pblk_rl_free_lines_dec(&pblk->rl, line, true);
return 0;
}
@@ -1259,6 +1270,24 @@ void pblk_line_recov_close(struct pblk *pblk, struct pblk_line *line)
line->emeta = NULL;
}
+static void pblk_line_reinit(struct pblk_line *line)
+{
+ *line->vsc = cpu_to_le32(EMPTY_ENTRY);
+
+ line->map_bitmap = NULL;
+ line->invalid_bitmap = NULL;
+ line->smeta = NULL;
+ line->emeta = NULL;
+}
+
+void pblk_line_free(struct pblk_line *line)
+{
+ kfree(line->map_bitmap);
+ kfree(line->invalid_bitmap);
+
+ pblk_line_reinit(line);
+}
+
struct pblk_line *pblk_line_get(struct pblk *pblk)
{
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
@@ -1292,10 +1321,14 @@ struct pblk_line *pblk_line_get(struct pblk *pblk)
ret = pblk_line_prepare(pblk, line);
if (ret) {
- if (ret == -EAGAIN) {
+ switch (ret) {
+ case -EAGAIN:
+ list_add(&line->list, &l_mg->bad_list);
+ goto retry;
+ case -EINTR:
list_add(&line->list, &l_mg->corrupt_list);
goto retry;
- } else {
+ default:
pr_err("pblk: failed to prepare line %d\n", line->id);
list_add(&line->list, &l_mg->free_list);
l_mg->nr_free_lines++;
@@ -1321,11 +1354,14 @@ static struct pblk_line *pblk_line_retry(struct pblk *pblk,
return NULL;
}
+ retry_line->map_bitmap = line->map_bitmap;
+ retry_line->invalid_bitmap = line->invalid_bitmap;
retry_line->smeta = line->smeta;
retry_line->emeta = line->emeta;
retry_line->meta_line = line->meta_line;
- pblk_line_free(pblk, line);
+ pblk_line_reinit(line);
+
l_mg->data_line = retry_line;
spin_unlock(&l_mg->free_lock);
@@ -1378,6 +1414,9 @@ struct pblk_line *pblk_line_get_first_data(struct pblk *pblk)
}
spin_unlock(&l_mg->free_lock);
+ if (pblk_line_alloc_bitmaps(pblk, line))
+ return NULL;
+
if (pblk_line_erase(pblk, line)) {
line = pblk_line_retry(pblk, line);
if (!line)
@@ -1449,7 +1488,7 @@ static void pblk_line_close_meta_sync(struct pblk *pblk)
flush_workqueue(pblk->close_wq);
}
-void pblk_pipeline_stop(struct pblk *pblk)
+void __pblk_pipeline_flush(struct pblk *pblk)
{
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
int ret;
@@ -1474,6 +1513,11 @@ void pblk_pipeline_stop(struct pblk *pblk)
flush_workqueue(pblk->bb_wq);
pblk_line_close_meta_sync(pblk);
+}
+
+void __pblk_pipeline_stop(struct pblk *pblk)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
spin_lock(&l_mg->free_lock);
pblk->state = PBLK_STATE_STOPPED;
@@ -1482,6 +1526,12 @@ void pblk_pipeline_stop(struct pblk *pblk)
spin_unlock(&l_mg->free_lock);
}
+void pblk_pipeline_stop(struct pblk *pblk)
+{
+ __pblk_pipeline_flush(pblk);
+ __pblk_pipeline_stop(pblk);
+}
+
struct pblk_line *pblk_line_replace_data(struct pblk *pblk)
{
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
@@ -1511,6 +1561,9 @@ struct pblk_line *pblk_line_replace_data(struct pblk *pblk)
goto retry_erase;
}
+ if (pblk_line_alloc_bitmaps(pblk, new))
+ return NULL;
+
retry_setup:
if (!pblk_line_init_metadata(pblk, new, cur)) {
new = pblk_line_retry(pblk, new);
@@ -1550,19 +1603,6 @@ struct pblk_line *pblk_line_replace_data(struct pblk *pblk)
return new;
}
-void pblk_line_free(struct pblk *pblk, struct pblk_line *line)
-{
- kfree(line->map_bitmap);
- kfree(line->invalid_bitmap);
-
- *line->vsc = cpu_to_le32(EMPTY_ENTRY);
-
- line->map_bitmap = NULL;
- line->invalid_bitmap = NULL;
- line->smeta = NULL;
- line->emeta = NULL;
-}
-
static void __pblk_line_put(struct pblk *pblk, struct pblk_line *line)
{
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
@@ -1572,9 +1612,14 @@ static void __pblk_line_put(struct pblk *pblk, struct pblk_line *line)
WARN_ON(line->state != PBLK_LINESTATE_GC);
line->state = PBLK_LINESTATE_FREE;
line->gc_group = PBLK_LINEGC_NONE;
- pblk_line_free(pblk, line);
- spin_unlock(&line->lock);
+ pblk_line_free(line);
+ if (line->w_err_gc->has_write_err) {
+ pblk_rl_werr_line_out(&pblk->rl);
+ line->w_err_gc->has_write_err = 0;
+ }
+
+ spin_unlock(&line->lock);
atomic_dec(&gc->pipeline_gc);
spin_lock(&l_mg->free_lock);
@@ -1593,7 +1638,7 @@ static void pblk_line_put_ws(struct work_struct *work)
struct pblk_line *line = line_put_ws->line;
__pblk_line_put(pblk, line);
- mempool_free(line_put_ws, pblk->gen_ws_pool);
+ mempool_free(line_put_ws, &pblk->gen_ws_pool);
}
void pblk_line_put(struct kref *ref)
@@ -1610,7 +1655,7 @@ void pblk_line_put_wq(struct kref *ref)
struct pblk *pblk = line->pblk;
struct pblk_line_ws *line_put_ws;
- line_put_ws = mempool_alloc(pblk->gen_ws_pool, GFP_ATOMIC);
+ line_put_ws = mempool_alloc(&pblk->gen_ws_pool, GFP_ATOMIC);
if (!line_put_ws)
return;
@@ -1737,11 +1782,34 @@ void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line)
spin_lock(&l_mg->close_lock);
spin_lock(&line->lock);
+
+ /* Update the in-memory start address for emeta, in case it has
+ * shifted due to write errors
+ */
+ if (line->emeta_ssec != line->cur_sec)
+ line->emeta_ssec = line->cur_sec;
+
list_add_tail(&line->list, &l_mg->emeta_list);
spin_unlock(&line->lock);
spin_unlock(&l_mg->close_lock);
pblk_line_should_sync_meta(pblk);
+
+
+}
+
+static void pblk_save_lba_list(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ unsigned int lba_list_size = lm->emeta_len[2];
+ struct pblk_w_err_gc *w_err_gc = line->w_err_gc;
+ struct pblk_emeta *emeta = line->emeta;
+
+ w_err_gc->lba_list = pblk_malloc(lba_list_size,
+ l_mg->emeta_alloc_type, GFP_KERNEL);
+ memcpy(w_err_gc->lba_list, emeta_to_lbas(pblk, emeta->buf),
+ lba_list_size);
}
void pblk_line_close_ws(struct work_struct *work)
@@ -1750,9 +1818,16 @@ void pblk_line_close_ws(struct work_struct *work)
ws);
struct pblk *pblk = line_ws->pblk;
struct pblk_line *line = line_ws->line;
+ struct pblk_w_err_gc *w_err_gc = line->w_err_gc;
+
+ /* Write errors makes the emeta start address stored in smeta invalid,
+ * so keep a copy of the lba list until we've gc'd the line
+ */
+ if (w_err_gc->has_write_err)
+ pblk_save_lba_list(pblk, line);
pblk_line_close(pblk, line);
- mempool_free(line_ws, pblk->gen_ws_pool);
+ mempool_free(line_ws, &pblk->gen_ws_pool);
}
void pblk_gen_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
@@ -1761,7 +1836,7 @@ void pblk_gen_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
{
struct pblk_line_ws *line_ws;
- line_ws = mempool_alloc(pblk->gen_ws_pool, gfp_mask);
+ line_ws = mempool_alloc(&pblk->gen_ws_pool, gfp_mask);
line_ws->pblk = pblk;
line_ws->line = line;
diff --git a/drivers/lightnvm/pblk-gc.c b/drivers/lightnvm/pblk-gc.c
index 6851a5c..df88f1b 100644
--- a/drivers/lightnvm/pblk-gc.c
+++ b/drivers/lightnvm/pblk-gc.c
@@ -129,6 +129,53 @@ static void pblk_gc_line_ws(struct work_struct *work)
kfree(gc_rq_ws);
}
+static __le64 *get_lba_list_from_emeta(struct pblk *pblk,
+ struct pblk_line *line)
+{
+ struct line_emeta *emeta_buf;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line_meta *lm = &pblk->lm;
+ unsigned int lba_list_size = lm->emeta_len[2];
+ __le64 *lba_list;
+ int ret;
+
+ emeta_buf = pblk_malloc(lm->emeta_len[0],
+ l_mg->emeta_alloc_type, GFP_KERNEL);
+ if (!emeta_buf)
+ return NULL;
+
+ ret = pblk_line_read_emeta(pblk, line, emeta_buf);
+ if (ret) {
+ pr_err("pblk: line %d read emeta failed (%d)\n",
+ line->id, ret);
+ pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
+ return NULL;
+ }
+
+ /* If this read fails, it means that emeta is corrupted.
+ * For now, leave the line untouched.
+ * TODO: Implement a recovery routine that scans and moves
+ * all sectors on the line.
+ */
+
+ ret = pblk_recov_check_emeta(pblk, emeta_buf);
+ if (ret) {
+ pr_err("pblk: inconsistent emeta (line %d)\n",
+ line->id);
+ pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
+ return NULL;
+ }
+
+ lba_list = pblk_malloc(lba_list_size,
+ l_mg->emeta_alloc_type, GFP_KERNEL);
+ if (lba_list)
+ memcpy(lba_list, emeta_to_lbas(pblk, emeta_buf), lba_list_size);
+
+ pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
+
+ return lba_list;
+}
+
static void pblk_gc_line_prepare_ws(struct work_struct *work)
{
struct pblk_line_ws *line_ws = container_of(work, struct pblk_line_ws,
@@ -138,46 +185,26 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
struct pblk_line_mgmt *l_mg = &pblk->l_mg;
struct pblk_line_meta *lm = &pblk->lm;
struct pblk_gc *gc = &pblk->gc;
- struct line_emeta *emeta_buf;
struct pblk_line_ws *gc_rq_ws;
struct pblk_gc_rq *gc_rq;
__le64 *lba_list;
unsigned long *invalid_bitmap;
int sec_left, nr_secs, bit;
- int ret;
invalid_bitmap = kmalloc(lm->sec_bitmap_len, GFP_KERNEL);
if (!invalid_bitmap)
goto fail_free_ws;
- emeta_buf = pblk_malloc(lm->emeta_len[0], l_mg->emeta_alloc_type,
- GFP_KERNEL);
- if (!emeta_buf) {
- pr_err("pblk: cannot use GC emeta\n");
- goto fail_free_bitmap;
- }
-
- ret = pblk_line_read_emeta(pblk, line, emeta_buf);
- if (ret) {
- pr_err("pblk: line %d read emeta failed (%d)\n", line->id, ret);
- goto fail_free_emeta;
- }
-
- /* If this read fails, it means that emeta is corrupted. For now, leave
- * the line untouched. TODO: Implement a recovery routine that scans and
- * moves all sectors on the line.
- */
-
- ret = pblk_recov_check_emeta(pblk, emeta_buf);
- if (ret) {
- pr_err("pblk: inconsistent emeta (line %d)\n", line->id);
- goto fail_free_emeta;
- }
-
- lba_list = emeta_to_lbas(pblk, emeta_buf);
- if (!lba_list) {
- pr_err("pblk: could not interpret emeta (line %d)\n", line->id);
- goto fail_free_emeta;
+ if (line->w_err_gc->has_write_err) {
+ lba_list = line->w_err_gc->lba_list;
+ line->w_err_gc->lba_list = NULL;
+ } else {
+ lba_list = get_lba_list_from_emeta(pblk, line);
+ if (!lba_list) {
+ pr_err("pblk: could not interpret emeta (line %d)\n",
+ line->id);
+ goto fail_free_ws;
+ }
}
spin_lock(&line->lock);
@@ -187,14 +214,14 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
if (sec_left < 0) {
pr_err("pblk: corrupted GC line (%d)\n", line->id);
- goto fail_free_emeta;
+ goto fail_free_lba_list;
}
bit = -1;
next_rq:
gc_rq = kmalloc(sizeof(struct pblk_gc_rq), GFP_KERNEL);
if (!gc_rq)
- goto fail_free_emeta;
+ goto fail_free_lba_list;
nr_secs = 0;
do {
@@ -240,7 +267,7 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
goto next_rq;
out:
- pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
+ pblk_mfree(lba_list, l_mg->emeta_alloc_type);
kfree(line_ws);
kfree(invalid_bitmap);
@@ -251,9 +278,8 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
fail_free_gc_rq:
kfree(gc_rq);
-fail_free_emeta:
- pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
-fail_free_bitmap:
+fail_free_lba_list:
+ pblk_mfree(lba_list, l_mg->emeta_alloc_type);
kfree(invalid_bitmap);
fail_free_ws:
kfree(line_ws);
@@ -349,12 +375,14 @@ static struct pblk_line *pblk_gc_get_victim_line(struct pblk *pblk,
static bool pblk_gc_should_run(struct pblk_gc *gc, struct pblk_rl *rl)
{
unsigned int nr_blocks_free, nr_blocks_need;
+ unsigned int werr_lines = atomic_read(&rl->werr_lines);
nr_blocks_need = pblk_rl_high_thrs(rl);
nr_blocks_free = pblk_rl_nr_free_blks(rl);
/* This is not critical, no need to take lock here */
- return ((gc->gc_active) && (nr_blocks_need > nr_blocks_free));
+ return ((werr_lines > 0) ||
+ ((gc->gc_active) && (nr_blocks_need > nr_blocks_free)));
}
void pblk_gc_free_full_lines(struct pblk *pblk)
@@ -649,7 +677,7 @@ int pblk_gc_init(struct pblk *pblk)
return ret;
}
-void pblk_gc_exit(struct pblk *pblk)
+void pblk_gc_exit(struct pblk *pblk, bool graceful)
{
struct pblk_gc *gc = &pblk->gc;
@@ -663,10 +691,12 @@ void pblk_gc_exit(struct pblk *pblk)
if (gc->gc_reader_ts)
kthread_stop(gc->gc_reader_ts);
- flush_workqueue(gc->gc_reader_wq);
- destroy_workqueue(gc->gc_reader_wq);
+ if (graceful) {
+ flush_workqueue(gc->gc_reader_wq);
+ flush_workqueue(gc->gc_line_reader_wq);
+ }
- flush_workqueue(gc->gc_line_reader_wq);
+ destroy_workqueue(gc->gc_reader_wq);
destroy_workqueue(gc->gc_line_reader_wq);
if (gc->gc_writer_ts)
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index 91a5bc2..ce561f5 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -20,10 +20,15 @@
#include "pblk.h"
+unsigned int write_buffer_size;
+
+module_param(write_buffer_size, uint, 0644);
+MODULE_PARM_DESC(write_buffer_size, "number of entries in a write buffer");
+
static struct kmem_cache *pblk_ws_cache, *pblk_rec_cache, *pblk_g_rq_cache,
*pblk_w_rq_cache;
static DECLARE_RWSEM(pblk_lock);
-struct bio_set *pblk_bio_set;
+struct bio_set pblk_bio_set;
static int pblk_rw_io(struct request_queue *q, struct pblk *pblk,
struct bio *bio)
@@ -127,10 +132,8 @@ static int pblk_l2p_recover(struct pblk *pblk, bool factory_init)
if (!line) {
/* Configure next line for user data */
line = pblk_line_get_first_data(pblk);
- if (!line) {
- pr_err("pblk: line list corrupted\n");
+ if (!line)
return -EFAULT;
- }
}
return 0;
@@ -141,6 +144,7 @@ static int pblk_l2p_init(struct pblk *pblk, bool factory_init)
sector_t i;
struct ppa_addr ppa;
size_t map_size;
+ int ret = 0;
map_size = pblk_trans_map_size(pblk);
pblk->trans_map = vmalloc(map_size);
@@ -152,7 +156,11 @@ static int pblk_l2p_init(struct pblk *pblk, bool factory_init)
for (i = 0; i < pblk->rl.nr_secs; i++)
pblk_trans_map_set(pblk, i, ppa);
- return pblk_l2p_recover(pblk, factory_init);
+ ret = pblk_l2p_recover(pblk, factory_init);
+ if (ret)
+ vfree(pblk->trans_map);
+
+ return ret;
}
static void pblk_rwb_free(struct pblk *pblk)
@@ -169,10 +177,15 @@ static int pblk_rwb_init(struct pblk *pblk)
struct nvm_tgt_dev *dev = pblk->dev;
struct nvm_geo *geo = &dev->geo;
struct pblk_rb_entry *entries;
- unsigned long nr_entries;
+ unsigned long nr_entries, buffer_size;
unsigned int power_size, power_seg_sz;
- nr_entries = pblk_rb_calculate_size(pblk->pgs_in_buffer);
+ if (write_buffer_size && (write_buffer_size > pblk->pgs_in_buffer))
+ buffer_size = write_buffer_size;
+ else
+ buffer_size = pblk->pgs_in_buffer;
+
+ nr_entries = pblk_rb_calculate_size(buffer_size);
entries = vzalloc(nr_entries * sizeof(struct pblk_rb_entry));
if (!entries)
@@ -341,7 +354,7 @@ static int pblk_core_init(struct pblk *pblk)
{
struct nvm_tgt_dev *dev = pblk->dev;
struct nvm_geo *geo = &dev->geo;
- int max_write_ppas;
+ int ret, max_write_ppas;
atomic64_set(&pblk->user_wa, 0);
atomic64_set(&pblk->pad_wa, 0);
@@ -375,33 +388,33 @@ static int pblk_core_init(struct pblk *pblk)
goto fail_free_pad_dist;
/* Internal bios can be at most the sectors signaled by the device. */
- pblk->page_bio_pool = mempool_create_page_pool(NVM_MAX_VLBA, 0);
- if (!pblk->page_bio_pool)
+ ret = mempool_init_page_pool(&pblk->page_bio_pool, NVM_MAX_VLBA, 0);
+ if (ret)
goto free_global_caches;
- pblk->gen_ws_pool = mempool_create_slab_pool(PBLK_GEN_WS_POOL_SIZE,
- pblk_ws_cache);
- if (!pblk->gen_ws_pool)
+ ret = mempool_init_slab_pool(&pblk->gen_ws_pool, PBLK_GEN_WS_POOL_SIZE,
+ pblk_ws_cache);
+ if (ret)
goto free_page_bio_pool;
- pblk->rec_pool = mempool_create_slab_pool(geo->all_luns,
- pblk_rec_cache);
- if (!pblk->rec_pool)
+ ret = mempool_init_slab_pool(&pblk->rec_pool, geo->all_luns,
+ pblk_rec_cache);
+ if (ret)
goto free_gen_ws_pool;
- pblk->r_rq_pool = mempool_create_slab_pool(geo->all_luns,
- pblk_g_rq_cache);
- if (!pblk->r_rq_pool)
+ ret = mempool_init_slab_pool(&pblk->r_rq_pool, geo->all_luns,
+ pblk_g_rq_cache);
+ if (ret)
goto free_rec_pool;
- pblk->e_rq_pool = mempool_create_slab_pool(geo->all_luns,
- pblk_g_rq_cache);
- if (!pblk->e_rq_pool)
+ ret = mempool_init_slab_pool(&pblk->e_rq_pool, geo->all_luns,
+ pblk_g_rq_cache);
+ if (ret)
goto free_r_rq_pool;
- pblk->w_rq_pool = mempool_create_slab_pool(geo->all_luns,
- pblk_w_rq_cache);
- if (!pblk->w_rq_pool)
+ ret = mempool_init_slab_pool(&pblk->w_rq_pool, geo->all_luns,
+ pblk_w_rq_cache);
+ if (ret)
goto free_e_rq_pool;
pblk->close_wq = alloc_workqueue("pblk-close-wq",
@@ -423,6 +436,7 @@ static int pblk_core_init(struct pblk *pblk)
goto free_r_end_wq;
INIT_LIST_HEAD(&pblk->compl_list);
+ INIT_LIST_HEAD(&pblk->resubmit_list);
return 0;
@@ -433,17 +447,17 @@ static int pblk_core_init(struct pblk *pblk)
free_close_wq:
destroy_workqueue(pblk->close_wq);
free_w_rq_pool:
- mempool_destroy(pblk->w_rq_pool);
+ mempool_exit(&pblk->w_rq_pool);
free_e_rq_pool:
- mempool_destroy(pblk->e_rq_pool);
+ mempool_exit(&pblk->e_rq_pool);
free_r_rq_pool:
- mempool_destroy(pblk->r_rq_pool);
+ mempool_exit(&pblk->r_rq_pool);
free_rec_pool:
- mempool_destroy(pblk->rec_pool);
+ mempool_exit(&pblk->rec_pool);
free_gen_ws_pool:
- mempool_destroy(pblk->gen_ws_pool);
+ mempool_exit(&pblk->gen_ws_pool);
free_page_bio_pool:
- mempool_destroy(pblk->page_bio_pool);
+ mempool_exit(&pblk->page_bio_pool);
free_global_caches:
pblk_free_global_caches(pblk);
fail_free_pad_dist:
@@ -462,12 +476,12 @@ static void pblk_core_free(struct pblk *pblk)
if (pblk->bb_wq)
destroy_workqueue(pblk->bb_wq);
- mempool_destroy(pblk->page_bio_pool);
- mempool_destroy(pblk->gen_ws_pool);
- mempool_destroy(pblk->rec_pool);
- mempool_destroy(pblk->r_rq_pool);
- mempool_destroy(pblk->e_rq_pool);
- mempool_destroy(pblk->w_rq_pool);
+ mempool_exit(&pblk->page_bio_pool);
+ mempool_exit(&pblk->gen_ws_pool);
+ mempool_exit(&pblk->rec_pool);
+ mempool_exit(&pblk->r_rq_pool);
+ mempool_exit(&pblk->e_rq_pool);
+ mempool_exit(&pblk->w_rq_pool);
pblk_free_global_caches(pblk);
kfree(pblk->pad_dist);
@@ -489,11 +503,17 @@ static void pblk_line_mg_free(struct pblk *pblk)
}
}
-static void pblk_line_meta_free(struct pblk_line *line)
+static void pblk_line_meta_free(struct pblk_line_mgmt *l_mg,
+ struct pblk_line *line)
{
+ struct pblk_w_err_gc *w_err_gc = line->w_err_gc;
+
kfree(line->blk_bitmap);
kfree(line->erase_bitmap);
kfree(line->chks);
+
+ pblk_mfree(w_err_gc->lba_list, l_mg->emeta_alloc_type);
+ kfree(w_err_gc);
}
static void pblk_lines_free(struct pblk *pblk)
@@ -506,8 +526,8 @@ static void pblk_lines_free(struct pblk *pblk)
for (i = 0; i < l_mg->nr_lines; i++) {
line = &pblk->lines[i];
- pblk_line_free(pblk, line);
- pblk_line_meta_free(line);
+ pblk_line_free(line);
+ pblk_line_meta_free(l_mg, line);
}
spin_unlock(&l_mg->free_lock);
@@ -748,14 +768,14 @@ static int pblk_setup_line_meta_20(struct pblk *pblk, struct pblk_line *line,
chunk->cnlb = chunk_meta->cnlb;
chunk->wp = chunk_meta->wp;
- if (!(chunk->state & NVM_CHK_ST_OFFLINE))
- continue;
-
if (chunk->type & NVM_CHK_TP_SZ_SPEC) {
WARN_ONCE(1, "pblk: custom-sized chunks unsupported\n");
continue;
}
+ if (!(chunk->state & NVM_CHK_ST_OFFLINE))
+ continue;
+
set_bit(pos, line->blk_bitmap);
nr_bad_chks++;
}
@@ -809,20 +829,28 @@ static int pblk_alloc_line_meta(struct pblk *pblk, struct pblk_line *line)
return -ENOMEM;
line->erase_bitmap = kzalloc(lm->blk_bitmap_len, GFP_KERNEL);
- if (!line->erase_bitmap) {
- kfree(line->blk_bitmap);
- return -ENOMEM;
- }
+ if (!line->erase_bitmap)
+ goto free_blk_bitmap;
+
line->chks = kmalloc(lm->blk_per_line * sizeof(struct nvm_chk_meta),
GFP_KERNEL);
- if (!line->chks) {
- kfree(line->erase_bitmap);
- kfree(line->blk_bitmap);
- return -ENOMEM;
- }
+ if (!line->chks)
+ goto free_erase_bitmap;
+
+ line->w_err_gc = kzalloc(sizeof(struct pblk_w_err_gc), GFP_KERNEL);
+ if (!line->w_err_gc)
+ goto free_chks;
return 0;
+
+free_chks:
+ kfree(line->chks);
+free_erase_bitmap:
+ kfree(line->erase_bitmap);
+free_blk_bitmap:
+ kfree(line->blk_bitmap);
+ return -ENOMEM;
}
static int pblk_line_mg_init(struct pblk *pblk)
@@ -847,12 +875,14 @@ static int pblk_line_mg_init(struct pblk *pblk)
INIT_LIST_HEAD(&l_mg->gc_mid_list);
INIT_LIST_HEAD(&l_mg->gc_low_list);
INIT_LIST_HEAD(&l_mg->gc_empty_list);
+ INIT_LIST_HEAD(&l_mg->gc_werr_list);
INIT_LIST_HEAD(&l_mg->emeta_list);
- l_mg->gc_lists[0] = &l_mg->gc_high_list;
- l_mg->gc_lists[1] = &l_mg->gc_mid_list;
- l_mg->gc_lists[2] = &l_mg->gc_low_list;
+ l_mg->gc_lists[0] = &l_mg->gc_werr_list;
+ l_mg->gc_lists[1] = &l_mg->gc_high_list;
+ l_mg->gc_lists[2] = &l_mg->gc_mid_list;
+ l_mg->gc_lists[3] = &l_mg->gc_low_list;
spin_lock_init(&l_mg->free_lock);
spin_lock_init(&l_mg->close_lock);
@@ -1047,6 +1077,11 @@ static int pblk_lines_init(struct pblk *pblk)
nr_free_chks += pblk_setup_line_meta(pblk, line, chunk_meta, i);
}
+ if (!nr_free_chks) {
+ pr_err("pblk: too many bad blocks prevent for sane instance\n");
+ return -EINTR;
+ }
+
pblk_set_provision(pblk, nr_free_chks);
kfree(chunk_meta);
@@ -1054,7 +1089,7 @@ static int pblk_lines_init(struct pblk *pblk)
fail_free_lines:
while (--i >= 0)
- pblk_line_meta_free(&pblk->lines[i]);
+ pblk_line_meta_free(l_mg, &pblk->lines[i]);
kfree(pblk->lines);
fail_free_chunk_meta:
kfree(chunk_meta);
@@ -1110,23 +1145,25 @@ static void pblk_free(struct pblk *pblk)
kfree(pblk);
}
-static void pblk_tear_down(struct pblk *pblk)
+static void pblk_tear_down(struct pblk *pblk, bool graceful)
{
- pblk_pipeline_stop(pblk);
+ if (graceful)
+ __pblk_pipeline_flush(pblk);
+ __pblk_pipeline_stop(pblk);
pblk_writer_stop(pblk);
pblk_rb_sync_l2p(&pblk->rwb);
pblk_rl_free(&pblk->rl);
- pr_debug("pblk: consistent tear down\n");
+ pr_debug("pblk: consistent tear down (graceful:%d)\n", graceful);
}
-static void pblk_exit(void *private)
+static void pblk_exit(void *private, bool graceful)
{
struct pblk *pblk = private;
down_write(&pblk_lock);
- pblk_gc_exit(pblk);
- pblk_tear_down(pblk);
+ pblk_gc_exit(pblk, graceful);
+ pblk_tear_down(pblk, graceful);
#ifdef CONFIG_NVM_DEBUG
pr_info("pblk exit: L2P CRC: %x\n", pblk_l2p_crc(pblk));
@@ -1175,6 +1212,7 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
pblk->state = PBLK_STATE_RUNNING;
pblk->gc.gc_enabled = 0;
+ spin_lock_init(&pblk->resubmit_lock);
spin_lock_init(&pblk->trans_lock);
spin_lock_init(&pblk->lock);
@@ -1297,18 +1335,18 @@ static int __init pblk_module_init(void)
{
int ret;
- pblk_bio_set = bioset_create(BIO_POOL_SIZE, 0, 0);
- if (!pblk_bio_set)
- return -ENOMEM;
+ ret = bioset_init(&pblk_bio_set, BIO_POOL_SIZE, 0, 0);
+ if (ret)
+ return ret;
ret = nvm_register_tgt_type(&tt_pblk);
if (ret)
- bioset_free(pblk_bio_set);
+ bioset_exit(&pblk_bio_set);
return ret;
}
static void pblk_module_exit(void)
{
- bioset_free(pblk_bio_set);
+ bioset_exit(&pblk_bio_set);
nvm_unregister_tgt_type(&tt_pblk);
}
diff --git a/drivers/lightnvm/pblk-map.c b/drivers/lightnvm/pblk-map.c
index 20dbaa8..953ca31 100644
--- a/drivers/lightnvm/pblk-map.c
+++ b/drivers/lightnvm/pblk-map.c
@@ -18,11 +18,11 @@
#include "pblk.h"
-static void pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
- struct ppa_addr *ppa_list,
- unsigned long *lun_bitmap,
- struct pblk_sec_meta *meta_list,
- unsigned int valid_secs)
+static int pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
+ struct ppa_addr *ppa_list,
+ unsigned long *lun_bitmap,
+ struct pblk_sec_meta *meta_list,
+ unsigned int valid_secs)
{
struct pblk_line *line = pblk_line_get_data(pblk);
struct pblk_emeta *emeta;
@@ -35,8 +35,14 @@ static void pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
if (pblk_line_is_full(line)) {
struct pblk_line *prev_line = line;
+ /* If we cannot allocate a new line, make sure to store metadata
+ * on current line and then fail
+ */
line = pblk_line_replace_data(pblk);
pblk_line_close_meta(pblk, prev_line);
+
+ if (!line)
+ return -EINTR;
}
emeta = line->emeta;
@@ -74,6 +80,7 @@ static void pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
}
pblk_down_rq(pblk, ppa_list, nr_secs, lun_bitmap);
+ return 0;
}
void pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
@@ -87,8 +94,12 @@ void pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
for (i = off; i < rqd->nr_ppas; i += min) {
map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
- pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i],
- lun_bitmap, &meta_list[i], map_secs);
+ if (pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i],
+ lun_bitmap, &meta_list[i], map_secs)) {
+ bio_put(rqd->bio);
+ pblk_free_rqd(pblk, rqd, PBLK_WRITE);
+ pblk_pipeline_stop(pblk);
+ }
}
}
@@ -108,8 +119,12 @@ void pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
for (i = 0; i < rqd->nr_ppas; i += min) {
map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
- pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i],
- lun_bitmap, &meta_list[i], map_secs);
+ if (pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i],
+ lun_bitmap, &meta_list[i], map_secs)) {
+ bio_put(rqd->bio);
+ pblk_free_rqd(pblk, rqd, PBLK_WRITE);
+ pblk_pipeline_stop(pblk);
+ }
erase_lun = pblk_ppa_to_pos(geo, rqd->ppa_list[i]);
diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c
index 52fdd85..00cd1f2 100644
--- a/drivers/lightnvm/pblk-rb.c
+++ b/drivers/lightnvm/pblk-rb.c
@@ -142,10 +142,9 @@ static void clean_wctx(struct pblk_w_ctx *w_ctx)
{
int flags;
-try:
flags = READ_ONCE(w_ctx->flags);
- if (!(flags & PBLK_SUBMITTED_ENTRY))
- goto try;
+ WARN_ONCE(!(flags & PBLK_SUBMITTED_ENTRY),
+ "pblk: overwriting unsubmitted data\n");
/* Release flags on context. Protect from writes and reads */
smp_store_release(&w_ctx->flags, PBLK_WRITABLE_ENTRY);
@@ -350,7 +349,7 @@ void pblk_rb_write_entry_gc(struct pblk_rb *rb, void *data,
}
static int pblk_rb_flush_point_set(struct pblk_rb *rb, struct bio *bio,
- unsigned int pos)
+ unsigned int pos)
{
struct pblk_rb_entry *entry;
unsigned int sync, flush_point;
@@ -420,7 +419,7 @@ void pblk_rb_flush(struct pblk_rb *rb)
if (pblk_rb_flush_point_set(rb, NULL, mem))
return;
- pblk_write_should_kick(pblk);
+ pblk_write_kick(pblk);
}
static int pblk_rb_may_write_flush(struct pblk_rb *rb, unsigned int nr_entries,
@@ -504,45 +503,6 @@ int pblk_rb_may_write_gc(struct pblk_rb *rb, unsigned int nr_entries,
}
/*
- * The caller of this function must ensure that the backpointer will not
- * overwrite the entries passed on the list.
- */
-unsigned int pblk_rb_read_to_bio_list(struct pblk_rb *rb, struct bio *bio,
- struct list_head *list,
- unsigned int max)
-{
- struct pblk_rb_entry *entry, *tentry;
- struct page *page;
- unsigned int read = 0;
- int ret;
-
- list_for_each_entry_safe(entry, tentry, list, index) {
- if (read > max) {
- pr_err("pblk: too many entries on list\n");
- goto out;
- }
-
- page = virt_to_page(entry->data);
- if (!page) {
- pr_err("pblk: could not allocate write bio page\n");
- goto out;
- }
-
- ret = bio_add_page(bio, page, rb->seg_size, 0);
- if (ret != rb->seg_size) {
- pr_err("pblk: could not add page to write bio\n");
- goto out;
- }
-
- list_del(&entry->index);
- read++;
- }
-
-out:
- return read;
-}
-
-/*
* Read available entries on rb and add them to the given bio. To avoid a memory
* copy, a page reference to the write buffer is used to be added to the bio.
*
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 9eee10f..1869469 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -39,10 +39,10 @@ static int pblk_read_from_cache(struct pblk *pblk, struct bio *bio,
}
static void pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd,
- sector_t blba, unsigned long *read_bitmap)
+ struct bio *bio, sector_t blba,
+ unsigned long *read_bitmap)
{
struct pblk_sec_meta *meta_list = rqd->meta_list;
- struct bio *bio = rqd->bio;
struct ppa_addr ppas[PBLK_MAX_REQ_ADDRS];
int nr_secs = rqd->nr_ppas;
bool advanced_bio = false;
@@ -102,34 +102,71 @@ static void pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd,
#endif
}
-static int pblk_submit_read_io(struct pblk *pblk, struct nvm_rq *rqd)
+
+static void pblk_read_check_seq(struct pblk *pblk, struct nvm_rq *rqd,
+ sector_t blba)
{
- int err;
-
- err = pblk_submit_io(pblk, rqd);
- if (err)
- return NVM_IO_ERR;
-
- return NVM_IO_OK;
-}
-
-static void pblk_read_check(struct pblk *pblk, struct nvm_rq *rqd,
- sector_t blba)
-{
- struct pblk_sec_meta *meta_list = rqd->meta_list;
+ struct pblk_sec_meta *meta_lba_list = rqd->meta_list;
int nr_lbas = rqd->nr_ppas;
int i;
for (i = 0; i < nr_lbas; i++) {
- u64 lba = le64_to_cpu(meta_list[i].lba);
+ u64 lba = le64_to_cpu(meta_lba_list[i].lba);
if (lba == ADDR_EMPTY)
continue;
- WARN(lba != blba + i, "pblk: corrupted read LBA\n");
+ if (lba != blba + i) {
+#ifdef CONFIG_NVM_DEBUG
+ struct ppa_addr *p;
+
+ p = (nr_lbas == 1) ? &rqd->ppa_list[i] : &rqd->ppa_addr;
+ print_ppa(&pblk->dev->geo, p, "seq", i);
+#endif
+ pr_err("pblk: corrupted read LBA (%llu/%llu)\n",
+ lba, (u64)blba + i);
+ WARN_ON(1);
+ }
}
}
+/*
+ * There can be holes in the lba list.
+ */
+static void pblk_read_check_rand(struct pblk *pblk, struct nvm_rq *rqd,
+ u64 *lba_list, int nr_lbas)
+{
+ struct pblk_sec_meta *meta_lba_list = rqd->meta_list;
+ int i, j;
+
+ for (i = 0, j = 0; i < nr_lbas; i++) {
+ u64 lba = lba_list[i];
+ u64 meta_lba;
+
+ if (lba == ADDR_EMPTY)
+ continue;
+
+ meta_lba = le64_to_cpu(meta_lba_list[j].lba);
+
+ if (lba != meta_lba) {
+#ifdef CONFIG_NVM_DEBUG
+ struct ppa_addr *p;
+ int nr_ppas = rqd->nr_ppas;
+
+ p = (nr_ppas == 1) ? &rqd->ppa_list[j] : &rqd->ppa_addr;
+ print_ppa(&pblk->dev->geo, p, "seq", j);
+#endif
+ pr_err("pblk: corrupted read LBA (%llu/%llu)\n",
+ lba, meta_lba);
+ WARN_ON(1);
+ }
+
+ j++;
+ }
+
+ WARN_ONCE(j != rqd->nr_ppas, "pblk: corrupted random request\n");
+}
+
static void pblk_read_put_rqd_kref(struct pblk *pblk, struct nvm_rq *rqd)
{
struct ppa_addr *ppa_list;
@@ -152,7 +189,6 @@ static void pblk_end_user_read(struct bio *bio)
WARN_ONCE(bio->bi_status, "pblk: corrupted read bio\n");
#endif
bio_endio(bio);
- bio_put(bio);
}
static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd,
@@ -160,23 +196,18 @@ static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd,
{
struct nvm_tgt_dev *dev = pblk->dev;
struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd);
- struct bio *bio = rqd->bio;
+ struct bio *int_bio = rqd->bio;
unsigned long start_time = r_ctx->start_time;
generic_end_io_acct(dev->q, READ, &pblk->disk->part0, start_time);
if (rqd->error)
pblk_log_read_err(pblk, rqd);
-#ifdef CONFIG_NVM_DEBUG
- else
- WARN_ONCE(bio->bi_status, "pblk: corrupted read error\n");
-#endif
- pblk_read_check(pblk, rqd, r_ctx->lba);
+ pblk_read_check_seq(pblk, rqd, r_ctx->lba);
- bio_put(bio);
- if (r_ctx->private)
- pblk_end_user_read((struct bio *)r_ctx->private);
+ if (int_bio)
+ bio_put(int_bio);
if (put_line)
pblk_read_put_rqd_kref(pblk, rqd);
@@ -193,16 +224,19 @@ static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd,
static void pblk_end_io_read(struct nvm_rq *rqd)
{
struct pblk *pblk = rqd->private;
+ struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd);
+ struct bio *bio = (struct bio *)r_ctx->private;
+ pblk_end_user_read(bio);
__pblk_end_io_read(pblk, rqd, true);
}
-static int pblk_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
- unsigned int bio_init_idx,
- unsigned long *read_bitmap)
+static int pblk_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
+ struct bio *orig_bio, unsigned int bio_init_idx,
+ unsigned long *read_bitmap)
{
- struct bio *new_bio, *bio = rqd->bio;
struct pblk_sec_meta *meta_list = rqd->meta_list;
+ struct bio *new_bio;
struct bio_vec src_bv, dst_bv;
void *ppa_ptr = NULL;
void *src_p, *dst_p;
@@ -219,11 +253,11 @@ static int pblk_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
new_bio = bio_alloc(GFP_KERNEL, nr_holes);
if (pblk_bio_add_pages(pblk, new_bio, GFP_KERNEL, nr_holes))
- goto err;
+ goto fail_add_pages;
if (nr_holes != new_bio->bi_vcnt) {
pr_err("pblk: malformed bio\n");
- goto err;
+ goto fail;
}
for (i = 0; i < nr_secs; i++)
@@ -246,7 +280,7 @@ static int pblk_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
if (ret) {
bio_put(rqd->bio);
pr_err("pblk: sync read IO submission failed\n");
- goto err;
+ goto fail;
}
if (rqd->error) {
@@ -282,7 +316,7 @@ static int pblk_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
meta_list[hole].lba = lba_list_media[i];
src_bv = new_bio->bi_io_vec[i++];
- dst_bv = bio->bi_io_vec[bio_init_idx + hole];
+ dst_bv = orig_bio->bi_io_vec[bio_init_idx + hole];
src_p = kmap_atomic(src_bv.bv_page);
dst_p = kmap_atomic(dst_bv.bv_page);
@@ -294,35 +328,33 @@ static int pblk_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
kunmap_atomic(src_p);
kunmap_atomic(dst_p);
- mempool_free(src_bv.bv_page, pblk->page_bio_pool);
+ mempool_free(src_bv.bv_page, &pblk->page_bio_pool);
hole = find_next_zero_bit(read_bitmap, nr_secs, hole + 1);
} while (hole < nr_secs);
bio_put(new_bio);
- /* Complete the original bio and associated request */
- bio_endio(bio);
- rqd->bio = bio;
+ /* restore original request */
+ rqd->bio = NULL;
rqd->nr_ppas = nr_secs;
__pblk_end_io_read(pblk, rqd, false);
- return NVM_IO_OK;
+ return NVM_IO_DONE;
-err:
- pr_err("pblk: failed to perform partial read\n");
-
+fail:
/* Free allocated pages in new bio */
- pblk_bio_free_pages(pblk, bio, 0, new_bio->bi_vcnt);
+ pblk_bio_free_pages(pblk, new_bio, 0, new_bio->bi_vcnt);
+fail_add_pages:
+ pr_err("pblk: failed to perform partial read\n");
__pblk_end_io_read(pblk, rqd, false);
return NVM_IO_ERR;
}
-static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd,
+static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd, struct bio *bio,
sector_t lba, unsigned long *read_bitmap)
{
struct pblk_sec_meta *meta_list = rqd->meta_list;
- struct bio *bio = rqd->bio;
struct ppa_addr ppa;
pblk_lookup_l2p_seq(pblk, &ppa, lba, 1);
@@ -386,14 +418,15 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
rqd = pblk_alloc_rqd(pblk, PBLK_READ);
rqd->opcode = NVM_OP_PREAD;
- rqd->bio = bio;
rqd->nr_ppas = nr_secs;
+ rqd->bio = NULL; /* cloned bio if needed */
rqd->private = pblk;
rqd->end_io = pblk_end_io_read;
r_ctx = nvm_rq_to_pdu(rqd);
r_ctx->start_time = jiffies;
r_ctx->lba = blba;
+ r_ctx->private = bio; /* original bio */
/* Save the index for this bio's start. This is needed in case
* we need to fill a partial read.
@@ -411,17 +444,15 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size;
rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size;
- pblk_read_ppalist_rq(pblk, rqd, blba, &read_bitmap);
+ pblk_read_ppalist_rq(pblk, rqd, bio, blba, &read_bitmap);
} else {
- pblk_read_rq(pblk, rqd, blba, &read_bitmap);
+ pblk_read_rq(pblk, rqd, bio, blba, &read_bitmap);
}
- bio_get(bio);
if (bitmap_full(&read_bitmap, nr_secs)) {
- bio_endio(bio);
atomic_inc(&pblk->inflight_io);
__pblk_end_io_read(pblk, rqd, false);
- return NVM_IO_OK;
+ return NVM_IO_DONE;
}
/* All sectors are to be read from the device */
@@ -429,20 +460,17 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
struct bio *int_bio = NULL;
/* Clone read bio to deal with read errors internally */
- int_bio = bio_clone_fast(bio, GFP_KERNEL, pblk_bio_set);
+ int_bio = bio_clone_fast(bio, GFP_KERNEL, &pblk_bio_set);
if (!int_bio) {
pr_err("pblk: could not clone read bio\n");
goto fail_end_io;
}
rqd->bio = int_bio;
- r_ctx->private = bio;
- ret = pblk_submit_read_io(pblk, rqd);
- if (ret) {
+ if (pblk_submit_io(pblk, rqd)) {
pr_err("pblk: read IO submission failed\n");
- if (int_bio)
- bio_put(int_bio);
+ ret = NVM_IO_ERR;
goto fail_end_io;
}
@@ -452,7 +480,7 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
/* The read bio request could be partially filled by the write buffer,
* but there are some holes that need to be read from the drive.
*/
- return pblk_partial_read_bio(pblk, rqd, bio_init_idx, &read_bitmap);
+ return pblk_partial_read(pblk, rqd, bio, bio_init_idx, &read_bitmap);
fail_rqd_free:
pblk_free_rqd(pblk, rqd, PBLK_READ);
@@ -585,6 +613,8 @@ int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
goto err_free_bio;
}
+ pblk_read_check_rand(pblk, &rqd, gc_rq->lba_list, gc_rq->nr_secs);
+
atomic_dec(&pblk->inflight_io);
if (rqd.error) {
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index 3e079c2..5983428 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -16,97 +16,6 @@
#include "pblk.h"
-void pblk_submit_rec(struct work_struct *work)
-{
- struct pblk_rec_ctx *recovery =
- container_of(work, struct pblk_rec_ctx, ws_rec);
- struct pblk *pblk = recovery->pblk;
- struct nvm_rq *rqd = recovery->rqd;
- struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
- struct bio *bio;
- unsigned int nr_rec_secs;
- unsigned int pgs_read;
- int ret;
-
- nr_rec_secs = bitmap_weight((unsigned long int *)&rqd->ppa_status,
- NVM_MAX_VLBA);
-
- bio = bio_alloc(GFP_KERNEL, nr_rec_secs);
-
- bio->bi_iter.bi_sector = 0;
- bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
- rqd->bio = bio;
- rqd->nr_ppas = nr_rec_secs;
-
- pgs_read = pblk_rb_read_to_bio_list(&pblk->rwb, bio, &recovery->failed,
- nr_rec_secs);
- if (pgs_read != nr_rec_secs) {
- pr_err("pblk: could not read recovery entries\n");
- goto err;
- }
-
- if (pblk_setup_w_rec_rq(pblk, rqd, c_ctx)) {
- pr_err("pblk: could not setup recovery request\n");
- goto err;
- }
-
-#ifdef CONFIG_NVM_DEBUG
- atomic_long_add(nr_rec_secs, &pblk->recov_writes);
-#endif
-
- ret = pblk_submit_io(pblk, rqd);
- if (ret) {
- pr_err("pblk: I/O submission failed: %d\n", ret);
- goto err;
- }
-
- mempool_free(recovery, pblk->rec_pool);
- return;
-
-err:
- bio_put(bio);
- pblk_free_rqd(pblk, rqd, PBLK_WRITE);
-}
-
-int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
- struct pblk_rec_ctx *recovery, u64 *comp_bits,
- unsigned int comp)
-{
- struct nvm_rq *rec_rqd;
- struct pblk_c_ctx *rec_ctx;
- int nr_entries = c_ctx->nr_valid + c_ctx->nr_padded;
-
- rec_rqd = pblk_alloc_rqd(pblk, PBLK_WRITE);
- rec_ctx = nvm_rq_to_pdu(rec_rqd);
-
- /* Copy completion bitmap, but exclude the first X completed entries */
- bitmap_shift_right((unsigned long int *)&rec_rqd->ppa_status,
- (unsigned long int *)comp_bits,
- comp, NVM_MAX_VLBA);
-
- /* Save the context for the entries that need to be re-written and
- * update current context with the completed entries.
- */
- rec_ctx->sentry = pblk_rb_wrap_pos(&pblk->rwb, c_ctx->sentry + comp);
- if (comp >= c_ctx->nr_valid) {
- rec_ctx->nr_valid = 0;
- rec_ctx->nr_padded = nr_entries - comp;
-
- c_ctx->nr_padded = comp - c_ctx->nr_valid;
- } else {
- rec_ctx->nr_valid = c_ctx->nr_valid - comp;
- rec_ctx->nr_padded = c_ctx->nr_padded;
-
- c_ctx->nr_valid = comp;
- c_ctx->nr_padded = 0;
- }
-
- recovery->rqd = rec_rqd;
- recovery->pblk = pblk;
-
- return 0;
-}
-
int pblk_recov_check_emeta(struct pblk *pblk, struct line_emeta *emeta_buf)
{
u32 crc;
@@ -865,18 +774,30 @@ static void pblk_recov_wa_counters(struct pblk *pblk,
}
static int pblk_line_was_written(struct pblk_line *line,
- struct pblk_line_meta *lm)
+ struct pblk *pblk)
{
- int i;
- int state_mask = NVM_CHK_ST_OFFLINE | NVM_CHK_ST_FREE;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct nvm_chk_meta *chunk;
+ struct ppa_addr bppa;
+ int smeta_blk;
- for (i = 0; i < lm->blk_per_line; i++) {
- if (!(line->chks[i].state & state_mask))
- return 1;
- }
+ if (line->state == PBLK_LINESTATE_BAD)
+ return 0;
- return 0;
+ smeta_blk = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line);
+ if (smeta_blk >= lm->blk_per_line)
+ return 0;
+
+ bppa = pblk->luns[smeta_blk].bppa;
+ chunk = &line->chks[pblk_ppa_to_pos(geo, bppa)];
+
+ if (chunk->state & NVM_CHK_ST_FREE)
+ return 0;
+
+ return 1;
}
struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
@@ -915,7 +836,7 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
line->lun_bitmap = ((void *)(smeta_buf)) +
sizeof(struct line_smeta);
- if (!pblk_line_was_written(line, lm))
+ if (!pblk_line_was_written(line, pblk))
continue;
/* Lines that cannot be read are assumed as not written here */
diff --git a/drivers/lightnvm/pblk-rl.c b/drivers/lightnvm/pblk-rl.c
index 883a711..6a0616a 100644
--- a/drivers/lightnvm/pblk-rl.c
+++ b/drivers/lightnvm/pblk-rl.c
@@ -73,6 +73,16 @@ void pblk_rl_user_in(struct pblk_rl *rl, int nr_entries)
pblk_rl_kick_u_timer(rl);
}
+void pblk_rl_werr_line_in(struct pblk_rl *rl)
+{
+ atomic_inc(&rl->werr_lines);
+}
+
+void pblk_rl_werr_line_out(struct pblk_rl *rl)
+{
+ atomic_dec(&rl->werr_lines);
+}
+
void pblk_rl_gc_in(struct pblk_rl *rl, int nr_entries)
{
atomic_add(nr_entries, &rl->rb_gc_cnt);
@@ -99,11 +109,21 @@ static void __pblk_rl_update_rates(struct pblk_rl *rl,
{
struct pblk *pblk = container_of(rl, struct pblk, rl);
int max = rl->rb_budget;
+ int werr_gc_needed = atomic_read(&rl->werr_lines);
if (free_blocks >= rl->high) {
- rl->rb_user_max = max;
- rl->rb_gc_max = 0;
- rl->rb_state = PBLK_RL_HIGH;
+ if (werr_gc_needed) {
+ /* Allocate a small budget for recovering
+ * lines with write errors
+ */
+ rl->rb_gc_max = 1 << rl->rb_windows_pw;
+ rl->rb_user_max = max - rl->rb_gc_max;
+ rl->rb_state = PBLK_RL_WERR;
+ } else {
+ rl->rb_user_max = max;
+ rl->rb_gc_max = 0;
+ rl->rb_state = PBLK_RL_OFF;
+ }
} else if (free_blocks < rl->high) {
int shift = rl->high_pw - rl->rb_windows_pw;
int user_windows = free_blocks >> shift;
@@ -124,7 +144,7 @@ static void __pblk_rl_update_rates(struct pblk_rl *rl,
rl->rb_state = PBLK_RL_LOW;
}
- if (rl->rb_state == (PBLK_RL_MID | PBLK_RL_LOW))
+ if (rl->rb_state != PBLK_RL_OFF)
pblk_gc_should_start(pblk);
else
pblk_gc_should_stop(pblk);
@@ -221,6 +241,7 @@ void pblk_rl_init(struct pblk_rl *rl, int budget)
atomic_set(&rl->rb_user_cnt, 0);
atomic_set(&rl->rb_gc_cnt, 0);
atomic_set(&rl->rb_space, -1);
+ atomic_set(&rl->werr_lines, 0);
timer_setup(&rl->u_timer, pblk_rl_u_timer, 0);
diff --git a/drivers/lightnvm/pblk-sysfs.c b/drivers/lightnvm/pblk-sysfs.c
index e61909a..88a0a7c 100644
--- a/drivers/lightnvm/pblk-sysfs.c
+++ b/drivers/lightnvm/pblk-sysfs.c
@@ -173,6 +173,8 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
int free_line_cnt = 0, closed_line_cnt = 0, emeta_line_cnt = 0;
int d_line_cnt = 0, l_line_cnt = 0;
int gc_full = 0, gc_high = 0, gc_mid = 0, gc_low = 0, gc_empty = 0;
+ int gc_werr = 0;
+
int bad = 0, cor = 0;
int msecs = 0, cur_sec = 0, vsc = 0, sec_in_line = 0;
int map_weight = 0, meta_weight = 0;
@@ -237,6 +239,15 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
gc_empty++;
}
+ list_for_each_entry(line, &l_mg->gc_werr_list, list) {
+ if (line->type == PBLK_LINETYPE_DATA)
+ d_line_cnt++;
+ else if (line->type == PBLK_LINETYPE_LOG)
+ l_line_cnt++;
+ closed_line_cnt++;
+ gc_werr++;
+ }
+
list_for_each_entry(line, &l_mg->bad_list, list)
bad++;
list_for_each_entry(line, &l_mg->corrupt_list, list)
@@ -275,8 +286,8 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
l_mg->nr_lines);
sz += snprintf(page + sz, PAGE_SIZE - sz,
- "GC: full:%d, high:%d, mid:%d, low:%d, empty:%d, queue:%d\n",
- gc_full, gc_high, gc_mid, gc_low, gc_empty,
+ "GC: full:%d, high:%d, mid:%d, low:%d, empty:%d, werr: %d, queue:%d\n",
+ gc_full, gc_high, gc_mid, gc_low, gc_empty, gc_werr,
atomic_read(&pblk->gc.read_inflight_gc));
sz += snprintf(page + sz, PAGE_SIZE - sz,
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index 3e6f1eb..f353e52 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -103,68 +103,150 @@ static void pblk_complete_write(struct pblk *pblk, struct nvm_rq *rqd,
pblk_rb_sync_end(&pblk->rwb, &flags);
}
-/* When a write fails, we are not sure whether the block has grown bad or a page
- * range is more susceptible to write errors. If a high number of pages fail, we
- * assume that the block is bad and we mark it accordingly. In all cases, we
- * remap and resubmit the failed entries as fast as possible; if a flush is
- * waiting on a completion, the whole stack would stall otherwise.
- */
+/* Map remaining sectors in chunk, starting from ppa */
+static void pblk_map_remaining(struct pblk *pblk, struct ppa_addr *ppa)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line *line;
+ struct ppa_addr map_ppa = *ppa;
+ u64 paddr;
+ int done = 0;
+
+ line = &pblk->lines[pblk_ppa_to_line(*ppa)];
+ spin_lock(&line->lock);
+
+ while (!done) {
+ paddr = pblk_dev_ppa_to_line_addr(pblk, map_ppa);
+
+ if (!test_and_set_bit(paddr, line->map_bitmap))
+ line->left_msecs--;
+
+ if (!test_and_set_bit(paddr, line->invalid_bitmap))
+ le32_add_cpu(line->vsc, -1);
+
+ if (geo->version == NVM_OCSSD_SPEC_12) {
+ map_ppa.ppa++;
+ if (map_ppa.g.pg == geo->num_pg)
+ done = 1;
+ } else {
+ map_ppa.m.sec++;
+ if (map_ppa.m.sec == geo->clba)
+ done = 1;
+ }
+ }
+
+ line->w_err_gc->has_write_err = 1;
+ spin_unlock(&line->lock);
+}
+
+static void pblk_prepare_resubmit(struct pblk *pblk, unsigned int sentry,
+ unsigned int nr_entries)
+{
+ struct pblk_rb *rb = &pblk->rwb;
+ struct pblk_rb_entry *entry;
+ struct pblk_line *line;
+ struct pblk_w_ctx *w_ctx;
+ struct ppa_addr ppa_l2p;
+ int flags;
+ unsigned int pos, i;
+
+ spin_lock(&pblk->trans_lock);
+ pos = sentry;
+ for (i = 0; i < nr_entries; i++) {
+ entry = &rb->entries[pos];
+ w_ctx = &entry->w_ctx;
+
+ /* Check if the lba has been overwritten */
+ ppa_l2p = pblk_trans_map_get(pblk, w_ctx->lba);
+ if (!pblk_ppa_comp(ppa_l2p, entry->cacheline))
+ w_ctx->lba = ADDR_EMPTY;
+
+ /* Mark up the entry as submittable again */
+ flags = READ_ONCE(w_ctx->flags);
+ flags |= PBLK_WRITTEN_DATA;
+ /* Release flags on write context. Protect from writes */
+ smp_store_release(&w_ctx->flags, flags);
+
+ /* Decrese the reference count to the line as we will
+ * re-map these entries
+ */
+ line = &pblk->lines[pblk_ppa_to_line(w_ctx->ppa)];
+ kref_put(&line->ref, pblk_line_put);
+
+ pos = (pos + 1) & (rb->nr_entries - 1);
+ }
+ spin_unlock(&pblk->trans_lock);
+}
+
+static void pblk_queue_resubmit(struct pblk *pblk, struct pblk_c_ctx *c_ctx)
+{
+ struct pblk_c_ctx *r_ctx;
+
+ r_ctx = kzalloc(sizeof(struct pblk_c_ctx), GFP_KERNEL);
+ if (!r_ctx)
+ return;
+
+ r_ctx->lun_bitmap = NULL;
+ r_ctx->sentry = c_ctx->sentry;
+ r_ctx->nr_valid = c_ctx->nr_valid;
+ r_ctx->nr_padded = c_ctx->nr_padded;
+
+ spin_lock(&pblk->resubmit_lock);
+ list_add_tail(&r_ctx->list, &pblk->resubmit_list);
+ spin_unlock(&pblk->resubmit_lock);
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(c_ctx->nr_valid, &pblk->recov_writes);
+#endif
+}
+
+static void pblk_submit_rec(struct work_struct *work)
+{
+ struct pblk_rec_ctx *recovery =
+ container_of(work, struct pblk_rec_ctx, ws_rec);
+ struct pblk *pblk = recovery->pblk;
+ struct nvm_rq *rqd = recovery->rqd;
+ struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
+ struct ppa_addr *ppa_list;
+
+ pblk_log_write_err(pblk, rqd);
+
+ if (rqd->nr_ppas == 1)
+ ppa_list = &rqd->ppa_addr;
+ else
+ ppa_list = rqd->ppa_list;
+
+ pblk_map_remaining(pblk, ppa_list);
+ pblk_queue_resubmit(pblk, c_ctx);
+
+ pblk_up_rq(pblk, rqd->ppa_list, rqd->nr_ppas, c_ctx->lun_bitmap);
+ if (c_ctx->nr_padded)
+ pblk_bio_free_pages(pblk, rqd->bio, c_ctx->nr_valid,
+ c_ctx->nr_padded);
+ bio_put(rqd->bio);
+ pblk_free_rqd(pblk, rqd, PBLK_WRITE);
+ mempool_free(recovery, &pblk->rec_pool);
+
+ atomic_dec(&pblk->inflight_io);
+}
+
+
static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd)
{
- void *comp_bits = &rqd->ppa_status;
- struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
struct pblk_rec_ctx *recovery;
- struct ppa_addr *ppa_list = rqd->ppa_list;
- int nr_ppas = rqd->nr_ppas;
- unsigned int c_entries;
- int bit, ret;
- if (unlikely(nr_ppas == 1))
- ppa_list = &rqd->ppa_addr;
-
- recovery = mempool_alloc(pblk->rec_pool, GFP_ATOMIC);
-
- INIT_LIST_HEAD(&recovery->failed);
-
- bit = -1;
- while ((bit = find_next_bit(comp_bits, nr_ppas, bit + 1)) < nr_ppas) {
- struct pblk_rb_entry *entry;
- struct ppa_addr ppa;
-
- /* Logic error */
- if (bit > c_ctx->nr_valid) {
- WARN_ONCE(1, "pblk: corrupted write request\n");
- mempool_free(recovery, pblk->rec_pool);
- goto out;
- }
-
- ppa = ppa_list[bit];
- entry = pblk_rb_sync_scan_entry(&pblk->rwb, &ppa);
- if (!entry) {
- pr_err("pblk: could not scan entry on write failure\n");
- mempool_free(recovery, pblk->rec_pool);
- goto out;
- }
-
- /* The list is filled first and emptied afterwards. No need for
- * protecting it with a lock
- */
- list_add_tail(&entry->index, &recovery->failed);
+ recovery = mempool_alloc(&pblk->rec_pool, GFP_ATOMIC);
+ if (!recovery) {
+ pr_err("pblk: could not allocate recovery work\n");
+ return;
}
- c_entries = find_first_bit(comp_bits, nr_ppas);
- ret = pblk_recov_setup_rq(pblk, c_ctx, recovery, comp_bits, c_entries);
- if (ret) {
- pr_err("pblk: could not recover from write failure\n");
- mempool_free(recovery, pblk->rec_pool);
- goto out;
- }
+ recovery->pblk = pblk;
+ recovery->rqd = rqd;
INIT_WORK(&recovery->ws_rec, pblk_submit_rec);
queue_work(pblk->close_wq, &recovery->ws_rec);
-
-out:
- pblk_complete_write(pblk, rqd, c_ctx);
}
static void pblk_end_io_write(struct nvm_rq *rqd)
@@ -173,8 +255,8 @@ static void pblk_end_io_write(struct nvm_rq *rqd)
struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
if (rqd->error) {
- pblk_log_write_err(pblk, rqd);
- return pblk_end_w_fail(pblk, rqd);
+ pblk_end_w_fail(pblk, rqd);
+ return;
}
#ifdef CONFIG_NVM_DEBUG
else
@@ -198,6 +280,7 @@ static void pblk_end_io_write_meta(struct nvm_rq *rqd)
if (rqd->error) {
pblk_log_write_err(pblk, rqd);
pr_err("pblk: metadata I/O failed. Line %d\n", line->id);
+ line->w_err_gc->has_write_err = 1;
}
sync = atomic_add_return(rqd->nr_ppas, &emeta->sync);
@@ -266,31 +349,6 @@ static int pblk_setup_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
return 0;
}
-int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd,
- struct pblk_c_ctx *c_ctx)
-{
- struct pblk_line_meta *lm = &pblk->lm;
- unsigned long *lun_bitmap;
- int ret;
-
- lun_bitmap = kzalloc(lm->lun_bitmap_len, GFP_KERNEL);
- if (!lun_bitmap)
- return -ENOMEM;
-
- c_ctx->lun_bitmap = lun_bitmap;
-
- ret = pblk_alloc_w_rq(pblk, rqd, rqd->nr_ppas, pblk_end_io_write);
- if (ret)
- return ret;
-
- pblk_map_rq(pblk, rqd, c_ctx->sentry, lun_bitmap, c_ctx->nr_valid, 0);
-
- rqd->ppa_status = (u64)0;
- rqd->flags = pblk_set_progr_mode(pblk, PBLK_WRITE);
-
- return ret;
-}
-
static int pblk_calc_secs_to_sync(struct pblk *pblk, unsigned int secs_avail,
unsigned int secs_to_flush)
{
@@ -339,6 +397,7 @@ int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line)
bio = pblk_bio_map_addr(pblk, data, rq_ppas, rq_len,
l_mg->emeta_alloc_type, GFP_KERNEL);
if (IS_ERR(bio)) {
+ pr_err("pblk: failed to map emeta io");
ret = PTR_ERR(bio);
goto fail_free_rqd;
}
@@ -515,27 +574,55 @@ static int pblk_submit_write(struct pblk *pblk)
unsigned int secs_avail, secs_to_sync, secs_to_com;
unsigned int secs_to_flush;
unsigned long pos;
+ unsigned int resubmit;
- /* If there are no sectors in the cache, flushes (bios without data)
- * will be cleared on the cache threads
- */
- secs_avail = pblk_rb_read_count(&pblk->rwb);
- if (!secs_avail)
- return 1;
+ spin_lock(&pblk->resubmit_lock);
+ resubmit = !list_empty(&pblk->resubmit_list);
+ spin_unlock(&pblk->resubmit_lock);
- secs_to_flush = pblk_rb_flush_point_count(&pblk->rwb);
- if (!secs_to_flush && secs_avail < pblk->min_write_pgs)
- return 1;
+ /* Resubmit failed writes first */
+ if (resubmit) {
+ struct pblk_c_ctx *r_ctx;
- secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail, secs_to_flush);
- if (secs_to_sync > pblk->max_write_pgs) {
- pr_err("pblk: bad buffer sync calculation\n");
- return 1;
+ spin_lock(&pblk->resubmit_lock);
+ r_ctx = list_first_entry(&pblk->resubmit_list,
+ struct pblk_c_ctx, list);
+ list_del(&r_ctx->list);
+ spin_unlock(&pblk->resubmit_lock);
+
+ secs_avail = r_ctx->nr_valid;
+ pos = r_ctx->sentry;
+
+ pblk_prepare_resubmit(pblk, pos, secs_avail);
+ secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail,
+ secs_avail);
+
+ kfree(r_ctx);
+ } else {
+ /* If there are no sectors in the cache,
+ * flushes (bios without data) will be cleared on
+ * the cache threads
+ */
+ secs_avail = pblk_rb_read_count(&pblk->rwb);
+ if (!secs_avail)
+ return 1;
+
+ secs_to_flush = pblk_rb_flush_point_count(&pblk->rwb);
+ if (!secs_to_flush && secs_avail < pblk->min_write_pgs)
+ return 1;
+
+ secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail,
+ secs_to_flush);
+ if (secs_to_sync > pblk->max_write_pgs) {
+ pr_err("pblk: bad buffer sync calculation\n");
+ return 1;
+ }
+
+ secs_to_com = (secs_to_sync > secs_avail) ?
+ secs_avail : secs_to_sync;
+ pos = pblk_rb_read_commit(&pblk->rwb, secs_to_com);
}
- secs_to_com = (secs_to_sync > secs_avail) ? secs_avail : secs_to_sync;
- pos = pblk_rb_read_commit(&pblk->rwb, secs_to_com);
-
bio = bio_alloc(GFP_KERNEL, secs_to_sync);
bio->bi_iter.bi_sector = 0; /* internal bio */
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 9c682ac..34cc1d6 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -89,12 +89,14 @@ struct pblk_sec_meta {
/* The number of GC lists and the rate-limiter states go together. This way the
* rate-limiter can dictate how much GC is needed based on resource utilization.
*/
-#define PBLK_GC_NR_LISTS 3
+#define PBLK_GC_NR_LISTS 4
enum {
- PBLK_RL_HIGH = 1,
- PBLK_RL_MID = 2,
- PBLK_RL_LOW = 3,
+ PBLK_RL_OFF = 0,
+ PBLK_RL_WERR = 1,
+ PBLK_RL_HIGH = 2,
+ PBLK_RL_MID = 3,
+ PBLK_RL_LOW = 4
};
#define pblk_dma_meta_size (sizeof(struct pblk_sec_meta) * PBLK_MAX_REQ_ADDRS)
@@ -128,7 +130,6 @@ struct pblk_pad_rq {
struct pblk_rec_ctx {
struct pblk *pblk;
struct nvm_rq *rqd;
- struct list_head failed;
struct work_struct ws_rec;
};
@@ -279,6 +280,8 @@ struct pblk_rl {
int rb_user_active;
int rb_gc_active;
+ atomic_t werr_lines; /* Number of write error lines that needs gc */
+
struct timer_list u_timer;
unsigned long long nr_secs;
@@ -312,6 +315,7 @@ enum {
PBLK_LINEGC_MID = 23,
PBLK_LINEGC_HIGH = 24,
PBLK_LINEGC_FULL = 25,
+ PBLK_LINEGC_WERR = 26
};
#define PBLK_MAGIC 0x70626c6b /*pblk*/
@@ -413,6 +417,11 @@ struct pblk_smeta {
struct line_smeta *buf; /* smeta buffer in persistent format */
};
+struct pblk_w_err_gc {
+ int has_write_err;
+ __le64 *lba_list;
+};
+
struct pblk_line {
struct pblk *pblk;
unsigned int id; /* Line number corresponds to the
@@ -458,6 +467,8 @@ struct pblk_line {
struct kref ref; /* Write buffer L2P references */
+ struct pblk_w_err_gc *w_err_gc; /* Write error gc recovery metadata */
+
spinlock_t lock; /* Necessary for invalid_bitmap only */
};
@@ -489,6 +500,8 @@ struct pblk_line_mgmt {
struct list_head gc_mid_list; /* Full lines ready to GC, mid isc */
struct list_head gc_low_list; /* Full lines ready to GC, low isc */
+ struct list_head gc_werr_list; /* Write err recovery list */
+
struct list_head gc_full_list; /* Full lines ready to GC, no valid */
struct list_head gc_empty_list; /* Full lines close, all valid */
@@ -664,12 +677,15 @@ struct pblk {
struct list_head compl_list;
- mempool_t *page_bio_pool;
- mempool_t *gen_ws_pool;
- mempool_t *rec_pool;
- mempool_t *r_rq_pool;
- mempool_t *w_rq_pool;
- mempool_t *e_rq_pool;
+ spinlock_t resubmit_lock; /* Resubmit list lock */
+ struct list_head resubmit_list; /* Resubmit list for failed writes*/
+
+ mempool_t page_bio_pool;
+ mempool_t gen_ws_pool;
+ mempool_t rec_pool;
+ mempool_t r_rq_pool;
+ mempool_t w_rq_pool;
+ mempool_t e_rq_pool;
struct workqueue_struct *close_wq;
struct workqueue_struct *bb_wq;
@@ -713,9 +729,6 @@ void pblk_rb_sync_l2p(struct pblk_rb *rb);
unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct nvm_rq *rqd,
unsigned int pos, unsigned int nr_entries,
unsigned int count);
-unsigned int pblk_rb_read_to_bio_list(struct pblk_rb *rb, struct bio *bio,
- struct list_head *list,
- unsigned int max);
int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba,
struct ppa_addr ppa, int bio_iter, bool advanced_bio);
unsigned int pblk_rb_read_commit(struct pblk_rb *rb, unsigned int entries);
@@ -766,11 +779,13 @@ struct pblk_line *pblk_line_get_data(struct pblk *pblk);
struct pblk_line *pblk_line_get_erase(struct pblk *pblk);
int pblk_line_erase(struct pblk *pblk, struct pblk_line *line);
int pblk_line_is_full(struct pblk_line *line);
-void pblk_line_free(struct pblk *pblk, struct pblk_line *line);
+void pblk_line_free(struct pblk_line *line);
void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line);
void pblk_line_close(struct pblk *pblk, struct pblk_line *line);
void pblk_line_close_ws(struct work_struct *work);
void pblk_pipeline_stop(struct pblk *pblk);
+void __pblk_pipeline_stop(struct pblk *pblk);
+void __pblk_pipeline_flush(struct pblk *pblk);
void pblk_gen_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
void (*work)(struct work_struct *), gfp_t gfp_mask,
struct workqueue_struct *wq);
@@ -794,7 +809,6 @@ void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
void pblk_down_page(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas);
void pblk_up_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
unsigned long *lun_bitmap);
-void pblk_end_io_sync(struct nvm_rq *rqd);
int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
int nr_pages);
void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off,
@@ -837,23 +851,20 @@ void pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
int pblk_write_ts(void *data);
void pblk_write_timer_fn(struct timer_list *t);
void pblk_write_should_kick(struct pblk *pblk);
+void pblk_write_kick(struct pblk *pblk);
/*
* pblk read path
*/
-extern struct bio_set *pblk_bio_set;
+extern struct bio_set pblk_bio_set;
int pblk_submit_read(struct pblk *pblk, struct bio *bio);
int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq);
/*
* pblk recovery
*/
-void pblk_submit_rec(struct work_struct *work);
struct pblk_line *pblk_recov_l2p(struct pblk *pblk);
int pblk_recov_pad(struct pblk *pblk);
int pblk_recov_check_emeta(struct pblk *pblk, struct line_emeta *emeta);
-int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
- struct pblk_rec_ctx *recovery, u64 *comp_bits,
- unsigned int comp);
/*
* pblk gc
@@ -864,7 +875,7 @@ int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
#define PBLK_GC_RSV_LINE 1 /* Reserved lines for GC */
int pblk_gc_init(struct pblk *pblk);
-void pblk_gc_exit(struct pblk *pblk);
+void pblk_gc_exit(struct pblk *pblk, bool graceful);
void pblk_gc_should_start(struct pblk *pblk);
void pblk_gc_should_stop(struct pblk *pblk);
void pblk_gc_should_kick(struct pblk *pblk);
@@ -894,6 +905,9 @@ void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line,
bool used);
int pblk_rl_is_limit(struct pblk_rl *rl);
+void pblk_rl_werr_line_in(struct pblk_rl *rl);
+void pblk_rl_werr_line_out(struct pblk_rl *rl);
+
/*
* pblk sysfs
*/
diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c
index 433dbed..6663893 100644
--- a/drivers/macintosh/via-pmu.c
+++ b/drivers/macintosh/via-pmu.c
@@ -191,10 +191,10 @@ static int init_pmu(void);
static void pmu_start(void);
static irqreturn_t via_pmu_interrupt(int irq, void *arg);
static irqreturn_t gpio1_interrupt(int irq, void *arg);
-static const struct file_operations pmu_info_proc_fops;
-static const struct file_operations pmu_irqstats_proc_fops;
+static int pmu_info_proc_show(struct seq_file *m, void *v);
+static int pmu_irqstats_proc_show(struct seq_file *m, void *v);
+static int pmu_battery_proc_show(struct seq_file *m, void *v);
static void pmu_pass_intr(unsigned char *data, int len);
-static const struct file_operations pmu_battery_proc_fops;
static const struct file_operations pmu_options_proc_fops;
#ifdef CONFIG_ADB
@@ -511,13 +511,15 @@ static int __init via_pmu_dev_init(void)
for (i=0; i<pmu_battery_count; i++) {
char title[16];
sprintf(title, "battery_%ld", i);
- proc_pmu_batt[i] = proc_create_data(title, 0, proc_pmu_root,
- &pmu_battery_proc_fops, (void *)i);
+ proc_pmu_batt[i] = proc_create_single_data(title, 0,
+ proc_pmu_root, pmu_battery_proc_show,
+ (void *)i);
}
- proc_pmu_info = proc_create("info", 0, proc_pmu_root, &pmu_info_proc_fops);
- proc_pmu_irqstats = proc_create("interrupts", 0, proc_pmu_root,
- &pmu_irqstats_proc_fops);
+ proc_pmu_info = proc_create_single("info", 0, proc_pmu_root,
+ pmu_info_proc_show);
+ proc_pmu_irqstats = proc_create_single("interrupts", 0,
+ proc_pmu_root, pmu_irqstats_proc_show);
proc_pmu_options = proc_create("options", 0600, proc_pmu_root,
&pmu_options_proc_fops);
}
@@ -811,19 +813,6 @@ static int pmu_info_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int pmu_info_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, pmu_info_proc_show, NULL);
-}
-
-static const struct file_operations pmu_info_proc_fops = {
- .owner = THIS_MODULE,
- .open = pmu_info_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int pmu_irqstats_proc_show(struct seq_file *m, void *v)
{
int i;
@@ -848,19 +837,6 @@ static int pmu_irqstats_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int pmu_irqstats_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, pmu_irqstats_proc_show, NULL);
-}
-
-static const struct file_operations pmu_irqstats_proc_fops = {
- .owner = THIS_MODULE,
- .open = pmu_irqstats_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int pmu_battery_proc_show(struct seq_file *m, void *v)
{
long batnum = (long)m->private;
@@ -875,19 +851,6 @@ static int pmu_battery_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int pmu_battery_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, pmu_battery_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations pmu_battery_proc_fops = {
- .owner = THIS_MODULE,
- .open = pmu_battery_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int pmu_options_proc_show(struct seq_file *m, void *v)
{
#if defined(CONFIG_SUSPEND) && defined(CONFIG_PPC32)
diff --git a/drivers/mailbox/pcc.c b/drivers/mailbox/pcc.c
index 3ef7f03..fc3c237 100644
--- a/drivers/mailbox/pcc.c
+++ b/drivers/mailbox/pcc.c
@@ -373,33 +373,24 @@ static const struct mbox_chan_ops pcc_chan_ops = {
};
/**
- * parse_pcc_subspace - Parse the PCC table and verify PCC subspace
- * entries. There should be one entry per PCC client.
+ * parse_pcc_subspaces -- Count PCC subspaces defined
* @header: Pointer to the ACPI subtable header under the PCCT.
* @end: End of subtable entry.
*
- * Return: 0 for Success, else errno.
+ * Return: If we find a PCC subspace entry of a valid type, return 0.
+ * Otherwise, return -EINVAL.
*
* This gets called for each entry in the PCC table.
*/
static int parse_pcc_subspace(struct acpi_subtable_header *header,
const unsigned long end)
{
- struct acpi_pcct_hw_reduced *pcct_ss;
+ struct acpi_pcct_subspace *ss = (struct acpi_pcct_subspace *) header;
- if (pcc_mbox_ctrl.num_chans <= MAX_PCC_SUBSPACES) {
- pcct_ss = (struct acpi_pcct_hw_reduced *) header;
+ if (ss->header.type < ACPI_PCCT_TYPE_RESERVED)
+ return 0;
- if ((pcct_ss->header.type !=
- ACPI_PCCT_TYPE_HW_REDUCED_SUBSPACE)
- && (pcct_ss->header.type !=
- ACPI_PCCT_TYPE_HW_REDUCED_SUBSPACE_TYPE2)) {
- pr_err("Incorrect PCC Subspace type detected\n");
- return -EINVAL;
- }
- }
-
- return 0;
+ return -EINVAL;
}
/**
@@ -449,8 +440,8 @@ static int __init acpi_pcc_probe(void)
struct acpi_table_header *pcct_tbl;
struct acpi_subtable_header *pcct_entry;
struct acpi_table_pcct *acpi_pcct_tbl;
+ struct acpi_subtable_proc proc[ACPI_PCCT_TYPE_RESERVED];
int count, i, rc;
- int sum = 0;
acpi_status status = AE_OK;
/* Search for PCCT */
@@ -459,43 +450,41 @@ static int __init acpi_pcc_probe(void)
if (ACPI_FAILURE(status) || !pcct_tbl)
return -ENODEV;
- count = acpi_table_parse_entries(ACPI_SIG_PCCT,
- sizeof(struct acpi_table_pcct),
- ACPI_PCCT_TYPE_HW_REDUCED_SUBSPACE,
- parse_pcc_subspace, MAX_PCC_SUBSPACES);
- sum += (count > 0) ? count : 0;
+ /* Set up the subtable handlers */
+ for (i = ACPI_PCCT_TYPE_GENERIC_SUBSPACE;
+ i < ACPI_PCCT_TYPE_RESERVED; i++) {
+ proc[i].id = i;
+ proc[i].count = 0;
+ proc[i].handler = parse_pcc_subspace;
+ }
- count = acpi_table_parse_entries(ACPI_SIG_PCCT,
- sizeof(struct acpi_table_pcct),
- ACPI_PCCT_TYPE_HW_REDUCED_SUBSPACE_TYPE2,
- parse_pcc_subspace, MAX_PCC_SUBSPACES);
- sum += (count > 0) ? count : 0;
-
- if (sum == 0 || sum >= MAX_PCC_SUBSPACES) {
- pr_err("Error parsing PCC subspaces from PCCT\n");
+ count = acpi_table_parse_entries_array(ACPI_SIG_PCCT,
+ sizeof(struct acpi_table_pcct), proc,
+ ACPI_PCCT_TYPE_RESERVED, MAX_PCC_SUBSPACES);
+ if (count == 0 || count > MAX_PCC_SUBSPACES) {
+ pr_warn("Invalid PCCT: %d PCC subspaces\n", count);
return -EINVAL;
}
- pcc_mbox_channels = kzalloc(sizeof(struct mbox_chan) *
- sum, GFP_KERNEL);
+ pcc_mbox_channels = kzalloc(sizeof(struct mbox_chan) * count, GFP_KERNEL);
if (!pcc_mbox_channels) {
pr_err("Could not allocate space for PCC mbox channels\n");
return -ENOMEM;
}
- pcc_doorbell_vaddr = kcalloc(sum, sizeof(void *), GFP_KERNEL);
+ pcc_doorbell_vaddr = kcalloc(count, sizeof(void *), GFP_KERNEL);
if (!pcc_doorbell_vaddr) {
rc = -ENOMEM;
goto err_free_mbox;
}
- pcc_doorbell_ack_vaddr = kcalloc(sum, sizeof(void *), GFP_KERNEL);
+ pcc_doorbell_ack_vaddr = kcalloc(count, sizeof(void *), GFP_KERNEL);
if (!pcc_doorbell_ack_vaddr) {
rc = -ENOMEM;
goto err_free_db_vaddr;
}
- pcc_doorbell_irq = kcalloc(sum, sizeof(int), GFP_KERNEL);
+ pcc_doorbell_irq = kcalloc(count, sizeof(int), GFP_KERNEL);
if (!pcc_doorbell_irq) {
rc = -ENOMEM;
goto err_free_db_ack_vaddr;
@@ -509,18 +498,24 @@ static int __init acpi_pcc_probe(void)
if (acpi_pcct_tbl->flags & ACPI_PCCT_DOORBELL)
pcc_mbox_ctrl.txdone_irq = true;
- for (i = 0; i < sum; i++) {
+ for (i = 0; i < count; i++) {
struct acpi_generic_address *db_reg;
- struct acpi_pcct_hw_reduced *pcct_ss;
+ struct acpi_pcct_subspace *pcct_ss;
pcc_mbox_channels[i].con_priv = pcct_entry;
- pcct_ss = (struct acpi_pcct_hw_reduced *) pcct_entry;
+ if (pcct_entry->type == ACPI_PCCT_TYPE_HW_REDUCED_SUBSPACE ||
+ pcct_entry->type == ACPI_PCCT_TYPE_HW_REDUCED_SUBSPACE_TYPE2) {
+ struct acpi_pcct_hw_reduced *pcct_hrss;
- if (pcc_mbox_ctrl.txdone_irq) {
- rc = pcc_parse_subspace_irq(i, pcct_ss);
- if (rc < 0)
- goto err;
+ pcct_hrss = (struct acpi_pcct_hw_reduced *) pcct_entry;
+
+ if (pcc_mbox_ctrl.txdone_irq) {
+ rc = pcc_parse_subspace_irq(i, pcct_hrss);
+ if (rc < 0)
+ goto err;
+ }
}
+ pcct_ss = (struct acpi_pcct_subspace *) pcct_entry;
/* If doorbell is in system memory cache the virt address */
db_reg = &pcct_ss->doorbell_register;
@@ -531,7 +526,7 @@ static int __init acpi_pcc_probe(void)
((unsigned long) pcct_entry + pcct_entry->length);
}
- pcc_mbox_ctrl.num_chans = sum;
+ pcc_mbox_ctrl.num_chans = count;
pr_info("Detected %d PCC Subspaces\n", pcc_mbox_ctrl.num_chans);
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 004cc3c..7fa2631 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -290,7 +290,7 @@ do { \
if (kthread_should_stop() || \
test_bit(CACHE_SET_IO_DISABLE, &ca->set->flags)) { \
set_current_state(TASK_RUNNING); \
- return 0; \
+ goto out; \
} \
\
schedule(); \
@@ -378,6 +378,9 @@ static int bch_allocator_thread(void *arg)
bch_prio_write(ca);
}
}
+out:
+ wait_for_kthread_stop();
+ return 0;
}
/* Allocation */
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index d338b70..d6bf294f 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -269,7 +269,7 @@ struct bcache_device {
atomic_t *stripe_sectors_dirty;
unsigned long *full_dirty_stripes;
- struct bio_set *bio_split;
+ struct bio_set bio_split;
unsigned data_csum:1;
@@ -345,6 +345,7 @@ struct cached_dev {
struct keybuf writeback_keys;
+ struct task_struct *status_update_thread;
/*
* Order the write-half of writeback operations strongly in dispatch
* order. (Maintain LBA order; don't allow reads completing out of
@@ -392,6 +393,9 @@ struct cached_dev {
#define DEFAULT_CACHED_DEV_ERROR_LIMIT 64
atomic_t io_errors;
unsigned error_limit;
+ unsigned offline_seconds;
+
+ char backing_dev_name[BDEVNAME_SIZE];
};
enum alloc_reserve {
@@ -464,6 +468,8 @@ struct cache {
atomic_long_t meta_sectors_written;
atomic_long_t btree_sectors_written;
atomic_long_t sectors_written;
+
+ char cache_dev_name[BDEVNAME_SIZE];
};
struct gc_stat {
@@ -524,9 +530,9 @@ struct cache_set {
struct closure sb_write;
struct semaphore sb_write_mutex;
- mempool_t *search;
- mempool_t *bio_meta;
- struct bio_set *bio_split;
+ mempool_t search;
+ mempool_t bio_meta;
+ struct bio_set bio_split;
/* For the btree cache */
struct shrinker shrink;
@@ -651,7 +657,7 @@ struct cache_set {
* A btree node on disk could have too many bsets for an iterator to fit
* on the stack - have to dynamically allocate them
*/
- mempool_t *fill_iter;
+ mempool_t fill_iter;
struct bset_sort_state sort;
@@ -952,8 +958,6 @@ void bch_prio_write(struct cache *);
void bch_write_bdev_super(struct cached_dev *, struct closure *);
extern struct workqueue_struct *bcache_wq;
-extern const char * const bch_cache_modes[];
-extern const char * const bch_stop_on_failure_modes[];
extern struct mutex bch_register_lock;
extern struct list_head bch_cache_sets;
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 579c696..f3403b4 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -1118,8 +1118,7 @@ struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter,
void bch_bset_sort_state_free(struct bset_sort_state *state)
{
- if (state->pool)
- mempool_destroy(state->pool);
+ mempool_exit(&state->pool);
}
int bch_bset_sort_state_init(struct bset_sort_state *state, unsigned page_order)
@@ -1129,11 +1128,7 @@ int bch_bset_sort_state_init(struct bset_sort_state *state, unsigned page_order)
state->page_order = page_order;
state->crit_factor = int_sqrt(1 << page_order);
- state->pool = mempool_create_page_pool(1, page_order);
- if (!state->pool)
- return -ENOMEM;
-
- return 0;
+ return mempool_init_page_pool(&state->pool, 1, page_order);
}
EXPORT_SYMBOL(bch_bset_sort_state_init);
@@ -1191,7 +1186,7 @@ static void __btree_sort(struct btree_keys *b, struct btree_iter *iter,
BUG_ON(order > state->page_order);
- outp = mempool_alloc(state->pool, GFP_NOIO);
+ outp = mempool_alloc(&state->pool, GFP_NOIO);
out = page_address(outp);
used_mempool = true;
order = state->page_order;
@@ -1220,7 +1215,7 @@ static void __btree_sort(struct btree_keys *b, struct btree_iter *iter,
}
if (used_mempool)
- mempool_free(virt_to_page(out), state->pool);
+ mempool_free(virt_to_page(out), &state->pool);
else
free_pages((unsigned long) out, order);
diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h
index 0c24280..b867f22 100644
--- a/drivers/md/bcache/bset.h
+++ b/drivers/md/bcache/bset.h
@@ -347,7 +347,7 @@ static inline struct bkey *bch_bset_search(struct btree_keys *b,
/* Sorting */
struct bset_sort_state {
- mempool_t *pool;
+ mempool_t pool;
unsigned page_order;
unsigned crit_factor;
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 17936b2..2a0968c0 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -204,7 +204,7 @@ void bch_btree_node_read_done(struct btree *b)
struct bset *i = btree_bset_first(b);
struct btree_iter *iter;
- iter = mempool_alloc(b->c->fill_iter, GFP_NOIO);
+ iter = mempool_alloc(&b->c->fill_iter, GFP_NOIO);
iter->size = b->c->sb.bucket_size / b->c->sb.block_size;
iter->used = 0;
@@ -271,7 +271,7 @@ void bch_btree_node_read_done(struct btree *b)
bch_bset_init_next(&b->keys, write_block(b),
bset_magic(&b->c->sb));
out:
- mempool_free(iter, b->c->fill_iter);
+ mempool_free(iter, &b->c->fill_iter);
return;
err:
set_btree_node_io_error(b);
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 028f7b3..d030ce3 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -106,7 +106,6 @@ void bch_btree_verify(struct btree *b)
void bch_data_verify(struct cached_dev *dc, struct bio *bio)
{
- char name[BDEVNAME_SIZE];
struct bio *check;
struct bio_vec bv, cbv;
struct bvec_iter iter, citer = { 0 };
@@ -134,7 +133,7 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio)
bv.bv_len),
dc->disk.c,
"verify failed at dev %s sector %llu",
- bdevname(dc->bdev, name),
+ dc->backing_dev_name,
(uint64_t) bio->bi_iter.bi_sector);
kunmap_atomic(p1);
@@ -251,7 +250,9 @@ void bch_debug_exit(void)
int __init bch_debug_init(struct kobject *kobj)
{
- bcache_debug = debugfs_create_dir("bcache", NULL);
+ if (!IS_ENABLED(CONFIG_DEBUG_FS))
+ return 0;
+ bcache_debug = debugfs_create_dir("bcache", NULL);
return IS_ERR_OR_NULL(bcache_debug);
}
diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index 7fac97a..9612873 100644
--- a/drivers/md/bcache/io.c
+++ b/drivers/md/bcache/io.c
@@ -17,12 +17,12 @@
void bch_bbio_free(struct bio *bio, struct cache_set *c)
{
struct bbio *b = container_of(bio, struct bbio, bio);
- mempool_free(b, c->bio_meta);
+ mempool_free(b, &c->bio_meta);
}
struct bio *bch_bbio_alloc(struct cache_set *c)
{
- struct bbio *b = mempool_alloc(c->bio_meta, GFP_NOIO);
+ struct bbio *b = mempool_alloc(&c->bio_meta, GFP_NOIO);
struct bio *bio = &b->bio;
bio_init(bio, bio->bi_inline_vecs, bucket_pages(c));
@@ -52,7 +52,6 @@ void bch_submit_bbio(struct bio *bio, struct cache_set *c,
/* IO errors */
void bch_count_backing_io_errors(struct cached_dev *dc, struct bio *bio)
{
- char buf[BDEVNAME_SIZE];
unsigned errors;
WARN_ONCE(!dc, "NULL pointer of struct cached_dev");
@@ -60,7 +59,7 @@ void bch_count_backing_io_errors(struct cached_dev *dc, struct bio *bio)
errors = atomic_add_return(1, &dc->io_errors);
if (errors < dc->error_limit)
pr_err("%s: IO error on backing device, unrecoverable",
- bio_devname(bio, buf));
+ dc->backing_dev_name);
else
bch_cached_dev_error(dc);
}
@@ -105,19 +104,18 @@ void bch_count_io_errors(struct cache *ca,
}
if (error) {
- char buf[BDEVNAME_SIZE];
unsigned errors = atomic_add_return(1 << IO_ERROR_SHIFT,
&ca->io_errors);
errors >>= IO_ERROR_SHIFT;
if (errors < ca->set->error_limit)
pr_err("%s: IO error on %s%s",
- bdevname(ca->bdev, buf), m,
+ ca->cache_dev_name, m,
is_read ? ", recovering." : ".");
else
bch_cache_set_error(ca->set,
"%s: too many IO errors %s",
- bdevname(ca->bdev, buf), m);
+ ca->cache_dev_name, m);
}
}
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index a65e336..ae67f5f 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -213,7 +213,7 @@ static void bch_data_insert_start(struct closure *cl)
do {
unsigned i;
struct bkey *k;
- struct bio_set *split = op->c->bio_split;
+ struct bio_set *split = &op->c->bio_split;
/* 1 for the device pointer and 1 for the chksum */
if (bch_keylist_realloc(&op->insert_keys,
@@ -548,7 +548,7 @@ static int cache_lookup_fn(struct btree_op *op, struct btree *b, struct bkey *k)
n = bio_next_split(bio, min_t(uint64_t, INT_MAX,
KEY_OFFSET(k) - bio->bi_iter.bi_sector),
- GFP_NOIO, s->d->bio_split);
+ GFP_NOIO, &s->d->bio_split);
bio_key = &container_of(n, struct bbio, bio)->key;
bch_bkey_copy_single_ptr(bio_key, k, ptr);
@@ -649,11 +649,8 @@ static void backing_request_endio(struct bio *bio)
*/
if (unlikely(s->iop.writeback &&
bio->bi_opf & REQ_PREFLUSH)) {
- char buf[BDEVNAME_SIZE];
-
- bio_devname(bio, buf);
pr_err("Can't flush %s: returned bi_status %i",
- buf, bio->bi_status);
+ dc->backing_dev_name, bio->bi_status);
} else {
/* set to orig_bio->bi_status in bio_complete() */
s->iop.status = bio->bi_status;
@@ -710,7 +707,7 @@ static void search_free(struct closure *cl)
bio_complete(s);
closure_debug_destroy(cl);
- mempool_free(s, s->d->c->search);
+ mempool_free(s, &s->d->c->search);
}
static inline struct search *search_alloc(struct bio *bio,
@@ -718,7 +715,7 @@ static inline struct search *search_alloc(struct bio *bio,
{
struct search *s;
- s = mempool_alloc(d->c->search, GFP_NOIO);
+ s = mempool_alloc(&d->c->search, GFP_NOIO);
closure_init(&s->cl, NULL);
do_bio_hook(s, bio, request_endio);
@@ -867,7 +864,7 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
s->cache_missed = 1;
if (s->cache_miss || s->iop.bypass) {
- miss = bio_next_split(bio, sectors, GFP_NOIO, s->d->bio_split);
+ miss = bio_next_split(bio, sectors, GFP_NOIO, &s->d->bio_split);
ret = miss == bio ? MAP_DONE : MAP_CONTINUE;
goto out_submit;
}
@@ -890,14 +887,14 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
s->iop.replace = true;
- miss = bio_next_split(bio, sectors, GFP_NOIO, s->d->bio_split);
+ miss = bio_next_split(bio, sectors, GFP_NOIO, &s->d->bio_split);
/* btree_search_recurse()'s btree iterator is no good anymore */
ret = miss == bio ? MAP_DONE : -EINTR;
cache_bio = bio_alloc_bioset(GFP_NOWAIT,
DIV_ROUND_UP(s->insert_bio_sectors, PAGE_SECTORS),
- dc->disk.bio_split);
+ &dc->disk.bio_split);
if (!cache_bio)
goto out_submit;
@@ -1011,7 +1008,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
struct bio *flush;
flush = bio_alloc_bioset(GFP_NOIO, 0,
- dc->disk.bio_split);
+ &dc->disk.bio_split);
if (!flush) {
s->iop.status = BLK_STS_RESOURCE;
goto insert_data;
@@ -1024,7 +1021,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
closure_bio_submit(s->iop.c, flush, cl);
}
} else {
- s->iop.bio = bio_clone_fast(bio, GFP_NOIO, dc->disk.bio_split);
+ s->iop.bio = bio_clone_fast(bio, GFP_NOIO, &dc->disk.bio_split);
/* I/O request sent to backing device */
bio->bi_end_io = backing_request_endio;
closure_bio_submit(s->iop.c, bio, cl);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index d90d9e5..a31e55b 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -37,24 +37,6 @@ static const char invalid_uuid[] = {
0xc8, 0x50, 0xfc, 0x5e, 0xcb, 0x16, 0xcd, 0x99
};
-/* Default is -1; we skip past it for struct cached_dev's cache mode */
-const char * const bch_cache_modes[] = {
- "default",
- "writethrough",
- "writeback",
- "writearound",
- "none",
- NULL
-};
-
-/* Default is -1; we skip past it for stop_when_cache_set_failed */
-const char * const bch_stop_on_failure_modes[] = {
- "default",
- "auto",
- "always",
- NULL
-};
-
static struct kobject *bcache_kobj;
struct mutex bch_register_lock;
LIST_HEAD(bch_cache_sets);
@@ -654,6 +636,11 @@ static int ioctl_dev(struct block_device *b, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
struct bcache_device *d = b->bd_disk->private_data;
+ struct cached_dev *dc = container_of(d, struct cached_dev, disk);
+
+ if (dc->io_disable)
+ return -EIO;
+
return d->ioctl(d, mode, cmd, arg);
}
@@ -766,8 +753,7 @@ static void bcache_device_free(struct bcache_device *d)
put_disk(d->disk);
}
- if (d->bio_split)
- bioset_free(d->bio_split);
+ bioset_exit(&d->bio_split);
kvfree(d->full_dirty_stripes);
kvfree(d->stripe_sectors_dirty);
@@ -809,9 +795,8 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
if (idx < 0)
return idx;
- if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio),
- BIOSET_NEED_BVECS |
- BIOSET_NEED_RESCUER)) ||
+ if (bioset_init(&d->bio_split, 4, offsetof(struct bbio, bio),
+ BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER) ||
!(d->disk = alloc_disk(BCACHE_MINORS))) {
ida_simple_remove(&bcache_device_idx, idx);
return -ENOMEM;
@@ -864,6 +849,44 @@ static void calc_cached_dev_sectors(struct cache_set *c)
c->cached_dev_sectors = sectors;
}
+#define BACKING_DEV_OFFLINE_TIMEOUT 5
+static int cached_dev_status_update(void *arg)
+{
+ struct cached_dev *dc = arg;
+ struct request_queue *q;
+
+ /*
+ * If this delayed worker is stopping outside, directly quit here.
+ * dc->io_disable might be set via sysfs interface, so check it
+ * here too.
+ */
+ while (!kthread_should_stop() && !dc->io_disable) {
+ q = bdev_get_queue(dc->bdev);
+ if (blk_queue_dying(q))
+ dc->offline_seconds++;
+ else
+ dc->offline_seconds = 0;
+
+ if (dc->offline_seconds >= BACKING_DEV_OFFLINE_TIMEOUT) {
+ pr_err("%s: device offline for %d seconds",
+ dc->backing_dev_name,
+ BACKING_DEV_OFFLINE_TIMEOUT);
+ pr_err("%s: disable I/O request due to backing "
+ "device offline", dc->disk.name);
+ dc->io_disable = true;
+ /* let others know earlier that io_disable is true */
+ smp_mb();
+ bcache_device_stop(&dc->disk);
+ break;
+ }
+ schedule_timeout_interruptible(HZ);
+ }
+
+ wait_for_kthread_stop();
+ return 0;
+}
+
+
void bch_cached_dev_run(struct cached_dev *dc)
{
struct bcache_device *d = &dc->disk;
@@ -906,6 +929,14 @@ void bch_cached_dev_run(struct cached_dev *dc)
if (sysfs_create_link(&d->kobj, &disk_to_dev(d->disk)->kobj, "dev") ||
sysfs_create_link(&disk_to_dev(d->disk)->kobj, &d->kobj, "bcache"))
pr_debug("error creating sysfs link");
+
+ dc->status_update_thread = kthread_run(cached_dev_status_update,
+ dc, "bcache_status_update");
+ if (IS_ERR(dc->status_update_thread)) {
+ pr_warn("failed to create bcache_status_update kthread, "
+ "continue to run without monitoring backing "
+ "device status");
+ }
}
/*
@@ -936,7 +967,6 @@ static void cancel_writeback_rate_update_dwork(struct cached_dev *dc)
static void cached_dev_detach_finish(struct work_struct *w)
{
struct cached_dev *dc = container_of(w, struct cached_dev, detach);
- char buf[BDEVNAME_SIZE];
struct closure cl;
closure_init_stack(&cl);
@@ -967,7 +997,7 @@ static void cached_dev_detach_finish(struct work_struct *w)
mutex_unlock(&bch_register_lock);
- pr_info("Caching disabled for %s", bdevname(dc->bdev, buf));
+ pr_info("Caching disabled for %s", dc->backing_dev_name);
/* Drop ref we took in cached_dev_detach() */
closure_put(&dc->disk.cl);
@@ -999,29 +1029,28 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
{
uint32_t rtime = cpu_to_le32(get_seconds());
struct uuid_entry *u;
- char buf[BDEVNAME_SIZE];
struct cached_dev *exist_dc, *t;
- bdevname(dc->bdev, buf);
-
if ((set_uuid && memcmp(set_uuid, c->sb.set_uuid, 16)) ||
(!set_uuid && memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16)))
return -ENOENT;
if (dc->disk.c) {
- pr_err("Can't attach %s: already attached", buf);
+ pr_err("Can't attach %s: already attached",
+ dc->backing_dev_name);
return -EINVAL;
}
if (test_bit(CACHE_SET_STOPPING, &c->flags)) {
- pr_err("Can't attach %s: shutting down", buf);
+ pr_err("Can't attach %s: shutting down",
+ dc->backing_dev_name);
return -EINVAL;
}
if (dc->sb.block_size < c->sb.block_size) {
/* Will die */
pr_err("Couldn't attach %s: block size less than set's block size",
- buf);
+ dc->backing_dev_name);
return -EINVAL;
}
@@ -1029,7 +1058,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
list_for_each_entry_safe(exist_dc, t, &c->cached_devs, list) {
if (!memcmp(dc->sb.uuid, exist_dc->sb.uuid, 16)) {
pr_err("Tried to attach %s but duplicate UUID already attached",
- buf);
+ dc->backing_dev_name);
return -EINVAL;
}
@@ -1047,13 +1076,15 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
if (!u) {
if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) {
- pr_err("Couldn't find uuid for %s in set", buf);
+ pr_err("Couldn't find uuid for %s in set",
+ dc->backing_dev_name);
return -ENOENT;
}
u = uuid_find_empty(c);
if (!u) {
- pr_err("Not caching %s, no room for UUID", buf);
+ pr_err("Not caching %s, no room for UUID",
+ dc->backing_dev_name);
return -EINVAL;
}
}
@@ -1112,7 +1143,8 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
up_write(&dc->writeback_lock);
pr_info("Caching %s as %s on set %pU",
- bdevname(dc->bdev, buf), dc->disk.disk->disk_name,
+ dc->backing_dev_name,
+ dc->disk.disk->disk_name,
dc->disk.c->sb.set_uuid);
return 0;
}
@@ -1138,6 +1170,8 @@ static void cached_dev_free(struct closure *cl)
kthread_stop(dc->writeback_thread);
if (dc->writeback_write_wq)
destroy_workqueue(dc->writeback_write_wq);
+ if (!IS_ERR_OR_NULL(dc->status_update_thread))
+ kthread_stop(dc->status_update_thread);
if (atomic_read(&dc->running))
bd_unlink_disk_holder(dc->bdev, dc->disk.disk);
@@ -1225,10 +1259,10 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
struct block_device *bdev,
struct cached_dev *dc)
{
- char name[BDEVNAME_SIZE];
const char *err = "cannot allocate memory";
struct cache_set *c;
+ bdevname(bdev, dc->backing_dev_name);
memcpy(&dc->sb, sb, sizeof(struct cache_sb));
dc->bdev = bdev;
dc->bdev->bd_holder = dc;
@@ -1237,6 +1271,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
bio_first_bvec_all(&dc->sb_bio)->bv_page = sb_page;
get_page(sb_page);
+
if (cached_dev_init(dc, sb->block_size << 9))
goto err;
@@ -1247,7 +1282,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
if (bch_cache_accounting_add_kobjs(&dc->accounting, &dc->disk.kobj))
goto err;
- pr_info("registered backing device %s", bdevname(bdev, name));
+ pr_info("registered backing device %s", dc->backing_dev_name);
list_add(&dc->list, &uncached_devices);
list_for_each_entry(c, &bch_cache_sets, list)
@@ -1259,7 +1294,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
return;
err:
- pr_notice("error %s: %s", bdevname(bdev, name), err);
+ pr_notice("error %s: %s", dc->backing_dev_name, err);
bcache_device_stop(&dc->disk);
}
@@ -1367,7 +1402,7 @@ int bch_flash_dev_create(struct cache_set *c, uint64_t size)
bool bch_cached_dev_error(struct cached_dev *dc)
{
- char name[BDEVNAME_SIZE];
+ struct cache_set *c;
if (!dc || test_bit(BCACHE_DEV_CLOSING, &dc->disk.flags))
return false;
@@ -1377,7 +1412,22 @@ bool bch_cached_dev_error(struct cached_dev *dc)
smp_mb();
pr_err("stop %s: too many IO errors on backing device %s\n",
- dc->disk.disk->disk_name, bdevname(dc->bdev, name));
+ dc->disk.disk->disk_name, dc->backing_dev_name);
+
+ /*
+ * If the cached device is still attached to a cache set,
+ * even dc->io_disable is true and no more I/O requests
+ * accepted, cache device internal I/O (writeback scan or
+ * garbage collection) may still prevent bcache device from
+ * being stopped. So here CACHE_SET_IO_DISABLE should be
+ * set to c->flags too, to make the internal I/O to cache
+ * device rejected and stopped immediately.
+ * If c is NULL, that means the bcache device is not attached
+ * to any cache set, then no CACHE_SET_IO_DISABLE bit to set.
+ */
+ c = dc->disk.c;
+ if (c && test_and_set_bit(CACHE_SET_IO_DISABLE, &c->flags))
+ pr_info("CACHE_SET_IO_DISABLE already set");
bcache_device_stop(&dc->disk);
return true;
@@ -1395,7 +1445,7 @@ bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...)
return false;
if (test_and_set_bit(CACHE_SET_IO_DISABLE, &c->flags))
- pr_warn("CACHE_SET_IO_DISABLE already set");
+ pr_info("CACHE_SET_IO_DISABLE already set");
/* XXX: we can be called from atomic context
acquire_console_sem();
@@ -1448,14 +1498,10 @@ static void cache_set_free(struct closure *cl)
if (c->moving_gc_wq)
destroy_workqueue(c->moving_gc_wq);
- if (c->bio_split)
- bioset_free(c->bio_split);
- if (c->fill_iter)
- mempool_destroy(c->fill_iter);
- if (c->bio_meta)
- mempool_destroy(c->bio_meta);
- if (c->search)
- mempool_destroy(c->search);
+ bioset_exit(&c->bio_split);
+ mempool_exit(&c->fill_iter);
+ mempool_exit(&c->bio_meta);
+ mempool_exit(&c->search);
kfree(c->devices);
mutex_lock(&bch_register_lock);
@@ -1539,6 +1585,20 @@ static void conditional_stop_bcache_device(struct cache_set *c,
*/
pr_warn("stop_when_cache_set_failed of %s is \"auto\" and cache is dirty, stop it to avoid potential data corruption.",
d->disk->disk_name);
+ /*
+ * There might be a small time gap that cache set is
+ * released but bcache device is not. Inside this time
+ * gap, regular I/O requests will directly go into
+ * backing device as no cache set attached to. This
+ * behavior may also introduce potential inconsistence
+ * data in writeback mode while cache is dirty.
+ * Therefore before calling bcache_device_stop() due
+ * to a broken cache device, dc->io_disable should be
+ * explicitly set to true.
+ */
+ dc->io_disable = true;
+ /* make others know io_disable is true earlier */
+ smp_mb();
bcache_device_stop(d);
} else {
/*
@@ -1652,21 +1712,17 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
INIT_LIST_HEAD(&c->btree_cache_freed);
INIT_LIST_HEAD(&c->data_buckets);
- c->search = mempool_create_slab_pool(32, bch_search_cache);
- if (!c->search)
- goto err;
-
iter_size = (sb->bucket_size / sb->block_size + 1) *
sizeof(struct btree_iter_set);
if (!(c->devices = kzalloc(c->nr_uuids * sizeof(void *), GFP_KERNEL)) ||
- !(c->bio_meta = mempool_create_kmalloc_pool(2,
- sizeof(struct bbio) + sizeof(struct bio_vec) *
- bucket_pages(c))) ||
- !(c->fill_iter = mempool_create_kmalloc_pool(1, iter_size)) ||
- !(c->bio_split = bioset_create(4, offsetof(struct bbio, bio),
- BIOSET_NEED_BVECS |
- BIOSET_NEED_RESCUER)) ||
+ mempool_init_slab_pool(&c->search, 32, bch_search_cache) ||
+ mempool_init_kmalloc_pool(&c->bio_meta, 2,
+ sizeof(struct bbio) + sizeof(struct bio_vec) *
+ bucket_pages(c)) ||
+ mempool_init_kmalloc_pool(&c->fill_iter, 1, iter_size) ||
+ bioset_init(&c->bio_split, 4, offsetof(struct bbio, bio),
+ BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER) ||
!(c->uuids = alloc_bucket_pages(GFP_KERNEL, c)) ||
!(c->moving_gc_wq = alloc_workqueue("bcache_gc",
WQ_MEM_RECLAIM, 0)) ||
@@ -2003,12 +2059,10 @@ static int cache_alloc(struct cache *ca)
static int register_cache(struct cache_sb *sb, struct page *sb_page,
struct block_device *bdev, struct cache *ca)
{
- char name[BDEVNAME_SIZE];
const char *err = NULL; /* must be set for any error case */
int ret = 0;
- bdevname(bdev, name);
-
+ bdevname(bdev, ca->cache_dev_name);
memcpy(&ca->sb, sb, sizeof(struct cache_sb));
ca->bdev = bdev;
ca->bdev->bd_holder = ca;
@@ -2045,14 +2099,14 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page,
goto out;
}
- pr_info("registered cache device %s", name);
+ pr_info("registered cache device %s", ca->cache_dev_name);
out:
kobject_put(&ca->kobj);
err:
if (err)
- pr_notice("error %s: %s", name, err);
+ pr_notice("error %s: %s", ca->cache_dev_name, err);
return ret;
}
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index dfeef58..8ccbc8f3 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -16,6 +16,22 @@
#include <linux/sort.h>
#include <linux/sched/clock.h>
+/* Default is -1; we skip past it for struct cached_dev's cache mode */
+static const char * const bch_cache_modes[] = {
+ "writethrough",
+ "writeback",
+ "writearound",
+ "none",
+ NULL
+};
+
+/* Default is -1; we skip past it for stop_when_cache_set_failed */
+static const char * const bch_stop_on_failure_modes[] = {
+ "auto",
+ "always",
+ NULL
+};
+
static const char * const cache_replacement_policies[] = {
"lru",
"fifo",
@@ -114,6 +130,20 @@ rw_attribute(btree_shrinker_disabled);
rw_attribute(copy_gc_enabled);
rw_attribute(size);
+static ssize_t bch_snprint_string_list(char *buf, size_t size, const char * const list[],
+ size_t selected)
+{
+ char *out = buf;
+ size_t i;
+
+ for (i = 0; list[i]; i++)
+ out += snprintf(out, buf + size - out,
+ i == selected ? "[%s] " : "%s ", list[i]);
+
+ out[-1] = '\n';
+ return out - buf;
+}
+
SHOW(__bch_cached_dev)
{
struct cached_dev *dc = container_of(kobj, struct cached_dev,
@@ -124,12 +154,12 @@ SHOW(__bch_cached_dev)
if (attr == &sysfs_cache_mode)
return bch_snprint_string_list(buf, PAGE_SIZE,
- bch_cache_modes + 1,
+ bch_cache_modes,
BDEV_CACHE_MODE(&dc->sb));
if (attr == &sysfs_stop_when_cache_set_failed)
return bch_snprint_string_list(buf, PAGE_SIZE,
- bch_stop_on_failure_modes + 1,
+ bch_stop_on_failure_modes,
dc->stop_when_cache_set_failed);
@@ -253,8 +283,7 @@ STORE(__cached_dev)
bch_cached_dev_run(dc);
if (attr == &sysfs_cache_mode) {
- v = bch_read_string_list(buf, bch_cache_modes + 1);
-
+ v = __sysfs_match_string(bch_cache_modes, -1, buf);
if (v < 0)
return v;
@@ -265,8 +294,7 @@ STORE(__cached_dev)
}
if (attr == &sysfs_stop_when_cache_set_failed) {
- v = bch_read_string_list(buf, bch_stop_on_failure_modes + 1);
-
+ v = __sysfs_match_string(bch_stop_on_failure_modes, -1, buf);
if (v < 0)
return v;
@@ -635,6 +663,7 @@ SHOW_LOCKED(bch_cache_set)
STORE(__bch_cache_set)
{
struct cache_set *c = container_of(kobj, struct cache_set, kobj);
+ ssize_t v;
if (attr == &sysfs_unregister)
bch_cache_set_unregister(c);
@@ -698,8 +727,7 @@ STORE(__bch_cache_set)
c->congested_write_threshold_us);
if (attr == &sysfs_errors) {
- ssize_t v = bch_read_string_list(buf, error_actions);
-
+ v = __sysfs_match_string(error_actions, -1, buf);
if (v < 0)
return v;
@@ -714,8 +742,7 @@ STORE(__bch_cache_set)
c->error_decay = strtoul_or_return(buf) / 88;
if (attr == &sysfs_io_disable) {
- int v = strtoul_or_return(buf);
-
+ v = strtoul_or_return(buf);
if (v) {
if (test_and_set_bit(CACHE_SET_IO_DISABLE,
&c->flags))
@@ -929,6 +956,7 @@ SHOW_LOCKED(bch_cache)
STORE(__bch_cache)
{
struct cache *ca = container_of(kobj, struct cache, kobj);
+ ssize_t v;
if (attr == &sysfs_discard) {
bool v = strtoul_or_return(buf);
@@ -943,8 +971,7 @@ STORE(__bch_cache)
}
if (attr == &sysfs_cache_replacement_policy) {
- ssize_t v = bch_read_string_list(buf, cache_replacement_policies);
-
+ v = __sysfs_match_string(cache_replacement_policies, -1, buf);
if (v < 0)
return v;
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index 74febd5..fc479b0 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -120,41 +120,6 @@ ssize_t bch_hprint(char *buf, int64_t v)
return sprintf(buf, "%llu.%i%c", q, t * 10 / 1024, units[u]);
}
-ssize_t bch_snprint_string_list(char *buf, size_t size, const char * const list[],
- size_t selected)
-{
- char *out = buf;
- size_t i;
-
- for (i = 0; list[i]; i++)
- out += snprintf(out, buf + size - out,
- i == selected ? "[%s] " : "%s ", list[i]);
-
- out[-1] = '\n';
- return out - buf;
-}
-
-ssize_t bch_read_string_list(const char *buf, const char * const list[])
-{
- size_t i;
- char *s, *d = kstrndup(buf, PAGE_SIZE - 1, GFP_KERNEL);
- if (!d)
- return -ENOMEM;
-
- s = strim(d);
-
- for (i = 0; list[i]; i++)
- if (!strcmp(list[i], s))
- break;
-
- kfree(d);
-
- if (!list[i])
- return -EINVAL;
-
- return i;
-}
-
bool bch_is_zero(const char *p, size_t n)
{
size_t i;
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 2680245..cced87f 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -365,11 +365,6 @@ ssize_t bch_hprint(char *buf, int64_t v);
bool bch_is_zero(const char *p, size_t n);
int bch_parse_uuid(const char *s, char *uuid);
-ssize_t bch_snprint_string_list(char *buf, size_t size, const char * const list[],
- size_t selected);
-
-ssize_t bch_read_string_list(const char *buf, const char * const list[]);
-
struct time_stats {
spinlock_t lock;
/*
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 4a9547c..ad45ebe 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -244,8 +244,10 @@ static void dirty_endio(struct bio *bio)
struct keybuf_key *w = bio->bi_private;
struct dirty_io *io = w->private;
- if (bio->bi_status)
+ if (bio->bi_status) {
SET_KEY_DIRTY(&w->key, false);
+ bch_count_backing_io_errors(io->dc, bio);
+ }
closure_put(&io->cl);
}
diff --git a/drivers/md/dm-bio-prison-v1.c b/drivers/md/dm-bio-prison-v1.c
index 874841f..e794e36 100644
--- a/drivers/md/dm-bio-prison-v1.c
+++ b/drivers/md/dm-bio-prison-v1.c
@@ -19,7 +19,7 @@
struct dm_bio_prison {
spinlock_t lock;
- mempool_t *cell_pool;
+ mempool_t cell_pool;
struct rb_root cells;
};
@@ -33,15 +33,16 @@ static struct kmem_cache *_cell_cache;
*/
struct dm_bio_prison *dm_bio_prison_create(void)
{
- struct dm_bio_prison *prison = kmalloc(sizeof(*prison), GFP_KERNEL);
+ struct dm_bio_prison *prison = kzalloc(sizeof(*prison), GFP_KERNEL);
+ int ret;
if (!prison)
return NULL;
spin_lock_init(&prison->lock);
- prison->cell_pool = mempool_create_slab_pool(MIN_CELLS, _cell_cache);
- if (!prison->cell_pool) {
+ ret = mempool_init_slab_pool(&prison->cell_pool, MIN_CELLS, _cell_cache);
+ if (ret) {
kfree(prison);
return NULL;
}
@@ -54,21 +55,21 @@ EXPORT_SYMBOL_GPL(dm_bio_prison_create);
void dm_bio_prison_destroy(struct dm_bio_prison *prison)
{
- mempool_destroy(prison->cell_pool);
+ mempool_exit(&prison->cell_pool);
kfree(prison);
}
EXPORT_SYMBOL_GPL(dm_bio_prison_destroy);
struct dm_bio_prison_cell *dm_bio_prison_alloc_cell(struct dm_bio_prison *prison, gfp_t gfp)
{
- return mempool_alloc(prison->cell_pool, gfp);
+ return mempool_alloc(&prison->cell_pool, gfp);
}
EXPORT_SYMBOL_GPL(dm_bio_prison_alloc_cell);
void dm_bio_prison_free_cell(struct dm_bio_prison *prison,
struct dm_bio_prison_cell *cell)
{
- mempool_free(cell, prison->cell_pool);
+ mempool_free(cell, &prison->cell_pool);
}
EXPORT_SYMBOL_GPL(dm_bio_prison_free_cell);
diff --git a/drivers/md/dm-bio-prison-v2.c b/drivers/md/dm-bio-prison-v2.c
index 8ce3a1a..f866bc9 100644
--- a/drivers/md/dm-bio-prison-v2.c
+++ b/drivers/md/dm-bio-prison-v2.c
@@ -21,7 +21,7 @@ struct dm_bio_prison_v2 {
struct workqueue_struct *wq;
spinlock_t lock;
- mempool_t *cell_pool;
+ mempool_t cell_pool;
struct rb_root cells;
};
@@ -35,7 +35,8 @@ static struct kmem_cache *_cell_cache;
*/
struct dm_bio_prison_v2 *dm_bio_prison_create_v2(struct workqueue_struct *wq)
{
- struct dm_bio_prison_v2 *prison = kmalloc(sizeof(*prison), GFP_KERNEL);
+ struct dm_bio_prison_v2 *prison = kzalloc(sizeof(*prison), GFP_KERNEL);
+ int ret;
if (!prison)
return NULL;
@@ -43,8 +44,8 @@ struct dm_bio_prison_v2 *dm_bio_prison_create_v2(struct workqueue_struct *wq)
prison->wq = wq;
spin_lock_init(&prison->lock);
- prison->cell_pool = mempool_create_slab_pool(MIN_CELLS, _cell_cache);
- if (!prison->cell_pool) {
+ ret = mempool_init_slab_pool(&prison->cell_pool, MIN_CELLS, _cell_cache);
+ if (ret) {
kfree(prison);
return NULL;
}
@@ -57,21 +58,21 @@ EXPORT_SYMBOL_GPL(dm_bio_prison_create_v2);
void dm_bio_prison_destroy_v2(struct dm_bio_prison_v2 *prison)
{
- mempool_destroy(prison->cell_pool);
+ mempool_exit(&prison->cell_pool);
kfree(prison);
}
EXPORT_SYMBOL_GPL(dm_bio_prison_destroy_v2);
struct dm_bio_prison_cell_v2 *dm_bio_prison_alloc_cell_v2(struct dm_bio_prison_v2 *prison, gfp_t gfp)
{
- return mempool_alloc(prison->cell_pool, gfp);
+ return mempool_alloc(&prison->cell_pool, gfp);
}
EXPORT_SYMBOL_GPL(dm_bio_prison_alloc_cell_v2);
void dm_bio_prison_free_cell_v2(struct dm_bio_prison_v2 *prison,
struct dm_bio_prison_cell_v2 *cell)
{
- mempool_free(cell, prison->cell_pool);
+ mempool_free(cell, &prison->cell_pool);
}
EXPORT_SYMBOL_GPL(dm_bio_prison_free_cell_v2);
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 12aa9ca..dc385b7 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1681,8 +1681,9 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign
if (block_size <= KMALLOC_MAX_SIZE &&
(block_size < PAGE_SIZE || !is_power_of_2(block_size))) {
- snprintf(slab_name, sizeof slab_name, "dm_bufio_cache-%u", c->block_size);
- c->slab_cache = kmem_cache_create(slab_name, c->block_size, ARCH_KMALLOC_MINALIGN,
+ unsigned align = min(1U << __ffs(block_size), (unsigned)PAGE_SIZE);
+ snprintf(slab_name, sizeof slab_name, "dm_bufio_cache-%u", block_size);
+ c->slab_cache = kmem_cache_create(slab_name, block_size, align,
SLAB_RECLAIM_ACCOUNT, NULL);
if (!c->slab_cache) {
r = -ENOMEM;
diff --git a/drivers/md/dm-cache-background-tracker.c b/drivers/md/dm-cache-background-tracker.c
index 1d0af0a..84814e8 100644
--- a/drivers/md/dm-cache-background-tracker.c
+++ b/drivers/md/dm-cache-background-tracker.c
@@ -166,7 +166,7 @@ static bool max_work_reached(struct background_tracker *b)
atomic_read(&b->pending_demotes) >= b->max_work;
}
-struct bt_work *alloc_work(struct background_tracker *b)
+static struct bt_work *alloc_work(struct background_tracker *b)
{
if (max_work_reached(b))
return NULL;
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index da20863..001c712 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -447,9 +447,9 @@ struct cache {
struct work_struct migration_worker;
struct delayed_work waker;
struct dm_bio_prison_v2 *prison;
- struct bio_set *bs;
+ struct bio_set bs;
- mempool_t *migration_pool;
+ mempool_t migration_pool;
struct dm_cache_policy *policy;
unsigned policy_nr_args;
@@ -550,7 +550,7 @@ static struct dm_cache_migration *alloc_migration(struct cache *cache)
{
struct dm_cache_migration *mg;
- mg = mempool_alloc(cache->migration_pool, GFP_NOWAIT);
+ mg = mempool_alloc(&cache->migration_pool, GFP_NOWAIT);
if (!mg)
return NULL;
@@ -569,7 +569,7 @@ static void free_migration(struct dm_cache_migration *mg)
if (atomic_dec_and_test(&cache->nr_allocated_migrations))
wake_up(&cache->migration_wait);
- mempool_free(mg, cache->migration_pool);
+ mempool_free(mg, &cache->migration_pool);
}
/*----------------------------------------------------------------*/
@@ -924,7 +924,7 @@ static void issue_op(struct bio *bio, void *context)
static void remap_to_origin_and_cache(struct cache *cache, struct bio *bio,
dm_oblock_t oblock, dm_cblock_t cblock)
{
- struct bio *origin_bio = bio_clone_fast(bio, GFP_NOIO, cache->bs);
+ struct bio *origin_bio = bio_clone_fast(bio, GFP_NOIO, &cache->bs);
BUG_ON(!origin_bio);
@@ -2011,7 +2011,7 @@ static void destroy(struct cache *cache)
{
unsigned i;
- mempool_destroy(cache->migration_pool);
+ mempool_exit(&cache->migration_pool);
if (cache->prison)
dm_bio_prison_destroy_v2(cache->prison);
@@ -2047,8 +2047,7 @@ static void destroy(struct cache *cache)
kfree(cache->ctr_args[i]);
kfree(cache->ctr_args);
- if (cache->bs)
- bioset_free(cache->bs);
+ bioset_exit(&cache->bs);
kfree(cache);
}
@@ -2498,8 +2497,8 @@ static int cache_create(struct cache_args *ca, struct cache **result)
cache->features = ca->features;
if (writethrough_mode(cache)) {
/* Create bioset for writethrough bios issued to origin */
- cache->bs = bioset_create(BIO_POOL_SIZE, 0, 0);
- if (!cache->bs)
+ r = bioset_init(&cache->bs, BIO_POOL_SIZE, 0, 0);
+ if (r)
goto bad;
}
@@ -2630,9 +2629,9 @@ static int cache_create(struct cache_args *ca, struct cache **result)
goto bad;
}
- cache->migration_pool = mempool_create_slab_pool(MIGRATION_POOL_SIZE,
- migration_cache);
- if (!cache->migration_pool) {
+ r = mempool_init_slab_pool(&cache->migration_pool, MIGRATION_POOL_SIZE,
+ migration_cache);
+ if (r) {
*error = "Error creating cache's migration mempool";
goto bad;
}
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 3222e21..f21c5d2 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -91,8 +91,8 @@ struct mapped_device {
/*
* io objects are allocated from here.
*/
- struct bio_set *io_bs;
- struct bio_set *bs;
+ struct bio_set io_bs;
+ struct bio_set bs;
/*
* freeze/thaw support require holding onto a super block
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 44ff473..da02f4d 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -143,14 +143,14 @@ struct crypt_config {
* pool for per bio private data, crypto requests,
* encryption requeusts/buffer pages and integrity tags
*/
- mempool_t *req_pool;
- mempool_t *page_pool;
- mempool_t *tag_pool;
+ mempool_t req_pool;
+ mempool_t page_pool;
+ mempool_t tag_pool;
unsigned tag_pool_max_sectors;
struct percpu_counter n_allocated_pages;
- struct bio_set *bs;
+ struct bio_set bs;
struct mutex bio_alloc_lock;
struct workqueue_struct *io_queue;
@@ -1245,7 +1245,7 @@ static void crypt_alloc_req_skcipher(struct crypt_config *cc,
unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1);
if (!ctx->r.req)
- ctx->r.req = mempool_alloc(cc->req_pool, GFP_NOIO);
+ ctx->r.req = mempool_alloc(&cc->req_pool, GFP_NOIO);
skcipher_request_set_tfm(ctx->r.req, cc->cipher_tfm.tfms[key_index]);
@@ -1262,7 +1262,7 @@ static void crypt_alloc_req_aead(struct crypt_config *cc,
struct convert_context *ctx)
{
if (!ctx->r.req_aead)
- ctx->r.req_aead = mempool_alloc(cc->req_pool, GFP_NOIO);
+ ctx->r.req_aead = mempool_alloc(&cc->req_pool, GFP_NOIO);
aead_request_set_tfm(ctx->r.req_aead, cc->cipher_tfm.tfms_aead[0]);
@@ -1290,7 +1290,7 @@ static void crypt_free_req_skcipher(struct crypt_config *cc,
struct dm_crypt_io *io = dm_per_bio_data(base_bio, cc->per_bio_data_size);
if ((struct skcipher_request *)(io + 1) != req)
- mempool_free(req, cc->req_pool);
+ mempool_free(req, &cc->req_pool);
}
static void crypt_free_req_aead(struct crypt_config *cc,
@@ -1299,7 +1299,7 @@ static void crypt_free_req_aead(struct crypt_config *cc,
struct dm_crypt_io *io = dm_per_bio_data(base_bio, cc->per_bio_data_size);
if ((struct aead_request *)(io + 1) != req)
- mempool_free(req, cc->req_pool);
+ mempool_free(req, &cc->req_pool);
}
static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_bio)
@@ -1409,7 +1409,7 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size)
if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM))
mutex_lock(&cc->bio_alloc_lock);
- clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, cc->bs);
+ clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, &cc->bs);
if (!clone)
goto out;
@@ -1418,7 +1418,7 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size)
remaining_size = size;
for (i = 0; i < nr_iovecs; i++) {
- page = mempool_alloc(cc->page_pool, gfp_mask);
+ page = mempool_alloc(&cc->page_pool, gfp_mask);
if (!page) {
crypt_free_buffer_pages(cc, clone);
bio_put(clone);
@@ -1453,7 +1453,7 @@ static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone)
bio_for_each_segment_all(bv, clone, i) {
BUG_ON(!bv->bv_page);
- mempool_free(bv->bv_page, cc->page_pool);
+ mempool_free(bv->bv_page, &cc->page_pool);
}
}
@@ -1492,7 +1492,7 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
crypt_free_req(cc, io->ctx.r.req, base_bio);
if (unlikely(io->integrity_metadata_from_pool))
- mempool_free(io->integrity_metadata, io->cc->tag_pool);
+ mempool_free(io->integrity_metadata, &io->cc->tag_pool);
else
kfree(io->integrity_metadata);
@@ -1565,7 +1565,7 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
* biovecs we don't need to worry about the block layer
* modifying the biovec array; so leverage bio_clone_fast().
*/
- clone = bio_clone_fast(io->base_bio, gfp, cc->bs);
+ clone = bio_clone_fast(io->base_bio, gfp, &cc->bs);
if (!clone)
return 1;
@@ -2219,15 +2219,13 @@ static void crypt_dtr(struct dm_target *ti)
crypt_free_tfms(cc);
- if (cc->bs)
- bioset_free(cc->bs);
+ bioset_exit(&cc->bs);
- mempool_destroy(cc->page_pool);
- mempool_destroy(cc->req_pool);
- mempool_destroy(cc->tag_pool);
+ mempool_exit(&cc->page_pool);
+ mempool_exit(&cc->req_pool);
+ mempool_exit(&cc->tag_pool);
- if (cc->page_pool)
- WARN_ON(percpu_counter_sum(&cc->n_allocated_pages) != 0);
+ WARN_ON(percpu_counter_sum(&cc->n_allocated_pages) != 0);
percpu_counter_destroy(&cc->n_allocated_pages);
if (cc->iv_gen_ops && cc->iv_gen_ops->dtr)
@@ -2743,8 +2741,6 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
iv_size_padding = align_mask;
}
- ret = -ENOMEM;
-
/* ...| IV + padding | original IV | original sec. number | bio tag offset | */
additional_req_size = sizeof(struct dm_crypt_request) +
iv_size_padding + cc->iv_size +
@@ -2752,8 +2748,8 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
sizeof(uint64_t) +
sizeof(unsigned int);
- cc->req_pool = mempool_create_kmalloc_pool(MIN_IOS, cc->dmreq_start + additional_req_size);
- if (!cc->req_pool) {
+ ret = mempool_init_kmalloc_pool(&cc->req_pool, MIN_IOS, cc->dmreq_start + additional_req_size);
+ if (ret) {
ti->error = "Cannot allocate crypt request mempool";
goto bad;
}
@@ -2762,14 +2758,14 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
ALIGN(sizeof(struct dm_crypt_io) + cc->dmreq_start + additional_req_size,
ARCH_KMALLOC_MINALIGN);
- cc->page_pool = mempool_create(BIO_MAX_PAGES, crypt_page_alloc, crypt_page_free, cc);
- if (!cc->page_pool) {
+ ret = mempool_init(&cc->page_pool, BIO_MAX_PAGES, crypt_page_alloc, crypt_page_free, cc);
+ if (ret) {
ti->error = "Cannot allocate page mempool";
goto bad;
}
- cc->bs = bioset_create(MIN_IOS, 0, BIOSET_NEED_BVECS);
- if (!cc->bs) {
+ ret = bioset_init(&cc->bs, MIN_IOS, 0, BIOSET_NEED_BVECS);
+ if (ret) {
ti->error = "Cannot allocate crypt bioset";
goto bad;
}
@@ -2806,11 +2802,10 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
if (!cc->tag_pool_max_sectors)
cc->tag_pool_max_sectors = 1;
- cc->tag_pool = mempool_create_kmalloc_pool(MIN_IOS,
+ ret = mempool_init_kmalloc_pool(&cc->tag_pool, MIN_IOS,
cc->tag_pool_max_sectors * cc->on_disk_tag_size);
- if (!cc->tag_pool) {
+ if (ret) {
ti->error = "Cannot allocate integrity tags mempool";
- ret = -ENOMEM;
goto bad;
}
@@ -2903,7 +2898,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN)))) {
if (bio_sectors(bio) > cc->tag_pool_max_sectors)
dm_accept_partial_bio(bio, cc->tag_pool_max_sectors);
- io->integrity_metadata = mempool_alloc(cc->tag_pool, GFP_NOIO);
+ io->integrity_metadata = mempool_alloc(&cc->tag_pool, GFP_NOIO);
io->integrity_metadata_from_pool = true;
}
}
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 77d9fe5..fc68c7a 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -142,7 +142,7 @@ struct dm_integrity_c {
unsigned tag_size;
__s8 log2_tag_size;
sector_t start;
- mempool_t *journal_io_mempool;
+ mempool_t journal_io_mempool;
struct dm_io_client *io;
struct dm_bufio_client *bufio;
struct workqueue_struct *metadata_wq;
@@ -1817,7 +1817,7 @@ static void complete_copy_from_journal(unsigned long error, void *context)
struct journal_completion *comp = io->comp;
struct dm_integrity_c *ic = comp->ic;
remove_range(ic, &io->range);
- mempool_free(io, ic->journal_io_mempool);
+ mempool_free(io, &ic->journal_io_mempool);
if (unlikely(error != 0))
dm_integrity_io_error(ic, "copying from journal", -EIO);
complete_journal_op(comp);
@@ -1886,7 +1886,7 @@ static void do_journal_write(struct dm_integrity_c *ic, unsigned write_start,
}
next_loop = k - 1;
- io = mempool_alloc(ic->journal_io_mempool, GFP_NOIO);
+ io = mempool_alloc(&ic->journal_io_mempool, GFP_NOIO);
io->comp = ∁
io->range.logical_sector = sec;
io->range.n_sectors = (k - j) << ic->sb->log2_sectors_per_block;
@@ -1918,7 +1918,7 @@ static void do_journal_write(struct dm_integrity_c *ic, unsigned write_start,
if (j == k) {
remove_range_unlocked(ic, &io->range);
spin_unlock_irq(&ic->endio_wait.lock);
- mempool_free(io, ic->journal_io_mempool);
+ mempool_free(io, &ic->journal_io_mempool);
goto skip_io;
}
for (l = j; l < k; l++) {
@@ -2440,7 +2440,7 @@ static void dm_integrity_free_journal_scatterlist(struct dm_integrity_c *ic, str
unsigned i;
for (i = 0; i < ic->journal_sections; i++)
kvfree(sl[i]);
- kfree(sl);
+ kvfree(sl);
}
static struct scatterlist **dm_integrity_alloc_journal_scatterlist(struct dm_integrity_c *ic, struct page_list *pl)
@@ -2980,9 +2980,8 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
goto bad;
}
- ic->journal_io_mempool = mempool_create_slab_pool(JOURNAL_IO_MEMPOOL, journal_io_cache);
- if (!ic->journal_io_mempool) {
- r = -ENOMEM;
+ r = mempool_init_slab_pool(&ic->journal_io_mempool, JOURNAL_IO_MEMPOOL, journal_io_cache);
+ if (r) {
ti->error = "Cannot allocate mempool";
goto bad;
}
@@ -3196,7 +3195,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
destroy_workqueue(ic->writer_wq);
if (ic->bufio)
dm_bufio_client_destroy(ic->bufio);
- mempool_destroy(ic->journal_io_mempool);
+ mempool_exit(&ic->journal_io_mempool);
if (ic->io)
dm_io_client_destroy(ic->io);
if (ic->dev)
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index a8d914d..81ffc59 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -22,8 +22,8 @@
#define DM_IO_MAX_REGIONS BITS_PER_LONG
struct dm_io_client {
- mempool_t *pool;
- struct bio_set *bios;
+ mempool_t pool;
+ struct bio_set bios;
};
/*
@@ -49,32 +49,33 @@ struct dm_io_client *dm_io_client_create(void)
{
struct dm_io_client *client;
unsigned min_ios = dm_get_reserved_bio_based_ios();
+ int ret;
- client = kmalloc(sizeof(*client), GFP_KERNEL);
+ client = kzalloc(sizeof(*client), GFP_KERNEL);
if (!client)
return ERR_PTR(-ENOMEM);
- client->pool = mempool_create_slab_pool(min_ios, _dm_io_cache);
- if (!client->pool)
+ ret = mempool_init_slab_pool(&client->pool, min_ios, _dm_io_cache);
+ if (ret)
goto bad;
- client->bios = bioset_create(min_ios, 0, BIOSET_NEED_BVECS);
- if (!client->bios)
+ ret = bioset_init(&client->bios, min_ios, 0, BIOSET_NEED_BVECS);
+ if (ret)
goto bad;
return client;
bad:
- mempool_destroy(client->pool);
+ mempool_exit(&client->pool);
kfree(client);
- return ERR_PTR(-ENOMEM);
+ return ERR_PTR(ret);
}
EXPORT_SYMBOL(dm_io_client_create);
void dm_io_client_destroy(struct dm_io_client *client)
{
- mempool_destroy(client->pool);
- bioset_free(client->bios);
+ mempool_exit(&client->pool);
+ bioset_exit(&client->bios);
kfree(client);
}
EXPORT_SYMBOL(dm_io_client_destroy);
@@ -120,7 +121,7 @@ static void complete_io(struct io *io)
invalidate_kernel_vmap_range(io->vma_invalidate_address,
io->vma_invalidate_size);
- mempool_free(io, io->client->pool);
+ mempool_free(io, &io->client->pool);
fn(error_bits, context);
}
@@ -344,7 +345,7 @@ static void do_region(int op, int op_flags, unsigned region,
dm_sector_div_up(remaining, (PAGE_SIZE >> SECTOR_SHIFT)));
}
- bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, io->client->bios);
+ bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, &io->client->bios);
bio->bi_iter.bi_sector = where->sector + (where->count - remaining);
bio_set_dev(bio, where->bdev);
bio->bi_end_io = endio;
@@ -442,7 +443,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
init_completion(&sio.wait);
- io = mempool_alloc(client->pool, GFP_NOIO);
+ io = mempool_alloc(&client->pool, GFP_NOIO);
io->error_bits = 0;
atomic_set(&io->count, 1); /* see dispatch_io() */
io->client = client;
@@ -474,7 +475,7 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions,
return -EIO;
}
- io = mempool_alloc(client->pool, GFP_NOIO);
+ io = mempool_alloc(&client->pool, GFP_NOIO);
io->error_bits = 0;
atomic_set(&io->count, 1); /* see dispatch_io() */
io->client = client;
diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index e6e7c68..ce7efc7 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -47,7 +47,7 @@ struct dm_kcopyd_client {
wait_queue_head_t destroyq;
atomic_t nr_jobs;
- mempool_t *job_pool;
+ mempool_t job_pool;
struct workqueue_struct *kcopyd_wq;
struct work_struct kcopyd_work;
@@ -479,7 +479,7 @@ static int run_complete_job(struct kcopyd_job *job)
*/
if (job->master_job == job) {
mutex_destroy(&job->lock);
- mempool_free(job, kc->job_pool);
+ mempool_free(job, &kc->job_pool);
}
fn(read_err, write_err, context);
@@ -751,7 +751,7 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from,
* Allocate an array of jobs consisting of one master job
* followed by SPLIT_COUNT sub jobs.
*/
- job = mempool_alloc(kc->job_pool, GFP_NOIO);
+ job = mempool_alloc(&kc->job_pool, GFP_NOIO);
mutex_init(&job->lock);
/*
@@ -835,7 +835,7 @@ void *dm_kcopyd_prepare_callback(struct dm_kcopyd_client *kc,
{
struct kcopyd_job *job;
- job = mempool_alloc(kc->job_pool, GFP_NOIO);
+ job = mempool_alloc(&kc->job_pool, GFP_NOIO);
memset(job, 0, sizeof(struct kcopyd_job));
job->kc = kc;
@@ -879,10 +879,10 @@ int kcopyd_cancel(struct kcopyd_job *job, int block)
*---------------------------------------------------------------*/
struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *throttle)
{
- int r = -ENOMEM;
+ int r;
struct dm_kcopyd_client *kc;
- kc = kmalloc(sizeof(*kc), GFP_KERNEL);
+ kc = kzalloc(sizeof(*kc), GFP_KERNEL);
if (!kc)
return ERR_PTR(-ENOMEM);
@@ -892,14 +892,16 @@ struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *thro
INIT_LIST_HEAD(&kc->pages_jobs);
kc->throttle = throttle;
- kc->job_pool = mempool_create_slab_pool(MIN_JOBS, _job_cache);
- if (!kc->job_pool)
+ r = mempool_init_slab_pool(&kc->job_pool, MIN_JOBS, _job_cache);
+ if (r)
goto bad_slab;
INIT_WORK(&kc->kcopyd_work, do_work);
kc->kcopyd_wq = alloc_workqueue("kcopyd", WQ_MEM_RECLAIM, 0);
- if (!kc->kcopyd_wq)
+ if (!kc->kcopyd_wq) {
+ r = -ENOMEM;
goto bad_workqueue;
+ }
kc->pages = NULL;
kc->nr_reserved_pages = kc->nr_free_pages = 0;
@@ -923,7 +925,7 @@ struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *thro
bad_client_pages:
destroy_workqueue(kc->kcopyd_wq);
bad_workqueue:
- mempool_destroy(kc->job_pool);
+ mempool_exit(&kc->job_pool);
bad_slab:
kfree(kc);
@@ -942,7 +944,7 @@ void dm_kcopyd_client_destroy(struct dm_kcopyd_client *kc)
destroy_workqueue(kc->kcopyd_wq);
dm_io_client_destroy(kc->io_client);
client_free_pages(kc);
- mempool_destroy(kc->job_pool);
+ mempool_exit(&kc->job_pool);
kfree(kc);
}
EXPORT_SYMBOL(dm_kcopyd_client_destroy);
diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c
index 53b7b06d..52090be 100644
--- a/drivers/md/dm-log-userspace-base.c
+++ b/drivers/md/dm-log-userspace-base.c
@@ -76,7 +76,7 @@ struct log_c {
*/
uint32_t integrated_flush;
- mempool_t *flush_entry_pool;
+ mempool_t flush_entry_pool;
};
static struct kmem_cache *_flush_entry_cache;
@@ -249,11 +249,10 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
goto out;
}
- lc->flush_entry_pool = mempool_create_slab_pool(FLUSH_ENTRY_POOL_SIZE,
- _flush_entry_cache);
- if (!lc->flush_entry_pool) {
+ r = mempool_init_slab_pool(&lc->flush_entry_pool, FLUSH_ENTRY_POOL_SIZE,
+ _flush_entry_cache);
+ if (r) {
DMERR("Failed to create flush_entry_pool");
- r = -ENOMEM;
goto out;
}
@@ -313,7 +312,7 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
out:
kfree(devices_rdata);
if (r) {
- mempool_destroy(lc->flush_entry_pool);
+ mempool_exit(&lc->flush_entry_pool);
kfree(lc);
kfree(ctr_str);
} else {
@@ -342,7 +341,7 @@ static void userspace_dtr(struct dm_dirty_log *log)
if (lc->log_dev)
dm_put_device(lc->ti, lc->log_dev);
- mempool_destroy(lc->flush_entry_pool);
+ mempool_exit(&lc->flush_entry_pool);
kfree(lc->usr_argv_str);
kfree(lc);
@@ -570,7 +569,7 @@ static int userspace_flush(struct dm_dirty_log *log)
int mark_list_is_empty;
int clear_list_is_empty;
struct dm_dirty_log_flush_entry *fe, *tmp_fe;
- mempool_t *flush_entry_pool = lc->flush_entry_pool;
+ mempool_t *flush_entry_pool = &lc->flush_entry_pool;
spin_lock_irqsave(&lc->flush_lock, flags);
list_splice_init(&lc->mark_list, &mark_list);
@@ -653,7 +652,7 @@ static void userspace_mark_region(struct dm_dirty_log *log, region_t region)
struct dm_dirty_log_flush_entry *fe;
/* Wait for an allocation, but _never_ fail */
- fe = mempool_alloc(lc->flush_entry_pool, GFP_NOIO);
+ fe = mempool_alloc(&lc->flush_entry_pool, GFP_NOIO);
BUG_ON(!fe);
spin_lock_irqsave(&lc->flush_lock, flags);
@@ -687,7 +686,7 @@ static void userspace_clear_region(struct dm_dirty_log *log, region_t region)
* to cause the region to be resync'ed when the
* device is activated next time.
*/
- fe = mempool_alloc(lc->flush_entry_pool, GFP_ATOMIC);
+ fe = mempool_alloc(&lc->flush_entry_pool, GFP_ATOMIC);
if (!fe) {
DMERR("Failed to allocate memory to clear region.");
return;
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 203a041..d94ba6f 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -520,7 +520,8 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
bdev = pgpath->path.dev->bdev;
q = bdev_get_queue(bdev);
- clone = blk_get_request(q, rq->cmd_flags | REQ_NOMERGE, GFP_ATOMIC);
+ clone = blk_get_request(q, rq->cmd_flags | REQ_NOMERGE,
+ BLK_MQ_REQ_NOWAIT);
if (IS_ERR(clone)) {
/* EBUSY, ENODEV or EWOULDBLOCK: requeue */
if (blk_queue_dying(q)) {
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 580c49c..5903e49 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -23,6 +23,8 @@
#define MAX_RECOVERY 1 /* Maximum number of regions recovered in parallel. */
+#define MAX_NR_MIRRORS (DM_KCOPYD_MAX_REGIONS + 1)
+
#define DM_RAID1_HANDLE_ERRORS 0x01
#define DM_RAID1_KEEP_LOG 0x02
#define errors_handled(p) ((p)->features & DM_RAID1_HANDLE_ERRORS)
@@ -255,7 +257,7 @@ static int mirror_flush(struct dm_target *ti)
unsigned long error_bits;
unsigned int i;
- struct dm_io_region io[ms->nr_mirrors];
+ struct dm_io_region io[MAX_NR_MIRRORS];
struct mirror *m;
struct dm_io_request io_req = {
.bi_op = REQ_OP_WRITE,
@@ -651,7 +653,7 @@ static void write_callback(unsigned long error, void *context)
static void do_write(struct mirror_set *ms, struct bio *bio)
{
unsigned int i;
- struct dm_io_region io[ms->nr_mirrors], *dest = io;
+ struct dm_io_region io[MAX_NR_MIRRORS], *dest = io;
struct mirror *m;
struct dm_io_request io_req = {
.bi_op = REQ_OP_WRITE,
@@ -1083,7 +1085,7 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv)
argc -= args_used;
if (!argc || sscanf(argv[0], "%u%c", &nr_mirrors, &dummy) != 1 ||
- nr_mirrors < 2 || nr_mirrors > DM_KCOPYD_MAX_REGIONS + 1) {
+ nr_mirrors < 2 || nr_mirrors > MAX_NR_MIRRORS) {
ti->error = "Invalid number of mirrors";
dm_dirty_log_destroy(dl);
return -EINVAL;
@@ -1404,7 +1406,7 @@ static void mirror_status(struct dm_target *ti, status_type_t type,
int num_feature_args = 0;
struct mirror_set *ms = (struct mirror_set *) ti->private;
struct dm_dirty_log *log = dm_rh_dirty_log(ms->rh);
- char buffer[ms->nr_mirrors + 1];
+ char buffer[MAX_NR_MIRRORS + 1];
switch (type) {
case STATUSTYPE_INFO:
diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c
index 85c32b2..abf3521 100644
--- a/drivers/md/dm-region-hash.c
+++ b/drivers/md/dm-region-hash.c
@@ -63,7 +63,7 @@ struct dm_region_hash {
/* hash table */
rwlock_t hash_lock;
- mempool_t *region_pool;
+ mempool_t region_pool;
unsigned mask;
unsigned nr_buckets;
unsigned prime;
@@ -169,6 +169,7 @@ struct dm_region_hash *dm_region_hash_create(
struct dm_region_hash *rh;
unsigned nr_buckets, max_buckets;
size_t i;
+ int ret;
/*
* Calculate a suitable number of buckets for our hash
@@ -179,7 +180,7 @@ struct dm_region_hash *dm_region_hash_create(
;
nr_buckets >>= 1;
- rh = kmalloc(sizeof(*rh), GFP_KERNEL);
+ rh = kzalloc(sizeof(*rh), GFP_KERNEL);
if (!rh) {
DMERR("unable to allocate region hash memory");
return ERR_PTR(-ENOMEM);
@@ -220,9 +221,9 @@ struct dm_region_hash *dm_region_hash_create(
INIT_LIST_HEAD(&rh->failed_recovered_regions);
rh->flush_failure = 0;
- rh->region_pool = mempool_create_kmalloc_pool(MIN_REGIONS,
- sizeof(struct dm_region));
- if (!rh->region_pool) {
+ ret = mempool_init_kmalloc_pool(&rh->region_pool, MIN_REGIONS,
+ sizeof(struct dm_region));
+ if (ret) {
vfree(rh->buckets);
kfree(rh);
rh = ERR_PTR(-ENOMEM);
@@ -242,14 +243,14 @@ void dm_region_hash_destroy(struct dm_region_hash *rh)
list_for_each_entry_safe(reg, nreg, rh->buckets + h,
hash_list) {
BUG_ON(atomic_read(®->pending));
- mempool_free(reg, rh->region_pool);
+ mempool_free(reg, &rh->region_pool);
}
}
if (rh->log)
dm_dirty_log_destroy(rh->log);
- mempool_destroy(rh->region_pool);
+ mempool_exit(&rh->region_pool);
vfree(rh->buckets);
kfree(rh);
}
@@ -287,7 +288,7 @@ static struct dm_region *__rh_alloc(struct dm_region_hash *rh, region_t region)
{
struct dm_region *reg, *nreg;
- nreg = mempool_alloc(rh->region_pool, GFP_ATOMIC);
+ nreg = mempool_alloc(&rh->region_pool, GFP_ATOMIC);
if (unlikely(!nreg))
nreg = kmalloc(sizeof(*nreg), GFP_NOIO | __GFP_NOFAIL);
@@ -303,7 +304,7 @@ static struct dm_region *__rh_alloc(struct dm_region_hash *rh, region_t region)
reg = __rh_lookup(rh, region);
if (reg)
/* We lost the race. */
- mempool_free(nreg, rh->region_pool);
+ mempool_free(nreg, &rh->region_pool);
else {
__rh_insert(rh, nreg);
if (nreg->state == DM_RH_CLEAN) {
@@ -481,17 +482,17 @@ void dm_rh_update_states(struct dm_region_hash *rh, int errors_handled)
list_for_each_entry_safe(reg, next, &recovered, list) {
rh->log->type->clear_region(rh->log, reg->key);
complete_resync_work(reg, 1);
- mempool_free(reg, rh->region_pool);
+ mempool_free(reg, &rh->region_pool);
}
list_for_each_entry_safe(reg, next, &failed_recovered, list) {
complete_resync_work(reg, errors_handled ? 0 : 1);
- mempool_free(reg, rh->region_pool);
+ mempool_free(reg, &rh->region_pool);
}
list_for_each_entry_safe(reg, next, &clean, list) {
rh->log->type->clear_region(rh->log, reg->key);
- mempool_free(reg, rh->region_pool);
+ mempool_free(reg, &rh->region_pool);
}
rh->log->type->flush(rh->log);
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index bf0b840..6e547b8 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -406,7 +406,7 @@ static blk_status_t dm_dispatch_clone_request(struct request *clone, struct requ
if (blk_queue_io_stat(clone->q))
clone->rq_flags |= RQF_IO_STAT;
- clone->start_time = jiffies;
+ clone->start_time_ns = ktime_get_ns();
r = blk_insert_cloned_request(clone->q, clone);
if (r != BLK_STS_OK && r != BLK_STS_RESOURCE && r != BLK_STS_DEV_RESOURCE)
/* must complete clone in terms of original request */
@@ -433,7 +433,7 @@ static int setup_clone(struct request *clone, struct request *rq,
{
int r;
- r = blk_rq_prep_clone(clone, rq, tio->md->bs, gfp_mask,
+ r = blk_rq_prep_clone(clone, rq, &tio->md->bs, gfp_mask,
dm_rq_bio_constructor, tio);
if (r)
return r;
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 216035b..f745404 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -87,7 +87,7 @@ struct dm_snapshot {
*/
struct list_head out_of_order_list;
- mempool_t *pending_pool;
+ mempool_t pending_pool;
struct dm_exception_table pending;
struct dm_exception_table complete;
@@ -682,7 +682,7 @@ static void free_completed_exception(struct dm_exception *e)
static struct dm_snap_pending_exception *alloc_pending_exception(struct dm_snapshot *s)
{
- struct dm_snap_pending_exception *pe = mempool_alloc(s->pending_pool,
+ struct dm_snap_pending_exception *pe = mempool_alloc(&s->pending_pool,
GFP_NOIO);
atomic_inc(&s->pending_exceptions_count);
@@ -695,7 +695,7 @@ static void free_pending_exception(struct dm_snap_pending_exception *pe)
{
struct dm_snapshot *s = pe->snap;
- mempool_free(pe, s->pending_pool);
+ mempool_free(pe, &s->pending_pool);
smp_mb__before_atomic();
atomic_dec(&s->pending_exceptions_count);
}
@@ -1120,7 +1120,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
origin_mode = FMODE_WRITE;
}
- s = kmalloc(sizeof(*s), GFP_KERNEL);
+ s = kzalloc(sizeof(*s), GFP_KERNEL);
if (!s) {
ti->error = "Cannot allocate private snapshot structure";
r = -ENOMEM;
@@ -1196,10 +1196,9 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
goto bad_kcopyd;
}
- s->pending_pool = mempool_create_slab_pool(MIN_IOS, pending_cache);
- if (!s->pending_pool) {
+ r = mempool_init_slab_pool(&s->pending_pool, MIN_IOS, pending_cache);
+ if (r) {
ti->error = "Could not allocate mempool for pending exceptions";
- r = -ENOMEM;
goto bad_pending_pool;
}
@@ -1259,7 +1258,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
unregister_snapshot(s);
bad_load_and_register:
- mempool_destroy(s->pending_pool);
+ mempool_exit(&s->pending_pool);
bad_pending_pool:
dm_kcopyd_client_destroy(s->kcopyd_client);
@@ -1355,7 +1354,7 @@ static void snapshot_dtr(struct dm_target *ti)
while (atomic_read(&s->pending_exceptions_count))
msleep(1);
/*
- * Ensure instructions in mempool_destroy aren't reordered
+ * Ensure instructions in mempool_exit aren't reordered
* before atomic_read.
*/
smp_mb();
@@ -1367,7 +1366,7 @@ static void snapshot_dtr(struct dm_target *ti)
__free_exceptions(s);
- mempool_destroy(s->pending_pool);
+ mempool_exit(&s->pending_pool);
dm_exception_store_destroy(s->store);
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index b111074..5772756 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -260,7 +260,7 @@ struct pool {
struct dm_deferred_set *all_io_ds;
struct dm_thin_new_mapping *next_mapping;
- mempool_t *mapping_pool;
+ mempool_t mapping_pool;
process_bio_fn process_bio;
process_bio_fn process_discard;
@@ -917,7 +917,7 @@ static void process_prepared_mapping_fail(struct dm_thin_new_mapping *m)
{
cell_error(m->tc->pool, m->cell);
list_del(&m->list);
- mempool_free(m, m->tc->pool->mapping_pool);
+ mempool_free(m, &m->tc->pool->mapping_pool);
}
static void process_prepared_mapping(struct dm_thin_new_mapping *m)
@@ -961,7 +961,7 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m)
out:
list_del(&m->list);
- mempool_free(m, pool->mapping_pool);
+ mempool_free(m, &pool->mapping_pool);
}
/*----------------------------------------------------------------*/
@@ -971,7 +971,7 @@ static void free_discard_mapping(struct dm_thin_new_mapping *m)
struct thin_c *tc = m->tc;
if (m->cell)
cell_defer_no_holder(tc, m->cell);
- mempool_free(m, tc->pool->mapping_pool);
+ mempool_free(m, &tc->pool->mapping_pool);
}
static void process_prepared_discard_fail(struct dm_thin_new_mapping *m)
@@ -999,7 +999,7 @@ static void process_prepared_discard_no_passdown(struct dm_thin_new_mapping *m)
bio_endio(m->bio);
cell_defer_no_holder(tc, m->cell);
- mempool_free(m, tc->pool->mapping_pool);
+ mempool_free(m, &tc->pool->mapping_pool);
}
/*----------------------------------------------------------------*/
@@ -1092,7 +1092,7 @@ static void process_prepared_discard_passdown_pt1(struct dm_thin_new_mapping *m)
metadata_operation_failed(pool, "dm_thin_remove_range", r);
bio_io_error(m->bio);
cell_defer_no_holder(tc, m->cell);
- mempool_free(m, pool->mapping_pool);
+ mempool_free(m, &pool->mapping_pool);
return;
}
@@ -1105,7 +1105,7 @@ static void process_prepared_discard_passdown_pt1(struct dm_thin_new_mapping *m)
metadata_operation_failed(pool, "dm_pool_inc_data_range", r);
bio_io_error(m->bio);
cell_defer_no_holder(tc, m->cell);
- mempool_free(m, pool->mapping_pool);
+ mempool_free(m, &pool->mapping_pool);
return;
}
@@ -1150,7 +1150,7 @@ static void process_prepared_discard_passdown_pt2(struct dm_thin_new_mapping *m)
bio_endio(m->bio);
cell_defer_no_holder(tc, m->cell);
- mempool_free(m, pool->mapping_pool);
+ mempool_free(m, &pool->mapping_pool);
}
static void process_prepared(struct pool *pool, struct list_head *head,
@@ -1196,7 +1196,7 @@ static int ensure_next_mapping(struct pool *pool)
if (pool->next_mapping)
return 0;
- pool->next_mapping = mempool_alloc(pool->mapping_pool, GFP_ATOMIC);
+ pool->next_mapping = mempool_alloc(&pool->mapping_pool, GFP_ATOMIC);
return pool->next_mapping ? 0 : -ENOMEM;
}
@@ -2835,8 +2835,8 @@ static void __pool_destroy(struct pool *pool)
destroy_workqueue(pool->wq);
if (pool->next_mapping)
- mempool_free(pool->next_mapping, pool->mapping_pool);
- mempool_destroy(pool->mapping_pool);
+ mempool_free(pool->next_mapping, &pool->mapping_pool);
+ mempool_exit(&pool->mapping_pool);
dm_deferred_set_destroy(pool->shared_read_ds);
dm_deferred_set_destroy(pool->all_io_ds);
kfree(pool);
@@ -2861,7 +2861,7 @@ static struct pool *pool_create(struct mapped_device *pool_md,
return (struct pool *)pmd;
}
- pool = kmalloc(sizeof(*pool), GFP_KERNEL);
+ pool = kzalloc(sizeof(*pool), GFP_KERNEL);
if (!pool) {
*error = "Error allocating memory for pool";
err_p = ERR_PTR(-ENOMEM);
@@ -2931,11 +2931,11 @@ static struct pool *pool_create(struct mapped_device *pool_md,
}
pool->next_mapping = NULL;
- pool->mapping_pool = mempool_create_slab_pool(MAPPING_POOL_SIZE,
- _new_mapping_cache);
- if (!pool->mapping_pool) {
+ r = mempool_init_slab_pool(&pool->mapping_pool, MAPPING_POOL_SIZE,
+ _new_mapping_cache);
+ if (r) {
*error = "Error creating pool's mapping mempool";
- err_p = ERR_PTR(-ENOMEM);
+ err_p = ERR_PTR(r);
goto bad_mapping_pool;
}
@@ -2955,7 +2955,7 @@ static struct pool *pool_create(struct mapped_device *pool_md,
return pool;
bad_sort_array:
- mempool_destroy(pool->mapping_pool);
+ mempool_exit(&pool->mapping_pool);
bad_mapping_pool:
dm_deferred_set_destroy(pool->all_io_ds);
bad_all_io_ds:
diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
index e13f908..684af08 100644
--- a/drivers/md/dm-verity-fec.c
+++ b/drivers/md/dm-verity-fec.c
@@ -309,13 +309,13 @@ static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio)
unsigned n;
if (!fio->rs)
- fio->rs = mempool_alloc(v->fec->rs_pool, GFP_NOIO);
+ fio->rs = mempool_alloc(&v->fec->rs_pool, GFP_NOIO);
fec_for_each_prealloc_buffer(n) {
if (fio->bufs[n])
continue;
- fio->bufs[n] = mempool_alloc(v->fec->prealloc_pool, GFP_NOWAIT);
+ fio->bufs[n] = mempool_alloc(&v->fec->prealloc_pool, GFP_NOWAIT);
if (unlikely(!fio->bufs[n])) {
DMERR("failed to allocate FEC buffer");
return -ENOMEM;
@@ -327,7 +327,7 @@ static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio)
if (fio->bufs[n])
continue;
- fio->bufs[n] = mempool_alloc(v->fec->extra_pool, GFP_NOWAIT);
+ fio->bufs[n] = mempool_alloc(&v->fec->extra_pool, GFP_NOWAIT);
/* we can manage with even one buffer if necessary */
if (unlikely(!fio->bufs[n]))
break;
@@ -335,7 +335,7 @@ static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio)
fio->nbufs = n;
if (!fio->output)
- fio->output = mempool_alloc(v->fec->output_pool, GFP_NOIO);
+ fio->output = mempool_alloc(&v->fec->output_pool, GFP_NOIO);
return 0;
}
@@ -493,15 +493,15 @@ void verity_fec_finish_io(struct dm_verity_io *io)
if (!verity_fec_is_enabled(io->v))
return;
- mempool_free(fio->rs, f->rs_pool);
+ mempool_free(fio->rs, &f->rs_pool);
fec_for_each_prealloc_buffer(n)
- mempool_free(fio->bufs[n], f->prealloc_pool);
+ mempool_free(fio->bufs[n], &f->prealloc_pool);
fec_for_each_extra_buffer(fio, n)
- mempool_free(fio->bufs[n], f->extra_pool);
+ mempool_free(fio->bufs[n], &f->extra_pool);
- mempool_free(fio->output, f->output_pool);
+ mempool_free(fio->output, &f->output_pool);
}
/*
@@ -549,9 +549,9 @@ void verity_fec_dtr(struct dm_verity *v)
if (!verity_fec_is_enabled(v))
goto out;
- mempool_destroy(f->rs_pool);
- mempool_destroy(f->prealloc_pool);
- mempool_destroy(f->extra_pool);
+ mempool_exit(&f->rs_pool);
+ mempool_exit(&f->prealloc_pool);
+ mempool_exit(&f->extra_pool);
kmem_cache_destroy(f->cache);
if (f->data_bufio)
@@ -570,7 +570,7 @@ static void *fec_rs_alloc(gfp_t gfp_mask, void *pool_data)
{
struct dm_verity *v = (struct dm_verity *)pool_data;
- return init_rs(8, 0x11d, 0, 1, v->fec->roots);
+ return init_rs_gfp(8, 0x11d, 0, 1, v->fec->roots, gfp_mask);
}
static void fec_rs_free(void *element, void *pool_data)
@@ -675,6 +675,7 @@ int verity_fec_ctr(struct dm_verity *v)
struct dm_verity_fec *f = v->fec;
struct dm_target *ti = v->ti;
u64 hash_blocks;
+ int ret;
if (!verity_fec_is_enabled(v)) {
verity_fec_dtr(v);
@@ -770,11 +771,11 @@ int verity_fec_ctr(struct dm_verity *v)
}
/* Preallocate an rs_control structure for each worker thread */
- f->rs_pool = mempool_create(num_online_cpus(), fec_rs_alloc,
- fec_rs_free, (void *) v);
- if (!f->rs_pool) {
+ ret = mempool_init(&f->rs_pool, num_online_cpus(), fec_rs_alloc,
+ fec_rs_free, (void *) v);
+ if (ret) {
ti->error = "Cannot allocate RS pool";
- return -ENOMEM;
+ return ret;
}
f->cache = kmem_cache_create("dm_verity_fec_buffers",
@@ -786,26 +787,26 @@ int verity_fec_ctr(struct dm_verity *v)
}
/* Preallocate DM_VERITY_FEC_BUF_PREALLOC buffers for each thread */
- f->prealloc_pool = mempool_create_slab_pool(num_online_cpus() *
- DM_VERITY_FEC_BUF_PREALLOC,
- f->cache);
- if (!f->prealloc_pool) {
+ ret = mempool_init_slab_pool(&f->prealloc_pool, num_online_cpus() *
+ DM_VERITY_FEC_BUF_PREALLOC,
+ f->cache);
+ if (ret) {
ti->error = "Cannot allocate FEC buffer prealloc pool";
- return -ENOMEM;
+ return ret;
}
- f->extra_pool = mempool_create_slab_pool(0, f->cache);
- if (!f->extra_pool) {
+ ret = mempool_init_slab_pool(&f->extra_pool, 0, f->cache);
+ if (ret) {
ti->error = "Cannot allocate FEC buffer extra pool";
- return -ENOMEM;
+ return ret;
}
/* Preallocate an output buffer for each thread */
- f->output_pool = mempool_create_kmalloc_pool(num_online_cpus(),
- 1 << v->data_dev_block_bits);
- if (!f->output_pool) {
+ ret = mempool_init_kmalloc_pool(&f->output_pool, num_online_cpus(),
+ 1 << v->data_dev_block_bits);
+ if (ret) {
ti->error = "Cannot allocate FEC output pool";
- return -ENOMEM;
+ return ret;
}
/* Reserve space for our per-bio data */
diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h
index bb31ce8..6ad803b 100644
--- a/drivers/md/dm-verity-fec.h
+++ b/drivers/md/dm-verity-fec.h
@@ -46,10 +46,10 @@ struct dm_verity_fec {
sector_t hash_blocks; /* blocks covered after v->hash_start */
unsigned char roots; /* number of parity bytes, M-N of RS(M, N) */
unsigned char rsn; /* N of RS(M, N) */
- mempool_t *rs_pool; /* mempool for fio->rs */
- mempool_t *prealloc_pool; /* mempool for preallocated buffers */
- mempool_t *extra_pool; /* mempool for extra buffers */
- mempool_t *output_pool; /* mempool for output */
+ mempool_t rs_pool; /* mempool for fio->rs */
+ mempool_t prealloc_pool; /* mempool for preallocated buffers */
+ mempool_t extra_pool; /* mempool for extra buffers */
+ mempool_t output_pool; /* mempool for output */
struct kmem_cache *cache; /* cache for buffers */
};
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index e73b077..30602d1 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -57,7 +57,7 @@ struct dmz_target {
struct workqueue_struct *chunk_wq;
/* For cloned BIOs to zones */
- struct bio_set *bio_set;
+ struct bio_set bio_set;
/* For flush */
spinlock_t flush_lock;
@@ -121,7 +121,7 @@ static int dmz_submit_read_bio(struct dmz_target *dmz, struct dm_zone *zone,
}
/* Partial BIO: we need to clone the BIO */
- clone = bio_clone_fast(bio, GFP_NOIO, dmz->bio_set);
+ clone = bio_clone_fast(bio, GFP_NOIO, &dmz->bio_set);
if (!clone)
return -ENOMEM;
@@ -779,10 +779,9 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv)
ti->len = (sector_t)dmz_nr_chunks(dmz->metadata) << dev->zone_nr_sectors_shift;
/* Zone BIO */
- dmz->bio_set = bioset_create(DMZ_MIN_BIOS, 0, 0);
- if (!dmz->bio_set) {
+ ret = bioset_init(&dmz->bio_set, DMZ_MIN_BIOS, 0, 0);
+ if (ret) {
ti->error = "Create BIO set failed";
- ret = -ENOMEM;
goto err_meta;
}
@@ -828,7 +827,7 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv)
destroy_workqueue(dmz->chunk_wq);
err_bio:
mutex_destroy(&dmz->chunk_lock);
- bioset_free(dmz->bio_set);
+ bioset_exit(&dmz->bio_set);
err_meta:
dmz_dtr_metadata(dmz->metadata);
err_dev:
@@ -858,7 +857,7 @@ static void dmz_dtr(struct dm_target *ti)
dmz_dtr_metadata(dmz->metadata);
- bioset_free(dmz->bio_set);
+ bioset_exit(&dmz->bio_set);
dmz_put_zoned_device(ti);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 4ea404d..98dff36 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -148,8 +148,8 @@ static int dm_numa_node = DM_NUMA_NODE;
* For mempools pre-allocation at the table loading time.
*/
struct dm_md_mempools {
- struct bio_set *bs;
- struct bio_set *io_bs;
+ struct bio_set bs;
+ struct bio_set io_bs;
};
struct table_device {
@@ -537,7 +537,7 @@ static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio)
struct dm_target_io *tio;
struct bio *clone;
- clone = bio_alloc_bioset(GFP_NOIO, 0, md->io_bs);
+ clone = bio_alloc_bioset(GFP_NOIO, 0, &md->io_bs);
if (!clone)
return NULL;
@@ -572,7 +572,7 @@ static struct dm_target_io *alloc_tio(struct clone_info *ci, struct dm_target *t
/* the dm_target_io embedded in ci->io is available */
tio = &ci->io->tio;
} else {
- struct bio *clone = bio_alloc_bioset(gfp_mask, 0, ci->io->md->bs);
+ struct bio *clone = bio_alloc_bioset(gfp_mask, 0, &ci->io->md->bs);
if (!clone)
return NULL;
@@ -1020,7 +1020,8 @@ int dm_set_target_max_io_len(struct dm_target *ti, sector_t len)
EXPORT_SYMBOL_GPL(dm_set_target_max_io_len);
static struct dm_target *dm_dax_get_live_target(struct mapped_device *md,
- sector_t sector, int *srcu_idx)
+ sector_t sector, int *srcu_idx)
+ __acquires(md->io_barrier)
{
struct dm_table *map;
struct dm_target *ti;
@@ -1037,7 +1038,7 @@ static struct dm_target *dm_dax_get_live_target(struct mapped_device *md,
}
static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
- long nr_pages, void **kaddr, pfn_t *pfn)
+ long nr_pages, void **kaddr, pfn_t *pfn)
{
struct mapped_device *md = dax_get_private(dax_dev);
sector_t sector = pgoff * PAGE_SECTORS;
@@ -1065,7 +1066,7 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
}
static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
- void *addr, size_t bytes, struct iov_iter *i)
+ void *addr, size_t bytes, struct iov_iter *i)
{
struct mapped_device *md = dax_get_private(dax_dev);
sector_t sector = pgoff * PAGE_SECTORS;
@@ -1582,7 +1583,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
* won't be affected by this reassignment.
*/
struct bio *b = bio_clone_bioset(bio, GFP_NOIO,
- md->queue->bio_split);
+ &md->queue->bio_split);
ci.io->orig_bio = b;
bio_advance(bio, (bio_sectors(bio) - ci.sector_count) << 9);
bio_chain(b, bio);
@@ -1784,10 +1785,8 @@ static void cleanup_mapped_device(struct mapped_device *md)
destroy_workqueue(md->wq);
if (md->kworker_task)
kthread_stop(md->kworker_task);
- if (md->bs)
- bioset_free(md->bs);
- if (md->io_bs)
- bioset_free(md->io_bs);
+ bioset_exit(&md->bs);
+ bioset_exit(&md->io_bs);
if (md->dax_dev) {
kill_dax(md->dax_dev);
@@ -1964,16 +1963,10 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
* If so, reload bioset because front_pad may have changed
* because a different table was loaded.
*/
- if (md->bs) {
- bioset_free(md->bs);
- md->bs = NULL;
- }
- if (md->io_bs) {
- bioset_free(md->io_bs);
- md->io_bs = NULL;
- }
+ bioset_exit(&md->bs);
+ bioset_exit(&md->io_bs);
- } else if (md->bs) {
+ } else if (bioset_initialized(&md->bs)) {
/*
* There's no need to reload with request-based dm
* because the size of front_pad doesn't change.
@@ -1985,12 +1978,14 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
goto out;
}
- BUG_ON(!p || md->bs || md->io_bs);
+ BUG_ON(!p ||
+ bioset_initialized(&md->bs) ||
+ bioset_initialized(&md->io_bs));
md->bs = p->bs;
- p->bs = NULL;
+ memset(&p->bs, 0, sizeof(p->bs));
md->io_bs = p->io_bs;
- p->io_bs = NULL;
+ memset(&p->io_bs, 0, sizeof(p->io_bs));
out:
/* mempool bind completed, no longer need any mempools in the table */
dm_table_free_md_mempools(t);
@@ -2904,6 +2899,7 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_qu
struct dm_md_mempools *pools = kzalloc_node(sizeof(*pools), GFP_KERNEL, md->numa_node_id);
unsigned int pool_size = 0;
unsigned int front_pad, io_front_pad;
+ int ret;
if (!pools)
return NULL;
@@ -2915,10 +2911,10 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_qu
pool_size = max(dm_get_reserved_bio_based_ios(), min_pool_size);
front_pad = roundup(per_io_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
io_front_pad = roundup(front_pad, __alignof__(struct dm_io)) + offsetof(struct dm_io, tio);
- pools->io_bs = bioset_create(pool_size, io_front_pad, 0);
- if (!pools->io_bs)
+ ret = bioset_init(&pools->io_bs, pool_size, io_front_pad, 0);
+ if (ret)
goto out;
- if (integrity && bioset_integrity_create(pools->io_bs, pool_size))
+ if (integrity && bioset_integrity_create(&pools->io_bs, pool_size))
goto out;
break;
case DM_TYPE_REQUEST_BASED:
@@ -2931,11 +2927,11 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_qu
BUG();
}
- pools->bs = bioset_create(pool_size, front_pad, 0);
- if (!pools->bs)
+ ret = bioset_init(&pools->bs, pool_size, front_pad, 0);
+ if (ret)
goto out;
- if (integrity && bioset_integrity_create(pools->bs, pool_size))
+ if (integrity && bioset_integrity_create(&pools->bs, pool_size))
goto out;
return pools;
@@ -2951,10 +2947,8 @@ void dm_free_md_mempools(struct dm_md_mempools *pools)
if (!pools)
return;
- if (pools->bs)
- bioset_free(pools->bs);
- if (pools->io_bs)
- bioset_free(pools->io_bs);
+ bioset_exit(&pools->bs);
+ bioset_exit(&pools->io_bs);
kfree(pools);
}
diff --git a/drivers/md/md-faulty.c b/drivers/md/md-faulty.c
index 38264b3..c2fdf89 100644
--- a/drivers/md/md-faulty.c
+++ b/drivers/md/md-faulty.c
@@ -214,7 +214,7 @@ static bool faulty_make_request(struct mddev *mddev, struct bio *bio)
}
}
if (failit) {
- struct bio *b = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
+ struct bio *b = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
bio_set_dev(b, conf->rdev->bdev);
b->bi_private = bio;
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 4964323..d45c697 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -269,7 +269,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
if (unlikely(bio_end_sector(bio) > end_sector)) {
/* This bio crosses a device boundary, so we have to split it */
struct bio *split = bio_split(bio, end_sector - bio_sector,
- GFP_NOIO, mddev->bio_set);
+ GFP_NOIO, &mddev->bio_set);
bio_chain(split, bio);
generic_make_request(bio);
bio = split;
diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c
index 0a7e99d..f71fcdb 100644
--- a/drivers/md/md-multipath.c
+++ b/drivers/md/md-multipath.c
@@ -80,7 +80,7 @@ static void multipath_end_bh_io(struct multipath_bh *mp_bh, blk_status_t status)
bio->bi_status = status;
bio_endio(bio);
- mempool_free(mp_bh, conf->pool);
+ mempool_free(mp_bh, &conf->pool);
}
static void multipath_end_request(struct bio *bio)
@@ -117,7 +117,7 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio)
return true;
}
- mp_bh = mempool_alloc(conf->pool, GFP_NOIO);
+ mp_bh = mempool_alloc(&conf->pool, GFP_NOIO);
mp_bh->master_bio = bio;
mp_bh->mddev = mddev;
@@ -125,7 +125,7 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio)
mp_bh->path = multipath_map(conf);
if (mp_bh->path < 0) {
bio_io_error(bio);
- mempool_free(mp_bh, conf->pool);
+ mempool_free(mp_bh, &conf->pool);
return true;
}
multipath = conf->multipaths + mp_bh->path;
@@ -378,6 +378,7 @@ static int multipath_run (struct mddev *mddev)
struct multipath_info *disk;
struct md_rdev *rdev;
int working_disks;
+ int ret;
if (md_check_no_bitmap(mddev))
return -EINVAL;
@@ -431,9 +432,9 @@ static int multipath_run (struct mddev *mddev)
}
mddev->degraded = conf->raid_disks - working_disks;
- conf->pool = mempool_create_kmalloc_pool(NR_RESERVED_BUFS,
- sizeof(struct multipath_bh));
- if (conf->pool == NULL)
+ ret = mempool_init_kmalloc_pool(&conf->pool, NR_RESERVED_BUFS,
+ sizeof(struct multipath_bh));
+ if (ret)
goto out_free_conf;
mddev->thread = md_register_thread(multipathd, mddev,
@@ -455,7 +456,7 @@ static int multipath_run (struct mddev *mddev)
return 0;
out_free_conf:
- mempool_destroy(conf->pool);
+ mempool_exit(&conf->pool);
kfree(conf->multipaths);
kfree(conf);
mddev->private = NULL;
@@ -467,7 +468,7 @@ static void multipath_free(struct mddev *mddev, void *priv)
{
struct mpconf *conf = priv;
- mempool_destroy(conf->pool);
+ mempool_exit(&conf->pool);
kfree(conf->multipaths);
kfree(conf);
}
diff --git a/drivers/md/md-multipath.h b/drivers/md/md-multipath.h
index 0adb941..b3099e5 100644
--- a/drivers/md/md-multipath.h
+++ b/drivers/md/md-multipath.h
@@ -13,7 +13,7 @@ struct mpconf {
spinlock_t device_lock;
struct list_head retry_list;
- mempool_t *pool;
+ mempool_t pool;
};
/*
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 3bea45e..fc692b7 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -193,10 +193,10 @@ struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
{
struct bio *b;
- if (!mddev || !mddev->bio_set)
+ if (!mddev || !bioset_initialized(&mddev->bio_set))
return bio_alloc(gfp_mask, nr_iovecs);
- b = bio_alloc_bioset(gfp_mask, nr_iovecs, mddev->bio_set);
+ b = bio_alloc_bioset(gfp_mask, nr_iovecs, &mddev->bio_set);
if (!b)
return NULL;
return b;
@@ -205,10 +205,10 @@ EXPORT_SYMBOL_GPL(bio_alloc_mddev);
static struct bio *md_bio_alloc_sync(struct mddev *mddev)
{
- if (!mddev || !mddev->sync_set)
+ if (!mddev || !bioset_initialized(&mddev->sync_set))
return bio_alloc(GFP_NOIO, 1);
- return bio_alloc_bioset(GFP_NOIO, 1, mddev->sync_set);
+ return bio_alloc_bioset(GFP_NOIO, 1, &mddev->sync_set);
}
/*
@@ -510,7 +510,10 @@ static void mddev_delayed_delete(struct work_struct *ws);
static void mddev_put(struct mddev *mddev)
{
- struct bio_set *bs = NULL, *sync_bs = NULL;
+ struct bio_set bs, sync_bs;
+
+ memset(&bs, 0, sizeof(bs));
+ memset(&sync_bs, 0, sizeof(sync_bs));
if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock))
return;
@@ -521,8 +524,8 @@ static void mddev_put(struct mddev *mddev)
list_del_init(&mddev->all_mddevs);
bs = mddev->bio_set;
sync_bs = mddev->sync_set;
- mddev->bio_set = NULL;
- mddev->sync_set = NULL;
+ memset(&mddev->bio_set, 0, sizeof(mddev->bio_set));
+ memset(&mddev->sync_set, 0, sizeof(mddev->sync_set));
if (mddev->gendisk) {
/* We did a probe so need to clean up. Call
* queue_work inside the spinlock so that
@@ -535,10 +538,8 @@ static void mddev_put(struct mddev *mddev)
kfree(mddev);
}
spin_unlock(&all_mddevs_lock);
- if (bs)
- bioset_free(bs);
- if (sync_bs)
- bioset_free(sync_bs);
+ bioset_exit(&bs);
+ bioset_exit(&sync_bs);
}
static void md_safemode_timeout(struct timer_list *t);
@@ -2123,7 +2124,7 @@ int md_integrity_register(struct mddev *mddev)
bdev_get_integrity(reference->bdev));
pr_debug("md: data integrity enabled on %s\n", mdname(mddev));
- if (bioset_integrity_create(mddev->bio_set, BIO_POOL_SIZE)) {
+ if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE)) {
pr_err("md: failed to create integrity pool for %s\n",
mdname(mddev));
return -EINVAL;
@@ -5497,17 +5498,15 @@ int md_run(struct mddev *mddev)
sysfs_notify_dirent_safe(rdev->sysfs_state);
}
- if (mddev->bio_set == NULL) {
- mddev->bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
- if (!mddev->bio_set)
- return -ENOMEM;
+ if (!bioset_initialized(&mddev->bio_set)) {
+ err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+ if (err)
+ return err;
}
- if (mddev->sync_set == NULL) {
- mddev->sync_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
- if (!mddev->sync_set) {
- err = -ENOMEM;
+ if (!bioset_initialized(&mddev->sync_set)) {
+ err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+ if (err)
goto abort;
- }
}
spin_lock(&pers_lock);
@@ -5668,14 +5667,8 @@ int md_run(struct mddev *mddev)
return 0;
abort:
- if (mddev->bio_set) {
- bioset_free(mddev->bio_set);
- mddev->bio_set = NULL;
- }
- if (mddev->sync_set) {
- bioset_free(mddev->sync_set);
- mddev->sync_set = NULL;
- }
+ bioset_exit(&mddev->bio_set);
+ bioset_exit(&mddev->sync_set);
return err;
}
@@ -5888,14 +5881,8 @@ void md_stop(struct mddev *mddev)
* This is called from dm-raid
*/
__md_stop(mddev);
- if (mddev->bio_set) {
- bioset_free(mddev->bio_set);
- mddev->bio_set = NULL;
- }
- if (mddev->sync_set) {
- bioset_free(mddev->sync_set);
- mddev->sync_set = NULL;
- }
+ bioset_exit(&mddev->bio_set);
+ bioset_exit(&mddev->sync_set);
}
EXPORT_SYMBOL_GPL(md_stop);
@@ -9256,8 +9243,10 @@ void md_reload_sb(struct mddev *mddev, int nr)
check_sb_changes(mddev, rdev);
/* Read all rdev's to update recovery_offset */
- rdev_for_each_rcu(rdev, mddev)
- read_rdev(mddev, rdev);
+ rdev_for_each_rcu(rdev, mddev) {
+ if (!test_bit(Faulty, &rdev->flags))
+ read_rdev(mddev, rdev);
+ }
}
EXPORT_SYMBOL(md_reload_sb);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index fbc925c..3507cab2 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -452,8 +452,8 @@ struct mddev {
struct attribute_group *to_remove;
- struct bio_set *bio_set;
- struct bio_set *sync_set; /* for sync operations like
+ struct bio_set bio_set;
+ struct bio_set sync_set; /* for sync operations like
* metadata and bitmap writes
*/
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 584c1034..65ae47a 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -479,7 +479,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
if (bio_end_sector(bio) > zone->zone_end) {
struct bio *split = bio_split(bio,
zone->zone_end - bio->bi_iter.bi_sector, GFP_NOIO,
- mddev->bio_set);
+ &mddev->bio_set);
bio_chain(split, bio);
generic_make_request(bio);
bio = split;
@@ -582,7 +582,8 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
sector = bio_sector;
if (sectors < bio_sectors(bio)) {
- struct bio *split = bio_split(bio, sectors, GFP_NOIO, mddev->bio_set);
+ struct bio *split = bio_split(bio, sectors, GFP_NOIO,
+ &mddev->bio_set);
bio_chain(split, bio);
generic_make_request(bio);
bio = split;
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index e2943fb..bad2852 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -221,7 +221,7 @@ static void free_r1bio(struct r1bio *r1_bio)
struct r1conf *conf = r1_bio->mddev->private;
put_all_bios(conf, r1_bio);
- mempool_free(r1_bio, conf->r1bio_pool);
+ mempool_free(r1_bio, &conf->r1bio_pool);
}
static void put_buf(struct r1bio *r1_bio)
@@ -236,7 +236,7 @@ static void put_buf(struct r1bio *r1_bio)
rdev_dec_pending(conf->mirrors[i].rdev, r1_bio->mddev);
}
- mempool_free(r1_bio, conf->r1buf_pool);
+ mempool_free(r1_bio, &conf->r1buf_pool);
lower_barrier(conf, sect);
}
@@ -854,7 +854,7 @@ static void flush_pending_writes(struct r1conf *conf)
* there is no normal IO happeing. It must arrange to call
* lower_barrier when the particular background IO completes.
*/
-static void raise_barrier(struct r1conf *conf, sector_t sector_nr)
+static sector_t raise_barrier(struct r1conf *conf, sector_t sector_nr)
{
int idx = sector_to_idx(sector_nr);
@@ -885,13 +885,23 @@ static void raise_barrier(struct r1conf *conf, sector_t sector_nr)
* max resync count which allowed on current I/O barrier bucket.
*/
wait_event_lock_irq(conf->wait_barrier,
- !conf->array_frozen &&
+ (!conf->array_frozen &&
!atomic_read(&conf->nr_pending[idx]) &&
- atomic_read(&conf->barrier[idx]) < RESYNC_DEPTH,
+ atomic_read(&conf->barrier[idx]) < RESYNC_DEPTH) ||
+ test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery),
conf->resync_lock);
+ if (test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) {
+ atomic_dec(&conf->barrier[idx]);
+ spin_unlock_irq(&conf->resync_lock);
+ wake_up(&conf->wait_barrier);
+ return -EINTR;
+ }
+
atomic_inc(&conf->nr_sync_pending);
spin_unlock_irq(&conf->resync_lock);
+
+ return 0;
}
static void lower_barrier(struct r1conf *conf, sector_t sector_nr)
@@ -1092,6 +1102,8 @@ static void alloc_behind_master_bio(struct r1bio *r1_bio,
goto skip_copy;
}
+ behind_bio->bi_write_hint = bio->bi_write_hint;
+
while (i < vcnt && size) {
struct page *page;
int len = min_t(int, PAGE_SIZE, size);
@@ -1166,7 +1178,7 @@ alloc_r1bio(struct mddev *mddev, struct bio *bio)
struct r1conf *conf = mddev->private;
struct r1bio *r1_bio;
- r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
+ r1_bio = mempool_alloc(&conf->r1bio_pool, GFP_NOIO);
/* Ensure no bio records IO_BLOCKED */
memset(r1_bio->bios, 0, conf->raid_disks * sizeof(r1_bio->bios[0]));
init_r1bio(r1_bio, mddev, bio);
@@ -1256,7 +1268,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
if (max_sectors < bio_sectors(bio)) {
struct bio *split = bio_split(bio, max_sectors,
- gfp, conf->bio_split);
+ gfp, &conf->bio_split);
bio_chain(split, bio);
generic_make_request(bio);
bio = split;
@@ -1266,7 +1278,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
r1_bio->read_disk = rdisk;
- read_bio = bio_clone_fast(bio, gfp, mddev->bio_set);
+ read_bio = bio_clone_fast(bio, gfp, &mddev->bio_set);
r1_bio->bios[rdisk] = read_bio;
@@ -1427,7 +1439,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
if (max_sectors < bio_sectors(bio)) {
struct bio *split = bio_split(bio, max_sectors,
- GFP_NOIO, conf->bio_split);
+ GFP_NOIO, &conf->bio_split);
bio_chain(split, bio);
generic_make_request(bio);
bio = split;
@@ -1467,9 +1479,9 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
if (r1_bio->behind_master_bio)
mbio = bio_clone_fast(r1_bio->behind_master_bio,
- GFP_NOIO, mddev->bio_set);
+ GFP_NOIO, &mddev->bio_set);
else
- mbio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
+ mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
if (r1_bio->behind_master_bio) {
if (test_bit(WriteMostly, &conf->mirrors[i].rdev->flags))
@@ -1645,8 +1657,7 @@ static void close_sync(struct r1conf *conf)
_allow_barrier(conf, idx);
}
- mempool_destroy(conf->r1buf_pool);
- conf->r1buf_pool = NULL;
+ mempool_exit(&conf->r1buf_pool);
}
static int raid1_spare_active(struct mddev *mddev)
@@ -2336,10 +2347,10 @@ static int narrow_write_error(struct r1bio *r1_bio, int i)
if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
wbio = bio_clone_fast(r1_bio->behind_master_bio,
GFP_NOIO,
- mddev->bio_set);
+ &mddev->bio_set);
} else {
wbio = bio_clone_fast(r1_bio->master_bio, GFP_NOIO,
- mddev->bio_set);
+ &mddev->bio_set);
}
bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
@@ -2552,17 +2563,15 @@ static int init_resync(struct r1conf *conf)
int buffs;
buffs = RESYNC_WINDOW / RESYNC_BLOCK_SIZE;
- BUG_ON(conf->r1buf_pool);
- conf->r1buf_pool = mempool_create(buffs, r1buf_pool_alloc, r1buf_pool_free,
- conf->poolinfo);
- if (!conf->r1buf_pool)
- return -ENOMEM;
- return 0;
+ BUG_ON(mempool_initialized(&conf->r1buf_pool));
+
+ return mempool_init(&conf->r1buf_pool, buffs, r1buf_pool_alloc,
+ r1buf_pool_free, conf->poolinfo);
}
static struct r1bio *raid1_alloc_init_r1buf(struct r1conf *conf)
{
- struct r1bio *r1bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO);
+ struct r1bio *r1bio = mempool_alloc(&conf->r1buf_pool, GFP_NOIO);
struct resync_pages *rps;
struct bio *bio;
int i;
@@ -2605,7 +2614,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
int idx = sector_to_idx(sector_nr);
int page_idx = 0;
- if (!conf->r1buf_pool)
+ if (!mempool_initialized(&conf->r1buf_pool))
if (init_resync(conf))
return 0;
@@ -2662,9 +2671,12 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
bitmap_cond_end_sync(mddev->bitmap, sector_nr,
mddev_is_clustered(mddev) && (sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high));
- r1_bio = raid1_alloc_init_r1buf(conf);
- raise_barrier(conf, sector_nr);
+
+ if (raise_barrier(conf, sector_nr))
+ return 0;
+
+ r1_bio = raid1_alloc_init_r1buf(conf);
rcu_read_lock();
/*
@@ -2938,14 +2950,13 @@ static struct r1conf *setup_conf(struct mddev *mddev)
if (!conf->poolinfo)
goto abort;
conf->poolinfo->raid_disks = mddev->raid_disks * 2;
- conf->r1bio_pool = mempool_create(NR_RAID1_BIOS, r1bio_pool_alloc,
- r1bio_pool_free,
- conf->poolinfo);
- if (!conf->r1bio_pool)
+ err = mempool_init(&conf->r1bio_pool, NR_RAID1_BIOS, r1bio_pool_alloc,
+ r1bio_pool_free, conf->poolinfo);
+ if (err)
goto abort;
- conf->bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
- if (!conf->bio_split)
+ err = bioset_init(&conf->bio_split, BIO_POOL_SIZE, 0, 0);
+ if (err)
goto abort;
conf->poolinfo->mddev = mddev;
@@ -3018,7 +3029,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
abort:
if (conf) {
- mempool_destroy(conf->r1bio_pool);
+ mempool_exit(&conf->r1bio_pool);
kfree(conf->mirrors);
safe_put_page(conf->tmppage);
kfree(conf->poolinfo);
@@ -3026,8 +3037,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
kfree(conf->nr_waiting);
kfree(conf->nr_queued);
kfree(conf->barrier);
- if (conf->bio_split)
- bioset_free(conf->bio_split);
+ bioset_exit(&conf->bio_split);
kfree(conf);
}
return ERR_PTR(err);
@@ -3129,7 +3139,7 @@ static void raid1_free(struct mddev *mddev, void *priv)
{
struct r1conf *conf = priv;
- mempool_destroy(conf->r1bio_pool);
+ mempool_exit(&conf->r1bio_pool);
kfree(conf->mirrors);
safe_put_page(conf->tmppage);
kfree(conf->poolinfo);
@@ -3137,8 +3147,7 @@ static void raid1_free(struct mddev *mddev, void *priv)
kfree(conf->nr_waiting);
kfree(conf->nr_queued);
kfree(conf->barrier);
- if (conf->bio_split)
- bioset_free(conf->bio_split);
+ bioset_exit(&conf->bio_split);
kfree(conf);
}
@@ -3184,13 +3193,17 @@ static int raid1_reshape(struct mddev *mddev)
* At the same time, we "pack" the devices so that all the missing
* devices have the higher raid_disk numbers.
*/
- mempool_t *newpool, *oldpool;
+ mempool_t newpool, oldpool;
struct pool_info *newpoolinfo;
struct raid1_info *newmirrors;
struct r1conf *conf = mddev->private;
int cnt, raid_disks;
unsigned long flags;
int d, d2;
+ int ret;
+
+ memset(&newpool, 0, sizeof(newpool));
+ memset(&oldpool, 0, sizeof(oldpool));
/* Cannot change chunk_size, layout, or level */
if (mddev->chunk_sectors != mddev->new_chunk_sectors ||
@@ -3222,17 +3235,17 @@ static int raid1_reshape(struct mddev *mddev)
newpoolinfo->mddev = mddev;
newpoolinfo->raid_disks = raid_disks * 2;
- newpool = mempool_create(NR_RAID1_BIOS, r1bio_pool_alloc,
- r1bio_pool_free, newpoolinfo);
- if (!newpool) {
+ ret = mempool_init(&newpool, NR_RAID1_BIOS, r1bio_pool_alloc,
+ r1bio_pool_free, newpoolinfo);
+ if (ret) {
kfree(newpoolinfo);
- return -ENOMEM;
+ return ret;
}
newmirrors = kzalloc(sizeof(struct raid1_info) * raid_disks * 2,
GFP_KERNEL);
if (!newmirrors) {
kfree(newpoolinfo);
- mempool_destroy(newpool);
+ mempool_exit(&newpool);
return -ENOMEM;
}
@@ -3272,7 +3285,7 @@ static int raid1_reshape(struct mddev *mddev)
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
- mempool_destroy(oldpool);
+ mempool_exit(&oldpool);
return 0;
}
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index eb84bc6..e7ccad89 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -118,10 +118,10 @@ struct r1conf {
* mempools - it changes when the array grows or shrinks
*/
struct pool_info *poolinfo;
- mempool_t *r1bio_pool;
- mempool_t *r1buf_pool;
+ mempool_t r1bio_pool;
+ mempool_t r1buf_pool;
- struct bio_set *bio_split;
+ struct bio_set bio_split;
/* temporary buffer to synchronous IO when attempting to repair
* a read error.
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 3c60774..37d4b23 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -291,14 +291,14 @@ static void free_r10bio(struct r10bio *r10_bio)
struct r10conf *conf = r10_bio->mddev->private;
put_all_bios(conf, r10_bio);
- mempool_free(r10_bio, conf->r10bio_pool);
+ mempool_free(r10_bio, &conf->r10bio_pool);
}
static void put_buf(struct r10bio *r10_bio)
{
struct r10conf *conf = r10_bio->mddev->private;
- mempool_free(r10_bio, conf->r10buf_pool);
+ mempool_free(r10_bio, &conf->r10buf_pool);
lower_barrier(conf);
}
@@ -1204,7 +1204,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
(unsigned long long)r10_bio->sector);
if (max_sectors < bio_sectors(bio)) {
struct bio *split = bio_split(bio, max_sectors,
- gfp, conf->bio_split);
+ gfp, &conf->bio_split);
bio_chain(split, bio);
generic_make_request(bio);
bio = split;
@@ -1213,7 +1213,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
}
slot = r10_bio->read_slot;
- read_bio = bio_clone_fast(bio, gfp, mddev->bio_set);
+ read_bio = bio_clone_fast(bio, gfp, &mddev->bio_set);
r10_bio->devs[slot].bio = read_bio;
r10_bio->devs[slot].rdev = rdev;
@@ -1261,7 +1261,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
} else
rdev = conf->mirrors[devnum].rdev;
- mbio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
+ mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
if (replacement)
r10_bio->devs[n_copy].repl_bio = mbio;
else
@@ -1509,7 +1509,7 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
if (r10_bio->sectors < bio_sectors(bio)) {
struct bio *split = bio_split(bio, r10_bio->sectors,
- GFP_NOIO, conf->bio_split);
+ GFP_NOIO, &conf->bio_split);
bio_chain(split, bio);
generic_make_request(bio);
bio = split;
@@ -1533,7 +1533,7 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
struct r10conf *conf = mddev->private;
struct r10bio *r10_bio;
- r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
+ r10_bio = mempool_alloc(&conf->r10bio_pool, GFP_NOIO);
r10_bio->master_bio = bio;
r10_bio->sectors = sectors;
@@ -1732,8 +1732,7 @@ static void close_sync(struct r10conf *conf)
wait_barrier(conf);
allow_barrier(conf);
- mempool_destroy(conf->r10buf_pool);
- conf->r10buf_pool = NULL;
+ mempool_exit(&conf->r10buf_pool);
}
static int raid10_spare_active(struct mddev *mddev)
@@ -2583,7 +2582,7 @@ static int narrow_write_error(struct r10bio *r10_bio, int i)
if (sectors > sect_to_write)
sectors = sect_to_write;
/* Write at 'sector' for 'sectors' */
- wbio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
+ wbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
bio_trim(wbio, sector - bio->bi_iter.bi_sector, sectors);
wsector = r10_bio->devs[i].addr + (sector - r10_bio->sector);
wbio->bi_iter.bi_sector = wsector +
@@ -2816,25 +2815,25 @@ static void raid10d(struct md_thread *thread)
static int init_resync(struct r10conf *conf)
{
- int buffs;
- int i;
+ int ret, buffs, i;
buffs = RESYNC_WINDOW / RESYNC_BLOCK_SIZE;
- BUG_ON(conf->r10buf_pool);
+ BUG_ON(mempool_initialized(&conf->r10buf_pool));
conf->have_replacement = 0;
for (i = 0; i < conf->geo.raid_disks; i++)
if (conf->mirrors[i].replacement)
conf->have_replacement = 1;
- conf->r10buf_pool = mempool_create(buffs, r10buf_pool_alloc, r10buf_pool_free, conf);
- if (!conf->r10buf_pool)
- return -ENOMEM;
+ ret = mempool_init(&conf->r10buf_pool, buffs,
+ r10buf_pool_alloc, r10buf_pool_free, conf);
+ if (ret)
+ return ret;
conf->next_resync = 0;
return 0;
}
static struct r10bio *raid10_alloc_init_r10buf(struct r10conf *conf)
{
- struct r10bio *r10bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+ struct r10bio *r10bio = mempool_alloc(&conf->r10buf_pool, GFP_NOIO);
struct rsync_pages *rp;
struct bio *bio;
int nalloc;
@@ -2945,7 +2944,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
sector_t chunk_mask = conf->geo.chunk_mask;
int page_idx = 0;
- if (!conf->r10buf_pool)
+ if (!mempool_initialized(&conf->r10buf_pool))
if (init_resync(conf))
return 0;
@@ -3699,13 +3698,13 @@ static struct r10conf *setup_conf(struct mddev *mddev)
conf->geo = geo;
conf->copies = copies;
- conf->r10bio_pool = mempool_create(NR_RAID10_BIOS, r10bio_pool_alloc,
- r10bio_pool_free, conf);
- if (!conf->r10bio_pool)
+ err = mempool_init(&conf->r10bio_pool, NR_RAID10_BIOS, r10bio_pool_alloc,
+ r10bio_pool_free, conf);
+ if (err)
goto out;
- conf->bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
- if (!conf->bio_split)
+ err = bioset_init(&conf->bio_split, BIO_POOL_SIZE, 0, 0);
+ if (err)
goto out;
calc_sectors(conf, mddev->dev_sectors);
@@ -3733,6 +3732,7 @@ static struct r10conf *setup_conf(struct mddev *mddev)
init_waitqueue_head(&conf->wait_barrier);
atomic_set(&conf->nr_pending, 0);
+ err = -ENOMEM;
conf->thread = md_register_thread(raid10d, mddev, "raid10");
if (!conf->thread)
goto out;
@@ -3742,11 +3742,10 @@ static struct r10conf *setup_conf(struct mddev *mddev)
out:
if (conf) {
- mempool_destroy(conf->r10bio_pool);
+ mempool_exit(&conf->r10bio_pool);
kfree(conf->mirrors);
safe_put_page(conf->tmppage);
- if (conf->bio_split)
- bioset_free(conf->bio_split);
+ bioset_exit(&conf->bio_split);
kfree(conf);
}
return ERR_PTR(err);
@@ -3953,7 +3952,7 @@ static int raid10_run(struct mddev *mddev)
out_free_conf:
md_unregister_thread(&mddev->thread);
- mempool_destroy(conf->r10bio_pool);
+ mempool_exit(&conf->r10bio_pool);
safe_put_page(conf->tmppage);
kfree(conf->mirrors);
kfree(conf);
@@ -3966,13 +3965,12 @@ static void raid10_free(struct mddev *mddev, void *priv)
{
struct r10conf *conf = priv;
- mempool_destroy(conf->r10bio_pool);
+ mempool_exit(&conf->r10bio_pool);
safe_put_page(conf->tmppage);
kfree(conf->mirrors);
kfree(conf->mirrors_old);
kfree(conf->mirrors_new);
- if (conf->bio_split)
- bioset_free(conf->bio_split);
+ bioset_exit(&conf->bio_split);
kfree(conf);
}
@@ -4543,7 +4541,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
* on all the target devices.
*/
// FIXME
- mempool_free(r10_bio, conf->r10buf_pool);
+ mempool_free(r10_bio, &conf->r10buf_pool);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
return sectors_done;
}
diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h
index e2e8840..d3eaaf3 100644
--- a/drivers/md/raid10.h
+++ b/drivers/md/raid10.h
@@ -93,10 +93,10 @@ struct r10conf {
*/
wait_queue_head_t wait_barrier;
- mempool_t *r10bio_pool;
- mempool_t *r10buf_pool;
+ mempool_t r10bio_pool;
+ mempool_t r10buf_pool;
struct page *tmppage;
- struct bio_set *bio_split;
+ struct bio_set bio_split;
/* When taking over an array from a different personality, we store
* the new thread here until we fully activate the array.
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 3c65f52..2b775ab 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -125,9 +125,9 @@ struct r5l_log {
struct list_head no_mem_stripes; /* pending stripes, -ENOMEM */
struct kmem_cache *io_kc;
- mempool_t *io_pool;
- struct bio_set *bs;
- mempool_t *meta_pool;
+ mempool_t io_pool;
+ struct bio_set bs;
+ mempool_t meta_pool;
struct md_thread *reclaim_thread;
unsigned long reclaim_target; /* number of space that need to be
@@ -579,7 +579,7 @@ static void r5l_log_endio(struct bio *bio)
md_error(log->rdev->mddev, log->rdev);
bio_put(bio);
- mempool_free(io->meta_page, log->meta_pool);
+ mempool_free(io->meta_page, &log->meta_pool);
spin_lock_irqsave(&log->io_list_lock, flags);
__r5l_set_io_unit_state(io, IO_UNIT_IO_END);
@@ -748,7 +748,7 @@ static void r5l_submit_current_io(struct r5l_log *log)
static struct bio *r5l_bio_alloc(struct r5l_log *log)
{
- struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES, log->bs);
+ struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES, &log->bs);
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
bio_set_dev(bio, log->rdev->bdev);
@@ -780,7 +780,7 @@ static struct r5l_io_unit *r5l_new_meta(struct r5l_log *log)
struct r5l_io_unit *io;
struct r5l_meta_block *block;
- io = mempool_alloc(log->io_pool, GFP_ATOMIC);
+ io = mempool_alloc(&log->io_pool, GFP_ATOMIC);
if (!io)
return NULL;
memset(io, 0, sizeof(*io));
@@ -791,7 +791,7 @@ static struct r5l_io_unit *r5l_new_meta(struct r5l_log *log)
bio_list_init(&io->flush_barriers);
io->state = IO_UNIT_RUNNING;
- io->meta_page = mempool_alloc(log->meta_pool, GFP_NOIO);
+ io->meta_page = mempool_alloc(&log->meta_pool, GFP_NOIO);
block = page_address(io->meta_page);
clear_page(block);
block->magic = cpu_to_le32(R5LOG_MAGIC);
@@ -1223,7 +1223,7 @@ static bool r5l_complete_finished_ios(struct r5l_log *log)
log->next_checkpoint = io->log_start;
list_del(&io->log_sibling);
- mempool_free(io, log->io_pool);
+ mempool_free(io, &log->io_pool);
r5l_run_no_mem_stripe(log);
found = true;
@@ -1647,7 +1647,7 @@ static int r5l_recovery_allocate_ra_pool(struct r5l_log *log,
{
struct page *page;
- ctx->ra_bio = bio_alloc_bioset(GFP_KERNEL, BIO_MAX_PAGES, log->bs);
+ ctx->ra_bio = bio_alloc_bioset(GFP_KERNEL, BIO_MAX_PAGES, &log->bs);
if (!ctx->ra_bio)
return -ENOMEM;
@@ -3066,6 +3066,7 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
struct request_queue *q = bdev_get_queue(rdev->bdev);
struct r5l_log *log;
char b[BDEVNAME_SIZE];
+ int ret;
pr_debug("md/raid:%s: using device %s as journal\n",
mdname(conf->mddev), bdevname(rdev->bdev, b));
@@ -3111,16 +3112,16 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
if (!log->io_kc)
goto io_kc;
- log->io_pool = mempool_create_slab_pool(R5L_POOL_SIZE, log->io_kc);
- if (!log->io_pool)
+ ret = mempool_init_slab_pool(&log->io_pool, R5L_POOL_SIZE, log->io_kc);
+ if (ret)
goto io_pool;
- log->bs = bioset_create(R5L_POOL_SIZE, 0, BIOSET_NEED_BVECS);
- if (!log->bs)
+ ret = bioset_init(&log->bs, R5L_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+ if (ret)
goto io_bs;
- log->meta_pool = mempool_create_page_pool(R5L_POOL_SIZE, 0);
- if (!log->meta_pool)
+ ret = mempool_init_page_pool(&log->meta_pool, R5L_POOL_SIZE, 0);
+ if (ret)
goto out_mempool;
spin_lock_init(&log->tree_lock);
@@ -3155,11 +3156,11 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
rcu_assign_pointer(conf->log, NULL);
md_unregister_thread(&log->reclaim_thread);
reclaim_thread:
- mempool_destroy(log->meta_pool);
+ mempool_exit(&log->meta_pool);
out_mempool:
- bioset_free(log->bs);
+ bioset_exit(&log->bs);
io_bs:
- mempool_destroy(log->io_pool);
+ mempool_exit(&log->io_pool);
io_pool:
kmem_cache_destroy(log->io_kc);
io_kc:
@@ -3178,9 +3179,9 @@ void r5l_exit_log(struct r5conf *conf)
wake_up(&conf->mddev->sb_wait);
flush_work(&log->disable_writeback_work);
md_unregister_thread(&log->reclaim_thread);
- mempool_destroy(log->meta_pool);
- bioset_free(log->bs);
- mempool_destroy(log->io_pool);
+ mempool_exit(&log->meta_pool);
+ bioset_exit(&log->bs);
+ mempool_exit(&log->io_pool);
kmem_cache_destroy(log->io_kc);
kfree(log);
}
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index 42890a08..3a7c363 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -105,9 +105,9 @@ struct ppl_conf {
atomic64_t seq; /* current log write sequence number */
struct kmem_cache *io_kc;
- mempool_t *io_pool;
- struct bio_set *bs;
- struct bio_set *flush_bs;
+ mempool_t io_pool;
+ struct bio_set bs;
+ struct bio_set flush_bs;
/* used only for recovery */
int recovered_entries;
@@ -244,7 +244,7 @@ static struct ppl_io_unit *ppl_new_iounit(struct ppl_log *log,
struct ppl_header *pplhdr;
struct page *header_page;
- io = mempool_alloc(ppl_conf->io_pool, GFP_NOWAIT);
+ io = mempool_alloc(&ppl_conf->io_pool, GFP_NOWAIT);
if (!io)
return NULL;
@@ -503,7 +503,7 @@ static void ppl_submit_iounit(struct ppl_io_unit *io)
struct bio *prev = bio;
bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES,
- ppl_conf->bs);
+ &ppl_conf->bs);
bio->bi_opf = prev->bi_opf;
bio_copy_dev(bio, prev);
bio->bi_iter.bi_sector = bio_end_sector(prev);
@@ -570,7 +570,7 @@ static void ppl_io_unit_finished(struct ppl_io_unit *io)
list_del(&io->log_sibling);
spin_unlock(&log->io_list_lock);
- mempool_free(io, ppl_conf->io_pool);
+ mempool_free(io, &ppl_conf->io_pool);
spin_lock(&ppl_conf->no_mem_stripes_lock);
if (!list_empty(&ppl_conf->no_mem_stripes)) {
@@ -642,7 +642,7 @@ static void ppl_do_flush(struct ppl_io_unit *io)
struct bio *bio;
char b[BDEVNAME_SIZE];
- bio = bio_alloc_bioset(GFP_NOIO, 0, ppl_conf->flush_bs);
+ bio = bio_alloc_bioset(GFP_NOIO, 0, &ppl_conf->flush_bs);
bio_set_dev(bio, bdev);
bio->bi_private = io;
bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
@@ -1246,11 +1246,9 @@ static void __ppl_exit_log(struct ppl_conf *ppl_conf)
kfree(ppl_conf->child_logs);
- if (ppl_conf->bs)
- bioset_free(ppl_conf->bs);
- if (ppl_conf->flush_bs)
- bioset_free(ppl_conf->flush_bs);
- mempool_destroy(ppl_conf->io_pool);
+ bioset_exit(&ppl_conf->bs);
+ bioset_exit(&ppl_conf->flush_bs);
+ mempool_exit(&ppl_conf->io_pool);
kmem_cache_destroy(ppl_conf->io_kc);
kfree(ppl_conf);
@@ -1387,24 +1385,18 @@ int ppl_init_log(struct r5conf *conf)
goto err;
}
- ppl_conf->io_pool = mempool_create(conf->raid_disks, ppl_io_pool_alloc,
- ppl_io_pool_free, ppl_conf->io_kc);
- if (!ppl_conf->io_pool) {
- ret = -ENOMEM;
+ ret = mempool_init(&ppl_conf->io_pool, conf->raid_disks, ppl_io_pool_alloc,
+ ppl_io_pool_free, ppl_conf->io_kc);
+ if (ret)
goto err;
- }
- ppl_conf->bs = bioset_create(conf->raid_disks, 0, BIOSET_NEED_BVECS);
- if (!ppl_conf->bs) {
- ret = -ENOMEM;
+ ret = bioset_init(&ppl_conf->bs, conf->raid_disks, 0, BIOSET_NEED_BVECS);
+ if (ret)
goto err;
- }
- ppl_conf->flush_bs = bioset_create(conf->raid_disks, 0, 0);
- if (!ppl_conf->flush_bs) {
- ret = -ENOMEM;
+ ret = bioset_init(&ppl_conf->flush_bs, conf->raid_disks, 0, 0);
+ if (ret)
goto err;
- }
ppl_conf->count = conf->raid_disks;
ppl_conf->child_logs = kcalloc(ppl_conf->count, sizeof(struct ppl_log),
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index be117d0..a2e6498 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5192,7 +5192,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
/*
* use bio_clone_fast to make a copy of the bio
*/
- align_bi = bio_clone_fast(raid_bio, GFP_NOIO, mddev->bio_set);
+ align_bi = bio_clone_fast(raid_bio, GFP_NOIO, &mddev->bio_set);
if (!align_bi)
return 0;
/*
@@ -5277,7 +5277,7 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
if (sectors < bio_sectors(raid_bio)) {
struct r5conf *conf = mddev->private;
- split = bio_split(raid_bio, sectors, GFP_NOIO, conf->bio_split);
+ split = bio_split(raid_bio, sectors, GFP_NOIO, &conf->bio_split);
bio_chain(split, raid_bio);
generic_make_request(raid_bio);
raid_bio = split;
@@ -6773,8 +6773,7 @@ static void free_conf(struct r5conf *conf)
if (conf->disks[i].extra_page)
put_page(conf->disks[i].extra_page);
kfree(conf->disks);
- if (conf->bio_split)
- bioset_free(conf->bio_split);
+ bioset_exit(&conf->bio_split);
kfree(conf->stripe_hashtbl);
kfree(conf->pending_data);
kfree(conf);
@@ -6853,6 +6852,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
int i;
int group_cnt, worker_cnt_per_group;
struct r5worker_group *new_group;
+ int ret;
if (mddev->new_level != 5
&& mddev->new_level != 4
@@ -6950,8 +6950,8 @@ static struct r5conf *setup_conf(struct mddev *mddev)
goto abort;
}
- conf->bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
- if (!conf->bio_split)
+ ret = bioset_init(&conf->bio_split, BIO_POOL_SIZE, 0, 0);
+ if (ret)
goto abort;
conf->mddev = mddev;
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 3f8da26..72e75ba 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -669,7 +669,7 @@ struct r5conf {
int pool_size; /* number of disks in stripeheads in pool */
spinlock_t device_lock;
struct disk_info *disks;
- struct bio_set *bio_split;
+ struct bio_set bio_split;
/* When taking over an array from a different personality, we store
* the new thread here until we fully activate the array.
diff --git a/drivers/media/i2c/saa7115.c b/drivers/media/i2c/saa7115.c
index e216cd7..b07114b 100644
--- a/drivers/media/i2c/saa7115.c
+++ b/drivers/media/i2c/saa7115.c
@@ -20,7 +20,7 @@
//
// VBI support (2004) and cleanups (2005) by Hans Verkuil <hverkuil@xs4all.nl>
//
-// Copyright (c) 2005-2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (c) 2005-2006 Mauro Carvalho Chehab <mchehab@kernel.org>
// SAA7111, SAA7113 and SAA7118 support
#include "saa711x_regs.h"
diff --git a/drivers/media/i2c/saa711x_regs.h b/drivers/media/i2c/saa711x_regs.h
index a50d480..44fabe0 100644
--- a/drivers/media/i2c/saa711x_regs.h
+++ b/drivers/media/i2c/saa711x_regs.h
@@ -2,7 +2,7 @@
* SPDX-License-Identifier: GPL-2.0+
* saa711x - Philips SAA711x video decoder register specifications
*
- * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@kernel.org>
*/
#define R_00_CHIP_VERSION 0x00
diff --git a/drivers/media/i2c/tda7432.c b/drivers/media/i2c/tda7432.c
index 1c5c61d..9b4f212 100644
--- a/drivers/media/i2c/tda7432.c
+++ b/drivers/media/i2c/tda7432.c
@@ -8,7 +8,7 @@
* Muting and tone control by Jonathan Isom <jisom@ematic.com>
*
* Copyright (c) 2000 Eric Sandeen <eric_sandeen@bigfoot.com>
- * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@kernel.org>
* This code is placed under the terms of the GNU General Public License
* Based on tda9855.c by Steve VanDeBogart (vandebo@uclink.berkeley.edu)
* Which was based on tda8425.c by Greg Alexander (c) 1998
diff --git a/drivers/media/i2c/tvp5150.c b/drivers/media/i2c/tvp5150.c
index 2476d81..1734ed4 100644
--- a/drivers/media/i2c/tvp5150.c
+++ b/drivers/media/i2c/tvp5150.c
@@ -2,7 +2,7 @@
//
// tvp5150 - Texas Instruments TVP5150A/AM1 and TVP5151 video decoder driver
//
-// Copyright (c) 2005,2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (c) 2005,2006 Mauro Carvalho Chehab <mchehab@kernel.org>
#include <dt-bindings/media/tvp5150.h>
#include <linux/i2c.h>
diff --git a/drivers/media/i2c/tvp5150_reg.h b/drivers/media/i2c/tvp5150_reg.h
index c43b7b8..d3a764c 100644
--- a/drivers/media/i2c/tvp5150_reg.h
+++ b/drivers/media/i2c/tvp5150_reg.h
@@ -3,7 +3,7 @@
*
* tvp5150 - Texas Instruments TVP5150A/AM1 video decoder registers
*
- * Copyright (c) 2005,2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2005,2006 Mauro Carvalho Chehab <mchehab@kernel.org>
*/
#define TVP5150_VD_IN_SRC_SEL_1 0x00 /* Video input source selection #1 */
diff --git a/drivers/media/i2c/tvp7002.c b/drivers/media/i2c/tvp7002.c
index a26c1a3..4599b7e 100644
--- a/drivers/media/i2c/tvp7002.c
+++ b/drivers/media/i2c/tvp7002.c
@@ -5,7 +5,7 @@
* Author: Santiago Nunez-Corrales <santiago.nunez@ridgerun.com>
*
* This code is partially based upon the TVP5150 driver
- * written by Mauro Carvalho Chehab (mchehab@infradead.org),
+ * written by Mauro Carvalho Chehab <mchehab@kernel.org>,
* the TVP514x driver written by Vaibhav Hiremath <hvaibhav@ti.com>
* and the TVP7002 driver in the TI LSP 2.10.00.14. Revisions by
* Muralidharan Karicheri and Snehaprabha Narnakaje (TI).
diff --git a/drivers/media/i2c/tvp7002_reg.h b/drivers/media/i2c/tvp7002_reg.h
index 3c8c8b0..7f56ba6 100644
--- a/drivers/media/i2c/tvp7002_reg.h
+++ b/drivers/media/i2c/tvp7002_reg.h
@@ -5,7 +5,7 @@
* Author: Santiago Nunez-Corrales <santiago.nunez@ridgerun.com>
*
* This code is partially based upon the TVP5150 driver
- * written by Mauro Carvalho Chehab (mchehab@infradead.org),
+ * written by Mauro Carvalho Chehab <mchehab@kernel.org>,
* the TVP514x driver written by Vaibhav Hiremath <hvaibhav@ti.com>
* and the TVP7002 driver in the TI LSP 2.10.00.14
*
diff --git a/drivers/media/media-devnode.c b/drivers/media/media-devnode.c
index 67ac51e..6b87a72 100644
--- a/drivers/media/media-devnode.c
+++ b/drivers/media/media-devnode.c
@@ -4,7 +4,7 @@
* Copyright (C) 2010 Nokia Corporation
*
* Based on drivers/media/video/v4l2_dev.c code authored by
- * Mauro Carvalho Chehab <mchehab@infradead.org> (version 2)
+ * Mauro Carvalho Chehab <mchehab@kernel.org> (version 2)
* Alan Cox, <alan@lxorguk.ukuu.org.uk> (version 1)
*
* Contacts: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
diff --git a/drivers/media/pci/bt8xx/bttv-audio-hook.c b/drivers/media/pci/bt8xx/bttv-audio-hook.c
index 9f1f9169..346fc7f 100644
--- a/drivers/media/pci/bt8xx/bttv-audio-hook.c
+++ b/drivers/media/pci/bt8xx/bttv-audio-hook.c
@@ -1,7 +1,7 @@
/*
* Handlers for board audio hooks, splitted from bttv-cards
*
- * Copyright (c) 2006 Mauro Carvalho Chehab (mchehab@infradead.org)
+ * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@kernel.org>
* This code is placed under the terms of the GNU General Public License
*/
diff --git a/drivers/media/pci/bt8xx/bttv-audio-hook.h b/drivers/media/pci/bt8xx/bttv-audio-hook.h
index 159d07a..be16a53 100644
--- a/drivers/media/pci/bt8xx/bttv-audio-hook.h
+++ b/drivers/media/pci/bt8xx/bttv-audio-hook.h
@@ -1,7 +1,7 @@
/*
* Handlers for board audio hooks, splitted from bttv-cards
*
- * Copyright (c) 2006 Mauro Carvalho Chehab (mchehab@infradead.org)
+ * Copyright (c) 2006 Mauro Carvalho Chehab <mchehab@kernel.org>
* This code is placed under the terms of the GNU General Public License
*/
diff --git a/drivers/media/pci/bt8xx/bttv-cards.c b/drivers/media/pci/bt8xx/bttv-cards.c
index 1902732..2616243 100644
--- a/drivers/media/pci/bt8xx/bttv-cards.c
+++ b/drivers/media/pci/bt8xx/bttv-cards.c
@@ -2447,7 +2447,7 @@ struct tvcard bttv_tvcards[] = {
},
/* ---- card 0x88---------------------------------- */
[BTTV_BOARD_ACORP_Y878F] = {
- /* Mauro Carvalho Chehab <mchehab@infradead.org> */
+ /* Mauro Carvalho Chehab <mchehab@kernel.org> */
.name = "Acorp Y878F",
.video_inputs = 3,
/* .audio_inputs= 1, */
@@ -2688,7 +2688,7 @@ struct tvcard bttv_tvcards[] = {
},
[BTTV_BOARD_ENLTV_FM_2] = {
/* Encore TV Tuner Pro ENL TV-FM-2
- Mauro Carvalho Chehab <mchehab@infradead.org */
+ Mauro Carvalho Chehab <mchehab@kernel.org> */
.name = "Encore ENL TV-FM-2",
.video_inputs = 3,
/* .audio_inputs= 1, */
diff --git a/drivers/media/pci/bt8xx/bttv-driver.c b/drivers/media/pci/bt8xx/bttv-driver.c
index 707f57a..de3f44b 100644
--- a/drivers/media/pci/bt8xx/bttv-driver.c
+++ b/drivers/media/pci/bt8xx/bttv-driver.c
@@ -13,7 +13,7 @@
(c) 2005-2006 Nickolay V. Shmyrev <nshmyrev@yandex.ru>
Fixes to be fully V4L2 compliant by
- (c) 2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ (c) 2006 Mauro Carvalho Chehab <mchehab@kernel.org>
Cropping and overscan support
Copyright (C) 2005, 2006 Michael H. Schimek <mschimek@gmx.at>
diff --git a/drivers/media/pci/bt8xx/bttv-i2c.c b/drivers/media/pci/bt8xx/bttv-i2c.c
index eccd1e3..c76823e 100644
--- a/drivers/media/pci/bt8xx/bttv-i2c.c
+++ b/drivers/media/pci/bt8xx/bttv-i2c.c
@@ -8,7 +8,7 @@
& Marcus Metzler (mocm@thp.uni-koeln.de)
(c) 1999-2003 Gerd Knorr <kraxel@bytesex.org>
- (c) 2005 Mauro Carvalho Chehab <mchehab@infradead.org>
+ (c) 2005 Mauro Carvalho Chehab <mchehab@kernel.org>
- Multituner support and i2c address binding
This program is free software; you can redistribute it and/or modify
diff --git a/drivers/media/pci/cx23885/cx23885-input.c b/drivers/media/pci/cx23885/cx23885-input.c
index be49589..395ff9b 100644
--- a/drivers/media/pci/cx23885/cx23885-input.c
+++ b/drivers/media/pci/cx23885/cx23885-input.c
@@ -13,7 +13,7 @@
* Copyright (C) 2008 <srinivasa.deevi at conexant dot com>
* Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it>
* Markus Rechberger <mrechberger@gmail.com>
- * Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Mauro Carvalho Chehab <mchehab@kernel.org>
* Sascha Sommer <saschasommer@freenet.de>
* Copyright (C) 2004, 2005 Chris Pascoe
* Copyright (C) 2003, 2004 Gerd Knorr
diff --git a/drivers/media/pci/cx88/cx88-alsa.c b/drivers/media/pci/cx88/cx88-alsa.c
index ab09bb5..8a28fda 100644
--- a/drivers/media/pci/cx88/cx88-alsa.c
+++ b/drivers/media/pci/cx88/cx88-alsa.c
@@ -4,7 +4,7 @@
*
* (c) 2007 Trent Piepho <xyzzy@speakeasy.org>
* (c) 2005,2006 Ricardo Cerqueira <v4l@cerqueira.org>
- * (c) 2005 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * (c) 2005 Mauro Carvalho Chehab <mchehab@kernel.org>
* Based on a dummy cx88 module by Gerd Knorr <kraxel@bytesex.org>
* Based on dummy.c by Jaroslav Kysela <perex@perex.cz>
*
@@ -103,7 +103,7 @@ MODULE_PARM_DESC(index, "Index value for cx88x capture interface(s).");
MODULE_DESCRIPTION("ALSA driver module for cx2388x based TV cards");
MODULE_AUTHOR("Ricardo Cerqueira");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
MODULE_LICENSE("GPL");
MODULE_VERSION(CX88_VERSION);
diff --git a/drivers/media/pci/cx88/cx88-blackbird.c b/drivers/media/pci/cx88/cx88-blackbird.c
index 0e0952e..7a4876c 100644
--- a/drivers/media/pci/cx88/cx88-blackbird.c
+++ b/drivers/media/pci/cx88/cx88-blackbird.c
@@ -5,7 +5,7 @@
* (c) 2004 Jelle Foks <jelle@foks.us>
* (c) 2004 Gerd Knorr <kraxel@bytesex.org>
*
- * (c) 2005-2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * (c) 2005-2006 Mauro Carvalho Chehab <mchehab@kernel.org>
* - video_ioctl2 conversion
*
* Includes parts from the ivtv driver <http://sourceforge.net/projects/ivtv/>
diff --git a/drivers/media/pci/cx88/cx88-core.c b/drivers/media/pci/cx88/cx88-core.c
index 8bfa5b7..60988e9 100644
--- a/drivers/media/pci/cx88/cx88-core.c
+++ b/drivers/media/pci/cx88/cx88-core.c
@@ -4,7 +4,7 @@
*
* (c) 2003 Gerd Knorr <kraxel@bytesex.org> [SuSE Labs]
*
- * (c) 2005-2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * (c) 2005-2006 Mauro Carvalho Chehab <mchehab@kernel.org>
* - Multituner support
* - video_ioctl2 conversion
* - PAL/M fixes
diff --git a/drivers/media/pci/cx88/cx88-i2c.c b/drivers/media/pci/cx88/cx88-i2c.c
index f769277..99f88a0 100644
--- a/drivers/media/pci/cx88/cx88-i2c.c
+++ b/drivers/media/pci/cx88/cx88-i2c.c
@@ -8,7 +8,7 @@
* (c) 2002 Yurij Sysoev <yurij@naturesoft.net>
* (c) 1999-2003 Gerd Knorr <kraxel@bytesex.org>
*
- * (c) 2005 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * (c) 2005 Mauro Carvalho Chehab <mchehab@kernel.org>
* - Multituner support and i2c address binding
*
* This program is free software; you can redistribute it and/or modify
diff --git a/drivers/media/pci/cx88/cx88-video.c b/drivers/media/pci/cx88/cx88-video.c
index 9be682c..7b113ba 100644
--- a/drivers/media/pci/cx88/cx88-video.c
+++ b/drivers/media/pci/cx88/cx88-video.c
@@ -5,7 +5,7 @@
*
* (c) 2003-04 Gerd Knorr <kraxel@bytesex.org> [SuSE Labs]
*
- * (c) 2005-2006 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * (c) 2005-2006 Mauro Carvalho Chehab <mchehab@kernel.org>
* - Multituner support
* - video_ioctl2 conversion
* - PAL/M fixes
diff --git a/drivers/media/pci/saa7164/saa7164-core.c b/drivers/media/pci/saa7164/saa7164-core.c
index fca36a4..d697e1a 100644
--- a/drivers/media/pci/saa7164/saa7164-core.c
+++ b/drivers/media/pci/saa7164/saa7164-core.c
@@ -1122,23 +1122,11 @@ static int saa7164_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int saa7164_proc_open(struct inode *inode, struct file *filp)
-{
- return single_open(filp, saa7164_proc_show, NULL);
-}
-
-static const struct file_operations saa7164_proc_fops = {
- .open = saa7164_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int saa7164_proc_create(void)
{
struct proc_dir_entry *pe;
- pe = proc_create("saa7164", S_IRUGO, NULL, &saa7164_proc_fops);
+ pe = proc_create_single("saa7164", S_IRUGO, NULL, saa7164_proc_show);
if (!pe)
return -ENOMEM;
diff --git a/drivers/media/pci/zoran/videocodec.c b/drivers/media/pci/zoran/videocodec.c
index 5ff23ef..4427ae7 100644
--- a/drivers/media/pci/zoran/videocodec.c
+++ b/drivers/media/pci/zoran/videocodec.c
@@ -344,19 +344,6 @@ static int proc_videocodecs_show(struct seq_file *m, void *v)
return 0;
}
-
-static int proc_videocodecs_open(struct inode *inode, struct file *file)
-{
- return single_open(file, proc_videocodecs_show, NULL);
-}
-
-static const struct file_operations videocodecs_proc_fops = {
- .owner = THIS_MODULE,
- .open = proc_videocodecs_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif
/* ===================== */
@@ -373,7 +360,8 @@ videocodec_init (void)
VIDEOCODEC_VERSION);
#ifdef CONFIG_PROC_FS
- videocodec_proc_entry = proc_create("videocodecs", 0, NULL, &videocodecs_proc_fops);
+ videocodec_proc_entry = proc_create_single("videocodecs", 0, NULL,
+ proc_videocodecs_show);
if (!videocodec_proc_entry) {
dprintk(1, KERN_ERR "videocodec: can't init procfs.\n");
}
diff --git a/drivers/media/radio/radio-aimslab.c b/drivers/media/radio/radio-aimslab.c
index 5ef635e..4c52ac6 100644
--- a/drivers/media/radio/radio-aimslab.c
+++ b/drivers/media/radio/radio-aimslab.c
@@ -4,7 +4,7 @@
* Copyright 1997 M. Kirkwood
*
* Converted to the radio-isa framework by Hans Verkuil <hans.verkuil@cisco.com>
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
* Converted to new API by Alan Cox <alan@lxorguk.ukuu.org.uk>
* Various bugfixes and enhancements by Russell Kroll <rkroll@exploits.org>
*
diff --git a/drivers/media/radio/radio-aztech.c b/drivers/media/radio/radio-aztech.c
index 9e12c60..840b7d6 100644
--- a/drivers/media/radio/radio-aztech.c
+++ b/drivers/media/radio/radio-aztech.c
@@ -2,7 +2,7 @@
* radio-aztech.c - Aztech radio card driver
*
* Converted to the radio-isa framework by Hans Verkuil <hans.verkuil@xs4all.nl>
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
* Adapted to support the Video for Linux API by
* Russell Kroll <rkroll@exploits.org>. Based on original tuner code by:
*
diff --git a/drivers/media/radio/radio-gemtek.c b/drivers/media/radio/radio-gemtek.c
index 3ff4c4e..f051f86 100644
--- a/drivers/media/radio/radio-gemtek.c
+++ b/drivers/media/radio/radio-gemtek.c
@@ -15,7 +15,7 @@
* Various bugfixes and enhancements by Russell Kroll <rkroll@exploits.org>
*
* Converted to the radio-isa framework by Hans Verkuil <hans.verkuil@cisco.com>
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
*
* Note: this card seems to swap the left and right audio channels!
*
diff --git a/drivers/media/radio/radio-maxiradio.c b/drivers/media/radio/radio-maxiradio.c
index 95f06f3..e4e7587 100644
--- a/drivers/media/radio/radio-maxiradio.c
+++ b/drivers/media/radio/radio-maxiradio.c
@@ -27,7 +27,7 @@
* BUGS:
* - card unmutes if you change frequency
*
- * (c) 2006, 2007 by Mauro Carvalho Chehab <mchehab@infradead.org>:
+ * (c) 2006, 2007 by Mauro Carvalho Chehab <mchehab@kernel.org>:
* - Conversion to V4L2 API
* - Uses video_ioctl2 for parsing and to add debug support
*/
diff --git a/drivers/media/radio/radio-rtrack2.c b/drivers/media/radio/radio-rtrack2.c
index abeaedd..5a1470e 100644
--- a/drivers/media/radio/radio-rtrack2.c
+++ b/drivers/media/radio/radio-rtrack2.c
@@ -7,7 +7,7 @@
* Various bugfixes and enhancements by Russell Kroll <rkroll@exploits.org>
*
* Converted to the radio-isa framework by Hans Verkuil <hans.verkuil@cisco.com>
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
*
* Fully tested with actual hardware and the v4l2-compliance tool.
*/
diff --git a/drivers/media/radio/radio-sf16fmi.c b/drivers/media/radio/radio-sf16fmi.c
index fc4e63d..4f9b97e 100644
--- a/drivers/media/radio/radio-sf16fmi.c
+++ b/drivers/media/radio/radio-sf16fmi.c
@@ -13,7 +13,7 @@
* No volume control - only mute/unmute - you have to use line volume
* control on SB-part of SF16-FMI/SF16-FMP/SF16-FMD
*
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
*/
#include <linux/kernel.h> /* __setup */
diff --git a/drivers/media/radio/radio-terratec.c b/drivers/media/radio/radio-terratec.c
index 4f116ea..1af8f29 100644
--- a/drivers/media/radio/radio-terratec.c
+++ b/drivers/media/radio/radio-terratec.c
@@ -17,7 +17,7 @@
* Volume Control is done digitally
*
* Converted to the radio-isa framework by Hans Verkuil <hans.verkuil@cisco.com>
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
*/
#include <linux/module.h> /* Modules */
diff --git a/drivers/media/radio/radio-trust.c b/drivers/media/radio/radio-trust.c
index 26a8c60..a4bad32 100644
--- a/drivers/media/radio/radio-trust.c
+++ b/drivers/media/radio/radio-trust.c
@@ -12,7 +12,7 @@
* Scott McGrath (smcgrath@twilight.vtc.vsc.edu)
* William McGrath (wmcgrath@twilight.vtc.vsc.edu)
*
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
*/
#include <stdarg.h>
diff --git a/drivers/media/radio/radio-typhoon.c b/drivers/media/radio/radio-typhoon.c
index eb72a4d..d0d67ad 100644
--- a/drivers/media/radio/radio-typhoon.c
+++ b/drivers/media/radio/radio-typhoon.c
@@ -25,7 +25,7 @@
* The frequency change is necessary since the card never seems to be
* completely silent.
*
- * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Converted to V4L2 API by Mauro Carvalho Chehab <mchehab@kernel.org>
*/
#include <linux/module.h> /* Modules */
diff --git a/drivers/media/radio/radio-zoltrix.c b/drivers/media/radio/radio-zoltrix.c
index 026e88e..6007cd0 100644
--- a/drivers/media/radio/radio-zoltrix.c
+++ b/drivers/media/radio/radio-zoltrix.c
@@ -27,7 +27,7 @@
* 2002-07-15 - Fix Stereo typo
*
* 2006-07-24 - Converted to V4L2 API
- * by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * by Mauro Carvalho Chehab <mchehab@kernel.org>
*
* Converted to the radio-isa framework by Hans Verkuil <hans.verkuil@cisco.com>
*
diff --git a/drivers/media/rc/keymaps/rc-avermedia-m135a.c b/drivers/media/rc/keymaps/rc-avermedia-m135a.c
index f6977df..d275d98 100644
--- a/drivers/media/rc/keymaps/rc-avermedia-m135a.c
+++ b/drivers/media/rc/keymaps/rc-avermedia-m135a.c
@@ -12,7 +12,7 @@
*
* On Avermedia M135A with IR model RM-JX, the same codes exist on both
* Positivo (BR) and original IR, initial version and remote control codes
- * added by Mauro Carvalho Chehab <mchehab@infradead.org>
+ * added by Mauro Carvalho Chehab <mchehab@kernel.org>
*
* Positivo also ships Avermedia M135A with model RM-K6, extra control
* codes added by Herton Ronaldo Krzesinski <herton@mandriva.com.br>
diff --git a/drivers/media/rc/keymaps/rc-encore-enltv-fm53.c b/drivers/media/rc/keymaps/rc-encore-enltv-fm53.c
index e4e78c1..057c13b 100644
--- a/drivers/media/rc/keymaps/rc-encore-enltv-fm53.c
+++ b/drivers/media/rc/keymaps/rc-encore-enltv-fm53.c
@@ -9,7 +9,7 @@
#include <linux/module.h>
/* Encore ENLTV-FM v5.3
- Mauro Carvalho Chehab <mchehab@infradead.org>
+ Mauro Carvalho Chehab <mchehab@kernel.org>
*/
static struct rc_map_table encore_enltv_fm53[] = {
diff --git a/drivers/media/rc/keymaps/rc-encore-enltv2.c b/drivers/media/rc/keymaps/rc-encore-enltv2.c
index c3d4437..cd05559 100644
--- a/drivers/media/rc/keymaps/rc-encore-enltv2.c
+++ b/drivers/media/rc/keymaps/rc-encore-enltv2.c
@@ -9,7 +9,7 @@
#include <linux/module.h>
/* Encore ENLTV2-FM - silver plastic - "Wand Media" written at the botton
- Mauro Carvalho Chehab <mchehab@infradead.org> */
+ Mauro Carvalho Chehab <mchehab@kernel.org> */
static struct rc_map_table encore_enltv2[] = {
{ 0x4c, KEY_POWER2 },
diff --git a/drivers/media/rc/keymaps/rc-kaiomy.c b/drivers/media/rc/keymaps/rc-kaiomy.c
index f0f88df..a000513 100644
--- a/drivers/media/rc/keymaps/rc-kaiomy.c
+++ b/drivers/media/rc/keymaps/rc-kaiomy.c
@@ -9,7 +9,7 @@
#include <linux/module.h>
/* Kaiomy TVnPC U2
- Mauro Carvalho Chehab <mchehab@infradead.org>
+ Mauro Carvalho Chehab <mchehab@kernel.org>
*/
static struct rc_map_table kaiomy[] = {
diff --git a/drivers/media/rc/keymaps/rc-kworld-plus-tv-analog.c b/drivers/media/rc/keymaps/rc-kworld-plus-tv-analog.c
index 453e0437..db5edde 100644
--- a/drivers/media/rc/keymaps/rc-kworld-plus-tv-analog.c
+++ b/drivers/media/rc/keymaps/rc-kworld-plus-tv-analog.c
@@ -9,7 +9,7 @@
#include <linux/module.h>
/* Kworld Plus TV Analog Lite PCI IR
- Mauro Carvalho Chehab <mchehab@infradead.org>
+ Mauro Carvalho Chehab <mchehab@kernel.org>
*/
static struct rc_map_table kworld_plus_tv_analog[] = {
diff --git a/drivers/media/rc/keymaps/rc-pixelview-new.c b/drivers/media/rc/keymaps/rc-pixelview-new.c
index 791130f..e4e34f2 100644
--- a/drivers/media/rc/keymaps/rc-pixelview-new.c
+++ b/drivers/media/rc/keymaps/rc-pixelview-new.c
@@ -9,7 +9,7 @@
#include <linux/module.h>
/*
- Mauro Carvalho Chehab <mchehab@infradead.org>
+ Mauro Carvalho Chehab <mchehab@kernel.org>
present on PV MPEG 8000GT
*/
diff --git a/drivers/media/tuners/tea5761.c b/drivers/media/tuners/tea5761.c
index 88b3e80..d78a2bd 100644
--- a/drivers/media/tuners/tea5761.c
+++ b/drivers/media/tuners/tea5761.c
@@ -2,7 +2,7 @@
// For Philips TEA5761 FM Chip
// I2C address is always 0x20 (0x10 at 7-bit mode).
//
-// Copyright (c) 2005-2007 Mauro Carvalho Chehab (mchehab@infradead.org)
+// Copyright (c) 2005-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
#include <linux/i2c.h>
#include <linux/slab.h>
@@ -337,5 +337,5 @@ EXPORT_SYMBOL_GPL(tea5761_attach);
EXPORT_SYMBOL_GPL(tea5761_autodetection);
MODULE_DESCRIPTION("Philips TEA5761 FM tuner driver");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/tuners/tea5767.c b/drivers/media/tuners/tea5767.c
index 2b2c064..016d0d5e 100644
--- a/drivers/media/tuners/tea5767.c
+++ b/drivers/media/tuners/tea5767.c
@@ -2,7 +2,7 @@
// For Philips TEA5767 FM Chip used on some TV Cards like Prolink Pixelview
// I2C address is always 0xC0.
//
-// Copyright (c) 2005 Mauro Carvalho Chehab (mchehab@infradead.org)
+// Copyright (c) 2005 Mauro Carvalho Chehab <mchehab@kernel.org>
//
// tea5767 autodetection thanks to Torsten Seeboth and Atsushi Nakagawa
// from their contributions on DScaler.
@@ -469,5 +469,5 @@ EXPORT_SYMBOL_GPL(tea5767_attach);
EXPORT_SYMBOL_GPL(tea5767_autodetection);
MODULE_DESCRIPTION("Philips TEA5767 FM tuner driver");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/tuners/tuner-xc2028-types.h b/drivers/media/tuners/tuner-xc2028-types.h
index bb0437c..50d017a 100644
--- a/drivers/media/tuners/tuner-xc2028-types.h
+++ b/drivers/media/tuners/tuner-xc2028-types.h
@@ -5,7 +5,7 @@
* This file includes internal tipes to be used inside tuner-xc2028.
* Shouldn't be included outside tuner-xc2028
*
- * Copyright (c) 2007-2008 Mauro Carvalho Chehab (mchehab@infradead.org)
+ * Copyright (c) 2007-2008 Mauro Carvalho Chehab <mchehab@kernel.org>
*/
/* xc3028 firmware types */
diff --git a/drivers/media/tuners/tuner-xc2028.c b/drivers/media/tuners/tuner-xc2028.c
index fca85e0..84744e1 100644
--- a/drivers/media/tuners/tuner-xc2028.c
+++ b/drivers/media/tuners/tuner-xc2028.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
// tuner-xc2028
//
-// Copyright (c) 2007-2008 Mauro Carvalho Chehab (mchehab@infradead.org)
+// Copyright (c) 2007-2008 Mauro Carvalho Chehab <mchehab@kernel.org>
//
// Copyright (c) 2007 Michel Ludwig (michel.ludwig@gmail.com)
// - frontend interface
@@ -1518,7 +1518,7 @@ EXPORT_SYMBOL(xc2028_attach);
MODULE_DESCRIPTION("Xceive xc2028/xc3028 tuner driver");
MODULE_AUTHOR("Michel Ludwig <michel.ludwig@gmail.com>");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
MODULE_LICENSE("GPL v2");
MODULE_FIRMWARE(XC2028_DEFAULT_FIRMWARE);
MODULE_FIRMWARE(XC3028L_DEFAULT_FIRMWARE);
diff --git a/drivers/media/tuners/tuner-xc2028.h b/drivers/media/tuners/tuner-xc2028.h
index 03fd6d4..7b58bc0 100644
--- a/drivers/media/tuners/tuner-xc2028.h
+++ b/drivers/media/tuners/tuner-xc2028.h
@@ -2,7 +2,7 @@
* SPDX-License-Identifier: GPL-2.0
* tuner-xc2028
*
- * Copyright (c) 2007-2008 Mauro Carvalho Chehab (mchehab@infradead.org)
+ * Copyright (c) 2007-2008 Mauro Carvalho Chehab <mchehab@kernel.org>
*/
#ifndef __TUNER_XC2028_H__
diff --git a/drivers/media/usb/em28xx/em28xx-camera.c b/drivers/media/usb/em28xx/em28xx-camera.c
index 3c2694a..d1e66b5 100644
--- a/drivers/media/usb/em28xx/em28xx-camera.c
+++ b/drivers/media/usb/em28xx/em28xx-camera.c
@@ -2,7 +2,7 @@
//
// em28xx-camera.c - driver for Empia EM25xx/27xx/28xx USB video capture devices
//
-// Copyright (C) 2009 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (C) 2009 Mauro Carvalho Chehab <mchehab@kernel.org>
// Copyright (C) 2013 Frank Schäfer <fschaefer.oss@googlemail.com>
//
// This program is free software; you can redistribute it and/or modify
diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c
index 6e0e67d..7c3203d 100644
--- a/drivers/media/usb/em28xx/em28xx-cards.c
+++ b/drivers/media/usb/em28xx/em28xx-cards.c
@@ -5,7 +5,7 @@
//
// Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it>
// Markus Rechberger <mrechberger@gmail.com>
-// Mauro Carvalho Chehab <mchehab@infradead.org>
+// Mauro Carvalho Chehab <mchehab@kernel.org>
// Sascha Sommer <saschasommer@freenet.de>
// Copyright (C) 2012 Frank Schäfer <fschaefer.oss@googlemail.com>
//
diff --git a/drivers/media/usb/em28xx/em28xx-core.c b/drivers/media/usb/em28xx/em28xx-core.c
index 36d341f..f289953 100644
--- a/drivers/media/usb/em28xx/em28xx-core.c
+++ b/drivers/media/usb/em28xx/em28xx-core.c
@@ -4,7 +4,7 @@
//
// Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it>
// Markus Rechberger <mrechberger@gmail.com>
-// Mauro Carvalho Chehab <mchehab@infradead.org>
+// Mauro Carvalho Chehab <mchehab@kernel.org>
// Sascha Sommer <saschasommer@freenet.de>
// Copyright (C) 2012 Frank Schäfer <fschaefer.oss@googlemail.com>
//
@@ -32,7 +32,7 @@
#define DRIVER_AUTHOR "Ludovico Cavedon <cavedon@sssup.it>, " \
"Markus Rechberger <mrechberger@gmail.com>, " \
- "Mauro Carvalho Chehab <mchehab@infradead.org>, " \
+ "Mauro Carvalho Chehab <mchehab@kernel.org>, " \
"Sascha Sommer <saschasommer@freenet.de>"
MODULE_AUTHOR(DRIVER_AUTHOR);
diff --git a/drivers/media/usb/em28xx/em28xx-dvb.c b/drivers/media/usb/em28xx/em28xx-dvb.c
index a54cb8d..3f493e0 100644
--- a/drivers/media/usb/em28xx/em28xx-dvb.c
+++ b/drivers/media/usb/em28xx/em28xx-dvb.c
@@ -2,7 +2,7 @@
//
// DVB device driver for em28xx
//
-// (c) 2008-2011 Mauro Carvalho Chehab <mchehab@infradead.org>
+// (c) 2008-2011 Mauro Carvalho Chehab <mchehab@kernel.org>
//
// (c) 2008 Devin Heitmueller <devin.heitmueller@gmail.com>
// - Fixes for the driver to properly work with HVR-950
@@ -63,7 +63,7 @@
#include "tc90522.h"
#include "qm1d1c0042.h"
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
MODULE_LICENSE("GPL v2");
MODULE_DESCRIPTION(DRIVER_DESC " - digital TV interface");
MODULE_VERSION(EM28XX_VERSION);
diff --git a/drivers/media/usb/em28xx/em28xx-i2c.c b/drivers/media/usb/em28xx/em28xx-i2c.c
index 9151bcc..6458682 100644
--- a/drivers/media/usb/em28xx/em28xx-i2c.c
+++ b/drivers/media/usb/em28xx/em28xx-i2c.c
@@ -4,7 +4,7 @@
//
// Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it>
// Markus Rechberger <mrechberger@gmail.com>
-// Mauro Carvalho Chehab <mchehab@infradead.org>
+// Mauro Carvalho Chehab <mchehab@kernel.org>
// Sascha Sommer <saschasommer@freenet.de>
// Copyright (C) 2013 Frank Schäfer <fschaefer.oss@googlemail.com>
//
diff --git a/drivers/media/usb/em28xx/em28xx-input.c b/drivers/media/usb/em28xx/em28xx-input.c
index 2dc1be0..f84a120 100644
--- a/drivers/media/usb/em28xx/em28xx-input.c
+++ b/drivers/media/usb/em28xx/em28xx-input.c
@@ -4,7 +4,7 @@
//
// Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it>
// Markus Rechberger <mrechberger@gmail.com>
-// Mauro Carvalho Chehab <mchehab@infradead.org>
+// Mauro Carvalho Chehab <mchehab@kernel.org>
// Sascha Sommer <saschasommer@freenet.de>
//
// This program is free software; you can redistribute it and/or modify
diff --git a/drivers/media/usb/em28xx/em28xx-video.c b/drivers/media/usb/em28xx/em28xx-video.c
index d70ee13..68571bf 100644
--- a/drivers/media/usb/em28xx/em28xx-video.c
+++ b/drivers/media/usb/em28xx/em28xx-video.c
@@ -5,7 +5,7 @@
//
// Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it>
// Markus Rechberger <mrechberger@gmail.com>
-// Mauro Carvalho Chehab <mchehab@infradead.org>
+// Mauro Carvalho Chehab <mchehab@kernel.org>
// Sascha Sommer <saschasommer@freenet.de>
// Copyright (C) 2012 Frank Schäfer <fschaefer.oss@googlemail.com>
//
@@ -44,7 +44,7 @@
#define DRIVER_AUTHOR "Ludovico Cavedon <cavedon@sssup.it>, " \
"Markus Rechberger <mrechberger@gmail.com>, " \
- "Mauro Carvalho Chehab <mchehab@infradead.org>, " \
+ "Mauro Carvalho Chehab <mchehab@kernel.org>, " \
"Sascha Sommer <saschasommer@freenet.de>"
static unsigned int isoc_debug;
diff --git a/drivers/media/usb/em28xx/em28xx.h b/drivers/media/usb/em28xx/em28xx.h
index 63c7c61..b0378e7 100644
--- a/drivers/media/usb/em28xx/em28xx.h
+++ b/drivers/media/usb/em28xx/em28xx.h
@@ -4,7 +4,7 @@
*
* Copyright (C) 2005 Markus Rechberger <mrechberger@gmail.com>
* Ludovico Cavedon <cavedon@sssup.it>
- * Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Mauro Carvalho Chehab <mchehab@kernel.org>
* Copyright (C) 2012 Frank Schäfer <fschaefer.oss@googlemail.com>
*
* Based on the em2800 driver from Sascha Sommer <saschasommer@freenet.de>
diff --git a/drivers/media/usb/gspca/zc3xx-reg.h b/drivers/media/usb/gspca/zc3xx-reg.h
index a1bd94e..71fda38 100644
--- a/drivers/media/usb/gspca/zc3xx-reg.h
+++ b/drivers/media/usb/gspca/zc3xx-reg.h
@@ -1,7 +1,7 @@
/*
* zc030x registers
*
- * Copyright (c) 2008 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2008 Mauro Carvalho Chehab <mchehab@kernel.org>
*
* The register aliases used here came from this driver:
* http://zc0302.sourceforge.net/zc0302.php
diff --git a/drivers/media/usb/tm6000/tm6000-cards.c b/drivers/media/usb/tm6000/tm6000-cards.c
index 70939e9..23df50a 100644
--- a/drivers/media/usb/tm6000/tm6000-cards.c
+++ b/drivers/media/usb/tm6000/tm6000-cards.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
// tm6000-cards.c - driver for TM5600/TM6000/TM6010 USB video capture devices
//
-// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
#include <linux/init.h>
#include <linux/module.h>
diff --git a/drivers/media/usb/tm6000/tm6000-core.c b/drivers/media/usb/tm6000/tm6000-core.c
index 23a1332..d3229aa 100644
--- a/drivers/media/usb/tm6000/tm6000-core.c
+++ b/drivers/media/usb/tm6000/tm6000-core.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
// tm6000-core.c - driver for TM5600/TM6000/TM6010 USB video capture devices
//
-// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
//
// Copyright (c) 2007 Michel Ludwig <michel.ludwig@gmail.com>
// - DVB-T support
diff --git a/drivers/media/usb/tm6000/tm6000-i2c.c b/drivers/media/usb/tm6000/tm6000-i2c.c
index c9a62bb..659b63f 100644
--- a/drivers/media/usb/tm6000/tm6000-i2c.c
+++ b/drivers/media/usb/tm6000/tm6000-i2c.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
// tm6000-i2c.c - driver for TM5600/TM6000/TM6010 USB video capture devices
//
-// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
//
// Copyright (c) 2007 Michel Ludwig <michel.ludwig@gmail.com>
// - Fix SMBus Read Byte command
diff --git a/drivers/media/usb/tm6000/tm6000-regs.h b/drivers/media/usb/tm6000/tm6000-regs.h
index 21587fc..d104246 100644
--- a/drivers/media/usb/tm6000/tm6000-regs.h
+++ b/drivers/media/usb/tm6000/tm6000-regs.h
@@ -2,7 +2,7 @@
* SPDX-License-Identifier: GPL-2.0
* tm6000-regs.h - driver for TM5600/TM6000/TM6010 USB video capture devices
*
- * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
*/
/*
diff --git a/drivers/media/usb/tm6000/tm6000-usb-isoc.h b/drivers/media/usb/tm6000/tm6000-usb-isoc.h
index 5c615b0..b275dbc 100644
--- a/drivers/media/usb/tm6000/tm6000-usb-isoc.h
+++ b/drivers/media/usb/tm6000/tm6000-usb-isoc.h
@@ -2,7 +2,7 @@
* SPDX-License-Identifier: GPL-2.0
* tm6000-buf.c - driver for TM5600/TM6000/TM6010 USB video capture devices
*
- * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
*/
#include <linux/videodev2.h>
diff --git a/drivers/media/usb/tm6000/tm6000-video.c b/drivers/media/usb/tm6000/tm6000-video.c
index b2399d4..aa85fe31 100644
--- a/drivers/media/usb/tm6000/tm6000-video.c
+++ b/drivers/media/usb/tm6000/tm6000-video.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
// tm6000-video.c - driver for TM5600/TM6000/TM6010 USB video capture devices
//
-// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+// Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
//
// Copyright (c) 2007 Michel Ludwig <michel.ludwig@gmail.com>
// - Fixed module load/unload
diff --git a/drivers/media/usb/tm6000/tm6000.h b/drivers/media/usb/tm6000/tm6000.h
index e1e4577..0864ed7 100644
--- a/drivers/media/usb/tm6000/tm6000.h
+++ b/drivers/media/usb/tm6000/tm6000.h
@@ -2,7 +2,7 @@
* SPDX-License-Identifier: GPL-2.0
* tm6000.h - driver for TM5600/TM6000/TM6010 USB video capture devices
*
- * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@infradead.org>
+ * Copyright (c) 2006-2007 Mauro Carvalho Chehab <mchehab@kernel.org>
*
* Copyright (c) 2007 Michel Ludwig <michel.ludwig@gmail.com>
* - DVB-T support
diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c
index 1d0b220..c080dcc 100644
--- a/drivers/media/v4l2-core/v4l2-dev.c
+++ b/drivers/media/v4l2-core/v4l2-dev.c
@@ -10,7 +10,7 @@
* 2 of the License, or (at your option) any later version.
*
* Authors: Alan Cox, <alan@lxorguk.ukuu.org.uk> (version 1)
- * Mauro Carvalho Chehab <mchehab@infradead.org> (version 2)
+ * Mauro Carvalho Chehab <mchehab@kernel.org> (version 2)
*
* Fixes: 20000516 Claudio Matsuoka <claudio@conectiva.com>
* - Added procfs support
@@ -1072,7 +1072,7 @@ static void __exit videodev_exit(void)
subsys_initcall(videodev_init);
module_exit(videodev_exit)
-MODULE_AUTHOR("Alan Cox, Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Alan Cox, Mauro Carvalho Chehab <mchehab@kernel.org>");
MODULE_DESCRIPTION("Device registrar for Video4Linux drivers v2");
MODULE_LICENSE("GPL");
MODULE_ALIAS_CHARDEV_MAJOR(VIDEO_MAJOR);
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index f48c505..de5d96d 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -9,7 +9,7 @@
* 2 of the License, or (at your option) any later version.
*
* Authors: Alan Cox, <alan@lxorguk.ukuu.org.uk> (version 1)
- * Mauro Carvalho Chehab <mchehab@infradead.org> (version 2)
+ * Mauro Carvalho Chehab <mchehab@kernel.org> (version 2)
*/
#include <linux/mm.h>
diff --git a/drivers/media/v4l2-core/videobuf-core.c b/drivers/media/v4l2-core/videobuf-core.c
index 2b39818..7491b33 100644
--- a/drivers/media/v4l2-core/videobuf-core.c
+++ b/drivers/media/v4l2-core/videobuf-core.c
@@ -1,11 +1,11 @@
/*
* generic helper functions for handling video4linux capture buffers
*
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
*
* Highly based on video-buf written originally by:
* (c) 2001,02 Gerd Knorr <kraxel@bytesex.org>
- * (c) 2006 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2006 Mauro Carvalho Chehab, <mchehab@kernel.org>
* (c) 2006 Ted Walther and John Sokol
*
* This program is free software; you can redistribute it and/or modify
@@ -38,7 +38,7 @@ static int debug;
module_param(debug, int, 0644);
MODULE_DESCRIPTION("helper module to manage video4linux buffers");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
MODULE_LICENSE("GPL");
#define dprintk(level, fmt, arg...) \
diff --git a/drivers/media/v4l2-core/videobuf-dma-contig.c b/drivers/media/v4l2-core/videobuf-dma-contig.c
index e02353e..f461325 100644
--- a/drivers/media/v4l2-core/videobuf-dma-contig.c
+++ b/drivers/media/v4l2-core/videobuf-dma-contig.c
@@ -7,7 +7,7 @@
* Copyright (c) 2008 Magnus Damm
*
* Based on videobuf-vmalloc.c,
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c
index add2edb..7770034 100644
--- a/drivers/media/v4l2-core/videobuf-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf-dma-sg.c
@@ -6,11 +6,11 @@
* into PAGE_SIZE chunks). They also assume the driver does not need
* to touch the video data.
*
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
*
* Highly based on video-buf written originally by:
* (c) 2001,02 Gerd Knorr <kraxel@bytesex.org>
- * (c) 2006 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2006 Mauro Carvalho Chehab, <mchehab@kernel.org>
* (c) 2006 Ted Walther and John Sokol
*
* This program is free software; you can redistribute it and/or modify
@@ -48,7 +48,7 @@ static int debug;
module_param(debug, int, 0644);
MODULE_DESCRIPTION("helper module to manage video4linux dma sg buffers");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
MODULE_LICENSE("GPL");
#define dprintk(level, fmt, arg...) \
diff --git a/drivers/media/v4l2-core/videobuf-vmalloc.c b/drivers/media/v4l2-core/videobuf-vmalloc.c
index 2ff7fcc..45fe781 100644
--- a/drivers/media/v4l2-core/videobuf-vmalloc.c
+++ b/drivers/media/v4l2-core/videobuf-vmalloc.c
@@ -6,7 +6,7 @@
* into PAGE_SIZE chunks). They also assume the driver does not need
* to touch the video data.
*
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -41,7 +41,7 @@ static int debug;
module_param(debug, int, 0644);
MODULE_DESCRIPTION("helper module to manage video4linux vmalloc buffers");
-MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@infradead.org>");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>");
MODULE_LICENSE("GPL");
#define dprintk(level, fmt, arg...) \
diff --git a/drivers/memory/emif-asm-offsets.c b/drivers/memory/emif-asm-offsets.c
index 71a89d5..db80430 100644
--- a/drivers/memory/emif-asm-offsets.c
+++ b/drivers/memory/emif-asm-offsets.c
@@ -16,77 +16,7 @@
int main(void)
{
- DEFINE(EMIF_SDCFG_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_sdcfg_val));
- DEFINE(EMIF_TIMING1_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_timing1_val));
- DEFINE(EMIF_TIMING2_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_timing2_val));
- DEFINE(EMIF_TIMING3_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_timing3_val));
- DEFINE(EMIF_REF_CTRL_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_ref_ctrl_val));
- DEFINE(EMIF_ZQCFG_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_zqcfg_val));
- DEFINE(EMIF_PMCR_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_pmcr_val));
- DEFINE(EMIF_PMCR_SHDW_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_pmcr_shdw_val));
- DEFINE(EMIF_RD_WR_LEVEL_RAMP_CTRL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_rd_wr_level_ramp_ctrl));
- DEFINE(EMIF_RD_WR_EXEC_THRESH_OFFSET,
- offsetof(struct emif_regs_amx3, emif_rd_wr_exec_thresh));
- DEFINE(EMIF_COS_CONFIG_OFFSET,
- offsetof(struct emif_regs_amx3, emif_cos_config));
- DEFINE(EMIF_PRIORITY_TO_COS_MAPPING_OFFSET,
- offsetof(struct emif_regs_amx3, emif_priority_to_cos_mapping));
- DEFINE(EMIF_CONNECT_ID_SERV_1_MAP_OFFSET,
- offsetof(struct emif_regs_amx3, emif_connect_id_serv_1_map));
- DEFINE(EMIF_CONNECT_ID_SERV_2_MAP_OFFSET,
- offsetof(struct emif_regs_amx3, emif_connect_id_serv_2_map));
- DEFINE(EMIF_OCP_CONFIG_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_ocp_config_val));
- DEFINE(EMIF_LPDDR2_NVM_TIM_OFFSET,
- offsetof(struct emif_regs_amx3, emif_lpddr2_nvm_tim));
- DEFINE(EMIF_LPDDR2_NVM_TIM_SHDW_OFFSET,
- offsetof(struct emif_regs_amx3, emif_lpddr2_nvm_tim_shdw));
- DEFINE(EMIF_DLL_CALIB_CTRL_VAL_OFFSET,
- offsetof(struct emif_regs_amx3, emif_dll_calib_ctrl_val));
- DEFINE(EMIF_DLL_CALIB_CTRL_VAL_SHDW_OFFSET,
- offsetof(struct emif_regs_amx3, emif_dll_calib_ctrl_val_shdw));
- DEFINE(EMIF_DDR_PHY_CTLR_1_OFFSET,
- offsetof(struct emif_regs_amx3, emif_ddr_phy_ctlr_1));
- DEFINE(EMIF_EXT_PHY_CTRL_VALS_OFFSET,
- offsetof(struct emif_regs_amx3, emif_ext_phy_ctrl_vals));
- DEFINE(EMIF_REGS_AMX3_SIZE, sizeof(struct emif_regs_amx3));
-
- BLANK();
-
- DEFINE(EMIF_PM_BASE_ADDR_VIRT_OFFSET,
- offsetof(struct ti_emif_pm_data, ti_emif_base_addr_virt));
- DEFINE(EMIF_PM_BASE_ADDR_PHYS_OFFSET,
- offsetof(struct ti_emif_pm_data, ti_emif_base_addr_phys));
- DEFINE(EMIF_PM_CONFIG_OFFSET,
- offsetof(struct ti_emif_pm_data, ti_emif_sram_config));
- DEFINE(EMIF_PM_REGS_VIRT_OFFSET,
- offsetof(struct ti_emif_pm_data, regs_virt));
- DEFINE(EMIF_PM_REGS_PHYS_OFFSET,
- offsetof(struct ti_emif_pm_data, regs_phys));
- DEFINE(EMIF_PM_DATA_SIZE, sizeof(struct ti_emif_pm_data));
-
- BLANK();
-
- DEFINE(EMIF_PM_SAVE_CONTEXT_OFFSET,
- offsetof(struct ti_emif_pm_functions, save_context));
- DEFINE(EMIF_PM_RESTORE_CONTEXT_OFFSET,
- offsetof(struct ti_emif_pm_functions, restore_context));
- DEFINE(EMIF_PM_ENTER_SR_OFFSET,
- offsetof(struct ti_emif_pm_functions, enter_sr));
- DEFINE(EMIF_PM_EXIT_SR_OFFSET,
- offsetof(struct ti_emif_pm_functions, exit_sr));
- DEFINE(EMIF_PM_ABORT_SR_OFFSET,
- offsetof(struct ti_emif_pm_functions, abort_sr));
- DEFINE(EMIF_PM_FUNCTIONS_SIZE, sizeof(struct ti_emif_pm_functions));
+ ti_emif_asm_offsets();
return 0;
}
diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c
index 57b13df..a15181f 100644
--- a/drivers/memstick/core/ms_block.c
+++ b/drivers/memstick/core/ms_block.c
@@ -2094,14 +2094,9 @@ static const struct block_device_operations msb_bdops = {
static int msb_init_disk(struct memstick_dev *card)
{
struct msb_data *msb = memstick_get_drvdata(card);
- struct memstick_host *host = card->host;
int rc;
- u64 limit = BLK_BOUNCE_HIGH;
unsigned long capacity;
- if (host->dev.dma_mask && *(host->dev.dma_mask))
- limit = *(host->dev.dma_mask);
-
mutex_lock(&msb_disk_lock);
msb->disk_id = idr_alloc(&msb_disk_idr, card, 0, 256, GFP_KERNEL);
mutex_unlock(&msb_disk_lock);
@@ -2123,7 +2118,6 @@ static int msb_init_disk(struct memstick_dev *card)
msb->queue->queuedata = card;
- blk_queue_bounce_limit(msb->queue, limit);
blk_queue_max_hw_sectors(msb->queue, MS_BLOCK_MAX_PAGES);
blk_queue_max_segments(msb->queue, MS_BLOCK_MAX_SEGS);
blk_queue_max_segment_size(msb->queue,
diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c
index 8897962..5ee9326 100644
--- a/drivers/memstick/core/mspro_block.c
+++ b/drivers/memstick/core/mspro_block.c
@@ -1170,17 +1170,12 @@ static int mspro_block_init_card(struct memstick_dev *card)
static int mspro_block_init_disk(struct memstick_dev *card)
{
struct mspro_block_data *msb = memstick_get_drvdata(card);
- struct memstick_host *host = card->host;
struct mspro_devinfo *dev_info = NULL;
struct mspro_sys_info *sys_info = NULL;
struct mspro_sys_attr *s_attr = NULL;
int rc, disk_id;
- u64 limit = BLK_BOUNCE_HIGH;
unsigned long capacity;
- if (host->dev.dma_mask && *(host->dev.dma_mask))
- limit = *(host->dev.dma_mask);
-
for (rc = 0; msb->attr_group.attrs[rc]; ++rc) {
s_attr = mspro_from_sysfs_attr(msb->attr_group.attrs[rc]);
@@ -1219,7 +1214,6 @@ static int mspro_block_init_disk(struct memstick_dev *card)
msb->queue->queuedata = card;
- blk_queue_bounce_limit(msb->queue, limit);
blk_queue_max_hw_sectors(msb->queue, MSPRO_BLOCK_MAX_PAGES);
blk_queue_max_segments(msb->queue, MSPRO_BLOCK_MAX_SEGS);
blk_queue_max_segment_size(msb->queue,
diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c
index 51eb1b0..a746ccd 100644
--- a/drivers/message/fusion/mptbase.c
+++ b/drivers/message/fusion/mptbase.c
@@ -197,9 +197,9 @@ static int mpt_host_page_access_control(MPT_ADAPTER *ioc, u8 access_control_valu
static int mpt_host_page_alloc(MPT_ADAPTER *ioc, pIOCInit_t ioc_init);
#ifdef CONFIG_PROC_FS
-static const struct file_operations mpt_summary_proc_fops;
-static const struct file_operations mpt_version_proc_fops;
-static const struct file_operations mpt_iocinfo_proc_fops;
+static int mpt_summary_proc_show(struct seq_file *m, void *v);
+static int mpt_version_proc_show(struct seq_file *m, void *v);
+static int mpt_iocinfo_proc_show(struct seq_file *m, void *v);
#endif
static void mpt_get_fw_exp_ver(char *buf, MPT_ADAPTER *ioc);
@@ -2040,8 +2040,10 @@ mpt_attach(struct pci_dev *pdev, const struct pci_device_id *id)
*/
dent = proc_mkdir(ioc->name, mpt_proc_root_dir);
if (dent) {
- proc_create_data("info", S_IRUGO, dent, &mpt_iocinfo_proc_fops, ioc);
- proc_create_data("summary", S_IRUGO, dent, &mpt_summary_proc_fops, ioc);
+ proc_create_single_data("info", S_IRUGO, dent,
+ mpt_iocinfo_proc_show, ioc);
+ proc_create_single_data("summary", S_IRUGO, dent,
+ mpt_summary_proc_show, ioc);
}
#endif
@@ -6606,8 +6608,10 @@ procmpt_create(void)
if (mpt_proc_root_dir == NULL)
return -ENOTDIR;
- proc_create("summary", S_IRUGO, mpt_proc_root_dir, &mpt_summary_proc_fops);
- proc_create("version", S_IRUGO, mpt_proc_root_dir, &mpt_version_proc_fops);
+ proc_create_single("summary", S_IRUGO, mpt_proc_root_dir,
+ mpt_summary_proc_show);
+ proc_create_single("version", S_IRUGO, mpt_proc_root_dir,
+ mpt_version_proc_show);
return 0;
}
@@ -6646,19 +6650,6 @@ static int mpt_summary_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int mpt_summary_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, mpt_summary_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations mpt_summary_proc_fops = {
- .owner = THIS_MODULE,
- .open = mpt_summary_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int mpt_version_proc_show(struct seq_file *m, void *v)
{
u8 cb_idx;
@@ -6701,19 +6692,6 @@ static int mpt_version_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int mpt_version_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, mpt_version_proc_show, NULL);
-}
-
-static const struct file_operations mpt_version_proc_fops = {
- .owner = THIS_MODULE,
- .open = mpt_version_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int mpt_iocinfo_proc_show(struct seq_file *m, void *v)
{
MPT_ADAPTER *ioc = m->private;
@@ -6793,19 +6771,6 @@ static int mpt_iocinfo_proc_show(struct seq_file *m, void *v)
return 0;
}
-
-static int mpt_iocinfo_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, mpt_iocinfo_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations mpt_iocinfo_proc_fops = {
- .owner = THIS_MODULE,
- .open = mpt_iocinfo_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif /* CONFIG_PROC_FS } */
/*=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=*/
diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c
index 231f3a1..19a5aa7 100644
--- a/drivers/message/fusion/mptsas.c
+++ b/drivers/message/fusion/mptsas.c
@@ -1929,7 +1929,7 @@ static enum blk_eh_timer_return mptsas_eh_timed_out(struct scsi_cmnd *sc)
MPT_SCSI_HOST *hd;
MPT_ADAPTER *ioc;
VirtDevice *vdevice;
- enum blk_eh_timer_return rc = BLK_EH_NOT_HANDLED;
+ enum blk_eh_timer_return rc = BLK_EH_DONE;
hd = shost_priv(sc->device->host);
if (hd == NULL) {
@@ -1994,6 +1994,7 @@ static struct scsi_host_template mptsas_driver_template = {
.cmd_per_lun = 7,
.use_clustering = ENABLE_CLUSTERING,
.shost_attrs = mptscsih_host_attrs,
+ .no_write_same = 1,
};
static int mptsas_get_linkerrors(struct sas_phy *phy)
diff --git a/drivers/mfd/cros_ec_spi.c b/drivers/mfd/cros_ec_spi.c
index 1b52b85..2060d14 100644
--- a/drivers/mfd/cros_ec_spi.c
+++ b/drivers/mfd/cros_ec_spi.c
@@ -419,10 +419,25 @@ static int cros_ec_pkt_xfer_spi(struct cros_ec_device *ec_dev,
/* Verify that EC can process command */
for (i = 0; i < len; i++) {
rx_byte = rx_buf[i];
+ /*
+ * Seeing the PAST_END, RX_BAD_DATA, or NOT_READY
+ * markers are all signs that the EC didn't fully
+ * receive our command. e.g., if the EC is flashing
+ * itself, it can't respond to any commands and instead
+ * clocks out EC_SPI_PAST_END from its SPI hardware
+ * buffer. Similar occurrences can happen if the AP is
+ * too slow to clock out data after asserting CS -- the
+ * EC will abort and fill its buffer with
+ * EC_SPI_RX_BAD_DATA.
+ *
+ * In all cases, these errors should be safe to retry.
+ * Report -EAGAIN and let the caller decide what to do
+ * about that.
+ */
if (rx_byte == EC_SPI_PAST_END ||
rx_byte == EC_SPI_RX_BAD_DATA ||
rx_byte == EC_SPI_NOT_READY) {
- ret = -EREMOTEIO;
+ ret = -EAGAIN;
break;
}
}
@@ -431,7 +446,7 @@ static int cros_ec_pkt_xfer_spi(struct cros_ec_device *ec_dev,
if (!ret)
ret = cros_ec_spi_receive_packet(ec_dev,
ec_msg->insize + sizeof(*response));
- else
+ else if (ret != -EAGAIN)
dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret);
final_ret = terminate_request(ec_dev);
@@ -537,10 +552,11 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev,
/* Verify that EC can process command */
for (i = 0; i < len; i++) {
rx_byte = rx_buf[i];
+ /* See comments in cros_ec_pkt_xfer_spi() */
if (rx_byte == EC_SPI_PAST_END ||
rx_byte == EC_SPI_RX_BAD_DATA ||
rx_byte == EC_SPI_NOT_READY) {
- ret = -EREMOTEIO;
+ ret = -EAGAIN;
break;
}
}
@@ -549,7 +565,7 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev,
if (!ret)
ret = cros_ec_spi_receive_response(ec_dev,
ec_msg->insize + EC_MSG_TX_PROTO_BYTES);
- else
+ else if (ret != -EAGAIN)
dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret);
final_ret = terminate_request(ec_dev);
diff --git a/drivers/mfd/mc13xxx-core.c b/drivers/mfd/mc13xxx-core.c
index d7f54e4..c63e331 100644
--- a/drivers/mfd/mc13xxx-core.c
+++ b/drivers/mfd/mc13xxx-core.c
@@ -279,8 +279,21 @@ int mc13xxx_adc_do_conversion(struct mc13xxx *mc13xxx, unsigned int mode,
adc0 = MC13XXX_ADC0_ADINC1 | MC13XXX_ADC0_ADINC2;
adc1 = MC13XXX_ADC1_ADEN | MC13XXX_ADC1_ADTRIGIGN | MC13XXX_ADC1_ASC;
- if (channel > 7)
+ /*
+ * Channels mapped through ADIN7:
+ * 7 - General purpose ADIN7
+ * 16 - UID
+ * 17 - Die temperature
+ */
+ if (channel > 7 && channel < 16) {
adc1 |= MC13XXX_ADC1_ADSEL;
+ } else if (channel == 16) {
+ adc0 |= MC13XXX_ADC0_ADIN7SEL_UID;
+ channel = 7;
+ } else if (channel == 17) {
+ adc0 |= MC13XXX_ADC0_ADIN7SEL_DIE;
+ channel = 7;
+ }
switch (mode) {
case MC13XXX_ADC_MODE_TS:
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index a4c9c82..918d4fb 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -717,6 +717,7 @@ struct cxl {
bool perst_select_user;
bool perst_same_image;
bool psl_timebase_synced;
+ bool tunneled_ops_supported;
/*
* number of contexts mapped on to this card. Possible values are:
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 83f1d08..4d6736f 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -1742,6 +1742,15 @@ static int cxl_configure_adapter(struct cxl *adapter, struct pci_dev *dev)
/* Required for devices using CAPP DMA mode, harmless for others */
pci_set_master(dev);
+ adapter->tunneled_ops_supported = false;
+
+ if (cxl_is_power9()) {
+ if (pnv_pci_set_tunnel_bar(dev, 0x00020000E0000000ull, 1))
+ dev_info(&dev->dev, "Tunneled operations unsupported\n");
+ else
+ adapter->tunneled_ops_supported = true;
+ }
+
if ((rc = pnv_phb_to_cxl_mode(dev, adapter->native->sl_ops->capi_mode)))
goto err;
@@ -1768,6 +1777,9 @@ static void cxl_deconfigure_adapter(struct cxl *adapter)
{
struct pci_dev *pdev = to_pci_dev(adapter->dev.parent);
+ if (cxl_is_power9())
+ pnv_pci_set_tunnel_bar(pdev, 0x00020000E0000000ull, 0);
+
cxl_native_release_psl_err_irq(adapter);
cxl_unmap_adapter_regs(adapter);
diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c
index 95285b7..4b5a4c5 100644
--- a/drivers/misc/cxl/sysfs.c
+++ b/drivers/misc/cxl/sysfs.c
@@ -78,6 +78,15 @@ static ssize_t psl_timebase_synced_show(struct device *device,
return scnprintf(buf, PAGE_SIZE, "%i\n", adapter->psl_timebase_synced);
}
+static ssize_t tunneled_ops_supported_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cxl *adapter = to_cxl_adapter(device);
+
+ return scnprintf(buf, PAGE_SIZE, "%i\n", adapter->tunneled_ops_supported);
+}
+
static ssize_t reset_adapter_store(struct device *device,
struct device_attribute *attr,
const char *buf, size_t count)
@@ -183,6 +192,7 @@ static struct device_attribute adapter_attrs[] = {
__ATTR_RO(base_image),
__ATTR_RO(image_loaded),
__ATTR_RO(psl_timebase_synced),
+ __ATTR_RO(tunneled_ops_supported),
__ATTR_RW(load_image_on_perst),
__ATTR_RW(perst_reloads_same_image),
__ATTR(reset, S_IWUSR, NULL, reset_adapter_store),
diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c
index 0c125f2..33053b0 100644
--- a/drivers/misc/eeprom/at24.c
+++ b/drivers/misc/eeprom/at24.c
@@ -518,7 +518,7 @@ static int at24_get_pdata(struct device *dev, struct at24_platform_data *pdata)
if (of_node && of_match_device(at24_of_match, dev))
cdata = of_device_get_match_data(dev);
else if (id)
- cdata = (void *)&id->driver_data;
+ cdata = (void *)id->driver_data;
else
cdata = acpi_device_get_match_data(dev);
diff --git a/drivers/misc/sgi-gru/gruprocfs.c b/drivers/misc/sgi-gru/gruprocfs.c
index 4f76359..42ea2ec 100644
--- a/drivers/misc/sgi-gru/gruprocfs.c
+++ b/drivers/misc/sgi-gru/gruprocfs.c
@@ -270,16 +270,6 @@ static int options_open(struct inode *inode, struct file *file)
return single_open(file, options_show, NULL);
}
-static int cch_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &cch_seq_ops);
-}
-
-static int gru_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &gru_seq_ops);
-}
-
/* *INDENT-OFF* */
static const struct file_operations statistics_fops = {
.open = statistics_open,
@@ -305,73 +295,30 @@ static const struct file_operations options_fops = {
.release = single_release,
};
-static const struct file_operations cch_fops = {
- .open = cch_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-static const struct file_operations gru_fops = {
- .open = gru_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-static struct proc_entry {
- char *name;
- umode_t mode;
- const struct file_operations *fops;
- struct proc_dir_entry *entry;
-} proc_files[] = {
- {"statistics", 0644, &statistics_fops},
- {"mcs_statistics", 0644, &mcs_statistics_fops},
- {"debug_options", 0644, &options_fops},
- {"cch_status", 0444, &cch_fops},
- {"gru_status", 0444, &gru_fops},
- {NULL}
-};
-/* *INDENT-ON* */
-
static struct proc_dir_entry *proc_gru __read_mostly;
-static int create_proc_file(struct proc_entry *p)
-{
- p->entry = proc_create(p->name, p->mode, proc_gru, p->fops);
- if (!p->entry)
- return -1;
- return 0;
-}
-
-static void delete_proc_files(void)
-{
- struct proc_entry *p;
-
- if (proc_gru) {
- for (p = proc_files; p->name; p++)
- if (p->entry)
- remove_proc_entry(p->name, proc_gru);
- proc_remove(proc_gru);
- }
-}
-
int gru_proc_init(void)
{
- struct proc_entry *p;
-
proc_gru = proc_mkdir("sgi_uv/gru", NULL);
-
- for (p = proc_files; p->name; p++)
- if (create_proc_file(p))
- goto err;
+ if (!proc_gru)
+ return -1;
+ if (!proc_create("statistics", 0644, proc_gru, &statistics_fops))
+ goto err;
+ if (!proc_create("mcs_statistics", 0644, proc_gru, &mcs_statistics_fops))
+ goto err;
+ if (!proc_create("debug_options", 0644, proc_gru, &options_fops))
+ goto err;
+ if (!proc_create_seq("cch_status", 0444, proc_gru, &cch_seq_ops))
+ goto err;
+ if (!proc_create_seq("gru_status", 0444, proc_gru, &gru_seq_ops))
+ goto err;
return 0;
-
err:
- delete_proc_files();
+ remove_proc_subtree("sgi_uv/gru", NULL);
return -1;
}
void gru_proc_exit(void)
{
- delete_proc_files();
+ remove_proc_subtree("sgi_uv/gru", NULL);
}
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 9e923cd..d89e178 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -244,7 +244,7 @@ static ssize_t power_ro_lock_store(struct device *dev,
mq = &md->queue;
/* Dispatch locking to the block layer */
- req = blk_get_request(mq->queue, REQ_OP_DRV_OUT, __GFP_RECLAIM);
+ req = blk_get_request(mq->queue, REQ_OP_DRV_OUT, 0);
if (IS_ERR(req)) {
count = PTR_ERR(req);
goto out_put;
@@ -650,8 +650,7 @@ static int mmc_blk_ioctl_cmd(struct mmc_blk_data *md,
*/
mq = &md->queue;
req = blk_get_request(mq->queue,
- idata->ic.write_flag ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN,
- __GFP_RECLAIM);
+ idata->ic.write_flag ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto cmd_done;
@@ -721,8 +720,7 @@ static int mmc_blk_ioctl_multi_cmd(struct mmc_blk_data *md,
*/
mq = &md->queue;
req = blk_get_request(mq->queue,
- idata[0]->ic.write_flag ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN,
- __GFP_RECLAIM);
+ idata[0]->ic.write_flag ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto cmd_err;
@@ -2485,7 +2483,7 @@ static long mmc_rpmb_ioctl(struct file *filp, unsigned int cmd,
break;
}
- return 0;
+ return ret;
}
#ifdef CONFIG_COMPAT
@@ -2750,7 +2748,7 @@ static int mmc_dbg_card_status_get(void *data, u64 *val)
int ret;
/* Ask the block layer about the card status */
- req = blk_get_request(mq->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+ req = blk_get_request(mq->queue, REQ_OP_DRV_IN, 0);
if (IS_ERR(req))
return PTR_ERR(req);
req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_CARD_STATUS;
@@ -2786,7 +2784,7 @@ static int mmc_ext_csd_open(struct inode *inode, struct file *filp)
return -ENOMEM;
/* Ask the block layer for the EXT CSD */
- req = blk_get_request(mq->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+ req = blk_get_request(mq->queue, REQ_OP_DRV_IN, 0);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out_free;
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index 56e9a80..648eb67 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -111,8 +111,9 @@ static enum blk_eh_timer_return mmc_cqe_timed_out(struct request *req)
__mmc_cqe_recovery_notifier(mq);
return BLK_EH_RESET_TIMER;
}
- /* No timeout */
- return BLK_EH_HANDLED;
+ /* No timeout (XXX: huh? comment doesn't make much sense) */
+ blk_mq_complete_request(req);
+ return BLK_EH_DONE;
default:
/* Timeout is handled by mmc core */
return BLK_EH_RESET_TIMER;
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index 2b32b88..b6d8203 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -139,7 +139,7 @@ static int sdio_bus_probe(struct device *dev)
return -ENODEV;
ret = dev_pm_domain_attach(dev, false);
- if (ret == -EPROBE_DEFER)
+ if (ret)
return ret;
/* Unbound SDIO functions are always suspended.
diff --git a/drivers/mmc/core/sdio_uart.c b/drivers/mmc/core/sdio_uart.c
index d3c91f4..25e1130 100644
--- a/drivers/mmc/core/sdio_uart.c
+++ b/drivers/mmc/core/sdio_uart.c
@@ -1008,19 +1008,6 @@ static int sdio_uart_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int sdio_uart_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, sdio_uart_proc_show, NULL);
-}
-
-static const struct file_operations sdio_uart_proc_fops = {
- .owner = THIS_MODULE,
- .open = sdio_uart_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static const struct tty_port_operations sdio_uart_port_ops = {
.dtr_rts = uart_dtr_rts,
.carrier_raised = uart_carrier_raised,
@@ -1045,7 +1032,7 @@ static const struct tty_operations sdio_uart_ops = {
.tiocmset = sdio_uart_tiocmset,
.install = sdio_uart_install,
.cleanup = sdio_uart_cleanup,
- .proc_fops = &sdio_uart_proc_fops,
+ .proc_show = sdio_uart_proc_show,
};
static struct tty_driver *sdio_uart_tty_driver;
diff --git a/drivers/mmc/host/renesas_sdhi_internal_dmac.c b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
index 8e0acd1..6af946d1 100644
--- a/drivers/mmc/host/renesas_sdhi_internal_dmac.c
+++ b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
@@ -9,6 +9,7 @@
* published by the Free Software Foundation.
*/
+#include <linux/bitops.h>
#include <linux/device.h>
#include <linux/dma-mapping.h>
#include <linux/io-64-nonatomic-hi-lo.h>
@@ -62,6 +63,17 @@
* need a custom accessor.
*/
+static unsigned long global_flags;
+/*
+ * Workaround for avoiding to use RX DMAC by multiple channels.
+ * On R-Car H3 ES1.* and M3-W ES1.0, when multiple SDHI channels use
+ * RX DMAC simultaneously, sometimes hundreds of bytes data are not
+ * stored into the system memory even if the DMAC interrupt happened.
+ * So, this driver then uses one RX DMAC channel only.
+ */
+#define SDHI_INTERNAL_DMAC_ONE_RX_ONLY 0
+#define SDHI_INTERNAL_DMAC_RX_IN_USE 1
+
/* Definitions for sampling clocks */
static struct renesas_sdhi_scc rcar_gen3_scc_taps[] = {
{
@@ -126,6 +138,9 @@ renesas_sdhi_internal_dmac_abort_dma(struct tmio_mmc_host *host) {
renesas_sdhi_internal_dmac_dm_write(host, DM_CM_RST,
RST_RESERVED_BITS | val);
+ if (host->data && host->data->flags & MMC_DATA_READ)
+ clear_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags);
+
renesas_sdhi_internal_dmac_enable_dma(host, true);
}
@@ -155,6 +170,9 @@ renesas_sdhi_internal_dmac_start_dma(struct tmio_mmc_host *host,
if (data->flags & MMC_DATA_READ) {
dtran_mode |= DTRAN_MODE_CH_NUM_CH1;
dir = DMA_FROM_DEVICE;
+ if (test_bit(SDHI_INTERNAL_DMAC_ONE_RX_ONLY, &global_flags) &&
+ test_and_set_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags))
+ goto force_pio;
} else {
dtran_mode |= DTRAN_MODE_CH_NUM_CH0;
dir = DMA_TO_DEVICE;
@@ -208,6 +226,9 @@ static void renesas_sdhi_internal_dmac_complete_tasklet_fn(unsigned long arg)
renesas_sdhi_internal_dmac_enable_dma(host, false);
dma_unmap_sg(&host->pdev->dev, host->sg_ptr, host->sg_len, dir);
+ if (dir == DMA_FROM_DEVICE)
+ clear_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags);
+
tmio_mmc_do_data_irq(host);
out:
spin_unlock_irq(&host->lock);
@@ -251,18 +272,24 @@ static const struct tmio_mmc_dma_ops renesas_sdhi_internal_dmac_dma_ops = {
* implementation as others may use a different implementation.
*/
static const struct soc_device_attribute gen3_soc_whitelist[] = {
- { .soc_id = "r8a7795", .revision = "ES1.*" },
- { .soc_id = "r8a7795", .revision = "ES2.0" },
- { .soc_id = "r8a7796", .revision = "ES1.0" },
- { .soc_id = "r8a77995", .revision = "ES1.0" },
- { /* sentinel */ }
+ { .soc_id = "r8a7795", .revision = "ES1.*",
+ .data = (void *)BIT(SDHI_INTERNAL_DMAC_ONE_RX_ONLY) },
+ { .soc_id = "r8a7795", .revision = "ES2.0" },
+ { .soc_id = "r8a7796", .revision = "ES1.0",
+ .data = (void *)BIT(SDHI_INTERNAL_DMAC_ONE_RX_ONLY) },
+ { .soc_id = "r8a77995", .revision = "ES1.0" },
+ { /* sentinel */ }
};
static int renesas_sdhi_internal_dmac_probe(struct platform_device *pdev)
{
- if (!soc_device_match(gen3_soc_whitelist))
+ const struct soc_device_attribute *soc = soc_device_match(gen3_soc_whitelist);
+
+ if (!soc)
return -ENODEV;
+ global_flags |= (unsigned long)soc->data;
+
return renesas_sdhi_probe(pdev, &renesas_sdhi_internal_dmac_dma_ops);
}
diff --git a/drivers/mmc/host/sdhci-iproc.c b/drivers/mmc/host/sdhci-iproc.c
index 0ef741b..d0e83db 100644
--- a/drivers/mmc/host/sdhci-iproc.c
+++ b/drivers/mmc/host/sdhci-iproc.c
@@ -33,6 +33,8 @@ struct sdhci_iproc_host {
const struct sdhci_iproc_data *data;
u32 shadow_cmd;
u32 shadow_blk;
+ bool is_cmd_shadowed;
+ bool is_blk_shadowed;
};
#define REG_OFFSET_IN_BITS(reg) ((reg) << 3 & 0x18)
@@ -48,8 +50,22 @@ static inline u32 sdhci_iproc_readl(struct sdhci_host *host, int reg)
static u16 sdhci_iproc_readw(struct sdhci_host *host, int reg)
{
- u32 val = sdhci_iproc_readl(host, (reg & ~3));
- u16 word = val >> REG_OFFSET_IN_BITS(reg) & 0xffff;
+ struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+ struct sdhci_iproc_host *iproc_host = sdhci_pltfm_priv(pltfm_host);
+ u32 val;
+ u16 word;
+
+ if ((reg == SDHCI_TRANSFER_MODE) && iproc_host->is_cmd_shadowed) {
+ /* Get the saved transfer mode */
+ val = iproc_host->shadow_cmd;
+ } else if ((reg == SDHCI_BLOCK_SIZE || reg == SDHCI_BLOCK_COUNT) &&
+ iproc_host->is_blk_shadowed) {
+ /* Get the saved block info */
+ val = iproc_host->shadow_blk;
+ } else {
+ val = sdhci_iproc_readl(host, (reg & ~3));
+ }
+ word = val >> REG_OFFSET_IN_BITS(reg) & 0xffff;
return word;
}
@@ -105,13 +121,15 @@ static void sdhci_iproc_writew(struct sdhci_host *host, u16 val, int reg)
if (reg == SDHCI_COMMAND) {
/* Write the block now as we are issuing a command */
- if (iproc_host->shadow_blk != 0) {
+ if (iproc_host->is_blk_shadowed) {
sdhci_iproc_writel(host, iproc_host->shadow_blk,
SDHCI_BLOCK_SIZE);
- iproc_host->shadow_blk = 0;
+ iproc_host->is_blk_shadowed = false;
}
oldval = iproc_host->shadow_cmd;
- } else if (reg == SDHCI_BLOCK_SIZE || reg == SDHCI_BLOCK_COUNT) {
+ iproc_host->is_cmd_shadowed = false;
+ } else if ((reg == SDHCI_BLOCK_SIZE || reg == SDHCI_BLOCK_COUNT) &&
+ iproc_host->is_blk_shadowed) {
/* Block size and count are stored in shadow reg */
oldval = iproc_host->shadow_blk;
} else {
@@ -123,9 +141,11 @@ static void sdhci_iproc_writew(struct sdhci_host *host, u16 val, int reg)
if (reg == SDHCI_TRANSFER_MODE) {
/* Save the transfer mode until the command is issued */
iproc_host->shadow_cmd = newval;
+ iproc_host->is_cmd_shadowed = true;
} else if (reg == SDHCI_BLOCK_SIZE || reg == SDHCI_BLOCK_COUNT) {
/* Save the block info until the command is issued */
iproc_host->shadow_blk = newval;
+ iproc_host->is_blk_shadowed = true;
} else {
/* Command or other regular 32-bit write */
sdhci_iproc_writel(host, newval, reg & ~3);
@@ -166,7 +186,7 @@ static const struct sdhci_ops sdhci_iproc_32only_ops = {
static const struct sdhci_pltfm_data sdhci_iproc_cygnus_pltfm_data = {
.quirks = SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK,
- .quirks2 = SDHCI_QUIRK2_ACMD23_BROKEN,
+ .quirks2 = SDHCI_QUIRK2_ACMD23_BROKEN | SDHCI_QUIRK2_HOST_OFF_CARD_ON,
.ops = &sdhci_iproc_32only_ops,
};
@@ -206,7 +226,6 @@ static const struct sdhci_iproc_data iproc_data = {
.caps1 = SDHCI_DRIVER_TYPE_C |
SDHCI_DRIVER_TYPE_D |
SDHCI_SUPPORT_DDR50,
- .mmc_caps = MMC_CAP_1_8V_DDR,
};
static const struct sdhci_pltfm_data sdhci_bcm2835_pltfm_data = {
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 787434e..78c25ad 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -1312,7 +1312,7 @@ static void amd_enable_manual_tuning(struct pci_dev *pdev)
pci_write_config_dword(pdev, AMD_SD_MISC_CONTROL, val);
}
-static int amd_execute_tuning(struct sdhci_host *host, u32 opcode)
+static int amd_execute_tuning_hs200(struct sdhci_host *host, u32 opcode)
{
struct sdhci_pci_slot *slot = sdhci_priv(host);
struct pci_dev *pdev = slot->chip->pdev;
@@ -1351,6 +1351,27 @@ static int amd_execute_tuning(struct sdhci_host *host, u32 opcode)
return 0;
}
+static int amd_execute_tuning(struct mmc_host *mmc, u32 opcode)
+{
+ struct sdhci_host *host = mmc_priv(mmc);
+
+ /* AMD requires custom HS200 tuning */
+ if (host->timing == MMC_TIMING_MMC_HS200)
+ return amd_execute_tuning_hs200(host, opcode);
+
+ /* Otherwise perform standard SDHCI tuning */
+ return sdhci_execute_tuning(mmc, opcode);
+}
+
+static int amd_probe_slot(struct sdhci_pci_slot *slot)
+{
+ struct mmc_host_ops *ops = &slot->host->mmc_host_ops;
+
+ ops->execute_tuning = amd_execute_tuning;
+
+ return 0;
+}
+
static int amd_probe(struct sdhci_pci_chip *chip)
{
struct pci_dev *smbus_dev;
@@ -1385,12 +1406,12 @@ static const struct sdhci_ops amd_sdhci_pci_ops = {
.set_bus_width = sdhci_set_bus_width,
.reset = sdhci_reset,
.set_uhs_signaling = sdhci_set_uhs_signaling,
- .platform_execute_tuning = amd_execute_tuning,
};
static const struct sdhci_pci_fixes sdhci_amd = {
.probe = amd_probe,
.ops = &amd_sdhci_pci_ops,
+ .probe_slot = amd_probe_slot,
};
static const struct pci_device_id pci_ids[] = {
diff --git a/drivers/mtd/chips/cfi_cmdset_0001.c b/drivers/mtd/chips/cfi_cmdset_0001.c
index d4c07b8..f5695be 100644
--- a/drivers/mtd/chips/cfi_cmdset_0001.c
+++ b/drivers/mtd/chips/cfi_cmdset_0001.c
@@ -45,6 +45,7 @@
#define I82802AB 0x00ad
#define I82802AC 0x00ac
#define PF38F4476 0x881c
+#define M28F00AP30 0x8963
/* STMicroelectronics chips */
#define M50LPW080 0x002F
#define M50FLW080A 0x0080
@@ -375,6 +376,17 @@ static void cfi_fixup_major_minor(struct cfi_private *cfi,
extp->MinorVersion = '1';
}
+static int cfi_is_micron_28F00AP30(struct cfi_private *cfi, struct flchip *chip)
+{
+ /*
+ * Micron(was Numonyx) 1Gbit bottom boot are buggy w.r.t
+ * Erase Supend for their small Erase Blocks(0x8000)
+ */
+ if (cfi->mfr == CFI_MFR_INTEL && cfi->id == M28F00AP30)
+ return 1;
+ return 0;
+}
+
static inline struct cfi_pri_intelext *
read_pri_intelext(struct map_info *map, __u16 adr)
{
@@ -831,21 +843,30 @@ static int chip_ready (struct map_info *map, struct flchip *chip, unsigned long
(mode == FL_WRITING && (cfip->SuspendCmdSupport & 1))))
goto sleep;
+ /* Do not allow suspend iff read/write to EB address */
+ if ((adr & chip->in_progress_block_mask) ==
+ chip->in_progress_block_addr)
+ goto sleep;
+
+ /* do not suspend small EBs, buggy Micron Chips */
+ if (cfi_is_micron_28F00AP30(cfi, chip) &&
+ (chip->in_progress_block_mask == ~(0x8000-1)))
+ goto sleep;
/* Erase suspend */
- map_write(map, CMD(0xB0), adr);
+ map_write(map, CMD(0xB0), chip->in_progress_block_addr);
/* If the flash has finished erasing, then 'erase suspend'
* appears to make some (28F320) flash devices switch to
* 'read' mode. Make sure that we switch to 'read status'
* mode so we get the right data. --rmk
*/
- map_write(map, CMD(0x70), adr);
+ map_write(map, CMD(0x70), chip->in_progress_block_addr);
chip->oldstate = FL_ERASING;
chip->state = FL_ERASE_SUSPENDING;
chip->erase_suspended = 1;
for (;;) {
- status = map_read(map, adr);
+ status = map_read(map, chip->in_progress_block_addr);
if (map_word_andequal(map, status, status_OK, status_OK))
break;
@@ -1041,8 +1062,8 @@ static void put_chip(struct map_info *map, struct flchip *chip, unsigned long ad
sending the 0x70 (Read Status) command to an erasing
chip and expecting it to be ignored, that's what we
do. */
- map_write(map, CMD(0xd0), adr);
- map_write(map, CMD(0x70), adr);
+ map_write(map, CMD(0xd0), chip->in_progress_block_addr);
+ map_write(map, CMD(0x70), chip->in_progress_block_addr);
chip->oldstate = FL_READY;
chip->state = FL_ERASING;
break;
@@ -1933,6 +1954,8 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip,
map_write(map, CMD(0xD0), adr);
chip->state = FL_ERASING;
chip->erase_suspended = 0;
+ chip->in_progress_block_addr = adr;
+ chip->in_progress_block_mask = ~(len - 1);
ret = INVAL_CACHE_AND_WAIT(map, chip, adr,
adr, len,
diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c
index 668e2cb..692902d 100644
--- a/drivers/mtd/chips/cfi_cmdset_0002.c
+++ b/drivers/mtd/chips/cfi_cmdset_0002.c
@@ -816,9 +816,10 @@ static int get_chip(struct map_info *map, struct flchip *chip, unsigned long adr
(mode == FL_WRITING && (cfip->EraseSuspend & 0x2))))
goto sleep;
- /* We could check to see if we're trying to access the sector
- * that is currently being erased. However, no user will try
- * anything like that so we just wait for the timeout. */
+ /* Do not allow suspend iff read/write to EB address */
+ if ((adr & chip->in_progress_block_mask) ==
+ chip->in_progress_block_addr)
+ goto sleep;
/* Erase suspend */
/* It's harmless to issue the Erase-Suspend and Erase-Resume
@@ -2267,6 +2268,7 @@ static int __xipram do_erase_chip(struct map_info *map, struct flchip *chip)
chip->state = FL_ERASING;
chip->erase_suspended = 0;
chip->in_progress_block_addr = adr;
+ chip->in_progress_block_mask = ~(map->size - 1);
INVALIDATE_CACHE_UDELAY(map, chip,
adr, map->size,
@@ -2356,6 +2358,7 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip,
chip->state = FL_ERASING;
chip->erase_suspended = 0;
chip->in_progress_block_addr = adr;
+ chip->in_progress_block_mask = ~(len - 1);
INVALIDATE_CACHE_UDELAY(map, chip,
adr, len,
diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig
index 6def544..57b02c4b 100644
--- a/drivers/mtd/devices/Kconfig
+++ b/drivers/mtd/devices/Kconfig
@@ -81,6 +81,7 @@
config MTD_M25P80
tristate "Support most SPI Flash chips (AT26DF, M25P, W25X, ...)"
depends on SPI_MASTER && MTD_SPI_NOR
+ select SPI_MEM
help
This enables access to most modern SPI flash chips, used for
program and data storage. Series supported include Atmel AT26DF,
diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index a4e18f6..e84563d 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -24,12 +24,13 @@
#include <linux/mtd/partitions.h>
#include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
#include <linux/spi/flash.h>
#include <linux/mtd/spi-nor.h>
#define MAX_CMD_SIZE 6
struct m25p {
- struct spi_device *spi;
+ struct spi_mem *spimem;
struct spi_nor spi_nor;
u8 command[MAX_CMD_SIZE];
};
@@ -37,97 +38,68 @@ struct m25p {
static int m25p80_read_reg(struct spi_nor *nor, u8 code, u8 *val, int len)
{
struct m25p *flash = nor->priv;
- struct spi_device *spi = flash->spi;
+ struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(code, 1),
+ SPI_MEM_OP_NO_ADDR,
+ SPI_MEM_OP_NO_DUMMY,
+ SPI_MEM_OP_DATA_IN(len, val, 1));
int ret;
- ret = spi_write_then_read(spi, &code, 1, val, len);
+ ret = spi_mem_exec_op(flash->spimem, &op);
if (ret < 0)
- dev_err(&spi->dev, "error %d reading %x\n", ret, code);
+ dev_err(&flash->spimem->spi->dev, "error %d reading %x\n", ret,
+ code);
return ret;
}
-static void m25p_addr2cmd(struct spi_nor *nor, unsigned int addr, u8 *cmd)
-{
- /* opcode is in cmd[0] */
- cmd[1] = addr >> (nor->addr_width * 8 - 8);
- cmd[2] = addr >> (nor->addr_width * 8 - 16);
- cmd[3] = addr >> (nor->addr_width * 8 - 24);
- cmd[4] = addr >> (nor->addr_width * 8 - 32);
-}
-
-static int m25p_cmdsz(struct spi_nor *nor)
-{
- return 1 + nor->addr_width;
-}
-
static int m25p80_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
{
struct m25p *flash = nor->priv;
- struct spi_device *spi = flash->spi;
+ struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(opcode, 1),
+ SPI_MEM_OP_NO_ADDR,
+ SPI_MEM_OP_NO_DUMMY,
+ SPI_MEM_OP_DATA_OUT(len, buf, 1));
- flash->command[0] = opcode;
- if (buf)
- memcpy(&flash->command[1], buf, len);
-
- return spi_write(spi, flash->command, len + 1);
+ return spi_mem_exec_op(flash->spimem, &op);
}
static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len,
const u_char *buf)
{
struct m25p *flash = nor->priv;
- struct spi_device *spi = flash->spi;
- unsigned int inst_nbits, addr_nbits, data_nbits, data_idx;
- struct spi_transfer t[3] = {};
- struct spi_message m;
- int cmd_sz = m25p_cmdsz(nor);
- ssize_t ret;
+ struct spi_mem_op op =
+ SPI_MEM_OP(SPI_MEM_OP_CMD(nor->program_opcode, 1),
+ SPI_MEM_OP_ADDR(nor->addr_width, to, 1),
+ SPI_MEM_OP_DUMMY(0, 1),
+ SPI_MEM_OP_DATA_OUT(len, buf, 1));
+ size_t remaining = len;
+ int ret;
/* get transfer protocols. */
- inst_nbits = spi_nor_get_protocol_inst_nbits(nor->write_proto);
- addr_nbits = spi_nor_get_protocol_addr_nbits(nor->write_proto);
- data_nbits = spi_nor_get_protocol_data_nbits(nor->write_proto);
-
- spi_message_init(&m);
+ op.cmd.buswidth = spi_nor_get_protocol_inst_nbits(nor->write_proto);
+ op.addr.buswidth = spi_nor_get_protocol_addr_nbits(nor->write_proto);
+ op.dummy.buswidth = op.addr.buswidth;
+ op.data.buswidth = spi_nor_get_protocol_data_nbits(nor->write_proto);
if (nor->program_opcode == SPINOR_OP_AAI_WP && nor->sst_write_second)
- cmd_sz = 1;
+ op.addr.nbytes = 0;
- flash->command[0] = nor->program_opcode;
- m25p_addr2cmd(nor, to, flash->command);
+ while (remaining) {
+ op.data.nbytes = remaining < UINT_MAX ? remaining : UINT_MAX;
+ ret = spi_mem_adjust_op_size(flash->spimem, &op);
+ if (ret)
+ return ret;
- t[0].tx_buf = flash->command;
- t[0].tx_nbits = inst_nbits;
- t[0].len = cmd_sz;
- spi_message_add_tail(&t[0], &m);
+ ret = spi_mem_exec_op(flash->spimem, &op);
+ if (ret)
+ return ret;
- /* split the op code and address bytes into two transfers if needed. */
- data_idx = 1;
- if (addr_nbits != inst_nbits) {
- t[0].len = 1;
-
- t[1].tx_buf = &flash->command[1];
- t[1].tx_nbits = addr_nbits;
- t[1].len = cmd_sz - 1;
- spi_message_add_tail(&t[1], &m);
-
- data_idx = 2;
+ op.addr.val += op.data.nbytes;
+ remaining -= op.data.nbytes;
+ op.data.buf.out += op.data.nbytes;
}
- t[data_idx].tx_buf = buf;
- t[data_idx].tx_nbits = data_nbits;
- t[data_idx].len = len;
- spi_message_add_tail(&t[data_idx], &m);
-
- ret = spi_sync(spi, &m);
- if (ret)
- return ret;
-
- ret = m.actual_length - cmd_sz;
- if (ret < 0)
- return -EIO;
- return ret;
+ return len;
}
/*
@@ -138,92 +110,39 @@ static ssize_t m25p80_read(struct spi_nor *nor, loff_t from, size_t len,
u_char *buf)
{
struct m25p *flash = nor->priv;
- struct spi_device *spi = flash->spi;
- unsigned int inst_nbits, addr_nbits, data_nbits, data_idx;
- struct spi_transfer t[3];
- struct spi_message m;
- unsigned int dummy = nor->read_dummy;
- ssize_t ret;
- int cmd_sz;
+ struct spi_mem_op op =
+ SPI_MEM_OP(SPI_MEM_OP_CMD(nor->read_opcode, 1),
+ SPI_MEM_OP_ADDR(nor->addr_width, from, 1),
+ SPI_MEM_OP_DUMMY(nor->read_dummy, 1),
+ SPI_MEM_OP_DATA_IN(len, buf, 1));
+ size_t remaining = len;
+ int ret;
/* get transfer protocols. */
- inst_nbits = spi_nor_get_protocol_inst_nbits(nor->read_proto);
- addr_nbits = spi_nor_get_protocol_addr_nbits(nor->read_proto);
- data_nbits = spi_nor_get_protocol_data_nbits(nor->read_proto);
+ op.cmd.buswidth = spi_nor_get_protocol_inst_nbits(nor->read_proto);
+ op.addr.buswidth = spi_nor_get_protocol_addr_nbits(nor->read_proto);
+ op.dummy.buswidth = op.addr.buswidth;
+ op.data.buswidth = spi_nor_get_protocol_data_nbits(nor->read_proto);
/* convert the dummy cycles to the number of bytes */
- dummy = (dummy * addr_nbits) / 8;
+ op.dummy.nbytes = (nor->read_dummy * op.dummy.buswidth) / 8;
- if (spi_flash_read_supported(spi)) {
- struct spi_flash_read_message msg;
-
- memset(&msg, 0, sizeof(msg));
-
- msg.buf = buf;
- msg.from = from;
- msg.len = len;
- msg.read_opcode = nor->read_opcode;
- msg.addr_width = nor->addr_width;
- msg.dummy_bytes = dummy;
- msg.opcode_nbits = inst_nbits;
- msg.addr_nbits = addr_nbits;
- msg.data_nbits = data_nbits;
-
- ret = spi_flash_read(spi, &msg);
- if (ret < 0)
+ while (remaining) {
+ op.data.nbytes = remaining < UINT_MAX ? remaining : UINT_MAX;
+ ret = spi_mem_adjust_op_size(flash->spimem, &op);
+ if (ret)
return ret;
- return msg.retlen;
+
+ ret = spi_mem_exec_op(flash->spimem, &op);
+ if (ret)
+ return ret;
+
+ op.addr.val += op.data.nbytes;
+ remaining -= op.data.nbytes;
+ op.data.buf.in += op.data.nbytes;
}
- spi_message_init(&m);
- memset(t, 0, (sizeof t));
-
- flash->command[0] = nor->read_opcode;
- m25p_addr2cmd(nor, from, flash->command);
-
- t[0].tx_buf = flash->command;
- t[0].tx_nbits = inst_nbits;
- t[0].len = m25p_cmdsz(nor) + dummy;
- spi_message_add_tail(&t[0], &m);
-
- /*
- * Set all dummy/mode cycle bits to avoid sending some manufacturer
- * specific pattern, which might make the memory enter its Continuous
- * Read mode by mistake.
- * Based on the different mode cycle bit patterns listed and described
- * in the JESD216B specification, the 0xff value works for all memories
- * and all manufacturers.
- */
- cmd_sz = t[0].len;
- memset(flash->command + cmd_sz - dummy, 0xff, dummy);
-
- /* split the op code and address bytes into two transfers if needed. */
- data_idx = 1;
- if (addr_nbits != inst_nbits) {
- t[0].len = 1;
-
- t[1].tx_buf = &flash->command[1];
- t[1].tx_nbits = addr_nbits;
- t[1].len = cmd_sz - 1;
- spi_message_add_tail(&t[1], &m);
-
- data_idx = 2;
- }
-
- t[data_idx].rx_buf = buf;
- t[data_idx].rx_nbits = data_nbits;
- t[data_idx].len = min3(len, spi_max_transfer_size(spi),
- spi_max_message_size(spi) - cmd_sz);
- spi_message_add_tail(&t[data_idx], &m);
-
- ret = spi_sync(spi, &m);
- if (ret)
- return ret;
-
- ret = m.actual_length - cmd_sz;
- if (ret < 0)
- return -EIO;
- return ret;
+ return len;
}
/*
@@ -231,8 +150,9 @@ static ssize_t m25p80_read(struct spi_nor *nor, loff_t from, size_t len,
* matches what the READ command supports, at least until this driver
* understands FAST_READ (for clocks over 25 MHz).
*/
-static int m25p_probe(struct spi_device *spi)
+static int m25p_probe(struct spi_mem *spimem)
{
+ struct spi_device *spi = spimem->spi;
struct flash_platform_data *data;
struct m25p *flash;
struct spi_nor *nor;
@@ -244,9 +164,9 @@ static int m25p_probe(struct spi_device *spi)
char *flash_name;
int ret;
- data = dev_get_platdata(&spi->dev);
+ data = dev_get_platdata(&spimem->spi->dev);
- flash = devm_kzalloc(&spi->dev, sizeof(*flash), GFP_KERNEL);
+ flash = devm_kzalloc(&spimem->spi->dev, sizeof(*flash), GFP_KERNEL);
if (!flash)
return -ENOMEM;
@@ -258,12 +178,12 @@ static int m25p_probe(struct spi_device *spi)
nor->write_reg = m25p80_write_reg;
nor->read_reg = m25p80_read_reg;
- nor->dev = &spi->dev;
+ nor->dev = &spimem->spi->dev;
spi_nor_set_flash_node(nor, spi->dev.of_node);
nor->priv = flash;
- spi_set_drvdata(spi, flash);
- flash->spi = spi;
+ spi_mem_set_drvdata(spimem, flash);
+ flash->spimem = spimem;
if (spi->mode & SPI_RX_QUAD) {
hwcaps.mask |= SNOR_HWCAPS_READ_1_1_4;
@@ -303,9 +223,9 @@ static int m25p_probe(struct spi_device *spi)
}
-static int m25p_remove(struct spi_device *spi)
+static int m25p_remove(struct spi_mem *spimem)
{
- struct m25p *flash = spi_get_drvdata(spi);
+ struct m25p *flash = spi_mem_get_drvdata(spimem);
spi_nor_restore(&flash->spi_nor);
@@ -313,9 +233,9 @@ static int m25p_remove(struct spi_device *spi)
return mtd_device_unregister(&flash->spi_nor.mtd);
}
-static void m25p_shutdown(struct spi_device *spi)
+static void m25p_shutdown(struct spi_mem *spimem)
{
- struct m25p *flash = spi_get_drvdata(spi);
+ struct m25p *flash = spi_mem_get_drvdata(spimem);
spi_nor_restore(&flash->spi_nor);
}
@@ -386,12 +306,14 @@ static const struct of_device_id m25p_of_table[] = {
};
MODULE_DEVICE_TABLE(of, m25p_of_table);
-static struct spi_driver m25p80_driver = {
- .driver = {
- .name = "m25p80",
- .of_match_table = m25p_of_table,
+static struct spi_mem_driver m25p80_driver = {
+ .spidrv = {
+ .driver = {
+ .name = "m25p80",
+ .of_match_table = m25p_of_table,
+ },
+ .id_table = m25p_ids,
},
- .id_table = m25p_ids,
.probe = m25p_probe,
.remove = m25p_remove,
.shutdown = m25p_shutdown,
@@ -402,7 +324,7 @@ static struct spi_driver m25p80_driver = {
*/
};
-module_spi_driver(m25p80_driver);
+module_spi_mem_driver(m25p80_driver);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Mike Lavender");
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index 16ae4ae..29c0bfd 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -82,7 +82,6 @@ static blk_status_t do_blktrans_request(struct mtd_blktrans_ops *tr,
block = blk_rq_pos(req) << 9 >> tr->blkshift;
nsect = blk_rq_cur_bytes(req) >> tr->blkshift;
- buf = bio_data(req->bio);
if (req_op(req) == REQ_OP_FLUSH) {
if (tr->flush(dev))
@@ -100,9 +99,14 @@ static blk_status_t do_blktrans_request(struct mtd_blktrans_ops *tr,
return BLK_STS_IOERR;
return BLK_STS_OK;
case REQ_OP_READ:
- for (; nsect > 0; nsect--, block++, buf += tr->blksize)
- if (tr->readsect(dev, block, buf))
+ buf = kmap(bio_page(req->bio)) + bio_offset(req->bio);
+ for (; nsect > 0; nsect--, block++, buf += tr->blksize) {
+ if (tr->readsect(dev, block, buf)) {
+ kunmap(bio_page(req->bio));
return BLK_STS_IOERR;
+ }
+ }
+ kunmap(bio_page(req->bio));
rq_flush_dcache_pages(req);
return BLK_STS_OK;
case REQ_OP_WRITE:
@@ -110,9 +114,14 @@ static blk_status_t do_blktrans_request(struct mtd_blktrans_ops *tr,
return BLK_STS_IOERR;
rq_flush_dcache_pages(req);
- for (; nsect > 0; nsect--, block++, buf += tr->blksize)
- if (tr->writesect(dev, block, buf))
+ buf = kmap(bio_page(req->bio)) + bio_offset(req->bio);
+ for (; nsect > 0; nsect--, block++, buf += tr->blksize) {
+ if (tr->writesect(dev, block, buf)) {
+ kunmap(bio_page(req->bio));
return BLK_STS_IOERR;
+ }
+ }
+ kunmap(bio_page(req->bio));
return BLK_STS_OK;
default:
return BLK_STS_IOERR;
@@ -418,7 +427,6 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
new->rq->queuedata = new;
blk_queue_logical_block_size(new->rq, tr->blksize);
- blk_queue_bounce_limit(new->rq, BLK_BOUNCE_HIGH);
blk_queue_flag_set(QUEUE_FLAG_NONROT, new->rq);
blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, new->rq);
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 807d17d..64a1fca 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -1829,18 +1829,6 @@ static int mtd_proc_show(struct seq_file *m, void *v)
mutex_unlock(&mtd_table_mutex);
return 0;
}
-
-static int mtd_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, mtd_proc_show, NULL);
-}
-
-static const struct file_operations mtd_proc_ops = {
- .open = mtd_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif /* CONFIG_PROC_FS */
/*====================================================================*/
@@ -1883,7 +1871,7 @@ static int __init init_mtd(void)
goto err_bdi;
}
- proc_mtd = proc_create("mtd", 0, NULL, &mtd_proc_ops);
+ proc_mtd = proc_create_single("mtd", 0, NULL, mtd_proc_show);
ret = init_mtdchar();
if (ret)
diff --git a/drivers/mtd/nand/core.c b/drivers/mtd/nand/core.c
index d0cd6f8..9c9f893 100644
--- a/drivers/mtd/nand/core.c
+++ b/drivers/mtd/nand/core.c
@@ -162,7 +162,6 @@ int nanddev_mtd_erase(struct mtd_info *mtd, struct erase_info *einfo)
ret = nanddev_erase(nand, &pos);
if (ret) {
einfo->fail_addr = nanddev_pos_to_offs(nand, &pos);
- einfo->state = MTD_ERASE_FAILED;
return ret;
}
@@ -170,8 +169,6 @@ int nanddev_mtd_erase(struct mtd_info *mtd, struct erase_info *einfo)
nanddev_pos_next_eraseblock(nand, &pos);
}
- einfo->state = MTD_ERASE_DONE;
-
return 0;
}
EXPORT_SYMBOL_GPL(nanddev_mtd_erase);
diff --git a/drivers/mtd/nand/onenand/omap2.c b/drivers/mtd/nand/onenand/omap2.c
index 9c159f0..3211371 100644
--- a/drivers/mtd/nand/onenand/omap2.c
+++ b/drivers/mtd/nand/onenand/omap2.c
@@ -375,56 +375,42 @@ static int omap2_onenand_read_bufferram(struct mtd_info *mtd, int area,
{
struct omap2_onenand *c = container_of(mtd, struct omap2_onenand, mtd);
struct onenand_chip *this = mtd->priv;
- dma_addr_t dma_src, dma_dst;
- int bram_offset;
+ struct device *dev = &c->pdev->dev;
void *buf = (void *)buffer;
+ dma_addr_t dma_src, dma_dst;
+ int bram_offset, err;
size_t xtra;
- int ret;
bram_offset = omap2_onenand_bufferram_offset(mtd, area) + area + offset;
- if (bram_offset & 3 || (size_t)buf & 3 || count < 384)
+ /*
+ * If the buffer address is not DMA-able, len is not long enough to make
+ * DMA transfers profitable or panic_write() may be in an interrupt
+ * context fallback to PIO mode.
+ */
+ if (!virt_addr_valid(buf) || bram_offset & 3 || (size_t)buf & 3 ||
+ count < 384 || in_interrupt() || oops_in_progress )
goto out_copy;
- /* panic_write() may be in an interrupt context */
- if (in_interrupt() || oops_in_progress)
- goto out_copy;
-
- if (buf >= high_memory) {
- struct page *p1;
-
- if (((size_t)buf & PAGE_MASK) !=
- ((size_t)(buf + count - 1) & PAGE_MASK))
- goto out_copy;
- p1 = vmalloc_to_page(buf);
- if (!p1)
- goto out_copy;
- buf = page_address(p1) + ((size_t)buf & ~PAGE_MASK);
- }
-
xtra = count & 3;
if (xtra) {
count -= xtra;
memcpy(buf + count, this->base + bram_offset + count, xtra);
}
+ dma_dst = dma_map_single(dev, buf, count, DMA_FROM_DEVICE);
dma_src = c->phys_base + bram_offset;
- dma_dst = dma_map_single(&c->pdev->dev, buf, count, DMA_FROM_DEVICE);
- if (dma_mapping_error(&c->pdev->dev, dma_dst)) {
- dev_err(&c->pdev->dev,
- "Couldn't DMA map a %d byte buffer\n",
- count);
+
+ if (dma_mapping_error(dev, dma_dst)) {
+ dev_err(dev, "Couldn't DMA map a %d byte buffer\n", count);
goto out_copy;
}
- ret = omap2_onenand_dma_transfer(c, dma_src, dma_dst, count);
- dma_unmap_single(&c->pdev->dev, dma_dst, count, DMA_FROM_DEVICE);
+ err = omap2_onenand_dma_transfer(c, dma_src, dma_dst, count);
+ dma_unmap_single(dev, dma_dst, count, DMA_FROM_DEVICE);
+ if (!err)
+ return 0;
- if (ret) {
- dev_err(&c->pdev->dev, "timeout waiting for DMA\n");
- goto out_copy;
- }
-
- return 0;
+ dev_err(dev, "timeout waiting for DMA\n");
out_copy:
memcpy(buf, this->base + bram_offset, count);
@@ -437,49 +423,34 @@ static int omap2_onenand_write_bufferram(struct mtd_info *mtd, int area,
{
struct omap2_onenand *c = container_of(mtd, struct omap2_onenand, mtd);
struct onenand_chip *this = mtd->priv;
- dma_addr_t dma_src, dma_dst;
- int bram_offset;
+ struct device *dev = &c->pdev->dev;
void *buf = (void *)buffer;
- int ret;
+ dma_addr_t dma_src, dma_dst;
+ int bram_offset, err;
bram_offset = omap2_onenand_bufferram_offset(mtd, area) + area + offset;
- if (bram_offset & 3 || (size_t)buf & 3 || count < 384)
+ /*
+ * If the buffer address is not DMA-able, len is not long enough to make
+ * DMA transfers profitable or panic_write() may be in an interrupt
+ * context fallback to PIO mode.
+ */
+ if (!virt_addr_valid(buf) || bram_offset & 3 || (size_t)buf & 3 ||
+ count < 384 || in_interrupt() || oops_in_progress )
goto out_copy;
- /* panic_write() may be in an interrupt context */
- if (in_interrupt() || oops_in_progress)
- goto out_copy;
-
- if (buf >= high_memory) {
- struct page *p1;
-
- if (((size_t)buf & PAGE_MASK) !=
- ((size_t)(buf + count - 1) & PAGE_MASK))
- goto out_copy;
- p1 = vmalloc_to_page(buf);
- if (!p1)
- goto out_copy;
- buf = page_address(p1) + ((size_t)buf & ~PAGE_MASK);
- }
-
- dma_src = dma_map_single(&c->pdev->dev, buf, count, DMA_TO_DEVICE);
+ dma_src = dma_map_single(dev, buf, count, DMA_TO_DEVICE);
dma_dst = c->phys_base + bram_offset;
- if (dma_mapping_error(&c->pdev->dev, dma_src)) {
- dev_err(&c->pdev->dev,
- "Couldn't DMA map a %d byte buffer\n",
- count);
- return -1;
- }
-
- ret = omap2_onenand_dma_transfer(c, dma_src, dma_dst, count);
- dma_unmap_single(&c->pdev->dev, dma_src, count, DMA_TO_DEVICE);
-
- if (ret) {
- dev_err(&c->pdev->dev, "timeout waiting for DMA\n");
+ if (dma_mapping_error(dev, dma_src)) {
+ dev_err(dev, "Couldn't DMA map a %d byte buffer\n", count);
goto out_copy;
}
- return 0;
+ err = omap2_onenand_dma_transfer(c, dma_src, dma_dst, count);
+ dma_unmap_page(dev, dma_src, count, DMA_TO_DEVICE);
+ if (!err)
+ return 0;
+
+ dev_err(dev, "timeout waiting for DMA\n");
out_copy:
memcpy(this->base + bram_offset, buf, count);
diff --git a/drivers/mtd/nand/raw/cafe_nand.c b/drivers/mtd/nand/raw/cafe_nand.c
index d8c8c9d..d721f48 100644
--- a/drivers/mtd/nand/raw/cafe_nand.c
+++ b/drivers/mtd/nand/raw/cafe_nand.c
@@ -394,12 +394,13 @@ static int cafe_nand_read_page(struct mtd_info *mtd, struct nand_chip *chip,
for (i=0; i<8; i+=2) {
uint32_t tmp = cafe_readl(cafe, NAND_ECC_SYN01 + (i*2));
- syn[i] = cafe->rs->index_of[tmp & 0xfff];
- syn[i+1] = cafe->rs->index_of[(tmp >> 16) & 0xfff];
+
+ syn[i] = cafe->rs->codec->index_of[tmp & 0xfff];
+ syn[i+1] = cafe->rs->codec->index_of[(tmp >> 16) & 0xfff];
}
n = decode_rs16(cafe->rs, NULL, NULL, 1367, syn, 0, pos, 0,
- pat);
+ pat);
for (i = 0; i < n; i++) {
int p = pos[i];
diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c
index 86a258de..2b7b2b9 100644
--- a/drivers/mtd/nand/raw/diskonchip.c
+++ b/drivers/mtd/nand/raw/diskonchip.c
@@ -66,6 +66,7 @@ struct doc_priv {
int curchip;
int mh0_page;
int mh1_page;
+ struct rs_control *rs_decoder;
struct mtd_info *nextdoc;
/* Handle the last stage of initialization (BBT scan, partitioning) */
@@ -123,9 +124,6 @@ MODULE_PARM_DESC(doc_config_location, "Physical memory address at which to probe
/* Number of symbols */
#define NN 1023
-/* the Reed Solomon control structure */
-static struct rs_control *rs_decoder;
-
/*
* The HW decoder in the DoC ASIC's provides us a error syndrome,
* which we must convert to a standard syndrome usable by the generic
@@ -140,6 +138,7 @@ static int doc_ecc_decode(struct rs_control *rs, uint8_t *data, uint8_t *ecc)
int i, j, nerr, errpos[8];
uint8_t parity;
uint16_t ds[4], s[5], tmp, errval[8], syn[4];
+ struct rs_codec *cd = rs->codec;
memset(syn, 0, sizeof(syn));
/* Convert the ecc bytes into words */
@@ -160,15 +159,15 @@ static int doc_ecc_decode(struct rs_control *rs, uint8_t *data, uint8_t *ecc)
for (j = 1; j < NROOTS; j++) {
if (ds[j] == 0)
continue;
- tmp = rs->index_of[ds[j]];
+ tmp = cd->index_of[ds[j]];
for (i = 0; i < NROOTS; i++)
- s[i] ^= rs->alpha_to[rs_modnn(rs, tmp + (FCR + i) * j)];
+ s[i] ^= cd->alpha_to[rs_modnn(cd, tmp + (FCR + i) * j)];
}
/* Calc syn[i] = s[i] / alpha^(v + i) */
for (i = 0; i < NROOTS; i++) {
if (s[i])
- syn[i] = rs_modnn(rs, rs->index_of[s[i]] + (NN - FCR - i));
+ syn[i] = rs_modnn(cd, cd->index_of[s[i]] + (NN - FCR - i));
}
/* Call the decoder library */
nerr = decode_rs16(rs, NULL, NULL, 1019, syn, 0, errpos, 0, errval);
@@ -930,7 +929,7 @@ static int doc200x_correct_data(struct mtd_info *mtd, u_char *dat,
calc_ecc[i] = ReadDOC_(docptr, DoC_ECCSyndrome0 + i);
}
- ret = doc_ecc_decode(rs_decoder, dat, calc_ecc);
+ ret = doc_ecc_decode(doc->rs_decoder, dat, calc_ecc);
if (ret > 0)
pr_err("doc200x_correct_data corrected %d errors\n",
ret);
@@ -1421,10 +1420,10 @@ static inline int __init doc2001plus_init(struct mtd_info *mtd)
static int __init doc_probe(unsigned long physadr)
{
+ struct nand_chip *nand = NULL;
+ struct doc_priv *doc = NULL;
unsigned char ChipID;
struct mtd_info *mtd;
- struct nand_chip *nand;
- struct doc_priv *doc;
void __iomem *virtadr;
unsigned char save_control;
unsigned char tmp, tmpb, tmpc;
@@ -1561,8 +1560,25 @@ static int __init doc_probe(unsigned long physadr)
goto fail;
}
+
+ /*
+ * Allocate a RS codec instance
+ *
+ * Symbolsize is 10 (bits)
+ * Primitve polynomial is x^10+x^3+1
+ * First consecutive root is 510
+ * Primitve element to generate roots = 1
+ * Generator polinomial degree = 4
+ */
+ doc = (struct doc_priv *) (nand + 1);
+ doc->rs_decoder = init_rs(10, 0x409, FCR, 1, NROOTS);
+ if (!doc->rs_decoder) {
+ pr_err("DiskOnChip: Could not create a RS codec\n");
+ ret = -ENOMEM;
+ goto fail;
+ }
+
mtd = nand_to_mtd(nand);
- doc = (struct doc_priv *) (nand + 1);
nand->bbt_td = (struct nand_bbt_descr *) (doc + 1);
nand->bbt_md = nand->bbt_td + 1;
@@ -1612,7 +1628,6 @@ static int __init doc_probe(unsigned long physadr)
haven't yet added it. This is handled without incident by
mtd_device_unregister, as far as I can tell. */
nand_release(mtd);
- kfree(nand);
goto fail;
}
@@ -1625,6 +1640,9 @@ static int __init doc_probe(unsigned long physadr)
actually a DiskOnChip. */
WriteDOC(save_control, virtadr, DOCControl);
fail:
+ if (doc)
+ free_rs(doc->rs_decoder);
+ kfree(nand);
iounmap(virtadr);
error_ioremap:
@@ -1647,6 +1665,7 @@ static void release_nanddoc(void)
nand_release(mtd);
iounmap(doc->virtadr);
release_mem_region(doc->physadr, DOC_IOREMAP_LEN);
+ free_rs(doc->rs_decoder);
kfree(nand);
}
}
@@ -1655,27 +1674,12 @@ static int __init init_nanddoc(void)
{
int i, ret = 0;
- /* We could create the decoder on demand, if memory is a concern.
- * This way we have it handy, if an error happens
- *
- * Symbolsize is 10 (bits)
- * Primitve polynomial is x^10+x^3+1
- * first consecutive root is 510
- * primitve element to generate roots = 1
- * generator polinomial degree = 4
- */
- rs_decoder = init_rs(10, 0x409, FCR, 1, NROOTS);
- if (!rs_decoder) {
- pr_err("DiskOnChip: Could not create a RS decoder\n");
- return -ENOMEM;
- }
-
if (doc_config_location) {
pr_info("Using configured DiskOnChip probe address 0x%lx\n",
doc_config_location);
ret = doc_probe(doc_config_location);
if (ret < 0)
- goto outerr;
+ return ret;
} else {
for (i = 0; (doc_locations[i] != 0xffffffff); i++) {
doc_probe(doc_locations[i]);
@@ -1686,11 +1690,7 @@ static int __init init_nanddoc(void)
if (!doclist) {
pr_info("No valid DiskOnChip devices found\n");
ret = -ENODEV;
- goto outerr;
}
- return 0;
- outerr:
- free_rs(rs_decoder);
return ret;
}
@@ -1698,11 +1698,6 @@ static void __exit cleanup_nanddoc(void)
{
/* Cleanup the nand/DoC resources */
release_nanddoc();
-
- /* Free the reed solomon resources */
- if (rs_decoder) {
- free_rs(rs_decoder);
- }
}
module_init(init_nanddoc);
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index 10e9532..ebb1d14 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -1074,7 +1074,7 @@ static int marvell_nfc_hw_ecc_hmg_do_write_page(struct nand_chip *chip,
return ret;
ret = marvell_nfc_wait_op(chip,
- chip->data_interface.timings.sdr.tPROG_max);
+ PSEC_TO_MSEC(chip->data_interface.timings.sdr.tPROG_max));
return ret;
}
@@ -1194,11 +1194,13 @@ static void marvell_nfc_hw_ecc_bch_read_chunk(struct nand_chip *chip, int chunk,
NDCB0_CMD2(NAND_CMD_READSTART);
/*
- * Trigger the naked read operation only on the last chunk.
- * Otherwise, use monolithic read.
+ * Trigger the monolithic read on the first chunk, then naked read on
+ * intermediate chunks and finally a last naked read on the last chunk.
*/
- if (lt->nchunks == 1 || (chunk < lt->nchunks - 1))
+ if (chunk == 0)
nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_MONOLITHIC_RW);
+ else if (chunk < lt->nchunks - 1)
+ nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_NAKED_RW);
else
nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_LAST_NAKED_RW);
@@ -1408,6 +1410,7 @@ marvell_nfc_hw_ecc_bch_write_chunk(struct nand_chip *chip, int chunk,
struct marvell_nand_chip *marvell_nand = to_marvell_nand(chip);
struct marvell_nfc *nfc = to_marvell_nfc(chip->controller);
const struct marvell_hw_ecc_layout *lt = to_marvell_nand(chip)->layout;
+ u32 xtype;
int ret;
struct marvell_nfc_op nfc_op = {
.ndcb[0] = NDCB0_CMD_TYPE(TYPE_WRITE) | NDCB0_LEN_OVRD,
@@ -1423,7 +1426,12 @@ marvell_nfc_hw_ecc_bch_write_chunk(struct nand_chip *chip, int chunk,
* last naked write.
*/
if (chunk == 0) {
- nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_WRITE_DISPATCH) |
+ if (lt->nchunks == 1)
+ xtype = XTYPE_MONOLITHIC_RW;
+ else
+ xtype = XTYPE_WRITE_DISPATCH;
+
+ nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(xtype) |
NDCB0_ADDR_CYC(marvell_nand->addr_cyc) |
NDCB0_CMD1(NAND_CMD_SEQIN);
nfc_op.ndcb[1] |= NDCB1_ADDRS_PAGE(page);
@@ -1494,7 +1502,7 @@ static int marvell_nfc_hw_ecc_bch_write_page(struct mtd_info *mtd,
}
ret = marvell_nfc_wait_op(chip,
- chip->data_interface.timings.sdr.tPROG_max);
+ PSEC_TO_MSEC(chip->data_interface.timings.sdr.tPROG_max));
marvell_nfc_disable_hw_ecc(chip);
@@ -2299,29 +2307,20 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc,
/*
* The legacy "num-cs" property indicates the number of CS on the only
* chip connected to the controller (legacy bindings does not support
- * more than one chip). CS are only incremented one by one while the RB
- * pin is always the #0.
+ * more than one chip). The CS and RB pins are always the #0.
*
* When not using legacy bindings, a couple of "reg" and "nand-rb"
* properties must be filled. For each chip, expressed as a subnode,
* "reg" points to the CS lines and "nand-rb" to the RB line.
*/
- if (pdata) {
+ if (pdata || nfc->caps->legacy_of_bindings) {
nsels = 1;
- } else if (nfc->caps->legacy_of_bindings &&
- !of_get_property(np, "num-cs", &nsels)) {
- dev_err(dev, "missing num-cs property\n");
- return -EINVAL;
- } else if (!of_get_property(np, "reg", &nsels)) {
- dev_err(dev, "missing reg property\n");
- return -EINVAL;
- }
-
- if (!pdata)
- nsels /= sizeof(u32);
- if (!nsels) {
- dev_err(dev, "invalid reg property size\n");
- return -EINVAL;
+ } else {
+ nsels = of_property_count_elems_of_size(np, "reg", sizeof(u32));
+ if (nsels <= 0) {
+ dev_err(dev, "missing/invalid reg property\n");
+ return -EINVAL;
+ }
}
/* Alloc the nand chip structure */
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 72f3a89..f28c3a5 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -706,12 +706,17 @@ static void nand_wait_status_ready(struct mtd_info *mtd, unsigned long timeo)
*/
int nand_soft_waitrdy(struct nand_chip *chip, unsigned long timeout_ms)
{
+ const struct nand_sdr_timings *timings;
u8 status = 0;
int ret;
if (!chip->exec_op)
return -ENOTSUPP;
+ /* Wait tWB before polling the STATUS reg. */
+ timings = nand_get_sdr_timings(&chip->data_interface);
+ ndelay(PSEC_TO_NSEC(timings->tWB_max));
+
ret = nand_status_op(chip, NULL);
if (ret)
return ret;
diff --git a/drivers/mtd/nand/raw/tango_nand.c b/drivers/mtd/nand/raw/tango_nand.c
index f54518f..f2052fa 100644
--- a/drivers/mtd/nand/raw/tango_nand.c
+++ b/drivers/mtd/nand/raw/tango_nand.c
@@ -645,7 +645,7 @@ static int tango_nand_probe(struct platform_device *pdev)
writel_relaxed(MODE_RAW, nfc->pbus_base + PBUS_PAD_MODE);
- clk = clk_get(&pdev->dev, NULL);
+ clk = devm_clk_get(&pdev->dev, NULL);
if (IS_ERR(clk))
return PTR_ERR(clk);
diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
index 4b8e918..5872f31 100644
--- a/drivers/mtd/spi-nor/cadence-quadspi.c
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -501,7 +501,9 @@ static int cqspi_indirect_read_execute(struct spi_nor *nor, u8 *rxbuf,
void __iomem *reg_base = cqspi->iobase;
void __iomem *ahb_base = cqspi->ahb_base;
unsigned int remaining = n_rx;
+ unsigned int mod_bytes = n_rx % 4;
unsigned int bytes_to_read = 0;
+ u8 *rxbuf_end = rxbuf + n_rx;
int ret = 0;
writel(from_addr, reg_base + CQSPI_REG_INDIRECTRDSTARTADDR);
@@ -530,11 +532,24 @@ static int cqspi_indirect_read_execute(struct spi_nor *nor, u8 *rxbuf,
}
while (bytes_to_read != 0) {
+ unsigned int word_remain = round_down(remaining, 4);
+
bytes_to_read *= cqspi->fifo_width;
bytes_to_read = bytes_to_read > remaining ?
remaining : bytes_to_read;
- ioread32_rep(ahb_base, rxbuf,
- DIV_ROUND_UP(bytes_to_read, 4));
+ bytes_to_read = round_down(bytes_to_read, 4);
+ /* Read 4 byte word chunks then single bytes */
+ if (bytes_to_read) {
+ ioread32_rep(ahb_base, rxbuf,
+ (bytes_to_read / 4));
+ } else if (!word_remain && mod_bytes) {
+ unsigned int temp = ioread32(ahb_base);
+
+ bytes_to_read = mod_bytes;
+ memcpy(rxbuf, &temp, min((unsigned int)
+ (rxbuf_end - rxbuf),
+ bytes_to_read));
+ }
rxbuf += bytes_to_read;
remaining -= bytes_to_read;
bytes_to_read = cqspi_get_rd_sram_level(cqspi);
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 1ed9529..5eb0df2 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -450,7 +450,7 @@ static void rlb_update_client(struct rlb_client_info *client_info)
{
int i;
- if (!client_info->slave)
+ if (!client_info->slave || !is_valid_ether_addr(client_info->mac_dst))
return;
for (i = 0; i < RLB_ARP_BURST_SIZE; i++) {
@@ -943,6 +943,10 @@ static void alb_send_lp_vid(struct slave *slave, u8 mac_addr[],
skb->priority = TC_PRIO_CONTROL;
skb->dev = slave->dev;
+ netdev_dbg(slave->bond->dev,
+ "Send learning packet: dev %s mac %pM vlan %d\n",
+ slave->dev->name, mac_addr, vid);
+
if (vid)
__vlan_hwaccel_put_tag(skb, vlan_proto, vid);
@@ -965,14 +969,13 @@ static int alb_upper_dev_walk(struct net_device *upper, void *_data)
u8 *mac_addr = data->mac_addr;
struct bond_vlan_tag *tags;
- if (is_vlan_dev(upper) && vlan_get_encap_level(upper) == 0) {
- if (strict_match &&
- ether_addr_equal_64bits(mac_addr,
- upper->dev_addr)) {
+ if (is_vlan_dev(upper) &&
+ bond->nest_level == vlan_get_encap_level(upper) - 1) {
+ if (upper->addr_assign_type == NET_ADDR_STOLEN) {
alb_send_lp_vid(slave, mac_addr,
vlan_dev_vlan_proto(upper),
vlan_dev_vlan_id(upper));
- } else if (!strict_match) {
+ } else {
alb_send_lp_vid(slave, upper->dev_addr,
vlan_dev_vlan_proto(upper),
vlan_dev_vlan_id(upper));
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b7b11301..1f1e97b 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1660,8 +1660,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
} /* switch(bond_mode) */
#ifdef CONFIG_NET_POLL_CONTROLLER
- slave_dev->npinfo = bond->dev->npinfo;
- if (slave_dev->npinfo) {
+ if (bond->dev->npinfo) {
if (slave_enable_netpoll(new_slave)) {
netdev_info(bond_dev, "master_dev is using netpoll, but new slave device does not support netpoll\n");
res = -EBUSY;
@@ -1739,6 +1738,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
if (bond_mode_uses_xmit_hash(bond))
bond_update_slave_arr(bond, NULL);
+ bond->nest_level = dev_get_nest_level(bond_dev);
+
netdev_info(bond_dev, "Enslaving %s as %s interface with %s link\n",
slave_dev->name,
bond_is_active_slave(new_slave) ? "an active" : "a backup",
diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c
index 01059f1..9f7d83e 100644
--- a/drivers/net/bonding/bond_procfs.c
+++ b/drivers/net/bonding/bond_procfs.c
@@ -10,7 +10,7 @@
static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(RCU)
{
- struct bonding *bond = seq->private;
+ struct bonding *bond = PDE_DATA(file_inode(seq->file));
struct list_head *iter;
struct slave *slave;
loff_t off = 0;
@@ -29,7 +29,7 @@ static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos)
static void *bond_info_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct bonding *bond = seq->private;
+ struct bonding *bond = PDE_DATA(file_inode(seq->file));
struct list_head *iter;
struct slave *slave;
bool found = false;
@@ -56,7 +56,7 @@ static void bond_info_seq_stop(struct seq_file *seq, void *v)
static void bond_info_show_master(struct seq_file *seq)
{
- struct bonding *bond = seq->private;
+ struct bonding *bond = PDE_DATA(file_inode(seq->file));
const struct bond_opt_value *optval;
struct slave *curr, *primary;
int i;
@@ -167,7 +167,7 @@ static void bond_info_show_master(struct seq_file *seq)
static void bond_info_show_slave(struct seq_file *seq,
const struct slave *slave)
{
- struct bonding *bond = seq->private;
+ struct bonding *bond = PDE_DATA(file_inode(seq->file));
seq_printf(seq, "\nSlave Interface: %s\n", slave->dev->name);
seq_printf(seq, "MII Status: %s\n", bond_slave_link_status(slave->link));
@@ -257,38 +257,14 @@ static const struct seq_operations bond_info_seq_ops = {
.show = bond_info_seq_show,
};
-static int bond_info_open(struct inode *inode, struct file *file)
-{
- struct seq_file *seq;
- int res;
-
- res = seq_open(file, &bond_info_seq_ops);
- if (!res) {
- /* recover the pointer buried in proc_dir_entry data */
- seq = file->private_data;
- seq->private = PDE_DATA(inode);
- }
-
- return res;
-}
-
-static const struct file_operations bond_info_fops = {
- .owner = THIS_MODULE,
- .open = bond_info_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
void bond_create_proc_entry(struct bonding *bond)
{
struct net_device *bond_dev = bond->dev;
struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id);
if (bn->proc_dir) {
- bond->proc_entry = proc_create_data(bond_dev->name,
- 0444, bn->proc_dir,
- &bond_info_fops, bond);
+ bond->proc_entry = proc_create_seq_data(bond_dev->name, 0444,
+ bn->proc_dir, &bond_info_seq_ops, bond);
if (bond->proc_entry == NULL)
netdev_warn(bond_dev, "Cannot create /proc/net/%s/%s\n",
DRV_NAME, bond_dev->name);
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index b177956..3c71f1c 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -605,7 +605,7 @@ void can_bus_off(struct net_device *dev)
{
struct can_priv *priv = netdev_priv(dev);
- netdev_dbg(dev, "bus-off\n");
+ netdev_info(dev, "bus-off\n");
netif_carrier_off(dev);
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 634c51e..d53a45b 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -200,6 +200,7 @@
#define FLEXCAN_QUIRK_DISABLE_MECR BIT(4) /* Disable Memory error detection */
#define FLEXCAN_QUIRK_USE_OFF_TIMESTAMP BIT(5) /* Use timestamp based offloading */
#define FLEXCAN_QUIRK_BROKEN_PERR_STATE BIT(6) /* No interrupt for error passive */
+#define FLEXCAN_QUIRK_DEFAULT_BIG_ENDIAN BIT(7) /* default to BE register access */
/* Structure of the message buffer */
struct flexcan_mb {
@@ -288,6 +289,12 @@ struct flexcan_priv {
static const struct flexcan_devtype_data fsl_p1010_devtype_data = {
.quirks = FLEXCAN_QUIRK_BROKEN_WERR_STATE |
+ FLEXCAN_QUIRK_BROKEN_PERR_STATE |
+ FLEXCAN_QUIRK_DEFAULT_BIG_ENDIAN,
+};
+
+static const struct flexcan_devtype_data fsl_imx25_devtype_data = {
+ .quirks = FLEXCAN_QUIRK_BROKEN_WERR_STATE |
FLEXCAN_QUIRK_BROKEN_PERR_STATE,
};
@@ -1251,9 +1258,9 @@ static void unregister_flexcandev(struct net_device *dev)
static const struct of_device_id flexcan_of_match[] = {
{ .compatible = "fsl,imx6q-flexcan", .data = &fsl_imx6q_devtype_data, },
{ .compatible = "fsl,imx28-flexcan", .data = &fsl_imx28_devtype_data, },
- { .compatible = "fsl,imx53-flexcan", .data = &fsl_p1010_devtype_data, },
- { .compatible = "fsl,imx35-flexcan", .data = &fsl_p1010_devtype_data, },
- { .compatible = "fsl,imx25-flexcan", .data = &fsl_p1010_devtype_data, },
+ { .compatible = "fsl,imx53-flexcan", .data = &fsl_imx25_devtype_data, },
+ { .compatible = "fsl,imx35-flexcan", .data = &fsl_imx25_devtype_data, },
+ { .compatible = "fsl,imx25-flexcan", .data = &fsl_imx25_devtype_data, },
{ .compatible = "fsl,p1010-flexcan", .data = &fsl_p1010_devtype_data, },
{ .compatible = "fsl,vf610-flexcan", .data = &fsl_vf610_devtype_data, },
{ .compatible = "fsl,ls1021ar2-flexcan", .data = &fsl_ls1021a_r2_devtype_data, },
@@ -1337,18 +1344,13 @@ static int flexcan_probe(struct platform_device *pdev)
priv = netdev_priv(dev);
- if (of_property_read_bool(pdev->dev.of_node, "big-endian")) {
+ if (of_property_read_bool(pdev->dev.of_node, "big-endian") ||
+ devtype_data->quirks & FLEXCAN_QUIRK_DEFAULT_BIG_ENDIAN) {
priv->read = flexcan_read_be;
priv->write = flexcan_write_be;
} else {
- if (of_device_is_compatible(pdev->dev.of_node,
- "fsl,p1010-flexcan")) {
- priv->read = flexcan_read_be;
- priv->write = flexcan_write_be;
- } else {
- priv->read = flexcan_read_le;
- priv->write = flexcan_write_le;
- }
+ priv->read = flexcan_read_le;
+ priv->write = flexcan_write_le;
}
priv->can.clock.freq = clock_freq;
diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c
index 5590c55..53e320c 100644
--- a/drivers/net/can/spi/hi311x.c
+++ b/drivers/net/can/spi/hi311x.c
@@ -91,6 +91,7 @@
#define HI3110_STAT_BUSOFF BIT(2)
#define HI3110_STAT_ERRP BIT(3)
#define HI3110_STAT_ERRW BIT(4)
+#define HI3110_STAT_TXMTY BIT(7)
#define HI3110_BTR0_SJW_SHIFT 6
#define HI3110_BTR0_BRP_SHIFT 0
@@ -427,8 +428,10 @@ static int hi3110_get_berr_counter(const struct net_device *net,
struct hi3110_priv *priv = netdev_priv(net);
struct spi_device *spi = priv->spi;
+ mutex_lock(&priv->hi3110_lock);
bec->txerr = hi3110_read(spi, HI3110_READ_TEC);
bec->rxerr = hi3110_read(spi, HI3110_READ_REC);
+ mutex_unlock(&priv->hi3110_lock);
return 0;
}
@@ -735,10 +738,7 @@ static irqreturn_t hi3110_can_ist(int irq, void *dev_id)
}
}
- if (intf == 0)
- break;
-
- if (intf & HI3110_INT_TXCPLT) {
+ if (priv->tx_len && statf & HI3110_STAT_TXMTY) {
net->stats.tx_packets++;
net->stats.tx_bytes += priv->tx_len - 1;
can_led_event(net, CAN_LED_EVENT_TX);
@@ -748,6 +748,9 @@ static irqreturn_t hi3110_can_ist(int irq, void *dev_id)
}
netif_wake_queue(net);
}
+
+ if (intf == 0)
+ break;
}
mutex_unlock(&priv->hi3110_lock);
return IRQ_HANDLED;
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 63587b8..daed57d 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -1179,7 +1179,7 @@ static void kvaser_usb_rx_can_msg(const struct kvaser_usb *dev,
skb = alloc_can_skb(priv->netdev, &cf);
if (!skb) {
- stats->tx_dropped++;
+ stats->rx_dropped++;
return;
}
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 7861678..3da5fca 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1712,6 +1712,18 @@ static const struct b53_chip_data b53_switch_chips[] = {
.duplex_reg = B53_DUPLEX_STAT_FE,
},
{
+ .chip_id = BCM5389_DEVICE_ID,
+ .dev_name = "BCM5389",
+ .vlans = 4096,
+ .enabled_ports = 0x1f,
+ .arl_entries = 4,
+ .cpu_port = B53_CPU_PORT,
+ .vta_regs = B53_VTA_REGS,
+ .duplex_reg = B53_DUPLEX_STAT_GE,
+ .jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+ .jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+ },
+ {
.chip_id = BCM5395_DEVICE_ID,
.dev_name = "BCM5395",
.vlans = 4096,
@@ -2034,6 +2046,7 @@ int b53_switch_detect(struct b53_device *dev)
else
dev->chip_id = BCM5365_DEVICE_ID;
break;
+ case BCM5389_DEVICE_ID:
case BCM5395_DEVICE_ID:
case BCM5397_DEVICE_ID:
case BCM5398_DEVICE_ID:
diff --git a/drivers/net/dsa/b53/b53_mdio.c b/drivers/net/dsa/b53/b53_mdio.c
index fa7556f..a533a90 100644
--- a/drivers/net/dsa/b53/b53_mdio.c
+++ b/drivers/net/dsa/b53/b53_mdio.c
@@ -285,6 +285,7 @@ static const struct b53_io_ops b53_mdio_ops = {
#define B53_BRCM_OUI_1 0x0143bc00
#define B53_BRCM_OUI_2 0x03625c00
#define B53_BRCM_OUI_3 0x00406000
+#define B53_BRCM_OUI_4 0x01410c00
static int b53_mdio_probe(struct mdio_device *mdiodev)
{
@@ -311,7 +312,8 @@ static int b53_mdio_probe(struct mdio_device *mdiodev)
*/
if ((phy_id & 0xfffffc00) != B53_BRCM_OUI_1 &&
(phy_id & 0xfffffc00) != B53_BRCM_OUI_2 &&
- (phy_id & 0xfffffc00) != B53_BRCM_OUI_3) {
+ (phy_id & 0xfffffc00) != B53_BRCM_OUI_3 &&
+ (phy_id & 0xfffffc00) != B53_BRCM_OUI_4) {
dev_err(&mdiodev->dev, "Unsupported device: 0x%08x\n", phy_id);
return -ENODEV;
}
@@ -360,6 +362,7 @@ static const struct of_device_id b53_of_match[] = {
{ .compatible = "brcm,bcm53125" },
{ .compatible = "brcm,bcm53128" },
{ .compatible = "brcm,bcm5365" },
+ { .compatible = "brcm,bcm5389" },
{ .compatible = "brcm,bcm5395" },
{ .compatible = "brcm,bcm5397" },
{ .compatible = "brcm,bcm5398" },
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index 1187ebd..3b57f47 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -48,6 +48,7 @@ struct b53_io_ops {
enum {
BCM5325_DEVICE_ID = 0x25,
BCM5365_DEVICE_ID = 0x65,
+ BCM5389_DEVICE_ID = 0x89,
BCM5395_DEVICE_ID = 0x95,
BCM5397_DEVICE_ID = 0x97,
BCM5398_DEVICE_ID = 0x98,
diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 23b45da..b89acae 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -354,10 +354,13 @@ static int bcm_sf2_cfp_ipv4_rule_set(struct bcm_sf2_priv *priv, int port,
/* Locate the first rule available */
if (fs->location == RX_CLS_LOC_ANY)
rule_index = find_first_zero_bit(priv->cfp.used,
- bcm_sf2_cfp_rule_size(priv));
+ priv->num_cfp_rules);
else
rule_index = fs->location;
+ if (rule_index > bcm_sf2_cfp_rule_size(priv))
+ return -ENOSPC;
+
layout = &udf_tcpip4_layout;
/* We only use one UDF slice for now */
slice_num = bcm_sf2_get_slice_number(layout, 0);
@@ -562,19 +565,21 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port,
* first half because the HW search is by incrementing addresses.
*/
if (fs->location == RX_CLS_LOC_ANY)
- rule_index[0] = find_first_zero_bit(priv->cfp.used,
- bcm_sf2_cfp_rule_size(priv));
+ rule_index[1] = find_first_zero_bit(priv->cfp.used,
+ priv->num_cfp_rules);
else
- rule_index[0] = fs->location;
+ rule_index[1] = fs->location;
+ if (rule_index[1] > bcm_sf2_cfp_rule_size(priv))
+ return -ENOSPC;
/* Flag it as used (cleared on error path) such that we can immediately
* obtain a second one to chain from.
*/
- set_bit(rule_index[0], priv->cfp.used);
+ set_bit(rule_index[1], priv->cfp.used);
- rule_index[1] = find_first_zero_bit(priv->cfp.used,
- bcm_sf2_cfp_rule_size(priv));
- if (rule_index[1] > bcm_sf2_cfp_rule_size(priv)) {
+ rule_index[0] = find_first_zero_bit(priv->cfp.used,
+ priv->num_cfp_rules);
+ if (rule_index[0] > bcm_sf2_cfp_rule_size(priv)) {
ret = -ENOSPC;
goto out_err;
}
@@ -712,14 +717,14 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port,
/* Flag the second half rule as being used now, return it as the
* location, and flag it as unique while dumping rules
*/
- set_bit(rule_index[1], priv->cfp.used);
+ set_bit(rule_index[0], priv->cfp.used);
set_bit(rule_index[1], priv->cfp.unique);
fs->location = rule_index[1];
return ret;
out_err:
- clear_bit(rule_index[0], priv->cfp.used);
+ clear_bit(rule_index[1], priv->cfp.used);
return ret;
}
@@ -785,10 +790,6 @@ static int bcm_sf2_cfp_rule_del_one(struct bcm_sf2_priv *priv, int port,
int ret;
u32 reg;
- /* Refuse deletion of unused rules, and the default reserved rule */
- if (!test_bit(loc, priv->cfp.used) || loc == 0)
- return -EINVAL;
-
/* Indicate which rule we want to read */
bcm_sf2_cfp_rule_addr_set(priv, loc);
@@ -826,6 +827,13 @@ static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
u32 next_loc = 0;
int ret;
+ /* Refuse deleting unused rules, and those that are not unique since
+ * that could leave IPv6 rules with one of the chained rule in the
+ * table.
+ */
+ if (!test_bit(loc, priv->cfp.unique) || loc == 0)
+ return -EINVAL;
+
ret = bcm_sf2_cfp_rule_del_one(priv, port, loc, &next_loc);
if (ret)
return ret;
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 3d20910..5b4374f 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3370,6 +3370,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_internal_phys = 5,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
@@ -3391,6 +3392,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_internal_phys = 0,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
@@ -3410,6 +3412,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_internal_phys = 8,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
@@ -3431,6 +3434,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_internal_phys = 5,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
@@ -3452,6 +3456,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_internal_phys = 0,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
@@ -3472,6 +3477,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_gpio = 11,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x10,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 3750,
@@ -3493,6 +3499,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_internal_phys = 5,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
@@ -3514,6 +3521,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_internal_phys = 0,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
@@ -3535,6 +3543,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_internal_phys = 5,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
@@ -3557,6 +3566,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_gpio = 15,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
@@ -3578,6 +3588,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_internal_phys = 5,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
@@ -3600,6 +3611,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_gpio = 15,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
@@ -3621,6 +3633,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_internal_phys = 0,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
@@ -3641,6 +3654,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_gpio = 16,
.max_vid = 8191,
.port_base_addr = 0x0,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.tag_protocol = DSA_TAG_PROTO_DSA,
@@ -3663,6 +3677,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_gpio = 16,
.max_vid = 8191,
.port_base_addr = 0x0,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 3750,
@@ -3684,6 +3699,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_internal_phys = 11,
.max_vid = 8191,
.port_base_addr = 0x0,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 3750,
@@ -3707,6 +3723,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_gpio = 15,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
@@ -3730,6 +3747,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_gpio = 16,
.max_vid = 8191,
.port_base_addr = 0x0,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 3750,
@@ -3753,6 +3771,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_gpio = 15,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
@@ -3776,6 +3795,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_gpio = 15,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
@@ -3798,6 +3818,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_gpio = 11,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x10,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 3750,
@@ -3820,6 +3841,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_internal_phys = 5,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
@@ -3841,6 +3863,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_internal_phys = 5,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
@@ -3863,6 +3886,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_gpio = 15,
.max_vid = 4095,
.port_base_addr = 0x10,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 15000,
@@ -3885,6 +3909,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_gpio = 16,
.max_vid = 8191,
.port_base_addr = 0x0,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 3750,
@@ -3907,6 +3932,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.num_gpio = 16,
.max_vid = 8191,
.port_base_addr = 0x0,
+ .phy_base_addr = 0x0,
.global1_addr = 0x1b,
.global2_addr = 0x1c,
.age_time_coeff = 3750,
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 80490f6..12b7f46 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -114,6 +114,7 @@ struct mv88e6xxx_info {
unsigned int num_gpio;
unsigned int max_vid;
unsigned int port_base_addr;
+ unsigned int phy_base_addr;
unsigned int global1_addr;
unsigned int global2_addr;
unsigned int age_time_coeff;
diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c
index 0ce627f..8d22d66 100644
--- a/drivers/net/dsa/mv88e6xxx/global2.c
+++ b/drivers/net/dsa/mv88e6xxx/global2.c
@@ -1118,7 +1118,7 @@ int mv88e6xxx_g2_irq_mdio_setup(struct mv88e6xxx_chip *chip,
err = irq;
goto out;
}
- bus->irq[chip->info->port_base_addr + phy] = irq;
+ bus->irq[chip->info->phy_base_addr + phy] = irq;
}
return 0;
out:
diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.c b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
index ac7694c7..a036c49 100644
--- a/drivers/net/dsa/mv88e6xxx/hwtstamp.c
+++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
@@ -285,10 +285,18 @@ static void mv88e6xxx_get_rxts(struct mv88e6xxx_chip *chip,
struct sk_buff_head *rxq)
{
u16 buf[4] = { 0 }, status, seq_id;
- u64 ns, timelo, timehi;
struct skb_shared_hwtstamps *shwt;
+ struct sk_buff_head received;
+ u64 ns, timelo, timehi;
+ unsigned long flags;
int err;
+ /* The latched timestamp belongs to one of the received frames. */
+ __skb_queue_head_init(&received);
+ spin_lock_irqsave(&rxq->lock, flags);
+ skb_queue_splice_tail_init(rxq, &received);
+ spin_unlock_irqrestore(&rxq->lock, flags);
+
mutex_lock(&chip->reg_lock);
err = mv88e6xxx_port_ptp_read(chip, ps->port_id,
reg, buf, ARRAY_SIZE(buf));
@@ -311,7 +319,7 @@ static void mv88e6xxx_get_rxts(struct mv88e6xxx_chip *chip,
/* Since the device can only handle one time stamp at a time,
* we purge any extra frames from the queue.
*/
- for ( ; skb; skb = skb_dequeue(rxq)) {
+ for ( ; skb; skb = __skb_dequeue(&received)) {
if (mv88e6xxx_ts_valid(status) && seq_match(skb, seq_id)) {
ns = timehi << 16 | timelo;
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 36c8950..176861b 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -1212,9 +1212,9 @@ static int vortex_probe1(struct device *gendev, void __iomem *ioaddr, int irq,
vp->mii.reg_num_mask = 0x1f;
/* Makes sure rings are at least 16 byte aligned. */
- vp->rx_ring = pci_alloc_consistent(pdev, sizeof(struct boom_rx_desc) * RX_RING_SIZE
+ vp->rx_ring = dma_alloc_coherent(gendev, sizeof(struct boom_rx_desc) * RX_RING_SIZE
+ sizeof(struct boom_tx_desc) * TX_RING_SIZE,
- &vp->rx_ring_dma);
+ &vp->rx_ring_dma, GFP_KERNEL);
retval = -ENOMEM;
if (!vp->rx_ring)
goto free_device;
@@ -1476,11 +1476,10 @@ static int vortex_probe1(struct device *gendev, void __iomem *ioaddr, int irq,
return 0;
free_ring:
- pci_free_consistent(pdev,
- sizeof(struct boom_rx_desc) * RX_RING_SIZE
- + sizeof(struct boom_tx_desc) * TX_RING_SIZE,
- vp->rx_ring,
- vp->rx_ring_dma);
+ dma_free_coherent(&pdev->dev,
+ sizeof(struct boom_rx_desc) * RX_RING_SIZE +
+ sizeof(struct boom_tx_desc) * TX_RING_SIZE,
+ vp->rx_ring, vp->rx_ring_dma);
free_device:
free_netdev(dev);
pr_err(PFX "vortex_probe1 fails. Returns %d\n", retval);
@@ -1751,9 +1750,9 @@ vortex_open(struct net_device *dev)
break; /* Bad news! */
skb_reserve(skb, NET_IP_ALIGN); /* Align IP on 16 byte boundaries */
- dma = pci_map_single(VORTEX_PCI(vp), skb->data,
- PKT_BUF_SZ, PCI_DMA_FROMDEVICE);
- if (dma_mapping_error(&VORTEX_PCI(vp)->dev, dma))
+ dma = dma_map_single(vp->gendev, skb->data,
+ PKT_BUF_SZ, DMA_FROM_DEVICE);
+ if (dma_mapping_error(vp->gendev, dma))
break;
vp->rx_ring[i].addr = cpu_to_le32(dma);
}
@@ -2067,9 +2066,9 @@ vortex_start_xmit(struct sk_buff *skb, struct net_device *dev)
if (vp->bus_master) {
/* Set the bus-master controller to transfer the packet. */
int len = (skb->len + 3) & ~3;
- vp->tx_skb_dma = pci_map_single(VORTEX_PCI(vp), skb->data, len,
- PCI_DMA_TODEVICE);
- if (dma_mapping_error(&VORTEX_PCI(vp)->dev, vp->tx_skb_dma)) {
+ vp->tx_skb_dma = dma_map_single(vp->gendev, skb->data, len,
+ DMA_TO_DEVICE);
+ if (dma_mapping_error(vp->gendev, vp->tx_skb_dma)) {
dev_kfree_skb_any(skb);
dev->stats.tx_dropped++;
return NETDEV_TX_OK;
@@ -2168,9 +2167,9 @@ boomerang_start_xmit(struct sk_buff *skb, struct net_device *dev)
vp->tx_ring[entry].status = cpu_to_le32(skb->len | TxIntrUploaded | AddTCPChksum | AddUDPChksum);
if (!skb_shinfo(skb)->nr_frags) {
- dma_addr = pci_map_single(VORTEX_PCI(vp), skb->data, skb->len,
- PCI_DMA_TODEVICE);
- if (dma_mapping_error(&VORTEX_PCI(vp)->dev, dma_addr))
+ dma_addr = dma_map_single(vp->gendev, skb->data, skb->len,
+ DMA_TO_DEVICE);
+ if (dma_mapping_error(vp->gendev, dma_addr))
goto out_dma_err;
vp->tx_ring[entry].frag[0].addr = cpu_to_le32(dma_addr);
@@ -2178,9 +2177,9 @@ boomerang_start_xmit(struct sk_buff *skb, struct net_device *dev)
} else {
int i;
- dma_addr = pci_map_single(VORTEX_PCI(vp), skb->data,
- skb_headlen(skb), PCI_DMA_TODEVICE);
- if (dma_mapping_error(&VORTEX_PCI(vp)->dev, dma_addr))
+ dma_addr = dma_map_single(vp->gendev, skb->data,
+ skb_headlen(skb), DMA_TO_DEVICE);
+ if (dma_mapping_error(vp->gendev, dma_addr))
goto out_dma_err;
vp->tx_ring[entry].frag[0].addr = cpu_to_le32(dma_addr);
@@ -2189,21 +2188,21 @@ boomerang_start_xmit(struct sk_buff *skb, struct net_device *dev)
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
- dma_addr = skb_frag_dma_map(&VORTEX_PCI(vp)->dev, frag,
+ dma_addr = skb_frag_dma_map(vp->gendev, frag,
0,
frag->size,
DMA_TO_DEVICE);
- if (dma_mapping_error(&VORTEX_PCI(vp)->dev, dma_addr)) {
+ if (dma_mapping_error(vp->gendev, dma_addr)) {
for(i = i-1; i >= 0; i--)
- dma_unmap_page(&VORTEX_PCI(vp)->dev,
+ dma_unmap_page(vp->gendev,
le32_to_cpu(vp->tx_ring[entry].frag[i+1].addr),
le32_to_cpu(vp->tx_ring[entry].frag[i+1].length),
DMA_TO_DEVICE);
- pci_unmap_single(VORTEX_PCI(vp),
+ dma_unmap_single(vp->gendev,
le32_to_cpu(vp->tx_ring[entry].frag[0].addr),
le32_to_cpu(vp->tx_ring[entry].frag[0].length),
- PCI_DMA_TODEVICE);
+ DMA_TO_DEVICE);
goto out_dma_err;
}
@@ -2218,8 +2217,8 @@ boomerang_start_xmit(struct sk_buff *skb, struct net_device *dev)
}
}
#else
- dma_addr = pci_map_single(VORTEX_PCI(vp), skb->data, skb->len, PCI_DMA_TODEVICE);
- if (dma_mapping_error(&VORTEX_PCI(vp)->dev, dma_addr))
+ dma_addr = dma_map_single(vp->gendev, skb->data, skb->len, DMA_TO_DEVICE);
+ if (dma_mapping_error(vp->gendev, dma_addr))
goto out_dma_err;
vp->tx_ring[entry].addr = cpu_to_le32(dma_addr);
vp->tx_ring[entry].length = cpu_to_le32(skb->len | LAST_FRAG);
@@ -2254,7 +2253,7 @@ boomerang_start_xmit(struct sk_buff *skb, struct net_device *dev)
out:
return NETDEV_TX_OK;
out_dma_err:
- dev_err(&VORTEX_PCI(vp)->dev, "Error mapping dma buffer\n");
+ dev_err(vp->gendev, "Error mapping dma buffer\n");
goto out;
}
@@ -2322,7 +2321,7 @@ vortex_interrupt(int irq, void *dev_id)
if (status & DMADone) {
if (ioread16(ioaddr + Wn7_MasterStatus) & 0x1000) {
iowrite16(0x1000, ioaddr + Wn7_MasterStatus); /* Ack the event. */
- pci_unmap_single(VORTEX_PCI(vp), vp->tx_skb_dma, (vp->tx_skb->len + 3) & ~3, PCI_DMA_TODEVICE);
+ dma_unmap_single(vp->gendev, vp->tx_skb_dma, (vp->tx_skb->len + 3) & ~3, DMA_TO_DEVICE);
pkts_compl++;
bytes_compl += vp->tx_skb->len;
dev_kfree_skb_irq(vp->tx_skb); /* Release the transferred buffer */
@@ -2459,19 +2458,19 @@ boomerang_interrupt(int irq, void *dev_id)
struct sk_buff *skb = vp->tx_skbuff[entry];
#if DO_ZEROCOPY
int i;
- pci_unmap_single(VORTEX_PCI(vp),
+ dma_unmap_single(vp->gendev,
le32_to_cpu(vp->tx_ring[entry].frag[0].addr),
le32_to_cpu(vp->tx_ring[entry].frag[0].length)&0xFFF,
- PCI_DMA_TODEVICE);
+ DMA_TO_DEVICE);
for (i=1; i<=skb_shinfo(skb)->nr_frags; i++)
- pci_unmap_page(VORTEX_PCI(vp),
+ dma_unmap_page(vp->gendev,
le32_to_cpu(vp->tx_ring[entry].frag[i].addr),
le32_to_cpu(vp->tx_ring[entry].frag[i].length)&0xFFF,
- PCI_DMA_TODEVICE);
+ DMA_TO_DEVICE);
#else
- pci_unmap_single(VORTEX_PCI(vp),
- le32_to_cpu(vp->tx_ring[entry].addr), skb->len, PCI_DMA_TODEVICE);
+ dma_unmap_single(vp->gendev,
+ le32_to_cpu(vp->tx_ring[entry].addr), skb->len, DMA_TO_DEVICE);
#endif
pkts_compl++;
bytes_compl += skb->len;
@@ -2561,14 +2560,14 @@ static int vortex_rx(struct net_device *dev)
/* 'skb_put()' points to the start of sk_buff data area. */
if (vp->bus_master &&
! (ioread16(ioaddr + Wn7_MasterStatus) & 0x8000)) {
- dma_addr_t dma = pci_map_single(VORTEX_PCI(vp), skb_put(skb, pkt_len),
- pkt_len, PCI_DMA_FROMDEVICE);
+ dma_addr_t dma = dma_map_single(vp->gendev, skb_put(skb, pkt_len),
+ pkt_len, DMA_FROM_DEVICE);
iowrite32(dma, ioaddr + Wn7_MasterAddr);
iowrite16((skb->len + 3) & ~3, ioaddr + Wn7_MasterLen);
iowrite16(StartDMAUp, ioaddr + EL3_CMD);
while (ioread16(ioaddr + Wn7_MasterStatus) & 0x8000)
;
- pci_unmap_single(VORTEX_PCI(vp), dma, pkt_len, PCI_DMA_FROMDEVICE);
+ dma_unmap_single(vp->gendev, dma, pkt_len, DMA_FROM_DEVICE);
} else {
ioread32_rep(ioaddr + RX_FIFO,
skb_put(skb, pkt_len),
@@ -2635,11 +2634,11 @@ boomerang_rx(struct net_device *dev)
if (pkt_len < rx_copybreak &&
(skb = netdev_alloc_skb(dev, pkt_len + 2)) != NULL) {
skb_reserve(skb, 2); /* Align IP on 16 byte boundaries */
- pci_dma_sync_single_for_cpu(VORTEX_PCI(vp), dma, PKT_BUF_SZ, PCI_DMA_FROMDEVICE);
+ dma_sync_single_for_cpu(vp->gendev, dma, PKT_BUF_SZ, DMA_FROM_DEVICE);
/* 'skb_put()' points to the start of sk_buff data area. */
skb_put_data(skb, vp->rx_skbuff[entry]->data,
pkt_len);
- pci_dma_sync_single_for_device(VORTEX_PCI(vp), dma, PKT_BUF_SZ, PCI_DMA_FROMDEVICE);
+ dma_sync_single_for_device(vp->gendev, dma, PKT_BUF_SZ, DMA_FROM_DEVICE);
vp->rx_copy++;
} else {
/* Pre-allocate the replacement skb. If it or its
@@ -2651,9 +2650,9 @@ boomerang_rx(struct net_device *dev)
dev->stats.rx_dropped++;
goto clear_complete;
}
- newdma = pci_map_single(VORTEX_PCI(vp), newskb->data,
- PKT_BUF_SZ, PCI_DMA_FROMDEVICE);
- if (dma_mapping_error(&VORTEX_PCI(vp)->dev, newdma)) {
+ newdma = dma_map_single(vp->gendev, newskb->data,
+ PKT_BUF_SZ, DMA_FROM_DEVICE);
+ if (dma_mapping_error(vp->gendev, newdma)) {
dev->stats.rx_dropped++;
consume_skb(newskb);
goto clear_complete;
@@ -2664,7 +2663,7 @@ boomerang_rx(struct net_device *dev)
vp->rx_skbuff[entry] = newskb;
vp->rx_ring[entry].addr = cpu_to_le32(newdma);
skb_put(skb, pkt_len);
- pci_unmap_single(VORTEX_PCI(vp), dma, PKT_BUF_SZ, PCI_DMA_FROMDEVICE);
+ dma_unmap_single(vp->gendev, dma, PKT_BUF_SZ, DMA_FROM_DEVICE);
vp->rx_nocopy++;
}
skb->protocol = eth_type_trans(skb, dev);
@@ -2761,8 +2760,8 @@ vortex_close(struct net_device *dev)
if (vp->full_bus_master_rx) { /* Free Boomerang bus master Rx buffers. */
for (i = 0; i < RX_RING_SIZE; i++)
if (vp->rx_skbuff[i]) {
- pci_unmap_single( VORTEX_PCI(vp), le32_to_cpu(vp->rx_ring[i].addr),
- PKT_BUF_SZ, PCI_DMA_FROMDEVICE);
+ dma_unmap_single(vp->gendev, le32_to_cpu(vp->rx_ring[i].addr),
+ PKT_BUF_SZ, DMA_FROM_DEVICE);
dev_kfree_skb(vp->rx_skbuff[i]);
vp->rx_skbuff[i] = NULL;
}
@@ -2775,12 +2774,12 @@ vortex_close(struct net_device *dev)
int k;
for (k=0; k<=skb_shinfo(skb)->nr_frags; k++)
- pci_unmap_single(VORTEX_PCI(vp),
+ dma_unmap_single(vp->gendev,
le32_to_cpu(vp->tx_ring[i].frag[k].addr),
le32_to_cpu(vp->tx_ring[i].frag[k].length)&0xFFF,
- PCI_DMA_TODEVICE);
+ DMA_TO_DEVICE);
#else
- pci_unmap_single(VORTEX_PCI(vp), le32_to_cpu(vp->tx_ring[i].addr), skb->len, PCI_DMA_TODEVICE);
+ dma_unmap_single(vp->gendev, le32_to_cpu(vp->tx_ring[i].addr), skb->len, DMA_TO_DEVICE);
#endif
dev_kfree_skb(skb);
vp->tx_skbuff[i] = NULL;
@@ -3288,11 +3287,10 @@ static void vortex_remove_one(struct pci_dev *pdev)
pci_iounmap(pdev, vp->ioaddr);
- pci_free_consistent(pdev,
- sizeof(struct boom_rx_desc) * RX_RING_SIZE
- + sizeof(struct boom_tx_desc) * TX_RING_SIZE,
- vp->rx_ring,
- vp->rx_ring_dma);
+ dma_free_coherent(&pdev->dev,
+ sizeof(struct boom_rx_desc) * RX_RING_SIZE +
+ sizeof(struct boom_tx_desc) * TX_RING_SIZE,
+ vp->rx_ring, vp->rx_ring_dma);
pci_release_regions(pdev);
diff --git a/drivers/net/ethernet/8390/ne.c b/drivers/net/ethernet/8390/ne.c
index ac99d08..1c97e39 100644
--- a/drivers/net/ethernet/8390/ne.c
+++ b/drivers/net/ethernet/8390/ne.c
@@ -164,7 +164,9 @@ bad_clone_list[] __initdata = {
#define NESM_START_PG 0x40 /* First page of TX buffer */
#define NESM_STOP_PG 0x80 /* Last page +1 of RX ring */
-#if defined(CONFIG_ATARI) /* 8-bit mode on Atari, normal on Q40 */
+#if defined(CONFIG_MACH_TX49XX)
+# define DCR_VAL 0x48 /* 8-bit mode */
+#elif defined(CONFIG_ATARI) /* 8-bit mode on Atari, normal on Q40 */
# define DCR_VAL (MACH_IS_ATARI ? 0x48 : 0x49)
#else
# define DCR_VAL 0x49
diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index a561705..be198cc 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -1552,22 +1552,26 @@ pcnet32_probe_pci(struct pci_dev *pdev, const struct pci_device_id *ent)
if (!ioaddr) {
if (pcnet32_debug & NETIF_MSG_PROBE)
pr_err("card has no PCI IO resources, aborting\n");
- return -ENODEV;
+ err = -ENODEV;
+ goto err_disable_dev;
}
err = pci_set_dma_mask(pdev, PCNET32_DMA_MASK);
if (err) {
if (pcnet32_debug & NETIF_MSG_PROBE)
pr_err("architecture does not support 32bit PCI busmaster DMA\n");
- return err;
+ goto err_disable_dev;
}
if (!request_region(ioaddr, PCNET32_TOTAL_SIZE, "pcnet32_probe_pci")) {
if (pcnet32_debug & NETIF_MSG_PROBE)
pr_err("io address range already allocated\n");
- return -EBUSY;
+ err = -EBUSY;
+ goto err_disable_dev;
}
err = pcnet32_probe1(ioaddr, 1, pdev);
+
+err_disable_dev:
if (err < 0)
pci_disable_device(pdev);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 7ea72ef..d272dc6 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -1321,6 +1321,10 @@
#define MDIO_VEND2_AN_STAT 0x8002
#endif
+#ifndef MDIO_VEND2_PMA_CDR_CONTROL
+#define MDIO_VEND2_PMA_CDR_CONTROL 0x8056
+#endif
+
#ifndef MDIO_CTRL1_SPEED1G
#define MDIO_CTRL1_SPEED1G (MDIO_CTRL1_SPEED10G & ~BMCR_SPEED100)
#endif
@@ -1369,6 +1373,10 @@
#define XGBE_AN_CL37_TX_CONFIG_MASK 0x08
#define XGBE_AN_CL37_MII_CTRL_8BIT 0x0100
+#define XGBE_PMA_CDR_TRACK_EN_MASK 0x01
+#define XGBE_PMA_CDR_TRACK_EN_OFF 0x00
+#define XGBE_PMA_CDR_TRACK_EN_ON 0x01
+
/* Bit setting and getting macros
* The get macro will extract the current bit field value from within
* the variable
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
index 7d128be..b911439 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
@@ -519,6 +519,22 @@ void xgbe_debugfs_init(struct xgbe_prv_data *pdata)
"debugfs_create_file failed\n");
}
+ if (pdata->vdata->an_cdr_workaround) {
+ pfile = debugfs_create_bool("an_cdr_workaround", 0600,
+ pdata->xgbe_debugfs,
+ &pdata->debugfs_an_cdr_workaround);
+ if (!pfile)
+ netdev_err(pdata->netdev,
+ "debugfs_create_bool failed\n");
+
+ pfile = debugfs_create_bool("an_cdr_track_early", 0600,
+ pdata->xgbe_debugfs,
+ &pdata->debugfs_an_cdr_track_early);
+ if (!pfile)
+ netdev_err(pdata->netdev,
+ "debugfs_create_bool failed\n");
+ }
+
kfree(buf);
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
index 795e556..441d0973 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
@@ -349,6 +349,7 @@ int xgbe_config_netdev(struct xgbe_prv_data *pdata)
XGMAC_SET_BITS(pdata->rss_options, MAC_RSSCR, UDP4TE, 1);
/* Call MDIO/PHY initialization routine */
+ pdata->debugfs_an_cdr_workaround = pdata->vdata->an_cdr_workaround;
ret = pdata->phy_if.phy_init(pdata);
if (ret)
return ret;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 072b9f6..1b45cd7 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -432,11 +432,16 @@ static void xgbe_an73_disable(struct xgbe_prv_data *pdata)
xgbe_an73_set(pdata, false, false);
xgbe_an73_disable_interrupts(pdata);
+ pdata->an_start = 0;
+
netif_dbg(pdata, link, pdata->netdev, "CL73 AN disabled\n");
}
static void xgbe_an_restart(struct xgbe_prv_data *pdata)
{
+ if (pdata->phy_if.phy_impl.an_pre)
+ pdata->phy_if.phy_impl.an_pre(pdata);
+
switch (pdata->an_mode) {
case XGBE_AN_MODE_CL73:
case XGBE_AN_MODE_CL73_REDRV:
@@ -453,6 +458,9 @@ static void xgbe_an_restart(struct xgbe_prv_data *pdata)
static void xgbe_an_disable(struct xgbe_prv_data *pdata)
{
+ if (pdata->phy_if.phy_impl.an_post)
+ pdata->phy_if.phy_impl.an_post(pdata);
+
switch (pdata->an_mode) {
case XGBE_AN_MODE_CL73:
case XGBE_AN_MODE_CL73_REDRV:
@@ -505,11 +513,11 @@ static enum xgbe_an xgbe_an73_tx_training(struct xgbe_prv_data *pdata,
XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL,
reg);
- if (pdata->phy_if.phy_impl.kr_training_post)
- pdata->phy_if.phy_impl.kr_training_post(pdata);
-
netif_dbg(pdata, link, pdata->netdev,
"KR training initiated\n");
+
+ if (pdata->phy_if.phy_impl.kr_training_post)
+ pdata->phy_if.phy_impl.kr_training_post(pdata);
}
return XGBE_AN_PAGE_RECEIVED;
@@ -637,11 +645,11 @@ static enum xgbe_an xgbe_an73_incompat_link(struct xgbe_prv_data *pdata)
return XGBE_AN_NO_LINK;
}
- xgbe_an73_disable(pdata);
+ xgbe_an_disable(pdata);
xgbe_switch_mode(pdata);
- xgbe_an73_restart(pdata);
+ xgbe_an_restart(pdata);
return XGBE_AN_INCOMPAT_LINK;
}
@@ -820,6 +828,9 @@ static void xgbe_an37_state_machine(struct xgbe_prv_data *pdata)
pdata->an_result = pdata->an_state;
pdata->an_state = XGBE_AN_READY;
+ if (pdata->phy_if.phy_impl.an_post)
+ pdata->phy_if.phy_impl.an_post(pdata);
+
netif_dbg(pdata, link, pdata->netdev, "CL37 AN result: %s\n",
xgbe_state_as_string(pdata->an_result));
}
@@ -903,6 +914,9 @@ static void xgbe_an73_state_machine(struct xgbe_prv_data *pdata)
pdata->kx_state = XGBE_RX_BPA;
pdata->an_start = 0;
+ if (pdata->phy_if.phy_impl.an_post)
+ pdata->phy_if.phy_impl.an_post(pdata);
+
netif_dbg(pdata, link, pdata->netdev, "CL73 AN result: %s\n",
xgbe_state_as_string(pdata->an_result));
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
index eb23f9b..82d1f41 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
@@ -456,6 +456,7 @@ static const struct xgbe_version_data xgbe_v2a = {
.irq_reissue_support = 1,
.tx_desc_prefetch = 5,
.rx_desc_prefetch = 5,
+ .an_cdr_workaround = 1,
};
static const struct xgbe_version_data xgbe_v2b = {
@@ -470,6 +471,7 @@ static const struct xgbe_version_data xgbe_v2b = {
.irq_reissue_support = 1,
.tx_desc_prefetch = 5,
.rx_desc_prefetch = 5,
+ .an_cdr_workaround = 1,
};
static const struct pci_device_id xgbe_pci_table[] = {
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 3304a29..aac8843 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -147,6 +147,14 @@
/* Rate-change complete wait/retry count */
#define XGBE_RATECHANGE_COUNT 500
+/* CDR delay values for KR support (in usec) */
+#define XGBE_CDR_DELAY_INIT 10000
+#define XGBE_CDR_DELAY_INC 10000
+#define XGBE_CDR_DELAY_MAX 100000
+
+/* RRC frequency during link status check */
+#define XGBE_RRC_FREQUENCY 10
+
enum xgbe_port_mode {
XGBE_PORT_MODE_RSVD = 0,
XGBE_PORT_MODE_BACKPLANE,
@@ -245,6 +253,10 @@ enum xgbe_sfp_speed {
#define XGBE_SFP_BASE_VENDOR_SN 4
#define XGBE_SFP_BASE_VENDOR_SN_LEN 16
+#define XGBE_SFP_EXTD_OPT1 1
+#define XGBE_SFP_EXTD_OPT1_RX_LOS BIT(1)
+#define XGBE_SFP_EXTD_OPT1_TX_FAULT BIT(3)
+
#define XGBE_SFP_EXTD_DIAG 28
#define XGBE_SFP_EXTD_DIAG_ADDR_CHANGE BIT(2)
@@ -324,6 +336,7 @@ struct xgbe_phy_data {
unsigned int sfp_gpio_address;
unsigned int sfp_gpio_mask;
+ unsigned int sfp_gpio_inputs;
unsigned int sfp_gpio_rx_los;
unsigned int sfp_gpio_tx_fault;
unsigned int sfp_gpio_mod_absent;
@@ -355,6 +368,10 @@ struct xgbe_phy_data {
unsigned int redrv_addr;
unsigned int redrv_lane;
unsigned int redrv_model;
+
+ /* KR AN support */
+ unsigned int phy_cdr_notrack;
+ unsigned int phy_cdr_delay;
};
/* I2C, MDIO and GPIO lines are muxed, so only one device at a time */
@@ -974,6 +991,49 @@ static void xgbe_phy_sfp_external_phy(struct xgbe_prv_data *pdata)
phy_data->sfp_phy_avail = 1;
}
+static bool xgbe_phy_check_sfp_rx_los(struct xgbe_phy_data *phy_data)
+{
+ u8 *sfp_extd = phy_data->sfp_eeprom.extd;
+
+ if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_RX_LOS))
+ return false;
+
+ if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS)
+ return false;
+
+ if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_rx_los))
+ return true;
+
+ return false;
+}
+
+static bool xgbe_phy_check_sfp_tx_fault(struct xgbe_phy_data *phy_data)
+{
+ u8 *sfp_extd = phy_data->sfp_eeprom.extd;
+
+ if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_TX_FAULT))
+ return false;
+
+ if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT)
+ return false;
+
+ if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_tx_fault))
+ return true;
+
+ return false;
+}
+
+static bool xgbe_phy_check_sfp_mod_absent(struct xgbe_phy_data *phy_data)
+{
+ if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT)
+ return false;
+
+ if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_mod_absent))
+ return true;
+
+ return false;
+}
+
static bool xgbe_phy_belfuse_parse_quirks(struct xgbe_prv_data *pdata)
{
struct xgbe_phy_data *phy_data = pdata->phy_data;
@@ -1019,6 +1079,10 @@ static void xgbe_phy_sfp_parse_eeprom(struct xgbe_prv_data *pdata)
if (sfp_base[XGBE_SFP_BASE_EXT_ID] != XGBE_SFP_EXT_ID_SFP)
return;
+ /* Update transceiver signals (eeprom extd/options) */
+ phy_data->sfp_tx_fault = xgbe_phy_check_sfp_tx_fault(phy_data);
+ phy_data->sfp_rx_los = xgbe_phy_check_sfp_rx_los(phy_data);
+
if (xgbe_phy_sfp_parse_quirks(pdata))
return;
@@ -1184,7 +1248,6 @@ static int xgbe_phy_sfp_read_eeprom(struct xgbe_prv_data *pdata)
static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata)
{
struct xgbe_phy_data *phy_data = pdata->phy_data;
- unsigned int gpio_input;
u8 gpio_reg, gpio_ports[2];
int ret;
@@ -1199,23 +1262,9 @@ static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata)
return;
}
- gpio_input = (gpio_ports[1] << 8) | gpio_ports[0];
+ phy_data->sfp_gpio_inputs = (gpio_ports[1] << 8) | gpio_ports[0];
- if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT) {
- /* No GPIO, just assume the module is present for now */
- phy_data->sfp_mod_absent = 0;
- } else {
- if (!(gpio_input & (1 << phy_data->sfp_gpio_mod_absent)))
- phy_data->sfp_mod_absent = 0;
- }
-
- if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS) &&
- (gpio_input & (1 << phy_data->sfp_gpio_rx_los)))
- phy_data->sfp_rx_los = 1;
-
- if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT) &&
- (gpio_input & (1 << phy_data->sfp_gpio_tx_fault)))
- phy_data->sfp_tx_fault = 1;
+ phy_data->sfp_mod_absent = xgbe_phy_check_sfp_mod_absent(phy_data);
}
static void xgbe_phy_sfp_mod_absent(struct xgbe_prv_data *pdata)
@@ -2361,7 +2410,7 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
return 1;
/* No link, attempt a receiver reset cycle */
- if (phy_data->rrc_count++) {
+ if (phy_data->rrc_count++ > XGBE_RRC_FREQUENCY) {
phy_data->rrc_count = 0;
xgbe_phy_rrc(pdata);
}
@@ -2669,6 +2718,103 @@ static bool xgbe_phy_port_enabled(struct xgbe_prv_data *pdata)
return true;
}
+static void xgbe_phy_cdr_track(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ if (!pdata->debugfs_an_cdr_workaround)
+ return;
+
+ if (!phy_data->phy_cdr_notrack)
+ return;
+
+ usleep_range(phy_data->phy_cdr_delay,
+ phy_data->phy_cdr_delay + 500);
+
+ XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL,
+ XGBE_PMA_CDR_TRACK_EN_MASK,
+ XGBE_PMA_CDR_TRACK_EN_ON);
+
+ phy_data->phy_cdr_notrack = 0;
+}
+
+static void xgbe_phy_cdr_notrack(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ if (!pdata->debugfs_an_cdr_workaround)
+ return;
+
+ if (phy_data->phy_cdr_notrack)
+ return;
+
+ XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL,
+ XGBE_PMA_CDR_TRACK_EN_MASK,
+ XGBE_PMA_CDR_TRACK_EN_OFF);
+
+ xgbe_phy_rrc(pdata);
+
+ phy_data->phy_cdr_notrack = 1;
+}
+
+static void xgbe_phy_kr_training_post(struct xgbe_prv_data *pdata)
+{
+ if (!pdata->debugfs_an_cdr_track_early)
+ xgbe_phy_cdr_track(pdata);
+}
+
+static void xgbe_phy_kr_training_pre(struct xgbe_prv_data *pdata)
+{
+ if (pdata->debugfs_an_cdr_track_early)
+ xgbe_phy_cdr_track(pdata);
+}
+
+static void xgbe_phy_an_post(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (pdata->an_mode) {
+ case XGBE_AN_MODE_CL73:
+ case XGBE_AN_MODE_CL73_REDRV:
+ if (phy_data->cur_mode != XGBE_MODE_KR)
+ break;
+
+ xgbe_phy_cdr_track(pdata);
+
+ switch (pdata->an_result) {
+ case XGBE_AN_READY:
+ case XGBE_AN_COMPLETE:
+ break;
+ default:
+ if (phy_data->phy_cdr_delay < XGBE_CDR_DELAY_MAX)
+ phy_data->phy_cdr_delay += XGBE_CDR_DELAY_INC;
+ else
+ phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT;
+ break;
+ }
+ break;
+ default:
+ break;
+ }
+}
+
+static void xgbe_phy_an_pre(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (pdata->an_mode) {
+ case XGBE_AN_MODE_CL73:
+ case XGBE_AN_MODE_CL73_REDRV:
+ if (phy_data->cur_mode != XGBE_MODE_KR)
+ break;
+
+ xgbe_phy_cdr_notrack(pdata);
+ break;
+ default:
+ break;
+ }
+}
+
static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
{
struct xgbe_phy_data *phy_data = pdata->phy_data;
@@ -2680,6 +2826,9 @@ static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
xgbe_phy_sfp_reset(phy_data);
xgbe_phy_sfp_mod_absent(pdata);
+ /* Reset CDR support */
+ xgbe_phy_cdr_track(pdata);
+
/* Power off the PHY */
xgbe_phy_power_off(pdata);
@@ -2712,6 +2861,9 @@ static int xgbe_phy_start(struct xgbe_prv_data *pdata)
/* Start in highest supported mode */
xgbe_phy_set_mode(pdata, phy_data->start_mode);
+ /* Reset CDR support */
+ xgbe_phy_cdr_track(pdata);
+
/* After starting the I2C controller, we can check for an SFP */
switch (phy_data->port_mode) {
case XGBE_PORT_MODE_SFP:
@@ -3019,6 +3171,8 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata)
}
}
+ phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT;
+
/* Register for driving external PHYs */
mii = devm_mdiobus_alloc(pdata->dev);
if (!mii) {
@@ -3071,4 +3225,10 @@ void xgbe_init_function_ptrs_phy_v2(struct xgbe_phy_if *phy_if)
phy_impl->an_advertising = xgbe_phy_an_advertising;
phy_impl->an_outcome = xgbe_phy_an_outcome;
+
+ phy_impl->an_pre = xgbe_phy_an_pre;
+ phy_impl->an_post = xgbe_phy_an_post;
+
+ phy_impl->kr_training_pre = xgbe_phy_kr_training_pre;
+ phy_impl->kr_training_post = xgbe_phy_kr_training_post;
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index ad102c8..95d4b56 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -833,6 +833,7 @@ struct xgbe_hw_if {
/* This structure represents implementation specific routines for an
* implementation of a PHY. All routines are required unless noted below.
* Optional routines:
+ * an_pre, an_post
* kr_training_pre, kr_training_post
*/
struct xgbe_phy_impl_if {
@@ -875,6 +876,10 @@ struct xgbe_phy_impl_if {
/* Process results of auto-negotiation */
enum xgbe_mode (*an_outcome)(struct xgbe_prv_data *);
+ /* Pre/Post auto-negotiation support */
+ void (*an_pre)(struct xgbe_prv_data *);
+ void (*an_post)(struct xgbe_prv_data *);
+
/* Pre/Post KR training enablement support */
void (*kr_training_pre)(struct xgbe_prv_data *);
void (*kr_training_post)(struct xgbe_prv_data *);
@@ -989,6 +994,7 @@ struct xgbe_version_data {
unsigned int irq_reissue_support;
unsigned int tx_desc_prefetch;
unsigned int rx_desc_prefetch;
+ unsigned int an_cdr_workaround;
};
struct xgbe_vxlan_data {
@@ -1257,6 +1263,9 @@ struct xgbe_prv_data {
unsigned int debugfs_xprop_reg;
unsigned int debugfs_xi2c_reg;
+
+ bool debugfs_an_cdr_workaround;
+ bool debugfs_an_cdr_track_early;
};
/* Function prototypes*/
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 32f6d2e..1a1a638 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -95,6 +95,7 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
/*rss rings */
cfg->vecs = min(cfg->aq_hw_caps->vecs, AQ_CFG_VECS_DEF);
cfg->vecs = min(cfg->vecs, num_online_cpus());
+ cfg->vecs = min(cfg->vecs, self->irqvecs);
/* cfg->vecs should be power of 2 for RSS */
if (cfg->vecs >= 8U)
cfg->vecs = 8U;
@@ -246,6 +247,8 @@ void aq_nic_ndev_init(struct aq_nic_s *self)
self->ndev->hw_features |= aq_hw_caps->hw_features;
self->ndev->features = aq_hw_caps->hw_features;
+ self->ndev->vlan_features |= NETIF_F_HW_CSUM | NETIF_F_RXCSUM |
+ NETIF_F_RXHASH | NETIF_F_SG | NETIF_F_LRO;
self->ndev->priv_flags = aq_hw_caps->hw_priv_flags;
self->ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index 219b550..faa533a0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -80,6 +80,7 @@ struct aq_nic_s {
struct pci_dev *pdev;
unsigned int msix_entry_mask;
+ u32 irqvecs;
};
static inline struct device *aq_nic_get_dev(struct aq_nic_s *self)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index ecc6306..a50e08b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -267,16 +267,16 @@ static int aq_pci_probe(struct pci_dev *pdev,
numvecs = min(numvecs, num_online_cpus());
/*enable interrupts */
#if !AQ_CFG_FORCE_LEGACY_INT
- err = pci_alloc_irq_vectors(self->pdev, numvecs, numvecs,
- PCI_IRQ_MSIX);
+ numvecs = pci_alloc_irq_vectors(self->pdev, 1, numvecs,
+ PCI_IRQ_MSIX | PCI_IRQ_MSI |
+ PCI_IRQ_LEGACY);
- if (err < 0) {
- err = pci_alloc_irq_vectors(self->pdev, 1, 1,
- PCI_IRQ_MSI | PCI_IRQ_LEGACY);
- if (err < 0)
- goto err_hwinit;
+ if (numvecs < 0) {
+ err = numvecs;
+ goto err_hwinit;
}
#endif
+ self->irqvecs = numvecs;
/* net device init */
aq_nic_cfg_start(self);
@@ -298,9 +298,9 @@ static int aq_pci_probe(struct pci_dev *pdev,
kfree(self->aq_hw);
err_ioremap:
free_netdev(ndev);
-err_pci_func:
- pci_release_regions(pdev);
err_ndev:
+ pci_release_regions(pdev);
+err_pci_func:
pci_disable_device(pdev);
return err;
}
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index f9a3c1a..f33b25f 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2144,14 +2144,21 @@ static const struct net_device_ops bcm_sysport_netdev_ops = {
.ndo_select_queue = bcm_sysport_select_queue,
};
-static int bcm_sysport_map_queues(struct net_device *dev,
+static int bcm_sysport_map_queues(struct notifier_block *nb,
struct dsa_notifier_register_info *info)
{
- struct bcm_sysport_priv *priv = netdev_priv(dev);
struct bcm_sysport_tx_ring *ring;
+ struct bcm_sysport_priv *priv;
struct net_device *slave_dev;
unsigned int num_tx_queues;
unsigned int q, start, port;
+ struct net_device *dev;
+
+ priv = container_of(nb, struct bcm_sysport_priv, dsa_notifier);
+ if (priv->netdev != info->master)
+ return 0;
+
+ dev = info->master;
/* We can't be setting up queue inspection for non directly attached
* switches
@@ -2174,11 +2181,12 @@ static int bcm_sysport_map_queues(struct net_device *dev,
if (priv->is_lite)
netif_set_real_num_tx_queues(slave_dev,
slave_dev->num_tx_queues / 2);
+
num_tx_queues = slave_dev->real_num_tx_queues;
if (priv->per_port_num_tx_queues &&
priv->per_port_num_tx_queues != num_tx_queues)
- netdev_warn(slave_dev, "asymetric number of per-port queues\n");
+ netdev_warn(slave_dev, "asymmetric number of per-port queues\n");
priv->per_port_num_tx_queues = num_tx_queues;
@@ -2201,7 +2209,7 @@ static int bcm_sysport_map_queues(struct net_device *dev,
return 0;
}
-static int bcm_sysport_dsa_notifier(struct notifier_block *unused,
+static int bcm_sysport_dsa_notifier(struct notifier_block *nb,
unsigned long event, void *ptr)
{
struct dsa_notifier_register_info *info;
@@ -2211,7 +2219,7 @@ static int bcm_sysport_dsa_notifier(struct notifier_block *unused,
info = ptr;
- return notifier_from_errno(bcm_sysport_map_queues(info->master, info));
+ return notifier_from_errno(bcm_sysport_map_queues(nb, info));
}
#define REV_FMT "v%2x.%02x"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 1f622ca..8ba14ae 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1927,22 +1927,39 @@ static char *bnxt_parse_pkglog(int desired_field, u8 *data, size_t datalen)
return retval;
}
-static char *bnxt_get_pkgver(struct net_device *dev, char *buf, size_t buflen)
+static void bnxt_get_pkgver(struct net_device *dev)
{
+ struct bnxt *bp = netdev_priv(dev);
u16 index = 0;
- u32 datalen;
+ char *pkgver;
+ u32 pkglen;
+ u8 *pkgbuf;
+ int len;
if (bnxt_find_nvram_item(dev, BNX_DIR_TYPE_PKG_LOG,
BNX_DIR_ORDINAL_FIRST, BNX_DIR_EXT_NONE,
- &index, NULL, &datalen) != 0)
- return NULL;
+ &index, NULL, &pkglen) != 0)
+ return;
- memset(buf, 0, buflen);
- if (bnxt_get_nvram_item(dev, index, 0, datalen, buf) != 0)
- return NULL;
+ pkgbuf = kzalloc(pkglen, GFP_KERNEL);
+ if (!pkgbuf) {
+ dev_err(&bp->pdev->dev, "Unable to allocate memory for pkg version, length = %u\n",
+ pkglen);
+ return;
+ }
- return bnxt_parse_pkglog(BNX_PKG_LOG_FIELD_IDX_PKG_VERSION, buf,
- datalen);
+ if (bnxt_get_nvram_item(dev, index, 0, pkglen, pkgbuf))
+ goto err;
+
+ pkgver = bnxt_parse_pkglog(BNX_PKG_LOG_FIELD_IDX_PKG_VERSION, pkgbuf,
+ pkglen);
+ if (pkgver && *pkgver != 0 && isdigit(*pkgver)) {
+ len = strlen(bp->fw_ver_str);
+ snprintf(bp->fw_ver_str + len, FW_VER_STR_LEN - len - 1,
+ "/pkg %s", pkgver);
+ }
+err:
+ kfree(pkgbuf);
}
static int bnxt_get_eeprom(struct net_device *dev,
@@ -2615,22 +2632,10 @@ void bnxt_ethtool_init(struct bnxt *bp)
struct hwrm_selftest_qlist_input req = {0};
struct bnxt_test_info *test_info;
struct net_device *dev = bp->dev;
- char *pkglog;
int i, rc;
- pkglog = kzalloc(BNX_PKG_LOG_MAX_LENGTH, GFP_KERNEL);
- if (pkglog) {
- char *pkgver;
- int len;
+ bnxt_get_pkgver(dev);
- pkgver = bnxt_get_pkgver(dev, pkglog, BNX_PKG_LOG_MAX_LENGTH);
- if (pkgver && *pkgver != 0 && isdigit(*pkgver)) {
- len = strlen(bp->fw_ver_str);
- snprintf(bp->fw_ver_str + len, FW_VER_STR_LEN - len - 1,
- "/pkg %s", pkgver);
- }
- kfree(pkglog);
- }
if (bp->hwrm_spec_code < 0x10704 || !BNXT_SINGLE_PF(bp))
return;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h
index 73f2249..8344481 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h
@@ -59,8 +59,6 @@ enum bnxt_nvm_directory_type {
#define BNX_DIR_ATTR_NO_CHKSUM (1 << 0)
#define BNX_DIR_ATTR_PROP_STREAM (1 << 1)
-#define BNX_PKG_LOG_MAX_LENGTH 4096
-
enum bnxnvm_pkglog_field_index {
BNX_PKG_LOG_FIELD_IDX_INSTALLED_TIMESTAMP = 0,
BNX_PKG_LOG_FIELD_IDX_PKG_DESCRIPTION = 1,
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 08bbb63..9f59b12 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -8733,14 +8733,15 @@ static void tg3_free_consistent(struct tg3 *tp)
tg3_mem_rx_release(tp);
tg3_mem_tx_release(tp);
- /* Protect tg3_get_stats64() from reading freed tp->hw_stats. */
- tg3_full_lock(tp, 0);
+ /* tp->hw_stats can be referenced safely:
+ * 1. under rtnl_lock
+ * 2. or under tp->lock if TG3_FLAG_INIT_COMPLETE is set.
+ */
if (tp->hw_stats) {
dma_free_coherent(&tp->pdev->dev, sizeof(struct tg3_hw_stats),
tp->hw_stats, tp->stats_mapping);
tp->hw_stats = NULL;
}
- tg3_full_unlock(tp);
}
/*
@@ -14178,7 +14179,7 @@ static void tg3_get_stats64(struct net_device *dev,
struct tg3 *tp = netdev_priv(dev);
spin_lock_bh(&tp->lock);
- if (!tp->hw_stats) {
+ if (!tp->hw_stats || !tg3_flag(tp, INIT_COMPLETE)) {
*stats = tp->net_stats_prev;
spin_unlock_bh(&tp->lock);
return;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
index b57acb8..dc25066 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
@@ -419,15 +419,15 @@ static const u32 t6_up_cim_reg_array[][IREG_NUM_ELEM + 1] = {
{0x7b50, 0x7b54, 0x280, 0x20, 0}, /* up_cim_280_to_2fc */
{0x7b50, 0x7b54, 0x300, 0x20, 0}, /* up_cim_300_to_37c */
{0x7b50, 0x7b54, 0x380, 0x14, 0}, /* up_cim_380_to_3cc */
- {0x7b50, 0x7b54, 0x2900, 0x4, 0x4}, /* up_cim_2900_to_3d40 */
- {0x7b50, 0x7b54, 0x2904, 0x4, 0x4}, /* up_cim_2904_to_3d44 */
- {0x7b50, 0x7b54, 0x2908, 0x4, 0x4}, /* up_cim_2908_to_3d48 */
- {0x7b50, 0x7b54, 0x2910, 0x4, 0x4}, /* up_cim_2910_to_3d4c */
- {0x7b50, 0x7b54, 0x2914, 0x4, 0x4}, /* up_cim_2914_to_3d50 */
- {0x7b50, 0x7b54, 0x2920, 0x10, 0x10}, /* up_cim_2920_to_2a10 */
- {0x7b50, 0x7b54, 0x2924, 0x10, 0x10}, /* up_cim_2924_to_2a14 */
- {0x7b50, 0x7b54, 0x2928, 0x10, 0x10}, /* up_cim_2928_to_2a18 */
- {0x7b50, 0x7b54, 0x292c, 0x10, 0x10}, /* up_cim_292c_to_2a1c */
+ {0x7b50, 0x7b54, 0x4900, 0x4, 0x4}, /* up_cim_4900_to_4c60 */
+ {0x7b50, 0x7b54, 0x4904, 0x4, 0x4}, /* up_cim_4904_to_4c64 */
+ {0x7b50, 0x7b54, 0x4908, 0x4, 0x4}, /* up_cim_4908_to_4c68 */
+ {0x7b50, 0x7b54, 0x4910, 0x4, 0x4}, /* up_cim_4910_to_4c70 */
+ {0x7b50, 0x7b54, 0x4914, 0x4, 0x4}, /* up_cim_4914_to_4c74 */
+ {0x7b50, 0x7b54, 0x4920, 0x10, 0x10}, /* up_cim_4920_to_4a10 */
+ {0x7b50, 0x7b54, 0x4924, 0x10, 0x10}, /* up_cim_4924_to_4a14 */
+ {0x7b50, 0x7b54, 0x4928, 0x10, 0x10}, /* up_cim_4928_to_4a18 */
+ {0x7b50, 0x7b54, 0x492c, 0x10, 0x10}, /* up_cim_492c_to_4a1c */
};
static const u32 t5_up_cim_reg_array[][IREG_NUM_ELEM + 1] = {
@@ -444,16 +444,6 @@ static const u32 t5_up_cim_reg_array[][IREG_NUM_ELEM + 1] = {
{0x7b50, 0x7b54, 0x280, 0x20, 0}, /* up_cim_280_to_2fc */
{0x7b50, 0x7b54, 0x300, 0x20, 0}, /* up_cim_300_to_37c */
{0x7b50, 0x7b54, 0x380, 0x14, 0}, /* up_cim_380_to_3cc */
- {0x7b50, 0x7b54, 0x2900, 0x4, 0x4}, /* up_cim_2900_to_3d40 */
- {0x7b50, 0x7b54, 0x2904, 0x4, 0x4}, /* up_cim_2904_to_3d44 */
- {0x7b50, 0x7b54, 0x2908, 0x4, 0x4}, /* up_cim_2908_to_3d48 */
- {0x7b50, 0x7b54, 0x2910, 0x4, 0x4}, /* up_cim_2910_to_3d4c */
- {0x7b50, 0x7b54, 0x2914, 0x4, 0x4}, /* up_cim_2914_to_3d50 */
- {0x7b50, 0x7b54, 0x2918, 0x4, 0x4}, /* up_cim_2918_to_3d54 */
- {0x7b50, 0x7b54, 0x291c, 0x4, 0x4}, /* up_cim_291c_to_3d58 */
- {0x7b50, 0x7b54, 0x2924, 0x10, 0x10}, /* up_cim_2924_to_2914 */
- {0x7b50, 0x7b54, 0x2928, 0x10, 0x10}, /* up_cim_2928_to_2a18 */
- {0x7b50, 0x7b54, 0x292c, 0x10, 0x10}, /* up_cim_292c_to_2a1c */
};
static const u32 t6_hma_ireg_array[][IREG_NUM_ELEM] = {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index db92f18..b76447b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -836,7 +836,7 @@ bool is_filter_exact_match(struct adapter *adap,
{
struct tp_params *tp = &adap->params.tp;
u64 hash_filter_mask = tp->hash_filter_mask;
- u32 mask;
+ u64 ntuple_mask = 0;
if (!is_hashfilter(adap))
return false;
@@ -865,73 +865,45 @@ bool is_filter_exact_match(struct adapter *adap,
if (!fs->val.fport || fs->mask.fport != 0xffff)
return false;
- if (tp->fcoe_shift >= 0) {
- mask = (hash_filter_mask >> tp->fcoe_shift) & FT_FCOE_W;
- if (mask && !fs->mask.fcoe)
- return false;
- }
+ /* calculate tuple mask and compare with mask configured in hw */
+ if (tp->fcoe_shift >= 0)
+ ntuple_mask |= (u64)fs->mask.fcoe << tp->fcoe_shift;
- if (tp->port_shift >= 0) {
- mask = (hash_filter_mask >> tp->port_shift) & FT_PORT_W;
- if (mask && !fs->mask.iport)
- return false;
- }
+ if (tp->port_shift >= 0)
+ ntuple_mask |= (u64)fs->mask.iport << tp->port_shift;
if (tp->vnic_shift >= 0) {
- mask = (hash_filter_mask >> tp->vnic_shift) & FT_VNIC_ID_W;
-
- if ((adap->params.tp.ingress_config & VNIC_F)) {
- if (mask && !fs->mask.pfvf_vld)
- return false;
- } else {
- if (mask && !fs->mask.ovlan_vld)
- return false;
- }
+ if ((adap->params.tp.ingress_config & VNIC_F))
+ ntuple_mask |= (u64)fs->mask.pfvf_vld << tp->vnic_shift;
+ else
+ ntuple_mask |= (u64)fs->mask.ovlan_vld <<
+ tp->vnic_shift;
}
- if (tp->vlan_shift >= 0) {
- mask = (hash_filter_mask >> tp->vlan_shift) & FT_VLAN_W;
- if (mask && !fs->mask.ivlan)
- return false;
- }
+ if (tp->vlan_shift >= 0)
+ ntuple_mask |= (u64)fs->mask.ivlan << tp->vlan_shift;
- if (tp->tos_shift >= 0) {
- mask = (hash_filter_mask >> tp->tos_shift) & FT_TOS_W;
- if (mask && !fs->mask.tos)
- return false;
- }
+ if (tp->tos_shift >= 0)
+ ntuple_mask |= (u64)fs->mask.tos << tp->tos_shift;
- if (tp->protocol_shift >= 0) {
- mask = (hash_filter_mask >> tp->protocol_shift) & FT_PROTOCOL_W;
- if (mask && !fs->mask.proto)
- return false;
- }
+ if (tp->protocol_shift >= 0)
+ ntuple_mask |= (u64)fs->mask.proto << tp->protocol_shift;
- if (tp->ethertype_shift >= 0) {
- mask = (hash_filter_mask >> tp->ethertype_shift) &
- FT_ETHERTYPE_W;
- if (mask && !fs->mask.ethtype)
- return false;
- }
+ if (tp->ethertype_shift >= 0)
+ ntuple_mask |= (u64)fs->mask.ethtype << tp->ethertype_shift;
- if (tp->macmatch_shift >= 0) {
- mask = (hash_filter_mask >> tp->macmatch_shift) & FT_MACMATCH_W;
- if (mask && !fs->mask.macidx)
- return false;
- }
+ if (tp->macmatch_shift >= 0)
+ ntuple_mask |= (u64)fs->mask.macidx << tp->macmatch_shift;
- if (tp->matchtype_shift >= 0) {
- mask = (hash_filter_mask >> tp->matchtype_shift) &
- FT_MPSHITTYPE_W;
- if (mask && !fs->mask.matchtype)
- return false;
- }
- if (tp->frag_shift >= 0) {
- mask = (hash_filter_mask >> tp->frag_shift) &
- FT_FRAGMENTATION_W;
- if (mask && !fs->mask.frag)
- return false;
- }
+ if (tp->matchtype_shift >= 0)
+ ntuple_mask |= (u64)fs->mask.matchtype << tp->matchtype_shift;
+
+ if (tp->frag_shift >= 0)
+ ntuple_mask |= (u64)fs->mask.frag << tp->frag_shift;
+
+ if (ntuple_mask != hash_filter_mask)
+ return false;
+
return true;
}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 24d2865..005283c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3433,8 +3433,8 @@ static int adap_config_hma(struct adapter *adapter)
sgl = adapter->hma.sgt->sgl;
node = dev_to_node(adapter->pdev_dev);
for_each_sg(sgl, iter, sgt->orig_nents, i) {
- newpage = alloc_pages_node(node, __GFP_NOWARN | GFP_KERNEL,
- page_order);
+ newpage = alloc_pages_node(node, __GFP_NOWARN | GFP_KERNEL |
+ __GFP_ZERO, page_order);
if (!newpage) {
dev_err(adapter->pdev_dev,
"Not enough memory for HMA page allocation\n");
@@ -5474,6 +5474,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
}
spin_lock_init(&adapter->mbox_lock);
INIT_LIST_HEAD(&adapter->mlist.list);
+ adapter->mbox_log->size = T4_OS_LOG_MBOX_CMDS;
pci_set_drvdata(pdev, adapter);
if (func != ent->driver_data) {
@@ -5508,8 +5509,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
goto out_free_adapter;
}
- adapter->mbox_log->size = T4_OS_LOG_MBOX_CMDS;
-
/* PCI device has been enabled */
adapter->flags |= DEV_ENABLED;
memset(adapter->chan_map, 0xff, sizeof(adapter->chan_map));
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 81684ac..8a8b12b 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2747,11 +2747,11 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
pci_set_master(pdev);
/* Query PCI controller on system for DMA addressing
- * limitation for the device. Try 64-bit first, and
+ * limitation for the device. Try 47-bit first, and
* fail to 32-bit.
*/
- err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+ err = pci_set_dma_mask(pdev, DMA_BIT_MASK(47));
if (err) {
err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
if (err) {
@@ -2765,10 +2765,10 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
goto err_out_release_regions;
}
} else {
- err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+ err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(47));
if (err) {
dev_err(dev, "Unable to obtain %u-bit DMA "
- "for consistent allocations, aborting\n", 64);
+ "for consistent allocations, aborting\n", 47);
goto err_out_release_regions;
}
using_dac = 1;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index c697e79..8f75500 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -3309,7 +3309,9 @@ void be_detect_error(struct be_adapter *adapter)
if ((val & POST_STAGE_FAT_LOG_START)
!= POST_STAGE_FAT_LOG_START &&
(val & POST_STAGE_ARMFW_UE)
- != POST_STAGE_ARMFW_UE)
+ != POST_STAGE_ARMFW_UE &&
+ (val & POST_STAGE_RECOVERABLE_ERR)
+ != POST_STAGE_RECOVERABLE_ERR)
return;
}
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index d4604bc..9d3eed4 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
/*
* Fast Ethernet Controller (FEC) driver for Motorola MPC8xx.
* Copyright (c) 1997 Dan Malek (dmalek@jlc.net)
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index f814397..43d9732 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -1,20 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Fast Ethernet Controller (ENET) PTP driver for MX6x.
*
* Copyright (C) 2012 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
index 4df282e..0beee2c 100644
--- a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
+++ b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
@@ -61,7 +61,7 @@ static const char hw_stat_gstrings[][ETH_GSTRING_LEN] = {
static const char tx_fw_stat_gstrings[][ETH_GSTRING_LEN] = {
"tx-single-collision",
"tx-multiple-collision",
- "tx-late-collsion",
+ "tx-late-collision",
"tx-aborted-frames",
"tx-lost-frames",
"tx-carrier-sense-errors",
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h
index 3e62692..fa5b30f 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.h
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.h
@@ -87,7 +87,7 @@ do { \
#define HNAE_AE_REGISTER 0x1
-#define RCB_RING_NAME_LEN 16
+#define RCB_RING_NAME_LEN (IFNAMSIZ + 4)
#define HNAE_LOWEST_LATENCY_COAL_PARAM 30
#define HNAE_LOW_LATENCY_COAL_PARAM 80
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index aad5658..5ec1185 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -192,6 +192,7 @@ static int alloc_long_term_buff(struct ibmvnic_adapter *adapter,
if (adapter->fw_done_rc) {
dev_err(dev, "Couldn't map long term buffer,rc = %d\n",
adapter->fw_done_rc);
+ dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr);
return -1;
}
return 0;
@@ -794,46 +795,66 @@ static int ibmvnic_login(struct net_device *netdev)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
unsigned long timeout = msecs_to_jiffies(30000);
- struct device *dev = &adapter->vdev->dev;
+ int retry_count = 0;
+ bool retry;
int rc;
do {
- if (adapter->renegotiate) {
- adapter->renegotiate = false;
+ retry = false;
+ if (retry_count > IBMVNIC_MAX_QUEUES) {
+ netdev_warn(netdev, "Login attempts exceeded\n");
+ return -1;
+ }
+
+ adapter->init_done_rc = 0;
+ reinit_completion(&adapter->init_done);
+ rc = send_login(adapter);
+ if (rc) {
+ netdev_warn(netdev, "Unable to login\n");
+ return rc;
+ }
+
+ if (!wait_for_completion_timeout(&adapter->init_done,
+ timeout)) {
+ netdev_warn(netdev, "Login timed out\n");
+ return -1;
+ }
+
+ if (adapter->init_done_rc == PARTIALSUCCESS) {
+ retry_count++;
release_sub_crqs(adapter, 1);
+ retry = true;
+ netdev_dbg(netdev,
+ "Received partial success, retrying...\n");
+ adapter->init_done_rc = 0;
reinit_completion(&adapter->init_done);
send_cap_queries(adapter);
if (!wait_for_completion_timeout(&adapter->init_done,
timeout)) {
- dev_err(dev, "Capabilities query timeout\n");
+ netdev_warn(netdev,
+ "Capabilities query timed out\n");
return -1;
}
+
rc = init_sub_crqs(adapter);
if (rc) {
- dev_err(dev,
- "Initialization of SCRQ's failed\n");
+ netdev_warn(netdev,
+ "SCRQ initialization failed\n");
return -1;
}
+
rc = init_sub_crq_irqs(adapter);
if (rc) {
- dev_err(dev,
- "Initialization of SCRQ's irqs failed\n");
+ netdev_warn(netdev,
+ "SCRQ irq initialization failed\n");
return -1;
}
- }
-
- reinit_completion(&adapter->init_done);
- rc = send_login(adapter);
- if (rc) {
- dev_err(dev, "Unable to attempt device login\n");
- return rc;
- } else if (!wait_for_completion_timeout(&adapter->init_done,
- timeout)) {
- dev_err(dev, "Login timeout\n");
+ } else if (adapter->init_done_rc) {
+ netdev_warn(netdev, "Adapter login failed\n");
return -1;
}
- } while (adapter->renegotiate);
+ } while (retry);
/* handle pending MAC address changes after successful login */
if (adapter->mac_change_pending) {
@@ -1034,16 +1055,14 @@ static int __ibmvnic_open(struct net_device *netdev)
netdev_dbg(netdev, "Enabling rx_scrq[%d] irq\n", i);
if (prev_state == VNIC_CLOSED)
enable_irq(adapter->rx_scrq[i]->irq);
- else
- enable_scrq_irq(adapter, adapter->rx_scrq[i]);
+ enable_scrq_irq(adapter, adapter->rx_scrq[i]);
}
for (i = 0; i < adapter->req_tx_queues; i++) {
netdev_dbg(netdev, "Enabling tx_scrq[%d] irq\n", i);
if (prev_state == VNIC_CLOSED)
enable_irq(adapter->tx_scrq[i]->irq);
- else
- enable_scrq_irq(adapter, adapter->tx_scrq[i]);
+ enable_scrq_irq(adapter, adapter->tx_scrq[i]);
}
rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_UP);
@@ -1115,7 +1134,7 @@ static void clean_rx_pools(struct ibmvnic_adapter *adapter)
if (!adapter->rx_pool)
return;
- rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
+ rx_scrqs = adapter->num_active_rx_pools;
rx_entries = adapter->req_rx_add_entries_per_subcrq;
/* Free any remaining skbs in the rx buffer pools */
@@ -1164,7 +1183,7 @@ static void clean_tx_pools(struct ibmvnic_adapter *adapter)
if (!adapter->tx_pool || !adapter->tso_pool)
return;
- tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
+ tx_scrqs = adapter->num_active_tx_pools;
/* Free any remaining skbs in the tx buffer pools */
for (i = 0; i < tx_scrqs; i++) {
@@ -1184,6 +1203,7 @@ static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter)
if (adapter->tx_scrq[i]->irq) {
netdev_dbg(netdev,
"Disabling tx_scrq[%d] irq\n", i);
+ disable_scrq_irq(adapter, adapter->tx_scrq[i]);
disable_irq(adapter->tx_scrq[i]->irq);
}
}
@@ -1193,6 +1213,7 @@ static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter)
if (adapter->rx_scrq[i]->irq) {
netdev_dbg(netdev,
"Disabling rx_scrq[%d] irq\n", i);
+ disable_scrq_irq(adapter, adapter->rx_scrq[i]);
disable_irq(adapter->rx_scrq[i]->irq);
}
}
@@ -1806,9 +1827,8 @@ static int do_reset(struct ibmvnic_adapter *adapter,
if (rc)
return rc;
}
+ ibmvnic_disable_irqs(adapter);
}
-
- ibmvnic_disable_irqs(adapter);
adapter->state = VNIC_CLOSED;
if (reset_state == VNIC_CLOSED)
@@ -1828,7 +1848,8 @@ static int do_reset(struct ibmvnic_adapter *adapter,
for (i = 0; i < adapter->req_rx_queues; i++)
napi_schedule(&adapter->napi[i]);
- if (adapter->reset_reason != VNIC_RESET_FAILOVER)
+ if (adapter->reset_reason != VNIC_RESET_FAILOVER &&
+ adapter->reset_reason != VNIC_RESET_CHANGE_PARAM)
netdev_notify_peers(netdev);
netif_carrier_on(netdev);
@@ -2607,6 +2628,16 @@ static int enable_scrq_irq(struct ibmvnic_adapter *adapter,
return 1;
}
+ if (adapter->resetting &&
+ adapter->reset_reason == VNIC_RESET_MOBILITY) {
+ u64 val = (0xff000000) | scrq->hw_irq;
+
+ rc = plpar_hcall_norets(H_EOI, val);
+ if (rc)
+ dev_err(dev, "H_EOI FAILED irq 0x%llx. rc=%ld\n",
+ val, rc);
+ }
+
rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address,
H_ENABLE_VIO_INTERRUPT, scrq->hw_irq, 0, 0);
if (rc)
@@ -3170,7 +3201,7 @@ static int send_version_xchg(struct ibmvnic_adapter *adapter)
struct vnic_login_client_data {
u8 type;
__be16 len;
- char name;
+ char name[];
} __packed;
static int vnic_client_data_len(struct ibmvnic_adapter *adapter)
@@ -3199,21 +3230,21 @@ static void vnic_add_client_data(struct ibmvnic_adapter *adapter,
vlcd->type = 1;
len = strlen(os_name) + 1;
vlcd->len = cpu_to_be16(len);
- strncpy(&vlcd->name, os_name, len);
- vlcd = (struct vnic_login_client_data *)((char *)&vlcd->name + len);
+ strncpy(vlcd->name, os_name, len);
+ vlcd = (struct vnic_login_client_data *)(vlcd->name + len);
/* Type 2 - LPAR name */
vlcd->type = 2;
len = strlen(utsname()->nodename) + 1;
vlcd->len = cpu_to_be16(len);
- strncpy(&vlcd->name, utsname()->nodename, len);
- vlcd = (struct vnic_login_client_data *)((char *)&vlcd->name + len);
+ strncpy(vlcd->name, utsname()->nodename, len);
+ vlcd = (struct vnic_login_client_data *)(vlcd->name + len);
/* Type 3 - device name */
vlcd->type = 3;
len = strlen(adapter->netdev->name) + 1;
vlcd->len = cpu_to_be16(len);
- strncpy(&vlcd->name, adapter->netdev->name, len);
+ strncpy(vlcd->name, adapter->netdev->name, len);
}
static int send_login(struct ibmvnic_adapter *adapter)
@@ -3942,7 +3973,7 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
* to resend the login buffer with fewer queues requested.
*/
if (login_rsp_crq->generic.rc.code) {
- adapter->renegotiate = true;
+ adapter->init_done_rc = login_rsp_crq->generic.rc.code;
complete(&adapter->init_done);
return 0;
}
@@ -4563,14 +4594,6 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter)
release_crq_queue(adapter);
}
- rc = init_stats_buffers(adapter);
- if (rc)
- return rc;
-
- rc = init_stats_token(adapter);
- if (rc)
- return rc;
-
return rc;
}
@@ -4639,13 +4662,21 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
goto ibmvnic_init_fail;
} while (rc == EAGAIN);
+ rc = init_stats_buffers(adapter);
+ if (rc)
+ goto ibmvnic_init_fail;
+
+ rc = init_stats_token(adapter);
+ if (rc)
+ goto ibmvnic_stats_fail;
+
netdev->mtu = adapter->req_mtu - ETH_HLEN;
netdev->min_mtu = adapter->min_mtu - ETH_HLEN;
netdev->max_mtu = adapter->max_mtu - ETH_HLEN;
rc = device_create_file(&dev->dev, &dev_attr_failover);
if (rc)
- goto ibmvnic_init_fail;
+ goto ibmvnic_dev_file_err;
netif_carrier_off(netdev);
rc = register_netdev(netdev);
@@ -4664,6 +4695,12 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
ibmvnic_register_fail:
device_remove_file(&dev->dev, &dev_attr_failover);
+ibmvnic_dev_file_err:
+ release_stats_token(adapter);
+
+ibmvnic_stats_fail:
+ release_stats_buffers(adapter);
+
ibmvnic_init_fail:
release_sub_crqs(adapter, 1);
release_crq_queue(adapter);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index 99c0b58..22391e8 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -1035,7 +1035,6 @@ struct ibmvnic_adapter {
struct ibmvnic_sub_crq_queue **tx_scrq;
struct ibmvnic_sub_crq_queue **rx_scrq;
- bool renegotiate;
/* rx structs */
struct napi_struct *napi;
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 5b13ca1..7dc5f04 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -586,7 +586,7 @@ struct ice_sw_rule_lg_act {
#define ICE_LG_ACT_MIRROR_VSI_ID_S 3
#define ICE_LG_ACT_MIRROR_VSI_ID_M (0x3FF << ICE_LG_ACT_MIRROR_VSI_ID_S)
- /* Action type = 5 - Large Action */
+ /* Action type = 5 - Generic Value */
#define ICE_LG_ACT_GENERIC 0x5
#define ICE_LG_ACT_GENERIC_VALUE_S 3
#define ICE_LG_ACT_GENERIC_VALUE_M (0xFFFF << ICE_LG_ACT_GENERIC_VALUE_S)
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 21977ec..71d032c 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -78,6 +78,7 @@ ice_aq_manage_mac_read(struct ice_hw *hw, void *buf, u16 buf_size,
struct ice_aq_desc desc;
enum ice_status status;
u16 flags;
+ u8 i;
cmd = &desc.params.mac_read;
@@ -98,8 +99,16 @@ ice_aq_manage_mac_read(struct ice_hw *hw, void *buf, u16 buf_size,
return ICE_ERR_CFG;
}
- ether_addr_copy(hw->port_info->mac.lan_addr, resp->mac_addr);
- ether_addr_copy(hw->port_info->mac.perm_addr, resp->mac_addr);
+ /* A single port can report up to two (LAN and WoL) addresses */
+ for (i = 0; i < cmd->num_addr; i++)
+ if (resp[i].addr_type == ICE_AQC_MAN_MAC_ADDR_TYPE_LAN) {
+ ether_addr_copy(hw->port_info->mac.lan_addr,
+ resp[i].mac_addr);
+ ether_addr_copy(hw->port_info->mac.perm_addr,
+ resp[i].mac_addr);
+ break;
+ }
+
return 0;
}
@@ -464,9 +473,12 @@ enum ice_status ice_init_hw(struct ice_hw *hw)
if (status)
goto err_unroll_sched;
- /* Get port MAC information */
- mac_buf_len = sizeof(struct ice_aqc_manage_mac_read_resp);
- mac_buf = devm_kzalloc(ice_hw_to_dev(hw), mac_buf_len, GFP_KERNEL);
+ /* Get MAC information */
+ /* A single port can report up to two (LAN and WoL) addresses */
+ mac_buf = devm_kcalloc(ice_hw_to_dev(hw), 2,
+ sizeof(struct ice_aqc_manage_mac_read_resp),
+ GFP_KERNEL);
+ mac_buf_len = 2 * sizeof(struct ice_aqc_manage_mac_read_resp);
if (!mac_buf) {
status = ICE_ERR_NO_MEMORY;
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index 5909a44..7c511f1 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -1014,10 +1014,10 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq,
desc = ICE_CTL_Q_DESC(cq->rq, ntc);
desc_idx = ntc;
+ cq->rq_last_status = (enum ice_aq_err)le16_to_cpu(desc->retval);
flags = le16_to_cpu(desc->flags);
if (flags & ICE_AQ_FLAG_ERR) {
ret_code = ICE_ERR_AQ_ERROR;
- cq->rq_last_status = (enum ice_aq_err)le16_to_cpu(desc->retval);
ice_debug(hw, ICE_DBG_AQ_MSG,
"Control Receive Queue Event received with error 0x%x\n",
cq->rq_last_status);
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 1b9e2ef..4999048 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -121,8 +121,6 @@
#define PFINT_FW_CTL_CAUSE_ENA_S 30
#define PFINT_FW_CTL_CAUSE_ENA_M BIT(PFINT_FW_CTL_CAUSE_ENA_S)
#define PFINT_OICR 0x0016CA00
-#define PFINT_OICR_INTEVENT_S 0
-#define PFINT_OICR_INTEVENT_M BIT(PFINT_OICR_INTEVENT_S)
#define PFINT_OICR_HLP_RDY_S 14
#define PFINT_OICR_HLP_RDY_M BIT(PFINT_OICR_HLP_RDY_S)
#define PFINT_OICR_CPM_RDY_S 15
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 210b791..5299caf 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1722,9 +1722,6 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
oicr = rd32(hw, PFINT_OICR);
ena_mask = rd32(hw, PFINT_OICR_ENA);
- if (!(oicr & PFINT_OICR_INTEVENT_M))
- goto ena_intr;
-
if (oicr & PFINT_OICR_GRST_M) {
u32 reset;
/* we have a reset warning */
@@ -1782,7 +1779,6 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
}
ret = IRQ_HANDLED;
-ena_intr:
/* re-enable interrupt causes that are not handled during this pass */
wr32(hw, PFINT_OICR_ENA, ena_mask);
if (!test_bit(__ICE_DOWN, pf->state)) {
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index f16ff3e..2e6c1d9 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -751,14 +751,14 @@ ice_sched_add_nodes_to_layer(struct ice_port_info *pi,
u16 num_added = 0;
u32 temp;
+ *num_nodes_added = 0;
+
if (!num_nodes)
return status;
if (!parent || layer < hw->sw_entry_point_layer)
return ICE_ERR_PARAM;
- *num_nodes_added = 0;
-
/* max children per node per layer */
max_child_nodes =
le16_to_cpu(hw->layer_info[parent->tx_sched_layer].max_children);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index c1c0bc3..cce7ada 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1700,7 +1700,22 @@ static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
WARN_ON(hw->mac.type != e1000_i210);
WARN_ON(queue < 0 || queue > 1);
- if (enable) {
+ if (enable || queue == 0) {
+ /* i210 does not allow the queue 0 to be in the Strict
+ * Priority mode while the Qav mode is enabled, so,
+ * instead of disabling strict priority mode, we give
+ * queue 0 the maximum of credits possible.
+ *
+ * See section 8.12.19 of the i210 datasheet, "Note:
+ * Queue0 QueueMode must be set to 1b when
+ * TransmitMode is set to Qav."
+ */
+ if (queue == 0 && !enable) {
+ /* max "linkspeed" idleslope in kbps */
+ idleslope = 1000000;
+ hicredit = ETH_FRAME_LEN;
+ }
+
set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index 68af127..cead23e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -943,8 +943,8 @@ void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter)
kfree(ipsec->ip_tbl);
kfree(ipsec->rx_tbl);
kfree(ipsec->tx_tbl);
+ kfree(ipsec);
err1:
- kfree(adapter->ipsec);
netdev_err(adapter->netdev, "Unable to allocate memory for SA tables");
}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index afadba9..2ecd558 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -9054,7 +9054,6 @@ static int parse_tc_actions(struct ixgbe_adapter *adapter,
{
const struct tc_action *a;
LIST_HEAD(actions);
- int err;
if (!tcf_exts_has_actions(exts))
return -EINVAL;
@@ -9075,11 +9074,11 @@ static int parse_tc_actions(struct ixgbe_adapter *adapter,
if (!dev)
return -EINVAL;
- err = handle_redirect_action(adapter, dev->ifindex, queue,
- action);
- if (err == 0)
- return err;
+ return handle_redirect_action(adapter, dev->ifindex,
+ queue, action);
}
+
+ return -EINVAL;
}
return -EINVAL;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index 3123267..9592f3e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -3427,6 +3427,9 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw)
hw->phy.sfp_setup_needed = false;
}
+ if (status == IXGBE_ERR_SFP_NOT_SUPPORTED)
+ return status;
+
/* Reset PHY */
if (!hw->phy.reset_disable && hw->phy.ops.reset)
hw->phy.ops.reset(hw);
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 3d9033f..850f8af 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -3420,7 +3420,7 @@ static int ixgbevf_setup_all_tx_resources(struct ixgbevf_adapter *adapter)
if (!err)
continue;
hw_dbg(&adapter->hw, "Allocation for XDP Queue %u failed\n", j);
- break;
+ goto err_setup_tx;
}
return 0;
@@ -4137,7 +4137,7 @@ static int ixgbevf_xmit_frame_ring(struct sk_buff *skb,
return NETDEV_TX_OK;
}
-static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
+static netdev_tx_t ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
{
struct ixgbevf_adapter *adapter = netdev_priv(netdev);
struct ixgbevf_ring *tx_ring;
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index 54a0389..6f41023 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -663,7 +663,7 @@ enum mvpp2_tag_type {
#define MVPP2_PE_VID_FILT_RANGE_END (MVPP2_PRS_TCAM_SRAM_SIZE - 31)
#define MVPP2_PE_VID_FILT_RANGE_START (MVPP2_PE_VID_FILT_RANGE_END - \
MVPP2_PRS_VLAN_FILT_RANGE_SIZE + 1)
-#define MVPP2_PE_LAST_FREE_TID (MVPP2_PE_VID_FILT_RANGE_START - 1)
+#define MVPP2_PE_LAST_FREE_TID (MVPP2_PE_MAC_RANGE_START - 1)
#define MVPP2_PE_IP6_EXT_PROTO_UN (MVPP2_PRS_TCAM_SRAM_SIZE - 30)
#define MVPP2_PE_IP6_ADDR_UN (MVPP2_PRS_TCAM_SRAM_SIZE - 29)
#define MVPP2_PE_IP4_ADDR_UN (MVPP2_PRS_TCAM_SRAM_SIZE - 28)
@@ -916,6 +916,8 @@ static struct {
#define MVPP2_MIB_COUNTERS_STATS_DELAY (1 * HZ)
+#define MVPP2_DESC_DMA_MASK DMA_BIT_MASK(40)
+
/* Definitions */
/* Shared Packet Processor resources */
@@ -940,6 +942,7 @@ struct mvpp2 {
struct clk *pp_clk;
struct clk *gop_clk;
struct clk *mg_clk;
+ struct clk *mg_core_clk;
struct clk *axi_clk;
/* List of pointers to port structures */
@@ -1429,7 +1432,7 @@ static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port,
if (port->priv->hw_version == MVPP21)
return tx_desc->pp21.buf_dma_addr;
else
- return tx_desc->pp22.buf_dma_addr_ptp & GENMASK_ULL(40, 0);
+ return tx_desc->pp22.buf_dma_addr_ptp & MVPP2_DESC_DMA_MASK;
}
static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
@@ -1447,7 +1450,7 @@ static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
} else {
u64 val = (u64)addr;
- tx_desc->pp22.buf_dma_addr_ptp &= ~GENMASK_ULL(40, 0);
+ tx_desc->pp22.buf_dma_addr_ptp &= ~MVPP2_DESC_DMA_MASK;
tx_desc->pp22.buf_dma_addr_ptp |= val;
tx_desc->pp22.packet_offset = offset;
}
@@ -1507,7 +1510,7 @@ static dma_addr_t mvpp2_rxdesc_dma_addr_get(struct mvpp2_port *port,
if (port->priv->hw_version == MVPP21)
return rx_desc->pp21.buf_dma_addr;
else
- return rx_desc->pp22.buf_dma_addr_key_hash & GENMASK_ULL(40, 0);
+ return rx_desc->pp22.buf_dma_addr_key_hash & MVPP2_DESC_DMA_MASK;
}
static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port,
@@ -1516,7 +1519,7 @@ static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port,
if (port->priv->hw_version == MVPP21)
return rx_desc->pp21.buf_cookie;
else
- return rx_desc->pp22.buf_cookie_misc & GENMASK_ULL(40, 0);
+ return rx_desc->pp22.buf_cookie_misc & MVPP2_DESC_DMA_MASK;
}
static size_t mvpp2_rxdesc_size_get(struct mvpp2_port *port,
@@ -8766,18 +8769,27 @@ static int mvpp2_probe(struct platform_device *pdev)
err = clk_prepare_enable(priv->mg_clk);
if (err < 0)
goto err_gop_clk;
+
+ priv->mg_core_clk = devm_clk_get(&pdev->dev, "mg_core_clk");
+ if (IS_ERR(priv->mg_core_clk)) {
+ priv->mg_core_clk = NULL;
+ } else {
+ err = clk_prepare_enable(priv->mg_core_clk);
+ if (err < 0)
+ goto err_mg_clk;
+ }
}
priv->axi_clk = devm_clk_get(&pdev->dev, "axi_clk");
if (IS_ERR(priv->axi_clk)) {
err = PTR_ERR(priv->axi_clk);
if (err == -EPROBE_DEFER)
- goto err_gop_clk;
+ goto err_mg_core_clk;
priv->axi_clk = NULL;
} else {
err = clk_prepare_enable(priv->axi_clk);
if (err < 0)
- goto err_gop_clk;
+ goto err_mg_core_clk;
}
/* Get system's tclk rate */
@@ -8789,9 +8801,9 @@ static int mvpp2_probe(struct platform_device *pdev)
}
if (priv->hw_version == MVPP22) {
- err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(40));
+ err = dma_set_mask(&pdev->dev, MVPP2_DESC_DMA_MASK);
if (err)
- goto err_mg_clk;
+ goto err_axi_clk;
/* Sadly, the BM pools all share the same register to
* store the high 32 bits of their address. So they
* must all have the same high 32 bits, which forces
@@ -8799,14 +8811,14 @@ static int mvpp2_probe(struct platform_device *pdev)
*/
err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
if (err)
- goto err_mg_clk;
+ goto err_axi_clk;
}
/* Initialize network controller */
err = mvpp2_init(pdev, priv);
if (err < 0) {
dev_err(&pdev->dev, "failed to initialize controller\n");
- goto err_mg_clk;
+ goto err_axi_clk;
}
/* Initialize ports */
@@ -8819,7 +8831,7 @@ static int mvpp2_probe(struct platform_device *pdev)
if (priv->port_count == 0) {
dev_err(&pdev->dev, "no ports enabled\n");
err = -ENODEV;
- goto err_mg_clk;
+ goto err_axi_clk;
}
/* Statistics must be gathered regularly because some of them (like
@@ -8847,8 +8859,13 @@ static int mvpp2_probe(struct platform_device *pdev)
mvpp2_port_remove(priv->port_list[i]);
i++;
}
-err_mg_clk:
+err_axi_clk:
clk_disable_unprepare(priv->axi_clk);
+
+err_mg_core_clk:
+ if (priv->hw_version == MVPP22)
+ clk_disable_unprepare(priv->mg_core_clk);
+err_mg_clk:
if (priv->hw_version == MVPP22)
clk_disable_unprepare(priv->mg_clk);
err_gop_clk:
@@ -8895,6 +8912,7 @@ static int mvpp2_remove(struct platform_device *pdev)
return 0;
clk_disable_unprepare(priv->axi_clk);
+ clk_disable_unprepare(priv->mg_core_clk);
clk_disable_unprepare(priv->mg_clk);
clk_disable_unprepare(priv->pp_clk);
clk_disable_unprepare(priv->gop_clk);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index a30a2e9..f11b450 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1027,6 +1027,22 @@ static int mlx4_en_set_coalesce(struct net_device *dev,
if (!coal->tx_max_coalesced_frames_irq)
return -EINVAL;
+ if (coal->tx_coalesce_usecs > MLX4_EN_MAX_COAL_TIME ||
+ coal->rx_coalesce_usecs > MLX4_EN_MAX_COAL_TIME ||
+ coal->rx_coalesce_usecs_low > MLX4_EN_MAX_COAL_TIME ||
+ coal->rx_coalesce_usecs_high > MLX4_EN_MAX_COAL_TIME) {
+ netdev_info(dev, "%s: maximum coalesce time supported is %d usecs\n",
+ __func__, MLX4_EN_MAX_COAL_TIME);
+ return -ERANGE;
+ }
+
+ if (coal->tx_max_coalesced_frames > MLX4_EN_MAX_COAL_PKTS ||
+ coal->rx_max_coalesced_frames > MLX4_EN_MAX_COAL_PKTS) {
+ netdev_info(dev, "%s: maximum coalesced frames supported is %d\n",
+ __func__, MLX4_EN_MAX_COAL_PKTS);
+ return -ERANGE;
+ }
+
priv->rx_frames = (coal->rx_max_coalesced_frames ==
MLX4_EN_AUTO_CONF) ?
MLX4_EN_RX_COAL_TARGET :
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index e0adac4..9670b33 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -3324,12 +3324,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
MAX_TX_RINGS, GFP_KERNEL);
if (!priv->tx_ring[t]) {
err = -ENOMEM;
- goto err_free_tx;
+ goto out;
}
priv->tx_cq[t] = kzalloc(sizeof(struct mlx4_en_cq *) *
MAX_TX_RINGS, GFP_KERNEL);
if (!priv->tx_cq[t]) {
- kfree(priv->tx_ring[t]);
err = -ENOMEM;
goto out;
}
@@ -3582,11 +3581,6 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
return 0;
-err_free_tx:
- while (t--) {
- kfree(priv->tx_ring[t]);
- kfree(priv->tx_cq[t]);
- }
out:
mlx4_en_destroy_netdev(dev);
return err;
diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c
index a822f7a..685337d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.c
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.c
@@ -43,12 +43,12 @@
#include "fw.h"
/*
- * We allocate in as big chunks as we can, up to a maximum of 256 KB
- * per chunk.
+ * We allocate in page size (default 4KB on many archs) chunks to avoid high
+ * order memory allocations in fragmented/high usage memory situation.
*/
enum {
- MLX4_ICM_ALLOC_SIZE = 1 << 18,
- MLX4_TABLE_CHUNK_SIZE = 1 << 18
+ MLX4_ICM_ALLOC_SIZE = PAGE_SIZE,
+ MLX4_TABLE_CHUNK_SIZE = PAGE_SIZE,
};
static void mlx4_free_icm_pages(struct mlx4_dev *dev, struct mlx4_icm_chunk *chunk)
@@ -398,9 +398,11 @@ int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table,
u64 size;
obj_per_chunk = MLX4_TABLE_CHUNK_SIZE / obj_size;
+ if (WARN_ON(!obj_per_chunk))
+ return -EINVAL;
num_icm = (nobj + obj_per_chunk - 1) / obj_per_chunk;
- table->icm = kcalloc(num_icm, sizeof(*table->icm), GFP_KERNEL);
+ table->icm = kvzalloc(num_icm * sizeof(*table->icm), GFP_KERNEL);
if (!table->icm)
return -ENOMEM;
table->virt = virt;
@@ -446,7 +448,7 @@ int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table,
mlx4_free_icm(dev, table->icm[i], use_coherent);
}
- kfree(table->icm);
+ kvfree(table->icm);
return -ENOMEM;
}
@@ -462,5 +464,5 @@ void mlx4_cleanup_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table)
mlx4_free_icm(dev, table->icm[i], table->coherent);
}
- kfree(table->icm);
+ kvfree(table->icm);
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 2edcce9..65482f0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -172,7 +172,7 @@ int mlx4_do_bond(struct mlx4_dev *dev, bool enable)
list_add_tail(&dev_ctx->list, &priv->ctx_list);
spin_unlock_irqrestore(&priv->ctx_lock, flags);
- mlx4_dbg(dev, "Inrerface for protocol %d restarted with when bonded mode is %s\n",
+ mlx4_dbg(dev, "Interface for protocol %d restarted with bonded mode %s\n",
dev_ctx->intf->protocol, enable ?
"enabled" : "disabled");
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index bfef692..60172a3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1317,7 +1317,7 @@ static int mlx4_mf_unbond(struct mlx4_dev *dev)
ret = mlx4_unbond_fs_rules(dev);
if (ret)
- mlx4_warn(dev, "multifunction unbond for flow rules failedi (%d)\n", ret);
+ mlx4_warn(dev, "multifunction unbond for flow rules failed (%d)\n", ret);
ret1 = mlx4_unbond_mac_table(dev);
if (ret1) {
mlx4_warn(dev, "multifunction unbond for MAC table failed (%d)\n", ret1);
@@ -2929,6 +2929,7 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port)
mlx4_err(dev, "Failed to create file for port %d\n", port);
devlink_port_unregister(&info->devlink_port);
info->port = -1;
+ return err;
}
sprintf(info->dev_mtu_name, "mlx4_port%d_mtu", port);
@@ -2950,9 +2951,10 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port)
&info->port_attr);
devlink_port_unregister(&info->devlink_port);
info->port = -1;
+ return err;
}
- return err;
+ return 0;
}
static void mlx4_cleanup_port_info(struct mlx4_port_info *info)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index f7c8113..ace6545 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -132,6 +132,9 @@
#define MLX4_EN_TX_COAL_PKTS 16
#define MLX4_EN_TX_COAL_TIME 0x10
+#define MLX4_EN_MAX_COAL_PKTS U16_MAX
+#define MLX4_EN_MAX_COAL_TIME U16_MAX
+
#define MLX4_EN_RX_RATE_LOW 400000
#define MLX4_EN_RX_COAL_TIME_LOW 0
#define MLX4_EN_RX_RATE_HIGH 450000
@@ -552,8 +555,8 @@ struct mlx4_en_priv {
u16 rx_usecs_low;
u32 pkt_rate_high;
u16 rx_usecs_high;
- u16 sample_interval;
- u16 adaptive_rx_coal;
+ u32 sample_interval;
+ u32 adaptive_rx_coal;
u32 msg_enable;
u32 loopback_ok;
u32 validate_loopback;
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 3aaf4ba..427e7a3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -393,11 +393,11 @@ struct mlx4_qp *mlx4_qp_lookup(struct mlx4_dev *dev, u32 qpn)
struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
struct mlx4_qp *qp;
- spin_lock(&qp_table->lock);
+ spin_lock_irq(&qp_table->lock);
qp = __mlx4_qp_lookup(dev, qpn);
- spin_unlock(&qp_table->lock);
+ spin_unlock_irq(&qp_table->lock);
return qp;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 3d46ef4..c641d56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -1007,12 +1007,14 @@ static void mlx5e_trust_update_sq_inline_mode(struct mlx5e_priv *priv)
mutex_lock(&priv->state_lock);
- if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
- goto out;
-
new_channels.params = priv->channels.params;
mlx5e_trust_update_tx_min_inline_mode(priv, &new_channels.params);
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+ priv->channels.params = new_channels.params;
+ goto out;
+ }
+
/* Skip if tx_min_inline is the same */
if (new_channels.params.tx_min_inline_mode ==
priv->channels.params.tx_min_inline_mode)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index d8f68e4..876c3e4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -877,13 +877,14 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = {
};
static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
- struct mlx5e_params *params)
+ struct mlx5e_params *params, u16 mtu)
{
u8 cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
params->hard_mtu = MLX5E_ETH_HARD_MTU;
+ params->sw_mtu = mtu;
params->log_sq_size = MLX5E_REP_PARAMS_LOG_SQ_SIZE;
params->rq_wq_type = MLX5_WQ_TYPE_LINKED_LIST;
params->log_rq_mtu_frames = MLX5E_REP_PARAMS_LOG_RQ_SIZE;
@@ -931,7 +932,7 @@ static void mlx5e_init_rep(struct mlx5_core_dev *mdev,
priv->channels.params.num_channels = profile->max_nch(mdev);
- mlx5e_build_rep_params(mdev, &priv->channels.params);
+ mlx5e_build_rep_params(mdev, &priv->channels.params, netdev->mtu);
mlx5e_build_rep_netdev(netdev);
mlx5e_timestamp_init(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 1766457..1ff0b0e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -615,6 +615,45 @@ static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth)
return (ethertype == htons(ETH_P_IP) || ethertype == htons(ETH_P_IPV6));
}
+static __be32 mlx5e_get_fcs(struct sk_buff *skb)
+{
+ int last_frag_sz, bytes_in_prev, nr_frags;
+ u8 *fcs_p1, *fcs_p2;
+ skb_frag_t *last_frag;
+ __be32 fcs_bytes;
+
+ if (!skb_is_nonlinear(skb))
+ return *(__be32 *)(skb->data + skb->len - ETH_FCS_LEN);
+
+ nr_frags = skb_shinfo(skb)->nr_frags;
+ last_frag = &skb_shinfo(skb)->frags[nr_frags - 1];
+ last_frag_sz = skb_frag_size(last_frag);
+
+ /* If all FCS data is in last frag */
+ if (last_frag_sz >= ETH_FCS_LEN)
+ return *(__be32 *)(skb_frag_address(last_frag) +
+ last_frag_sz - ETH_FCS_LEN);
+
+ fcs_p2 = (u8 *)skb_frag_address(last_frag);
+ bytes_in_prev = ETH_FCS_LEN - last_frag_sz;
+
+ /* Find where the other part of the FCS is - Linear or another frag */
+ if (nr_frags == 1) {
+ fcs_p1 = skb_tail_pointer(skb);
+ } else {
+ skb_frag_t *prev_frag = &skb_shinfo(skb)->frags[nr_frags - 2];
+
+ fcs_p1 = skb_frag_address(prev_frag) +
+ skb_frag_size(prev_frag);
+ }
+ fcs_p1 -= bytes_in_prev;
+
+ memcpy(&fcs_bytes, fcs_p1, bytes_in_prev);
+ memcpy(((u8 *)&fcs_bytes) + bytes_in_prev, fcs_p2, last_frag_sz);
+
+ return fcs_bytes;
+}
+
static inline void mlx5e_handle_csum(struct net_device *netdev,
struct mlx5_cqe64 *cqe,
struct mlx5e_rq *rq,
@@ -643,6 +682,9 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
skb->csum = csum_partial(skb->data + ETH_HLEN,
network_depth - ETH_HLEN,
skb->csum);
+ if (unlikely(netdev->features & NETIF_F_RXFCS))
+ skb->csum = csum_add(skb->csum,
+ (__force __wsum)mlx5e_get_fcs(skb));
rq->stats.csum_complete++;
return;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 7079764..027f54a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -290,7 +290,7 @@ static int mlx5e_test_loopback(struct mlx5e_priv *priv)
if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
netdev_err(priv->netdev,
- "\tCan't perform loobpack test while device is down\n");
+ "\tCan't perform loopback test while device is down\n");
return -ENODEV;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 4197001..b94276d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1261,6 +1261,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
f->mask);
addr_type = key->addr_type;
+ /* the HW doesn't support frag first/later */
+ if (mask->flags & FLOW_DIS_FIRST_FRAG)
+ return -EOPNOTSUPP;
+
if (mask->flags & FLOW_DIS_IS_FRAGMENT) {
MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1);
MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag,
@@ -1864,7 +1868,8 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
}
ip_proto = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol);
- if (modify_ip_header && ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) {
+ if (modify_ip_header && ip_proto != IPPROTO_TCP &&
+ ip_proto != IPPROTO_UDP && ip_proto != IPPROTO_ICMP) {
pr_info("can't offload re-write of ip proto %d\n", ip_proto);
return false;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 2029710..5532aa3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -255,7 +255,7 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb,
dma_addr = dma_map_single(sq->pdev, skb_data, headlen,
DMA_TO_DEVICE);
if (unlikely(dma_mapping_error(sq->pdev, dma_addr)))
- return -ENOMEM;
+ goto dma_unmap_wqe_err;
dseg->addr = cpu_to_be64(dma_addr);
dseg->lkey = sq->mkey_be;
@@ -273,7 +273,7 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb,
dma_addr = skb_frag_dma_map(sq->pdev, frag, 0, fsz,
DMA_TO_DEVICE);
if (unlikely(dma_mapping_error(sq->pdev, dma_addr)))
- return -ENOMEM;
+ goto dma_unmap_wqe_err;
dseg->addr = cpu_to_be64(dma_addr);
dseg->lkey = sq->mkey_be;
@@ -285,6 +285,10 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb,
}
return num_dma;
+
+dma_unmap_wqe_err:
+ mlx5e_dma_unmap_wqe_err(sq, num_dma);
+ return -ENOMEM;
}
static inline void
@@ -380,17 +384,15 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen,
(struct mlx5_wqe_data_seg *)cseg + ds_cnt);
if (unlikely(num_dma < 0))
- goto dma_unmap_wqe_err;
+ goto err_drop;
mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt + num_dma,
num_bytes, num_dma, wi, cseg);
return NETDEV_TX_OK;
-dma_unmap_wqe_err:
+err_drop:
sq->stats.dropped++;
- mlx5e_dma_unmap_wqe_err(sq, wi->num_dma);
-
dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
@@ -645,17 +647,15 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen,
(struct mlx5_wqe_data_seg *)cseg + ds_cnt);
if (unlikely(num_dma < 0))
- goto dma_unmap_wqe_err;
+ goto err_drop;
mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt + num_dma,
num_bytes, num_dma, wi, cseg);
return NETDEV_TX_OK;
-dma_unmap_wqe_err:
+err_drop:
sq->stats.dropped++;
- mlx5e_dma_unmap_wqe_err(sq, wi->num_dma);
-
dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index c1c9497..1814f80 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -34,6 +34,9 @@
#include <linux/module.h>
#include <linux/mlx5/driver.h>
#include <linux/mlx5/cmd.h>
+#ifdef CONFIG_RFS_ACCEL
+#include <linux/cpu_rmap.h>
+#endif
#include "mlx5_core.h"
#include "fpga/core.h"
#include "eswitch.h"
@@ -923,3 +926,28 @@ int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
MLX5_SET(query_eq_in, in, eq_number, eq->eqn);
return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
}
+
+/* This function should only be called after mlx5_cmd_force_teardown_hca */
+void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
+{
+ struct mlx5_eq_table *table = &dev->priv.eq_table;
+ struct mlx5_eq *eq;
+
+#ifdef CONFIG_RFS_ACCEL
+ if (dev->rmap) {
+ free_irq_cpu_rmap(dev->rmap);
+ dev->rmap = NULL;
+ }
+#endif
+ list_for_each_entry(eq, &table->comp_eqs_list, list)
+ free_irq(eq->irqn, eq);
+
+ free_irq(table->pages_eq.irqn, &table->pages_eq);
+ free_irq(table->async_eq.irqn, &table->async_eq);
+ free_irq(table->cmd_eq.irqn, &table->cmd_eq);
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+ if (MLX5_CAP_GEN(dev, pg))
+ free_irq(table->pfault_eq.irqn, &table->pfault_eq);
+#endif
+ pci_free_irq_vectors(dev->pdev);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 332bc56..1352d13 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -2175,26 +2175,35 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
memset(vf_stats, 0, sizeof(*vf_stats));
vf_stats->rx_packets =
MLX5_GET_CTR(out, received_eth_unicast.packets) +
+ MLX5_GET_CTR(out, received_ib_unicast.packets) +
MLX5_GET_CTR(out, received_eth_multicast.packets) +
+ MLX5_GET_CTR(out, received_ib_multicast.packets) +
MLX5_GET_CTR(out, received_eth_broadcast.packets);
vf_stats->rx_bytes =
MLX5_GET_CTR(out, received_eth_unicast.octets) +
+ MLX5_GET_CTR(out, received_ib_unicast.octets) +
MLX5_GET_CTR(out, received_eth_multicast.octets) +
+ MLX5_GET_CTR(out, received_ib_multicast.octets) +
MLX5_GET_CTR(out, received_eth_broadcast.octets);
vf_stats->tx_packets =
MLX5_GET_CTR(out, transmitted_eth_unicast.packets) +
+ MLX5_GET_CTR(out, transmitted_ib_unicast.packets) +
MLX5_GET_CTR(out, transmitted_eth_multicast.packets) +
+ MLX5_GET_CTR(out, transmitted_ib_multicast.packets) +
MLX5_GET_CTR(out, transmitted_eth_broadcast.packets);
vf_stats->tx_bytes =
MLX5_GET_CTR(out, transmitted_eth_unicast.octets) +
+ MLX5_GET_CTR(out, transmitted_ib_unicast.octets) +
MLX5_GET_CTR(out, transmitted_eth_multicast.octets) +
+ MLX5_GET_CTR(out, transmitted_ib_multicast.octets) +
MLX5_GET_CTR(out, transmitted_eth_broadcast.octets);
vf_stats->multicast =
- MLX5_GET_CTR(out, received_eth_multicast.packets);
+ MLX5_GET_CTR(out, received_eth_multicast.packets) +
+ MLX5_GET_CTR(out, received_ib_multicast.packets);
vf_stats->broadcast =
MLX5_GET_CTR(out, received_eth_broadcast.packets);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
index 0f5da49..fad8c2e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
@@ -237,19 +237,17 @@ static void *mlx5_fpga_ipsec_cmd_exec(struct mlx5_core_dev *mdev,
context->buf.sg[0].data = &context->command;
spin_lock_irqsave(&fdev->ipsec->pending_cmds_lock, flags);
- list_add_tail(&context->list, &fdev->ipsec->pending_cmds);
+ res = mlx5_fpga_sbu_conn_sendmsg(fdev->ipsec->conn, &context->buf);
+ if (!res)
+ list_add_tail(&context->list, &fdev->ipsec->pending_cmds);
spin_unlock_irqrestore(&fdev->ipsec->pending_cmds_lock, flags);
- res = mlx5_fpga_sbu_conn_sendmsg(fdev->ipsec->conn, &context->buf);
if (res) {
- mlx5_fpga_warn(fdev, "Failure sending IPSec command: %d\n",
- res);
- spin_lock_irqsave(&fdev->ipsec->pending_cmds_lock, flags);
- list_del(&context->list);
- spin_unlock_irqrestore(&fdev->ipsec->pending_cmds_lock, flags);
+ mlx5_fpga_warn(fdev, "Failed to send IPSec command: %d\n", res);
kfree(context);
return ERR_PTR(res);
}
+
/* Context will be freed by wait func after completion */
return context;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index de51e7c..c39c169 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -187,6 +187,7 @@ static void del_sw_ns(struct fs_node *node);
static void del_sw_hw_rule(struct fs_node *node);
static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
struct mlx5_flow_destination *d2);
+static void cleanup_root_ns(struct mlx5_flow_root_namespace *root_ns);
static struct mlx5_flow_rule *
find_flow_rule(struct fs_fte *fte,
struct mlx5_flow_destination *dest);
@@ -481,7 +482,8 @@ static void del_sw_hw_rule(struct fs_node *node)
if (rule->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER &&
--fte->dests_size) {
- modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION);
+ modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION) |
+ BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS);
fte->action.action &= ~MLX5_FLOW_CONTEXT_ACTION_COUNT;
update_fte = true;
goto out;
@@ -2351,23 +2353,27 @@ static int create_anchor_flow_table(struct mlx5_flow_steering *steering)
static int init_root_ns(struct mlx5_flow_steering *steering)
{
+ int err;
+
steering->root_ns = create_root_ns(steering, FS_FT_NIC_RX);
if (!steering->root_ns)
- goto cleanup;
+ return -ENOMEM;
- if (init_root_tree(steering, &root_fs, &steering->root_ns->ns.node))
- goto cleanup;
+ err = init_root_tree(steering, &root_fs, &steering->root_ns->ns.node);
+ if (err)
+ goto out_err;
set_prio_attrs(steering->root_ns);
-
- if (create_anchor_flow_table(steering))
- goto cleanup;
+ err = create_anchor_flow_table(steering);
+ if (err)
+ goto out_err;
return 0;
-cleanup:
- mlx5_cleanup_fs(steering->dev);
- return -ENOMEM;
+out_err:
+ cleanup_root_ns(steering->root_ns);
+ steering->root_ns = NULL;
+ return err;
}
static void clean_tree(struct fs_node *node)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 63a8ea3..e2c465b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1587,6 +1587,14 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev)
mlx5_enter_error_state(dev, true);
+ /* Some platforms requiring freeing the IRQ's in the shutdown
+ * flow. If they aren't freed they can't be allocated after
+ * kexec. There is no need to cleanup the mlx5_core software
+ * contexts.
+ */
+ mlx5_irq_clear_affinity_hints(dev);
+ mlx5_core_eq_free_irqs(dev);
+
return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 7d001fe..023882d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -128,6 +128,8 @@ int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
u32 *out, int outlen);
int mlx5_start_eqs(struct mlx5_core_dev *dev);
void mlx5_stop_eqs(struct mlx5_core_dev *dev);
+/* This function should only be called after mlx5_cmd_force_teardown_hca */
+void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev);
struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn);
u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq *eq);
void mlx5_cq_tasklet_cb(unsigned long data);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 93ea566..e13ac3b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1100,11 +1100,11 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
err_alloc_lag_mapping:
mlxsw_ports_fini(mlxsw_core);
err_ports_init:
- mlxsw_bus->fini(bus_priv);
-err_bus_init:
if (!reload)
devlink_resources_unregister(devlink, NULL);
err_register_resources:
+ mlxsw_bus->fini(bus_priv);
+err_bus_init:
if (!reload)
devlink_free(devlink);
err_devlink_alloc:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index ca38a30..adc6ab2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4433,6 +4433,11 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
NL_SET_ERR_MSG_MOD(extack, "Can not put a VLAN on an OVS port");
return -EINVAL;
}
+ if (is_vlan_dev(upper_dev) &&
+ vlan_dev_vlan_id(upper_dev) == 1) {
+ NL_SET_ERR_MSG_MOD(extack, "Creating a VLAN device with VID 1 is unsupported: VLAN 1 carries untagged traffic");
+ return -EINVAL;
+ }
break;
case NETDEV_CHANGEUPPER:
upper_dev = info->upper_dev;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index c11c9a6..4ed0118 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1718,13 +1718,11 @@ __mlxsw_sp_port_mdb_del(struct mlxsw_sp_port *mlxsw_sp_port,
struct net_device *dev = mlxsw_sp_port->dev;
int err;
- if (bridge_port->bridge_device->multicast_enabled) {
- if (bridge_port->bridge_device->multicast_enabled) {
- err = mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid,
- false);
- if (err)
- netdev_err(dev, "Unable to remove port from SMID\n");
- }
+ if (bridge_port->bridge_device->multicast_enabled &&
+ !bridge_port->mrouter) {
+ err = mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid, false);
+ if (err)
+ netdev_err(dev, "Unable to remove port from SMID\n");
}
err = mlxsw_sp_port_remove_from_mid(mlxsw_sp_port, mid);
diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index 7ed0848..c805dcb 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -84,7 +84,7 @@ static int sonic_open(struct net_device *dev)
for (i = 0; i < SONIC_NUM_RRS; i++) {
dma_addr_t laddr = dma_map_single(lp->device, skb_put(lp->rx_skb[i], SONIC_RBSIZE),
SONIC_RBSIZE, DMA_FROM_DEVICE);
- if (!laddr) {
+ if (dma_mapping_error(lp->device, laddr)) {
while(i > 0) { /* free any that were mapped successfully */
i--;
dma_unmap_single(lp->device, lp->rx_laddr[i], SONIC_RBSIZE, DMA_FROM_DEVICE);
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index 1dc4246..35fb31f 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -335,7 +335,7 @@ static int nfp_bpf_parse_capabilities(struct nfp_app *app)
return PTR_ERR(mem) == -ENOENT ? 0 : PTR_ERR(mem);
start = mem;
- while (mem - start + 8 < nfp_cpp_area_size(area)) {
+ while (mem - start + 8 <= nfp_cpp_area_size(area)) {
u8 __iomem *value;
u32 type, length;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index b3567a5..80df9a5 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -183,17 +183,21 @@ static int
nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun,
const struct tc_action *action,
struct nfp_fl_pre_tunnel *pre_tun,
- enum nfp_flower_tun_type tun_type)
+ enum nfp_flower_tun_type tun_type,
+ struct net_device *netdev)
{
size_t act_size = sizeof(struct nfp_fl_set_ipv4_udp_tun);
struct ip_tunnel_info *ip_tun = tcf_tunnel_info(action);
u32 tmp_set_ip_tun_type_index = 0;
/* Currently support one pre-tunnel so index is always 0. */
int pretun_idx = 0;
+ struct net *net;
if (ip_tun->options_len)
return -EOPNOTSUPP;
+ net = dev_net(netdev);
+
set_tun->head.jump_id = NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL;
set_tun->head.len_lw = act_size >> NFP_FL_LW_SIZ;
@@ -204,6 +208,7 @@ nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun,
set_tun->tun_type_index = cpu_to_be32(tmp_set_ip_tun_type_index);
set_tun->tun_id = ip_tun->key.tun_id;
+ set_tun->ttl = net->ipv4.sysctl_ip_default_ttl;
/* Complete pre_tunnel action. */
pre_tun->ipv4_dst = ip_tun->key.u.ipv4.dst;
@@ -511,7 +516,8 @@ nfp_flower_loop_action(const struct tc_action *a,
*a_len += sizeof(struct nfp_fl_pre_tunnel);
set_tun = (void *)&nfp_fl->action_data[*a_len];
- err = nfp_fl_set_ipv4_udp_tun(set_tun, a, pre_tun, *tun_type);
+ err = nfp_fl_set_ipv4_udp_tun(set_tun, a, pre_tun, *tun_type,
+ netdev);
if (err)
return err;
*a_len += sizeof(struct nfp_fl_set_ipv4_udp_tun);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
index 3735c09..577659f 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
@@ -258,9 +258,6 @@ nfp_flower_cmsg_process_one_rx(struct nfp_app *app, struct sk_buff *skb)
case NFP_FLOWER_CMSG_TYPE_ACTIVE_TUNS:
nfp_tunnel_keep_alive(app, skb);
break;
- case NFP_FLOWER_CMSG_TYPE_TUN_NEIGH:
- /* Acks from the NFP that the route is added - ignore. */
- break;
default:
nfp_flower_cmsg_warn(app, "Cannot handle invalid repr control type %u\n",
type);
@@ -275,18 +272,49 @@ nfp_flower_cmsg_process_one_rx(struct nfp_app *app, struct sk_buff *skb)
void nfp_flower_cmsg_process_rx(struct work_struct *work)
{
+ struct sk_buff_head cmsg_joined;
struct nfp_flower_priv *priv;
struct sk_buff *skb;
priv = container_of(work, struct nfp_flower_priv, cmsg_work);
+ skb_queue_head_init(&cmsg_joined);
- while ((skb = skb_dequeue(&priv->cmsg_skbs)))
+ spin_lock_bh(&priv->cmsg_skbs_high.lock);
+ skb_queue_splice_tail_init(&priv->cmsg_skbs_high, &cmsg_joined);
+ spin_unlock_bh(&priv->cmsg_skbs_high.lock);
+
+ spin_lock_bh(&priv->cmsg_skbs_low.lock);
+ skb_queue_splice_tail_init(&priv->cmsg_skbs_low, &cmsg_joined);
+ spin_unlock_bh(&priv->cmsg_skbs_low.lock);
+
+ while ((skb = __skb_dequeue(&cmsg_joined)))
nfp_flower_cmsg_process_one_rx(priv->app, skb);
}
+static void
+nfp_flower_queue_ctl_msg(struct nfp_app *app, struct sk_buff *skb, int type)
+{
+ struct nfp_flower_priv *priv = app->priv;
+ struct sk_buff_head *skb_head;
+
+ if (type == NFP_FLOWER_CMSG_TYPE_PORT_REIFY ||
+ type == NFP_FLOWER_CMSG_TYPE_PORT_MOD)
+ skb_head = &priv->cmsg_skbs_high;
+ else
+ skb_head = &priv->cmsg_skbs_low;
+
+ if (skb_queue_len(skb_head) >= NFP_FLOWER_WORKQ_MAX_SKBS) {
+ nfp_flower_cmsg_warn(app, "Dropping queued control messages\n");
+ dev_kfree_skb_any(skb);
+ return;
+ }
+
+ skb_queue_tail(skb_head, skb);
+ schedule_work(&priv->cmsg_work);
+}
+
void nfp_flower_cmsg_rx(struct nfp_app *app, struct sk_buff *skb)
{
- struct nfp_flower_priv *priv = app->priv;
struct nfp_flower_cmsg_hdr *cmsg_hdr;
cmsg_hdr = nfp_flower_cmsg_get_hdr(skb);
@@ -306,8 +334,10 @@ void nfp_flower_cmsg_rx(struct nfp_app *app, struct sk_buff *skb)
nfp_flower_process_mtu_ack(app, skb)) {
/* Handle MTU acks outside wq to prevent RTNL conflict. */
dev_consume_skb_any(skb);
+ } else if (cmsg_hdr->type == NFP_FLOWER_CMSG_TYPE_TUN_NEIGH) {
+ /* Acks from the NFP that the route is added - ignore. */
+ dev_consume_skb_any(skb);
} else {
- skb_queue_tail(&priv->cmsg_skbs, skb);
- schedule_work(&priv->cmsg_work);
+ nfp_flower_queue_ctl_msg(app, skb, cmsg_hdr->type);
}
}
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index 96bc0e3..bee4367 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -108,6 +108,8 @@
#define NFP_FL_IPV4_TUNNEL_TYPE GENMASK(7, 4)
#define NFP_FL_IPV4_PRE_TUN_INDEX GENMASK(2, 0)
+#define NFP_FLOWER_WORKQ_MAX_SKBS 30000
+
#define nfp_flower_cmsg_warn(app, fmt, args...) \
do { \
if (net_ratelimit()) \
@@ -188,7 +190,10 @@ struct nfp_fl_set_ipv4_udp_tun {
__be16 reserved;
__be64 tun_id __packed;
__be32 tun_type_index;
- __be32 extra[3];
+ __be16 reserved2;
+ u8 ttl;
+ u8 reserved3;
+ __be32 extra[2];
};
/* Metadata with L2 (1W/4B)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index 6357e07..84e3b9f 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -52,8 +52,6 @@
#define NFP_FLOWER_ALLOWED_VER 0x0001000000010000UL
-#define NFP_FLOWER_FRAME_HEADROOM 158
-
static const char *nfp_flower_extra_cap(struct nfp_app *app, struct nfp_net *nn)
{
return "FLOWER";
@@ -360,7 +358,7 @@ nfp_flower_spawn_phy_reprs(struct nfp_app *app, struct nfp_flower_priv *priv)
}
SET_NETDEV_DEV(repr, &priv->nn->pdev->dev);
- nfp_net_get_mac_addr(app->pf, port);
+ nfp_net_get_mac_addr(app->pf, repr, port);
cmsg_port_id = nfp_flower_cmsg_phys_port(phys_port);
err = nfp_repr_init(app, repr,
@@ -519,7 +517,8 @@ static int nfp_flower_init(struct nfp_app *app)
app->priv = app_priv;
app_priv->app = app;
- skb_queue_head_init(&app_priv->cmsg_skbs);
+ skb_queue_head_init(&app_priv->cmsg_skbs_high);
+ skb_queue_head_init(&app_priv->cmsg_skbs_low);
INIT_WORK(&app_priv->cmsg_work, nfp_flower_cmsg_process_rx);
init_waitqueue_head(&app_priv->reify_wait_queue);
@@ -549,7 +548,8 @@ static void nfp_flower_clean(struct nfp_app *app)
{
struct nfp_flower_priv *app_priv = app->priv;
- skb_queue_purge(&app_priv->cmsg_skbs);
+ skb_queue_purge(&app_priv->cmsg_skbs_high);
+ skb_queue_purge(&app_priv->cmsg_skbs_low);
flush_work(&app_priv->cmsg_work);
nfp_flower_metadata_cleanup(app);
@@ -557,22 +557,6 @@ static void nfp_flower_clean(struct nfp_app *app)
app->priv = NULL;
}
-static int
-nfp_flower_check_mtu(struct nfp_app *app, struct net_device *netdev,
- int new_mtu)
-{
- /* The flower fw reserves NFP_FLOWER_FRAME_HEADROOM bytes of the
- * supported max MTU to allow for appending tunnel headers. To prevent
- * unexpected behaviour this needs to be accounted for.
- */
- if (new_mtu > netdev->max_mtu - NFP_FLOWER_FRAME_HEADROOM) {
- nfp_err(app->cpp, "New MTU (%d) is not valid\n", new_mtu);
- return -EINVAL;
- }
-
- return 0;
-}
-
static bool nfp_flower_check_ack(struct nfp_flower_priv *app_priv)
{
bool ret;
@@ -654,7 +638,6 @@ const struct nfp_app_type app_flower = {
.init = nfp_flower_init,
.clean = nfp_flower_clean,
- .check_mtu = nfp_flower_check_mtu,
.repr_change_mtu = nfp_flower_repr_change_mtu,
.vnic_alloc = nfp_flower_vnic_alloc,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index e030b3c..c67e1b5 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -107,7 +107,10 @@ struct nfp_mtu_conf {
* @mask_table: Hash table used to store masks
* @flow_table: Hash table used to store flower rules
* @cmsg_work: Workqueue for control messages processing
- * @cmsg_skbs: List of skbs for control message processing
+ * @cmsg_skbs_high: List of higher priority skbs for control message
+ * processing
+ * @cmsg_skbs_low: List of lower priority skbs for control message
+ * processing
* @nfp_mac_off_list: List of MAC addresses to offload
* @nfp_mac_index_list: List of unique 8-bit indexes for non NFP netdevs
* @nfp_ipv4_off_list: List of IPv4 addresses to offload
@@ -136,7 +139,8 @@ struct nfp_flower_priv {
DECLARE_HASHTABLE(mask_table, NFP_FLOWER_MASK_HASH_BITS);
DECLARE_HASHTABLE(flow_table, NFP_FLOWER_HASH_BITS);
struct work_struct cmsg_work;
- struct sk_buff_head cmsg_skbs;
+ struct sk_buff_head cmsg_skbs_high;
+ struct sk_buff_head cmsg_skbs_low;
struct list_head nfp_mac_off_list;
struct list_head nfp_mac_index_list;
struct list_head nfp_ipv4_off_list;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app_nic.c b/drivers/net/ethernet/netronome/nfp/nfp_app_nic.c
index 2a2f2fb..b9618c3 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app_nic.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app_nic.c
@@ -69,7 +69,7 @@ int nfp_app_nic_vnic_alloc(struct nfp_app *app, struct nfp_net *nn,
if (err)
return err < 0 ? err : 0;
- nfp_net_get_mac_addr(app->pf, nn->port);
+ nfp_net_get_mac_addr(app->pf, nn->dp.netdev, nn->port);
return 0;
}
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.h b/drivers/net/ethernet/netronome/nfp/nfp_main.h
index add46e2..4221108 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.h
@@ -171,7 +171,9 @@ void nfp_net_pci_remove(struct nfp_pf *pf);
int nfp_hwmon_register(struct nfp_pf *pf);
void nfp_hwmon_unregister(struct nfp_pf *pf);
-void nfp_net_get_mac_addr(struct nfp_pf *pf, struct nfp_port *port);
+void
+nfp_net_get_mac_addr(struct nfp_pf *pf, struct net_device *netdev,
+ struct nfp_port *port);
bool nfp_ctrl_tx(struct nfp_net *nn, struct sk_buff *skb);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
index 15fa47f..45cd209 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
@@ -67,23 +67,26 @@
/**
* nfp_net_get_mac_addr() - Get the MAC address.
* @pf: NFP PF handle
+ * @netdev: net_device to set MAC address on
* @port: NFP port structure
*
* First try to get the MAC address from NSP ETH table. If that
* fails generate a random address.
*/
-void nfp_net_get_mac_addr(struct nfp_pf *pf, struct nfp_port *port)
+void
+nfp_net_get_mac_addr(struct nfp_pf *pf, struct net_device *netdev,
+ struct nfp_port *port)
{
struct nfp_eth_table_port *eth_port;
eth_port = __nfp_port_get_eth_port(port);
if (!eth_port) {
- eth_hw_addr_random(port->netdev);
+ eth_hw_addr_random(netdev);
return;
}
- ether_addr_copy(port->netdev->dev_addr, eth_port->mac_addr);
- ether_addr_copy(port->netdev->perm_addr, eth_port->mac_addr);
+ ether_addr_copy(netdev->dev_addr, eth_port->mac_addr);
+ ether_addr_copy(netdev->perm_addr, eth_port->mac_addr);
}
static struct nfp_eth_table_port *
@@ -511,16 +514,18 @@ static int nfp_net_pci_map_mem(struct nfp_pf *pf)
return PTR_ERR(mem);
}
- min_size = NFP_MAC_STATS_SIZE * (pf->eth_tbl->max_index + 1);
- pf->mac_stats_mem = nfp_rtsym_map(pf->rtbl, "_mac_stats",
- "net.macstats", min_size,
- &pf->mac_stats_bar);
- if (IS_ERR(pf->mac_stats_mem)) {
- if (PTR_ERR(pf->mac_stats_mem) != -ENOENT) {
- err = PTR_ERR(pf->mac_stats_mem);
- goto err_unmap_ctrl;
+ if (pf->eth_tbl) {
+ min_size = NFP_MAC_STATS_SIZE * (pf->eth_tbl->max_index + 1);
+ pf->mac_stats_mem = nfp_rtsym_map(pf->rtbl, "_mac_stats",
+ "net.macstats", min_size,
+ &pf->mac_stats_bar);
+ if (IS_ERR(pf->mac_stats_mem)) {
+ if (PTR_ERR(pf->mac_stats_mem) != -ENOENT) {
+ err = PTR_ERR(pf->mac_stats_mem);
+ goto err_unmap_ctrl;
+ }
+ pf->mac_stats_mem = NULL;
}
- pf->mac_stats_mem = NULL;
}
pf->vf_cfg_mem = nfp_net_pf_map_rtsym(pf, "net.vfcfg",
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c
index f7b9581..cb28ac0 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c
@@ -211,8 +211,11 @@ int nfp_cpp_mutex_lock(struct nfp_cpp_mutex *mutex)
break;
err = msleep_interruptible(timeout_ms);
- if (err != 0)
+ if (err != 0) {
+ nfp_info(mutex->cpp,
+ "interrupted waiting for NFP mutex\n");
return -ERESTARTSYS;
+ }
if (time_is_before_eq_jiffies(warn_at)) {
warn_at = jiffies + NFP_MUTEX_WAIT_NEXT_WARN * HZ;
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
index 99bb679..2abee0f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
@@ -281,8 +281,7 @@ nfp_nsp_wait_reg(struct nfp_cpp *cpp, u64 *reg, u32 nsp_cpp, u64 addr,
if ((*reg & mask) == val)
return 0;
- if (msleep_interruptible(25))
- return -ERESTARTSYS;
+ msleep(25);
if (time_after(start_time, wait_until))
return -ETIMEDOUT;
diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c
index 27364b75..b092894 100644
--- a/drivers/net/ethernet/ni/nixge.c
+++ b/drivers/net/ethernet/ni/nixge.c
@@ -1170,7 +1170,7 @@ static void *nixge_get_nvmem_address(struct device *dev)
cell = nvmem_cell_get(dev, "address");
if (IS_ERR(cell))
- return cell;
+ return NULL;
mac = nvmem_cell_read(cell, &cell_size);
nvmem_cell_put(cell);
@@ -1183,7 +1183,7 @@ static int nixge_probe(struct platform_device *pdev)
struct nixge_priv *priv;
struct net_device *ndev;
struct resource *dmares;
- const char *mac_addr;
+ const u8 *mac_addr;
int err;
ndev = alloc_etherdev(sizeof(*priv));
@@ -1202,10 +1202,12 @@ static int nixge_probe(struct platform_device *pdev)
ndev->max_mtu = NIXGE_JUMBO_MTU;
mac_addr = nixge_get_nvmem_address(&pdev->dev);
- if (mac_addr && is_valid_ether_addr(mac_addr))
+ if (mac_addr && is_valid_ether_addr(mac_addr)) {
ether_addr_copy(ndev->dev_addr, mac_addr);
- else
+ kfree(mac_addr);
+ } else {
eth_hw_addr_random(ndev);
+ }
priv = netdev_priv(ndev);
priv->ndev = ndev;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index 00f41c1..820b226 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -77,7 +77,7 @@
#define ILT_CFG_REG(cli, reg) PSWRQ2_REG_ ## cli ## _ ## reg ## _RT_OFFSET
/* ILT entry structure */
-#define ILT_ENTRY_PHY_ADDR_MASK 0x000FFFFFFFFFFFULL
+#define ILT_ENTRY_PHY_ADDR_MASK (~0ULL >> 12)
#define ILT_ENTRY_PHY_ADDR_SHIFT 0
#define ILT_ENTRY_VALID_MASK 0x1ULL
#define ILT_ENTRY_VALID_SHIFT 52
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index e874504..8667799d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -115,8 +115,7 @@ int qed_l2_alloc(struct qed_hwfn *p_hwfn)
void qed_l2_setup(struct qed_hwfn *p_hwfn)
{
- if (p_hwfn->hw_info.personality != QED_PCI_ETH &&
- p_hwfn->hw_info.personality != QED_PCI_ETH_ROCE)
+ if (!QED_IS_L2_PERSONALITY(p_hwfn))
return;
mutex_init(&p_hwfn->p_l2_info->lock);
@@ -126,8 +125,7 @@ void qed_l2_free(struct qed_hwfn *p_hwfn)
{
u32 i;
- if (p_hwfn->hw_info.personality != QED_PCI_ETH &&
- p_hwfn->hw_info.personality != QED_PCI_ETH_ROCE)
+ if (!QED_IS_L2_PERSONALITY(p_hwfn))
return;
if (!p_hwfn->p_l2_info)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 74fc626..468c59d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -292,6 +292,7 @@ static void qed_ll2_txq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
struct qed_ll2_tx_packet *p_pkt = NULL;
struct qed_ll2_info *p_ll2_conn;
struct qed_ll2_tx_queue *p_tx;
+ unsigned long flags = 0;
dma_addr_t tx_frag;
p_ll2_conn = qed_ll2_handle_sanity_inactive(p_hwfn, connection_handle);
@@ -300,6 +301,7 @@ static void qed_ll2_txq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
p_tx = &p_ll2_conn->tx_queue;
+ spin_lock_irqsave(&p_tx->lock, flags);
while (!list_empty(&p_tx->active_descq)) {
p_pkt = list_first_entry(&p_tx->active_descq,
struct qed_ll2_tx_packet, list_entry);
@@ -309,6 +311,7 @@ static void qed_ll2_txq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
list_del(&p_pkt->list_entry);
b_last_packet = list_empty(&p_tx->active_descq);
list_add_tail(&p_pkt->list_entry, &p_tx->free_descq);
+ spin_unlock_irqrestore(&p_tx->lock, flags);
if (p_ll2_conn->input.conn_type == QED_LL2_TYPE_OOO) {
struct qed_ooo_buffer *p_buffer;
@@ -328,7 +331,9 @@ static void qed_ll2_txq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
b_last_frag,
b_last_packet);
}
+ spin_lock_irqsave(&p_tx->lock, flags);
}
+ spin_unlock_irqrestore(&p_tx->lock, flags);
}
static int qed_ll2_txq_completion(struct qed_hwfn *p_hwfn, void *p_cookie)
@@ -556,6 +561,7 @@ static void qed_ll2_rxq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
struct qed_ll2_info *p_ll2_conn = NULL;
struct qed_ll2_rx_packet *p_pkt = NULL;
struct qed_ll2_rx_queue *p_rx;
+ unsigned long flags = 0;
p_ll2_conn = qed_ll2_handle_sanity_inactive(p_hwfn, connection_handle);
if (!p_ll2_conn)
@@ -563,13 +569,14 @@ static void qed_ll2_rxq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
p_rx = &p_ll2_conn->rx_queue;
+ spin_lock_irqsave(&p_rx->lock, flags);
while (!list_empty(&p_rx->active_descq)) {
p_pkt = list_first_entry(&p_rx->active_descq,
struct qed_ll2_rx_packet, list_entry);
if (!p_pkt)
break;
-
list_move_tail(&p_pkt->list_entry, &p_rx->free_descq);
+ spin_unlock_irqrestore(&p_rx->lock, flags);
if (p_ll2_conn->input.conn_type == QED_LL2_TYPE_OOO) {
struct qed_ooo_buffer *p_buffer;
@@ -588,7 +595,30 @@ static void qed_ll2_rxq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
cookie,
rx_buf_addr, b_last);
}
+ spin_lock_irqsave(&p_rx->lock, flags);
}
+ spin_unlock_irqrestore(&p_rx->lock, flags);
+}
+
+static bool
+qed_ll2_lb_rxq_handler_slowpath(struct qed_hwfn *p_hwfn,
+ struct core_rx_slow_path_cqe *p_cqe)
+{
+ struct ooo_opaque *iscsi_ooo;
+ u32 cid;
+
+ if (p_cqe->ramrod_cmd_id != CORE_RAMROD_RX_QUEUE_FLUSH)
+ return false;
+
+ iscsi_ooo = (struct ooo_opaque *)&p_cqe->opaque_data;
+ if (iscsi_ooo->ooo_opcode != TCP_EVENT_DELETE_ISLES)
+ return false;
+
+ /* Need to make a flush */
+ cid = le32_to_cpu(iscsi_ooo->cid);
+ qed_ooo_release_connection_isles(p_hwfn, p_hwfn->p_ooo_info, cid);
+
+ return true;
}
static int qed_ll2_lb_rxq_handler(struct qed_hwfn *p_hwfn,
@@ -617,6 +647,11 @@ static int qed_ll2_lb_rxq_handler(struct qed_hwfn *p_hwfn,
cq_old_idx = qed_chain_get_cons_idx(&p_rx->rcq_chain);
cqe_type = cqe->rx_cqe_sp.type;
+ if (cqe_type == CORE_RX_CQE_TYPE_SLOW_PATH)
+ if (qed_ll2_lb_rxq_handler_slowpath(p_hwfn,
+ &cqe->rx_cqe_sp))
+ continue;
+
if (cqe_type != CORE_RX_CQE_TYPE_REGULAR) {
DP_NOTICE(p_hwfn,
"Got a non-regular LB LL2 completion [type 0x%02x]\n",
@@ -794,6 +829,9 @@ static int qed_ll2_lb_rxq_completion(struct qed_hwfn *p_hwfn, void *p_cookie)
struct qed_ll2_info *p_ll2_conn = (struct qed_ll2_info *)p_cookie;
int rc;
+ if (!QED_LL2_RX_REGISTERED(p_ll2_conn))
+ return 0;
+
rc = qed_ll2_lb_rxq_handler(p_hwfn, p_ll2_conn);
if (rc)
return rc;
@@ -814,6 +852,9 @@ static int qed_ll2_lb_txq_completion(struct qed_hwfn *p_hwfn, void *p_cookie)
u16 new_idx = 0, num_bds = 0;
int rc;
+ if (!QED_LL2_TX_REGISTERED(p_ll2_conn))
+ return 0;
+
new_idx = le16_to_cpu(*p_tx->p_fw_cons);
num_bds = ((s16)new_idx - (s16)p_tx->bds_idx);
@@ -1867,17 +1908,25 @@ int qed_ll2_terminate_connection(void *cxt, u8 connection_handle)
/* Stop Tx & Rx of connection, if needed */
if (QED_LL2_TX_REGISTERED(p_ll2_conn)) {
+ p_ll2_conn->tx_queue.b_cb_registred = false;
+ smp_wmb(); /* Make sure this is seen by ll2_lb_rxq_completion */
rc = qed_sp_ll2_tx_queue_stop(p_hwfn, p_ll2_conn);
if (rc)
goto out;
+
qed_ll2_txq_flush(p_hwfn, connection_handle);
+ qed_int_unregister_cb(p_hwfn, p_ll2_conn->tx_queue.tx_sb_index);
}
if (QED_LL2_RX_REGISTERED(p_ll2_conn)) {
+ p_ll2_conn->rx_queue.b_cb_registred = false;
+ smp_wmb(); /* Make sure this is seen by ll2_lb_rxq_completion */
rc = qed_sp_ll2_rx_queue_stop(p_hwfn, p_ll2_conn);
if (rc)
goto out;
+
qed_ll2_rxq_flush(p_hwfn, connection_handle);
+ qed_int_unregister_cb(p_hwfn, p_ll2_conn->rx_queue.rx_sb_index);
}
if (p_ll2_conn->input.conn_type == QED_LL2_TYPE_OOO)
@@ -1925,16 +1974,6 @@ void qed_ll2_release_connection(void *cxt, u8 connection_handle)
if (!p_ll2_conn)
return;
- if (QED_LL2_RX_REGISTERED(p_ll2_conn)) {
- p_ll2_conn->rx_queue.b_cb_registred = false;
- qed_int_unregister_cb(p_hwfn, p_ll2_conn->rx_queue.rx_sb_index);
- }
-
- if (QED_LL2_TX_REGISTERED(p_ll2_conn)) {
- p_ll2_conn->tx_queue.b_cb_registred = false;
- qed_int_unregister_cb(p_hwfn, p_ll2_conn->tx_queue.tx_sb_index);
- }
-
kfree(p_ll2_conn->tx_queue.descq_mem);
qed_chain_free(p_hwfn->cdev, &p_ll2_conn->tx_queue.txq_chain);
@@ -2370,7 +2409,7 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb)
u8 flags = 0;
if (unlikely(skb->ip_summed != CHECKSUM_NONE)) {
- DP_INFO(cdev, "Cannot transmit a checksumed packet\n");
+ DP_INFO(cdev, "Cannot transmit a checksummed packet\n");
return -EINVAL;
}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 9854aa9..7870ae2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -680,7 +680,7 @@ static int qed_nic_stop(struct qed_dev *cdev)
tasklet_disable(p_hwfn->sp_dpc);
p_hwfn->b_sp_dpc_enabled = false;
DP_VERBOSE(cdev, NETIF_MSG_IFDOWN,
- "Disabled sp taskelt [hwfn %d] at %p\n",
+ "Disabled sp tasklet [hwfn %d] at %p\n",
i, p_hwfn->sp_dpc);
}
}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index fb7c2d1..6acfd43 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -848,7 +848,7 @@ int qed_roce_query_qp(struct qed_hwfn *p_hwfn,
if (!(qp->resp_offloaded)) {
DP_NOTICE(p_hwfn,
- "The responder's qp should be offloded before requester's\n");
+ "The responder's qp should be offloaded before requester's\n");
return -EINVAL;
}
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index a01e7d6..f6655e2 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1066,13 +1066,12 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
DP_INFO(edev, "Starting qede_remove\n");
+ qede_rdma_dev_remove(edev);
unregister_netdev(ndev);
cancel_delayed_work_sync(&edev->sp_task);
qede_ptp_disable(edev);
- qede_rdma_dev_remove(edev);
-
edev->ops->common->set_power_state(cdev, PCI_D0);
pci_set_drvdata(pdev, NULL);
diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
index 50b142f..1900bf7 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
@@ -238,7 +238,7 @@ qede_rdma_get_free_event_node(struct qede_dev *edev)
}
if (!found) {
- event_node = kzalloc(sizeof(*event_node), GFP_KERNEL);
+ event_node = kzalloc(sizeof(*event_node), GFP_ATOMIC);
if (!event_node) {
DP_NOTICE(edev,
"qedr: Could not allocate memory for rdma work\n");
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index d339885..5f4e447 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -350,15 +350,16 @@ static int rmnet_fill_info(struct sk_buff *skb, const struct net_device *dev)
real_dev = priv->real_dev;
- if (!rmnet_is_real_dev_registered(real_dev))
- return -ENODEV;
-
if (nla_put_u16(skb, IFLA_RMNET_MUX_ID, priv->mux_id))
goto nla_put_failure;
- port = rmnet_get_port_rtnl(real_dev);
+ if (rmnet_is_real_dev_registered(real_dev)) {
+ port = rmnet_get_port_rtnl(real_dev);
+ f.flags = port->data_format;
+ } else {
+ f.flags = 0;
+ }
- f.flags = port->data_format;
f.mask = ~0;
if (nla_put(skb, IFLA_RMNET_FLAGS, sizeof(f), &f))
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index d24b47b..d118da5 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -2224,7 +2224,7 @@ static void rtl8139_poll_controller(struct net_device *dev)
struct rtl8139_private *tp = netdev_priv(dev);
const int irq = tp->pci_dev->irq;
- disable_irq(irq);
+ disable_irq_nosync(irq);
rtl8139_interrupt(irq, dev);
enable_irq(irq);
}
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 604ae78..c7aac1f 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -4981,6 +4981,9 @@ static void rtl_pll_power_down(struct rtl8169_private *tp)
static void rtl_pll_power_up(struct rtl8169_private *tp)
{
rtl_generic_op(tp, tp->pll_power_ops.up);
+
+ /* give MAC/PHY some time to resume */
+ msleep(20);
}
static void rtl_init_pll_power_ops(struct rtl8169_private *tp)
diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
index a5b792c..1bf930d 100644
--- a/drivers/net/ethernet/renesas/sh_eth.h
+++ b/drivers/net/ethernet/renesas/sh_eth.h
@@ -163,7 +163,7 @@ enum {
};
/* Driver's parameters */
-#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_SHMOBILE)
+#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_RENESAS)
#define SH_ETH_RX_ALIGN 32
#else
#define SH_ETH_RX_ALIGN 2
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 50daad0..d90a7b1 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -3999,29 +3999,6 @@ static void efx_ef10_prepare_flr(struct efx_nic *efx)
atomic_set(&efx->active_queues, 0);
}
-static bool efx_ef10_filter_equal(const struct efx_filter_spec *left,
- const struct efx_filter_spec *right)
-{
- if ((left->match_flags ^ right->match_flags) |
- ((left->flags ^ right->flags) &
- (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX)))
- return false;
-
- return memcmp(&left->outer_vid, &right->outer_vid,
- sizeof(struct efx_filter_spec) -
- offsetof(struct efx_filter_spec, outer_vid)) == 0;
-}
-
-static unsigned int efx_ef10_filter_hash(const struct efx_filter_spec *spec)
-{
- BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3);
- return jhash2((const u32 *)&spec->outer_vid,
- (sizeof(struct efx_filter_spec) -
- offsetof(struct efx_filter_spec, outer_vid)) / 4,
- 0);
- /* XXX should we randomise the initval? */
-}
-
/* Decide whether a filter should be exclusive or else should allow
* delivery to additional recipients. Currently we decide that
* filters for specific local unicast MAC and IP addresses are
@@ -4346,7 +4323,7 @@ static s32 efx_ef10_filter_insert(struct efx_nic *efx,
goto out_unlock;
match_pri = rc;
- hash = efx_ef10_filter_hash(spec);
+ hash = efx_filter_spec_hash(spec);
is_mc_recip = efx_filter_is_mc_recipient(spec);
if (is_mc_recip)
bitmap_zero(mc_rem_map, EFX_EF10_FILTER_SEARCH_LIMIT);
@@ -4378,7 +4355,7 @@ static s32 efx_ef10_filter_insert(struct efx_nic *efx,
if (!saved_spec) {
if (ins_index < 0)
ins_index = i;
- } else if (efx_ef10_filter_equal(spec, saved_spec)) {
+ } else if (efx_filter_spec_equal(spec, saved_spec)) {
if (spec->priority < saved_spec->priority &&
spec->priority != EFX_FILTER_PRI_AUTO) {
rc = -EPERM;
@@ -4762,28 +4739,63 @@ static s32 efx_ef10_filter_get_rx_ids(struct efx_nic *efx,
static bool efx_ef10_filter_rfs_expire_one(struct efx_nic *efx, u32 flow_id,
unsigned int filter_idx)
{
+ struct efx_filter_spec *spec, saved_spec;
struct efx_ef10_filter_table *table;
- struct efx_filter_spec *spec;
- bool ret;
+ struct efx_arfs_rule *rule = NULL;
+ bool ret = true, force = false;
+ u16 arfs_id;
down_read(&efx->filter_sem);
table = efx->filter_state;
down_write(&table->lock);
spec = efx_ef10_filter_entry_spec(table, filter_idx);
- if (!spec || spec->priority != EFX_FILTER_PRI_HINT) {
- ret = true;
+ if (!spec || spec->priority != EFX_FILTER_PRI_HINT)
goto out_unlock;
- }
- if (!rps_may_expire_flow(efx->net_dev, spec->dmaq_id,
- flow_id, filter_idx)) {
+ spin_lock_bh(&efx->rps_hash_lock);
+ if (!efx->rps_hash_table) {
+ /* In the absence of the table, we always return 0 to ARFS. */
+ arfs_id = 0;
+ } else {
+ rule = efx_rps_hash_find(efx, spec);
+ if (!rule)
+ /* ARFS table doesn't know of this filter, so remove it */
+ goto expire;
+ arfs_id = rule->arfs_id;
+ ret = efx_rps_check_rule(rule, filter_idx, &force);
+ if (force)
+ goto expire;
+ if (!ret) {
+ spin_unlock_bh(&efx->rps_hash_lock);
+ goto out_unlock;
+ }
+ }
+ if (!rps_may_expire_flow(efx->net_dev, spec->dmaq_id, flow_id, arfs_id))
ret = false;
- goto out_unlock;
+ else if (rule)
+ rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING;
+expire:
+ saved_spec = *spec; /* remove operation will kfree spec */
+ spin_unlock_bh(&efx->rps_hash_lock);
+ /* At this point (since we dropped the lock), another thread might queue
+ * up a fresh insertion request (but the actual insertion will be held
+ * up by our possession of the filter table lock). In that case, it
+ * will set rule->filter_id to EFX_ARFS_FILTER_ID_PENDING, meaning that
+ * the rule is not removed by efx_rps_hash_del() below.
+ */
+ if (ret)
+ ret = efx_ef10_filter_remove_internal(efx, 1U << spec->priority,
+ filter_idx, true) == 0;
+ /* While we can't safely dereference rule (we dropped the lock), we can
+ * still test it for NULL.
+ */
+ if (ret && rule) {
+ /* Expiring, so remove entry from ARFS table */
+ spin_lock_bh(&efx->rps_hash_lock);
+ efx_rps_hash_del(efx, &saved_spec);
+ spin_unlock_bh(&efx->rps_hash_lock);
}
-
- ret = efx_ef10_filter_remove_internal(efx, 1U << spec->priority,
- filter_idx, true) == 0;
out_unlock:
up_write(&table->lock);
up_read(&efx->filter_sem);
@@ -5265,7 +5277,7 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx,
ids = vlan->uc;
}
- filter_flags = efx_rss_enabled(efx) ? EFX_FILTER_FLAG_RX_RSS : 0;
+ filter_flags = efx_rss_active(&efx->rss_context) ? EFX_FILTER_FLAG_RX_RSS : 0;
/* Insert/renew filters */
for (i = 0; i < addr_count; i++) {
@@ -5334,7 +5346,7 @@ static int efx_ef10_filter_insert_def(struct efx_nic *efx,
int rc;
u16 *id;
- filter_flags = efx_rss_enabled(efx) ? EFX_FILTER_FLAG_RX_RSS : 0;
+ filter_flags = efx_rss_active(&efx->rss_context) ? EFX_FILTER_FLAG_RX_RSS : 0;
efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0);
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 692dd72..661828e 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1289,9 +1289,8 @@ static int efx_init_io(struct efx_nic *efx)
pci_set_master(pci_dev);
- /* Set the PCI DMA mask. Try all possibilities from our
- * genuine mask down to 32 bits, because some architectures
- * (e.g. x86_64 with iommu_sac_force set) will allow 40 bit
+ /* Set the PCI DMA mask. Try all possibilities from our genuine mask
+ * down to 32 bits, because some architectures will allow 40 bit
* masks event though they reject 46 bit masks.
*/
while (dma_mask > 0x7fffffffUL) {
@@ -3027,6 +3026,10 @@ static int efx_init_struct(struct efx_nic *efx,
mutex_init(&efx->mac_lock);
#ifdef CONFIG_RFS_ACCEL
mutex_init(&efx->rps_mutex);
+ spin_lock_init(&efx->rps_hash_lock);
+ /* Failure to allocate is not fatal, but may degrade ARFS performance */
+ efx->rps_hash_table = kcalloc(EFX_ARFS_HASH_TABLE_SIZE,
+ sizeof(*efx->rps_hash_table), GFP_KERNEL);
#endif
efx->phy_op = &efx_dummy_phy_operations;
efx->mdio.dev = net_dev;
@@ -3070,6 +3073,10 @@ static void efx_fini_struct(struct efx_nic *efx)
{
int i;
+#ifdef CONFIG_RFS_ACCEL
+ kfree(efx->rps_hash_table);
+#endif
+
for (i = 0; i < EFX_MAX_CHANNELS; i++)
kfree(efx->channel[i]);
@@ -3092,6 +3099,141 @@ void efx_update_sw_stats(struct efx_nic *efx, u64 *stats)
stats[GENERIC_STAT_rx_noskb_drops] = atomic_read(&efx->n_rx_noskb_drops);
}
+bool efx_filter_spec_equal(const struct efx_filter_spec *left,
+ const struct efx_filter_spec *right)
+{
+ if ((left->match_flags ^ right->match_flags) |
+ ((left->flags ^ right->flags) &
+ (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX)))
+ return false;
+
+ return memcmp(&left->outer_vid, &right->outer_vid,
+ sizeof(struct efx_filter_spec) -
+ offsetof(struct efx_filter_spec, outer_vid)) == 0;
+}
+
+u32 efx_filter_spec_hash(const struct efx_filter_spec *spec)
+{
+ BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3);
+ return jhash2((const u32 *)&spec->outer_vid,
+ (sizeof(struct efx_filter_spec) -
+ offsetof(struct efx_filter_spec, outer_vid)) / 4,
+ 0);
+}
+
+#ifdef CONFIG_RFS_ACCEL
+bool efx_rps_check_rule(struct efx_arfs_rule *rule, unsigned int filter_idx,
+ bool *force)
+{
+ if (rule->filter_id == EFX_ARFS_FILTER_ID_PENDING) {
+ /* ARFS is currently updating this entry, leave it */
+ return false;
+ }
+ if (rule->filter_id == EFX_ARFS_FILTER_ID_ERROR) {
+ /* ARFS tried and failed to update this, so it's probably out
+ * of date. Remove the filter and the ARFS rule entry.
+ */
+ rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING;
+ *force = true;
+ return true;
+ } else if (WARN_ON(rule->filter_id != filter_idx)) { /* can't happen */
+ /* ARFS has moved on, so old filter is not needed. Since we did
+ * not mark the rule with EFX_ARFS_FILTER_ID_REMOVING, it will
+ * not be removed by efx_rps_hash_del() subsequently.
+ */
+ *force = true;
+ return true;
+ }
+ /* Remove it iff ARFS wants to. */
+ return true;
+}
+
+struct hlist_head *efx_rps_hash_bucket(struct efx_nic *efx,
+ const struct efx_filter_spec *spec)
+{
+ u32 hash = efx_filter_spec_hash(spec);
+
+ WARN_ON(!spin_is_locked(&efx->rps_hash_lock));
+ if (!efx->rps_hash_table)
+ return NULL;
+ return &efx->rps_hash_table[hash % EFX_ARFS_HASH_TABLE_SIZE];
+}
+
+struct efx_arfs_rule *efx_rps_hash_find(struct efx_nic *efx,
+ const struct efx_filter_spec *spec)
+{
+ struct efx_arfs_rule *rule;
+ struct hlist_head *head;
+ struct hlist_node *node;
+
+ head = efx_rps_hash_bucket(efx, spec);
+ if (!head)
+ return NULL;
+ hlist_for_each(node, head) {
+ rule = container_of(node, struct efx_arfs_rule, node);
+ if (efx_filter_spec_equal(spec, &rule->spec))
+ return rule;
+ }
+ return NULL;
+}
+
+struct efx_arfs_rule *efx_rps_hash_add(struct efx_nic *efx,
+ const struct efx_filter_spec *spec,
+ bool *new)
+{
+ struct efx_arfs_rule *rule;
+ struct hlist_head *head;
+ struct hlist_node *node;
+
+ head = efx_rps_hash_bucket(efx, spec);
+ if (!head)
+ return NULL;
+ hlist_for_each(node, head) {
+ rule = container_of(node, struct efx_arfs_rule, node);
+ if (efx_filter_spec_equal(spec, &rule->spec)) {
+ *new = false;
+ return rule;
+ }
+ }
+ rule = kmalloc(sizeof(*rule), GFP_ATOMIC);
+ *new = true;
+ if (rule) {
+ memcpy(&rule->spec, spec, sizeof(rule->spec));
+ hlist_add_head(&rule->node, head);
+ }
+ return rule;
+}
+
+void efx_rps_hash_del(struct efx_nic *efx, const struct efx_filter_spec *spec)
+{
+ struct efx_arfs_rule *rule;
+ struct hlist_head *head;
+ struct hlist_node *node;
+
+ head = efx_rps_hash_bucket(efx, spec);
+ if (WARN_ON(!head))
+ return;
+ hlist_for_each(node, head) {
+ rule = container_of(node, struct efx_arfs_rule, node);
+ if (efx_filter_spec_equal(spec, &rule->spec)) {
+ /* Someone already reused the entry. We know that if
+ * this check doesn't fire (i.e. filter_id == REMOVING)
+ * then the REMOVING mark was put there by our caller,
+ * because caller is holding a lock on filter table and
+ * only holders of that lock set REMOVING.
+ */
+ if (rule->filter_id != EFX_ARFS_FILTER_ID_REMOVING)
+ return;
+ hlist_del(node);
+ kfree(rule);
+ return;
+ }
+ }
+ /* We didn't find it. */
+ WARN_ON(1);
+}
+#endif
+
/* RSS contexts. We're using linked lists and crappy O(n) algorithms, because
* (a) this is an infrequent control-plane operation and (b) n is small (max 64)
*/
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index a3140e1..3f759eb 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -186,6 +186,27 @@ static inline void efx_filter_rfs_expire(struct work_struct *data) {}
#endif
bool efx_filter_is_mc_recipient(const struct efx_filter_spec *spec);
+bool efx_filter_spec_equal(const struct efx_filter_spec *left,
+ const struct efx_filter_spec *right);
+u32 efx_filter_spec_hash(const struct efx_filter_spec *spec);
+
+#ifdef CONFIG_RFS_ACCEL
+bool efx_rps_check_rule(struct efx_arfs_rule *rule, unsigned int filter_idx,
+ bool *force);
+
+struct efx_arfs_rule *efx_rps_hash_find(struct efx_nic *efx,
+ const struct efx_filter_spec *spec);
+
+/* @new is written to indicate if entry was newly added (true) or if an old
+ * entry was found and returned (false).
+ */
+struct efx_arfs_rule *efx_rps_hash_add(struct efx_nic *efx,
+ const struct efx_filter_spec *spec,
+ bool *new);
+
+void efx_rps_hash_del(struct efx_nic *efx, const struct efx_filter_spec *spec);
+#endif
+
/* RSS contexts */
struct efx_rss_context *efx_alloc_rss_context_entry(struct efx_nic *efx);
struct efx_rss_context *efx_find_rss_context_entry(struct efx_nic *efx, u32 id);
diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c
index 3d6c91e..dd5530a 100644
--- a/drivers/net/ethernet/sfc/falcon/efx.c
+++ b/drivers/net/ethernet/sfc/falcon/efx.c
@@ -1242,9 +1242,8 @@ static int ef4_init_io(struct ef4_nic *efx)
pci_set_master(pci_dev);
- /* Set the PCI DMA mask. Try all possibilities from our
- * genuine mask down to 32 bits, because some architectures
- * (e.g. x86_64 with iommu_sac_force set) will allow 40 bit
+ /* Set the PCI DMA mask. Try all possibilities from our genuine mask
+ * down to 32 bits, because some architectures will allow 40 bit
* masks event though they reject 46 bit masks.
*/
while (dma_mask > 0x7fffffffUL) {
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index 4a19c7e..c72adf8 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -2905,18 +2905,45 @@ bool efx_farch_filter_rfs_expire_one(struct efx_nic *efx, u32 flow_id,
{
struct efx_farch_filter_state *state = efx->filter_state;
struct efx_farch_filter_table *table;
- bool ret = false;
+ bool ret = false, force = false;
+ u16 arfs_id;
down_write(&state->lock);
+ spin_lock_bh(&efx->rps_hash_lock);
table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP];
if (test_bit(index, table->used_bitmap) &&
- table->spec[index].priority == EFX_FILTER_PRI_HINT &&
- rps_may_expire_flow(efx->net_dev, table->spec[index].dmaq_id,
- flow_id, index)) {
- efx_farch_filter_table_clear_entry(efx, table, index);
- ret = true;
- }
+ table->spec[index].priority == EFX_FILTER_PRI_HINT) {
+ struct efx_arfs_rule *rule = NULL;
+ struct efx_filter_spec spec;
+ efx_farch_filter_to_gen_spec(&spec, &table->spec[index]);
+ if (!efx->rps_hash_table) {
+ /* In the absence of the table, we always returned 0 to
+ * ARFS, so use the same to query it.
+ */
+ arfs_id = 0;
+ } else {
+ rule = efx_rps_hash_find(efx, &spec);
+ if (!rule) {
+ /* ARFS table doesn't know of this filter, remove it */
+ force = true;
+ } else {
+ arfs_id = rule->arfs_id;
+ if (!efx_rps_check_rule(rule, index, &force))
+ goto out_unlock;
+ }
+ }
+ if (force || rps_may_expire_flow(efx->net_dev, spec.dmaq_id,
+ flow_id, arfs_id)) {
+ if (rule)
+ rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING;
+ efx_rps_hash_del(efx, &spec);
+ efx_farch_filter_table_clear_entry(efx, table, index);
+ ret = true;
+ }
+ }
+out_unlock:
+ spin_unlock_bh(&efx->rps_hash_lock);
up_write(&state->lock);
return ret;
}
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 5e379a8..6556892 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -733,6 +733,56 @@ struct efx_rss_context {
u32 rx_indir_table[128];
};
+#ifdef CONFIG_RFS_ACCEL
+/* Order of these is important, since filter_id >= %EFX_ARFS_FILTER_ID_PENDING
+ * is used to test if filter does or will exist.
+ */
+#define EFX_ARFS_FILTER_ID_PENDING -1
+#define EFX_ARFS_FILTER_ID_ERROR -2
+#define EFX_ARFS_FILTER_ID_REMOVING -3
+/**
+ * struct efx_arfs_rule - record of an ARFS filter and its IDs
+ * @node: linkage into hash table
+ * @spec: details of the filter (used as key for hash table). Use efx->type to
+ * determine which member to use.
+ * @rxq_index: channel to which the filter will steer traffic.
+ * @arfs_id: filter ID which was returned to ARFS
+ * @filter_id: index in software filter table. May be
+ * %EFX_ARFS_FILTER_ID_PENDING if filter was not inserted yet,
+ * %EFX_ARFS_FILTER_ID_ERROR if filter insertion failed, or
+ * %EFX_ARFS_FILTER_ID_REMOVING if expiry is currently removing the filter.
+ */
+struct efx_arfs_rule {
+ struct hlist_node node;
+ struct efx_filter_spec spec;
+ u16 rxq_index;
+ u16 arfs_id;
+ s32 filter_id;
+};
+
+/* Size chosen so that the table is one page (4kB) */
+#define EFX_ARFS_HASH_TABLE_SIZE 512
+
+/**
+ * struct efx_async_filter_insertion - Request to asynchronously insert a filter
+ * @net_dev: Reference to the netdevice
+ * @spec: The filter to insert
+ * @work: Workitem for this request
+ * @rxq_index: Identifies the channel for which this request was made
+ * @flow_id: Identifies the kernel-side flow for which this request was made
+ */
+struct efx_async_filter_insertion {
+ struct net_device *net_dev;
+ struct efx_filter_spec spec;
+ struct work_struct work;
+ u16 rxq_index;
+ u32 flow_id;
+};
+
+/* Maximum number of ARFS workitems that may be in flight on an efx_nic */
+#define EFX_RPS_MAX_IN_FLIGHT 8
+#endif /* CONFIG_RFS_ACCEL */
+
/**
* struct efx_nic - an Efx NIC
* @name: Device name (net device name or bus id before net device registered)
@@ -850,6 +900,12 @@ struct efx_rss_context {
* @rps_expire_channel: Next channel to check for expiry
* @rps_expire_index: Next index to check for expiry in
* @rps_expire_channel's @rps_flow_id
+ * @rps_slot_map: bitmap of in-flight entries in @rps_slot
+ * @rps_slot: array of ARFS insertion requests for efx_filter_rfs_work()
+ * @rps_hash_lock: Protects ARFS filter mapping state (@rps_hash_table and
+ * @rps_next_id).
+ * @rps_hash_table: Mapping between ARFS filters and their various IDs
+ * @rps_next_id: next arfs_id for an ARFS filter
* @active_queues: Count of RX and TX queues that haven't been flushed and drained.
* @rxq_flush_pending: Count of number of receive queues that need to be flushed.
* Decremented when the efx_flush_rx_queue() is called.
@@ -1004,6 +1060,11 @@ struct efx_nic {
struct mutex rps_mutex;
unsigned int rps_expire_channel;
unsigned int rps_expire_index;
+ unsigned long rps_slot_map;
+ struct efx_async_filter_insertion rps_slot[EFX_RPS_MAX_IN_FLIGHT];
+ spinlock_t rps_hash_lock;
+ struct hlist_head *rps_hash_table;
+ u32 rps_next_id;
#endif
atomic_t active_queues;
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 9568283..d2e254f 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -827,31 +827,38 @@ MODULE_PARM_DESC(rx_refill_threshold,
#ifdef CONFIG_RFS_ACCEL
-/**
- * struct efx_async_filter_insertion - Request to asynchronously insert a filter
- * @net_dev: Reference to the netdevice
- * @spec: The filter to insert
- * @work: Workitem for this request
- * @rxq_index: Identifies the channel for which this request was made
- * @flow_id: Identifies the kernel-side flow for which this request was made
- */
-struct efx_async_filter_insertion {
- struct net_device *net_dev;
- struct efx_filter_spec spec;
- struct work_struct work;
- u16 rxq_index;
- u32 flow_id;
-};
-
static void efx_filter_rfs_work(struct work_struct *data)
{
struct efx_async_filter_insertion *req = container_of(data, struct efx_async_filter_insertion,
work);
struct efx_nic *efx = netdev_priv(req->net_dev);
struct efx_channel *channel = efx_get_channel(efx, req->rxq_index);
+ int slot_idx = req - efx->rps_slot;
+ struct efx_arfs_rule *rule;
+ u16 arfs_id = 0;
int rc;
- rc = efx->type->filter_insert(efx, &req->spec, false);
+ rc = efx->type->filter_insert(efx, &req->spec, true);
+ if (rc >= 0)
+ rc %= efx->type->max_rx_ip_filters;
+ if (efx->rps_hash_table) {
+ spin_lock_bh(&efx->rps_hash_lock);
+ rule = efx_rps_hash_find(efx, &req->spec);
+ /* The rule might have already gone, if someone else's request
+ * for the same spec was already worked and then expired before
+ * we got around to our work. In that case we have nothing
+ * tying us to an arfs_id, meaning that as soon as the filter
+ * is considered for expiry it will be removed.
+ */
+ if (rule) {
+ if (rc < 0)
+ rule->filter_id = EFX_ARFS_FILTER_ID_ERROR;
+ else
+ rule->filter_id = rc;
+ arfs_id = rule->arfs_id;
+ }
+ spin_unlock_bh(&efx->rps_hash_lock);
+ }
if (rc >= 0) {
/* Remember this so we can check whether to expire the filter
* later.
@@ -863,23 +870,23 @@ static void efx_filter_rfs_work(struct work_struct *data)
if (req->spec.ether_type == htons(ETH_P_IP))
netif_info(efx, rx_status, efx->net_dev,
- "steering %s %pI4:%u:%pI4:%u to queue %u [flow %u filter %d]\n",
+ "steering %s %pI4:%u:%pI4:%u to queue %u [flow %u filter %d id %u]\n",
(req->spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP",
req->spec.rem_host, ntohs(req->spec.rem_port),
req->spec.loc_host, ntohs(req->spec.loc_port),
- req->rxq_index, req->flow_id, rc);
+ req->rxq_index, req->flow_id, rc, arfs_id);
else
netif_info(efx, rx_status, efx->net_dev,
- "steering %s [%pI6]:%u:[%pI6]:%u to queue %u [flow %u filter %d]\n",
+ "steering %s [%pI6]:%u:[%pI6]:%u to queue %u [flow %u filter %d id %u]\n",
(req->spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP",
req->spec.rem_host, ntohs(req->spec.rem_port),
req->spec.loc_host, ntohs(req->spec.loc_port),
- req->rxq_index, req->flow_id, rc);
+ req->rxq_index, req->flow_id, rc, arfs_id);
}
/* Release references */
+ clear_bit(slot_idx, &efx->rps_slot_map);
dev_put(req->net_dev);
- kfree(req);
}
int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
@@ -887,23 +894,39 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
{
struct efx_nic *efx = netdev_priv(net_dev);
struct efx_async_filter_insertion *req;
+ struct efx_arfs_rule *rule;
struct flow_keys fk;
+ int slot_idx;
+ bool new;
+ int rc;
- if (flow_id == RPS_FLOW_ID_INVALID)
- return -EINVAL;
+ /* find a free slot */
+ for (slot_idx = 0; slot_idx < EFX_RPS_MAX_IN_FLIGHT; slot_idx++)
+ if (!test_and_set_bit(slot_idx, &efx->rps_slot_map))
+ break;
+ if (slot_idx >= EFX_RPS_MAX_IN_FLIGHT)
+ return -EBUSY;
- if (!skb_flow_dissect_flow_keys(skb, &fk, 0))
- return -EPROTONOSUPPORT;
+ if (flow_id == RPS_FLOW_ID_INVALID) {
+ rc = -EINVAL;
+ goto out_clear;
+ }
- if (fk.basic.n_proto != htons(ETH_P_IP) && fk.basic.n_proto != htons(ETH_P_IPV6))
- return -EPROTONOSUPPORT;
- if (fk.control.flags & FLOW_DIS_IS_FRAGMENT)
- return -EPROTONOSUPPORT;
+ if (!skb_flow_dissect_flow_keys(skb, &fk, 0)) {
+ rc = -EPROTONOSUPPORT;
+ goto out_clear;
+ }
- req = kmalloc(sizeof(*req), GFP_ATOMIC);
- if (!req)
- return -ENOMEM;
+ if (fk.basic.n_proto != htons(ETH_P_IP) && fk.basic.n_proto != htons(ETH_P_IPV6)) {
+ rc = -EPROTONOSUPPORT;
+ goto out_clear;
+ }
+ if (fk.control.flags & FLOW_DIS_IS_FRAGMENT) {
+ rc = -EPROTONOSUPPORT;
+ goto out_clear;
+ }
+ req = efx->rps_slot + slot_idx;
efx_filter_init_rx(&req->spec, EFX_FILTER_PRI_HINT,
efx->rx_scatter ? EFX_FILTER_FLAG_RX_SCATTER : 0,
rxq_index);
@@ -927,12 +950,45 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
req->spec.rem_port = fk.ports.src;
req->spec.loc_port = fk.ports.dst;
+ if (efx->rps_hash_table) {
+ /* Add it to ARFS hash table */
+ spin_lock(&efx->rps_hash_lock);
+ rule = efx_rps_hash_add(efx, &req->spec, &new);
+ if (!rule) {
+ rc = -ENOMEM;
+ goto out_unlock;
+ }
+ if (new)
+ rule->arfs_id = efx->rps_next_id++ % RPS_NO_FILTER;
+ rc = rule->arfs_id;
+ /* Skip if existing or pending filter already does the right thing */
+ if (!new && rule->rxq_index == rxq_index &&
+ rule->filter_id >= EFX_ARFS_FILTER_ID_PENDING)
+ goto out_unlock;
+ rule->rxq_index = rxq_index;
+ rule->filter_id = EFX_ARFS_FILTER_ID_PENDING;
+ spin_unlock(&efx->rps_hash_lock);
+ } else {
+ /* Without an ARFS hash table, we just use arfs_id 0 for all
+ * filters. This means if multiple flows hash to the same
+ * flow_id, all but the most recently touched will be eligible
+ * for expiry.
+ */
+ rc = 0;
+ }
+
+ /* Queue the request */
dev_hold(req->net_dev = net_dev);
INIT_WORK(&req->work, efx_filter_rfs_work);
req->rxq_index = rxq_index;
req->flow_id = flow_id;
schedule_work(&req->work);
- return 0;
+ return rc;
+out_unlock:
+ spin_unlock(&efx->rps_hash_lock);
+out_clear:
+ clear_bit(slot_idx, &efx->rps_slot_map);
+ return rc;
}
bool __efx_filter_rfs_expire(struct efx_nic *efx, unsigned int quota)
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index f4c0b02..59fbf74 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -1674,8 +1674,8 @@ static int netsec_probe(struct platform_device *pdev)
if (ret)
goto unreg_napi;
- if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)))
- dev_warn(&pdev->dev, "Failed to enable 64-bit DMA\n");
+ if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40)))
+ dev_warn(&pdev->dev, "Failed to set DMA mask\n");
ret = register_netdev(ndev);
if (ret) {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index c7bff59..dedd406 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -347,7 +347,7 @@ enum power_event {
#define MTL_RX_OVERFLOW_INT BIT(16)
/* Default operating mode of the MAC */
-#define GMAC_CORE_INIT (GMAC_CONFIG_JD | GMAC_CONFIG_PS | GMAC_CONFIG_ACS | \
+#define GMAC_CORE_INIT (GMAC_CONFIG_JD | GMAC_CONFIG_PS | \
GMAC_CONFIG_BE | GMAC_CONFIG_DCRS)
/* To dump the core regs excluding the Address Registers */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index a3af92e..517b1f6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -31,13 +31,6 @@ static void dwmac4_core_init(struct mac_device_info *hw,
value |= GMAC_CORE_INIT;
- /* Clear ACS bit because Ethernet switch tagging formats such as
- * Broadcom tags can look like invalid LLC/SNAP packets and cause the
- * hardware to truncate packets on reception.
- */
- if (netdev_uses_dsa(dev))
- value &= ~GMAC_CONFIG_ACS;
-
if (mtu > 1500)
value |= GMAC_CONFIG_2K;
if (mtu > 2000)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 9a16931..b65e2d1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3495,8 +3495,13 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
/* ACS is set; GMAC core strips PAD/FCS for IEEE 802.3
* Type frames (LLC/LLC-SNAP)
+ *
+ * llc_snap is never checked in GMAC >= 4, so this ACS
+ * feature is always disabled and packets need to be
+ * stripped manually.
*/
- if (unlikely(status != llc_snap))
+ if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00) ||
+ unlikely(status != llc_snap))
frame_len -= ETH_FCS_LEN;
if (netif_msg_rx_status(priv)) {
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index f081de4..88c1247 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -3443,7 +3443,7 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np,
len = (val & RCR_ENTRY_L2_LEN) >>
RCR_ENTRY_L2_LEN_SHIFT;
- len -= ETH_FCS_LEN;
+ append_size = len + ETH_HLEN + ETH_FCS_LEN;
addr = (val & RCR_ENTRY_PKT_BUF_ADDR) <<
RCR_ENTRY_PKT_BUF_ADDR_SHIFT;
@@ -3453,7 +3453,6 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np,
RCR_ENTRY_PKTBUFSZ_SHIFT];
off = addr & ~PAGE_MASK;
- append_size = rcr_size;
if (num_rcr == 1) {
int ptype;
@@ -3466,7 +3465,7 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np,
else
skb_checksum_none_assert(skb);
} else if (!(val & RCR_ENTRY_MULTI))
- append_size = len - skb->len;
+ append_size = append_size - skb->len;
niu_rx_skb_append(skb, page, off, append_size, rcr_size);
if ((page->index + rp->rbr_block_size) - rcr_size == addr) {
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 3037127..28d893b 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -129,7 +129,7 @@ do { \
#define RX_PRIORITY_MAPPING 0x76543210
#define TX_PRIORITY_MAPPING 0x33221100
-#define CPDMA_TX_PRIORITY_MAP 0x01234567
+#define CPDMA_TX_PRIORITY_MAP 0x76543210
#define CPSW_VLAN_AWARE BIT(1)
#define CPSW_RX_VLAN_ENCAP BIT(2)
@@ -1340,6 +1340,8 @@ static inline void cpsw_add_dual_emac_def_ale_entries(
cpsw_ale_add_ucast(cpsw->ale, priv->mac_addr,
HOST_PORT_NUM, ALE_VLAN |
ALE_SECURE, slave->port_vlan);
+ cpsw_ale_control_set(cpsw->ale, slave_port,
+ ALE_PORT_DROP_UNKNOWN_VLAN, 1);
}
static void soft_reset_slave(struct cpsw_slave *slave)
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index abceea8..38828ab 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -1873,7 +1873,7 @@ static int davinci_emac_probe(struct platform_device *pdev)
if (IS_ERR(priv->txchan)) {
dev_err(&pdev->dev, "error initializing tx dma channel\n");
rc = PTR_ERR(priv->txchan);
- goto no_cpdma_chan;
+ goto err_free_dma;
}
priv->rxchan = cpdma_chan_create(priv->dma, EMAC_DEF_RX_CH,
@@ -1881,14 +1881,14 @@ static int davinci_emac_probe(struct platform_device *pdev)
if (IS_ERR(priv->rxchan)) {
dev_err(&pdev->dev, "error initializing rx dma channel\n");
rc = PTR_ERR(priv->rxchan);
- goto no_cpdma_chan;
+ goto err_free_txchan;
}
res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
if (!res) {
dev_err(&pdev->dev, "error getting irq res\n");
rc = -ENOENT;
- goto no_cpdma_chan;
+ goto err_free_rxchan;
}
ndev->irq = res->start;
@@ -1914,7 +1914,7 @@ static int davinci_emac_probe(struct platform_device *pdev)
pm_runtime_put_noidle(&pdev->dev);
dev_err(&pdev->dev, "%s: failed to get_sync(%d)\n",
__func__, rc);
- goto no_cpdma_chan;
+ goto err_napi_del;
}
/* register the network device */
@@ -1924,7 +1924,7 @@ static int davinci_emac_probe(struct platform_device *pdev)
dev_err(&pdev->dev, "error in register_netdev\n");
rc = -ENODEV;
pm_runtime_put(&pdev->dev);
- goto no_cpdma_chan;
+ goto err_napi_del;
}
@@ -1937,11 +1937,13 @@ static int davinci_emac_probe(struct platform_device *pdev)
return 0;
-no_cpdma_chan:
- if (priv->txchan)
- cpdma_chan_destroy(priv->txchan);
- if (priv->rxchan)
- cpdma_chan_destroy(priv->rxchan);
+err_napi_del:
+ netif_napi_del(&priv->napi);
+err_free_rxchan:
+ cpdma_chan_destroy(priv->rxchan);
+err_free_txchan:
+ cpdma_chan_destroy(priv->txchan);
+err_free_dma:
cpdma_ctlr_destroy(priv->dma);
no_pdata:
if (of_phy_is_fixed_link(np))
diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index dfabbae..f347fd9 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -449,20 +449,6 @@ static const struct seq_operations bpq_seqops = {
.show = bpq_seq_show,
};
-static int bpq_info_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &bpq_seqops);
-}
-
-static const struct file_operations bpq_info_fops = {
- .owner = THIS_MODULE,
- .open = bpq_info_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-
/* ------------------------------------------------------------------------ */
static const struct net_device_ops bpq_netdev_ops = {
@@ -590,7 +576,7 @@ static int bpq_device_event(struct notifier_block *this,
static int __init bpq_init_driver(void)
{
#ifdef CONFIG_PROC_FS
- if (!proc_create("bpqether", 0444, init_net.proc_net, &bpq_info_fops)) {
+ if (!proc_create_seq("bpqether", 0444, init_net.proc_net, &bpq_seqops)) {
printk(KERN_ERR
"bpq: cannot create /proc/net/bpqether entry.\n");
return -ENOENT;
diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c
index 3de2729..6c03932 100644
--- a/drivers/net/hamradio/scc.c
+++ b/drivers/net/hamradio/scc.c
@@ -2084,21 +2084,6 @@ static const struct seq_operations scc_net_seq_ops = {
.stop = scc_net_seq_stop,
.show = scc_net_seq_show,
};
-
-
-static int scc_net_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &scc_net_seq_ops);
-}
-
-static const struct file_operations scc_net_seq_fops = {
- .owner = THIS_MODULE,
- .open = scc_net_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_private,
-};
-
#endif /* CONFIG_PROC_FS */
@@ -2122,7 +2107,7 @@ static int __init scc_init_driver (void)
}
rtnl_unlock();
- proc_create("z8530drv", 0, init_net.proc_net, &scc_net_seq_fops);
+ proc_create_seq("z8530drv", 0, init_net.proc_net, &scc_net_seq_ops);
return 0;
}
diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c
index 83034eb..16ec7af 100644
--- a/drivers/net/hamradio/yam.c
+++ b/drivers/net/hamradio/yam.c
@@ -841,20 +841,6 @@ static const struct seq_operations yam_seqops = {
.stop = yam_seq_stop,
.show = yam_seq_show,
};
-
-static int yam_info_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &yam_seqops);
-}
-
-static const struct file_operations yam_info_fops = {
- .owner = THIS_MODULE,
- .open = yam_info_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
#endif
@@ -1168,7 +1154,7 @@ static int __init yam_init_driver(void)
yam_timer.expires = jiffies + HZ / 100;
add_timer(&yam_timer);
- proc_create("yam", 0444, init_net.proc_net, &yam_info_fops);
+ proc_create_seq("yam", 0444, init_net.proc_net, &yam_seqops);
return 0;
error:
while (--i >= 0) {
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index ecc8495..da07ccd 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1840,7 +1840,8 @@ static int netvsc_vf_join(struct net_device *vf_netdev,
goto rx_handler_failed;
}
- ret = netdev_upper_dev_link(vf_netdev, ndev, NULL);
+ ret = netdev_master_upper_dev_link(vf_netdev, ndev,
+ NULL, NULL, NULL);
if (ret != 0) {
netdev_err(vf_netdev,
"can not set master device %s (err = %d)\n",
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 6b127be..e7ca5b5 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1288,7 +1288,7 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
rndis_device->link_state ? "down" : "up");
if (net_device->nvsp_version < NVSP_PROTOCOL_VERSION_5)
- return net_device;
+ goto out;
rndis_filter_query_link_speed(rndis_device, net_device);
diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c
index 9fb9b56..4f684cb 100644
--- a/drivers/net/ieee802154/atusb.c
+++ b/drivers/net/ieee802154/atusb.c
@@ -1045,7 +1045,7 @@ static int atusb_probe(struct usb_interface *interface,
atusb->tx_dr.bRequest = ATUSB_TX;
atusb->tx_dr.wValue = cpu_to_le16(0);
- atusb->tx_urb = usb_alloc_urb(0, GFP_ATOMIC);
+ atusb->tx_urb = usb_alloc_urb(0, GFP_KERNEL);
if (!atusb->tx_urb)
goto fail;
diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c
index 55a22c7..de0d7f2 100644
--- a/drivers/net/ieee802154/mcr20a.c
+++ b/drivers/net/ieee802154/mcr20a.c
@@ -1267,7 +1267,7 @@ mcr20a_probe(struct spi_device *spi)
ret = mcr20a_get_platform_data(spi, pdata);
if (ret < 0) {
dev_crit(&spi->dev, "mcr20a_get_platform_data failed.\n");
- return ret;
+ goto free_pdata;
}
/* init reset gpio */
@@ -1275,7 +1275,7 @@ mcr20a_probe(struct spi_device *spi)
ret = devm_gpio_request_one(&spi->dev, pdata->rst_gpio,
GPIOF_OUT_INIT_HIGH, "reset");
if (ret)
- return ret;
+ goto free_pdata;
}
/* reset mcr20a */
@@ -1291,7 +1291,8 @@ mcr20a_probe(struct spi_device *spi)
hw = ieee802154_alloc_hw(sizeof(*lp), &mcr20a_hw_ops);
if (!hw) {
dev_crit(&spi->dev, "ieee802154_alloc_hw failed\n");
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto free_pdata;
}
/* init mcr20a local data */
@@ -1308,8 +1309,10 @@ mcr20a_probe(struct spi_device *spi)
/* init buf */
lp->buf = devm_kzalloc(&spi->dev, SPI_COMMAND_BUFFER, GFP_KERNEL);
- if (!lp->buf)
- return -ENOMEM;
+ if (!lp->buf) {
+ ret = -ENOMEM;
+ goto free_dev;
+ }
mcr20a_setup_tx_spi_messages(lp);
mcr20a_setup_rx_spi_messages(lp);
@@ -1366,6 +1369,8 @@ mcr20a_probe(struct spi_device *spi)
free_dev:
ieee802154_free_hw(lp->hw);
+free_pdata:
+ kfree(pdata);
return ret;
}
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 450eec2..4377c26 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -792,8 +792,10 @@ static int ipvlan_device_event(struct notifier_block *unused,
break;
case NETDEV_CHANGEADDR:
- list_for_each_entry(ipvlan, &port->ipvlans, pnode)
+ list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
ether_addr_copy(ipvlan->dev->dev_addr, dev->dev_addr);
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, ipvlan->dev);
+ }
break;
case NETDEV_PRE_TYPE_CHANGE:
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 9cbb0c8..7de88b3 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -3277,7 +3277,7 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
err = netdev_upper_dev_link(real_dev, dev, extack);
if (err < 0)
- goto put_dev;
+ goto unregister;
/* need to be already registered so that ->init has run and
* the MAC addr is set
@@ -3316,8 +3316,7 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
macsec_del_dev(macsec);
unlink:
netdev_upper_dev_unlink(real_dev, dev);
-put_dev:
- dev_put(real_dev);
+unregister:
unregister_netdevice(dev);
return err;
}
diff --git a/drivers/net/phy/bcm-cygnus.c b/drivers/net/phy/bcm-cygnus.c
index 6838129..e757b09 100644
--- a/drivers/net/phy/bcm-cygnus.c
+++ b/drivers/net/phy/bcm-cygnus.c
@@ -61,17 +61,17 @@ static int bcm_cygnus_afe_config(struct phy_device *phydev)
return rc;
/* make rcal=100, since rdb default is 000 */
- rc = bcm_phy_write_exp(phydev, MII_BRCM_CORE_EXPB1, 0x10);
+ rc = bcm_phy_write_exp_sel(phydev, MII_BRCM_CORE_EXPB1, 0x10);
if (rc < 0)
return rc;
/* CORE_EXPB0, Reset R_CAL/RC_CAL Engine */
- rc = bcm_phy_write_exp(phydev, MII_BRCM_CORE_EXPB0, 0x10);
+ rc = bcm_phy_write_exp_sel(phydev, MII_BRCM_CORE_EXPB0, 0x10);
if (rc < 0)
return rc;
/* CORE_EXPB0, Disable Reset R_CAL/RC_CAL Engine */
- rc = bcm_phy_write_exp(phydev, MII_BRCM_CORE_EXPB0, 0x00);
+ rc = bcm_phy_write_exp_sel(phydev, MII_BRCM_CORE_EXPB0, 0x00);
return 0;
}
diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c
index 5ad130c..d5e0833 100644
--- a/drivers/net/phy/bcm-phy-lib.c
+++ b/drivers/net/phy/bcm-phy-lib.c
@@ -56,7 +56,7 @@ int bcm54xx_auxctl_read(struct phy_device *phydev, u16 regnum)
/* The register must be written to both the Shadow Register Select and
* the Shadow Read Register Selector
*/
- phy_write(phydev, MII_BCM54XX_AUX_CTL, regnum |
+ phy_write(phydev, MII_BCM54XX_AUX_CTL, MII_BCM54XX_AUXCTL_SHDWSEL_MASK |
regnum << MII_BCM54XX_AUXCTL_SHDWSEL_READ_SHIFT);
return phy_read(phydev, MII_BCM54XX_AUX_CTL);
}
diff --git a/drivers/net/phy/bcm-phy-lib.h b/drivers/net/phy/bcm-phy-lib.h
index 7c73808..81cceaa 100644
--- a/drivers/net/phy/bcm-phy-lib.h
+++ b/drivers/net/phy/bcm-phy-lib.h
@@ -14,11 +14,18 @@
#ifndef _LINUX_BCM_PHY_LIB_H
#define _LINUX_BCM_PHY_LIB_H
+#include <linux/brcmphy.h>
#include <linux/phy.h>
int bcm_phy_write_exp(struct phy_device *phydev, u16 reg, u16 val);
int bcm_phy_read_exp(struct phy_device *phydev, u16 reg);
+static inline int bcm_phy_write_exp_sel(struct phy_device *phydev,
+ u16 reg, u16 val)
+{
+ return bcm_phy_write_exp(phydev, reg | MII_BCM54XX_EXP_SEL_ER, val);
+}
+
int bcm54xx_auxctl_write(struct phy_device *phydev, u16 regnum, u16 val);
int bcm54xx_auxctl_read(struct phy_device *phydev, u16 regnum);
diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index 29b1c88..01d2ff2f 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -65,10 +65,10 @@ struct bcm7xxx_phy_priv {
static void r_rc_cal_reset(struct phy_device *phydev)
{
/* Reset R_CAL/RC_CAL Engine */
- bcm_phy_write_exp(phydev, 0x00b0, 0x0010);
+ bcm_phy_write_exp_sel(phydev, 0x00b0, 0x0010);
/* Disable Reset R_AL/RC_CAL Engine */
- bcm_phy_write_exp(phydev, 0x00b0, 0x0000);
+ bcm_phy_write_exp_sel(phydev, 0x00b0, 0x0000);
}
static int bcm7xxx_28nm_b0_afe_config_init(struct phy_device *phydev)
diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 3bb6b66..f9c2591 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -720,6 +720,15 @@ static struct phy_driver broadcom_drivers[] = {
.get_strings = bcm_phy_get_strings,
.get_stats = bcm53xx_phy_get_stats,
.probe = bcm53xx_phy_probe,
+}, {
+ .phy_id = PHY_ID_BCM89610,
+ .phy_id_mask = 0xfffffff0,
+ .name = "Broadcom BCM89610",
+ .features = PHY_GBIT_FEATURES,
+ .flags = PHY_HAS_INTERRUPT,
+ .config_init = bcm54xx_config_init,
+ .ack_interrupt = bcm_phy_ack_intr,
+ .config_intr = bcm_phy_config_intr,
} };
module_phy_driver(broadcom_drivers);
@@ -741,6 +750,7 @@ static struct mdio_device_id __maybe_unused broadcom_tbl[] = {
{ PHY_ID_BCMAC131, 0xfffffff0 },
{ PHY_ID_BCM5241, 0xfffffff0 },
{ PHY_ID_BCM5395, 0xfffffff0 },
+ { PHY_ID_BCM89610, 0xfffffff0 },
{ }
};
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index c22e8e3..25e2a09 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1393,6 +1393,15 @@ static int m88e1318_set_wol(struct phy_device *phydev,
if (err < 0)
goto error;
+ /* If WOL event happened once, the LED[2] interrupt pin
+ * will not be cleared unless we reading the interrupt status
+ * register. If interrupts are in use, the normal interrupt
+ * handling will clear the WOL event. Clear the WOL event
+ * before enabling it if !phy_interrupt_is_valid()
+ */
+ if (!phy_interrupt_is_valid(phydev))
+ phy_read(phydev, MII_M1011_IEVENT);
+
/* Enable the WOL interrupt */
err = __phy_modify(phydev, MII_88E1318S_PHY_CSIER, 0,
MII_88E1318S_PHY_CSIER_WOL_EIE);
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index f41b224..ab195f0 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -573,9 +573,40 @@ static int ksz9031_config_init(struct phy_device *phydev)
ksz9031_of_load_skew_values(phydev, of_node,
MII_KSZ9031RN_TX_DATA_PAD_SKEW, 4,
tx_data_skews, 4);
+
+ /* Silicon Errata Sheet (DS80000691D or DS80000692D):
+ * When the device links in the 1000BASE-T slave mode only,
+ * the optional 125MHz reference output clock (CLK125_NDO)
+ * has wide duty cycle variation.
+ *
+ * The optional CLK125_NDO clock does not meet the RGMII
+ * 45/55 percent (min/max) duty cycle requirement and therefore
+ * cannot be used directly by the MAC side for clocking
+ * applications that have setup/hold time requirements on
+ * rising and falling clock edges.
+ *
+ * Workaround:
+ * Force the phy to be the master to receive a stable clock
+ * which meets the duty cycle requirement.
+ */
+ if (of_property_read_bool(of_node, "micrel,force-master")) {
+ result = phy_read(phydev, MII_CTRL1000);
+ if (result < 0)
+ goto err_force_master;
+
+ /* enable master mode, config & prefer master */
+ result |= CTL1000_ENABLE_MASTER | CTL1000_AS_MASTER;
+ result = phy_write(phydev, MII_CTRL1000, result);
+ if (result < 0)
+ goto err_force_master;
+ }
}
return ksz9031_center_flp_timing(phydev);
+
+err_force_master:
+ phydev_err(phydev, "failed to force the phy to master mode\n");
+ return result;
}
#define KSZ8873MLL_GLOBAL_CONTROL_4 0x06
diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c
index 0f293ef..a97ac8c1 100644
--- a/drivers/net/phy/microchip.c
+++ b/drivers/net/phy/microchip.c
@@ -20,6 +20,7 @@
#include <linux/ethtool.h>
#include <linux/phy.h>
#include <linux/microchipphy.h>
+#include <linux/delay.h>
#define DRIVER_AUTHOR "WOOJUNG HUH <woojung.huh@microchip.com>"
#define DRIVER_DESC "Microchip LAN88XX PHY driver"
@@ -30,6 +31,16 @@ struct lan88xx_priv {
__u32 wolopts;
};
+static int lan88xx_read_page(struct phy_device *phydev)
+{
+ return __phy_read(phydev, LAN88XX_EXT_PAGE_ACCESS);
+}
+
+static int lan88xx_write_page(struct phy_device *phydev, int page)
+{
+ return __phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, page);
+}
+
static int lan88xx_phy_config_intr(struct phy_device *phydev)
{
int rc;
@@ -66,6 +77,150 @@ static int lan88xx_suspend(struct phy_device *phydev)
return 0;
}
+static int lan88xx_TR_reg_set(struct phy_device *phydev, u16 regaddr,
+ u32 data)
+{
+ int val, save_page, ret = 0;
+ u16 buf;
+
+ /* Save current page */
+ save_page = phy_save_page(phydev);
+ if (save_page < 0) {
+ pr_warn("Failed to get current page\n");
+ goto err;
+ }
+
+ /* Switch to TR page */
+ lan88xx_write_page(phydev, LAN88XX_EXT_PAGE_ACCESS_TR);
+
+ ret = __phy_write(phydev, LAN88XX_EXT_PAGE_TR_LOW_DATA,
+ (data & 0xFFFF));
+ if (ret < 0) {
+ pr_warn("Failed to write TR low data\n");
+ goto err;
+ }
+
+ ret = __phy_write(phydev, LAN88XX_EXT_PAGE_TR_HIGH_DATA,
+ (data & 0x00FF0000) >> 16);
+ if (ret < 0) {
+ pr_warn("Failed to write TR high data\n");
+ goto err;
+ }
+
+ /* Config control bits [15:13] of register */
+ buf = (regaddr & ~(0x3 << 13));/* Clr [14:13] to write data in reg */
+ buf |= 0x8000; /* Set [15] to Packet transmit */
+
+ ret = __phy_write(phydev, LAN88XX_EXT_PAGE_TR_CR, buf);
+ if (ret < 0) {
+ pr_warn("Failed to write data in reg\n");
+ goto err;
+ }
+
+ usleep_range(1000, 2000);/* Wait for Data to be written */
+ val = __phy_read(phydev, LAN88XX_EXT_PAGE_TR_CR);
+ if (!(val & 0x8000))
+ pr_warn("TR Register[0x%X] configuration failed\n", regaddr);
+err:
+ return phy_restore_page(phydev, save_page, ret);
+}
+
+static void lan88xx_config_TR_regs(struct phy_device *phydev)
+{
+ int err;
+
+ /* Get access to Channel 0x1, Node 0xF , Register 0x01.
+ * Write 24-bit value 0x12B00A to register. Setting MrvlTrFix1000Kf,
+ * MrvlTrFix1000Kp, MasterEnableTR bits.
+ */
+ err = lan88xx_TR_reg_set(phydev, 0x0F82, 0x12B00A);
+ if (err < 0)
+ pr_warn("Failed to Set Register[0x0F82]\n");
+
+ /* Get access to Channel b'10, Node b'1101, Register 0x06.
+ * Write 24-bit value 0xD2C46F to register. Setting SSTrKf1000Slv,
+ * SSTrKp1000Mas bits.
+ */
+ err = lan88xx_TR_reg_set(phydev, 0x168C, 0xD2C46F);
+ if (err < 0)
+ pr_warn("Failed to Set Register[0x168C]\n");
+
+ /* Get access to Channel b'10, Node b'1111, Register 0x11.
+ * Write 24-bit value 0x620 to register. Setting rem_upd_done_thresh
+ * bits
+ */
+ err = lan88xx_TR_reg_set(phydev, 0x17A2, 0x620);
+ if (err < 0)
+ pr_warn("Failed to Set Register[0x17A2]\n");
+
+ /* Get access to Channel b'10, Node b'1101, Register 0x10.
+ * Write 24-bit value 0xEEFFDD to register. Setting
+ * eee_TrKp1Long_1000, eee_TrKp2Long_1000, eee_TrKp3Long_1000,
+ * eee_TrKp1Short_1000,eee_TrKp2Short_1000, eee_TrKp3Short_1000 bits.
+ */
+ err = lan88xx_TR_reg_set(phydev, 0x16A0, 0xEEFFDD);
+ if (err < 0)
+ pr_warn("Failed to Set Register[0x16A0]\n");
+
+ /* Get access to Channel b'10, Node b'1101, Register 0x13.
+ * Write 24-bit value 0x071448 to register. Setting
+ * slv_lpi_tr_tmr_val1, slv_lpi_tr_tmr_val2 bits.
+ */
+ err = lan88xx_TR_reg_set(phydev, 0x16A6, 0x071448);
+ if (err < 0)
+ pr_warn("Failed to Set Register[0x16A6]\n");
+
+ /* Get access to Channel b'10, Node b'1101, Register 0x12.
+ * Write 24-bit value 0x13132F to register. Setting
+ * slv_sigdet_timer_val1, slv_sigdet_timer_val2 bits.
+ */
+ err = lan88xx_TR_reg_set(phydev, 0x16A4, 0x13132F);
+ if (err < 0)
+ pr_warn("Failed to Set Register[0x16A4]\n");
+
+ /* Get access to Channel b'10, Node b'1101, Register 0x14.
+ * Write 24-bit value 0x0 to register. Setting eee_3level_delay,
+ * eee_TrKf_freeze_delay bits.
+ */
+ err = lan88xx_TR_reg_set(phydev, 0x16A8, 0x0);
+ if (err < 0)
+ pr_warn("Failed to Set Register[0x16A8]\n");
+
+ /* Get access to Channel b'01, Node b'1111, Register 0x34.
+ * Write 24-bit value 0x91B06C to register. Setting
+ * FastMseSearchThreshLong1000, FastMseSearchThreshShort1000,
+ * FastMseSearchUpdGain1000 bits.
+ */
+ err = lan88xx_TR_reg_set(phydev, 0x0FE8, 0x91B06C);
+ if (err < 0)
+ pr_warn("Failed to Set Register[0x0FE8]\n");
+
+ /* Get access to Channel b'01, Node b'1111, Register 0x3E.
+ * Write 24-bit value 0xC0A028 to register. Setting
+ * FastMseKp2ThreshLong1000, FastMseKp2ThreshShort1000,
+ * FastMseKp2UpdGain1000, FastMseKp2ExitEn1000 bits.
+ */
+ err = lan88xx_TR_reg_set(phydev, 0x0FFC, 0xC0A028);
+ if (err < 0)
+ pr_warn("Failed to Set Register[0x0FFC]\n");
+
+ /* Get access to Channel b'01, Node b'1111, Register 0x35.
+ * Write 24-bit value 0x041600 to register. Setting
+ * FastMseSearchPhShNum1000, FastMseSearchClksPerPh1000,
+ * FastMsePhChangeDelay1000 bits.
+ */
+ err = lan88xx_TR_reg_set(phydev, 0x0FEA, 0x041600);
+ if (err < 0)
+ pr_warn("Failed to Set Register[0x0FEA]\n");
+
+ /* Get access to Channel b'10, Node b'1101, Register 0x03.
+ * Write 24-bit value 0x000004 to register. Setting TrFreeze bits.
+ */
+ err = lan88xx_TR_reg_set(phydev, 0x1686, 0x000004);
+ if (err < 0)
+ pr_warn("Failed to Set Register[0x1686]\n");
+}
+
static int lan88xx_probe(struct phy_device *phydev)
{
struct device *dev = &phydev->mdio.dev;
@@ -132,6 +287,25 @@ static void lan88xx_set_mdix(struct phy_device *phydev)
phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, LAN88XX_EXT_PAGE_SPACE_0);
}
+static int lan88xx_config_init(struct phy_device *phydev)
+{
+ int val;
+
+ genphy_config_init(phydev);
+ /*Zerodetect delay enable */
+ val = phy_read_mmd(phydev, MDIO_MMD_PCS,
+ PHY_ARDENNES_MMD_DEV_3_PHY_CFG);
+ val |= PHY_ARDENNES_MMD_DEV_3_PHY_CFG_ZD_DLY_EN_;
+
+ phy_write_mmd(phydev, MDIO_MMD_PCS, PHY_ARDENNES_MMD_DEV_3_PHY_CFG,
+ val);
+
+ /* Config DSP registers */
+ lan88xx_config_TR_regs(phydev);
+
+ return 0;
+}
+
static int lan88xx_config_aneg(struct phy_device *phydev)
{
lan88xx_set_mdix(phydev);
@@ -151,7 +325,7 @@ static struct phy_driver microchip_phy_driver[] = {
.probe = lan88xx_probe,
.remove = lan88xx_remove,
- .config_init = genphy_config_init,
+ .config_init = lan88xx_config_init,
.config_aneg = lan88xx_config_aneg,
.ack_interrupt = lan88xx_phy_ack_interrupt,
@@ -160,6 +334,8 @@ static struct phy_driver microchip_phy_driver[] = {
.suspend = lan88xx_suspend,
.resume = genphy_resume,
.set_wol = lan88xx_set_wol,
+ .read_page = lan88xx_read_page,
+ .write_page = lan88xx_write_page,
} };
module_phy_driver(microchip_phy_driver);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index ac23322a..9e4ba8e 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -535,8 +535,17 @@ static int get_phy_id(struct mii_bus *bus, int addr, u32 *phy_id,
/* Grab the bits from PHYIR1, and put them in the upper half */
phy_reg = mdiobus_read(bus, addr, MII_PHYSID1);
- if (phy_reg < 0)
+ if (phy_reg < 0) {
+ /* if there is no device, return without an error so scanning
+ * the bus works properly
+ */
+ if (phy_reg == -EIO || phy_reg == -ENODEV) {
+ *phy_id = 0xffffffff;
+ return 0;
+ }
+
return -EIO;
+ }
*phy_id = (phy_reg & 0xffff) << 16;
diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index 0381da7..fd6c23f 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -125,7 +125,7 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id,
if (id->base.br_nominal) {
if (id->base.br_nominal != 255) {
br_nom = id->base.br_nominal * 100;
- br_min = br_nom + id->base.br_nominal * id->ext.br_min;
+ br_min = br_nom - id->base.br_nominal * id->ext.br_min;
br_max = br_nom + id->base.br_nominal * id->ext.br_max;
} else if (id->ext.br_max) {
br_nom = 250 * id->ext.br_max;
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index dc7c7ec..02ad03a 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -605,30 +605,13 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
if (cmd == PPPIOCDETACH) {
/*
- * We have to be careful here... if the file descriptor
- * has been dup'd, we could have another process in the
- * middle of a poll using the same file *, so we had
- * better not free the interface data structures -
- * instead we fail the ioctl. Even in this case, we
- * shut down the interface if we are the owner of it.
- * Actually, we should get rid of PPPIOCDETACH, userland
- * (i.e. pppd) could achieve the same effect by closing
- * this fd and reopening /dev/ppp.
+ * PPPIOCDETACH is no longer supported as it was heavily broken,
+ * and is only known to have been used by pppd older than
+ * ppp-2.4.2 (released November 2003).
*/
+ pr_warn_once("%s (%d) used obsolete PPPIOCDETACH ioctl\n",
+ current->comm, current->pid);
err = -EINVAL;
- if (pf->kind == INTERFACE) {
- ppp = PF_TO_PPP(pf);
- rtnl_lock();
- if (file == ppp->owner)
- unregister_netdevice(ppp->dev);
- rtnl_unlock();
- }
- if (atomic_long_read(&file->f_count) < 2) {
- ppp_release(NULL, file);
- err = 0;
- } else
- pr_warn("PPPIOCDETACH file->f_count=%ld\n",
- atomic_long_read(&file->f_count));
goto out;
}
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 1483bc7..de51e8f70f 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -620,6 +620,10 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr,
lock_sock(sk);
error = -EINVAL;
+
+ if (sockaddr_len != sizeof(struct sockaddr_pppox))
+ goto end;
+
if (sp->sa_protocol != PX_PROTO_OE)
goto end;
@@ -1092,21 +1096,6 @@ static const struct seq_operations pppoe_seq_ops = {
.stop = pppoe_seq_stop,
.show = pppoe_seq_show,
};
-
-static int pppoe_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &pppoe_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-static const struct file_operations pppoe_seq_fops = {
- .owner = THIS_MODULE,
- .open = pppoe_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
#endif /* CONFIG_PROC_FS */
static const struct proto_ops pppoe_ops = {
@@ -1118,7 +1107,7 @@ static const struct proto_ops pppoe_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = pppoe_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
@@ -1142,7 +1131,8 @@ static __net_init int pppoe_init_net(struct net *net)
rwlock_init(&pn->hash_lock);
- pde = proc_create("pppoe", 0444, net->proc_net, &pppoe_seq_fops);
+ pde = proc_create_net("pppoe", 0444, net->proc_net,
+ &pppoe_seq_ops, sizeof(struct seq_net_private));
#ifdef CONFIG_PROC_FS
if (!pde)
return -ENOMEM;
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index c4267ec..157b67c 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -624,7 +624,6 @@ static const struct proto_ops pptp_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = pptp_getname,
- .poll = sock_no_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index a6c6ce1..ddb6bf8 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -261,6 +261,17 @@ static void __team_option_inst_mark_removed_port(struct team *team,
}
}
+static bool __team_option_inst_tmp_find(const struct list_head *opts,
+ const struct team_option_inst *needle)
+{
+ struct team_option_inst *opt_inst;
+
+ list_for_each_entry(opt_inst, opts, tmp_list)
+ if (opt_inst == needle)
+ return true;
+ return false;
+}
+
static int __team_options_register(struct team *team,
const struct team_option *option,
size_t option_count)
@@ -1061,14 +1072,11 @@ static void team_port_leave(struct team *team, struct team_port *port)
}
#ifdef CONFIG_NET_POLL_CONTROLLER
-static int team_port_enable_netpoll(struct team *team, struct team_port *port)
+static int __team_port_enable_netpoll(struct team_port *port)
{
struct netpoll *np;
int err;
- if (!team->dev->npinfo)
- return 0;
-
np = kzalloc(sizeof(*np), GFP_KERNEL);
if (!np)
return -ENOMEM;
@@ -1082,6 +1090,14 @@ static int team_port_enable_netpoll(struct team *team, struct team_port *port)
return err;
}
+static int team_port_enable_netpoll(struct team_port *port)
+{
+ if (!port->team->dev->npinfo)
+ return 0;
+
+ return __team_port_enable_netpoll(port);
+}
+
static void team_port_disable_netpoll(struct team_port *port)
{
struct netpoll *np = port->np;
@@ -1096,7 +1112,7 @@ static void team_port_disable_netpoll(struct team_port *port)
kfree(np);
}
#else
-static int team_port_enable_netpoll(struct team *team, struct team_port *port)
+static int team_port_enable_netpoll(struct team_port *port)
{
return 0;
}
@@ -1210,7 +1226,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
goto err_vids_add;
}
- err = team_port_enable_netpoll(team, port);
+ err = team_port_enable_netpoll(port);
if (err) {
netdev_err(dev, "Failed to enable netpoll on device %s\n",
portname);
@@ -1907,7 +1923,7 @@ static int team_netpoll_setup(struct net_device *dev,
mutex_lock(&team->lock);
list_for_each_entry(port, &team->port_list, list) {
- err = team_port_enable_netpoll(team, port);
+ err = __team_port_enable_netpoll(port);
if (err) {
__team_netpoll_cleanup(team);
break;
@@ -2568,6 +2584,14 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
if (err)
goto team_put;
opt_inst->changed = true;
+
+ /* dumb/evil user-space can send us duplicate opt,
+ * keep only the last one
+ */
+ if (__team_option_inst_tmp_find(&opt_inst_list,
+ opt_inst))
+ continue;
+
list_add(&opt_inst->tmp_list, &opt_inst_list);
}
if (!opt_found) {
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 28583aa..23e9eb6 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -681,15 +681,6 @@ static void tun_queue_purge(struct tun_file *tfile)
skb_queue_purge(&tfile->sk.sk_error_queue);
}
-static void tun_cleanup_tx_ring(struct tun_file *tfile)
-{
- if (tfile->tx_ring.queue) {
- ptr_ring_cleanup(&tfile->tx_ring, tun_ptr_free);
- xdp_rxq_info_unreg(&tfile->xdp_rxq);
- memset(&tfile->tx_ring, 0, sizeof(tfile->tx_ring));
- }
-}
-
static void __tun_detach(struct tun_file *tfile, bool clean)
{
struct tun_file *ntfile;
@@ -736,7 +727,9 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
tun->dev->reg_state == NETREG_REGISTERED)
unregister_netdevice(tun->dev);
}
- tun_cleanup_tx_ring(tfile);
+ if (tun)
+ xdp_rxq_info_unreg(&tfile->xdp_rxq);
+ ptr_ring_cleanup(&tfile->tx_ring, tun_ptr_free);
sock_put(&tfile->sk);
}
}
@@ -783,14 +776,14 @@ static void tun_detach_all(struct net_device *dev)
tun_napi_del(tun, tfile);
/* Drop read queue */
tun_queue_purge(tfile);
+ xdp_rxq_info_unreg(&tfile->xdp_rxq);
sock_put(&tfile->sk);
- tun_cleanup_tx_ring(tfile);
}
list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) {
tun_enable_queue(tfile);
tun_queue_purge(tfile);
+ xdp_rxq_info_unreg(&tfile->xdp_rxq);
sock_put(&tfile->sk);
- tun_cleanup_tx_ring(tfile);
}
BUG_ON(tun->numdisabled != 0);
@@ -834,7 +827,8 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
}
if (!tfile->detached &&
- ptr_ring_init(&tfile->tx_ring, dev->tx_queue_len, GFP_KERNEL)) {
+ ptr_ring_resize(&tfile->tx_ring, dev->tx_queue_len,
+ GFP_KERNEL, tun_ptr_free)) {
err = -ENOMEM;
goto out;
}
@@ -1102,12 +1096,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
goto drop;
len = run_ebpf_filter(tun, skb, len);
-
- /* Trim extra bytes since we may insert vlan proto & TCI
- * in tun_put_user().
- */
- len -= skb_vlan_tag_present(skb) ? sizeof(struct veth) : 0;
- if (len <= 0 || pskb_trim(skb, len))
+ if (len == 0 || pskb_trim(skb, len))
goto drop;
if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC)))
@@ -1434,6 +1423,13 @@ static void tun_net_init(struct net_device *dev)
dev->max_mtu = MAX_MTU - dev->hard_header_len;
}
+static bool tun_sock_writeable(struct tun_struct *tun, struct tun_file *tfile)
+{
+ struct sock *sk = tfile->socket.sk;
+
+ return (tun->dev->flags & IFF_UP) && sock_writeable(sk);
+}
+
/* Character device part */
/* Poll */
@@ -1456,10 +1452,14 @@ static __poll_t tun_chr_poll(struct file *file, poll_table *wait)
if (!ptr_ring_empty(&tfile->tx_ring))
mask |= EPOLLIN | EPOLLRDNORM;
- if (tun->dev->flags & IFF_UP &&
- (sock_writeable(sk) ||
- (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
- sock_writeable(sk))))
+ /* Make sure SOCKWQ_ASYNC_NOSPACE is set if not writable to
+ * guarantee EPOLLOUT to be raised by either here or
+ * tun_sock_write_space(). Then process could get notification
+ * after it writes to a down device and meets -EIO.
+ */
+ if (tun_sock_writeable(tun, tfile) ||
+ (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
+ tun_sock_writeable(tun, tfile)))
mask |= EPOLLOUT | EPOLLWRNORM;
if (tun->dev->reg_state != NETREG_REGISTERED)
@@ -1650,7 +1650,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
else
*skb_xdp = 0;
- preempt_disable();
+ local_bh_disable();
rcu_read_lock();
xdp_prog = rcu_dereference(tun->xdp_prog);
if (xdp_prog && !*skb_xdp) {
@@ -1675,7 +1675,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
if (err)
goto err_redirect;
rcu_read_unlock();
- preempt_enable();
+ local_bh_enable();
return NULL;
case XDP_TX:
get_page(alloc_frag->page);
@@ -1684,7 +1684,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
goto err_redirect;
tun_xdp_flush(tun->dev);
rcu_read_unlock();
- preempt_enable();
+ local_bh_enable();
return NULL;
case XDP_PASS:
delta = orig_data - xdp.data;
@@ -1703,7 +1703,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
skb = build_skb(buf, buflen);
if (!skb) {
rcu_read_unlock();
- preempt_enable();
+ local_bh_enable();
return ERR_PTR(-ENOMEM);
}
@@ -1713,7 +1713,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
alloc_frag->offset += buflen;
rcu_read_unlock();
- preempt_enable();
+ local_bh_enable();
return skb;
@@ -1721,7 +1721,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
put_page(alloc_frag->page);
err_xdp:
rcu_read_unlock();
- preempt_enable();
+ local_bh_enable();
this_cpu_inc(tun->pcpu_stats->rx_dropped);
return NULL;
}
@@ -1917,16 +1917,19 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
struct bpf_prog *xdp_prog;
int ret;
+ local_bh_disable();
rcu_read_lock();
xdp_prog = rcu_dereference(tun->xdp_prog);
if (xdp_prog) {
ret = do_xdp_generic(xdp_prog, skb);
if (ret != XDP_PASS) {
rcu_read_unlock();
+ local_bh_enable();
return total_len;
}
}
rcu_read_unlock();
+ local_bh_enable();
}
rcu_read_lock();
@@ -3224,6 +3227,11 @@ static int tun_chr_open(struct inode *inode, struct file * file)
&tun_proto, 0);
if (!tfile)
return -ENOMEM;
+ if (ptr_ring_init(&tfile->tx_ring, 0, GFP_KERNEL)) {
+ sk_free(&tfile->sk);
+ return -ENOMEM;
+ }
+
RCU_INIT_POINTER(tfile->tun, NULL);
tfile->flags = 0;
tfile->ifindex = 0;
@@ -3244,8 +3252,6 @@ static int tun_chr_open(struct inode *inode, struct file * file)
sock_set_flag(&tfile->sk, SOCK_ZEROCOPY);
- memset(&tfile->tx_ring, 0, sizeof(tfile->tx_ring));
-
return 0;
}
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 7220cd6..0362acd 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -609,7 +609,7 @@ static const struct driver_info cdc_mbim_info_ndp_to_end = {
*/
static const struct driver_info cdc_mbim_info_avoid_altsetting_toggle = {
.description = "CDC MBIM",
- .flags = FLAG_NO_SETINT | FLAG_MULTI_PACKET | FLAG_WWAN,
+ .flags = FLAG_NO_SETINT | FLAG_MULTI_PACKET | FLAG_WWAN | FLAG_SEND_ZLP,
.bind = cdc_mbim_bind,
.unbind = cdc_mbim_unbind,
.manage_power = cdc_mbim_manage_power,
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index ca066b7..0946808 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1098,15 +1098,18 @@ static const struct usb_device_id products[] = {
{QMI_FIXED_INTF(0x05c6, 0x9080, 8)},
{QMI_FIXED_INTF(0x05c6, 0x9083, 3)},
{QMI_FIXED_INTF(0x05c6, 0x9084, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x90b2, 3)}, /* ublox R410M */
{QMI_FIXED_INTF(0x05c6, 0x920d, 0)},
{QMI_FIXED_INTF(0x05c6, 0x920d, 5)},
{QMI_QUIRK_SET_DTR(0x05c6, 0x9625, 4)}, /* YUGA CLM920-NC5 */
{QMI_FIXED_INTF(0x0846, 0x68a2, 8)},
+ {QMI_FIXED_INTF(0x0846, 0x68d3, 8)}, /* Netgear Aircard 779S */
{QMI_FIXED_INTF(0x12d1, 0x140c, 1)}, /* Huawei E173 */
{QMI_FIXED_INTF(0x12d1, 0x14ac, 1)}, /* Huawei E1820 */
{QMI_FIXED_INTF(0x1435, 0xd181, 3)}, /* Wistron NeWeb D18Q1 */
{QMI_FIXED_INTF(0x1435, 0xd181, 4)}, /* Wistron NeWeb D18Q1 */
{QMI_FIXED_INTF(0x1435, 0xd181, 5)}, /* Wistron NeWeb D18Q1 */
+ {QMI_FIXED_INTF(0x1435, 0xd191, 4)}, /* Wistron NeWeb D19Q1 */
{QMI_FIXED_INTF(0x16d8, 0x6003, 0)}, /* CMOTech 6003 */
{QMI_FIXED_INTF(0x16d8, 0x6007, 0)}, /* CMOTech CHE-628S */
{QMI_FIXED_INTF(0x16d8, 0x6008, 0)}, /* CMOTech CMU-301 */
@@ -1342,6 +1345,18 @@ static int qmi_wwan_probe(struct usb_interface *intf,
id->driver_info = (unsigned long)&qmi_wwan_info;
}
+ /* There are devices where the same interface number can be
+ * configured as different functions. We should only bind to
+ * vendor specific functions when matching on interface number
+ */
+ if (id->match_flags & USB_DEVICE_ID_MATCH_INT_NUMBER &&
+ desc->bInterfaceClass != USB_CLASS_VENDOR_SPEC) {
+ dev_dbg(&intf->dev,
+ "Rejecting interface number match for class %02x\n",
+ desc->bInterfaceClass);
+ return -ENODEV;
+ }
+
/* Quectel EC20 quirk where we've QMI on interface 4 instead of 0 */
if (quectel_ec20_detected(intf) && desc->bInterfaceNumber == 0) {
dev_dbg(&intf->dev, "Quectel EC20 quirk, skipping interface 0\n");
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7b187ec..032e1ac 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -147,6 +147,17 @@ struct receive_queue {
struct xdp_rxq_info xdp_rxq;
};
+/* Control VQ buffers: protected by the rtnl lock */
+struct control_buf {
+ struct virtio_net_ctrl_hdr hdr;
+ virtio_net_ctrl_ack status;
+ struct virtio_net_ctrl_mq mq;
+ u8 promisc;
+ u8 allmulti;
+ __virtio16 vid;
+ __virtio64 offloads;
+};
+
struct virtnet_info {
struct virtio_device *vdev;
struct virtqueue *cvq;
@@ -192,14 +203,7 @@ struct virtnet_info {
struct hlist_node node;
struct hlist_node node_dead;
- /* Control VQ buffers: protected by the rtnl lock */
- struct virtio_net_ctrl_hdr ctrl_hdr;
- virtio_net_ctrl_ack ctrl_status;
- struct virtio_net_ctrl_mq ctrl_mq;
- u8 ctrl_promisc;
- u8 ctrl_allmulti;
- u16 ctrl_vid;
- u64 ctrl_offloads;
+ struct control_buf *ctrl;
/* Ethtool settings */
u8 duplex;
@@ -703,6 +707,13 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
void *data;
u32 act;
+ /* Transient failure which in theory could occur if
+ * in-flight packets from before XDP was enabled reach
+ * the receive path after XDP is loaded.
+ */
+ if (unlikely(hdr->hdr.gso_type))
+ goto err_xdp;
+
/* This happens when rx buffer size is underestimated
* or headroom is not enough because of the buffer
* was refilled before XDP is set. This should only
@@ -723,14 +734,6 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
xdp_page = page;
}
- /* Transient failure which in theory could occur if
- * in-flight packets from before XDP was enabled reach
- * the receive path after XDP is loaded. In practice I
- * was not able to create this condition.
- */
- if (unlikely(hdr->hdr.gso_type))
- goto err_xdp;
-
/* Allow consuming headroom but reserve enough space to push
* the descriptor on if we get an XDP_TX return code.
*/
@@ -771,7 +774,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
}
*xdp_xmit = true;
if (unlikely(xdp_page != page))
- goto err_xdp;
+ put_page(page);
rcu_read_unlock();
goto xdp_xmit;
case XDP_REDIRECT:
@@ -783,7 +786,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
}
*xdp_xmit = true;
if (unlikely(xdp_page != page))
- goto err_xdp;
+ put_page(page);
rcu_read_unlock();
goto xdp_xmit;
default:
@@ -871,7 +874,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
rcu_read_unlock();
err_skb:
put_page(page);
- while (--num_buf) {
+ while (num_buf-- > 1) {
buf = virtqueue_get_buf(rq->vq, &len);
if (unlikely(!buf)) {
pr_debug("%s: rx error: %d buffers missing\n",
@@ -1269,7 +1272,9 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
{
struct receive_queue *rq =
container_of(napi, struct receive_queue, napi);
- unsigned int received;
+ struct virtnet_info *vi = rq->vq->vdev->priv;
+ struct send_queue *sq;
+ unsigned int received, qp;
bool xdp_xmit = false;
virtnet_poll_cleantx(rq);
@@ -1280,8 +1285,13 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
if (received < budget)
virtqueue_napi_complete(napi, rq->vq, received);
- if (xdp_xmit)
+ if (xdp_xmit) {
+ qp = vi->curr_queue_pairs - vi->xdp_queue_pairs +
+ smp_processor_id();
+ sq = &vi->sq[qp];
+ virtqueue_kick(sq->vq);
xdp_do_flush_map();
+ }
return received;
}
@@ -1454,25 +1464,25 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
/* Caller should know better */
BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ));
- vi->ctrl_status = ~0;
- vi->ctrl_hdr.class = class;
- vi->ctrl_hdr.cmd = cmd;
+ vi->ctrl->status = ~0;
+ vi->ctrl->hdr.class = class;
+ vi->ctrl->hdr.cmd = cmd;
/* Add header */
- sg_init_one(&hdr, &vi->ctrl_hdr, sizeof(vi->ctrl_hdr));
+ sg_init_one(&hdr, &vi->ctrl->hdr, sizeof(vi->ctrl->hdr));
sgs[out_num++] = &hdr;
if (out)
sgs[out_num++] = out;
/* Add return status. */
- sg_init_one(&stat, &vi->ctrl_status, sizeof(vi->ctrl_status));
+ sg_init_one(&stat, &vi->ctrl->status, sizeof(vi->ctrl->status));
sgs[out_num] = &stat;
BUG_ON(out_num + 1 > ARRAY_SIZE(sgs));
virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC);
if (unlikely(!virtqueue_kick(vi->cvq)))
- return vi->ctrl_status == VIRTIO_NET_OK;
+ return vi->ctrl->status == VIRTIO_NET_OK;
/* Spin for a response, the kick causes an ioport write, trapping
* into the hypervisor, so the request should be handled immediately.
@@ -1481,7 +1491,7 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
!virtqueue_is_broken(vi->cvq))
cpu_relax();
- return vi->ctrl_status == VIRTIO_NET_OK;
+ return vi->ctrl->status == VIRTIO_NET_OK;
}
static int virtnet_set_mac_address(struct net_device *dev, void *p)
@@ -1593,8 +1603,8 @@ static int _virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ))
return 0;
- vi->ctrl_mq.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs);
- sg_init_one(&sg, &vi->ctrl_mq, sizeof(vi->ctrl_mq));
+ vi->ctrl->mq.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs);
+ sg_init_one(&sg, &vi->ctrl->mq, sizeof(vi->ctrl->mq));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ,
VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg)) {
@@ -1653,22 +1663,22 @@ static void virtnet_set_rx_mode(struct net_device *dev)
if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX))
return;
- vi->ctrl_promisc = ((dev->flags & IFF_PROMISC) != 0);
- vi->ctrl_allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
+ vi->ctrl->promisc = ((dev->flags & IFF_PROMISC) != 0);
+ vi->ctrl->allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
- sg_init_one(sg, &vi->ctrl_promisc, sizeof(vi->ctrl_promisc));
+ sg_init_one(sg, &vi->ctrl->promisc, sizeof(vi->ctrl->promisc));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
VIRTIO_NET_CTRL_RX_PROMISC, sg))
dev_warn(&dev->dev, "Failed to %sable promisc mode.\n",
- vi->ctrl_promisc ? "en" : "dis");
+ vi->ctrl->promisc ? "en" : "dis");
- sg_init_one(sg, &vi->ctrl_allmulti, sizeof(vi->ctrl_allmulti));
+ sg_init_one(sg, &vi->ctrl->allmulti, sizeof(vi->ctrl->allmulti));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
VIRTIO_NET_CTRL_RX_ALLMULTI, sg))
dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n",
- vi->ctrl_allmulti ? "en" : "dis");
+ vi->ctrl->allmulti ? "en" : "dis");
uc_count = netdev_uc_count(dev);
mc_count = netdev_mc_count(dev);
@@ -1714,8 +1724,8 @@ static int virtnet_vlan_rx_add_vid(struct net_device *dev,
struct virtnet_info *vi = netdev_priv(dev);
struct scatterlist sg;
- vi->ctrl_vid = vid;
- sg_init_one(&sg, &vi->ctrl_vid, sizeof(vi->ctrl_vid));
+ vi->ctrl->vid = cpu_to_virtio16(vi->vdev, vid);
+ sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
VIRTIO_NET_CTRL_VLAN_ADD, &sg))
@@ -1729,8 +1739,8 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev,
struct virtnet_info *vi = netdev_priv(dev);
struct scatterlist sg;
- vi->ctrl_vid = vid;
- sg_init_one(&sg, &vi->ctrl_vid, sizeof(vi->ctrl_vid));
+ vi->ctrl->vid = cpu_to_virtio16(vi->vdev, vid);
+ sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
VIRTIO_NET_CTRL_VLAN_DEL, &sg))
@@ -2126,9 +2136,9 @@ static int virtnet_restore_up(struct virtio_device *vdev)
static int virtnet_set_guest_offloads(struct virtnet_info *vi, u64 offloads)
{
struct scatterlist sg;
- vi->ctrl_offloads = cpu_to_virtio64(vi->vdev, offloads);
+ vi->ctrl->offloads = cpu_to_virtio64(vi->vdev, offloads);
- sg_init_one(&sg, &vi->ctrl_offloads, sizeof(vi->ctrl_offloads));
+ sg_init_one(&sg, &vi->ctrl->offloads, sizeof(vi->ctrl->offloads));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_GUEST_OFFLOADS,
VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET, &sg)) {
@@ -2351,6 +2361,7 @@ static void virtnet_free_queues(struct virtnet_info *vi)
kfree(vi->rq);
kfree(vi->sq);
+ kfree(vi->ctrl);
}
static void _free_receive_bufs(struct virtnet_info *vi)
@@ -2543,6 +2554,9 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
{
int i;
+ vi->ctrl = kzalloc(sizeof(*vi->ctrl), GFP_KERNEL);
+ if (!vi->ctrl)
+ goto err_ctrl;
vi->sq = kzalloc(sizeof(*vi->sq) * vi->max_queue_pairs, GFP_KERNEL);
if (!vi->sq)
goto err_sq;
@@ -2571,6 +2585,8 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
err_rq:
kfree(vi->sq);
err_sq:
+ kfree(vi->ctrl);
+err_ctrl:
return -ENOMEM;
}
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index e04937f..27a9bb8 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -369,6 +369,11 @@ vmxnet3_tq_tx_complete(struct vmxnet3_tx_queue *tq,
gdesc = tq->comp_ring.base + tq->comp_ring.next2proc;
while (VMXNET3_TCD_GET_GEN(&gdesc->tcd) == tq->comp_ring.gen) {
+ /* Prevent any &gdesc->tcd field from being (speculatively)
+ * read before (&gdesc->tcd)->gen is read.
+ */
+ dma_rmb();
+
completed += vmxnet3_unmap_pkt(VMXNET3_TCD_GET_TXIDX(
&gdesc->tcd), tq, adapter->pdev,
adapter);
@@ -1103,6 +1108,11 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
gdesc->txd.tci = skb_vlan_tag_get(skb);
}
+ /* Ensure that the write to (&gdesc->txd)->gen will be observed after
+ * all other writes to &gdesc->txd.
+ */
+ dma_wmb();
+
/* finally flips the GEN bit of the SOP desc. */
gdesc->dword[2] = cpu_to_le32(le32_to_cpu(gdesc->dword[2]) ^
VMXNET3_TXD_GEN);
@@ -1218,6 +1228,7 @@ vmxnet3_get_hdr_len(struct vmxnet3_adapter *adapter, struct sk_buff *skb,
union {
void *ptr;
struct ethhdr *eth;
+ struct vlan_ethhdr *veth;
struct iphdr *ipv4;
struct ipv6hdr *ipv6;
struct tcphdr *tcp;
@@ -1228,16 +1239,24 @@ vmxnet3_get_hdr_len(struct vmxnet3_adapter *adapter, struct sk_buff *skb,
if (unlikely(sizeof(struct iphdr) + sizeof(struct tcphdr) > maplen))
return 0;
+ if (skb->protocol == cpu_to_be16(ETH_P_8021Q) ||
+ skb->protocol == cpu_to_be16(ETH_P_8021AD))
+ hlen = sizeof(struct vlan_ethhdr);
+ else
+ hlen = sizeof(struct ethhdr);
+
hdr.eth = eth_hdr(skb);
if (gdesc->rcd.v4) {
- BUG_ON(hdr.eth->h_proto != htons(ETH_P_IP));
- hdr.ptr += sizeof(struct ethhdr);
+ BUG_ON(hdr.eth->h_proto != htons(ETH_P_IP) &&
+ hdr.veth->h_vlan_encapsulated_proto != htons(ETH_P_IP));
+ hdr.ptr += hlen;
BUG_ON(hdr.ipv4->protocol != IPPROTO_TCP);
hlen = hdr.ipv4->ihl << 2;
hdr.ptr += hdr.ipv4->ihl << 2;
} else if (gdesc->rcd.v6) {
- BUG_ON(hdr.eth->h_proto != htons(ETH_P_IPV6));
- hdr.ptr += sizeof(struct ethhdr);
+ BUG_ON(hdr.eth->h_proto != htons(ETH_P_IPV6) &&
+ hdr.veth->h_vlan_encapsulated_proto != htons(ETH_P_IPV6));
+ hdr.ptr += hlen;
/* Use an estimated value, since we also need to handle
* TSO case.
*/
@@ -1289,6 +1308,12 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
*/
break;
}
+
+ /* Prevent any rcd field from being (speculatively) read before
+ * rcd->gen is read.
+ */
+ dma_rmb();
+
BUG_ON(rcd->rqID != rq->qid && rcd->rqID != rq->qid2 &&
rcd->rqID != rq->dataRingQid);
idx = rcd->rxdIdx;
@@ -1519,6 +1544,12 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
ring->next2comp = idx;
num_to_alloc = vmxnet3_cmd_ring_desc_avail(ring);
ring = rq->rx_ring + ring_idx;
+
+ /* Ensure that the writes to rxd->gen bits will be observed
+ * after all other writes to rxd objects.
+ */
+ dma_wmb();
+
while (num_to_alloc) {
vmxnet3_getRxDesc(rxd, &ring->base[ring->next2fill].rxd,
&rxCmdDesc);
@@ -2679,7 +2710,7 @@ vmxnet3_set_mac_addr(struct net_device *netdev, void *p)
/* ==================== initialization and cleanup routines ============ */
static int
-vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64)
+vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter)
{
int err;
unsigned long mmio_start, mmio_len;
@@ -2691,30 +2722,12 @@ vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64)
return err;
}
- if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) == 0) {
- if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)) != 0) {
- dev_err(&pdev->dev,
- "pci_set_consistent_dma_mask failed\n");
- err = -EIO;
- goto err_set_mask;
- }
- *dma64 = true;
- } else {
- if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) {
- dev_err(&pdev->dev,
- "pci_set_dma_mask failed\n");
- err = -EIO;
- goto err_set_mask;
- }
- *dma64 = false;
- }
-
err = pci_request_selected_regions(pdev, (1 << 2) - 1,
vmxnet3_driver_name);
if (err) {
dev_err(&pdev->dev,
"Failed to request region for adapter: error %d\n", err);
- goto err_set_mask;
+ goto err_enable_device;
}
pci_set_master(pdev);
@@ -2742,7 +2755,7 @@ vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64)
iounmap(adapter->hw_addr0);
err_ioremap:
pci_release_selected_regions(pdev, (1 << 2) - 1);
-err_set_mask:
+err_enable_device:
pci_disable_device(pdev);
return err;
}
@@ -3245,7 +3258,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
#endif
};
int err;
- bool dma64 = false; /* stupid gcc */
+ bool dma64;
u32 ver;
struct net_device *netdev;
struct vmxnet3_adapter *adapter;
@@ -3291,6 +3304,24 @@ vmxnet3_probe_device(struct pci_dev *pdev,
adapter->rx_ring_size = VMXNET3_DEF_RX_RING_SIZE;
adapter->rx_ring2_size = VMXNET3_DEF_RX_RING2_SIZE;
+ if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) == 0) {
+ if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)) != 0) {
+ dev_err(&pdev->dev,
+ "pci_set_consistent_dma_mask failed\n");
+ err = -EIO;
+ goto err_set_mask;
+ }
+ dma64 = true;
+ } else {
+ if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) {
+ dev_err(&pdev->dev,
+ "pci_set_dma_mask failed\n");
+ err = -EIO;
+ goto err_set_mask;
+ }
+ dma64 = false;
+ }
+
spin_lock_init(&adapter->cmd_lock);
adapter->adapter_pa = dma_map_single(&adapter->pdev->dev, adapter,
sizeof(struct vmxnet3_adapter),
@@ -3298,7 +3329,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
if (dma_mapping_error(&adapter->pdev->dev, adapter->adapter_pa)) {
dev_err(&pdev->dev, "Failed to map dma\n");
err = -EFAULT;
- goto err_dma_map;
+ goto err_set_mask;
}
adapter->shared = dma_alloc_coherent(
&adapter->pdev->dev,
@@ -3349,7 +3380,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
}
#endif /* VMXNET3_RSS */
- err = vmxnet3_alloc_pci_resources(adapter, &dma64);
+ err = vmxnet3_alloc_pci_resources(adapter);
if (err < 0)
goto err_alloc_pci;
@@ -3495,7 +3526,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
err_alloc_shared:
dma_unmap_single(&adapter->pdev->dev, adapter->adapter_pa,
sizeof(struct vmxnet3_adapter), PCI_DMA_TODEVICE);
-err_dma_map:
+err_set_mask:
free_netdev(netdev);
return err;
}
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index 59ec340..a2c554f 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -69,10 +69,12 @@
/*
* Version numbers
*/
-#define VMXNET3_DRIVER_VERSION_STRING "1.4.13.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING "1.4.16.0-k"
-/* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */
-#define VMXNET3_DRIVER_VERSION_NUM 0x01040d00
+/* Each byte of this 32-bit integer encodes a version number in
+ * VMXNET3_DRIVER_VERSION_STRING.
+ */
+#define VMXNET3_DRIVER_VERSION_NUM 0x01041000
#if defined(CONFIG_PCI_MSI)
/* RSS only makes sense if MSI-X is supported. */
diff --git a/drivers/net/wireless/atmel/atmel.c b/drivers/net/wireless/atmel/atmel.c
index d122386..b01dc34 100644
--- a/drivers/net/wireless/atmel/atmel.c
+++ b/drivers/net/wireless/atmel/atmel.c
@@ -1482,18 +1482,6 @@ static int atmel_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int atmel_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, atmel_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations atmel_proc_fops = {
- .open = atmel_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static const struct net_device_ops atmel_netdev_ops = {
.ndo_open = atmel_open,
.ndo_stop = atmel_close,
@@ -1614,7 +1602,8 @@ struct net_device *init_atmel_card(unsigned short irq, unsigned long port,
netif_carrier_off(dev);
- if (!proc_create_data("driver/atmel", 0, NULL, &atmel_proc_fops, priv))
+ if (!proc_create_single_data("driver/atmel", 0, NULL, atmel_proc_show,
+ priv))
printk(KERN_WARNING "atmel: unable to create /proc entry.\n");
printk(KERN_INFO "%s: Atmel at76c50x. Version %d.%d. MAC %pM\n",
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
index 9277f4c..94e177d 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c
@@ -459,7 +459,7 @@ static void brcmf_fw_free_request(struct brcmf_fw_request *req)
kfree(req);
}
-static void brcmf_fw_request_nvram_done(const struct firmware *fw, void *ctx)
+static int brcmf_fw_request_nvram_done(const struct firmware *fw, void *ctx)
{
struct brcmf_fw *fwctx = ctx;
struct brcmf_fw_item *cur;
@@ -498,13 +498,10 @@ static void brcmf_fw_request_nvram_done(const struct firmware *fw, void *ctx)
brcmf_dbg(TRACE, "nvram %p len %d\n", nvram, nvram_length);
cur->nv_data.data = nvram;
cur->nv_data.len = nvram_length;
- return;
+ return 0;
fail:
- brcmf_dbg(TRACE, "failed: dev=%s\n", dev_name(fwctx->dev));
- fwctx->done(fwctx->dev, -ENOENT, NULL);
- brcmf_fw_free_request(fwctx->req);
- kfree(fwctx);
+ return -ENOENT;
}
static int brcmf_fw_request_next_item(struct brcmf_fw *fwctx, bool async)
@@ -553,20 +550,27 @@ static void brcmf_fw_request_done(const struct firmware *fw, void *ctx)
brcmf_dbg(TRACE, "enter: firmware %s %sfound\n", cur->path,
fw ? "" : "not ");
- if (fw) {
- if (cur->type == BRCMF_FW_TYPE_BINARY)
- cur->binary = fw;
- else if (cur->type == BRCMF_FW_TYPE_NVRAM)
- brcmf_fw_request_nvram_done(fw, fwctx);
- else
- release_firmware(fw);
- } else if (cur->type == BRCMF_FW_TYPE_NVRAM) {
- brcmf_fw_request_nvram_done(NULL, fwctx);
- } else if (!(cur->flags & BRCMF_FW_REQF_OPTIONAL)) {
+ if (!fw)
ret = -ENOENT;
+
+ switch (cur->type) {
+ case BRCMF_FW_TYPE_NVRAM:
+ ret = brcmf_fw_request_nvram_done(fw, fwctx);
+ break;
+ case BRCMF_FW_TYPE_BINARY:
+ cur->binary = fw;
+ break;
+ default:
+ /* something fishy here so bail out early */
+ brcmf_err("unknown fw type: %d\n", cur->type);
+ release_firmware(fw);
+ ret = -EINVAL;
goto fail;
}
+ if (ret < 0 && !(cur->flags & BRCMF_FW_REQF_OPTIONAL))
+ goto fail;
+
do {
if (++fwctx->curpos == fwctx->req->n_items) {
ret = 0;
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
index 7af3a0f5..a17c4a7 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
@@ -8,6 +8,7 @@
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
@@ -30,7 +31,7 @@
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
@@ -749,13 +750,9 @@ struct iwl_scan_req_umac {
} __packed;
#define IWL_SCAN_REQ_UMAC_SIZE_V8 sizeof(struct iwl_scan_req_umac)
-#define IWL_SCAN_REQ_UMAC_SIZE_V7 (sizeof(struct iwl_scan_req_umac) - \
- 4 * sizeof(u8))
-#define IWL_SCAN_REQ_UMAC_SIZE_V6 (sizeof(struct iwl_scan_req_umac) - \
- 2 * sizeof(u8) - sizeof(__le16))
-#define IWL_SCAN_REQ_UMAC_SIZE_V1 (sizeof(struct iwl_scan_req_umac) - \
- 2 * sizeof(__le32) - 2 * sizeof(u8) - \
- sizeof(__le16))
+#define IWL_SCAN_REQ_UMAC_SIZE_V7 48
+#define IWL_SCAN_REQ_UMAC_SIZE_V6 44
+#define IWL_SCAN_REQ_UMAC_SIZE_V1 36
/**
* struct iwl_umac_scan_abort
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 8928613..ca017468 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -76,6 +76,7 @@
#include "iwl-io.h"
#include "iwl-csr.h"
#include "fw/acpi.h"
+#include "fw/api/nvm-reg.h"
/* NVM offsets (in words) definitions */
enum nvm_offsets {
@@ -146,8 +147,8 @@ static const u8 iwl_ext_nvm_channels[] = {
149, 153, 157, 161, 165, 169, 173, 177, 181
};
-#define IWL_NUM_CHANNELS ARRAY_SIZE(iwl_nvm_channels)
-#define IWL_NUM_CHANNELS_EXT ARRAY_SIZE(iwl_ext_nvm_channels)
+#define IWL_NVM_NUM_CHANNELS ARRAY_SIZE(iwl_nvm_channels)
+#define IWL_NVM_NUM_CHANNELS_EXT ARRAY_SIZE(iwl_ext_nvm_channels)
#define NUM_2GHZ_CHANNELS 14
#define NUM_2GHZ_CHANNELS_EXT 14
#define FIRST_2GHZ_HT_MINUS 5
@@ -301,11 +302,11 @@ static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg,
const u8 *nvm_chan;
if (cfg->nvm_type != IWL_NVM_EXT) {
- num_of_ch = IWL_NUM_CHANNELS;
+ num_of_ch = IWL_NVM_NUM_CHANNELS;
nvm_chan = &iwl_nvm_channels[0];
num_2ghz_channels = NUM_2GHZ_CHANNELS;
} else {
- num_of_ch = IWL_NUM_CHANNELS_EXT;
+ num_of_ch = IWL_NVM_NUM_CHANNELS_EXT;
nvm_chan = &iwl_ext_nvm_channels[0];
num_2ghz_channels = NUM_2GHZ_CHANNELS_EXT;
}
@@ -720,12 +721,12 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
if (cfg->nvm_type != IWL_NVM_EXT)
data = kzalloc(sizeof(*data) +
sizeof(struct ieee80211_channel) *
- IWL_NUM_CHANNELS,
+ IWL_NVM_NUM_CHANNELS,
GFP_KERNEL);
else
data = kzalloc(sizeof(*data) +
sizeof(struct ieee80211_channel) *
- IWL_NUM_CHANNELS_EXT,
+ IWL_NVM_NUM_CHANNELS_EXT,
GFP_KERNEL);
if (!data)
return NULL;
@@ -842,24 +843,34 @@ static u32 iwl_nvm_get_regdom_bw_flags(const u8 *nvm_chan,
return flags;
}
+struct regdb_ptrs {
+ struct ieee80211_wmm_rule *rule;
+ u32 token;
+};
+
struct ieee80211_regdomain *
iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
- int num_of_ch, __le32 *channels, u16 fw_mcc)
+ int num_of_ch, __le32 *channels, u16 fw_mcc,
+ u16 geo_info)
{
int ch_idx;
u16 ch_flags;
u32 reg_rule_flags, prev_reg_rule_flags = 0;
const u8 *nvm_chan = cfg->nvm_type == IWL_NVM_EXT ?
iwl_ext_nvm_channels : iwl_nvm_channels;
- struct ieee80211_regdomain *regd;
- int size_of_regd;
+ struct ieee80211_regdomain *regd, *copy_rd;
+ int size_of_regd, regd_to_copy, wmms_to_copy;
+ int size_of_wmms = 0;
struct ieee80211_reg_rule *rule;
+ struct ieee80211_wmm_rule *wmm_rule, *d_wmm, *s_wmm;
+ struct regdb_ptrs *regdb_ptrs;
enum nl80211_band band;
int center_freq, prev_center_freq = 0;
- int valid_rules = 0;
+ int valid_rules = 0, n_wmms = 0;
+ int i;
bool new_rule;
int max_num_ch = cfg->nvm_type == IWL_NVM_EXT ?
- IWL_NUM_CHANNELS_EXT : IWL_NUM_CHANNELS;
+ IWL_NVM_NUM_CHANNELS_EXT : IWL_NVM_NUM_CHANNELS;
if (WARN_ON_ONCE(num_of_ch > NL80211_MAX_SUPP_REG_RULES))
return ERR_PTR(-EINVAL);
@@ -875,10 +886,26 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
sizeof(struct ieee80211_regdomain) +
num_of_ch * sizeof(struct ieee80211_reg_rule);
- regd = kzalloc(size_of_regd, GFP_KERNEL);
+ if (geo_info & GEO_WMM_ETSI_5GHZ_INFO)
+ size_of_wmms =
+ num_of_ch * sizeof(struct ieee80211_wmm_rule);
+
+ regd = kzalloc(size_of_regd + size_of_wmms, GFP_KERNEL);
if (!regd)
return ERR_PTR(-ENOMEM);
+ regdb_ptrs = kcalloc(num_of_ch, sizeof(*regdb_ptrs), GFP_KERNEL);
+ if (!regdb_ptrs) {
+ copy_rd = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+
+ /* set alpha2 from FW. */
+ regd->alpha2[0] = fw_mcc >> 8;
+ regd->alpha2[1] = fw_mcc & 0xff;
+
+ wmm_rule = (struct ieee80211_wmm_rule *)((u8 *)regd + size_of_regd);
+
for (ch_idx = 0; ch_idx < num_of_ch; ch_idx++) {
ch_flags = (u16)__le32_to_cpup(channels + ch_idx);
band = (ch_idx < NUM_2GHZ_CHANNELS) ?
@@ -927,14 +954,66 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
iwl_nvm_print_channel_flags(dev, IWL_DL_LAR,
nvm_chan[ch_idx], ch_flags);
+
+ if (!(geo_info & GEO_WMM_ETSI_5GHZ_INFO) ||
+ band == NL80211_BAND_2GHZ)
+ continue;
+
+ if (!reg_query_regdb_wmm(regd->alpha2, center_freq,
+ ®db_ptrs[n_wmms].token, wmm_rule)) {
+ /* Add only new rules */
+ for (i = 0; i < n_wmms; i++) {
+ if (regdb_ptrs[i].token ==
+ regdb_ptrs[n_wmms].token) {
+ rule->wmm_rule = regdb_ptrs[i].rule;
+ break;
+ }
+ }
+ if (i == n_wmms) {
+ rule->wmm_rule = wmm_rule;
+ regdb_ptrs[n_wmms++].rule = wmm_rule;
+ wmm_rule++;
+ }
+ }
}
regd->n_reg_rules = valid_rules;
+ regd->n_wmm_rules = n_wmms;
- /* set alpha2 from FW. */
- regd->alpha2[0] = fw_mcc >> 8;
- regd->alpha2[1] = fw_mcc & 0xff;
+ /*
+ * Narrow down regdom for unused regulatory rules to prevent hole
+ * between reg rules to wmm rules.
+ */
+ regd_to_copy = sizeof(struct ieee80211_regdomain) +
+ valid_rules * sizeof(struct ieee80211_reg_rule);
- return regd;
+ wmms_to_copy = sizeof(struct ieee80211_wmm_rule) * n_wmms;
+
+ copy_rd = kzalloc(regd_to_copy + wmms_to_copy, GFP_KERNEL);
+ if (!copy_rd) {
+ copy_rd = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+
+ memcpy(copy_rd, regd, regd_to_copy);
+ memcpy((u8 *)copy_rd + regd_to_copy, (u8 *)regd + size_of_regd,
+ wmms_to_copy);
+
+ d_wmm = (struct ieee80211_wmm_rule *)((u8 *)copy_rd + regd_to_copy);
+ s_wmm = (struct ieee80211_wmm_rule *)((u8 *)regd + size_of_regd);
+
+ for (i = 0; i < regd->n_reg_rules; i++) {
+ if (!regd->reg_rules[i].wmm_rule)
+ continue;
+
+ copy_rd->reg_rules[i].wmm_rule = d_wmm +
+ (regd->reg_rules[i].wmm_rule - s_wmm) /
+ sizeof(struct ieee80211_wmm_rule);
+ }
+
+out:
+ kfree(regdb_ptrs);
+ kfree(regd);
+ return copy_rd;
}
IWL_EXPORT_SYMBOL(iwl_parse_nvm_mcc_info);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
index 306736c..3071a23b 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
@@ -101,12 +101,14 @@ void iwl_init_sbands(struct device *dev, const struct iwl_cfg *cfg,
*
* This function parses the regulatory channel data received as a
* MCC_UPDATE_CMD command. It returns a newly allocation regulatory domain,
- * to be fed into the regulatory core. An ERR_PTR is returned on error.
+ * to be fed into the regulatory core. In case the geo_info is set handle
+ * accordingly. An ERR_PTR is returned on error.
* If not given to the regulatory core, the user is responsible for freeing
* the regdomain returned here with kfree.
*/
struct ieee80211_regdomain *
iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
- int num_of_ch, __le32 *channels, u16 fw_mcc);
+ int num_of_ch, __le32 *channels, u16 fw_mcc,
+ u16 geo_info);
#endif /* __iwl_nvm_parse_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 51b3042..90f8c89 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -311,7 +311,8 @@ struct ieee80211_regdomain *iwl_mvm_get_regdomain(struct wiphy *wiphy,
regd = iwl_parse_nvm_mcc_info(mvm->trans->dev, mvm->cfg,
__le32_to_cpu(resp->n_channels),
resp->channels,
- __le16_to_cpu(resp->mcc));
+ __le16_to_cpu(resp->mcc),
+ __le16_to_cpu(resp->geo_info));
/* Store the return source id */
src_id = resp->source_id;
kfree(resp);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index f8a0234..5517ea4 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -1590,14 +1590,13 @@ static void iwl_pcie_set_interrupt_capa(struct pci_dev *pdev,
struct iwl_trans *trans)
{
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
- int max_irqs, num_irqs, i, ret, nr_online_cpus;
+ int max_irqs, num_irqs, i, ret;
u16 pci_cmd;
if (!trans->cfg->mq_rx_supported)
goto enable_msi;
- nr_online_cpus = num_online_cpus();
- max_irqs = min_t(u32, nr_online_cpus + 2, IWL_MAX_RX_HW_QUEUES);
+ max_irqs = min_t(u32, num_online_cpus() + 2, IWL_MAX_RX_HW_QUEUES);
for (i = 0; i < max_irqs; i++)
trans_pcie->msix_entries[i].entry = i;
@@ -1623,16 +1622,17 @@ static void iwl_pcie_set_interrupt_capa(struct pci_dev *pdev,
* Two interrupts less: non rx causes shared with FBQ and RSS.
* More than two interrupts: we will use fewer RSS queues.
*/
- if (num_irqs <= nr_online_cpus) {
+ if (num_irqs <= max_irqs - 2) {
trans_pcie->trans->num_rx_queues = num_irqs + 1;
trans_pcie->shared_vec_mask = IWL_SHARED_IRQ_NON_RX |
IWL_SHARED_IRQ_FIRST_RSS;
- } else if (num_irqs == nr_online_cpus + 1) {
+ } else if (num_irqs == max_irqs - 1) {
trans_pcie->trans->num_rx_queues = num_irqs;
trans_pcie->shared_vec_mask = IWL_SHARED_IRQ_NON_RX;
} else {
trans_pcie->trans->num_rx_queues = num_irqs - 1;
}
+ WARN_ON(trans_pcie->trans->num_rx_queues > IWL_MAX_RX_HW_QUEUES);
trans_pcie->alloc_vecs = num_irqs;
trans_pcie->msix_enabled = true;
diff --git a/drivers/net/wireless/intersil/hostap/hostap_ap.c b/drivers/net/wireless/intersil/hostap/hostap_ap.c
index b4dfe189..d1884b8 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_ap.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_ap.c
@@ -69,7 +69,7 @@ static void prism2_send_mgmt(struct net_device *dev,
#ifndef PRISM2_NO_PROCFS_DEBUG
static int ap_debug_proc_show(struct seq_file *m, void *v)
{
- struct ap_data *ap = m->private;
+ struct ap_data *ap = PDE_DATA(file_inode(m->file));
seq_printf(m, "BridgedUnicastFrames=%u\n", ap->bridged_unicast);
seq_printf(m, "BridgedMulticastFrames=%u\n", ap->bridged_multicast);
@@ -81,18 +81,6 @@ static int ap_debug_proc_show(struct seq_file *m, void *v)
seq_printf(m, "tx_drop_nonassoc=%u\n", ap->tx_drop_nonassoc);
return 0;
}
-
-static int ap_debug_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ap_debug_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations ap_debug_proc_fops = {
- .open = ap_debug_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif /* PRISM2_NO_PROCFS_DEBUG */
@@ -333,7 +321,7 @@ void hostap_deauth_all_stas(struct net_device *dev, struct ap_data *ap,
static int ap_control_proc_show(struct seq_file *m, void *v)
{
- struct ap_data *ap = m->private;
+ struct ap_data *ap = PDE_DATA(file_inode(m->file));
char *policy_txt;
struct mac_entry *entry;
@@ -365,20 +353,20 @@ static int ap_control_proc_show(struct seq_file *m, void *v)
static void *ap_control_proc_start(struct seq_file *m, loff_t *_pos)
{
- struct ap_data *ap = m->private;
+ struct ap_data *ap = PDE_DATA(file_inode(m->file));
spin_lock_bh(&ap->mac_restrictions.lock);
return seq_list_start_head(&ap->mac_restrictions.mac_list, *_pos);
}
static void *ap_control_proc_next(struct seq_file *m, void *v, loff_t *_pos)
{
- struct ap_data *ap = m->private;
+ struct ap_data *ap = PDE_DATA(file_inode(m->file));
return seq_list_next(v, &ap->mac_restrictions.mac_list, _pos);
}
static void ap_control_proc_stop(struct seq_file *m, void *v)
{
- struct ap_data *ap = m->private;
+ struct ap_data *ap = PDE_DATA(file_inode(m->file));
spin_unlock_bh(&ap->mac_restrictions.lock);
}
@@ -389,24 +377,6 @@ static const struct seq_operations ap_control_proc_seqops = {
.show = ap_control_proc_show,
};
-static int ap_control_proc_open(struct inode *inode, struct file *file)
-{
- int ret = seq_open(file, &ap_control_proc_seqops);
- if (ret == 0) {
- struct seq_file *m = file->private_data;
- m->private = PDE_DATA(inode);
- }
- return ret;
-}
-
-static const struct file_operations ap_control_proc_fops = {
- .open = ap_control_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-
int ap_control_add_mac(struct mac_restrictions *mac_restrictions, u8 *mac)
{
struct mac_entry *entry;
@@ -585,20 +555,20 @@ static int prism2_ap_proc_show(struct seq_file *m, void *v)
static void *prism2_ap_proc_start(struct seq_file *m, loff_t *_pos)
{
- struct ap_data *ap = m->private;
+ struct ap_data *ap = PDE_DATA(file_inode(m->file));
spin_lock_bh(&ap->sta_table_lock);
return seq_list_start_head(&ap->sta_list, *_pos);
}
static void *prism2_ap_proc_next(struct seq_file *m, void *v, loff_t *_pos)
{
- struct ap_data *ap = m->private;
+ struct ap_data *ap = PDE_DATA(file_inode(m->file));
return seq_list_next(v, &ap->sta_list, _pos);
}
static void prism2_ap_proc_stop(struct seq_file *m, void *v)
{
- struct ap_data *ap = m->private;
+ struct ap_data *ap = PDE_DATA(file_inode(m->file));
spin_unlock_bh(&ap->sta_table_lock);
}
@@ -608,23 +578,6 @@ static const struct seq_operations prism2_ap_proc_seqops = {
.stop = prism2_ap_proc_stop,
.show = prism2_ap_proc_show,
};
-
-static int prism2_ap_proc_open(struct inode *inode, struct file *file)
-{
- int ret = seq_open(file, &prism2_ap_proc_seqops);
- if (ret == 0) {
- struct seq_file *m = file->private_data;
- m->private = PDE_DATA(inode);
- }
- return ret;
-}
-
-static const struct file_operations prism2_ap_proc_fops = {
- .open = prism2_ap_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
@@ -896,12 +849,13 @@ void hostap_init_ap_proc(local_info_t *local)
return;
#ifndef PRISM2_NO_PROCFS_DEBUG
- proc_create_data("ap_debug", 0, ap->proc, &ap_debug_proc_fops, ap);
+ proc_create_single_data("ap_debug", 0, ap->proc, ap_debug_proc_show, ap);
#endif /* PRISM2_NO_PROCFS_DEBUG */
#ifndef PRISM2_NO_KERNEL_IEEE80211_MGMT
- proc_create_data("ap_control", 0, ap->proc, &ap_control_proc_fops, ap);
- proc_create_data("ap", 0, ap->proc, &prism2_ap_proc_fops, ap);
+ proc_create_seq_data("ap_control", 0, ap->proc, &ap_control_proc_seqops,
+ ap);
+ proc_create_seq_data("ap", 0, ap->proc, &prism2_ap_proc_seqops, ap);
#endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
}
@@ -1106,18 +1060,6 @@ static int prism2_sta_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int prism2_sta_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, prism2_sta_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations prism2_sta_proc_fops = {
- .open = prism2_sta_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static void handle_add_proc_queue(struct work_struct *work)
{
struct ap_data *ap = container_of(work, struct ap_data,
@@ -1138,9 +1080,9 @@ static void handle_add_proc_queue(struct work_struct *work)
if (sta) {
sprintf(name, "%pM", sta->addr);
- sta->proc = proc_create_data(
+ sta->proc = proc_create_single_data(
name, 0, ap->proc,
- &prism2_sta_proc_fops, sta);
+ prism2_sta_proc_show, sta);
atomic_dec(&sta->users);
}
diff --git a/drivers/net/wireless/intersil/hostap/hostap_hw.c b/drivers/net/wireless/intersil/hostap/hostap_hw.c
index 5c4a17a..2720aa39 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_hw.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_hw.c
@@ -2951,19 +2951,6 @@ static int prism2_registers_proc_show(struct seq_file *m, void *v)
return 0;
}
-
-static int prism2_registers_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, prism2_registers_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations prism2_registers_proc_fops = {
- .open = prism2_registers_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
#endif /* PRISM2_NO_PROCFS_DEBUG */
@@ -3279,8 +3266,8 @@ static int hostap_hw_ready(struct net_device *dev)
}
hostap_init_proc(local);
#ifndef PRISM2_NO_PROCFS_DEBUG
- proc_create_data("registers", 0, local->proc,
- &prism2_registers_proc_fops, local);
+ proc_create_single_data("registers", 0, local->proc,
+ prism2_registers_proc_show, local);
#endif /* PRISM2_NO_PROCFS_DEBUG */
hostap_init_ap_proc(local);
return 0;
diff --git a/drivers/net/wireless/intersil/hostap/hostap_proc.c b/drivers/net/wireless/intersil/hostap/hostap_proc.c
index d234231..5b33cca 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_proc.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_proc.c
@@ -43,18 +43,6 @@ static int prism2_debug_proc_show(struct seq_file *m, void *v)
return 0;
}
-
-static int prism2_debug_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, prism2_debug_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations prism2_debug_proc_fops = {
- .open = prism2_debug_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif /* PRISM2_NO_PROCFS_DEBUG */
@@ -95,19 +83,6 @@ static int prism2_stats_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int prism2_stats_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, prism2_stats_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations prism2_stats_proc_fops = {
- .open = prism2_stats_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-
static int prism2_wds_proc_show(struct seq_file *m, void *v)
{
struct list_head *ptr = v;
@@ -122,20 +97,20 @@ static int prism2_wds_proc_show(struct seq_file *m, void *v)
static void *prism2_wds_proc_start(struct seq_file *m, loff_t *_pos)
{
- local_info_t *local = m->private;
+ local_info_t *local = PDE_DATA(file_inode(m->file));
read_lock_bh(&local->iface_lock);
return seq_list_start(&local->hostap_interfaces, *_pos);
}
static void *prism2_wds_proc_next(struct seq_file *m, void *v, loff_t *_pos)
{
- local_info_t *local = m->private;
+ local_info_t *local = PDE_DATA(file_inode(m->file));
return seq_list_next(v, &local->hostap_interfaces, _pos);
}
static void prism2_wds_proc_stop(struct seq_file *m, void *v)
{
- local_info_t *local = m->private;
+ local_info_t *local = PDE_DATA(file_inode(m->file));
read_unlock_bh(&local->iface_lock);
}
@@ -146,27 +121,9 @@ static const struct seq_operations prism2_wds_proc_seqops = {
.show = prism2_wds_proc_show,
};
-static int prism2_wds_proc_open(struct inode *inode, struct file *file)
-{
- int ret = seq_open(file, &prism2_wds_proc_seqops);
- if (ret == 0) {
- struct seq_file *m = file->private_data;
- m->private = PDE_DATA(inode);
- }
- return ret;
-}
-
-static const struct file_operations prism2_wds_proc_fops = {
- .open = prism2_wds_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-
static int prism2_bss_list_proc_show(struct seq_file *m, void *v)
{
- local_info_t *local = m->private;
+ local_info_t *local = PDE_DATA(file_inode(m->file));
struct list_head *ptr = v;
struct hostap_bss_info *bss;
@@ -193,20 +150,20 @@ static int prism2_bss_list_proc_show(struct seq_file *m, void *v)
static void *prism2_bss_list_proc_start(struct seq_file *m, loff_t *_pos)
{
- local_info_t *local = m->private;
+ local_info_t *local = PDE_DATA(file_inode(m->file));
spin_lock_bh(&local->lock);
return seq_list_start_head(&local->bss_list, *_pos);
}
static void *prism2_bss_list_proc_next(struct seq_file *m, void *v, loff_t *_pos)
{
- local_info_t *local = m->private;
+ local_info_t *local = PDE_DATA(file_inode(m->file));
return seq_list_next(v, &local->bss_list, _pos);
}
static void prism2_bss_list_proc_stop(struct seq_file *m, void *v)
{
- local_info_t *local = m->private;
+ local_info_t *local = PDE_DATA(file_inode(m->file));
spin_unlock_bh(&local->lock);
}
@@ -217,24 +174,6 @@ static const struct seq_operations prism2_bss_list_proc_seqops = {
.show = prism2_bss_list_proc_show,
};
-static int prism2_bss_list_proc_open(struct inode *inode, struct file *file)
-{
- int ret = seq_open(file, &prism2_bss_list_proc_seqops);
- if (ret == 0) {
- struct seq_file *m = file->private_data;
- m->private = PDE_DATA(inode);
- }
- return ret;
-}
-
-static const struct file_operations prism2_bss_list_proc_fops = {
- .open = prism2_bss_list_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-
static int prism2_crypt_proc_show(struct seq_file *m, void *v)
{
local_info_t *local = m->private;
@@ -252,19 +191,6 @@ static int prism2_crypt_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int prism2_crypt_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, prism2_crypt_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations prism2_crypt_proc_fops = {
- .open = prism2_crypt_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-
static ssize_t prism2_pda_proc_read(struct file *file, char __user *buf,
size_t count, loff_t *_pos)
{
@@ -342,7 +268,7 @@ static int prism2_io_debug_proc_read(char *page, char **start, off_t off,
#ifndef PRISM2_NO_STATION_MODES
static int prism2_scan_results_proc_show(struct seq_file *m, void *v)
{
- local_info_t *local = m->private;
+ local_info_t *local = PDE_DATA(file_inode(m->file));
unsigned long entry;
int i, len;
struct hfa384x_hostscan_result *scanres;
@@ -392,7 +318,7 @@ static int prism2_scan_results_proc_show(struct seq_file *m, void *v)
static void *prism2_scan_results_proc_start(struct seq_file *m, loff_t *_pos)
{
- local_info_t *local = m->private;
+ local_info_t *local = PDE_DATA(file_inode(m->file));
spin_lock_bh(&local->lock);
/* We have a header (pos 0) + N results to show (pos 1...N) */
@@ -403,7 +329,7 @@ static void *prism2_scan_results_proc_start(struct seq_file *m, loff_t *_pos)
static void *prism2_scan_results_proc_next(struct seq_file *m, void *v, loff_t *_pos)
{
- local_info_t *local = m->private;
+ local_info_t *local = PDE_DATA(file_inode(m->file));
++*_pos;
if (*_pos > local->last_scan_results_count)
@@ -413,7 +339,7 @@ static void *prism2_scan_results_proc_next(struct seq_file *m, void *v, loff_t *
static void prism2_scan_results_proc_stop(struct seq_file *m, void *v)
{
- local_info_t *local = m->private;
+ local_info_t *local = PDE_DATA(file_inode(m->file));
spin_unlock_bh(&local->lock);
}
@@ -423,25 +349,6 @@ static const struct seq_operations prism2_scan_results_proc_seqops = {
.stop = prism2_scan_results_proc_stop,
.show = prism2_scan_results_proc_show,
};
-
-static int prism2_scan_results_proc_open(struct inode *inode, struct file *file)
-{
- int ret = seq_open(file, &prism2_scan_results_proc_seqops);
- if (ret == 0) {
- struct seq_file *m = file->private_data;
- m->private = PDE_DATA(inode);
- }
- return ret;
-}
-
-static const struct file_operations prism2_scan_results_proc_fops = {
- .open = prism2_scan_results_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-
#endif /* PRISM2_NO_STATION_MODES */
@@ -463,29 +370,29 @@ void hostap_init_proc(local_info_t *local)
}
#ifndef PRISM2_NO_PROCFS_DEBUG
- proc_create_data("debug", 0, local->proc,
- &prism2_debug_proc_fops, local);
+ proc_create_single_data("debug", 0, local->proc,
+ prism2_debug_proc_show, local);
#endif /* PRISM2_NO_PROCFS_DEBUG */
- proc_create_data("stats", 0, local->proc,
- &prism2_stats_proc_fops, local);
- proc_create_data("wds", 0, local->proc,
- &prism2_wds_proc_fops, local);
+ proc_create_single_data("stats", 0, local->proc, prism2_stats_proc_show,
+ local);
+ proc_create_seq_data("wds", 0, local->proc,
+ &prism2_wds_proc_seqops, local);
proc_create_data("pda", 0, local->proc,
&prism2_pda_proc_fops, local);
proc_create_data("aux_dump", 0, local->proc,
local->func->read_aux_fops ?: &prism2_aux_dump_proc_fops,
local);
- proc_create_data("bss_list", 0, local->proc,
- &prism2_bss_list_proc_fops, local);
- proc_create_data("crypt", 0, local->proc,
- &prism2_crypt_proc_fops, local);
+ proc_create_seq_data("bss_list", 0, local->proc,
+ &prism2_bss_list_proc_seqops, local);
+ proc_create_single_data("crypt", 0, local->proc, prism2_crypt_proc_show,
+ local);
#ifdef PRISM2_IO_DEBUG
- proc_create_data("io_debug", 0, local->proc,
- &prism2_io_debug_proc_fops, local);
+ proc_create_single_data("io_debug", 0, local->proc,
+ prism2_debug_proc_show, local);
#endif /* PRISM2_IO_DEBUG */
#ifndef PRISM2_NO_STATION_MODES
- proc_create_data("scan_results", 0, local->proc,
- &prism2_scan_results_proc_fops, local);
+ proc_create_seq_data("scan_results", 0, local->proc,
+ &prism2_scan_results_proc_seqops, local);
#endif /* PRISM2_NO_STATION_MODES */
}
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 96d26cf..920c23e 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -3236,6 +3236,7 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info)
GENL_SET_ERR_MSG(info,"MAC is no valid source addr");
NL_SET_BAD_ATTR(info->extack,
info->attrs[HWSIM_ATTR_PERM_ADDR]);
+ kfree(hwname);
return -EINVAL;
}
@@ -3339,7 +3340,7 @@ static int hwsim_get_radio_nl(struct sk_buff *msg, struct genl_info *info)
static int hwsim_dump_radio_nl(struct sk_buff *skb,
struct netlink_callback *cb)
{
- int last_idx = cb->args[0];
+ int last_idx = cb->args[0] - 1;
struct mac80211_hwsim_data *data = NULL;
int res = 0;
void *hdr;
@@ -3367,7 +3368,7 @@ static int hwsim_dump_radio_nl(struct sk_buff *skb,
last_idx = data->idx;
}
- cb->args[0] = last_idx;
+ cb->args[0] = last_idx + 1;
/* list changed, but no new element sent, set interrupted flag */
if (skb->len == 0 && cb->prev_seq && cb->seq != cb->prev_seq) {
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
index a6884e7..7ddee98 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
@@ -372,16 +372,15 @@ static void rt2x00queue_create_tx_descriptor_ht(struct rt2x00_dev *rt2x00dev,
/*
* Determine IFS values
- * - Use TXOP_BACKOFF for probe and management frames except beacons
+ * - Use TXOP_BACKOFF for management frames except beacons
* - Use TXOP_SIFS for fragment bursts
* - Use TXOP_HTTXOP for everything else
*
* Note: rt2800 devices won't use CTS protection (if used)
* for frames not transmitted with TXOP_HTTXOP
*/
- if ((ieee80211_is_mgmt(hdr->frame_control) &&
- !ieee80211_is_beacon(hdr->frame_control)) ||
- (tx_info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE))
+ if (ieee80211_is_mgmt(hdr->frame_control) &&
+ !ieee80211_is_beacon(hdr->frame_control))
txdesc->u.ht.txop = TXOP_BACKOFF;
else if (!(tx_info->flags & IEEE80211_TX_CTL_FIRST_FRAGMENT))
txdesc->u.ht.txop = TXOP_SIFS;
diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c
index 7f9b16b..a7e0a17 100644
--- a/drivers/net/wireless/ray_cs.c
+++ b/drivers/net/wireless/ray_cs.c
@@ -2663,19 +2663,6 @@ static int ray_cs_proc_show(struct seq_file *m, void *v)
}
return 0;
}
-
-static int ray_cs_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ray_cs_proc_show, NULL);
-}
-
-static const struct file_operations ray_cs_proc_fops = {
- .owner = THIS_MODULE,
- .open = ray_cs_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif
/*===========================================================================*/
static int build_auth_frame(ray_dev_t *local, UCHAR *dest, int auth_type)
@@ -2814,7 +2801,7 @@ static int __init init_ray_cs(void)
#ifdef CONFIG_PROC_FS
proc_mkdir("driver/ray_cs", NULL);
- proc_create("driver/ray_cs/ray_cs", 0, NULL, &ray_cs_proc_fops);
+ proc_create_single("driver/ray_cs/ray_cs", 0, NULL, ray_cs_proc_show);
proc_create("driver/ray_cs/essid", 0200, NULL, &ray_cs_essid_proc_fops);
proc_create_data("driver/ray_cs/net_type", 0200, NULL, &int_proc_fops,
&net_type);
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c
index 8b6b07a..b026e80 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c
@@ -158,16 +158,6 @@ static u8 halbtc_get_wifi_central_chnl(struct btc_coexist *btcoexist)
static u8 rtl_get_hwpg_single_ant_path(struct rtl_priv *rtlpriv)
{
- struct rtl_mod_params *mod_params = rtlpriv->cfg->mod_params;
-
- /* override ant_num / ant_path */
- if (mod_params->ant_sel) {
- rtlpriv->btcoexist.btc_info.ant_num =
- (mod_params->ant_sel == 1 ? ANT_X2 : ANT_X1);
-
- rtlpriv->btcoexist.btc_info.single_ant_path =
- (mod_params->ant_sel == 1 ? 0 : 1);
- }
return rtlpriv->btcoexist.btc_info.single_ant_path;
}
@@ -178,7 +168,6 @@ static u8 rtl_get_hwpg_bt_type(struct rtl_priv *rtlpriv)
static u8 rtl_get_hwpg_ant_num(struct rtl_priv *rtlpriv)
{
- struct rtl_mod_params *mod_params = rtlpriv->cfg->mod_params;
u8 num;
if (rtlpriv->btcoexist.btc_info.ant_num == ANT_X2)
@@ -186,10 +175,6 @@ static u8 rtl_get_hwpg_ant_num(struct rtl_priv *rtlpriv)
else
num = 1;
- /* override ant_num / ant_path */
- if (mod_params->ant_sel)
- num = (mod_params->ant_sel == 1 ? ANT_X2 : ANT_X1) + 1;
-
return num;
}
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c
index e7bbbc9..b4f3f91 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c
@@ -848,6 +848,9 @@ static bool _rtl8723be_init_mac(struct ieee80211_hw *hw)
return false;
}
+ if (rtlpriv->cfg->ops->get_btc_status())
+ rtlpriv->btcoexist.btc_ops->btc_power_on_setting(rtlpriv);
+
bytetmp = rtl_read_byte(rtlpriv, REG_MULTI_FUNC_CTRL);
rtl_write_byte(rtlpriv, REG_MULTI_FUNC_CTRL, bytetmp | BIT(3));
@@ -2696,21 +2699,21 @@ void rtl8723be_read_bt_coexist_info_from_hwpg(struct ieee80211_hw *hw,
rtlpriv->btcoexist.btc_info.bt_type = BT_RTL8723B;
rtlpriv->btcoexist.btc_info.ant_num = (value & 0x1);
rtlpriv->btcoexist.btc_info.single_ant_path =
- (value & 0x40); /*0xc3[6]*/
+ (value & 0x40 ? ANT_AUX : ANT_MAIN); /*0xc3[6]*/
} else {
rtlpriv->btcoexist.btc_info.btcoexist = 0;
rtlpriv->btcoexist.btc_info.bt_type = BT_RTL8723B;
rtlpriv->btcoexist.btc_info.ant_num = ANT_X2;
- rtlpriv->btcoexist.btc_info.single_ant_path = 0;
+ rtlpriv->btcoexist.btc_info.single_ant_path = ANT_MAIN;
}
/* override ant_num / ant_path */
if (mod_params->ant_sel) {
rtlpriv->btcoexist.btc_info.ant_num =
- (mod_params->ant_sel == 1 ? ANT_X2 : ANT_X1);
+ (mod_params->ant_sel == 1 ? ANT_X1 : ANT_X2);
rtlpriv->btcoexist.btc_info.single_ant_path =
- (mod_params->ant_sel == 1 ? 0 : 1);
+ (mod_params->ant_sel == 1 ? ANT_AUX : ANT_MAIN);
}
}
diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h
index d27e339..ce17540 100644
--- a/drivers/net/wireless/realtek/rtlwifi/wifi.h
+++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h
@@ -2823,6 +2823,11 @@ enum bt_ant_num {
ANT_X1 = 1,
};
+enum bt_ant_path {
+ ANT_MAIN = 0,
+ ANT_AUX = 1,
+};
+
enum bt_co_type {
BT_2WIRE = 0,
BT_ISSC_3WIRE = 1,
diff --git a/drivers/nubus/proc.c b/drivers/nubus/proc.c
index c2e5a7e..88e1f9a 100644
--- a/drivers/nubus/proc.c
+++ b/drivers/nubus/proc.c
@@ -45,18 +45,6 @@ nubus_devices_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int nubus_devices_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, nubus_devices_proc_show, NULL);
-}
-
-static const struct file_operations nubus_devices_proc_fops = {
- .open = nubus_devices_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static struct proc_dir_entry *proc_bus_nubus_dir;
/*
@@ -149,18 +137,6 @@ static int nubus_proc_rsrc_show(struct seq_file *m, void *v)
return 0;
}
-static int nubus_proc_rsrc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, nubus_proc_rsrc_show, inode);
-}
-
-static const struct file_operations nubus_proc_rsrc_fops = {
- .open = nubus_proc_rsrc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
void nubus_proc_add_rsrc_mem(struct proc_dir_entry *procdir,
const struct nubus_dirent *ent,
unsigned int size)
@@ -176,8 +152,8 @@ void nubus_proc_add_rsrc_mem(struct proc_dir_entry *procdir,
pde_data = nubus_proc_alloc_pde_data(nubus_dirptr(ent), size);
else
pde_data = NULL;
- proc_create_data(name, S_IFREG | 0444, procdir,
- &nubus_proc_rsrc_fops, pde_data);
+ proc_create_single_data(name, S_IFREG | 0444, procdir,
+ nubus_proc_rsrc_show, pde_data);
}
void nubus_proc_add_rsrc(struct proc_dir_entry *procdir,
@@ -190,32 +166,21 @@ void nubus_proc_add_rsrc(struct proc_dir_entry *procdir,
return;
snprintf(name, sizeof(name), "%x", ent->type);
- proc_create_data(name, S_IFREG | 0444, procdir,
- &nubus_proc_rsrc_fops,
- nubus_proc_alloc_pde_data(data, 0));
+ proc_create_single_data(name, S_IFREG | 0444, procdir,
+ nubus_proc_rsrc_show,
+ nubus_proc_alloc_pde_data(data, 0));
}
/*
* /proc/nubus stuff
*/
-static int nubus_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, nubus_proc_show, NULL);
-}
-
-static const struct file_operations nubus_proc_fops = {
- .open = nubus_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
void __init nubus_proc_init(void)
{
- proc_create("nubus", 0, NULL, &nubus_proc_fops);
+ proc_create_single("nubus", 0, NULL, nubus_proc_show);
proc_bus_nubus_dir = proc_mkdir("bus/nubus", NULL);
if (!proc_bus_nubus_dir)
return;
- proc_create("devices", 0, proc_bus_nubus_dir, &nubus_devices_proc_fops);
+ proc_create_single("devices", 0, proc_bus_nubus_dir,
+ nubus_devices_proc_show);
}
diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig
index 8599718..9d36473 100644
--- a/drivers/nvdimm/Kconfig
+++ b/drivers/nvdimm/Kconfig
@@ -103,8 +103,7 @@
Select Y if unsure
config OF_PMEM
- # FIXME: make tristate once OF_NUMA dependency removed
- bool "Device-tree support for persistent memory regions"
+ tristate "Device-tree support for persistent memory regions"
depends on OF
default LIBNVDIMM
help
diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c
index 3085227..2e96b34 100644
--- a/drivers/nvdimm/claim.c
+++ b/drivers/nvdimm/claim.c
@@ -276,7 +276,8 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns,
if (rw == READ) {
if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align)))
return -EIO;
- return memcpy_mcsafe(buf, nsio->addr + offset, size);
+ if (memcpy_mcsafe(buf, nsio->addr + offset, size) != 0)
+ return -EIO;
}
if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align))) {
diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c
index e00d455..8d348b2 100644
--- a/drivers/nvdimm/dimm_devs.c
+++ b/drivers/nvdimm/dimm_devs.c
@@ -88,9 +88,9 @@ int nvdimm_init_nsarea(struct nvdimm_drvdata *ndd)
int nvdimm_init_config_data(struct nvdimm_drvdata *ndd)
{
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(ndd->dev);
+ int rc = validate_dimm(ndd), cmd_rc = 0;
struct nd_cmd_get_config_data_hdr *cmd;
struct nvdimm_bus_descriptor *nd_desc;
- int rc = validate_dimm(ndd);
u32 max_cmd_size, config_size;
size_t offset;
@@ -124,9 +124,11 @@ int nvdimm_init_config_data(struct nvdimm_drvdata *ndd)
cmd->in_offset = offset;
rc = nd_desc->ndctl(nd_desc, to_nvdimm(ndd->dev),
ND_CMD_GET_CONFIG_DATA, cmd,
- cmd->in_length + sizeof(*cmd), NULL);
- if (rc || cmd->status) {
- rc = -ENXIO;
+ cmd->in_length + sizeof(*cmd), &cmd_rc);
+ if (rc < 0)
+ break;
+ if (cmd_rc < 0) {
+ rc = cmd_rc;
break;
}
memcpy(ndd->data + offset, cmd->out_buf, cmd->in_length);
@@ -140,9 +142,9 @@ int nvdimm_init_config_data(struct nvdimm_drvdata *ndd)
int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset,
void *buf, size_t len)
{
- int rc = validate_dimm(ndd);
size_t max_cmd_size, buf_offset;
struct nd_cmd_set_config_hdr *cmd;
+ int rc = validate_dimm(ndd), cmd_rc = 0;
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(ndd->dev);
struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
@@ -164,7 +166,6 @@ int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset,
for (buf_offset = 0; len; len -= cmd->in_length,
buf_offset += cmd->in_length) {
size_t cmd_size;
- u32 *status;
cmd->in_offset = offset + buf_offset;
cmd->in_length = min(max_cmd_size, len);
@@ -172,12 +173,13 @@ int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset,
/* status is output in the last 4-bytes of the command buffer */
cmd_size = sizeof(*cmd) + cmd->in_length + sizeof(u32);
- status = ((void *) cmd) + cmd_size - sizeof(u32);
rc = nd_desc->ndctl(nd_desc, to_nvdimm(ndd->dev),
- ND_CMD_SET_CONFIG_DATA, cmd, cmd_size, NULL);
- if (rc || *status) {
- rc = rc ? rc : -ENXIO;
+ ND_CMD_SET_CONFIG_DATA, cmd, cmd_size, &cmd_rc);
+ if (rc < 0)
+ break;
+ if (cmd_rc < 0) {
+ rc = cmd_rc;
break;
}
}
diff --git a/drivers/nvdimm/of_pmem.c b/drivers/nvdimm/of_pmem.c
index 85013ba..0a70183 100644
--- a/drivers/nvdimm/of_pmem.c
+++ b/drivers/nvdimm/of_pmem.c
@@ -67,7 +67,7 @@ static int of_pmem_region_probe(struct platform_device *pdev)
*/
memset(&ndr_desc, 0, sizeof(ndr_desc));
ndr_desc.attr_groups = region_attr_groups;
- ndr_desc.numa_node = of_node_to_nid(np);
+ ndr_desc.numa_node = dev_to_node(&pdev->dev);
ndr_desc.res = &pdev->resource[i];
ndr_desc.of_node = np;
set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 9d71492..e023d6a 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -101,15 +101,15 @@ static blk_status_t read_pmem(struct page *page, unsigned int off,
void *pmem_addr, unsigned int len)
{
unsigned int chunk;
- int rc;
+ unsigned long rem;
void *mem;
while (len) {
mem = kmap_atomic(page);
chunk = min_t(unsigned int, len, PAGE_SIZE);
- rc = memcpy_mcsafe(mem + off, pmem_addr, chunk);
+ rem = memcpy_mcsafe(mem + off, pmem_addr, chunk);
kunmap_atomic(mem);
- if (rc)
+ if (rem)
return BLK_STS_IOERR;
len -= chunk;
off = 0;
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index b979cf3..88a8b59 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -27,7 +27,7 @@
config NVME_RDMA
tristate "NVM Express over Fabrics RDMA host driver"
- depends on INFINIBAND && BLOCK
+ depends on INFINIBAND && INFINIBAND_ADDR_TRANS && BLOCK
select NVME_CORE
select NVME_FABRICS
select SG_POOL
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 9df4f71..c8b3006 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -99,6 +99,16 @@ static struct class *nvme_subsys_class;
static void nvme_ns_remove(struct nvme_ns *ns);
static int nvme_revalidate_disk(struct gendisk *disk);
+static void nvme_put_subsystem(struct nvme_subsystem *subsys);
+
+static void nvme_queue_scan(struct nvme_ctrl *ctrl)
+{
+ /*
+ * Only new queue scan work when admin and IO queues are both alive
+ */
+ if (ctrl->state == NVME_CTRL_LIVE)
+ queue_work(nvme_wq, &ctrl->scan_work);
+}
int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
{
@@ -117,7 +127,8 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
ret = nvme_reset_ctrl(ctrl);
if (!ret) {
flush_work(&ctrl->reset_work);
- if (ctrl->state != NVME_CTRL_LIVE)
+ if (ctrl->state != NVME_CTRL_LIVE &&
+ ctrl->state != NVME_CTRL_ADMIN_ONLY)
ret = -ENETRESET;
}
@@ -242,9 +253,6 @@ EXPORT_SYMBOL_GPL(nvme_complete_rq);
void nvme_cancel_request(struct request *req, void *data, bool reserved)
{
- if (!blk_mq_request_started(req))
- return;
-
dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device,
"Cancelling I/O %d", req->tag);
@@ -349,7 +357,8 @@ static void nvme_free_ns_head(struct kref *ref)
nvme_mpath_remove_disk(head);
ida_simple_remove(&head->subsys->ns_ida, head->instance);
list_del_init(&head->entry);
- cleanup_srcu_struct(&head->srcu);
+ cleanup_srcu_struct_quiesced(&head->srcu);
+ nvme_put_subsystem(head->subsys);
kfree(head);
}
@@ -764,6 +773,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
ret = PTR_ERR(meta);
goto out_unmap;
}
+ req->cmd_flags |= REQ_INTEGRITY;
}
}
@@ -1029,6 +1039,21 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
}
EXPORT_SYMBOL_GPL(nvme_set_queue_count);
+#define NVME_AEN_SUPPORTED \
+ (NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT)
+
+static void nvme_enable_aen(struct nvme_ctrl *ctrl)
+{
+ u32 result;
+ int status;
+
+ status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT,
+ ctrl->oaes & NVME_AEN_SUPPORTED, NULL, 0, &result);
+ if (status)
+ dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n",
+ ctrl->oaes & NVME_AEN_SUPPORTED);
+}
+
static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
{
struct nvme_user_io io;
@@ -1347,13 +1372,19 @@ static void nvme_set_chunk_size(struct nvme_ns *ns)
blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(chunk_size));
}
-static void nvme_config_discard(struct nvme_ctrl *ctrl,
- unsigned stream_alignment, struct request_queue *queue)
+static void nvme_config_discard(struct nvme_ns *ns)
{
+ struct nvme_ctrl *ctrl = ns->ctrl;
+ struct request_queue *queue = ns->queue;
u32 size = queue_logical_block_size(queue);
- if (stream_alignment)
- size *= stream_alignment;
+ if (!(ctrl->oncs & NVME_CTRL_ONCS_DSM)) {
+ blk_queue_flag_clear(QUEUE_FLAG_DISCARD, queue);
+ return;
+ }
+
+ if (ctrl->nr_streams && ns->sws && ns->sgs)
+ size *= ns->sws * ns->sgs;
BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
NVME_DSM_MAX_RANGES);
@@ -1361,9 +1392,12 @@ static void nvme_config_discard(struct nvme_ctrl *ctrl,
queue->limits.discard_alignment = 0;
queue->limits.discard_granularity = size;
+ /* If discard is already enabled, don't reset queue limits */
+ if (blk_queue_flag_test_and_set(QUEUE_FLAG_DISCARD, queue))
+ return;
+
blk_queue_max_discard_sectors(queue, UINT_MAX);
blk_queue_max_discard_segments(queue, NVME_DSM_MAX_RANGES);
- blk_queue_flag_set(QUEUE_FLAG_DISCARD, queue);
if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
@@ -1407,10 +1441,6 @@ static void nvme_update_disk_info(struct gendisk *disk,
{
sector_t capacity = le64_to_cpup(&id->nsze) << (ns->lba_shift - 9);
unsigned short bs = 1 << ns->lba_shift;
- unsigned stream_alignment = 0;
-
- if (ns->ctrl->nr_streams && ns->sws && ns->sgs)
- stream_alignment = ns->sws * ns->sgs;
blk_mq_freeze_queue(disk->queue);
blk_integrity_unregister(disk);
@@ -1424,10 +1454,9 @@ static void nvme_update_disk_info(struct gendisk *disk,
nvme_init_integrity(disk, ns->ms, ns->pi_type);
if (ns->ms && !nvme_ns_has_pi(ns) && !blk_get_integrity(disk))
capacity = 0;
- set_capacity(disk, capacity);
- if (ns->ctrl->oncs & NVME_CTRL_ONCS_DSM)
- nvme_config_discard(ns->ctrl, stream_alignment, disk->queue);
+ set_capacity(disk, capacity);
+ nvme_config_discard(ns);
blk_mq_unfreeze_queue(disk->queue);
}
@@ -1443,8 +1472,8 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
if (ns->lba_shift == 0)
ns->lba_shift = 9;
ns->noiob = le16_to_cpu(id->noiob);
- ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms);
+ ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
/* the PI implementation requires metadata equal t10 pi tuple size */
if (ns->ms == sizeof(struct t10_pi_tuple))
ns->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
@@ -1573,7 +1602,7 @@ static int nvme_pr_reserve(struct block_device *bdev, u64 key,
static int nvme_pr_preempt(struct block_device *bdev, u64 old, u64 new,
enum pr_type type, bool abort)
{
- u32 cdw10 = nvme_pr_type(type) << 8 | abort ? 2 : 1;
+ u32 cdw10 = nvme_pr_type(type) << 8 | (abort ? 2 : 1);
return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_acquire);
}
@@ -1585,7 +1614,7 @@ static int nvme_pr_clear(struct block_device *bdev, u64 key)
static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
{
- u32 cdw10 = nvme_pr_type(type) << 8 | key ? 1 << 3 : 0;
+ u32 cdw10 = nvme_pr_type(type) << 8 | (key ? 1 << 3 : 0);
return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release);
}
@@ -2179,7 +2208,8 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
* Verify that the subsystem actually supports multiple
* controllers, else bail out.
*/
- if (nvme_active_ctrls(found) && !(id->cmic & (1 << 1))) {
+ if (!ctrl->opts->discovery_nqn &&
+ nvme_active_ctrls(found) && !(id->cmic & (1 << 1))) {
dev_err(ctrl->device,
"ignoring ctrl due to duplicate subnqn (%s).\n",
found->subnqn);
@@ -2310,7 +2340,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
if (id->lpa & NVME_CTRL_LPA_CMD_EFFECTS_LOG) {
ret = nvme_get_effects_log(ctrl);
if (ret < 0)
- return ret;
+ goto out_free;
}
if (!ctrl->identified) {
@@ -2341,6 +2371,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
ctrl->oacs = le16_to_cpu(id->oacs);
ctrl->oncs = le16_to_cpup(&id->oncs);
+ ctrl->oaes = le32_to_cpu(id->oaes);
atomic_set(&ctrl->abort_limit, id->acl + 1);
ctrl->vwc = id->vwc;
ctrl->cntlid = le16_to_cpup(&id->cntlid);
@@ -2860,6 +2891,9 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
goto out_cleanup_srcu;
list_add_tail(&head->entry, &ctrl->subsys->nsheads);
+
+ kref_get(&ctrl->subsys->ref);
+
return head;
out_cleanup_srcu:
cleanup_srcu_struct(&head->srcu);
@@ -2997,31 +3031,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
if (nvme_init_ns_head(ns, nsid, id))
goto out_free_id;
nvme_setup_streams_ns(ctrl, ns);
-
-#ifdef CONFIG_NVME_MULTIPATH
- /*
- * If multipathing is enabled we need to always use the subsystem
- * instance number for numbering our devices to avoid conflicts
- * between subsystems that have multiple controllers and thus use
- * the multipath-aware subsystem node and those that have a single
- * controller and use the controller node directly.
- */
- if (ns->head->disk) {
- sprintf(disk_name, "nvme%dc%dn%d", ctrl->subsys->instance,
- ctrl->cntlid, ns->head->instance);
- flags = GENHD_FL_HIDDEN;
- } else {
- sprintf(disk_name, "nvme%dn%d", ctrl->subsys->instance,
- ns->head->instance);
- }
-#else
- /*
- * But without the multipath code enabled, multiple controller per
- * subsystems are visible as devices and thus we cannot use the
- * subsystem instance.
- */
- sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
-#endif
+ nvme_set_disk_name(disk_name, ns, ctrl, &flags);
if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) {
if (nvme_nvm_register(ns, disk_name, node)) {
@@ -3187,6 +3197,42 @@ static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl, unsigned nn)
nvme_remove_invalid_namespaces(ctrl, nn);
}
+static bool nvme_scan_changed_ns_log(struct nvme_ctrl *ctrl)
+{
+ size_t log_size = NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32);
+ __le32 *log;
+ int error, i;
+ bool ret = false;
+
+ log = kzalloc(log_size, GFP_KERNEL);
+ if (!log)
+ return false;
+
+ error = nvme_get_log(ctrl, NVME_LOG_CHANGED_NS, log, log_size);
+ if (error) {
+ dev_warn(ctrl->device,
+ "reading changed ns log failed: %d\n", error);
+ goto out_free_log;
+ }
+
+ if (log[0] == cpu_to_le32(0xffffffff))
+ goto out_free_log;
+
+ for (i = 0; i < NVME_MAX_CHANGED_NAMESPACES; i++) {
+ u32 nsid = le32_to_cpu(log[i]);
+
+ if (nsid == 0)
+ break;
+ dev_info(ctrl->device, "rescanning namespace %d.\n", nsid);
+ nvme_validate_ns(ctrl, nsid);
+ }
+ ret = true;
+
+out_free_log:
+ kfree(log);
+ return ret;
+}
+
static void nvme_scan_work(struct work_struct *work)
{
struct nvme_ctrl *ctrl =
@@ -3199,6 +3245,12 @@ static void nvme_scan_work(struct work_struct *work)
WARN_ON_ONCE(!ctrl->tagset);
+ if (test_and_clear_bit(EVENT_NS_CHANGED, &ctrl->events)) {
+ if (nvme_scan_changed_ns_log(ctrl))
+ goto out_sort_namespaces;
+ dev_info(ctrl->device, "rescanning namespaces.\n");
+ }
+
if (nvme_identify_ctrl(ctrl, &id))
return;
@@ -3206,26 +3258,17 @@ static void nvme_scan_work(struct work_struct *work)
if (ctrl->vs >= NVME_VS(1, 1, 0) &&
!(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) {
if (!nvme_scan_ns_list(ctrl, nn))
- goto done;
+ goto out_free_id;
}
nvme_scan_ns_sequential(ctrl, nn);
- done:
+out_free_id:
+ kfree(id);
+out_sort_namespaces:
down_write(&ctrl->namespaces_rwsem);
list_sort(NULL, &ctrl->namespaces, ns_cmp);
up_write(&ctrl->namespaces_rwsem);
- kfree(id);
}
-void nvme_queue_scan(struct nvme_ctrl *ctrl)
-{
- /*
- * Only new queue scan work when admin and IO queues are both alive
- */
- if (ctrl->state == NVME_CTRL_LIVE)
- queue_work(nvme_wq, &ctrl->scan_work);
-}
-EXPORT_SYMBOL_GPL(nvme_queue_scan);
-
/*
* This function iterates the namespace list unlocked to allow recovery from
* controller failure. It is up to the caller to ensure the namespace list is
@@ -3339,8 +3382,23 @@ static void nvme_fw_act_work(struct work_struct *work)
nvme_get_fw_slot_info(ctrl);
}
+static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
+{
+ switch ((result & 0xff00) >> 8) {
+ case NVME_AER_NOTICE_NS_CHANGED:
+ set_bit(EVENT_NS_CHANGED, &ctrl->events);
+ nvme_queue_scan(ctrl);
+ break;
+ case NVME_AER_NOTICE_FW_ACT_STARTING:
+ queue_work(nvme_wq, &ctrl->fw_act_work);
+ break;
+ default:
+ dev_warn(ctrl->device, "async event result %08x\n", result);
+ }
+}
+
void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
- union nvme_result *res)
+ volatile union nvme_result *res)
{
u32 result = le32_to_cpu(res->u32);
@@ -3348,6 +3406,9 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
return;
switch (result & 0x7) {
+ case NVME_AER_NOTICE:
+ nvme_handle_aen_notice(ctrl, result);
+ break;
case NVME_AER_ERROR:
case NVME_AER_SMART:
case NVME_AER_CSS:
@@ -3357,18 +3418,6 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
default:
break;
}
-
- switch (result & 0xff07) {
- case NVME_AER_NOTICE_NS_CHANGED:
- dev_info(ctrl->device, "rescanning\n");
- nvme_queue_scan(ctrl);
- break;
- case NVME_AER_NOTICE_FW_ACT_STARTING:
- queue_work(nvme_wq, &ctrl->fw_act_work);
- break;
- default:
- dev_warn(ctrl->device, "async event result %08x\n", result);
- }
queue_work(nvme_wq, &ctrl->async_event_work);
}
EXPORT_SYMBOL_GPL(nvme_complete_async_event);
@@ -3391,6 +3440,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl)
if (ctrl->queue_count > 1) {
nvme_queue_scan(ctrl);
+ nvme_enable_aen(ctrl);
queue_work(nvme_wq, &ctrl->async_event_work);
nvme_start_queues(ctrl);
}
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 124c4588..5f5f706 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -57,7 +57,7 @@ static struct nvmf_host *nvmf_host_add(const char *hostnqn)
goto out_unlock;
kref_init(&host->ref);
- memcpy(host->nqn, hostnqn, NVMF_NQN_SIZE);
+ strlcpy(host->nqn, hostnqn, NVMF_NQN_SIZE);
list_add_tail(&host->list, &nvmf_hosts);
out_unlock:
@@ -545,71 +545,54 @@ blk_status_t nvmf_check_if_ready(struct nvme_ctrl *ctrl, struct request *rq,
return BLK_STS_OK;
switch (ctrl->state) {
- case NVME_CTRL_DELETING:
- goto reject_io;
-
case NVME_CTRL_NEW:
case NVME_CTRL_CONNECTING:
+ case NVME_CTRL_DELETING:
+ /*
+ * This is the case of starting a new or deleting an association
+ * but connectivity was lost before it was fully created or torn
+ * down. We need to error the commands used to initialize the
+ * controller so the reconnect can go into a retry attempt. The
+ * commands should all be marked REQ_FAILFAST_DRIVER, which will
+ * hit the reject path below. Anything else will be queued while
+ * the state settles.
+ */
if (!is_connected)
- /*
- * This is the case of starting a new
- * association but connectivity was lost
- * before it was fully created. We need to
- * error the commands used to initialize the
- * controller so the reconnect can go into a
- * retry attempt. The commands should all be
- * marked REQ_FAILFAST_DRIVER, which will hit
- * the reject path below. Anything else will
- * be queued while the state settles.
- */
- goto reject_or_queue_io;
+ break;
- if ((queue_live &&
- !(nvme_req(rq)->flags & NVME_REQ_USERCMD)) ||
- (!queue_live && blk_rq_is_passthrough(rq) &&
- cmd->common.opcode == nvme_fabrics_command &&
- cmd->fabrics.fctype == nvme_fabrics_type_connect))
- /*
- * If queue is live, allow only commands that
- * are internally generated pass through. These
- * are commands on the admin queue to initialize
- * the controller. This will reject any ioctl
- * admin cmds received while initializing.
- *
- * If the queue is not live, allow only a
- * connect command. This will reject any ioctl
- * admin cmd as well as initialization commands
- * if the controller reverted the queue to non-live.
- */
+ /*
+ * If queue is live, allow only commands that are internally
+ * generated pass through. These are commands on the admin
+ * queue to initialize the controller. This will reject any
+ * ioctl admin cmds received while initializing.
+ */
+ if (queue_live && !(nvme_req(rq)->flags & NVME_REQ_USERCMD))
return BLK_STS_OK;
/*
- * fall-thru to the reject_or_queue_io clause
+ * If the queue is not live, allow only a connect command. This
+ * will reject any ioctl admin cmd as well as initialization
+ * commands if the controller reverted the queue to non-live.
*/
+ if (!queue_live && blk_rq_is_passthrough(rq) &&
+ cmd->common.opcode == nvme_fabrics_command &&
+ cmd->fabrics.fctype == nvme_fabrics_type_connect)
+ return BLK_STS_OK;
break;
-
- /* these cases fall-thru
- * case NVME_CTRL_LIVE:
- * case NVME_CTRL_RESETTING:
- */
default:
break;
}
-reject_or_queue_io:
/*
- * Any other new io is something we're not in a state to send
- * to the device. Default action is to busy it and retry it
- * after the controller state is recovered. However, anything
- * marked for failfast or nvme multipath is immediately failed.
- * Note: commands used to initialize the controller will be
- * marked for failfast.
+ * Any other new io is something we're not in a state to send to the
+ * device. Default action is to busy it and retry it after the
+ * controller state is recovered. However, anything marked for failfast
+ * or nvme multipath is immediately failed. Note: commands used to
+ * initialize the controller will be marked for failfast.
* Note: nvme cli/ioctl commands are marked for failfast.
*/
if (!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
return BLK_STS_RESOURCE;
-
-reject_io:
nvme_req(rq)->status = NVME_SC_ABORT_REQ;
return BLK_STS_IOERR;
}
@@ -668,6 +651,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
ret = -ENOMEM;
goto out;
}
+ kfree(opts->transport);
opts->transport = p;
break;
case NVMF_OPT_NQN:
@@ -676,6 +660,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
ret = -ENOMEM;
goto out;
}
+ kfree(opts->subsysnqn);
opts->subsysnqn = p;
nqnlen = strlen(opts->subsysnqn);
if (nqnlen >= NVMF_NQN_SIZE) {
@@ -687,10 +672,6 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
opts->discovery_nqn =
!(strcmp(opts->subsysnqn,
NVME_DISC_SUBSYS_NAME));
- if (opts->discovery_nqn) {
- opts->kato = 0;
- opts->nr_io_queues = 0;
- }
break;
case NVMF_OPT_TRADDR:
p = match_strdup(args);
@@ -698,6 +679,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
ret = -ENOMEM;
goto out;
}
+ kfree(opts->traddr);
opts->traddr = p;
break;
case NVMF_OPT_TRSVCID:
@@ -706,6 +688,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
ret = -ENOMEM;
goto out;
}
+ kfree(opts->trsvcid);
opts->trsvcid = p;
break;
case NVMF_OPT_QUEUE_SIZE:
@@ -792,6 +775,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
ret = -EINVAL;
goto out;
}
+ nvmf_host_put(opts->host);
opts->host = nvmf_host_add(p);
kfree(p);
if (!opts->host) {
@@ -817,6 +801,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
ret = -ENOMEM;
goto out;
}
+ kfree(opts->host_traddr);
opts->host_traddr = p;
break;
case NVMF_OPT_HOST_ID:
@@ -845,6 +830,11 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
}
}
+ if (opts->discovery_nqn) {
+ opts->kato = 0;
+ opts->nr_io_queues = 0;
+ opts->duplicate_connect = true;
+ }
if (ctrl_loss_tmo < 0)
opts->max_reconnects = -1;
else
@@ -977,16 +967,6 @@ nvmf_create_ctrl(struct device *dev, const char *buf, size_t count)
goto out_module_put;
}
- if (strcmp(ctrl->subsys->subnqn, opts->subsysnqn)) {
- dev_warn(ctrl->device,
- "controller returned incorrect NQN: \"%s\".\n",
- ctrl->subsys->subnqn);
- module_put(ops->module);
- up_read(&nvmf_transports_rwsem);
- nvme_delete_ctrl_sync(ctrl);
- return ERR_PTR(-EINVAL);
- }
-
module_put(ops->module);
up_read(&nvmf_transports_rwsem);
return ctrl;
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index ef46c91..0cf0460 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -139,7 +139,9 @@ static inline bool
nvmf_ctlr_matches_baseopts(struct nvme_ctrl *ctrl,
struct nvmf_ctrl_options *opts)
{
- if (strcmp(opts->subsysnqn, ctrl->opts->subsysnqn) ||
+ if (ctrl->state == NVME_CTRL_DELETING ||
+ ctrl->state == NVME_CTRL_DEAD ||
+ strcmp(opts->subsysnqn, ctrl->opts->subsysnqn) ||
strcmp(opts->host->nqn, ctrl->opts->host->nqn) ||
memcmp(&opts->host->id, &ctrl->opts->host->id, sizeof(uuid_t)))
return false;
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 6cb26bc..0bad658 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1686,16 +1686,6 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
goto check_error;
}
- /*
- * Force failures of commands if we're killing the controller
- * or have an error on a command used to create an new association
- */
- if (status &&
- (blk_queue_dying(rq->q) ||
- ctrl->ctrl.state == NVME_CTRL_NEW ||
- ctrl->ctrl.state == NVME_CTRL_CONNECTING))
- status |= cpu_to_le16(NVME_SC_DNR << 1);
-
__nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate);
nvme_end_request(rq, status, result);
@@ -2403,9 +2393,6 @@ nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved)
struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req);
- if (!blk_mq_request_started(req))
- return;
-
__nvme_fc_abort_op(ctrl, op);
}
@@ -3284,6 +3271,8 @@ nvme_fc_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts)
}
spin_unlock_irqrestore(&nvme_fc_lock, flags);
+ pr_warn("%s: %s - %s combination not found\n",
+ __func__, opts->traddr, opts->host_traddr);
return ERR_PTR(-ENOENT);
}
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 956e0b8..d7b664a 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -15,10 +15,32 @@
#include "nvme.h"
static bool multipath = true;
-module_param(multipath, bool, 0644);
+module_param(multipath, bool, 0444);
MODULE_PARM_DESC(multipath,
"turn on native support for multiple controllers per subsystem");
+/*
+ * If multipathing is enabled we need to always use the subsystem instance
+ * number for numbering our devices to avoid conflicts between subsystems that
+ * have multiple controllers and thus use the multipath-aware subsystem node
+ * and those that have a single controller and use the controller node
+ * directly.
+ */
+void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
+ struct nvme_ctrl *ctrl, int *flags)
+{
+ if (!multipath) {
+ sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
+ } else if (ns->head->disk) {
+ sprintf(disk_name, "nvme%dc%dn%d", ctrl->subsys->instance,
+ ctrl->cntlid, ns->head->instance);
+ *flags = GENHD_FL_HIDDEN;
+ } else {
+ sprintf(disk_name, "nvme%dn%d", ctrl->subsys->instance,
+ ns->head->instance);
+ }
+}
+
void nvme_failover_req(struct request *req)
{
struct nvme_ns *ns = req->q->queuedata;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 061fecf..de24fe7 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -22,6 +22,7 @@
#include <linux/lightnvm.h>
#include <linux/sed-opal.h>
#include <linux/fault-inject.h>
+#include <linux/rcupdate.h>
extern unsigned int nvme_io_timeout;
#define NVME_IO_TIMEOUT (nvme_io_timeout * HZ)
@@ -84,6 +85,11 @@ enum nvme_quirks {
* Supports the LighNVM command set if indicated in vs[1].
*/
NVME_QUIRK_LIGHTNVM = (1 << 6),
+
+ /*
+ * Set MEDIUM priority on SQ creation
+ */
+ NVME_QUIRK_MEDIUM_PRIO_SQ = (1 << 7),
};
/*
@@ -175,6 +181,7 @@ struct nvme_ctrl {
u16 kas;
u8 npss;
u8 apsta;
+ u32 oaes;
u32 aen_result;
unsigned int shutdown_timeout;
unsigned int kato;
@@ -187,6 +194,8 @@ struct nvme_ctrl {
struct delayed_work ka_work;
struct nvme_command ka_cmd;
struct work_struct fw_act_work;
+#define EVENT_NS_CHANGED (1 << 0)
+ unsigned long events;
/* Power saving configuration */
u64 ps_max_latency_us;
@@ -393,14 +402,13 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl);
void nvme_put_ctrl(struct nvme_ctrl *ctrl);
int nvme_init_identify(struct nvme_ctrl *ctrl);
-void nvme_queue_scan(struct nvme_ctrl *ctrl);
void nvme_remove_namespaces(struct nvme_ctrl *ctrl);
int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
bool send);
void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
- union nvme_result *res);
+ volatile union nvme_result *res);
void nvme_stop_queues(struct nvme_ctrl *ctrl);
void nvme_start_queues(struct nvme_ctrl *ctrl);
@@ -436,6 +444,8 @@ extern const struct attribute_group nvme_ns_id_attr_group;
extern const struct block_device_operations nvme_ns_head_ops;
#ifdef CONFIG_NVME_MULTIPATH
+void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
+ struct nvme_ctrl *ctrl, int *flags);
void nvme_failover_req(struct request *req);
bool nvme_req_needs_failover(struct request *req, blk_status_t error);
void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
@@ -447,7 +457,7 @@ static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
{
struct nvme_ns_head *head = ns->head;
- if (head && ns == srcu_dereference(head->current_path, &head->srcu))
+ if (head && ns == rcu_access_pointer(head->current_path))
rcu_assign_pointer(head->current_path, NULL);
}
struct nvme_ns *nvme_find_path(struct nvme_ns_head *head);
@@ -461,6 +471,16 @@ static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
}
#else
+/*
+ * Without the multipath code enabled, multiple controller per subsystems are
+ * visible as devices and thus we cannot use the subsystem instance.
+ */
+static inline void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
+ struct nvme_ctrl *ctrl, int *flags)
+{
+ sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
+}
+
static inline void nvme_failover_req(struct request *req)
{
}
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index fbc71fa..e526437 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -13,6 +13,7 @@
*/
#include <linux/aer.h>
+#include <linux/async.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/blk-mq-pci.h>
@@ -68,7 +69,6 @@ MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2");
struct nvme_dev;
struct nvme_queue;
-static void nvme_process_cq(struct nvme_queue *nvmeq);
static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown);
/*
@@ -147,9 +147,10 @@ static inline struct nvme_dev *to_nvme_dev(struct nvme_ctrl *ctrl)
struct nvme_queue {
struct device *q_dmadev;
struct nvme_dev *dev;
- spinlock_t q_lock;
+ spinlock_t sq_lock;
struct nvme_command *sq_cmds;
struct nvme_command __iomem *sq_cmds_io;
+ spinlock_t cq_lock ____cacheline_aligned_in_smp;
volatile struct nvme_completion *cqes;
struct blk_mq_tags **tags;
dma_addr_t sq_dma_addr;
@@ -159,9 +160,9 @@ struct nvme_queue {
s16 cq_vector;
u16 sq_tail;
u16 cq_head;
+ u16 last_cq_head;
u16 qid;
u8 cq_phase;
- u8 cqe_seen;
u32 *dbbuf_sq_db;
u32 *dbbuf_cq_db;
u32 *dbbuf_sq_ei;
@@ -420,28 +421,25 @@ static int nvme_pci_map_queues(struct blk_mq_tag_set *set)
}
/**
- * __nvme_submit_cmd() - Copy a command into a queue and ring the doorbell
+ * nvme_submit_cmd() - Copy a command into a queue and ring the doorbell
* @nvmeq: The queue to use
* @cmd: The command to send
- *
- * Safe to use from interrupt context
*/
-static void __nvme_submit_cmd(struct nvme_queue *nvmeq,
- struct nvme_command *cmd)
+static void nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
{
- u16 tail = nvmeq->sq_tail;
-
+ spin_lock(&nvmeq->sq_lock);
if (nvmeq->sq_cmds_io)
- memcpy_toio(&nvmeq->sq_cmds_io[tail], cmd, sizeof(*cmd));
+ memcpy_toio(&nvmeq->sq_cmds_io[nvmeq->sq_tail], cmd,
+ sizeof(*cmd));
else
- memcpy(&nvmeq->sq_cmds[tail], cmd, sizeof(*cmd));
+ memcpy(&nvmeq->sq_cmds[nvmeq->sq_tail], cmd, sizeof(*cmd));
- if (++tail == nvmeq->q_depth)
- tail = 0;
- if (nvme_dbbuf_update_and_check_event(tail, nvmeq->dbbuf_sq_db,
- nvmeq->dbbuf_sq_ei))
- writel(tail, nvmeq->q_db);
- nvmeq->sq_tail = tail;
+ if (++nvmeq->sq_tail == nvmeq->q_depth)
+ nvmeq->sq_tail = 0;
+ if (nvme_dbbuf_update_and_check_event(nvmeq->sq_tail,
+ nvmeq->dbbuf_sq_db, nvmeq->dbbuf_sq_ei))
+ writel(nvmeq->sq_tail, nvmeq->q_db);
+ spin_unlock(&nvmeq->sq_lock);
}
static void **nvme_pci_iod_list(struct request *req)
@@ -872,6 +870,13 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
struct nvme_command cmnd;
blk_status_t ret;
+ /*
+ * We should not need to do this, but we're still using this to
+ * ensure we can drain requests on a dying queue.
+ */
+ if (unlikely(nvmeq->cq_vector < 0))
+ return BLK_STS_IOERR;
+
ret = nvme_setup_cmd(ns, req, &cmnd);
if (ret)
return ret;
@@ -887,16 +892,7 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
}
blk_mq_start_request(req);
-
- spin_lock_irq(&nvmeq->q_lock);
- if (unlikely(nvmeq->cq_vector < 0)) {
- ret = BLK_STS_IOERR;
- spin_unlock_irq(&nvmeq->q_lock);
- goto out_cleanup_iod;
- }
- __nvme_submit_cmd(nvmeq, &cmnd);
- nvme_process_cq(nvmeq);
- spin_unlock_irq(&nvmeq->q_lock);
+ nvme_submit_cmd(nvmeq, &cmnd);
return BLK_STS_OK;
out_cleanup_iod:
nvme_free_iod(dev, req);
@@ -914,10 +910,10 @@ static void nvme_pci_complete_rq(struct request *req)
}
/* We read the CQE phase first to check if the rest of the entry is valid */
-static inline bool nvme_cqe_valid(struct nvme_queue *nvmeq, u16 head,
- u16 phase)
+static inline bool nvme_cqe_pending(struct nvme_queue *nvmeq)
{
- return (le16_to_cpu(nvmeq->cqes[head].status) & 1) == phase;
+ return (le16_to_cpu(nvmeq->cqes[nvmeq->cq_head].status) & 1) ==
+ nvmeq->cq_phase;
}
static inline void nvme_ring_cq_doorbell(struct nvme_queue *nvmeq)
@@ -931,9 +927,9 @@ static inline void nvme_ring_cq_doorbell(struct nvme_queue *nvmeq)
}
}
-static inline void nvme_handle_cqe(struct nvme_queue *nvmeq,
- struct nvme_completion *cqe)
+static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
{
+ volatile struct nvme_completion *cqe = &nvmeq->cqes[idx];
struct request *req;
if (unlikely(cqe->command_id >= nvmeq->q_depth)) {
@@ -956,83 +952,87 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq,
return;
}
- nvmeq->cqe_seen = 1;
req = blk_mq_tag_to_rq(*nvmeq->tags, cqe->command_id);
nvme_end_request(req, cqe->status, cqe->result);
}
-static inline bool nvme_read_cqe(struct nvme_queue *nvmeq,
- struct nvme_completion *cqe)
+static void nvme_complete_cqes(struct nvme_queue *nvmeq, u16 start, u16 end)
{
- if (nvme_cqe_valid(nvmeq, nvmeq->cq_head, nvmeq->cq_phase)) {
- *cqe = nvmeq->cqes[nvmeq->cq_head];
-
- if (++nvmeq->cq_head == nvmeq->q_depth) {
- nvmeq->cq_head = 0;
- nvmeq->cq_phase = !nvmeq->cq_phase;
- }
- return true;
+ while (start != end) {
+ nvme_handle_cqe(nvmeq, start);
+ if (++start == nvmeq->q_depth)
+ start = 0;
}
- return false;
}
-static void nvme_process_cq(struct nvme_queue *nvmeq)
+static inline void nvme_update_cq_head(struct nvme_queue *nvmeq)
{
- struct nvme_completion cqe;
- int consumed = 0;
-
- while (nvme_read_cqe(nvmeq, &cqe)) {
- nvme_handle_cqe(nvmeq, &cqe);
- consumed++;
+ if (++nvmeq->cq_head == nvmeq->q_depth) {
+ nvmeq->cq_head = 0;
+ nvmeq->cq_phase = !nvmeq->cq_phase;
}
+}
- if (consumed)
+static inline bool nvme_process_cq(struct nvme_queue *nvmeq, u16 *start,
+ u16 *end, int tag)
+{
+ bool found = false;
+
+ *start = nvmeq->cq_head;
+ while (!found && nvme_cqe_pending(nvmeq)) {
+ if (nvmeq->cqes[nvmeq->cq_head].command_id == tag)
+ found = true;
+ nvme_update_cq_head(nvmeq);
+ }
+ *end = nvmeq->cq_head;
+
+ if (*start != *end)
nvme_ring_cq_doorbell(nvmeq);
+ return found;
}
static irqreturn_t nvme_irq(int irq, void *data)
{
- irqreturn_t result;
struct nvme_queue *nvmeq = data;
- spin_lock(&nvmeq->q_lock);
- nvme_process_cq(nvmeq);
- result = nvmeq->cqe_seen ? IRQ_HANDLED : IRQ_NONE;
- nvmeq->cqe_seen = 0;
- spin_unlock(&nvmeq->q_lock);
- return result;
+ irqreturn_t ret = IRQ_NONE;
+ u16 start, end;
+
+ spin_lock(&nvmeq->cq_lock);
+ if (nvmeq->cq_head != nvmeq->last_cq_head)
+ ret = IRQ_HANDLED;
+ nvme_process_cq(nvmeq, &start, &end, -1);
+ nvmeq->last_cq_head = nvmeq->cq_head;
+ spin_unlock(&nvmeq->cq_lock);
+
+ if (start != end) {
+ nvme_complete_cqes(nvmeq, start, end);
+ return IRQ_HANDLED;
+ }
+
+ return ret;
}
static irqreturn_t nvme_irq_check(int irq, void *data)
{
struct nvme_queue *nvmeq = data;
- if (nvme_cqe_valid(nvmeq, nvmeq->cq_head, nvmeq->cq_phase))
+ if (nvme_cqe_pending(nvmeq))
return IRQ_WAKE_THREAD;
return IRQ_NONE;
}
static int __nvme_poll(struct nvme_queue *nvmeq, unsigned int tag)
{
- struct nvme_completion cqe;
- int found = 0, consumed = 0;
+ u16 start, end;
+ bool found;
- if (!nvme_cqe_valid(nvmeq, nvmeq->cq_head, nvmeq->cq_phase))
+ if (!nvme_cqe_pending(nvmeq))
return 0;
- spin_lock_irq(&nvmeq->q_lock);
- while (nvme_read_cqe(nvmeq, &cqe)) {
- nvme_handle_cqe(nvmeq, &cqe);
- consumed++;
+ spin_lock_irq(&nvmeq->cq_lock);
+ found = nvme_process_cq(nvmeq, &start, &end, tag);
+ spin_unlock_irq(&nvmeq->cq_lock);
- if (tag == cqe.command_id) {
- found = 1;
- break;
- }
- }
-
- if (consumed)
- nvme_ring_cq_doorbell(nvmeq);
- spin_unlock_irq(&nvmeq->q_lock);
-
+ nvme_complete_cqes(nvmeq, start, end);
return found;
}
@@ -1052,10 +1052,7 @@ static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl)
memset(&c, 0, sizeof(c));
c.common.opcode = nvme_admin_async_event;
c.common.command_id = NVME_AQ_BLK_MQ_DEPTH;
-
- spin_lock_irq(&nvmeq->q_lock);
- __nvme_submit_cmd(nvmeq, &c);
- spin_unlock_irq(&nvmeq->q_lock);
+ nvme_submit_cmd(nvmeq, &c);
}
static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
@@ -1070,7 +1067,7 @@ static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
}
static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
- struct nvme_queue *nvmeq)
+ struct nvme_queue *nvmeq, s16 vector)
{
struct nvme_command c;
int flags = NVME_QUEUE_PHYS_CONTIG | NVME_CQ_IRQ_ENABLED;
@@ -1085,7 +1082,7 @@ static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
c.create_cq.cqid = cpu_to_le16(qid);
c.create_cq.qsize = cpu_to_le16(nvmeq->q_depth - 1);
c.create_cq.cq_flags = cpu_to_le16(flags);
- c.create_cq.irq_vector = cpu_to_le16(nvmeq->cq_vector);
+ c.create_cq.irq_vector = cpu_to_le16(vector);
return nvme_submit_sync_cmd(dev->ctrl.admin_q, &c, NULL, 0);
}
@@ -1093,10 +1090,19 @@ static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
struct nvme_queue *nvmeq)
{
+ struct nvme_ctrl *ctrl = &dev->ctrl;
struct nvme_command c;
int flags = NVME_QUEUE_PHYS_CONTIG;
/*
+ * Some drives have a bug that auto-enables WRRU if MEDIUM isn't
+ * set. Since URGENT priority is zeroes, it makes all queues
+ * URGENT.
+ */
+ if (ctrl->quirks & NVME_QUIRK_MEDIUM_PRIO_SQ)
+ flags |= NVME_SQ_PRIO_MEDIUM;
+
+ /*
* Note: we (ab)use the fact that the prp fields survive if no data
* is attached to the request.
*/
@@ -1199,7 +1205,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
nvme_warn_reset(dev, csts);
nvme_dev_disable(dev, false);
nvme_reset_ctrl(&dev->ctrl);
- return BLK_EH_HANDLED;
+ return BLK_EH_DONE;
}
/*
@@ -1209,24 +1215,24 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
dev_warn(dev->ctrl.device,
"I/O %d QID %d timeout, completion polled\n",
req->tag, nvmeq->qid);
- return BLK_EH_HANDLED;
+ return BLK_EH_DONE;
}
/*
* Shutdown immediately if controller times out while starting. The
* reset work will see the pci device disabled when it gets the forced
* cancellation error. All outstanding requests are completed on
- * shutdown, so we return BLK_EH_HANDLED.
+ * shutdown, so we return BLK_EH_DONE.
*/
switch (dev->ctrl.state) {
case NVME_CTRL_CONNECTING:
case NVME_CTRL_RESETTING:
- dev_warn(dev->ctrl.device,
+ dev_warn_ratelimited(dev->ctrl.device,
"I/O %d QID %d timeout, disable controller\n",
req->tag, nvmeq->qid);
nvme_dev_disable(dev, false);
nvme_req(req)->flags |= NVME_REQ_CANCELLED;
- return BLK_EH_HANDLED;
+ return BLK_EH_DONE;
default:
break;
}
@@ -1243,12 +1249,8 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
nvme_dev_disable(dev, false);
nvme_reset_ctrl(&dev->ctrl);
- /*
- * Mark the request as handled, since the inline shutdown
- * forces all outstanding requests to complete.
- */
nvme_req(req)->flags |= NVME_REQ_CANCELLED;
- return BLK_EH_HANDLED;
+ return BLK_EH_DONE;
}
if (atomic_dec_return(&dev->ctrl.abort_limit) < 0) {
@@ -1312,15 +1314,21 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
{
int vector;
- spin_lock_irq(&nvmeq->q_lock);
+ spin_lock_irq(&nvmeq->cq_lock);
if (nvmeq->cq_vector == -1) {
- spin_unlock_irq(&nvmeq->q_lock);
+ spin_unlock_irq(&nvmeq->cq_lock);
return 1;
}
vector = nvmeq->cq_vector;
nvmeq->dev->online_queues--;
nvmeq->cq_vector = -1;
- spin_unlock_irq(&nvmeq->q_lock);
+ spin_unlock_irq(&nvmeq->cq_lock);
+
+ /*
+ * Ensure that nvme_queue_rq() sees it ->cq_vector == -1 without
+ * having to grab the lock.
+ */
+ mb();
if (!nvmeq->qid && nvmeq->dev->ctrl.admin_q)
blk_mq_quiesce_queue(nvmeq->dev->ctrl.admin_q);
@@ -1333,15 +1341,18 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown)
{
struct nvme_queue *nvmeq = &dev->queues[0];
+ u16 start, end;
if (shutdown)
nvme_shutdown_ctrl(&dev->ctrl);
else
nvme_disable_ctrl(&dev->ctrl, dev->ctrl.cap);
- spin_lock_irq(&nvmeq->q_lock);
- nvme_process_cq(nvmeq);
- spin_unlock_irq(&nvmeq->q_lock);
+ spin_lock_irq(&nvmeq->cq_lock);
+ nvme_process_cq(nvmeq, &start, &end, -1);
+ spin_unlock_irq(&nvmeq->cq_lock);
+
+ nvme_complete_cqes(nvmeq, start, end);
}
static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
@@ -1399,7 +1410,8 @@ static int nvme_alloc_queue(struct nvme_dev *dev, int qid, int depth)
nvmeq->q_dmadev = dev->dev;
nvmeq->dev = dev;
- spin_lock_init(&nvmeq->q_lock);
+ spin_lock_init(&nvmeq->sq_lock);
+ spin_lock_init(&nvmeq->cq_lock);
nvmeq->cq_head = 0;
nvmeq->cq_phase = 1;
nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
@@ -1435,7 +1447,7 @@ static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
{
struct nvme_dev *dev = nvmeq->dev;
- spin_lock_irq(&nvmeq->q_lock);
+ spin_lock_irq(&nvmeq->cq_lock);
nvmeq->sq_tail = 0;
nvmeq->cq_head = 0;
nvmeq->cq_phase = 1;
@@ -1443,13 +1455,14 @@ static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
nvme_dbbuf_init(dev, nvmeq, qid);
dev->online_queues++;
- spin_unlock_irq(&nvmeq->q_lock);
+ spin_unlock_irq(&nvmeq->cq_lock);
}
static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
{
struct nvme_dev *dev = nvmeq->dev;
int result;
+ s16 vector;
if (dev->cmb && use_cmb_sqes && (dev->cmbsz & NVME_CMBSZ_SQS)) {
unsigned offset = (qid - 1) * roundup(SQ_SIZE(nvmeq->q_depth),
@@ -1462,15 +1475,21 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
* A queue's vector matches the queue identifier unless the controller
* has only one vector available.
*/
- nvmeq->cq_vector = dev->num_vecs == 1 ? 0 : qid;
- result = adapter_alloc_cq(dev, qid, nvmeq);
+ vector = dev->num_vecs == 1 ? 0 : qid;
+ result = adapter_alloc_cq(dev, qid, nvmeq, vector);
if (result < 0)
- goto release_vector;
+ goto out;
result = adapter_alloc_sq(dev, qid, nvmeq);
if (result < 0)
goto release_cq;
+ /*
+ * Set cq_vector after alloc cq/sq, otherwise nvme_suspend_queue will
+ * invoke free_irq for it and cause a 'Trying to free already-free IRQ
+ * xxx' warning if the create CQ/SQ command times out.
+ */
+ nvmeq->cq_vector = vector;
nvme_init_queue(nvmeq, qid);
result = queue_request_irq(nvmeq);
if (result < 0)
@@ -1478,13 +1497,13 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
return result;
- release_sq:
+release_sq:
+ nvmeq->cq_vector = -1;
dev->online_queues--;
adapter_delete_sq(dev, qid);
- release_cq:
+release_cq:
adapter_delete_cq(dev, qid);
- release_vector:
- nvmeq->cq_vector = -1;
+out:
return result;
}
@@ -1988,19 +2007,22 @@ static void nvme_del_queue_end(struct request *req, blk_status_t error)
static void nvme_del_cq_end(struct request *req, blk_status_t error)
{
struct nvme_queue *nvmeq = req->end_io_data;
+ u16 start, end;
if (!error) {
unsigned long flags;
/*
- * We might be called with the AQ q_lock held
- * and the I/O queue q_lock should always
+ * We might be called with the AQ cq_lock held
+ * and the I/O queue cq_lock should always
* nest inside the AQ one.
*/
- spin_lock_irqsave_nested(&nvmeq->q_lock, flags,
+ spin_lock_irqsave_nested(&nvmeq->cq_lock, flags,
SINGLE_DEPTH_NESTING);
- nvme_process_cq(nvmeq);
- spin_unlock_irqrestore(&nvmeq->q_lock, flags);
+ nvme_process_cq(nvmeq, &start, &end, -1);
+ spin_unlock_irqrestore(&nvmeq->cq_lock, flags);
+
+ nvme_complete_cqes(nvmeq, start, end);
}
nvme_del_queue_end(req, error);
@@ -2488,6 +2510,15 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
return 0;
}
+static void nvme_async_probe(void *data, async_cookie_t cookie)
+{
+ struct nvme_dev *dev = data;
+
+ nvme_reset_ctrl_sync(&dev->ctrl);
+ flush_work(&dev->ctrl.scan_work);
+ nvme_put_ctrl(&dev->ctrl);
+}
+
static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
int node, result = -ENOMEM;
@@ -2532,7 +2563,8 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
- nvme_reset_ctrl(&dev->ctrl);
+ nvme_get_ctrl(&dev->ctrl);
+ async_schedule(nvme_async_probe, dev);
return 0;
@@ -2676,6 +2708,9 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
static void nvme_error_resume(struct pci_dev *pdev)
{
+ struct nvme_dev *dev = pci_get_drvdata(pdev);
+
+ flush_work(&dev->ctrl.reset_work);
pci_cleanup_aer_uncorrect_error_status(pdev);
}
@@ -2701,9 +2736,12 @@ static const struct pci_device_id nvme_id_table[] = {
.driver_data = NVME_QUIRK_STRIPE_SIZE |
NVME_QUIRK_DEALLOCATE_ZEROES, },
{ PCI_VDEVICE(INTEL, 0xf1a5), /* Intel 600P/P3100 */
- .driver_data = NVME_QUIRK_NO_DEEPEST_PS },
+ .driver_data = NVME_QUIRK_NO_DEEPEST_PS |
+ NVME_QUIRK_MEDIUM_PRIO_SQ },
{ PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */
.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
+ { PCI_DEVICE(0x1bb1, 0x0100), /* Seagate Nytro Flash Storage */
+ .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
{ PCI_DEVICE(0x1c58, 0x0003), /* HGST adapter */
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
{ PCI_DEVICE(0x1c58, 0x0023), /* WDC SN200 adapter */
@@ -2718,6 +2756,8 @@ static const struct pci_device_id nvme_id_table[] = {
.driver_data = NVME_QUIRK_LIGHTNVM, },
{ PCI_DEVICE(0x1d1d, 0x2807), /* CNEX WL */
.driver_data = NVME_QUIRK_LIGHTNVM, },
+ { PCI_DEVICE(0x1d1d, 0x2601), /* CNEX Granby */
+ .driver_data = NVME_QUIRK_LIGHTNVM, },
{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 1eb4438..7b3f084 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -778,7 +778,7 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
if (error) {
dev_err(ctrl->ctrl.device,
"prop_get NVME_REG_CAP failed\n");
- goto out_cleanup_queue;
+ goto out_stop_queue;
}
ctrl->ctrl.sqsize =
@@ -786,23 +786,25 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
if (error)
- goto out_cleanup_queue;
+ goto out_stop_queue;
ctrl->ctrl.max_hw_sectors =
(ctrl->max_fr_pages - 1) << (ilog2(SZ_4K) - 9);
error = nvme_init_identify(&ctrl->ctrl);
if (error)
- goto out_cleanup_queue;
+ goto out_stop_queue;
error = nvme_rdma_alloc_qe(ctrl->queues[0].device->dev,
&ctrl->async_event_sqe, sizeof(struct nvme_command),
DMA_TO_DEVICE);
if (error)
- goto out_cleanup_queue;
+ goto out_stop_queue;
return 0;
+out_stop_queue:
+ nvme_rdma_stop_queue(&ctrl->queues[0]);
out_cleanup_queue:
if (new)
blk_cleanup_queue(ctrl->ctrl.admin_q);
@@ -1598,7 +1600,7 @@ nvme_rdma_timeout(struct request *rq, bool reserved)
/* fail with DNR on cmd timeout */
nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR;
- return BLK_EH_HANDLED;
+ return BLK_EH_DONE;
}
static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h
index ea91fcc..01390f0 100644
--- a/drivers/nvme/host/trace.h
+++ b/drivers/nvme/host/trace.h
@@ -148,8 +148,8 @@ TRACE_EVENT(nvme_complete_rq,
__entry->flags = nvme_req(req)->flags;
__entry->status = nvme_req(req)->status;
),
- TP_printk("cmdid=%u, qid=%d, res=%llu, retries=%u, flags=0x%x, status=%u",
- __entry->cid, __entry->qid, __entry->result,
+ TP_printk("qid=%d, cmdid=%u, res=%llu, retries=%u, flags=0x%x, status=%u",
+ __entry->qid, __entry->cid, __entry->result,
__entry->retries, __entry->flags, __entry->status)
);
diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig
index 5f4f8b1..3c7b61d 100644
--- a/drivers/nvme/target/Kconfig
+++ b/drivers/nvme/target/Kconfig
@@ -27,7 +27,7 @@
config NVME_TARGET_RDMA
tristate "NVMe over Fabrics RDMA target support"
- depends on INFINIBAND
+ depends on INFINIBAND && INFINIBAND_ADDR_TRANS
depends on NVME_TARGET
select SGL_ALLOC
help
diff --git a/drivers/nvme/target/Makefile b/drivers/nvme/target/Makefile
index 4882501..8118c93 100644
--- a/drivers/nvme/target/Makefile
+++ b/drivers/nvme/target/Makefile
@@ -6,8 +6,8 @@
obj-$(CONFIG_NVME_TARGET_FC) += nvmet-fc.o
obj-$(CONFIG_NVME_TARGET_FCLOOP) += nvme-fcloop.o
-nvmet-y += core.o configfs.o admin-cmd.o io-cmd.o fabrics-cmd.o \
- discovery.o
+nvmet-y += core.o configfs.o admin-cmd.o fabrics-cmd.o \
+ discovery.o io-cmd-file.o io-cmd-bdev.o
nvme-loop-y += loop.o
nvmet-rdma-y += rdma.o
nvmet-fc-y += fc.o
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 5e0e9fc..ead8fbe 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -32,6 +32,11 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd)
return len;
}
+static void nvmet_execute_get_log_page_noop(struct nvmet_req *req)
+{
+ nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->data_len));
+}
+
static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
struct nvme_smart_log *slog)
{
@@ -45,6 +50,10 @@ static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
return NVME_SC_INVALID_NS;
}
+ /* we don't have the right data for file backed ns */
+ if (!ns->bdev)
+ goto out;
+
host_reads = part_stat_read(ns->bdev->bd_part, ios[READ]);
data_units_read = part_stat_read(ns->bdev->bd_part, sectors[READ]);
host_writes = part_stat_read(ns->bdev->bd_part, ios[WRITE]);
@@ -54,6 +63,7 @@ static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
put_unaligned_le64(data_units_read, &slog->data_units_read[0]);
put_unaligned_le64(host_writes, &slog->host_writes[0]);
put_unaligned_le64(data_units_written, &slog->data_units_written[0]);
+out:
nvmet_put_namespace(ns);
return NVME_SC_SUCCESS;
@@ -71,6 +81,9 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req,
rcu_read_lock();
list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link) {
+ /* we don't have the right data for file backed ns */
+ if (!ns->bdev)
+ continue;
host_reads += part_stat_read(ns->bdev->bd_part, ios[READ]);
data_units_read +=
part_stat_read(ns->bdev->bd_part, sectors[READ]);
@@ -89,74 +102,50 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req,
return NVME_SC_SUCCESS;
}
-static u16 nvmet_get_smart_log(struct nvmet_req *req,
- struct nvme_smart_log *slog)
+static void nvmet_execute_get_log_page_smart(struct nvmet_req *req)
{
- u16 status;
+ struct nvme_smart_log *log;
+ u16 status = NVME_SC_INTERNAL;
- WARN_ON(req == NULL || slog == NULL);
+ if (req->data_len != sizeof(*log))
+ goto out;
+
+ log = kzalloc(sizeof(*log), GFP_KERNEL);
+ if (!log)
+ goto out;
+
if (req->cmd->get_log_page.nsid == cpu_to_le32(NVME_NSID_ALL))
- status = nvmet_get_smart_log_all(req, slog);
+ status = nvmet_get_smart_log_all(req, log);
else
- status = nvmet_get_smart_log_nsid(req, slog);
- return status;
+ status = nvmet_get_smart_log_nsid(req, log);
+ if (status)
+ goto out;
+
+ status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log));
+out:
+ nvmet_req_complete(req, status);
}
-static void nvmet_execute_get_log_page(struct nvmet_req *req)
+static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req)
{
- struct nvme_smart_log *smart_log;
- size_t data_len = nvmet_get_log_page_len(req->cmd);
- void *buf;
- u16 status = 0;
+ struct nvmet_ctrl *ctrl = req->sq->ctrl;
+ u16 status = NVME_SC_INTERNAL;
+ size_t len;
- buf = kzalloc(data_len, GFP_KERNEL);
- if (!buf) {
- status = NVME_SC_INTERNAL;
+ if (req->data_len != NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32))
goto out;
- }
- switch (req->cmd->get_log_page.lid) {
- case NVME_LOG_ERROR:
- /*
- * We currently never set the More bit in the status field,
- * so all error log entries are invalid and can be zeroed out.
- * This is called a minum viable implementation (TM) of this
- * mandatory log page.
- */
- break;
- case NVME_LOG_SMART:
- /*
- * XXX: fill out actual smart log
- *
- * We might have a hard time coming up with useful values for
- * many of the fields, and even when we have useful data
- * available (e.g. units or commands read/written) those aren't
- * persistent over power loss.
- */
- if (data_len != sizeof(*smart_log)) {
- status = NVME_SC_INTERNAL;
- goto err;
- }
- smart_log = buf;
- status = nvmet_get_smart_log(req, smart_log);
- if (status)
- goto err;
- break;
- case NVME_LOG_FW_SLOT:
- /*
- * We only support a single firmware slot which always is
- * active, so we can zero out the whole firmware slot log and
- * still claim to fully implement this mandatory log page.
- */
- break;
- default:
- BUG();
- }
-
- status = nvmet_copy_to_sgl(req, 0, buf, data_len);
-
-err:
- kfree(buf);
+ mutex_lock(&ctrl->lock);
+ if (ctrl->nr_changed_ns == U32_MAX)
+ len = sizeof(__le32);
+ else
+ len = ctrl->nr_changed_ns * sizeof(__le32);
+ status = nvmet_copy_to_sgl(req, 0, ctrl->changed_ns_list, len);
+ if (!status)
+ status = nvmet_zero_sgl(req, len, req->data_len - len);
+ ctrl->nr_changed_ns = 0;
+ clear_bit(NVME_AEN_CFG_NS_ATTR, &ctrl->aen_masked);
+ mutex_unlock(&ctrl->lock);
out:
nvmet_req_complete(req, status);
}
@@ -201,7 +190,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
id->ver = cpu_to_le32(ctrl->subsys->ver);
/* XXX: figure out what to do about RTD3R/RTD3 */
- id->oaes = cpu_to_le32(1 << 8);
+ id->oaes = cpu_to_le32(NVMET_AEN_CFG_OPTIONAL);
id->ctratt = cpu_to_le32(1 << 0);
id->oacs = 0;
@@ -447,6 +436,16 @@ static void nvmet_execute_set_features(struct nvmet_req *req)
req->sq->ctrl->kato = DIV_ROUND_UP(val32, 1000);
nvmet_set_result(req, req->sq->ctrl->kato);
break;
+ case NVME_FEAT_ASYNC_EVENT:
+ val32 = le32_to_cpu(req->cmd->common.cdw10[1]);
+ if (val32 & ~NVMET_AEN_CFG_ALL) {
+ status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ break;
+ }
+
+ WRITE_ONCE(req->sq->ctrl->aen_enabled, val32);
+ nvmet_set_result(req, val32);
+ break;
case NVME_FEAT_HOST_ID:
status = NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
break;
@@ -485,9 +484,10 @@ static void nvmet_execute_get_features(struct nvmet_req *req)
break;
case NVME_FEAT_WRITE_ATOMIC:
break;
- case NVME_FEAT_ASYNC_EVENT:
- break;
#endif
+ case NVME_FEAT_ASYNC_EVENT:
+ nvmet_set_result(req, READ_ONCE(req->sq->ctrl->aen_enabled));
+ break;
case NVME_FEAT_VOLATILE_WC:
nvmet_set_result(req, 1);
break;
@@ -548,8 +548,6 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
struct nvme_command *cmd = req->cmd;
u16 ret;
- req->ns = NULL;
-
ret = nvmet_check_ctrl_status(req, cmd);
if (unlikely(ret))
return ret;
@@ -560,9 +558,28 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
switch (cmd->get_log_page.lid) {
case NVME_LOG_ERROR:
+ /*
+ * We currently never set the More bit in the status
+ * field, so all error log entries are invalid and can
+ * be zeroed out. This is called a minum viable
+ * implementation (TM) of this mandatory log page.
+ */
+ req->execute = nvmet_execute_get_log_page_noop;
+ return 0;
case NVME_LOG_SMART:
+ req->execute = nvmet_execute_get_log_page_smart;
+ return 0;
case NVME_LOG_FW_SLOT:
- req->execute = nvmet_execute_get_log_page;
+ /*
+ * We only support a single firmware slot which always
+ * is active, so we can zero out the whole firmware slot
+ * log and still claim to fully implement this mandatory
+ * log page.
+ */
+ req->execute = nvmet_execute_get_log_page_noop;
+ return 0;
+ case NVME_LOG_CHANGED_NS:
+ req->execute = nvmet_execute_get_log_changed_ns;
return 0;
}
break;
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index e95424f1..a03da76 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -57,6 +57,13 @@ u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf, size_t len)
return 0;
}
+u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len)
+{
+ if (sg_zero_buffer(req->sg, req->sg_cnt, len, off) != len)
+ return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
+ return 0;
+}
+
static unsigned int nvmet_max_nsid(struct nvmet_subsys *subsys)
{
struct nvmet_ns *ns;
@@ -137,6 +144,51 @@ static void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
schedule_work(&ctrl->async_event_work);
}
+static bool nvmet_aen_disabled(struct nvmet_ctrl *ctrl, u32 aen)
+{
+ if (!(READ_ONCE(ctrl->aen_enabled) & aen))
+ return true;
+ return test_and_set_bit(aen, &ctrl->aen_masked);
+}
+
+static void nvmet_add_to_changed_ns_log(struct nvmet_ctrl *ctrl, __le32 nsid)
+{
+ u32 i;
+
+ mutex_lock(&ctrl->lock);
+ if (ctrl->nr_changed_ns > NVME_MAX_CHANGED_NAMESPACES)
+ goto out_unlock;
+
+ for (i = 0; i < ctrl->nr_changed_ns; i++) {
+ if (ctrl->changed_ns_list[i] == nsid)
+ goto out_unlock;
+ }
+
+ if (ctrl->nr_changed_ns == NVME_MAX_CHANGED_NAMESPACES) {
+ ctrl->changed_ns_list[0] = cpu_to_le32(0xffffffff);
+ ctrl->nr_changed_ns = U32_MAX;
+ goto out_unlock;
+ }
+
+ ctrl->changed_ns_list[ctrl->nr_changed_ns++] = nsid;
+out_unlock:
+ mutex_unlock(&ctrl->lock);
+}
+
+static void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
+{
+ struct nvmet_ctrl *ctrl;
+
+ list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
+ nvmet_add_to_changed_ns_log(ctrl, cpu_to_le32(nsid));
+ if (nvmet_aen_disabled(ctrl, NVME_AEN_CFG_NS_ATTR))
+ continue;
+ nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
+ NVME_AER_NOTICE_NS_CHANGED,
+ NVME_LOG_CHANGED_NS);
+ }
+}
+
int nvmet_register_transport(const struct nvmet_fabrics_ops *ops)
{
int ret = 0;
@@ -271,33 +323,31 @@ void nvmet_put_namespace(struct nvmet_ns *ns)
percpu_ref_put(&ns->ref);
}
+static void nvmet_ns_dev_disable(struct nvmet_ns *ns)
+{
+ nvmet_bdev_ns_disable(ns);
+ nvmet_file_ns_disable(ns);
+}
+
int nvmet_ns_enable(struct nvmet_ns *ns)
{
struct nvmet_subsys *subsys = ns->subsys;
- struct nvmet_ctrl *ctrl;
int ret = 0;
mutex_lock(&subsys->lock);
if (ns->enabled)
goto out_unlock;
- ns->bdev = blkdev_get_by_path(ns->device_path, FMODE_READ | FMODE_WRITE,
- NULL);
- if (IS_ERR(ns->bdev)) {
- pr_err("failed to open block device %s: (%ld)\n",
- ns->device_path, PTR_ERR(ns->bdev));
- ret = PTR_ERR(ns->bdev);
- ns->bdev = NULL;
+ ret = nvmet_bdev_ns_enable(ns);
+ if (ret)
+ ret = nvmet_file_ns_enable(ns);
+ if (ret)
goto out_unlock;
- }
-
- ns->size = i_size_read(ns->bdev->bd_inode);
- ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev));
ret = percpu_ref_init(&ns->ref, nvmet_destroy_namespace,
0, GFP_KERNEL);
if (ret)
- goto out_blkdev_put;
+ goto out_dev_put;
if (ns->nsid > subsys->max_nsid)
subsys->max_nsid = ns->nsid;
@@ -320,24 +370,20 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
list_add_tail_rcu(&ns->dev_link, &old->dev_link);
}
- list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
- nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE, 0, 0);
-
+ nvmet_ns_changed(subsys, ns->nsid);
ns->enabled = true;
ret = 0;
out_unlock:
mutex_unlock(&subsys->lock);
return ret;
-out_blkdev_put:
- blkdev_put(ns->bdev, FMODE_WRITE|FMODE_READ);
- ns->bdev = NULL;
+out_dev_put:
+ nvmet_ns_dev_disable(ns);
goto out_unlock;
}
void nvmet_ns_disable(struct nvmet_ns *ns)
{
struct nvmet_subsys *subsys = ns->subsys;
- struct nvmet_ctrl *ctrl;
mutex_lock(&subsys->lock);
if (!ns->enabled)
@@ -363,11 +409,8 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
percpu_ref_exit(&ns->ref);
mutex_lock(&subsys->lock);
- list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
- nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE, 0, 0);
-
- if (ns->bdev)
- blkdev_put(ns->bdev, FMODE_WRITE|FMODE_READ);
+ nvmet_ns_changed(subsys, ns->nsid);
+ nvmet_ns_dev_disable(ns);
out_unlock:
mutex_unlock(&subsys->lock);
}
@@ -499,6 +542,25 @@ int nvmet_sq_init(struct nvmet_sq *sq)
}
EXPORT_SYMBOL_GPL(nvmet_sq_init);
+static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
+{
+ struct nvme_command *cmd = req->cmd;
+ u16 ret;
+
+ ret = nvmet_check_ctrl_status(req, cmd);
+ if (unlikely(ret))
+ return ret;
+
+ req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid);
+ if (unlikely(!req->ns))
+ return NVME_SC_INVALID_NS | NVME_SC_DNR;
+
+ if (req->ns->file)
+ return nvmet_file_parse_io_cmd(req);
+ else
+ return nvmet_bdev_parse_io_cmd(req);
+}
+
bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
struct nvmet_sq *sq, const struct nvmet_fabrics_ops *ops)
{
@@ -710,15 +772,14 @@ u16 nvmet_ctrl_find_get(const char *subsysnqn, const char *hostnqn, u16 cntlid,
u16 nvmet_check_ctrl_status(struct nvmet_req *req, struct nvme_command *cmd)
{
if (unlikely(!(req->sq->ctrl->cc & NVME_CC_ENABLE))) {
- pr_err("got io cmd %d while CC.EN == 0 on qid = %d\n",
+ pr_err("got cmd %d while CC.EN == 0 on qid = %d\n",
cmd->common.opcode, req->sq->qid);
return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
}
if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
- pr_err("got io cmd %d while CSTS.RDY == 0 on qid = %d\n",
+ pr_err("got cmd %d while CSTS.RDY == 0 on qid = %d\n",
cmd->common.opcode, req->sq->qid);
- req->ns = NULL;
return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
}
return 0;
@@ -809,12 +870,18 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
kref_init(&ctrl->ref);
ctrl->subsys = subsys;
+ WRITE_ONCE(ctrl->aen_enabled, NVMET_AEN_CFG_OPTIONAL);
+
+ ctrl->changed_ns_list = kmalloc_array(NVME_MAX_CHANGED_NAMESPACES,
+ sizeof(__le32), GFP_KERNEL);
+ if (!ctrl->changed_ns_list)
+ goto out_free_ctrl;
ctrl->cqs = kcalloc(subsys->max_qid + 1,
sizeof(struct nvmet_cq *),
GFP_KERNEL);
if (!ctrl->cqs)
- goto out_free_ctrl;
+ goto out_free_changed_ns_list;
ctrl->sqs = kcalloc(subsys->max_qid + 1,
sizeof(struct nvmet_sq *),
@@ -872,6 +939,8 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
kfree(ctrl->sqs);
out_free_cqs:
kfree(ctrl->cqs);
+out_free_changed_ns_list:
+ kfree(ctrl->changed_ns_list);
out_free_ctrl:
kfree(ctrl);
out_put_subsystem:
@@ -898,6 +967,7 @@ static void nvmet_ctrl_free(struct kref *ref)
kfree(ctrl->sqs);
kfree(ctrl->cqs);
+ kfree(ctrl->changed_ns_list);
kfree(ctrl);
nvmet_subsys_put(subsys);
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 231e04e..08656b8 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -187,8 +187,6 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
- req->ns = NULL;
-
if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
pr_err("got cmd %d while not ready\n",
cmd->common.opcode);
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index 19e9e42..d84ae004 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -77,8 +77,6 @@ u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
- req->ns = NULL;
-
switch (cmd->fabrics.fctype) {
case nvme_fabrics_type_property_set:
req->data_len = 0;
@@ -242,8 +240,6 @@ u16 nvmet_parse_connect_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
- req->ns = NULL;
-
if (cmd->common.opcode != nvme_fabrics_command) {
pr_err("invalid command 0x%x on unconnected queue.\n",
cmd->fabrics.opcode);
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 33ee8d3..408279c 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -31,7 +31,7 @@
/* *************************** Data Structures/Defines ****************** */
-#define NVMET_LS_CTX_COUNT 4
+#define NVMET_LS_CTX_COUNT 256
/* for this implementation, assume small single frame rqst/rsp */
#define NVME_FC_MAX_LS_BUFFER_SIZE 2048
diff --git a/drivers/nvme/target/io-cmd.c b/drivers/nvme/target/io-cmd-bdev.c
similarity index 76%
rename from drivers/nvme/target/io-cmd.c
rename to drivers/nvme/target/io-cmd-bdev.c
index cd23441..e0b0f7d 100644
--- a/drivers/nvme/target/io-cmd.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -16,6 +16,34 @@
#include <linux/module.h>
#include "nvmet.h"
+int nvmet_bdev_ns_enable(struct nvmet_ns *ns)
+{
+ int ret;
+
+ ns->bdev = blkdev_get_by_path(ns->device_path,
+ FMODE_READ | FMODE_WRITE, NULL);
+ if (IS_ERR(ns->bdev)) {
+ ret = PTR_ERR(ns->bdev);
+ if (ret != -ENOTBLK) {
+ pr_err("failed to open block device %s: (%ld)\n",
+ ns->device_path, PTR_ERR(ns->bdev));
+ }
+ ns->bdev = NULL;
+ return ret;
+ }
+ ns->size = i_size_read(ns->bdev->bd_inode);
+ ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev));
+ return 0;
+}
+
+void nvmet_bdev_ns_disable(struct nvmet_ns *ns)
+{
+ if (ns->bdev) {
+ blkdev_put(ns->bdev, FMODE_WRITE | FMODE_READ);
+ ns->bdev = NULL;
+ }
+}
+
static void nvmet_bio_done(struct bio *bio)
{
struct nvmet_req *req = bio->bi_private;
@@ -23,20 +51,14 @@ static void nvmet_bio_done(struct bio *bio)
nvmet_req_complete(req,
bio->bi_status ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
- if (bio != &req->inline_bio)
+ if (bio != &req->b.inline_bio)
bio_put(bio);
}
-static inline u32 nvmet_rw_len(struct nvmet_req *req)
-{
- return ((u32)le16_to_cpu(req->cmd->rw.length) + 1) <<
- req->ns->blksize_shift;
-}
-
-static void nvmet_execute_rw(struct nvmet_req *req)
+static void nvmet_bdev_execute_rw(struct nvmet_req *req)
{
int sg_cnt = req->sg_cnt;
- struct bio *bio = &req->inline_bio;
+ struct bio *bio = &req->b.inline_bio;
struct scatterlist *sg;
sector_t sector;
blk_qc_t cookie;
@@ -89,9 +111,9 @@ static void nvmet_execute_rw(struct nvmet_req *req)
blk_poll(bdev_get_queue(req->ns->bdev), cookie);
}
-static void nvmet_execute_flush(struct nvmet_req *req)
+static void nvmet_bdev_execute_flush(struct nvmet_req *req)
{
- struct bio *bio = &req->inline_bio;
+ struct bio *bio = &req->b.inline_bio;
bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec));
bio_set_dev(bio, req->ns->bdev);
@@ -102,7 +124,7 @@ static void nvmet_execute_flush(struct nvmet_req *req)
submit_bio(bio);
}
-static u16 nvmet_discard_range(struct nvmet_ns *ns,
+static u16 nvmet_bdev_discard_range(struct nvmet_ns *ns,
struct nvme_dsm_range *range, struct bio **bio)
{
int ret;
@@ -116,7 +138,7 @@ static u16 nvmet_discard_range(struct nvmet_ns *ns,
return 0;
}
-static void nvmet_execute_discard(struct nvmet_req *req)
+static void nvmet_bdev_execute_discard(struct nvmet_req *req)
{
struct nvme_dsm_range range;
struct bio *bio = NULL;
@@ -129,7 +151,7 @@ static void nvmet_execute_discard(struct nvmet_req *req)
if (status)
break;
- status = nvmet_discard_range(req->ns, &range, &bio);
+ status = nvmet_bdev_discard_range(req->ns, &range, &bio);
if (status)
break;
}
@@ -148,11 +170,11 @@ static void nvmet_execute_discard(struct nvmet_req *req)
}
}
-static void nvmet_execute_dsm(struct nvmet_req *req)
+static void nvmet_bdev_execute_dsm(struct nvmet_req *req)
{
switch (le32_to_cpu(req->cmd->dsm.attributes)) {
case NVME_DSMGMT_AD:
- nvmet_execute_discard(req);
+ nvmet_bdev_execute_discard(req);
return;
case NVME_DSMGMT_IDR:
case NVME_DSMGMT_IDW:
@@ -163,7 +185,7 @@ static void nvmet_execute_dsm(struct nvmet_req *req)
}
}
-static void nvmet_execute_write_zeroes(struct nvmet_req *req)
+static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req)
{
struct nvme_write_zeroes_cmd *write_zeroes = &req->cmd->write_zeroes;
struct bio *bio = NULL;
@@ -189,38 +211,27 @@ static void nvmet_execute_write_zeroes(struct nvmet_req *req)
}
}
-u16 nvmet_parse_io_cmd(struct nvmet_req *req)
+u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
- u16 ret;
-
- ret = nvmet_check_ctrl_status(req, cmd);
- if (unlikely(ret)) {
- req->ns = NULL;
- return ret;
- }
-
- req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid);
- if (unlikely(!req->ns))
- return NVME_SC_INVALID_NS | NVME_SC_DNR;
switch (cmd->common.opcode) {
case nvme_cmd_read:
case nvme_cmd_write:
- req->execute = nvmet_execute_rw;
+ req->execute = nvmet_bdev_execute_rw;
req->data_len = nvmet_rw_len(req);
return 0;
case nvme_cmd_flush:
- req->execute = nvmet_execute_flush;
+ req->execute = nvmet_bdev_execute_flush;
req->data_len = 0;
return 0;
case nvme_cmd_dsm:
- req->execute = nvmet_execute_dsm;
+ req->execute = nvmet_bdev_execute_dsm;
req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) *
sizeof(struct nvme_dsm_range);
return 0;
case nvme_cmd_write_zeroes:
- req->execute = nvmet_execute_write_zeroes;
+ req->execute = nvmet_bdev_execute_write_zeroes;
return 0;
default:
pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode,
diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
new file mode 100644
index 0000000..8c42b3a
--- /dev/null
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -0,0 +1,304 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVMe Over Fabrics Target File I/O commands implementation.
+ * Copyright (c) 2017-2018 Western Digital Corporation or its
+ * affiliates.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/uio.h>
+#include <linux/falloc.h>
+#include <linux/file.h>
+#include "nvmet.h"
+
+#define NVMET_MAX_MPOOL_BVEC 16
+#define NVMET_MIN_MPOOL_OBJ 16
+
+void nvmet_file_ns_disable(struct nvmet_ns *ns)
+{
+ if (ns->file) {
+ mempool_destroy(ns->bvec_pool);
+ ns->bvec_pool = NULL;
+ kmem_cache_destroy(ns->bvec_cache);
+ ns->bvec_cache = NULL;
+ fput(ns->file);
+ ns->file = NULL;
+ }
+}
+
+int nvmet_file_ns_enable(struct nvmet_ns *ns)
+{
+ int ret;
+ struct kstat stat;
+
+ ns->file = filp_open(ns->device_path,
+ O_RDWR | O_LARGEFILE | O_DIRECT, 0);
+ if (IS_ERR(ns->file)) {
+ pr_err("failed to open file %s: (%ld)\n",
+ ns->device_path, PTR_ERR(ns->file));
+ return PTR_ERR(ns->file);
+ }
+
+ ret = vfs_getattr(&ns->file->f_path,
+ &stat, STATX_SIZE, AT_STATX_FORCE_SYNC);
+ if (ret)
+ goto err;
+
+ ns->size = stat.size;
+ ns->blksize_shift = file_inode(ns->file)->i_blkbits;
+
+ ns->bvec_cache = kmem_cache_create("nvmet-bvec",
+ NVMET_MAX_MPOOL_BVEC * sizeof(struct bio_vec),
+ 0, SLAB_HWCACHE_ALIGN, NULL);
+ if (!ns->bvec_cache) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ ns->bvec_pool = mempool_create(NVMET_MIN_MPOOL_OBJ, mempool_alloc_slab,
+ mempool_free_slab, ns->bvec_cache);
+
+ if (!ns->bvec_pool) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ return ret;
+err:
+ ns->size = 0;
+ ns->blksize_shift = 0;
+ nvmet_file_ns_disable(ns);
+ return ret;
+}
+
+static void nvmet_file_init_bvec(struct bio_vec *bv, struct sg_page_iter *iter)
+{
+ bv->bv_page = sg_page_iter_page(iter);
+ bv->bv_offset = iter->sg->offset;
+ bv->bv_len = PAGE_SIZE - iter->sg->offset;
+}
+
+static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos,
+ unsigned long nr_segs, size_t count)
+{
+ struct kiocb *iocb = &req->f.iocb;
+ ssize_t (*call_iter)(struct kiocb *iocb, struct iov_iter *iter);
+ struct iov_iter iter;
+ int ki_flags = 0, rw;
+ ssize_t ret;
+
+ if (req->cmd->rw.opcode == nvme_cmd_write) {
+ if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA))
+ ki_flags = IOCB_DSYNC;
+ call_iter = req->ns->file->f_op->write_iter;
+ rw = WRITE;
+ } else {
+ call_iter = req->ns->file->f_op->read_iter;
+ rw = READ;
+ }
+
+ iov_iter_bvec(&iter, ITER_BVEC | rw, req->f.bvec, nr_segs, count);
+
+ iocb->ki_pos = pos;
+ iocb->ki_filp = req->ns->file;
+ iocb->ki_flags = IOCB_DIRECT | ki_flags;
+
+ ret = call_iter(iocb, &iter);
+
+ if (ret != -EIOCBQUEUED && iocb->ki_complete)
+ iocb->ki_complete(iocb, ret, 0);
+
+ return ret;
+}
+
+static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2)
+{
+ struct nvmet_req *req = container_of(iocb, struct nvmet_req, f.iocb);
+
+ if (req->f.bvec != req->inline_bvec) {
+ if (likely(req->f.mpool_alloc == false))
+ kfree(req->f.bvec);
+ else
+ mempool_free(req->f.bvec, req->ns->bvec_pool);
+ }
+
+ nvmet_req_complete(req, ret != req->data_len ?
+ NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+}
+
+static void nvmet_file_execute_rw(struct nvmet_req *req)
+{
+ ssize_t nr_bvec = DIV_ROUND_UP(req->data_len, PAGE_SIZE);
+ struct sg_page_iter sg_pg_iter;
+ unsigned long bv_cnt = 0;
+ bool is_sync = false;
+ size_t len = 0, total_len = 0;
+ ssize_t ret = 0;
+ loff_t pos;
+
+ if (!req->sg_cnt || !nr_bvec) {
+ nvmet_req_complete(req, 0);
+ return;
+ }
+
+ if (nr_bvec > NVMET_MAX_INLINE_BIOVEC)
+ req->f.bvec = kmalloc_array(nr_bvec, sizeof(struct bio_vec),
+ GFP_KERNEL);
+ else
+ req->f.bvec = req->inline_bvec;
+
+ req->f.mpool_alloc = false;
+ if (unlikely(!req->f.bvec)) {
+ /* fallback under memory pressure */
+ req->f.bvec = mempool_alloc(req->ns->bvec_pool, GFP_KERNEL);
+ req->f.mpool_alloc = true;
+ if (nr_bvec > NVMET_MAX_MPOOL_BVEC)
+ is_sync = true;
+ }
+
+ pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift;
+
+ memset(&req->f.iocb, 0, sizeof(struct kiocb));
+ for_each_sg_page(req->sg, &sg_pg_iter, req->sg_cnt, 0) {
+ nvmet_file_init_bvec(&req->f.bvec[bv_cnt], &sg_pg_iter);
+ len += req->f.bvec[bv_cnt].bv_len;
+ total_len += req->f.bvec[bv_cnt].bv_len;
+ bv_cnt++;
+
+ WARN_ON_ONCE((nr_bvec - 1) < 0);
+
+ if (unlikely(is_sync) &&
+ (nr_bvec - 1 == 0 || bv_cnt == NVMET_MAX_MPOOL_BVEC)) {
+ ret = nvmet_file_submit_bvec(req, pos, bv_cnt, len);
+ if (ret < 0)
+ goto out;
+ pos += len;
+ bv_cnt = 0;
+ len = 0;
+ }
+ nr_bvec--;
+ }
+
+ if (WARN_ON_ONCE(total_len != req->data_len))
+ ret = -EIO;
+out:
+ if (unlikely(is_sync || ret)) {
+ nvmet_file_io_done(&req->f.iocb, ret < 0 ? ret : total_len, 0);
+ return;
+ }
+ req->f.iocb.ki_complete = nvmet_file_io_done;
+ nvmet_file_submit_bvec(req, pos, bv_cnt, total_len);
+}
+
+static void nvmet_file_flush_work(struct work_struct *w)
+{
+ struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
+ int ret;
+
+ ret = vfs_fsync(req->ns->file, 1);
+
+ nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+}
+
+static void nvmet_file_execute_flush(struct nvmet_req *req)
+{
+ INIT_WORK(&req->f.work, nvmet_file_flush_work);
+ schedule_work(&req->f.work);
+}
+
+static void nvmet_file_execute_discard(struct nvmet_req *req)
+{
+ int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
+ struct nvme_dsm_range range;
+ loff_t offset;
+ loff_t len;
+ int i, ret;
+
+ for (i = 0; i <= le32_to_cpu(req->cmd->dsm.nr); i++) {
+ if (nvmet_copy_from_sgl(req, i * sizeof(range), &range,
+ sizeof(range)))
+ break;
+ offset = le64_to_cpu(range.slba) << req->ns->blksize_shift;
+ len = le32_to_cpu(range.nlb) << req->ns->blksize_shift;
+ ret = vfs_fallocate(req->ns->file, mode, offset, len);
+ if (ret)
+ break;
+ }
+
+ nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+}
+
+static void nvmet_file_dsm_work(struct work_struct *w)
+{
+ struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
+
+ switch (le32_to_cpu(req->cmd->dsm.attributes)) {
+ case NVME_DSMGMT_AD:
+ nvmet_file_execute_discard(req);
+ return;
+ case NVME_DSMGMT_IDR:
+ case NVME_DSMGMT_IDW:
+ default:
+ /* Not supported yet */
+ nvmet_req_complete(req, 0);
+ return;
+ }
+}
+
+static void nvmet_file_execute_dsm(struct nvmet_req *req)
+{
+ INIT_WORK(&req->f.work, nvmet_file_dsm_work);
+ schedule_work(&req->f.work);
+}
+
+static void nvmet_file_write_zeroes_work(struct work_struct *w)
+{
+ struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
+ struct nvme_write_zeroes_cmd *write_zeroes = &req->cmd->write_zeroes;
+ int mode = FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE;
+ loff_t offset;
+ loff_t len;
+ int ret;
+
+ offset = le64_to_cpu(write_zeroes->slba) << req->ns->blksize_shift;
+ len = (((sector_t)le16_to_cpu(write_zeroes->length) + 1) <<
+ req->ns->blksize_shift);
+
+ ret = vfs_fallocate(req->ns->file, mode, offset, len);
+ nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+}
+
+static void nvmet_file_execute_write_zeroes(struct nvmet_req *req)
+{
+ INIT_WORK(&req->f.work, nvmet_file_write_zeroes_work);
+ schedule_work(&req->f.work);
+}
+
+u16 nvmet_file_parse_io_cmd(struct nvmet_req *req)
+{
+ struct nvme_command *cmd = req->cmd;
+
+ switch (cmd->common.opcode) {
+ case nvme_cmd_read:
+ case nvme_cmd_write:
+ req->execute = nvmet_file_execute_rw;
+ req->data_len = nvmet_rw_len(req);
+ return 0;
+ case nvme_cmd_flush:
+ req->execute = nvmet_file_execute_flush;
+ req->data_len = 0;
+ return 0;
+ case nvme_cmd_dsm:
+ req->execute = nvmet_file_execute_dsm;
+ req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) *
+ sizeof(struct nvme_dsm_range);
+ return 0;
+ case nvme_cmd_write_zeroes:
+ req->execute = nvmet_file_execute_write_zeroes;
+ req->data_len = 0;
+ return 0;
+ default:
+ pr_err("unhandled cmd for file ns %d on qid %d\n",
+ cmd->common.opcode, req->sq->qid);
+ return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+ }
+}
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 31fdfba..1304ec3 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -45,6 +45,7 @@ struct nvme_loop_ctrl {
struct nvme_ctrl ctrl;
struct nvmet_ctrl *target_ctrl;
+ struct nvmet_port *port;
};
static inline struct nvme_loop_ctrl *to_loop_ctrl(struct nvme_ctrl *ctrl)
@@ -63,7 +64,8 @@ struct nvme_loop_queue {
unsigned long flags;
};
-static struct nvmet_port *nvmet_loop_port;
+static LIST_HEAD(nvme_loop_ports);
+static DEFINE_MUTEX(nvme_loop_ports_mutex);
static LIST_HEAD(nvme_loop_ctrl_list);
static DEFINE_MUTEX(nvme_loop_ctrl_mutex);
@@ -146,7 +148,7 @@ nvme_loop_timeout(struct request *rq, bool reserved)
/* fail with DNR on admin cmd timeout */
nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR;
- return BLK_EH_HANDLED;
+ return BLK_EH_DONE;
}
static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
@@ -169,12 +171,12 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
blk_mq_start_request(req);
iod->cmd.common.flags |= NVME_CMD_SGL_METABUF;
- iod->req.port = nvmet_loop_port;
+ iod->req.port = queue->ctrl->port;
if (!nvmet_req_init(&iod->req, &queue->nvme_cq,
&queue->nvme_sq, &nvme_loop_ops))
return BLK_STS_OK;
- if (blk_rq_payload_bytes(req)) {
+ if (blk_rq_nr_phys_segments(req)) {
iod->sg_table.sgl = iod->first_sgl;
if (sg_alloc_table_chained(&iod->sg_table,
blk_rq_nr_phys_segments(req),
@@ -469,6 +471,12 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
nvme_stop_ctrl(&ctrl->ctrl);
nvme_loop_shutdown_ctrl(ctrl);
+ if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
+ /* state change failure should never happen */
+ WARN_ON_ONCE(1);
+ return;
+ }
+
ret = nvme_loop_configure_admin_queue(ctrl);
if (ret)
goto out_disable;
@@ -511,6 +519,7 @@ static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
.free_ctrl = nvme_loop_free_ctrl,
.submit_async_event = nvme_loop_submit_async_event,
.delete_ctrl = nvme_loop_delete_ctrl_host,
+ .get_address = nvmf_get_address,
};
static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
@@ -559,6 +568,23 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
return ret;
}
+static struct nvmet_port *nvme_loop_find_port(struct nvme_ctrl *ctrl)
+{
+ struct nvmet_port *p, *found = NULL;
+
+ mutex_lock(&nvme_loop_ports_mutex);
+ list_for_each_entry(p, &nvme_loop_ports, entry) {
+ /* if no transport address is specified use the first port */
+ if ((ctrl->opts->mask & NVMF_OPT_TRADDR) &&
+ strcmp(ctrl->opts->traddr, p->disc_addr.traddr))
+ continue;
+ found = p;
+ break;
+ }
+ mutex_unlock(&nvme_loop_ports_mutex);
+ return found;
+}
+
static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
struct nvmf_ctrl_options *opts)
{
@@ -583,6 +609,7 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
ctrl->ctrl.sqsize = opts->queue_size - 1;
ctrl->ctrl.kato = opts->kato;
+ ctrl->port = nvme_loop_find_port(&ctrl->ctrl);
ctrl->queues = kcalloc(opts->nr_io_queues + 1, sizeof(*ctrl->queues),
GFP_KERNEL);
@@ -640,27 +667,17 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
static int nvme_loop_add_port(struct nvmet_port *port)
{
- /*
- * XXX: disalow adding more than one port so
- * there is no connection rejections when a
- * a subsystem is assigned to a port for which
- * loop doesn't have a pointer.
- * This scenario would be possible if we allowed
- * more than one port to be added and a subsystem
- * was assigned to a port other than nvmet_loop_port.
- */
-
- if (nvmet_loop_port)
- return -EPERM;
-
- nvmet_loop_port = port;
+ mutex_lock(&nvme_loop_ports_mutex);
+ list_add_tail(&port->entry, &nvme_loop_ports);
+ mutex_unlock(&nvme_loop_ports_mutex);
return 0;
}
static void nvme_loop_remove_port(struct nvmet_port *port)
{
- if (port == nvmet_loop_port)
- nvmet_loop_port = NULL;
+ mutex_lock(&nvme_loop_ports_mutex);
+ list_del_init(&port->entry);
+ mutex_unlock(&nvme_loop_ports_mutex);
}
static const struct nvmet_fabrics_ops nvme_loop_ops = {
@@ -676,6 +693,7 @@ static struct nvmf_transport_ops nvme_loop_transport = {
.name = "loop",
.module = THIS_MODULE,
.create_ctrl = nvme_loop_create_ctrl,
+ .allowed_opts = NVMF_OPT_TRADDR,
};
static int __init nvme_loop_init_module(void)
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 15fd84a..480dfe1 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -30,6 +30,21 @@
#define NVMET_ASYNC_EVENTS 4
#define NVMET_ERROR_LOG_SLOTS 128
+
+/*
+ * Supported optional AENs:
+ */
+#define NVMET_AEN_CFG_OPTIONAL \
+ NVME_AEN_CFG_NS_ATTR
+
+/*
+ * Plus mandatory SMART AENs (we'll never send them, but allow enabling them):
+ */
+#define NVMET_AEN_CFG_ALL \
+ (NVME_SMART_CRIT_SPARE | NVME_SMART_CRIT_TEMPERATURE | \
+ NVME_SMART_CRIT_RELIABILITY | NVME_SMART_CRIT_MEDIA | \
+ NVME_SMART_CRIT_VOLATILE_MEMORY | NVMET_AEN_CFG_OPTIONAL)
+
/* Helper Macros when NVMe error is NVME_SC_CONNECT_INVALID_PARAM
* The 16 bit shift is to set IATTR bit to 1, which means offending
* offset starts in the data section of connect()
@@ -43,6 +58,7 @@ struct nvmet_ns {
struct list_head dev_link;
struct percpu_ref ref;
struct block_device *bdev;
+ struct file *file;
u32 nsid;
u32 blksize_shift;
loff_t size;
@@ -57,6 +73,8 @@ struct nvmet_ns {
struct config_group group;
struct completion disable_done;
+ mempool_t *bvec_pool;
+ struct kmem_cache *bvec_cache;
};
static inline struct nvmet_ns *to_nvmet_ns(struct config_item *item)
@@ -82,7 +100,7 @@ struct nvmet_sq {
/**
* struct nvmet_port - Common structure to keep port
* information for the target.
- * @entry: List head for holding a list of these elements.
+ * @entry: Entry into referrals or transport list.
* @disc_addr: Address information is stored in a format defined
* for a discovery log page entry.
* @group: ConfigFS group for this element's folder.
@@ -120,6 +138,8 @@ struct nvmet_ctrl {
u16 cntlid;
u32 kato;
+ u32 aen_enabled;
+ unsigned long aen_masked;
struct nvmet_req *async_event_cmds[NVMET_ASYNC_EVENTS];
unsigned int nr_async_event_cmds;
struct list_head async_events;
@@ -132,6 +152,9 @@ struct nvmet_ctrl {
const struct nvmet_fabrics_ops *ops;
+ __le32 *changed_ns_list;
+ u32 nr_changed_ns;
+
char subsysnqn[NVMF_NQN_FIELD_LEN];
char hostnqn[NVMF_NQN_FIELD_LEN];
};
@@ -222,8 +245,18 @@ struct nvmet_req {
struct nvmet_cq *cq;
struct nvmet_ns *ns;
struct scatterlist *sg;
- struct bio inline_bio;
struct bio_vec inline_bvec[NVMET_MAX_INLINE_BIOVEC];
+ union {
+ struct {
+ struct bio inline_bio;
+ } b;
+ struct {
+ bool mpool_alloc;
+ struct kiocb iocb;
+ struct bio_vec *bvec;
+ struct work_struct work;
+ } f;
+ };
int sg_cnt;
/* data length as parsed from the command: */
size_t data_len;
@@ -263,7 +296,8 @@ struct nvmet_async_event {
};
u16 nvmet_parse_connect_cmd(struct nvmet_req *req);
-u16 nvmet_parse_io_cmd(struct nvmet_req *req);
+u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req);
+u16 nvmet_file_parse_io_cmd(struct nvmet_req *req);
u16 nvmet_parse_admin_cmd(struct nvmet_req *req);
u16 nvmet_parse_discovery_cmd(struct nvmet_req *req);
u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req);
@@ -316,6 +350,7 @@ u16 nvmet_copy_to_sgl(struct nvmet_req *req, off_t off, const void *buf,
size_t len);
u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf,
size_t len);
+u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len);
u32 nvmet_get_log_page_len(struct nvme_command *cmd);
@@ -338,4 +373,14 @@ extern struct rw_semaphore nvmet_config_sem;
bool nvmet_host_allowed(struct nvmet_req *req, struct nvmet_subsys *subsys,
const char *hostnqn);
+int nvmet_bdev_ns_enable(struct nvmet_ns *ns);
+int nvmet_file_ns_enable(struct nvmet_ns *ns);
+void nvmet_bdev_ns_disable(struct nvmet_ns *ns);
+void nvmet_file_ns_disable(struct nvmet_ns *ns);
+
+static inline u32 nvmet_rw_len(struct nvmet_req *req)
+{
+ return ((u32)le16_to_cpu(req->cmd->rw.length) + 1) <<
+ req->ns->blksize_shift;
+}
#endif /* _NVMET_H */
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 064c818..33d8551 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -76,6 +76,8 @@ int of_device_add(struct platform_device *ofdev)
* of_dma_configure - Setup DMA configuration
* @dev: Device to apply DMA configuration
* @np: Pointer to OF node having DMA configuration
+ * @force_dma: Whether device is to be set up by of_dma_configure() even if
+ * DMA capability is not explicitly described by firmware.
*
* Try to get devices's DMA configuration from DT and update it
* accordingly.
@@ -84,7 +86,7 @@ int of_device_add(struct platform_device *ofdev)
* can use a platform bus notifier and handle BUS_NOTIFY_ADD_DEVICE events
* to fix up DMA configuration.
*/
-int of_dma_configure(struct device *dev, struct device_node *np)
+int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
{
u64 dma_addr, paddr, size = 0;
int ret;
@@ -100,7 +102,7 @@ int of_dma_configure(struct device *dev, struct device_node *np)
* DMA configuration regardless of whether "dma-ranges" is
* correctly specified or not.
*/
- if (!dev->bus->force_dma)
+ if (!force_dma)
return ret == -ENODEV ? 0 : ret;
dma_addr = offset = 0;
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 84aa9d6..6da20b9 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -942,7 +942,7 @@ int __init early_init_dt_scan_chosen_stdout(void)
int offset;
const char *p, *q, *options = NULL;
int l;
- const struct earlycon_id *match;
+ const struct earlycon_id **p_match;
const void *fdt = initial_boot_params;
offset = fdt_path_offset(fdt, "/chosen");
@@ -969,7 +969,10 @@ int __init early_init_dt_scan_chosen_stdout(void)
return 0;
}
- for (match = __earlycon_table; match < __earlycon_table_end; match++) {
+ for (p_match = __earlycon_table; p_match < __earlycon_table_end;
+ p_match++) {
+ const struct earlycon_id *match = *p_match;
+
if (!match->compatible[0])
continue;
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 9a4f4246..895c83e 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -353,7 +353,7 @@ int of_reserved_mem_device_init_by_idx(struct device *dev,
/* ensure that dma_ops is set for virtual devices
* using reserved memory
*/
- of_dma_configure(dev, np);
+ of_dma_configure(dev, np, true);
dev_info(dev, "assigned reserved memory node %s\n", rmem->name);
} else {
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index b35fe88..7baa53e 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -102,12 +102,28 @@ static DEFINE_IDR(ovcs_idr);
static BLOCKING_NOTIFIER_HEAD(overlay_notify_chain);
+/**
+ * of_overlay_notifier_register() - Register notifier for overlay operations
+ * @nb: Notifier block to register
+ *
+ * Register for notification on overlay operations on device tree nodes. The
+ * reported actions definied by @of_reconfig_change. The notifier callback
+ * furthermore receives a pointer to the affected device tree node.
+ *
+ * Note that a notifier callback is not supposed to store pointers to a device
+ * tree node or its content beyond @OF_OVERLAY_POST_REMOVE corresponding to the
+ * respective node it received.
+ */
int of_overlay_notifier_register(struct notifier_block *nb)
{
return blocking_notifier_chain_register(&overlay_notify_chain, nb);
}
EXPORT_SYMBOL_GPL(of_overlay_notifier_register);
+/**
+ * of_overlay_notifier_register() - Unregister notifier for overlay operations
+ * @nb: Notifier block to unregister
+ */
int of_overlay_notifier_unregister(struct notifier_block *nb)
{
return blocking_notifier_chain_unregister(&overlay_notify_chain, nb);
@@ -671,17 +687,13 @@ static void free_overlay_changeset(struct overlay_changeset *ovcs)
of_node_put(ovcs->fragments[i].overlay);
}
kfree(ovcs->fragments);
-
/*
- * TODO
- *
- * would like to: kfree(ovcs->overlay_tree);
- * but can not since drivers may have pointers into this data
- *
- * would like to: kfree(ovcs->fdt);
- * but can not since drivers may have pointers into this data
+ * There should be no live pointers into ovcs->overlay_tree and
+ * ovcs->fdt due to the policy that overlay notifiers are not allowed
+ * to retain pointers into the overlay devicetree.
*/
-
+ kfree(ovcs->overlay_tree);
+ kfree(ovcs->fdt);
kfree(ovcs);
}
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 92fa94a..ab2f3fe 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -33,8 +33,6 @@ LIST_HEAD(opp_tables);
/* Lock to allow exclusive modification to the device and opp lists */
DEFINE_MUTEX(opp_table_lock);
-static void dev_pm_opp_get(struct dev_pm_opp *opp);
-
static struct opp_device *_find_opp_dev(const struct device *dev,
struct opp_table *opp_table)
{
@@ -281,6 +279,23 @@ unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev)
}
EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp_freq);
+int _get_opp_count(struct opp_table *opp_table)
+{
+ struct dev_pm_opp *opp;
+ int count = 0;
+
+ mutex_lock(&opp_table->lock);
+
+ list_for_each_entry(opp, &opp_table->opp_list, node) {
+ if (opp->available)
+ count++;
+ }
+
+ mutex_unlock(&opp_table->lock);
+
+ return count;
+}
+
/**
* dev_pm_opp_get_opp_count() - Get number of opps available in the opp table
* @dev: device for which we do this operation
@@ -291,25 +306,17 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp_freq);
int dev_pm_opp_get_opp_count(struct device *dev)
{
struct opp_table *opp_table;
- struct dev_pm_opp *temp_opp;
- int count = 0;
+ int count;
opp_table = _find_opp_table(dev);
if (IS_ERR(opp_table)) {
count = PTR_ERR(opp_table);
dev_dbg(dev, "%s: OPP table not found (%d)\n",
__func__, count);
- return count;
+ return 0;
}
- mutex_lock(&opp_table->lock);
-
- list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
- if (temp_opp->available)
- count++;
- }
-
- mutex_unlock(&opp_table->lock);
+ count = _get_opp_count(opp_table);
dev_pm_opp_put_opp_table(opp_table);
return count;
@@ -892,7 +899,7 @@ static void _opp_kref_release(struct kref *kref)
dev_pm_opp_put_opp_table(opp_table);
}
-static void dev_pm_opp_get(struct dev_pm_opp *opp)
+void dev_pm_opp_get(struct dev_pm_opp *opp)
{
kref_get(&opp->kref);
}
@@ -985,6 +992,43 @@ static bool _opp_supported_by_regulators(struct dev_pm_opp *opp,
return true;
}
+static int _opp_is_duplicate(struct device *dev, struct dev_pm_opp *new_opp,
+ struct opp_table *opp_table,
+ struct list_head **head)
+{
+ struct dev_pm_opp *opp;
+
+ /*
+ * Insert new OPP in order of increasing frequency and discard if
+ * already present.
+ *
+ * Need to use &opp_table->opp_list in the condition part of the 'for'
+ * loop, don't replace it with head otherwise it will become an infinite
+ * loop.
+ */
+ list_for_each_entry(opp, &opp_table->opp_list, node) {
+ if (new_opp->rate > opp->rate) {
+ *head = &opp->node;
+ continue;
+ }
+
+ if (new_opp->rate < opp->rate)
+ return 0;
+
+ /* Duplicate OPPs */
+ dev_warn(dev, "%s: duplicate OPPs detected. Existing: freq: %lu, volt: %lu, enabled: %d. New: freq: %lu, volt: %lu, enabled: %d\n",
+ __func__, opp->rate, opp->supplies[0].u_volt,
+ opp->available, new_opp->rate,
+ new_opp->supplies[0].u_volt, new_opp->available);
+
+ /* Should we compare voltages for all regulators here ? */
+ return opp->available &&
+ new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? -EBUSY : -EEXIST;
+ }
+
+ return 0;
+}
+
/*
* Returns:
* 0: On success. And appropriate error message for duplicate OPPs.
@@ -996,49 +1040,22 @@ static bool _opp_supported_by_regulators(struct dev_pm_opp *opp,
* should be considered an error by the callers of _opp_add().
*/
int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
- struct opp_table *opp_table)
+ struct opp_table *opp_table, bool rate_not_available)
{
- struct dev_pm_opp *opp;
struct list_head *head;
int ret;
- /*
- * Insert new OPP in order of increasing frequency and discard if
- * already present.
- *
- * Need to use &opp_table->opp_list in the condition part of the 'for'
- * loop, don't replace it with head otherwise it will become an infinite
- * loop.
- */
mutex_lock(&opp_table->lock);
head = &opp_table->opp_list;
- list_for_each_entry(opp, &opp_table->opp_list, node) {
- if (new_opp->rate > opp->rate) {
- head = &opp->node;
- continue;
+ if (likely(!rate_not_available)) {
+ ret = _opp_is_duplicate(dev, new_opp, opp_table, &head);
+ if (ret) {
+ mutex_unlock(&opp_table->lock);
+ return ret;
}
-
- if (new_opp->rate < opp->rate)
- break;
-
- /* Duplicate OPPs */
- dev_warn(dev, "%s: duplicate OPPs detected. Existing: freq: %lu, volt: %lu, enabled: %d. New: freq: %lu, volt: %lu, enabled: %d\n",
- __func__, opp->rate, opp->supplies[0].u_volt,
- opp->available, new_opp->rate,
- new_opp->supplies[0].u_volt, new_opp->available);
-
- /* Should we compare voltages for all regulators here ? */
- ret = opp->available &&
- new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? -EBUSY : -EEXIST;
-
- mutex_unlock(&opp_table->lock);
- return ret;
}
- if (opp_table->get_pstate)
- new_opp->pstate = opp_table->get_pstate(dev, new_opp->rate);
-
list_add(&new_opp->node, head);
mutex_unlock(&opp_table->lock);
@@ -1104,7 +1121,7 @@ int _opp_add_v1(struct opp_table *opp_table, struct device *dev,
new_opp->available = true;
new_opp->dynamic = dynamic;
- ret = _opp_add(dev, new_opp, opp_table);
+ ret = _opp_add(dev, new_opp, opp_table, false);
if (ret) {
/* Don't return error for duplicate OPPs */
if (ret == -EBUSY)
@@ -1140,7 +1157,6 @@ struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev,
const u32 *versions, unsigned int count)
{
struct opp_table *opp_table;
- int ret;
opp_table = dev_pm_opp_get_opp_table(dev);
if (!opp_table)
@@ -1149,29 +1165,20 @@ struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev,
/* Make sure there are no concurrent readers while updating opp_table */
WARN_ON(!list_empty(&opp_table->opp_list));
- /* Do we already have a version hierarchy associated with opp_table? */
- if (opp_table->supported_hw) {
- dev_err(dev, "%s: Already have supported hardware list\n",
- __func__);
- ret = -EBUSY;
- goto err;
- }
+ /* Another CPU that shares the OPP table has set the property ? */
+ if (opp_table->supported_hw)
+ return opp_table;
opp_table->supported_hw = kmemdup(versions, count * sizeof(*versions),
GFP_KERNEL);
if (!opp_table->supported_hw) {
- ret = -ENOMEM;
- goto err;
+ dev_pm_opp_put_opp_table(opp_table);
+ return ERR_PTR(-ENOMEM);
}
opp_table->supported_hw_count = count;
return opp_table;
-
-err:
- dev_pm_opp_put_opp_table(opp_table);
-
- return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(dev_pm_opp_set_supported_hw);
@@ -1188,12 +1195,6 @@ void dev_pm_opp_put_supported_hw(struct opp_table *opp_table)
/* Make sure there are no concurrent readers while updating opp_table */
WARN_ON(!list_empty(&opp_table->opp_list));
- if (!opp_table->supported_hw) {
- pr_err("%s: Doesn't have supported hardware list\n",
- __func__);
- return;
- }
-
kfree(opp_table->supported_hw);
opp_table->supported_hw = NULL;
opp_table->supported_hw_count = 0;
@@ -1215,7 +1216,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_supported_hw);
struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name)
{
struct opp_table *opp_table;
- int ret;
opp_table = dev_pm_opp_get_opp_table(dev);
if (!opp_table)
@@ -1224,26 +1224,17 @@ struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name)
/* Make sure there are no concurrent readers while updating opp_table */
WARN_ON(!list_empty(&opp_table->opp_list));
- /* Do we already have a prop-name associated with opp_table? */
- if (opp_table->prop_name) {
- dev_err(dev, "%s: Already have prop-name %s\n", __func__,
- opp_table->prop_name);
- ret = -EBUSY;
- goto err;
- }
+ /* Another CPU that shares the OPP table has set the property ? */
+ if (opp_table->prop_name)
+ return opp_table;
opp_table->prop_name = kstrdup(name, GFP_KERNEL);
if (!opp_table->prop_name) {
- ret = -ENOMEM;
- goto err;
+ dev_pm_opp_put_opp_table(opp_table);
+ return ERR_PTR(-ENOMEM);
}
return opp_table;
-
-err:
- dev_pm_opp_put_opp_table(opp_table);
-
- return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(dev_pm_opp_set_prop_name);
@@ -1260,11 +1251,6 @@ void dev_pm_opp_put_prop_name(struct opp_table *opp_table)
/* Make sure there are no concurrent readers while updating opp_table */
WARN_ON(!list_empty(&opp_table->opp_list));
- if (!opp_table->prop_name) {
- pr_err("%s: Doesn't have a prop-name\n", __func__);
- return;
- }
-
kfree(opp_table->prop_name);
opp_table->prop_name = NULL;
@@ -1334,11 +1320,9 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
goto err;
}
- /* Already have regulators set */
- if (opp_table->regulators) {
- ret = -EBUSY;
- goto err;
- }
+ /* Another CPU that shares the OPP table has set the regulators ? */
+ if (opp_table->regulators)
+ return opp_table;
opp_table->regulators = kmalloc_array(count,
sizeof(*opp_table->regulators),
@@ -1392,10 +1376,8 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table)
{
int i;
- if (!opp_table->regulators) {
- pr_err("%s: Doesn't have regulators set\n", __func__);
- return;
- }
+ if (!opp_table->regulators)
+ goto put_opp_table;
/* Make sure there are no concurrent readers while updating opp_table */
WARN_ON(!list_empty(&opp_table->opp_list));
@@ -1409,6 +1391,7 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table)
opp_table->regulators = NULL;
opp_table->regulator_count = 0;
+put_opp_table:
dev_pm_opp_put_opp_table(opp_table);
}
EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulators);
@@ -1494,7 +1477,6 @@ struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev,
int (*set_opp)(struct dev_pm_set_opp_data *data))
{
struct opp_table *opp_table;
- int ret;
if (!set_opp)
return ERR_PTR(-EINVAL);
@@ -1505,24 +1487,15 @@ struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev,
/* This should be called before OPPs are initialized */
if (WARN_ON(!list_empty(&opp_table->opp_list))) {
- ret = -EBUSY;
- goto err;
+ dev_pm_opp_put_opp_table(opp_table);
+ return ERR_PTR(-EBUSY);
}
- /* Already have custom set_opp helper */
- if (WARN_ON(opp_table->set_opp)) {
- ret = -EBUSY;
- goto err;
- }
-
- opp_table->set_opp = set_opp;
+ /* Another CPU that shares the OPP table has set the helper ? */
+ if (!opp_table->set_opp)
+ opp_table->set_opp = set_opp;
return opp_table;
-
-err:
- dev_pm_opp_put_opp_table(opp_table);
-
- return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(dev_pm_opp_register_set_opp_helper);
@@ -1535,97 +1508,15 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_register_set_opp_helper);
*/
void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table)
{
- if (!opp_table->set_opp) {
- pr_err("%s: Doesn't have custom set_opp helper set\n",
- __func__);
- return;
- }
-
/* Make sure there are no concurrent readers while updating opp_table */
WARN_ON(!list_empty(&opp_table->opp_list));
opp_table->set_opp = NULL;
-
dev_pm_opp_put_opp_table(opp_table);
}
EXPORT_SYMBOL_GPL(dev_pm_opp_unregister_set_opp_helper);
/**
- * dev_pm_opp_register_get_pstate_helper() - Register get_pstate() helper.
- * @dev: Device for which the helper is getting registered.
- * @get_pstate: Helper.
- *
- * TODO: Remove this callback after the same information is available via Device
- * Tree.
- *
- * This allows a platform to initialize the performance states of individual
- * OPPs for its devices, until we get similar information directly from DT.
- *
- * This must be called before the OPPs are initialized for the device.
- */
-struct opp_table *dev_pm_opp_register_get_pstate_helper(struct device *dev,
- int (*get_pstate)(struct device *dev, unsigned long rate))
-{
- struct opp_table *opp_table;
- int ret;
-
- if (!get_pstate)
- return ERR_PTR(-EINVAL);
-
- opp_table = dev_pm_opp_get_opp_table(dev);
- if (!opp_table)
- return ERR_PTR(-ENOMEM);
-
- /* This should be called before OPPs are initialized */
- if (WARN_ON(!list_empty(&opp_table->opp_list))) {
- ret = -EBUSY;
- goto err;
- }
-
- /* Already have genpd_performance_state set */
- if (WARN_ON(opp_table->genpd_performance_state)) {
- ret = -EBUSY;
- goto err;
- }
-
- opp_table->genpd_performance_state = true;
- opp_table->get_pstate = get_pstate;
-
- return opp_table;
-
-err:
- dev_pm_opp_put_opp_table(opp_table);
-
- return ERR_PTR(ret);
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_register_get_pstate_helper);
-
-/**
- * dev_pm_opp_unregister_get_pstate_helper() - Releases resources blocked for
- * get_pstate() helper
- * @opp_table: OPP table returned from dev_pm_opp_register_get_pstate_helper().
- *
- * Release resources blocked for platform specific get_pstate() helper.
- */
-void dev_pm_opp_unregister_get_pstate_helper(struct opp_table *opp_table)
-{
- if (!opp_table->genpd_performance_state) {
- pr_err("%s: Doesn't have performance states set\n",
- __func__);
- return;
- }
-
- /* Make sure there are no concurrent readers while updating opp_table */
- WARN_ON(!list_empty(&opp_table->opp_list));
-
- opp_table->genpd_performance_state = false;
- opp_table->get_pstate = NULL;
-
- dev_pm_opp_put_opp_table(opp_table);
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_unregister_get_pstate_helper);
-
-/**
* dev_pm_opp_add() - Add an OPP table from a table definitions
* @dev: device for which we do this operation
* @freq: Frequency in Hz for this OPP
diff --git a/drivers/opp/debugfs.c b/drivers/opp/debugfs.c
index b03c035..e6828e5 100644
--- a/drivers/opp/debugfs.c
+++ b/drivers/opp/debugfs.c
@@ -77,10 +77,21 @@ int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table)
{
struct dentry *pdentry = opp_table->dentry;
struct dentry *d;
+ unsigned long id;
char name[25]; /* 20 chars for 64 bit value + 5 (opp:\0) */
- /* Rate is unique to each OPP, use it to give opp-name */
- snprintf(name, sizeof(name), "opp:%lu", opp->rate);
+ /*
+ * Get directory name for OPP.
+ *
+ * - Normally rate is unique to each OPP, use it to get unique opp-name.
+ * - For some devices rate isn't available, use index instead.
+ */
+ if (likely(opp->rate))
+ id = opp->rate;
+ else
+ id = _get_opp_count(opp_table);
+
+ snprintf(name, sizeof(name), "opp:%lu", id);
/* Create per-opp directory */
d = debugfs_create_dir(name, pdentry);
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index cb716aa..7af0dde 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -17,6 +17,7 @@
#include <linux/errno.h>
#include <linux/device.h>
#include <linux/of_device.h>
+#include <linux/pm_domain.h>
#include <linux/slab.h>
#include <linux/export.h>
@@ -250,20 +251,17 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table);
/* Returns opp descriptor node for a device node, caller must
* do of_node_put() */
-static struct device_node *_opp_of_get_opp_desc_node(struct device_node *np)
+static struct device_node *_opp_of_get_opp_desc_node(struct device_node *np,
+ int index)
{
- /*
- * There should be only ONE phandle present in "operating-points-v2"
- * property.
- */
-
- return of_parse_phandle(np, "operating-points-v2", 0);
+ /* "operating-points-v2" can be an array for power domain providers */
+ return of_parse_phandle(np, "operating-points-v2", index);
}
/* Returns opp descriptor node for a device, caller must do of_node_put() */
struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev)
{
- return _opp_of_get_opp_desc_node(dev->of_node);
+ return _opp_of_get_opp_desc_node(dev->of_node, 0);
}
EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_opp_desc_node);
@@ -289,9 +287,10 @@ static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
struct device_node *np)
{
struct dev_pm_opp *new_opp;
- u64 rate;
+ u64 rate = 0;
u32 val;
int ret;
+ bool rate_not_available = false;
new_opp = _opp_allocate(opp_table);
if (!new_opp)
@@ -299,8 +298,21 @@ static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
ret = of_property_read_u64(np, "opp-hz", &rate);
if (ret < 0) {
- dev_err(dev, "%s: opp-hz not found\n", __func__);
- goto free_opp;
+ /* "opp-hz" is optional for devices like power domains. */
+ if (!of_find_property(dev->of_node, "#power-domain-cells",
+ NULL)) {
+ dev_err(dev, "%s: opp-hz not found\n", __func__);
+ goto free_opp;
+ }
+
+ rate_not_available = true;
+ } else {
+ /*
+ * Rate is defined as an unsigned long in clk API, and so
+ * casting explicitly to its type. Must be fixed once rate is 64
+ * bit guaranteed in clk API.
+ */
+ new_opp->rate = (unsigned long)rate;
}
/* Check if the OPP supports hardware's hierarchy of versions or not */
@@ -309,12 +321,6 @@ static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
goto free_opp;
}
- /*
- * Rate is defined as an unsigned long in clk API, and so casting
- * explicitly to its type. Must be fixed once rate is 64 bit
- * guaranteed in clk API.
- */
- new_opp->rate = (unsigned long)rate;
new_opp->turbo = of_property_read_bool(np, "turbo-mode");
new_opp->np = np;
@@ -324,11 +330,13 @@ static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
if (!of_property_read_u32(np, "clock-latency-ns", &val))
new_opp->clock_latency_ns = val;
+ new_opp->pstate = of_genpd_opp_to_performance_state(dev, np);
+
ret = opp_parse_supplies(new_opp, dev, opp_table);
if (ret)
goto free_opp;
- ret = _opp_add(dev, new_opp, opp_table);
+ ret = _opp_add(dev, new_opp, opp_table, rate_not_available);
if (ret) {
/* Don't return error for duplicate OPPs */
if (ret == -EBUSY)
@@ -374,7 +382,8 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
{
struct device_node *np;
struct opp_table *opp_table;
- int ret = 0, count = 0;
+ int ret = 0, count = 0, pstate_count = 0;
+ struct dev_pm_opp *opp;
opp_table = _managed_opp(opp_np);
if (opp_table) {
@@ -408,6 +417,20 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
goto put_opp_table;
}
+ list_for_each_entry(opp, &opp_table->opp_list, node)
+ pstate_count += !!opp->pstate;
+
+ /* Either all or none of the nodes shall have performance state set */
+ if (pstate_count && pstate_count != count) {
+ dev_err(dev, "Not all nodes have performance state set (%d: %d)\n",
+ count, pstate_count);
+ ret = -ENOENT;
+ goto put_opp_table;
+ }
+
+ if (pstate_count)
+ opp_table->genpd_performance_state = true;
+
opp_table->np = opp_np;
if (of_property_read_bool(opp_np, "opp-shared"))
opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED;
@@ -509,6 +532,54 @@ int dev_pm_opp_of_add_table(struct device *dev)
}
EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table);
+/**
+ * dev_pm_opp_of_add_table_indexed() - Initialize indexed opp table from device tree
+ * @dev: device pointer used to lookup OPP table.
+ * @index: Index number.
+ *
+ * Register the initial OPP table with the OPP library for given device only
+ * using the "operating-points-v2" property.
+ *
+ * Return:
+ * 0 On success OR
+ * Duplicate OPPs (both freq and volt are same) and opp->available
+ * -EEXIST Freq are same and volt are different OR
+ * Duplicate OPPs (both freq and volt are same) and !opp->available
+ * -ENOMEM Memory allocation failure
+ * -ENODEV when 'operating-points' property is not found or is invalid data
+ * in device node.
+ * -ENODATA when empty 'operating-points' property is found
+ * -EINVAL when invalid entries are found in opp-v2 table
+ */
+int dev_pm_opp_of_add_table_indexed(struct device *dev, int index)
+{
+ struct device_node *opp_np;
+ int ret, count;
+
+again:
+ opp_np = _opp_of_get_opp_desc_node(dev->of_node, index);
+ if (!opp_np) {
+ /*
+ * If only one phandle is present, then the same OPP table
+ * applies for all index requests.
+ */
+ count = of_count_phandle_with_args(dev->of_node,
+ "operating-points-v2", NULL);
+ if (count == 1 && index) {
+ index = 0;
+ goto again;
+ }
+
+ return -ENODEV;
+ }
+
+ ret = _of_add_opp_table_v2(dev, opp_np);
+ of_node_put(opp_np);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table_indexed);
+
/* CPU device specific helpers */
/**
@@ -613,7 +684,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev,
}
/* Get OPP descriptor node */
- tmp_np = _opp_of_get_opp_desc_node(cpu_np);
+ tmp_np = _opp_of_get_opp_desc_node(cpu_np, 0);
of_node_put(cpu_np);
if (!tmp_np) {
pr_err("%pOF: Couldn't find opp node\n", cpu_np);
@@ -633,3 +704,76 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev,
return ret;
}
EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_sharing_cpus);
+
+/**
+ * of_dev_pm_opp_find_required_opp() - Search for required OPP.
+ * @dev: The device whose OPP node is referenced by the 'np' DT node.
+ * @np: Node that contains the "required-opps" property.
+ *
+ * Returns the OPP of the device 'dev', whose phandle is present in the "np"
+ * node. Although the "required-opps" property supports having multiple
+ * phandles, this helper routine only parses the very first phandle in the list.
+ *
+ * Return: Matching opp, else returns ERR_PTR in case of error and should be
+ * handled using IS_ERR.
+ *
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
+ */
+struct dev_pm_opp *of_dev_pm_opp_find_required_opp(struct device *dev,
+ struct device_node *np)
+{
+ struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ENODEV);
+ struct device_node *required_np;
+ struct opp_table *opp_table;
+
+ opp_table = _find_opp_table(dev);
+ if (IS_ERR(opp_table))
+ return ERR_CAST(opp_table);
+
+ required_np = of_parse_phandle(np, "required-opps", 0);
+ if (unlikely(!required_np)) {
+ dev_err(dev, "Unable to parse required-opps\n");
+ goto put_opp_table;
+ }
+
+ mutex_lock(&opp_table->lock);
+
+ list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
+ if (temp_opp->available && temp_opp->np == required_np) {
+ opp = temp_opp;
+
+ /* Increment the reference count of OPP */
+ dev_pm_opp_get(opp);
+ break;
+ }
+ }
+
+ mutex_unlock(&opp_table->lock);
+
+ of_node_put(required_np);
+put_opp_table:
+ dev_pm_opp_put_opp_table(opp_table);
+
+ return opp;
+}
+EXPORT_SYMBOL_GPL(of_dev_pm_opp_find_required_opp);
+
+/**
+ * dev_pm_opp_get_of_node() - Gets the DT node corresponding to an opp
+ * @opp: opp for which DT node has to be returned for
+ *
+ * Return: DT node corresponding to the opp, else 0 on success.
+ *
+ * The caller needs to put the node with of_node_put() after using it.
+ */
+struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp)
+{
+ if (IS_ERR_OR_NULL(opp)) {
+ pr_err("%s: Invalid parameters\n", __func__);
+ return NULL;
+ }
+
+ return of_node_get(opp->np);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_of_node);
diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h
index 4d00061..7c540fd 100644
--- a/drivers/opp/opp.h
+++ b/drivers/opp/opp.h
@@ -140,7 +140,6 @@ enum opp_table_access {
* @genpd_performance_state: Device's power domain support performance state.
* @set_opp: Platform specific set_opp callback
* @set_opp_data: Data to be passed to set_opp callback
- * @get_pstate: Platform specific get_pstate callback
* @dentry: debugfs dentry pointer of the real device directory (not links).
* @dentry_name: Name of the real dentry.
*
@@ -178,7 +177,6 @@ struct opp_table {
int (*set_opp)(struct dev_pm_set_opp_data *data);
struct dev_pm_set_opp_data *set_opp_data;
- int (*get_pstate)(struct device *dev, unsigned long rate);
#ifdef CONFIG_DEBUG_FS
struct dentry *dentry;
@@ -187,14 +185,16 @@ struct opp_table {
};
/* Routines internal to opp core */
+void dev_pm_opp_get(struct dev_pm_opp *opp);
void _get_opp_table_kref(struct opp_table *opp_table);
+int _get_opp_count(struct opp_table *opp_table);
struct opp_table *_find_opp_table(struct device *dev);
struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table);
void _dev_pm_opp_remove_table(struct opp_table *opp_table, struct device *dev, bool remove_all);
void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all);
struct dev_pm_opp *_opp_allocate(struct opp_table *opp_table);
void _opp_free(struct dev_pm_opp *opp);
-int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table);
+int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table, bool rate_not_available);
int _opp_add_v1(struct opp_table *opp_table, struct device *dev, unsigned long freq, long u_volt, bool dynamic);
void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of);
struct opp_table *_add_opp_table(struct device *dev);
diff --git a/drivers/parisc/Kconfig b/drivers/parisc/Kconfig
index 3a102a8..5a48b56 100644
--- a/drivers/parisc/Kconfig
+++ b/drivers/parisc/Kconfig
@@ -103,11 +103,6 @@
depends on PCI_LBA
default PCI_LBA
-config IOMMU_HELPER
- bool
- depends on IOMMU_SBA || IOMMU_CCIO
- default y
-
source "drivers/pcmcia/Kconfig"
endmenu
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index acba1f5..6148236 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -1108,19 +1108,6 @@ static int ccio_proc_info(struct seq_file *m, void *p)
return 0;
}
-static int ccio_proc_info_open(struct inode *inode, struct file *file)
-{
- return single_open(file, &ccio_proc_info, NULL);
-}
-
-static const struct file_operations ccio_proc_info_fops = {
- .owner = THIS_MODULE,
- .open = ccio_proc_info_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int ccio_proc_bitmap_info(struct seq_file *m, void *p)
{
struct ioc *ioc = ioc_list;
@@ -1135,19 +1122,6 @@ static int ccio_proc_bitmap_info(struct seq_file *m, void *p)
return 0;
}
-
-static int ccio_proc_bitmap_open(struct inode *inode, struct file *file)
-{
- return single_open(file, &ccio_proc_bitmap_info, NULL);
-}
-
-static const struct file_operations ccio_proc_bitmap_fops = {
- .owner = THIS_MODULE,
- .open = ccio_proc_bitmap_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif /* CONFIG_PROC_FS */
/**
@@ -1195,7 +1169,7 @@ void * ccio_get_iommu(const struct parisc_device *dev)
* to/from certain pages. To avoid this happening, we mark these pages
* as `used', and ensure that nothing will try to allocate from them.
*/
-void ccio_cujo20_fixup(struct parisc_device *cujo, u32 iovp)
+void __init ccio_cujo20_fixup(struct parisc_device *cujo, u32 iovp)
{
unsigned int idx;
struct parisc_device *dev = parisc_parent(cujo);
@@ -1263,7 +1237,7 @@ static struct parisc_driver ccio_driver __refdata = {
* I/O Page Directory, the resource map, and initalizing the
* U2/Uturn chip into virtual mode.
*/
-static void
+static void __init
ccio_ioc_init(struct ioc *ioc)
{
int i;
@@ -1589,15 +1563,13 @@ static int __init ccio_probe(struct parisc_device *dev)
#ifdef CONFIG_PROC_FS
if (ioc_count == 0) {
- proc_create(MODULE_NAME, 0, proc_runway_root,
- &ccio_proc_info_fops);
- proc_create(MODULE_NAME"-bitmap", 0, proc_runway_root,
- &ccio_proc_bitmap_fops);
+ proc_create_single(MODULE_NAME, 0, proc_runway_root,
+ ccio_proc_info);
+ proc_create_single(MODULE_NAME"-bitmap", 0, proc_runway_root,
+ ccio_proc_bitmap_info);
}
#endif
ioc_count++;
-
- parisc_has_iommu();
return 0;
}
diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index 0a9c762..11de0ec 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -1864,20 +1864,6 @@ static int sba_proc_info(struct seq_file *m, void *p)
}
static int
-sba_proc_open(struct inode *i, struct file *f)
-{
- return single_open(f, &sba_proc_info, NULL);
-}
-
-static const struct file_operations sba_proc_fops = {
- .owner = THIS_MODULE,
- .open = sba_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-static int
sba_proc_bitmap_info(struct seq_file *m, void *p)
{
struct sba_device *sba_dev = sba_list;
@@ -1889,20 +1875,6 @@ sba_proc_bitmap_info(struct seq_file *m, void *p)
return 0;
}
-
-static int
-sba_proc_bitmap_open(struct inode *i, struct file *f)
-{
- return single_open(f, &sba_proc_bitmap_info, NULL);
-}
-
-static const struct file_operations sba_proc_bitmap_fops = {
- .owner = THIS_MODULE,
- .open = sba_proc_bitmap_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif /* CONFIG_PROC_FS */
static const struct parisc_device_id sba_tbl[] __initconst = {
@@ -2014,11 +1986,9 @@ static int __init sba_driver_callback(struct parisc_device *dev)
break;
}
- proc_create("sba_iommu", 0, root, &sba_proc_fops);
- proc_create("sba_iommu-bitmap", 0, root, &sba_proc_bitmap_fops);
+ proc_create_single("sba_iommu", 0, root, sba_proc_info);
+ proc_create_single("sba_iommu-bitmap", 0, root, sba_proc_bitmap_info);
#endif
-
- parisc_has_iommu();
return 0;
}
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 34b56a8..29a487f 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -5,10 +5,6 @@
source "drivers/pci/pcie/Kconfig"
-config PCI_BUS_ADDR_T_64BIT
- def_bool y if (ARCH_DMA_ADDR_T_64BIT || 64BIT)
- depends on PCI
-
config PCI_MSI
bool "Message Signaled Interrupts (MSI and MSI-X)"
depends on PCI
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index bc2ded4..35b7fc8 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -120,7 +120,7 @@ int devm_request_pci_bus_resources(struct device *dev,
EXPORT_SYMBOL_GPL(devm_request_pci_bus_resources);
static struct pci_bus_region pci_32_bit = {0, 0xffffffffULL};
-#ifdef CONFIG_PCI_BUS_ADDR_T_64BIT
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
static struct pci_bus_region pci_64_bit = {0,
(pci_bus_addr_t) 0xffffffffffffffffULL};
static struct pci_bus_region pci_high = {(pci_bus_addr_t) 0x100000000ULL,
@@ -230,7 +230,7 @@ int pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res,
resource_size_t),
void *alignf_data)
{
-#ifdef CONFIG_PCI_BUS_ADDR_T_64BIT
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
int rc;
if (res->flags & IORESOURCE_MEM_64) {
diff --git a/drivers/pci/dwc/pcie-kirin.c b/drivers/pci/dwc/pcie-kirin.c
index a6b88c7..d2970a0 100644
--- a/drivers/pci/dwc/pcie-kirin.c
+++ b/drivers/pci/dwc/pcie-kirin.c
@@ -486,7 +486,7 @@ static int kirin_pcie_probe(struct platform_device *pdev)
return ret;
kirin_pcie->gpio_id_reset = of_get_named_gpio(dev->of_node,
- "reset-gpio", 0);
+ "reset-gpios", 0);
if (kirin_pcie->gpio_id_reset < 0)
return -ENODEV;
diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c
index b04d37b..9abf549 100644
--- a/drivers/pci/host/pci-aardvark.c
+++ b/drivers/pci/host/pci-aardvark.c
@@ -29,6 +29,7 @@
#define PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT 5
#define PCIE_CORE_DEV_CTRL_STATS_SNOOP_DISABLE (0 << 11)
#define PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT 12
+#define PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SZ 0x2
#define PCIE_CORE_LINK_CTRL_STAT_REG 0xd0
#define PCIE_CORE_LINK_L0S_ENTRY BIT(0)
#define PCIE_CORE_LINK_TRAINING BIT(5)
@@ -100,7 +101,8 @@
#define PCIE_ISR1_MASK_REG (CONTROL_BASE_ADDR + 0x4C)
#define PCIE_ISR1_POWER_STATE_CHANGE BIT(4)
#define PCIE_ISR1_FLUSH BIT(5)
-#define PCIE_ISR1_ALL_MASK GENMASK(5, 4)
+#define PCIE_ISR1_INTX_ASSERT(val) BIT(8 + (val))
+#define PCIE_ISR1_ALL_MASK GENMASK(11, 4)
#define PCIE_MSI_ADDR_LOW_REG (CONTROL_BASE_ADDR + 0x50)
#define PCIE_MSI_ADDR_HIGH_REG (CONTROL_BASE_ADDR + 0x54)
#define PCIE_MSI_STATUS_REG (CONTROL_BASE_ADDR + 0x58)
@@ -172,8 +174,6 @@
#define PCIE_CONFIG_WR_TYPE0 0xa
#define PCIE_CONFIG_WR_TYPE1 0xb
-/* PCI_BDF shifts 8bit, so we need extra 4bit shift */
-#define PCIE_BDF(dev) (dev << 4)
#define PCIE_CONF_BUS(bus) (((bus) & 0xff) << 20)
#define PCIE_CONF_DEV(dev) (((dev) & 0x1f) << 15)
#define PCIE_CONF_FUNC(fun) (((fun) & 0x7) << 12)
@@ -296,7 +296,8 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie)
reg = PCIE_CORE_DEV_CTRL_STATS_RELAX_ORDER_DISABLE |
(7 << PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT) |
PCIE_CORE_DEV_CTRL_STATS_SNOOP_DISABLE |
- PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT;
+ (PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SZ <<
+ PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT);
advk_writel(pcie, reg, PCIE_CORE_DEV_CTRL_STATS_REG);
/* Program PCIe Control 2 to disable strict ordering */
@@ -437,7 +438,7 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
u32 reg;
int ret;
- if (PCI_SLOT(devfn) != 0) {
+ if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0) {
*val = 0xffffffff;
return PCIBIOS_DEVICE_NOT_FOUND;
}
@@ -456,7 +457,7 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
advk_writel(pcie, reg, PIO_CTRL);
/* Program the address registers */
- reg = PCIE_BDF(devfn) | PCIE_CONF_REG(where);
+ reg = PCIE_CONF_ADDR(bus->number, devfn, where);
advk_writel(pcie, reg, PIO_ADDR_LS);
advk_writel(pcie, 0, PIO_ADDR_MS);
@@ -491,7 +492,7 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
int offset;
int ret;
- if (PCI_SLOT(devfn) != 0)
+ if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0)
return PCIBIOS_DEVICE_NOT_FOUND;
if (where % size)
@@ -609,9 +610,9 @@ static void advk_pcie_irq_mask(struct irq_data *d)
irq_hw_number_t hwirq = irqd_to_hwirq(d);
u32 mask;
- mask = advk_readl(pcie, PCIE_ISR0_MASK_REG);
- mask |= PCIE_ISR0_INTX_ASSERT(hwirq);
- advk_writel(pcie, mask, PCIE_ISR0_MASK_REG);
+ mask = advk_readl(pcie, PCIE_ISR1_MASK_REG);
+ mask |= PCIE_ISR1_INTX_ASSERT(hwirq);
+ advk_writel(pcie, mask, PCIE_ISR1_MASK_REG);
}
static void advk_pcie_irq_unmask(struct irq_data *d)
@@ -620,9 +621,9 @@ static void advk_pcie_irq_unmask(struct irq_data *d)
irq_hw_number_t hwirq = irqd_to_hwirq(d);
u32 mask;
- mask = advk_readl(pcie, PCIE_ISR0_MASK_REG);
- mask &= ~PCIE_ISR0_INTX_ASSERT(hwirq);
- advk_writel(pcie, mask, PCIE_ISR0_MASK_REG);
+ mask = advk_readl(pcie, PCIE_ISR1_MASK_REG);
+ mask &= ~PCIE_ISR1_INTX_ASSERT(hwirq);
+ advk_writel(pcie, mask, PCIE_ISR1_MASK_REG);
}
static int advk_pcie_irq_map(struct irq_domain *h,
@@ -765,29 +766,35 @@ static void advk_pcie_handle_msi(struct advk_pcie *pcie)
static void advk_pcie_handle_int(struct advk_pcie *pcie)
{
- u32 val, mask, status;
+ u32 isr0_val, isr0_mask, isr0_status;
+ u32 isr1_val, isr1_mask, isr1_status;
int i, virq;
- val = advk_readl(pcie, PCIE_ISR0_REG);
- mask = advk_readl(pcie, PCIE_ISR0_MASK_REG);
- status = val & ((~mask) & PCIE_ISR0_ALL_MASK);
+ isr0_val = advk_readl(pcie, PCIE_ISR0_REG);
+ isr0_mask = advk_readl(pcie, PCIE_ISR0_MASK_REG);
+ isr0_status = isr0_val & ((~isr0_mask) & PCIE_ISR0_ALL_MASK);
- if (!status) {
- advk_writel(pcie, val, PCIE_ISR0_REG);
+ isr1_val = advk_readl(pcie, PCIE_ISR1_REG);
+ isr1_mask = advk_readl(pcie, PCIE_ISR1_MASK_REG);
+ isr1_status = isr1_val & ((~isr1_mask) & PCIE_ISR1_ALL_MASK);
+
+ if (!isr0_status && !isr1_status) {
+ advk_writel(pcie, isr0_val, PCIE_ISR0_REG);
+ advk_writel(pcie, isr1_val, PCIE_ISR1_REG);
return;
}
/* Process MSI interrupts */
- if (status & PCIE_ISR0_MSI_INT_PENDING)
+ if (isr0_status & PCIE_ISR0_MSI_INT_PENDING)
advk_pcie_handle_msi(pcie);
/* Process legacy interrupts */
for (i = 0; i < PCI_NUM_INTX; i++) {
- if (!(status & PCIE_ISR0_INTX_ASSERT(i)))
+ if (!(isr1_status & PCIE_ISR1_INTX_ASSERT(i)))
continue;
- advk_writel(pcie, PCIE_ISR0_INTX_ASSERT(i),
- PCIE_ISR0_REG);
+ advk_writel(pcie, PCIE_ISR1_INTX_ASSERT(i),
+ PCIE_ISR1_REG);
virq = irq_find_mapping(pcie->irq_domain, i);
generic_handle_irq(virq);
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 3025063..f45b74f 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1434,6 +1434,9 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
{
struct irq_domain *domain;
+ if (WARN_ON(info->flags & MSI_FLAG_LEVEL_CAPABLE))
+ info->flags &= ~MSI_FLAG_LEVEL_CAPABLE;
+
if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS)
pci_msi_domain_update_dom_ops(info);
if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 6ace470..18ba62c 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -16,6 +16,8 @@
#include <linux/pm_runtime.h>
#include <linux/suspend.h>
#include <linux/kexec.h>
+#include <linux/of_device.h>
+#include <linux/acpi.h>
#include "pci.h"
#include "pcie/portdrv.h"
@@ -753,10 +755,11 @@ static int pci_pm_suspend(struct device *dev)
* better to resume the device from runtime suspend here.
*/
if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) ||
- !pci_dev_keep_suspended(pci_dev))
+ !pci_dev_keep_suspended(pci_dev)) {
pm_runtime_resume(dev);
+ pci_dev->state_saved = false;
+ }
- pci_dev->state_saved = false;
if (pm->suspend) {
pci_power_t prev = pci_dev->current_state;
int error;
@@ -958,10 +961,11 @@ static int pci_pm_freeze(struct device *dev)
* devices should not be touched during freeze/thaw transitions,
* however.
*/
- if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND))
+ if (!dev_pm_smart_suspend_and_suspended(dev)) {
pm_runtime_resume(dev);
+ pci_dev->state_saved = false;
+ }
- pci_dev->state_saved = false;
if (pm->freeze) {
int error;
@@ -1576,6 +1580,35 @@ static int pci_bus_num_vf(struct device *dev)
return pci_num_vf(to_pci_dev(dev));
}
+/**
+ * pci_dma_configure - Setup DMA configuration
+ * @dev: ptr to dev structure
+ *
+ * Function to update PCI devices's DMA configuration using the same
+ * info from the OF node or ACPI node of host bridge's parent (if any).
+ */
+static int pci_dma_configure(struct device *dev)
+{
+ struct device *bridge;
+ int ret = 0;
+
+ bridge = pci_get_host_bridge_device(to_pci_dev(dev));
+
+ if (IS_ENABLED(CONFIG_OF) && bridge->parent &&
+ bridge->parent->of_node) {
+ ret = of_dma_configure(dev, bridge->parent->of_node, true);
+ } else if (has_acpi_companion(bridge)) {
+ struct acpi_device *adev = to_acpi_device_node(bridge->fwnode);
+ enum dev_dma_attr attr = acpi_get_dma_attr(adev);
+
+ if (attr != DEV_DMA_NOT_SUPPORTED)
+ ret = acpi_dma_configure(dev, attr);
+ }
+
+ pci_put_host_bridge_device(bridge);
+ return ret;
+}
+
struct bus_type pci_bus_type = {
.name = "pci",
.match = pci_bus_match,
@@ -1588,7 +1621,7 @@ struct bus_type pci_bus_type = {
.drv_groups = pci_drv_groups,
.pm = PCI_PM_OPS_PTR,
.num_vf = pci_bus_num_vf,
- .force_dma = true,
+ .dma_configure = pci_dma_configure,
};
EXPORT_SYMBOL(pci_bus_type);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index e597655..e90cf5c 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1910,7 +1910,7 @@ void pci_pme_active(struct pci_dev *dev, bool enable)
EXPORT_SYMBOL(pci_pme_active);
/**
- * pci_enable_wake - enable PCI device as wakeup event source
+ * __pci_enable_wake - enable PCI device as wakeup event source
* @dev: PCI device affected
* @state: PCI state from which device will issue wakeup events
* @enable: True to enable event generation; false to disable
@@ -1928,7 +1928,7 @@ EXPORT_SYMBOL(pci_pme_active);
* Error code depending on the platform is returned if both the platform and
* the native mechanism fail to enable the generation of wake-up events
*/
-int pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable)
+static int __pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable)
{
int ret = 0;
@@ -1969,6 +1969,23 @@ int pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable)
return ret;
}
+
+/**
+ * pci_enable_wake - change wakeup settings for a PCI device
+ * @pci_dev: Target device
+ * @state: PCI state from which device will issue wakeup events
+ * @enable: Whether or not to enable event generation
+ *
+ * If @enable is set, check device_may_wakeup() for the device before calling
+ * __pci_enable_wake() for it.
+ */
+int pci_enable_wake(struct pci_dev *pci_dev, pci_power_t state, bool enable)
+{
+ if (enable && !device_may_wakeup(&pci_dev->dev))
+ return -EINVAL;
+
+ return __pci_enable_wake(pci_dev, state, enable);
+}
EXPORT_SYMBOL(pci_enable_wake);
/**
@@ -1981,9 +1998,9 @@ EXPORT_SYMBOL(pci_enable_wake);
* should not be called twice in a row to enable wake-up due to PCI PM vs ACPI
* ordering constraints.
*
- * This function only returns error code if the device is not capable of
- * generating PME# from both D3_hot and D3_cold, and the platform is unable to
- * enable wake-up power for it.
+ * This function only returns error code if the device is not allowed to wake
+ * up the system from sleep or it is not capable of generating PME# from both
+ * D3_hot and D3_cold and the platform is unable to enable wake-up power for it.
*/
int pci_wake_from_d3(struct pci_dev *dev, bool enable)
{
@@ -2008,8 +2025,7 @@ static pci_power_t pci_target_state(struct pci_dev *dev, bool wakeup)
if (platform_pci_power_manageable(dev)) {
/*
- * Call the platform to choose the target state of the device
- * and enable wake-up from this state if supported.
+ * Call the platform to find the target state for the device.
*/
pci_power_t state = platform_pci_choose_state(dev);
@@ -2042,8 +2058,7 @@ static pci_power_t pci_target_state(struct pci_dev *dev, bool wakeup)
if (wakeup) {
/*
* Find the deepest state from which the device can generate
- * wake-up events, make it the target state and enable device
- * to generate PME#.
+ * PME#.
*/
if (dev->pme_support) {
while (target_state
@@ -2114,7 +2129,7 @@ int pci_finish_runtime_suspend(struct pci_dev *dev)
dev->runtime_d3cold = target_state == PCI_D3cold;
- pci_enable_wake(dev, target_state, pci_dev_run_wake(dev));
+ __pci_enable_wake(dev, target_state, pci_dev_run_wake(dev));
error = pci_set_power_state(dev, target_state);
@@ -2138,16 +2153,16 @@ bool pci_dev_run_wake(struct pci_dev *dev)
{
struct pci_bus *bus = dev->bus;
- if (device_can_wakeup(&dev->dev))
- return true;
-
if (!dev->pme_support)
return false;
/* PME-capable in principle, but not from the target power state */
- if (!pci_pme_capable(dev, pci_target_state(dev, false)))
+ if (!pci_pme_capable(dev, pci_target_state(dev, true)))
return false;
+ if (device_can_wakeup(&dev->dev))
+ return true;
+
while (bus->parent) {
struct pci_dev *bridge = bus->self;
@@ -5273,11 +5288,11 @@ void pcie_print_link_status(struct pci_dev *dev)
bw_avail = pcie_bandwidth_available(dev, &limiting_dev, &speed, &width);
if (bw_avail >= bw_cap)
- pci_info(dev, "%u.%03u Gb/s available bandwidth (%s x%d link)\n",
+ pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth (%s x%d link)\n",
bw_cap / 1000, bw_cap % 1000,
PCIE_SPEED2STR(speed_cap), width_cap);
else
- pci_info(dev, "%u.%03u Gb/s available bandwidth, limited by %s x%d link at %s (capable of %u.%03u Gb/s with %s x%d link)\n",
+ pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth, limited by %s x%d link at %s (capable of %u.%03u Gb/s with %s x%d link)\n",
bw_avail / 1000, bw_avail % 1000,
PCIE_SPEED2STR(speed), width,
limiting_dev ? pci_name(limiting_dev) : "<unknown>",
diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index 1ee8927..7ac035af 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -435,25 +435,12 @@ int pci_proc_detach_bus(struct pci_bus *bus)
return 0;
}
-static int proc_bus_pci_dev_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &proc_bus_pci_devices_op);
-}
-
-static const struct file_operations proc_bus_pci_dev_operations = {
- .owner = THIS_MODULE,
- .open = proc_bus_pci_dev_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static int __init pci_proc_init(void)
{
struct pci_dev *dev = NULL;
proc_bus_pci_dir = proc_mkdir("bus/pci", NULL);
- proc_create("devices", 0, proc_bus_pci_dir,
- &proc_bus_pci_dev_operations);
+ proc_create_seq("devices", 0, proc_bus_pci_dir,
+ &proc_bus_pci_devices_op);
proc_initialized = 1;
for_each_pci_dev(dev)
pci_proc_attach_device(dev);
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index b1ae161..fee9225 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -1622,22 +1622,30 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq)
if (!need_valid_mask) {
irq_base = devm_irq_alloc_descs(pctrl->dev, -1, 0,
- chip->ngpio, NUMA_NO_NODE);
+ community->npins, NUMA_NO_NODE);
if (irq_base < 0) {
dev_err(pctrl->dev, "Failed to allocate IRQ numbers\n");
return irq_base;
}
- } else {
- irq_base = 0;
}
- ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, irq_base,
+ ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, 0,
handle_bad_irq, IRQ_TYPE_NONE);
if (ret) {
dev_err(pctrl->dev, "failed to add IRQ chip\n");
return ret;
}
+ if (!need_valid_mask) {
+ for (i = 0; i < community->ngpio_ranges; i++) {
+ range = &community->gpio_ranges[i];
+
+ irq_domain_associate_many(chip->irq.domain, irq_base,
+ range->base, range->npins);
+ irq_base += range->npins;
+ }
+ }
+
gpiochip_set_chained_irqchip(chip, &chv_gpio_irqchip, irq,
chv_gpio_irq_handler);
return 0;
diff --git a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
index 8870a41..fee3435 100644
--- a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
+++ b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
@@ -36,6 +36,27 @@
.npins = ((e) - (s) + 1), \
}
+#define SPTH_GPP(r, s, e, g) \
+ { \
+ .reg_num = (r), \
+ .base = (s), \
+ .size = ((e) - (s) + 1), \
+ .gpio_base = (g), \
+ }
+
+#define SPTH_COMMUNITY(b, s, e, g) \
+ { \
+ .barno = (b), \
+ .padown_offset = SPT_PAD_OWN, \
+ .padcfglock_offset = SPT_PADCFGLOCK, \
+ .hostown_offset = SPT_HOSTSW_OWN, \
+ .ie_offset = SPT_GPI_IE, \
+ .pin_base = (s), \
+ .npins = ((e) - (s) + 1), \
+ .gpps = (g), \
+ .ngpps = ARRAY_SIZE(g), \
+ }
+
/* Sunrisepoint-LP */
static const struct pinctrl_pin_desc sptlp_pins[] = {
/* GPP_A */
@@ -531,10 +552,28 @@ static const struct intel_function spth_functions[] = {
FUNCTION("i2c2", spth_i2c2_groups),
};
+static const struct intel_padgroup spth_community0_gpps[] = {
+ SPTH_GPP(0, 0, 23, 0), /* GPP_A */
+ SPTH_GPP(1, 24, 47, 24), /* GPP_B */
+};
+
+static const struct intel_padgroup spth_community1_gpps[] = {
+ SPTH_GPP(0, 48, 71, 48), /* GPP_C */
+ SPTH_GPP(1, 72, 95, 72), /* GPP_D */
+ SPTH_GPP(2, 96, 108, 96), /* GPP_E */
+ SPTH_GPP(3, 109, 132, 120), /* GPP_F */
+ SPTH_GPP(4, 133, 156, 144), /* GPP_G */
+ SPTH_GPP(5, 157, 180, 168), /* GPP_H */
+};
+
+static const struct intel_padgroup spth_community3_gpps[] = {
+ SPTH_GPP(0, 181, 191, 192), /* GPP_I */
+};
+
static const struct intel_community spth_communities[] = {
- SPT_COMMUNITY(0, 0, 47),
- SPT_COMMUNITY(1, 48, 180),
- SPT_COMMUNITY(2, 181, 191),
+ SPTH_COMMUNITY(0, 0, 47, spth_community0_gpps),
+ SPTH_COMMUNITY(1, 48, 180, spth_community1_gpps),
+ SPTH_COMMUNITY(2, 181, 191, spth_community3_gpps),
};
static const struct intel_pinctrl_soc_data spth_soc_data = {
diff --git a/drivers/pinctrl/meson/pinctrl-meson-axg.c b/drivers/pinctrl/meson/pinctrl-meson-axg.c
index 4b91ff7..99a6cea 100644
--- a/drivers/pinctrl/meson/pinctrl-meson-axg.c
+++ b/drivers/pinctrl/meson/pinctrl-meson-axg.c
@@ -898,7 +898,7 @@ static struct meson_bank meson_axg_periphs_banks[] = {
static struct meson_bank meson_axg_aobus_banks[] = {
/* name first last irq pullen pull dir out in */
- BANK("AO", GPIOAO_0, GPIOAO_9, 0, 13, 0, 16, 0, 0, 0, 0, 0, 16, 1, 0),
+ BANK("AO", GPIOAO_0, GPIOAO_13, 0, 13, 0, 16, 0, 0, 0, 0, 0, 16, 1, 0),
};
static struct meson_pmx_bank meson_axg_periphs_pmx_banks[] = {
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
index 6cbcff4..dfed609 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -267,12 +267,13 @@ static void stm32_gpio_irq_release_resources(struct irq_data *irq_data)
}
static struct irq_chip stm32_gpio_irq_chip = {
- .name = "stm32gpio",
- .irq_ack = irq_chip_ack_parent,
- .irq_mask = irq_chip_mask_parent,
- .irq_unmask = irq_chip_unmask_parent,
- .irq_set_type = irq_chip_set_type_parent,
- .irq_set_wake = irq_chip_set_wake_parent,
+ .name = "stm32gpio",
+ .irq_eoi = irq_chip_eoi_parent,
+ .irq_ack = irq_chip_ack_parent,
+ .irq_mask = irq_chip_mask_parent,
+ .irq_unmask = irq_chip_unmask_parent,
+ .irq_set_type = irq_chip_set_type_parent,
+ .irq_set_wake = irq_chip_set_wake_parent,
.irq_request_resources = stm32_gpio_irq_request_resources,
.irq_release_resources = stm32_gpio_irq_release_resources,
};
diff --git a/drivers/platform/chrome/Kconfig b/drivers/platform/chrome/Kconfig
index e728a96..cb0df9e 100644
--- a/drivers/platform/chrome/Kconfig
+++ b/drivers/platform/chrome/Kconfig
@@ -38,6 +38,17 @@
If you have a supported Chromebook, choose Y or M here.
The module will be called chromeos_pstore.
+config CHROMEOS_TBMC
+ tristate "ChromeOS Tablet Switch Controller"
+ depends on ACPI
+ depends on INPUT
+ help
+ This option adds a driver for the tablet switch on
+ select Chrome OS systems.
+
+ To compile this driver as a module, choose M here: the
+ module will be called chromeos_tbmc.
+
config CROS_EC_CTL
tristate
diff --git a/drivers/platform/chrome/Makefile b/drivers/platform/chrome/Makefile
index ff3b369..e44c37a 100644
--- a/drivers/platform/chrome/Makefile
+++ b/drivers/platform/chrome/Makefile
@@ -2,6 +2,7 @@
obj-$(CONFIG_CHROMEOS_LAPTOP) += chromeos_laptop.o
obj-$(CONFIG_CHROMEOS_PSTORE) += chromeos_pstore.o
+obj-$(CONFIG_CHROMEOS_TBMC) += chromeos_tbmc.o
cros_ec_ctl-objs := cros_ec_sysfs.o cros_ec_lightbar.o \
cros_ec_vbc.o cros_ec_debugfs.o
obj-$(CONFIG_CROS_EC_CTL) += cros_ec_ctl.o
diff --git a/drivers/platform/chrome/chromeos_laptop.c b/drivers/platform/chrome/chromeos_laptop.c
index 5c47f45..24326ee 100644
--- a/drivers/platform/chrome/chromeos_laptop.c
+++ b/drivers/platform/chrome/chromeos_laptop.c
@@ -6,6 +6,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/acpi.h>
#include <linux/dmi.h>
#include <linux/i2c.h>
#include <linux/input.h>
@@ -54,6 +55,11 @@ struct i2c_peripheral {
struct i2c_client *client;
};
+struct acpi_peripheral {
+ char hid[ACPI_ID_LEN];
+ const struct property_entry *properties;
+};
+
struct chromeos_laptop {
/*
* Note that we can't mark this pointer as const because
@@ -61,6 +67,9 @@ struct chromeos_laptop {
*/
struct i2c_peripheral *i2c_peripherals;
unsigned int num_i2c_peripherals;
+
+ const struct acpi_peripheral *acpi_peripherals;
+ unsigned int num_acpi_peripherals;
};
static const struct chromeos_laptop *cros_laptop;
@@ -148,6 +157,38 @@ static void chromeos_laptop_check_adapter(struct i2c_adapter *adapter)
}
}
+static bool chromeos_laptop_adjust_client(struct i2c_client *client)
+{
+ const struct acpi_peripheral *acpi_dev;
+ struct acpi_device_id acpi_ids[2] = { };
+ int i;
+ int error;
+
+ if (!has_acpi_companion(&client->dev))
+ return false;
+
+ for (i = 0; i < cros_laptop->num_acpi_peripherals; i++) {
+ acpi_dev = &cros_laptop->acpi_peripherals[i];
+
+ memcpy(acpi_ids[0].id, acpi_dev->hid, ACPI_ID_LEN);
+
+ if (acpi_match_device(acpi_ids, &client->dev)) {
+ error = device_add_properties(&client->dev,
+ acpi_dev->properties);
+ if (error) {
+ dev_err(&client->dev,
+ "failed to add properties: %d\n",
+ error);
+ break;
+ }
+
+ return true;
+ }
+ }
+
+ return false;
+}
+
static void chromeos_laptop_detach_i2c_client(struct i2c_client *client)
{
struct i2c_peripheral *i2c_dev;
@@ -170,6 +211,8 @@ static int chromeos_laptop_i2c_notifier_call(struct notifier_block *nb,
case BUS_NOTIFY_ADD_DEVICE:
if (dev->type == &i2c_adapter_type)
chromeos_laptop_check_adapter(to_i2c_adapter(dev));
+ else if (dev->type == &i2c_client_type)
+ chromeos_laptop_adjust_client(to_i2c_client(dev));
break;
case BUS_NOTIFY_REMOVED_DEVICE:
@@ -191,6 +234,12 @@ static const struct chromeos_laptop _name __initconst = { \
.num_i2c_peripherals = ARRAY_SIZE(_name##_peripherals), \
}
+#define DECLARE_ACPI_CROS_LAPTOP(_name) \
+static const struct chromeos_laptop _name __initconst = { \
+ .acpi_peripherals = _name##_peripherals, \
+ .num_acpi_peripherals = ARRAY_SIZE(_name##_peripherals), \
+}
+
static struct i2c_peripheral samsung_series_5_550_peripherals[] __initdata = {
/* Touchpad. */
{
@@ -234,16 +283,25 @@ static const int chromebook_pixel_tp_keys[] __initconst = {
static const struct property_entry
chromebook_pixel_trackpad_props[] __initconst = {
+ PROPERTY_ENTRY_STRING("compatible", "atmel,maxtouch"),
PROPERTY_ENTRY_U32_ARRAY("linux,gpio-keymap", chromebook_pixel_tp_keys),
{ }
};
+static const struct property_entry
+chromebook_atmel_touchscreen_props[] __initconst = {
+ PROPERTY_ENTRY_STRING("compatible", "atmel,maxtouch"),
+ { }
+};
+
static struct i2c_peripheral chromebook_pixel_peripherals[] __initdata = {
/* Touch Screen. */
{
.board_info = {
I2C_BOARD_INFO("atmel_mxt_ts",
ATMEL_TS_I2C_ADDR),
+ .properties =
+ chromebook_atmel_touchscreen_props,
.flags = I2C_CLIENT_WAKE,
},
.dmi_name = "touchscreen",
@@ -354,6 +412,8 @@ static struct i2c_peripheral acer_c720_peripherals[] __initdata = {
.board_info = {
I2C_BOARD_INFO("atmel_mxt_ts",
ATMEL_TS_I2C_ADDR),
+ .properties =
+ chromebook_atmel_touchscreen_props,
.flags = I2C_CLIENT_WAKE,
},
.dmi_name = "touchscreen",
@@ -419,6 +479,47 @@ static struct i2c_peripheral cr48_peripherals[] __initdata = {
};
DECLARE_CROS_LAPTOP(cr48);
+static const u32 samus_touchpad_buttons[] __initconst = {
+ KEY_RESERVED,
+ KEY_RESERVED,
+ KEY_RESERVED,
+ BTN_LEFT
+};
+
+static const struct property_entry samus_trackpad_props[] __initconst = {
+ PROPERTY_ENTRY_STRING("compatible", "atmel,maxtouch"),
+ PROPERTY_ENTRY_U32_ARRAY("linux,gpio-keymap", samus_touchpad_buttons),
+ { }
+};
+
+static struct acpi_peripheral samus_peripherals[] __initdata = {
+ /* Touchpad */
+ {
+ .hid = "ATML0000",
+ .properties = samus_trackpad_props,
+ },
+ /* Touchsceen */
+ {
+ .hid = "ATML0001",
+ .properties = chromebook_atmel_touchscreen_props,
+ },
+};
+DECLARE_ACPI_CROS_LAPTOP(samus);
+
+static struct acpi_peripheral generic_atmel_peripherals[] __initdata = {
+ /* Touchpad */
+ {
+ .hid = "ATML0000",
+ .properties = chromebook_pixel_trackpad_props,
+ },
+ /* Touchsceen */
+ {
+ .hid = "ATML0001",
+ .properties = chromebook_atmel_touchscreen_props,
+ },
+};
+DECLARE_ACPI_CROS_LAPTOP(generic_atmel);
+
static const struct dmi_system_id chromeos_laptop_dmi_table[] __initconst = {
{
.ident = "Samsung Series 5 550",
@@ -502,17 +603,72 @@ static const struct dmi_system_id chromeos_laptop_dmi_table[] __initconst = {
},
.driver_data = (void *)&cr48,
},
+ /* Devices with peripherals incompletely described in ACPI */
+ {
+ .ident = "Chromebook Pro",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Google"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Caroline"),
+ },
+ .driver_data = (void *)&samus,
+ },
+ {
+ .ident = "Google Pixel 2 (2015)",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Samus"),
+ },
+ .driver_data = (void *)&samus,
+ },
+ {
+ .ident = "Samsung Chromebook 3",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Celes"),
+ },
+ .driver_data = (void *)&samus,
+ },
+ {
+ /*
+ * Other Chromebooks with Atmel touch controllers:
+ * - Winky (touchpad)
+ * - Clapper, Expresso, Rambi, Glimmer (touchscreen)
+ */
+ .ident = "Other Chromebook",
+ .matches = {
+ /*
+ * This will match all Google devices, not only devices
+ * with Atmel, but we will validate that the device
+ * actually has matching peripherals.
+ */
+ DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"),
+ },
+ .driver_data = (void *)&generic_atmel,
+ },
{ }
};
MODULE_DEVICE_TABLE(dmi, chromeos_laptop_dmi_table);
-static int __init chromeos_laptop_scan_adapter(struct device *dev, void *data)
+static int __init chromeos_laptop_scan_peripherals(struct device *dev, void *data)
{
- struct i2c_adapter *adapter;
+ int error;
- adapter = i2c_verify_adapter(dev);
- if (adapter)
- chromeos_laptop_check_adapter(adapter);
+ if (dev->type == &i2c_adapter_type) {
+ chromeos_laptop_check_adapter(to_i2c_adapter(dev));
+ } else if (dev->type == &i2c_client_type) {
+ if (chromeos_laptop_adjust_client(to_i2c_client(dev))) {
+ /*
+ * Now that we have needed properties re-trigger
+ * driver probe in case driver was initialized
+ * earlier and probe failed.
+ */
+ error = device_attach(dev);
+ if (error < 0)
+ dev_warn(dev,
+ "%s: device_attach() failed: %d\n",
+ __func__, error);
+ }
+ }
return 0;
}
@@ -556,27 +712,24 @@ static int __init chromeos_laptop_setup_irq(struct i2c_peripheral *i2c_dev)
return 0;
}
-static struct chromeos_laptop * __init
-chromeos_laptop_prepare(const struct chromeos_laptop *src)
+static int __init
+chromeos_laptop_prepare_i2c_peripherals(struct chromeos_laptop *cros_laptop,
+ const struct chromeos_laptop *src)
{
- struct chromeos_laptop *cros_laptop;
struct i2c_peripheral *i2c_dev;
struct i2c_board_info *info;
- int error;
int i;
+ int error;
- cros_laptop = kzalloc(sizeof(*cros_laptop), GFP_KERNEL);
- if (!cros_laptop)
- return ERR_PTR(-ENOMEM);
+ if (!src->num_i2c_peripherals)
+ return 0;
cros_laptop->i2c_peripherals = kmemdup(src->i2c_peripherals,
src->num_i2c_peripherals *
sizeof(*src->i2c_peripherals),
GFP_KERNEL);
- if (!cros_laptop->i2c_peripherals) {
- error = -ENOMEM;
- goto err_free_cros_laptop;
- }
+ if (!cros_laptop->i2c_peripherals)
+ return -ENOMEM;
cros_laptop->num_i2c_peripherals = src->num_i2c_peripherals;
@@ -586,7 +739,7 @@ chromeos_laptop_prepare(const struct chromeos_laptop *src)
error = chromeos_laptop_setup_irq(i2c_dev);
if (error)
- goto err_destroy_cros_peripherals;
+ goto err_out;
/* We need to deep-copy properties */
if (info->properties) {
@@ -594,14 +747,14 @@ chromeos_laptop_prepare(const struct chromeos_laptop *src)
property_entries_dup(info->properties);
if (IS_ERR(info->properties)) {
error = PTR_ERR(info->properties);
- goto err_destroy_cros_peripherals;
+ goto err_out;
}
}
}
- return cros_laptop;
+ return 0;
-err_destroy_cros_peripherals:
+err_out:
while (--i >= 0) {
i2c_dev = &cros_laptop->i2c_peripherals[i];
info = &i2c_dev->board_info;
@@ -609,13 +762,74 @@ chromeos_laptop_prepare(const struct chromeos_laptop *src)
property_entries_free(info->properties);
}
kfree(cros_laptop->i2c_peripherals);
-err_free_cros_laptop:
- kfree(cros_laptop);
- return ERR_PTR(error);
+ return error;
+}
+
+static int __init
+chromeos_laptop_prepare_acpi_peripherals(struct chromeos_laptop *cros_laptop,
+ const struct chromeos_laptop *src)
+{
+ struct acpi_peripheral *acpi_peripherals;
+ struct acpi_peripheral *acpi_dev;
+ const struct acpi_peripheral *src_dev;
+ int n_peripherals = 0;
+ int i;
+ int error;
+
+ for (i = 0; i < src->num_acpi_peripherals; i++) {
+ if (acpi_dev_present(src->acpi_peripherals[i].hid, NULL, -1))
+ n_peripherals++;
+ }
+
+ if (!n_peripherals)
+ return 0;
+
+ acpi_peripherals = kcalloc(n_peripherals,
+ sizeof(*src->acpi_peripherals),
+ GFP_KERNEL);
+ if (!acpi_peripherals)
+ return -ENOMEM;
+
+ acpi_dev = acpi_peripherals;
+ for (i = 0; i < src->num_acpi_peripherals; i++) {
+ src_dev = &src->acpi_peripherals[i];
+ if (!acpi_dev_present(src_dev->hid, NULL, -1))
+ continue;
+
+ *acpi_dev = *src_dev;
+
+ /* We need to deep-copy properties */
+ if (src_dev->properties) {
+ acpi_dev->properties =
+ property_entries_dup(src_dev->properties);
+ if (IS_ERR(acpi_dev->properties)) {
+ error = PTR_ERR(acpi_dev->properties);
+ goto err_out;
+ }
+ }
+
+ acpi_dev++;
+ }
+
+ cros_laptop->acpi_peripherals = acpi_peripherals;
+ cros_laptop->num_acpi_peripherals = n_peripherals;
+
+ return 0;
+
+err_out:
+ while (--i >= 0) {
+ acpi_dev = &acpi_peripherals[i];
+ if (acpi_dev->properties)
+ property_entries_free(acpi_dev->properties);
+ }
+
+ kfree(acpi_peripherals);
+ return error;
}
static void chromeos_laptop_destroy(const struct chromeos_laptop *cros_laptop)
{
+ const struct acpi_peripheral *acpi_dev;
struct i2c_peripheral *i2c_dev;
struct i2c_board_info *info;
int i;
@@ -631,10 +845,41 @@ static void chromeos_laptop_destroy(const struct chromeos_laptop *cros_laptop)
property_entries_free(info->properties);
}
+ for (i = 0; i < cros_laptop->num_acpi_peripherals; i++) {
+ acpi_dev = &cros_laptop->acpi_peripherals[i];
+
+ if (acpi_dev->properties)
+ property_entries_free(acpi_dev->properties);
+ }
+
kfree(cros_laptop->i2c_peripherals);
+ kfree(cros_laptop->acpi_peripherals);
kfree(cros_laptop);
}
+static struct chromeos_laptop * __init
+chromeos_laptop_prepare(const struct chromeos_laptop *src)
+{
+ struct chromeos_laptop *cros_laptop;
+ int error;
+
+ cros_laptop = kzalloc(sizeof(*cros_laptop), GFP_KERNEL);
+ if (!cros_laptop)
+ return ERR_PTR(-ENOMEM);
+
+ error = chromeos_laptop_prepare_i2c_peripherals(cros_laptop, src);
+ if (!error)
+ error = chromeos_laptop_prepare_acpi_peripherals(cros_laptop,
+ src);
+
+ if (error) {
+ chromeos_laptop_destroy(cros_laptop);
+ return ERR_PTR(error);
+ }
+
+ return cros_laptop;
+}
+
static int __init chromeos_laptop_init(void)
{
const struct dmi_system_id *dmi_id;
@@ -652,21 +897,33 @@ static int __init chromeos_laptop_init(void)
if (IS_ERR(cros_laptop))
return PTR_ERR(cros_laptop);
+ if (!cros_laptop->num_i2c_peripherals &&
+ !cros_laptop->num_acpi_peripherals) {
+ pr_debug("no relevant devices detected\n");
+ error = -ENODEV;
+ goto err_destroy_cros_laptop;
+ }
+
error = bus_register_notifier(&i2c_bus_type,
&chromeos_laptop_i2c_notifier);
if (error) {
- pr_err("failed to register i2c bus notifier: %d\n", error);
- chromeos_laptop_destroy(cros_laptop);
- return error;
+ pr_err("failed to register i2c bus notifier: %d\n",
+ error);
+ goto err_destroy_cros_laptop;
}
/*
- * Scan adapters that have been registered before we installed
- * the notifier to make sure we do not miss any devices.
+ * Scan adapters that have been registered and clients that have
+ * been created before we installed the notifier to make sure
+ * we do not miss any devices.
*/
- i2c_for_each_dev(NULL, chromeos_laptop_scan_adapter);
+ i2c_for_each_dev(NULL, chromeos_laptop_scan_peripherals);
return 0;
+
+err_destroy_cros_laptop:
+ chromeos_laptop_destroy(cros_laptop);
+ return error;
}
static void __exit chromeos_laptop_exit(void)
diff --git a/drivers/platform/chrome/chromeos_tbmc.c b/drivers/platform/chrome/chromeos_tbmc.c
new file mode 100644
index 0000000..b935df6
--- /dev/null
+++ b/drivers/platform/chrome/chromeos_tbmc.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Driver to detect Tablet Mode for ChromeOS convertible.
+//
+// Copyright (C) 2017 Google, Inc.
+// Author: Gwendal Grignou <gwendal@chromium.org>
+
+#include <linux/acpi.h>
+#include <linux/input.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+
+#define DRV_NAME "chromeos_tbmc"
+#define ACPI_DRV_NAME "GOOG0006"
+
+static int chromeos_tbmc_query_switch(struct acpi_device *adev,
+ struct input_dev *idev)
+{
+ unsigned long long state;
+ acpi_status status;
+
+ status = acpi_evaluate_integer(adev->handle, "TBMC", NULL, &state);
+ if (ACPI_FAILURE(status))
+ return -ENODEV;
+
+ /* input layer checks if event is redundant */
+ input_report_switch(idev, SW_TABLET_MODE, state);
+ input_sync(idev);
+
+ return 0;
+}
+
+static __maybe_unused int chromeos_tbmc_resume(struct device *dev)
+{
+ struct acpi_device *adev = to_acpi_device(dev);
+
+ return chromeos_tbmc_query_switch(adev, adev->driver_data);
+}
+
+static void chromeos_tbmc_notify(struct acpi_device *adev, u32 event)
+{
+ switch (event) {
+ case 0x80:
+ chromeos_tbmc_query_switch(adev, adev->driver_data);
+ break;
+ default:
+ dev_err(&adev->dev, "Unexpected event: 0x%08X\n", event);
+ }
+}
+
+static int chromeos_tbmc_open(struct input_dev *idev)
+{
+ struct acpi_device *adev = input_get_drvdata(idev);
+
+ return chromeos_tbmc_query_switch(adev, idev);
+}
+
+static int chromeos_tbmc_add(struct acpi_device *adev)
+{
+ struct input_dev *idev;
+ struct device *dev = &adev->dev;
+ int ret;
+
+ idev = devm_input_allocate_device(dev);
+ if (!idev)
+ return -ENOMEM;
+
+ idev->name = "Tablet Mode Switch";
+ idev->phys = acpi_device_hid(adev);
+
+ idev->id.bustype = BUS_HOST;
+ idev->id.version = 1;
+ idev->id.product = 0;
+ idev->open = chromeos_tbmc_open;
+
+ input_set_drvdata(idev, adev);
+ adev->driver_data = idev;
+
+ input_set_capability(idev, EV_SW, SW_TABLET_MODE);
+ ret = input_register_device(idev);
+ if (ret) {
+ dev_err(dev, "cannot register input device\n");
+ return ret;
+ }
+ return 0;
+}
+
+static const struct acpi_device_id chromeos_tbmc_acpi_device_ids[] = {
+ { ACPI_DRV_NAME, 0 },
+ { }
+};
+MODULE_DEVICE_TABLE(acpi, chromeos_tbmc_acpi_device_ids);
+
+static const SIMPLE_DEV_PM_OPS(chromeos_tbmc_pm_ops, NULL,
+ chromeos_tbmc_resume);
+
+static struct acpi_driver chromeos_tbmc_driver = {
+ .name = DRV_NAME,
+ .class = DRV_NAME,
+ .ids = chromeos_tbmc_acpi_device_ids,
+ .ops = {
+ .add = chromeos_tbmc_add,
+ .notify = chromeos_tbmc_notify,
+ },
+ .drv.pm = &chromeos_tbmc_pm_ops,
+};
+
+module_acpi_driver(chromeos_tbmc_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("ChromeOS ACPI tablet switch driver");
diff --git a/drivers/platform/chrome/cros_ec_lightbar.c b/drivers/platform/chrome/cros_ec_lightbar.c
index 6ea79d4..68193bb 100644
--- a/drivers/platform/chrome/cros_ec_lightbar.c
+++ b/drivers/platform/chrome/cros_ec_lightbar.c
@@ -170,8 +170,7 @@ static ssize_t version_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
uint32_t version = 0, flags = 0;
- struct cros_ec_dev *ec = container_of(dev,
- struct cros_ec_dev, class_dev);
+ struct cros_ec_dev *ec = to_cros_ec_dev(dev);
int ret;
ret = lb_throttle();
@@ -193,8 +192,7 @@ static ssize_t brightness_store(struct device *dev,
struct cros_ec_command *msg;
int ret;
unsigned int val;
- struct cros_ec_dev *ec = container_of(dev,
- struct cros_ec_dev, class_dev);
+ struct cros_ec_dev *ec = to_cros_ec_dev(dev);
if (kstrtouint(buf, 0, &val))
return -EINVAL;
@@ -238,8 +236,7 @@ static ssize_t led_rgb_store(struct device *dev, struct device_attribute *attr,
{
struct ec_params_lightbar *param;
struct cros_ec_command *msg;
- struct cros_ec_dev *ec = container_of(dev,
- struct cros_ec_dev, class_dev);
+ struct cros_ec_dev *ec = to_cros_ec_dev(dev);
unsigned int val[4];
int ret, i = 0, j = 0, ok = 0;
@@ -311,8 +308,7 @@ static ssize_t sequence_show(struct device *dev,
struct ec_response_lightbar *resp;
struct cros_ec_command *msg;
int ret;
- struct cros_ec_dev *ec = container_of(dev,
- struct cros_ec_dev, class_dev);
+ struct cros_ec_dev *ec = to_cros_ec_dev(dev);
msg = alloc_lightbar_cmd_msg(ec);
if (!msg)
@@ -439,8 +435,7 @@ static ssize_t sequence_store(struct device *dev, struct device_attribute *attr,
struct cros_ec_command *msg;
unsigned int num;
int ret, len;
- struct cros_ec_dev *ec = container_of(dev,
- struct cros_ec_dev, class_dev);
+ struct cros_ec_dev *ec = to_cros_ec_dev(dev);
for (len = 0; len < count; len++)
if (!isalnum(buf[len]))
@@ -488,8 +483,7 @@ static ssize_t program_store(struct device *dev, struct device_attribute *attr,
int extra_bytes, max_size, ret;
struct ec_params_lightbar *param;
struct cros_ec_command *msg;
- struct cros_ec_dev *ec = container_of(dev, struct cros_ec_dev,
- class_dev);
+ struct cros_ec_dev *ec = to_cros_ec_dev(dev);
/*
* We might need to reject the program for size reasons. The EC
@@ -599,8 +593,7 @@ static umode_t cros_ec_lightbar_attrs_are_visible(struct kobject *kobj,
struct attribute *a, int n)
{
struct device *dev = container_of(kobj, struct device, kobj);
- struct cros_ec_dev *ec = container_of(dev,
- struct cros_ec_dev, class_dev);
+ struct cros_ec_dev *ec = to_cros_ec_dev(dev);
struct platform_device *pdev = to_platform_device(ec->dev);
struct cros_ec_platform *pdata = pdev->dev.platform_data;
int is_cros_ec;
diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c
index 3682e15..31c8b8c 100644
--- a/drivers/platform/chrome/cros_ec_lpc.c
+++ b/drivers/platform/chrome/cros_ec_lpc.c
@@ -435,7 +435,13 @@ static int __init cros_ec_lpc_init(void)
int ret;
acpi_status status;
- if (!dmi_check_system(cros_ec_lpc_dmi_table)) {
+ status = acpi_get_devices(ACPI_DRV_NAME, cros_ec_lpc_parse_device,
+ &cros_ec_lpc_acpi_device_found, NULL);
+ if (ACPI_FAILURE(status))
+ pr_warn(DRV_NAME ": Looking for %s failed\n", ACPI_DRV_NAME);
+
+ if (!cros_ec_lpc_acpi_device_found &&
+ !dmi_check_system(cros_ec_lpc_dmi_table)) {
pr_err(DRV_NAME ": unsupported system.\n");
return -ENODEV;
}
@@ -450,11 +456,6 @@ static int __init cros_ec_lpc_init(void)
return ret;
}
- status = acpi_get_devices(ACPI_DRV_NAME, cros_ec_lpc_parse_device,
- &cros_ec_lpc_acpi_device_found, NULL);
- if (ACPI_FAILURE(status))
- pr_warn(DRV_NAME ": Looking for %s failed\n", ACPI_DRV_NAME);
-
if (!cros_ec_lpc_acpi_device_found) {
/* Register the device, and it'll get hooked up automatically */
ret = platform_device_register(&cros_ec_lpc_device);
diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c
index e7bbdf9..8350ca2 100644
--- a/drivers/platform/chrome/cros_ec_proto.c
+++ b/drivers/platform/chrome/cros_ec_proto.c
@@ -91,6 +91,8 @@ static int send_command(struct cros_ec_device *ec_dev,
usleep_range(10000, 11000);
ret = (*xfer_fxn)(ec_dev, status_msg);
+ if (ret == -EAGAIN)
+ continue;
if (ret < 0)
break;
diff --git a/drivers/platform/chrome/cros_ec_sysfs.c b/drivers/platform/chrome/cros_ec_sysfs.c
index 5a6db3f..f34a501 100644
--- a/drivers/platform/chrome/cros_ec_sysfs.c
+++ b/drivers/platform/chrome/cros_ec_sysfs.c
@@ -34,8 +34,6 @@
#include <linux/types.h>
#include <linux/uaccess.h>
-#define to_cros_ec_dev(dev) container_of(dev, struct cros_ec_dev, class_dev)
-
/* Accessor functions */
static ssize_t reboot_show(struct device *dev,
diff --git a/drivers/platform/chrome/cros_ec_vbc.c b/drivers/platform/chrome/cros_ec_vbc.c
index 6d38e6b..5356f26bc 100644
--- a/drivers/platform/chrome/cros_ec_vbc.c
+++ b/drivers/platform/chrome/cros_ec_vbc.c
@@ -29,8 +29,7 @@ static ssize_t vboot_context_read(struct file *filp, struct kobject *kobj,
loff_t pos, size_t count)
{
struct device *dev = container_of(kobj, struct device, kobj);
- struct cros_ec_dev *ec = container_of(dev, struct cros_ec_dev,
- class_dev);
+ struct cros_ec_dev *ec = to_cros_ec_dev(dev);
struct cros_ec_device *ecdev = ec->ec_dev;
struct ec_params_vbnvcontext *params;
struct cros_ec_command *msg;
@@ -70,8 +69,7 @@ static ssize_t vboot_context_write(struct file *filp, struct kobject *kobj,
loff_t pos, size_t count)
{
struct device *dev = container_of(kobj, struct device, kobj);
- struct cros_ec_dev *ec = container_of(dev, struct cros_ec_dev,
- class_dev);
+ struct cros_ec_dev *ec = to_cros_ec_dev(dev);
struct cros_ec_device *ecdev = ec->ec_dev;
struct ec_params_vbnvcontext *params;
struct cros_ec_command *msg;
@@ -111,8 +109,7 @@ static umode_t cros_ec_vbc_is_visible(struct kobject *kobj,
struct bin_attribute *a, int n)
{
struct device *dev = container_of(kobj, struct device, kobj);
- struct cros_ec_dev *ec = container_of(dev, struct cros_ec_dev,
- class_dev);
+ struct cros_ec_dev *ec = to_cros_ec_dev(dev);
struct device_node *np = ec->ec_dev->dev->of_node;
if (IS_ENABLED(CONFIG_OF) && np) {
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 39d06dd..566644b 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -154,7 +154,7 @@
depends on ACPI_VIDEO || ACPI_VIDEO = n
depends on RFKILL || RFKILL = n
depends on SERIO_I8042
- select DELL_SMBIOS
+ depends on DELL_SMBIOS
select POWER_SUPPLY
select LEDS_CLASS
select NEW_LEDS
@@ -168,8 +168,8 @@
depends on DMI
depends on INPUT
depends on ACPI_VIDEO || ACPI_VIDEO = n
+ depends on DELL_SMBIOS
select DELL_WMI_DESCRIPTOR
- select DELL_SMBIOS
select INPUT_SPARSEKMAP
---help---
Say Y here if you want to support WMI-based hotkeys on Dell laptops.
diff --git a/drivers/platform/x86/asus-wireless.c b/drivers/platform/x86/asus-wireless.c
index d4aeac3..f086469 100644
--- a/drivers/platform/x86/asus-wireless.c
+++ b/drivers/platform/x86/asus-wireless.c
@@ -178,8 +178,10 @@ static int asus_wireless_remove(struct acpi_device *adev)
{
struct asus_wireless_data *data = acpi_driver_data(adev);
- if (data->wq)
+ if (data->wq) {
+ devm_led_classdev_unregister(&adev->dev, &data->led);
destroy_workqueue(data->wq);
+ }
return 0;
}
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index a32c5c0..ffffb99 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -163,6 +163,16 @@ MODULE_LICENSE("GPL");
static const char * const ashs_ids[] = { "ATK4001", "ATK4002", NULL };
+static bool ashs_present(void)
+{
+ int i = 0;
+ while (ashs_ids[i]) {
+ if (acpi_dev_found(ashs_ids[i++]))
+ return true;
+ }
+ return false;
+}
+
struct bios_args {
u32 arg0;
u32 arg1;
@@ -1025,6 +1035,9 @@ static int asus_new_rfkill(struct asus_wmi *asus,
static void asus_wmi_rfkill_exit(struct asus_wmi *asus)
{
+ if (asus->driver->wlan_ctrl_by_user && ashs_present())
+ return;
+
asus_unregister_rfkill_notifier(asus, "\\_SB.PCI0.P0P5");
asus_unregister_rfkill_notifier(asus, "\\_SB.PCI0.P0P6");
asus_unregister_rfkill_notifier(asus, "\\_SB.PCI0.P0P7");
@@ -2121,16 +2134,6 @@ static int asus_wmi_fan_init(struct asus_wmi *asus)
return 0;
}
-static bool ashs_present(void)
-{
- int i = 0;
- while (ashs_ids[i]) {
- if (acpi_dev_found(ashs_ids[i++]))
- return true;
- }
- return false;
-}
-
/*
* WMI Driver
*/
diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c
index e8d058c..eef76bf 100644
--- a/drivers/platform/x86/toshiba_acpi.c
+++ b/drivers/platform/x86/toshiba_acpi.c
@@ -1689,19 +1689,6 @@ static int version_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int version_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, version_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations version_proc_fops = {
- .owner = THIS_MODULE,
- .open = version_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/*
* Proc and module init
*/
@@ -1722,8 +1709,8 @@ static void create_toshiba_proc_entries(struct toshiba_acpi_dev *dev)
if (dev->hotkey_dev)
proc_create_data("keys", S_IRUGO | S_IWUSR, toshiba_proc_dir,
&keys_proc_fops, dev);
- proc_create_data("version", S_IRUGO, toshiba_proc_dir,
- &version_proc_fops, dev);
+ proc_create_single_data("version", S_IRUGO, toshiba_proc_dir,
+ version_proc_show, dev);
}
static void remove_toshiba_proc_entries(struct toshiba_acpi_dev *dev)
diff --git a/drivers/pnp/pnpbios/proc.c b/drivers/pnp/pnpbios/proc.c
index 7d4aca7..fe1c8f5 100644
--- a/drivers/pnp/pnpbios/proc.c
+++ b/drivers/pnp/pnpbios/proc.c
@@ -47,19 +47,6 @@ static int pnpconfig_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int pnpconfig_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, pnpconfig_proc_show, NULL);
-}
-
-static const struct file_operations pnpconfig_proc_fops = {
- .owner = THIS_MODULE,
- .open = pnpconfig_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int escd_info_proc_show(struct seq_file *m, void *v)
{
struct escd_info_struc escd;
@@ -74,19 +61,6 @@ static int escd_info_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int escd_info_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, escd_info_proc_show, NULL);
-}
-
-static const struct file_operations escd_info_proc_fops = {
- .owner = THIS_MODULE,
- .open = escd_info_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
#define MAX_SANE_ESCD_SIZE (32*1024)
static int escd_proc_show(struct seq_file *m, void *v)
{
@@ -129,19 +103,6 @@ static int escd_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int escd_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, escd_proc_show, NULL);
-}
-
-static const struct file_operations escd_proc_fops = {
- .owner = THIS_MODULE,
- .open = escd_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int pnp_legacyres_proc_show(struct seq_file *m, void *v)
{
void *buf;
@@ -159,19 +120,6 @@ static int pnp_legacyres_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int pnp_legacyres_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, pnp_legacyres_proc_show, NULL);
-}
-
-static const struct file_operations pnp_legacyres_proc_fops = {
- .owner = THIS_MODULE,
- .open = pnp_legacyres_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int pnp_devices_proc_show(struct seq_file *m, void *v)
{
struct pnp_bios_node *node;
@@ -202,19 +150,6 @@ static int pnp_devices_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int pnp_devices_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, pnp_devices_proc_show, NULL);
-}
-
-static const struct file_operations pnp_devices_proc_fops = {
- .owner = THIS_MODULE,
- .open = pnp_devices_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int pnpbios_proc_show(struct seq_file *m, void *v)
{
void *data = m->private;
@@ -318,12 +253,13 @@ int __init pnpbios_proc_init(void)
proc_pnp_boot = proc_mkdir("boot", proc_pnp);
if (!proc_pnp_boot)
return -EIO;
- proc_create("devices", 0, proc_pnp, &pnp_devices_proc_fops);
- proc_create("configuration_info", 0, proc_pnp, &pnpconfig_proc_fops);
- proc_create("escd_info", 0, proc_pnp, &escd_info_proc_fops);
- proc_create("escd", S_IRUSR, proc_pnp, &escd_proc_fops);
- proc_create("legacy_device_resources", 0, proc_pnp, &pnp_legacyres_proc_fops);
-
+ proc_create_single("devices", 0, proc_pnp, pnp_devices_proc_show);
+ proc_create_single("configuration_info", 0, proc_pnp,
+ pnpconfig_proc_show);
+ proc_create_single("escd_info", 0, proc_pnp, escd_info_proc_show);
+ proc_create_single("escd", S_IRUSR, proc_pnp, escd_proc_show);
+ proc_create_single("legacy_device_resources", 0, proc_pnp,
+ pnp_legacyres_proc_show);
return 0;
}
diff --git a/drivers/power/avs/rockchip-io-domain.c b/drivers/power/avs/rockchip-io-domain.c
index ed2b109..d6a5e6b 100644
--- a/drivers/power/avs/rockchip-io-domain.c
+++ b/drivers/power/avs/rockchip-io-domain.c
@@ -39,6 +39,10 @@
#define MAX_VOLTAGE_1_8 1980000
#define MAX_VOLTAGE_3_3 3600000
+#define PX30_IO_VSEL 0x180
+#define PX30_IO_VSEL_VCCIO6_SRC BIT(0)
+#define PX30_IO_VSEL_VCCIO6_SUPPLY_NUM 1
+
#define RK3288_SOC_CON2 0x24c
#define RK3288_SOC_CON2_FLASH0 BIT(7)
#define RK3288_SOC_FLASH_SUPPLY_NUM 2
@@ -151,6 +155,25 @@ static int rockchip_iodomain_notify(struct notifier_block *nb,
return NOTIFY_OK;
}
+static void px30_iodomain_init(struct rockchip_iodomain *iod)
+{
+ int ret;
+ u32 val;
+
+ /* if no VCCIO0 supply we should leave things alone */
+ if (!iod->supplies[PX30_IO_VSEL_VCCIO6_SUPPLY_NUM].reg)
+ return;
+
+ /*
+ * set vccio0 iodomain to also use this framework
+ * instead of a special gpio.
+ */
+ val = PX30_IO_VSEL_VCCIO6_SRC | (PX30_IO_VSEL_VCCIO6_SRC << 16);
+ ret = regmap_write(iod->grf, PX30_IO_VSEL, val);
+ if (ret < 0)
+ dev_warn(iod->dev, "couldn't update vccio0 ctrl\n");
+}
+
static void rk3288_iodomain_init(struct rockchip_iodomain *iod)
{
int ret;
@@ -227,6 +250,43 @@ static void rk3399_pmu_iodomain_init(struct rockchip_iodomain *iod)
dev_warn(iod->dev, "couldn't update pmu io iodomain ctrl\n");
}
+static const struct rockchip_iodomain_soc_data soc_data_px30 = {
+ .grf_offset = 0x180,
+ .supply_names = {
+ NULL,
+ "vccio6",
+ "vccio1",
+ "vccio2",
+ "vccio3",
+ "vccio4",
+ "vccio5",
+ "vccio-oscgpi",
+ },
+ .init = px30_iodomain_init,
+};
+
+static const struct rockchip_iodomain_soc_data soc_data_px30_pmu = {
+ .grf_offset = 0x100,
+ .supply_names = {
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ "pmuio1",
+ "pmuio2",
+ },
+};
+
/*
* On the rk3188 the io-domains are handled by a shared register with the
* lower 8 bits being still being continuing drive-strength settings.
@@ -381,6 +441,14 @@ static const struct rockchip_iodomain_soc_data soc_data_rv1108_pmu = {
static const struct of_device_id rockchip_iodomain_match[] = {
{
+ .compatible = "rockchip,px30-io-voltage-domain",
+ .data = (void *)&soc_data_px30
+ },
+ {
+ .compatible = "rockchip,px30-pmu-io-voltage-domain",
+ .data = (void *)&soc_data_px30_pmu
+ },
+ {
.compatible = "rockchip,rk3188-io-voltage-domain",
.data = &soc_data_rk3188
},
diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c
index 9d27016c..0434ab7 100644
--- a/drivers/rapidio/devices/rio_mport_cdev.c
+++ b/drivers/rapidio/devices/rio_mport_cdev.c
@@ -740,10 +740,7 @@ static int do_dma_request(struct mport_dma_req *req,
tx->callback = dma_xfer_callback;
tx->callback_param = req;
- req->dmach = chan;
- req->sync = sync;
req->status = DMA_IN_PROGRESS;
- init_completion(&req->req_comp);
kref_get(&req->refcount);
cookie = dmaengine_submit(tx);
@@ -831,13 +828,20 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode,
if (!req)
return -ENOMEM;
- kref_init(&req->refcount);
-
ret = get_dma_channel(priv);
if (ret) {
kfree(req);
return ret;
}
+ chan = priv->dmach;
+
+ kref_init(&req->refcount);
+ init_completion(&req->req_comp);
+ req->dir = dir;
+ req->filp = filp;
+ req->priv = priv;
+ req->dmach = chan;
+ req->sync = sync;
/*
* If parameter loc_addr != NULL, we are transferring data from/to
@@ -925,11 +929,6 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode,
xfer->offset, xfer->length);
}
- req->dir = dir;
- req->filp = filp;
- req->priv = priv;
- chan = priv->dmach;
-
nents = dma_map_sg(chan->device->dev,
req->sgt.sgl, req->sgt.nents, dir);
if (nents == 0) {
diff --git a/drivers/remoteproc/qcom_q6v5_pil.c b/drivers/remoteproc/qcom_q6v5_pil.c
index 8e70a62..cbbafdc 100644
--- a/drivers/remoteproc/qcom_q6v5_pil.c
+++ b/drivers/remoteproc/qcom_q6v5_pil.c
@@ -1083,6 +1083,7 @@ static int q6v5_alloc_memory_region(struct q6v5 *qproc)
dev_err(qproc->dev, "unable to resolve mba region\n");
return ret;
}
+ of_node_put(node);
qproc->mba_phys = r.start;
qproc->mba_size = resource_size(&r);
@@ -1100,6 +1101,7 @@ static int q6v5_alloc_memory_region(struct q6v5 *qproc)
dev_err(qproc->dev, "unable to resolve mpss region\n");
return ret;
}
+ of_node_put(node);
qproc->mpss_phys = qproc->mpss_reloc = r.start;
qproc->mpss_size = resource_size(&r);
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 6d9c583..a9609d9 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -1163,7 +1163,7 @@ int rproc_trigger_recovery(struct rproc *rproc)
if (ret)
return ret;
- ret = rproc_stop(rproc, false);
+ ret = rproc_stop(rproc, true);
if (ret)
goto unlock_mutex;
@@ -1316,7 +1316,7 @@ void rproc_shutdown(struct rproc *rproc)
if (!atomic_dec_and_test(&rproc->power))
goto out;
- ret = rproc_stop(rproc, true);
+ ret = rproc_stop(rproc, false);
if (ret) {
atomic_inc(&rproc->power);
goto out;
diff --git a/drivers/reset/reset-uniphier.c b/drivers/reset/reset-uniphier.c
index 360e06b..ac18f2f 100644
--- a/drivers/reset/reset-uniphier.c
+++ b/drivers/reset/reset-uniphier.c
@@ -110,7 +110,7 @@ static const struct uniphier_reset_data uniphier_ld20_sys_reset_data[] = {
UNIPHIER_RESETX(4, 0x200c, 2), /* eMMC */
UNIPHIER_RESETX(6, 0x200c, 6), /* Ether */
UNIPHIER_RESETX(8, 0x200c, 8), /* STDMAC (HSC) */
- UNIPHIER_RESETX(12, 0x200c, 5), /* GIO (PCIe, USB3) */
+ UNIPHIER_RESETX(14, 0x200c, 5), /* USB30 */
UNIPHIER_RESETX(16, 0x200c, 12), /* USB30-PHY0 */
UNIPHIER_RESETX(17, 0x200c, 13), /* USB30-PHY1 */
UNIPHIER_RESETX(18, 0x200c, 14), /* USB30-PHY2 */
@@ -127,8 +127,8 @@ static const struct uniphier_reset_data uniphier_pxs3_sys_reset_data[] = {
UNIPHIER_RESETX(6, 0x200c, 9), /* Ether0 */
UNIPHIER_RESETX(7, 0x200c, 10), /* Ether1 */
UNIPHIER_RESETX(8, 0x200c, 12), /* STDMAC */
- UNIPHIER_RESETX(12, 0x200c, 4), /* USB30 link (GIO0) */
- UNIPHIER_RESETX(13, 0x200c, 5), /* USB31 link (GIO1) */
+ UNIPHIER_RESETX(12, 0x200c, 4), /* USB30 link */
+ UNIPHIER_RESETX(13, 0x200c, 5), /* USB31 link */
UNIPHIER_RESETX(16, 0x200c, 16), /* USB30-PHY0 */
UNIPHIER_RESETX(17, 0x200c, 18), /* USB30-PHY1 */
UNIPHIER_RESETX(18, 0x200c, 20), /* USB30-PHY2 */
diff --git a/drivers/rpmsg/rpmsg_char.c b/drivers/rpmsg/rpmsg_char.c
index 64b6de9..1efdf9f 100644
--- a/drivers/rpmsg/rpmsg_char.c
+++ b/drivers/rpmsg/rpmsg_char.c
@@ -581,4 +581,6 @@ static void rpmsg_chrdev_exit(void)
unregister_chrdev_region(rpmsg_major, RPMSG_DEV_MAX);
}
module_exit(rpmsg_chrdev_exit);
+
+MODULE_ALIAS("rpmsg:rpmsg_chrdev");
MODULE_LICENSE("GPL v2");
diff --git a/drivers/rtc/rtc-opal.c b/drivers/rtc/rtc-opal.c
index 304e891..60f2250 100644
--- a/drivers/rtc/rtc-opal.c
+++ b/drivers/rtc/rtc-opal.c
@@ -57,7 +57,7 @@ static void tm_to_opal(struct rtc_time *tm, u32 *y_m_d, u64 *h_m_s_ms)
static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm)
{
- long rc = OPAL_BUSY;
+ s64 rc = OPAL_BUSY;
int retries = 10;
u32 y_m_d;
u64 h_m_s_ms;
@@ -66,13 +66,17 @@ static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm)
while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
- if (rc == OPAL_BUSY_EVENT)
+ if (rc == OPAL_BUSY_EVENT) {
+ msleep(OPAL_BUSY_DELAY_MS);
opal_poll_events(NULL);
- else if (retries-- && (rc == OPAL_HARDWARE
- || rc == OPAL_INTERNAL_ERROR))
- msleep(10);
- else if (rc != OPAL_BUSY && rc != OPAL_BUSY_EVENT)
- break;
+ } else if (rc == OPAL_BUSY) {
+ msleep(OPAL_BUSY_DELAY_MS);
+ } else if (rc == OPAL_HARDWARE || rc == OPAL_INTERNAL_ERROR) {
+ if (retries--) {
+ msleep(10); /* Wait 10ms before retry */
+ rc = OPAL_BUSY; /* go around again */
+ }
+ }
}
if (rc != OPAL_SUCCESS)
@@ -87,21 +91,26 @@ static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm)
static int opal_set_rtc_time(struct device *dev, struct rtc_time *tm)
{
- long rc = OPAL_BUSY;
+ s64 rc = OPAL_BUSY;
int retries = 10;
u32 y_m_d = 0;
u64 h_m_s_ms = 0;
tm_to_opal(tm, &y_m_d, &h_m_s_ms);
+
while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
rc = opal_rtc_write(y_m_d, h_m_s_ms);
- if (rc == OPAL_BUSY_EVENT)
+ if (rc == OPAL_BUSY_EVENT) {
+ msleep(OPAL_BUSY_DELAY_MS);
opal_poll_events(NULL);
- else if (retries-- && (rc == OPAL_HARDWARE
- || rc == OPAL_INTERNAL_ERROR))
- msleep(10);
- else if (rc != OPAL_BUSY && rc != OPAL_BUSY_EVENT)
- break;
+ } else if (rc == OPAL_BUSY) {
+ msleep(OPAL_BUSY_DELAY_MS);
+ } else if (rc == OPAL_HARDWARE || rc == OPAL_INTERNAL_ERROR) {
+ if (retries--) {
+ msleep(10); /* Wait 10ms before retry */
+ rc = OPAL_BUSY; /* go around again */
+ }
+ }
}
return rc == OPAL_SUCCESS ? 0 : -EIO;
diff --git a/drivers/rtc/rtc-proc.c b/drivers/rtc/rtc-proc.c
index 31e7e23..a9dd921 100644
--- a/drivers/rtc/rtc-proc.c
+++ b/drivers/rtc/rtc-proc.c
@@ -107,40 +107,11 @@ static int rtc_proc_show(struct seq_file *seq, void *offset)
return 0;
}
-static int rtc_proc_open(struct inode *inode, struct file *file)
-{
- int ret;
- struct rtc_device *rtc = PDE_DATA(inode);
-
- if (!try_module_get(rtc->owner))
- return -ENODEV;
-
- ret = single_open(file, rtc_proc_show, rtc);
- if (ret)
- module_put(rtc->owner);
- return ret;
-}
-
-static int rtc_proc_release(struct inode *inode, struct file *file)
-{
- int res = single_release(inode, file);
- struct rtc_device *rtc = PDE_DATA(inode);
-
- module_put(rtc->owner);
- return res;
-}
-
-static const struct file_operations rtc_proc_fops = {
- .open = rtc_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = rtc_proc_release,
-};
-
void rtc_proc_add_device(struct rtc_device *rtc)
{
if (is_rtc_hctosys(rtc))
- proc_create_data("driver/rtc", 0, NULL, &rtc_proc_fops, rtc);
+ proc_create_single_data("driver/rtc", 0, NULL, rtc_proc_show,
+ rtc);
}
void rtc_proc_del_device(struct rtc_device *rtc)
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 04143c0..73cce3e 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -2569,14 +2569,11 @@ EXPORT_SYMBOL(dasd_sleep_on_immediatly);
* Cancellation of a request is an asynchronous operation! The calling
* function has to wait until the request is properly returned via callback.
*/
-int dasd_cancel_req(struct dasd_ccw_req *cqr)
+static int __dasd_cancel_req(struct dasd_ccw_req *cqr)
{
struct dasd_device *device = cqr->startdev;
- unsigned long flags;
- int rc;
+ int rc = 0;
- rc = 0;
- spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
switch (cqr->status) {
case DASD_CQR_QUEUED:
/* request was not started - just set to cleared */
@@ -2596,11 +2593,21 @@ int dasd_cancel_req(struct dasd_ccw_req *cqr)
default: /* already finished or clear pending - do nothing */
break;
}
- spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
dasd_schedule_device_bh(device);
return rc;
}
-EXPORT_SYMBOL(dasd_cancel_req);
+
+int dasd_cancel_req(struct dasd_ccw_req *cqr)
+{
+ struct dasd_device *device = cqr->startdev;
+ unsigned long flags;
+ int rc;
+
+ spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
+ rc = __dasd_cancel_req(cqr);
+ spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
+ return rc;
+}
/*
* SECTION: Operations of the dasd_block layer.
@@ -3034,7 +3041,8 @@ static blk_status_t do_dasd_request(struct blk_mq_hw_ctx *hctx,
cqr->callback_data = req;
cqr->status = DASD_CQR_FILLED;
cqr->dq = dq;
- req->completion_data = cqr;
+ *((struct dasd_ccw_req **) blk_mq_rq_to_pdu(req)) = cqr;
+
blk_mq_start_request(req);
spin_lock(&block->queue_lock);
list_add_tail(&cqr->blocklist, &block->ccw_queue);
@@ -3053,19 +3061,20 @@ static blk_status_t do_dasd_request(struct blk_mq_hw_ctx *hctx,
*
* Return values:
* BLK_EH_RESET_TIMER if the request should be left running
- * BLK_EH_NOT_HANDLED if the request is handled or terminated
+ * BLK_EH_DONE if the request is handled or terminated
* by the driver.
*/
enum blk_eh_timer_return dasd_times_out(struct request *req, bool reserved)
{
- struct dasd_ccw_req *cqr = req->completion_data;
struct dasd_block *block = req->q->queuedata;
struct dasd_device *device;
+ struct dasd_ccw_req *cqr;
unsigned long flags;
int rc = 0;
+ cqr = *((struct dasd_ccw_req **) blk_mq_rq_to_pdu(req));
if (!cqr)
- return BLK_EH_NOT_HANDLED;
+ return BLK_EH_DONE;
spin_lock_irqsave(&cqr->dq->lock, flags);
device = cqr->startdev ? cqr->startdev : block->base;
@@ -3082,12 +3091,10 @@ enum blk_eh_timer_return dasd_times_out(struct request *req, bool reserved)
cqr->retries = -1;
cqr->intrc = -ETIMEDOUT;
if (cqr->status >= DASD_CQR_QUEUED) {
- spin_unlock(get_ccwdev_lock(device->cdev));
- rc = dasd_cancel_req(cqr);
+ rc = __dasd_cancel_req(cqr);
} else if (cqr->status == DASD_CQR_FILLED ||
cqr->status == DASD_CQR_NEED_ERP) {
cqr->status = DASD_CQR_TERMINATED;
- spin_unlock(get_ccwdev_lock(device->cdev));
} else if (cqr->status == DASD_CQR_IN_ERP) {
struct dasd_ccw_req *searchcqr, *nextcqr, *tmpcqr;
@@ -3102,9 +3109,7 @@ enum blk_eh_timer_return dasd_times_out(struct request *req, bool reserved)
searchcqr->retries = -1;
searchcqr->intrc = -ETIMEDOUT;
if (searchcqr->status >= DASD_CQR_QUEUED) {
- spin_unlock(get_ccwdev_lock(device->cdev));
- rc = dasd_cancel_req(searchcqr);
- spin_lock(get_ccwdev_lock(device->cdev));
+ rc = __dasd_cancel_req(searchcqr);
} else if ((searchcqr->status == DASD_CQR_FILLED) ||
(searchcqr->status == DASD_CQR_NEED_ERP)) {
searchcqr->status = DASD_CQR_TERMINATED;
@@ -3118,13 +3123,13 @@ enum blk_eh_timer_return dasd_times_out(struct request *req, bool reserved)
}
break;
}
- spin_unlock(get_ccwdev_lock(device->cdev));
}
+ spin_unlock(get_ccwdev_lock(device->cdev));
dasd_schedule_block_bh(block);
spin_unlock(&block->queue_lock);
spin_unlock_irqrestore(&cqr->dq->lock, flags);
- return rc ? BLK_EH_RESET_TIMER : BLK_EH_NOT_HANDLED;
+ return rc ? BLK_EH_RESET_TIMER : BLK_EH_DONE;
}
static int dasd_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
@@ -3169,6 +3174,7 @@ static int dasd_alloc_queue(struct dasd_block *block)
int rc;
block->tag_set.ops = &dasd_mq_ops;
+ block->tag_set.cmd_size = sizeof(struct dasd_ccw_req *);
block->tag_set.nr_hw_queues = DASD_NR_HW_QUEUES;
block->tag_set.queue_depth = DASD_MAX_LCU_DEV * DASD_REQ_PER_DEV;
block->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c
index 62f5f04..5e963fe 100644
--- a/drivers/s390/block/dasd_alias.c
+++ b/drivers/s390/block/dasd_alias.c
@@ -592,13 +592,22 @@ static int _schedule_lcu_update(struct alias_lcu *lcu,
int dasd_alias_add_device(struct dasd_device *device)
{
struct dasd_eckd_private *private = device->private;
- struct alias_lcu *lcu;
+ __u8 uaddr = private->uid.real_unit_addr;
+ struct alias_lcu *lcu = private->lcu;
unsigned long flags;
int rc;
- lcu = private->lcu;
rc = 0;
spin_lock_irqsave(&lcu->lock, flags);
+ /*
+ * Check if device and lcu type differ. If so, the uac data may be
+ * outdated and needs to be updated.
+ */
+ if (private->uid.type != lcu->uac->unit[uaddr].ua_type) {
+ lcu->flags |= UPDATE_PENDING;
+ DBF_DEV_EVENT(DBF_WARNING, device, "%s",
+ "uid type mismatch - trigger rescan");
+ }
if (!(lcu->flags & UPDATE_PENDING)) {
rc = _add_device_to_lcu(lcu, device, device);
if (rc)
diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c
index f035c2f..131f198 100644
--- a/drivers/s390/block/dasd_diag.c
+++ b/drivers/s390/block/dasd_diag.c
@@ -27,7 +27,6 @@
#include <asm/io.h>
#include <asm/irq.h>
#include <asm/vtoc.h>
-#include <asm/diag.h>
#include "dasd_int.h"
#include "dasd_diag.h"
diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
index 7bdc6aa..2016e0e 100644
--- a/drivers/s390/block/dasd_ioctl.c
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -18,7 +18,6 @@
#include <linux/fs.h>
#include <linux/blkpg.h>
#include <linux/slab.h>
-#include <asm/compat.h>
#include <asm/ccwdev.h>
#include <asm/schid.h>
#include <asm/cmb.h>
diff --git a/drivers/s390/block/dasd_proc.c b/drivers/s390/block/dasd_proc.c
index c33788a..5cb80c6 100644
--- a/drivers/s390/block/dasd_proc.c
+++ b/drivers/s390/block/dasd_proc.c
@@ -131,19 +131,6 @@ static const struct seq_operations dasd_devices_seq_ops = {
.show = dasd_devices_show,
};
-static int dasd_devices_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &dasd_devices_seq_ops);
-}
-
-static const struct file_operations dasd_devices_file_ops = {
- .owner = THIS_MODULE,
- .open = dasd_devices_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
#ifdef CONFIG_DASD_PROFILE
static int dasd_stats_all_block_on(void)
{
@@ -352,10 +339,10 @@ dasd_proc_init(void)
dasd_proc_root_entry = proc_mkdir("dasd", NULL);
if (!dasd_proc_root_entry)
goto out_nodasd;
- dasd_devices_entry = proc_create("devices",
+ dasd_devices_entry = proc_create_seq("devices",
S_IFREG | S_IRUGO | S_IWUSR,
dasd_proc_root_entry,
- &dasd_devices_file_ops);
+ &dasd_devices_seq_ops);
if (!dasd_devices_entry)
goto out_nodevices;
dasd_statistics_entry = proc_create("statistics",
diff --git a/drivers/s390/char/Makefile b/drivers/s390/char/Makefile
index d049e2d..0a4c13e 100644
--- a/drivers/s390/char/Makefile
+++ b/drivers/s390/char/Makefile
@@ -54,3 +54,6 @@
hmcdrv-objs := hmcdrv_mod.o hmcdrv_dev.o hmcdrv_ftp.o hmcdrv_cache.o diag_ftp.o sclp_ftp.o
obj-$(CONFIG_HMC_DRV) += hmcdrv.o
+
+chkbss := sclp_early_core.o
+include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/drivers/s390/char/fs3270.c b/drivers/s390/char/fs3270.c
index 6182248..16a4e85 100644
--- a/drivers/s390/char/fs3270.c
+++ b/drivers/s390/char/fs3270.c
@@ -19,7 +19,6 @@
#include <linux/slab.h>
#include <linux/types.h>
-#include <asm/compat.h>
#include <asm/ccwdev.h>
#include <asm/cio.h>
#include <asm/ebcdic.h>
diff --git a/drivers/s390/char/sclp_ctl.c b/drivers/s390/char/sclp_ctl.c
index a78cea0..248b5db 100644
--- a/drivers/s390/char/sclp_ctl.c
+++ b/drivers/s390/char/sclp_ctl.c
@@ -14,7 +14,6 @@
#include <linux/init.h>
#include <linux/ioctl.h>
#include <linux/fs.h>
-#include <asm/compat.h>
#include <asm/sclp_ctl.h>
#include <asm/sclp.h>
diff --git a/drivers/s390/char/sclp_early_core.c b/drivers/s390/char/sclp_early_core.c
index 5f8d9ea..eceba38 100644
--- a/drivers/s390/char/sclp_early_core.c
+++ b/drivers/s390/char/sclp_early_core.c
@@ -18,7 +18,7 @@ int sclp_init_state __section(.data) = sclp_init_state_uninitialized;
* Used to keep track of the size of the event masks. Qemu until version 2.11
* only supports 4 and needs a workaround.
*/
-bool sclp_mask_compat_mode;
+bool sclp_mask_compat_mode __section(.data);
void sclp_early_wait_irq(void)
{
diff --git a/drivers/s390/char/tape_proc.c b/drivers/s390/char/tape_proc.c
index faae304..32a14ee 100644
--- a/drivers/s390/char/tape_proc.c
+++ b/drivers/s390/char/tape_proc.c
@@ -105,29 +105,14 @@ static const struct seq_operations tape_proc_seq = {
.show = tape_proc_show,
};
-static int tape_proc_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &tape_proc_seq);
-}
-
-static const struct file_operations tape_proc_ops =
-{
- .owner = THIS_MODULE,
- .open = tape_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
/*
* Initialize procfs stuff on startup
*/
void
tape_proc_init(void)
{
- tape_proc_devices =
- proc_create("tapedevices", S_IFREG | S_IRUGO | S_IWUSR, NULL,
- &tape_proc_ops);
+ tape_proc_devices = proc_create_seq("tapedevices",
+ S_IFREG | S_IRUGO | S_IWUSR, NULL, &tape_proc_seq);
if (tape_proc_devices == NULL) {
return;
}
diff --git a/drivers/s390/char/vmcp.c b/drivers/s390/char/vmcp.c
index 17e411c..948ce82 100644
--- a/drivers/s390/char/vmcp.c
+++ b/drivers/s390/char/vmcp.c
@@ -23,7 +23,6 @@
#include <linux/mutex.h>
#include <linux/cma.h>
#include <linux/mm.h>
-#include <asm/compat.h>
#include <asm/cpcmd.h>
#include <asm/debug.h>
#include <asm/vmcp.h>
diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c
index 5535312..db9c854 100644
--- a/drivers/s390/cio/ccwgroup.c
+++ b/drivers/s390/cio/ccwgroup.c
@@ -561,6 +561,12 @@ static struct bus_type ccwgroup_bus_type = {
.pm = &ccwgroup_pm_ops,
};
+bool dev_is_ccwgroup(struct device *dev)
+{
+ return dev->bus == &ccwgroup_bus_type;
+}
+EXPORT_SYMBOL(dev_is_ccwgroup);
+
/**
* ccwgroup_driver_register() - register a ccw group driver
* @cdriver: driver to be registered
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index 6652a49..9029804 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -452,6 +452,7 @@ static void chsc_process_sei_link_incident(struct chsc_sei_nt0_area *sei_area)
static void chsc_process_sei_res_acc(struct chsc_sei_nt0_area *sei_area)
{
+ struct channel_path *chp;
struct chp_link link;
struct chp_id chpid;
int status;
@@ -464,10 +465,17 @@ static void chsc_process_sei_res_acc(struct chsc_sei_nt0_area *sei_area)
chpid.id = sei_area->rsid;
/* allocate a new channel path structure, if needed */
status = chp_get_status(chpid);
- if (status < 0)
- chp_new(chpid);
- else if (!status)
+ if (!status)
return;
+
+ if (status < 0) {
+ chp_new(chpid);
+ } else {
+ chp = chpid_to_chp(chpid);
+ mutex_lock(&chp->lock);
+ chp_update_desc(chp);
+ mutex_unlock(&chp->lock);
+ }
memset(&link, 0, sizeof(struct chp_link));
link.chpid = chpid;
if ((sei_area->vf & 0xc0) != 0) {
diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c
index 0015729..8d9f366 100644
--- a/drivers/s390/cio/chsc_sch.c
+++ b/drivers/s390/cio/chsc_sch.c
@@ -16,7 +16,6 @@
#include <linux/miscdevice.h>
#include <linux/kernel_stat.h>
-#include <asm/compat.h>
#include <asm/cio.h>
#include <asm/chsc.h>
#include <asm/isc.h>
diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c
index aecfebb..4435ae0 100644
--- a/drivers/s390/cio/device_ops.c
+++ b/drivers/s390/cio/device_ops.c
@@ -473,6 +473,36 @@ struct channel_path_desc_fmt0 *ccw_device_get_chp_desc(struct ccw_device *cdev,
}
/**
+ * ccw_device_get_util_str() - return newly allocated utility strings
+ * @cdev: device to obtain the utility strings for
+ * @chp_idx: index of the channel path
+ *
+ * On success return a newly allocated copy of the utility strings
+ * associated with the given channel path. Return %NULL on error.
+ */
+u8 *ccw_device_get_util_str(struct ccw_device *cdev, int chp_idx)
+{
+ struct subchannel *sch = to_subchannel(cdev->dev.parent);
+ struct channel_path *chp;
+ struct chp_id chpid;
+ u8 *util_str;
+
+ chp_id_init(&chpid);
+ chpid.id = sch->schib.pmcw.chpid[chp_idx];
+ chp = chpid_to_chp(chpid);
+
+ util_str = kmalloc(sizeof(chp->desc_fmt3.util_str), GFP_KERNEL);
+ if (!util_str)
+ return NULL;
+
+ mutex_lock(&chp->lock);
+ memcpy(util_str, chp->desc_fmt3.util_str, sizeof(chp->desc_fmt3.util_str));
+ mutex_unlock(&chp->lock);
+
+ return util_str;
+}
+
+/**
* ccw_device_get_id() - obtain a ccw device id
* @cdev: device to obtain the id for
* @dev_id: where to fill in the values
@@ -682,3 +712,4 @@ EXPORT_SYMBOL(ccw_device_start_key);
EXPORT_SYMBOL(ccw_device_get_ciw);
EXPORT_SYMBOL(ccw_device_get_path_mask);
EXPORT_SYMBOL_GPL(ccw_device_get_chp_desc);
+EXPORT_SYMBOL_GPL(ccw_device_get_util_str);
diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c
index 439991d..4c14ce4 100644
--- a/drivers/s390/cio/qdio_setup.c
+++ b/drivers/s390/cio/qdio_setup.c
@@ -141,7 +141,7 @@ static int __qdio_allocate_qs(struct qdio_q **irq_ptr_qs, int nr_queues)
int i;
for (i = 0; i < nr_queues; i++) {
- q = kmem_cache_alloc(qdio_q_cache, GFP_KERNEL);
+ q = kmem_cache_zalloc(qdio_q_cache, GFP_KERNEL);
if (!q)
return -ENOMEM;
@@ -456,7 +456,6 @@ int qdio_setup_irq(struct qdio_initialize *init_data)
{
struct ciw *ciw;
struct qdio_irq *irq_ptr = init_data->cdev->private->qdio_data;
- int rc;
memset(&irq_ptr->qib, 0, sizeof(irq_ptr->qib));
memset(&irq_ptr->siga_flag, 0, sizeof(irq_ptr->siga_flag));
@@ -493,16 +492,14 @@ int qdio_setup_irq(struct qdio_initialize *init_data)
ciw = ccw_device_get_ciw(init_data->cdev, CIW_TYPE_EQUEUE);
if (!ciw) {
DBF_ERROR("%4x NO EQ", irq_ptr->schid.sch_no);
- rc = -EINVAL;
- goto out_err;
+ return -EINVAL;
}
irq_ptr->equeue = *ciw;
ciw = ccw_device_get_ciw(init_data->cdev, CIW_TYPE_AQUEUE);
if (!ciw) {
DBF_ERROR("%4x NO AQ", irq_ptr->schid.sch_no);
- rc = -EINVAL;
- goto out_err;
+ return -EINVAL;
}
irq_ptr->aqueue = *ciw;
@@ -512,9 +509,6 @@ int qdio_setup_irq(struct qdio_initialize *init_data)
init_data->cdev->handler = qdio_int_handler;
spin_unlock_irq(get_ccwdev_lock(irq_ptr->cdev));
return 0;
-out_err:
- qdio_release_memory(irq_ptr);
- return rc;
}
void qdio_print_subchannel_info(struct qdio_irq *irq_ptr,
diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index 2c75507..dce92b2 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -715,6 +715,10 @@ void cp_free(struct channel_program *cp)
* and stores the result to ccwchain list. @cp must have been
* initialized by a previous call with cp_init(). Otherwise, undefined
* behavior occurs.
+ * For each chain composing the channel program:
+ * - On entry ch_len holds the count of CCWs to be translated.
+ * - On exit ch_len is adjusted to the count of successfully translated CCWs.
+ * This allows cp_free to find in ch_len the count of CCWs to free in a chain.
*
* The S/390 CCW Translation APIS (prefixed by 'cp_') are introduced
* as helpers to do ccw chain translation inside the kernel. Basically
@@ -749,11 +753,18 @@ int cp_prefetch(struct channel_program *cp)
for (idx = 0; idx < len; idx++) {
ret = ccwchain_fetch_one(chain, idx, cp);
if (ret)
- return ret;
+ goto out_err;
}
}
return 0;
+out_err:
+ /* Only cleanup the chain elements that were actually translated. */
+ chain->ch_len = idx;
+ list_for_each_entry_continue(chain, &cp->ccwchain_list, next) {
+ chain->ch_len = 0;
+ }
+ return ret;
}
/**
diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
index ff6963a..3c80064 100644
--- a/drivers/s390/cio/vfio_ccw_fsm.c
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -20,12 +20,12 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
int ccode;
__u8 lpm;
unsigned long flags;
+ int ret;
sch = private->sch;
spin_lock_irqsave(sch->lock, flags);
private->state = VFIO_CCW_STATE_BUSY;
- spin_unlock_irqrestore(sch->lock, flags);
orb = cp_get_orb(&private->cp, (u32)(addr_t)sch, sch->lpm);
@@ -38,10 +38,12 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
* Initialize device status information
*/
sch->schib.scsw.cmd.actl |= SCSW_ACTL_START_PEND;
- return 0;
+ ret = 0;
+ break;
case 1: /* Status pending */
case 2: /* Busy */
- return -EBUSY;
+ ret = -EBUSY;
+ break;
case 3: /* Device/path not operational */
{
lpm = orb->cmd.lpm;
@@ -51,13 +53,16 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
sch->lpm = 0;
if (cio_update_schib(sch))
- return -ENODEV;
-
- return sch->lpm ? -EACCES : -ENODEV;
+ ret = -ENODEV;
+ else
+ ret = sch->lpm ? -EACCES : -ENODEV;
+ break;
}
default:
- return ccode;
+ ret = ccode;
}
+ spin_unlock_irqrestore(sch->lock, flags);
+ return ret;
}
static void fsm_notoper(struct vfio_ccw_private *private,
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 02184cf..6a273c5 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -198,11 +198,18 @@ struct ap_message {
*/
static inline void ap_init_message(struct ap_message *ap_msg)
{
- ap_msg->psmid = 0;
- ap_msg->length = 0;
- ap_msg->rc = 0;
- ap_msg->special = 0;
- ap_msg->receive = NULL;
+ memset(ap_msg, 0, sizeof(*ap_msg));
+}
+
+/**
+ * ap_release_message() - Release ap_message.
+ * Releases all memory used internal within the ap_message struct
+ * Currently this is the message and private field.
+ */
+static inline void ap_release_message(struct ap_message *ap_msg)
+{
+ kzfree(ap_msg->message);
+ kzfree(ap_msg->private);
}
#define for_each_ap_card(_ac) \
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 5efd848..febcdb5 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -371,6 +371,7 @@ long zcrypt_send_cprb(struct ica_xcRB *xcRB)
trace_s390_zcrypt_req(xcRB, TB_ZSECSENDCPRB);
+ ap_init_message(&ap_msg);
rc = get_cprb_fc(xcRB, &ap_msg, &func_code, &domain);
if (rc)
goto out;
@@ -425,6 +426,7 @@ long zcrypt_send_cprb(struct ica_xcRB *xcRB)
spin_unlock(&zcrypt_list_lock);
out:
+ ap_release_message(&ap_msg);
trace_s390_zcrypt_rep(xcRB, func_code, rc,
AP_QID_CARD(qid), AP_QID_QUEUE(qid));
return rc;
@@ -468,6 +470,8 @@ static long zcrypt_send_ep11_cprb(struct ep11_urb *xcrb)
trace_s390_zcrypt_req(xcrb, TP_ZSENDEP11CPRB);
+ ap_init_message(&ap_msg);
+
target_num = (unsigned short) xcrb->targets_num;
/* empty list indicates autoselect (all available targets) */
@@ -485,7 +489,7 @@ static long zcrypt_send_ep11_cprb(struct ep11_urb *xcrb)
if (copy_from_user(targets, uptr,
target_num * sizeof(*targets))) {
rc = -EFAULT;
- goto out;
+ goto out_free;
}
}
@@ -542,6 +546,7 @@ static long zcrypt_send_ep11_cprb(struct ep11_urb *xcrb)
out_free:
kfree(targets);
out:
+ ap_release_message(&ap_msg);
trace_s390_zcrypt_rep(xcrb, func_code, rc,
AP_QID_CARD(qid), AP_QID_QUEUE(qid));
return rc;
@@ -559,6 +564,7 @@ static long zcrypt_rng(char *buffer)
trace_s390_zcrypt_req(buffer, TP_HWRNGCPRB);
+ ap_init_message(&ap_msg);
rc = get_rng_fc(&ap_msg, &func_code, &domain);
if (rc)
goto out;
@@ -589,8 +595,10 @@ static long zcrypt_rng(char *buffer)
pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight);
spin_unlock(&zcrypt_list_lock);
- if (!pref_zq)
- return -ENODEV;
+ if (!pref_zq) {
+ rc = -ENODEV;
+ goto out;
+ }
qid = pref_zq->queue->qid;
rc = pref_zq->ops->rng(pref_zq, buffer, &ap_msg);
@@ -600,6 +608,7 @@ static long zcrypt_rng(char *buffer)
spin_unlock(&zcrypt_list_lock);
out:
+ ap_release_message(&ap_msg);
trace_s390_zcrypt_rep(buffer, func_code, rc,
AP_QID_CARD(qid), AP_QID_QUEUE(qid));
return rc;
diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c
index f54bef4..97d4bac 100644
--- a/drivers/s390/crypto/zcrypt_msgtype6.c
+++ b/drivers/s390/crypto/zcrypt_msgtype6.c
@@ -1084,6 +1084,13 @@ static long zcrypt_msgtype6_modexpo_crt(struct zcrypt_queue *zq,
return rc;
}
+/**
+ * Fetch function code from cprb.
+ * Extracting the fc requires to copy the cprb from userspace.
+ * So this function allocates memory and needs an ap_msg prepared
+ * by the caller with ap_init_message(). Also the caller has to
+ * make sure ap_release_message() is always called even on failure.
+ */
unsigned int get_cprb_fc(struct ica_xcRB *xcRB,
struct ap_message *ap_msg,
unsigned int *func_code, unsigned short **dom)
@@ -1091,9 +1098,7 @@ unsigned int get_cprb_fc(struct ica_xcRB *xcRB,
struct response_type resp_type = {
.type = PCIXCC_RESPONSE_TYPE_XCRB,
};
- int rc;
- ap_init_message(ap_msg);
ap_msg->message = kmalloc(MSGTYPE06_MAX_MSG_SIZE, GFP_KERNEL);
if (!ap_msg->message)
return -ENOMEM;
@@ -1101,17 +1106,10 @@ unsigned int get_cprb_fc(struct ica_xcRB *xcRB,
ap_msg->psmid = (((unsigned long long) current->pid) << 32) +
atomic_inc_return(&zcrypt_step);
ap_msg->private = kmalloc(sizeof(resp_type), GFP_KERNEL);
- if (!ap_msg->private) {
- kzfree(ap_msg->message);
+ if (!ap_msg->private)
return -ENOMEM;
- }
memcpy(ap_msg->private, &resp_type, sizeof(resp_type));
- rc = XCRB_msg_to_type6CPRB_msgX(ap_msg, xcRB, func_code, dom);
- if (rc) {
- kzfree(ap_msg->message);
- kzfree(ap_msg->private);
- }
- return rc;
+ return XCRB_msg_to_type6CPRB_msgX(ap_msg, xcRB, func_code, dom);
}
/**
@@ -1139,11 +1137,16 @@ static long zcrypt_msgtype6_send_cprb(struct zcrypt_queue *zq,
/* Signal pending. */
ap_cancel_message(zq->queue, ap_msg);
- kzfree(ap_msg->message);
- kzfree(ap_msg->private);
return rc;
}
+/**
+ * Fetch function code from ep11 cprb.
+ * Extracting the fc requires to copy the ep11 cprb from userspace.
+ * So this function allocates memory and needs an ap_msg prepared
+ * by the caller with ap_init_message(). Also the caller has to
+ * make sure ap_release_message() is always called even on failure.
+ */
unsigned int get_ep11cprb_fc(struct ep11_urb *xcrb,
struct ap_message *ap_msg,
unsigned int *func_code)
@@ -1151,9 +1154,7 @@ unsigned int get_ep11cprb_fc(struct ep11_urb *xcrb,
struct response_type resp_type = {
.type = PCIXCC_RESPONSE_TYPE_EP11,
};
- int rc;
- ap_init_message(ap_msg);
ap_msg->message = kmalloc(MSGTYPE06_MAX_MSG_SIZE, GFP_KERNEL);
if (!ap_msg->message)
return -ENOMEM;
@@ -1161,17 +1162,10 @@ unsigned int get_ep11cprb_fc(struct ep11_urb *xcrb,
ap_msg->psmid = (((unsigned long long) current->pid) << 32) +
atomic_inc_return(&zcrypt_step);
ap_msg->private = kmalloc(sizeof(resp_type), GFP_KERNEL);
- if (!ap_msg->private) {
- kzfree(ap_msg->message);
+ if (!ap_msg->private)
return -ENOMEM;
- }
memcpy(ap_msg->private, &resp_type, sizeof(resp_type));
- rc = xcrb_msg_to_type6_ep11cprb_msgx(ap_msg, xcrb, func_code);
- if (rc) {
- kzfree(ap_msg->message);
- kzfree(ap_msg->private);
- }
- return rc;
+ return xcrb_msg_to_type6_ep11cprb_msgx(ap_msg, xcrb, func_code);
}
/**
@@ -1246,8 +1240,6 @@ static long zcrypt_msgtype6_send_ep11_cprb(struct zcrypt_queue *zq,
/* Signal pending. */
ap_cancel_message(zq->queue, ap_msg);
- kzfree(ap_msg->message);
- kzfree(ap_msg->private);
return rc;
}
@@ -1258,7 +1250,6 @@ unsigned int get_rng_fc(struct ap_message *ap_msg, int *func_code,
.type = PCIXCC_RESPONSE_TYPE_XCRB,
};
- ap_init_message(ap_msg);
ap_msg->message = kmalloc(MSGTYPE06_MAX_MSG_SIZE, GFP_KERNEL);
if (!ap_msg->message)
return -ENOMEM;
@@ -1266,10 +1257,8 @@ unsigned int get_rng_fc(struct ap_message *ap_msg, int *func_code,
ap_msg->psmid = (((unsigned long long) current->pid) << 32) +
atomic_inc_return(&zcrypt_step);
ap_msg->private = kmalloc(sizeof(resp_type), GFP_KERNEL);
- if (!ap_msg->private) {
- kzfree(ap_msg->message);
+ if (!ap_msg->private)
return -ENOMEM;
- }
memcpy(ap_msg->private, &resp_type, sizeof(resp_type));
rng_type6CPRB_msgX(ap_msg, ZCRYPT_RNG_BUFFER_SIZE, domain);
@@ -1313,8 +1302,6 @@ static long zcrypt_msgtype6_rng(struct zcrypt_queue *zq,
/* Signal pending. */
ap_cancel_message(zq->queue, ap_msg);
- kzfree(ap_msg->message);
- kzfree(ap_msg->private);
return rc;
}
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 4326715..78b98b3 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -557,7 +557,6 @@ enum qeth_prot_versions {
enum qeth_cmd_buffer_state {
BUF_STATE_FREE,
BUF_STATE_LOCKED,
- BUF_STATE_PROCESSED,
};
enum qeth_cq {
@@ -601,7 +600,6 @@ struct qeth_channel {
struct qeth_cmd_buffer iob[QETH_CMD_BUFFER_NO];
atomic_t irq_pending;
int io_buf_no;
- int buf_no;
};
/**
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 04fefa5..f5a0d89 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -10,6 +10,7 @@
#define KMSG_COMPONENT "qeth"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+#include <linux/compat.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/string.h>
@@ -32,7 +33,6 @@
#include <asm/chpid.h>
#include <asm/io.h>
#include <asm/sysinfo.h>
-#include <asm/compat.h>
#include <asm/diag.h>
#include <asm/cio.h>
#include <asm/ccwdev.h>
@@ -706,7 +706,6 @@ void qeth_clear_ipacmd_list(struct qeth_card *card)
qeth_put_reply(reply);
}
spin_unlock_irqrestore(&card->lock, flags);
- atomic_set(&card->write.irq_pending, 0);
}
EXPORT_SYMBOL_GPL(qeth_clear_ipacmd_list);
@@ -818,7 +817,6 @@ void qeth_clear_cmd_buffers(struct qeth_channel *channel)
for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++)
qeth_release_buffer(channel, &channel->iob[cnt]);
- channel->buf_no = 0;
channel->io_buf_no = 0;
}
EXPORT_SYMBOL_GPL(qeth_clear_cmd_buffers);
@@ -924,7 +922,6 @@ static int qeth_setup_channel(struct qeth_channel *channel)
kfree(channel->iob[cnt].data);
return -ENOMEM;
}
- channel->buf_no = 0;
channel->io_buf_no = 0;
atomic_set(&channel->irq_pending, 0);
spin_lock_init(&channel->iob_lock);
@@ -1100,16 +1097,9 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
{
int rc;
int cstat, dstat;
- struct qeth_cmd_buffer *buffer;
+ struct qeth_cmd_buffer *iob = NULL;
struct qeth_channel *channel;
struct qeth_card *card;
- struct qeth_cmd_buffer *iob;
- __u8 index;
-
- if (__qeth_check_irb_error(cdev, intparm, irb))
- return;
- cstat = irb->scsw.cmd.cstat;
- dstat = irb->scsw.cmd.dstat;
card = CARD_FROM_CDEV(cdev);
if (!card)
@@ -1127,6 +1117,19 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
channel = &card->data;
QETH_CARD_TEXT(card, 5, "data");
}
+
+ if (qeth_intparm_is_iob(intparm))
+ iob = (struct qeth_cmd_buffer *) __va((addr_t)intparm);
+
+ if (__qeth_check_irb_error(cdev, intparm, irb)) {
+ /* IO was terminated, free its resources. */
+ if (iob)
+ qeth_release_buffer(iob->channel, iob);
+ atomic_set(&channel->irq_pending, 0);
+ wake_up(&card->wait_q);
+ return;
+ }
+
atomic_set(&channel->irq_pending, 0);
if (irb->scsw.cmd.fctl & (SCSW_FCTL_CLEAR_FUNC))
@@ -1150,6 +1153,10 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
/* we don't have to handle this further */
intparm = 0;
}
+
+ cstat = irb->scsw.cmd.cstat;
+ dstat = irb->scsw.cmd.dstat;
+
if ((dstat & DEV_STAT_UNIT_EXCEP) ||
(dstat & DEV_STAT_UNIT_CHECK) ||
(cstat)) {
@@ -1182,25 +1189,15 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
channel->state = CH_STATE_RCD_DONE;
goto out;
}
- if (intparm) {
- buffer = (struct qeth_cmd_buffer *) __va((addr_t)intparm);
- buffer->state = BUF_STATE_PROCESSED;
- }
if (channel == &card->data)
return;
if (channel == &card->read &&
channel->state == CH_STATE_UP)
__qeth_issue_next_read(card);
- iob = channel->iob;
- index = channel->buf_no;
- while (iob[index].state == BUF_STATE_PROCESSED) {
- if (iob[index].callback != NULL)
- iob[index].callback(channel, iob + index);
+ if (iob && iob->callback)
+ iob->callback(iob->channel, iob);
- index = (index + 1) % QETH_CMD_BUFFER_NO;
- }
- channel->buf_no = index;
out:
wake_up(&card->wait_q);
return;
@@ -1870,8 +1867,8 @@ static int qeth_idx_activate_get_answer(struct qeth_channel *channel,
atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0);
QETH_DBF_TEXT(SETUP, 6, "noirqpnd");
spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
- rc = ccw_device_start(channel->ccwdev,
- &channel->ccw, (addr_t) iob, 0, 0);
+ rc = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
+ (addr_t) iob, 0, 0, QETH_TIMEOUT);
spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
if (rc) {
@@ -1888,7 +1885,6 @@ static int qeth_idx_activate_get_answer(struct qeth_channel *channel,
if (channel->state != CH_STATE_UP) {
rc = -ETIME;
QETH_DBF_TEXT_(SETUP, 2, "3err%d", rc);
- qeth_clear_cmd_buffers(channel);
} else
rc = 0;
return rc;
@@ -1942,8 +1938,8 @@ static int qeth_idx_activate_channel(struct qeth_channel *channel,
atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0);
QETH_DBF_TEXT(SETUP, 6, "noirqpnd");
spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
- rc = ccw_device_start(channel->ccwdev,
- &channel->ccw, (addr_t) iob, 0, 0);
+ rc = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
+ (addr_t) iob, 0, 0, QETH_TIMEOUT);
spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
if (rc) {
@@ -1964,7 +1960,6 @@ static int qeth_idx_activate_channel(struct qeth_channel *channel,
QETH_DBF_MESSAGE(2, "%s IDX activate timed out\n",
dev_name(&channel->ccwdev->dev));
QETH_DBF_TEXT_(SETUP, 2, "2err%d", -ETIME);
- qeth_clear_cmd_buffers(channel);
return -ETIME;
}
return qeth_idx_activate_get_answer(channel, idx_reply_cb);
@@ -2166,8 +2161,8 @@ int qeth_send_control_data(struct qeth_card *card, int len,
QETH_CARD_TEXT(card, 6, "noirqpnd");
spin_lock_irqsave(get_ccwdev_lock(card->write.ccwdev), flags);
- rc = ccw_device_start(card->write.ccwdev, &card->write.ccw,
- (addr_t) iob, 0, 0);
+ rc = ccw_device_start_timeout(CARD_WDEV(card), &card->write.ccw,
+ (addr_t) iob, 0, 0, event_timeout);
spin_unlock_irqrestore(get_ccwdev_lock(card->write.ccwdev), flags);
if (rc) {
QETH_DBF_MESSAGE(2, "%s qeth_send_control_data: "
@@ -2199,8 +2194,6 @@ int qeth_send_control_data(struct qeth_card *card, int len,
}
}
- if (reply->rc == -EIO)
- goto error;
rc = reply->rc;
qeth_put_reply(reply);
return rc;
@@ -2211,10 +2204,6 @@ int qeth_send_control_data(struct qeth_card *card, int len,
list_del_init(&reply->list);
spin_unlock_irqrestore(&reply->card->lock, flags);
atomic_inc(&reply->received);
-error:
- atomic_set(&card->write.irq_pending, 0);
- qeth_release_buffer(iob->channel, iob);
- card->write.buf_no = (card->write.buf_no + 1) % QETH_CMD_BUFFER_NO;
rc = reply->rc;
qeth_put_reply(reply);
return rc;
@@ -3033,28 +3022,23 @@ static int qeth_send_startlan(struct qeth_card *card)
return rc;
}
-static int qeth_default_setadapterparms_cb(struct qeth_card *card,
- struct qeth_reply *reply, unsigned long data)
+static int qeth_setadpparms_inspect_rc(struct qeth_ipa_cmd *cmd)
{
- struct qeth_ipa_cmd *cmd;
-
- QETH_CARD_TEXT(card, 4, "defadpcb");
-
- cmd = (struct qeth_ipa_cmd *) data;
- if (cmd->hdr.return_code == 0)
+ if (!cmd->hdr.return_code)
cmd->hdr.return_code =
cmd->data.setadapterparms.hdr.return_code;
- return 0;
+ return cmd->hdr.return_code;
}
static int qeth_query_setadapterparms_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
QETH_CARD_TEXT(card, 3, "quyadpcb");
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
- cmd = (struct qeth_ipa_cmd *) data;
if (cmd->data.setadapterparms.data.query_cmds_supp.lan_type & 0x7f) {
card->info.link_type =
cmd->data.setadapterparms.data.query_cmds_supp.lan_type;
@@ -3062,7 +3046,7 @@ static int qeth_query_setadapterparms_cb(struct qeth_card *card,
}
card->options.adp.supported_funcs =
cmd->data.setadapterparms.data.query_cmds_supp.supported_cmds;
- return qeth_default_setadapterparms_cb(card, reply, (unsigned long)cmd);
+ return 0;
}
static struct qeth_cmd_buffer *qeth_get_adapter_cmd(struct qeth_card *card,
@@ -3154,22 +3138,20 @@ EXPORT_SYMBOL_GPL(qeth_query_ipassists);
static int qeth_query_switch_attributes_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
- struct qeth_switch_info *sw_info;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
struct qeth_query_switch_attributes *attrs;
+ struct qeth_switch_info *sw_info;
QETH_CARD_TEXT(card, 2, "qswiatcb");
- cmd = (struct qeth_ipa_cmd *) data;
- sw_info = (struct qeth_switch_info *)reply->param;
- if (cmd->data.setadapterparms.hdr.return_code == 0) {
- attrs = &cmd->data.setadapterparms.data.query_switch_attributes;
- sw_info->capabilities = attrs->capabilities;
- sw_info->settings = attrs->settings;
- QETH_CARD_TEXT_(card, 2, "%04x%04x", sw_info->capabilities,
- sw_info->settings);
- }
- qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
+ sw_info = (struct qeth_switch_info *)reply->param;
+ attrs = &cmd->data.setadapterparms.data.query_switch_attributes;
+ sw_info->capabilities = attrs->capabilities;
+ sw_info->settings = attrs->settings;
+ QETH_CARD_TEXT_(card, 2, "%04x%04x", sw_info->capabilities,
+ sw_info->settings);
return 0;
}
@@ -4207,16 +4189,13 @@ EXPORT_SYMBOL_GPL(qeth_do_send_packet);
static int qeth_setadp_promisc_mode_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
struct qeth_ipacmd_setadpparms *setparms;
QETH_CARD_TEXT(card, 4, "prmadpcb");
- cmd = (struct qeth_ipa_cmd *) data;
setparms = &(cmd->data.setadapterparms);
-
- qeth_default_setadapterparms_cb(card, reply, (unsigned long)cmd);
- if (cmd->hdr.return_code) {
+ if (qeth_setadpparms_inspect_rc(cmd)) {
QETH_CARD_TEXT_(card, 4, "prmrc%x", cmd->hdr.return_code);
setparms->data.mode = SET_PROMISC_MODE_OFF;
}
@@ -4286,18 +4265,18 @@ EXPORT_SYMBOL_GPL(qeth_get_stats);
static int qeth_setadpparms_change_macaddr_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
QETH_CARD_TEXT(card, 4, "chgmaccb");
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
- cmd = (struct qeth_ipa_cmd *) data;
if (!card->options.layer2 ||
!(card->info.mac_bits & QETH_LAYER2_MAC_READ)) {
ether_addr_copy(card->dev->dev_addr,
cmd->data.setadapterparms.data.change_addr.addr);
card->info.mac_bits |= QETH_LAYER2_MAC_READ;
}
- qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
return 0;
}
@@ -4328,13 +4307,15 @@ EXPORT_SYMBOL_GPL(qeth_setadpparms_change_macaddr);
static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
struct qeth_set_access_ctrl *access_ctrl_req;
int fallback = *(int *)reply->param;
QETH_CARD_TEXT(card, 4, "setaccb");
+ if (cmd->hdr.return_code)
+ return 0;
+ qeth_setadpparms_inspect_rc(cmd);
- cmd = (struct qeth_ipa_cmd *) data;
access_ctrl_req = &cmd->data.setadapterparms.data.set_access_ctrl;
QETH_DBF_TEXT_(SETUP, 2, "setaccb");
QETH_DBF_TEXT_(SETUP, 2, "%s", card->gdev->dev.kobj.name);
@@ -4407,7 +4388,6 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card,
card->options.isolation = card->options.prev_isolation;
break;
}
- qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
return 0;
}
@@ -4695,14 +4675,15 @@ static int qeth_snmp_command(struct qeth_card *card, char __user *udata)
static int qeth_setadpparms_query_oat_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *)data;
struct qeth_qoat_priv *priv;
char *resdata;
int resdatalen;
QETH_CARD_TEXT(card, 3, "qoatcb");
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
- cmd = (struct qeth_ipa_cmd *)data;
priv = (struct qeth_qoat_priv *)reply->param;
resdatalen = cmd->data.setadapterparms.hdr.cmdlength;
resdata = (char *)data + 28;
@@ -4796,21 +4777,18 @@ static int qeth_query_oat_command(struct qeth_card *card, char __user *udata)
static int qeth_query_card_info_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct carrier_info *carrier_info = (struct carrier_info *)reply->param;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *)data;
struct qeth_query_card_info *card_info;
- struct carrier_info *carrier_info;
QETH_CARD_TEXT(card, 2, "qcrdincb");
- carrier_info = (struct carrier_info *)reply->param;
- cmd = (struct qeth_ipa_cmd *)data;
- card_info = &cmd->data.setadapterparms.data.card_info;
- if (cmd->data.setadapterparms.hdr.return_code == 0) {
- carrier_info->card_type = card_info->card_type;
- carrier_info->port_mode = card_info->port_mode;
- carrier_info->port_speed = card_info->port_speed;
- }
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
- qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
+ card_info = &cmd->data.setadapterparms.data.card_info;
+ carrier_info->card_type = card_info->card_type;
+ carrier_info->port_mode = card_info->port_mode;
+ carrier_info->port_speed = card_info->port_speed;
return 0;
}
@@ -4857,7 +4835,7 @@ int qeth_vm_request_mac(struct qeth_card *card)
goto out;
}
- ccw_device_get_id(CARD_DDEV(card), &id);
+ ccw_device_get_id(CARD_RDEV(card), &id);
request->resp_buf_len = sizeof(*response);
request->resp_version = DIAG26C_VERSION2;
request->op_code = DIAG26C_GET_MAC;
@@ -6563,10 +6541,14 @@ static int __init qeth_core_init(void)
mutex_init(&qeth_mod_mutex);
qeth_wq = create_singlethread_workqueue("qeth_wq");
+ if (!qeth_wq) {
+ rc = -ENOMEM;
+ goto out_err;
+ }
rc = qeth_register_dbf_views();
if (rc)
- goto out_err;
+ goto dbf_err;
qeth_core_root_dev = root_device_register("qeth");
rc = PTR_ERR_OR_ZERO(qeth_core_root_dev);
if (rc)
@@ -6603,6 +6585,8 @@ static int __init qeth_core_init(void)
root_device_unregister(qeth_core_root_dev);
register_err:
qeth_unregister_dbf_views();
+dbf_err:
+ destroy_workqueue(qeth_wq);
out_err:
pr_err("Initializing the qeth device driver failed\n");
return rc;
diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h
index 619f897..f4d1ec0b 100644
--- a/drivers/s390/net/qeth_core_mpc.h
+++ b/drivers/s390/net/qeth_core_mpc.h
@@ -35,6 +35,18 @@ extern unsigned char IPA_PDU_HEADER[];
#define QETH_HALT_CHANNEL_PARM -11
#define QETH_RCD_PARM -12
+static inline bool qeth_intparm_is_iob(unsigned long intparm)
+{
+ switch (intparm) {
+ case QETH_CLEAR_CHANNEL_PARM:
+ case QETH_HALT_CHANNEL_PARM:
+ case QETH_RCD_PARM:
+ case 0:
+ return false;
+ }
+ return true;
+}
+
/*****************************************************************************/
/* IP Assist related definitions */
/*****************************************************************************/
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 50a3138..b8079f2 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -21,7 +21,6 @@
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/hashtable.h>
-#include <linux/string.h>
#include <asm/setup.h>
#include "qeth_core.h"
#include "qeth_l2.h"
@@ -122,13 +121,10 @@ static int qeth_l2_send_setmac(struct qeth_card *card, __u8 *mac)
QETH_CARD_TEXT(card, 2, "L2Setmac");
rc = qeth_l2_send_setdelmac(card, mac, IPA_CMD_SETVMAC);
if (rc == 0) {
- card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
- ether_addr_copy(card->dev->dev_addr, mac);
dev_info(&card->gdev->dev,
- "MAC address %pM successfully registered on device %s\n",
- card->dev->dev_addr, card->dev->name);
+ "MAC address %pM successfully registered on device %s\n",
+ mac, card->dev->name);
} else {
- card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED;
switch (rc) {
case -EEXIST:
dev_warn(&card->gdev->dev,
@@ -143,19 +139,6 @@ static int qeth_l2_send_setmac(struct qeth_card *card, __u8 *mac)
return rc;
}
-static int qeth_l2_send_delmac(struct qeth_card *card, __u8 *mac)
-{
- int rc;
-
- QETH_CARD_TEXT(card, 2, "L2Delmac");
- if (!(card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED))
- return 0;
- rc = qeth_l2_send_setdelmac(card, mac, IPA_CMD_DELVMAC);
- if (rc == 0)
- card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED;
- return rc;
-}
-
static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac)
{
enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ?
@@ -520,6 +503,7 @@ static int qeth_l2_set_mac_address(struct net_device *dev, void *p)
{
struct sockaddr *addr = p;
struct qeth_card *card = dev->ml_priv;
+ u8 old_addr[ETH_ALEN];
int rc = 0;
QETH_CARD_TEXT(card, 3, "setmac");
@@ -531,14 +515,35 @@ static int qeth_l2_set_mac_address(struct net_device *dev, void *p)
return -EOPNOTSUPP;
}
QETH_CARD_HEX(card, 3, addr->sa_data, ETH_ALEN);
+ if (!is_valid_ether_addr(addr->sa_data))
+ return -EADDRNOTAVAIL;
+
if (qeth_wait_for_threads(card, QETH_RECOVER_THREAD)) {
QETH_CARD_TEXT(card, 3, "setmcREC");
return -ERESTARTSYS;
}
- rc = qeth_l2_send_delmac(card, &card->dev->dev_addr[0]);
- if (!rc || (rc == -ENOENT))
- rc = qeth_l2_send_setmac(card, addr->sa_data);
- return rc ? -EINVAL : 0;
+
+ if (!qeth_card_hw_is_reachable(card)) {
+ ether_addr_copy(dev->dev_addr, addr->sa_data);
+ return 0;
+ }
+
+ /* don't register the same address twice */
+ if (ether_addr_equal_64bits(dev->dev_addr, addr->sa_data) &&
+ (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED))
+ return 0;
+
+ /* add the new address, switch over, drop the old */
+ rc = qeth_l2_send_setmac(card, addr->sa_data);
+ if (rc)
+ return rc;
+ ether_addr_copy(old_addr, dev->dev_addr);
+ ether_addr_copy(dev->dev_addr, addr->sa_data);
+
+ if (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED)
+ qeth_l2_remove_mac(card, old_addr);
+ card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
+ return 0;
}
static void qeth_promisc_to_bridge(struct qeth_card *card)
@@ -1068,8 +1073,9 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode)
goto out_remove;
}
- if (card->info.type != QETH_CARD_TYPE_OSN)
- qeth_l2_send_setmac(card, &card->dev->dev_addr[0]);
+ if (card->info.type != QETH_CARD_TYPE_OSN &&
+ !qeth_l2_send_setmac(card, card->dev->dev_addr))
+ card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
if (qeth_is_diagass_supported(card, QETH_DIAGS_CMD_TRAP)) {
if (card->info.hwtrap &&
@@ -1339,8 +1345,8 @@ static int qeth_osn_send_control_data(struct qeth_card *card, int len,
qeth_prepare_control_data(card, len, iob);
QETH_CARD_TEXT(card, 6, "osnoirqp");
spin_lock_irqsave(get_ccwdev_lock(card->write.ccwdev), flags);
- rc = ccw_device_start(card->write.ccwdev, &card->write.ccw,
- (addr_t) iob, 0, 0);
+ rc = ccw_device_start_timeout(CARD_WDEV(card), &card->write.ccw,
+ (addr_t) iob, 0, 0, QETH_IPA_TIMEOUT);
spin_unlock_irqrestore(get_ccwdev_lock(card->write.ccwdev), flags);
if (rc) {
QETH_DBF_MESSAGE(2, "qeth_osn_send_control_data: "
diff --git a/drivers/s390/net/smsgiucv.c b/drivers/s390/net/smsgiucv.c
index 3b0c8b8..066b5c3 100644
--- a/drivers/s390/net/smsgiucv.c
+++ b/drivers/s390/net/smsgiucv.c
@@ -176,7 +176,7 @@ static struct device_driver smsg_driver = {
static void __exit smsg_exit(void)
{
- cpcmd("SET SMSG IUCV", NULL, 0, NULL);
+ cpcmd("SET SMSG OFF", NULL, 0, NULL);
device_unregister(smsg_dev);
iucv_unregister(&smsg_handler, 1);
driver_unregister(&smsg_driver);
diff --git a/drivers/s390/scsi/zfcp_dbf.c b/drivers/s390/scsi/zfcp_dbf.c
index a8b8310..18c4f93 100644
--- a/drivers/s390/scsi/zfcp_dbf.c
+++ b/drivers/s390/scsi/zfcp_dbf.c
@@ -4,7 +4,7 @@
*
* Debug traces for zfcp.
*
- * Copyright IBM Corp. 2002, 2017
+ * Copyright IBM Corp. 2002, 2018
*/
#define KMSG_COMPONENT "zfcp"
@@ -308,6 +308,27 @@ void zfcp_dbf_rec_trig(char *tag, struct zfcp_adapter *adapter,
spin_unlock_irqrestore(&dbf->rec_lock, flags);
}
+/**
+ * zfcp_dbf_rec_trig_lock - trace event related to triggered recovery with lock
+ * @tag: identifier for event
+ * @adapter: adapter on which the erp_action should run
+ * @port: remote port involved in the erp_action
+ * @sdev: scsi device involved in the erp_action
+ * @want: wanted erp_action
+ * @need: required erp_action
+ *
+ * The adapter->erp_lock must not be held.
+ */
+void zfcp_dbf_rec_trig_lock(char *tag, struct zfcp_adapter *adapter,
+ struct zfcp_port *port, struct scsi_device *sdev,
+ u8 want, u8 need)
+{
+ unsigned long flags;
+
+ read_lock_irqsave(&adapter->erp_lock, flags);
+ zfcp_dbf_rec_trig(tag, adapter, port, sdev, want, need);
+ read_unlock_irqrestore(&adapter->erp_lock, flags);
+}
/**
* zfcp_dbf_rec_run_lvl - trace event related to running recovery
diff --git a/drivers/s390/scsi/zfcp_ext.h b/drivers/s390/scsi/zfcp_ext.h
index bf8ea4d..e5eed8a 100644
--- a/drivers/s390/scsi/zfcp_ext.h
+++ b/drivers/s390/scsi/zfcp_ext.h
@@ -4,7 +4,7 @@
*
* External function declarations.
*
- * Copyright IBM Corp. 2002, 2016
+ * Copyright IBM Corp. 2002, 2018
*/
#ifndef ZFCP_EXT_H
@@ -35,6 +35,9 @@ extern int zfcp_dbf_adapter_register(struct zfcp_adapter *);
extern void zfcp_dbf_adapter_unregister(struct zfcp_adapter *);
extern void zfcp_dbf_rec_trig(char *, struct zfcp_adapter *,
struct zfcp_port *, struct scsi_device *, u8, u8);
+extern void zfcp_dbf_rec_trig_lock(char *tag, struct zfcp_adapter *adapter,
+ struct zfcp_port *port,
+ struct scsi_device *sdev, u8 want, u8 need);
extern void zfcp_dbf_rec_run(char *, struct zfcp_erp_action *);
extern void zfcp_dbf_rec_run_lvl(int level, char *tag,
struct zfcp_erp_action *erp);
diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c
index 4d2ba56..22f9562 100644
--- a/drivers/s390/scsi/zfcp_scsi.c
+++ b/drivers/s390/scsi/zfcp_scsi.c
@@ -4,7 +4,7 @@
*
* Interface to Linux SCSI midlayer.
*
- * Copyright IBM Corp. 2002, 2017
+ * Copyright IBM Corp. 2002, 2018
*/
#define KMSG_COMPONENT "zfcp"
@@ -618,9 +618,9 @@ static void zfcp_scsi_rport_register(struct zfcp_port *port)
ids.port_id = port->d_id;
ids.roles = FC_RPORT_ROLE_FCP_TARGET;
- zfcp_dbf_rec_trig("scpaddy", port->adapter, port, NULL,
- ZFCP_PSEUDO_ERP_ACTION_RPORT_ADD,
- ZFCP_PSEUDO_ERP_ACTION_RPORT_ADD);
+ zfcp_dbf_rec_trig_lock("scpaddy", port->adapter, port, NULL,
+ ZFCP_PSEUDO_ERP_ACTION_RPORT_ADD,
+ ZFCP_PSEUDO_ERP_ACTION_RPORT_ADD);
rport = fc_remote_port_add(port->adapter->scsi_host, 0, &ids);
if (!rport) {
dev_err(&port->adapter->ccw_device->dev,
@@ -642,9 +642,9 @@ static void zfcp_scsi_rport_block(struct zfcp_port *port)
struct fc_rport *rport = port->rport;
if (rport) {
- zfcp_dbf_rec_trig("scpdely", port->adapter, port, NULL,
- ZFCP_PSEUDO_ERP_ACTION_RPORT_DEL,
- ZFCP_PSEUDO_ERP_ACTION_RPORT_DEL);
+ zfcp_dbf_rec_trig_lock("scpdely", port->adapter, port, NULL,
+ ZFCP_PSEUDO_ERP_ACTION_RPORT_DEL,
+ ZFCP_PSEUDO_ERP_ACTION_RPORT_DEL);
fc_remote_port_delete(rport);
port->rport = NULL;
}
diff --git a/drivers/sbus/char/Kconfig b/drivers/sbus/char/Kconfig
index bf3c5f7..89edd13 100644
--- a/drivers/sbus/char/Kconfig
+++ b/drivers/sbus/char/Kconfig
@@ -28,13 +28,6 @@
events, and can also notice the attachment/detachment of external
monitors and mice.
-config SUN_JSFLASH
- tristate "JavaStation OS Flash SIMM"
- depends on SPARC32
- help
- If you say Y here, you will be able to boot from your JavaStation's
- Flash memory.
-
config BBC_I2C
tristate "UltraSPARC-III bootbus i2c controller driver"
depends on PCI && SPARC64
diff --git a/drivers/sbus/char/Makefile b/drivers/sbus/char/Makefile
index 8c48ed9..44347c9 100644
--- a/drivers/sbus/char/Makefile
+++ b/drivers/sbus/char/Makefile
@@ -15,6 +15,5 @@
obj-$(CONFIG_OBP_FLASH) += flash.o
obj-$(CONFIG_SUN_OPENPROMIO) += openprom.o
obj-$(CONFIG_TADPOLE_TS102_UCTRL) += uctrl.o
-obj-$(CONFIG_SUN_JSFLASH) += jsflash.o
obj-$(CONFIG_BBC_I2C) += bbc.o
obj-$(CONFIG_ORACLE_DAX) += oradax.o
diff --git a/drivers/sbus/char/jsflash.c b/drivers/sbus/char/jsflash.c
deleted file mode 100644
index 14f377a..0000000
--- a/drivers/sbus/char/jsflash.c
+++ /dev/null
@@ -1,658 +0,0 @@
-/*
- * drivers/sbus/char/jsflash.c
- *
- * Copyright (C) 1991, 1992 Linus Torvalds (drivers/char/mem.c)
- * Copyright (C) 1997 Eddie C. Dost (drivers/sbus/char/flash.c)
- * Copyright (C) 1997-2000 Pavel Machek <pavel@ucw.cz> (drivers/block/nbd.c)
- * Copyright (C) 1999-2000 Pete Zaitcev
- *
- * This driver is used to program OS into a Flash SIMM on
- * Krups and Espresso platforms.
- *
- * TODO: do not allow erase/programming if file systems are mounted.
- * TODO: Erase/program both banks of a 8MB SIMM.
- *
- * It is anticipated that programming an OS Flash will be a routine
- * procedure. In the same time it is exceedingly dangerous because
- * a user can program its OBP flash with OS image and effectively
- * kill the machine.
- *
- * This driver uses an interface different from Eddie's flash.c
- * as a silly safeguard.
- *
- * XXX The flash.c manipulates page caching characteristics in a certain
- * dubious way; also it assumes that remap_pfn_range() can remap
- * PCI bus locations, which may be false. ioremap() must be used
- * instead. We should discuss this.
- */
-
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/types.h>
-#include <linux/errno.h>
-#include <linux/miscdevice.h>
-#include <linux/fcntl.h>
-#include <linux/poll.h>
-#include <linux/init.h>
-#include <linux/string.h>
-#include <linux/genhd.h>
-#include <linux/blkdev.h>
-#include <linux/uaccess.h>
-#include <asm/pgtable.h>
-#include <asm/io.h>
-#include <asm/pcic.h>
-#include <asm/oplib.h>
-
-#include <asm/jsflash.h> /* ioctl arguments. <linux/> ?? */
-#define JSFIDSZ (sizeof(struct jsflash_ident_arg))
-#define JSFPRGSZ (sizeof(struct jsflash_program_arg))
-
-/*
- * Our device numbers have no business in system headers.
- * The only thing a user knows is the device name /dev/jsflash.
- *
- * Block devices are laid out like this:
- * minor+0 - Bootstrap, for 8MB SIMM 0x20400000[0x800000]
- * minor+1 - Filesystem to mount, normally 0x20400400[0x7ffc00]
- * minor+2 - Whole flash area for any case... 0x20000000[0x01000000]
- * Total 3 minors per flash device.
- *
- * It is easier to have static size vectors, so we define
- * a total minor range JSF_MAX, which must cover all minors.
- */
-/* character device */
-#define JSF_MINOR 178 /* 178 is registered with hpa */
-/* block device */
-#define JSF_MAX 3 /* 3 minors wasted total so far. */
-#define JSF_NPART 3 /* 3 minors per flash device */
-#define JSF_PART_BITS 2 /* 2 bits of minors to cover JSF_NPART */
-#define JSF_PART_MASK 0x3 /* 2 bits mask */
-
-static DEFINE_MUTEX(jsf_mutex);
-
-/*
- * Access functions.
- * We could ioremap(), but it's easier this way.
- */
-static unsigned int jsf_inl(unsigned long addr)
-{
- unsigned long retval;
-
- __asm__ __volatile__("lda [%1] %2, %0\n\t" :
- "=r" (retval) :
- "r" (addr), "i" (ASI_M_BYPASS));
- return retval;
-}
-
-static void jsf_outl(unsigned long addr, __u32 data)
-{
-
- __asm__ __volatile__("sta %0, [%1] %2\n\t" : :
- "r" (data), "r" (addr), "i" (ASI_M_BYPASS) :
- "memory");
-}
-
-/*
- * soft carrier
- */
-
-struct jsfd_part {
- unsigned long dbase;
- unsigned long dsize;
-};
-
-struct jsflash {
- unsigned long base;
- unsigned long size;
- unsigned long busy; /* In use? */
- struct jsflash_ident_arg id;
- /* int mbase; */ /* Minor base, typically zero */
- struct jsfd_part dv[JSF_NPART];
-};
-
-/*
- * We do not map normal memory or obio as a safety precaution.
- * But offsets are real, for ease of userland programming.
- */
-#define JSF_BASE_TOP 0x30000000
-#define JSF_BASE_ALL 0x20000000
-
-#define JSF_BASE_JK 0x20400000
-
-/*
- */
-static struct gendisk *jsfd_disk[JSF_MAX];
-
-/*
- * Let's pretend we may have several of these...
- */
-static struct jsflash jsf0;
-
-/*
- * Wait for AMD to finish its embedded algorithm.
- * We use the Toggle bit DQ6 (0x40) because it does not
- * depend on the data value as /DATA bit DQ7 does.
- *
- * XXX Do we need any timeout here? So far it never hanged, beware broken hw.
- */
-static void jsf_wait(unsigned long p) {
- unsigned int x1, x2;
-
- for (;;) {
- x1 = jsf_inl(p);
- x2 = jsf_inl(p);
- if ((x1 & 0x40404040) == (x2 & 0x40404040)) return;
- }
-}
-
-/*
- * Programming will only work if Flash is clean,
- * we leave it to the programmer application.
- *
- * AMD must be programmed one byte at a time;
- * thus, Simple Tech SIMM must be written 4 bytes at a time.
- *
- * Write waits for the chip to become ready after the write
- * was finished. This is done so that application would read
- * consistent data after the write is done.
- */
-static void jsf_write4(unsigned long fa, u32 data) {
-
- jsf_outl(fa, 0xAAAAAAAA); /* Unlock 1 Write 1 */
- jsf_outl(fa, 0x55555555); /* Unlock 1 Write 2 */
- jsf_outl(fa, 0xA0A0A0A0); /* Byte Program */
- jsf_outl(fa, data);
-
- jsf_wait(fa);
-}
-
-/*
- */
-static void jsfd_read(char *buf, unsigned long p, size_t togo) {
- union byte4 {
- char s[4];
- unsigned int n;
- } b;
-
- while (togo >= 4) {
- togo -= 4;
- b.n = jsf_inl(p);
- memcpy(buf, b.s, 4);
- p += 4;
- buf += 4;
- }
-}
-
-static int jsfd_queue;
-
-static struct request *jsfd_next_request(void)
-{
- struct request_queue *q;
- struct request *rq;
- int old_pos = jsfd_queue;
-
- do {
- q = jsfd_disk[jsfd_queue]->queue;
- if (++jsfd_queue == JSF_MAX)
- jsfd_queue = 0;
- if (q) {
- rq = blk_fetch_request(q);
- if (rq)
- return rq;
- }
- } while (jsfd_queue != old_pos);
-
- return NULL;
-}
-
-static void jsfd_request(void)
-{
- struct request *req;
-
- req = jsfd_next_request();
- while (req) {
- struct jsfd_part *jdp = req->rq_disk->private_data;
- unsigned long offset = blk_rq_pos(req) << 9;
- size_t len = blk_rq_cur_bytes(req);
- blk_status_t err = BLK_STS_IOERR;
-
- if ((offset + len) > jdp->dsize)
- goto end;
-
- if (rq_data_dir(req) != READ) {
- printk(KERN_ERR "jsfd: write\n");
- goto end;
- }
-
- if ((jdp->dbase & 0xff000000) != 0x20000000) {
- printk(KERN_ERR "jsfd: bad base %x\n", (int)jdp->dbase);
- goto end;
- }
-
- jsfd_read(bio_data(req->bio), jdp->dbase + offset, len);
- err = BLK_STS_OK;
- end:
- if (!__blk_end_request_cur(req, err))
- req = jsfd_next_request();
- }
-}
-
-static void jsfd_do_request(struct request_queue *q)
-{
- jsfd_request();
-}
-
-/*
- * The memory devices use the full 32/64 bits of the offset, and so we cannot
- * check against negative addresses: they are ok. The return value is weird,
- * though, in that case (0).
- *
- * also note that seeking relative to the "end of file" isn't supported:
- * it has no meaning, so it returns -EINVAL.
- */
-static loff_t jsf_lseek(struct file * file, loff_t offset, int orig)
-{
- loff_t ret;
-
- mutex_lock(&jsf_mutex);
- switch (orig) {
- case 0:
- file->f_pos = offset;
- ret = file->f_pos;
- break;
- case 1:
- file->f_pos += offset;
- ret = file->f_pos;
- break;
- default:
- ret = -EINVAL;
- }
- mutex_unlock(&jsf_mutex);
- return ret;
-}
-
-/*
- * OS SIMM Cannot be read in other size but a 32bits word.
- */
-static ssize_t jsf_read(struct file * file, char __user * buf,
- size_t togo, loff_t *ppos)
-{
- unsigned long p = *ppos;
- char __user *tmp = buf;
-
- union byte4 {
- char s[4];
- unsigned int n;
- } b;
-
- if (p < JSF_BASE_ALL || p >= JSF_BASE_TOP) {
- return 0;
- }
-
- if ((p + togo) < p /* wrap */
- || (p + togo) >= JSF_BASE_TOP) {
- togo = JSF_BASE_TOP - p;
- }
-
- if (p < JSF_BASE_ALL && togo != 0) {
-#if 0 /* __bzero XXX */
- size_t x = JSF_BASE_ALL - p;
- if (x > togo) x = togo;
- clear_user(tmp, x);
- tmp += x;
- p += x;
- togo -= x;
-#else
- /*
- * Implementation of clear_user() calls __bzero
- * without regard to modversions,
- * so we cannot build a module.
- */
- return 0;
-#endif
- }
-
- while (togo >= 4) {
- togo -= 4;
- b.n = jsf_inl(p);
- if (copy_to_user(tmp, b.s, 4))
- return -EFAULT;
- tmp += 4;
- p += 4;
- }
-
- /*
- * XXX Small togo may remain if 1 byte is ordered.
- * It would be nice if we did a word size read and unpacked it.
- */
-
- *ppos = p;
- return tmp-buf;
-}
-
-static ssize_t jsf_write(struct file * file, const char __user * buf,
- size_t count, loff_t *ppos)
-{
- return -ENOSPC;
-}
-
-/*
- */
-static int jsf_ioctl_erase(unsigned long arg)
-{
- unsigned long p;
-
- /* p = jsf0.base; hits wrong bank */
- p = 0x20400000;
-
- jsf_outl(p, 0xAAAAAAAA); /* Unlock 1 Write 1 */
- jsf_outl(p, 0x55555555); /* Unlock 1 Write 2 */
- jsf_outl(p, 0x80808080); /* Erase setup */
- jsf_outl(p, 0xAAAAAAAA); /* Unlock 2 Write 1 */
- jsf_outl(p, 0x55555555); /* Unlock 2 Write 2 */
- jsf_outl(p, 0x10101010); /* Chip erase */
-
-#if 0
- /*
- * This code is ok, except that counter based timeout
- * has no place in this world. Let's just drop timeouts...
- */
- {
- int i;
- __u32 x;
- for (i = 0; i < 1000000; i++) {
- x = jsf_inl(p);
- if ((x & 0x80808080) == 0x80808080) break;
- }
- if ((x & 0x80808080) != 0x80808080) {
- printk("jsf0: erase timeout with 0x%08x\n", x);
- } else {
- printk("jsf0: erase done with 0x%08x\n", x);
- }
- }
-#else
- jsf_wait(p);
-#endif
-
- return 0;
-}
-
-/*
- * Program a block of flash.
- * Very simple because we can do it byte by byte anyway.
- */
-static int jsf_ioctl_program(void __user *arg)
-{
- struct jsflash_program_arg abuf;
- char __user *uptr;
- unsigned long p;
- unsigned int togo;
- union {
- unsigned int n;
- char s[4];
- } b;
-
- if (copy_from_user(&abuf, arg, JSFPRGSZ))
- return -EFAULT;
- p = abuf.off;
- togo = abuf.size;
- if ((togo & 3) || (p & 3)) return -EINVAL;
-
- uptr = (char __user *) (unsigned long) abuf.data;
- while (togo != 0) {
- togo -= 4;
- if (copy_from_user(&b.s[0], uptr, 4))
- return -EFAULT;
- jsf_write4(p, b.n);
- p += 4;
- uptr += 4;
- }
-
- return 0;
-}
-
-static long jsf_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
-{
- mutex_lock(&jsf_mutex);
- int error = -ENOTTY;
- void __user *argp = (void __user *)arg;
-
- if (!capable(CAP_SYS_ADMIN)) {
- mutex_unlock(&jsf_mutex);
- return -EPERM;
- }
- switch (cmd) {
- case JSFLASH_IDENT:
- if (copy_to_user(argp, &jsf0.id, JSFIDSZ)) {
- mutex_unlock(&jsf_mutex);
- return -EFAULT;
- }
- break;
- case JSFLASH_ERASE:
- error = jsf_ioctl_erase(arg);
- break;
- case JSFLASH_PROGRAM:
- error = jsf_ioctl_program(argp);
- break;
- }
-
- mutex_unlock(&jsf_mutex);
- return error;
-}
-
-static int jsf_mmap(struct file * file, struct vm_area_struct * vma)
-{
- return -ENXIO;
-}
-
-static int jsf_open(struct inode * inode, struct file * filp)
-{
- mutex_lock(&jsf_mutex);
- if (jsf0.base == 0) {
- mutex_unlock(&jsf_mutex);
- return -ENXIO;
- }
- if (test_and_set_bit(0, (void *)&jsf0.busy) != 0) {
- mutex_unlock(&jsf_mutex);
- return -EBUSY;
- }
-
- mutex_unlock(&jsf_mutex);
- return 0; /* XXX What security? */
-}
-
-static int jsf_release(struct inode *inode, struct file *file)
-{
- jsf0.busy = 0;
- return 0;
-}
-
-static const struct file_operations jsf_fops = {
- .owner = THIS_MODULE,
- .llseek = jsf_lseek,
- .read = jsf_read,
- .write = jsf_write,
- .unlocked_ioctl = jsf_ioctl,
- .mmap = jsf_mmap,
- .open = jsf_open,
- .release = jsf_release,
-};
-
-static struct miscdevice jsf_dev = { JSF_MINOR, "jsflash", &jsf_fops };
-
-static const struct block_device_operations jsfd_fops = {
- .owner = THIS_MODULE,
-};
-
-static int jsflash_init(void)
-{
- int rc;
- struct jsflash *jsf;
- phandle node;
- char banner[128];
- struct linux_prom_registers reg0;
-
- node = prom_getchild(prom_root_node);
- node = prom_searchsiblings(node, "flash-memory");
- if (node != 0 && (s32)node != -1) {
- if (prom_getproperty(node, "reg",
- (char *)®0, sizeof(reg0)) == -1) {
- printk("jsflash: no \"reg\" property\n");
- return -ENXIO;
- }
- if (reg0.which_io != 0) {
- printk("jsflash: bus number nonzero: 0x%x:%x\n",
- reg0.which_io, reg0.phys_addr);
- return -ENXIO;
- }
- /*
- * Flash may be somewhere else, for instance on Ebus.
- * So, don't do the following check for IIep flash space.
- */
-#if 0
- if ((reg0.phys_addr >> 24) != 0x20) {
- printk("jsflash: suspicious address: 0x%x:%x\n",
- reg0.which_io, reg0.phys_addr);
- return -ENXIO;
- }
-#endif
- if ((int)reg0.reg_size <= 0) {
- printk("jsflash: bad size 0x%x\n", (int)reg0.reg_size);
- return -ENXIO;
- }
- } else {
- /* XXX Remove this code once PROLL ID12 got widespread */
- printk("jsflash: no /flash-memory node, use PROLL >= 12\n");
- prom_getproperty(prom_root_node, "banner-name", banner, 128);
- if (strcmp (banner, "JavaStation-NC") != 0 &&
- strcmp (banner, "JavaStation-E") != 0) {
- return -ENXIO;
- }
- reg0.which_io = 0;
- reg0.phys_addr = 0x20400000;
- reg0.reg_size = 0x00800000;
- }
-
- /* Let us be really paranoid for modifications to probing code. */
- if (sparc_cpu_model != sun4m) {
- /* We must be on sun4m because we use MMU Bypass ASI. */
- return -ENXIO;
- }
-
- if (jsf0.base == 0) {
- jsf = &jsf0;
-
- jsf->base = reg0.phys_addr;
- jsf->size = reg0.reg_size;
-
- /* XXX Redo the userland interface. */
- jsf->id.off = JSF_BASE_ALL;
- jsf->id.size = 0x01000000; /* 16M - all segments */
- strcpy(jsf->id.name, "Krups_all");
-
- jsf->dv[0].dbase = jsf->base;
- jsf->dv[0].dsize = jsf->size;
- jsf->dv[1].dbase = jsf->base + 1024;
- jsf->dv[1].dsize = jsf->size - 1024;
- jsf->dv[2].dbase = JSF_BASE_ALL;
- jsf->dv[2].dsize = 0x01000000;
-
- printk("Espresso Flash @0x%lx [%d MB]\n", jsf->base,
- (int) (jsf->size / (1024*1024)));
- }
-
- if ((rc = misc_register(&jsf_dev)) != 0) {
- printk(KERN_ERR "jsf: unable to get misc minor %d\n",
- JSF_MINOR);
- jsf0.base = 0;
- return rc;
- }
-
- return 0;
-}
-
-static int jsfd_init(void)
-{
- static DEFINE_SPINLOCK(lock);
- struct jsflash *jsf;
- struct jsfd_part *jdp;
- int err;
- int i;
-
- if (jsf0.base == 0)
- return -ENXIO;
-
- err = -ENOMEM;
- for (i = 0; i < JSF_MAX; i++) {
- struct gendisk *disk = alloc_disk(1);
- if (!disk)
- goto out;
- disk->queue = blk_init_queue(jsfd_do_request, &lock);
- if (!disk->queue) {
- put_disk(disk);
- goto out;
- }
- blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH);
- jsfd_disk[i] = disk;
- }
-
- if (register_blkdev(JSFD_MAJOR, "jsfd")) {
- err = -EIO;
- goto out;
- }
-
- for (i = 0; i < JSF_MAX; i++) {
- struct gendisk *disk = jsfd_disk[i];
- if ((i & JSF_PART_MASK) >= JSF_NPART) continue;
- jsf = &jsf0; /* actually, &jsfv[i >> JSF_PART_BITS] */
- jdp = &jsf->dv[i&JSF_PART_MASK];
-
- disk->major = JSFD_MAJOR;
- disk->first_minor = i;
- sprintf(disk->disk_name, "jsfd%d", i);
- disk->fops = &jsfd_fops;
- set_capacity(disk, jdp->dsize >> 9);
- disk->private_data = jdp;
- add_disk(disk);
- set_disk_ro(disk, 1);
- }
- return 0;
-out:
- while (i--)
- put_disk(jsfd_disk[i]);
- return err;
-}
-
-MODULE_LICENSE("GPL");
-
-static int __init jsflash_init_module(void) {
- int rc;
-
- if ((rc = jsflash_init()) == 0) {
- jsfd_init();
- return 0;
- }
- return rc;
-}
-
-static void __exit jsflash_cleanup_module(void)
-{
- int i;
-
- for (i = 0; i < JSF_MAX; i++) {
- if ((i & JSF_PART_MASK) >= JSF_NPART) continue;
- del_gendisk(jsfd_disk[i]);
- blk_cleanup_queue(jsfd_disk[i]->queue);
- put_disk(jsfd_disk[i]);
- }
- if (jsf0.busy)
- printk("jsf0: cleaning busy unit\n");
- jsf0.base = 0;
- jsf0.busy = 0;
-
- misc_deregister(&jsf_dev);
- unregister_blkdev(JSFD_MAJOR, "jsfd");
-}
-
-module_init(jsflash_init_module);
-module_exit(jsflash_cleanup_module);
diff --git a/drivers/sbus/char/oradax.c b/drivers/sbus/char/oradax.c
index c44d7c7..1754f55 100644
--- a/drivers/sbus/char/oradax.c
+++ b/drivers/sbus/char/oradax.c
@@ -3,7 +3,7 @@
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
+ * the Free Software Foundation, either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index e29f9b8..56c9403 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -182,7 +182,7 @@
NCR_Q720_mod-objs := NCR_Q720.o ncr53c8xx.o
# Files generated that shall be removed upon make clean
-clean-files := 53c700_d.h 53c700_u.h
+clean-files := 53c700_d.h 53c700_u.h scsi_devinfo_tbl.c
$(obj)/53c700.o $(MODVERDIR)/$(obj)/53c700.ver: $(obj)/53c700_d.h
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index 0156c96..d62ddd6 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -724,6 +724,8 @@ int aac_hba_send(u8 command, struct fib *fibptr, fib_callback callback,
int wait;
unsigned long flags = 0;
unsigned long mflags = 0;
+ struct aac_hba_cmd_req *hbacmd = (struct aac_hba_cmd_req *)
+ fibptr->hw_fib_va;
fibptr->flags = (FIB_CONTEXT_FLAG | FIB_CONTEXT_FLAG_NATIVE_HBA);
if (callback) {
@@ -734,11 +736,9 @@ int aac_hba_send(u8 command, struct fib *fibptr, fib_callback callback,
wait = 1;
- if (command == HBA_IU_TYPE_SCSI_CMD_REQ) {
- struct aac_hba_cmd_req *hbacmd =
- (struct aac_hba_cmd_req *)fibptr->hw_fib_va;
+ hbacmd->iu_type = command;
- hbacmd->iu_type = command;
+ if (command == HBA_IU_TYPE_SCSI_CMD_REQ) {
/* bit1 of request_id must be 0 */
hbacmd->request_id =
cpu_to_le32((((u32)(fibptr - dev->fibs)) << 2) + 1);
diff --git a/drivers/scsi/fnic/fnic_trace.c b/drivers/scsi/fnic/fnic_trace.c
index abddde1..98597b5 100644
--- a/drivers/scsi/fnic/fnic_trace.c
+++ b/drivers/scsi/fnic/fnic_trace.c
@@ -296,7 +296,7 @@ int fnic_get_stats_data(struct stats_debug_info *debug,
"Number of Abort FW Timeouts: %lld\n"
"Number of Abort IO NOT Found: %lld\n"
- "Abord issued times: \n"
+ "Abort issued times: \n"
" < 6 sec : %lld\n"
" 6 sec - 20 sec : %lld\n"
" 20 sec - 30 sec : %lld\n"
diff --git a/drivers/scsi/gdth.c b/drivers/scsi/gdth.c
index c35f05c4..8560479 100644
--- a/drivers/scsi/gdth.c
+++ b/drivers/scsi/gdth.c
@@ -3882,7 +3882,7 @@ static enum blk_eh_timer_return gdth_timed_out(struct scsi_cmnd *scp)
struct gdth_cmndinfo *cmndinfo = gdth_cmnd_priv(scp);
u8 b, t;
unsigned long flags;
- enum blk_eh_timer_return retval = BLK_EH_NOT_HANDLED;
+ enum blk_eh_timer_return retval = BLK_EH_DONE;
TRACE(("%s() cmd 0x%x\n", scp->cmnd[0], __func__));
b = scp->device->channel;
diff --git a/drivers/scsi/isci/port_config.c b/drivers/scsi/isci/port_config.c
index edb7be7..9e8de14 100644
--- a/drivers/scsi/isci/port_config.c
+++ b/drivers/scsi/isci/port_config.c
@@ -291,7 +291,7 @@ sci_mpc_agent_validate_phy_configuration(struct isci_host *ihost,
* Note: We have not moved the current phy_index so we will actually
* compare the startting phy with itself.
* This is expected and required to add the phy to the port. */
- while (phy_index < SCI_MAX_PHYS) {
+ for (; phy_index < SCI_MAX_PHYS; phy_index++) {
if ((phy_mask & (1 << phy_index)) == 0)
continue;
sci_phy_get_sas_address(&ihost->phys[phy_index],
@@ -311,7 +311,6 @@ sci_mpc_agent_validate_phy_configuration(struct isci_host *ihost,
&ihost->phys[phy_index]);
assigned_phy_mask |= (1 << phy_index);
- phy_index++;
}
}
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 15a2fef..71bdc0b 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -1963,7 +1963,7 @@ static int iscsi_has_ping_timed_out(struct iscsi_conn *conn)
enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
{
- enum blk_eh_timer_return rc = BLK_EH_NOT_HANDLED;
+ enum blk_eh_timer_return rc = BLK_EH_DONE;
struct iscsi_task *task = NULL, *running_task;
struct iscsi_cls_session *cls_session;
struct iscsi_session *session;
@@ -1982,7 +1982,7 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
* Raced with completion. Blk layer has taken ownership
* so let timeout code complete it now.
*/
- rc = BLK_EH_HANDLED;
+ rc = BLK_EH_DONE;
goto done;
}
@@ -1997,7 +1997,7 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
if (unlikely(system_state != SYSTEM_RUNNING)) {
sc->result = DID_NO_CONNECT << 16;
ISCSI_DBG_EH(session, "sc on shutdown, handled\n");
- rc = BLK_EH_HANDLED;
+ rc = BLK_EH_DONE;
goto done;
}
/*
diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c
index 7195cff..91f5e2c 100644
--- a/drivers/scsi/megaraid.c
+++ b/drivers/scsi/megaraid.c
@@ -2731,53 +2731,6 @@ proc_show_rdrv_40(struct seq_file *m, void *v)
return proc_show_rdrv(m, m->private, 30, 39);
}
-
-/*
- * seq_file wrappers for procfile show routines.
- */
-static int mega_proc_open(struct inode *inode, struct file *file)
-{
- adapter_t *adapter = proc_get_parent_data(inode);
- int (*show)(struct seq_file *, void *) = PDE_DATA(inode);
-
- return single_open(file, show, adapter);
-}
-
-static const struct file_operations mega_proc_fops = {
- .open = mega_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-/*
- * Table of proc files we need to create.
- */
-struct mega_proc_file {
- const char *name;
- unsigned short ptr_offset;
- int (*show) (struct seq_file *m, void *v);
-};
-
-static const struct mega_proc_file mega_proc_files[] = {
- { "config", offsetof(adapter_t, proc_read), proc_show_config },
- { "stat", offsetof(adapter_t, proc_stat), proc_show_stat },
- { "mailbox", offsetof(adapter_t, proc_mbox), proc_show_mbox },
-#if MEGA_HAVE_ENH_PROC
- { "rebuild-rate", offsetof(adapter_t, proc_rr), proc_show_rebuild_rate },
- { "battery-status", offsetof(adapter_t, proc_battery), proc_show_battery },
- { "diskdrives-ch0", offsetof(adapter_t, proc_pdrvstat[0]), proc_show_pdrv_ch0 },
- { "diskdrives-ch1", offsetof(adapter_t, proc_pdrvstat[1]), proc_show_pdrv_ch1 },
- { "diskdrives-ch2", offsetof(adapter_t, proc_pdrvstat[2]), proc_show_pdrv_ch2 },
- { "diskdrives-ch3", offsetof(adapter_t, proc_pdrvstat[3]), proc_show_pdrv_ch3 },
- { "raiddrives-0-9", offsetof(adapter_t, proc_rdrvstat[0]), proc_show_rdrv_10 },
- { "raiddrives-10-19", offsetof(adapter_t, proc_rdrvstat[1]), proc_show_rdrv_20 },
- { "raiddrives-20-29", offsetof(adapter_t, proc_rdrvstat[2]), proc_show_rdrv_30 },
- { "raiddrives-30-39", offsetof(adapter_t, proc_rdrvstat[3]), proc_show_rdrv_40 },
-#endif
- { NULL }
-};
-
/**
* mega_create_proc_entry()
* @index - index in soft state array
@@ -2788,31 +2741,45 @@ static const struct mega_proc_file mega_proc_files[] = {
static void
mega_create_proc_entry(int index, struct proc_dir_entry *parent)
{
- const struct mega_proc_file *f;
- adapter_t *adapter = hba_soft_state[index];
- struct proc_dir_entry *dir, *de, **ppde;
- u8 string[16];
+ adapter_t *adapter = hba_soft_state[index];
+ struct proc_dir_entry *dir;
+ u8 string[16];
sprintf(string, "hba%d", adapter->host->host_no);
-
- dir = adapter->controller_proc_dir_entry =
- proc_mkdir_data(string, 0, parent, adapter);
- if(!dir) {
+ dir = proc_mkdir_data(string, 0, parent, adapter);
+ if (!dir) {
dev_warn(&adapter->dev->dev, "proc_mkdir failed\n");
return;
}
- for (f = mega_proc_files; f->name; f++) {
- de = proc_create_data(f->name, S_IRUSR, dir, &mega_proc_fops,
- f->show);
- if (!de) {
- dev_warn(&adapter->dev->dev, "proc_create failed\n");
- return;
- }
-
- ppde = (void *)adapter + f->ptr_offset;
- *ppde = de;
- }
+ proc_create_single_data("config", S_IRUSR, dir,
+ proc_show_config, adapter);
+ proc_create_single_data("stat", S_IRUSR, dir,
+ proc_show_stat, adapter);
+ proc_create_single_data("mailbox", S_IRUSR, dir,
+ proc_show_mbox, adapter);
+#if MEGA_HAVE_ENH_PROC
+ proc_create_single_data("rebuild-rate", S_IRUSR, dir,
+ proc_show_rebuild_rate, adapter);
+ proc_create_single_data("battery-status", S_IRUSR, dir,
+ proc_show_battery, adapter);
+ proc_create_single_data("diskdrives-ch0", S_IRUSR, dir,
+ proc_show_pdrv_ch0, adapter);
+ proc_create_single_data("diskdrives-ch1", S_IRUSR, dir,
+ proc_show_pdrv_ch1, adapter);
+ proc_create_single_data("diskdrives-ch2", S_IRUSR, dir,
+ proc_show_pdrv_ch2, adapter);
+ proc_create_single_data("diskdrives-ch3", S_IRUSR, dir,
+ proc_show_pdrv_ch3, adapter);
+ proc_create_single_data("raiddrives-0-9", S_IRUSR, dir,
+ proc_show_rdrv_10, adapter);
+ proc_create_single_data("raiddrives-10-19", S_IRUSR, dir,
+ proc_show_rdrv_20, adapter);
+ proc_create_single_data("raiddrives-20-29", S_IRUSR, dir,
+ proc_show_rdrv_30, adapter);
+ proc_create_single_data("raiddrives-30-39", S_IRUSR, dir,
+ proc_show_rdrv_40, adapter);
+#endif
}
#else
@@ -4580,6 +4547,7 @@ megaraid_remove_one(struct pci_dev *pdev)
{
struct Scsi_Host *host = pci_get_drvdata(pdev);
adapter_t *adapter = (adapter_t *)host->hostdata;
+ char buf[12] = { 0 };
scsi_remove_host(host);
@@ -4594,44 +4562,8 @@ megaraid_remove_one(struct pci_dev *pdev)
mega_free_sgl(adapter);
-#ifdef CONFIG_PROC_FS
- if (adapter->controller_proc_dir_entry) {
- remove_proc_entry("stat", adapter->controller_proc_dir_entry);
- remove_proc_entry("config",
- adapter->controller_proc_dir_entry);
- remove_proc_entry("mailbox",
- adapter->controller_proc_dir_entry);
-#if MEGA_HAVE_ENH_PROC
- remove_proc_entry("rebuild-rate",
- adapter->controller_proc_dir_entry);
- remove_proc_entry("battery-status",
- adapter->controller_proc_dir_entry);
-
- remove_proc_entry("diskdrives-ch0",
- adapter->controller_proc_dir_entry);
- remove_proc_entry("diskdrives-ch1",
- adapter->controller_proc_dir_entry);
- remove_proc_entry("diskdrives-ch2",
- adapter->controller_proc_dir_entry);
- remove_proc_entry("diskdrives-ch3",
- adapter->controller_proc_dir_entry);
-
- remove_proc_entry("raiddrives-0-9",
- adapter->controller_proc_dir_entry);
- remove_proc_entry("raiddrives-10-19",
- adapter->controller_proc_dir_entry);
- remove_proc_entry("raiddrives-20-29",
- adapter->controller_proc_dir_entry);
- remove_proc_entry("raiddrives-30-39",
- adapter->controller_proc_dir_entry);
-#endif
- {
- char buf[12] = { 0 };
- sprintf(buf, "hba%d", adapter->host->host_no);
- remove_proc_entry(buf, mega_proc_dir_entry);
- }
- }
-#endif
+ sprintf(buf, "hba%d", adapter->host->host_no);
+ remove_proc_subtree(buf, mega_proc_dir_entry);
pci_free_consistent(adapter->dev, MEGA_BUFFER_SIZE,
adapter->mega_buffer, adapter->buf_dma_handle);
diff --git a/drivers/scsi/megaraid.h b/drivers/scsi/megaraid.h
index 21eba2f..18e85d9 100644
--- a/drivers/scsi/megaraid.h
+++ b/drivers/scsi/megaraid.h
@@ -814,18 +814,6 @@ typedef struct {
#ifdef CONFIG_PROC_FS
struct proc_dir_entry *controller_proc_dir_entry;
- struct proc_dir_entry *proc_read;
- struct proc_dir_entry *proc_stat;
- struct proc_dir_entry *proc_mbox;
-
-#if MEGA_HAVE_ENH_PROC
- struct proc_dir_entry *proc_rr;
- struct proc_dir_entry *proc_battery;
-#define MAX_PROC_CHANNELS 4
- struct proc_dir_entry *proc_pdrvstat[MAX_PROC_CHANNELS];
- struct proc_dir_entry *proc_rdrvstat[MAX_PROC_CHANNELS];
-#endif
-
#endif
int has_64bit_addr; /* are we using 64-bit addressing */
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index b89c6e6..ce656c4 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -2772,7 +2772,7 @@ blk_eh_timer_return megasas_reset_timer(struct scsi_cmnd *scmd)
if (time_after(jiffies, scmd->jiffies_at_alloc +
(scmd_timeout * 2) * HZ)) {
- return BLK_EH_NOT_HANDLED;
+ return BLK_EH_DONE;
}
instance = (struct megasas_instance *)scmd->device->host->hostdata;
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index ce97cde..f4d988d 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -1124,12 +1124,12 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
goto fail_fw_init;
}
- ret = 0;
+ return 0;
fail_fw_init:
dev_err(&instance->pdev->dev,
- "Init cmd return status %s for SCSI host %d\n",
- ret ? "FAILED" : "SUCCESS", instance->host->host_no);
+ "Init cmd return status FAILED for SCSI host %d\n",
+ instance->host->host_no);
return ret;
}
diff --git a/drivers/scsi/mvumi.c b/drivers/scsi/mvumi.c
index fe97401..afd2716 100644
--- a/drivers/scsi/mvumi.c
+++ b/drivers/scsi/mvumi.c
@@ -2155,7 +2155,7 @@ static enum blk_eh_timer_return mvumi_timed_out(struct scsi_cmnd *scmd)
mvumi_return_cmd(mhba, cmd);
spin_unlock_irqrestore(mhba->shost->host_lock, flags);
- return BLK_EH_NOT_HANDLED;
+ return BLK_EH_DONE;
}
static int
diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c
index e188771..5a33e1a 100644
--- a/drivers/scsi/osd/osd_initiator.c
+++ b/drivers/scsi/osd/osd_initiator.c
@@ -99,7 +99,7 @@ static int _osd_get_print_system_info(struct osd_dev *od,
int nelem = ARRAY_SIZE(get_attrs), a = 0;
int ret;
- or = osd_start_request(od, GFP_KERNEL);
+ or = osd_start_request(od);
if (!or)
return -ENOMEM;
@@ -409,16 +409,15 @@ static void _osd_request_free(struct osd_request *or)
kfree(or);
}
-struct osd_request *osd_start_request(struct osd_dev *dev, gfp_t gfp)
+struct osd_request *osd_start_request(struct osd_dev *dev)
{
struct osd_request *or;
- or = _osd_request_alloc(gfp);
+ or = _osd_request_alloc(GFP_KERNEL);
if (!or)
return NULL;
or->osd_dev = dev;
- or->alloc_flags = gfp;
or->timeout = dev->def_timeout;
or->retries = OSD_REQ_RETRIES;
@@ -546,7 +545,7 @@ static int _osd_realloc_seg(struct osd_request *or,
if (seg->alloc_size >= max_bytes)
return 0;
- buff = krealloc(seg->buff, max_bytes, or->alloc_flags);
+ buff = krealloc(seg->buff, max_bytes, GFP_KERNEL);
if (!buff) {
OSD_ERR("Failed to Realloc %d-bytes was-%d\n", max_bytes,
seg->alloc_size);
@@ -728,7 +727,7 @@ static int _osd_req_list_objects(struct osd_request *or,
_osd_req_encode_olist(or, list);
WARN_ON(or->in.bio);
- bio = bio_map_kern(q, list, len, or->alloc_flags);
+ bio = bio_map_kern(q, list, len, GFP_KERNEL);
if (IS_ERR(bio)) {
OSD_ERR("!!! Failed to allocate list_objects BIO\n");
return PTR_ERR(bio);
@@ -1190,14 +1189,14 @@ static int _req_append_segment(struct osd_request *or,
pad_buff = io->pad_buff;
ret = blk_rq_map_kern(io->req->q, io->req, pad_buff, padding,
- or->alloc_flags);
+ GFP_KERNEL);
if (ret)
return ret;
io->total_bytes += padding;
}
ret = blk_rq_map_kern(io->req->q, io->req, seg->buff, seg->total_bytes,
- or->alloc_flags);
+ GFP_KERNEL);
if (ret)
return ret;
@@ -1564,14 +1563,14 @@ static int _osd_req_finalize_data_integrity(struct osd_request *or,
* osd_finalize_request and helpers
*/
static struct request *_make_request(struct request_queue *q, bool has_write,
- struct _osd_io_info *oii, gfp_t flags)
+ struct _osd_io_info *oii)
{
struct request *req;
struct bio *bio = oii->bio;
int ret;
req = blk_get_request(q, has_write ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
- flags);
+ 0);
if (IS_ERR(req))
return req;
@@ -1589,13 +1588,12 @@ static struct request *_make_request(struct request_queue *q, bool has_write,
static int _init_blk_request(struct osd_request *or,
bool has_in, bool has_out)
{
- gfp_t flags = or->alloc_flags;
struct scsi_device *scsi_device = or->osd_dev->scsi_device;
struct request_queue *q = scsi_device->request_queue;
struct request *req;
int ret;
- req = _make_request(q, has_out, has_out ? &or->out : &or->in, flags);
+ req = _make_request(q, has_out, has_out ? &or->out : &or->in);
if (IS_ERR(req)) {
ret = PTR_ERR(req);
goto out;
@@ -1611,7 +1609,7 @@ static int _init_blk_request(struct osd_request *or,
or->out.req = req;
if (has_in) {
/* allocate bidi request */
- req = _make_request(q, false, &or->in, flags);
+ req = _make_request(q, false, &or->in);
if (IS_ERR(req)) {
OSD_DEBUG("blk_get_request for bidi failed\n");
ret = PTR_ERR(req);
diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c
index 20ec1c0..2bbe797 100644
--- a/drivers/scsi/osst.c
+++ b/drivers/scsi/osst.c
@@ -368,7 +368,7 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd,
int write = (data_direction == DMA_TO_DEVICE);
req = blk_get_request(SRpnt->stp->device->request_queue,
- write ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, GFP_KERNEL);
+ write ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
if (IS_ERR(req))
return DRIVER_ERROR << 24;
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index 94c14ce..0e13349 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -1848,7 +1848,7 @@ static enum blk_eh_timer_return qla4xxx_eh_cmd_timed_out(struct scsi_cmnd *sc)
struct iscsi_cls_session *session;
struct iscsi_session *sess;
unsigned long flags;
- enum blk_eh_timer_return ret = BLK_EH_NOT_HANDLED;
+ enum blk_eh_timer_return ret = BLK_EH_DONE;
session = starget_to_session(scsi_target(sc->device));
sess = session->dd_data;
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 9ef5e3b..656c98e 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -234,11 +234,13 @@ static const char *sdebug_version_date = "20180128";
#define F_INV_OP 0x200
#define F_FAKE_RW 0x400
#define F_M_ACCESS 0x800 /* media access */
-#define F_LONG_DELAY 0x1000
+#define F_SSU_DELAY 0x1000
+#define F_SYNC_DELAY 0x2000
#define FF_RESPOND (F_RL_WLUN_OK | F_SKIP_UA | F_DELAY_OVERR)
#define FF_MEDIA_IO (F_M_ACCESS | F_FAKE_RW)
#define FF_SA (F_SA_HIGH | F_SA_LOW)
+#define F_LONG_DELAY (F_SSU_DELAY | F_SYNC_DELAY)
#define SDEBUG_MAX_PARTS 4
@@ -510,7 +512,7 @@ static const struct opcode_info_t release_iarr[] = {
};
static const struct opcode_info_t sync_cache_iarr[] = {
- {0, 0x91, 0, F_LONG_DELAY | F_M_ACCESS, resp_sync_cache, NULL,
+ {0, 0x91, 0, F_SYNC_DELAY | F_M_ACCESS, resp_sync_cache, NULL,
{16, 0x6, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
0xff, 0xff, 0xff, 0xff, 0x3f, 0xc7} }, /* SYNC_CACHE (16) */
};
@@ -553,7 +555,7 @@ static const struct opcode_info_t opcode_info_arr[SDEB_I_LAST_ELEMENT + 1] = {
resp_write_dt0, write_iarr, /* WRITE(16) */
{16, 0xfa, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
0xff, 0xff, 0xff, 0xff, 0xff, 0xc7} },
- {0, 0x1b, 0, F_LONG_DELAY, resp_start_stop, NULL,/* START STOP UNIT */
+ {0, 0x1b, 0, F_SSU_DELAY, resp_start_stop, NULL,/* START STOP UNIT */
{6, 0x1, 0, 0xf, 0xf7, 0xc7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} },
{ARRAY_SIZE(sa_in_16_iarr), 0x9e, 0x10, F_SA_LOW | F_D_IN,
resp_readcap16, sa_in_16_iarr, /* SA_IN(16), READ CAPACITY(16) */
@@ -606,7 +608,7 @@ static const struct opcode_info_t opcode_info_arr[SDEB_I_LAST_ELEMENT + 1] = {
resp_write_same_10, write_same_iarr, /* WRITE SAME(10) */
{10, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f, 0xff, 0xff, 0xc7, 0,
0, 0, 0, 0, 0} },
- {ARRAY_SIZE(sync_cache_iarr), 0x35, 0, F_LONG_DELAY | F_M_ACCESS,
+ {ARRAY_SIZE(sync_cache_iarr), 0x35, 0, F_SYNC_DELAY | F_M_ACCESS,
resp_sync_cache, sync_cache_iarr,
{10, 0x7, 0xff, 0xff, 0xff, 0xff, 0x3f, 0xff, 0xff, 0xc7, 0, 0,
0, 0, 0, 0} }, /* SYNC_CACHE (10) */
@@ -667,6 +669,7 @@ static bool sdebug_strict = DEF_STRICT;
static bool sdebug_any_injecting_opt;
static bool sdebug_verbose;
static bool have_dif_prot;
+static bool write_since_sync;
static bool sdebug_statistics = DEF_STATISTICS;
static unsigned int sdebug_store_sectors;
@@ -1607,6 +1610,7 @@ static int resp_start_stop(struct scsi_cmnd *scp,
{
unsigned char *cmd = scp->cmnd;
int power_cond, stop;
+ bool changing;
power_cond = (cmd[4] & 0xf0) >> 4;
if (power_cond) {
@@ -1614,8 +1618,12 @@ static int resp_start_stop(struct scsi_cmnd *scp,
return check_condition_result;
}
stop = !(cmd[4] & 1);
+ changing = atomic_read(&devip->stopped) == !stop;
atomic_xchg(&devip->stopped, stop);
- return (cmd[1] & 0x1) ? SDEG_RES_IMMED_MASK : 0; /* check IMMED bit */
+ if (!changing || cmd[1] & 0x1) /* state unchanged or IMMED set */
+ return SDEG_RES_IMMED_MASK;
+ else
+ return 0;
}
static sector_t get_sdebug_capacity(void)
@@ -2473,6 +2481,7 @@ static int do_device_access(struct scsi_cmnd *scmd, u32 sg_skip, u64 lba,
if (do_write) {
sdb = scsi_out(scmd);
dir = DMA_TO_DEVICE;
+ write_since_sync = true;
} else {
sdb = scsi_in(scmd);
dir = DMA_FROM_DEVICE;
@@ -3583,6 +3592,7 @@ static int resp_get_lba_status(struct scsi_cmnd *scp,
static int resp_sync_cache(struct scsi_cmnd *scp,
struct sdebug_dev_info *devip)
{
+ int res = 0;
u64 lba;
u32 num_blocks;
u8 *cmd = scp->cmnd;
@@ -3598,7 +3608,11 @@ static int resp_sync_cache(struct scsi_cmnd *scp,
mk_sense_buffer(scp, ILLEGAL_REQUEST, LBA_OUT_OF_RANGE, 0);
return check_condition_result;
}
- return (cmd[1] & 0x2) ? SDEG_RES_IMMED_MASK : 0; /* check IMMED bit */
+ if (!write_since_sync || cmd[1] & 0x2)
+ res = SDEG_RES_IMMED_MASK;
+ else /* delay if write_since_sync and IMMED clear */
+ write_since_sync = false;
+ return res;
}
#define RL_BUCKET_ELEMS 8
@@ -5777,13 +5791,14 @@ static int scsi_debug_queuecommand(struct Scsi_Host *shost,
return schedule_resp(scp, devip, errsts, pfp, 0, 0);
else if ((sdebug_jdelay || sdebug_ndelay) && (flags & F_LONG_DELAY)) {
/*
- * If any delay is active, want F_LONG_DELAY to be at least 1
+ * If any delay is active, for F_SSU_DELAY want at least 1
* second and if sdebug_jdelay>0 want a long delay of that
- * many seconds.
+ * many seconds; for F_SYNC_DELAY want 1/20 of that.
*/
int jdelay = (sdebug_jdelay < 2) ? 1 : sdebug_jdelay;
+ int denom = (flags & F_SYNC_DELAY) ? 20 : 1;
- jdelay = mult_frac(USER_HZ * jdelay, HZ, USER_HZ);
+ jdelay = mult_frac(USER_HZ * jdelay, HZ, denom * USER_HZ);
return schedule_resp(scp, devip, errsts, pfp, jdelay, 0);
} else
return schedule_resp(scp, devip, errsts, pfp, sdebug_jdelay,
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 9460391..9c02ba2 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -282,7 +282,7 @@ void scsi_eh_scmd_add(struct scsi_cmnd *scmd)
enum blk_eh_timer_return scsi_times_out(struct request *req)
{
struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(req);
- enum blk_eh_timer_return rtn = BLK_EH_NOT_HANDLED;
+ enum blk_eh_timer_return rtn = BLK_EH_DONE;
struct Scsi_Host *host = scmd->device->host;
trace_scsi_dispatch_cmd_timeout(scmd);
@@ -294,7 +294,7 @@ enum blk_eh_timer_return scsi_times_out(struct request *req)
if (host->hostt->eh_timed_out)
rtn = host->hostt->eh_timed_out(scmd);
- if (rtn == BLK_EH_NOT_HANDLED) {
+ if (rtn == BLK_EH_DONE) {
if (scsi_abort_command(scmd) != SUCCESS) {
set_host_byte(scmd, DID_TIME_OUT);
scsi_eh_scmd_add(scmd);
@@ -1933,11 +1933,7 @@ static void scsi_eh_lock_door(struct scsi_device *sdev)
struct request *req;
struct scsi_request *rq;
- /*
- * blk_get_request with GFP_KERNEL (__GFP_RECLAIM) sleeps until a
- * request becomes available
- */
- req = blk_get_request(sdev->request_queue, REQ_OP_SCSI_IN, GFP_KERNEL);
+ req = blk_get_request(sdev->request_queue, REQ_OP_SCSI_IN, 0);
if (IS_ERR(req))
return;
rq = scsi_req(req);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index e9b4f27..fb38aef 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -265,7 +265,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
struct scsi_request *rq;
int ret = DRIVER_ERROR << 24;
- req = blk_get_request_flags(sdev->request_queue,
+ req = blk_get_request(sdev->request_queue,
data_direction == DMA_TO_DEVICE ?
REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, BLK_MQ_REQ_PREEMPT);
if (IS_ERR(req))
@@ -273,7 +273,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
rq = scsi_req(req);
if (bufflen && blk_rq_map_kern(sdev->request_queue, req,
- buffer, bufflen, __GFP_RECLAIM))
+ buffer, bufflen, GFP_NOIO))
goto out;
rq->cmd_len = COMMAND_SIZE(cmd[0]);
@@ -2149,27 +2149,6 @@ static int scsi_map_queues(struct blk_mq_tag_set *set)
return blk_mq_map_queues(set);
}
-static u64 scsi_calculate_bounce_limit(struct Scsi_Host *shost)
-{
- struct device *host_dev;
- u64 bounce_limit = 0xffffffff;
-
- if (shost->unchecked_isa_dma)
- return BLK_BOUNCE_ISA;
- /*
- * Platforms with virtual-DMA translation
- * hardware have no practical limit.
- */
- if (!PCI_DMA_BUS_IS_PHYS)
- return BLK_BOUNCE_ANY;
-
- host_dev = scsi_get_device(shost);
- if (host_dev && host_dev->dma_mask)
- bounce_limit = (u64)dma_max_pfn(host_dev) << PAGE_SHIFT;
-
- return bounce_limit;
-}
-
void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
{
struct device *dev = shost->dma_dev;
@@ -2189,7 +2168,8 @@ void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
}
blk_queue_max_hw_sectors(q, shost->max_sectors);
- blk_queue_bounce_limit(q, scsi_calculate_bounce_limit(shost));
+ if (shost->unchecked_isa_dma)
+ blk_queue_bounce_limit(q, BLK_BOUNCE_ISA);
blk_queue_segment_boundary(q, shost->dma_boundary);
dma_set_seg_boundary(dev, shost->dma_boundary);
diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c
index be3be0f..1da3d71 100644
--- a/drivers/scsi/scsi_transport_fc.c
+++ b/drivers/scsi/scsi_transport_fc.c
@@ -2087,7 +2087,7 @@ fc_eh_timed_out(struct scsi_cmnd *scmd)
if (rport->port_state == FC_PORTSTATE_BLOCKED)
return BLK_EH_RESET_TIMER;
- return BLK_EH_NOT_HANDLED;
+ return BLK_EH_DONE;
}
EXPORT_SYMBOL(fc_eh_timed_out);
@@ -3591,10 +3591,9 @@ fc_bsg_job_timeout(struct request *req)
}
/* the blk_end_sync_io() doesn't check the error */
- if (!inflight)
- return BLK_EH_NOT_HANDLED;
- else
- return BLK_EH_HANDLED;
+ if (inflight)
+ blk_mq_complete_request(req);
+ return BLK_EH_DONE;
}
/**
@@ -3781,8 +3780,7 @@ fc_bsg_hostadd(struct Scsi_Host *shost, struct fc_host_attrs *fc_host)
snprintf(bsg_name, sizeof(bsg_name),
"fc_host%d", shost->host_no);
- q = bsg_setup_queue(dev, bsg_name, fc_bsg_dispatch, i->f->dd_bsg_size,
- NULL);
+ q = bsg_setup_queue(dev, bsg_name, fc_bsg_dispatch, i->f->dd_bsg_size);
if (IS_ERR(q)) {
dev_err(dev,
"fc_host%d: bsg interface failed to initialize - setup queue\n",
@@ -3827,8 +3825,8 @@ fc_bsg_rportadd(struct Scsi_Host *shost, struct fc_rport *rport)
if (!i->f->bsg_request)
return -ENOTSUPP;
- q = bsg_setup_queue(dev, NULL, fc_bsg_dispatch, i->f->dd_bsg_size,
- NULL);
+ q = bsg_setup_queue(dev, dev_name(dev), fc_bsg_dispatch,
+ i->f->dd_bsg_size);
if (IS_ERR(q)) {
dev_err(dev, "failed to setup bsg queue\n");
return PTR_ERR(q);
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index f4b52b4..6fd2fe2 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -1542,7 +1542,7 @@ iscsi_bsg_host_add(struct Scsi_Host *shost, struct iscsi_cls_host *ihost)
return -ENOTSUPP;
snprintf(bsg_name, sizeof(bsg_name), "iscsi_host%d", shost->host_no);
- q = bsg_setup_queue(dev, bsg_name, iscsi_bsg_host_dispatch, 0, NULL);
+ q = bsg_setup_queue(dev, bsg_name, iscsi_bsg_host_dispatch, 0);
if (IS_ERR(q)) {
shost_printk(KERN_ERR, shost, "bsg interface failed to "
"initialize - no request queue\n");
@@ -2322,6 +2322,12 @@ iscsi_multicast_skb(struct sk_buff *skb, uint32_t group, gfp_t gfp)
return nlmsg_multicast(nls, skb, 0, group, gfp);
}
+static int
+iscsi_unicast_skb(struct sk_buff *skb, u32 portid)
+{
+ return nlmsg_unicast(nls, skb, portid);
+}
+
int iscsi_recv_pdu(struct iscsi_cls_conn *conn, struct iscsi_hdr *hdr,
char *data, uint32_t data_size)
{
@@ -2524,14 +2530,11 @@ void iscsi_ping_comp_event(uint32_t host_no, struct iscsi_transport *transport,
EXPORT_SYMBOL_GPL(iscsi_ping_comp_event);
static int
-iscsi_if_send_reply(uint32_t group, int seq, int type, int done, int multi,
- void *payload, int size)
+iscsi_if_send_reply(u32 portid, int type, void *payload, int size)
{
struct sk_buff *skb;
struct nlmsghdr *nlh;
int len = nlmsg_total_size(size);
- int flags = multi ? NLM_F_MULTI : 0;
- int t = done ? NLMSG_DONE : type;
skb = alloc_skb(len, GFP_ATOMIC);
if (!skb) {
@@ -2539,10 +2542,9 @@ iscsi_if_send_reply(uint32_t group, int seq, int type, int done, int multi,
return -ENOMEM;
}
- nlh = __nlmsg_put(skb, 0, 0, t, (len - sizeof(*nlh)), 0);
- nlh->nlmsg_flags = flags;
+ nlh = __nlmsg_put(skb, 0, 0, type, (len - sizeof(*nlh)), 0);
memcpy(nlmsg_data(nlh), payload, size);
- return iscsi_multicast_skb(skb, group, GFP_ATOMIC);
+ return iscsi_unicast_skb(skb, portid);
}
static int
@@ -3470,6 +3472,7 @@ static int
iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group)
{
int err = 0;
+ u32 portid;
struct iscsi_uevent *ev = nlmsg_data(nlh);
struct iscsi_transport *transport = NULL;
struct iscsi_internal *priv;
@@ -3490,10 +3493,12 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group)
if (!try_module_get(transport->owner))
return -EINVAL;
+ portid = NETLINK_CB(skb).portid;
+
switch (nlh->nlmsg_type) {
case ISCSI_UEVENT_CREATE_SESSION:
err = iscsi_if_create_session(priv, ep, ev,
- NETLINK_CB(skb).portid,
+ portid,
ev->u.c_session.initial_cmdsn,
ev->u.c_session.cmds_max,
ev->u.c_session.queue_depth);
@@ -3506,7 +3511,7 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group)
}
err = iscsi_if_create_session(priv, ep, ev,
- NETLINK_CB(skb).portid,
+ portid,
ev->u.c_bound_session.initial_cmdsn,
ev->u.c_bound_session.cmds_max,
ev->u.c_bound_session.queue_depth);
@@ -3664,6 +3669,8 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group)
static void
iscsi_if_rx(struct sk_buff *skb)
{
+ u32 portid = NETLINK_CB(skb).portid;
+
mutex_lock(&rx_queue_mutex);
while (skb->len >= NLMSG_HDRLEN) {
int err;
@@ -3699,8 +3706,8 @@ iscsi_if_rx(struct sk_buff *skb)
break;
if (ev->type == ISCSI_UEVENT_GET_CHAP && !err)
break;
- err = iscsi_if_send_reply(group, nlh->nlmsg_seq,
- nlh->nlmsg_type, 0, 0, ev, sizeof(*ev));
+ err = iscsi_if_send_reply(portid, nlh->nlmsg_type,
+ ev, sizeof(*ev));
} while (err < 0 && err != -ECONNREFUSED && err != -ESRCH);
skb_pull(skb, rlen);
}
diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index 08acbab..e2953b4 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -187,16 +187,6 @@ static int sas_smp_dispatch(struct bsg_job *job)
return 0;
}
-static void sas_host_release(struct device *dev)
-{
- struct Scsi_Host *shost = dev_to_shost(dev);
- struct sas_host_attrs *sas_host = to_sas_host_attrs(shost);
- struct request_queue *q = sas_host->q;
-
- if (q)
- blk_cleanup_queue(q);
-}
-
static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy)
{
struct request_queue *q;
@@ -208,7 +198,7 @@ static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy)
if (rphy) {
q = bsg_setup_queue(&rphy->dev, dev_name(&rphy->dev),
- sas_smp_dispatch, 0, NULL);
+ sas_smp_dispatch, 0);
if (IS_ERR(q))
return PTR_ERR(q);
rphy->q = q;
@@ -217,7 +207,7 @@ static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy)
snprintf(name, sizeof(name), "sas_host%d", shost->host_no);
q = bsg_setup_queue(&shost->shost_gendev, name,
- sas_smp_dispatch, 0, sas_host_release);
+ sas_smp_dispatch, 0);
if (IS_ERR(q))
return PTR_ERR(q);
to_sas_host_attrs(shost)->q = q;
@@ -260,8 +250,11 @@ static int sas_host_remove(struct transport_container *tc, struct device *dev,
struct Scsi_Host *shost = dev_to_shost(dev);
struct request_queue *q = to_sas_host_attrs(shost)->q;
- if (q)
+ if (q) {
bsg_unregister_queue(q);
+ blk_cleanup_queue(q);
+ }
+
return 0;
}
diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c
index 36f6190..4e46fdb 100644
--- a/drivers/scsi/scsi_transport_srp.c
+++ b/drivers/scsi/scsi_transport_srp.c
@@ -51,6 +51,8 @@ struct srp_internal {
struct transport_container rport_attr_cont;
};
+static int scsi_is_srp_rport(const struct device *dev);
+
#define to_srp_internal(tmpl) container_of(tmpl, struct srp_internal, t)
#define dev_to_rport(d) container_of(d, struct srp_rport, dev)
@@ -60,9 +62,24 @@ static inline struct Scsi_Host *rport_to_shost(struct srp_rport *r)
return dev_to_shost(r->dev.parent);
}
+static int find_child_rport(struct device *dev, void *data)
+{
+ struct device **child = data;
+
+ if (scsi_is_srp_rport(dev)) {
+ WARN_ON_ONCE(*child);
+ *child = dev;
+ }
+ return 0;
+}
+
static inline struct srp_rport *shost_to_rport(struct Scsi_Host *shost)
{
- return transport_class_to_srp_rport(&shost->shost_gendev);
+ struct device *child = NULL;
+
+ WARN_ON_ONCE(device_for_each_child(&shost->shost_gendev, &child,
+ find_child_rport) < 0);
+ return child ? dev_to_rport(child) : NULL;
}
/**
@@ -587,7 +604,7 @@ EXPORT_SYMBOL(srp_reconnect_rport);
*
* If a timeout occurs while an rport is in the blocked state, ask the SCSI
* EH to continue waiting (BLK_EH_RESET_TIMER). Otherwise let the SCSI core
- * handle the timeout (BLK_EH_NOT_HANDLED).
+ * handle the timeout (BLK_EH_DONE).
*
* Note: This function is called from soft-IRQ context and with the request
* queue lock held.
@@ -600,9 +617,10 @@ enum blk_eh_timer_return srp_timed_out(struct scsi_cmnd *scmd)
struct srp_rport *rport = shost_to_rport(shost);
pr_debug("timeout for sdev %s\n", dev_name(&sdev->sdev_gendev));
- return rport->fast_io_fail_tmo < 0 && rport->dev_loss_tmo < 0 &&
+ return rport && rport->fast_io_fail_tmo < 0 &&
+ rport->dev_loss_tmo < 0 &&
i->f->reset_timer_if_blocked && scsi_device_blocked(sdev) ?
- BLK_EH_RESET_TIMER : BLK_EH_NOT_HANDLED;
+ BLK_EH_RESET_TIMER : BLK_EH_DONE;
}
EXPORT_SYMBOL(srp_timed_out);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index a6201e6..9421d98 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2121,6 +2121,8 @@ sd_spinup_disk(struct scsi_disk *sdkp)
break; /* standby */
if (sshdr.asc == 4 && sshdr.ascq == 0xc)
break; /* unavailable */
+ if (sshdr.asc == 4 && sshdr.ascq == 0x1b)
+ break; /* sanitize in progress */
/*
* Issue command to spin up drive when not ready
*/
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index 41df75e..210407c 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -400,8 +400,10 @@ static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf)
*
* Check that all zones of the device are equal. The last zone can however
* be smaller. The zone size must also be a power of two number of LBAs.
+ *
+ * Returns the zone size in bytes upon success or an error code upon failure.
*/
-static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
+static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp)
{
u64 zone_blocks = 0;
sector_t block = 0;
@@ -412,8 +414,6 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
int ret;
u8 same;
- sdkp->zone_blocks = 0;
-
/* Get a buffer */
buf = kmalloc(SD_ZBC_BUF_SIZE, GFP_KERNEL);
if (!buf)
@@ -445,16 +445,17 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
/* Parse zone descriptors */
while (rec < buf + buf_len) {
- zone_blocks = get_unaligned_be64(&rec[8]);
- if (sdkp->zone_blocks == 0) {
- sdkp->zone_blocks = zone_blocks;
- } else if (zone_blocks != sdkp->zone_blocks &&
- (block + zone_blocks < sdkp->capacity
- || zone_blocks > sdkp->zone_blocks)) {
- zone_blocks = 0;
+ u64 this_zone_blocks = get_unaligned_be64(&rec[8]);
+
+ if (zone_blocks == 0) {
+ zone_blocks = this_zone_blocks;
+ } else if (this_zone_blocks != zone_blocks &&
+ (block + this_zone_blocks < sdkp->capacity
+ || this_zone_blocks > zone_blocks)) {
+ this_zone_blocks = 0;
goto out;
}
- block += zone_blocks;
+ block += this_zone_blocks;
rec += 64;
}
@@ -467,8 +468,6 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
} while (block < sdkp->capacity);
- zone_blocks = sdkp->zone_blocks;
-
out:
if (!zone_blocks) {
if (sdkp->first_scan)
@@ -488,8 +487,7 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
"Zone size too large\n");
ret = -ENODEV;
} else {
- sdkp->zone_blocks = zone_blocks;
- sdkp->zone_shift = ilog2(zone_blocks);
+ ret = zone_blocks;
}
out_free:
@@ -500,15 +498,14 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
/**
* sd_zbc_alloc_zone_bitmap - Allocate a zone bitmap (one bit per zone).
- * @sdkp: The disk of the bitmap
+ * @nr_zones: Number of zones to allocate space for.
+ * @numa_node: NUMA node to allocate the memory from.
*/
-static inline unsigned long *sd_zbc_alloc_zone_bitmap(struct scsi_disk *sdkp)
+static inline unsigned long *
+sd_zbc_alloc_zone_bitmap(u32 nr_zones, int numa_node)
{
- struct request_queue *q = sdkp->disk->queue;
-
- return kzalloc_node(BITS_TO_LONGS(sdkp->nr_zones)
- * sizeof(unsigned long),
- GFP_KERNEL, q->node);
+ return kzalloc_node(BITS_TO_LONGS(nr_zones) * sizeof(unsigned long),
+ GFP_KERNEL, numa_node);
}
/**
@@ -516,6 +513,7 @@ static inline unsigned long *sd_zbc_alloc_zone_bitmap(struct scsi_disk *sdkp)
* @sdkp: disk used
* @buf: report reply buffer
* @buflen: length of @buf
+ * @zone_shift: logarithm base 2 of the number of blocks in a zone
* @seq_zones_bitmap: bitmap of sequential zones to set
*
* Parse reported zone descriptors in @buf to identify sequential zones and
@@ -525,7 +523,7 @@ static inline unsigned long *sd_zbc_alloc_zone_bitmap(struct scsi_disk *sdkp)
* Return the LBA after the last zone reported.
*/
static sector_t sd_zbc_get_seq_zones(struct scsi_disk *sdkp, unsigned char *buf,
- unsigned int buflen,
+ unsigned int buflen, u32 zone_shift,
unsigned long *seq_zones_bitmap)
{
sector_t lba, next_lba = sdkp->capacity;
@@ -544,7 +542,7 @@ static sector_t sd_zbc_get_seq_zones(struct scsi_disk *sdkp, unsigned char *buf,
if (type != ZBC_ZONE_TYPE_CONV &&
cond != ZBC_ZONE_COND_READONLY &&
cond != ZBC_ZONE_COND_OFFLINE)
- set_bit(lba >> sdkp->zone_shift, seq_zones_bitmap);
+ set_bit(lba >> zone_shift, seq_zones_bitmap);
next_lba = lba + get_unaligned_be64(&rec[8]);
rec += 64;
}
@@ -553,12 +551,16 @@ static sector_t sd_zbc_get_seq_zones(struct scsi_disk *sdkp, unsigned char *buf,
}
/**
- * sd_zbc_setup_seq_zones_bitmap - Initialize the disk seq zone bitmap.
+ * sd_zbc_setup_seq_zones_bitmap - Initialize a seq zone bitmap.
* @sdkp: target disk
+ * @zone_shift: logarithm base 2 of the number of blocks in a zone
+ * @nr_zones: number of zones to set up a seq zone bitmap for
*
* Allocate a zone bitmap and initialize it by identifying sequential zones.
*/
-static int sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp)
+static unsigned long *
+sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp, u32 zone_shift,
+ u32 nr_zones)
{
struct request_queue *q = sdkp->disk->queue;
unsigned long *seq_zones_bitmap;
@@ -566,9 +568,9 @@ static int sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp)
unsigned char *buf;
int ret = -ENOMEM;
- seq_zones_bitmap = sd_zbc_alloc_zone_bitmap(sdkp);
+ seq_zones_bitmap = sd_zbc_alloc_zone_bitmap(nr_zones, q->node);
if (!seq_zones_bitmap)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
buf = kmalloc(SD_ZBC_BUF_SIZE, GFP_KERNEL);
if (!buf)
@@ -579,7 +581,7 @@ static int sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp)
if (ret)
goto out;
lba = sd_zbc_get_seq_zones(sdkp, buf, SD_ZBC_BUF_SIZE,
- seq_zones_bitmap);
+ zone_shift, seq_zones_bitmap);
}
if (lba != sdkp->capacity) {
@@ -591,12 +593,9 @@ static int sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp)
kfree(buf);
if (ret) {
kfree(seq_zones_bitmap);
- return ret;
+ return ERR_PTR(ret);
}
-
- q->seq_zones_bitmap = seq_zones_bitmap;
-
- return 0;
+ return seq_zones_bitmap;
}
static void sd_zbc_cleanup(struct scsi_disk *sdkp)
@@ -612,44 +611,64 @@ static void sd_zbc_cleanup(struct scsi_disk *sdkp)
q->nr_zones = 0;
}
-static int sd_zbc_setup(struct scsi_disk *sdkp)
+static int sd_zbc_setup(struct scsi_disk *sdkp, u32 zone_blocks)
{
struct request_queue *q = sdkp->disk->queue;
+ u32 zone_shift = ilog2(zone_blocks);
+ u32 nr_zones;
int ret;
- /* READ16/WRITE16 is mandatory for ZBC disks */
- sdkp->device->use_16_for_rw = 1;
- sdkp->device->use_10_for_rw = 0;
-
/* chunk_sectors indicates the zone size */
- blk_queue_chunk_sectors(sdkp->disk->queue,
- logical_to_sectors(sdkp->device, sdkp->zone_blocks));
- sdkp->nr_zones =
- round_up(sdkp->capacity, sdkp->zone_blocks) >> sdkp->zone_shift;
+ blk_queue_chunk_sectors(q,
+ logical_to_sectors(sdkp->device, zone_blocks));
+ nr_zones = round_up(sdkp->capacity, zone_blocks) >> zone_shift;
/*
* Initialize the device request queue information if the number
* of zones changed.
*/
- if (sdkp->nr_zones != q->nr_zones) {
+ if (nr_zones != sdkp->nr_zones || nr_zones != q->nr_zones) {
+ unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL;
+ size_t zone_bitmap_size;
- sd_zbc_cleanup(sdkp);
-
- q->nr_zones = sdkp->nr_zones;
- if (sdkp->nr_zones) {
- q->seq_zones_wlock = sd_zbc_alloc_zone_bitmap(sdkp);
- if (!q->seq_zones_wlock) {
+ if (nr_zones) {
+ seq_zones_wlock = sd_zbc_alloc_zone_bitmap(nr_zones,
+ q->node);
+ if (!seq_zones_wlock) {
ret = -ENOMEM;
goto err;
}
- ret = sd_zbc_setup_seq_zones_bitmap(sdkp);
- if (ret) {
- sd_zbc_cleanup(sdkp);
+ seq_zones_bitmap = sd_zbc_setup_seq_zones_bitmap(sdkp,
+ zone_shift, nr_zones);
+ if (IS_ERR(seq_zones_bitmap)) {
+ ret = PTR_ERR(seq_zones_bitmap);
+ kfree(seq_zones_wlock);
goto err;
}
}
+ zone_bitmap_size = BITS_TO_LONGS(nr_zones) *
+ sizeof(unsigned long);
+ blk_mq_freeze_queue(q);
+ if (q->nr_zones != nr_zones) {
+ /* READ16/WRITE16 is mandatory for ZBC disks */
+ sdkp->device->use_16_for_rw = 1;
+ sdkp->device->use_10_for_rw = 0;
+ sdkp->zone_blocks = zone_blocks;
+ sdkp->zone_shift = zone_shift;
+ sdkp->nr_zones = nr_zones;
+ q->nr_zones = nr_zones;
+ swap(q->seq_zones_wlock, seq_zones_wlock);
+ swap(q->seq_zones_bitmap, seq_zones_bitmap);
+ } else if (memcmp(q->seq_zones_bitmap, seq_zones_bitmap,
+ zone_bitmap_size) != 0) {
+ memcpy(q->seq_zones_bitmap, seq_zones_bitmap,
+ zone_bitmap_size);
+ }
+ blk_mq_unfreeze_queue(q);
+ kfree(seq_zones_wlock);
+ kfree(seq_zones_bitmap);
}
return 0;
@@ -661,6 +680,7 @@ static int sd_zbc_setup(struct scsi_disk *sdkp)
int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
{
+ int64_t zone_blocks;
int ret;
if (!sd_is_zoned(sdkp))
@@ -697,12 +717,16 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
* Check zone size: only devices with a constant zone size (except
* an eventual last runt zone) that is a power of 2 are supported.
*/
- ret = sd_zbc_check_zone_size(sdkp);
- if (ret)
+ zone_blocks = sd_zbc_check_zone_size(sdkp);
+ ret = -EFBIG;
+ if (zone_blocks != (u32)zone_blocks)
+ goto err;
+ ret = zone_blocks;
+ if (ret < 0)
goto err;
/* The drive satisfies the kernel restrictions: set it up */
- ret = sd_zbc_setup(sdkp);
+ ret = sd_zbc_setup(sdkp, zone_blocks);
if (ret)
goto err;
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index c198b963..6fc58e2 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -66,7 +66,6 @@ static int sg_version_num = 30536; /* 2 digits for each component */
static char *sg_version_date = "20140603";
static int sg_proc_init(void);
-static void sg_proc_cleanup(void);
#endif
#define SG_ALLOW_DIO_DEF 0
@@ -1661,7 +1660,7 @@ static void __exit
exit_sg(void)
{
#ifdef CONFIG_SCSI_PROC_FS
- sg_proc_cleanup();
+ remove_proc_subtree("scsi/sg", NULL);
#endif /* CONFIG_SCSI_PROC_FS */
scsi_unregister_interface(&sg_interface);
class_destroy(sg_sysfs_class);
@@ -1715,7 +1714,7 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
* does not sleep except under memory pressure.
*/
rq = blk_get_request(q, hp->dxfer_direction == SG_DXFER_TO_DEV ?
- REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, GFP_KERNEL);
+ REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
if (IS_ERR(rq)) {
kfree(long_cmdp);
return PTR_ERR(rq);
@@ -1894,7 +1893,7 @@ sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size)
num = (rem_sz > scatter_elem_sz_prev) ?
scatter_elem_sz_prev : rem_sz;
- schp->pages[k] = alloc_pages(gfp_mask, order);
+ schp->pages[k] = alloc_pages(gfp_mask | __GFP_ZERO, order);
if (!schp->pages[k])
goto out;
@@ -2274,11 +2273,6 @@ sg_get_dev(int dev)
}
#ifdef CONFIG_SCSI_PROC_FS
-
-static struct proc_dir_entry *sg_proc_sgp = NULL;
-
-static char sg_proc_sg_dirname[] = "scsi/sg";
-
static int sg_proc_seq_show_int(struct seq_file *s, void *v);
static int sg_proc_single_open_adio(struct inode *inode, struct file *file);
@@ -2306,37 +2300,11 @@ static const struct file_operations dressz_fops = {
};
static int sg_proc_seq_show_version(struct seq_file *s, void *v);
-static int sg_proc_single_open_version(struct inode *inode, struct file *file);
-static const struct file_operations version_fops = {
- .owner = THIS_MODULE,
- .open = sg_proc_single_open_version,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int sg_proc_seq_show_devhdr(struct seq_file *s, void *v);
-static int sg_proc_single_open_devhdr(struct inode *inode, struct file *file);
-static const struct file_operations devhdr_fops = {
- .owner = THIS_MODULE,
- .open = sg_proc_single_open_devhdr,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int sg_proc_seq_show_dev(struct seq_file *s, void *v);
-static int sg_proc_open_dev(struct inode *inode, struct file *file);
static void * dev_seq_start(struct seq_file *s, loff_t *pos);
static void * dev_seq_next(struct seq_file *s, void *v, loff_t *pos);
static void dev_seq_stop(struct seq_file *s, void *v);
-static const struct file_operations dev_fops = {
- .owner = THIS_MODULE,
- .open = sg_proc_open_dev,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
static const struct seq_operations dev_seq_ops = {
.start = dev_seq_start,
.next = dev_seq_next,
@@ -2345,14 +2313,6 @@ static const struct seq_operations dev_seq_ops = {
};
static int sg_proc_seq_show_devstrs(struct seq_file *s, void *v);
-static int sg_proc_open_devstrs(struct inode *inode, struct file *file);
-static const struct file_operations devstrs_fops = {
- .owner = THIS_MODULE,
- .open = sg_proc_open_devstrs,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
static const struct seq_operations devstrs_seq_ops = {
.start = dev_seq_start,
.next = dev_seq_next,
@@ -2361,14 +2321,6 @@ static const struct seq_operations devstrs_seq_ops = {
};
static int sg_proc_seq_show_debug(struct seq_file *s, void *v);
-static int sg_proc_open_debug(struct inode *inode, struct file *file);
-static const struct file_operations debug_fops = {
- .owner = THIS_MODULE,
- .open = sg_proc_open_debug,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
static const struct seq_operations debug_seq_ops = {
.start = dev_seq_start,
.next = dev_seq_next,
@@ -2376,52 +2328,25 @@ static const struct seq_operations debug_seq_ops = {
.show = sg_proc_seq_show_debug,
};
-
-struct sg_proc_leaf {
- const char * name;
- const struct file_operations * fops;
-};
-
-static const struct sg_proc_leaf sg_proc_leaf_arr[] = {
- {"allow_dio", &adio_fops},
- {"debug", &debug_fops},
- {"def_reserved_size", &dressz_fops},
- {"device_hdr", &devhdr_fops},
- {"devices", &dev_fops},
- {"device_strs", &devstrs_fops},
- {"version", &version_fops}
-};
-
static int
sg_proc_init(void)
{
- int num_leaves = ARRAY_SIZE(sg_proc_leaf_arr);
- int k;
+ struct proc_dir_entry *p;
- sg_proc_sgp = proc_mkdir(sg_proc_sg_dirname, NULL);
- if (!sg_proc_sgp)
+ p = proc_mkdir("scsi/sg", NULL);
+ if (!p)
return 1;
- for (k = 0; k < num_leaves; ++k) {
- const struct sg_proc_leaf *leaf = &sg_proc_leaf_arr[k];
- umode_t mask = leaf->fops->write ? S_IRUGO | S_IWUSR : S_IRUGO;
- proc_create(leaf->name, mask, sg_proc_sgp, leaf->fops);
- }
+
+ proc_create("allow_dio", S_IRUGO | S_IWUSR, p, &adio_fops);
+ proc_create_seq("debug", S_IRUGO, p, &debug_seq_ops);
+ proc_create("def_reserved_size", S_IRUGO | S_IWUSR, p, &dressz_fops);
+ proc_create_single("device_hdr", S_IRUGO, p, sg_proc_seq_show_devhdr);
+ proc_create_seq("devices", S_IRUGO, p, &dev_seq_ops);
+ proc_create_seq("device_strs", S_IRUGO, p, &devstrs_seq_ops);
+ proc_create_single("version", S_IRUGO, p, sg_proc_seq_show_version);
return 0;
}
-static void
-sg_proc_cleanup(void)
-{
- int k;
- int num_leaves = ARRAY_SIZE(sg_proc_leaf_arr);
-
- if (!sg_proc_sgp)
- return;
- for (k = 0; k < num_leaves; ++k)
- remove_proc_entry(sg_proc_leaf_arr[k].name, sg_proc_sgp);
- remove_proc_entry(sg_proc_sg_dirname, NULL);
-}
-
static int sg_proc_seq_show_int(struct seq_file *s, void *v)
{
@@ -2482,22 +2407,12 @@ static int sg_proc_seq_show_version(struct seq_file *s, void *v)
return 0;
}
-static int sg_proc_single_open_version(struct inode *inode, struct file *file)
-{
- return single_open(file, sg_proc_seq_show_version, NULL);
-}
-
static int sg_proc_seq_show_devhdr(struct seq_file *s, void *v)
{
seq_puts(s, "host\tchan\tid\tlun\ttype\topens\tqdepth\tbusy\tonline\n");
return 0;
}
-static int sg_proc_single_open_devhdr(struct inode *inode, struct file *file)
-{
- return single_open(file, sg_proc_seq_show_devhdr, NULL);
-}
-
struct sg_proc_deviter {
loff_t index;
size_t max;
@@ -2531,11 +2446,6 @@ static void dev_seq_stop(struct seq_file *s, void *v)
kfree(s->private);
}
-static int sg_proc_open_dev(struct inode *inode, struct file *file)
-{
- return seq_open(file, &dev_seq_ops);
-}
-
static int sg_proc_seq_show_dev(struct seq_file *s, void *v)
{
struct sg_proc_deviter * it = (struct sg_proc_deviter *) v;
@@ -2562,11 +2472,6 @@ static int sg_proc_seq_show_dev(struct seq_file *s, void *v)
return 0;
}
-static int sg_proc_open_devstrs(struct inode *inode, struct file *file)
-{
- return seq_open(file, &devstrs_seq_ops);
-}
-
static int sg_proc_seq_show_devstrs(struct seq_file *s, void *v)
{
struct sg_proc_deviter * it = (struct sg_proc_deviter *) v;
@@ -2650,11 +2555,6 @@ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp)
}
}
-static int sg_proc_open_debug(struct inode *inode, struct file *file)
-{
- return seq_open(file, &debug_seq_ops);
-}
-
static int sg_proc_seq_show_debug(struct seq_file *s, void *v)
{
struct sg_proc_deviter * it = (struct sg_proc_deviter *) v;
diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c
index 2a21f2d..35fab1e 100644
--- a/drivers/scsi/sr_ioctl.c
+++ b/drivers/scsi/sr_ioctl.c
@@ -188,9 +188,13 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
struct scsi_device *SDev;
struct scsi_sense_hdr sshdr;
int result, err = 0, retries = 0;
+ unsigned char sense_buffer[SCSI_SENSE_BUFFERSIZE], *senseptr = NULL;
SDev = cd->device;
+ if (cgc->sense)
+ senseptr = sense_buffer;
+
retry:
if (!scsi_block_when_processing_errors(SDev)) {
err = -ENODEV;
@@ -198,10 +202,12 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
}
result = scsi_execute(SDev, cgc->cmd, cgc->data_direction,
- cgc->buffer, cgc->buflen,
- (unsigned char *)cgc->sense, &sshdr,
+ cgc->buffer, cgc->buflen, senseptr, &sshdr,
cgc->timeout, IOCTL_RETRIES, 0, 0, NULL);
+ if (cgc->sense)
+ memcpy(cgc->sense, sense_buffer, sizeof(*cgc->sense));
+
/* Minimal error checking. Ignore cases we know about, and report the rest. */
if (driver_byte(result) != 0) {
switch (sshdr.sense_key) {
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 6c39948..a427ce9 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -545,7 +545,7 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd,
req = blk_get_request(SRpnt->stp->device->request_queue,
data_direction == DMA_TO_DEVICE ?
- REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, GFP_KERNEL);
+ REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
if (IS_ERR(req))
return DRIVER_ERROR << 24;
rq = scsi_req(req);
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 8c51d62..a2ec0bc 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1722,11 +1722,14 @@ static int storvsc_probe(struct hv_device *device,
max_targets = STORVSC_MAX_TARGETS;
max_channels = STORVSC_MAX_CHANNELS;
/*
- * On Windows8 and above, we support sub-channels for storage.
+ * On Windows8 and above, we support sub-channels for storage
+ * on SCSI and FC controllers.
* The number of sub-channels offerred is based on the number of
* VCPUs in the guest.
*/
- max_sub_channels = (num_cpus / storvsc_vcpus_per_sub_channel);
+ if (!dev_is_ide)
+ max_sub_channels =
+ (num_cpus - 1) / storvsc_vcpus_per_sub_channel;
}
scsi_driver.can_queue = (max_outstanding_req_per_channel *
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index c5b1bf1..d0a1674 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -276,6 +276,35 @@ static inline void ufshcd_remove_non_printable(char *val)
*val = ' ';
}
+static void ufshcd_add_cmd_upiu_trace(struct ufs_hba *hba, unsigned int tag,
+ const char *str)
+{
+ struct utp_upiu_req *rq = hba->lrb[tag].ucd_req_ptr;
+
+ trace_ufshcd_upiu(dev_name(hba->dev), str, &rq->header, &rq->sc.cdb);
+}
+
+static void ufshcd_add_query_upiu_trace(struct ufs_hba *hba, unsigned int tag,
+ const char *str)
+{
+ struct utp_upiu_req *rq = hba->lrb[tag].ucd_req_ptr;
+
+ trace_ufshcd_upiu(dev_name(hba->dev), str, &rq->header, &rq->qr);
+}
+
+static void ufshcd_add_tm_upiu_trace(struct ufs_hba *hba, unsigned int tag,
+ const char *str)
+{
+ struct utp_task_req_desc *descp;
+ struct utp_upiu_task_req *task_req;
+ int off = (int)tag - hba->nutrs;
+
+ descp = &hba->utmrdl_base_addr[off];
+ task_req = (struct utp_upiu_task_req *)descp->task_req_upiu;
+ trace_ufshcd_upiu(dev_name(hba->dev), str, &task_req->header,
+ &task_req->input_param1);
+}
+
static void ufshcd_add_command_trace(struct ufs_hba *hba,
unsigned int tag, const char *str)
{
@@ -285,6 +314,9 @@ static void ufshcd_add_command_trace(struct ufs_hba *hba,
struct ufshcd_lrb *lrbp;
int transfer_len = -1;
+ /* trace UPIU also */
+ ufshcd_add_cmd_upiu_trace(hba, tag, str);
+
if (!trace_ufshcd_command_enabled())
return;
@@ -2550,6 +2582,7 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba,
hba->dev_cmd.complete = &wait;
+ ufshcd_add_query_upiu_trace(hba, tag, "query_send");
/* Make sure descriptors are ready before ringing the doorbell */
wmb();
spin_lock_irqsave(hba->host->host_lock, flags);
@@ -2559,6 +2592,9 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba,
err = ufshcd_wait_for_dev_cmd(hba, lrbp, timeout);
+ ufshcd_add_query_upiu_trace(hba, tag,
+ err ? "query_complete_err" : "query_complete");
+
out_put_tag:
ufshcd_put_dev_cmd_tag(hba, tag);
wake_up(&hba->dev_cmd.tag_wq);
@@ -5443,11 +5479,14 @@ static int ufshcd_issue_tm_cmd(struct ufs_hba *hba, int lun_id, int task_id,
spin_unlock_irqrestore(host->host_lock, flags);
+ ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_send");
+
/* wait until the task management command is completed */
err = wait_event_timeout(hba->tm_wq,
test_bit(free_slot, &hba->tm_condition),
msecs_to_jiffies(TM_CMD_TIMEOUT));
if (!err) {
+ ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_complete_err");
dev_err(hba->dev, "%s: task management cmd 0x%.2x timed-out\n",
__func__, tm_function);
if (ufshcd_clear_tm_cmd(hba, free_slot))
@@ -5456,6 +5495,7 @@ static int ufshcd_issue_tm_cmd(struct ufs_hba *hba, int lun_id, int task_id,
err = -ETIMEDOUT;
} else {
err = ufshcd_task_req_compl(hba, free_slot, tm_response);
+ ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_complete");
}
clear_bit(free_slot, &hba->tm_condition);
@@ -6457,12 +6497,12 @@ static enum blk_eh_timer_return ufshcd_eh_timed_out(struct scsi_cmnd *scmd)
bool found = false;
if (!scmd || !scmd->device || !scmd->device->host)
- return BLK_EH_NOT_HANDLED;
+ return BLK_EH_DONE;
host = scmd->device->host;
hba = shost_priv(host);
if (!hba)
- return BLK_EH_NOT_HANDLED;
+ return BLK_EH_DONE;
spin_lock_irqsave(host->host_lock, flags);
@@ -6480,7 +6520,7 @@ static enum blk_eh_timer_return ufshcd_eh_timed_out(struct scsi_cmnd *scmd)
* SCSI command was not actually dispatched to UFS driver, otherwise
* let SCSI layer handle the error as usual.
*/
- return found ? BLK_EH_NOT_HANDLED : BLK_EH_RESET_TIMER;
+ return found ? BLK_EH_DONE : BLK_EH_RESET_TIMER;
}
static const struct attribute_group *ufshcd_driver_groups[] = {
diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c
index c374e3b..777e5f1 100644
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -609,7 +609,7 @@ static void pvscsi_complete_request(struct pvscsi_adapter *adapter,
break;
case BTSTAT_ABORTQUEUE:
- cmd->result = (DID_ABORT << 16);
+ cmd->result = (DID_BUS_BUSY << 16);
break;
case BTSTAT_SCSIPARITY:
diff --git a/drivers/slimbus/messaging.c b/drivers/slimbus/messaging.c
index 884419c..457ea1f 100644
--- a/drivers/slimbus/messaging.c
+++ b/drivers/slimbus/messaging.c
@@ -183,7 +183,7 @@ static u16 slim_slicesize(int code)
0, 1, 2, 3, 3, 4, 4, 5, 5, 5, 5, 6, 6, 6, 6, 7
};
- clamp(code, 1, (int)ARRAY_SIZE(sizetocode));
+ code = clamp(code, 1, (int)ARRAY_SIZE(sizetocode));
return sizetocode[code - 1];
}
diff --git a/drivers/soc/bcm/raspberrypi-power.c b/drivers/soc/bcm/raspberrypi-power.c
index fe96a8b..f7ed118 100644
--- a/drivers/soc/bcm/raspberrypi-power.c
+++ b/drivers/soc/bcm/raspberrypi-power.c
@@ -45,7 +45,7 @@ struct rpi_power_domains {
struct rpi_power_domain_packet {
u32 domain;
u32 on;
-} __packet;
+};
/*
* Asks the firmware to enable or disable power on a specific power
diff --git a/drivers/soc/lantiq/gphy.c b/drivers/soc/lantiq/gphy.c
index 8d865946..feeb17c 100644
--- a/drivers/soc/lantiq/gphy.c
+++ b/drivers/soc/lantiq/gphy.c
@@ -30,7 +30,6 @@ struct xway_gphy_priv {
struct clk *gphy_clk_gate;
struct reset_control *gphy_reset;
struct reset_control *gphy_reset2;
- struct notifier_block gphy_reboot_nb;
void __iomem *membase;
char *fw_name;
};
@@ -64,24 +63,6 @@ static const struct of_device_id xway_gphy_match[] = {
};
MODULE_DEVICE_TABLE(of, xway_gphy_match);
-static struct xway_gphy_priv *to_xway_gphy_priv(struct notifier_block *nb)
-{
- return container_of(nb, struct xway_gphy_priv, gphy_reboot_nb);
-}
-
-static int xway_gphy_reboot_notify(struct notifier_block *reboot_nb,
- unsigned long code, void *unused)
-{
- struct xway_gphy_priv *priv = to_xway_gphy_priv(reboot_nb);
-
- if (priv) {
- reset_control_assert(priv->gphy_reset);
- reset_control_assert(priv->gphy_reset2);
- }
-
- return NOTIFY_DONE;
-}
-
static int xway_gphy_load(struct device *dev, struct xway_gphy_priv *priv,
dma_addr_t *dev_addr)
{
@@ -205,14 +186,6 @@ static int xway_gphy_probe(struct platform_device *pdev)
reset_control_deassert(priv->gphy_reset);
reset_control_deassert(priv->gphy_reset2);
- /* assert the gphy reset because it can hang after a reboot: */
- priv->gphy_reboot_nb.notifier_call = xway_gphy_reboot_notify;
- priv->gphy_reboot_nb.priority = -1;
-
- ret = register_reboot_notifier(&priv->gphy_reboot_nb);
- if (ret)
- dev_warn(dev, "Failed to register reboot notifier\n");
-
platform_set_drvdata(pdev, priv);
return ret;
@@ -220,21 +193,12 @@ static int xway_gphy_probe(struct platform_device *pdev)
static int xway_gphy_remove(struct platform_device *pdev)
{
- struct device *dev = &pdev->dev;
struct xway_gphy_priv *priv = platform_get_drvdata(pdev);
- int ret;
-
- reset_control_assert(priv->gphy_reset);
- reset_control_assert(priv->gphy_reset2);
iowrite32be(0, priv->membase);
clk_disable_unprepare(priv->gphy_clk_gate);
- ret = unregister_reboot_notifier(&priv->gphy_reboot_nb);
- if (ret)
- dev_warn(dev, "Failed to unregister reboot notifier\n");
-
return 0;
}
diff --git a/drivers/soc/tegra/pmc.c b/drivers/soc/tegra/pmc.c
index d9fcdb5..3e3d12c 100644
--- a/drivers/soc/tegra/pmc.c
+++ b/drivers/soc/tegra/pmc.c
@@ -559,22 +559,28 @@ EXPORT_SYMBOL(tegra_powergate_remove_clamping);
int tegra_powergate_sequence_power_up(unsigned int id, struct clk *clk,
struct reset_control *rst)
{
- struct tegra_powergate pg;
+ struct tegra_powergate *pg;
int err;
if (!tegra_powergate_is_available(id))
return -EINVAL;
- pg.id = id;
- pg.clks = &clk;
- pg.num_clks = 1;
- pg.reset = rst;
- pg.pmc = pmc;
+ pg = kzalloc(sizeof(*pg), GFP_KERNEL);
+ if (!pg)
+ return -ENOMEM;
- err = tegra_powergate_power_up(&pg, false);
+ pg->id = id;
+ pg->clks = &clk;
+ pg->num_clks = 1;
+ pg->reset = rst;
+ pg->pmc = pmc;
+
+ err = tegra_powergate_power_up(pg, false);
if (err)
pr_err("failed to turn on partition %d: %d\n", id, err);
+ kfree(pg);
+
return err;
}
EXPORT_SYMBOL(tegra_powergate_sequence_power_up);
diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c
index d5f3a70..283b283 100644
--- a/drivers/soundwire/bus_type.c
+++ b/drivers/soundwire/bus_type.c
@@ -83,17 +83,16 @@ static int sdw_drv_probe(struct device *dev)
* attach to power domain but don't turn on (last arg)
*/
ret = dev_pm_domain_attach(dev, false);
- if (ret != -EPROBE_DEFER) {
- ret = drv->probe(slave, id);
- if (ret) {
- dev_err(dev, "Probe of %s failed: %d\n", drv->name, ret);
- dev_pm_domain_detach(dev, false);
- }
- }
-
if (ret)
return ret;
+ ret = drv->probe(slave, id);
+ if (ret) {
+ dev_err(dev, "Probe of %s failed: %d\n", drv->name, ret);
+ dev_pm_domain_detach(dev, false);
+ return ret;
+ }
+
/* device is probed so let's read the properties now */
if (slave->ops && slave->ops->read_prop)
slave->ops->read_prop(slave);
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 2d4146c..ad5d68e 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -47,6 +47,13 @@
if SPI_MASTER
+config SPI_MEM
+ bool "SPI memory extension"
+ help
+ Enable this option if you want to enable the SPI memory extension.
+ This extension is meant to simplify interaction with SPI memories
+ by providing a high-level interface to send memory-like commands.
+
comment "SPI Master Controller Drivers"
config SPI_ALTERA
@@ -71,7 +78,6 @@
config SPI_ATMEL
tristate "Atmel SPI Controller"
- depends on HAS_DMA
depends on ARCH_AT91 || COMPILE_TEST
help
This selects a driver for the Atmel SPI Controller, present on
@@ -115,14 +121,6 @@
"universal SPI master", and the regular SPI controller.
This driver is for the universal/auxiliary SPI controller.
-config SPI_BCM53XX
- tristate "Broadcom BCM53xx SPI controller"
- depends on ARCH_BCM_5301X
- depends on BCMA_POSSIBLE
- select BCMA
- help
- Enable support for the SPI controller on Broadcom BCM53xx ARM SoCs.
-
config SPI_BCM63XX
tristate "Broadcom BCM63xx SPI controller"
depends on BCM63XX || COMPILE_TEST
@@ -233,7 +231,6 @@
config SPI_EP93XX
tristate "Cirrus Logic EP93xx SPI controller"
- depends on HAS_DMA
depends on ARCH_EP93XX || COMPILE_TEST
help
This enables using the Cirrus EP93xx SPI controller in master
@@ -355,7 +352,6 @@
config SPI_FSL_DSPI
tristate "Freescale DSPI controller"
select REGMAP_MMIO
- depends on HAS_DMA
depends on SOC_VF610 || SOC_LS1021A || ARCH_LAYERSCAPE || M5441x || COMPILE_TEST
help
This enables support for the Freescale DSPI controller in master
@@ -431,7 +427,6 @@
config SPI_OMAP24XX
tristate "McSPI driver for OMAP"
- depends on HAS_DMA
depends on ARCH_OMAP2PLUS || COMPILE_TEST
select SG_SPLIT
help
@@ -440,7 +435,6 @@
config SPI_TI_QSPI
tristate "DRA7xxx QSPI controller support"
- depends on HAS_DMA
depends on ARCH_OMAP2PLUS || COMPILE_TEST
help
QSPI master controller for DRA7xxx used for flash devices.
@@ -469,7 +463,6 @@
config SPI_PIC32_SQI
tristate "Microchip PIC32 Quad SPI driver"
depends on MACH_PIC32 || COMPILE_TEST
- depends on HAS_DMA
help
SPI driver for PIC32 Quad SPI controller.
@@ -572,7 +565,7 @@
config SPI_SH_MSIOF
tristate "SuperH MSIOF SPI controller"
- depends on HAVE_CLK && HAS_DMA
+ depends on HAVE_CLK
depends on ARCH_SHMOBILE || ARCH_RENESAS || COMPILE_TEST
help
SPI driver for SuperH and SH Mobile MSIOF blocks.
@@ -650,7 +643,7 @@
config SPI_TEGRA114
tristate "NVIDIA Tegra114 SPI Controller"
depends on (ARCH_TEGRA && TEGRA20_APB_DMA) || COMPILE_TEST
- depends on RESET_CONTROLLER && HAS_DMA
+ depends on RESET_CONTROLLER
help
SPI driver for NVIDIA Tegra114 SPI Controller interface. This controller
is different than the older SoCs SPI controller and also register interface
@@ -668,7 +661,7 @@
config SPI_TEGRA20_SLINK
tristate "Nvidia Tegra20/Tegra30 SLINK Controller"
depends on (ARCH_TEGRA && TEGRA20_APB_DMA) || COMPILE_TEST
- depends on RESET_CONTROLLER && HAS_DMA
+ depends on RESET_CONTROLLER
help
SPI driver for Nvidia Tegra20/Tegra30 SLINK Controller interface.
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index b935f10..cb1f437 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -8,6 +8,7 @@
# small core, mostly translating board-specific
# config declarations into driver model code
obj-$(CONFIG_SPI_MASTER) += spi.o
+obj-$(CONFIG_SPI_MEM) += spi-mem.o
obj-$(CONFIG_SPI_SPIDEV) += spidev.o
obj-$(CONFIG_SPI_LOOPBACK_TEST) += spi-loopback-test.o
@@ -20,7 +21,6 @@
obj-$(CONFIG_SPI_AXI_SPI_ENGINE) += spi-axi-spi-engine.o
obj-$(CONFIG_SPI_BCM2835) += spi-bcm2835.o
obj-$(CONFIG_SPI_BCM2835AUX) += spi-bcm2835aux.o
-obj-$(CONFIG_SPI_BCM53XX) += spi-bcm53xx.o
obj-$(CONFIG_SPI_BCM63XX) += spi-bcm63xx.o
obj-$(CONFIG_SPI_BCM63XX_HSSPI) += spi-bcm63xx-hsspi.o
obj-$(CONFIG_SPI_BCM_QSPI) += spi-iproc-qspi.o spi-brcmstb-qspi.o spi-bcm-qspi.o
diff --git a/drivers/spi/internals.h b/drivers/spi/internals.h
new file mode 100644
index 0000000..4a28a83
--- /dev/null
+++ b/drivers/spi/internals.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (C) 2018 Exceet Electronics GmbH
+ * Copyright (C) 2018 Bootlin
+ *
+ * Author: Boris Brezillon <boris.brezillon@bootlin.com>
+ *
+ * Helpers needed by the spi or spi-mem logic. Should not be used outside of
+ * spi-mem.c and spi.c.
+ */
+
+#ifndef __LINUX_SPI_INTERNALS_H
+#define __LINUX_SPI_INTERNALS_H
+
+#include <linux/device.h>
+#include <linux/dma-direction.h>
+#include <linux/scatterlist.h>
+#include <linux/spi/spi.h>
+
+void spi_flush_queue(struct spi_controller *ctrl);
+
+#ifdef CONFIG_HAS_DMA
+int spi_map_buf(struct spi_controller *ctlr, struct device *dev,
+ struct sg_table *sgt, void *buf, size_t len,
+ enum dma_data_direction dir);
+void spi_unmap_buf(struct spi_controller *ctlr, struct device *dev,
+ struct sg_table *sgt, enum dma_data_direction dir);
+#else /* !CONFIG_HAS_DMA */
+static inline int spi_map_buf(struct spi_controller *ctlr, struct device *dev,
+ struct sg_table *sgt, void *buf, size_t len,
+ enum dma_data_direction dir)
+{
+ return -EINVAL;
+}
+
+static inline void spi_unmap_buf(struct spi_controller *ctlr,
+ struct device *dev, struct sg_table *sgt,
+ enum dma_data_direction dir)
+{
+}
+#endif /* CONFIG_HAS_DMA */
+
+#endif /* __LINUX_SPI_INTERNALS_H */
diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c
index 1596d35..8612525 100644
--- a/drivers/spi/spi-bcm-qspi.c
+++ b/drivers/spi/spi-bcm-qspi.c
@@ -30,6 +30,7 @@
#include <linux/platform_device.h>
#include <linux/slab.h>
#include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
#include <linux/sysfs.h>
#include <linux/types.h>
#include "spi-bcm-qspi.h"
@@ -215,10 +216,10 @@ struct bcm_qspi {
int bspi_maj_rev;
int bspi_min_rev;
int bspi_enabled;
- struct spi_flash_read_message *bspi_rf_msg;
- u32 bspi_rf_msg_idx;
- u32 bspi_rf_msg_len;
- u32 bspi_rf_msg_status;
+ const struct spi_mem_op *bspi_rf_op;
+ u32 bspi_rf_op_idx;
+ u32 bspi_rf_op_len;
+ u32 bspi_rf_op_status;
struct bcm_xfer_mode xfer_mode;
u32 s3_strap_override_ctrl;
bool bspi_mode;
@@ -313,26 +314,26 @@ static inline void bcm_qspi_bspi_lr_clear(struct bcm_qspi *qspi)
static void bcm_qspi_bspi_lr_data_read(struct bcm_qspi *qspi)
{
- u32 *buf = (u32 *)qspi->bspi_rf_msg->buf;
+ u32 *buf = (u32 *)qspi->bspi_rf_op->data.buf.in;
u32 data = 0;
- dev_dbg(&qspi->pdev->dev, "xfer %p rx %p rxlen %d\n", qspi->bspi_rf_msg,
- qspi->bspi_rf_msg->buf, qspi->bspi_rf_msg_len);
+ dev_dbg(&qspi->pdev->dev, "xfer %p rx %p rxlen %d\n", qspi->bspi_rf_op,
+ qspi->bspi_rf_op->data.buf.in, qspi->bspi_rf_op_len);
while (!bcm_qspi_bspi_lr_is_fifo_empty(qspi)) {
data = bcm_qspi_bspi_lr_read_fifo(qspi);
- if (likely(qspi->bspi_rf_msg_len >= 4) &&
+ if (likely(qspi->bspi_rf_op_len >= 4) &&
IS_ALIGNED((uintptr_t)buf, 4)) {
- buf[qspi->bspi_rf_msg_idx++] = data;
- qspi->bspi_rf_msg_len -= 4;
+ buf[qspi->bspi_rf_op_idx++] = data;
+ qspi->bspi_rf_op_len -= 4;
} else {
/* Read out remaining bytes, make sure*/
- u8 *cbuf = (u8 *)&buf[qspi->bspi_rf_msg_idx];
+ u8 *cbuf = (u8 *)&buf[qspi->bspi_rf_op_idx];
data = cpu_to_le32(data);
- while (qspi->bspi_rf_msg_len) {
+ while (qspi->bspi_rf_op_len) {
*cbuf++ = (u8)data;
data >>= 8;
- qspi->bspi_rf_msg_len--;
+ qspi->bspi_rf_op_len--;
}
}
}
@@ -349,14 +350,12 @@ static void bcm_qspi_bspi_set_xfer_params(struct bcm_qspi *qspi, u8 cmd_byte,
}
static int bcm_qspi_bspi_set_flex_mode(struct bcm_qspi *qspi,
- struct spi_flash_read_message *msg,
- int hp)
+ const struct spi_mem_op *op, int hp)
{
int bpc = 0, bpp = 0;
- u8 command = msg->read_opcode;
- int width = msg->data_nbits ? msg->data_nbits : SPI_NBITS_SINGLE;
- int addrlen = msg->addr_width;
- int addr_nbits = msg->addr_nbits ? msg->addr_nbits : SPI_NBITS_SINGLE;
+ u8 command = op->cmd.opcode;
+ int width = op->cmd.buswidth ? op->cmd.buswidth : SPI_NBITS_SINGLE;
+ int addrlen = op->addr.nbytes * 8;
int flex_mode = 1;
dev_dbg(&qspi->pdev->dev, "set flex mode w %x addrlen %x hp %d\n",
@@ -365,7 +364,7 @@ static int bcm_qspi_bspi_set_flex_mode(struct bcm_qspi *qspi,
if (addrlen == BSPI_ADDRLEN_4BYTES)
bpp = BSPI_BPP_ADDR_SELECT_MASK;
- bpp |= msg->dummy_bytes * (8/addr_nbits);
+ bpp |= (op->dummy.nbytes * 8) / op->dummy.buswidth;
switch (width) {
case SPI_NBITS_SINGLE:
@@ -397,11 +396,10 @@ static int bcm_qspi_bspi_set_flex_mode(struct bcm_qspi *qspi,
}
static int bcm_qspi_bspi_set_override(struct bcm_qspi *qspi,
- struct spi_flash_read_message *msg,
- int hp)
+ const struct spi_mem_op *op, int hp)
{
- int width = msg->data_nbits ? msg->data_nbits : SPI_NBITS_SINGLE;
- int addrlen = msg->addr_width;
+ int width = op->data.buswidth ? op->data.buswidth : SPI_NBITS_SINGLE;
+ int addrlen = op->addr.nbytes;
u32 data = bcm_qspi_read(qspi, BSPI, BSPI_STRAP_OVERRIDE_CTRL);
dev_dbg(&qspi->pdev->dev, "set override mode w %x addrlen %x hp %d\n",
@@ -437,17 +435,17 @@ static int bcm_qspi_bspi_set_override(struct bcm_qspi *qspi,
/* set the override mode */
data |= BSPI_STRAP_OVERRIDE_CTRL_OVERRIDE;
bcm_qspi_write(qspi, BSPI, BSPI_STRAP_OVERRIDE_CTRL, data);
- bcm_qspi_bspi_set_xfer_params(qspi, msg->read_opcode, 0, 0, 0);
+ bcm_qspi_bspi_set_xfer_params(qspi, op->cmd.opcode, 0, 0, 0);
return 0;
}
static int bcm_qspi_bspi_set_mode(struct bcm_qspi *qspi,
- struct spi_flash_read_message *msg, int hp)
+ const struct spi_mem_op *op, int hp)
{
int error = 0;
- int width = msg->data_nbits ? msg->data_nbits : SPI_NBITS_SINGLE;
- int addrlen = msg->addr_width;
+ int width = op->data.buswidth ? op->data.buswidth : SPI_NBITS_SINGLE;
+ int addrlen = op->addr.nbytes;
/* default mode */
qspi->xfer_mode.flex_mode = true;
@@ -460,12 +458,12 @@ static int bcm_qspi_bspi_set_mode(struct bcm_qspi *qspi,
if (val & mask || qspi->s3_strap_override_ctrl & mask) {
qspi->xfer_mode.flex_mode = false;
bcm_qspi_write(qspi, BSPI, BSPI_FLEX_MODE_ENABLE, 0);
- error = bcm_qspi_bspi_set_override(qspi, msg, hp);
+ error = bcm_qspi_bspi_set_override(qspi, op, hp);
}
}
if (qspi->xfer_mode.flex_mode)
- error = bcm_qspi_bspi_set_flex_mode(qspi, msg, hp);
+ error = bcm_qspi_bspi_set_flex_mode(qspi, op, hp);
if (error) {
dev_warn(&qspi->pdev->dev,
@@ -490,7 +488,7 @@ static int bcm_qspi_bspi_set_mode(struct bcm_qspi *qspi,
static void bcm_qspi_enable_bspi(struct bcm_qspi *qspi)
{
- if (!has_bspi(qspi) || (qspi->bspi_enabled))
+ if (!has_bspi(qspi))
return;
qspi->bspi_enabled = 1;
@@ -505,7 +503,7 @@ static void bcm_qspi_enable_bspi(struct bcm_qspi *qspi)
static void bcm_qspi_disable_bspi(struct bcm_qspi *qspi)
{
- if (!has_bspi(qspi) || (!qspi->bspi_enabled))
+ if (!has_bspi(qspi))
return;
qspi->bspi_enabled = 0;
@@ -519,16 +517,19 @@ static void bcm_qspi_disable_bspi(struct bcm_qspi *qspi)
static void bcm_qspi_chip_select(struct bcm_qspi *qspi, int cs)
{
- u32 data = 0;
+ u32 rd = 0;
+ u32 wr = 0;
- if (qspi->curr_cs == cs)
- return;
if (qspi->base[CHIP_SELECT]) {
- data = bcm_qspi_read(qspi, CHIP_SELECT, 0);
- data = (data & ~0xff) | (1 << cs);
- bcm_qspi_write(qspi, CHIP_SELECT, 0, data);
+ rd = bcm_qspi_read(qspi, CHIP_SELECT, 0);
+ wr = (rd & ~0xff) | (1 << cs);
+ if (rd == wr)
+ return;
+ bcm_qspi_write(qspi, CHIP_SELECT, 0, wr);
usleep_range(10, 20);
}
+
+ dev_dbg(&qspi->pdev->dev, "using cs:%d\n", cs);
qspi->curr_cs = cs;
}
@@ -755,8 +756,13 @@ static int write_to_hw(struct bcm_qspi *qspi, struct spi_device *spi)
dev_dbg(&qspi->pdev->dev, "WR %04x\n", val);
}
mspi_cdram = MSPI_CDRAM_CONT_BIT;
- mspi_cdram |= (~(1 << spi->chip_select) &
- MSPI_CDRAM_PCS);
+
+ if (has_bspi(qspi))
+ mspi_cdram &= ~1;
+ else
+ mspi_cdram |= (~(1 << spi->chip_select) &
+ MSPI_CDRAM_PCS);
+
mspi_cdram |= ((tp.trans->bits_per_word <= 8) ? 0 :
MSPI_CDRAM_BITSE_BIT);
@@ -794,19 +800,20 @@ static int write_to_hw(struct bcm_qspi *qspi, struct spi_device *spi)
return slot;
}
-static int bcm_qspi_bspi_flash_read(struct spi_device *spi,
- struct spi_flash_read_message *msg)
+static int bcm_qspi_bspi_exec_mem_op(struct spi_device *spi,
+ const struct spi_mem_op *op)
{
struct bcm_qspi *qspi = spi_master_get_devdata(spi->master);
- u32 addr = 0, len, rdlen, len_words;
+ u32 addr = 0, len, rdlen, len_words, from = 0;
int ret = 0;
unsigned long timeo = msecs_to_jiffies(100);
struct bcm_qspi_soc_intc *soc_intc = qspi->soc_intc;
if (bcm_qspi_bspi_ver_three(qspi))
- if (msg->addr_width == BSPI_ADDRLEN_4BYTES)
+ if (op->addr.nbytes == BSPI_ADDRLEN_4BYTES)
return -EIO;
+ from = op->addr.val;
bcm_qspi_chip_select(qspi, spi->chip_select);
bcm_qspi_write(qspi, MSPI, MSPI_WRITE_LOCK, 0);
@@ -815,15 +822,15 @@ static int bcm_qspi_bspi_flash_read(struct spi_device *spi,
* the upper address byte to bspi
*/
if (bcm_qspi_bspi_ver_three(qspi) == false) {
- addr = msg->from & 0xff000000;
+ addr = from & 0xff000000;
bcm_qspi_write(qspi, BSPI,
BSPI_BSPI_FLASH_UPPER_ADDR_BYTE, addr);
}
if (!qspi->xfer_mode.flex_mode)
- addr = msg->from;
+ addr = from;
else
- addr = msg->from & 0x00ffffff;
+ addr = from & 0x00ffffff;
if (bcm_qspi_bspi_ver_three(qspi) == true)
addr = (addr + 0xc00000) & 0xffffff;
@@ -832,8 +839,8 @@ static int bcm_qspi_bspi_flash_read(struct spi_device *spi,
* read into the entire buffer by breaking the reads
* into RAF buffer read lengths
*/
- len = msg->len;
- qspi->bspi_rf_msg_idx = 0;
+ len = op->data.nbytes;
+ qspi->bspi_rf_op_idx = 0;
do {
if (len > BSPI_READ_LENGTH)
@@ -844,9 +851,9 @@ static int bcm_qspi_bspi_flash_read(struct spi_device *spi,
reinit_completion(&qspi->bspi_done);
bcm_qspi_enable_bspi(qspi);
len_words = (rdlen + 3) >> 2;
- qspi->bspi_rf_msg = msg;
- qspi->bspi_rf_msg_status = 0;
- qspi->bspi_rf_msg_len = rdlen;
+ qspi->bspi_rf_op = op;
+ qspi->bspi_rf_op_status = 0;
+ qspi->bspi_rf_op_len = rdlen;
dev_dbg(&qspi->pdev->dev,
"bspi xfr addr 0x%x len 0x%x", addr, rdlen);
bcm_qspi_write(qspi, BSPI, BSPI_RAF_START_ADDR, addr);
@@ -871,7 +878,6 @@ static int bcm_qspi_bspi_flash_read(struct spi_device *spi,
}
/* set msg return length */
- msg->retlen += rdlen;
addr += rdlen;
len -= rdlen;
} while (len);
@@ -906,61 +912,63 @@ static int bcm_qspi_transfer_one(struct spi_master *master,
return 0;
}
-static int bcm_qspi_mspi_flash_read(struct spi_device *spi,
- struct spi_flash_read_message *msg)
+static int bcm_qspi_mspi_exec_mem_op(struct spi_device *spi,
+ const struct spi_mem_op *op)
{
- struct bcm_qspi *qspi = spi_master_get_devdata(spi->master);
+ struct spi_master *master = spi->master;
+ struct bcm_qspi *qspi = spi_master_get_devdata(master);
struct spi_transfer t[2];
- u8 cmd[6];
- int ret;
+ u8 cmd[6] = { };
+ int ret, i;
memset(cmd, 0, sizeof(cmd));
memset(t, 0, sizeof(t));
/* tx */
/* opcode is in cmd[0] */
- cmd[0] = msg->read_opcode;
- cmd[1] = msg->from >> (msg->addr_width * 8 - 8);
- cmd[2] = msg->from >> (msg->addr_width * 8 - 16);
- cmd[3] = msg->from >> (msg->addr_width * 8 - 24);
- cmd[4] = msg->from >> (msg->addr_width * 8 - 32);
+ cmd[0] = op->cmd.opcode;
+ for (i = 0; i < op->addr.nbytes; i++)
+ cmd[1 + i] = op->addr.val >> (8 * (op->addr.nbytes - i - 1));
+
t[0].tx_buf = cmd;
- t[0].len = msg->addr_width + msg->dummy_bytes + 1;
+ t[0].len = op->addr.nbytes + op->dummy.nbytes + 1;
t[0].bits_per_word = spi->bits_per_word;
- t[0].tx_nbits = msg->opcode_nbits;
+ t[0].tx_nbits = op->cmd.buswidth;
/* lets mspi know that this is not last transfer */
qspi->trans_pos.mspi_last_trans = false;
- ret = bcm_qspi_transfer_one(spi->master, spi, &t[0]);
+ ret = bcm_qspi_transfer_one(master, spi, &t[0]);
/* rx */
qspi->trans_pos.mspi_last_trans = true;
if (!ret) {
/* rx */
- t[1].rx_buf = msg->buf;
- t[1].len = msg->len;
- t[1].rx_nbits = msg->data_nbits;
+ t[1].rx_buf = op->data.buf.in;
+ t[1].len = op->data.nbytes;
+ t[1].rx_nbits = op->data.buswidth;
t[1].bits_per_word = spi->bits_per_word;
- ret = bcm_qspi_transfer_one(spi->master, spi, &t[1]);
+ ret = bcm_qspi_transfer_one(master, spi, &t[1]);
}
- if (!ret)
- msg->retlen = msg->len;
-
return ret;
}
-static int bcm_qspi_flash_read(struct spi_device *spi,
- struct spi_flash_read_message *msg)
+static int bcm_qspi_exec_mem_op(struct spi_mem *mem,
+ const struct spi_mem_op *op)
{
+ struct spi_device *spi = mem->spi;
struct bcm_qspi *qspi = spi_master_get_devdata(spi->master);
int ret = 0;
bool mspi_read = false;
- u32 addr, len;
+ u32 addr = 0, len;
u_char *buf;
- buf = msg->buf;
- addr = msg->from;
- len = msg->len;
+ if (!op->data.nbytes || !op->addr.nbytes || op->addr.nbytes > 4 ||
+ op->data.dir != SPI_MEM_DATA_IN)
+ return -ENOTSUPP;
+
+ buf = op->data.buf.in;
+ addr = op->addr.val;
+ len = op->data.nbytes;
if (bcm_qspi_bspi_ver_three(qspi) == true) {
/*
@@ -982,12 +990,12 @@ static int bcm_qspi_flash_read(struct spi_device *spi,
mspi_read = true;
if (mspi_read)
- return bcm_qspi_mspi_flash_read(spi, msg);
+ return bcm_qspi_mspi_exec_mem_op(spi, op);
- ret = bcm_qspi_bspi_set_mode(qspi, msg, -1);
+ ret = bcm_qspi_bspi_set_mode(qspi, op, -1);
if (!ret)
- ret = bcm_qspi_bspi_flash_read(spi, msg);
+ ret = bcm_qspi_bspi_exec_mem_op(spi, op);
return ret;
}
@@ -1026,10 +1034,10 @@ static irqreturn_t bcm_qspi_bspi_lr_l2_isr(int irq, void *dev_id)
struct bcm_qspi_soc_intc *soc_intc = qspi->soc_intc;
u32 status = qspi_dev_id->irqp->mask;
- if (qspi->bspi_enabled && qspi->bspi_rf_msg) {
+ if (qspi->bspi_enabled && qspi->bspi_rf_op) {
bcm_qspi_bspi_lr_data_read(qspi);
- if (qspi->bspi_rf_msg_len == 0) {
- qspi->bspi_rf_msg = NULL;
+ if (qspi->bspi_rf_op_len == 0) {
+ qspi->bspi_rf_op = NULL;
if (qspi->soc_intc) {
/* disable soc BSPI interrupt */
soc_intc->bcm_qspi_int_set(soc_intc, BSPI_DONE,
@@ -1038,7 +1046,7 @@ static irqreturn_t bcm_qspi_bspi_lr_l2_isr(int irq, void *dev_id)
status = INTR_BSPI_LR_SESSION_DONE_MASK;
}
- if (qspi->bspi_rf_msg_status)
+ if (qspi->bspi_rf_op_status)
bcm_qspi_bspi_lr_clear(qspi);
else
bcm_qspi_bspi_flush_prefetch_buffers(qspi);
@@ -1050,7 +1058,7 @@ static irqreturn_t bcm_qspi_bspi_lr_l2_isr(int irq, void *dev_id)
}
status &= INTR_BSPI_LR_SESSION_DONE_MASK;
- if (qspi->bspi_enabled && status && qspi->bspi_rf_msg_len == 0)
+ if (qspi->bspi_enabled && status && qspi->bspi_rf_op_len == 0)
complete(&qspi->bspi_done);
return IRQ_HANDLED;
@@ -1063,7 +1071,7 @@ static irqreturn_t bcm_qspi_bspi_lr_err_l2_isr(int irq, void *dev_id)
struct bcm_qspi_soc_intc *soc_intc = qspi->soc_intc;
dev_err(&qspi->pdev->dev, "BSPI INT error\n");
- qspi->bspi_rf_msg_status = -EIO;
+ qspi->bspi_rf_op_status = -EIO;
if (qspi->soc_intc)
/* clear soc interrupt */
soc_intc->bcm_qspi_int_ack(soc_intc, BSPI_ERR);
@@ -1186,6 +1194,10 @@ static void bcm_qspi_hw_uninit(struct bcm_qspi *qspi)
}
+static const struct spi_controller_mem_ops bcm_qspi_mem_ops = {
+ .exec_op = bcm_qspi_exec_mem_op,
+};
+
static const struct of_device_id bcm_qspi_of_match[] = {
{ .compatible = "brcm,spi-bcm-qspi" },
{},
@@ -1228,7 +1240,7 @@ int bcm_qspi_probe(struct platform_device *pdev,
master->mode_bits = SPI_CPHA | SPI_CPOL | SPI_RX_DUAL | SPI_RX_QUAD;
master->setup = bcm_qspi_setup;
master->transfer_one = bcm_qspi_transfer_one;
- master->spi_flash_read = bcm_qspi_flash_read;
+ master->mem_ops = &bcm_qspi_mem_ops;
master->cleanup = bcm_qspi_cleanup;
master->dev.of_node = dev->of_node;
master->num_chipselect = NUM_CHIPSELECT;
diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c
index 1431cb98..3094d81 100644
--- a/drivers/spi/spi-bcm2835aux.c
+++ b/drivers/spi/spi-bcm2835aux.c
@@ -184,6 +184,11 @@ static irqreturn_t bcm2835aux_spi_interrupt(int irq, void *dev_id)
struct bcm2835aux_spi *bs = spi_master_get_devdata(master);
irqreturn_t ret = IRQ_NONE;
+ /* IRQ may be shared, so return if our interrupts are disabled */
+ if (!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_CNTL1) &
+ (BCM2835_AUX_SPI_CNTL1_TXEMPTY | BCM2835_AUX_SPI_CNTL1_IDLE)))
+ return ret;
+
/* check if we have data to read */
while (bs->rx_len &&
(!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_STAT) &
diff --git a/drivers/spi/spi-bcm53xx.c b/drivers/spi/spi-bcm53xx.c
deleted file mode 100644
index d02ceb7..0000000
--- a/drivers/spi/spi-bcm53xx.c
+++ /dev/null
@@ -1,360 +0,0 @@
-/*
- * Copyright (C) 2014-2016 Rafał Miłecki <rafal@milecki.pl>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/delay.h>
-#include <linux/bcma/bcma.h>
-#include <linux/spi/spi.h>
-
-#include "spi-bcm53xx.h"
-
-#define BCM53XXSPI_MAX_SPI_BAUD 13500000 /* 216 MHz? */
-#define BCM53XXSPI_FLASH_WINDOW SZ_32M
-
-/* The longest observed required wait was 19 ms */
-#define BCM53XXSPI_SPE_TIMEOUT_MS 80
-
-struct bcm53xxspi {
- struct bcma_device *core;
- struct spi_master *master;
- void __iomem *mmio_base;
- bool bspi; /* Boot SPI mode with memory mapping */
-};
-
-static inline u32 bcm53xxspi_read(struct bcm53xxspi *b53spi, u16 offset)
-{
- return bcma_read32(b53spi->core, offset);
-}
-
-static inline void bcm53xxspi_write(struct bcm53xxspi *b53spi, u16 offset,
- u32 value)
-{
- bcma_write32(b53spi->core, offset, value);
-}
-
-static void bcm53xxspi_disable_bspi(struct bcm53xxspi *b53spi)
-{
- struct device *dev = &b53spi->core->dev;
- unsigned long deadline;
- u32 tmp;
-
- if (!b53spi->bspi)
- return;
-
- tmp = bcm53xxspi_read(b53spi, B53SPI_BSPI_MAST_N_BOOT_CTRL);
- if (tmp & 0x1)
- return;
-
- deadline = jiffies + usecs_to_jiffies(200);
- do {
- tmp = bcm53xxspi_read(b53spi, B53SPI_BSPI_BUSY_STATUS);
- if (!(tmp & 0x1)) {
- bcm53xxspi_write(b53spi, B53SPI_BSPI_MAST_N_BOOT_CTRL,
- 0x1);
- ndelay(200);
- b53spi->bspi = false;
- return;
- }
- udelay(1);
- } while (!time_after_eq(jiffies, deadline));
-
- dev_warn(dev, "Timeout disabling BSPI\n");
-}
-
-static void bcm53xxspi_enable_bspi(struct bcm53xxspi *b53spi)
-{
- u32 tmp;
-
- if (b53spi->bspi)
- return;
-
- tmp = bcm53xxspi_read(b53spi, B53SPI_BSPI_MAST_N_BOOT_CTRL);
- if (!(tmp & 0x1))
- return;
-
- bcm53xxspi_write(b53spi, B53SPI_BSPI_MAST_N_BOOT_CTRL, 0x0);
- b53spi->bspi = true;
-}
-
-static inline unsigned int bcm53xxspi_calc_timeout(size_t len)
-{
- /* Do some magic calculation based on length and buad. Add 10% and 1. */
- return (len * 9000 / BCM53XXSPI_MAX_SPI_BAUD * 110 / 100) + 1;
-}
-
-static int bcm53xxspi_wait(struct bcm53xxspi *b53spi, unsigned int timeout_ms)
-{
- unsigned long deadline;
- u32 tmp;
-
- /* SPE bit has to be 0 before we read MSPI STATUS */
- deadline = jiffies + msecs_to_jiffies(BCM53XXSPI_SPE_TIMEOUT_MS);
- do {
- tmp = bcm53xxspi_read(b53spi, B53SPI_MSPI_SPCR2);
- if (!(tmp & B53SPI_MSPI_SPCR2_SPE))
- break;
- udelay(5);
- } while (!time_after_eq(jiffies, deadline));
-
- if (tmp & B53SPI_MSPI_SPCR2_SPE)
- goto spi_timeout;
-
- /* Check status */
- deadline = jiffies + msecs_to_jiffies(timeout_ms);
- do {
- tmp = bcm53xxspi_read(b53spi, B53SPI_MSPI_MSPI_STATUS);
- if (tmp & B53SPI_MSPI_MSPI_STATUS_SPIF) {
- bcm53xxspi_write(b53spi, B53SPI_MSPI_MSPI_STATUS, 0);
- return 0;
- }
-
- cpu_relax();
- udelay(100);
- } while (!time_after_eq(jiffies, deadline));
-
-spi_timeout:
- bcm53xxspi_write(b53spi, B53SPI_MSPI_MSPI_STATUS, 0);
-
- pr_err("Timeout waiting for SPI to be ready!\n");
-
- return -EBUSY;
-}
-
-static void bcm53xxspi_buf_write(struct bcm53xxspi *b53spi, u8 *w_buf,
- size_t len, bool cont)
-{
- u32 tmp;
- int i;
-
- for (i = 0; i < len; i++) {
- /* Transmit Register File MSB */
- bcm53xxspi_write(b53spi, B53SPI_MSPI_TXRAM + 4 * (i * 2),
- (unsigned int)w_buf[i]);
- }
-
- for (i = 0; i < len; i++) {
- tmp = B53SPI_CDRAM_CONT | B53SPI_CDRAM_PCS_DISABLE_ALL |
- B53SPI_CDRAM_PCS_DSCK;
- if (!cont && i == len - 1)
- tmp &= ~B53SPI_CDRAM_CONT;
- tmp &= ~0x1;
- /* Command Register File */
- bcm53xxspi_write(b53spi, B53SPI_MSPI_CDRAM + 4 * i, tmp);
- }
-
- /* Set queue pointers */
- bcm53xxspi_write(b53spi, B53SPI_MSPI_NEWQP, 0);
- bcm53xxspi_write(b53spi, B53SPI_MSPI_ENDQP, len - 1);
-
- if (cont)
- bcm53xxspi_write(b53spi, B53SPI_MSPI_WRITE_LOCK, 1);
-
- /* Start SPI transfer */
- tmp = bcm53xxspi_read(b53spi, B53SPI_MSPI_SPCR2);
- tmp |= B53SPI_MSPI_SPCR2_SPE;
- if (cont)
- tmp |= B53SPI_MSPI_SPCR2_CONT_AFTER_CMD;
- bcm53xxspi_write(b53spi, B53SPI_MSPI_SPCR2, tmp);
-
- /* Wait for SPI to finish */
- bcm53xxspi_wait(b53spi, bcm53xxspi_calc_timeout(len));
-
- if (!cont)
- bcm53xxspi_write(b53spi, B53SPI_MSPI_WRITE_LOCK, 0);
-}
-
-static void bcm53xxspi_buf_read(struct bcm53xxspi *b53spi, u8 *r_buf,
- size_t len, bool cont)
-{
- u32 tmp;
- int i;
-
- for (i = 0; i < len; i++) {
- tmp = B53SPI_CDRAM_CONT | B53SPI_CDRAM_PCS_DISABLE_ALL |
- B53SPI_CDRAM_PCS_DSCK;
- if (!cont && i == len - 1)
- tmp &= ~B53SPI_CDRAM_CONT;
- tmp &= ~0x1;
- /* Command Register File */
- bcm53xxspi_write(b53spi, B53SPI_MSPI_CDRAM + 4 * i, tmp);
- }
-
- /* Set queue pointers */
- bcm53xxspi_write(b53spi, B53SPI_MSPI_NEWQP, 0);
- bcm53xxspi_write(b53spi, B53SPI_MSPI_ENDQP, len - 1);
-
- if (cont)
- bcm53xxspi_write(b53spi, B53SPI_MSPI_WRITE_LOCK, 1);
-
- /* Start SPI transfer */
- tmp = bcm53xxspi_read(b53spi, B53SPI_MSPI_SPCR2);
- tmp |= B53SPI_MSPI_SPCR2_SPE;
- if (cont)
- tmp |= B53SPI_MSPI_SPCR2_CONT_AFTER_CMD;
- bcm53xxspi_write(b53spi, B53SPI_MSPI_SPCR2, tmp);
-
- /* Wait for SPI to finish */
- bcm53xxspi_wait(b53spi, bcm53xxspi_calc_timeout(len));
-
- if (!cont)
- bcm53xxspi_write(b53spi, B53SPI_MSPI_WRITE_LOCK, 0);
-
- for (i = 0; i < len; ++i) {
- u16 reg = B53SPI_MSPI_RXRAM + 4 * (1 + i * 2);
-
- /* Data stored in the transmit register file LSB */
- r_buf[i] = (u8)bcm53xxspi_read(b53spi, reg);
- }
-}
-
-static int bcm53xxspi_transfer_one(struct spi_master *master,
- struct spi_device *spi,
- struct spi_transfer *t)
-{
- struct bcm53xxspi *b53spi = spi_master_get_devdata(master);
- u8 *buf;
- size_t left;
-
- bcm53xxspi_disable_bspi(b53spi);
-
- if (t->tx_buf) {
- buf = (u8 *)t->tx_buf;
- left = t->len;
- while (left) {
- size_t to_write = min_t(size_t, 16, left);
- bool cont = !spi_transfer_is_last(master, t) ||
- left - to_write > 0;
-
- bcm53xxspi_buf_write(b53spi, buf, to_write, cont);
- left -= to_write;
- buf += to_write;
- }
- }
-
- if (t->rx_buf) {
- buf = (u8 *)t->rx_buf;
- left = t->len;
- while (left) {
- size_t to_read = min_t(size_t, 16, left);
- bool cont = !spi_transfer_is_last(master, t) ||
- left - to_read > 0;
-
- bcm53xxspi_buf_read(b53spi, buf, to_read, cont);
- left -= to_read;
- buf += to_read;
- }
- }
-
- return 0;
-}
-
-static int bcm53xxspi_flash_read(struct spi_device *spi,
- struct spi_flash_read_message *msg)
-{
- struct bcm53xxspi *b53spi = spi_master_get_devdata(spi->master);
- int ret = 0;
-
- if (msg->from + msg->len > BCM53XXSPI_FLASH_WINDOW)
- return -EINVAL;
-
- bcm53xxspi_enable_bspi(b53spi);
- memcpy_fromio(msg->buf, b53spi->mmio_base + msg->from, msg->len);
- msg->retlen = msg->len;
-
- return ret;
-}
-
-/**************************************************
- * BCMA
- **************************************************/
-
-static const struct bcma_device_id bcm53xxspi_bcma_tbl[] = {
- BCMA_CORE(BCMA_MANUF_BCM, BCMA_CORE_NS_QSPI, BCMA_ANY_REV, BCMA_ANY_CLASS),
- {},
-};
-MODULE_DEVICE_TABLE(bcma, bcm53xxspi_bcma_tbl);
-
-static int bcm53xxspi_bcma_probe(struct bcma_device *core)
-{
- struct device *dev = &core->dev;
- struct bcm53xxspi *b53spi;
- struct spi_master *master;
- int err;
-
- if (core->bus->drv_cc.core->id.rev != 42) {
- pr_err("SPI on SoC with unsupported ChipCommon rev\n");
- return -ENOTSUPP;
- }
-
- master = spi_alloc_master(dev, sizeof(*b53spi));
- if (!master)
- return -ENOMEM;
-
- b53spi = spi_master_get_devdata(master);
- b53spi->master = master;
- b53spi->core = core;
-
- if (core->addr_s[0])
- b53spi->mmio_base = devm_ioremap(dev, core->addr_s[0],
- BCM53XXSPI_FLASH_WINDOW);
- b53spi->bspi = true;
- bcm53xxspi_disable_bspi(b53spi);
-
- master->dev.of_node = dev->of_node;
- master->transfer_one = bcm53xxspi_transfer_one;
- if (b53spi->mmio_base)
- master->spi_flash_read = bcm53xxspi_flash_read;
-
- bcma_set_drvdata(core, b53spi);
-
- err = devm_spi_register_master(dev, master);
- if (err) {
- spi_master_put(master);
- bcma_set_drvdata(core, NULL);
- return err;
- }
-
- return 0;
-}
-
-static struct bcma_driver bcm53xxspi_bcma_driver = {
- .name = KBUILD_MODNAME,
- .id_table = bcm53xxspi_bcma_tbl,
- .probe = bcm53xxspi_bcma_probe,
-};
-
-/**************************************************
- * Init & exit
- **************************************************/
-
-static int __init bcm53xxspi_module_init(void)
-{
- int err = 0;
-
- err = bcma_driver_register(&bcm53xxspi_bcma_driver);
- if (err)
- pr_err("Failed to register bcma driver: %d\n", err);
-
- return err;
-}
-
-static void __exit bcm53xxspi_module_exit(void)
-{
- bcma_driver_unregister(&bcm53xxspi_bcma_driver);
-}
-
-module_init(bcm53xxspi_module_init);
-module_exit(bcm53xxspi_module_exit);
-
-MODULE_DESCRIPTION("Broadcom BCM53xx SPI Controller driver");
-MODULE_AUTHOR("Rafał Miłecki <zajec5@gmail.com>");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/spi/spi-bcm53xx.h b/drivers/spi/spi-bcm53xx.h
deleted file mode 100644
index 03e3442..0000000
--- a/drivers/spi/spi-bcm53xx.h
+++ /dev/null
@@ -1,73 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef SPI_BCM53XX_H
-#define SPI_BCM53XX_H
-
-#define B53SPI_BSPI_REVISION_ID 0x000
-#define B53SPI_BSPI_SCRATCH 0x004
-#define B53SPI_BSPI_MAST_N_BOOT_CTRL 0x008
-#define B53SPI_BSPI_BUSY_STATUS 0x00c
-#define B53SPI_BSPI_INTR_STATUS 0x010
-#define B53SPI_BSPI_B0_STATUS 0x014
-#define B53SPI_BSPI_B0_CTRL 0x018
-#define B53SPI_BSPI_B1_STATUS 0x01c
-#define B53SPI_BSPI_B1_CTRL 0x020
-#define B53SPI_BSPI_STRAP_OVERRIDE_CTRL 0x024
-#define B53SPI_BSPI_FLEX_MODE_ENABLE 0x028
-#define B53SPI_BSPI_BITS_PER_CYCLE 0x02c
-#define B53SPI_BSPI_BITS_PER_PHASE 0x030
-#define B53SPI_BSPI_CMD_AND_MODE_BYTE 0x034
-#define B53SPI_BSPI_BSPI_FLASH_UPPER_ADDR_BYTE 0x038
-#define B53SPI_BSPI_BSPI_XOR_VALUE 0x03c
-#define B53SPI_BSPI_BSPI_XOR_ENABLE 0x040
-#define B53SPI_BSPI_BSPI_PIO_MODE_ENABLE 0x044
-#define B53SPI_BSPI_BSPI_PIO_IODIR 0x048
-#define B53SPI_BSPI_BSPI_PIO_DATA 0x04c
-
-/* RAF */
-#define B53SPI_RAF_START_ADDR 0x100
-#define B53SPI_RAF_NUM_WORDS 0x104
-#define B53SPI_RAF_CTRL 0x108
-#define B53SPI_RAF_FULLNESS 0x10c
-#define B53SPI_RAF_WATERMARK 0x110
-#define B53SPI_RAF_STATUS 0x114
-#define B53SPI_RAF_READ_DATA 0x118
-#define B53SPI_RAF_WORD_CNT 0x11c
-#define B53SPI_RAF_CURR_ADDR 0x120
-
-/* MSPI */
-#define B53SPI_MSPI_SPCR0_LSB 0x200
-#define B53SPI_MSPI_SPCR0_MSB 0x204
-#define B53SPI_MSPI_SPCR1_LSB 0x208
-#define B53SPI_MSPI_SPCR1_MSB 0x20c
-#define B53SPI_MSPI_NEWQP 0x210
-#define B53SPI_MSPI_ENDQP 0x214
-#define B53SPI_MSPI_SPCR2 0x218
-#define B53SPI_MSPI_SPCR2_SPE 0x00000040
-#define B53SPI_MSPI_SPCR2_CONT_AFTER_CMD 0x00000080
-#define B53SPI_MSPI_MSPI_STATUS 0x220
-#define B53SPI_MSPI_MSPI_STATUS_SPIF 0x00000001
-#define B53SPI_MSPI_CPTQP 0x224
-#define B53SPI_MSPI_TXRAM 0x240 /* 32 registers, up to 0x2b8 */
-#define B53SPI_MSPI_RXRAM 0x2c0 /* 32 registers, up to 0x33c */
-#define B53SPI_MSPI_CDRAM 0x340 /* 16 registers, up to 0x37c */
-#define B53SPI_CDRAM_PCS_PCS0 0x00000001
-#define B53SPI_CDRAM_PCS_PCS1 0x00000002
-#define B53SPI_CDRAM_PCS_PCS2 0x00000004
-#define B53SPI_CDRAM_PCS_PCS3 0x00000008
-#define B53SPI_CDRAM_PCS_DISABLE_ALL 0x0000000f
-#define B53SPI_CDRAM_PCS_DSCK 0x00000010
-#define B53SPI_CDRAM_BITSE 0x00000040
-#define B53SPI_CDRAM_CONT 0x00000080
-#define B53SPI_MSPI_WRITE_LOCK 0x380
-#define B53SPI_MSPI_DISABLE_FLUSH_GEN 0x384
-
-/* Interrupt */
-#define B53SPI_INTR_RAF_LR_FULLNESS_REACHED 0x3a0
-#define B53SPI_INTR_RAF_LR_TRUNCATED 0x3a4
-#define B53SPI_INTR_RAF_LR_IMPATIENT 0x3a8
-#define B53SPI_INTR_RAF_LR_SESSION_DONE 0x3ac
-#define B53SPI_INTR_RAF_LR_OVERREAD 0x3b0
-#define B53SPI_INTR_MSPI_DONE 0x3b4
-#define B53SPI_INTR_MSPI_HALT_SET_TRANSACTION_DONE 0x3b8
-
-#endif /* SPI_BCM53XX_H */
diff --git a/drivers/spi/spi-bcm63xx-hsspi.c b/drivers/spi/spi-bcm63xx-hsspi.c
index cbcba61..c23849f 100644
--- a/drivers/spi/spi-bcm63xx-hsspi.c
+++ b/drivers/spi/spi-bcm63xx-hsspi.c
@@ -352,22 +352,31 @@ static int bcm63xx_hsspi_probe(struct platform_device *pdev)
if (IS_ERR(clk))
return PTR_ERR(clk);
+ ret = clk_prepare_enable(clk);
+ if (ret)
+ return ret;
+
rate = clk_get_rate(clk);
if (!rate) {
struct clk *pll_clk = devm_clk_get(dev, "pll");
- if (IS_ERR(pll_clk))
- return PTR_ERR(pll_clk);
+ if (IS_ERR(pll_clk)) {
+ ret = PTR_ERR(pll_clk);
+ goto out_disable_clk;
+ }
+
+ ret = clk_prepare_enable(pll_clk);
+ if (ret)
+ goto out_disable_clk;
rate = clk_get_rate(pll_clk);
- if (!rate)
- return -EINVAL;
+ clk_disable_unprepare(pll_clk);
+ if (!rate) {
+ ret = -EINVAL;
+ goto out_disable_clk;
+ }
}
- ret = clk_prepare_enable(clk);
- if (ret)
- return ret;
-
master = spi_alloc_master(&pdev->dev, sizeof(*bs));
if (!master) {
ret = -ENOMEM;
diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c
index 5c9516a..f3dad6f 100644
--- a/drivers/spi/spi-cadence.c
+++ b/drivers/spi/spi-cadence.c
@@ -313,6 +313,14 @@ static void cdns_spi_fill_tx_fifo(struct cdns_spi *xspi)
while ((trans_cnt < CDNS_SPI_FIFO_DEPTH) &&
(xspi->tx_bytes > 0)) {
+
+ /* When xspi in busy condition, bytes may send failed,
+ * then spi control did't work thoroughly, add one byte delay
+ */
+ if (cdns_spi_read(xspi, CDNS_SPI_ISR) &
+ CDNS_SPI_IXR_TXFULL)
+ usleep_range(10, 20);
+
if (xspi->txbuf)
cdns_spi_write(xspi, CDNS_SPI_TXD, *xspi->txbuf++);
else
@@ -686,8 +694,7 @@ static int cdns_spi_remove(struct platform_device *pdev)
*/
static int __maybe_unused cdns_spi_suspend(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct spi_master *master = platform_get_drvdata(pdev);
+ struct spi_master *master = dev_get_drvdata(dev);
return spi_master_suspend(master);
}
@@ -702,8 +709,7 @@ static int __maybe_unused cdns_spi_suspend(struct device *dev)
*/
static int __maybe_unused cdns_spi_resume(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct spi_master *master = platform_get_drvdata(pdev);
+ struct spi_master *master = dev_get_drvdata(dev);
struct cdns_spi *xspi = spi_master_get_devdata(master);
cdns_spi_init_hw(xspi);
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index cb3c730..e6d5cc6 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -1,19 +1,8 @@
-/*
- * Freescale i.MX7ULP LPSPI driver
- *
- * Copyright 2016 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Freescale i.MX7ULP LPSPI driver
+//
+// Copyright 2016 Freescale Semiconductor, Inc.
#include <linux/clk.h>
#include <linux/completion.h>
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 6f57592..866246f 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -1,22 +1,6 @@
-/*
- * Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
- * Copyright (C) 2008 Juergen Beisert
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation
- * 51 Franklin Street, Fifth Floor
- * Boston, MA 02110-1301, USA.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
+// Copyright (C) 2008 Juergen Beisert
#include <linux/clk.h>
#include <linux/completion.h>
@@ -1701,7 +1685,7 @@ static struct platform_driver spi_imx_driver = {
};
module_platform_driver(spi_imx_driver);
-MODULE_DESCRIPTION("SPI Master Controller driver");
+MODULE_DESCRIPTION("SPI Controller driver");
MODULE_AUTHOR("Sascha Hauer, Pengutronix");
MODULE_LICENSE("GPL");
MODULE_ALIAS("platform:" DRIVER_NAME);
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
new file mode 100644
index 0000000..990770d
--- /dev/null
+++ b/drivers/spi/spi-mem.c
@@ -0,0 +1,410 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2018 Exceet Electronics GmbH
+ * Copyright (C) 2018 Bootlin
+ *
+ * Author: Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+#include <linux/dmaengine.h>
+#include <linux/pm_runtime.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
+
+#include "internals.h"
+
+/**
+ * spi_controller_dma_map_mem_op_data() - DMA-map the buffer attached to a
+ * memory operation
+ * @ctlr: the SPI controller requesting this dma_map()
+ * @op: the memory operation containing the buffer to map
+ * @sgt: a pointer to a non-initialized sg_table that will be filled by this
+ * function
+ *
+ * Some controllers might want to do DMA on the data buffer embedded in @op.
+ * This helper prepares everything for you and provides a ready-to-use
+ * sg_table. This function is not intended to be called from spi drivers.
+ * Only SPI controller drivers should use it.
+ * Note that the caller must ensure the memory region pointed by
+ * op->data.buf.{in,out} is DMA-able before calling this function.
+ *
+ * Return: 0 in case of success, a negative error code otherwise.
+ */
+int spi_controller_dma_map_mem_op_data(struct spi_controller *ctlr,
+ const struct spi_mem_op *op,
+ struct sg_table *sgt)
+{
+ struct device *dmadev;
+
+ if (!op->data.nbytes)
+ return -EINVAL;
+
+ if (op->data.dir == SPI_MEM_DATA_OUT && ctlr->dma_tx)
+ dmadev = ctlr->dma_tx->device->dev;
+ else if (op->data.dir == SPI_MEM_DATA_IN && ctlr->dma_rx)
+ dmadev = ctlr->dma_rx->device->dev;
+ else
+ dmadev = ctlr->dev.parent;
+
+ if (!dmadev)
+ return -EINVAL;
+
+ return spi_map_buf(ctlr, dmadev, sgt, op->data.buf.in, op->data.nbytes,
+ op->data.dir == SPI_MEM_DATA_IN ?
+ DMA_FROM_DEVICE : DMA_TO_DEVICE);
+}
+EXPORT_SYMBOL_GPL(spi_controller_dma_map_mem_op_data);
+
+/**
+ * spi_controller_dma_unmap_mem_op_data() - DMA-unmap the buffer attached to a
+ * memory operation
+ * @ctlr: the SPI controller requesting this dma_unmap()
+ * @op: the memory operation containing the buffer to unmap
+ * @sgt: a pointer to an sg_table previously initialized by
+ * spi_controller_dma_map_mem_op_data()
+ *
+ * Some controllers might want to do DMA on the data buffer embedded in @op.
+ * This helper prepares things so that the CPU can access the
+ * op->data.buf.{in,out} buffer again.
+ *
+ * This function is not intended to be called from SPI drivers. Only SPI
+ * controller drivers should use it.
+ *
+ * This function should be called after the DMA operation has finished and is
+ * only valid if the previous spi_controller_dma_map_mem_op_data() call
+ * returned 0.
+ *
+ * Return: 0 in case of success, a negative error code otherwise.
+ */
+void spi_controller_dma_unmap_mem_op_data(struct spi_controller *ctlr,
+ const struct spi_mem_op *op,
+ struct sg_table *sgt)
+{
+ struct device *dmadev;
+
+ if (!op->data.nbytes)
+ return;
+
+ if (op->data.dir == SPI_MEM_DATA_OUT && ctlr->dma_tx)
+ dmadev = ctlr->dma_tx->device->dev;
+ else if (op->data.dir == SPI_MEM_DATA_IN && ctlr->dma_rx)
+ dmadev = ctlr->dma_rx->device->dev;
+ else
+ dmadev = ctlr->dev.parent;
+
+ spi_unmap_buf(ctlr, dmadev, sgt,
+ op->data.dir == SPI_MEM_DATA_IN ?
+ DMA_FROM_DEVICE : DMA_TO_DEVICE);
+}
+EXPORT_SYMBOL_GPL(spi_controller_dma_unmap_mem_op_data);
+
+static int spi_check_buswidth_req(struct spi_mem *mem, u8 buswidth, bool tx)
+{
+ u32 mode = mem->spi->mode;
+
+ switch (buswidth) {
+ case 1:
+ return 0;
+
+ case 2:
+ if ((tx && (mode & (SPI_TX_DUAL | SPI_TX_QUAD))) ||
+ (!tx && (mode & (SPI_RX_DUAL | SPI_RX_QUAD))))
+ return 0;
+
+ break;
+
+ case 4:
+ if ((tx && (mode & SPI_TX_QUAD)) ||
+ (!tx && (mode & SPI_RX_QUAD)))
+ return 0;
+
+ break;
+
+ default:
+ break;
+ }
+
+ return -ENOTSUPP;
+}
+
+static bool spi_mem_default_supports_op(struct spi_mem *mem,
+ const struct spi_mem_op *op)
+{
+ if (spi_check_buswidth_req(mem, op->cmd.buswidth, true))
+ return false;
+
+ if (op->addr.nbytes &&
+ spi_check_buswidth_req(mem, op->addr.buswidth, true))
+ return false;
+
+ if (op->dummy.nbytes &&
+ spi_check_buswidth_req(mem, op->dummy.buswidth, true))
+ return false;
+
+ if (op->data.nbytes &&
+ spi_check_buswidth_req(mem, op->data.buswidth,
+ op->data.dir == SPI_MEM_DATA_OUT))
+ return false;
+
+ return true;
+}
+EXPORT_SYMBOL_GPL(spi_mem_default_supports_op);
+
+/**
+ * spi_mem_supports_op() - Check if a memory device and the controller it is
+ * connected to support a specific memory operation
+ * @mem: the SPI memory
+ * @op: the memory operation to check
+ *
+ * Some controllers are only supporting Single or Dual IOs, others might only
+ * support specific opcodes, or it can even be that the controller and device
+ * both support Quad IOs but the hardware prevents you from using it because
+ * only 2 IO lines are connected.
+ *
+ * This function checks whether a specific operation is supported.
+ *
+ * Return: true if @op is supported, false otherwise.
+ */
+bool spi_mem_supports_op(struct spi_mem *mem, const struct spi_mem_op *op)
+{
+ struct spi_controller *ctlr = mem->spi->controller;
+
+ if (ctlr->mem_ops && ctlr->mem_ops->supports_op)
+ return ctlr->mem_ops->supports_op(mem, op);
+
+ return spi_mem_default_supports_op(mem, op);
+}
+EXPORT_SYMBOL_GPL(spi_mem_supports_op);
+
+/**
+ * spi_mem_exec_op() - Execute a memory operation
+ * @mem: the SPI memory
+ * @op: the memory operation to execute
+ *
+ * Executes a memory operation.
+ *
+ * This function first checks that @op is supported and then tries to execute
+ * it.
+ *
+ * Return: 0 in case of success, a negative error code otherwise.
+ */
+int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
+{
+ unsigned int tmpbufsize, xferpos = 0, totalxferlen = 0;
+ struct spi_controller *ctlr = mem->spi->controller;
+ struct spi_transfer xfers[4] = { };
+ struct spi_message msg;
+ u8 *tmpbuf;
+ int ret;
+
+ if (!spi_mem_supports_op(mem, op))
+ return -ENOTSUPP;
+
+ if (ctlr->mem_ops) {
+ /*
+ * Flush the message queue before executing our SPI memory
+ * operation to prevent preemption of regular SPI transfers.
+ */
+ spi_flush_queue(ctlr);
+
+ if (ctlr->auto_runtime_pm) {
+ ret = pm_runtime_get_sync(ctlr->dev.parent);
+ if (ret < 0) {
+ dev_err(&ctlr->dev,
+ "Failed to power device: %d\n",
+ ret);
+ return ret;
+ }
+ }
+
+ mutex_lock(&ctlr->bus_lock_mutex);
+ mutex_lock(&ctlr->io_mutex);
+ ret = ctlr->mem_ops->exec_op(mem, op);
+ mutex_unlock(&ctlr->io_mutex);
+ mutex_unlock(&ctlr->bus_lock_mutex);
+
+ if (ctlr->auto_runtime_pm)
+ pm_runtime_put(ctlr->dev.parent);
+
+ /*
+ * Some controllers only optimize specific paths (typically the
+ * read path) and expect the core to use the regular SPI
+ * interface in other cases.
+ */
+ if (!ret || ret != -ENOTSUPP)
+ return ret;
+ }
+
+ tmpbufsize = sizeof(op->cmd.opcode) + op->addr.nbytes +
+ op->dummy.nbytes;
+
+ /*
+ * Allocate a buffer to transmit the CMD, ADDR cycles with kmalloc() so
+ * we're guaranteed that this buffer is DMA-able, as required by the
+ * SPI layer.
+ */
+ tmpbuf = kzalloc(tmpbufsize, GFP_KERNEL | GFP_DMA);
+ if (!tmpbuf)
+ return -ENOMEM;
+
+ spi_message_init(&msg);
+
+ tmpbuf[0] = op->cmd.opcode;
+ xfers[xferpos].tx_buf = tmpbuf;
+ xfers[xferpos].len = sizeof(op->cmd.opcode);
+ xfers[xferpos].tx_nbits = op->cmd.buswidth;
+ spi_message_add_tail(&xfers[xferpos], &msg);
+ xferpos++;
+ totalxferlen++;
+
+ if (op->addr.nbytes) {
+ int i;
+
+ for (i = 0; i < op->addr.nbytes; i++)
+ tmpbuf[i + 1] = op->addr.val >>
+ (8 * (op->addr.nbytes - i - 1));
+
+ xfers[xferpos].tx_buf = tmpbuf + 1;
+ xfers[xferpos].len = op->addr.nbytes;
+ xfers[xferpos].tx_nbits = op->addr.buswidth;
+ spi_message_add_tail(&xfers[xferpos], &msg);
+ xferpos++;
+ totalxferlen += op->addr.nbytes;
+ }
+
+ if (op->dummy.nbytes) {
+ memset(tmpbuf + op->addr.nbytes + 1, 0xff, op->dummy.nbytes);
+ xfers[xferpos].tx_buf = tmpbuf + op->addr.nbytes + 1;
+ xfers[xferpos].len = op->dummy.nbytes;
+ xfers[xferpos].tx_nbits = op->dummy.buswidth;
+ spi_message_add_tail(&xfers[xferpos], &msg);
+ xferpos++;
+ totalxferlen += op->dummy.nbytes;
+ }
+
+ if (op->data.nbytes) {
+ if (op->data.dir == SPI_MEM_DATA_IN) {
+ xfers[xferpos].rx_buf = op->data.buf.in;
+ xfers[xferpos].rx_nbits = op->data.buswidth;
+ } else {
+ xfers[xferpos].tx_buf = op->data.buf.out;
+ xfers[xferpos].tx_nbits = op->data.buswidth;
+ }
+
+ xfers[xferpos].len = op->data.nbytes;
+ spi_message_add_tail(&xfers[xferpos], &msg);
+ xferpos++;
+ totalxferlen += op->data.nbytes;
+ }
+
+ ret = spi_sync(mem->spi, &msg);
+
+ kfree(tmpbuf);
+
+ if (ret)
+ return ret;
+
+ if (msg.actual_length != totalxferlen)
+ return -EIO;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(spi_mem_exec_op);
+
+/**
+ * spi_mem_adjust_op_size() - Adjust the data size of a SPI mem operation to
+ * match controller limitations
+ * @mem: the SPI memory
+ * @op: the operation to adjust
+ *
+ * Some controllers have FIFO limitations and must split a data transfer
+ * operation into multiple ones, others require a specific alignment for
+ * optimized accesses. This function allows SPI mem drivers to split a single
+ * operation into multiple sub-operations when required.
+ *
+ * Return: a negative error code if the controller can't properly adjust @op,
+ * 0 otherwise. Note that @op->data.nbytes will be updated if @op
+ * can't be handled in a single step.
+ */
+int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op)
+{
+ struct spi_controller *ctlr = mem->spi->controller;
+
+ if (ctlr->mem_ops && ctlr->mem_ops->adjust_op_size)
+ return ctlr->mem_ops->adjust_op_size(mem, op);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(spi_mem_adjust_op_size);
+
+static inline struct spi_mem_driver *to_spi_mem_drv(struct device_driver *drv)
+{
+ return container_of(drv, struct spi_mem_driver, spidrv.driver);
+}
+
+static int spi_mem_probe(struct spi_device *spi)
+{
+ struct spi_mem_driver *memdrv = to_spi_mem_drv(spi->dev.driver);
+ struct spi_mem *mem;
+
+ mem = devm_kzalloc(&spi->dev, sizeof(*mem), GFP_KERNEL);
+ if (!mem)
+ return -ENOMEM;
+
+ mem->spi = spi;
+ spi_set_drvdata(spi, mem);
+
+ return memdrv->probe(mem);
+}
+
+static int spi_mem_remove(struct spi_device *spi)
+{
+ struct spi_mem_driver *memdrv = to_spi_mem_drv(spi->dev.driver);
+ struct spi_mem *mem = spi_get_drvdata(spi);
+
+ if (memdrv->remove)
+ return memdrv->remove(mem);
+
+ return 0;
+}
+
+static void spi_mem_shutdown(struct spi_device *spi)
+{
+ struct spi_mem_driver *memdrv = to_spi_mem_drv(spi->dev.driver);
+ struct spi_mem *mem = spi_get_drvdata(spi);
+
+ if (memdrv->shutdown)
+ memdrv->shutdown(mem);
+}
+
+/**
+ * spi_mem_driver_register_with_owner() - Register a SPI memory driver
+ * @memdrv: the SPI memory driver to register
+ * @owner: the owner of this driver
+ *
+ * Registers a SPI memory driver.
+ *
+ * Return: 0 in case of success, a negative error core otherwise.
+ */
+
+int spi_mem_driver_register_with_owner(struct spi_mem_driver *memdrv,
+ struct module *owner)
+{
+ memdrv->spidrv.probe = spi_mem_probe;
+ memdrv->spidrv.remove = spi_mem_remove;
+ memdrv->spidrv.shutdown = spi_mem_shutdown;
+
+ return __spi_register_driver(owner, &memdrv->spidrv);
+}
+EXPORT_SYMBOL_GPL(spi_mem_driver_register_with_owner);
+
+/**
+ * spi_mem_driver_unregister_with_owner() - Unregister a SPI memory driver
+ * @memdrv: the SPI memory driver to unregister
+ *
+ * Unregisters a SPI memory driver.
+ */
+void spi_mem_driver_unregister(struct spi_mem_driver *memdrv)
+{
+ spi_unregister_driver(&memdrv->spidrv);
+}
+EXPORT_SYMBOL_GPL(spi_mem_driver_unregister);
diff --git a/drivers/spi/spi-meson-spicc.c b/drivers/spi/spi-meson-spicc.c
index 5c82910..7fe4488 100644
--- a/drivers/spi/spi-meson-spicc.c
+++ b/drivers/spi/spi-meson-spicc.c
@@ -574,10 +574,15 @@ static int meson_spicc_probe(struct platform_device *pdev)
master->max_speed_hz = rate >> 2;
ret = devm_spi_register_master(&pdev->dev, master);
- if (!ret)
- return 0;
+ if (ret) {
+ dev_err(&pdev->dev, "spi master registration failed\n");
+ goto out_clk;
+ }
- dev_err(&pdev->dev, "spi master registration failed\n");
+ return 0;
+
+out_clk:
+ clk_disable_unprepare(spicc->core);
out_master:
spi_master_put(master);
diff --git a/drivers/spi/spi-mpc52xx.c b/drivers/spi/spi-mpc52xx.c
index e8b59ce..0e55784 100644
--- a/drivers/spi/spi-mpc52xx.c
+++ b/drivers/spi/spi-mpc52xx.c
@@ -447,7 +447,7 @@ static int mpc52xx_spi_probe(struct platform_device *op)
for (i = 0; i < ms->gpio_cs_count; i++) {
gpio_cs = of_get_gpio(op->dev.of_node, i);
- if (gpio_cs < 0) {
+ if (!gpio_is_valid(gpio_cs)) {
dev_err(&op->dev,
"could not parse the gpio field in oftree\n");
rc = -ENODEV;
diff --git a/drivers/spi/spi-mxs.c b/drivers/spi/spi-mxs.c
index 3d216b9..6ac95a2 100644
--- a/drivers/spi/spi-mxs.c
+++ b/drivers/spi/spi-mxs.c
@@ -1,32 +1,22 @@
-/*
- * Freescale MXS SPI master driver
- *
- * Copyright 2012 DENX Software Engineering, GmbH.
- * Copyright 2012 Freescale Semiconductor, Inc.
- * Copyright 2008 Embedded Alley Solutions, Inc All Rights Reserved.
- *
- * Rework and transition to new API by:
- * Marek Vasut <marex@denx.de>
- *
- * Based on previous attempt by:
- * Fabio Estevam <fabio.estevam@freescale.com>
- *
- * Based on code from U-Boot bootloader by:
- * Marek Vasut <marex@denx.de>
- *
- * Based on spi-stmp.c, which is:
- * Author: Dmitry Pervushin <dimka@embeddedalley.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Freescale MXS SPI master driver
+//
+// Copyright 2012 DENX Software Engineering, GmbH.
+// Copyright 2012 Freescale Semiconductor, Inc.
+// Copyright 2008 Embedded Alley Solutions, Inc All Rights Reserved.
+//
+// Rework and transition to new API by:
+// Marek Vasut <marex@denx.de>
+//
+// Based on previous attempt by:
+// Fabio Estevam <fabio.estevam@freescale.com>
+//
+// Based on code from U-Boot bootloader by:
+// Marek Vasut <marex@denx.de>
+//
+// Based on spi-stmp.c, which is:
+// Author: Dmitry Pervushin <dimka@embeddedalley.com>
#include <linux/kernel.h>
#include <linux/ioport.h>
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 9bf64e6..6c628a5 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -255,6 +255,7 @@ static void omap2_mcspi_set_cs(struct spi_device *spi, bool enable)
if (spi->controller_state) {
int err = pm_runtime_get_sync(mcspi->dev);
if (err < 0) {
+ pm_runtime_put_noidle(mcspi->dev);
dev_err(mcspi->dev, "failed to get sync: %d\n", err);
return;
}
@@ -350,20 +351,6 @@ static void omap2_mcspi_set_fifo(const struct spi_device *spi,
mcspi->fifo_depth = 0;
}
-static void omap2_mcspi_restore_ctx(struct omap2_mcspi *mcspi)
-{
- struct spi_master *spi_cntrl = mcspi->master;
- struct omap2_mcspi_regs *ctx = &mcspi->ctx;
- struct omap2_mcspi_cs *cs;
-
- /* McSPI: context restore */
- mcspi_write_reg(spi_cntrl, OMAP2_MCSPI_MODULCTRL, ctx->modulctrl);
- mcspi_write_reg(spi_cntrl, OMAP2_MCSPI_WAKEUPENABLE, ctx->wakeupenable);
-
- list_for_each_entry(cs, &ctx->cs, node)
- writel_relaxed(cs->chconf0, cs->base + OMAP2_MCSPI_CHCONF0);
-}
-
static int mcspi_wait_for_reg_bit(void __iomem *reg, unsigned long bit)
{
unsigned long timeout;
@@ -1065,8 +1052,11 @@ static int omap2_mcspi_setup(struct spi_device *spi)
}
ret = pm_runtime_get_sync(mcspi->dev);
- if (ret < 0)
+ if (ret < 0) {
+ pm_runtime_put_noidle(mcspi->dev);
+
return ret;
+ }
ret = omap2_mcspi_setup_transfer(spi, NULL);
pm_runtime_mark_last_busy(mcspi->dev);
@@ -1284,8 +1274,11 @@ static int omap2_mcspi_master_setup(struct omap2_mcspi *mcspi)
int ret = 0;
ret = pm_runtime_get_sync(mcspi->dev);
- if (ret < 0)
+ if (ret < 0) {
+ pm_runtime_put_noidle(mcspi->dev);
+
return ret;
+ }
mcspi_write_reg(master, OMAP2_MCSPI_WAKEUPENABLE,
OMAP2_MCSPI_WAKEUPENABLE_WKEN);
@@ -1297,14 +1290,39 @@ static int omap2_mcspi_master_setup(struct omap2_mcspi *mcspi)
return 0;
}
+/*
+ * When SPI wake up from off-mode, CS is in activate state. If it was in
+ * inactive state when driver was suspend, then force it to inactive state at
+ * wake up.
+ */
static int omap_mcspi_runtime_resume(struct device *dev)
{
- struct omap2_mcspi *mcspi;
- struct spi_master *master;
+ struct spi_master *master = dev_get_drvdata(dev);
+ struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
+ struct omap2_mcspi_regs *ctx = &mcspi->ctx;
+ struct omap2_mcspi_cs *cs;
- master = dev_get_drvdata(dev);
- mcspi = spi_master_get_devdata(master);
- omap2_mcspi_restore_ctx(mcspi);
+ /* McSPI: context restore */
+ mcspi_write_reg(master, OMAP2_MCSPI_MODULCTRL, ctx->modulctrl);
+ mcspi_write_reg(master, OMAP2_MCSPI_WAKEUPENABLE, ctx->wakeupenable);
+
+ list_for_each_entry(cs, &ctx->cs, node) {
+ /*
+ * We need to toggle CS state for OMAP take this
+ * change in account.
+ */
+ if ((cs->chconf0 & OMAP2_MCSPI_CHCONF_FORCE) == 0) {
+ cs->chconf0 |= OMAP2_MCSPI_CHCONF_FORCE;
+ writel_relaxed(cs->chconf0,
+ cs->base + OMAP2_MCSPI_CHCONF0);
+ cs->chconf0 &= ~OMAP2_MCSPI_CHCONF_FORCE;
+ writel_relaxed(cs->chconf0,
+ cs->base + OMAP2_MCSPI_CHCONF0);
+ } else {
+ writel_relaxed(cs->chconf0,
+ cs->base + OMAP2_MCSPI_CHCONF0);
+ }
+ }
return 0;
}
@@ -1447,50 +1465,33 @@ static int omap2_mcspi_remove(struct platform_device *pdev)
MODULE_ALIAS("platform:omap2_mcspi");
#ifdef CONFIG_SUSPEND
-/*
- * When SPI wake up from off-mode, CS is in activate state. If it was in
- * unactive state when driver was suspend, then force it to unactive state at
- * wake up.
- */
-static int omap2_mcspi_resume(struct device *dev)
-{
- struct spi_master *master = dev_get_drvdata(dev);
- struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
- struct omap2_mcspi_regs *ctx = &mcspi->ctx;
- struct omap2_mcspi_cs *cs;
-
- pm_runtime_get_sync(mcspi->dev);
- list_for_each_entry(cs, &ctx->cs, node) {
- if ((cs->chconf0 & OMAP2_MCSPI_CHCONF_FORCE) == 0) {
- /*
- * We need to toggle CS state for OMAP take this
- * change in account.
- */
- cs->chconf0 |= OMAP2_MCSPI_CHCONF_FORCE;
- writel_relaxed(cs->chconf0, cs->base + OMAP2_MCSPI_CHCONF0);
- cs->chconf0 &= ~OMAP2_MCSPI_CHCONF_FORCE;
- writel_relaxed(cs->chconf0, cs->base + OMAP2_MCSPI_CHCONF0);
- }
- }
- pm_runtime_mark_last_busy(mcspi->dev);
- pm_runtime_put_autosuspend(mcspi->dev);
-
- return pinctrl_pm_select_default_state(dev);
-}
-
-static int omap2_mcspi_suspend(struct device *dev)
+static int omap2_mcspi_suspend_noirq(struct device *dev)
{
return pinctrl_pm_select_sleep_state(dev);
}
+static int omap2_mcspi_resume_noirq(struct device *dev)
+{
+ struct spi_master *master = dev_get_drvdata(dev);
+ struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
+ int error;
+
+ error = pinctrl_pm_select_default_state(dev);
+ if (error)
+ dev_warn(mcspi->dev, "%s: failed to set pins: %i\n",
+ __func__, error);
+
+ return 0;
+}
+
#else
-#define omap2_mcspi_suspend NULL
-#define omap2_mcspi_resume NULL
+#define omap2_mcspi_suspend_noirq NULL
+#define omap2_mcspi_resume_noirq NULL
#endif
static const struct dev_pm_ops omap2_mcspi_pm_ops = {
- .resume = omap2_mcspi_resume,
- .suspend = omap2_mcspi_suspend,
+ .suspend_noirq = omap2_mcspi_suspend_noirq,
+ .resume_noirq = omap2_mcspi_resume_noirq,
.runtime_resume = omap_mcspi_runtime_resume,
};
diff --git a/drivers/spi/spi-pxa2xx-dma.c b/drivers/spi/spi-pxa2xx-dma.c
index 3d7f660..2fa7f4b 100644
--- a/drivers/spi/spi-pxa2xx-dma.c
+++ b/drivers/spi/spi-pxa2xx-dma.c
@@ -51,19 +51,15 @@ static void pxa2xx_spi_dma_transfer_complete(struct driver_data *drv_data,
if (!pxa25x_ssp_comp(drv_data))
pxa2xx_spi_write(drv_data, SSTO, 0);
- if (!error) {
- msg->actual_length += drv_data->len;
- msg->state = pxa2xx_spi_next_transfer(drv_data);
- } else {
+ if (error) {
/* In case we got an error we disable the SSP now */
pxa2xx_spi_write(drv_data, SSCR0,
pxa2xx_spi_read(drv_data, SSCR0)
& ~SSCR0_SSE);
-
- msg->state = ERROR_STATE;
+ msg->status = -EIO;
}
- tasklet_schedule(&drv_data->pump_transfers);
+ spi_finalize_current_transfer(drv_data->master);
}
}
@@ -74,11 +70,11 @@ static void pxa2xx_spi_dma_callback(void *data)
static struct dma_async_tx_descriptor *
pxa2xx_spi_dma_prepare_one(struct driver_data *drv_data,
- enum dma_transfer_direction dir)
+ enum dma_transfer_direction dir,
+ struct spi_transfer *xfer)
{
struct chip_data *chip =
spi_get_ctldata(drv_data->master->cur_msg->spi);
- struct spi_transfer *xfer = drv_data->cur_transfer;
enum dma_slave_buswidth width;
struct dma_slave_config cfg;
struct dma_chan *chan;
@@ -144,12 +140,13 @@ irqreturn_t pxa2xx_spi_dma_transfer(struct driver_data *drv_data)
return IRQ_NONE;
}
-int pxa2xx_spi_dma_prepare(struct driver_data *drv_data, u32 dma_burst)
+int pxa2xx_spi_dma_prepare(struct driver_data *drv_data,
+ struct spi_transfer *xfer)
{
struct dma_async_tx_descriptor *tx_desc, *rx_desc;
int err;
- tx_desc = pxa2xx_spi_dma_prepare_one(drv_data, DMA_MEM_TO_DEV);
+ tx_desc = pxa2xx_spi_dma_prepare_one(drv_data, DMA_MEM_TO_DEV, xfer);
if (!tx_desc) {
dev_err(&drv_data->pdev->dev,
"failed to get DMA TX descriptor\n");
@@ -157,7 +154,7 @@ int pxa2xx_spi_dma_prepare(struct driver_data *drv_data, u32 dma_burst)
goto err_tx;
}
- rx_desc = pxa2xx_spi_dma_prepare_one(drv_data, DMA_DEV_TO_MEM);
+ rx_desc = pxa2xx_spi_dma_prepare_one(drv_data, DMA_DEV_TO_MEM, xfer);
if (!rx_desc) {
dev_err(&drv_data->pdev->dev,
"failed to get DMA RX descriptor\n");
@@ -187,6 +184,13 @@ void pxa2xx_spi_dma_start(struct driver_data *drv_data)
atomic_set(&drv_data->dma_running, 1);
}
+void pxa2xx_spi_dma_stop(struct driver_data *drv_data)
+{
+ atomic_set(&drv_data->dma_running, 0);
+ dmaengine_terminate_sync(drv_data->master->dma_rx);
+ dmaengine_terminate_sync(drv_data->master->dma_tx);
+}
+
int pxa2xx_spi_dma_setup(struct driver_data *drv_data)
{
struct pxa2xx_spi_master *pdata = drv_data->master_info;
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 82dcb88..0b2d60d 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -340,9 +340,11 @@ static void lpss_ssp_setup(struct driver_data *drv_data)
}
}
-static void lpss_ssp_select_cs(struct driver_data *drv_data,
+static void lpss_ssp_select_cs(struct spi_device *spi,
const struct lpss_config *config)
{
+ struct driver_data *drv_data =
+ spi_controller_get_devdata(spi->controller);
u32 value, cs;
if (!config->cs_sel_mask)
@@ -350,7 +352,7 @@ static void lpss_ssp_select_cs(struct driver_data *drv_data,
value = __lpss_ssp_read_priv(drv_data, config->reg_cs_ctrl);
- cs = drv_data->master->cur_msg->spi->chip_select;
+ cs = spi->chip_select;
cs <<= config->cs_sel_shift;
if (cs != (value & config->cs_sel_mask)) {
/*
@@ -369,15 +371,17 @@ static void lpss_ssp_select_cs(struct driver_data *drv_data,
}
}
-static void lpss_ssp_cs_control(struct driver_data *drv_data, bool enable)
+static void lpss_ssp_cs_control(struct spi_device *spi, bool enable)
{
+ struct driver_data *drv_data =
+ spi_controller_get_devdata(spi->controller);
const struct lpss_config *config;
u32 value;
config = lpss_get_config(drv_data);
if (enable)
- lpss_ssp_select_cs(drv_data, config);
+ lpss_ssp_select_cs(spi, config);
value = __lpss_ssp_read_priv(drv_data, config->reg_cs_ctrl);
if (enable)
@@ -387,10 +391,11 @@ static void lpss_ssp_cs_control(struct driver_data *drv_data, bool enable)
__lpss_ssp_write_priv(drv_data, config->reg_cs_ctrl, value);
}
-static void cs_assert(struct driver_data *drv_data)
+static void cs_assert(struct spi_device *spi)
{
- struct chip_data *chip =
- spi_get_ctldata(drv_data->master->cur_msg->spi);
+ struct chip_data *chip = spi_get_ctldata(spi);
+ struct driver_data *drv_data =
+ spi_controller_get_devdata(spi->controller);
if (drv_data->ssp_type == CE4100_SSP) {
pxa2xx_spi_write(drv_data, SSSR, chip->frm);
@@ -408,13 +413,14 @@ static void cs_assert(struct driver_data *drv_data)
}
if (is_lpss_ssp(drv_data))
- lpss_ssp_cs_control(drv_data, true);
+ lpss_ssp_cs_control(spi, true);
}
-static void cs_deassert(struct driver_data *drv_data)
+static void cs_deassert(struct spi_device *spi)
{
- struct chip_data *chip =
- spi_get_ctldata(drv_data->master->cur_msg->spi);
+ struct chip_data *chip = spi_get_ctldata(spi);
+ struct driver_data *drv_data =
+ spi_controller_get_devdata(spi->controller);
unsigned long timeout;
if (drv_data->ssp_type == CE4100_SSP)
@@ -437,7 +443,15 @@ static void cs_deassert(struct driver_data *drv_data)
}
if (is_lpss_ssp(drv_data))
- lpss_ssp_cs_control(drv_data, false);
+ lpss_ssp_cs_control(spi, false);
+}
+
+static void pxa2xx_spi_set_cs(struct spi_device *spi, bool level)
+{
+ if (level)
+ cs_deassert(spi);
+ else
+ cs_assert(spi);
}
int pxa2xx_spi_flush(struct driver_data *drv_data)
@@ -549,70 +563,6 @@ static int u32_reader(struct driver_data *drv_data)
return drv_data->rx == drv_data->rx_end;
}
-void *pxa2xx_spi_next_transfer(struct driver_data *drv_data)
-{
- struct spi_message *msg = drv_data->master->cur_msg;
- struct spi_transfer *trans = drv_data->cur_transfer;
-
- /* Move to next transfer */
- if (trans->transfer_list.next != &msg->transfers) {
- drv_data->cur_transfer =
- list_entry(trans->transfer_list.next,
- struct spi_transfer,
- transfer_list);
- return RUNNING_STATE;
- } else
- return DONE_STATE;
-}
-
-/* caller already set message->status; dma and pio irqs are blocked */
-static void giveback(struct driver_data *drv_data)
-{
- struct spi_transfer* last_transfer;
- struct spi_message *msg;
-
- msg = drv_data->master->cur_msg;
- drv_data->cur_transfer = NULL;
-
- last_transfer = list_last_entry(&msg->transfers, struct spi_transfer,
- transfer_list);
-
- /* Delay if requested before any change in chip select */
- if (last_transfer->delay_usecs)
- udelay(last_transfer->delay_usecs);
-
- /* Drop chip select UNLESS cs_change is true or we are returning
- * a message with an error, or next message is for another chip
- */
- if (!last_transfer->cs_change)
- cs_deassert(drv_data);
- else {
- struct spi_message *next_msg;
-
- /* Holding of cs was hinted, but we need to make sure
- * the next message is for the same chip. Don't waste
- * time with the following tests unless this was hinted.
- *
- * We cannot postpone this until pump_messages, because
- * after calling msg->complete (below) the driver that
- * sent the current message could be unloaded, which
- * could invalidate the cs_control() callback...
- */
-
- /* get a pointer to the next message, if any */
- next_msg = spi_get_next_queued_message(drv_data->master);
-
- /* see if the next and current messages point
- * to the same chip
- */
- if ((next_msg && next_msg->spi != msg->spi) ||
- msg->state == ERROR_STATE)
- cs_deassert(drv_data);
- }
-
- spi_finalize_current_message(drv_data->master);
-}
-
static void reset_sccr1(struct driver_data *drv_data)
{
struct chip_data *chip =
@@ -648,8 +598,8 @@ static void int_error_stop(struct driver_data *drv_data, const char* msg)
dev_err(&drv_data->pdev->dev, "%s\n", msg);
- drv_data->master->cur_msg->state = ERROR_STATE;
- tasklet_schedule(&drv_data->pump_transfers);
+ drv_data->master->cur_msg->status = -EIO;
+ spi_finalize_current_transfer(drv_data->master);
}
static void int_transfer_complete(struct driver_data *drv_data)
@@ -660,19 +610,7 @@ static void int_transfer_complete(struct driver_data *drv_data)
if (!pxa25x_ssp_comp(drv_data))
pxa2xx_spi_write(drv_data, SSTO, 0);
- /* Update total byte transferred return count actual bytes read */
- drv_data->master->cur_msg->actual_length += drv_data->len -
- (drv_data->rx_end - drv_data->rx);
-
- /* Transfer delays and chip select release are
- * handled in pump_transfers or giveback
- */
-
- /* Move to next transfer */
- drv_data->master->cur_msg->state = pxa2xx_spi_next_transfer(drv_data);
-
- /* Schedule transfer tasklet */
- tasklet_schedule(&drv_data->pump_transfers);
+ spi_finalize_current_transfer(drv_data->master);
}
static irqreturn_t interrupt_transfer(struct driver_data *drv_data)
@@ -973,17 +911,16 @@ static bool pxa2xx_spi_can_dma(struct spi_controller *master,
xfer->len >= chip->dma_burst_size;
}
-static void pump_transfers(unsigned long data)
+static int pxa2xx_spi_transfer_one(struct spi_controller *master,
+ struct spi_device *spi,
+ struct spi_transfer *transfer)
{
- struct driver_data *drv_data = (struct driver_data *)data;
- struct spi_controller *master = drv_data->master;
+ struct driver_data *drv_data = spi_controller_get_devdata(master);
struct spi_message *message = master->cur_msg;
struct chip_data *chip = spi_get_ctldata(message->spi);
u32 dma_thresh = chip->dma_threshold;
u32 dma_burst = chip->dma_burst_size;
u32 change_mask = pxa2xx_spi_get_ssrc1_change_mask(drv_data);
- struct spi_transfer *transfer;
- struct spi_transfer *previous;
u32 clk_div;
u8 bits;
u32 speed;
@@ -992,36 +929,6 @@ static void pump_transfers(unsigned long data)
int err;
int dma_mapped;
- /* Get current state information */
- transfer = drv_data->cur_transfer;
-
- /* Handle for abort */
- if (message->state == ERROR_STATE) {
- message->status = -EIO;
- giveback(drv_data);
- return;
- }
-
- /* Handle end of message */
- if (message->state == DONE_STATE) {
- message->status = 0;
- giveback(drv_data);
- return;
- }
-
- /* Delay if requested at end of transfer before CS change */
- if (message->state == RUNNING_STATE) {
- previous = list_entry(transfer->transfer_list.prev,
- struct spi_transfer,
- transfer_list);
- if (previous->delay_usecs)
- udelay(previous->delay_usecs);
-
- /* Drop chip select only if cs_change is requested */
- if (previous->cs_change)
- cs_deassert(drv_data);
- }
-
/* Check if we can DMA this transfer */
if (transfer->len > MAX_DMA_LEN && chip->enable_dma) {
@@ -1029,34 +936,27 @@ static void pump_transfers(unsigned long data)
if (message->is_dma_mapped
|| transfer->rx_dma || transfer->tx_dma) {
dev_err(&drv_data->pdev->dev,
- "pump_transfers: mapped transfer length of "
- "%u is greater than %d\n",
+ "Mapped transfer length of %u is greater than %d\n",
transfer->len, MAX_DMA_LEN);
- message->status = -EINVAL;
- giveback(drv_data);
- return;
+ return -EINVAL;
}
/* warn ... we force this to PIO mode */
dev_warn_ratelimited(&message->spi->dev,
- "pump_transfers: DMA disabled for transfer length %ld "
- "greater than %d\n",
- (long)drv_data->len, MAX_DMA_LEN);
+ "DMA disabled for transfer length %ld greater than %d\n",
+ (long)transfer->len, MAX_DMA_LEN);
}
/* Setup the transfer state based on the type of transfer */
if (pxa2xx_spi_flush(drv_data) == 0) {
- dev_err(&drv_data->pdev->dev, "pump_transfers: flush failed\n");
- message->status = -EIO;
- giveback(drv_data);
- return;
+ dev_err(&drv_data->pdev->dev, "Flush failed\n");
+ return -EIO;
}
drv_data->n_bytes = chip->n_bytes;
drv_data->tx = (void *)transfer->tx_buf;
drv_data->tx_end = drv_data->tx + transfer->len;
drv_data->rx = transfer->rx_buf;
drv_data->rx_end = drv_data->rx + transfer->len;
- drv_data->len = transfer->len;
drv_data->write = drv_data->tx ? chip->write : null_writer;
drv_data->read = drv_data->rx ? chip->read : null_reader;
@@ -1095,11 +995,9 @@ static void pump_transfers(unsigned long data)
bits, &dma_burst,
&dma_thresh))
dev_warn_ratelimited(&message->spi->dev,
- "pump_transfers: DMA burst size reduced to match bits_per_word\n");
+ "DMA burst size reduced to match bits_per_word\n");
}
- message->state = RUNNING_STATE;
-
dma_mapped = master->can_dma &&
master->can_dma(master, message->spi, transfer) &&
master->cur_msg_mapped;
@@ -1108,12 +1006,9 @@ static void pump_transfers(unsigned long data)
/* Ensure we have the correct interrupt handler */
drv_data->transfer_handler = pxa2xx_spi_dma_transfer;
- err = pxa2xx_spi_dma_prepare(drv_data, dma_burst);
- if (err) {
- message->status = err;
- giveback(drv_data);
- return;
- }
+ err = pxa2xx_spi_dma_prepare(drv_data, transfer);
+ if (err)
+ return err;
/* Clear status and start DMA engine */
cr1 = chip->cr1 | dma_thresh | drv_data->dma_cr1;
@@ -1175,27 +1070,40 @@ static void pump_transfers(unsigned long data)
pxa2xx_spi_write(drv_data, SSTO, chip->timeout);
}
- cs_assert(drv_data);
-
- /* after chip select, release the data by enabling service
- * requests and interrupts, without changing any mode bits */
+ /*
+ * Release the data by enabling service requests and interrupts,
+ * without changing any mode bits
+ */
pxa2xx_spi_write(drv_data, SSCR1, cr1);
+
+ return 1;
}
-static int pxa2xx_spi_transfer_one_message(struct spi_controller *master,
- struct spi_message *msg)
+static void pxa2xx_spi_handle_err(struct spi_controller *master,
+ struct spi_message *msg)
{
struct driver_data *drv_data = spi_controller_get_devdata(master);
- /* Initial message state*/
- msg->state = START_STATE;
- drv_data->cur_transfer = list_entry(msg->transfers.next,
- struct spi_transfer,
- transfer_list);
+ /* Disable the SSP */
+ pxa2xx_spi_write(drv_data, SSCR0,
+ pxa2xx_spi_read(drv_data, SSCR0) & ~SSCR0_SSE);
+ /* Clear and disable interrupts and service requests */
+ write_SSSR_CS(drv_data, drv_data->clear_sr);
+ pxa2xx_spi_write(drv_data, SSCR1,
+ pxa2xx_spi_read(drv_data, SSCR1)
+ & ~(drv_data->int_cr1 | drv_data->dma_cr1));
+ if (!pxa25x_ssp_comp(drv_data))
+ pxa2xx_spi_write(drv_data, SSTO, 0);
- /* Mark as busy and launch transfers */
- tasklet_schedule(&drv_data->pump_transfers);
- return 0;
+ /*
+ * Stop the DMA if running. Note DMA callback handler may have unset
+ * the dma_running already, which is fine as stopping is not needed
+ * then but we shouldn't rely this flag for anything else than
+ * stopping. For instance to differentiate between PIO and DMA
+ * transfers.
+ */
+ if (atomic_read(&drv_data->dma_running))
+ pxa2xx_spi_dma_stop(drv_data);
}
static int pxa2xx_spi_unprepare_transfer(struct spi_controller *master)
@@ -1651,7 +1559,9 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
master->dma_alignment = DMA_ALIGNMENT;
master->cleanup = cleanup;
master->setup = setup;
- master->transfer_one_message = pxa2xx_spi_transfer_one_message;
+ master->set_cs = pxa2xx_spi_set_cs;
+ master->transfer_one = pxa2xx_spi_transfer_one;
+ master->handle_err = pxa2xx_spi_handle_err;
master->unprepare_transfer_hardware = pxa2xx_spi_unprepare_transfer;
master->fw_translate_cs = pxa2xx_spi_fw_translate_cs;
master->auto_runtime_pm = true;
@@ -1702,7 +1612,9 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
}
/* Enable SOC clock */
- clk_prepare_enable(ssp->clk);
+ status = clk_prepare_enable(ssp->clk);
+ if (status)
+ goto out_error_dma_irq_alloc;
master->max_speed_hz = clk_get_rate(ssp->clk);
@@ -1787,9 +1699,6 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
}
}
- tasklet_init(&drv_data->pump_transfers, pump_transfers,
- (unsigned long)drv_data);
-
pm_runtime_set_autosuspend_delay(&pdev->dev, 50);
pm_runtime_use_autosuspend(&pdev->dev);
pm_runtime_set_active(&pdev->dev);
@@ -1809,6 +1718,8 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
pm_runtime_put_noidle(&pdev->dev);
pm_runtime_disable(&pdev->dev);
clk_disable_unprepare(ssp->clk);
+
+out_error_dma_irq_alloc:
pxa2xx_spi_dma_release(drv_data);
free_irq(ssp->irq, drv_data);
@@ -1882,8 +1793,11 @@ static int pxa2xx_spi_resume(struct device *dev)
int status;
/* Enable the SSP clock */
- if (!pm_runtime_suspended(dev))
- clk_prepare_enable(ssp->clk);
+ if (!pm_runtime_suspended(dev)) {
+ status = clk_prepare_enable(ssp->clk);
+ if (status)
+ return status;
+ }
/* Restore LPSS private register bits */
if (is_lpss_ssp(drv_data))
@@ -1912,9 +1826,10 @@ static int pxa2xx_spi_runtime_suspend(struct device *dev)
static int pxa2xx_spi_runtime_resume(struct device *dev)
{
struct driver_data *drv_data = dev_get_drvdata(dev);
+ int status;
- clk_prepare_enable(drv_data->ssp->clk);
- return 0;
+ status = clk_prepare_enable(drv_data->ssp->clk);
+ return status;
}
#endif
diff --git a/drivers/spi/spi-pxa2xx.h b/drivers/spi/spi-pxa2xx.h
index 513ec6c..513c53a 100644
--- a/drivers/spi/spi-pxa2xx.h
+++ b/drivers/spi/spi-pxa2xx.h
@@ -38,7 +38,7 @@ struct driver_data {
/* SSP register addresses */
void __iomem *ioaddr;
- u32 ssdr_physical;
+ phys_addr_t ssdr_physical;
/* SSP masks*/
u32 dma_cr1;
@@ -46,15 +46,10 @@ struct driver_data {
u32 clear_sr;
u32 mask_sr;
- /* Message Transfer pump */
- struct tasklet_struct pump_transfers;
-
/* DMA engine support */
atomic_t dma_running;
- /* Current message transfer state info */
- struct spi_transfer *cur_transfer;
- size_t len;
+ /* Current transfer state info */
void *tx;
void *tx_end;
void *rx;
@@ -104,11 +99,6 @@ static inline void pxa2xx_spi_write(const struct driver_data *drv_data,
__raw_writel(val, drv_data->ioaddr + reg);
}
-#define START_STATE ((void *)0)
-#define RUNNING_STATE ((void *)1)
-#define DONE_STATE ((void *)2)
-#define ERROR_STATE ((void *)-1)
-
#define DMA_ALIGNMENT 8
static inline int pxa25x_ssp_comp(struct driver_data *drv_data)
@@ -133,14 +123,15 @@ static inline void write_SSSR_CS(struct driver_data *drv_data, u32 val)
}
extern int pxa2xx_spi_flush(struct driver_data *drv_data);
-extern void *pxa2xx_spi_next_transfer(struct driver_data *drv_data);
#define MAX_DMA_LEN SZ_64K
#define DEFAULT_DMA_CR1 (SSCR1_TSRE | SSCR1_RSRE | SSCR1_TRAIL)
extern irqreturn_t pxa2xx_spi_dma_transfer(struct driver_data *drv_data);
-extern int pxa2xx_spi_dma_prepare(struct driver_data *drv_data, u32 dma_burst);
+extern int pxa2xx_spi_dma_prepare(struct driver_data *drv_data,
+ struct spi_transfer *xfer);
extern void pxa2xx_spi_dma_start(struct driver_data *drv_data);
+extern void pxa2xx_spi_dma_stop(struct driver_data *drv_data);
extern int pxa2xx_spi_dma_setup(struct driver_data *drv_data);
extern void pxa2xx_spi_dma_release(struct driver_data *drv_data);
extern int pxa2xx_spi_set_dma_burst_and_threshold(struct chip_data *chip,
diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index baa3a9f..7b7151e 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -28,15 +28,15 @@
#define S3C64XX_SPI_CH_CFG 0x00
#define S3C64XX_SPI_CLK_CFG 0x04
-#define S3C64XX_SPI_MODE_CFG 0x08
-#define S3C64XX_SPI_SLAVE_SEL 0x0C
+#define S3C64XX_SPI_MODE_CFG 0x08
+#define S3C64XX_SPI_SLAVE_SEL 0x0C
#define S3C64XX_SPI_INT_EN 0x10
#define S3C64XX_SPI_STATUS 0x14
#define S3C64XX_SPI_TX_DATA 0x18
#define S3C64XX_SPI_RX_DATA 0x1C
-#define S3C64XX_SPI_PACKET_CNT 0x20
-#define S3C64XX_SPI_PENDING_CLR 0x24
-#define S3C64XX_SPI_SWAP_CFG 0x28
+#define S3C64XX_SPI_PACKET_CNT 0x20
+#define S3C64XX_SPI_PENDING_CLR 0x24
+#define S3C64XX_SPI_SWAP_CFG 0x28
#define S3C64XX_SPI_FB_CLK 0x2C
#define S3C64XX_SPI_CH_HS_EN (1<<6) /* High Speed Enable */
@@ -77,9 +77,9 @@
#define S3C64XX_SPI_INT_TX_FIFORDY_EN (1<<0)
#define S3C64XX_SPI_ST_RX_OVERRUN_ERR (1<<5)
-#define S3C64XX_SPI_ST_RX_UNDERRUN_ERR (1<<4)
+#define S3C64XX_SPI_ST_RX_UNDERRUN_ERR (1<<4)
#define S3C64XX_SPI_ST_TX_OVERRUN_ERR (1<<3)
-#define S3C64XX_SPI_ST_TX_UNDERRUN_ERR (1<<2)
+#define S3C64XX_SPI_ST_TX_UNDERRUN_ERR (1<<2)
#define S3C64XX_SPI_ST_RX_FIFORDY (1<<1)
#define S3C64XX_SPI_ST_TX_FIFORDY (1<<0)
@@ -100,7 +100,7 @@
#define S3C64XX_SPI_SWAP_TX_BIT (1<<1)
#define S3C64XX_SPI_SWAP_TX_EN (1<<0)
-#define S3C64XX_SPI_FBCLK_MSK (3<<0)
+#define S3C64XX_SPI_FBCLK_MSK (3<<0)
#define FIFO_LVL_MASK(i) ((i)->port_conf->fifo_lvl_mask[i->port_id])
#define S3C64XX_SPI_ST_TX_DONE(v, i) (((v) & \
@@ -156,7 +156,6 @@ struct s3c64xx_spi_port_config {
* @ioclk: Pointer to the i/o clock between master and slave
* @master: Pointer to the SPI Protocol master.
* @cntrlr_info: Platform specific data for the controller this driver manages.
- * @tgl_spi: Pointer to the last CS left untoggled by the cs_change hint.
* @lock: Controller specific lock.
* @state: Set of FLAGS to indicate status.
* @rx_dmach: Controller's DMA channel for Rx.
@@ -177,7 +176,6 @@ struct s3c64xx_spi_driver_data {
struct platform_device *pdev;
struct spi_master *master;
struct s3c64xx_spi_info *cntrlr_info;
- struct spi_device *tgl_spi;
spinlock_t lock;
unsigned long sfr_start;
struct completion xfer_completion;
@@ -190,7 +188,7 @@ struct s3c64xx_spi_driver_data {
unsigned int port_id;
};
-static void flush_fifo(struct s3c64xx_spi_driver_data *sdd)
+static void s3c64xx_flush_fifo(struct s3c64xx_spi_driver_data *sdd)
{
void __iomem *regs = sdd->regs;
unsigned long loops;
@@ -350,9 +348,8 @@ static bool s3c64xx_spi_can_dma(struct spi_master *master,
return xfer->len > (FIFO_LVL_MASK(sdd) >> 1) + 1;
}
-static void enable_datapath(struct s3c64xx_spi_driver_data *sdd,
- struct spi_device *spi,
- struct spi_transfer *xfer, int dma_mode)
+static void s3c64xx_enable_datapath(struct s3c64xx_spi_driver_data *sdd,
+ struct spi_transfer *xfer, int dma_mode)
{
void __iomem *regs = sdd->regs;
u32 modecfg, chcfg;
@@ -442,8 +439,8 @@ static u32 s3c64xx_spi_wait_for_timeout(struct s3c64xx_spi_driver_data *sdd,
return RX_FIFO_LVL(status, sdd);
}
-static int wait_for_dma(struct s3c64xx_spi_driver_data *sdd,
- struct spi_transfer *xfer)
+static int s3c64xx_wait_for_dma(struct s3c64xx_spi_driver_data *sdd,
+ struct spi_transfer *xfer)
{
void __iomem *regs = sdd->regs;
unsigned long val;
@@ -485,8 +482,8 @@ static int wait_for_dma(struct s3c64xx_spi_driver_data *sdd,
return 0;
}
-static int wait_for_pio(struct s3c64xx_spi_driver_data *sdd,
- struct spi_transfer *xfer)
+static int s3c64xx_wait_for_pio(struct s3c64xx_spi_driver_data *sdd,
+ struct spi_transfer *xfer)
{
void __iomem *regs = sdd->regs;
unsigned long val;
@@ -505,6 +502,8 @@ static int wait_for_pio(struct s3c64xx_spi_driver_data *sdd,
status = readl(regs + S3C64XX_SPI_STATUS);
} while (RX_FIFO_LVL(status, sdd) < xfer->len && --val);
+ if (!val)
+ return -EIO;
/* If it was only Tx */
if (!xfer->rx_buf) {
@@ -635,11 +634,15 @@ static int s3c64xx_spi_transfer_one(struct spi_master *master,
struct spi_transfer *xfer)
{
struct s3c64xx_spi_driver_data *sdd = spi_master_get_devdata(master);
+ const unsigned int fifo_len = (FIFO_LVL_MASK(sdd) >> 1) + 1;
+ const void *tx_buf = NULL;
+ void *rx_buf = NULL;
+ int target_len = 0, origin_len = 0;
+ int use_dma = 0;
int status;
u32 speed;
u8 bpw;
unsigned long flags;
- int use_dma;
reinit_completion(&sdd->xfer_completion);
@@ -654,48 +657,77 @@ static int s3c64xx_spi_transfer_one(struct spi_master *master,
s3c64xx_spi_config(sdd);
}
- /* Polling method for xfers not bigger than FIFO capacity */
- use_dma = 0;
- if (!is_polling(sdd) &&
- (sdd->rx_dma.ch && sdd->tx_dma.ch &&
- (xfer->len > ((FIFO_LVL_MASK(sdd) >> 1) + 1))))
+ if (!is_polling(sdd) && (xfer->len > fifo_len) &&
+ sdd->rx_dma.ch && sdd->tx_dma.ch) {
use_dma = 1;
- spin_lock_irqsave(&sdd->lock, flags);
+ } else if (is_polling(sdd) && xfer->len > fifo_len) {
+ tx_buf = xfer->tx_buf;
+ rx_buf = xfer->rx_buf;
+ origin_len = xfer->len;
- /* Pending only which is to be done */
- sdd->state &= ~RXBUSY;
- sdd->state &= ~TXBUSY;
+ target_len = xfer->len;
+ if (xfer->len > fifo_len)
+ xfer->len = fifo_len;
+ }
- enable_datapath(sdd, spi, xfer, use_dma);
+ do {
+ spin_lock_irqsave(&sdd->lock, flags);
- /* Start the signals */
- s3c64xx_spi_set_cs(spi, true);
+ /* Pending only which is to be done */
+ sdd->state &= ~RXBUSY;
+ sdd->state &= ~TXBUSY;
- spin_unlock_irqrestore(&sdd->lock, flags);
+ s3c64xx_enable_datapath(sdd, xfer, use_dma);
- if (use_dma)
- status = wait_for_dma(sdd, xfer);
- else
- status = wait_for_pio(sdd, xfer);
+ /* Start the signals */
+ s3c64xx_spi_set_cs(spi, true);
- if (status) {
- dev_err(&spi->dev, "I/O Error: rx-%d tx-%d res:rx-%c tx-%c len-%d\n",
- xfer->rx_buf ? 1 : 0, xfer->tx_buf ? 1 : 0,
- (sdd->state & RXBUSY) ? 'f' : 'p',
- (sdd->state & TXBUSY) ? 'f' : 'p',
- xfer->len);
+ spin_unlock_irqrestore(&sdd->lock, flags);
- if (use_dma) {
- if (xfer->tx_buf != NULL
- && (sdd->state & TXBUSY))
- dmaengine_terminate_all(sdd->tx_dma.ch);
- if (xfer->rx_buf != NULL
- && (sdd->state & RXBUSY))
- dmaengine_terminate_all(sdd->rx_dma.ch);
+ if (use_dma)
+ status = s3c64xx_wait_for_dma(sdd, xfer);
+ else
+ status = s3c64xx_wait_for_pio(sdd, xfer);
+
+ if (status) {
+ dev_err(&spi->dev,
+ "I/O Error: rx-%d tx-%d res:rx-%c tx-%c len-%d\n",
+ xfer->rx_buf ? 1 : 0, xfer->tx_buf ? 1 : 0,
+ (sdd->state & RXBUSY) ? 'f' : 'p',
+ (sdd->state & TXBUSY) ? 'f' : 'p',
+ xfer->len);
+
+ if (use_dma) {
+ if (xfer->tx_buf && (sdd->state & TXBUSY))
+ dmaengine_terminate_all(sdd->tx_dma.ch);
+ if (xfer->rx_buf && (sdd->state & RXBUSY))
+ dmaengine_terminate_all(sdd->rx_dma.ch);
+ }
+ } else {
+ s3c64xx_flush_fifo(sdd);
}
- } else {
- flush_fifo(sdd);
+ if (target_len > 0) {
+ target_len -= xfer->len;
+
+ if (xfer->tx_buf)
+ xfer->tx_buf += xfer->len;
+
+ if (xfer->rx_buf)
+ xfer->rx_buf += xfer->len;
+
+ if (target_len > fifo_len)
+ xfer->len = fifo_len;
+ else
+ xfer->len = target_len;
+ }
+ } while (target_len > 0);
+
+ if (origin_len) {
+ /* Restore original xfer buffers and length */
+ xfer->tx_buf = tx_buf;
+ xfer->rx_buf = rx_buf;
+ xfer->len = origin_len;
}
return status;
@@ -891,7 +923,7 @@ static irqreturn_t s3c64xx_spi_irq(int irq, void *data)
return IRQ_HANDLED;
}
-static void s3c64xx_spi_hwinit(struct s3c64xx_spi_driver_data *sdd, int channel)
+static void s3c64xx_spi_hwinit(struct s3c64xx_spi_driver_data *sdd)
{
struct s3c64xx_spi_info *sci = sdd->cntrlr_info;
void __iomem *regs = sdd->regs;
@@ -929,7 +961,7 @@ static void s3c64xx_spi_hwinit(struct s3c64xx_spi_driver_data *sdd, int channel)
val |= (S3C64XX_SPI_TRAILCNT << S3C64XX_SPI_TRAILCNT_OFF);
writel(val, regs + S3C64XX_SPI_MODE_CFG);
- flush_fifo(sdd);
+ s3c64xx_flush_fifo(sdd);
}
#ifdef CONFIG_OF
@@ -1145,7 +1177,7 @@ static int s3c64xx_spi_probe(struct platform_device *pdev)
pm_runtime_get_sync(&pdev->dev);
/* Setup Deufult Mode */
- s3c64xx_spi_hwinit(sdd, sdd->port_id);
+ s3c64xx_spi_hwinit(sdd);
spin_lock_init(&sdd->lock);
init_completion(&sdd->xfer_completion);
@@ -1260,8 +1292,6 @@ static int s3c64xx_spi_resume(struct device *dev)
if (ret < 0)
return ret;
- s3c64xx_spi_hwinit(sdd, sdd->port_id);
-
return spi_master_resume(master);
}
#endif /* CONFIG_PM_SLEEP */
@@ -1299,6 +1329,8 @@ static int s3c64xx_spi_runtime_resume(struct device *dev)
if (ret != 0)
goto err_disable_src_clk;
+ s3c64xx_spi_hwinit(sdd);
+
return 0;
err_disable_src_clk:
@@ -1344,15 +1376,6 @@ static struct s3c64xx_spi_port_config exynos4_spi_port_config = {
.clk_from_cmu = true,
};
-static struct s3c64xx_spi_port_config exynos5440_spi_port_config = {
- .fifo_lvl_mask = { 0x1ff },
- .rx_lvl_offset = 15,
- .tx_st_done = 25,
- .high_speed = true,
- .clk_from_cmu = true,
- .quirks = S3C64XX_SPI_QUIRK_POLL,
-};
-
static struct s3c64xx_spi_port_config exynos7_spi_port_config = {
.fifo_lvl_mask = { 0x1ff, 0x7F, 0x7F, 0x7F, 0x7F, 0x1ff},
.rx_lvl_offset = 15,
@@ -1396,9 +1419,6 @@ static const struct of_device_id s3c64xx_spi_dt_match[] = {
{ .compatible = "samsung,exynos4210-spi",
.data = (void *)&exynos4_spi_port_config,
},
- { .compatible = "samsung,exynos5440-spi",
- .data = (void *)&exynos5440_spi_port_config,
- },
{ .compatible = "samsung,exynos7-spi",
.data = (void *)&exynos7_spi_port_config,
},
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index ae086aa..0e74cbf 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -39,7 +39,7 @@ struct sh_msiof_chipdata {
u16 tx_fifo_size;
u16 rx_fifo_size;
u16 master_flags;
- u16 min_div;
+ u16 min_div_pow;
};
struct sh_msiof_spi_priv {
@@ -51,7 +51,7 @@ struct sh_msiof_spi_priv {
struct completion done;
unsigned int tx_fifo_size;
unsigned int rx_fifo_size;
- unsigned int min_div;
+ unsigned int min_div_pow;
void *tx_dma_page;
void *rx_dma_page;
dma_addr_t tx_dma_addr;
@@ -249,42 +249,46 @@ static irqreturn_t sh_msiof_spi_irq(int irq, void *data)
return IRQ_HANDLED;
}
-static struct {
- unsigned short div;
- unsigned short brdv;
-} const sh_msiof_spi_div_table[] = {
- { 1, SCR_BRDV_DIV_1 },
- { 2, SCR_BRDV_DIV_2 },
- { 4, SCR_BRDV_DIV_4 },
- { 8, SCR_BRDV_DIV_8 },
- { 16, SCR_BRDV_DIV_16 },
- { 32, SCR_BRDV_DIV_32 },
+static const u32 sh_msiof_spi_div_array[] = {
+ SCR_BRDV_DIV_1, SCR_BRDV_DIV_2, SCR_BRDV_DIV_4,
+ SCR_BRDV_DIV_8, SCR_BRDV_DIV_16, SCR_BRDV_DIV_32,
};
static void sh_msiof_spi_set_clk_regs(struct sh_msiof_spi_priv *p,
unsigned long parent_rate, u32 spi_hz)
{
- unsigned long div = 1024;
+ unsigned long div;
u32 brps, scr;
- size_t k;
+ unsigned int div_pow = p->min_div_pow;
- if (!WARN_ON(!spi_hz || !parent_rate))
- div = DIV_ROUND_UP(parent_rate, spi_hz);
-
- div = max_t(unsigned long, div, p->min_div);
-
- for (k = 0; k < ARRAY_SIZE(sh_msiof_spi_div_table); k++) {
- brps = DIV_ROUND_UP(div, sh_msiof_spi_div_table[k].div);
- /* SCR_BRDV_DIV_1 is valid only if BRPS is x 1/1 or x 1/2 */
- if (sh_msiof_spi_div_table[k].div == 1 && brps > 2)
- continue;
- if (brps <= 32) /* max of brdv is 32 */
- break;
+ if (!spi_hz || !parent_rate) {
+ WARN(1, "Invalid clock rate parameters %lu and %u\n",
+ parent_rate, spi_hz);
+ return;
}
- k = min_t(int, k, ARRAY_SIZE(sh_msiof_spi_div_table) - 1);
+ div = DIV_ROUND_UP(parent_rate, spi_hz);
+ if (div <= 1024) {
+ /* SCR_BRDV_DIV_1 is valid only if BRPS is x 1/1 or x 1/2 */
+ if (!div_pow && div <= 32 && div > 2)
+ div_pow = 1;
- scr = sh_msiof_spi_div_table[k].brdv | SCR_BRPS(brps);
+ if (div_pow)
+ brps = (div + 1) >> div_pow;
+ else
+ brps = div;
+
+ for (; brps > 32; div_pow++)
+ brps = (brps + 1) >> 1;
+ } else {
+ /* Set transfer rate composite divisor to 2^5 * 32 = 1024 */
+ dev_err(&p->pdev->dev,
+ "Requested SPI transfer rate %d is too low\n", spi_hz);
+ div_pow = 5;
+ brps = 32;
+ }
+
+ scr = sh_msiof_spi_div_array[div_pow] | SCR_BRPS(brps);
sh_msiof_write(p, TSCR, scr);
if (!(p->master->flags & SPI_MASTER_MUST_TX))
sh_msiof_write(p, RSCR, scr);
@@ -563,14 +567,16 @@ static int sh_msiof_spi_setup(struct spi_device *spi)
/* Configure native chip select mode/polarity early */
clr = MDR1_SYNCMD_MASK;
- set = MDR1_TRMD | TMDR1_PCON | MDR1_SYNCMD_SPI;
+ set = MDR1_SYNCMD_SPI;
if (spi->mode & SPI_CS_HIGH)
clr |= BIT(MDR1_SYNCAC_SHIFT);
else
set |= BIT(MDR1_SYNCAC_SHIFT);
pm_runtime_get_sync(&p->pdev->dev);
tmp = sh_msiof_read(p, TMDR1) & ~clr;
- sh_msiof_write(p, TMDR1, tmp | set);
+ sh_msiof_write(p, TMDR1, tmp | set | MDR1_TRMD | TMDR1_PCON);
+ tmp = sh_msiof_read(p, RMDR1) & ~clr;
+ sh_msiof_write(p, RMDR1, tmp | set);
pm_runtime_put(&p->pdev->dev);
p->native_cs_high = spi->mode & SPI_CS_HIGH;
p->native_cs_inited = true;
@@ -1040,21 +1046,21 @@ static const struct sh_msiof_chipdata sh_data = {
.tx_fifo_size = 64,
.rx_fifo_size = 64,
.master_flags = 0,
- .min_div = 1,
+ .min_div_pow = 0,
};
static const struct sh_msiof_chipdata rcar_gen2_data = {
.tx_fifo_size = 64,
.rx_fifo_size = 64,
.master_flags = SPI_MASTER_MUST_TX,
- .min_div = 1,
+ .min_div_pow = 0,
};
static const struct sh_msiof_chipdata rcar_gen3_data = {
.tx_fifo_size = 64,
.rx_fifo_size = 64,
.master_flags = SPI_MASTER_MUST_TX,
- .min_div = 2,
+ .min_div_pow = 1,
};
static const struct of_device_id sh_msiof_match[] = {
@@ -1318,7 +1324,7 @@ static int sh_msiof_spi_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, p);
p->master = master;
p->info = info;
- p->min_div = chipdata->min_div;
+ p->min_div_pow = chipdata->min_div_pow;
init_completion(&p->done);
diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index ba9743f..ad1e55d 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -1129,7 +1129,7 @@ static int stm32_spi_probe(struct platform_device *pdev)
if (!spi->clk_rate) {
dev_err(&pdev->dev, "clk rate = 0\n");
ret = -EINVAL;
- goto err_master_put;
+ goto err_clk_disable;
}
spi->rst = devm_reset_control_get_exclusive(&pdev->dev, NULL);
diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c
index c24d9b4..5f19016 100644
--- a/drivers/spi/spi-ti-qspi.c
+++ b/drivers/spi/spi-ti-qspi.c
@@ -36,6 +36,7 @@
#include <linux/sizes.h>
#include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
struct ti_qspi_regs {
u32 clkctrl;
@@ -50,6 +51,7 @@ struct ti_qspi {
struct spi_master *master;
void __iomem *base;
void __iomem *mmap_base;
+ size_t mmap_size;
struct regmap *ctrl_base;
unsigned int ctrl_reg;
struct clk *fclk;
@@ -434,12 +436,10 @@ static int ti_qspi_dma_xfer(struct ti_qspi *qspi, dma_addr_t dma_dst,
return 0;
}
-static int ti_qspi_dma_bounce_buffer(struct ti_qspi *qspi,
- struct spi_flash_read_message *msg)
+static int ti_qspi_dma_bounce_buffer(struct ti_qspi *qspi, loff_t offs,
+ void *to, size_t readsize)
{
- size_t readsize = msg->len;
- void *to = msg->buf;
- dma_addr_t dma_src = qspi->mmap_phys_base + msg->from;
+ dma_addr_t dma_src = qspi->mmap_phys_base + offs;
int ret = 0;
/*
@@ -507,13 +507,14 @@ static void ti_qspi_disable_memory_map(struct spi_device *spi)
qspi->mmap_enabled = false;
}
-static void ti_qspi_setup_mmap_read(struct spi_device *spi,
- struct spi_flash_read_message *msg)
+static void ti_qspi_setup_mmap_read(struct spi_device *spi, u8 opcode,
+ u8 data_nbits, u8 addr_width,
+ u8 dummy_bytes)
{
struct ti_qspi *qspi = spi_master_get_devdata(spi->master);
- u32 memval = msg->read_opcode;
+ u32 memval = opcode;
- switch (msg->data_nbits) {
+ switch (data_nbits) {
case SPI_NBITS_QUAD:
memval |= QSPI_SETUP_RD_QUAD;
break;
@@ -524,48 +525,64 @@ static void ti_qspi_setup_mmap_read(struct spi_device *spi,
memval |= QSPI_SETUP_RD_NORMAL;
break;
}
- memval |= ((msg->addr_width - 1) << QSPI_SETUP_ADDR_SHIFT |
- msg->dummy_bytes << QSPI_SETUP_DUMMY_SHIFT);
+ memval |= ((addr_width - 1) << QSPI_SETUP_ADDR_SHIFT |
+ dummy_bytes << QSPI_SETUP_DUMMY_SHIFT);
ti_qspi_write(qspi, memval,
QSPI_SPI_SETUP_REG(spi->chip_select));
}
-static bool ti_qspi_spi_flash_can_dma(struct spi_device *spi,
- struct spi_flash_read_message *msg)
+static int ti_qspi_exec_mem_op(struct spi_mem *mem,
+ const struct spi_mem_op *op)
{
- return virt_addr_valid(msg->buf);
-}
-
-static int ti_qspi_spi_flash_read(struct spi_device *spi,
- struct spi_flash_read_message *msg)
-{
- struct ti_qspi *qspi = spi_master_get_devdata(spi->master);
+ struct ti_qspi *qspi = spi_master_get_devdata(mem->spi->master);
+ u32 from = 0;
int ret = 0;
+ /* Only optimize read path. */
+ if (!op->data.nbytes || op->data.dir != SPI_MEM_DATA_IN ||
+ !op->addr.nbytes || op->addr.nbytes > 4)
+ return -ENOTSUPP;
+
+ /* Address exceeds MMIO window size, fall back to regular mode. */
+ from = op->addr.val;
+ if (from + op->data.nbytes > qspi->mmap_size)
+ return -ENOTSUPP;
+
mutex_lock(&qspi->list_lock);
if (!qspi->mmap_enabled)
- ti_qspi_enable_memory_map(spi);
- ti_qspi_setup_mmap_read(spi, msg);
+ ti_qspi_enable_memory_map(mem->spi);
+ ti_qspi_setup_mmap_read(mem->spi, op->cmd.opcode, op->data.buswidth,
+ op->addr.nbytes, op->dummy.nbytes);
if (qspi->rx_chan) {
- if (msg->cur_msg_mapped)
- ret = ti_qspi_dma_xfer_sg(qspi, msg->rx_sg, msg->from);
- else
- ret = ti_qspi_dma_bounce_buffer(qspi, msg);
- if (ret)
- goto err_unlock;
- } else {
- memcpy_fromio(msg->buf, qspi->mmap_base + msg->from, msg->len);
- }
- msg->retlen = msg->len;
+ struct sg_table sgt;
-err_unlock:
+ if (virt_addr_valid(op->data.buf.in) &&
+ !spi_controller_dma_map_mem_op_data(mem->spi->master, op,
+ &sgt)) {
+ ret = ti_qspi_dma_xfer_sg(qspi, sgt, from);
+ spi_controller_dma_unmap_mem_op_data(mem->spi->master,
+ op, &sgt);
+ } else {
+ ret = ti_qspi_dma_bounce_buffer(qspi, from,
+ op->data.buf.in,
+ op->data.nbytes);
+ }
+ } else {
+ memcpy_fromio(op->data.buf.in, qspi->mmap_base + from,
+ op->data.nbytes);
+ }
+
mutex_unlock(&qspi->list_lock);
return ret;
}
+static const struct spi_controller_mem_ops ti_qspi_mem_ops = {
+ .exec_op = ti_qspi_exec_mem_op,
+};
+
static int ti_qspi_start_transfer_one(struct spi_master *master,
struct spi_message *m)
{
@@ -672,7 +689,7 @@ static int ti_qspi_probe(struct platform_device *pdev)
master->dev.of_node = pdev->dev.of_node;
master->bits_per_word_mask = SPI_BPW_MASK(32) | SPI_BPW_MASK(16) |
SPI_BPW_MASK(8);
- master->spi_flash_read = ti_qspi_spi_flash_read;
+ master->mem_ops = &ti_qspi_mem_ops;
if (!of_property_read_u32(np, "num-cs", &num_cs))
master->num_chipselect = num_cs;
@@ -702,6 +719,9 @@ static int ti_qspi_probe(struct platform_device *pdev)
}
}
+ if (res_mmap)
+ qspi->mmap_size = resource_size(res_mmap);
+
irq = platform_get_irq(pdev, 0);
if (irq < 0) {
dev_err(&pdev->dev, "no irq resource?\n");
@@ -770,7 +790,6 @@ static int ti_qspi_probe(struct platform_device *pdev)
dma_release_channel(qspi->rx_chan);
goto no_dma;
}
- master->spi_flash_can_dma = ti_qspi_spi_flash_can_dma;
master->dma_rx = qspi->rx_chan;
init_completion(&qspi->transfer_complete);
if (res_mmap)
@@ -784,7 +803,7 @@ static int ti_qspi_probe(struct platform_device *pdev)
"mmap failed with error %ld using PIO mode\n",
PTR_ERR(qspi->mmap_base));
qspi->mmap_base = NULL;
- master->spi_flash_read = NULL;
+ master->mem_ops = NULL;
}
}
qspi->mmap_enabled = false;
diff --git a/drivers/spi/spi-zynqmp-gqspi.c b/drivers/spi/spi-zynqmp-gqspi.c
index 18aeace..cc4d310 100644
--- a/drivers/spi/spi-zynqmp-gqspi.c
+++ b/drivers/spi/spi-zynqmp-gqspi.c
@@ -20,6 +20,7 @@
#include <linux/of_irq.h>
#include <linux/of_address.h>
#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
#include <linux/spi/spi.h>
#include <linux/spinlock.h>
#include <linux/workqueue.h>
@@ -135,6 +136,7 @@
#define GQSPI_DMA_UNALIGN 0x3
#define GQSPI_DEFAULT_NUM_CS 1 /* Default number of chip selects */
+#define SPI_AUTOSUSPEND_TIMEOUT 3000
enum mode_type {GQSPI_MODE_IO, GQSPI_MODE_DMA};
/**
@@ -356,21 +358,9 @@ static void zynqmp_qspi_copy_read_data(struct zynqmp_qspi *xqspi,
static int zynqmp_prepare_transfer_hardware(struct spi_master *master)
{
struct zynqmp_qspi *xqspi = spi_master_get_devdata(master);
- int ret;
-
- ret = clk_enable(xqspi->refclk);
- if (ret)
- return ret;
-
- ret = clk_enable(xqspi->pclk);
- if (ret)
- goto clk_err;
zynqmp_gqspi_write(xqspi, GQSPI_EN_OFST, GQSPI_EN_MASK);
return 0;
-clk_err:
- clk_disable(xqspi->refclk);
- return ret;
}
/**
@@ -387,8 +377,6 @@ static int zynqmp_unprepare_transfer_hardware(struct spi_master *master)
struct zynqmp_qspi *xqspi = spi_master_get_devdata(master);
zynqmp_gqspi_write(xqspi, GQSPI_EN_OFST, 0x0);
- clk_disable(xqspi->refclk);
- clk_disable(xqspi->pclk);
return 0;
}
@@ -918,8 +906,7 @@ static int zynqmp_qspi_start_transfer(struct spi_master *master,
*/
static int __maybe_unused zynqmp_qspi_suspend(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct spi_master *master = platform_get_drvdata(pdev);
+ struct spi_master *master = dev_get_drvdata(dev);
spi_master_suspend(master);
@@ -939,8 +926,7 @@ static int __maybe_unused zynqmp_qspi_suspend(struct device *dev)
*/
static int __maybe_unused zynqmp_qspi_resume(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct spi_master *master = platform_get_drvdata(pdev);
+ struct spi_master *master = dev_get_drvdata(dev);
struct zynqmp_qspi *xqspi = spi_master_get_devdata(master);
int ret = 0;
@@ -959,11 +945,67 @@ static int __maybe_unused zynqmp_qspi_resume(struct device *dev)
spi_master_resume(master);
+ clk_disable(xqspi->refclk);
+ clk_disable(xqspi->pclk);
return 0;
}
-static SIMPLE_DEV_PM_OPS(zynqmp_qspi_dev_pm_ops, zynqmp_qspi_suspend,
- zynqmp_qspi_resume);
+/**
+ * zynqmp_runtime_suspend - Runtime suspend method for the SPI driver
+ * @dev: Address of the platform_device structure
+ *
+ * This function disables the clocks
+ *
+ * Return: Always 0
+ */
+static int __maybe_unused zynqmp_runtime_suspend(struct device *dev)
+{
+ struct platform_device *pdev = to_platform_device(dev);
+ struct spi_master *master = platform_get_drvdata(pdev);
+ struct zynqmp_qspi *xqspi = spi_master_get_devdata(master);
+
+ clk_disable(xqspi->refclk);
+ clk_disable(xqspi->pclk);
+
+ return 0;
+}
+
+/**
+ * zynqmp_runtime_resume - Runtime resume method for the SPI driver
+ * @dev: Address of the platform_device structure
+ *
+ * This function enables the clocks
+ *
+ * Return: 0 on success and error value on error
+ */
+static int __maybe_unused zynqmp_runtime_resume(struct device *dev)
+{
+ struct platform_device *pdev = to_platform_device(dev);
+ struct spi_master *master = platform_get_drvdata(pdev);
+ struct zynqmp_qspi *xqspi = spi_master_get_devdata(master);
+ int ret;
+
+ ret = clk_enable(xqspi->pclk);
+ if (ret) {
+ dev_err(dev, "Cannot enable APB clock.\n");
+ return ret;
+ }
+
+ ret = clk_enable(xqspi->refclk);
+ if (ret) {
+ dev_err(dev, "Cannot enable device clock.\n");
+ clk_disable(xqspi->pclk);
+ return ret;
+ }
+
+ return 0;
+}
+
+static const struct dev_pm_ops zynqmp_qspi_dev_pm_ops = {
+ SET_RUNTIME_PM_OPS(zynqmp_runtime_suspend,
+ zynqmp_runtime_resume, NULL)
+ SET_SYSTEM_SLEEP_PM_OPS(zynqmp_qspi_suspend, zynqmp_qspi_resume)
+};
/**
* zynqmp_qspi_probe: Probe method for the QSPI driver
@@ -1023,9 +1065,15 @@ static int zynqmp_qspi_probe(struct platform_device *pdev)
goto clk_dis_pclk;
}
+ pm_runtime_use_autosuspend(&pdev->dev);
+ pm_runtime_set_autosuspend_delay(&pdev->dev, SPI_AUTOSUSPEND_TIMEOUT);
+ pm_runtime_set_active(&pdev->dev);
+ pm_runtime_enable(&pdev->dev);
/* QSPI controller initializations */
zynqmp_qspi_init_hw(xqspi);
+ pm_runtime_mark_last_busy(&pdev->dev);
+ pm_runtime_put_autosuspend(&pdev->dev);
xqspi->irq = platform_get_irq(pdev, 0);
if (xqspi->irq <= 0) {
ret = -ENXIO;
@@ -1063,6 +1111,8 @@ static int zynqmp_qspi_probe(struct platform_device *pdev)
return 0;
clk_dis_all:
+ pm_runtime_set_suspended(&pdev->dev);
+ pm_runtime_disable(&pdev->dev);
clk_disable_unprepare(xqspi->refclk);
clk_dis_pclk:
clk_disable_unprepare(xqspi->pclk);
@@ -1090,6 +1140,8 @@ static int zynqmp_qspi_remove(struct platform_device *pdev)
zynqmp_gqspi_write(xqspi, GQSPI_EN_OFST, 0x0);
clk_disable_unprepare(xqspi->refclk);
clk_disable_unprepare(xqspi->pclk);
+ pm_runtime_set_suspended(&pdev->dev);
+ pm_runtime_disable(&pdev->dev);
spi_unregister_master(master);
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 7b213fa..efc624f 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -28,6 +28,7 @@
#include <linux/slab.h>
#include <linux/mod_devicetable.h>
#include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
#include <linux/of_gpio.h>
#include <linux/pm_runtime.h>
#include <linux/pm_domain.h>
@@ -46,6 +47,8 @@
#define CREATE_TRACE_POINTS
#include <trace/events/spi.h>
+#include "internals.h"
+
static DEFINE_IDR(spi_master_idr);
static void spidev_release(struct device *dev)
@@ -356,11 +359,12 @@ static int spi_drv_probe(struct device *dev)
}
ret = dev_pm_domain_attach(dev, true);
- if (ret != -EPROBE_DEFER) {
- ret = sdrv->probe(spi);
- if (ret)
- dev_pm_domain_detach(dev, true);
- }
+ if (ret)
+ return ret;
+
+ ret = sdrv->probe(spi);
+ if (ret)
+ dev_pm_domain_detach(dev, true);
return ret;
}
@@ -740,9 +744,9 @@ static void spi_set_cs(struct spi_device *spi, bool enable)
}
#ifdef CONFIG_HAS_DMA
-static int spi_map_buf(struct spi_controller *ctlr, struct device *dev,
- struct sg_table *sgt, void *buf, size_t len,
- enum dma_data_direction dir)
+int spi_map_buf(struct spi_controller *ctlr, struct device *dev,
+ struct sg_table *sgt, void *buf, size_t len,
+ enum dma_data_direction dir)
{
const bool vmalloced_buf = is_vmalloc_addr(buf);
unsigned int max_seg_size = dma_get_max_seg_size(dev);
@@ -821,8 +825,8 @@ static int spi_map_buf(struct spi_controller *ctlr, struct device *dev,
return 0;
}
-static void spi_unmap_buf(struct spi_controller *ctlr, struct device *dev,
- struct sg_table *sgt, enum dma_data_direction dir)
+void spi_unmap_buf(struct spi_controller *ctlr, struct device *dev,
+ struct sg_table *sgt, enum dma_data_direction dir)
{
if (sgt->orig_nents) {
dma_unmap_sg(dev, sgt->sgl, sgt->orig_nents, dir);
@@ -907,19 +911,6 @@ static int __spi_unmap_msg(struct spi_controller *ctlr, struct spi_message *msg)
return 0;
}
#else /* !CONFIG_HAS_DMA */
-static inline int spi_map_buf(struct spi_controller *ctlr, struct device *dev,
- struct sg_table *sgt, void *buf, size_t len,
- enum dma_data_direction dir)
-{
- return -EINVAL;
-}
-
-static inline void spi_unmap_buf(struct spi_controller *ctlr,
- struct device *dev, struct sg_table *sgt,
- enum dma_data_direction dir)
-{
-}
-
static inline int __spi_map_msg(struct spi_controller *ctlr,
struct spi_message *msg)
{
@@ -1222,6 +1213,7 @@ static void __spi_pump_messages(struct spi_controller *ctlr, bool in_kthread)
if (!was_busy && ctlr->auto_runtime_pm) {
ret = pm_runtime_get_sync(ctlr->dev.parent);
if (ret < 0) {
+ pm_runtime_put_noidle(ctlr->dev.parent);
dev_err(&ctlr->dev, "Failed to power device: %d\n",
ret);
mutex_unlock(&ctlr->io_mutex);
@@ -1533,6 +1525,22 @@ static int spi_controller_initialize_queue(struct spi_controller *ctlr)
return ret;
}
+/**
+ * spi_flush_queue - Send all pending messages in the queue from the callers'
+ * context
+ * @ctlr: controller to process queue for
+ *
+ * This should be used when one wants to ensure all pending messages have been
+ * sent before doing something. Is used by the spi-mem code to make sure SPI
+ * memory operations do not preempt regular SPI transfers that have been queued
+ * before the spi-mem operation.
+ */
+void spi_flush_queue(struct spi_controller *ctlr)
+{
+ if (ctlr->transfer == spi_queued_transfer)
+ __spi_pump_messages(ctlr, false);
+}
+
/*-------------------------------------------------------------------------*/
#if defined(CONFIG_OF)
@@ -2063,6 +2071,26 @@ static int of_spi_register_master(struct spi_controller *ctlr)
}
#endif
+static int spi_controller_check_ops(struct spi_controller *ctlr)
+{
+ /*
+ * The controller may implement only the high-level SPI-memory like
+ * operations if it does not support regular SPI transfers, and this is
+ * valid use case.
+ * If ->mem_ops is NULL, we request that at least one of the
+ * ->transfer_xxx() method be implemented.
+ */
+ if (ctlr->mem_ops) {
+ if (!ctlr->mem_ops->exec_op)
+ return -EINVAL;
+ } else if (!ctlr->transfer && !ctlr->transfer_one &&
+ !ctlr->transfer_one_message) {
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
/**
* spi_register_controller - register SPI master or slave controller
* @ctlr: initialized master, originally from spi_alloc_master() or
@@ -2096,6 +2124,14 @@ int spi_register_controller(struct spi_controller *ctlr)
if (!dev)
return -ENODEV;
+ /*
+ * Make sure all necessary hooks are implemented before registering
+ * the SPI controller.
+ */
+ status = spi_controller_check_ops(ctlr);
+ if (status)
+ return status;
+
if (!spi_controller_is_slave(ctlr)) {
status = of_spi_register_master(ctlr);
if (status)
@@ -2161,10 +2197,14 @@ int spi_register_controller(struct spi_controller *ctlr)
spi_controller_is_slave(ctlr) ? "slave" : "master",
dev_name(&ctlr->dev));
- /* If we're using a queued driver, start the queue */
- if (ctlr->transfer)
+ /*
+ * If we're using a queued driver, start the queue. Note that we don't
+ * need the queueing logic if the driver is only supporting high-level
+ * memory operations.
+ */
+ if (ctlr->transfer) {
dev_info(dev, "controller is unqueued, this is deprecated\n");
- else {
+ } else if (ctlr->transfer_one || ctlr->transfer_one_message) {
status = spi_controller_initialize_queue(ctlr);
if (status) {
device_del(&ctlr->dev);
@@ -2894,6 +2934,13 @@ static int __spi_async(struct spi_device *spi, struct spi_message *message)
{
struct spi_controller *ctlr = spi->controller;
+ /*
+ * Some controllers do not support doing regular SPI transfers. Return
+ * ENOTSUPP when this is the case.
+ */
+ if (!ctlr->transfer)
+ return -ENOTSUPP;
+
message->spi = spi;
SPI_STATISTICS_INCREMENT_FIELD(&ctlr->statistics, spi_async);
@@ -3010,63 +3057,6 @@ int spi_async_locked(struct spi_device *spi, struct spi_message *message)
}
EXPORT_SYMBOL_GPL(spi_async_locked);
-
-int spi_flash_read(struct spi_device *spi,
- struct spi_flash_read_message *msg)
-
-{
- struct spi_controller *master = spi->controller;
- struct device *rx_dev = NULL;
- int ret;
-
- if ((msg->opcode_nbits == SPI_NBITS_DUAL ||
- msg->addr_nbits == SPI_NBITS_DUAL) &&
- !(spi->mode & (SPI_TX_DUAL | SPI_TX_QUAD)))
- return -EINVAL;
- if ((msg->opcode_nbits == SPI_NBITS_QUAD ||
- msg->addr_nbits == SPI_NBITS_QUAD) &&
- !(spi->mode & SPI_TX_QUAD))
- return -EINVAL;
- if (msg->data_nbits == SPI_NBITS_DUAL &&
- !(spi->mode & (SPI_RX_DUAL | SPI_RX_QUAD)))
- return -EINVAL;
- if (msg->data_nbits == SPI_NBITS_QUAD &&
- !(spi->mode & SPI_RX_QUAD))
- return -EINVAL;
-
- if (master->auto_runtime_pm) {
- ret = pm_runtime_get_sync(master->dev.parent);
- if (ret < 0) {
- dev_err(&master->dev, "Failed to power device: %d\n",
- ret);
- return ret;
- }
- }
-
- mutex_lock(&master->bus_lock_mutex);
- mutex_lock(&master->io_mutex);
- if (master->dma_rx && master->spi_flash_can_dma(spi, msg)) {
- rx_dev = master->dma_rx->device->dev;
- ret = spi_map_buf(master, rx_dev, &msg->rx_sg,
- msg->buf, msg->len,
- DMA_FROM_DEVICE);
- if (!ret)
- msg->cur_msg_mapped = true;
- }
- ret = master->spi_flash_read(spi, msg);
- if (msg->cur_msg_mapped)
- spi_unmap_buf(master, rx_dev, &msg->rx_sg,
- DMA_FROM_DEVICE);
- mutex_unlock(&master->io_mutex);
- mutex_unlock(&master->bus_lock_mutex);
-
- if (master->auto_runtime_pm)
- pm_runtime_put(master->dev.parent);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(spi_flash_read);
-
/*-------------------------------------------------------------------------*/
/* Utility methods for SPI protocol drivers, layered on
diff --git a/drivers/ssb/Kconfig b/drivers/ssb/Kconfig
index 9371651..c574dd2 100644
--- a/drivers/ssb/Kconfig
+++ b/drivers/ssb/Kconfig
@@ -117,7 +117,7 @@
config SSB_DRIVER_PCICORE_POSSIBLE
bool
- depends on SSB_PCIHOST && SSB = y
+ depends on SSB_PCIHOST
default y
config SSB_DRIVER_PCICORE
@@ -131,7 +131,7 @@
config SSB_PCICORE_HOSTMODE
bool "Hostmode support for SSB PCI core"
- depends on SSB_DRIVER_PCICORE && SSB_DRIVER_MIPS
+ depends on SSB_DRIVER_PCICORE && SSB_DRIVER_MIPS && SSB = y
help
PCIcore hostmode operation (external PCI bus).
diff --git a/drivers/staging/comedi/drivers/serial2002.c b/drivers/staging/comedi/drivers/serial2002.c
index b3f3b4a..5471b22 100644
--- a/drivers/staging/comedi/drivers/serial2002.c
+++ b/drivers/staging/comedi/drivers/serial2002.c
@@ -113,7 +113,7 @@ static void serial2002_tty_read_poll_wait(struct file *f, int timeout)
long elapsed;
__poll_t mask;
- mask = f->f_op->poll(f, &table.pt);
+ mask = vfs_poll(f, &table.pt);
if (mask & (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN |
EPOLLHUP | EPOLLERR)) {
break;
@@ -136,7 +136,7 @@ static int serial2002_tty_read(struct file *f, int timeout)
result = -1;
if (!IS_ERR(f)) {
- if (f->f_op->poll) {
+ if (file_can_poll(f)) {
serial2002_tty_read_poll_wait(f, timeout);
if (kernel_read(f, &ch, 1, &pos) == 1)
diff --git a/drivers/staging/comedi/proc.c b/drivers/staging/comedi/proc.c
index 50d3893..8bc8e42 100644
--- a/drivers/staging/comedi/proc.c
+++ b/drivers/staging/comedi/proc.c
@@ -62,25 +62,9 @@ static int comedi_read(struct seq_file *m, void *v)
return 0;
}
-/*
- * seq_file wrappers for procfile show routines.
- */
-static int comedi_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, comedi_read, NULL);
-}
-
-static const struct file_operations comedi_proc_fops = {
- .owner = THIS_MODULE,
- .open = comedi_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
void __init comedi_proc_init(void)
{
- if (!proc_create("comedi", 0444, NULL, &comedi_proc_fops))
+ if (!proc_create_single("comedi", 0444, NULL, comedi_read))
pr_warn("comedi: unable to create proc entry\n");
}
diff --git a/drivers/staging/fwserial/fwserial.c b/drivers/staging/fwserial/fwserial.c
index e8bfe55..fa0dd42 100644
--- a/drivers/staging/fwserial/fwserial.c
+++ b/drivers/staging/fwserial/fwserial.c
@@ -1506,11 +1506,6 @@ static int fwtty_debugfs_peers_show(struct seq_file *m, void *v)
return 0;
}
-static int fwtty_proc_open(struct inode *inode, struct file *fp)
-{
- return single_open(fp, fwtty_proc_show, NULL);
-}
-
static int fwtty_stats_open(struct inode *inode, struct file *fp)
{
return single_open(fp, fwtty_debugfs_stats_show, inode->i_private);
@@ -1537,14 +1532,6 @@ static const struct file_operations fwtty_peers_fops = {
.release = single_release,
};
-static const struct file_operations fwtty_proc_fops = {
- .owner = THIS_MODULE,
- .open = fwtty_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static const struct tty_port_operations fwtty_port_ops = {
.dtr_rts = fwtty_port_dtr_rts,
.carrier_raised = fwtty_port_carrier_raised,
@@ -1570,7 +1557,7 @@ static const struct tty_operations fwtty_ops = {
.tiocmget = fwtty_tiocmget,
.tiocmset = fwtty_tiocmset,
.get_icount = fwtty_get_icount,
- .proc_fops = &fwtty_proc_fops,
+ .proc_show = fwtty_proc_show,
};
static const struct tty_operations fwloop_ops = {
diff --git a/drivers/staging/ipx/af_ipx.c b/drivers/staging/ipx/af_ipx.c
index 5703dd1..208b5c1 100644
--- a/drivers/staging/ipx/af_ipx.c
+++ b/drivers/staging/ipx/af_ipx.c
@@ -1965,7 +1965,7 @@ static const struct proto_ops ipx_dgram_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = ipx_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = ipx_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ipx_compat_ioctl,
diff --git a/drivers/staging/ipx/ipx_proc.c b/drivers/staging/ipx/ipx_proc.c
index b9232e4..360f0ad 100644
--- a/drivers/staging/ipx/ipx_proc.c
+++ b/drivers/staging/ipx/ipx_proc.c
@@ -244,42 +244,6 @@ static const struct seq_operations ipx_seq_socket_ops = {
.show = ipx_seq_socket_show,
};
-static int ipx_seq_route_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &ipx_seq_route_ops);
-}
-
-static int ipx_seq_interface_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &ipx_seq_interface_ops);
-}
-
-static int ipx_seq_socket_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &ipx_seq_socket_ops);
-}
-
-static const struct file_operations ipx_seq_interface_fops = {
- .open = ipx_seq_interface_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-static const struct file_operations ipx_seq_route_fops = {
- .open = ipx_seq_route_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-static const struct file_operations ipx_seq_socket_fops = {
- .open = ipx_seq_socket_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static struct proc_dir_entry *ipx_proc_dir;
int __init ipx_proc_init(void)
@@ -291,16 +255,17 @@ int __init ipx_proc_init(void)
if (!ipx_proc_dir)
goto out;
- p = proc_create("interface", S_IRUGO,
- ipx_proc_dir, &ipx_seq_interface_fops);
+ p = proc_create_seq("interface", S_IRUGO, ipx_proc_dir,
+ &ipx_seq_interface_ops);
if (!p)
goto out_interface;
- p = proc_create("route", S_IRUGO, ipx_proc_dir, &ipx_seq_route_fops);
+ p = proc_create_seq("route", S_IRUGO, ipx_proc_dir, &ipx_seq_route_ops);
if (!p)
goto out_route;
- p = proc_create("socket", S_IRUGO, ipx_proc_dir, &ipx_seq_socket_fops);
+ p = proc_create_seq("socket", S_IRUGO, ipx_proc_dir,
+ &ipx_seq_socket_ops);
if (!p)
goto out_socket;
diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c
index 16cab40..aeab05f 100644
--- a/drivers/staging/media/imx/imx-media-csi.c
+++ b/drivers/staging/media/imx/imx-media-csi.c
@@ -1799,7 +1799,7 @@ static int imx_csi_probe(struct platform_device *pdev)
priv->dev->of_node = pdata->of_node;
pinctrl = devm_pinctrl_get_select_default(priv->dev);
if (IS_ERR(pinctrl)) {
- ret = PTR_ERR(priv->vdev);
+ ret = PTR_ERR(pinctrl);
dev_dbg(priv->dev,
"devm_pinctrl_get_select_default() failed: %d\n", ret);
if (ret != -ENODEV)
diff --git a/drivers/staging/ncpfs/dir.c b/drivers/staging/ncpfs/dir.c
index 0c57c5c..072bcb1 100644
--- a/drivers/staging/ncpfs/dir.c
+++ b/drivers/staging/ncpfs/dir.c
@@ -823,12 +823,11 @@ static struct dentry *ncp_lookup(struct inode *dir, struct dentry *dentry, unsig
struct ncp_server *server = NCP_SERVER(dir);
struct inode *inode = NULL;
struct ncp_entry_info finfo;
- int error, res, len;
+ int res, len;
__u8 __name[NCP_MAXPATHLEN + 1];
- error = -EIO;
if (!ncp_conn_valid(server))
- goto finished;
+ return ERR_PTR(-EIO);
ncp_vdbg("server lookup for %pd2\n", dentry);
@@ -847,31 +846,20 @@ static struct dentry *ncp_lookup(struct inode *dir, struct dentry *dentry, unsig
res = ncp_obtain_info(server, dir, __name, &(finfo.i));
}
ncp_vdbg("looked for %pd2, res=%d\n", dentry, res);
- /*
- * If we didn't find an entry, make a negative dentry.
- */
- if (res)
- goto add_entry;
-
- /*
- * Create an inode for the entry.
- */
- finfo.opened = 0;
- finfo.ino = iunique(dir->i_sb, 2);
- finfo.volume = finfo.i.volNumber;
- error = -EACCES;
- inode = ncp_iget(dir->i_sb, &finfo);
-
- if (inode) {
- ncp_new_dentry(dentry);
-add_entry:
- d_add(dentry, inode);
- error = 0;
+ if (!res) {
+ /*
+ * Entry found; create an inode for it.
+ */
+ finfo.opened = 0;
+ finfo.ino = iunique(dir->i_sb, 2);
+ finfo.volume = finfo.i.volNumber;
+ inode = ncp_iget(dir->i_sb, &finfo);
+ if (unlikely(!inode))
+ inode = ERR_PTR(-EACCES);
+ else
+ ncp_new_dentry(dentry);
}
-
-finished:
- ncp_vdbg("result=%d\n", error);
- return ERR_PTR(error);
+ return d_splice_alias(inode, dentry);
}
/*
diff --git a/drivers/staging/rtl8192u/r8192U_core.c b/drivers/staging/rtl8192u/r8192U_core.c
index d607c59..7a0dbc0 100644
--- a/drivers/staging/rtl8192u/r8192U_core.c
+++ b/drivers/staging/rtl8192u/r8192U_core.c
@@ -646,64 +646,25 @@ static void rtl8192_proc_module_init(void)
rtl8192_proc = proc_mkdir(RTL819xU_MODULE_NAME, init_net.proc_net);
}
-/*
- * seq_file wrappers for procfile show routines.
- */
-static int rtl8192_proc_open(struct inode *inode, struct file *file)
-{
- struct net_device *dev = proc_get_parent_data(inode);
- int (*show)(struct seq_file *, void *) = PDE_DATA(inode);
-
- return single_open(file, show, dev);
-}
-
-static const struct file_operations rtl8192_proc_fops = {
- .open = rtl8192_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-/*
- * Table of proc files we need to create.
- */
-struct rtl8192_proc_file {
- char name[12];
- int (*show)(struct seq_file *, void *);
-};
-
-static const struct rtl8192_proc_file rtl8192_proc_files[] = {
- { "stats-rx", &proc_get_stats_rx },
- { "stats-tx", &proc_get_stats_tx },
- { "stats-ap", &proc_get_stats_ap },
- { "registers", &proc_get_registers },
- { "" }
-};
-
static void rtl8192_proc_init_one(struct net_device *dev)
{
- const struct rtl8192_proc_file *f;
struct proc_dir_entry *dir;
- if (rtl8192_proc) {
- dir = proc_mkdir_data(dev->name, 0, rtl8192_proc, dev);
- if (!dir) {
- RT_TRACE(COMP_ERR,
- "Unable to initialize /proc/net/rtl8192/%s\n",
- dev->name);
- return;
- }
+ if (!rtl8192_proc)
+ return;
- for (f = rtl8192_proc_files; f->name[0]; f++) {
- if (!proc_create_data(f->name, S_IFREG | S_IRUGO, dir,
- &rtl8192_proc_fops, f->show)) {
- RT_TRACE(COMP_ERR,
- "Unable to initialize /proc/net/rtl8192/%s/%s\n",
- dev->name, f->name);
- return;
- }
- }
- }
+ dir = proc_mkdir_data(dev->name, 0, rtl8192_proc, dev);
+ if (!dir)
+ return;
+
+ proc_create_single("stats-rx", S_IFREG | S_IRUGO, dir,
+ proc_get_stats_rx);
+ proc_create_single("stats-tx", S_IFREG | S_IRUGO, dir,
+ proc_get_stats_tx);
+ proc_create_single("stats-ap", S_IFREG | S_IRUGO, dir,
+ proc_get_stats_ap);
+ proc_create_single("registers", S_IFREG | S_IRUGO, dir,
+ proc_get_registers);
}
static void rtl8192_proc_remove_one(struct net_device *dev)
diff --git a/drivers/staging/wilc1000/host_interface.c b/drivers/staging/wilc1000/host_interface.c
index 6b5300c..885f5fc 100644
--- a/drivers/staging/wilc1000/host_interface.c
+++ b/drivers/staging/wilc1000/host_interface.c
@@ -1390,7 +1390,7 @@ static inline void host_int_parse_assoc_resp_info(struct wilc_vif *vif,
}
if (hif_drv->usr_conn_req.ies) {
- conn_info.req_ies = kmemdup(conn_info.req_ies,
+ conn_info.req_ies = kmemdup(hif_drv->usr_conn_req.ies,
hif_drv->usr_conn_req.ies_len,
GFP_KERNEL);
if (conn_info.req_ies)
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 07c814c..ce1321a 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -94,8 +94,8 @@ static int iblock_configure_device(struct se_device *dev)
return -EINVAL;
}
- ib_dev->ibd_bio_set = bioset_create(IBLOCK_BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
- if (!ib_dev->ibd_bio_set) {
+ ret = bioset_init(&ib_dev->ibd_bio_set, IBLOCK_BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+ if (ret) {
pr_err("IBLOCK: Unable to create bioset\n");
goto out;
}
@@ -141,7 +141,7 @@ static int iblock_configure_device(struct se_device *dev)
bi = bdev_get_integrity(bd);
if (bi) {
- struct bio_set *bs = ib_dev->ibd_bio_set;
+ struct bio_set *bs = &ib_dev->ibd_bio_set;
if (!strcmp(bi->profile->name, "T10-DIF-TYPE3-IP") ||
!strcmp(bi->profile->name, "T10-DIF-TYPE1-IP")) {
@@ -164,7 +164,7 @@ static int iblock_configure_device(struct se_device *dev)
goto out_blkdev_put;
}
pr_debug("IBLOCK setup BIP bs->bio_integrity_pool: %p\n",
- bs->bio_integrity_pool);
+ &bs->bio_integrity_pool);
}
dev->dev_attrib.hw_pi_prot_type = dev->dev_attrib.pi_prot_type;
}
@@ -174,8 +174,7 @@ static int iblock_configure_device(struct se_device *dev)
out_blkdev_put:
blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL);
out_free_bioset:
- bioset_free(ib_dev->ibd_bio_set);
- ib_dev->ibd_bio_set = NULL;
+ bioset_exit(&ib_dev->ibd_bio_set);
out:
return ret;
}
@@ -199,8 +198,7 @@ static void iblock_destroy_device(struct se_device *dev)
if (ib_dev->ibd_bd != NULL)
blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL);
- if (ib_dev->ibd_bio_set != NULL)
- bioset_free(ib_dev->ibd_bio_set);
+ bioset_exit(&ib_dev->ibd_bio_set);
}
static unsigned long long iblock_emulate_read_cap_with_block_size(
@@ -332,7 +330,7 @@ iblock_get_bio(struct se_cmd *cmd, sector_t lba, u32 sg_num, int op,
if (sg_num > BIO_MAX_PAGES)
sg_num = BIO_MAX_PAGES;
- bio = bio_alloc_bioset(GFP_NOIO, sg_num, ib_dev->ibd_bio_set);
+ bio = bio_alloc_bioset(GFP_NOIO, sg_num, &ib_dev->ibd_bio_set);
if (!bio) {
pr_err("Unable to allocate memory for bio\n");
return NULL;
@@ -427,8 +425,8 @@ iblock_execute_zero_out(struct block_device *bdev, struct se_cmd *cmd)
{
struct se_device *dev = cmd->se_dev;
struct scatterlist *sg = &cmd->t_data_sg[0];
- unsigned char *buf, zero = 0x00, *p = &zero;
- int rc, ret;
+ unsigned char *buf, *not_zero;
+ int ret;
buf = kmap(sg_page(sg)) + sg->offset;
if (!buf)
@@ -437,10 +435,10 @@ iblock_execute_zero_out(struct block_device *bdev, struct se_cmd *cmd)
* Fall back to block_execute_write_same() slow-path if
* incoming WRITE_SAME payload does not contain zeros.
*/
- rc = memcmp(buf, p, cmd->data_length);
+ not_zero = memchr_inv(buf, 0x00, cmd->data_length);
kunmap(sg_page(sg));
- if (rc)
+ if (not_zero)
return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
ret = blkdev_issue_zeroout(bdev,
diff --git a/drivers/target/target_core_iblock.h b/drivers/target/target_core_iblock.h
index b4aeb25..9cc3843 100644
--- a/drivers/target/target_core_iblock.h
+++ b/drivers/target/target_core_iblock.h
@@ -22,7 +22,7 @@ struct iblock_dev {
struct se_device dev;
unsigned char ibd_udev_path[SE_UDEV_PATH_LEN];
u32 ibd_flags;
- struct bio_set *ibd_bio_set;
+ struct bio_set ibd_bio_set;
struct block_device *ibd_bd;
bool ibd_readonly;
} ____cacheline_aligned;
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 0d99b24..668934e 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -890,6 +890,7 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
bytes = min(bytes, data_len);
if (!bio) {
+new_bio:
nr_vecs = min_t(int, BIO_MAX_PAGES, nr_pages);
nr_pages -= nr_vecs;
/*
@@ -931,6 +932,7 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
* be allocated with pscsi_get_bio() above.
*/
bio = NULL;
+ goto new_bio;
}
data_len -= bytes;
@@ -984,8 +986,7 @@ pscsi_execute_cmd(struct se_cmd *cmd)
req = blk_get_request(pdv->pdv_sd->request_queue,
cmd->data_direction == DMA_TO_DEVICE ?
- REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
- GFP_KERNEL);
+ REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0);
if (IS_ERR(req)) {
pr_err("PSCSI: blk_get_request() failed\n");
ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 4ad89ea..4f26bdc 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -2121,6 +2121,8 @@ static ssize_t tcmu_qfull_time_out_store(struct config_item *item,
if (val >= 0) {
udev->qfull_time_out = val * MSEC_PER_SEC;
+ } else if (val == -1) {
+ udev->qfull_time_out = val;
} else {
printk(KERN_ERR "Invalid qfull timeout value %d\n", val);
return -EINVAL;
diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c
index 0124a91..dd46b75 100644
--- a/drivers/tee/tee_core.c
+++ b/drivers/tee/tee_core.c
@@ -238,6 +238,17 @@ static int params_from_user(struct tee_context *ctx, struct tee_param *params,
if (IS_ERR(shm))
return PTR_ERR(shm);
+ /*
+ * Ensure offset + size does not overflow offset
+ * and does not overflow the size of the referred
+ * shared memory object.
+ */
+ if ((ip.a + ip.b) < ip.a ||
+ (ip.a + ip.b) > shm->size) {
+ tee_shm_put(shm);
+ return -EINVAL;
+ }
+
params[n].u.memref.shm_offs = ip.a;
params[n].u.memref.size = ip.b;
params[n].u.memref.shm = shm;
diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c
index 556960a..07d3be6 100644
--- a/drivers/tee/tee_shm.c
+++ b/drivers/tee/tee_shm.c
@@ -360,9 +360,10 @@ int tee_shm_get_fd(struct tee_shm *shm)
if (!(shm->flags & TEE_SHM_DMA_BUF))
return -EINVAL;
+ get_dma_buf(shm->dmabuf);
fd = dma_buf_fd(shm->dmabuf, O_CLOEXEC);
- if (fd >= 0)
- get_dma_buf(shm->dmabuf);
+ if (fd < 0)
+ dma_buf_put(shm->dmabuf);
return fd;
}
diff --git a/drivers/thermal/int340x_thermal/int3403_thermal.c b/drivers/thermal/int340x_thermal/int3403_thermal.c
index 8a7f24d..0c19fcd5 100644
--- a/drivers/thermal/int340x_thermal/int3403_thermal.c
+++ b/drivers/thermal/int340x_thermal/int3403_thermal.c
@@ -194,6 +194,7 @@ static int int3403_cdev_add(struct int3403_priv *priv)
return -EFAULT;
}
+ priv->priv = obj;
obj->max_state = p->package.count - 1;
obj->cdev =
thermal_cooling_device_register(acpi_device_bid(priv->adev),
@@ -201,8 +202,6 @@ static int int3403_cdev_add(struct int3403_priv *priv)
if (IS_ERR(obj->cdev))
result = PTR_ERR(obj->cdev);
- priv->priv = obj;
-
kfree(buf.pointer);
/* TODO: add ACPI notification support */
diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c
index ed805c7..ac83f72 100644
--- a/drivers/thermal/samsung/exynos_tmu.c
+++ b/drivers/thermal/samsung/exynos_tmu.c
@@ -185,6 +185,7 @@
* @regulator: pointer to the TMU regulator structure.
* @reg_conf: pointer to structure to register with core thermal.
* @ntrip: number of supported trip points.
+ * @enabled: current status of TMU device
* @tmu_initialize: SoC specific TMU initialization method
* @tmu_control: SoC specific TMU control method
* @tmu_read: SoC specific TMU temperature read method
@@ -205,6 +206,7 @@ struct exynos_tmu_data {
struct regulator *regulator;
struct thermal_zone_device *tzd;
unsigned int ntrip;
+ bool enabled;
int (*tmu_initialize)(struct platform_device *pdev);
void (*tmu_control)(struct platform_device *pdev, bool on);
@@ -398,6 +400,7 @@ static void exynos_tmu_control(struct platform_device *pdev, bool on)
mutex_lock(&data->lock);
clk_enable(data->clk);
data->tmu_control(pdev, on);
+ data->enabled = on;
clk_disable(data->clk);
mutex_unlock(&data->lock);
}
@@ -889,19 +892,24 @@ static void exynos7_tmu_control(struct platform_device *pdev, bool on)
static int exynos_get_temp(void *p, int *temp)
{
struct exynos_tmu_data *data = p;
+ int value, ret = 0;
- if (!data || !data->tmu_read)
+ if (!data || !data->tmu_read || !data->enabled)
return -EINVAL;
mutex_lock(&data->lock);
clk_enable(data->clk);
- *temp = code_to_temp(data, data->tmu_read(data)) * MCELSIUS;
+ value = data->tmu_read(data);
+ if (value < 0)
+ ret = value;
+ else
+ *temp = code_to_temp(data, value) * MCELSIUS;
clk_disable(data->clk);
mutex_unlock(&data->lock);
- return 0;
+ return ret;
}
#ifdef CONFIG_THERMAL_EMULATION
diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c
index 2d2ceda..500911f 100644
--- a/drivers/thunderbolt/icm.c
+++ b/drivers/thunderbolt/icm.c
@@ -1255,7 +1255,7 @@ static int icm_ar_get_boot_acl(struct tb *tb, uuid_t *uuids, size_t nuuids)
/* Map empty entries to null UUID */
uuid[0] = 0;
uuid[1] = 0;
- } else {
+ } else if (uuid[0] != 0 || uuid[1] != 0) {
/* Upper two DWs are always one's */
uuid[2] = 0xffffffff;
uuid[3] = 0xffffffff;
diff --git a/drivers/tty/amiserial.c b/drivers/tty/amiserial.c
index 32d7ce4..34dead6 100644
--- a/drivers/tty/amiserial.c
+++ b/drivers/tty/amiserial.c
@@ -1566,19 +1566,6 @@ static int rs_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int rs_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, rs_proc_show, NULL);
-}
-
-static const struct file_operations rs_proc_fops = {
- .owner = THIS_MODULE,
- .open = rs_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/*
* ---------------------------------------------------------------------
* rs_init() and friends
@@ -1620,7 +1607,7 @@ static const struct tty_operations serial_ops = {
.tiocmget = rs_tiocmget,
.tiocmset = rs_tiocmset,
.get_icount = rs_get_icount,
- .proc_fops = &rs_proc_fops,
+ .proc_show = rs_proc_show,
};
static int amiga_carrier_raised(struct tty_port *port)
diff --git a/drivers/tty/cyclades.c b/drivers/tty/cyclades.c
index cf0bde3..6d3c580 100644
--- a/drivers/tty/cyclades.c
+++ b/drivers/tty/cyclades.c
@@ -3972,19 +3972,6 @@ static int cyclades_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int cyclades_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, cyclades_proc_show, NULL);
-}
-
-static const struct file_operations cyclades_proc_fops = {
- .owner = THIS_MODULE,
- .open = cyclades_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/* The serial driver boot-time initialization code!
Hardware I/O ports are mapped to character special devices on a
first found, first allocated manner. That is, this code searches
@@ -4024,7 +4011,7 @@ static const struct tty_operations cy_ops = {
.tiocmget = cy_tiocmget,
.tiocmset = cy_tiocmset,
.get_icount = cy_get_icount,
- .proc_fops = &cyclades_proc_fops,
+ .proc_show = cyclades_proc_show,
};
static int __init cy_init(void)
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index 3b3e1f6..1dbe27c 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -121,6 +121,9 @@ struct gsm_dlci {
struct mutex mutex;
/* Link layer */
+ int mode;
+#define DLCI_MODE_ABM 0 /* Normal Asynchronous Balanced Mode */
+#define DLCI_MODE_ADM 1 /* Asynchronous Disconnected Mode */
spinlock_t lock; /* Protects the internal state */
struct timer_list t1; /* Retransmit timer for SABM and UA */
int retries;
@@ -1364,7 +1367,13 @@ static struct gsm_control *gsm_control_send(struct gsm_mux *gsm,
ctrl->data = data;
ctrl->len = clen;
gsm->pending_cmd = ctrl;
- gsm->cretries = gsm->n2;
+
+ /* If DLCI0 is in ADM mode skip retries, it won't respond */
+ if (gsm->dlci[0]->mode == DLCI_MODE_ADM)
+ gsm->cretries = 1;
+ else
+ gsm->cretries = gsm->n2;
+
mod_timer(&gsm->t2_timer, jiffies + gsm->t2 * HZ / 100);
gsm_control_transmit(gsm, ctrl);
spin_unlock_irqrestore(&gsm->control_lock, flags);
@@ -1472,6 +1481,7 @@ static void gsm_dlci_t1(struct timer_list *t)
if (debug & 8)
pr_info("DLCI %d opening in ADM mode.\n",
dlci->addr);
+ dlci->mode = DLCI_MODE_ADM;
gsm_dlci_open(dlci);
} else {
gsm_dlci_close(dlci);
@@ -2861,11 +2871,22 @@ static int gsmtty_modem_update(struct gsm_dlci *dlci, u8 brk)
static int gsm_carrier_raised(struct tty_port *port)
{
struct gsm_dlci *dlci = container_of(port, struct gsm_dlci, port);
+ struct gsm_mux *gsm = dlci->gsm;
+
/* Not yet open so no carrier info */
if (dlci->state != DLCI_OPEN)
return 0;
if (debug & 2)
return 1;
+
+ /*
+ * Basic mode with control channel in ADM mode may not respond
+ * to CMD_MSC at all and modem_rx is empty.
+ */
+ if (gsm->encoding == 0 && gsm->dlci[0]->mode == DLCI_MODE_ADM &&
+ !dlci->modem_rx)
+ return 1;
+
return dlci->modem_rx & TIOCM_CD;
}
diff --git a/drivers/tty/serial/earlycon.c b/drivers/tty/serial/earlycon.c
index a242783..2268339 100644
--- a/drivers/tty/serial/earlycon.c
+++ b/drivers/tty/serial/earlycon.c
@@ -169,7 +169,7 @@ static int __init register_earlycon(char *buf, const struct earlycon_id *match)
*/
int __init setup_earlycon(char *buf)
{
- const struct earlycon_id *match;
+ const struct earlycon_id **p_match;
if (!buf || !buf[0])
return -EINVAL;
@@ -177,7 +177,9 @@ int __init setup_earlycon(char *buf)
if (early_con.flags & CON_ENABLED)
return -EALREADY;
- for (match = __earlycon_table; match < __earlycon_table_end; match++) {
+ for (p_match = __earlycon_table; p_match < __earlycon_table_end;
+ p_match++) {
+ const struct earlycon_id *match = *p_match;
size_t len = strlen(match->name);
if (strncmp(buf, match->name, len))
diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 91f3a1a..c2fc6be 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -316,7 +316,7 @@ static u32 imx_uart_readl(struct imx_port *sport, u32 offset)
* differ from the value that was last written. As it only
* clears after being set, reread conditionally.
*/
- if (sport->ucr2 & UCR2_SRST)
+ if (!(sport->ucr2 & UCR2_SRST))
sport->ucr2 = readl(sport->port.membase + offset);
return sport->ucr2;
break;
@@ -1833,6 +1833,11 @@ static int imx_uart_rs485_config(struct uart_port *port,
rs485conf->flags &= ~SER_RS485_ENABLED;
if (rs485conf->flags & SER_RS485_ENABLED) {
+ /* Enable receiver if low-active RTS signal is requested */
+ if (sport->have_rtscts && !sport->have_rtsgpio &&
+ !(rs485conf->flags & SER_RS485_RTS_ON_SEND))
+ rs485conf->flags |= SER_RS485_RX_DURING_TX;
+
/* disable transmitter */
ucr2 = imx_uart_readl(sport, UCR2);
if (rs485conf->flags & SER_RS485_RTS_AFTER_SEND)
@@ -2265,6 +2270,18 @@ static int imx_uart_probe(struct platform_device *pdev)
(!sport->have_rtscts && !sport->have_rtsgpio))
dev_err(&pdev->dev, "no RTS control, disabling rs485\n");
+ /*
+ * If using the i.MX UART RTS/CTS control then the RTS (CTS_B)
+ * signal cannot be set low during transmission in case the
+ * receiver is off (limitation of the i.MX UART IP).
+ */
+ if (sport->port.rs485.flags & SER_RS485_ENABLED &&
+ sport->have_rtscts && !sport->have_rtsgpio &&
+ (!(sport->port.rs485.flags & SER_RS485_RTS_ON_SEND) &&
+ !(sport->port.rs485.flags & SER_RS485_RX_DURING_TX)))
+ dev_err(&pdev->dev,
+ "low-active RTS not possible when receiver is off, enabling receiver\n");
+
imx_uart_rs485_config(&sport->port, &sport->port.rs485);
/* Disable interrupts before requesting them */
diff --git a/drivers/tty/serial/mvebu-uart.c b/drivers/tty/serial/mvebu-uart.c
index 750e564..f503fab 100644
--- a/drivers/tty/serial/mvebu-uart.c
+++ b/drivers/tty/serial/mvebu-uart.c
@@ -495,7 +495,6 @@ static void mvebu_uart_set_termios(struct uart_port *port,
termios->c_iflag |= old->c_iflag & ~(INPCK | IGNPAR);
termios->c_cflag &= CREAD | CBAUD;
termios->c_cflag |= old->c_cflag & ~(CREAD | CBAUD);
- termios->c_lflag = old->c_lflag;
}
spin_unlock_irqrestore(&port->lock, flags);
diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index 65ff669..a1b3eb0 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -1022,6 +1022,7 @@ static int qcom_geni_serial_probe(struct platform_device *pdev)
struct qcom_geni_serial_port *port;
struct uart_port *uport;
struct resource *res;
+ int irq;
if (pdev->dev.of_node)
line = of_alias_get_id(pdev->dev.of_node, "serial");
@@ -1061,11 +1062,12 @@ static int qcom_geni_serial_probe(struct platform_device *pdev)
port->rx_fifo_depth = DEF_FIFO_DEPTH_WORDS;
port->tx_fifo_width = DEF_FIFO_WIDTH_BITS;
- uport->irq = platform_get_irq(pdev, 0);
- if (uport->irq < 0) {
- dev_err(&pdev->dev, "Failed to get IRQ %d\n", uport->irq);
- return uport->irq;
+ irq = platform_get_irq(pdev, 0);
+ if (irq < 0) {
+ dev_err(&pdev->dev, "Failed to get IRQ %d\n", irq);
+ return irq;
}
+ uport->irq = irq;
uport->private_data = &qcom_geni_console_driver;
platform_set_drvdata(pdev, port);
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 0466f9f..6ff9405 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1829,19 +1829,6 @@ static int uart_proc_show(struct seq_file *m, void *v)
uart_line_info(m, drv, i);
return 0;
}
-
-static int uart_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, uart_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations uart_proc_fops = {
- .owner = THIS_MODULE,
- .open = uart_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif
#if defined(CONFIG_SERIAL_CORE_CONSOLE) || defined(CONFIG_CONSOLE_POLL)
@@ -2415,7 +2402,7 @@ static const struct tty_operations uart_ops = {
.break_ctl = uart_break_ctl,
.wait_until_sent= uart_wait_until_sent,
#ifdef CONFIG_PROC_FS
- .proc_fops = &uart_proc_fops,
+ .proc_show = uart_proc_show,
#endif
.tiocmget = uart_tiocmget,
.tiocmset = uart_tiocmset,
diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index abcb4d0..bd72dd8 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -1181,7 +1181,7 @@ static int __init cdns_early_console_setup(struct earlycon_device *device,
/* only set baud if specified on command line - otherwise
* assume it has been initialized by a boot loader.
*/
- if (device->baud) {
+ if (port->uartclk && device->baud) {
u32 cd = 0, bdiv = 0;
u32 mr;
int div8;
diff --git a/drivers/tty/synclink.c b/drivers/tty/synclink.c
index 3c4ad71..fbdf4d0 100644
--- a/drivers/tty/synclink.c
+++ b/drivers/tty/synclink.c
@@ -3534,19 +3534,6 @@ static int mgsl_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int mgsl_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, mgsl_proc_show, NULL);
-}
-
-static const struct file_operations mgsl_proc_fops = {
- .owner = THIS_MODULE,
- .open = mgsl_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/* mgsl_allocate_dma_buffers()
*
* Allocate and format DMA buffers (ISA adapter)
@@ -4298,7 +4285,7 @@ static const struct tty_operations mgsl_ops = {
.tiocmget = tiocmget,
.tiocmset = tiocmset,
.get_icount = msgl_get_icount,
- .proc_fops = &mgsl_proc_fops,
+ .proc_show = mgsl_proc_show,
};
/*
diff --git a/drivers/tty/synclink_gt.c b/drivers/tty/synclink_gt.c
index 255c496..a940865 100644
--- a/drivers/tty/synclink_gt.c
+++ b/drivers/tty/synclink_gt.c
@@ -1316,19 +1316,6 @@ static int synclink_gt_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int synclink_gt_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, synclink_gt_proc_show, NULL);
-}
-
-static const struct file_operations synclink_gt_proc_fops = {
- .owner = THIS_MODULE,
- .open = synclink_gt_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/*
* return count of bytes in transmit buffer
*/
@@ -3721,7 +3708,7 @@ static const struct tty_operations ops = {
.tiocmget = tiocmget,
.tiocmset = tiocmset,
.get_icount = get_icount,
- .proc_fops = &synclink_gt_proc_fops,
+ .proc_show = synclink_gt_proc_show,
};
static void slgt_cleanup(void)
diff --git a/drivers/tty/synclinkmp.c b/drivers/tty/synclinkmp.c
index 75f11ce..1e4d5b9 100644
--- a/drivers/tty/synclinkmp.c
+++ b/drivers/tty/synclinkmp.c
@@ -1421,19 +1421,6 @@ static int synclinkmp_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int synclinkmp_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, synclinkmp_proc_show, NULL);
-}
-
-static const struct file_operations synclinkmp_proc_fops = {
- .owner = THIS_MODULE,
- .open = synclinkmp_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/* Return the count of bytes in transmit buffer
*/
static int chars_in_buffer(struct tty_struct *tty)
@@ -3899,7 +3886,7 @@ static const struct tty_operations ops = {
.tiocmget = tiocmget,
.tiocmset = tiocmset,
.get_icount = get_icount,
- .proc_fops = &synclinkmp_proc_fops,
+ .proc_show = synclinkmp_proc_show,
};
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 63114ea..7c838b9 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2816,7 +2816,10 @@ struct tty_struct *alloc_tty_struct(struct tty_driver *driver, int idx)
kref_init(&tty->kref);
tty->magic = TTY_MAGIC;
- tty_ldisc_init(tty);
+ if (tty_ldisc_init(tty)) {
+ kfree(tty);
+ return NULL;
+ }
tty->session = NULL;
tty->pgrp = NULL;
mutex_init(&tty->legacy_mutex);
diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c
index 050f4d6..fc4c97c 100644
--- a/drivers/tty/tty_ldisc.c
+++ b/drivers/tty/tty_ldisc.c
@@ -176,12 +176,11 @@ static struct tty_ldisc *tty_ldisc_get(struct tty_struct *tty, int disc)
return ERR_CAST(ldops);
}
- ld = kmalloc(sizeof(struct tty_ldisc), GFP_KERNEL);
- if (ld == NULL) {
- put_ldops(ldops);
- return ERR_PTR(-ENOMEM);
- }
-
+ /*
+ * There is no way to handle allocation failure of only 16 bytes.
+ * Let's simplify error handling and save more memory.
+ */
+ ld = kmalloc(sizeof(struct tty_ldisc), GFP_KERNEL | __GFP_NOFAIL);
ld->ops = ldops;
ld->tty = tty;
@@ -230,26 +229,13 @@ static int tty_ldiscs_seq_show(struct seq_file *m, void *v)
return 0;
}
-static const struct seq_operations tty_ldiscs_seq_ops = {
+const struct seq_operations tty_ldiscs_seq_ops = {
.start = tty_ldiscs_seq_start,
.next = tty_ldiscs_seq_next,
.stop = tty_ldiscs_seq_stop,
.show = tty_ldiscs_seq_show,
};
-static int proc_tty_ldiscs_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &tty_ldiscs_seq_ops);
-}
-
-const struct file_operations tty_ldiscs_proc_fops = {
- .owner = THIS_MODULE,
- .open = proc_tty_ldiscs_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
/**
* tty_ldisc_ref_wait - wait for the tty ldisc
* @tty: tty device
@@ -527,19 +513,16 @@ static int tty_ldisc_failto(struct tty_struct *tty, int ld)
static void tty_ldisc_restore(struct tty_struct *tty, struct tty_ldisc *old)
{
/* There is an outstanding reference here so this is safe */
- old = tty_ldisc_get(tty, old->ops->num);
- WARN_ON(IS_ERR(old));
- tty->ldisc = old;
- tty_set_termios_ldisc(tty, old->ops->num);
- if (tty_ldisc_open(tty, old) < 0) {
- tty_ldisc_put(old);
+ if (tty_ldisc_failto(tty, old->ops->num) < 0) {
+ const char *name = tty_name(tty);
+
+ pr_warn("Falling back ldisc for %s.\n", name);
/* The traditional behaviour is to fall back to N_TTY, we
want to avoid falling back to N_NULL unless we have no
choice to avoid the risk of breaking anything */
if (tty_ldisc_failto(tty, N_TTY) < 0 &&
tty_ldisc_failto(tty, N_NULL) < 0)
- panic("Couldn't open N_NULL ldisc for %s.",
- tty_name(tty));
+ panic("Couldn't open N_NULL ldisc for %s.", name);
}
}
@@ -824,12 +807,13 @@ EXPORT_SYMBOL_GPL(tty_ldisc_release);
* the tty structure is not completely set up when this call is made.
*/
-void tty_ldisc_init(struct tty_struct *tty)
+int tty_ldisc_init(struct tty_struct *tty)
{
struct tty_ldisc *ld = tty_ldisc_get(tty, N_TTY);
if (IS_ERR(ld))
- panic("n_tty: init_tty");
+ return PTR_ERR(ld);
tty->ldisc = ld;
+ return 0;
}
/**
diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c
index f695a7e..c690d10 100644
--- a/drivers/uio/uio_hv_generic.c
+++ b/drivers/uio/uio_hv_generic.c
@@ -19,7 +19,7 @@
* # echo -n "ed963694-e847-4b2a-85af-bc9cfc11d6f3" \
* > /sys/bus/vmbus/drivers/uio_hv_generic/bind
*/
-
+#define DEBUG 1
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/device.h>
@@ -94,10 +94,11 @@ hv_uio_irqcontrol(struct uio_info *info, s32 irq_state)
*/
static void hv_uio_channel_cb(void *context)
{
- struct hv_uio_private_data *pdata = context;
- struct hv_device *dev = pdata->device;
+ struct vmbus_channel *chan = context;
+ struct hv_device *hv_dev = chan->device_obj;
+ struct hv_uio_private_data *pdata = hv_get_drvdata(hv_dev);
- dev->channel->inbound.ring_buffer->interrupt_mask = 1;
+ chan->inbound.ring_buffer->interrupt_mask = 1;
virt_mb();
uio_event_notify(&pdata->info);
@@ -121,78 +122,46 @@ static void hv_uio_rescind(struct vmbus_channel *channel)
uio_event_notify(&pdata->info);
}
-/*
- * Handle fault when looking for sub channel ring buffer
- * Subchannel ring buffer is same as resource 0 which is main ring buffer
- * This is derived from uio_vma_fault
+/* Sysfs API to allow mmap of the ring buffers
+ * The ring buffer is allocated as contiguous memory by vmbus_open
*/
-static int hv_uio_vma_fault(struct vm_fault *vmf)
-{
- struct vm_area_struct *vma = vmf->vma;
- void *ring_buffer = vma->vm_private_data;
- struct page *page;
- void *addr;
-
- addr = ring_buffer + (vmf->pgoff << PAGE_SHIFT);
- page = virt_to_page(addr);
- get_page(page);
- vmf->page = page;
- return 0;
-}
-
-static const struct vm_operations_struct hv_uio_vm_ops = {
- .fault = hv_uio_vma_fault,
-};
-
-/* Sysfs API to allow mmap of the ring buffers */
static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj,
struct bin_attribute *attr,
struct vm_area_struct *vma)
{
struct vmbus_channel *channel
= container_of(kobj, struct vmbus_channel, kobj);
- unsigned long requested_pages, actual_pages;
+ struct hv_device *dev = channel->primary_channel->device_obj;
+ u16 q_idx = channel->offermsg.offer.sub_channel_index;
- if (vma->vm_end < vma->vm_start)
- return -EINVAL;
+ dev_dbg(&dev->device, "mmap channel %u pages %#lx at %#lx\n",
+ q_idx, vma_pages(vma), vma->vm_pgoff);
- /* only allow 0 for now */
- if (vma->vm_pgoff > 0)
- return -EINVAL;
-
- requested_pages = vma_pages(vma);
- actual_pages = 2 * HV_RING_SIZE;
- if (requested_pages > actual_pages)
- return -EINVAL;
-
- vma->vm_private_data = channel->ringbuffer_pages;
- vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
- vma->vm_ops = &hv_uio_vm_ops;
- return 0;
+ return vm_iomap_memory(vma, virt_to_phys(channel->ringbuffer_pages),
+ channel->ringbuffer_pagecount << PAGE_SHIFT);
}
-static struct bin_attribute ring_buffer_bin_attr __ro_after_init = {
+static const struct bin_attribute ring_buffer_bin_attr = {
.attr = {
.name = "ring",
.mode = 0600,
- /* size is set at init time */
},
+ .size = 2 * HV_RING_SIZE * PAGE_SIZE,
.mmap = hv_uio_ring_mmap,
};
-/* Callback from VMBUS subystem when new channel created. */
+/* Callback from VMBUS subsystem when new channel created. */
static void
hv_uio_new_channel(struct vmbus_channel *new_sc)
{
struct hv_device *hv_dev = new_sc->primary_channel->device_obj;
struct device *device = &hv_dev->device;
- struct hv_uio_private_data *pdata = hv_get_drvdata(hv_dev);
const size_t ring_bytes = HV_RING_SIZE * PAGE_SIZE;
int ret;
/* Create host communication ring */
ret = vmbus_open(new_sc, ring_bytes, ring_bytes, NULL, 0,
- hv_uio_channel_cb, pdata);
+ hv_uio_channel_cb, new_sc);
if (ret) {
dev_err(device, "vmbus_open subchannel failed: %d\n", ret);
return;
@@ -234,7 +203,7 @@ hv_uio_probe(struct hv_device *dev,
ret = vmbus_open(dev->channel, HV_RING_SIZE * PAGE_SIZE,
HV_RING_SIZE * PAGE_SIZE, NULL, 0,
- hv_uio_channel_cb, pdata);
+ hv_uio_channel_cb, dev->channel);
if (ret)
goto fail;
@@ -326,6 +295,11 @@ hv_uio_probe(struct hv_device *dev,
vmbus_set_chn_rescind_callback(dev->channel, hv_uio_rescind);
vmbus_set_sc_create_callback(dev->channel, hv_uio_new_channel);
+ ret = sysfs_create_bin_file(&dev->channel->kobj, &ring_buffer_bin_attr);
+ if (ret)
+ dev_notice(&dev->device,
+ "sysfs create ring bin file failed; %d\n", ret);
+
hv_set_drvdata(dev, pdata);
return 0;
diff --git a/drivers/usb/Kconfig b/drivers/usb/Kconfig
index 75f7fb1..987fc5b 100644
--- a/drivers/usb/Kconfig
+++ b/drivers/usb/Kconfig
@@ -207,5 +207,6 @@
config USB_ROLE_SWITCH
tristate
+ select USB_COMMON
endif # USB_SUPPORT
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index c821b4b..7b5cb28 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -191,7 +191,9 @@ static const unsigned short full_speed_maxpacket_maxes[4] = {
static const unsigned short high_speed_maxpacket_maxes[4] = {
[USB_ENDPOINT_XFER_CONTROL] = 64,
[USB_ENDPOINT_XFER_ISOC] = 1024,
- [USB_ENDPOINT_XFER_BULK] = 512,
+
+ /* Bulk should be 512, but some devices use 1024: we will warn below */
+ [USB_ENDPOINT_XFER_BULK] = 1024,
[USB_ENDPOINT_XFER_INT] = 1024,
};
static const unsigned short super_speed_maxpacket_maxes[4] = {
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 777036a..0a42c5df 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2262,7 +2262,8 @@ int hcd_bus_suspend(struct usb_device *rhdev, pm_message_t msg)
hcd->state = HC_STATE_SUSPENDED;
if (!PMSG_IS_AUTO(msg))
- usb_phy_roothub_power_off(hcd->phy_roothub);
+ usb_phy_roothub_suspend(hcd->self.sysdev,
+ hcd->phy_roothub);
/* Did we race with a root-hub wakeup event? */
if (rhdev->do_remote_wakeup) {
@@ -2302,7 +2303,8 @@ int hcd_bus_resume(struct usb_device *rhdev, pm_message_t msg)
}
if (!PMSG_IS_AUTO(msg)) {
- status = usb_phy_roothub_power_on(hcd->phy_roothub);
+ status = usb_phy_roothub_resume(hcd->self.sysdev,
+ hcd->phy_roothub);
if (status)
return status;
}
@@ -2344,7 +2346,7 @@ int hcd_bus_resume(struct usb_device *rhdev, pm_message_t msg)
}
} else {
hcd->state = old_state;
- usb_phy_roothub_power_off(hcd->phy_roothub);
+ usb_phy_roothub_suspend(hcd->self.sysdev, hcd->phy_roothub);
dev_dbg(&rhdev->dev, "bus %s fail, err %d\n",
"resume", status);
if (status != -ESHUTDOWN)
@@ -2377,6 +2379,7 @@ void usb_hcd_resume_root_hub (struct usb_hcd *hcd)
spin_lock_irqsave (&hcd_root_hub_lock, flags);
if (hcd->rh_registered) {
+ pm_wakeup_event(&hcd->self.root_hub->dev, 0);
set_bit(HCD_FLAG_WAKEUP_PENDING, &hcd->flags);
queue_work(pm_wq, &hcd->wakeup_work);
}
@@ -2758,12 +2761,16 @@ int usb_add_hcd(struct usb_hcd *hcd,
}
if (!hcd->skip_phy_initialization && usb_hcd_is_primary_hcd(hcd)) {
- hcd->phy_roothub = usb_phy_roothub_init(hcd->self.sysdev);
+ hcd->phy_roothub = usb_phy_roothub_alloc(hcd->self.sysdev);
if (IS_ERR(hcd->phy_roothub)) {
retval = PTR_ERR(hcd->phy_roothub);
- goto err_phy_roothub_init;
+ goto err_phy_roothub_alloc;
}
+ retval = usb_phy_roothub_init(hcd->phy_roothub);
+ if (retval)
+ goto err_phy_roothub_alloc;
+
retval = usb_phy_roothub_power_on(hcd->phy_roothub);
if (retval)
goto err_usb_phy_roothub_power_on;
@@ -2936,7 +2943,7 @@ int usb_add_hcd(struct usb_hcd *hcd,
usb_phy_roothub_power_off(hcd->phy_roothub);
err_usb_phy_roothub_power_on:
usb_phy_roothub_exit(hcd->phy_roothub);
-err_phy_roothub_init:
+err_phy_roothub_alloc:
if (hcd->remove_phy && hcd->usb_phy) {
usb_phy_shutdown(hcd->usb_phy);
usb_put_phy(hcd->usb_phy);
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index f6ea16e..aa9968d 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -653,12 +653,17 @@ void usb_wakeup_notification(struct usb_device *hdev,
unsigned int portnum)
{
struct usb_hub *hub;
+ struct usb_port *port_dev;
if (!hdev)
return;
hub = usb_hub_to_struct_hub(hdev);
if (hub) {
+ port_dev = hub->ports[portnum - 1];
+ if (port_dev && port_dev->child)
+ pm_wakeup_event(&port_dev->child->dev, 0);
+
set_bit(portnum, hub->wakeup_bits);
kick_hub_wq(hub);
}
@@ -3434,8 +3439,11 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg)
/* Skip the initial Clear-Suspend step for a remote wakeup */
status = hub_port_status(hub, port1, &portstatus, &portchange);
- if (status == 0 && !port_is_suspended(hub, portstatus))
+ if (status == 0 && !port_is_suspended(hub, portstatus)) {
+ if (portchange & USB_PORT_STAT_C_SUSPEND)
+ pm_wakeup_event(&udev->dev, 0);
goto SuspendCleared;
+ }
/* see 7.1.7.7; affects power usage, but not budgeting */
if (hub_is_superspeed(hub->hdev))
diff --git a/drivers/usb/core/phy.c b/drivers/usb/core/phy.c
index 09b7c43..9879767 100644
--- a/drivers/usb/core/phy.c
+++ b/drivers/usb/core/phy.c
@@ -19,19 +19,6 @@ struct usb_phy_roothub {
struct list_head list;
};
-static struct usb_phy_roothub *usb_phy_roothub_alloc(struct device *dev)
-{
- struct usb_phy_roothub *roothub_entry;
-
- roothub_entry = devm_kzalloc(dev, sizeof(*roothub_entry), GFP_KERNEL);
- if (!roothub_entry)
- return ERR_PTR(-ENOMEM);
-
- INIT_LIST_HEAD(&roothub_entry->list);
-
- return roothub_entry;
-}
-
static int usb_phy_roothub_add_phy(struct device *dev, int index,
struct list_head *list)
{
@@ -45,9 +32,11 @@ static int usb_phy_roothub_add_phy(struct device *dev, int index,
return PTR_ERR(phy);
}
- roothub_entry = usb_phy_roothub_alloc(dev);
- if (IS_ERR(roothub_entry))
- return PTR_ERR(roothub_entry);
+ roothub_entry = devm_kzalloc(dev, sizeof(*roothub_entry), GFP_KERNEL);
+ if (!roothub_entry)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&roothub_entry->list);
roothub_entry->phy = phy;
@@ -56,28 +45,44 @@ static int usb_phy_roothub_add_phy(struct device *dev, int index,
return 0;
}
-struct usb_phy_roothub *usb_phy_roothub_init(struct device *dev)
+struct usb_phy_roothub *usb_phy_roothub_alloc(struct device *dev)
{
struct usb_phy_roothub *phy_roothub;
- struct usb_phy_roothub *roothub_entry;
- struct list_head *head;
int i, num_phys, err;
+ if (!IS_ENABLED(CONFIG_GENERIC_PHY))
+ return NULL;
+
num_phys = of_count_phandle_with_args(dev->of_node, "phys",
"#phy-cells");
if (num_phys <= 0)
return NULL;
- phy_roothub = usb_phy_roothub_alloc(dev);
- if (IS_ERR(phy_roothub))
- return phy_roothub;
+ phy_roothub = devm_kzalloc(dev, sizeof(*phy_roothub), GFP_KERNEL);
+ if (!phy_roothub)
+ return ERR_PTR(-ENOMEM);
+
+ INIT_LIST_HEAD(&phy_roothub->list);
for (i = 0; i < num_phys; i++) {
err = usb_phy_roothub_add_phy(dev, i, &phy_roothub->list);
if (err)
- goto err_out;
+ return ERR_PTR(err);
}
+ return phy_roothub;
+}
+EXPORT_SYMBOL_GPL(usb_phy_roothub_alloc);
+
+int usb_phy_roothub_init(struct usb_phy_roothub *phy_roothub)
+{
+ struct usb_phy_roothub *roothub_entry;
+ struct list_head *head;
+ int err;
+
+ if (!phy_roothub)
+ return 0;
+
head = &phy_roothub->list;
list_for_each_entry(roothub_entry, head, list) {
@@ -86,14 +91,13 @@ struct usb_phy_roothub *usb_phy_roothub_init(struct device *dev)
goto err_exit_phys;
}
- return phy_roothub;
+ return 0;
err_exit_phys:
list_for_each_entry_continue_reverse(roothub_entry, head, list)
phy_exit(roothub_entry->phy);
-err_out:
- return ERR_PTR(err);
+ return err;
}
EXPORT_SYMBOL_GPL(usb_phy_roothub_init);
@@ -111,7 +115,7 @@ int usb_phy_roothub_exit(struct usb_phy_roothub *phy_roothub)
list_for_each_entry(roothub_entry, head, list) {
err = phy_exit(roothub_entry->phy);
if (err)
- ret = ret;
+ ret = err;
}
return ret;
@@ -156,3 +160,38 @@ void usb_phy_roothub_power_off(struct usb_phy_roothub *phy_roothub)
phy_power_off(roothub_entry->phy);
}
EXPORT_SYMBOL_GPL(usb_phy_roothub_power_off);
+
+int usb_phy_roothub_suspend(struct device *controller_dev,
+ struct usb_phy_roothub *phy_roothub)
+{
+ usb_phy_roothub_power_off(phy_roothub);
+
+ /* keep the PHYs initialized so the device can wake up the system */
+ if (device_may_wakeup(controller_dev))
+ return 0;
+
+ return usb_phy_roothub_exit(phy_roothub);
+}
+EXPORT_SYMBOL_GPL(usb_phy_roothub_suspend);
+
+int usb_phy_roothub_resume(struct device *controller_dev,
+ struct usb_phy_roothub *phy_roothub)
+{
+ int err;
+
+ /* if the device can't wake up the system _exit was called */
+ if (!device_may_wakeup(controller_dev)) {
+ err = usb_phy_roothub_init(phy_roothub);
+ if (err)
+ return err;
+ }
+
+ err = usb_phy_roothub_power_on(phy_roothub);
+
+ /* undo _init if _power_on failed */
+ if (err && !device_may_wakeup(controller_dev))
+ usb_phy_roothub_exit(phy_roothub);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(usb_phy_roothub_resume);
diff --git a/drivers/usb/core/phy.h b/drivers/usb/core/phy.h
index 6fde59b..88a3c037e 100644
--- a/drivers/usb/core/phy.h
+++ b/drivers/usb/core/phy.h
@@ -1,7 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * USB roothub wrapper
+ *
+ * Copyright (C) 2018 Martin Blumenstingl <martin.blumenstingl@googlemail.com>
+ */
+
+#ifndef __USB_CORE_PHY_H_
+#define __USB_CORE_PHY_H_
+
+struct device;
struct usb_phy_roothub;
-struct usb_phy_roothub *usb_phy_roothub_init(struct device *dev);
+struct usb_phy_roothub *usb_phy_roothub_alloc(struct device *dev);
+
+int usb_phy_roothub_init(struct usb_phy_roothub *phy_roothub);
int usb_phy_roothub_exit(struct usb_phy_roothub *phy_roothub);
int usb_phy_roothub_power_on(struct usb_phy_roothub *phy_roothub);
void usb_phy_roothub_power_off(struct usb_phy_roothub *phy_roothub);
+
+int usb_phy_roothub_suspend(struct device *controller_dev,
+ struct usb_phy_roothub *phy_roothub);
+int usb_phy_roothub_resume(struct device *controller_dev,
+ struct usb_phy_roothub *phy_roothub);
+
+#endif /* __USB_CORE_PHY_H_ */
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 920f48a..c55def2 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -186,6 +186,9 @@ static const struct usb_device_id usb_quirk_list[] = {
{ USB_DEVICE(0x03f0, 0x0701), .driver_info =
USB_QUIRK_STRING_FETCH_255 },
+ /* HP v222w 16GB Mini USB Drive */
+ { USB_DEVICE(0x03f0, 0x3f40), .driver_info = USB_QUIRK_DELAY_INIT },
+
/* Creative SB Audigy 2 NX */
{ USB_DEVICE(0x041e, 0x3020), .driver_info = USB_QUIRK_RESET_RESUME },
diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h
index d83be56..a666e07 100644
--- a/drivers/usb/dwc2/core.h
+++ b/drivers/usb/dwc2/core.h
@@ -985,6 +985,7 @@ struct dwc2_hsotg {
/* DWC OTG HW Release versions */
#define DWC2_CORE_REV_2_71a 0x4f54271a
+#define DWC2_CORE_REV_2_72a 0x4f54272a
#define DWC2_CORE_REV_2_80a 0x4f54280a
#define DWC2_CORE_REV_2_90a 0x4f54290a
#define DWC2_CORE_REV_2_91a 0x4f54291a
@@ -992,6 +993,7 @@ struct dwc2_hsotg {
#define DWC2_CORE_REV_2_94a 0x4f54294a
#define DWC2_CORE_REV_3_00a 0x4f54300a
#define DWC2_CORE_REV_3_10a 0x4f54310a
+#define DWC2_CORE_REV_4_00a 0x4f54400a
#define DWC2_FS_IOT_REV_1_00a 0x5531100a
#define DWC2_HS_IOT_REV_1_00a 0x5532100a
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index 6c32bf2..83cb557 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -3928,6 +3928,27 @@ static int dwc2_hsotg_ep_enable(struct usb_ep *ep,
if (index && !hs_ep->isochronous)
epctrl |= DXEPCTL_SETD0PID;
+ /* WA for Full speed ISOC IN in DDMA mode.
+ * By Clear NAK status of EP, core will send ZLP
+ * to IN token and assert NAK interrupt relying
+ * on TxFIFO status only
+ */
+
+ if (hsotg->gadget.speed == USB_SPEED_FULL &&
+ hs_ep->isochronous && dir_in) {
+ /* The WA applies only to core versions from 2.72a
+ * to 4.00a (including both). Also for FS_IOT_1.00a
+ * and HS_IOT_1.00a.
+ */
+ u32 gsnpsid = dwc2_readl(hsotg->regs + GSNPSID);
+
+ if ((gsnpsid >= DWC2_CORE_REV_2_72a &&
+ gsnpsid <= DWC2_CORE_REV_4_00a) ||
+ gsnpsid == DWC2_FS_IOT_REV_1_00a ||
+ gsnpsid == DWC2_HS_IOT_REV_1_00a)
+ epctrl |= DXEPCTL_CNAK;
+ }
+
dev_dbg(hsotg->dev, "%s: write DxEPCTL=0x%08x\n",
__func__, epctrl);
diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c
index 190f959..c51b73b 100644
--- a/drivers/usb/dwc2/hcd.c
+++ b/drivers/usb/dwc2/hcd.c
@@ -358,9 +358,14 @@ static void dwc2_gusbcfg_init(struct dwc2_hsotg *hsotg)
static int dwc2_vbus_supply_init(struct dwc2_hsotg *hsotg)
{
+ int ret;
+
hsotg->vbus_supply = devm_regulator_get_optional(hsotg->dev, "vbus");
- if (IS_ERR(hsotg->vbus_supply))
- return 0;
+ if (IS_ERR(hsotg->vbus_supply)) {
+ ret = PTR_ERR(hsotg->vbus_supply);
+ hsotg->vbus_supply = NULL;
+ return ret == -ENODEV ? 0 : ret;
+ }
return regulator_enable(hsotg->vbus_supply);
}
@@ -4342,9 +4347,7 @@ static int _dwc2_hcd_start(struct usb_hcd *hcd)
spin_unlock_irqrestore(&hsotg->lock, flags);
- dwc2_vbus_supply_init(hsotg);
-
- return 0;
+ return dwc2_vbus_supply_init(hsotg);
}
/*
diff --git a/drivers/usb/dwc2/pci.c b/drivers/usb/dwc2/pci.c
index 7f21747..bea2e8e 100644
--- a/drivers/usb/dwc2/pci.c
+++ b/drivers/usb/dwc2/pci.c
@@ -141,8 +141,10 @@ static int dwc2_pci_probe(struct pci_dev *pci,
goto err;
glue = devm_kzalloc(dev, sizeof(*glue), GFP_KERNEL);
- if (!glue)
+ if (!glue) {
+ ret = -ENOMEM;
goto err;
+ }
ret = platform_device_add(dwc2);
if (ret) {
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 8796a5ee..0dedf8a 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -166,7 +166,7 @@ static void dwc3_ep_inc_deq(struct dwc3_ep *dep)
dwc3_ep_inc_trb(&dep->trb_dequeue);
}
-void dwc3_gadget_del_and_unmap_request(struct dwc3_ep *dep,
+static void dwc3_gadget_del_and_unmap_request(struct dwc3_ep *dep,
struct dwc3_request *req, int status)
{
struct dwc3 *dwc = dep->dwc;
@@ -1424,7 +1424,7 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,
dwc->lock);
if (!r->trb)
- goto out1;
+ goto out0;
if (r->num_pending_sgs) {
struct dwc3_trb *trb;
diff --git a/drivers/usb/gadget/function/f_phonet.c b/drivers/usb/gadget/function/f_phonet.c
index 7889bcc..8b72b19 100644
--- a/drivers/usb/gadget/function/f_phonet.c
+++ b/drivers/usb/gadget/function/f_phonet.c
@@ -221,7 +221,7 @@ static void pn_tx_complete(struct usb_ep *ep, struct usb_request *req)
netif_wake_queue(dev);
}
-static int pn_net_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t pn_net_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct phonet_port *port = netdev_priv(dev);
struct f_phonet *fp;
diff --git a/drivers/usb/gadget/udc/at91_udc.c b/drivers/usb/gadget/udc/at91_udc.c
index ad743a8..03959dc 100644
--- a/drivers/usb/gadget/udc/at91_udc.c
+++ b/drivers/usb/gadget/udc/at91_udc.c
@@ -234,22 +234,10 @@ static int proc_udc_show(struct seq_file *s, void *unused)
return 0;
}
-static int proc_udc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, proc_udc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations proc_ops = {
- .owner = THIS_MODULE,
- .open = proc_udc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static void create_debug_file(struct at91_udc *udc)
{
- udc->pde = proc_create_data(debug_filename, 0, NULL, &proc_ops, udc);
+ udc->pde = proc_create_single_data(debug_filename, 0, NULL,
+ proc_udc_show, udc);
}
static void remove_debug_file(struct at91_udc *udc)
diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c
index 56b517a..7d8af29 100644
--- a/drivers/usb/gadget/udc/fsl_udc_core.c
+++ b/drivers/usb/gadget/udc/fsl_udc_core.c
@@ -2207,22 +2207,8 @@ static int fsl_proc_read(struct seq_file *m, void *v)
return 0;
}
-/*
- * seq_file wrappers for procfile show routines.
- */
-static int fsl_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, fsl_proc_read, NULL);
-}
-
-static const struct file_operations fsl_proc_fops = {
- .open = fsl_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-#define create_proc_file() proc_create(proc_filename, 0, NULL, &fsl_proc_fops)
+#define create_proc_file() \
+ proc_create_single(proc_filename, 0, NULL, fsl_proc_read)
#define remove_proc_file() remove_proc_entry(proc_filename, NULL)
#else /* !CONFIG_USB_GADGET_DEBUG_FILES */
diff --git a/drivers/usb/gadget/udc/goku_udc.c b/drivers/usb/gadget/udc/goku_udc.c
index 4504d0b..c372122 100644
--- a/drivers/usb/gadget/udc/goku_udc.c
+++ b/drivers/usb/gadget/udc/goku_udc.c
@@ -1241,22 +1241,6 @@ static int udc_proc_read(struct seq_file *m, void *v)
local_irq_restore(flags);
return 0;
}
-
-/*
- * seq_file wrappers for procfile show routines.
- */
-static int udc_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, udc_proc_read, PDE_DATA(file_inode(file)));
-}
-
-static const struct file_operations udc_proc_fops = {
- .open = udc_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
#endif /* CONFIG_USB_GADGET_DEBUG_FILES */
/*-------------------------------------------------------------------------*/
@@ -1826,7 +1810,7 @@ static int goku_probe(struct pci_dev *pdev, const struct pci_device_id *id)
#ifdef CONFIG_USB_GADGET_DEBUG_FILES
- proc_create_data(proc_node_name, 0, NULL, &udc_proc_fops, dev);
+ proc_create_single_data(proc_node_name, 0, NULL, udc_proc_read, dev);
#endif
retval = usb_add_gadget_udc_release(&pdev->dev, &dev->gadget,
diff --git a/drivers/usb/gadget/udc/omap_udc.c b/drivers/usb/gadget/udc/omap_udc.c
index dc35a54..3a16431 100644
--- a/drivers/usb/gadget/udc/omap_udc.c
+++ b/drivers/usb/gadget/udc/omap_udc.c
@@ -2432,22 +2432,9 @@ static int proc_udc_show(struct seq_file *s, void *_)
return 0;
}
-static int proc_udc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, proc_udc_show, NULL);
-}
-
-static const struct file_operations proc_ops = {
- .owner = THIS_MODULE,
- .open = proc_udc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static void create_proc_file(void)
{
- proc_create(proc_filename, 0, NULL, &proc_ops);
+ proc_create_single(proc_filename, 0, NULL, proc_udc_show);
}
static void remove_proc_file(void)
diff --git a/drivers/usb/host/ehci-mem.c b/drivers/usb/host/ehci-mem.c
index 4c6c08b..21307d8 100644
--- a/drivers/usb/host/ehci-mem.c
+++ b/drivers/usb/host/ehci-mem.c
@@ -73,9 +73,10 @@ static struct ehci_qh *ehci_qh_alloc (struct ehci_hcd *ehci, gfp_t flags)
if (!qh)
goto done;
qh->hw = (struct ehci_qh_hw *)
- dma_pool_zalloc(ehci->qh_pool, flags, &dma);
+ dma_pool_alloc(ehci->qh_pool, flags, &dma);
if (!qh->hw)
goto fail;
+ memset(qh->hw, 0, sizeof *qh->hw);
qh->qh_dma = dma;
// INIT_LIST_HEAD (&qh->qh_list);
INIT_LIST_HEAD (&qh->qtd_list);
diff --git a/drivers/usb/host/ehci-sched.c b/drivers/usb/host/ehci-sched.c
index 28e2a33..e56db44 100644
--- a/drivers/usb/host/ehci-sched.c
+++ b/drivers/usb/host/ehci-sched.c
@@ -1287,7 +1287,7 @@ itd_urb_transaction(
} else {
alloc_itd:
spin_unlock_irqrestore(&ehci->lock, flags);
- itd = dma_pool_zalloc(ehci->itd_pool, mem_flags,
+ itd = dma_pool_alloc(ehci->itd_pool, mem_flags,
&itd_dma);
spin_lock_irqsave(&ehci->lock, flags);
if (!itd) {
@@ -1297,6 +1297,7 @@ itd_urb_transaction(
}
}
+ memset(itd, 0, sizeof(*itd));
itd->itd_dma = itd_dma;
itd->frame = NO_FRAME;
list_add(&itd->itd_list, &sched->td_list);
@@ -2080,7 +2081,7 @@ sitd_urb_transaction(
} else {
alloc_sitd:
spin_unlock_irqrestore(&ehci->lock, flags);
- sitd = dma_pool_zalloc(ehci->sitd_pool, mem_flags,
+ sitd = dma_pool_alloc(ehci->sitd_pool, mem_flags,
&sitd_dma);
spin_lock_irqsave(&ehci->lock, flags);
if (!sitd) {
@@ -2090,6 +2091,7 @@ sitd_urb_transaction(
}
}
+ memset(sitd, 0, sizeof(*sitd));
sitd->sitd_dma = sitd_dma;
sitd->frame = NO_FRAME;
list_add(&sitd->sitd_list, &iso_sched->td_list);
diff --git a/drivers/usb/host/xhci-dbgtty.c b/drivers/usb/host/xhci-dbgtty.c
index 48779c4..eb494ec5 100644
--- a/drivers/usb/host/xhci-dbgtty.c
+++ b/drivers/usb/host/xhci-dbgtty.c
@@ -320,9 +320,11 @@ int xhci_dbc_tty_register_driver(struct xhci_hcd *xhci)
void xhci_dbc_tty_unregister_driver(void)
{
- tty_unregister_driver(dbc_tty_driver);
- put_tty_driver(dbc_tty_driver);
- dbc_tty_driver = NULL;
+ if (dbc_tty_driver) {
+ tty_unregister_driver(dbc_tty_driver);
+ put_tty_driver(dbc_tty_driver);
+ dbc_tty_driver = NULL;
+ }
}
static void dbc_rx_push(unsigned long _port)
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 72ebbc9..32cd52c 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -354,7 +354,7 @@ int xhci_find_slot_id_by_port(struct usb_hcd *hcd, struct xhci_hcd *xhci,
slot_id = 0;
for (i = 0; i < MAX_HC_SLOTS; i++) {
- if (!xhci->devs[i])
+ if (!xhci->devs[i] || !xhci->devs[i]->udev)
continue;
speed = xhci->devs[i]->udev->speed;
if (((speed >= USB_SPEED_SUPER) == (hcd->speed >= HCD_USB3))
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index f17b7ea..85ffda8 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -126,7 +126,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_find_chipset_info())
xhci->quirks |= XHCI_AMD_PLL_FIX;
- if (pdev->vendor == PCI_VENDOR_ID_AMD && pdev->device == 0x43bb)
+ if (pdev->vendor == PCI_VENDOR_ID_AMD &&
+ (pdev->device == 0x15e0 ||
+ pdev->device == 0x15e1 ||
+ pdev->device == 0x43bb))
xhci->quirks |= XHCI_SUSPEND_DELAY;
if (pdev->vendor == PCI_VENDOR_ID_AMD)
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index df327dc..c1b22fc 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -157,6 +157,7 @@ static int xhci_plat_probe(struct platform_device *pdev)
struct resource *res;
struct usb_hcd *hcd;
struct clk *clk;
+ struct clk *reg_clk;
int ret;
int irq;
@@ -226,17 +227,27 @@ static int xhci_plat_probe(struct platform_device *pdev)
hcd->rsrc_len = resource_size(res);
/*
- * Not all platforms have a clk so it is not an error if the
- * clock does not exists.
+ * Not all platforms have clks so it is not an error if the
+ * clock do not exist.
*/
+ reg_clk = devm_clk_get(&pdev->dev, "reg");
+ if (!IS_ERR(reg_clk)) {
+ ret = clk_prepare_enable(reg_clk);
+ if (ret)
+ goto put_hcd;
+ } else if (PTR_ERR(reg_clk) == -EPROBE_DEFER) {
+ ret = -EPROBE_DEFER;
+ goto put_hcd;
+ }
+
clk = devm_clk_get(&pdev->dev, NULL);
if (!IS_ERR(clk)) {
ret = clk_prepare_enable(clk);
if (ret)
- goto put_hcd;
+ goto disable_reg_clk;
} else if (PTR_ERR(clk) == -EPROBE_DEFER) {
ret = -EPROBE_DEFER;
- goto put_hcd;
+ goto disable_reg_clk;
}
xhci = hcd_to_xhci(hcd);
@@ -252,6 +263,7 @@ static int xhci_plat_probe(struct platform_device *pdev)
device_wakeup_enable(hcd->self.controller);
xhci->clk = clk;
+ xhci->reg_clk = reg_clk;
xhci->main_hcd = hcd;
xhci->shared_hcd = __usb_create_hcd(driver, sysdev, &pdev->dev,
dev_name(&pdev->dev), hcd);
@@ -320,8 +332,10 @@ static int xhci_plat_probe(struct platform_device *pdev)
usb_put_hcd(xhci->shared_hcd);
disable_clk:
- if (!IS_ERR(clk))
- clk_disable_unprepare(clk);
+ clk_disable_unprepare(clk);
+
+disable_reg_clk:
+ clk_disable_unprepare(reg_clk);
put_hcd:
usb_put_hcd(hcd);
@@ -338,6 +352,7 @@ static int xhci_plat_remove(struct platform_device *dev)
struct usb_hcd *hcd = platform_get_drvdata(dev);
struct xhci_hcd *xhci = hcd_to_xhci(hcd);
struct clk *clk = xhci->clk;
+ struct clk *reg_clk = xhci->reg_clk;
xhci->xhc_state |= XHCI_STATE_REMOVING;
@@ -347,8 +362,8 @@ static int xhci_plat_remove(struct platform_device *dev)
usb_remove_hcd(hcd);
usb_put_hcd(xhci->shared_hcd);
- if (!IS_ERR(clk))
- clk_disable_unprepare(clk);
+ clk_disable_unprepare(clk);
+ clk_disable_unprepare(reg_clk);
usb_put_hcd(hcd);
pm_runtime_set_suspended(&dev->dev);
@@ -420,7 +435,6 @@ MODULE_DEVICE_TABLE(acpi, usb_xhci_acpi_match);
static struct platform_driver usb_xhci_driver = {
.probe = xhci_plat_probe,
.remove = xhci_plat_remove,
- .shutdown = usb_hcd_platform_shutdown,
.driver = {
.name = "xhci-hcd",
.pm = &xhci_plat_pm_ops,
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 9b27798..711da33 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -3621,6 +3621,7 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev)
del_timer_sync(&virt_dev->eps[i].stop_cmd_timer);
}
xhci_debugfs_remove_slot(xhci, udev->slot_id);
+ virt_dev->udev = NULL;
ret = xhci_disable_slot(xhci, udev->slot_id);
if (ret)
xhci_free_virt_device(xhci, udev->slot_id);
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 05c909b..6dfc486 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1729,8 +1729,9 @@ struct xhci_hcd {
int page_shift;
/* msi-x vectors */
int msix_count;
- /* optional clock */
+ /* optional clocks */
struct clk *clk;
+ struct clk *reg_clk;
/* data structures */
struct xhci_device_context_array *dcbaa;
struct xhci_ring *cmd_ring;
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index 05a679d..6a60bc0 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -451,7 +451,6 @@ static int dsps_musb_init(struct musb *musb)
if (!rev)
return -ENODEV;
- usb_phy_init(musb->xceiv);
if (IS_ERR(musb->phy)) {
musb->phy = NULL;
} else {
@@ -501,7 +500,6 @@ static int dsps_musb_exit(struct musb *musb)
struct dsps_glue *glue = dev_get_drvdata(dev->parent);
del_timer_sync(&musb->dev_timer);
- usb_phy_shutdown(musb->xceiv);
phy_power_off(musb->phy);
phy_exit(musb->phy);
debugfs_remove_recursive(glue->dbgfs_root);
diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c
index e564695..71c5835 100644
--- a/drivers/usb/musb/musb_gadget.c
+++ b/drivers/usb/musb/musb_gadget.c
@@ -417,7 +417,6 @@ void musb_g_tx(struct musb *musb, u8 epnum)
req = next_request(musb_ep);
request = &req->request;
- trace_musb_req_tx(req);
csr = musb_readw(epio, MUSB_TXCSR);
musb_dbg(musb, "<== %s, txcsr %04x", musb_ep->end_point.name, csr);
@@ -456,6 +455,8 @@ void musb_g_tx(struct musb *musb, u8 epnum)
u8 is_dma = 0;
bool short_packet = false;
+ trace_musb_req_tx(req);
+
if (dma && (csr & MUSB_TXCSR_DMAENAB)) {
is_dma = 1;
csr |= MUSB_TXCSR_P_WZC_BITS;
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index 3a8451a..15a42ce 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -990,7 +990,9 @@ static void musb_bulk_nak_timeout(struct musb *musb, struct musb_hw_ep *ep,
/* set tx_reinit and schedule the next qh */
ep->tx_reinit = 1;
}
- musb_start_urb(musb, is_in, next_qh);
+
+ if (next_qh)
+ musb_start_urb(musb, is_in, next_qh);
}
}
@@ -2522,8 +2524,11 @@ static int musb_bus_suspend(struct usb_hcd *hcd)
{
struct musb *musb = hcd_to_musb(hcd);
u8 devctl;
+ int ret;
- musb_port_suspend(musb, true);
+ ret = musb_port_suspend(musb, true);
+ if (ret)
+ return ret;
if (!is_host_active(musb))
return 0;
@@ -2754,6 +2759,7 @@ int musb_host_setup(struct musb *musb, int power_budget)
hcd->self.otg_port = 1;
musb->xceiv->otg->host = &hcd->self;
hcd->power_budget = 2 * (power_budget ? : 250);
+ hcd->skip_phy_initialization = 1;
ret = usb_add_hcd(hcd, 0, 0);
if (ret < 0)
diff --git a/drivers/usb/musb/musb_host.h b/drivers/usb/musb/musb_host.h
index 72392bb..2999845 100644
--- a/drivers/usb/musb/musb_host.h
+++ b/drivers/usb/musb/musb_host.h
@@ -67,7 +67,7 @@ extern void musb_host_rx(struct musb *, u8);
extern void musb_root_disconnect(struct musb *musb);
extern void musb_host_resume_root_hub(struct musb *musb);
extern void musb_host_poke_root_hub(struct musb *musb);
-extern void musb_port_suspend(struct musb *musb, bool do_suspend);
+extern int musb_port_suspend(struct musb *musb, bool do_suspend);
extern void musb_port_reset(struct musb *musb, bool do_reset);
extern void musb_host_finish_resume(struct work_struct *work);
#else
@@ -99,7 +99,10 @@ static inline void musb_root_disconnect(struct musb *musb) {}
static inline void musb_host_resume_root_hub(struct musb *musb) {}
static inline void musb_host_poll_rh_status(struct musb *musb) {}
static inline void musb_host_poke_root_hub(struct musb *musb) {}
-static inline void musb_port_suspend(struct musb *musb, bool do_suspend) {}
+static inline int musb_port_suspend(struct musb *musb, bool do_suspend)
+{
+ return 0;
+}
static inline void musb_port_reset(struct musb *musb, bool do_reset) {}
static inline void musb_host_finish_resume(struct work_struct *work) {}
#endif
diff --git a/drivers/usb/musb/musb_virthub.c b/drivers/usb/musb/musb_virthub.c
index 5165d2b..2f8dd98 100644
--- a/drivers/usb/musb/musb_virthub.c
+++ b/drivers/usb/musb/musb_virthub.c
@@ -48,14 +48,14 @@ void musb_host_finish_resume(struct work_struct *work)
spin_unlock_irqrestore(&musb->lock, flags);
}
-void musb_port_suspend(struct musb *musb, bool do_suspend)
+int musb_port_suspend(struct musb *musb, bool do_suspend)
{
struct usb_otg *otg = musb->xceiv->otg;
u8 power;
void __iomem *mbase = musb->mregs;
if (!is_host_active(musb))
- return;
+ return 0;
/* NOTE: this doesn't necessarily put PHY into low power mode,
* turning off its clock; that's a function of PHY integration and
@@ -66,16 +66,20 @@ void musb_port_suspend(struct musb *musb, bool do_suspend)
if (do_suspend) {
int retries = 10000;
- power &= ~MUSB_POWER_RESUME;
- power |= MUSB_POWER_SUSPENDM;
- musb_writeb(mbase, MUSB_POWER, power);
+ if (power & MUSB_POWER_RESUME)
+ return -EBUSY;
- /* Needed for OPT A tests */
- power = musb_readb(mbase, MUSB_POWER);
- while (power & MUSB_POWER_SUSPENDM) {
+ if (!(power & MUSB_POWER_SUSPENDM)) {
+ power |= MUSB_POWER_SUSPENDM;
+ musb_writeb(mbase, MUSB_POWER, power);
+
+ /* Needed for OPT A tests */
power = musb_readb(mbase, MUSB_POWER);
- if (retries-- < 1)
- break;
+ while (power & MUSB_POWER_SUSPENDM) {
+ power = musb_readb(mbase, MUSB_POWER);
+ if (retries-- < 1)
+ break;
+ }
}
musb_dbg(musb, "Root port suspended, power %02x", power);
@@ -111,6 +115,7 @@ void musb_port_suspend(struct musb *musb, bool do_suspend)
schedule_delayed_work(&musb->finish_resume_work,
msecs_to_jiffies(USB_RESUME_TIMEOUT));
}
+ return 0;
}
void musb_port_reset(struct musb *musb, bool do_reset)
diff --git a/drivers/usb/serial/Kconfig b/drivers/usb/serial/Kconfig
index a646820..533f127 100644
--- a/drivers/usb/serial/Kconfig
+++ b/drivers/usb/serial/Kconfig
@@ -62,6 +62,7 @@
- Fundamental Software dongle.
- Google USB serial devices
- HP4x calculators
+ - Libtransistor USB console
- a number of Motorola phones
- Motorola Tetra devices
- Novatel Wireless GPS receivers
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index de1e759..eb6c26c 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -214,6 +214,7 @@ static const struct usb_device_id id_table[] = {
{ USB_DEVICE(0x3195, 0xF190) }, /* Link Instruments MSO-19 */
{ USB_DEVICE(0x3195, 0xF280) }, /* Link Instruments MSO-28 */
{ USB_DEVICE(0x3195, 0xF281) }, /* Link Instruments MSO-28 */
+ { USB_DEVICE(0x3923, 0x7A0B) }, /* National Instruments USB Serial Console */
{ USB_DEVICE(0x413C, 0x9500) }, /* DW700 GPS USB interface */
{ } /* Terminating Entry */
};
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 87202ad..7ea221d 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1898,7 +1898,8 @@ static int ftdi_8u2232c_probe(struct usb_serial *serial)
return ftdi_jtag_probe(serial);
if (udev->product &&
- (!strcmp(udev->product, "BeagleBone/XDS100V2") ||
+ (!strcmp(udev->product, "Arrow USB Blaster") ||
+ !strcmp(udev->product, "BeagleBone/XDS100V2") ||
!strcmp(udev->product, "SNAP Connect E10")))
return ftdi_jtag_probe(serial);
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index c3f2522..2058852 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -233,6 +233,8 @@ static void option_instat_callback(struct urb *urb);
/* These Quectel products use Qualcomm's vendor ID */
#define QUECTEL_PRODUCT_UC20 0x9003
#define QUECTEL_PRODUCT_UC15 0x9090
+/* These u-blox products use Qualcomm's vendor ID */
+#define UBLOX_PRODUCT_R410M 0x90b2
/* These Yuga products use Qualcomm's vendor ID */
#define YUGA_PRODUCT_CLM920_NC5 0x9625
@@ -1065,6 +1067,9 @@ static const struct usb_device_id option_ids[] = {
/* Yuga products use Qualcomm vendor ID */
{ USB_DEVICE(QUALCOMM_VENDOR_ID, YUGA_PRODUCT_CLM920_NC5),
.driver_info = RSVD(1) | RSVD(4) },
+ /* u-blox products using Qualcomm vendor ID */
+ { USB_DEVICE(QUALCOMM_VENDOR_ID, UBLOX_PRODUCT_R410M),
+ .driver_info = RSVD(1) | RSVD(3) },
/* Quectel products using Quectel vendor ID */
{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21),
.driver_info = RSVD(4) },
diff --git a/drivers/usb/serial/usb-serial-simple.c b/drivers/usb/serial/usb-serial-simple.c
index 4ef79e2..40864c2 100644
--- a/drivers/usb/serial/usb-serial-simple.c
+++ b/drivers/usb/serial/usb-serial-simple.c
@@ -63,6 +63,11 @@ DEVICE(flashloader, FLASHLOADER_IDS);
0x01) }
DEVICE(google, GOOGLE_IDS);
+/* Libtransistor USB console */
+#define LIBTRANSISTOR_IDS() \
+ { USB_DEVICE(0x1209, 0x8b00) }
+DEVICE(libtransistor, LIBTRANSISTOR_IDS);
+
/* ViVOpay USB Serial Driver */
#define VIVOPAY_IDS() \
{ USB_DEVICE(0x1d5f, 0x1004) } /* ViVOpay 8800 */
@@ -110,6 +115,7 @@ static struct usb_serial_driver * const serial_drivers[] = {
&funsoft_device,
&flashloader_device,
&google_device,
+ &libtransistor_device,
&vivopay_device,
&moto_modem_device,
&motorola_tetra_device,
@@ -126,6 +132,7 @@ static const struct usb_device_id id_table[] = {
FUNSOFT_IDS(),
FLASHLOADER_IDS(),
GOOGLE_IDS(),
+ LIBTRANSISTOR_IDS(),
VIVOPAY_IDS(),
MOTO_IDS(),
MOTOROLA_TETRA_IDS(),
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index 790e0cb..268ffa6 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -476,19 +476,6 @@ static int serial_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int serial_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, serial_proc_show, NULL);
-}
-
-static const struct file_operations serial_proc_fops = {
- .owner = THIS_MODULE,
- .open = serial_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int serial_tiocmget(struct tty_struct *tty)
{
struct usb_serial_port *port = tty->driver_data;
@@ -1192,7 +1179,7 @@ static const struct tty_operations serial_ops = {
.get_icount = serial_get_icount,
.cleanup = serial_cleanup,
.install = serial_install,
- .proc_fops = &serial_proc_fops,
+ .proc_show = serial_proc_show,
};
diff --git a/drivers/usb/serial/visor.c b/drivers/usb/serial/visor.c
index f5373ed..8ddbecc 100644
--- a/drivers/usb/serial/visor.c
+++ b/drivers/usb/serial/visor.c
@@ -335,47 +335,48 @@ static int palm_os_3_probe(struct usb_serial *serial,
goto exit;
}
- if (retval == sizeof(*connection_info)) {
- connection_info = (struct visor_connection_info *)
- transfer_buffer;
-
- num_ports = le16_to_cpu(connection_info->num_ports);
- for (i = 0; i < num_ports; ++i) {
- switch (
- connection_info->connections[i].port_function_id) {
- case VISOR_FUNCTION_GENERIC:
- string = "Generic";
- break;
- case VISOR_FUNCTION_DEBUGGER:
- string = "Debugger";
- break;
- case VISOR_FUNCTION_HOTSYNC:
- string = "HotSync";
- break;
- case VISOR_FUNCTION_CONSOLE:
- string = "Console";
- break;
- case VISOR_FUNCTION_REMOTE_FILE_SYS:
- string = "Remote File System";
- break;
- default:
- string = "unknown";
- break;
- }
- dev_info(dev, "%s: port %d, is for %s use\n",
- serial->type->description,
- connection_info->connections[i].port, string);
- }
+ if (retval != sizeof(*connection_info)) {
+ dev_err(dev, "Invalid connection information received from device\n");
+ retval = -ENODEV;
+ goto exit;
}
- /*
- * Handle devices that report invalid stuff here.
- */
+
+ connection_info = (struct visor_connection_info *)transfer_buffer;
+
+ num_ports = le16_to_cpu(connection_info->num_ports);
+
+ /* Handle devices that report invalid stuff here. */
if (num_ports == 0 || num_ports > 2) {
dev_warn(dev, "%s: No valid connect info available\n",
serial->type->description);
num_ports = 2;
}
+ for (i = 0; i < num_ports; ++i) {
+ switch (connection_info->connections[i].port_function_id) {
+ case VISOR_FUNCTION_GENERIC:
+ string = "Generic";
+ break;
+ case VISOR_FUNCTION_DEBUGGER:
+ string = "Debugger";
+ break;
+ case VISOR_FUNCTION_HOTSYNC:
+ string = "HotSync";
+ break;
+ case VISOR_FUNCTION_CONSOLE:
+ string = "Console";
+ break;
+ case VISOR_FUNCTION_REMOTE_FILE_SYS:
+ string = "Remote File System";
+ break;
+ default:
+ string = "unknown";
+ break;
+ }
+ dev_info(dev, "%s: port %d, is for %s use\n",
+ serial->type->description,
+ connection_info->connections[i].port, string);
+ }
dev_info(dev, "%s: Number of ports: %d\n", serial->type->description,
num_ports);
diff --git a/drivers/usb/typec/tcpm.c b/drivers/usb/typec/tcpm.c
index 677d121..ded49e3 100644
--- a/drivers/usb/typec/tcpm.c
+++ b/drivers/usb/typec/tcpm.c
@@ -3725,6 +3725,7 @@ void tcpm_unregister_port(struct tcpm_port *port)
for (i = 0; i < ARRAY_SIZE(port->port_altmode); i++)
typec_unregister_altmode(port->port_altmode[i]);
typec_unregister_port(port->typec_port);
+ usb_role_switch_put(port->role_sw);
tcpm_debugfs_exit(port);
destroy_workqueue(port->wq);
}
diff --git a/drivers/usb/typec/tps6598x.c b/drivers/usb/typec/tps6598x.c
index 8b84068..4b4c8d2 100644
--- a/drivers/usb/typec/tps6598x.c
+++ b/drivers/usb/typec/tps6598x.c
@@ -73,6 +73,7 @@ struct tps6598x {
struct device *dev;
struct regmap *regmap;
struct mutex lock; /* device lock */
+ u8 i2c_protocol:1;
struct typec_port *port;
struct typec_partner *partner;
@@ -80,19 +81,39 @@ struct tps6598x {
struct typec_capability typec_cap;
};
+static int
+tps6598x_block_read(struct tps6598x *tps, u8 reg, void *val, size_t len)
+{
+ u8 data[len + 1];
+ int ret;
+
+ if (!tps->i2c_protocol)
+ return regmap_raw_read(tps->regmap, reg, val, len);
+
+ ret = regmap_raw_read(tps->regmap, reg, data, sizeof(data));
+ if (ret)
+ return ret;
+
+ if (data[0] < len)
+ return -EIO;
+
+ memcpy(val, &data[1], len);
+ return 0;
+}
+
static inline int tps6598x_read16(struct tps6598x *tps, u8 reg, u16 *val)
{
- return regmap_raw_read(tps->regmap, reg, val, sizeof(u16));
+ return tps6598x_block_read(tps, reg, val, sizeof(u16));
}
static inline int tps6598x_read32(struct tps6598x *tps, u8 reg, u32 *val)
{
- return regmap_raw_read(tps->regmap, reg, val, sizeof(u32));
+ return tps6598x_block_read(tps, reg, val, sizeof(u32));
}
static inline int tps6598x_read64(struct tps6598x *tps, u8 reg, u64 *val)
{
- return regmap_raw_read(tps->regmap, reg, val, sizeof(u64));
+ return tps6598x_block_read(tps, reg, val, sizeof(u64));
}
static inline int tps6598x_write16(struct tps6598x *tps, u8 reg, u16 val)
@@ -121,8 +142,8 @@ static int tps6598x_read_partner_identity(struct tps6598x *tps)
struct tps6598x_rx_identity_reg id;
int ret;
- ret = regmap_raw_read(tps->regmap, TPS_REG_RX_IDENTITY_SOP,
- &id, sizeof(id));
+ ret = tps6598x_block_read(tps, TPS_REG_RX_IDENTITY_SOP,
+ &id, sizeof(id));
if (ret)
return ret;
@@ -224,13 +245,13 @@ static int tps6598x_exec_cmd(struct tps6598x *tps, const char *cmd,
} while (val);
if (out_len) {
- ret = regmap_raw_read(tps->regmap, TPS_REG_DATA1,
- out_data, out_len);
+ ret = tps6598x_block_read(tps, TPS_REG_DATA1,
+ out_data, out_len);
if (ret)
return ret;
val = out_data[0];
} else {
- ret = regmap_read(tps->regmap, TPS_REG_DATA1, &val);
+ ret = tps6598x_block_read(tps, TPS_REG_DATA1, &val, sizeof(u8));
if (ret)
return ret;
}
@@ -385,6 +406,16 @@ static int tps6598x_probe(struct i2c_client *client)
if (!vid)
return -ENODEV;
+ /*
+ * Checking can the adapter handle SMBus protocol. If it can not, the
+ * driver needs to take care of block reads separately.
+ *
+ * FIXME: Testing with I2C_FUNC_I2C. regmap-i2c uses I2C protocol
+ * unconditionally if the adapter has I2C_FUNC_I2C set.
+ */
+ if (i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
+ tps->i2c_protocol = true;
+
ret = tps6598x_read32(tps, TPS_REG_STATUS, &status);
if (ret < 0)
return ret;
diff --git a/drivers/usb/typec/ucsi/Makefile b/drivers/usb/typec/ucsi/Makefile
index b57891c..7afbea5 100644
--- a/drivers/usb/typec/ucsi/Makefile
+++ b/drivers/usb/typec/ucsi/Makefile
@@ -5,6 +5,6 @@
typec_ucsi-y := ucsi.o
-typec_ucsi-$(CONFIG_FTRACE) += trace.o
+typec_ucsi-$(CONFIG_TRACING) += trace.o
obj-$(CONFIG_UCSI_ACPI) += ucsi_acpi.o
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index bf0977f..bd5cca5 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -28,7 +28,7 @@
* difficult to estimate the time it takes for the system to process the command
* before it is actually passed to the PPM.
*/
-#define UCSI_TIMEOUT_MS 1000
+#define UCSI_TIMEOUT_MS 5000
/*
* UCSI_SWAP_TIMEOUT_MS - Timeout for role swap requests
diff --git a/drivers/usb/usbip/stub.h b/drivers/usb/usbip/stub.h
index 14a72357..35618ce 100644
--- a/drivers/usb/usbip/stub.h
+++ b/drivers/usb/usbip/stub.h
@@ -73,6 +73,7 @@ struct bus_id_priv {
struct stub_device *sdev;
struct usb_device *udev;
char shutdown_busid;
+ spinlock_t busid_lock;
};
/* stub_priv is allocated from stub_priv_cache */
@@ -83,6 +84,7 @@ extern struct usb_device_driver stub_driver;
/* stub_main.c */
struct bus_id_priv *get_busid_priv(const char *busid);
+void put_busid_priv(struct bus_id_priv *bid);
int del_match_busid(char *busid);
void stub_device_cleanup_urbs(struct stub_device *sdev);
diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c
index dd8ef36..c0d6ff1 100644
--- a/drivers/usb/usbip/stub_dev.c
+++ b/drivers/usb/usbip/stub_dev.c
@@ -300,9 +300,9 @@ static int stub_probe(struct usb_device *udev)
struct stub_device *sdev = NULL;
const char *udev_busid = dev_name(&udev->dev);
struct bus_id_priv *busid_priv;
- int rc;
+ int rc = 0;
- dev_dbg(&udev->dev, "Enter\n");
+ dev_dbg(&udev->dev, "Enter probe\n");
/* check we should claim or not by busid_table */
busid_priv = get_busid_priv(udev_busid);
@@ -317,13 +317,15 @@ static int stub_probe(struct usb_device *udev)
* other matched drivers by the driver core.
* See driver_probe_device() in driver/base/dd.c
*/
- return -ENODEV;
+ rc = -ENODEV;
+ goto call_put_busid_priv;
}
if (udev->descriptor.bDeviceClass == USB_CLASS_HUB) {
dev_dbg(&udev->dev, "%s is a usb hub device... skip!\n",
udev_busid);
- return -ENODEV;
+ rc = -ENODEV;
+ goto call_put_busid_priv;
}
if (!strcmp(udev->bus->bus_name, "vhci_hcd")) {
@@ -331,13 +333,16 @@ static int stub_probe(struct usb_device *udev)
"%s is attached on vhci_hcd... skip!\n",
udev_busid);
- return -ENODEV;
+ rc = -ENODEV;
+ goto call_put_busid_priv;
}
/* ok, this is my device */
sdev = stub_device_alloc(udev);
- if (!sdev)
- return -ENOMEM;
+ if (!sdev) {
+ rc = -ENOMEM;
+ goto call_put_busid_priv;
+ }
dev_info(&udev->dev,
"usbip-host: register new device (bus %u dev %u)\n",
@@ -369,7 +374,9 @@ static int stub_probe(struct usb_device *udev)
}
busid_priv->status = STUB_BUSID_ALLOC;
- return 0;
+ rc = 0;
+ goto call_put_busid_priv;
+
err_files:
usb_hub_release_port(udev->parent, udev->portnum,
(struct usb_dev_state *) udev);
@@ -379,6 +386,9 @@ static int stub_probe(struct usb_device *udev)
busid_priv->sdev = NULL;
stub_device_free(sdev);
+
+call_put_busid_priv:
+ put_busid_priv(busid_priv);
return rc;
}
@@ -404,7 +414,7 @@ static void stub_disconnect(struct usb_device *udev)
struct bus_id_priv *busid_priv;
int rc;
- dev_dbg(&udev->dev, "Enter\n");
+ dev_dbg(&udev->dev, "Enter disconnect\n");
busid_priv = get_busid_priv(udev_busid);
if (!busid_priv) {
@@ -417,7 +427,7 @@ static void stub_disconnect(struct usb_device *udev)
/* get stub_device */
if (!sdev) {
dev_err(&udev->dev, "could not get device");
- return;
+ goto call_put_busid_priv;
}
dev_set_drvdata(&udev->dev, NULL);
@@ -432,12 +442,12 @@ static void stub_disconnect(struct usb_device *udev)
(struct usb_dev_state *) udev);
if (rc) {
dev_dbg(&udev->dev, "unable to release port\n");
- return;
+ goto call_put_busid_priv;
}
/* If usb reset is called from event handler */
if (usbip_in_eh(current))
- return;
+ goto call_put_busid_priv;
/* shutdown the current connection */
shutdown_busid(busid_priv);
@@ -448,12 +458,11 @@ static void stub_disconnect(struct usb_device *udev)
busid_priv->sdev = NULL;
stub_device_free(sdev);
- if (busid_priv->status == STUB_BUSID_ALLOC) {
+ if (busid_priv->status == STUB_BUSID_ALLOC)
busid_priv->status = STUB_BUSID_ADDED;
- } else {
- busid_priv->status = STUB_BUSID_OTHER;
- del_match_busid((char *)udev_busid);
- }
+
+call_put_busid_priv:
+ put_busid_priv(busid_priv);
}
#ifdef CONFIG_PM
diff --git a/drivers/usb/usbip/stub_main.c b/drivers/usb/usbip/stub_main.c
index c31c840..bf8a5fe 100644
--- a/drivers/usb/usbip/stub_main.c
+++ b/drivers/usb/usbip/stub_main.c
@@ -14,6 +14,7 @@
#define DRIVER_DESC "USB/IP Host Driver"
struct kmem_cache *stub_priv_cache;
+
/*
* busid_tables defines matching busids that usbip can grab. A user can change
* dynamically what device is locally used and what device is exported to a
@@ -25,6 +26,8 @@ static spinlock_t busid_table_lock;
static void init_busid_table(void)
{
+ int i;
+
/*
* This also sets the bus_table[i].status to
* STUB_BUSID_OTHER, which is 0.
@@ -32,6 +35,9 @@ static void init_busid_table(void)
memset(busid_table, 0, sizeof(busid_table));
spin_lock_init(&busid_table_lock);
+
+ for (i = 0; i < MAX_BUSID; i++)
+ spin_lock_init(&busid_table[i].busid_lock);
}
/*
@@ -43,15 +49,20 @@ static int get_busid_idx(const char *busid)
int i;
int idx = -1;
- for (i = 0; i < MAX_BUSID; i++)
+ for (i = 0; i < MAX_BUSID; i++) {
+ spin_lock(&busid_table[i].busid_lock);
if (busid_table[i].name[0])
if (!strncmp(busid_table[i].name, busid, BUSID_SIZE)) {
idx = i;
+ spin_unlock(&busid_table[i].busid_lock);
break;
}
+ spin_unlock(&busid_table[i].busid_lock);
+ }
return idx;
}
+/* Returns holding busid_lock. Should call put_busid_priv() to unlock */
struct bus_id_priv *get_busid_priv(const char *busid)
{
int idx;
@@ -59,13 +70,22 @@ struct bus_id_priv *get_busid_priv(const char *busid)
spin_lock(&busid_table_lock);
idx = get_busid_idx(busid);
- if (idx >= 0)
+ if (idx >= 0) {
bid = &(busid_table[idx]);
+ /* get busid_lock before returning */
+ spin_lock(&bid->busid_lock);
+ }
spin_unlock(&busid_table_lock);
return bid;
}
+void put_busid_priv(struct bus_id_priv *bid)
+{
+ if (bid)
+ spin_unlock(&bid->busid_lock);
+}
+
static int add_match_busid(char *busid)
{
int i;
@@ -78,15 +98,19 @@ static int add_match_busid(char *busid)
goto out;
}
- for (i = 0; i < MAX_BUSID; i++)
+ for (i = 0; i < MAX_BUSID; i++) {
+ spin_lock(&busid_table[i].busid_lock);
if (!busid_table[i].name[0]) {
strlcpy(busid_table[i].name, busid, BUSID_SIZE);
if ((busid_table[i].status != STUB_BUSID_ALLOC) &&
(busid_table[i].status != STUB_BUSID_REMOV))
busid_table[i].status = STUB_BUSID_ADDED;
ret = 0;
+ spin_unlock(&busid_table[i].busid_lock);
break;
}
+ spin_unlock(&busid_table[i].busid_lock);
+ }
out:
spin_unlock(&busid_table_lock);
@@ -107,6 +131,8 @@ int del_match_busid(char *busid)
/* found */
ret = 0;
+ spin_lock(&busid_table[idx].busid_lock);
+
if (busid_table[idx].status == STUB_BUSID_OTHER)
memset(busid_table[idx].name, 0, BUSID_SIZE);
@@ -114,6 +140,7 @@ int del_match_busid(char *busid)
(busid_table[idx].status != STUB_BUSID_ADDED))
busid_table[idx].status = STUB_BUSID_REMOV;
+ spin_unlock(&busid_table[idx].busid_lock);
out:
spin_unlock(&busid_table_lock);
@@ -126,9 +153,12 @@ static ssize_t match_busid_show(struct device_driver *drv, char *buf)
char *out = buf;
spin_lock(&busid_table_lock);
- for (i = 0; i < MAX_BUSID; i++)
+ for (i = 0; i < MAX_BUSID; i++) {
+ spin_lock(&busid_table[i].busid_lock);
if (busid_table[i].name[0])
out += sprintf(out, "%s ", busid_table[i].name);
+ spin_unlock(&busid_table[i].busid_lock);
+ }
spin_unlock(&busid_table_lock);
out += sprintf(out, "\n");
@@ -169,6 +199,51 @@ static ssize_t match_busid_store(struct device_driver *dev, const char *buf,
}
static DRIVER_ATTR_RW(match_busid);
+static int do_rebind(char *busid, struct bus_id_priv *busid_priv)
+{
+ int ret;
+
+ /* device_attach() callers should hold parent lock for USB */
+ if (busid_priv->udev->dev.parent)
+ device_lock(busid_priv->udev->dev.parent);
+ ret = device_attach(&busid_priv->udev->dev);
+ if (busid_priv->udev->dev.parent)
+ device_unlock(busid_priv->udev->dev.parent);
+ if (ret < 0) {
+ dev_err(&busid_priv->udev->dev, "rebind failed\n");
+ return ret;
+ }
+ return 0;
+}
+
+static void stub_device_rebind(void)
+{
+#if IS_MODULE(CONFIG_USBIP_HOST)
+ struct bus_id_priv *busid_priv;
+ int i;
+
+ /* update status to STUB_BUSID_OTHER so probe ignores the device */
+ spin_lock(&busid_table_lock);
+ for (i = 0; i < MAX_BUSID; i++) {
+ if (busid_table[i].name[0] &&
+ busid_table[i].shutdown_busid) {
+ busid_priv = &(busid_table[i]);
+ busid_priv->status = STUB_BUSID_OTHER;
+ }
+ }
+ spin_unlock(&busid_table_lock);
+
+ /* now run rebind - no need to hold locks. driver files are removed */
+ for (i = 0; i < MAX_BUSID; i++) {
+ if (busid_table[i].name[0] &&
+ busid_table[i].shutdown_busid) {
+ busid_priv = &(busid_table[i]);
+ do_rebind(busid_table[i].name, busid_priv);
+ }
+ }
+#endif
+}
+
static ssize_t rebind_store(struct device_driver *dev, const char *buf,
size_t count)
{
@@ -186,11 +261,17 @@ static ssize_t rebind_store(struct device_driver *dev, const char *buf,
if (!bid)
return -ENODEV;
- ret = device_attach(&bid->udev->dev);
- if (ret < 0) {
- dev_err(&bid->udev->dev, "rebind failed\n");
+ /* mark the device for deletion so probe ignores it during rescan */
+ bid->status = STUB_BUSID_OTHER;
+ /* release the busid lock */
+ put_busid_priv(bid);
+
+ ret = do_rebind((char *) buf, bid);
+ if (ret < 0)
return ret;
- }
+
+ /* delete device from busid_table */
+ del_match_busid((char *) buf);
return count;
}
@@ -312,6 +393,9 @@ static void __exit usbip_host_exit(void)
*/
usb_deregister_device_driver(&stub_driver);
+ /* initiate scan to attach devices */
+ stub_device_rebind();
+
kmem_cache_destroy(stub_priv_cache);
}
diff --git a/drivers/usb/usbip/usbip_common.h b/drivers/usb/usbip/usbip_common.h
index 473fb8a..bf8afe9 100644
--- a/drivers/usb/usbip/usbip_common.h
+++ b/drivers/usb/usbip/usbip_common.h
@@ -243,7 +243,7 @@ enum usbip_side {
#define VUDC_EVENT_ERROR_USB (USBIP_EH_SHUTDOWN | USBIP_EH_UNUSABLE)
#define VUDC_EVENT_ERROR_MALLOC (USBIP_EH_SHUTDOWN | USBIP_EH_UNUSABLE)
-#define VDEV_EVENT_REMOVED (USBIP_EH_SHUTDOWN | USBIP_EH_BYE)
+#define VDEV_EVENT_REMOVED (USBIP_EH_SHUTDOWN | USBIP_EH_RESET | USBIP_EH_BYE)
#define VDEV_EVENT_DOWN (USBIP_EH_SHUTDOWN | USBIP_EH_RESET)
#define VDEV_EVENT_ERROR_TCP (USBIP_EH_SHUTDOWN | USBIP_EH_RESET)
#define VDEV_EVENT_ERROR_MALLOC (USBIP_EH_SHUTDOWN | USBIP_EH_UNUSABLE)
diff --git a/drivers/usb/usbip/usbip_event.c b/drivers/usb/usbip/usbip_event.c
index 5b4c086..5d88917 100644
--- a/drivers/usb/usbip/usbip_event.c
+++ b/drivers/usb/usbip/usbip_event.c
@@ -91,10 +91,6 @@ static void event_handler(struct work_struct *work)
unset_event(ud, USBIP_EH_UNUSABLE);
}
- /* Stop the error handler. */
- if (ud->event & USBIP_EH_BYE)
- usbip_dbg_eh("removed %p\n", ud);
-
wake_up(&ud->eh_waitq);
}
}
diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c
index 20e3d46..d11f3f8 100644
--- a/drivers/usb/usbip/vhci_hcd.c
+++ b/drivers/usb/usbip/vhci_hcd.c
@@ -354,6 +354,8 @@ static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
usbip_dbg_vhci_rh(" ClearHubFeature\n");
break;
case ClearPortFeature:
+ if (rhport < 0)
+ goto error;
switch (wValue) {
case USB_PORT_FEAT_SUSPEND:
if (hcd->speed == HCD_USB3) {
@@ -511,11 +513,16 @@ static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
goto error;
}
+ if (rhport < 0)
+ goto error;
+
vhci_hcd->port_status[rhport] |= USB_PORT_STAT_SUSPEND;
break;
case USB_PORT_FEAT_POWER:
usbip_dbg_vhci_rh(
" SetPortFeature: USB_PORT_FEAT_POWER\n");
+ if (rhport < 0)
+ goto error;
if (hcd->speed == HCD_USB3)
vhci_hcd->port_status[rhport] |= USB_SS_PORT_STAT_POWER;
else
@@ -524,6 +531,8 @@ static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
case USB_PORT_FEAT_BH_PORT_RESET:
usbip_dbg_vhci_rh(
" SetPortFeature: USB_PORT_FEAT_BH_PORT_RESET\n");
+ if (rhport < 0)
+ goto error;
/* Applicable only for USB3.0 hub */
if (hcd->speed != HCD_USB3) {
pr_err("USB_PORT_FEAT_BH_PORT_RESET req not "
@@ -534,6 +543,8 @@ static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
case USB_PORT_FEAT_RESET:
usbip_dbg_vhci_rh(
" SetPortFeature: USB_PORT_FEAT_RESET\n");
+ if (rhport < 0)
+ goto error;
/* if it's already enabled, disable */
if (hcd->speed == HCD_USB3) {
vhci_hcd->port_status[rhport] = 0;
@@ -554,6 +565,8 @@ static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
default:
usbip_dbg_vhci_rh(" SetPortFeature: default %d\n",
wValue);
+ if (rhport < 0)
+ goto error;
if (hcd->speed == HCD_USB3) {
if ((vhci_hcd->port_status[rhport] &
USB_SS_PORT_STAT_POWER) != 0) {
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 5c212bf..3c082451 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -404,6 +404,7 @@ static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
{
unsigned long pfn = 0;
long ret, pinned = 0, lock_acct = 0;
+ bool rsvd;
dma_addr_t iova = vaddr - dma->vaddr + dma->iova;
/* This code path is only user initiated */
@@ -414,23 +415,14 @@ static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
if (ret)
return ret;
- if (is_invalid_reserved_pfn(*pfn_base)) {
- struct vm_area_struct *vma;
-
- down_read(¤t->mm->mmap_sem);
- vma = find_vma_intersection(current->mm, vaddr, vaddr + 1);
- pinned = min_t(long, npage, vma_pages(vma));
- up_read(¤t->mm->mmap_sem);
- return pinned;
- }
-
pinned++;
+ rsvd = is_invalid_reserved_pfn(*pfn_base);
/*
* Reserved pages aren't counted against the user, externally pinned
* pages are already counted against the user.
*/
- if (!vfio_find_vpfn(dma, iova)) {
+ if (!rsvd && !vfio_find_vpfn(dma, iova)) {
if (!lock_cap && current->mm->locked_vm + 1 > limit) {
put_pfn(*pfn_base, dma->prot);
pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n", __func__,
@@ -450,12 +442,13 @@ static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
if (ret)
break;
- if (pfn != *pfn_base + pinned) {
+ if (pfn != *pfn_base + pinned ||
+ rsvd != is_invalid_reserved_pfn(pfn)) {
put_pfn(pfn, dma->prot);
break;
}
- if (!vfio_find_vpfn(dma, iova)) {
+ if (!rsvd && !vfio_find_vpfn(dma, iova)) {
if (!lock_cap &&
current->mm->locked_vm + lock_acct + 1 > limit) {
put_pfn(pfn, dma->prot);
@@ -473,8 +466,10 @@ static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
unpin_out:
if (ret) {
- for (pfn = *pfn_base ; pinned ; pfn++, pinned--)
- put_pfn(pfn, dma->prot);
+ if (!rsvd) {
+ for (pfn = *pfn_base ; pinned ; pfn++, pinned--)
+ put_pfn(pfn, dma->prot);
+ }
return ret;
}
diff --git a/drivers/vfio/virqfd.c b/drivers/vfio/virqfd.c
index 085700f..2a1be85 100644
--- a/drivers/vfio/virqfd.c
+++ b/drivers/vfio/virqfd.c
@@ -166,7 +166,7 @@ int vfio_virqfd_enable(void *opaque,
init_waitqueue_func_entry(&virqfd->wait, virqfd_wakeup);
init_poll_funcptr(&virqfd->pt, virqfd_ptable_queue_proc);
- events = irqfd.file->f_op->poll(irqfd.file, &virqfd->pt);
+ events = vfs_poll(irqfd.file, &virqfd->pt);
/*
* Check if there was an event already pending on the eventfd
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 986058a..eeaf673 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -105,7 +105,9 @@ struct vhost_net_virtqueue {
/* vhost zerocopy support fields below: */
/* last used idx for outstanding DMA zerocopy buffers */
int upend_idx;
- /* first used idx for DMA done zerocopy buffers */
+ /* For TX, first used idx for DMA done zerocopy buffers
+ * For RX, number of batched heads
+ */
int done_idx;
/* an array of userspace buffers info */
struct ubuf_info *ubuf_info;
@@ -626,6 +628,18 @@ static int sk_has_rx_data(struct sock *sk)
return skb_queue_empty(&sk->sk_receive_queue);
}
+static void vhost_rx_signal_used(struct vhost_net_virtqueue *nvq)
+{
+ struct vhost_virtqueue *vq = &nvq->vq;
+ struct vhost_dev *dev = vq->dev;
+
+ if (!nvq->done_idx)
+ return;
+
+ vhost_add_used_and_signal_n(dev, vq, vq->heads, nvq->done_idx);
+ nvq->done_idx = 0;
+}
+
static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
{
struct vhost_net_virtqueue *rvq = &net->vqs[VHOST_NET_VQ_RX];
@@ -635,6 +649,8 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
int len = peek_head_len(rvq, sk);
if (!len && vq->busyloop_timeout) {
+ /* Flush batched heads first */
+ vhost_rx_signal_used(rvq);
/* Both tx vq and rx socket were polled here */
mutex_lock_nested(&vq->mutex, 1);
vhost_disable_notify(&net->dev, vq);
@@ -762,7 +778,7 @@ static void handle_rx(struct vhost_net *net)
};
size_t total_len = 0;
int err, mergeable;
- s16 headcount, nheads = 0;
+ s16 headcount;
size_t vhost_hlen, sock_hlen;
size_t vhost_len, sock_len;
struct socket *sock;
@@ -790,8 +806,8 @@ static void handle_rx(struct vhost_net *net)
while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk))) {
sock_len += sock_hlen;
vhost_len = sock_len + vhost_hlen;
- headcount = get_rx_bufs(vq, vq->heads + nheads, vhost_len,
- &in, vq_log, &log,
+ headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx,
+ vhost_len, &in, vq_log, &log,
likely(mergeable) ? UIO_MAXIOV : 1);
/* On error, stop handling until the next kick. */
if (unlikely(headcount < 0))
@@ -862,12 +878,9 @@ static void handle_rx(struct vhost_net *net)
vhost_discard_vq_desc(vq, headcount);
goto out;
}
- nheads += headcount;
- if (nheads > VHOST_RX_BATCH) {
- vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
- nheads);
- nheads = 0;
- }
+ nvq->done_idx += headcount;
+ if (nvq->done_idx > VHOST_RX_BATCH)
+ vhost_rx_signal_used(nvq);
if (unlikely(vq_log))
vhost_log_write(vq, vq_log, log, vhost_len);
total_len += vhost_len;
@@ -878,9 +891,7 @@ static void handle_rx(struct vhost_net *net)
}
vhost_net_enable_vq(net, vq);
out:
- if (nheads)
- vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
- nheads);
+ vhost_rx_signal_used(nvq);
mutex_unlock(&vq->mutex);
}
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index f3bd8e9..895eaa2 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -208,7 +208,7 @@ int vhost_poll_start(struct vhost_poll *poll, struct file *file)
if (poll->wqh)
return 0;
- mask = file->f_op->poll(file, &poll->table);
+ mask = vfs_poll(file, &poll->table);
if (mask)
vhost_poll_wakeup(&poll->wait, 0, 0, poll_to_key(mask));
if (mask & EPOLLERR) {
@@ -981,6 +981,7 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev,
{
int ret = 0;
+ mutex_lock(&dev->mutex);
vhost_dev_lock_vqs(dev);
switch (msg->type) {
case VHOST_IOTLB_UPDATE:
@@ -1016,6 +1017,8 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev,
}
vhost_dev_unlock_vqs(dev);
+ mutex_unlock(&dev->mutex);
+
return ret;
}
ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index f741ba8..924d073 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -713,19 +713,6 @@ static const struct seq_operations proc_fb_seq_ops = {
.show = fb_seq_show,
};
-static int proc_fb_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &proc_fb_seq_ops);
-}
-
-static const struct file_operations fb_proc_fops = {
- .owner = THIS_MODULE,
- .open = proc_fb_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
/*
* We hold a reference to the fb_info in file->private_data,
* but if the current registered fb has changed, we don't
@@ -1877,7 +1864,7 @@ fbmem_init(void)
{
int ret;
- if (!proc_create("fb", 0, NULL, &fb_proc_fops))
+ if (!proc_create_seq("fb", 0, NULL, &proc_fb_seq_ops))
return -ENOMEM;
ret = register_chrdev(FB_MAJOR, "fb", &fb_fops);
diff --git a/drivers/video/fbdev/via/viafbdev.c b/drivers/video/fbdev/via/viafbdev.c
index badee04..9b451259 100644
--- a/drivers/video/fbdev/via/viafbdev.c
+++ b/drivers/video/fbdev/via/viafbdev.c
@@ -1475,19 +1475,6 @@ static int viafb_sup_odev_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int viafb_sup_odev_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, viafb_sup_odev_proc_show, NULL);
-}
-
-static const struct file_operations viafb_sup_odev_proc_fops = {
- .owner = THIS_MODULE,
- .open = viafb_sup_odev_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static ssize_t odev_update(const char __user *buffer, size_t count, u32 *odev)
{
char buf[64], *ptr = buf;
@@ -1616,8 +1603,8 @@ static void viafb_init_proc(struct viafb_shared *shared)
&viafb_vt1636_proc_fops);
#endif /* CONFIG_FB_VIA_DIRECT_PROCFS */
- proc_create("supported_output_devices", 0, viafb_entry,
- &viafb_sup_odev_proc_fops);
+ proc_create_single("supported_output_devices", 0, viafb_entry,
+ viafb_sup_odev_proc_show);
iga1_entry = proc_mkdir("iga1", viafb_entry);
shared->iga1_proc_entry = iga1_entry;
proc_create("output_devices", 0, iga1_entry,
diff --git a/drivers/virt/vboxguest/vboxguest_core.c b/drivers/virt/vboxguest/vboxguest_core.c
index 190dbf8..2f3856a 100644
--- a/drivers/virt/vboxguest/vboxguest_core.c
+++ b/drivers/virt/vboxguest/vboxguest_core.c
@@ -114,7 +114,7 @@ static void vbg_guest_mappings_init(struct vbg_dev *gdev)
}
out:
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
kfree(pages);
}
@@ -144,7 +144,7 @@ static void vbg_guest_mappings_exit(struct vbg_dev *gdev)
rc = vbg_req_perform(gdev, req);
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
if (rc < 0) {
vbg_err("%s error: %d\n", __func__, rc);
@@ -214,8 +214,8 @@ static int vbg_report_guest_info(struct vbg_dev *gdev)
ret = vbg_status_code_to_errno(rc);
out_free:
- kfree(req2);
- kfree(req1);
+ vbg_req_free(req2, sizeof(*req2));
+ vbg_req_free(req1, sizeof(*req1));
return ret;
}
@@ -245,7 +245,7 @@ static int vbg_report_driver_status(struct vbg_dev *gdev, bool active)
if (rc == VERR_NOT_IMPLEMENTED) /* Compatibility with older hosts. */
rc = VINF_SUCCESS;
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
return vbg_status_code_to_errno(rc);
}
@@ -431,7 +431,7 @@ static int vbg_heartbeat_host_config(struct vbg_dev *gdev, bool enabled)
rc = vbg_req_perform(gdev, req);
do_div(req->interval_ns, 1000000); /* ns -> ms */
gdev->heartbeat_interval_ms = req->interval_ns;
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
return vbg_status_code_to_errno(rc);
}
@@ -454,12 +454,6 @@ static int vbg_heartbeat_init(struct vbg_dev *gdev)
if (ret < 0)
return ret;
- /*
- * Preallocate the request to use it from the timer callback because:
- * 1) on Windows vbg_req_alloc must be called at IRQL <= APC_LEVEL
- * and the timer callback runs at DISPATCH_LEVEL;
- * 2) avoid repeated allocations.
- */
gdev->guest_heartbeat_req = vbg_req_alloc(
sizeof(*gdev->guest_heartbeat_req),
VMMDEVREQ_GUEST_HEARTBEAT);
@@ -481,8 +475,8 @@ static void vbg_heartbeat_exit(struct vbg_dev *gdev)
{
del_timer_sync(&gdev->heartbeat_timer);
vbg_heartbeat_host_config(gdev, false);
- kfree(gdev->guest_heartbeat_req);
-
+ vbg_req_free(gdev->guest_heartbeat_req,
+ sizeof(*gdev->guest_heartbeat_req));
}
/**
@@ -543,7 +537,7 @@ static int vbg_reset_host_event_filter(struct vbg_dev *gdev,
if (rc < 0)
vbg_err("%s error, rc: %d\n", __func__, rc);
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
return vbg_status_code_to_errno(rc);
}
@@ -617,7 +611,7 @@ static int vbg_set_session_event_filter(struct vbg_dev *gdev,
out:
mutex_unlock(&gdev->session_mutex);
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
return ret;
}
@@ -642,7 +636,7 @@ static int vbg_reset_host_capabilities(struct vbg_dev *gdev)
if (rc < 0)
vbg_err("%s error, rc: %d\n", __func__, rc);
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
return vbg_status_code_to_errno(rc);
}
@@ -712,7 +706,7 @@ static int vbg_set_session_capabilities(struct vbg_dev *gdev,
out:
mutex_unlock(&gdev->session_mutex);
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
return ret;
}
@@ -733,8 +727,10 @@ static int vbg_query_host_version(struct vbg_dev *gdev)
rc = vbg_req_perform(gdev, req);
ret = vbg_status_code_to_errno(rc);
- if (ret)
+ if (ret) {
+ vbg_err("%s error: %d\n", __func__, rc);
goto out;
+ }
snprintf(gdev->host_version, sizeof(gdev->host_version), "%u.%u.%ur%u",
req->major, req->minor, req->build, req->revision);
@@ -749,7 +745,7 @@ static int vbg_query_host_version(struct vbg_dev *gdev)
}
out:
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
return ret;
}
@@ -847,11 +843,16 @@ int vbg_core_init(struct vbg_dev *gdev, u32 fixed_events)
return 0;
err_free_reqs:
- kfree(gdev->mouse_status_req);
- kfree(gdev->ack_events_req);
- kfree(gdev->cancel_req);
- kfree(gdev->mem_balloon.change_req);
- kfree(gdev->mem_balloon.get_req);
+ vbg_req_free(gdev->mouse_status_req,
+ sizeof(*gdev->mouse_status_req));
+ vbg_req_free(gdev->ack_events_req,
+ sizeof(*gdev->ack_events_req));
+ vbg_req_free(gdev->cancel_req,
+ sizeof(*gdev->cancel_req));
+ vbg_req_free(gdev->mem_balloon.change_req,
+ sizeof(*gdev->mem_balloon.change_req));
+ vbg_req_free(gdev->mem_balloon.get_req,
+ sizeof(*gdev->mem_balloon.get_req));
return ret;
}
@@ -872,11 +873,16 @@ void vbg_core_exit(struct vbg_dev *gdev)
vbg_reset_host_capabilities(gdev);
vbg_core_set_mouse_status(gdev, 0);
- kfree(gdev->mouse_status_req);
- kfree(gdev->ack_events_req);
- kfree(gdev->cancel_req);
- kfree(gdev->mem_balloon.change_req);
- kfree(gdev->mem_balloon.get_req);
+ vbg_req_free(gdev->mouse_status_req,
+ sizeof(*gdev->mouse_status_req));
+ vbg_req_free(gdev->ack_events_req,
+ sizeof(*gdev->ack_events_req));
+ vbg_req_free(gdev->cancel_req,
+ sizeof(*gdev->cancel_req));
+ vbg_req_free(gdev->mem_balloon.change_req,
+ sizeof(*gdev->mem_balloon.change_req));
+ vbg_req_free(gdev->mem_balloon.get_req,
+ sizeof(*gdev->mem_balloon.get_req));
}
/**
@@ -1415,7 +1421,7 @@ static int vbg_ioctl_write_core_dump(struct vbg_dev *gdev,
req->flags = dump->u.in.flags;
dump->hdr.rc = vbg_req_perform(gdev, req);
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
return 0;
}
@@ -1513,7 +1519,7 @@ int vbg_core_set_mouse_status(struct vbg_dev *gdev, u32 features)
if (rc < 0)
vbg_err("%s error, rc: %d\n", __func__, rc);
- kfree(req);
+ vbg_req_free(req, sizeof(*req));
return vbg_status_code_to_errno(rc);
}
diff --git a/drivers/virt/vboxguest/vboxguest_core.h b/drivers/virt/vboxguest/vboxguest_core.h
index 6c784bf..7ad9ec4 100644
--- a/drivers/virt/vboxguest/vboxguest_core.h
+++ b/drivers/virt/vboxguest/vboxguest_core.h
@@ -171,4 +171,13 @@ irqreturn_t vbg_core_isr(int irq, void *dev_id);
void vbg_linux_mouse_event(struct vbg_dev *gdev);
+/* Private (non exported) functions form vboxguest_utils.c */
+void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type);
+void vbg_req_free(void *req, size_t len);
+int vbg_req_perform(struct vbg_dev *gdev, void *req);
+int vbg_hgcm_call32(
+ struct vbg_dev *gdev, u32 client_id, u32 function, u32 timeout_ms,
+ struct vmmdev_hgcm_function_parameter32 *parm32, u32 parm_count,
+ int *vbox_status);
+
#endif
diff --git a/drivers/virt/vboxguest/vboxguest_linux.c b/drivers/virt/vboxguest/vboxguest_linux.c
index 82e280d..398d226 100644
--- a/drivers/virt/vboxguest/vboxguest_linux.c
+++ b/drivers/virt/vboxguest/vboxguest_linux.c
@@ -87,6 +87,7 @@ static long vbg_misc_device_ioctl(struct file *filp, unsigned int req,
struct vbg_session *session = filp->private_data;
size_t returned_size, size;
struct vbg_ioctl_hdr hdr;
+ bool is_vmmdev_req;
int ret = 0;
void *buf;
@@ -106,8 +107,17 @@ static long vbg_misc_device_ioctl(struct file *filp, unsigned int req,
if (size > SZ_16M)
return -E2BIG;
- /* __GFP_DMA32 because IOCTL_VMMDEV_REQUEST passes this to the host */
- buf = kmalloc(size, GFP_KERNEL | __GFP_DMA32);
+ /*
+ * IOCTL_VMMDEV_REQUEST needs the buffer to be below 4G to avoid
+ * the need for a bounce-buffer and another copy later on.
+ */
+ is_vmmdev_req = (req & ~IOCSIZE_MASK) == VBG_IOCTL_VMMDEV_REQUEST(0) ||
+ req == VBG_IOCTL_VMMDEV_REQUEST_BIG;
+
+ if (is_vmmdev_req)
+ buf = vbg_req_alloc(size, VBG_IOCTL_HDR_TYPE_DEFAULT);
+ else
+ buf = kmalloc(size, GFP_KERNEL);
if (!buf)
return -ENOMEM;
@@ -132,7 +142,10 @@ static long vbg_misc_device_ioctl(struct file *filp, unsigned int req,
ret = -EFAULT;
out:
- kfree(buf);
+ if (is_vmmdev_req)
+ vbg_req_free(buf, size);
+ else
+ kfree(buf);
return ret;
}
diff --git a/drivers/virt/vboxguest/vboxguest_utils.c b/drivers/virt/vboxguest/vboxguest_utils.c
index 0f0dab8..bf447421 100644
--- a/drivers/virt/vboxguest/vboxguest_utils.c
+++ b/drivers/virt/vboxguest/vboxguest_utils.c
@@ -65,8 +65,9 @@ VBG_LOG(vbg_debug, pr_debug);
void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type)
{
struct vmmdev_request_header *req;
+ int order = get_order(PAGE_ALIGN(len));
- req = kmalloc(len, GFP_KERNEL | __GFP_DMA32);
+ req = (void *)__get_free_pages(GFP_KERNEL | GFP_DMA32, order);
if (!req)
return NULL;
@@ -82,6 +83,14 @@ void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type)
return req;
}
+void vbg_req_free(void *req, size_t len)
+{
+ if (!req)
+ return;
+
+ free_pages((unsigned long)req, get_order(PAGE_ALIGN(len)));
+}
+
/* Note this function returns a VBox status code, not a negative errno!! */
int vbg_req_perform(struct vbg_dev *gdev, void *req)
{
@@ -137,7 +146,7 @@ int vbg_hgcm_connect(struct vbg_dev *gdev,
rc = hgcm_connect->header.result;
}
- kfree(hgcm_connect);
+ vbg_req_free(hgcm_connect, sizeof(*hgcm_connect));
*vbox_status = rc;
return 0;
@@ -166,7 +175,7 @@ int vbg_hgcm_disconnect(struct vbg_dev *gdev, u32 client_id, int *vbox_status)
if (rc >= 0)
rc = hgcm_disconnect->header.result;
- kfree(hgcm_disconnect);
+ vbg_req_free(hgcm_disconnect, sizeof(*hgcm_disconnect));
*vbox_status = rc;
return 0;
@@ -623,7 +632,7 @@ int vbg_hgcm_call(struct vbg_dev *gdev, u32 client_id, u32 function,
}
if (!leak_it)
- kfree(call);
+ vbg_req_free(call, size);
free_bounce_bufs:
if (bounce_bufs) {
diff --git a/drivers/w1/w1_io.c b/drivers/w1/w1_io.c
index 075d120..0364d33 100644
--- a/drivers/w1/w1_io.c
+++ b/drivers/w1/w1_io.c
@@ -194,6 +194,7 @@ static u8 w1_read_bit(struct w1_master *dev)
* bit 0 = id_bit
* bit 1 = comp_bit
* bit 2 = dir_taken
+ *
* If both bits 0 & 1 are set, the search should be restarted.
*
* Return: bit fields - see above
diff --git a/drivers/watchdog/aspeed_wdt.c b/drivers/watchdog/aspeed_wdt.c
index a5b8eb2..1abe4d0 100644
--- a/drivers/watchdog/aspeed_wdt.c
+++ b/drivers/watchdog/aspeed_wdt.c
@@ -55,6 +55,8 @@ MODULE_DEVICE_TABLE(of, aspeed_wdt_of_table);
#define WDT_CTRL_WDT_INTR BIT(2)
#define WDT_CTRL_RESET_SYSTEM BIT(1)
#define WDT_CTRL_ENABLE BIT(0)
+#define WDT_TIMEOUT_STATUS 0x10
+#define WDT_TIMEOUT_STATUS_BOOT_SECONDARY BIT(1)
/*
* WDT_RESET_WIDTH controls the characteristics of the external pulse (if
@@ -192,6 +194,7 @@ static int aspeed_wdt_probe(struct platform_device *pdev)
struct device_node *np;
const char *reset_type;
u32 duration;
+ u32 status;
int ret;
wdt = devm_kzalloc(&pdev->dev, sizeof(*wdt), GFP_KERNEL);
@@ -307,6 +310,10 @@ static int aspeed_wdt_probe(struct platform_device *pdev)
writel(duration - 1, wdt->base + WDT_RESET_WIDTH);
}
+ status = readl(wdt->base + WDT_TIMEOUT_STATUS);
+ if (status & WDT_TIMEOUT_STATUS_BOOT_SECONDARY)
+ wdt->wdd.bootstatus = WDIOF_CARDRESET;
+
ret = devm_watchdog_register_device(&pdev->dev, &wdt->wdd);
if (ret) {
dev_err(&pdev->dev, "failed to register\n");
diff --git a/drivers/watchdog/renesas_wdt.c b/drivers/watchdog/renesas_wdt.c
index 6b8c6dd..514db5c 100644
--- a/drivers/watchdog/renesas_wdt.c
+++ b/drivers/watchdog/renesas_wdt.c
@@ -121,7 +121,8 @@ static int rwdt_restart(struct watchdog_device *wdev, unsigned long action,
}
static const struct watchdog_info rwdt_ident = {
- .options = WDIOF_MAGICCLOSE | WDIOF_KEEPALIVEPING | WDIOF_SETTIMEOUT,
+ .options = WDIOF_MAGICCLOSE | WDIOF_KEEPALIVEPING | WDIOF_SETTIMEOUT |
+ WDIOF_CARDRESET,
.identity = "Renesas WDT Watchdog",
};
@@ -197,9 +198,10 @@ static int rwdt_probe(struct platform_device *pdev)
return PTR_ERR(clk);
pm_runtime_enable(&pdev->dev);
-
pm_runtime_get_sync(&pdev->dev);
priv->clk_rate = clk_get_rate(clk);
+ priv->wdev.bootstatus = (readb_relaxed(priv->base + RWTCSRA) &
+ RWTCSRA_WOVF) ? WDIOF_CARDRESET : 0;
pm_runtime_put(&pdev->dev);
if (!priv->clk_rate) {
diff --git a/drivers/watchdog/sch311x_wdt.c b/drivers/watchdog/sch311x_wdt.c
index 43d0cbb..814cdf5 100644
--- a/drivers/watchdog/sch311x_wdt.c
+++ b/drivers/watchdog/sch311x_wdt.c
@@ -299,7 +299,7 @@ static long sch311x_wdt_ioctl(struct file *file, unsigned int cmd,
if (sch311x_wdt_set_heartbeat(new_timeout))
return -EINVAL;
sch311x_wdt_keepalive();
- /* Fall */
+ /* Fall through */
case WDIOC_GETTIMEOUT:
return put_user(timeout, p);
default:
diff --git a/drivers/watchdog/w83977f_wdt.c b/drivers/watchdog/w83977f_wdt.c
index 20e2bba..672b61a 100644
--- a/drivers/watchdog/w83977f_wdt.c
+++ b/drivers/watchdog/w83977f_wdt.c
@@ -427,7 +427,7 @@ static long wdt_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
return -EINVAL;
wdt_keepalive();
- /* Fall */
+ /* Fall through */
case WDIOC_GETTIMEOUT:
return put_user(timeout, uarg.i);
diff --git a/drivers/watchdog/wafer5823wdt.c b/drivers/watchdog/wafer5823wdt.c
index db0da7e..93c5b61 100644
--- a/drivers/watchdog/wafer5823wdt.c
+++ b/drivers/watchdog/wafer5823wdt.c
@@ -178,7 +178,7 @@ static long wafwdt_ioctl(struct file *file, unsigned int cmd,
timeout = new_timeout;
wafwdt_stop();
wafwdt_start();
- /* Fall */
+ /* Fall through */
case WDIOC_GETTIMEOUT:
return put_user(timeout, p);
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index e1c6089..a6f9ba8 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -351,7 +351,7 @@ xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
* physical address */
phys = xen_bus_to_phys(dev_addr);
- if (((dev_addr + size - 1 > dma_mask)) ||
+ if (((dev_addr + size - 1 <= dma_mask)) ||
range_straddles_page_boundary(phys, size))
xen_destroy_contiguous_region(phys, order);
diff --git a/drivers/xen/xen-pciback/conf_space_quirks.c b/drivers/xen/xen-pciback/conf_space_quirks.c
index 89d9744..ed593d1 100644
--- a/drivers/xen/xen-pciback/conf_space_quirks.c
+++ b/drivers/xen/xen-pciback/conf_space_quirks.c
@@ -95,7 +95,7 @@ int xen_pcibk_config_quirks_init(struct pci_dev *dev)
struct xen_pcibk_config_quirk *quirk;
int ret = 0;
- quirk = kzalloc(sizeof(*quirk), GFP_ATOMIC);
+ quirk = kzalloc(sizeof(*quirk), GFP_KERNEL);
if (!quirk) {
ret = -ENOMEM;
goto out;
diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c
index 9e480fd..59661db 100644
--- a/drivers/xen/xen-pciback/pci_stub.c
+++ b/drivers/xen/xen-pciback/pci_stub.c
@@ -71,7 +71,7 @@ static struct pcistub_device *pcistub_device_alloc(struct pci_dev *dev)
dev_dbg(&dev->dev, "pcistub_device_alloc\n");
- psdev = kzalloc(sizeof(*psdev), GFP_ATOMIC);
+ psdev = kzalloc(sizeof(*psdev), GFP_KERNEL);
if (!psdev)
return NULL;
@@ -364,7 +364,7 @@ static int pcistub_init_device(struct pci_dev *dev)
* here and then to call kfree(pci_get_drvdata(psdev->dev)).
*/
dev_data = kzalloc(sizeof(*dev_data) + strlen(DRV_NAME "[]")
- + strlen(pci_name(dev)) + 1, GFP_ATOMIC);
+ + strlen(pci_name(dev)) + 1, GFP_KERNEL);
if (!dev_data) {
err = -ENOMEM;
goto out;
@@ -577,7 +577,7 @@ static int pcistub_probe(struct pci_dev *dev, const struct pci_device_id *id)
}
if (!match) {
- pci_dev_id = kmalloc(sizeof(*pci_dev_id), GFP_ATOMIC);
+ pci_dev_id = kmalloc(sizeof(*pci_dev_id), GFP_KERNEL);
if (!pci_dev_id) {
err = -ENOMEM;
goto out;
@@ -1149,7 +1149,7 @@ static int pcistub_reg_add(int domain, int bus, int slot, int func,
}
dev = psdev->dev;
- field = kzalloc(sizeof(*field), GFP_ATOMIC);
+ field = kzalloc(sizeof(*field), GFP_KERNEL);
if (!field) {
err = -ENOMEM;
goto out;
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 0d6d926..c3e20102 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -403,7 +403,7 @@ static int xenbus_command_reply(struct xenbus_file_priv *u,
{
struct {
struct xsd_sockmsg hdr;
- const char body[16];
+ char body[16];
} msg;
int rc;
@@ -412,6 +412,7 @@ static int xenbus_command_reply(struct xenbus_file_priv *u,
msg.hdr.len = strlen(reply) + 1;
if (msg.hdr.len > sizeof(msg.body))
return -E2BIG;
+ memcpy(&msg.body, reply, msg.hdr.len);
mutex_lock(&u->reply_mutex);
rc = queue_reply(&u->read_buffers, &msg, sizeof(msg.hdr) + msg.hdr.len);
diff --git a/drivers/zorro/proc.c b/drivers/zorro/proc.c
index df05a26..2e4ca4d 100644
--- a/drivers/zorro/proc.c
+++ b/drivers/zorro/proc.c
@@ -96,19 +96,6 @@ static const struct seq_operations zorro_devices_seq_ops = {
.show = zorro_seq_show,
};
-static int zorro_devices_proc_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &zorro_devices_seq_ops);
-}
-
-static const struct file_operations zorro_devices_proc_fops = {
- .owner = THIS_MODULE,
- .open = zorro_devices_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static struct proc_dir_entry *proc_bus_zorro_dir;
static int __init zorro_proc_attach_device(unsigned int slot)
@@ -132,8 +119,8 @@ static int __init zorro_proc_init(void)
if (MACH_IS_AMIGA && AMIGAHW_PRESENT(ZORRO)) {
proc_bus_zorro_dir = proc_mkdir("bus/zorro", NULL);
- proc_create("devices", 0, proc_bus_zorro_dir,
- &zorro_devices_proc_fops);
+ proc_create_seq("devices", 0, proc_bus_zorro_dir,
+ &zorro_devices_seq_ops);
for (slot = 0; slot < zorro_num_autocon; slot++)
zorro_proc_attach_device(slot);
}
diff --git a/drivers/zorro/zorro.c b/drivers/zorro/zorro.c
index 4772847..67fa900 100644
--- a/drivers/zorro/zorro.c
+++ b/drivers/zorro/zorro.c
@@ -101,6 +101,7 @@ static void __init mark_region(unsigned long start, unsigned long end,
end = end > Z2RAM_END ? Z2RAM_SIZE : end-Z2RAM_START;
while (start < end) {
u32 chunk = start>>Z2RAM_CHUNKSHIFT;
+
if (flag)
set_bit(chunk, zorro_unused_z2ram);
else
@@ -117,6 +118,7 @@ static struct resource __init *zorro_find_parent_resource(
for (i = 0; i < bridge->num_resources; i++) {
struct resource *r = &bridge->resource[i];
+
if (zorro_resource_start(z) >= r->start &&
zorro_resource_end(z) <= r->end)
return r;
@@ -168,6 +170,7 @@ static int __init amiga_zorro_probe(struct platform_device *pdev)
if (z->id == ZORRO_PROD_GVP_EPC_BASE) {
/* GVP quirk */
unsigned long magic = zi->boardaddr + 0x8000;
+
z->id |= *(u16 *)ZTWO_VADDR(magic) & GVP_PRODMASK;
}
z->slotaddr = zi->slotaddr;
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 9ee5341..42e102e 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -823,28 +823,21 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
if (IS_ERR(dfid))
return ERR_CAST(dfid);
- name = dentry->d_name.name;
- fid = p9_client_walk(dfid, 1, &name, 1);
- if (IS_ERR(fid)) {
- if (fid == ERR_PTR(-ENOENT)) {
- d_add(dentry, NULL);
- return NULL;
- }
- return ERR_CAST(fid);
- }
/*
* Make sure we don't use a wrong inode due to parallel
* unlink. For cached mode create calls request for new
* inode. But with cache disabled, lookup should do this.
*/
- if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
+ name = dentry->d_name.name;
+ fid = p9_client_walk(dfid, 1, &name, 1);
+ if (fid == ERR_PTR(-ENOENT))
+ inode = NULL;
+ else if (IS_ERR(fid))
+ inode = ERR_CAST(fid);
+ else if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb);
else
inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
- if (IS_ERR(inode)) {
- p9_client_clunk(fid);
- return ERR_CAST(inode);
- }
/*
* If we had a rename on the server and a parallel lookup
* for the new name, then make sure we instantiate with
@@ -853,12 +846,14 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
* k/b.
*/
res = d_splice_alias(inode, dentry);
- if (!res)
- v9fs_fid_add(dentry, fid);
- else if (!IS_ERR(res))
- v9fs_fid_add(res, fid);
- else
- p9_client_clunk(fid);
+ if (!IS_ERR(fid)) {
+ if (!res)
+ v9fs_fid_add(dentry, fid);
+ else if (!IS_ERR(res))
+ v9fs_fid_add(res, fid);
+ else
+ p9_client_clunk(fid);
+ }
return res;
}
diff --git a/fs/Kconfig b/fs/Kconfig
index bc821a8..ac4ac90 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -196,7 +196,7 @@
help
hugetlbfs is a filesystem backing for HugeTLB pages, based on
ramfs. For architectures that support it, say Y here and read
- <file:Documentation/vm/hugetlbpage.txt> for details.
+ <file:Documentation/admin-guide/mm/hugetlbpage.rst> for details.
If unsure, say N.
diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c
index 29444c8..e18eff8 100644
--- a/fs/adfs/dir.c
+++ b/fs/adfs/dir.c
@@ -146,20 +146,6 @@ adfs_dir_lookup_byname(struct inode *inode, const struct qstr *name, struct obje
obj->parent_id = inode->i_ino;
- /*
- * '.' is handled by reserved_lookup() in fs/namei.c
- */
- if (name->len == 2 && name->name[0] == '.' && name->name[1] == '.') {
- /*
- * Currently unable to fill in the rest of 'obj',
- * but this is better than nothing. We need to
- * ascend one level to find it's parent.
- */
- obj->name_len = 0;
- obj->file_id = obj->parent_id;
- goto free_out;
- }
-
read_lock(&adfs_dir_lock);
ret = ops->setpos(&dir, 0);
@@ -266,17 +252,17 @@ adfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
error = adfs_dir_lookup_byname(dir, &dentry->d_name, &obj);
if (error == 0) {
- error = -EACCES;
/*
* This only returns NULL if get_empty_inode
* fails.
*/
inode = adfs_iget(dir->i_sb, &obj);
- if (inode)
- error = 0;
+ if (!inode)
+ inode = ERR_PTR(-EACCES);
+ } else if (error != -ENOENT) {
+ inode = ERR_PTR(error);
}
- d_add(dentry, inode);
- return ERR_PTR(error);
+ return d_splice_alias(inode, dentry);
}
/*
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index d8aa0ae..41c5749 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -201,14 +201,16 @@ affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
struct super_block *sb = dir->i_sb;
struct buffer_head *bh;
struct inode *inode = NULL;
+ struct dentry *res;
pr_debug("%s(\"%pd\")\n", __func__, dentry);
affs_lock_dir(dir);
bh = affs_find_entry(dir, dentry);
- affs_unlock_dir(dir);
- if (IS_ERR(bh))
+ if (IS_ERR(bh)) {
+ affs_unlock_dir(dir);
return ERR_CAST(bh);
+ }
if (bh) {
u32 ino = bh->b_blocknr;
@@ -222,11 +224,12 @@ affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
}
affs_brelse(bh);
inode = affs_iget(sb, ino);
- if (IS_ERR(inode))
- return ERR_CAST(inode);
}
- d_add(dentry, inode);
- return NULL;
+ res = d_splice_alias(inode, dentry);
+ if (!IS_ERR_OR_NULL(res))
+ res->d_fsdata = dentry->d_fsdata;
+ affs_unlock_dir(dir);
+ return res;
}
int
diff --git a/fs/affs/super.c b/fs/affs/super.c
index e602619..d1ad11a 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -241,6 +241,7 @@ parse_options(char *options, kuid_t *uid, kgid_t *gid, int *mode, int *reserved,
affs_set_opt(*mount_opts, SF_NO_TRUNCATE);
break;
case Opt_prefix:
+ kfree(*prefix);
*prefix = match_strdup(&args[0]);
if (!*prefix)
return 0;
diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c
index 3bedfed..7587fb6 100644
--- a/fs/afs/addr_list.c
+++ b/fs/afs/addr_list.c
@@ -121,7 +121,7 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len,
p = text;
do {
struct sockaddr_rxrpc *srx = &alist->addrs[alist->nr_addrs];
- char tdelim = delim;
+ const char *q, *stop;
if (*p == delim) {
p++;
@@ -130,28 +130,33 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len,
if (*p == '[') {
p++;
- tdelim = ']';
+ q = memchr(p, ']', end - p);
+ } else {
+ for (q = p; q < end; q++)
+ if (*q == '+' || *q == delim)
+ break;
}
- if (in4_pton(p, end - p,
+ if (in4_pton(p, q - p,
(u8 *)&srx->transport.sin6.sin6_addr.s6_addr32[3],
- tdelim, &p)) {
+ -1, &stop)) {
srx->transport.sin6.sin6_addr.s6_addr32[0] = 0;
srx->transport.sin6.sin6_addr.s6_addr32[1] = 0;
srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
- } else if (in6_pton(p, end - p,
+ } else if (in6_pton(p, q - p,
srx->transport.sin6.sin6_addr.s6_addr,
- tdelim, &p)) {
+ -1, &stop)) {
/* Nothing to do */
} else {
goto bad_address;
}
- if (tdelim == ']') {
- if (p == end || *p != ']')
- goto bad_address;
+ if (stop != q)
+ goto bad_address;
+
+ p = q;
+ if (q < end && *q == ']')
p++;
- }
if (p < end) {
if (*p == '+') {
diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index abd9a84..571437d 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -23,36 +23,55 @@
/*
* Set up an interest-in-callbacks record for a volume on a server and
* register it with the server.
- * - Called with volume->server_sem held.
+ * - Called with vnode->io_lock held.
*/
int afs_register_server_cb_interest(struct afs_vnode *vnode,
- struct afs_server_entry *entry)
+ struct afs_server_list *slist,
+ unsigned int index)
{
- struct afs_cb_interest *cbi = entry->cb_interest, *vcbi, *new, *x;
+ struct afs_server_entry *entry = &slist->servers[index];
+ struct afs_cb_interest *cbi, *vcbi, *new, *old;
struct afs_server *server = entry->server;
again:
+ if (vnode->cb_interest &&
+ likely(vnode->cb_interest == entry->cb_interest))
+ return 0;
+
+ read_lock(&slist->lock);
+ cbi = afs_get_cb_interest(entry->cb_interest);
+ read_unlock(&slist->lock);
+
vcbi = vnode->cb_interest;
if (vcbi) {
- if (vcbi == cbi)
- return 0;
-
- if (cbi && vcbi->server == cbi->server) {
- write_seqlock(&vnode->cb_lock);
- vnode->cb_interest = afs_get_cb_interest(cbi);
- write_sequnlock(&vnode->cb_lock);
+ if (vcbi == cbi) {
afs_put_cb_interest(afs_v2net(vnode), cbi);
return 0;
}
+ /* Use a new interest in the server list for the same server
+ * rather than an old one that's still attached to a vnode.
+ */
+ if (cbi && vcbi->server == cbi->server) {
+ write_seqlock(&vnode->cb_lock);
+ old = vnode->cb_interest;
+ vnode->cb_interest = cbi;
+ write_sequnlock(&vnode->cb_lock);
+ afs_put_cb_interest(afs_v2net(vnode), old);
+ return 0;
+ }
+
+ /* Re-use the one attached to the vnode. */
if (!cbi && vcbi->server == server) {
- afs_get_cb_interest(vcbi);
- x = cmpxchg(&entry->cb_interest, cbi, vcbi);
- if (x != cbi) {
- cbi = x;
- afs_put_cb_interest(afs_v2net(vnode), vcbi);
+ write_lock(&slist->lock);
+ if (entry->cb_interest) {
+ write_unlock(&slist->lock);
+ afs_put_cb_interest(afs_v2net(vnode), cbi);
goto again;
}
+
+ entry->cb_interest = cbi;
+ write_unlock(&slist->lock);
return 0;
}
}
@@ -72,13 +91,16 @@ int afs_register_server_cb_interest(struct afs_vnode *vnode,
list_add_tail(&new->cb_link, &server->cb_interests);
write_unlock(&server->cb_break_lock);
- x = cmpxchg(&entry->cb_interest, cbi, new);
- if (x == cbi) {
+ write_lock(&slist->lock);
+ if (!entry->cb_interest) {
+ entry->cb_interest = afs_get_cb_interest(new);
cbi = new;
+ new = NULL;
} else {
- cbi = x;
- afs_put_cb_interest(afs_v2net(vnode), new);
+ cbi = afs_get_cb_interest(entry->cb_interest);
}
+ write_unlock(&slist->lock);
+ afs_put_cb_interest(afs_v2net(vnode), new);
}
ASSERT(cbi);
@@ -88,11 +110,14 @@ int afs_register_server_cb_interest(struct afs_vnode *vnode,
*/
write_seqlock(&vnode->cb_lock);
- vnode->cb_interest = afs_get_cb_interest(cbi);
+ old = vnode->cb_interest;
+ vnode->cb_interest = cbi;
vnode->cb_s_break = cbi->server->cb_s_break;
+ vnode->cb_v_break = vnode->volume->cb_v_break;
clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
write_sequnlock(&vnode->cb_lock);
+ afs_put_cb_interest(afs_v2net(vnode), old);
return 0;
}
@@ -171,13 +196,24 @@ static void afs_break_one_callback(struct afs_server *server,
if (cbi->vid != fid->vid)
continue;
- data.volume = NULL;
- data.fid = *fid;
- inode = ilookup5_nowait(cbi->sb, fid->vnode, afs_iget5_test, &data);
- if (inode) {
- vnode = AFS_FS_I(inode);
- afs_break_callback(vnode);
- iput(inode);
+ if (fid->vnode == 0 && fid->unique == 0) {
+ /* The callback break applies to an entire volume. */
+ struct afs_super_info *as = AFS_FS_S(cbi->sb);
+ struct afs_volume *volume = as->volume;
+
+ write_lock(&volume->cb_break_lock);
+ volume->cb_v_break++;
+ write_unlock(&volume->cb_break_lock);
+ } else {
+ data.volume = NULL;
+ data.fid = *fid;
+ inode = ilookup5_nowait(cbi->sb, fid->vnode,
+ afs_iget5_test, &data);
+ if (inode) {
+ vnode = AFS_FS_I(inode);
+ afs_break_callback(vnode);
+ iput(inode);
+ }
}
}
@@ -195,6 +231,8 @@ void afs_break_callbacks(struct afs_server *server, size_t count,
ASSERT(server != NULL);
ASSERTCMP(count, <=, AFSCBMAX);
+ /* TODO: Sort the callback break list by volume ID */
+
for (; count > 0; callbacks++, count--) {
_debug("- Fid { vl=%08x n=%u u=%u } CB { v=%u x=%u t=%u }",
callbacks->fid.vid,
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index 357de90..c332c95 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -133,21 +133,10 @@ bool afs_cm_incoming_call(struct afs_call *call)
}
/*
- * clean up a cache manager call
+ * Clean up a cache manager call.
*/
static void afs_cm_destructor(struct afs_call *call)
{
- _enter("");
-
- /* Break the callbacks here so that we do it after the final ACK is
- * received. The step number here must match the final number in
- * afs_deliver_cb_callback().
- */
- if (call->unmarshall == 5) {
- ASSERT(call->cm_server && call->count && call->request);
- afs_break_callbacks(call->cm_server, call->count, call->request);
- }
-
kfree(call->buffer);
call->buffer = NULL;
}
@@ -161,14 +150,14 @@ static void SRXAFSCB_CallBack(struct work_struct *work)
_enter("");
- /* be sure to send the reply *before* attempting to spam the AFS server
- * with FSFetchStatus requests on the vnodes with broken callbacks lest
- * the AFS server get into a vicious cycle of trying to break further
- * callbacks because it hadn't received completion of the CBCallBack op
- * yet */
- afs_send_empty_reply(call);
+ /* We need to break the callbacks before sending the reply as the
+ * server holds up change visibility till it receives our reply so as
+ * to maintain cache coherency.
+ */
+ if (call->cm_server)
+ afs_break_callbacks(call->cm_server, call->count, call->request);
- afs_break_callbacks(call->cm_server, call->count, call->request);
+ afs_send_empty_reply(call);
afs_put_call(call);
_leave("");
}
@@ -180,7 +169,6 @@ static int afs_deliver_cb_callback(struct afs_call *call)
{
struct afs_callback_break *cb;
struct sockaddr_rxrpc srx;
- struct afs_server *server;
__be32 *bp;
int ret, loop;
@@ -267,15 +255,6 @@ static int afs_deliver_cb_callback(struct afs_call *call)
call->offset = 0;
call->unmarshall++;
-
- /* Record that the message was unmarshalled successfully so
- * that the call destructor can know do the callback breaking
- * work, even if the final ACK isn't received.
- *
- * If the step number changes, then afs_cm_destructor() must be
- * updated also.
- */
- call->unmarshall++;
case 5:
break;
}
@@ -286,10 +265,9 @@ static int afs_deliver_cb_callback(struct afs_call *call)
/* we'll need the file server record as that tells us which set of
* vnodes to operate upon */
rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx);
- server = afs_find_server(call->net, &srx);
- if (!server)
- return -ENOTCONN;
- call->cm_server = server;
+ call->cm_server = afs_find_server(call->net, &srx);
+ if (!call->cm_server)
+ trace_afs_cm_no_server(call, &srx);
return afs_queue_call_work(call);
}
@@ -303,7 +281,8 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work)
_enter("{%p}", call->cm_server);
- afs_init_callback_state(call->cm_server);
+ if (call->cm_server)
+ afs_init_callback_state(call->cm_server);
afs_send_empty_reply(call);
afs_put_call(call);
_leave("");
@@ -315,7 +294,6 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work)
static int afs_deliver_cb_init_call_back_state(struct afs_call *call)
{
struct sockaddr_rxrpc srx;
- struct afs_server *server;
int ret;
_enter("");
@@ -328,10 +306,9 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call)
/* we'll need the file server record as that tells us which set of
* vnodes to operate upon */
- server = afs_find_server(call->net, &srx);
- if (!server)
- return -ENOTCONN;
- call->cm_server = server;
+ call->cm_server = afs_find_server(call->net, &srx);
+ if (!call->cm_server)
+ trace_afs_cm_no_server(call, &srx);
return afs_queue_call_work(call);
}
@@ -341,8 +318,6 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call)
*/
static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
{
- struct sockaddr_rxrpc srx;
- struct afs_server *server;
struct afs_uuid *r;
unsigned loop;
__be32 *b;
@@ -398,11 +373,11 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
/* we'll need the file server record as that tells us which set of
* vnodes to operate upon */
- rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx);
- server = afs_find_server(call->net, &srx);
- if (!server)
- return -ENOTCONN;
- call->cm_server = server;
+ rcu_read_lock();
+ call->cm_server = afs_find_server_by_uuid(call->net, call->request);
+ rcu_read_unlock();
+ if (!call->cm_server)
+ trace_afs_cm_no_server_u(call, call->request);
return afs_queue_call_work(call);
}
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 5889f70..7d623008 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -180,6 +180,7 @@ static int afs_dir_open(struct inode *inode, struct file *file)
* get reclaimed during the iteration.
*/
static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key)
+ __acquires(&dvnode->validate_lock)
{
struct afs_read *req;
loff_t i_size;
@@ -261,18 +262,21 @@ static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key)
/* If we're going to reload, we need to lock all the pages to prevent
* races.
*/
+ ret = -ERESTARTSYS;
+ if (down_read_killable(&dvnode->validate_lock) < 0)
+ goto error;
+
+ if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
+ goto success;
+
+ up_read(&dvnode->validate_lock);
+ if (down_write_killable(&dvnode->validate_lock) < 0)
+ goto error;
+
if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) {
- ret = -ERESTARTSYS;
- for (i = 0; i < req->nr_pages; i++)
- if (lock_page_killable(req->pages[i]) < 0)
- goto error_unlock;
-
- if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
- goto success;
-
ret = afs_fetch_data(dvnode, key, req);
if (ret < 0)
- goto error_unlock_all;
+ goto error_unlock;
task_io_account_read(PAGE_SIZE * req->nr_pages);
@@ -284,33 +288,26 @@ static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key)
for (i = 0; i < req->nr_pages; i++)
if (!afs_dir_check_page(dvnode, req->pages[i],
req->actual_len))
- goto error_unlock_all;
+ goto error_unlock;
// TODO: Trim excess pages
set_bit(AFS_VNODE_DIR_VALID, &dvnode->flags);
}
+ downgrade_write(&dvnode->validate_lock);
success:
- i = req->nr_pages;
- while (i > 0)
- unlock_page(req->pages[--i]);
return req;
-error_unlock_all:
- i = req->nr_pages;
error_unlock:
- while (i > 0)
- unlock_page(req->pages[--i]);
+ up_write(&dvnode->validate_lock);
error:
afs_put_read(req);
_leave(" = %d", ret);
return ERR_PTR(ret);
content_has_grown:
- i = req->nr_pages;
- while (i > 0)
- unlock_page(req->pages[--i]);
+ up_write(&dvnode->validate_lock);
afs_put_read(req);
goto retry;
}
@@ -473,6 +470,7 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx,
}
out:
+ up_read(&dvnode->validate_lock);
afs_put_read(req);
_leave(" = %d", ret);
return ret;
@@ -1143,7 +1141,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, dvnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(dvnode);
afs_fs_create(&fc, dentry->d_name.name, mode, data_version,
&newfid, &newstatus, &newcb);
}
@@ -1213,7 +1211,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, dvnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(dvnode);
afs_fs_remove(&fc, dentry->d_name.name, true,
data_version);
}
@@ -1316,7 +1314,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, dvnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(dvnode);
afs_fs_remove(&fc, dentry->d_name.name, false,
data_version);
}
@@ -1373,7 +1371,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, dvnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(dvnode);
afs_fs_create(&fc, dentry->d_name.name, mode, data_version,
&newfid, &newstatus, &newcb);
}
@@ -1443,8 +1441,8 @@ static int afs_link(struct dentry *from, struct inode *dir,
}
while (afs_select_fileserver(&fc)) {
- fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
- fc.cb_break_2 = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(dvnode);
+ fc.cb_break_2 = afs_calc_vnode_cb_break(vnode);
afs_fs_link(&fc, vnode, dentry->d_name.name, data_version);
}
@@ -1512,7 +1510,7 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry,
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, dvnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(dvnode);
afs_fs_symlink(&fc, dentry->d_name.name,
content, data_version,
&newfid, &newstatus);
@@ -1588,8 +1586,8 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
}
}
while (afs_select_fileserver(&fc)) {
- fc.cb_break = orig_dvnode->cb_break + orig_dvnode->cb_s_break;
- fc.cb_break_2 = new_dvnode->cb_break + new_dvnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(orig_dvnode);
+ fc.cb_break_2 = afs_calc_vnode_cb_break(new_dvnode);
afs_fs_rename(&fc, old_dentry->d_name.name,
new_dvnode, new_dentry->d_name.name,
orig_data_version, new_data_version);
diff --git a/fs/afs/file.c b/fs/afs/file.c
index c24c080..7d4f261 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -238,7 +238,7 @@ int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *de
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_fetch_data(&fc, desc);
}
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index 7a0e017..dc62d15 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -86,7 +86,7 @@ static int afs_set_lock(struct afs_vnode *vnode, struct key *key,
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_set_lock(&fc, type);
}
@@ -117,7 +117,7 @@ static int afs_extend_lock(struct afs_vnode *vnode, struct key *key)
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_current_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_extend_lock(&fc);
}
@@ -148,7 +148,7 @@ static int afs_release_lock(struct afs_vnode *vnode, struct key *key)
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_current_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_release_lock(&fc);
}
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index efacdb7..b273e1d 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -134,6 +134,7 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call,
struct afs_read *read_req)
{
const struct afs_xdr_AFSFetchStatus *xdr = (const void *)*_bp;
+ bool inline_error = (call->operation_ID == afs_FS_InlineBulkStatus);
u64 data_version, size;
u32 type, abort_code;
u8 flags = 0;
@@ -142,13 +143,32 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call,
if (vnode)
write_seqlock(&vnode->cb_lock);
+ abort_code = ntohl(xdr->abort_code);
+
if (xdr->if_version != htonl(AFS_FSTATUS_VERSION)) {
+ if (xdr->if_version == htonl(0) &&
+ abort_code != 0 &&
+ inline_error) {
+ /* The OpenAFS fileserver has a bug in FS.InlineBulkStatus
+ * whereby it doesn't set the interface version in the error
+ * case.
+ */
+ status->abort_code = abort_code;
+ ret = 0;
+ goto out;
+ }
+
pr_warn("Unknown AFSFetchStatus version %u\n", ntohl(xdr->if_version));
goto bad;
}
+ if (abort_code != 0 && inline_error) {
+ status->abort_code = abort_code;
+ ret = 0;
+ goto out;
+ }
+
type = ntohl(xdr->type);
- abort_code = ntohl(xdr->abort_code);
switch (type) {
case AFS_FTYPE_FILE:
case AFS_FTYPE_DIR:
@@ -165,13 +185,6 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call,
}
status->type = type;
break;
- case AFS_FTYPE_INVALID:
- if (abort_code != 0) {
- status->abort_code = abort_code;
- ret = 0;
- goto out;
- }
- /* Fall through */
default:
goto bad;
}
@@ -248,7 +261,7 @@ static void xdr_decode_AFSCallBack(struct afs_call *call,
write_seqlock(&vnode->cb_lock);
- if (call->cb_break == (vnode->cb_break + cbi->server->cb_s_break)) {
+ if (call->cb_break == afs_cb_break_sum(vnode, cbi)) {
vnode->cb_version = ntohl(*bp++);
cb_expiry = ntohl(*bp++);
vnode->cb_type = ntohl(*bp++);
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 06194cf..479b7fd 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -108,7 +108,7 @@ int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool new_inode)
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_fetch_file_status(&fc, NULL, new_inode);
}
@@ -393,15 +393,18 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
read_seqlock_excl(&vnode->cb_lock);
if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
- if (vnode->cb_s_break != vnode->cb_interest->server->cb_s_break) {
+ if (vnode->cb_s_break != vnode->cb_interest->server->cb_s_break ||
+ vnode->cb_v_break != vnode->volume->cb_v_break) {
vnode->cb_s_break = vnode->cb_interest->server->cb_s_break;
+ vnode->cb_v_break = vnode->volume->cb_v_break;
+ valid = false;
} else if (vnode->status.type == AFS_FTYPE_DIR &&
test_bit(AFS_VNODE_DIR_VALID, &vnode->flags) &&
vnode->cb_expires_at - 10 > now) {
- valid = true;
+ valid = true;
} else if (!test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags) &&
vnode->cb_expires_at - 10 > now) {
- valid = true;
+ valid = true;
}
} else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
valid = true;
@@ -415,7 +418,7 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
if (valid)
goto valid;
- mutex_lock(&vnode->validate_lock);
+ down_write(&vnode->validate_lock);
/* if the promise has expired, we need to check the server again to get
* a new promise - note that if the (parent) directory's metadata was
@@ -444,13 +447,13 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
* different */
if (test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags))
afs_zap_data(vnode);
- mutex_unlock(&vnode->validate_lock);
+ up_write(&vnode->validate_lock);
valid:
_leave(" = 0");
return 0;
error_unlock:
- mutex_unlock(&vnode->validate_lock);
+ up_write(&vnode->validate_lock);
_leave(" = %d", ret);
return ret;
}
@@ -574,7 +577,7 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr)
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_setattr(&fc, attr);
}
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index f8086ec..e3f8a46 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -396,6 +396,7 @@ struct afs_server {
#define AFS_SERVER_FL_PROBED 5 /* The fileserver has been probed */
#define AFS_SERVER_FL_PROBING 6 /* Fileserver is being probed */
#define AFS_SERVER_FL_NO_IBULK 7 /* Fileserver doesn't support FS.InlineBulkStatus */
+#define AFS_SERVER_FL_MAY_HAVE_CB 8 /* May have callbacks on this fileserver */
atomic_t usage;
u32 addr_version; /* Address list version */
@@ -433,6 +434,7 @@ struct afs_server_list {
unsigned short index; /* Server currently in use */
unsigned short vnovol_mask; /* Servers to be skipped due to VNOVOL */
unsigned int seq; /* Set to ->servers_seq when installed */
+ rwlock_t lock;
struct afs_server_entry servers[];
};
@@ -459,6 +461,9 @@ struct afs_volume {
rwlock_t servers_lock; /* Lock for ->servers */
unsigned int servers_seq; /* Incremented each time ->servers changes */
+ unsigned cb_v_break; /* Break-everything counter. */
+ rwlock_t cb_break_lock;
+
afs_voltype_t type; /* type of volume */
short error;
char type_force; /* force volume type (suppress R/O -> R/W) */
@@ -494,7 +499,7 @@ struct afs_vnode {
#endif
struct afs_permits __rcu *permit_cache; /* cache of permits so far obtained */
struct mutex io_lock; /* Lock for serialising I/O on this mutex */
- struct mutex validate_lock; /* lock for validating this vnode */
+ struct rw_semaphore validate_lock; /* lock for validating this vnode */
spinlock_t wb_lock; /* lock for wb_keys */
spinlock_t lock; /* waitqueue/flags lock */
unsigned long flags;
@@ -519,6 +524,7 @@ struct afs_vnode {
/* outstanding callback notification on this file */
struct afs_cb_interest *cb_interest; /* Server on which this resides */
unsigned int cb_s_break; /* Mass break counter on ->server */
+ unsigned int cb_v_break; /* Mass break counter on ->volume */
unsigned int cb_break; /* Break counter on vnode */
seqlock_t cb_lock; /* Lock for ->cb_interest, ->status, ->cb_*break */
@@ -648,16 +654,29 @@ extern void afs_init_callback_state(struct afs_server *);
extern void afs_break_callback(struct afs_vnode *);
extern void afs_break_callbacks(struct afs_server *, size_t, struct afs_callback_break*);
-extern int afs_register_server_cb_interest(struct afs_vnode *, struct afs_server_entry *);
+extern int afs_register_server_cb_interest(struct afs_vnode *,
+ struct afs_server_list *, unsigned int);
extern void afs_put_cb_interest(struct afs_net *, struct afs_cb_interest *);
extern void afs_clear_callback_interests(struct afs_net *, struct afs_server_list *);
static inline struct afs_cb_interest *afs_get_cb_interest(struct afs_cb_interest *cbi)
{
- refcount_inc(&cbi->usage);
+ if (cbi)
+ refcount_inc(&cbi->usage);
return cbi;
}
+static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode)
+{
+ return vnode->cb_break + vnode->cb_s_break + vnode->cb_v_break;
+}
+
+static inline unsigned int afs_cb_break_sum(struct afs_vnode *vnode,
+ struct afs_cb_interest *cbi)
+{
+ return vnode->cb_break + cbi->server->cb_s_break + vnode->volume->cb_v_break;
+}
+
/*
* cell.c
*/
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index 839a222..3aad327 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -62,7 +62,6 @@ static const struct file_operations afs_proc_rootcell_fops = {
.llseek = no_llseek,
};
-static int afs_proc_cell_volumes_open(struct inode *inode, struct file *file);
static void *afs_proc_cell_volumes_start(struct seq_file *p, loff_t *pos);
static void *afs_proc_cell_volumes_next(struct seq_file *p, void *v,
loff_t *pos);
@@ -76,15 +75,6 @@ static const struct seq_operations afs_proc_cell_volumes_ops = {
.show = afs_proc_cell_volumes_show,
};
-static const struct file_operations afs_proc_cell_volumes_fops = {
- .open = afs_proc_cell_volumes_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-static int afs_proc_cell_vlservers_open(struct inode *inode,
- struct file *file);
static void *afs_proc_cell_vlservers_start(struct seq_file *p, loff_t *pos);
static void *afs_proc_cell_vlservers_next(struct seq_file *p, void *v,
loff_t *pos);
@@ -98,14 +88,6 @@ static const struct seq_operations afs_proc_cell_vlservers_ops = {
.show = afs_proc_cell_vlservers_show,
};
-static const struct file_operations afs_proc_cell_vlservers_fops = {
- .open = afs_proc_cell_vlservers_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-static int afs_proc_servers_open(struct inode *inode, struct file *file);
static void *afs_proc_servers_start(struct seq_file *p, loff_t *pos);
static void *afs_proc_servers_next(struct seq_file *p, void *v,
loff_t *pos);
@@ -119,13 +101,6 @@ static const struct seq_operations afs_proc_servers_ops = {
.show = afs_proc_servers_show,
};
-static const struct file_operations afs_proc_servers_fops = {
- .open = afs_proc_servers_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static int afs_proc_sysname_open(struct inode *inode, struct file *file);
static int afs_proc_sysname_release(struct inode *inode, struct file *file);
static void *afs_proc_sysname_start(struct seq_file *p, loff_t *pos);
@@ -152,7 +127,7 @@ static const struct file_operations afs_proc_sysname_fops = {
.write = afs_proc_sysname_write,
};
-static const struct file_operations afs_proc_stats_fops;
+static int afs_proc_stats_show(struct seq_file *m, void *v);
/*
* initialise the /proc/fs/afs/ directory
@@ -167,8 +142,8 @@ int afs_proc_init(struct afs_net *net)
if (!proc_create("cells", 0644, net->proc_afs, &afs_proc_cells_fops) ||
!proc_create("rootcell", 0644, net->proc_afs, &afs_proc_rootcell_fops) ||
- !proc_create("servers", 0644, net->proc_afs, &afs_proc_servers_fops) ||
- !proc_create("stats", 0644, net->proc_afs, &afs_proc_stats_fops) ||
+ !proc_create_seq("servers", 0644, net->proc_afs, &afs_proc_servers_ops) ||
+ !proc_create_single("stats", 0644, net->proc_afs, afs_proc_stats_show) ||
!proc_create("sysname", 0644, net->proc_afs, &afs_proc_sysname_fops))
goto error_tree;
@@ -196,16 +171,7 @@ void afs_proc_cleanup(struct afs_net *net)
*/
static int afs_proc_cells_open(struct inode *inode, struct file *file)
{
- struct seq_file *m;
- int ret;
-
- ret = seq_open(file, &afs_proc_cells_ops);
- if (ret < 0)
- return ret;
-
- m = file->private_data;
- m->private = PDE_DATA(inode);
- return 0;
+ return seq_open(file, &afs_proc_cells_ops);
}
/*
@@ -430,10 +396,11 @@ int afs_proc_cell_setup(struct afs_net *net, struct afs_cell *cell)
if (!dir)
goto error_dir;
- if (!proc_create_data("vlservers", 0, dir,
- &afs_proc_cell_vlservers_fops, cell) ||
- !proc_create_data("volumes", 0, dir,
- &afs_proc_cell_volumes_fops, cell))
+ if (!proc_create_seq_data("vlservers", 0, dir,
+ &afs_proc_cell_vlservers_ops, cell))
+ goto error_tree;
+ if (!proc_create_seq_data("volumes", 0, dir, &afs_proc_cell_volumes_ops,
+ cell))
goto error_tree;
_leave(" = 0");
@@ -459,36 +426,13 @@ void afs_proc_cell_remove(struct afs_net *net, struct afs_cell *cell)
}
/*
- * open "/proc/fs/afs/<cell>/volumes" which provides a summary of extant cells
- */
-static int afs_proc_cell_volumes_open(struct inode *inode, struct file *file)
-{
- struct afs_cell *cell;
- struct seq_file *m;
- int ret;
-
- cell = PDE_DATA(inode);
- if (!cell)
- return -ENOENT;
-
- ret = seq_open(file, &afs_proc_cell_volumes_ops);
- if (ret < 0)
- return ret;
-
- m = file->private_data;
- m->private = cell;
-
- return 0;
-}
-
-/*
* set up the iterator to start reading from the cells list and return the
* first item
*/
static void *afs_proc_cell_volumes_start(struct seq_file *m, loff_t *_pos)
__acquires(cell->proc_lock)
{
- struct afs_cell *cell = m->private;
+ struct afs_cell *cell = PDE_DATA(file_inode(m->file));
_enter("cell=%p pos=%Ld", cell, *_pos);
@@ -502,7 +446,7 @@ static void *afs_proc_cell_volumes_start(struct seq_file *m, loff_t *_pos)
static void *afs_proc_cell_volumes_next(struct seq_file *p, void *v,
loff_t *_pos)
{
- struct afs_cell *cell = p->private;
+ struct afs_cell *cell = PDE_DATA(file_inode(p->file));
_enter("cell=%p pos=%Ld", cell, *_pos);
return seq_list_next(v, &cell->proc_volumes, _pos);
@@ -514,7 +458,7 @@ static void *afs_proc_cell_volumes_next(struct seq_file *p, void *v,
static void afs_proc_cell_volumes_stop(struct seq_file *p, void *v)
__releases(cell->proc_lock)
{
- struct afs_cell *cell = p->private;
+ struct afs_cell *cell = PDE_DATA(file_inode(p->file));
read_unlock(&cell->proc_lock);
}
@@ -530,7 +474,7 @@ static const char afs_vol_types[3][3] = {
*/
static int afs_proc_cell_volumes_show(struct seq_file *m, void *v)
{
- struct afs_cell *cell = m->private;
+ struct afs_cell *cell = PDE_DATA(file_inode(m->file));
struct afs_volume *vol = list_entry(v, struct afs_volume, proc_link);
/* Display header on line 1 */
@@ -547,30 +491,6 @@ static int afs_proc_cell_volumes_show(struct seq_file *m, void *v)
}
/*
- * open "/proc/fs/afs/<cell>/vlservers" which provides a list of volume
- * location server
- */
-static int afs_proc_cell_vlservers_open(struct inode *inode, struct file *file)
-{
- struct afs_cell *cell;
- struct seq_file *m;
- int ret;
-
- cell = PDE_DATA(inode);
- if (!cell)
- return -ENOENT;
-
- ret = seq_open(file, &afs_proc_cell_vlservers_ops);
- if (ret<0)
- return ret;
-
- m = file->private_data;
- m->private = cell;
-
- return 0;
-}
-
-/*
* set up the iterator to start reading from the cells list and return the
* first item
*/
@@ -578,7 +498,7 @@ static void *afs_proc_cell_vlservers_start(struct seq_file *m, loff_t *_pos)
__acquires(rcu)
{
struct afs_addr_list *alist;
- struct afs_cell *cell = m->private;
+ struct afs_cell *cell = PDE_DATA(file_inode(m->file));
loff_t pos = *_pos;
rcu_read_lock();
@@ -603,7 +523,7 @@ static void *afs_proc_cell_vlservers_next(struct seq_file *p, void *v,
loff_t *_pos)
{
struct afs_addr_list *alist;
- struct afs_cell *cell = p->private;
+ struct afs_cell *cell = PDE_DATA(file_inode(p->file));
loff_t pos;
alist = rcu_dereference(cell->vl_addrs);
@@ -644,15 +564,6 @@ static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v)
}
/*
- * open "/proc/fs/afs/servers" which provides a summary of active
- * servers
- */
-static int afs_proc_servers_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &afs_proc_servers_ops);
-}
-
-/*
* Set up the iterator to start reading from the server list and return the
* first item.
*/
@@ -931,18 +842,3 @@ static int afs_proc_stats_show(struct seq_file *m, void *v)
atomic_long_read(&net->n_store_bytes));
return 0;
}
-
-/*
- * Open "/proc/fs/afs/stats" to allow reading of the stat counters.
- */
-static int afs_proc_stats_open(struct inode *inode, struct file *file)
-{
- return single_open(file, afs_proc_stats_show, NULL);
-}
-
-static const struct file_operations afs_proc_stats_fops = {
- .open = afs_proc_stats_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index ac0feac..e065bc0 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -179,7 +179,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
*/
if (fc->flags & AFS_FS_CURSOR_VNOVOL) {
fc->ac.error = -EREMOTEIO;
- goto failed;
+ goto next_server;
}
write_lock(&vnode->volume->servers_lock);
@@ -201,7 +201,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
*/
if (vnode->volume->servers == fc->server_list) {
fc->ac.error = -EREMOTEIO;
- goto failed;
+ goto next_server;
}
/* Try again */
@@ -350,8 +350,8 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
* break request before we've finished decoding the reply and
* installing the vnode.
*/
- fc->ac.error = afs_register_server_cb_interest(
- vnode, &fc->server_list->servers[fc->index]);
+ fc->ac.error = afs_register_server_cb_interest(vnode, fc->server_list,
+ fc->index);
if (fc->ac.error < 0)
goto failed;
@@ -369,8 +369,16 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
if (!test_bit(AFS_SERVER_FL_PROBED, &server->flags)) {
fc->ac.alist = afs_get_addrlist(alist);
- if (!afs_probe_fileserver(fc))
- goto failed;
+ if (!afs_probe_fileserver(fc)) {
+ switch (fc->ac.error) {
+ case -ENOMEM:
+ case -ERESTARTSYS:
+ case -EINTR:
+ goto failed;
+ default:
+ goto next_server;
+ }
+ }
}
if (!fc->ac.alist)
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 5c62639..0873594 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -41,6 +41,7 @@ int afs_open_socket(struct afs_net *net)
{
struct sockaddr_rxrpc srx;
struct socket *socket;
+ unsigned int min_level;
int ret;
_enter("");
@@ -60,6 +61,12 @@ int afs_open_socket(struct afs_net *net)
srx.transport.sin6.sin6_family = AF_INET6;
srx.transport.sin6.sin6_port = htons(AFS_CM_PORT);
+ min_level = RXRPC_SECURITY_ENCRYPT;
+ ret = kernel_setsockopt(socket, SOL_RXRPC, RXRPC_MIN_SECURITY_LEVEL,
+ (void *)&min_level, sizeof(min_level));
+ if (ret < 0)
+ goto error_2;
+
ret = kernel_bind(socket, (struct sockaddr *) &srx, sizeof(srx));
if (ret == -EADDRINUSE) {
srx.transport.sin6.sin6_port = 0;
@@ -482,8 +489,12 @@ static void afs_deliver_to_call(struct afs_call *call)
state = READ_ONCE(call->state);
switch (ret) {
case 0:
- if (state == AFS_CALL_CL_PROC_REPLY)
+ if (state == AFS_CALL_CL_PROC_REPLY) {
+ if (call->cbi)
+ set_bit(AFS_SERVER_FL_MAY_HAVE_CB,
+ &call->cbi->server->flags);
goto call_complete;
+ }
ASSERTCMP(state, >, AFS_CALL_CL_PROC_REPLY);
goto done;
case -EINPROGRESS:
@@ -493,11 +504,6 @@ static void afs_deliver_to_call(struct afs_call *call)
case -ECONNABORTED:
ASSERTCMP(state, ==, AFS_CALL_COMPLETE);
goto done;
- case -ENOTCONN:
- abort_code = RX_CALL_DEAD;
- rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
- abort_code, ret, "KNC");
- goto local_abort;
case -ENOTSUPP:
abort_code = RXGEN_OPCODE;
rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
diff --git a/fs/afs/security.c b/fs/afs/security.c
index cea2fff..81dfedb 100644
--- a/fs/afs/security.c
+++ b/fs/afs/security.c
@@ -147,8 +147,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key,
break;
}
- if (cb_break != (vnode->cb_break +
- vnode->cb_interest->server->cb_s_break)) {
+ if (cb_break != afs_cb_break_sum(vnode, vnode->cb_interest)) {
changed = true;
break;
}
@@ -178,7 +177,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key,
}
}
- if (cb_break != (vnode->cb_break + vnode->cb_interest->server->cb_s_break))
+ if (cb_break != afs_cb_break_sum(vnode, vnode->cb_interest))
goto someone_else_changed_it;
/* We need a ref on any permits list we want to copy as we'll have to
@@ -257,7 +256,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key,
spin_lock(&vnode->lock);
zap = rcu_access_pointer(vnode->permit_cache);
- if (cb_break == (vnode->cb_break + vnode->cb_interest->server->cb_s_break) &&
+ if (cb_break == afs_cb_break_sum(vnode, vnode->cb_interest) &&
zap == permits)
rcu_assign_pointer(vnode->permit_cache, replacement);
else
@@ -373,18 +372,14 @@ int afs_permission(struct inode *inode, int mask)
mask, access, S_ISDIR(inode->i_mode) ? "dir" : "file");
if (S_ISDIR(inode->i_mode)) {
- if (mask & MAY_EXEC) {
+ if (mask & (MAY_EXEC | MAY_READ | MAY_CHDIR)) {
if (!(access & AFS_ACE_LOOKUP))
goto permission_denied;
- } else if (mask & MAY_READ) {
- if (!(access & AFS_ACE_LOOKUP))
- goto permission_denied;
- } else if (mask & MAY_WRITE) {
+ }
+ if (mask & MAY_WRITE) {
if (!(access & (AFS_ACE_DELETE | /* rmdir, unlink, rename from */
AFS_ACE_INSERT))) /* create, mkdir, symlink, rename to */
goto permission_denied;
- } else {
- BUG();
}
} else {
if (!(access & AFS_ACE_LOOKUP))
diff --git a/fs/afs/server.c b/fs/afs/server.c
index e23be63..3af4625 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -67,12 +67,6 @@ struct afs_server *afs_find_server(struct afs_net *net,
sizeof(struct in6_addr));
if (diff == 0)
goto found;
- if (diff < 0) {
- // TODO: Sort the list
- //if (i == alist->nr_ipv4)
- // goto not_found;
- break;
- }
}
}
} else {
@@ -87,17 +81,10 @@ struct afs_server *afs_find_server(struct afs_net *net,
(u32 __force)b->sin6_addr.s6_addr32[3]);
if (diff == 0)
goto found;
- if (diff < 0) {
- // TODO: Sort the list
- //if (i == 0)
- // goto not_found;
- break;
- }
}
}
}
- //not_found:
server = NULL;
found:
if (server && !atomic_inc_not_zero(&server->usage))
@@ -395,14 +382,16 @@ static void afs_destroy_server(struct afs_net *net, struct afs_server *server)
struct afs_addr_list *alist = rcu_access_pointer(server->addresses);
struct afs_addr_cursor ac = {
.alist = alist,
- .addr = &alist->addrs[0],
.start = alist->index,
- .index = alist->index,
+ .index = 0,
+ .addr = &alist->addrs[alist->index],
.error = 0,
};
_enter("%p", server);
- afs_fs_give_up_all_callbacks(net, server, &ac, NULL);
+ if (test_bit(AFS_SERVER_FL_MAY_HAVE_CB, &server->flags))
+ afs_fs_give_up_all_callbacks(net, server, &ac, NULL);
+
call_rcu(&server->rcu, afs_server_rcu);
afs_dec_servers_outstanding(net);
}
@@ -428,8 +417,15 @@ static void afs_gc_servers(struct afs_net *net, struct afs_server *gc_list)
}
write_sequnlock(&net->fs_lock);
- if (deleted)
+ if (deleted) {
+ write_seqlock(&net->fs_addr_lock);
+ if (!hlist_unhashed(&server->addr4_link))
+ hlist_del_rcu(&server->addr4_link);
+ if (!hlist_unhashed(&server->addr6_link))
+ hlist_del_rcu(&server->addr6_link);
+ write_sequnlock(&net->fs_addr_lock);
afs_destroy_server(net, server);
+ }
}
}
diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c
index 0f8dc4c..8a5760a 100644
--- a/fs/afs/server_list.c
+++ b/fs/afs/server_list.c
@@ -49,6 +49,7 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell,
goto error;
refcount_set(&slist->usage, 1);
+ rwlock_init(&slist->lock);
/* Make sure a records exists for each server in the list. */
for (i = 0; i < vldb->nr_servers; i++) {
@@ -64,9 +65,11 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell,
goto error_2;
}
- /* Insertion-sort by server pointer */
+ /* Insertion-sort by UUID */
for (j = 0; j < slist->nr_servers; j++)
- if (slist->servers[j].server >= server)
+ if (memcmp(&slist->servers[j].server->uuid,
+ &server->uuid,
+ sizeof(server->uuid)) >= 0)
break;
if (j < slist->nr_servers) {
if (slist->servers[j].server == server) {
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 65081ec..9e5d796 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -590,7 +590,7 @@ static void afs_i_init_once(void *_vnode)
memset(vnode, 0, sizeof(*vnode));
inode_init_once(&vnode->vfs_inode);
mutex_init(&vnode->io_lock);
- mutex_init(&vnode->validate_lock);
+ init_rwsem(&vnode->validate_lock);
spin_lock_init(&vnode->wb_lock);
spin_lock_init(&vnode->lock);
INIT_LIST_HEAD(&vnode->wb_keys);
@@ -688,7 +688,7 @@ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf)
if (afs_begin_vnode_operation(&fc, vnode, key)) {
fc.flags |= AFS_FS_CURSOR_NO_VSLEEP;
while (afs_select_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_get_volume_status(&fc, &vs);
}
diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c
index 1ed7e2f..c3b7408 100644
--- a/fs/afs/vlclient.c
+++ b/fs/afs/vlclient.c
@@ -23,7 +23,7 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
struct afs_uvldbentry__xdr *uvldb;
struct afs_vldb_entry *entry;
bool new_only = false;
- u32 tmp, nr_servers;
+ u32 tmp, nr_servers, vlflags;
int i, ret;
_enter("");
@@ -55,6 +55,7 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
new_only = true;
}
+ vlflags = ntohl(uvldb->flags);
for (i = 0; i < nr_servers; i++) {
struct afs_uuid__xdr *xdr;
struct afs_uuid *uuid;
@@ -64,12 +65,13 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
if (tmp & AFS_VLSF_DONTUSE ||
(new_only && !(tmp & AFS_VLSF_NEWREPSITE)))
continue;
- if (tmp & AFS_VLSF_RWVOL)
+ if (tmp & AFS_VLSF_RWVOL) {
entry->fs_mask[i] |= AFS_VOL_VTM_RW;
+ if (vlflags & AFS_VLF_BACKEXISTS)
+ entry->fs_mask[i] |= AFS_VOL_VTM_BAK;
+ }
if (tmp & AFS_VLSF_ROVOL)
entry->fs_mask[i] |= AFS_VOL_VTM_RO;
- if (tmp & AFS_VLSF_BACKVOL)
- entry->fs_mask[i] |= AFS_VOL_VTM_BAK;
if (!entry->fs_mask[i])
continue;
@@ -89,15 +91,14 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
for (i = 0; i < AFS_MAXTYPES; i++)
entry->vid[i] = ntohl(uvldb->volumeId[i]);
- tmp = ntohl(uvldb->flags);
- if (tmp & AFS_VLF_RWEXISTS)
+ if (vlflags & AFS_VLF_RWEXISTS)
__set_bit(AFS_VLDB_HAS_RW, &entry->flags);
- if (tmp & AFS_VLF_ROEXISTS)
+ if (vlflags & AFS_VLF_ROEXISTS)
__set_bit(AFS_VLDB_HAS_RO, &entry->flags);
- if (tmp & AFS_VLF_BACKEXISTS)
+ if (vlflags & AFS_VLF_BACKEXISTS)
__set_bit(AFS_VLDB_HAS_BAK, &entry->flags);
- if (!(tmp & (AFS_VLF_RWEXISTS | AFS_VLF_ROEXISTS | AFS_VLF_BACKEXISTS))) {
+ if (!(vlflags & (AFS_VLF_RWEXISTS | AFS_VLF_ROEXISTS | AFS_VLF_BACKEXISTS))) {
entry->error = -ENOMEDIUM;
__set_bit(AFS_VLDB_QUERY_ERROR, &entry->flags);
}
diff --git a/fs/afs/write.c b/fs/afs/write.c
index c164698..8b39e6e 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -351,7 +351,7 @@ static int afs_store_data(struct address_space *mapping,
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, wbk->key)) {
while (afs_select_fileserver(&fc)) {
- fc.cb_break = vnode->cb_break + vnode->cb_s_break;
+ fc.cb_break = afs_calc_vnode_cb_break(vnode);
afs_fs_store_data(&fc, mapping, first, last, offset, to);
}
diff --git a/fs/aio.c b/fs/aio.c
index 88d7927..b850e92 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -5,6 +5,7 @@
* Implements an efficient asynchronous io interface.
*
* Copyright 2000, 2001, 2002 Red Hat, Inc. All Rights Reserved.
+ * Copyright 2018 Christoph Hellwig.
*
* See ../COPYING for licensing terms.
*/
@@ -46,6 +47,8 @@
#include "internal.h"
+#define KIOCB_KEY 0
+
#define AIO_RING_MAGIC 0xa10a10a1
#define AIO_RING_COMPAT_FEATURES 1
#define AIO_RING_INCOMPAT_FEATURES 0
@@ -156,21 +159,29 @@ struct kioctx {
unsigned id;
};
-/*
- * We use ki_cancel == KIOCB_CANCELLED to indicate that a kiocb has been either
- * cancelled or completed (this makes a certain amount of sense because
- * successful cancellation - io_cancel() - does deliver the completion to
- * userspace).
- *
- * And since most things don't implement kiocb cancellation and we'd really like
- * kiocb completion to be lockless when possible, we use ki_cancel to
- * synchronize cancellation and completion - we only set it to KIOCB_CANCELLED
- * with xchg() or cmpxchg(), see batch_complete_aio() and kiocb_cancel().
- */
-#define KIOCB_CANCELLED ((void *) (~0ULL))
+struct fsync_iocb {
+ struct work_struct work;
+ struct file *file;
+ bool datasync;
+};
+
+struct poll_iocb {
+ struct file *file;
+ __poll_t events;
+ struct wait_queue_head *head;
+
+ union {
+ struct wait_queue_entry wait;
+ struct work_struct work;
+ };
+};
struct aio_kiocb {
- struct kiocb common;
+ union {
+ struct kiocb rw;
+ struct fsync_iocb fsync;
+ struct poll_iocb poll;
+ };
struct kioctx *ki_ctx;
kiocb_cancel_fn *ki_cancel;
@@ -264,9 +275,6 @@ static int __init aio_setup(void)
kiocb_cachep = KMEM_CACHE(aio_kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
-
- pr_debug("sizeof(struct page) = %zu\n", sizeof(struct page));
-
return 0;
}
__initcall(aio_setup);
@@ -552,42 +560,20 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events)
void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
{
- struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, common);
+ struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw);
struct kioctx *ctx = req->ki_ctx;
unsigned long flags;
+ if (WARN_ON_ONCE(!list_empty(&req->ki_list)))
+ return;
+
spin_lock_irqsave(&ctx->ctx_lock, flags);
-
- if (!req->ki_list.next)
- list_add(&req->ki_list, &ctx->active_reqs);
-
+ list_add_tail(&req->ki_list, &ctx->active_reqs);
req->ki_cancel = cancel;
-
spin_unlock_irqrestore(&ctx->ctx_lock, flags);
}
EXPORT_SYMBOL(kiocb_set_cancel_fn);
-static int kiocb_cancel(struct aio_kiocb *kiocb)
-{
- kiocb_cancel_fn *old, *cancel;
-
- /*
- * Don't want to set kiocb->ki_cancel = KIOCB_CANCELLED unless it
- * actually has a cancel function, hence the cmpxchg()
- */
-
- cancel = READ_ONCE(kiocb->ki_cancel);
- do {
- if (!cancel || cancel == KIOCB_CANCELLED)
- return -EINVAL;
-
- old = cancel;
- cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED);
- } while (cancel != old);
-
- return cancel(&kiocb->common);
-}
-
/*
* free_ioctx() should be RCU delayed to synchronize against the RCU
* protected lookup_ioctx() and also needs process context to call
@@ -634,9 +620,8 @@ static void free_ioctx_users(struct percpu_ref *ref)
while (!list_empty(&ctx->active_reqs)) {
req = list_first_entry(&ctx->active_reqs,
struct aio_kiocb, ki_list);
-
+ req->ki_cancel(&req->rw);
list_del_init(&req->ki_list);
- kiocb_cancel(req);
}
spin_unlock_irq(&ctx->ctx_lock);
@@ -1042,7 +1027,7 @@ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
goto out_put;
percpu_ref_get(&ctx->reqs);
-
+ INIT_LIST_HEAD(&req->ki_list);
req->ki_ctx = ctx;
return req;
out_put:
@@ -1050,15 +1035,6 @@ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
return NULL;
}
-static void kiocb_free(struct aio_kiocb *req)
-{
- if (req->common.ki_filp)
- fput(req->common.ki_filp);
- if (req->ki_eventfd != NULL)
- eventfd_ctx_put(req->ki_eventfd);
- kmem_cache_free(kiocb_cachep, req);
-}
-
static struct kioctx *lookup_ioctx(unsigned long ctx_id)
{
struct aio_ring __user *ring = (void __user *)ctx_id;
@@ -1078,8 +1054,8 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
ctx = rcu_dereference(table->table[id]);
if (ctx && ctx->user_id == ctx_id) {
- percpu_ref_get(&ctx->users);
- ret = ctx;
+ if (percpu_ref_tryget_live(&ctx->users))
+ ret = ctx;
}
out:
rcu_read_unlock();
@@ -1089,44 +1065,14 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
/* aio_complete
* Called when the io request on the given iocb is complete.
*/
-static void aio_complete(struct kiocb *kiocb, long res, long res2)
+static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
{
- struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, common);
struct kioctx *ctx = iocb->ki_ctx;
struct aio_ring *ring;
struct io_event *ev_page, *event;
unsigned tail, pos, head;
unsigned long flags;
- if (kiocb->ki_flags & IOCB_WRITE) {
- struct file *file = kiocb->ki_filp;
-
- /*
- * Tell lockdep we inherited freeze protection from submission
- * thread.
- */
- if (S_ISREG(file_inode(file)->i_mode))
- __sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE);
- file_end_write(file);
- }
-
- /*
- * Special case handling for sync iocbs:
- * - events go directly into the iocb for fast handling
- * - the sync task with the iocb in its stack holds the single iocb
- * ref, no other paths have a way to get another ref
- * - the sync task helpfully left a reference to itself in the iocb
- */
- BUG_ON(is_sync_kiocb(kiocb));
-
- if (iocb->ki_list.next) {
- unsigned long flags;
-
- spin_lock_irqsave(&ctx->ctx_lock, flags);
- list_del(&iocb->ki_list);
- spin_unlock_irqrestore(&ctx->ctx_lock, flags);
- }
-
/*
* Add a completion event to the ring buffer. Must be done holding
* ctx->completion_lock to prevent other code from messing with the tail
@@ -1180,11 +1126,12 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2)
* eventfd. The eventfd_signal() function is safe to be called
* from IRQ context.
*/
- if (iocb->ki_eventfd != NULL)
+ if (iocb->ki_eventfd) {
eventfd_signal(iocb->ki_eventfd, 1);
+ eventfd_ctx_put(iocb->ki_eventfd);
+ }
- /* everything turned out well, dispose of the aiocb. */
- kiocb_free(iocb);
+ kmem_cache_free(kiocb_cachep, iocb);
/*
* We have to order our ring_info tail store above and test
@@ -1250,14 +1197,13 @@ static long aio_read_events_ring(struct kioctx *ctx,
if (head == tail)
break;
- avail = min(avail, nr - ret);
- avail = min_t(long, avail, AIO_EVENTS_PER_PAGE -
- ((head + AIO_EVENTS_OFFSET) % AIO_EVENTS_PER_PAGE));
-
pos = head + AIO_EVENTS_OFFSET;
page = ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE];
pos %= AIO_EVENTS_PER_PAGE;
+ avail = min(avail, nr - ret);
+ avail = min_t(long, avail, AIO_EVENTS_PER_PAGE - pos);
+
ev = kmap(page);
copy_ret = copy_to_user(event + ret, ev + pos,
sizeof(*ev) * avail);
@@ -1328,10 +1274,6 @@ static long read_events(struct kioctx *ctx, long min_nr, long nr,
wait_event_interruptible_hrtimeout(ctx->wait,
aio_read_events(ctx, min_nr, nr, event, &ret),
until);
-
- if (!ret && signal_pending(current))
- ret = -EINTR;
-
return ret;
}
@@ -1447,6 +1389,58 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
return -EINVAL;
}
+static void aio_remove_iocb(struct aio_kiocb *iocb)
+{
+ struct kioctx *ctx = iocb->ki_ctx;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ctx->ctx_lock, flags);
+ list_del(&iocb->ki_list);
+ spin_unlock_irqrestore(&ctx->ctx_lock, flags);
+}
+
+static void aio_complete_rw(struct kiocb *kiocb, long res, long res2)
+{
+ struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, rw);
+
+ if (!list_empty_careful(&iocb->ki_list))
+ aio_remove_iocb(iocb);
+
+ if (kiocb->ki_flags & IOCB_WRITE) {
+ struct inode *inode = file_inode(kiocb->ki_filp);
+
+ /*
+ * Tell lockdep we inherited freeze protection from submission
+ * thread.
+ */
+ if (S_ISREG(inode->i_mode))
+ __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
+ file_end_write(kiocb->ki_filp);
+ }
+
+ fput(kiocb->ki_filp);
+ aio_complete(iocb, res, res2);
+}
+
+static int aio_prep_rw(struct kiocb *req, struct iocb *iocb)
+{
+ int ret;
+
+ req->ki_filp = fget(iocb->aio_fildes);
+ if (unlikely(!req->ki_filp))
+ return -EBADF;
+ req->ki_complete = aio_complete_rw;
+ req->ki_pos = iocb->aio_offset;
+ req->ki_flags = iocb_flags(req->ki_filp);
+ if (iocb->aio_flags & IOCB_FLAG_RESFD)
+ req->ki_flags |= IOCB_EVENTFD;
+ req->ki_hint = file_write_hint(req->ki_filp);
+ ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags);
+ if (unlikely(ret))
+ fput(req->ki_filp);
+ return ret;
+}
+
static int aio_setup_rw(int rw, struct iocb *iocb, struct iovec **iovec,
bool vectored, bool compat, struct iov_iter *iter)
{
@@ -1466,11 +1460,11 @@ static int aio_setup_rw(int rw, struct iocb *iocb, struct iovec **iovec,
return import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter);
}
-static inline ssize_t aio_ret(struct kiocb *req, ssize_t ret)
+static inline void aio_rw_done(struct kiocb *req, ssize_t ret)
{
switch (ret) {
case -EIOCBQUEUED:
- return ret;
+ break;
case -ERESTARTSYS:
case -ERESTARTNOINTR:
case -ERESTARTNOHAND:
@@ -1482,85 +1476,270 @@ static inline ssize_t aio_ret(struct kiocb *req, ssize_t ret)
ret = -EINTR;
/*FALLTHRU*/
default:
- aio_complete(req, ret, 0);
- return 0;
+ aio_complete_rw(req, ret, 0);
}
}
static ssize_t aio_read(struct kiocb *req, struct iocb *iocb, bool vectored,
bool compat)
{
- struct file *file = req->ki_filp;
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct iov_iter iter;
+ struct file *file;
ssize_t ret;
+ ret = aio_prep_rw(req, iocb);
+ if (ret)
+ return ret;
+ file = req->ki_filp;
+
+ ret = -EBADF;
if (unlikely(!(file->f_mode & FMODE_READ)))
- return -EBADF;
+ goto out_fput;
+ ret = -EINVAL;
if (unlikely(!file->f_op->read_iter))
- return -EINVAL;
+ goto out_fput;
ret = aio_setup_rw(READ, iocb, &iovec, vectored, compat, &iter);
if (ret)
- return ret;
+ goto out_fput;
ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter));
if (!ret)
- ret = aio_ret(req, call_read_iter(file, req, &iter));
+ aio_rw_done(req, call_read_iter(file, req, &iter));
kfree(iovec);
+out_fput:
+ if (unlikely(ret))
+ fput(file);
return ret;
}
static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
bool compat)
{
- struct file *file = req->ki_filp;
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct iov_iter iter;
- ssize_t ret;
-
- if (unlikely(!(file->f_mode & FMODE_WRITE)))
- return -EBADF;
- if (unlikely(!file->f_op->write_iter))
- return -EINVAL;
-
- ret = aio_setup_rw(WRITE, iocb, &iovec, vectored, compat, &iter);
- if (ret)
- return ret;
- ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter));
- if (!ret) {
- req->ki_flags |= IOCB_WRITE;
- file_start_write(file);
- ret = aio_ret(req, call_write_iter(file, req, &iter));
- /*
- * We release freeze protection in aio_complete(). Fool lockdep
- * by telling it the lock got released so that it doesn't
- * complain about held lock when we return to userspace.
- */
- if (S_ISREG(file_inode(file)->i_mode))
- __sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
- }
- kfree(iovec);
- return ret;
-}
-
-static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
- struct iocb *iocb, bool compat)
-{
- struct aio_kiocb *req;
struct file *file;
ssize_t ret;
+ ret = aio_prep_rw(req, iocb);
+ if (ret)
+ return ret;
+ file = req->ki_filp;
+
+ ret = -EBADF;
+ if (unlikely(!(file->f_mode & FMODE_WRITE)))
+ goto out_fput;
+ ret = -EINVAL;
+ if (unlikely(!file->f_op->write_iter))
+ goto out_fput;
+
+ ret = aio_setup_rw(WRITE, iocb, &iovec, vectored, compat, &iter);
+ if (ret)
+ goto out_fput;
+ ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter));
+ if (!ret) {
+ /*
+ * Open-code file_start_write here to grab freeze protection,
+ * which will be released by another thread in
+ * aio_complete_rw(). Fool lockdep by telling it the lock got
+ * released so that it doesn't complain about the held lock when
+ * we return to userspace.
+ */
+ if (S_ISREG(file_inode(file)->i_mode)) {
+ __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true);
+ __sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
+ }
+ req->ki_flags |= IOCB_WRITE;
+ aio_rw_done(req, call_write_iter(file, req, &iter));
+ }
+ kfree(iovec);
+out_fput:
+ if (unlikely(ret))
+ fput(file);
+ return ret;
+}
+
+static void aio_fsync_work(struct work_struct *work)
+{
+ struct fsync_iocb *req = container_of(work, struct fsync_iocb, work);
+ int ret;
+
+ ret = vfs_fsync(req->file, req->datasync);
+ fput(req->file);
+ aio_complete(container_of(req, struct aio_kiocb, fsync), ret, 0);
+}
+
+static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
+{
+ if (unlikely(iocb->aio_buf || iocb->aio_offset || iocb->aio_nbytes ||
+ iocb->aio_rw_flags))
+ return -EINVAL;
+ req->file = fget(iocb->aio_fildes);
+ if (unlikely(!req->file))
+ return -EBADF;
+ if (unlikely(!req->file->f_op->fsync)) {
+ fput(req->file);
+ return -EINVAL;
+ }
+
+ req->datasync = datasync;
+ INIT_WORK(&req->work, aio_fsync_work);
+ schedule_work(&req->work);
+ return 0;
+}
+
+/* need to use list_del_init so we can check if item was present */
+static inline bool __aio_poll_remove(struct poll_iocb *req)
+{
+ if (list_empty(&req->wait.entry))
+ return false;
+ list_del_init(&req->wait.entry);
+ return true;
+}
+
+static inline void __aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask)
+{
+ fput(iocb->poll.file);
+ aio_complete(iocb, mangle_poll(mask), 0);
+}
+
+static void aio_poll_work(struct work_struct *work)
+{
+ struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, poll.work);
+
+ if (!list_empty_careful(&iocb->ki_list))
+ aio_remove_iocb(iocb);
+ __aio_poll_complete(iocb, iocb->poll.events);
+}
+
+static int aio_poll_cancel(struct kiocb *iocb)
+{
+ struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw);
+ struct poll_iocb *req = &aiocb->poll;
+ struct wait_queue_head *head = req->head;
+ bool found = false;
+
+ spin_lock(&head->lock);
+ found = __aio_poll_remove(req);
+ spin_unlock(&head->lock);
+
+ if (found) {
+ req->events = 0;
+ INIT_WORK(&req->work, aio_poll_work);
+ schedule_work(&req->work);
+ }
+ return 0;
+}
+
+static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
+ void *key)
+{
+ struct poll_iocb *req = container_of(wait, struct poll_iocb, wait);
+ struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
+ struct file *file = req->file;
+ __poll_t mask = key_to_poll(key);
+
+ assert_spin_locked(&req->head->lock);
+
+ /* for instances that support it check for an event match first: */
+ if (mask && !(mask & req->events))
+ return 0;
+
+ mask = file->f_op->poll_mask(file, req->events);
+ if (!mask)
+ return 0;
+
+ __aio_poll_remove(req);
+
+ /*
+ * Try completing without a context switch if we can acquire ctx_lock
+ * without spinning. Otherwise we need to defer to a workqueue to
+ * avoid a deadlock due to the lock order.
+ */
+ if (spin_trylock(&iocb->ki_ctx->ctx_lock)) {
+ list_del_init(&iocb->ki_list);
+ spin_unlock(&iocb->ki_ctx->ctx_lock);
+
+ __aio_poll_complete(iocb, mask);
+ } else {
+ req->events = mask;
+ INIT_WORK(&req->work, aio_poll_work);
+ schedule_work(&req->work);
+ }
+
+ return 1;
+}
+
+static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
+{
+ struct kioctx *ctx = aiocb->ki_ctx;
+ struct poll_iocb *req = &aiocb->poll;
+ __poll_t mask;
+
+ /* reject any unknown events outside the normal event mask. */
+ if ((u16)iocb->aio_buf != iocb->aio_buf)
+ return -EINVAL;
+ /* reject fields that are not defined for poll */
+ if (iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags)
+ return -EINVAL;
+
+ req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP;
+ req->file = fget(iocb->aio_fildes);
+ if (unlikely(!req->file))
+ return -EBADF;
+ if (!file_has_poll_mask(req->file))
+ goto out_fail;
+
+ req->head = req->file->f_op->get_poll_head(req->file, req->events);
+ if (!req->head)
+ goto out_fail;
+ if (IS_ERR(req->head)) {
+ mask = EPOLLERR;
+ goto done;
+ }
+
+ init_waitqueue_func_entry(&req->wait, aio_poll_wake);
+ aiocb->ki_cancel = aio_poll_cancel;
+
+ spin_lock_irq(&ctx->ctx_lock);
+ spin_lock(&req->head->lock);
+ mask = req->file->f_op->poll_mask(req->file, req->events);
+ if (!mask) {
+ __add_wait_queue(req->head, &req->wait);
+ list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
+ }
+ spin_unlock(&req->head->lock);
+ spin_unlock_irq(&ctx->ctx_lock);
+done:
+ if (mask)
+ __aio_poll_complete(aiocb, mask);
+ return 0;
+out_fail:
+ fput(req->file);
+ return -EINVAL; /* same as no support for IOCB_CMD_POLL */
+}
+
+static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
+ bool compat)
+{
+ struct aio_kiocb *req;
+ struct iocb iocb;
+ ssize_t ret;
+
+ if (unlikely(copy_from_user(&iocb, user_iocb, sizeof(iocb))))
+ return -EFAULT;
+
/* enforce forwards compatibility on users */
- if (unlikely(iocb->aio_reserved2)) {
+ if (unlikely(iocb.aio_reserved2)) {
pr_debug("EINVAL: reserve field set\n");
return -EINVAL;
}
/* prevent overflows */
if (unlikely(
- (iocb->aio_buf != (unsigned long)iocb->aio_buf) ||
- (iocb->aio_nbytes != (size_t)iocb->aio_nbytes) ||
- ((ssize_t)iocb->aio_nbytes < 0)
+ (iocb.aio_buf != (unsigned long)iocb.aio_buf) ||
+ (iocb.aio_nbytes != (size_t)iocb.aio_nbytes) ||
+ ((ssize_t)iocb.aio_nbytes < 0)
)) {
pr_debug("EINVAL: overflow check\n");
return -EINVAL;
@@ -1570,37 +1749,19 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
if (unlikely(!req))
return -EAGAIN;
- req->common.ki_filp = file = fget(iocb->aio_fildes);
- if (unlikely(!req->common.ki_filp)) {
- ret = -EBADF;
- goto out_put_req;
- }
- req->common.ki_pos = iocb->aio_offset;
- req->common.ki_complete = aio_complete;
- req->common.ki_flags = iocb_flags(req->common.ki_filp);
- req->common.ki_hint = file_write_hint(file);
-
- if (iocb->aio_flags & IOCB_FLAG_RESFD) {
+ if (iocb.aio_flags & IOCB_FLAG_RESFD) {
/*
* If the IOCB_FLAG_RESFD flag of aio_flags is set, get an
* instance of the file* now. The file descriptor must be
* an eventfd() fd, and will be signaled for each completed
* event using the eventfd_signal() function.
*/
- req->ki_eventfd = eventfd_ctx_fdget((int) iocb->aio_resfd);
+ req->ki_eventfd = eventfd_ctx_fdget((int) iocb.aio_resfd);
if (IS_ERR(req->ki_eventfd)) {
ret = PTR_ERR(req->ki_eventfd);
req->ki_eventfd = NULL;
goto out_put_req;
}
-
- req->common.ki_flags |= IOCB_EVENTFD;
- }
-
- ret = kiocb_set_rw_flags(&req->common, iocb->aio_rw_flags);
- if (unlikely(ret)) {
- pr_debug("EINVAL: aio_rw_flags\n");
- goto out_put_req;
}
ret = put_user(KIOCB_KEY, &user_iocb->aio_key);
@@ -1610,92 +1771,53 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
}
req->ki_user_iocb = user_iocb;
- req->ki_user_data = iocb->aio_data;
+ req->ki_user_data = iocb.aio_data;
- get_file(file);
- switch (iocb->aio_lio_opcode) {
+ switch (iocb.aio_lio_opcode) {
case IOCB_CMD_PREAD:
- ret = aio_read(&req->common, iocb, false, compat);
+ ret = aio_read(&req->rw, &iocb, false, compat);
break;
case IOCB_CMD_PWRITE:
- ret = aio_write(&req->common, iocb, false, compat);
+ ret = aio_write(&req->rw, &iocb, false, compat);
break;
case IOCB_CMD_PREADV:
- ret = aio_read(&req->common, iocb, true, compat);
+ ret = aio_read(&req->rw, &iocb, true, compat);
break;
case IOCB_CMD_PWRITEV:
- ret = aio_write(&req->common, iocb, true, compat);
+ ret = aio_write(&req->rw, &iocb, true, compat);
+ break;
+ case IOCB_CMD_FSYNC:
+ ret = aio_fsync(&req->fsync, &iocb, false);
+ break;
+ case IOCB_CMD_FDSYNC:
+ ret = aio_fsync(&req->fsync, &iocb, true);
+ break;
+ case IOCB_CMD_POLL:
+ ret = aio_poll(req, &iocb);
break;
default:
- pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode);
+ pr_debug("invalid aio operation %d\n", iocb.aio_lio_opcode);
ret = -EINVAL;
break;
}
- fput(file);
- if (ret && ret != -EIOCBQUEUED)
+ /*
+ * If ret is 0, we'd either done aio_complete() ourselves or have
+ * arranged for that to be done asynchronously. Anything non-zero
+ * means that we need to destroy req ourselves.
+ */
+ if (ret)
goto out_put_req;
return 0;
out_put_req:
put_reqs_available(ctx, 1);
percpu_ref_put(&ctx->reqs);
- kiocb_free(req);
+ if (req->ki_eventfd)
+ eventfd_ctx_put(req->ki_eventfd);
+ kmem_cache_free(kiocb_cachep, req);
return ret;
}
-static long do_io_submit(aio_context_t ctx_id, long nr,
- struct iocb __user *__user *iocbpp, bool compat)
-{
- struct kioctx *ctx;
- long ret = 0;
- int i = 0;
- struct blk_plug plug;
-
- if (unlikely(nr < 0))
- return -EINVAL;
-
- if (unlikely(nr > LONG_MAX/sizeof(*iocbpp)))
- nr = LONG_MAX/sizeof(*iocbpp);
-
- if (unlikely(!access_ok(VERIFY_READ, iocbpp, (nr*sizeof(*iocbpp)))))
- return -EFAULT;
-
- ctx = lookup_ioctx(ctx_id);
- if (unlikely(!ctx)) {
- pr_debug("EINVAL: invalid context id\n");
- return -EINVAL;
- }
-
- blk_start_plug(&plug);
-
- /*
- * AKPM: should this return a partial result if some of the IOs were
- * successfully submitted?
- */
- for (i=0; i<nr; i++) {
- struct iocb __user *user_iocb;
- struct iocb tmp;
-
- if (unlikely(__get_user(user_iocb, iocbpp + i))) {
- ret = -EFAULT;
- break;
- }
-
- if (unlikely(copy_from_user(&tmp, user_iocb, sizeof(tmp)))) {
- ret = -EFAULT;
- break;
- }
-
- ret = io_submit_one(ctx, user_iocb, &tmp, compat);
- if (ret)
- break;
- }
- blk_finish_plug(&plug);
-
- percpu_ref_put(&ctx->users);
- return i ? i : ret;
-}
-
/* sys_io_submit:
* Queue the nr iocbs pointed to by iocbpp for processing. Returns
* the number of iocbs queued. May return -EINVAL if the aio_context
@@ -1711,44 +1833,80 @@ static long do_io_submit(aio_context_t ctx_id, long nr,
SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
struct iocb __user * __user *, iocbpp)
{
- return do_io_submit(ctx_id, nr, iocbpp, 0);
-}
-
-#ifdef CONFIG_COMPAT
-static inline long
-copy_iocb(long nr, u32 __user *ptr32, struct iocb __user * __user *ptr64)
-{
- compat_uptr_t uptr;
- int i;
-
- for (i = 0; i < nr; ++i) {
- if (get_user(uptr, ptr32 + i))
- return -EFAULT;
- if (put_user(compat_ptr(uptr), ptr64 + i))
- return -EFAULT;
- }
- return 0;
-}
-
-#define MAX_AIO_SUBMITS (PAGE_SIZE/sizeof(struct iocb *))
-
-COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
- int, nr, u32 __user *, iocb)
-{
- struct iocb __user * __user *iocb64;
- long ret;
+ struct kioctx *ctx;
+ long ret = 0;
+ int i = 0;
+ struct blk_plug plug;
if (unlikely(nr < 0))
return -EINVAL;
- if (nr > MAX_AIO_SUBMITS)
- nr = MAX_AIO_SUBMITS;
+ ctx = lookup_ioctx(ctx_id);
+ if (unlikely(!ctx)) {
+ pr_debug("EINVAL: invalid context id\n");
+ return -EINVAL;
+ }
- iocb64 = compat_alloc_user_space(nr * sizeof(*iocb64));
- ret = copy_iocb(nr, iocb, iocb64);
- if (!ret)
- ret = do_io_submit(ctx_id, nr, iocb64, 1);
- return ret;
+ if (nr > ctx->nr_events)
+ nr = ctx->nr_events;
+
+ blk_start_plug(&plug);
+ for (i = 0; i < nr; i++) {
+ struct iocb __user *user_iocb;
+
+ if (unlikely(get_user(user_iocb, iocbpp + i))) {
+ ret = -EFAULT;
+ break;
+ }
+
+ ret = io_submit_one(ctx, user_iocb, false);
+ if (ret)
+ break;
+ }
+ blk_finish_plug(&plug);
+
+ percpu_ref_put(&ctx->users);
+ return i ? i : ret;
+}
+
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
+ int, nr, compat_uptr_t __user *, iocbpp)
+{
+ struct kioctx *ctx;
+ long ret = 0;
+ int i = 0;
+ struct blk_plug plug;
+
+ if (unlikely(nr < 0))
+ return -EINVAL;
+
+ ctx = lookup_ioctx(ctx_id);
+ if (unlikely(!ctx)) {
+ pr_debug("EINVAL: invalid context id\n");
+ return -EINVAL;
+ }
+
+ if (nr > ctx->nr_events)
+ nr = ctx->nr_events;
+
+ blk_start_plug(&plug);
+ for (i = 0; i < nr; i++) {
+ compat_uptr_t user_iocb;
+
+ if (unlikely(get_user(user_iocb, iocbpp + i))) {
+ ret = -EFAULT;
+ break;
+ }
+
+ ret = io_submit_one(ctx, compat_ptr(user_iocb), true);
+ if (ret)
+ break;
+ }
+ blk_finish_plug(&plug);
+
+ percpu_ref_put(&ctx->users);
+ return i ? i : ret;
}
#endif
@@ -1756,15 +1914,12 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
* Finds a given iocb for cancellation.
*/
static struct aio_kiocb *
-lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb, u32 key)
+lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb)
{
struct aio_kiocb *kiocb;
assert_spin_locked(&ctx->ctx_lock);
- if (key != KIOCB_KEY)
- return NULL;
-
/* TODO: use a hash or array, this sucks. */
list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) {
if (kiocb->ki_user_iocb == iocb)
@@ -1788,25 +1943,24 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
{
struct kioctx *ctx;
struct aio_kiocb *kiocb;
+ int ret = -EINVAL;
u32 key;
- int ret;
- ret = get_user(key, &iocb->aio_key);
- if (unlikely(ret))
+ if (unlikely(get_user(key, &iocb->aio_key)))
return -EFAULT;
+ if (unlikely(key != KIOCB_KEY))
+ return -EINVAL;
ctx = lookup_ioctx(ctx_id);
if (unlikely(!ctx))
return -EINVAL;
spin_lock_irq(&ctx->ctx_lock);
-
- kiocb = lookup_kiocb(ctx, iocb, key);
- if (kiocb)
- ret = kiocb_cancel(kiocb);
- else
- ret = -EINVAL;
-
+ kiocb = lookup_kiocb(ctx, iocb);
+ if (kiocb) {
+ ret = kiocb->ki_cancel(&kiocb->rw);
+ list_del_init(&kiocb->ki_list);
+ }
spin_unlock_irq(&ctx->ctx_lock);
if (!ret) {
@@ -1861,13 +2015,60 @@ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id,
struct timespec __user *, timeout)
{
struct timespec64 ts;
+ int ret;
- if (timeout) {
- if (unlikely(get_timespec64(&ts, timeout)))
+ if (timeout && unlikely(get_timespec64(&ts, timeout)))
+ return -EFAULT;
+
+ ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
+ if (!ret && signal_pending(current))
+ ret = -EINTR;
+ return ret;
+}
+
+SYSCALL_DEFINE6(io_pgetevents,
+ aio_context_t, ctx_id,
+ long, min_nr,
+ long, nr,
+ struct io_event __user *, events,
+ struct timespec __user *, timeout,
+ const struct __aio_sigset __user *, usig)
+{
+ struct __aio_sigset ksig = { NULL, };
+ sigset_t ksigmask, sigsaved;
+ struct timespec64 ts;
+ int ret;
+
+ if (timeout && unlikely(get_timespec64(&ts, timeout)))
+ return -EFAULT;
+
+ if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
+ return -EFAULT;
+
+ if (ksig.sigmask) {
+ if (ksig.sigsetsize != sizeof(sigset_t))
+ return -EINVAL;
+ if (copy_from_user(&ksigmask, ksig.sigmask, sizeof(ksigmask)))
return -EFAULT;
+ sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
+ sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
}
- return do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
+ ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
+ if (signal_pending(current)) {
+ if (ksig.sigmask) {
+ current->saved_sigmask = sigsaved;
+ set_restore_sigmask();
+ }
+
+ if (!ret)
+ ret = -ERESTARTNOHAND;
+ } else {
+ if (ksig.sigmask)
+ sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+ }
+
+ return ret;
}
#ifdef CONFIG_COMPAT
@@ -1878,13 +2079,64 @@ COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id,
struct compat_timespec __user *, timeout)
{
struct timespec64 t;
+ int ret;
- if (timeout) {
- if (compat_get_timespec64(&t, timeout))
+ if (timeout && compat_get_timespec64(&t, timeout))
+ return -EFAULT;
+
+ ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
+ if (!ret && signal_pending(current))
+ ret = -EINTR;
+ return ret;
+}
+
+
+struct __compat_aio_sigset {
+ compat_sigset_t __user *sigmask;
+ compat_size_t sigsetsize;
+};
+
+COMPAT_SYSCALL_DEFINE6(io_pgetevents,
+ compat_aio_context_t, ctx_id,
+ compat_long_t, min_nr,
+ compat_long_t, nr,
+ struct io_event __user *, events,
+ struct compat_timespec __user *, timeout,
+ const struct __compat_aio_sigset __user *, usig)
+{
+ struct __compat_aio_sigset ksig = { NULL, };
+ sigset_t ksigmask, sigsaved;
+ struct timespec64 t;
+ int ret;
+
+ if (timeout && compat_get_timespec64(&t, timeout))
+ return -EFAULT;
+
+ if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
+ return -EFAULT;
+
+ if (ksig.sigmask) {
+ if (ksig.sigsetsize != sizeof(compat_sigset_t))
+ return -EINVAL;
+ if (get_compat_sigset(&ksigmask, ksig.sigmask))
return -EFAULT;
-
+ sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
+ sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
}
- return do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
+ ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
+ if (signal_pending(current)) {
+ if (ksig.sigmask) {
+ current->saved_sigmask = sigsaved;
+ set_restore_sigmask();
+ }
+ if (!ret)
+ ret = -ERESTARTNOHAND;
+ } else {
+ if (ksig.sigmask)
+ sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+ }
+
+ return ret;
}
#endif
diff --git a/fs/attr.c b/fs/attr.c
index 12ffdb6..d0b4d34 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -18,6 +18,32 @@
#include <linux/evm.h>
#include <linux/ima.h>
+static bool chown_ok(const struct inode *inode, kuid_t uid)
+{
+ if (uid_eq(current_fsuid(), inode->i_uid) &&
+ uid_eq(uid, inode->i_uid))
+ return true;
+ if (capable_wrt_inode_uidgid(inode, CAP_CHOWN))
+ return true;
+ if (uid_eq(inode->i_uid, INVALID_UID) &&
+ ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN))
+ return true;
+ return false;
+}
+
+static bool chgrp_ok(const struct inode *inode, kgid_t gid)
+{
+ if (uid_eq(current_fsuid(), inode->i_uid) &&
+ (in_group_p(gid) || gid_eq(gid, inode->i_gid)))
+ return true;
+ if (capable_wrt_inode_uidgid(inode, CAP_CHOWN))
+ return true;
+ if (gid_eq(inode->i_gid, INVALID_GID) &&
+ ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN))
+ return true;
+ return false;
+}
+
/**
* setattr_prepare - check if attribute changes to a dentry are allowed
* @dentry: dentry to check
@@ -52,17 +78,11 @@ int setattr_prepare(struct dentry *dentry, struct iattr *attr)
goto kill_priv;
/* Make sure a caller can chown. */
- if ((ia_valid & ATTR_UID) &&
- (!uid_eq(current_fsuid(), inode->i_uid) ||
- !uid_eq(attr->ia_uid, inode->i_uid)) &&
- !capable_wrt_inode_uidgid(inode, CAP_CHOWN))
+ if ((ia_valid & ATTR_UID) && !chown_ok(inode, attr->ia_uid))
return -EPERM;
/* Make sure caller can chgrp. */
- if ((ia_valid & ATTR_GID) &&
- (!uid_eq(current_fsuid(), inode->i_uid) ||
- (!in_group_p(attr->ia_gid) && !gid_eq(attr->ia_gid, inode->i_gid))) &&
- !capable_wrt_inode_uidgid(inode, CAP_CHOWN))
+ if ((ia_valid & ATTR_GID) && !chgrp_ok(inode, attr->ia_gid))
return -EPERM;
/* Make sure a caller can chmod. */
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 82e8f6e..b12e37f 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -749,7 +749,7 @@ static int autofs4_dir_mkdir(struct inode *dir,
autofs4_del_active(dentry);
- inode = autofs4_get_inode(dir->i_sb, S_IFDIR | 0555);
+ inode = autofs4_get_inode(dir->i_sb, S_IFDIR | mode);
if (!inode)
return -ENOMEM;
d_add(dentry, inode);
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index af2832a..4700b45 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -198,23 +198,16 @@ befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
if (ret == BEFS_BT_NOT_FOUND) {
befs_debug(sb, "<--- %s %pd not found", __func__, dentry);
- d_add(dentry, NULL);
- return ERR_PTR(-ENOENT);
-
+ inode = NULL;
} else if (ret != BEFS_OK || offset == 0) {
befs_error(sb, "<--- %s Error", __func__);
- return ERR_PTR(-ENODATA);
+ inode = ERR_PTR(-ENODATA);
+ } else {
+ inode = befs_iget(dir->i_sb, (ino_t) offset);
}
-
- inode = befs_iget(dir->i_sb, (ino_t) offset);
- if (IS_ERR(inode))
- return ERR_CAST(inode);
-
- d_add(dentry, inode);
-
befs_debug(sb, "<--- %s", __func__);
- return NULL;
+ return d_splice_alias(inode, dentry);
}
static int
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index ee832ca..f32f21c 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -21,10 +21,9 @@
#define dprintf(x...)
#endif
-static int bfs_add_entry(struct inode *dir, const unsigned char *name,
- int namelen, int ino);
+static int bfs_add_entry(struct inode *dir, const struct qstr *child, int ino);
static struct buffer_head *bfs_find_entry(struct inode *dir,
- const unsigned char *name, int namelen,
+ const struct qstr *child,
struct bfs_dirent **res_dir);
static int bfs_readdir(struct file *f, struct dir_context *ctx)
@@ -111,8 +110,7 @@ static int bfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
mark_inode_dirty(inode);
bfs_dump_imap("create", s);
- err = bfs_add_entry(dir, dentry->d_name.name, dentry->d_name.len,
- inode->i_ino);
+ err = bfs_add_entry(dir, &dentry->d_name, inode->i_ino);
if (err) {
inode_dec_link_count(inode);
mutex_unlock(&info->bfs_lock);
@@ -136,19 +134,14 @@ static struct dentry *bfs_lookup(struct inode *dir, struct dentry *dentry,
return ERR_PTR(-ENAMETOOLONG);
mutex_lock(&info->bfs_lock);
- bh = bfs_find_entry(dir, dentry->d_name.name, dentry->d_name.len, &de);
+ bh = bfs_find_entry(dir, &dentry->d_name, &de);
if (bh) {
unsigned long ino = (unsigned long)le16_to_cpu(de->ino);
brelse(bh);
inode = bfs_iget(dir->i_sb, ino);
- if (IS_ERR(inode)) {
- mutex_unlock(&info->bfs_lock);
- return ERR_CAST(inode);
- }
}
mutex_unlock(&info->bfs_lock);
- d_add(dentry, inode);
- return NULL;
+ return d_splice_alias(inode, dentry);
}
static int bfs_link(struct dentry *old, struct inode *dir,
@@ -159,8 +152,7 @@ static int bfs_link(struct dentry *old, struct inode *dir,
int err;
mutex_lock(&info->bfs_lock);
- err = bfs_add_entry(dir, new->d_name.name, new->d_name.len,
- inode->i_ino);
+ err = bfs_add_entry(dir, &new->d_name, inode->i_ino);
if (err) {
mutex_unlock(&info->bfs_lock);
return err;
@@ -183,7 +175,7 @@ static int bfs_unlink(struct inode *dir, struct dentry *dentry)
struct bfs_sb_info *info = BFS_SB(inode->i_sb);
mutex_lock(&info->bfs_lock);
- bh = bfs_find_entry(dir, dentry->d_name.name, dentry->d_name.len, &de);
+ bh = bfs_find_entry(dir, &dentry->d_name, &de);
if (!bh || (le16_to_cpu(de->ino) != inode->i_ino))
goto out_brelse;
@@ -228,27 +220,21 @@ static int bfs_rename(struct inode *old_dir, struct dentry *old_dentry,
info = BFS_SB(old_inode->i_sb);
mutex_lock(&info->bfs_lock);
- old_bh = bfs_find_entry(old_dir,
- old_dentry->d_name.name,
- old_dentry->d_name.len, &old_de);
+ old_bh = bfs_find_entry(old_dir, &old_dentry->d_name, &old_de);
if (!old_bh || (le16_to_cpu(old_de->ino) != old_inode->i_ino))
goto end_rename;
error = -EPERM;
new_inode = d_inode(new_dentry);
- new_bh = bfs_find_entry(new_dir,
- new_dentry->d_name.name,
- new_dentry->d_name.len, &new_de);
+ new_bh = bfs_find_entry(new_dir, &new_dentry->d_name, &new_de);
if (new_bh && !new_inode) {
brelse(new_bh);
new_bh = NULL;
}
if (!new_bh) {
- error = bfs_add_entry(new_dir,
- new_dentry->d_name.name,
- new_dentry->d_name.len,
+ error = bfs_add_entry(new_dir, &new_dentry->d_name,
old_inode->i_ino);
if (error)
goto end_rename;
@@ -278,9 +264,10 @@ const struct inode_operations bfs_dir_inops = {
.rename = bfs_rename,
};
-static int bfs_add_entry(struct inode *dir, const unsigned char *name,
- int namelen, int ino)
+static int bfs_add_entry(struct inode *dir, const struct qstr *child, int ino)
{
+ const unsigned char *name = child->name;
+ int namelen = child->len;
struct buffer_head *bh;
struct bfs_dirent *de;
int block, sblock, eblock, off, pos;
@@ -332,12 +319,14 @@ static inline int bfs_namecmp(int len, const unsigned char *name,
}
static struct buffer_head *bfs_find_entry(struct inode *dir,
- const unsigned char *name, int namelen,
+ const struct qstr *child,
struct bfs_dirent **res_dir)
{
unsigned long block = 0, offset = 0;
struct buffer_head *bh = NULL;
struct bfs_dirent *de;
+ const unsigned char *name = child->name;
+ int namelen = child->len;
*res_dir = NULL;
if (namelen > BFS_NAMELEN)
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 41e0418..4ad6f66 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -377,10 +377,10 @@ static unsigned long elf_map(struct file *filep, unsigned long addr,
} else
map_addr = vm_mmap(filep, addr, size, prot, type, off);
- if ((type & MAP_FIXED_NOREPLACE) && BAD_ADDR(map_addr))
- pr_info("%d (%s): Uhuuh, elf segment at %p requested but the memory is mapped already\n",
- task_pid_nr(current), current->comm,
- (void *)addr);
+ if ((type & MAP_FIXED_NOREPLACE) &&
+ PTR_ERR((void *)map_addr) == -EEXIST)
+ pr_info("%d (%s): Uhuuh, elf segment at %px requested but the memory is mapped already\n",
+ task_pid_nr(current), current->comm, (void *)addr);
return(map_addr);
}
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 7ec920e..bef6934 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -272,7 +272,7 @@ struct blkdev_dio {
struct bio bio;
};
-static struct bio_set *blkdev_dio_pool __read_mostly;
+static struct bio_set blkdev_dio_pool;
static void blkdev_bio_end_io(struct bio *bio)
{
@@ -334,7 +334,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
(bdev_logical_block_size(bdev) - 1))
return -EINVAL;
- bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, blkdev_dio_pool);
+ bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, &blkdev_dio_pool);
bio_get(bio); /* extra ref for the completion handler */
dio = container_of(bio, struct blkdev_dio, bio);
@@ -432,10 +432,7 @@ blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
static __init int blkdev_init(void)
{
- blkdev_dio_pool = bioset_create(4, offsetof(struct blkdev_dio, bio), BIOSET_NEED_BVECS);
- if (!blkdev_dio_pool)
- return -ENOMEM;
- return 0;
+ return bioset_init(&blkdev_dio_pool, 4, offsetof(struct blkdev_dio, bio), BIOSET_NEED_BVECS);
}
module_init(blkdev_init);
@@ -1322,27 +1319,30 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty)
* check_disk_size_change - checks for disk size change and adjusts bdev size.
* @disk: struct gendisk to check
* @bdev: struct bdev to adjust.
+ * @verbose: if %true log a message about a size change if there is any
*
* This routine checks to see if the bdev size does not match the disk size
* and adjusts it if it differs. When shrinking the bdev size, its all caches
* are freed.
*/
-void check_disk_size_change(struct gendisk *disk, struct block_device *bdev)
+void check_disk_size_change(struct gendisk *disk, struct block_device *bdev,
+ bool verbose)
{
loff_t disk_size, bdev_size;
disk_size = (loff_t)get_capacity(disk) << 9;
bdev_size = i_size_read(bdev->bd_inode);
if (disk_size != bdev_size) {
- printk(KERN_INFO
- "%s: detected capacity change from %lld to %lld\n",
- disk->disk_name, bdev_size, disk_size);
+ if (verbose) {
+ printk(KERN_INFO
+ "%s: detected capacity change from %lld to %lld\n",
+ disk->disk_name, bdev_size, disk_size);
+ }
i_size_write(bdev->bd_inode, disk_size);
if (bdev_size > disk_size)
flush_disk(bdev, false);
}
}
-EXPORT_SYMBOL(check_disk_size_change);
/**
* revalidate_disk - wrapper for lower-level driver's revalidate_disk call-back
@@ -1364,7 +1364,7 @@ int revalidate_disk(struct gendisk *disk)
return ret;
mutex_lock(&bdev->bd_mutex);
- check_disk_size_change(disk, bdev);
+ check_disk_size_change(disk, bdev, ret == 0);
bdev->bd_invalidated = 0;
mutex_unlock(&bdev->bd_mutex);
bdput(bdev);
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 234bae5..7e07534 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -19,17 +19,17 @@
* ordered operations list so that we make sure to flush out any
* new data the application may have written before commit.
*/
-#define BTRFS_INODE_ORDERED_DATA_CLOSE 0
-#define BTRFS_INODE_ORPHAN_META_RESERVED 1
-#define BTRFS_INODE_DUMMY 2
-#define BTRFS_INODE_IN_DEFRAG 3
-#define BTRFS_INODE_HAS_ORPHAN_ITEM 4
-#define BTRFS_INODE_HAS_ASYNC_EXTENT 5
-#define BTRFS_INODE_NEEDS_FULL_SYNC 6
-#define BTRFS_INODE_COPY_EVERYTHING 7
-#define BTRFS_INODE_IN_DELALLOC_LIST 8
-#define BTRFS_INODE_READDIO_NEED_LOCK 9
-#define BTRFS_INODE_HAS_PROPS 10
+enum {
+ BTRFS_INODE_ORDERED_DATA_CLOSE = 0,
+ BTRFS_INODE_DUMMY,
+ BTRFS_INODE_IN_DEFRAG,
+ BTRFS_INODE_HAS_ASYNC_EXTENT,
+ BTRFS_INODE_NEEDS_FULL_SYNC,
+ BTRFS_INODE_COPY_EVERYTHING,
+ BTRFS_INODE_IN_DELALLOC_LIST,
+ BTRFS_INODE_READDIO_NEED_LOCK,
+ BTRFS_INODE_HAS_PROPS,
+};
/* in memory btrfs inode */
struct btrfs_inode {
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 1061575..d3e447b 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -990,12 +990,7 @@ static void __free_workspace(int type, struct list_head *workspace,
btrfs_compress_op[idx]->free_workspace(workspace);
atomic_dec(total_ws);
wake:
- /*
- * Make sure counter is updated before we wake up waiters.
- */
- smp_mb();
- if (waitqueue_active(ws_wait))
- wake_up(ws_wait);
+ cond_wake_up(ws_wait);
}
static void free_workspace(int type, struct list_head *ws)
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index cc605f7..ddda9b8 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -6,6 +6,8 @@
#ifndef BTRFS_COMPRESSION_H
#define BTRFS_COMPRESSION_H
+#include <linux/sizes.h>
+
/*
* We want to make sure that amount of RAM required to uncompress an extent is
* reasonable, so we limit the total size in ram of a compressed extent to
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 3fd4483..4bc326d 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -2330,7 +2330,7 @@ static noinline void unlock_up(struct btrfs_path *path, int level,
no_skips = 1;
t = path->nodes[i];
- if (i >= lowest_unlock && i > skip_level && path->locks[i]) {
+ if (i >= lowest_unlock && i > skip_level) {
btrfs_tree_unlock_rw(t, path->locks[i]);
path->locks[i] = 0;
if (write_lock_level &&
@@ -2432,14 +2432,11 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
btrfs_unlock_up_safe(p, level + 1);
btrfs_set_path_blocking(p);
- free_extent_buffer(tmp);
if (p->reada != READA_NONE)
reada_for_search(fs_info, p, level, slot, key->objectid);
- btrfs_release_path(p);
-
ret = -EAGAIN;
- tmp = read_tree_block(fs_info, blocknr, 0, parent_level - 1,
+ tmp = read_tree_block(fs_info, blocknr, gen, parent_level - 1,
&first_key);
if (!IS_ERR(tmp)) {
/*
@@ -2448,12 +2445,14 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
* and give up so that our caller doesn't loop forever
* on our EAGAINs.
*/
- if (!btrfs_buffer_uptodate(tmp, 0, 0))
+ if (!extent_buffer_uptodate(tmp))
ret = -EIO;
free_extent_buffer(tmp);
} else {
ret = PTR_ERR(tmp);
}
+
+ btrfs_release_path(p);
return ret;
}
@@ -2599,6 +2598,78 @@ int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path,
return 0;
}
+static struct extent_buffer *btrfs_search_slot_get_root(struct btrfs_root *root,
+ struct btrfs_path *p,
+ int write_lock_level)
+{
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct extent_buffer *b;
+ int root_lock;
+ int level = 0;
+
+ /* We try very hard to do read locks on the root */
+ root_lock = BTRFS_READ_LOCK;
+
+ if (p->search_commit_root) {
+ /* The commit roots are read only so we always do read locks */
+ if (p->need_commit_sem)
+ down_read(&fs_info->commit_root_sem);
+ b = root->commit_root;
+ extent_buffer_get(b);
+ level = btrfs_header_level(b);
+ if (p->need_commit_sem)
+ up_read(&fs_info->commit_root_sem);
+ /*
+ * Ensure that all callers have set skip_locking when
+ * p->search_commit_root = 1.
+ */
+ ASSERT(p->skip_locking == 1);
+
+ goto out;
+ }
+
+ if (p->skip_locking) {
+ b = btrfs_root_node(root);
+ level = btrfs_header_level(b);
+ goto out;
+ }
+
+ /*
+ * If the level is set to maximum, we can skip trying to get the read
+ * lock.
+ */
+ if (write_lock_level < BTRFS_MAX_LEVEL) {
+ /*
+ * We don't know the level of the root node until we actually
+ * have it read locked
+ */
+ b = btrfs_read_lock_root_node(root);
+ level = btrfs_header_level(b);
+ if (level > write_lock_level)
+ goto out;
+
+ /* Whoops, must trade for write lock */
+ btrfs_tree_read_unlock(b);
+ free_extent_buffer(b);
+ }
+
+ b = btrfs_lock_root_node(root);
+ root_lock = BTRFS_WRITE_LOCK;
+
+ /* The level might have changed, check again */
+ level = btrfs_header_level(b);
+
+out:
+ p->nodes[level] = b;
+ if (!p->skip_locking)
+ p->locks[level] = root_lock;
+ /*
+ * Callers are responsible for dropping b's references.
+ */
+ return b;
+}
+
+
/*
* btrfs_search_slot - look for a key in a tree and perform necessary
* modifications to preserve tree invariants.
@@ -2635,7 +2706,6 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
int err;
int level;
int lowest_unlock = 1;
- int root_lock;
/* everything at write_lock_level or lower must be write locked */
int write_lock_level = 0;
u8 lowest_level = 0;
@@ -2673,50 +2743,7 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
again:
prev_cmp = -1;
- /*
- * we try very hard to do read locks on the root
- */
- root_lock = BTRFS_READ_LOCK;
- level = 0;
- if (p->search_commit_root) {
- /*
- * the commit roots are read only
- * so we always do read locks
- */
- if (p->need_commit_sem)
- down_read(&fs_info->commit_root_sem);
- b = root->commit_root;
- extent_buffer_get(b);
- level = btrfs_header_level(b);
- if (p->need_commit_sem)
- up_read(&fs_info->commit_root_sem);
- if (!p->skip_locking)
- btrfs_tree_read_lock(b);
- } else {
- if (p->skip_locking) {
- b = btrfs_root_node(root);
- level = btrfs_header_level(b);
- } else {
- /* we don't know the level of the root node
- * until we actually have it read locked
- */
- b = btrfs_read_lock_root_node(root);
- level = btrfs_header_level(b);
- if (level <= write_lock_level) {
- /* whoops, must trade for write lock */
- btrfs_tree_read_unlock(b);
- free_extent_buffer(b);
- b = btrfs_lock_root_node(root);
- root_lock = BTRFS_WRITE_LOCK;
-
- /* the level might have changed, check again */
- level = btrfs_header_level(b);
- }
- }
- }
- p->nodes[level] = b;
- if (!p->skip_locking)
- p->locks[level] = root_lock;
+ b = btrfs_search_slot_get_root(root, p, write_lock_level);
while (b) {
level = btrfs_header_level(b);
@@ -5414,12 +5441,24 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
down_read(&fs_info->commit_root_sem);
left_level = btrfs_header_level(left_root->commit_root);
left_root_level = left_level;
- left_path->nodes[left_level] = left_root->commit_root;
+ left_path->nodes[left_level] =
+ btrfs_clone_extent_buffer(left_root->commit_root);
+ if (!left_path->nodes[left_level]) {
+ up_read(&fs_info->commit_root_sem);
+ ret = -ENOMEM;
+ goto out;
+ }
extent_buffer_get(left_path->nodes[left_level]);
right_level = btrfs_header_level(right_root->commit_root);
right_root_level = right_level;
- right_path->nodes[right_level] = right_root->commit_root;
+ right_path->nodes[right_level] =
+ btrfs_clone_extent_buffer(right_root->commit_root);
+ if (!right_path->nodes[right_level]) {
+ up_read(&fs_info->commit_root_sem);
+ ret = -ENOMEM;
+ goto out;
+ }
extent_buffer_get(right_path->nodes[right_level]);
up_read(&fs_info->commit_root_sem);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 5474ef1..f4bf787 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -459,6 +459,25 @@ struct btrfs_block_rsv {
unsigned short full;
unsigned short type;
unsigned short failfast;
+
+ /*
+ * Qgroup equivalent for @size @reserved
+ *
+ * Unlike normal @size/@reserved for inode rsv, qgroup doesn't care
+ * about things like csum size nor how many tree blocks it will need to
+ * reserve.
+ *
+ * Qgroup cares more about net change of the extent usage.
+ *
+ * So for one newly inserted file extent, in worst case it will cause
+ * leaf split and level increase, nodesize for each file extent is
+ * already too much.
+ *
+ * In short, qgroup_size/reserved is the upper limit of possible needed
+ * qgroup metadata reservation.
+ */
+ u64 qgroup_rsv_size;
+ u64 qgroup_rsv_reserved;
};
/*
@@ -714,6 +733,18 @@ struct btrfs_delayed_root;
*/
#define BTRFS_FS_EXCL_OP 16
+/*
+ * To info transaction_kthread we need an immediate commit so it doesn't
+ * need to wait for commit_interval
+ */
+#define BTRFS_FS_NEED_ASYNC_COMMIT 17
+
+/*
+ * Indicate that balance has been set up from the ioctl and is in the main
+ * phase. The fs_info::balance_ctl is initialized.
+ */
+#define BTRFS_FS_BALANCE_RUNNING 18
+
struct btrfs_fs_info {
u8 fsid[BTRFS_FSID_SIZE];
u8 chunk_tree_uuid[BTRFS_UUID_SIZE];
@@ -813,7 +844,6 @@ struct btrfs_fs_info {
struct mutex transaction_kthread_mutex;
struct mutex cleaner_mutex;
struct mutex chunk_mutex;
- struct mutex volume_mutex;
/*
* this is taken to make sure we don't set block groups ro after
@@ -979,7 +1009,6 @@ struct btrfs_fs_info {
/* restriper state */
spinlock_t balance_lock;
struct mutex balance_mutex;
- atomic_t balance_running;
atomic_t balance_pause_req;
atomic_t balance_cancel_req;
struct btrfs_balance_control *balance_ctl;
@@ -1194,9 +1223,6 @@ struct btrfs_root {
spinlock_t log_extents_lock[2];
struct list_head logged_list[2];
- spinlock_t orphan_lock;
- atomic_t orphan_inodes;
- struct btrfs_block_rsv *orphan_block_rsv;
int orphan_cleanup_state;
spinlock_t inode_lock;
@@ -2739,13 +2765,9 @@ void btrfs_delalloc_release_space(struct inode *inode,
void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
u64 len);
void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans);
-int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
- struct btrfs_inode *inode);
-void btrfs_orphan_release_metadata(struct btrfs_inode *inode);
int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
struct btrfs_block_rsv *rsv,
- int nitems,
- u64 *qgroup_reserved, bool use_global_rsv);
+ int nitems, bool use_global_rsv);
void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *rsv);
void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
@@ -2803,7 +2825,7 @@ void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
void check_system_chunk(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, const u64 type);
u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
- struct btrfs_fs_info *info, u64 start, u64 end);
+ u64 start, u64 end);
/* ctree.c */
int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
@@ -3017,11 +3039,9 @@ void btrfs_update_root_times(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
/* uuid-tree.c */
-int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info, u8 *uuid, u8 type,
+int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
u64 subid);
-int btrfs_uuid_tree_rem(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info, u8 *uuid, u8 type,
+int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
u64 subid);
int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info,
int (*check_func)(struct btrfs_fs_info *, u8 *, u8,
@@ -3138,18 +3158,6 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
struct extent_map *em);
/* inode.c */
-struct btrfs_delalloc_work {
- struct inode *inode;
- int delay_iput;
- struct completion completion;
- struct list_head list;
- struct btrfs_work work;
-};
-
-struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
- int delay_iput);
-void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work);
-
struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
struct page *page, size_t pg_offset, u64 start,
u64 len, int create);
@@ -3157,6 +3165,8 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
u64 *orig_start, u64 *orig_block_len,
u64 *ram_bytes);
+void __btrfs_del_delalloc_inode(struct btrfs_root *root,
+ struct btrfs_inode *inode);
struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry);
int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index);
int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
@@ -3166,10 +3176,7 @@ int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
int btrfs_add_link(struct btrfs_trans_handle *trans,
struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
const char *name, int name_len, int add_backref, u64 index);
-int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- struct inode *dir, u64 objectid,
- const char *name, int name_len);
+int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry);
int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
int front);
int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
@@ -3177,9 +3184,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
struct inode *inode, u64 new_size,
u32 min_type);
-int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput);
-int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput,
- int nr);
+int btrfs_start_delalloc_inodes(struct btrfs_root *root);
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int nr);
int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
unsigned int extra_bits,
struct extent_state **cached_state, int dedupe);
@@ -3213,10 +3219,7 @@ int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
int btrfs_orphan_add(struct btrfs_trans_handle *trans,
struct btrfs_inode *inode);
int btrfs_orphan_cleanup(struct btrfs_root *root);
-void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans,
- struct btrfs_root *root);
int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size);
-void btrfs_invalidate_inodes(struct btrfs_root *root);
void btrfs_add_delayed_iput(struct inode *inode);
void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info);
int btrfs_prealloc_file_range(struct inode *inode, int mode,
@@ -3235,14 +3238,14 @@ void btrfs_test_inode_set_ops(struct inode *inode);
long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
int btrfs_ioctl_get_supported_features(void __user *arg);
-void btrfs_update_iflags(struct inode *inode);
+void btrfs_sync_inode_flags_to_i_flags(struct inode *inode);
int btrfs_is_empty_uuid(u8 *uuid);
int btrfs_defrag_file(struct inode *inode, struct file *file,
struct btrfs_ioctl_defrag_range_args *range,
u64 newer_than, unsigned long max_pages);
void btrfs_get_block_group_info(struct list_head *groups_list,
struct btrfs_ioctl_space_info *space);
-void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
+void btrfs_update_ioctl_balance_args(struct btrfs_fs_info *fs_info,
struct btrfs_ioctl_balance_args *bargs);
ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
struct file *dst_file, u64 dst_loff);
@@ -3740,4 +3743,26 @@ static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info)
return 0;
}
+static inline void cond_wake_up(struct wait_queue_head *wq)
+{
+ /*
+ * This implies a full smp_mb barrier, see comments for
+ * waitqueue_active why.
+ */
+ if (wq_has_sleeper(wq))
+ wake_up(wq);
+}
+
+static inline void cond_wake_up_nomb(struct wait_queue_head *wq)
+{
+ /*
+ * Special case for conditional wakeup where the barrier required for
+ * waitqueue_active is implied by some of the preceding code. Eg. one
+ * of such atomic operations (atomic_dec_and_return, ...), or a
+ * unlock/lock sequence, etc.
+ */
+ if (waitqueue_active(wq))
+ wake_up(wq);
+}
+
#endif
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 06ec8ab..fe6caa7 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -460,13 +460,10 @@ static void finish_one_item(struct btrfs_delayed_root *delayed_root)
{
int seq = atomic_inc_return(&delayed_root->items_seq);
- /*
- * atomic_dec_return implies a barrier for waitqueue_active
- */
+ /* atomic_dec_return implies a barrier */
if ((atomic_dec_return(&delayed_root->items) <
- BTRFS_DELAYED_BACKGROUND || seq % BTRFS_DELAYED_BATCH == 0) &&
- waitqueue_active(&delayed_root->wait))
- wake_up(&delayed_root->wait);
+ BTRFS_DELAYED_BACKGROUND || seq % BTRFS_DELAYED_BATCH == 0))
+ cond_wake_up_nomb(&delayed_root->wait);
}
static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item)
@@ -556,6 +553,12 @@ static int btrfs_delayed_item_reserve_metadata(struct btrfs_trans_handle *trans,
dst_rsv = &fs_info->delayed_block_rsv;
num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
+
+ /*
+ * Here we migrate space rsv from transaction rsv, since have already
+ * reserved space when starting a transaction. So no need to reserve
+ * qgroup space here.
+ */
ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1);
if (!ret) {
trace_btrfs_space_reservation(fs_info, "delayed_item",
@@ -577,7 +580,10 @@ static void btrfs_delayed_item_release_metadata(struct btrfs_root *root,
return;
rsv = &fs_info->delayed_block_rsv;
- btrfs_qgroup_convert_reserved_meta(root, item->bytes_reserved);
+ /*
+ * Check btrfs_delayed_item_reserve_metadata() to see why we don't need
+ * to release/reserve qgroup space.
+ */
trace_btrfs_space_reservation(fs_info, "delayed_item",
item->key.objectid, item->bytes_reserved,
0);
@@ -602,9 +608,6 @@ static int btrfs_delayed_inode_reserve_metadata(
num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
- ret = btrfs_qgroup_reserve_meta_prealloc(root, num_bytes, true);
- if (ret < 0)
- return ret;
/*
* btrfs_dirty_inode will update the inode under btrfs_join_transaction
* which doesn't reserve space for speed. This is a problem since we
@@ -616,6 +619,10 @@ static int btrfs_delayed_inode_reserve_metadata(
*/
if (!src_rsv || (!trans->bytes_reserved &&
src_rsv->type != BTRFS_BLOCK_RSV_DELALLOC)) {
+ ret = btrfs_qgroup_reserve_meta_prealloc(root,
+ fs_info->nodesize, true);
+ if (ret < 0)
+ return ret;
ret = btrfs_block_rsv_add(root, dst_rsv, num_bytes,
BTRFS_RESERVE_NO_FLUSH);
/*
@@ -634,6 +641,8 @@ static int btrfs_delayed_inode_reserve_metadata(
"delayed_inode",
btrfs_ino(inode),
num_bytes, 1);
+ } else {
+ btrfs_qgroup_free_meta_prealloc(root, fs_info->nodesize);
}
return ret;
}
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 9e98295..03dec67 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -286,10 +286,10 @@ static bool merge_ref(struct btrfs_trans_handle *trans,
}
void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_delayed_ref_root *delayed_refs,
struct btrfs_delayed_ref_head *head)
{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_delayed_ref_node *ref;
struct rb_node *node;
u64 seq = 0;
@@ -323,9 +323,7 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
}
}
-int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
- struct btrfs_delayed_ref_root *delayed_refs,
- u64 seq)
+int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq)
{
struct seq_list *elem;
int ret = 0;
@@ -336,10 +334,9 @@ int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
struct seq_list, list);
if (seq >= elem->seq) {
btrfs_debug(fs_info,
- "holding back delayed_ref %#x.%x, lowest is %#x.%x (%p)",
+ "holding back delayed_ref %#x.%x, lowest is %#x.%x",
(u32)(seq >> 32), (u32)seq,
- (u32)(elem->seq >> 32), (u32)elem->seq,
- delayed_refs);
+ (u32)(elem->seq >> 32), (u32)elem->seq);
ret = 1;
}
}
@@ -529,31 +526,20 @@ update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs,
spin_unlock(&existing->lock);
}
-/*
- * helper function to actually insert a head node into the rbtree.
- * this does all the dirty work in terms of maintaining the correct
- * overall modification count.
- */
-static noinline struct btrfs_delayed_ref_head *
-add_delayed_ref_head(struct btrfs_fs_info *fs_info,
- struct btrfs_trans_handle *trans,
- struct btrfs_delayed_ref_head *head_ref,
- struct btrfs_qgroup_extent_record *qrecord,
- u64 bytenr, u64 num_bytes, u64 ref_root, u64 reserved,
- int action, int is_data, int *qrecord_inserted_ret,
- int *old_ref_mod, int *new_ref_mod)
+static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref,
+ struct btrfs_qgroup_extent_record *qrecord,
+ u64 bytenr, u64 num_bytes, u64 ref_root,
+ u64 reserved, int action, bool is_data,
+ bool is_system)
{
- struct btrfs_delayed_ref_head *existing;
- struct btrfs_delayed_ref_root *delayed_refs;
int count_mod = 1;
int must_insert_reserved = 0;
- int qrecord_inserted = 0;
/* If reserved is provided, it must be a data extent. */
BUG_ON(!is_data && reserved);
/*
- * the head node stores the sum of all the mods, so dropping a ref
+ * The head node stores the sum of all the mods, so dropping a ref
* should drop the sum in the head node by one.
*/
if (action == BTRFS_UPDATE_DELAYED_HEAD)
@@ -562,12 +548,11 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
count_mod = -1;
/*
- * BTRFS_ADD_DELAYED_EXTENT means that we need to update
- * the reserved accounting when the extent is finally added, or
- * if a later modification deletes the delayed ref without ever
- * inserting the extent into the extent allocation tree.
- * ref->must_insert_reserved is the flag used to record
- * that accounting mods are required.
+ * BTRFS_ADD_DELAYED_EXTENT means that we need to update the reserved
+ * accounting when the extent is finally added, or if a later
+ * modification deletes the delayed ref without ever inserting the
+ * extent into the extent allocation tree. ref->must_insert_reserved
+ * is the flag used to record that accounting mods are required.
*
* Once we record must_insert_reserved, switch the action to
* BTRFS_ADD_DELAYED_REF because other special casing is not required.
@@ -577,14 +562,13 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
else
must_insert_reserved = 0;
- delayed_refs = &trans->transaction->delayed_refs;
-
refcount_set(&head_ref->refs, 1);
head_ref->bytenr = bytenr;
head_ref->num_bytes = num_bytes;
head_ref->ref_mod = count_mod;
head_ref->must_insert_reserved = must_insert_reserved;
head_ref->is_data = is_data;
+ head_ref->is_system = is_system;
head_ref->ref_tree = RB_ROOT;
INIT_LIST_HEAD(&head_ref->ref_add_list);
RB_CLEAR_NODE(&head_ref->href_node);
@@ -595,7 +579,6 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
spin_lock_init(&head_ref->lock);
mutex_init(&head_ref->mutex);
- /* Record qgroup extent info if provided */
if (qrecord) {
if (ref_root && reserved) {
head_ref->qgroup_ref_root = ref_root;
@@ -605,20 +588,44 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
qrecord->bytenr = bytenr;
qrecord->num_bytes = num_bytes;
qrecord->old_roots = NULL;
+ }
+}
- if(btrfs_qgroup_trace_extent_nolock(fs_info,
+/*
+ * helper function to actually insert a head node into the rbtree.
+ * this does all the dirty work in terms of maintaining the correct
+ * overall modification count.
+ */
+static noinline struct btrfs_delayed_ref_head *
+add_delayed_ref_head(struct btrfs_trans_handle *trans,
+ struct btrfs_delayed_ref_head *head_ref,
+ struct btrfs_qgroup_extent_record *qrecord,
+ int action, int *qrecord_inserted_ret,
+ int *old_ref_mod, int *new_ref_mod)
+{
+ struct btrfs_delayed_ref_head *existing;
+ struct btrfs_delayed_ref_root *delayed_refs;
+ int qrecord_inserted = 0;
+
+ delayed_refs = &trans->transaction->delayed_refs;
+
+ /* Record qgroup extent info if provided */
+ if (qrecord) {
+ if (btrfs_qgroup_trace_extent_nolock(trans->fs_info,
delayed_refs, qrecord))
kfree(qrecord);
else
qrecord_inserted = 1;
}
- trace_add_delayed_ref_head(fs_info, head_ref, action);
+ trace_add_delayed_ref_head(trans->fs_info, head_ref, action);
existing = htree_insert(&delayed_refs->href_root,
&head_ref->href_node);
if (existing) {
- WARN_ON(ref_root && reserved && existing->qgroup_ref_root
+ WARN_ON(qrecord && head_ref->qgroup_ref_root
+ && head_ref->qgroup_reserved
+ && existing->qgroup_ref_root
&& existing->qgroup_reserved);
update_existing_head_ref(delayed_refs, existing, head_ref,
old_ref_mod);
@@ -631,8 +638,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
} else {
if (old_ref_mod)
*old_ref_mod = 0;
- if (is_data && count_mod < 0)
- delayed_refs->pending_csums += num_bytes;
+ if (head_ref->is_data && head_ref->ref_mod < 0)
+ delayed_refs->pending_csums += head_ref->num_bytes;
delayed_refs->num_heads++;
delayed_refs->num_heads_ready++;
atomic_inc(&delayed_refs->num_entries);
@@ -642,33 +649,48 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
*qrecord_inserted_ret = qrecord_inserted;
if (new_ref_mod)
*new_ref_mod = head_ref->total_ref_mod;
+
return head_ref;
}
/*
- * helper to insert a delayed tree ref into the rbtree.
+ * init_delayed_ref_common - Initialize the structure which represents a
+ * modification to a an extent.
+ *
+ * @fs_info: Internal to the mounted filesystem mount structure.
+ *
+ * @ref: The structure which is going to be initialized.
+ *
+ * @bytenr: The logical address of the extent for which a modification is
+ * going to be recorded.
+ *
+ * @num_bytes: Size of the extent whose modification is being recorded.
+ *
+ * @ref_root: The id of the root where this modification has originated, this
+ * can be either one of the well-known metadata trees or the
+ * subvolume id which references this extent.
+ *
+ * @action: Can be one of BTRFS_ADD_DELAYED_REF/BTRFS_DROP_DELAYED_REF or
+ * BTRFS_ADD_DELAYED_EXTENT
+ *
+ * @ref_type: Holds the type of the extent which is being recorded, can be
+ * one of BTRFS_SHARED_BLOCK_REF_KEY/BTRFS_TREE_BLOCK_REF_KEY
+ * when recording a metadata extent or BTRFS_SHARED_DATA_REF_KEY/
+ * BTRFS_EXTENT_DATA_REF_KEY when recording data extent
*/
-static noinline void
-add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
- struct btrfs_trans_handle *trans,
- struct btrfs_delayed_ref_head *head_ref,
- struct btrfs_delayed_ref_node *ref, u64 bytenr,
- u64 num_bytes, u64 parent, u64 ref_root, int level,
- int action)
+static void init_delayed_ref_common(struct btrfs_fs_info *fs_info,
+ struct btrfs_delayed_ref_node *ref,
+ u64 bytenr, u64 num_bytes, u64 ref_root,
+ int action, u8 ref_type)
{
- struct btrfs_delayed_tree_ref *full_ref;
- struct btrfs_delayed_ref_root *delayed_refs;
u64 seq = 0;
- int ret;
if (action == BTRFS_ADD_DELAYED_EXTENT)
action = BTRFS_ADD_DELAYED_REF;
if (is_fstree(ref_root))
seq = atomic64_read(&fs_info->tree_mod_seq);
- delayed_refs = &trans->transaction->delayed_refs;
- /* first set the basic ref node struct up */
refcount_set(&ref->refs, 1);
ref->bytenr = bytenr;
ref->num_bytes = num_bytes;
@@ -677,82 +699,9 @@ add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
ref->is_head = 0;
ref->in_tree = 1;
ref->seq = seq;
+ ref->type = ref_type;
RB_CLEAR_NODE(&ref->ref_node);
INIT_LIST_HEAD(&ref->add_list);
-
- full_ref = btrfs_delayed_node_to_tree_ref(ref);
- full_ref->parent = parent;
- full_ref->root = ref_root;
- if (parent)
- ref->type = BTRFS_SHARED_BLOCK_REF_KEY;
- else
- ref->type = BTRFS_TREE_BLOCK_REF_KEY;
- full_ref->level = level;
-
- trace_add_delayed_tree_ref(fs_info, ref, full_ref, action);
-
- ret = insert_delayed_ref(trans, delayed_refs, head_ref, ref);
-
- /*
- * XXX: memory should be freed at the same level allocated.
- * But bad practice is anywhere... Follow it now. Need cleanup.
- */
- if (ret > 0)
- kmem_cache_free(btrfs_delayed_tree_ref_cachep, full_ref);
-}
-
-/*
- * helper to insert a delayed data ref into the rbtree.
- */
-static noinline void
-add_delayed_data_ref(struct btrfs_fs_info *fs_info,
- struct btrfs_trans_handle *trans,
- struct btrfs_delayed_ref_head *head_ref,
- struct btrfs_delayed_ref_node *ref, u64 bytenr,
- u64 num_bytes, u64 parent, u64 ref_root, u64 owner,
- u64 offset, int action)
-{
- struct btrfs_delayed_data_ref *full_ref;
- struct btrfs_delayed_ref_root *delayed_refs;
- u64 seq = 0;
- int ret;
-
- if (action == BTRFS_ADD_DELAYED_EXTENT)
- action = BTRFS_ADD_DELAYED_REF;
-
- delayed_refs = &trans->transaction->delayed_refs;
-
- if (is_fstree(ref_root))
- seq = atomic64_read(&fs_info->tree_mod_seq);
-
- /* first set the basic ref node struct up */
- refcount_set(&ref->refs, 1);
- ref->bytenr = bytenr;
- ref->num_bytes = num_bytes;
- ref->ref_mod = 1;
- ref->action = action;
- ref->is_head = 0;
- ref->in_tree = 1;
- ref->seq = seq;
- RB_CLEAR_NODE(&ref->ref_node);
- INIT_LIST_HEAD(&ref->add_list);
-
- full_ref = btrfs_delayed_node_to_data_ref(ref);
- full_ref->parent = parent;
- full_ref->root = ref_root;
- if (parent)
- ref->type = BTRFS_SHARED_DATA_REF_KEY;
- else
- ref->type = BTRFS_EXTENT_DATA_REF_KEY;
-
- full_ref->objectid = owner;
- full_ref->offset = offset;
-
- trace_add_delayed_data_ref(fs_info, ref, full_ref, action);
-
- ret = insert_delayed_ref(trans, delayed_refs, head_ref, ref);
- if (ret > 0)
- kmem_cache_free(btrfs_delayed_data_ref_cachep, full_ref);
}
/*
@@ -772,12 +721,25 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
struct btrfs_delayed_ref_root *delayed_refs;
struct btrfs_qgroup_extent_record *record = NULL;
int qrecord_inserted;
+ bool is_system = (ref_root == BTRFS_CHUNK_TREE_OBJECTID);
+ int ret;
+ u8 ref_type;
BUG_ON(extent_op && extent_op->is_data);
ref = kmem_cache_alloc(btrfs_delayed_tree_ref_cachep, GFP_NOFS);
if (!ref)
return -ENOMEM;
+ if (parent)
+ ref_type = BTRFS_SHARED_BLOCK_REF_KEY;
+ else
+ ref_type = BTRFS_TREE_BLOCK_REF_KEY;
+ init_delayed_ref_common(fs_info, &ref->node, bytenr, num_bytes,
+ ref_root, action, ref_type);
+ ref->root = ref_root;
+ ref->parent = parent;
+ ref->level = level;
+
head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
if (!head_ref)
goto free_ref;
@@ -789,6 +751,8 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
goto free_head_ref;
}
+ init_delayed_ref_head(head_ref, record, bytenr, num_bytes,
+ ref_root, 0, action, false, is_system);
head_ref->extent_op = extent_op;
delayed_refs = &trans->transaction->delayed_refs;
@@ -798,15 +762,19 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
* insert both the head node and the new ref without dropping
* the spin lock
*/
- head_ref = add_delayed_ref_head(fs_info, trans, head_ref, record,
- bytenr, num_bytes, 0, 0, action, 0,
- &qrecord_inserted, old_ref_mod,
- new_ref_mod);
+ head_ref = add_delayed_ref_head(trans, head_ref, record,
+ action, &qrecord_inserted,
+ old_ref_mod, new_ref_mod);
- add_delayed_tree_ref(fs_info, trans, head_ref, &ref->node, bytenr,
- num_bytes, parent, ref_root, level, action);
+ ret = insert_delayed_ref(trans, delayed_refs, head_ref, &ref->node);
spin_unlock(&delayed_refs->lock);
+ trace_add_delayed_tree_ref(fs_info, &ref->node, ref,
+ action == BTRFS_ADD_DELAYED_EXTENT ?
+ BTRFS_ADD_DELAYED_REF : action);
+ if (ret > 0)
+ kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
+
if (qrecord_inserted)
btrfs_qgroup_trace_extent_post(fs_info, record);
@@ -835,11 +803,25 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
struct btrfs_delayed_ref_root *delayed_refs;
struct btrfs_qgroup_extent_record *record = NULL;
int qrecord_inserted;
+ int ret;
+ u8 ref_type;
ref = kmem_cache_alloc(btrfs_delayed_data_ref_cachep, GFP_NOFS);
if (!ref)
return -ENOMEM;
+ if (parent)
+ ref_type = BTRFS_SHARED_DATA_REF_KEY;
+ else
+ ref_type = BTRFS_EXTENT_DATA_REF_KEY;
+ init_delayed_ref_common(fs_info, &ref->node, bytenr, num_bytes,
+ ref_root, action, ref_type);
+ ref->root = ref_root;
+ ref->parent = parent;
+ ref->objectid = owner;
+ ref->offset = offset;
+
+
head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
if (!head_ref) {
kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
@@ -857,6 +839,8 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
}
}
+ init_delayed_ref_head(head_ref, record, bytenr, num_bytes, ref_root,
+ reserved, action, true, false);
head_ref->extent_op = NULL;
delayed_refs = &trans->transaction->delayed_refs;
@@ -866,16 +850,20 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
* insert both the head node and the new ref without dropping
* the spin lock
*/
- head_ref = add_delayed_ref_head(fs_info, trans, head_ref, record,
- bytenr, num_bytes, ref_root, reserved,
- action, 1, &qrecord_inserted,
+ head_ref = add_delayed_ref_head(trans, head_ref, record,
+ action, &qrecord_inserted,
old_ref_mod, new_ref_mod);
- add_delayed_data_ref(fs_info, trans, head_ref, &ref->node, bytenr,
- num_bytes, parent, ref_root, owner, offset,
- action);
+ ret = insert_delayed_ref(trans, delayed_refs, head_ref, &ref->node);
spin_unlock(&delayed_refs->lock);
+ trace_add_delayed_data_ref(trans->fs_info, &ref->node, ref,
+ action == BTRFS_ADD_DELAYED_EXTENT ?
+ BTRFS_ADD_DELAYED_REF : action);
+ if (ret > 0)
+ kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
+
+
if (qrecord_inserted)
return btrfs_qgroup_trace_extent_post(fs_info, record);
return 0;
@@ -893,14 +881,16 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
if (!head_ref)
return -ENOMEM;
+ init_delayed_ref_head(head_ref, NULL, bytenr, num_bytes, 0, 0,
+ BTRFS_UPDATE_DELAYED_HEAD, extent_op->is_data,
+ false);
head_ref->extent_op = extent_op;
delayed_refs = &trans->transaction->delayed_refs;
spin_lock(&delayed_refs->lock);
- add_delayed_ref_head(fs_info, trans, head_ref, NULL, bytenr,
- num_bytes, 0, 0, BTRFS_UPDATE_DELAYED_HEAD,
- extent_op->is_data, NULL, NULL, NULL);
+ add_delayed_ref_head(trans, head_ref, NULL, BTRFS_UPDATE_DELAYED_HEAD,
+ NULL, NULL, NULL);
spin_unlock(&delayed_refs->lock);
return 0;
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index 741869d..ea1aecb 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -127,6 +127,7 @@ struct btrfs_delayed_ref_head {
*/
unsigned int must_insert_reserved:1;
unsigned int is_data:1;
+ unsigned int is_system:1;
unsigned int processing:1;
};
@@ -250,7 +251,6 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
u64 bytenr, u64 num_bytes,
struct btrfs_delayed_extent_op *extent_op);
void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_delayed_ref_root *delayed_refs,
struct btrfs_delayed_ref_head *head);
@@ -268,9 +268,7 @@ static inline void btrfs_delayed_ref_unlock(struct btrfs_delayed_ref_head *head)
struct btrfs_delayed_ref_head *
btrfs_select_ref_head(struct btrfs_trans_handle *trans);
-int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
- struct btrfs_delayed_ref_root *delayed_refs,
- u64 seq);
+int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq);
/*
* helper functions to cast a node into its container
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index f82be26..e2ba041 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -33,8 +33,6 @@ static void btrfs_dev_replace_update_device_in_mapping_tree(
struct btrfs_device *srcdev,
struct btrfs_device *tgtdev);
static int btrfs_dev_replace_kthread(void *data);
-static int btrfs_dev_replace_continue_on_mount(struct btrfs_fs_info *fs_info);
-
int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info)
{
@@ -179,6 +177,105 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info)
}
/*
+ * Initialize a new device for device replace target from a given source dev
+ * and path.
+ *
+ * Return 0 and new device in @device_out, otherwise return < 0
+ */
+static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
+ const char *device_path,
+ struct btrfs_device *srcdev,
+ struct btrfs_device **device_out)
+{
+ struct btrfs_device *device;
+ struct block_device *bdev;
+ struct list_head *devices;
+ struct rcu_string *name;
+ u64 devid = BTRFS_DEV_REPLACE_DEVID;
+ int ret = 0;
+
+ *device_out = NULL;
+ if (fs_info->fs_devices->seeding) {
+ btrfs_err(fs_info, "the filesystem is a seed filesystem!");
+ return -EINVAL;
+ }
+
+ bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
+ fs_info->bdev_holder);
+ if (IS_ERR(bdev)) {
+ btrfs_err(fs_info, "target device %s is invalid!", device_path);
+ return PTR_ERR(bdev);
+ }
+
+ filemap_write_and_wait(bdev->bd_inode->i_mapping);
+
+ devices = &fs_info->fs_devices->devices;
+ list_for_each_entry(device, devices, dev_list) {
+ if (device->bdev == bdev) {
+ btrfs_err(fs_info,
+ "target device is in the filesystem!");
+ ret = -EEXIST;
+ goto error;
+ }
+ }
+
+
+ if (i_size_read(bdev->bd_inode) <
+ btrfs_device_get_total_bytes(srcdev)) {
+ btrfs_err(fs_info,
+ "target device is smaller than source device!");
+ ret = -EINVAL;
+ goto error;
+ }
+
+
+ device = btrfs_alloc_device(NULL, &devid, NULL);
+ if (IS_ERR(device)) {
+ ret = PTR_ERR(device);
+ goto error;
+ }
+
+ name = rcu_string_strdup(device_path, GFP_KERNEL);
+ if (!name) {
+ btrfs_free_device(device);
+ ret = -ENOMEM;
+ goto error;
+ }
+ rcu_assign_pointer(device->name, name);
+
+ mutex_lock(&fs_info->fs_devices->device_list_mutex);
+ set_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
+ device->generation = 0;
+ device->io_width = fs_info->sectorsize;
+ device->io_align = fs_info->sectorsize;
+ device->sector_size = fs_info->sectorsize;
+ device->total_bytes = btrfs_device_get_total_bytes(srcdev);
+ device->disk_total_bytes = btrfs_device_get_disk_total_bytes(srcdev);
+ device->bytes_used = btrfs_device_get_bytes_used(srcdev);
+ device->commit_total_bytes = srcdev->commit_total_bytes;
+ device->commit_bytes_used = device->bytes_used;
+ device->fs_info = fs_info;
+ device->bdev = bdev;
+ set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
+ set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
+ device->mode = FMODE_EXCL;
+ device->dev_stats_valid = 1;
+ set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
+ device->fs_devices = fs_info->fs_devices;
+ list_add(&device->dev_list, &fs_info->fs_devices->devices);
+ fs_info->fs_devices->num_devices++;
+ fs_info->fs_devices->open_devices++;
+ mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+
+ *device_out = device;
+ return 0;
+
+error:
+ blkdev_put(bdev, FMODE_EXCL);
+ return ret;
+}
+
+/*
* called from commit_transaction. Writes changed device replace state to
* disk.
*/
@@ -317,18 +414,13 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
struct btrfs_device *tgt_device = NULL;
struct btrfs_device *src_device = NULL;
- /* the disk copy procedure reuses the scrub code */
- mutex_lock(&fs_info->volume_mutex);
ret = btrfs_find_device_by_devspec(fs_info, srcdevid,
srcdev_name, &src_device);
- if (ret) {
- mutex_unlock(&fs_info->volume_mutex);
+ if (ret)
return ret;
- }
ret = btrfs_init_dev_replace_tgtdev(fs_info, tgtdev_name,
src_device, &tgt_device);
- mutex_unlock(&fs_info->volume_mutex);
if (ret)
return ret;
@@ -360,7 +452,6 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
dev_replace->cont_reading_from_srcdev_mode = read_src;
WARN_ON(!src_device);
dev_replace->srcdev = src_device;
- WARN_ON(!tgt_device);
dev_replace->tgtdev = tgt_device;
btrfs_info_in_rcu(fs_info,
@@ -503,7 +594,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
* flush all outstanding I/O and inode extent mappings before the
* copy operation is declared as being finished
*/
- ret = btrfs_start_delalloc_roots(fs_info, 0, -1);
+ ret = btrfs_start_delalloc_roots(fs_info, -1);
if (ret) {
mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
return ret;
@@ -518,7 +609,6 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
ret = btrfs_commit_transaction(trans);
WARN_ON(ret);
- mutex_lock(&uuid_mutex);
/* keep away write_all_supers() during the finishing procedure */
mutex_lock(&fs_info->fs_devices->device_list_mutex);
mutex_lock(&fs_info->chunk_mutex);
@@ -545,7 +635,6 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
btrfs_dev_replace_write_unlock(dev_replace);
mutex_unlock(&fs_info->chunk_mutex);
mutex_unlock(&fs_info->fs_devices->device_list_mutex);
- mutex_unlock(&uuid_mutex);
btrfs_rm_dev_replace_blocked(fs_info);
if (tgt_device)
btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
@@ -596,7 +685,6 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
*/
mutex_unlock(&fs_info->chunk_mutex);
mutex_unlock(&fs_info->fs_devices->device_list_mutex);
- mutex_unlock(&uuid_mutex);
/* replace the sysfs entry */
btrfs_sysfs_rm_device_link(fs_info->fs_devices, src_device);
@@ -800,7 +888,17 @@ int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info)
}
btrfs_dev_replace_write_unlock(dev_replace);
- WARN_ON(test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags));
+ /*
+ * This could collide with a paused balance, but the exclusive op logic
+ * should never allow both to start and pause. We don't want to allow
+ * dev-replace to start anyway.
+ */
+ if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
+ btrfs_info(fs_info,
+ "cannot resume dev-replace, other exclusive operation running");
+ return 0;
+ }
+
task = kthread_run(btrfs_dev_replace_kthread, fs_info, "btrfs-devrepl");
return PTR_ERR_OR_ZERO(task);
}
@@ -810,6 +908,7 @@ static int btrfs_dev_replace_kthread(void *data)
struct btrfs_fs_info *fs_info = data;
struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
u64 progress;
+ int ret;
progress = btrfs_dev_replace_progress(fs_info);
progress = div_u64(progress, 10);
@@ -820,23 +919,14 @@ static int btrfs_dev_replace_kthread(void *data)
btrfs_dev_name(dev_replace->tgtdev),
(unsigned int)progress);
- btrfs_dev_replace_continue_on_mount(fs_info);
- clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
-
- return 0;
-}
-
-static int btrfs_dev_replace_continue_on_mount(struct btrfs_fs_info *fs_info)
-{
- struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
- int ret;
-
ret = btrfs_scrub_dev(fs_info, dev_replace->srcdev->devid,
dev_replace->committed_cursor_left,
btrfs_device_get_total_bytes(dev_replace->srcdev),
&dev_replace->scrub_progress, 0, 1);
ret = btrfs_dev_replace_finishing(fs_info, ret);
WARN_ON(ret);
+
+ clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
return 0;
}
@@ -916,9 +1006,9 @@ void btrfs_dev_replace_clear_lock_blocking(
ASSERT(atomic_read(&dev_replace->read_locks) > 0);
ASSERT(atomic_read(&dev_replace->blocking_readers) > 0);
read_lock(&dev_replace->lock);
- if (atomic_dec_and_test(&dev_replace->blocking_readers) &&
- waitqueue_active(&dev_replace->read_lock_wq))
- wake_up(&dev_replace->read_lock_wq);
+ /* Barrier implied by atomic_dec_and_test */
+ if (atomic_dec_and_test(&dev_replace->blocking_readers))
+ cond_wake_up_nomb(&dev_replace->read_lock_wq);
}
void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info)
@@ -929,9 +1019,7 @@ void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info)
void btrfs_bio_counter_sub(struct btrfs_fs_info *fs_info, s64 amount)
{
percpu_counter_sub(&fs_info->bio_counter, amount);
-
- if (waitqueue_active(&fs_info->replace_wait))
- wake_up(&fs_info->replace_wait);
+ cond_wake_up_nomb(&fs_info->replace_wait);
}
void btrfs_bio_counter_inc_blocked(struct btrfs_fs_info *fs_info)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 4ac8b1d..205092d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -55,7 +55,6 @@
static const struct extent_io_ops btree_extent_io_ops;
static void end_workqueue_fn(struct btrfs_work *work);
static void free_fs_root(struct btrfs_root *root);
-static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info);
static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
struct btrfs_fs_info *fs_info);
@@ -416,7 +415,7 @@ static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info,
static int verify_level_key(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb, int level,
- struct btrfs_key *first_key)
+ struct btrfs_key *first_key, u64 parent_transid)
{
int found_level;
struct btrfs_key found_key;
@@ -454,10 +453,11 @@ static int verify_level_key(struct btrfs_fs_info *fs_info,
if (ret) {
WARN_ON(1);
btrfs_err(fs_info,
-"tree first key mismatch detected, bytenr=%llu key expected=(%llu, %u, %llu) has=(%llu, %u, %llu)",
- eb->start, first_key->objectid, first_key->type,
- first_key->offset, found_key.objectid,
- found_key.type, found_key.offset);
+"tree first key mismatch detected, bytenr=%llu parent_transid=%llu key expected=(%llu,%u,%llu) has=(%llu,%u,%llu)",
+ eb->start, parent_transid, first_key->objectid,
+ first_key->type, first_key->offset,
+ found_key.objectid, found_key.type,
+ found_key.offset);
}
#endif
return ret;
@@ -493,7 +493,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info,
parent_transid, 0))
ret = -EIO;
else if (verify_level_key(fs_info, eb, level,
- first_key))
+ first_key, parent_transid))
ret = -EUCLEAN;
else
break;
@@ -1185,7 +1185,6 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
root->inode_tree = RB_ROOT;
INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC);
root->block_rsv = NULL;
- root->orphan_block_rsv = NULL;
INIT_LIST_HEAD(&root->dirty_list);
INIT_LIST_HEAD(&root->root_list);
@@ -1195,7 +1194,6 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
INIT_LIST_HEAD(&root->ordered_root);
INIT_LIST_HEAD(&root->logged_list[0]);
INIT_LIST_HEAD(&root->logged_list[1]);
- spin_lock_init(&root->orphan_lock);
spin_lock_init(&root->inode_lock);
spin_lock_init(&root->delalloc_lock);
spin_lock_init(&root->ordered_extent_lock);
@@ -1216,7 +1214,6 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
atomic_set(&root->log_commit[1], 0);
atomic_set(&root->log_writers, 0);
atomic_set(&root->log_batch, 0);
- atomic_set(&root->orphan_inodes, 0);
refcount_set(&root->refs, 1);
atomic_set(&root->will_be_snapshotted, 0);
root->log_transid = 0;
@@ -1824,6 +1821,7 @@ static int transaction_kthread(void *arg)
now = get_seconds();
if (cur->state < TRANS_STATE_BLOCKED &&
+ !test_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags) &&
(now < cur->start_time ||
now - cur->start_time < fs_info->commit_interval)) {
spin_unlock(&fs_info->trans_lock);
@@ -2163,7 +2161,6 @@ static void btrfs_init_balance(struct btrfs_fs_info *fs_info)
{
spin_lock_init(&fs_info->balance_lock);
mutex_init(&fs_info->balance_mutex);
- atomic_set(&fs_info->balance_running, 0);
atomic_set(&fs_info->balance_pause_req, 0);
atomic_set(&fs_info->balance_cancel_req, 0);
fs_info->balance_ctl = NULL;
@@ -2441,6 +2438,211 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
return ret;
}
+/*
+ * Real super block validation
+ * NOTE: super csum type and incompat features will not be checked here.
+ *
+ * @sb: super block to check
+ * @mirror_num: the super block number to check its bytenr:
+ * 0 the primary (1st) sb
+ * 1, 2 2nd and 3rd backup copy
+ * -1 skip bytenr check
+ */
+static int validate_super(struct btrfs_fs_info *fs_info,
+ struct btrfs_super_block *sb, int mirror_num)
+{
+ u64 nodesize = btrfs_super_nodesize(sb);
+ u64 sectorsize = btrfs_super_sectorsize(sb);
+ int ret = 0;
+
+ if (btrfs_super_magic(sb) != BTRFS_MAGIC) {
+ btrfs_err(fs_info, "no valid FS found");
+ ret = -EINVAL;
+ }
+ if (btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP) {
+ btrfs_err(fs_info, "unrecognized or unsupported super flag: %llu",
+ btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP);
+ ret = -EINVAL;
+ }
+ if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) {
+ btrfs_err(fs_info, "tree_root level too big: %d >= %d",
+ btrfs_super_root_level(sb), BTRFS_MAX_LEVEL);
+ ret = -EINVAL;
+ }
+ if (btrfs_super_chunk_root_level(sb) >= BTRFS_MAX_LEVEL) {
+ btrfs_err(fs_info, "chunk_root level too big: %d >= %d",
+ btrfs_super_chunk_root_level(sb), BTRFS_MAX_LEVEL);
+ ret = -EINVAL;
+ }
+ if (btrfs_super_log_root_level(sb) >= BTRFS_MAX_LEVEL) {
+ btrfs_err(fs_info, "log_root level too big: %d >= %d",
+ btrfs_super_log_root_level(sb), BTRFS_MAX_LEVEL);
+ ret = -EINVAL;
+ }
+
+ /*
+ * Check sectorsize and nodesize first, other check will need it.
+ * Check all possible sectorsize(4K, 8K, 16K, 32K, 64K) here.
+ */
+ if (!is_power_of_2(sectorsize) || sectorsize < 4096 ||
+ sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) {
+ btrfs_err(fs_info, "invalid sectorsize %llu", sectorsize);
+ ret = -EINVAL;
+ }
+ /* Only PAGE SIZE is supported yet */
+ if (sectorsize != PAGE_SIZE) {
+ btrfs_err(fs_info,
+ "sectorsize %llu not supported yet, only support %lu",
+ sectorsize, PAGE_SIZE);
+ ret = -EINVAL;
+ }
+ if (!is_power_of_2(nodesize) || nodesize < sectorsize ||
+ nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) {
+ btrfs_err(fs_info, "invalid nodesize %llu", nodesize);
+ ret = -EINVAL;
+ }
+ if (nodesize != le32_to_cpu(sb->__unused_leafsize)) {
+ btrfs_err(fs_info, "invalid leafsize %u, should be %llu",
+ le32_to_cpu(sb->__unused_leafsize), nodesize);
+ ret = -EINVAL;
+ }
+
+ /* Root alignment check */
+ if (!IS_ALIGNED(btrfs_super_root(sb), sectorsize)) {
+ btrfs_warn(fs_info, "tree_root block unaligned: %llu",
+ btrfs_super_root(sb));
+ ret = -EINVAL;
+ }
+ if (!IS_ALIGNED(btrfs_super_chunk_root(sb), sectorsize)) {
+ btrfs_warn(fs_info, "chunk_root block unaligned: %llu",
+ btrfs_super_chunk_root(sb));
+ ret = -EINVAL;
+ }
+ if (!IS_ALIGNED(btrfs_super_log_root(sb), sectorsize)) {
+ btrfs_warn(fs_info, "log_root block unaligned: %llu",
+ btrfs_super_log_root(sb));
+ ret = -EINVAL;
+ }
+
+ if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_FSID_SIZE) != 0) {
+ btrfs_err(fs_info,
+ "dev_item UUID does not match fsid: %pU != %pU",
+ fs_info->fsid, sb->dev_item.fsid);
+ ret = -EINVAL;
+ }
+
+ /*
+ * Hint to catch really bogus numbers, bitflips or so, more exact checks are
+ * done later
+ */
+ if (btrfs_super_bytes_used(sb) < 6 * btrfs_super_nodesize(sb)) {
+ btrfs_err(fs_info, "bytes_used is too small %llu",
+ btrfs_super_bytes_used(sb));
+ ret = -EINVAL;
+ }
+ if (!is_power_of_2(btrfs_super_stripesize(sb))) {
+ btrfs_err(fs_info, "invalid stripesize %u",
+ btrfs_super_stripesize(sb));
+ ret = -EINVAL;
+ }
+ if (btrfs_super_num_devices(sb) > (1UL << 31))
+ btrfs_warn(fs_info, "suspicious number of devices: %llu",
+ btrfs_super_num_devices(sb));
+ if (btrfs_super_num_devices(sb) == 0) {
+ btrfs_err(fs_info, "number of devices is 0");
+ ret = -EINVAL;
+ }
+
+ if (mirror_num >= 0 &&
+ btrfs_super_bytenr(sb) != btrfs_sb_offset(mirror_num)) {
+ btrfs_err(fs_info, "super offset mismatch %llu != %u",
+ btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET);
+ ret = -EINVAL;
+ }
+
+ /*
+ * Obvious sys_chunk_array corruptions, it must hold at least one key
+ * and one chunk
+ */
+ if (btrfs_super_sys_array_size(sb) > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) {
+ btrfs_err(fs_info, "system chunk array too big %u > %u",
+ btrfs_super_sys_array_size(sb),
+ BTRFS_SYSTEM_CHUNK_ARRAY_SIZE);
+ ret = -EINVAL;
+ }
+ if (btrfs_super_sys_array_size(sb) < sizeof(struct btrfs_disk_key)
+ + sizeof(struct btrfs_chunk)) {
+ btrfs_err(fs_info, "system chunk array too small %u < %zu",
+ btrfs_super_sys_array_size(sb),
+ sizeof(struct btrfs_disk_key)
+ + sizeof(struct btrfs_chunk));
+ ret = -EINVAL;
+ }
+
+ /*
+ * The generation is a global counter, we'll trust it more than the others
+ * but it's still possible that it's the one that's wrong.
+ */
+ if (btrfs_super_generation(sb) < btrfs_super_chunk_root_generation(sb))
+ btrfs_warn(fs_info,
+ "suspicious: generation < chunk_root_generation: %llu < %llu",
+ btrfs_super_generation(sb),
+ btrfs_super_chunk_root_generation(sb));
+ if (btrfs_super_generation(sb) < btrfs_super_cache_generation(sb)
+ && btrfs_super_cache_generation(sb) != (u64)-1)
+ btrfs_warn(fs_info,
+ "suspicious: generation < cache_generation: %llu < %llu",
+ btrfs_super_generation(sb),
+ btrfs_super_cache_generation(sb));
+
+ return ret;
+}
+
+/*
+ * Validation of super block at mount time.
+ * Some checks already done early at mount time, like csum type and incompat
+ * flags will be skipped.
+ */
+static int btrfs_validate_mount_super(struct btrfs_fs_info *fs_info)
+{
+ return validate_super(fs_info, fs_info->super_copy, 0);
+}
+
+/*
+ * Validation of super block at write time.
+ * Some checks like bytenr check will be skipped as their values will be
+ * overwritten soon.
+ * Extra checks like csum type and incompat flags will be done here.
+ */
+static int btrfs_validate_write_super(struct btrfs_fs_info *fs_info,
+ struct btrfs_super_block *sb)
+{
+ int ret;
+
+ ret = validate_super(fs_info, sb, -1);
+ if (ret < 0)
+ goto out;
+ if (btrfs_super_csum_type(sb) != BTRFS_CSUM_TYPE_CRC32) {
+ ret = -EUCLEAN;
+ btrfs_err(fs_info, "invalid csum type, has %u want %u",
+ btrfs_super_csum_type(sb), BTRFS_CSUM_TYPE_CRC32);
+ goto out;
+ }
+ if (btrfs_super_incompat_flags(sb) & ~BTRFS_FEATURE_INCOMPAT_SUPP) {
+ ret = -EUCLEAN;
+ btrfs_err(fs_info,
+ "invalid incompat flags, has 0x%llx valid mask 0x%llx",
+ btrfs_super_incompat_flags(sb),
+ (unsigned long long)BTRFS_FEATURE_INCOMPAT_SUPP);
+ goto out;
+ }
+out:
+ if (ret < 0)
+ btrfs_err(fs_info,
+ "super block corruption detected before writing it to disk");
+ return ret;
+}
+
int open_ctree(struct super_block *sb,
struct btrfs_fs_devices *fs_devices,
char *options)
@@ -2600,7 +2802,6 @@ int open_ctree(struct super_block *sb,
mutex_init(&fs_info->chunk_mutex);
mutex_init(&fs_info->transaction_kthread_mutex);
mutex_init(&fs_info->cleaner_mutex);
- mutex_init(&fs_info->volume_mutex);
mutex_init(&fs_info->ro_block_group_mutex);
init_rwsem(&fs_info->commit_root_sem);
init_rwsem(&fs_info->cleanup_work_sem);
@@ -2667,7 +2868,7 @@ int open_ctree(struct super_block *sb,
memcpy(fs_info->fsid, fs_info->super_copy->fsid, BTRFS_FSID_SIZE);
- ret = btrfs_check_super_valid(fs_info);
+ ret = btrfs_validate_mount_super(fs_info);
if (ret) {
btrfs_err(fs_info, "superblock contains fatal errors");
err = -EINVAL;
@@ -3522,7 +3723,7 @@ int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags)
for (raid_type = 0; raid_type < BTRFS_NR_RAID_TYPES; raid_type++) {
if (raid_type == BTRFS_RAID_SINGLE)
continue;
- if (!(flags & btrfs_raid_group[raid_type]))
+ if (!(flags & btrfs_raid_array[raid_type].bg_flag))
continue;
min_tolerated = min(min_tolerated,
btrfs_raid_array[raid_type].
@@ -3602,6 +3803,14 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors)
flags = btrfs_super_flags(sb);
btrfs_set_super_flags(sb, flags | BTRFS_HEADER_FLAG_WRITTEN);
+ ret = btrfs_validate_write_super(fs_info, sb);
+ if (ret < 0) {
+ mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+ btrfs_handle_fs_error(fs_info, -EUCLEAN,
+ "unexpected superblock corruption detected");
+ return -EUCLEAN;
+ }
+
ret = write_dev_supers(dev, sb, max_mirrors);
if (ret)
total_errors++;
@@ -3673,8 +3882,6 @@ static void free_fs_root(struct btrfs_root *root)
{
iput(root->ino_cache_inode);
WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
- btrfs_free_block_rsv(root->fs_info, root->orphan_block_rsv);
- root->orphan_block_rsv = NULL;
if (root->anon_dev)
free_anon_bdev(root->anon_dev);
if (root->subv_writers)
@@ -3765,7 +3972,6 @@ int btrfs_commit_super(struct btrfs_fs_info *fs_info)
void close_ctree(struct btrfs_fs_info *fs_info)
{
- struct btrfs_root *root = fs_info->tree_root;
int ret;
set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags);
@@ -3817,6 +4023,7 @@ void close_ctree(struct btrfs_fs_info *fs_info)
set_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags);
btrfs_free_qgroup_config(fs_info);
+ ASSERT(list_empty(&fs_info->delalloc_roots));
if (percpu_counter_sum(&fs_info->delalloc_bytes)) {
btrfs_info(fs_info, "at unmount delalloc count %lld",
@@ -3860,9 +4067,6 @@ void close_ctree(struct btrfs_fs_info *fs_info)
btrfs_free_stripe_hash_table(fs_info);
btrfs_free_ref_cache(fs_info);
- __btrfs_free_block_rsv(root->orphan_block_rsv);
- root->orphan_block_rsv = NULL;
-
while (!list_empty(&fs_info->pinned_chunks)) {
struct extent_map *em;
@@ -3973,166 +4177,17 @@ int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid, int level,
level, first_key);
}
-static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info)
-{
- struct btrfs_super_block *sb = fs_info->super_copy;
- u64 nodesize = btrfs_super_nodesize(sb);
- u64 sectorsize = btrfs_super_sectorsize(sb);
- int ret = 0;
-
- if (btrfs_super_magic(sb) != BTRFS_MAGIC) {
- btrfs_err(fs_info, "no valid FS found");
- ret = -EINVAL;
- }
- if (btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP) {
- btrfs_err(fs_info, "unrecognized or unsupported super flag: %llu",
- btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP);
- ret = -EINVAL;
- }
- if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) {
- btrfs_err(fs_info, "tree_root level too big: %d >= %d",
- btrfs_super_root_level(sb), BTRFS_MAX_LEVEL);
- ret = -EINVAL;
- }
- if (btrfs_super_chunk_root_level(sb) >= BTRFS_MAX_LEVEL) {
- btrfs_err(fs_info, "chunk_root level too big: %d >= %d",
- btrfs_super_chunk_root_level(sb), BTRFS_MAX_LEVEL);
- ret = -EINVAL;
- }
- if (btrfs_super_log_root_level(sb) >= BTRFS_MAX_LEVEL) {
- btrfs_err(fs_info, "log_root level too big: %d >= %d",
- btrfs_super_log_root_level(sb), BTRFS_MAX_LEVEL);
- ret = -EINVAL;
- }
-
- /*
- * Check sectorsize and nodesize first, other check will need it.
- * Check all possible sectorsize(4K, 8K, 16K, 32K, 64K) here.
- */
- if (!is_power_of_2(sectorsize) || sectorsize < 4096 ||
- sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) {
- btrfs_err(fs_info, "invalid sectorsize %llu", sectorsize);
- ret = -EINVAL;
- }
- /* Only PAGE SIZE is supported yet */
- if (sectorsize != PAGE_SIZE) {
- btrfs_err(fs_info,
- "sectorsize %llu not supported yet, only support %lu",
- sectorsize, PAGE_SIZE);
- ret = -EINVAL;
- }
- if (!is_power_of_2(nodesize) || nodesize < sectorsize ||
- nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) {
- btrfs_err(fs_info, "invalid nodesize %llu", nodesize);
- ret = -EINVAL;
- }
- if (nodesize != le32_to_cpu(sb->__unused_leafsize)) {
- btrfs_err(fs_info, "invalid leafsize %u, should be %llu",
- le32_to_cpu(sb->__unused_leafsize), nodesize);
- ret = -EINVAL;
- }
-
- /* Root alignment check */
- if (!IS_ALIGNED(btrfs_super_root(sb), sectorsize)) {
- btrfs_warn(fs_info, "tree_root block unaligned: %llu",
- btrfs_super_root(sb));
- ret = -EINVAL;
- }
- if (!IS_ALIGNED(btrfs_super_chunk_root(sb), sectorsize)) {
- btrfs_warn(fs_info, "chunk_root block unaligned: %llu",
- btrfs_super_chunk_root(sb));
- ret = -EINVAL;
- }
- if (!IS_ALIGNED(btrfs_super_log_root(sb), sectorsize)) {
- btrfs_warn(fs_info, "log_root block unaligned: %llu",
- btrfs_super_log_root(sb));
- ret = -EINVAL;
- }
-
- if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_FSID_SIZE) != 0) {
- btrfs_err(fs_info,
- "dev_item UUID does not match fsid: %pU != %pU",
- fs_info->fsid, sb->dev_item.fsid);
- ret = -EINVAL;
- }
-
- /*
- * Hint to catch really bogus numbers, bitflips or so, more exact checks are
- * done later
- */
- if (btrfs_super_bytes_used(sb) < 6 * btrfs_super_nodesize(sb)) {
- btrfs_err(fs_info, "bytes_used is too small %llu",
- btrfs_super_bytes_used(sb));
- ret = -EINVAL;
- }
- if (!is_power_of_2(btrfs_super_stripesize(sb))) {
- btrfs_err(fs_info, "invalid stripesize %u",
- btrfs_super_stripesize(sb));
- ret = -EINVAL;
- }
- if (btrfs_super_num_devices(sb) > (1UL << 31))
- btrfs_warn(fs_info, "suspicious number of devices: %llu",
- btrfs_super_num_devices(sb));
- if (btrfs_super_num_devices(sb) == 0) {
- btrfs_err(fs_info, "number of devices is 0");
- ret = -EINVAL;
- }
-
- if (btrfs_super_bytenr(sb) != BTRFS_SUPER_INFO_OFFSET) {
- btrfs_err(fs_info, "super offset mismatch %llu != %u",
- btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET);
- ret = -EINVAL;
- }
-
- /*
- * Obvious sys_chunk_array corruptions, it must hold at least one key
- * and one chunk
- */
- if (btrfs_super_sys_array_size(sb) > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) {
- btrfs_err(fs_info, "system chunk array too big %u > %u",
- btrfs_super_sys_array_size(sb),
- BTRFS_SYSTEM_CHUNK_ARRAY_SIZE);
- ret = -EINVAL;
- }
- if (btrfs_super_sys_array_size(sb) < sizeof(struct btrfs_disk_key)
- + sizeof(struct btrfs_chunk)) {
- btrfs_err(fs_info, "system chunk array too small %u < %zu",
- btrfs_super_sys_array_size(sb),
- sizeof(struct btrfs_disk_key)
- + sizeof(struct btrfs_chunk));
- ret = -EINVAL;
- }
-
- /*
- * The generation is a global counter, we'll trust it more than the others
- * but it's still possible that it's the one that's wrong.
- */
- if (btrfs_super_generation(sb) < btrfs_super_chunk_root_generation(sb))
- btrfs_warn(fs_info,
- "suspicious: generation < chunk_root_generation: %llu < %llu",
- btrfs_super_generation(sb),
- btrfs_super_chunk_root_generation(sb));
- if (btrfs_super_generation(sb) < btrfs_super_cache_generation(sb)
- && btrfs_super_cache_generation(sb) != (u64)-1)
- btrfs_warn(fs_info,
- "suspicious: generation < cache_generation: %llu < %llu",
- btrfs_super_generation(sb),
- btrfs_super_cache_generation(sb));
-
- return ret;
-}
-
static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info)
{
+ /* cleanup FS via transaction */
+ btrfs_cleanup_transaction(fs_info);
+
mutex_lock(&fs_info->cleaner_mutex);
btrfs_run_delayed_iputs(fs_info);
mutex_unlock(&fs_info->cleaner_mutex);
down_write(&fs_info->cleanup_work_sem);
up_write(&fs_info->cleanup_work_sem);
-
- /* cleanup FS via transaction */
- btrfs_cleanup_transaction(fs_info);
}
static void btrfs_destroy_ordered_extents(struct btrfs_root *root)
@@ -4257,19 +4312,23 @@ static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root)
list_splice_init(&root->delalloc_inodes, &splice);
while (!list_empty(&splice)) {
+ struct inode *inode = NULL;
btrfs_inode = list_first_entry(&splice, struct btrfs_inode,
delalloc_inodes);
-
- list_del_init(&btrfs_inode->delalloc_inodes);
- clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
- &btrfs_inode->runtime_flags);
+ __btrfs_del_delalloc_inode(root, btrfs_inode);
spin_unlock(&root->delalloc_lock);
- btrfs_invalidate_inodes(btrfs_inode->root);
-
+ /*
+ * Make sure we get a live inode and that it'll not disappear
+ * meanwhile.
+ */
+ inode = igrab(&btrfs_inode->vfs_inode);
+ if (inode) {
+ invalidate_inode_pages2(inode->i_mapping);
+ iput(inode);
+ }
spin_lock(&root->delalloc_lock);
}
-
spin_unlock(&root->delalloc_lock);
}
@@ -4285,7 +4344,6 @@ static void btrfs_destroy_all_delalloc_inodes(struct btrfs_fs_info *fs_info)
while (!list_empty(&splice)) {
root = list_first_entry(&splice, struct btrfs_root,
delalloc_root);
- list_del_init(&root->delalloc_root);
root = btrfs_grab_fs_root(root);
BUG_ON(!root);
spin_unlock(&fs_info->delalloc_root_lock);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 75cfb80..3d9fe58 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -66,10 +66,8 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
u64 flags, u64 owner, u64 offset,
struct btrfs_key *ins, int ref_mod);
static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
- u64 parent, u64 root_objectid,
- u64 flags, struct btrfs_disk_key *key,
- int level, struct btrfs_key *ins);
+ struct btrfs_delayed_ref_node *node,
+ struct btrfs_delayed_extent_op *extent_op);
static int do_chunk_alloc(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 flags,
int force);
@@ -256,7 +254,7 @@ static int exclude_super_stripes(struct btrfs_fs_info *fs_info,
for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
bytenr = btrfs_sb_offset(i);
ret = btrfs_rmap_block(fs_info, cache->key.objectid,
- bytenr, 0, &logical, &nr, &stripe_len);
+ bytenr, &logical, &nr, &stripe_len);
if (ret)
return ret;
@@ -343,8 +341,9 @@ static void fragment_free_space(struct btrfs_block_group_cache *block_group)
* since their free space will be released as soon as the transaction commits.
*/
u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
- struct btrfs_fs_info *info, u64 start, u64 end)
+ u64 start, u64 end)
{
+ struct btrfs_fs_info *info = block_group->fs_info;
u64 extent_start, extent_end, size, total_added = 0;
int ret;
@@ -489,8 +488,7 @@ static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl)
if (key.type == BTRFS_EXTENT_ITEM_KEY ||
key.type == BTRFS_METADATA_ITEM_KEY) {
- total_found += add_new_free_space(block_group,
- fs_info, last,
+ total_found += add_new_free_space(block_group, last,
key.objectid);
if (key.type == BTRFS_METADATA_ITEM_KEY)
last = key.objectid +
@@ -508,7 +506,7 @@ static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl)
}
ret = 0;
- total_found += add_new_free_space(block_group, fs_info, last,
+ total_found += add_new_free_space(block_group, last,
block_group->key.objectid +
block_group->key.offset);
caching_ctl->progress = (u64)-1;
@@ -744,12 +742,12 @@ static struct btrfs_space_info *__find_space_info(struct btrfs_fs_info *info,
}
static void add_pinned_bytes(struct btrfs_fs_info *fs_info, s64 num_bytes,
- u64 owner, u64 root_objectid)
+ bool metadata, u64 root_objectid)
{
struct btrfs_space_info *space_info;
u64 flags;
- if (owner < BTRFS_FIRST_FREE_OBJECTID) {
+ if (metadata) {
if (root_objectid == BTRFS_CHUNK_TREE_OBJECTID)
flags = BTRFS_BLOCK_GROUP_SYSTEM;
else
@@ -2200,8 +2198,11 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
&old_ref_mod, &new_ref_mod);
}
- if (ret == 0 && old_ref_mod < 0 && new_ref_mod >= 0)
- add_pinned_bytes(fs_info, -num_bytes, owner, root_objectid);
+ if (ret == 0 && old_ref_mod < 0 && new_ref_mod >= 0) {
+ bool metadata = owner < BTRFS_FIRST_FREE_OBJECTID;
+
+ add_pinned_bytes(fs_info, -num_bytes, metadata, root_objectid);
+ }
return ret;
}
@@ -2428,10 +2429,8 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
{
int ret = 0;
struct btrfs_delayed_tree_ref *ref;
- struct btrfs_key ins;
u64 parent = 0;
u64 ref_root = 0;
- bool skinny_metadata = btrfs_fs_incompat(fs_info, SKINNY_METADATA);
ref = btrfs_delayed_node_to_tree_ref(node);
trace_run_delayed_tree_ref(fs_info, node, ref, node->action);
@@ -2440,15 +2439,6 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
parent = ref->parent;
ref_root = ref->root;
- ins.objectid = node->bytenr;
- if (skinny_metadata) {
- ins.offset = ref->level;
- ins.type = BTRFS_METADATA_ITEM_KEY;
- } else {
- ins.offset = node->num_bytes;
- ins.type = BTRFS_EXTENT_ITEM_KEY;
- }
-
if (node->ref_mod != 1) {
btrfs_err(fs_info,
"btree block(%llu) has %d references rather than 1: action %d ref_root %llu parent %llu",
@@ -2458,11 +2448,7 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
}
if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) {
BUG_ON(!extent_op || !extent_op->update_flags);
- ret = alloc_reserved_tree_block(trans, fs_info,
- parent, ref_root,
- extent_op->flags_to_set,
- &extent_op->key,
- ref->level, &ins);
+ ret = alloc_reserved_tree_block(trans, node, extent_op);
} else if (node->action == BTRFS_ADD_DELAYED_REF) {
ret = __btrfs_inc_extent_ref(trans, fs_info, node,
parent, ref_root,
@@ -2594,20 +2580,26 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans,
delayed_refs->num_heads--;
rb_erase(&head->href_node, &delayed_refs->href_root);
RB_CLEAR_NODE(&head->href_node);
- spin_unlock(&delayed_refs->lock);
spin_unlock(&head->lock);
+ spin_unlock(&delayed_refs->lock);
atomic_dec(&delayed_refs->num_entries);
trace_run_delayed_ref_head(fs_info, head, 0);
if (head->total_ref_mod < 0) {
- struct btrfs_block_group_cache *cache;
+ struct btrfs_space_info *space_info;
+ u64 flags;
- cache = btrfs_lookup_block_group(fs_info, head->bytenr);
- ASSERT(cache);
- percpu_counter_add(&cache->space_info->total_bytes_pinned,
+ if (head->is_data)
+ flags = BTRFS_BLOCK_GROUP_DATA;
+ else if (head->is_system)
+ flags = BTRFS_BLOCK_GROUP_SYSTEM;
+ else
+ flags = BTRFS_BLOCK_GROUP_METADATA;
+ space_info = __find_space_info(fs_info, flags);
+ ASSERT(space_info);
+ percpu_counter_add(&space_info->total_bytes_pinned,
-head->num_bytes);
- btrfs_put_block_group(cache);
if (head->is_data) {
spin_lock(&delayed_refs->lock);
@@ -2694,17 +2686,12 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
* insert_inline_extent_backref()).
*/
spin_lock(&locked_ref->lock);
- btrfs_merge_delayed_refs(trans, fs_info, delayed_refs,
- locked_ref);
+ btrfs_merge_delayed_refs(trans, delayed_refs, locked_ref);
- /*
- * locked_ref is the head node, so we have to go one
- * node back for any delayed ref updates
- */
ref = select_delayed_ref(locked_ref);
if (ref && ref->seq &&
- btrfs_check_delayed_seq(fs_info, delayed_refs, ref->seq)) {
+ btrfs_check_delayed_seq(fs_info, ref->seq)) {
spin_unlock(&locked_ref->lock);
unselect_delayed_ref_head(delayed_refs, locked_ref);
locked_ref = NULL;
@@ -3136,7 +3123,11 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
struct rb_node *node;
int ret = 0;
+ spin_lock(&root->fs_info->trans_lock);
cur_trans = root->fs_info->running_transaction;
+ if (cur_trans)
+ refcount_inc(&cur_trans->use_count);
+ spin_unlock(&root->fs_info->trans_lock);
if (!cur_trans)
return 0;
@@ -3145,6 +3136,7 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
if (!head) {
spin_unlock(&delayed_refs->lock);
+ btrfs_put_transaction(cur_trans);
return 0;
}
@@ -3161,6 +3153,7 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
mutex_lock(&head->mutex);
mutex_unlock(&head->mutex);
btrfs_put_delayed_ref_head(head);
+ btrfs_put_transaction(cur_trans);
return -EAGAIN;
}
spin_unlock(&delayed_refs->lock);
@@ -3193,6 +3186,7 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
}
spin_unlock(&head->lock);
mutex_unlock(&head->mutex);
+ btrfs_put_transaction(cur_trans);
return ret;
}
@@ -3278,7 +3272,7 @@ int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset,
path = btrfs_alloc_path();
if (!path)
- return -ENOENT;
+ return -ENOMEM;
do {
ret = check_committed_ref(root, path, objectid,
@@ -4013,8 +4007,7 @@ static const char *alloc_name(u64 flags)
};
}
-static int create_space_info(struct btrfs_fs_info *info, u64 flags,
- struct btrfs_space_info **new)
+static int create_space_info(struct btrfs_fs_info *info, u64 flags)
{
struct btrfs_space_info *space_info;
@@ -4052,7 +4045,6 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags,
return ret;
}
- *new = space_info;
list_add_rcu(&space_info->list, &info->space_info);
if (flags & BTRFS_BLOCK_GROUP_DATA)
info->data_sinfo = space_info;
@@ -4109,7 +4101,7 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
* returns target flags in extended format or 0 if restripe for this
* chunk_type is not in progress
*
- * should be called with either volume_mutex or balance_lock held
+ * should be called with balance_lock held
*/
static u64 get_restripe_target(struct btrfs_fs_info *fs_info, u64 flags)
{
@@ -4165,7 +4157,7 @@ static u64 btrfs_reduce_alloc_profile(struct btrfs_fs_info *fs_info, u64 flags)
/* First, mask out the RAID levels which aren't possible */
for (raid_type = 0; raid_type < BTRFS_NR_RAID_TYPES; raid_type++) {
if (num_devices >= btrfs_raid_array[raid_type].devs_min)
- allowed |= btrfs_raid_group[raid_type];
+ allowed |= btrfs_raid_array[raid_type].bg_flag;
}
allowed &= flags;
@@ -4328,7 +4320,7 @@ int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes)
need_commit--;
if (need_commit > 0) {
- btrfs_start_delalloc_roots(fs_info, 0, -1);
+ btrfs_start_delalloc_roots(fs_info, -1);
btrfs_wait_ordered_roots(fs_info, U64_MAX, 0,
(u64)-1);
}
@@ -4665,12 +4657,14 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans,
trans->allocating_chunk = false;
spin_lock(&space_info->lock);
- if (ret < 0 && ret != -ENOSPC)
- goto out;
- if (ret)
- space_info->full = 1;
- else
+ if (ret < 0) {
+ if (ret == -ENOSPC)
+ space_info->full = 1;
+ else
+ goto out;
+ } else {
ret = 1;
+ }
space_info->force_alloc = CHUNK_ALLOC_NO_FORCE;
out:
@@ -4779,7 +4773,7 @@ static void btrfs_writeback_inodes_sb_nr(struct btrfs_fs_info *fs_info,
* the filesystem is readonly(all dirty pages are written to
* the disk).
*/
- btrfs_start_delalloc_roots(fs_info, 0, nr_items);
+ btrfs_start_delalloc_roots(fs_info, nr_items);
if (!current->journal_info)
btrfs_wait_ordered_roots(fs_info, nr_items, 0, (u64)-1);
}
@@ -5559,14 +5553,18 @@ static void space_info_add_new_bytes(struct btrfs_fs_info *fs_info,
static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *block_rsv,
- struct btrfs_block_rsv *dest, u64 num_bytes)
+ struct btrfs_block_rsv *dest, u64 num_bytes,
+ u64 *qgroup_to_release_ret)
{
struct btrfs_space_info *space_info = block_rsv->space_info;
+ u64 qgroup_to_release = 0;
u64 ret;
spin_lock(&block_rsv->lock);
- if (num_bytes == (u64)-1)
+ if (num_bytes == (u64)-1) {
num_bytes = block_rsv->size;
+ qgroup_to_release = block_rsv->qgroup_rsv_size;
+ }
block_rsv->size -= num_bytes;
if (block_rsv->reserved >= block_rsv->size) {
num_bytes = block_rsv->reserved - block_rsv->size;
@@ -5575,6 +5573,13 @@ static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
} else {
num_bytes = 0;
}
+ if (block_rsv->qgroup_rsv_reserved >= block_rsv->qgroup_rsv_size) {
+ qgroup_to_release = block_rsv->qgroup_rsv_reserved -
+ block_rsv->qgroup_rsv_size;
+ block_rsv->qgroup_rsv_reserved = block_rsv->qgroup_rsv_size;
+ } else {
+ qgroup_to_release = 0;
+ }
spin_unlock(&block_rsv->lock);
ret = num_bytes;
@@ -5597,6 +5602,8 @@ static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
space_info_add_old_bytes(fs_info, space_info,
num_bytes);
}
+ if (qgroup_to_release_ret)
+ *qgroup_to_release_ret = qgroup_to_release;
return ret;
}
@@ -5738,17 +5745,21 @@ static int btrfs_inode_rsv_refill(struct btrfs_inode *inode,
struct btrfs_root *root = inode->root;
struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
u64 num_bytes = 0;
+ u64 qgroup_num_bytes = 0;
int ret = -ENOSPC;
spin_lock(&block_rsv->lock);
if (block_rsv->reserved < block_rsv->size)
num_bytes = block_rsv->size - block_rsv->reserved;
+ if (block_rsv->qgroup_rsv_reserved < block_rsv->qgroup_rsv_size)
+ qgroup_num_bytes = block_rsv->qgroup_rsv_size -
+ block_rsv->qgroup_rsv_reserved;
spin_unlock(&block_rsv->lock);
if (num_bytes == 0)
return 0;
- ret = btrfs_qgroup_reserve_meta_prealloc(root, num_bytes, true);
+ ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_num_bytes, true);
if (ret)
return ret;
ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
@@ -5756,7 +5767,13 @@ static int btrfs_inode_rsv_refill(struct btrfs_inode *inode,
block_rsv_add_bytes(block_rsv, num_bytes, 0);
trace_btrfs_space_reservation(root->fs_info, "delalloc",
btrfs_ino(inode), num_bytes, 1);
- }
+
+ /* Don't forget to increase qgroup_rsv_reserved */
+ spin_lock(&block_rsv->lock);
+ block_rsv->qgroup_rsv_reserved += qgroup_num_bytes;
+ spin_unlock(&block_rsv->lock);
+ } else
+ btrfs_qgroup_free_meta_prealloc(root, qgroup_num_bytes);
return ret;
}
@@ -5777,20 +5794,23 @@ static void btrfs_inode_rsv_release(struct btrfs_inode *inode, bool qgroup_free)
struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
u64 released = 0;
+ u64 qgroup_to_release = 0;
/*
* Since we statically set the block_rsv->size we just want to say we
* are releasing 0 bytes, and then we'll just get the reservation over
* the size free'd.
*/
- released = block_rsv_release_bytes(fs_info, block_rsv, global_rsv, 0);
+ released = block_rsv_release_bytes(fs_info, block_rsv, global_rsv, 0,
+ &qgroup_to_release);
if (released > 0)
trace_btrfs_space_reservation(fs_info, "delalloc",
btrfs_ino(inode), released, 0);
if (qgroup_free)
- btrfs_qgroup_free_meta_prealloc(inode->root, released);
+ btrfs_qgroup_free_meta_prealloc(inode->root, qgroup_to_release);
else
- btrfs_qgroup_convert_reserved_meta(inode->root, released);
+ btrfs_qgroup_convert_reserved_meta(inode->root,
+ qgroup_to_release);
}
void btrfs_block_rsv_release(struct btrfs_fs_info *fs_info,
@@ -5802,7 +5822,7 @@ void btrfs_block_rsv_release(struct btrfs_fs_info *fs_info,
if (global_rsv == block_rsv ||
block_rsv->space_info != global_rsv->space_info)
global_rsv = NULL;
- block_rsv_release_bytes(fs_info, block_rsv, global_rsv, num_bytes);
+ block_rsv_release_bytes(fs_info, block_rsv, global_rsv, num_bytes, NULL);
}
static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
@@ -5882,7 +5902,7 @@ static void init_global_block_rsv(struct btrfs_fs_info *fs_info)
static void release_global_block_rsv(struct btrfs_fs_info *fs_info)
{
block_rsv_release_bytes(fs_info, &fs_info->global_block_rsv, NULL,
- (u64)-1);
+ (u64)-1, NULL);
WARN_ON(fs_info->trans_block_rsv.size > 0);
WARN_ON(fs_info->trans_block_rsv.reserved > 0);
WARN_ON(fs_info->chunk_block_rsv.size > 0);
@@ -5906,48 +5926,10 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans)
WARN_ON_ONCE(!list_empty(&trans->new_bgs));
block_rsv_release_bytes(fs_info, &fs_info->chunk_block_rsv, NULL,
- trans->chunk_bytes_reserved);
+ trans->chunk_bytes_reserved, NULL);
trans->chunk_bytes_reserved = 0;
}
-/* Can only return 0 or -ENOSPC */
-int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
- struct btrfs_inode *inode)
-{
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
- struct btrfs_root *root = inode->root;
- /*
- * We always use trans->block_rsv here as we will have reserved space
- * for our orphan when starting the transaction, using get_block_rsv()
- * here will sometimes make us choose the wrong block rsv as we could be
- * doing a reloc inode for a non refcounted root.
- */
- struct btrfs_block_rsv *src_rsv = trans->block_rsv;
- struct btrfs_block_rsv *dst_rsv = root->orphan_block_rsv;
-
- /*
- * We need to hold space in order to delete our orphan item once we've
- * added it, so this takes the reservation so we can release it later
- * when we are truly done with the orphan item.
- */
- u64 num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
-
- trace_btrfs_space_reservation(fs_info, "orphan", btrfs_ino(inode),
- num_bytes, 1);
- return btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1);
-}
-
-void btrfs_orphan_release_metadata(struct btrfs_inode *inode)
-{
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
- struct btrfs_root *root = inode->root;
- u64 num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
-
- trace_btrfs_space_reservation(fs_info, "orphan", btrfs_ino(inode),
- num_bytes, 0);
- btrfs_block_rsv_release(fs_info, root->orphan_block_rsv, num_bytes);
-}
-
/*
* btrfs_subvolume_reserve_metadata() - reserve space for subvolume operation
* root: the root of the parent directory
@@ -5965,7 +5947,6 @@ void btrfs_orphan_release_metadata(struct btrfs_inode *inode)
int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
struct btrfs_block_rsv *rsv,
int items,
- u64 *qgroup_reserved,
bool use_global_rsv)
{
u64 num_bytes;
@@ -5983,8 +5964,6 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
num_bytes = 0;
}
- *qgroup_reserved = num_bytes;
-
num_bytes = btrfs_calc_trans_metadata_size(fs_info, items);
rsv->space_info = __find_space_info(fs_info,
BTRFS_BLOCK_GROUP_METADATA);
@@ -5994,8 +5973,8 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
if (ret == -ENOSPC && use_global_rsv)
ret = btrfs_block_rsv_migrate(global_rsv, rsv, num_bytes, 1);
- if (ret && *qgroup_reserved)
- btrfs_qgroup_free_meta_prealloc(root, *qgroup_reserved);
+ if (ret && num_bytes)
+ btrfs_qgroup_free_meta_prealloc(root, num_bytes);
return ret;
}
@@ -6011,6 +5990,7 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
{
struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
u64 reserve_size = 0;
+ u64 qgroup_rsv_size = 0;
u64 csum_leaves;
unsigned outstanding_extents;
@@ -6023,9 +6003,17 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
inode->csum_bytes);
reserve_size += btrfs_calc_trans_metadata_size(fs_info,
csum_leaves);
+ /*
+ * For qgroup rsv, the calculation is very simple:
+ * account one nodesize for each outstanding extent
+ *
+ * This is overestimating in most cases.
+ */
+ qgroup_rsv_size = outstanding_extents * fs_info->nodesize;
spin_lock(&block_rsv->lock);
block_rsv->size = reserve_size;
+ block_rsv->qgroup_rsv_size = qgroup_rsv_size;
spin_unlock(&block_rsv->lock);
}
@@ -6306,6 +6294,7 @@ static int update_block_group(struct btrfs_trans_handle *trans,
spin_lock(&info->unused_bgs_lock);
if (list_empty(&cache->bg_list)) {
btrfs_get_block_group(cache);
+ trace_btrfs_add_unused_block_group(cache);
list_add_tail(&cache->bg_list,
&info->unused_bgs);
}
@@ -6463,6 +6452,7 @@ int btrfs_exclude_logged_extents(struct btrfs_fs_info *fs_info,
struct btrfs_key key;
int found_type;
int i;
+ int ret = 0;
if (!btrfs_fs_incompat(fs_info, MIXED_GROUPS))
return 0;
@@ -6479,10 +6469,12 @@ int btrfs_exclude_logged_extents(struct btrfs_fs_info *fs_info,
continue;
key.objectid = btrfs_file_extent_disk_bytenr(eb, item);
key.offset = btrfs_file_extent_disk_num_bytes(eb, item);
- __exclude_logged_extent(fs_info, key.objectid, key.offset);
+ ret = __exclude_logged_extent(fs_info, key.objectid, key.offset);
+ if (ret)
+ break;
}
- return 0;
+ return ret;
}
static void
@@ -7074,7 +7066,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
}
}
- ret = add_to_free_space_tree(trans, info, bytenr, num_bytes);
+ ret = add_to_free_space_tree(trans, bytenr, num_bytes);
if (ret) {
btrfs_abort_transaction(trans, ret);
goto out;
@@ -7218,7 +7210,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
}
out:
if (pin)
- add_pinned_bytes(fs_info, buf->len, btrfs_header_level(buf),
+ add_pinned_bytes(fs_info, buf->len, true,
root->root_key.objectid);
if (last_ref) {
@@ -7272,8 +7264,11 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans,
&old_ref_mod, &new_ref_mod);
}
- if (ret == 0 && old_ref_mod >= 0 && new_ref_mod < 0)
- add_pinned_bytes(fs_info, num_bytes, owner, root_objectid);
+ if (ret == 0 && old_ref_mod >= 0 && new_ref_mod < 0) {
+ bool metadata = owner < BTRFS_FIRST_FREE_OBJECTID;
+
+ add_pinned_bytes(fs_info, num_bytes, metadata, root_objectid);
+ }
return ret;
}
@@ -7325,24 +7320,6 @@ wait_block_group_cache_done(struct btrfs_block_group_cache *cache)
return ret;
}
-static const char *btrfs_raid_type_names[BTRFS_NR_RAID_TYPES] = {
- [BTRFS_RAID_RAID10] = "raid10",
- [BTRFS_RAID_RAID1] = "raid1",
- [BTRFS_RAID_DUP] = "dup",
- [BTRFS_RAID_RAID0] = "raid0",
- [BTRFS_RAID_SINGLE] = "single",
- [BTRFS_RAID_RAID5] = "raid5",
- [BTRFS_RAID_RAID6] = "raid6",
-};
-
-static const char *get_raid_name(enum btrfs_raid_types type)
-{
- if (type >= BTRFS_NR_RAID_TYPES)
- return NULL;
-
- return btrfs_raid_type_names[type];
-}
-
enum btrfs_loop_type {
LOOP_CACHING_NOWAIT = 0,
LOOP_CACHING_WAIT = 1,
@@ -7614,7 +7591,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
if (offset) {
/* we have a block, we're done */
spin_unlock(&last_ptr->refill_lock);
- trace_btrfs_reserve_extent_cluster(fs_info,
+ trace_btrfs_reserve_extent_cluster(
used_block_group,
search_start, num_bytes);
if (used_block_group != block_group) {
@@ -7687,7 +7664,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
if (offset) {
/* we found one, proceed */
spin_unlock(&last_ptr->refill_lock);
- trace_btrfs_reserve_extent_cluster(fs_info,
+ trace_btrfs_reserve_extent_cluster(
block_group, search_start,
num_bytes);
goto checks;
@@ -7787,8 +7764,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
ins->objectid = search_start;
ins->offset = num_bytes;
- trace_btrfs_reserve_extent(fs_info, block_group,
- search_start, num_bytes);
+ trace_btrfs_reserve_extent(block_group, search_start, num_bytes);
btrfs_release_block_group(block_group, delalloc);
break;
loop:
@@ -8136,8 +8112,7 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
btrfs_mark_buffer_dirty(path->nodes[0]);
btrfs_free_path(path);
- ret = remove_from_free_space_tree(trans, fs_info, ins->objectid,
- ins->offset);
+ ret = remove_from_free_space_tree(trans, ins->objectid, ins->offset);
if (ret)
return ret;
@@ -8152,37 +8127,52 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
}
static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
- u64 parent, u64 root_objectid,
- u64 flags, struct btrfs_disk_key *key,
- int level, struct btrfs_key *ins)
+ struct btrfs_delayed_ref_node *node,
+ struct btrfs_delayed_extent_op *extent_op)
{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
int ret;
struct btrfs_extent_item *extent_item;
+ struct btrfs_key extent_key;
struct btrfs_tree_block_info *block_info;
struct btrfs_extent_inline_ref *iref;
struct btrfs_path *path;
struct extent_buffer *leaf;
+ struct btrfs_delayed_tree_ref *ref;
u32 size = sizeof(*extent_item) + sizeof(*iref);
- u64 num_bytes = ins->offset;
+ u64 num_bytes;
+ u64 flags = extent_op->flags_to_set;
bool skinny_metadata = btrfs_fs_incompat(fs_info, SKINNY_METADATA);
- if (!skinny_metadata)
+ ref = btrfs_delayed_node_to_tree_ref(node);
+
+ extent_key.objectid = node->bytenr;
+ if (skinny_metadata) {
+ extent_key.offset = ref->level;
+ extent_key.type = BTRFS_METADATA_ITEM_KEY;
+ num_bytes = fs_info->nodesize;
+ } else {
+ extent_key.offset = node->num_bytes;
+ extent_key.type = BTRFS_EXTENT_ITEM_KEY;
size += sizeof(*block_info);
+ num_bytes = node->num_bytes;
+ }
path = btrfs_alloc_path();
if (!path) {
- btrfs_free_and_pin_reserved_extent(fs_info, ins->objectid,
+ btrfs_free_and_pin_reserved_extent(fs_info,
+ extent_key.objectid,
fs_info->nodesize);
return -ENOMEM;
}
path->leave_spinning = 1;
ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path,
- ins, size);
+ &extent_key, size);
if (ret) {
btrfs_free_path(path);
- btrfs_free_and_pin_reserved_extent(fs_info, ins->objectid,
+ btrfs_free_and_pin_reserved_extent(fs_info,
+ extent_key.objectid,
fs_info->nodesize);
return ret;
}
@@ -8197,42 +8187,41 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
if (skinny_metadata) {
iref = (struct btrfs_extent_inline_ref *)(extent_item + 1);
- num_bytes = fs_info->nodesize;
} else {
block_info = (struct btrfs_tree_block_info *)(extent_item + 1);
- btrfs_set_tree_block_key(leaf, block_info, key);
- btrfs_set_tree_block_level(leaf, block_info, level);
+ btrfs_set_tree_block_key(leaf, block_info, &extent_op->key);
+ btrfs_set_tree_block_level(leaf, block_info, ref->level);
iref = (struct btrfs_extent_inline_ref *)(block_info + 1);
}
- if (parent > 0) {
+ if (node->type == BTRFS_SHARED_BLOCK_REF_KEY) {
BUG_ON(!(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF));
btrfs_set_extent_inline_ref_type(leaf, iref,
BTRFS_SHARED_BLOCK_REF_KEY);
- btrfs_set_extent_inline_ref_offset(leaf, iref, parent);
+ btrfs_set_extent_inline_ref_offset(leaf, iref, ref->parent);
} else {
btrfs_set_extent_inline_ref_type(leaf, iref,
BTRFS_TREE_BLOCK_REF_KEY);
- btrfs_set_extent_inline_ref_offset(leaf, iref, root_objectid);
+ btrfs_set_extent_inline_ref_offset(leaf, iref, ref->root);
}
btrfs_mark_buffer_dirty(leaf);
btrfs_free_path(path);
- ret = remove_from_free_space_tree(trans, fs_info, ins->objectid,
+ ret = remove_from_free_space_tree(trans, extent_key.objectid,
num_bytes);
if (ret)
return ret;
- ret = update_block_group(trans, fs_info, ins->objectid,
+ ret = update_block_group(trans, fs_info, extent_key.objectid,
fs_info->nodesize, 1);
if (ret) { /* -ENOENT, logic error */
btrfs_err(fs_info, "update block group failed for %llu %llu",
- ins->objectid, ins->offset);
+ extent_key.objectid, extent_key.offset);
BUG();
}
- trace_btrfs_reserved_extent_alloc(fs_info, ins->objectid,
+ trace_btrfs_reserved_extent_alloc(fs_info, extent_key.objectid,
fs_info->nodesize);
return ret;
}
@@ -8403,7 +8392,7 @@ static void unuse_block_rsv(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *block_rsv, u32 blocksize)
{
block_rsv_add_bytes(block_rsv, blocksize, 0);
- block_rsv_release_bytes(fs_info, block_rsv, NULL, 0);
+ block_rsv_release_bytes(fs_info, block_rsv, NULL, 0, NULL);
}
/*
@@ -10125,8 +10114,7 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
} else if (btrfs_block_group_used(&cache->item) == 0) {
cache->last_byte_to_unpin = (u64)-1;
cache->cached = BTRFS_CACHE_FINISHED;
- add_new_free_space(cache, info,
- found_key.objectid,
+ add_new_free_space(cache, found_key.objectid,
found_key.objectid +
found_key.offset);
free_excluded_extents(info, cache);
@@ -10156,6 +10144,7 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
/* Should always be true but just in case. */
if (list_empty(&cache->bg_list)) {
btrfs_get_block_group(cache);
+ trace_btrfs_add_unused_block_group(cache);
list_add_tail(&cache->bg_list,
&info->unused_bgs);
}
@@ -10221,7 +10210,7 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
key.offset);
if (ret)
btrfs_abort_transaction(trans, ret);
- add_block_group_free_space(trans, fs_info, block_group);
+ add_block_group_free_space(trans, block_group);
/* already aborted the transaction if it failed. */
next:
list_del_init(&block_group->bg_list);
@@ -10262,7 +10251,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
return ret;
}
- add_new_free_space(cache, fs_info, chunk_offset, chunk_offset + size);
+ add_new_free_space(cache, chunk_offset, chunk_offset + size);
free_excluded_extents(fs_info, cache);
@@ -10343,6 +10332,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
BUG_ON(!block_group);
BUG_ON(!block_group->ro);
+ trace_btrfs_remove_block_group(block_group);
/*
* Free the reserved super bytes from this block group before
* remove it.
@@ -10600,7 +10590,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
mutex_unlock(&fs_info->chunk_mutex);
- ret = remove_block_group_free_space(trans, fs_info, block_group);
+ ret = remove_block_group_free_space(trans, block_group);
if (ret)
goto out;
@@ -10707,6 +10697,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
* the ro check in case balance is currently acting on
* this block group.
*/
+ trace_btrfs_skip_unused_block_group(block_group);
spin_unlock(&block_group->lock);
up_write(&space_info->groups_sem);
goto next;
@@ -10829,7 +10820,6 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
int btrfs_init_space_info(struct btrfs_fs_info *fs_info)
{
- struct btrfs_space_info *space_info;
struct btrfs_super_block *disk_super;
u64 features;
u64 flags;
@@ -10845,21 +10835,21 @@ int btrfs_init_space_info(struct btrfs_fs_info *fs_info)
mixed = 1;
flags = BTRFS_BLOCK_GROUP_SYSTEM;
- ret = create_space_info(fs_info, flags, &space_info);
+ ret = create_space_info(fs_info, flags);
if (ret)
goto out;
if (mixed) {
flags = BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA;
- ret = create_space_info(fs_info, flags, &space_info);
+ ret = create_space_info(fs_info, flags);
} else {
flags = BTRFS_BLOCK_GROUP_METADATA;
- ret = create_space_info(fs_info, flags, &space_info);
+ ret = create_space_info(fs_info, flags);
if (ret)
goto out;
flags = BTRFS_BLOCK_GROUP_DATA;
- ret = create_space_info(fs_info, flags, &space_info);
+ ret = create_space_info(fs_info, flags);
}
out:
return ret;
@@ -11044,12 +11034,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
void btrfs_end_write_no_snapshotting(struct btrfs_root *root)
{
percpu_counter_dec(&root->subv_writers->counter);
- /*
- * Make sure counter is updated before we wake up waiters.
- */
- smp_mb();
- if (waitqueue_active(&root->subv_writers->wait))
- wake_up(&root->subv_writers->wait);
+ cond_wake_up(&root->subv_writers->wait);
}
int btrfs_start_write_no_snapshotting(struct btrfs_root *root)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index e99b329..51fc015 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -26,7 +26,7 @@
static struct kmem_cache *extent_state_cache;
static struct kmem_cache *extent_buffer_cache;
-static struct bio_set *btrfs_bioset;
+static struct bio_set btrfs_bioset;
static inline bool extent_state_in_tree(const struct extent_state *state)
{
@@ -162,20 +162,18 @@ int __init extent_io_init(void)
if (!extent_buffer_cache)
goto free_state_cache;
- btrfs_bioset = bioset_create(BIO_POOL_SIZE,
- offsetof(struct btrfs_io_bio, bio),
- BIOSET_NEED_BVECS);
- if (!btrfs_bioset)
+ if (bioset_init(&btrfs_bioset, BIO_POOL_SIZE,
+ offsetof(struct btrfs_io_bio, bio),
+ BIOSET_NEED_BVECS))
goto free_buffer_cache;
- if (bioset_integrity_create(btrfs_bioset, BIO_POOL_SIZE))
+ if (bioset_integrity_create(&btrfs_bioset, BIO_POOL_SIZE))
goto free_bioset;
return 0;
free_bioset:
- bioset_free(btrfs_bioset);
- btrfs_bioset = NULL;
+ bioset_exit(&btrfs_bioset);
free_buffer_cache:
kmem_cache_destroy(extent_buffer_cache);
@@ -198,8 +196,7 @@ void __cold extent_io_exit(void)
rcu_barrier();
kmem_cache_destroy(extent_state_cache);
kmem_cache_destroy(extent_buffer_cache);
- if (btrfs_bioset)
- bioset_free(btrfs_bioset);
+ bioset_exit(&btrfs_bioset);
}
void extent_io_tree_init(struct extent_io_tree *tree,
@@ -2679,7 +2676,7 @@ struct bio *btrfs_bio_alloc(struct block_device *bdev, u64 first_byte)
{
struct bio *bio;
- bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, btrfs_bioset);
+ bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &btrfs_bioset);
bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector = first_byte >> 9;
btrfs_io_bio_init(btrfs_io_bio(bio));
@@ -2692,7 +2689,7 @@ struct bio *btrfs_bio_clone(struct bio *bio)
struct bio *new;
/* Bio allocation backed by a bioset does not fail */
- new = bio_clone_fast(bio, GFP_NOFS, btrfs_bioset);
+ new = bio_clone_fast(bio, GFP_NOFS, &btrfs_bioset);
btrfs_bio = btrfs_io_bio(new);
btrfs_io_bio_init(btrfs_bio);
btrfs_bio->iter = bio->bi_iter;
@@ -2704,7 +2701,7 @@ struct bio *btrfs_io_bio_alloc(unsigned int nr_iovecs)
struct bio *bio;
/* Bio allocation backed by a bioset does not fail */
- bio = bio_alloc_bioset(GFP_NOFS, nr_iovecs, btrfs_bioset);
+ bio = bio_alloc_bioset(GFP_NOFS, nr_iovecs, &btrfs_bioset);
btrfs_io_bio_init(btrfs_io_bio(bio));
return bio;
}
@@ -2715,7 +2712,7 @@ struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size)
struct btrfs_io_bio *btrfs_bio;
/* this will never fail when it's backed by a bioset */
- bio = bio_clone_fast(orig, GFP_NOFS, btrfs_bioset);
+ bio = bio_clone_fast(orig, GFP_NOFS, &btrfs_bioset);
ASSERT(bio);
btrfs_bio = btrfs_io_bio(bio);
@@ -4109,14 +4106,13 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
return ret;
}
-int extent_writepages(struct extent_io_tree *tree,
- struct address_space *mapping,
+int extent_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
int ret = 0;
struct extent_page_data epd = {
.bio = NULL,
- .tree = tree,
+ .tree = &BTRFS_I(mapping->host)->io_tree,
.extent_locked = 0,
.sync_io = wbc->sync_mode == WB_SYNC_ALL,
};
@@ -4126,9 +4122,8 @@ int extent_writepages(struct extent_io_tree *tree,
return ret;
}
-int extent_readpages(struct extent_io_tree *tree,
- struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+int extent_readpages(struct address_space *mapping, struct list_head *pages,
+ unsigned nr_pages)
{
struct bio *bio = NULL;
unsigned page_idx;
@@ -4136,6 +4131,7 @@ int extent_readpages(struct extent_io_tree *tree,
struct page *pagepool[16];
struct page *page;
struct extent_map *em_cached = NULL;
+ struct extent_io_tree *tree = &BTRFS_I(mapping->host)->io_tree;
int nr = 0;
u64 prev_em_start = (u64)-1;
@@ -4202,8 +4198,7 @@ int extent_invalidatepage(struct extent_io_tree *tree,
* are locked or under IO and drops the related state bits if it is safe
* to drop the page.
*/
-static int try_release_extent_state(struct extent_map_tree *map,
- struct extent_io_tree *tree,
+static int try_release_extent_state(struct extent_io_tree *tree,
struct page *page, gfp_t mask)
{
u64 start = page_offset(page);
@@ -4238,13 +4233,13 @@ static int try_release_extent_state(struct extent_map_tree *map,
* in the range corresponding to the page, both state records and extent
* map records are removed
*/
-int try_release_extent_mapping(struct extent_map_tree *map,
- struct extent_io_tree *tree, struct page *page,
- gfp_t mask)
+int try_release_extent_mapping(struct page *page, gfp_t mask)
{
struct extent_map *em;
u64 start = page_offset(page);
u64 end = start + PAGE_SIZE - 1;
+ struct extent_io_tree *tree = &BTRFS_I(page->mapping->host)->io_tree;
+ struct extent_map_tree *map = &BTRFS_I(page->mapping->host)->extent_tree;
if (gfpflags_allow_blocking(mask) &&
page->mapping->host->i_size > SZ_16M) {
@@ -4278,7 +4273,7 @@ int try_release_extent_mapping(struct extent_map_tree *map,
free_extent_map(em);
}
}
- return try_release_extent_state(map, tree, page, mask);
+ return try_release_extent_state(tree, page, mask);
}
/*
@@ -5620,46 +5615,6 @@ void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src,
}
}
-void le_bitmap_set(u8 *map, unsigned int start, int len)
-{
- u8 *p = map + BIT_BYTE(start);
- const unsigned int size = start + len;
- int bits_to_set = BITS_PER_BYTE - (start % BITS_PER_BYTE);
- u8 mask_to_set = BITMAP_FIRST_BYTE_MASK(start);
-
- while (len - bits_to_set >= 0) {
- *p |= mask_to_set;
- len -= bits_to_set;
- bits_to_set = BITS_PER_BYTE;
- mask_to_set = ~0;
- p++;
- }
- if (len) {
- mask_to_set &= BITMAP_LAST_BYTE_MASK(size);
- *p |= mask_to_set;
- }
-}
-
-void le_bitmap_clear(u8 *map, unsigned int start, int len)
-{
- u8 *p = map + BIT_BYTE(start);
- const unsigned int size = start + len;
- int bits_to_clear = BITS_PER_BYTE - (start % BITS_PER_BYTE);
- u8 mask_to_clear = BITMAP_FIRST_BYTE_MASK(start);
-
- while (len - bits_to_clear >= 0) {
- *p &= ~mask_to_clear;
- len -= bits_to_clear;
- bits_to_clear = BITS_PER_BYTE;
- mask_to_clear = ~0;
- p++;
- }
- if (len) {
- mask_to_clear &= BITMAP_LAST_BYTE_MASK(size);
- *p &= ~mask_to_clear;
- }
-}
-
/*
* eb_bitmap_offset() - calculate the page and offset of the byte containing the
* given bit number
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index a530096..0bfd4ae 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -79,14 +79,6 @@
#define BITMAP_LAST_BYTE_MASK(nbits) \
(BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1)))
-static inline int le_test_bit(int nr, const u8 *addr)
-{
- return 1U & (addr[BIT_BYTE(nr)] >> (nr & (BITS_PER_BYTE-1)));
-}
-
-void le_bitmap_set(u8 *map, unsigned int start, int len);
-void le_bitmap_clear(u8 *map, unsigned int start, int len);
-
struct extent_state;
struct btrfs_root;
struct btrfs_inode;
@@ -278,9 +270,7 @@ typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode,
int create);
void extent_io_tree_init(struct extent_io_tree *tree, void *private_data);
-int try_release_extent_mapping(struct extent_map_tree *map,
- struct extent_io_tree *tree, struct page *page,
- gfp_t mask);
+int try_release_extent_mapping(struct page *page, gfp_t mask);
int try_release_extent_buffer(struct page *page);
int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
struct extent_state **cached);
@@ -421,14 +411,12 @@ int extent_invalidatepage(struct extent_io_tree *tree,
int extent_write_full_page(struct page *page, struct writeback_control *wbc);
int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
int mode);
-int extent_writepages(struct extent_io_tree *tree,
- struct address_space *mapping,
+int extent_writepages(struct address_space *mapping,
struct writeback_control *wbc);
int btree_write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc);
-int extent_readpages(struct extent_io_tree *tree,
- struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages);
+int extent_readpages(struct address_space *mapping, struct list_head *pages,
+ unsigned nr_pages);
int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len);
void set_page_extent_mapped(struct page *page);
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 1b8a078..6648d55 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -518,6 +518,7 @@ static noinline int merge_extent_mapping(struct extent_map_tree *em_tree,
/**
* btrfs_add_extent_mapping - add extent mapping into em_tree
+ * @fs_info - used for tracepoint
* @em_tree - the extent tree into which we want to insert the extent mapping
* @em_in - extent we are inserting
* @start - start of the logical range btrfs_get_extent() is requesting
@@ -535,7 +536,8 @@ static noinline int merge_extent_mapping(struct extent_map_tree *em_tree,
* Return 0 on success, otherwise -EEXIST.
*
*/
-int btrfs_add_extent_mapping(struct extent_map_tree *em_tree,
+int btrfs_add_extent_mapping(struct btrfs_fs_info *fs_info,
+ struct extent_map_tree *em_tree,
struct extent_map **em_in, u64 start, u64 len)
{
int ret;
@@ -553,7 +555,7 @@ int btrfs_add_extent_mapping(struct extent_map_tree *em_tree,
existing = search_extent_mapping(em_tree, start, len);
- trace_btrfs_handle_em_exist(existing, em, start, len);
+ trace_btrfs_handle_em_exist(fs_info, existing, em, start, len);
/*
* existing will always be non-NULL, since there must be
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index 5fcb80a..25d985e 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -92,7 +92,8 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len, u64 gen
void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em);
struct extent_map *search_extent_mapping(struct extent_map_tree *tree,
u64 start, u64 len);
-int btrfs_add_extent_mapping(struct extent_map_tree *em_tree,
+int btrfs_add_extent_mapping(struct btrfs_fs_info *fs_info,
+ struct extent_map_tree *em_tree,
struct extent_map **em_in, u64 start, u64 len);
#endif
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 0167a9c..f660ba1 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1748,7 +1748,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
unlock_extent_cached(&BTRFS_I(inode)->io_tree,
lockstart, lockend, &cached_state);
btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes,
- (ret != 0));
+ true);
if (ret) {
btrfs_drop_pages(pages, num_pages);
break;
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index e5b569b..d5f80cb 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -253,10 +253,8 @@ int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans,
truncate_pagecache(inode, 0);
/*
- * We don't need an orphan item because truncating the free space cache
- * will never be split across transactions.
- * We don't need to check for -EAGAIN because we're a free space
- * cache inode
+ * We skip the throttling logic for free space cache inodes, so we don't
+ * need to check for -EAGAIN.
*/
ret = btrfs_truncate_inode_items(trans, root, inode,
0, BTRFS_EXTENT_DATA_KEY);
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index 32a0f6c..b5950aa 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -12,7 +12,6 @@
#include "transaction.h"
static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group,
struct btrfs_path *path);
@@ -45,11 +44,10 @@ void set_free_space_tree_thresholds(struct btrfs_block_group_cache *cache)
}
static int add_new_free_space_info(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group,
struct btrfs_path *path)
{
- struct btrfs_root *root = fs_info->free_space_root;
+ struct btrfs_root *root = trans->fs_info->free_space_root;
struct btrfs_free_space_info *info;
struct btrfs_key key;
struct extent_buffer *leaf;
@@ -138,10 +136,11 @@ static inline u32 free_space_bitmap_size(u64 size, u32 sectorsize)
return DIV_ROUND_UP((u32)div_u64(size, sectorsize), BITS_PER_BYTE);
}
-static u8 *alloc_bitmap(u32 bitmap_size)
+static unsigned long *alloc_bitmap(u32 bitmap_size)
{
- u8 *ret;
+ unsigned long *ret;
unsigned int nofs_flag;
+ u32 bitmap_rounded_size = round_up(bitmap_size, sizeof(unsigned long));
/*
* GFP_NOFS doesn't work with kvmalloc(), but we really can't recurse
@@ -152,21 +151,42 @@ static u8 *alloc_bitmap(u32 bitmap_size)
* know that recursion is unsafe.
*/
nofs_flag = memalloc_nofs_save();
- ret = kvzalloc(bitmap_size, GFP_KERNEL);
+ ret = kvzalloc(bitmap_rounded_size, GFP_KERNEL);
memalloc_nofs_restore(nofs_flag);
return ret;
}
+static void le_bitmap_set(unsigned long *map, unsigned int start, int len)
+{
+ u8 *p = ((u8 *)map) + BIT_BYTE(start);
+ const unsigned int size = start + len;
+ int bits_to_set = BITS_PER_BYTE - (start % BITS_PER_BYTE);
+ u8 mask_to_set = BITMAP_FIRST_BYTE_MASK(start);
+
+ while (len - bits_to_set >= 0) {
+ *p |= mask_to_set;
+ len -= bits_to_set;
+ bits_to_set = BITS_PER_BYTE;
+ mask_to_set = ~0;
+ p++;
+ }
+ if (len) {
+ mask_to_set &= BITMAP_LAST_BYTE_MASK(size);
+ *p |= mask_to_set;
+ }
+}
+
int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group,
struct btrfs_path *path)
{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_root *root = fs_info->free_space_root;
struct btrfs_free_space_info *info;
struct btrfs_key key, found_key;
struct extent_buffer *leaf;
- u8 *bitmap, *bitmap_cursor;
+ unsigned long *bitmap;
+ char *bitmap_cursor;
u64 start, end;
u64 bitmap_range, i;
u32 bitmap_size, flags, expected_extent_count;
@@ -255,7 +275,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
goto out;
}
- bitmap_cursor = bitmap;
+ bitmap_cursor = (char *)bitmap;
bitmap_range = fs_info->sectorsize * BTRFS_FREE_SPACE_BITMAP_BITS;
i = start;
while (i < end) {
@@ -296,21 +316,18 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
}
int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group,
struct btrfs_path *path)
{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_root *root = fs_info->free_space_root;
struct btrfs_free_space_info *info;
struct btrfs_key key, found_key;
struct extent_buffer *leaf;
- u8 *bitmap;
+ unsigned long *bitmap;
u64 start, end;
- /* Initialize to silence GCC. */
- u64 extent_start = 0;
- u64 offset;
u32 bitmap_size, flags, expected_extent_count;
- int prev_bit = 0, bit, bitnr;
+ unsigned long nrbits, start_bit, end_bit;
u32 extent_count = 0;
int done = 0, nr;
int ret;
@@ -348,7 +365,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
break;
} else if (found_key.type == BTRFS_FREE_SPACE_BITMAP_KEY) {
unsigned long ptr;
- u8 *bitmap_cursor;
+ char *bitmap_cursor;
u32 bitmap_pos, data_size;
ASSERT(found_key.objectid >= start);
@@ -358,7 +375,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
bitmap_pos = div_u64(found_key.objectid - start,
fs_info->sectorsize *
BITS_PER_BYTE);
- bitmap_cursor = bitmap + bitmap_pos;
+ bitmap_cursor = ((char *)bitmap) + bitmap_pos;
data_size = free_space_bitmap_size(found_key.offset,
fs_info->sectorsize);
@@ -392,32 +409,16 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
btrfs_mark_buffer_dirty(leaf);
btrfs_release_path(path);
- offset = start;
- bitnr = 0;
- while (offset < end) {
- bit = !!le_test_bit(bitnr, bitmap);
- if (prev_bit == 0 && bit == 1) {
- extent_start = offset;
- } else if (prev_bit == 1 && bit == 0) {
- key.objectid = extent_start;
- key.type = BTRFS_FREE_SPACE_EXTENT_KEY;
- key.offset = offset - extent_start;
+ nrbits = div_u64(block_group->key.offset, block_group->fs_info->sectorsize);
+ start_bit = find_next_bit_le(bitmap, nrbits, 0);
- ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
- if (ret)
- goto out;
- btrfs_release_path(path);
+ while (start_bit < nrbits) {
+ end_bit = find_next_zero_bit_le(bitmap, nrbits, start_bit);
+ ASSERT(start_bit < end_bit);
- extent_count++;
- }
- prev_bit = bit;
- offset += fs_info->sectorsize;
- bitnr++;
- }
- if (prev_bit == 1) {
- key.objectid = extent_start;
+ key.objectid = start + start_bit * block_group->fs_info->sectorsize;
key.type = BTRFS_FREE_SPACE_EXTENT_KEY;
- key.offset = end - extent_start;
+ key.offset = (end_bit - start_bit) * block_group->fs_info->sectorsize;
ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
if (ret)
@@ -425,6 +426,8 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
btrfs_release_path(path);
extent_count++;
+
+ start_bit = find_next_bit_le(bitmap, nrbits, end_bit);
}
if (extent_count != expected_extent_count) {
@@ -446,7 +449,6 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
}
static int update_free_space_extent_count(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group,
struct btrfs_path *path,
int new_extents)
@@ -459,7 +461,8 @@ static int update_free_space_extent_count(struct btrfs_trans_handle *trans,
if (new_extents == 0)
return 0;
- info = search_free_space_info(trans, fs_info, block_group, path, 1);
+ info = search_free_space_info(trans, trans->fs_info, block_group, path,
+ 1);
if (IS_ERR(info)) {
ret = PTR_ERR(info);
goto out;
@@ -474,12 +477,10 @@ static int update_free_space_extent_count(struct btrfs_trans_handle *trans,
if (!(flags & BTRFS_FREE_SPACE_USING_BITMAPS) &&
extent_count > block_group->bitmap_high_thresh) {
- ret = convert_free_space_to_bitmaps(trans, fs_info, block_group,
- path);
+ ret = convert_free_space_to_bitmaps(trans, block_group, path);
} else if ((flags & BTRFS_FREE_SPACE_USING_BITMAPS) &&
extent_count < block_group->bitmap_low_thresh) {
- ret = convert_free_space_to_extents(trans, fs_info, block_group,
- path);
+ ret = convert_free_space_to_extents(trans, block_group, path);
}
out:
@@ -576,12 +577,11 @@ static int free_space_next_bitmap(struct btrfs_trans_handle *trans,
* the bitmap.
*/
static int modify_free_space_bitmap(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group,
struct btrfs_path *path,
u64 start, u64 size, int remove)
{
- struct btrfs_root *root = fs_info->free_space_root;
+ struct btrfs_root *root = block_group->fs_info->free_space_root;
struct btrfs_key key;
u64 end = start + size;
u64 cur_start, cur_size;
@@ -682,7 +682,7 @@ static int modify_free_space_bitmap(struct btrfs_trans_handle *trans,
}
btrfs_release_path(path);
- ret = update_free_space_extent_count(trans, fs_info, block_group, path,
+ ret = update_free_space_extent_count(trans, block_group, path,
new_extents);
out:
@@ -690,12 +690,11 @@ static int modify_free_space_bitmap(struct btrfs_trans_handle *trans,
}
static int remove_free_space_extent(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group,
struct btrfs_path *path,
u64 start, u64 size)
{
- struct btrfs_root *root = fs_info->free_space_root;
+ struct btrfs_root *root = trans->fs_info->free_space_root;
struct btrfs_key key;
u64 found_start, found_end;
u64 end = start + size;
@@ -769,7 +768,7 @@ static int remove_free_space_extent(struct btrfs_trans_handle *trans,
}
btrfs_release_path(path);
- ret = update_free_space_extent_count(trans, fs_info, block_group, path,
+ ret = update_free_space_extent_count(trans, block_group, path,
new_extents);
out:
@@ -777,7 +776,6 @@ static int remove_free_space_extent(struct btrfs_trans_handle *trans,
}
int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group,
struct btrfs_path *path, u64 start, u64 size)
{
@@ -786,36 +784,35 @@ int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
int ret;
if (block_group->needs_free_space) {
- ret = __add_block_group_free_space(trans, fs_info, block_group,
- path);
+ ret = __add_block_group_free_space(trans, block_group, path);
if (ret)
return ret;
}
- info = search_free_space_info(NULL, fs_info, block_group, path, 0);
+ info = search_free_space_info(NULL, trans->fs_info, block_group, path,
+ 0);
if (IS_ERR(info))
return PTR_ERR(info);
flags = btrfs_free_space_flags(path->nodes[0], info);
btrfs_release_path(path);
if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) {
- return modify_free_space_bitmap(trans, fs_info, block_group,
- path, start, size, 1);
+ return modify_free_space_bitmap(trans, block_group, path,
+ start, size, 1);
} else {
- return remove_free_space_extent(trans, fs_info, block_group,
- path, start, size);
+ return remove_free_space_extent(trans, block_group, path,
+ start, size);
}
}
int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
u64 start, u64 size)
{
struct btrfs_block_group_cache *block_group;
struct btrfs_path *path;
int ret;
- if (!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
+ if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE))
return 0;
path = btrfs_alloc_path();
@@ -824,7 +821,7 @@ int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
goto out;
}
- block_group = btrfs_lookup_block_group(fs_info, start);
+ block_group = btrfs_lookup_block_group(trans->fs_info, start);
if (!block_group) {
ASSERT(0);
ret = -ENOENT;
@@ -832,8 +829,8 @@ int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
}
mutex_lock(&block_group->free_space_lock);
- ret = __remove_from_free_space_tree(trans, fs_info, block_group, path,
- start, size);
+ ret = __remove_from_free_space_tree(trans, block_group, path, start,
+ size);
mutex_unlock(&block_group->free_space_lock);
btrfs_put_block_group(block_group);
@@ -845,12 +842,11 @@ int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
}
static int add_free_space_extent(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group,
struct btrfs_path *path,
u64 start, u64 size)
{
- struct btrfs_root *root = fs_info->free_space_root;
+ struct btrfs_root *root = trans->fs_info->free_space_root;
struct btrfs_key key, new_key;
u64 found_start, found_end;
u64 end = start + size;
@@ -965,7 +961,7 @@ static int add_free_space_extent(struct btrfs_trans_handle *trans,
goto out;
btrfs_release_path(path);
- ret = update_free_space_extent_count(trans, fs_info, block_group, path,
+ ret = update_free_space_extent_count(trans, block_group, path,
new_extents);
out:
@@ -973,17 +969,16 @@ static int add_free_space_extent(struct btrfs_trans_handle *trans,
}
int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group,
struct btrfs_path *path, u64 start, u64 size)
{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_free_space_info *info;
u32 flags;
int ret;
if (block_group->needs_free_space) {
- ret = __add_block_group_free_space(trans, fs_info, block_group,
- path);
+ ret = __add_block_group_free_space(trans, block_group, path);
if (ret)
return ret;
}
@@ -995,23 +990,22 @@ int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
btrfs_release_path(path);
if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) {
- return modify_free_space_bitmap(trans, fs_info, block_group,
- path, start, size, 0);
+ return modify_free_space_bitmap(trans, block_group, path,
+ start, size, 0);
} else {
- return add_free_space_extent(trans, fs_info, block_group, path,
- start, size);
+ return add_free_space_extent(trans, block_group, path, start,
+ size);
}
}
int add_to_free_space_tree(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
u64 start, u64 size)
{
struct btrfs_block_group_cache *block_group;
struct btrfs_path *path;
int ret;
- if (!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
+ if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE))
return 0;
path = btrfs_alloc_path();
@@ -1020,7 +1014,7 @@ int add_to_free_space_tree(struct btrfs_trans_handle *trans,
goto out;
}
- block_group = btrfs_lookup_block_group(fs_info, start);
+ block_group = btrfs_lookup_block_group(trans->fs_info, start);
if (!block_group) {
ASSERT(0);
ret = -ENOENT;
@@ -1028,8 +1022,7 @@ int add_to_free_space_tree(struct btrfs_trans_handle *trans,
}
mutex_lock(&block_group->free_space_lock);
- ret = __add_to_free_space_tree(trans, fs_info, block_group, path, start,
- size);
+ ret = __add_to_free_space_tree(trans, block_group, path, start, size);
mutex_unlock(&block_group->free_space_lock);
btrfs_put_block_group(block_group);
@@ -1046,10 +1039,9 @@ int add_to_free_space_tree(struct btrfs_trans_handle *trans,
* through the normal add/remove hooks.
*/
static int populate_free_space_tree(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group)
{
- struct btrfs_root *extent_root = fs_info->extent_root;
+ struct btrfs_root *extent_root = trans->fs_info->extent_root;
struct btrfs_path *path, *path2;
struct btrfs_key key;
u64 start, end;
@@ -1066,7 +1058,7 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
return -ENOMEM;
}
- ret = add_new_free_space_info(trans, fs_info, block_group, path2);
+ ret = add_new_free_space_info(trans, block_group, path2);
if (ret)
goto out;
@@ -1099,7 +1091,7 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
break;
if (start < key.objectid) {
- ret = __add_to_free_space_tree(trans, fs_info,
+ ret = __add_to_free_space_tree(trans,
block_group,
path2, start,
key.objectid -
@@ -1109,7 +1101,7 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
}
start = key.objectid;
if (key.type == BTRFS_METADATA_ITEM_KEY)
- start += fs_info->nodesize;
+ start += trans->fs_info->nodesize;
else
start += key.offset;
} else if (key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) {
@@ -1124,8 +1116,8 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
break;
}
if (start < end) {
- ret = __add_to_free_space_tree(trans, fs_info, block_group,
- path2, start, end - start);
+ ret = __add_to_free_space_tree(trans, block_group, path2,
+ start, end - start);
if (ret)
goto out_locked;
}
@@ -1165,7 +1157,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
while (node) {
block_group = rb_entry(node, struct btrfs_block_group_cache,
cache_node);
- ret = populate_free_space_tree(trans, fs_info, block_group);
+ ret = populate_free_space_tree(trans, block_group);
if (ret)
goto abort;
node = rb_next(node);
@@ -1269,7 +1261,6 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info)
}
static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group,
struct btrfs_path *path)
{
@@ -1277,19 +1268,19 @@ static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
block_group->needs_free_space = 0;
- ret = add_new_free_space_info(trans, fs_info, block_group, path);
+ ret = add_new_free_space_info(trans, block_group, path);
if (ret)
return ret;
- return __add_to_free_space_tree(trans, fs_info, block_group, path,
+ return __add_to_free_space_tree(trans, block_group, path,
block_group->key.objectid,
block_group->key.offset);
}
int add_block_group_free_space(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group)
{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_path *path = NULL;
int ret = 0;
@@ -1306,7 +1297,7 @@ int add_block_group_free_space(struct btrfs_trans_handle *trans,
goto out;
}
- ret = __add_block_group_free_space(trans, fs_info, block_group, path);
+ ret = __add_block_group_free_space(trans, block_group, path);
out:
btrfs_free_path(path);
@@ -1317,10 +1308,9 @@ int add_block_group_free_space(struct btrfs_trans_handle *trans,
}
int remove_block_group_free_space(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group)
{
- struct btrfs_root *root = fs_info->free_space_root;
+ struct btrfs_root *root = trans->fs_info->free_space_root;
struct btrfs_path *path;
struct btrfs_key key, found_key;
struct extent_buffer *leaf;
@@ -1328,7 +1318,7 @@ int remove_block_group_free_space(struct btrfs_trans_handle *trans,
int done = 0, nr;
int ret;
- if (!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
+ if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE))
return 0;
if (block_group->needs_free_space) {
@@ -1439,7 +1429,6 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
extent_start = offset;
} else if (prev_bit == 1 && bit == 0) {
total_found += add_new_free_space(block_group,
- fs_info,
extent_start,
offset);
if (total_found > CACHING_CTL_WAKE_UP) {
@@ -1453,8 +1442,8 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
}
}
if (prev_bit == 1) {
- total_found += add_new_free_space(block_group, fs_info,
- extent_start, end);
+ total_found += add_new_free_space(block_group, extent_start,
+ end);
extent_count++;
}
@@ -1511,8 +1500,7 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl,
caching_ctl->progress = key.objectid;
- total_found += add_new_free_space(block_group, fs_info,
- key.objectid,
+ total_found += add_new_free_space(block_group, key.objectid,
key.objectid + key.offset);
if (total_found > CACHING_CTL_WAKE_UP) {
total_found = 0;
diff --git a/fs/btrfs/free-space-tree.h b/fs/btrfs/free-space-tree.h
index 874b4fe..3133651d 100644
--- a/fs/btrfs/free-space-tree.h
+++ b/fs/btrfs/free-space-tree.h
@@ -19,16 +19,12 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info);
int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info);
int load_free_space_tree(struct btrfs_caching_control *caching_ctl);
int add_block_group_free_space(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group);
int remove_block_group_free_space(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group);
int add_to_free_space_tree(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
u64 start, u64 size);
int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
u64 start, u64 size);
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
@@ -38,19 +34,15 @@ search_free_space_info(struct btrfs_trans_handle *trans,
struct btrfs_block_group_cache *block_group,
struct btrfs_path *path, int cow);
int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group,
struct btrfs_path *path, u64 start, u64 size);
int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group,
struct btrfs_path *path, u64 start, u64 size);
int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group,
struct btrfs_path *path);
int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *block_group,
struct btrfs_path *path);
int free_space_test_bit(struct btrfs_block_group_cache *block_group,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e064c49..89b2082 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -31,6 +31,7 @@
#include <linux/uio.h>
#include <linux/magic.h>
#include <linux/iversion.h>
+#include <asm/unaligned.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
@@ -1017,8 +1018,10 @@ static noinline int cow_file_range(struct inode *inode,
ram_size, /* ram_bytes */
BTRFS_COMPRESS_NONE, /* compress_type */
BTRFS_ORDERED_REGULAR /* type */);
- if (IS_ERR(em))
+ if (IS_ERR(em)) {
+ ret = PTR_ERR(em);
goto out_reserve;
+ }
free_extent_map(em);
ret = btrfs_add_ordered_extent(inode, start, ins.objectid,
@@ -1155,13 +1158,10 @@ static noinline void async_cow_submit(struct btrfs_work *work)
nr_pages = (async_cow->end - async_cow->start + PAGE_SIZE) >>
PAGE_SHIFT;
- /*
- * atomic_sub_return implies a barrier for waitqueue_active
- */
+ /* atomic_sub_return implies a barrier */
if (atomic_sub_return(nr_pages, &fs_info->async_delalloc_pages) <
- 5 * SZ_1M &&
- waitqueue_active(&fs_info->async_submit_wait))
- wake_up(&fs_info->async_submit_wait);
+ 5 * SZ_1M)
+ cond_wake_up_nomb(&fs_info->async_submit_wait);
if (async_cow->inode)
submit_compressed_extents(async_cow->inode, async_cow);
@@ -1372,6 +1372,13 @@ static noinline int run_delalloc_nocow(struct inode *inode,
btrfs_file_extent_encryption(leaf, fi) ||
btrfs_file_extent_other_encoding(leaf, fi))
goto out_check;
+ /*
+ * Do the same check as in btrfs_cross_ref_exist but
+ * without the unnecessary search.
+ */
+ if (btrfs_file_extent_generation(leaf, fi) <=
+ btrfs_root_last_snapshot(&root->root_item))
+ goto out_check;
if (extent_type == BTRFS_FILE_EXTENT_REG && !force)
goto out_check;
if (btrfs_extent_readonly(fs_info, disk_bytenr))
@@ -1741,24 +1748,32 @@ static void btrfs_add_delalloc_inodes(struct btrfs_root *root,
spin_unlock(&root->delalloc_lock);
}
-static void btrfs_del_delalloc_inode(struct btrfs_root *root,
- struct btrfs_inode *inode)
+
+void __btrfs_del_delalloc_inode(struct btrfs_root *root,
+ struct btrfs_inode *inode)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
- spin_lock(&root->delalloc_lock);
if (!list_empty(&inode->delalloc_inodes)) {
list_del_init(&inode->delalloc_inodes);
clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
&inode->runtime_flags);
root->nr_delalloc_inodes--;
if (!root->nr_delalloc_inodes) {
+ ASSERT(list_empty(&root->delalloc_inodes));
spin_lock(&fs_info->delalloc_root_lock);
BUG_ON(list_empty(&root->delalloc_root));
list_del_init(&root->delalloc_root);
spin_unlock(&fs_info->delalloc_root_lock);
}
}
+}
+
+static void btrfs_del_delalloc_inode(struct btrfs_root *root,
+ struct btrfs_inode *inode)
+{
+ spin_lock(&root->delalloc_lock);
+ __btrfs_del_delalloc_inode(root, inode);
spin_unlock(&root->delalloc_lock);
}
@@ -3150,6 +3165,9 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
/* once for the tree */
btrfs_put_ordered_extent(ordered_extent);
+ /* Try to release some metadata so we don't get an OOM but don't wait */
+ btrfs_btree_balance_dirty_nodelay(fs_info);
+
return ret;
}
@@ -3292,177 +3310,31 @@ void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info)
}
/*
- * This is called in transaction commit time. If there are no orphan
- * files in the subvolume, it removes orphan item and frees block_rsv
- * structure.
- */
-void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans,
- struct btrfs_root *root)
-{
- struct btrfs_fs_info *fs_info = root->fs_info;
- struct btrfs_block_rsv *block_rsv;
- int ret;
-
- if (atomic_read(&root->orphan_inodes) ||
- root->orphan_cleanup_state != ORPHAN_CLEANUP_DONE)
- return;
-
- spin_lock(&root->orphan_lock);
- if (atomic_read(&root->orphan_inodes)) {
- spin_unlock(&root->orphan_lock);
- return;
- }
-
- if (root->orphan_cleanup_state != ORPHAN_CLEANUP_DONE) {
- spin_unlock(&root->orphan_lock);
- return;
- }
-
- block_rsv = root->orphan_block_rsv;
- root->orphan_block_rsv = NULL;
- spin_unlock(&root->orphan_lock);
-
- if (test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state) &&
- btrfs_root_refs(&root->root_item) > 0) {
- ret = btrfs_del_orphan_item(trans, fs_info->tree_root,
- root->root_key.objectid);
- if (ret)
- btrfs_abort_transaction(trans, ret);
- else
- clear_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED,
- &root->state);
- }
-
- if (block_rsv) {
- WARN_ON(block_rsv->size > 0);
- btrfs_free_block_rsv(fs_info, block_rsv);
- }
-}
-
-/*
- * This creates an orphan entry for the given inode in case something goes
- * wrong in the middle of an unlink/truncate.
- *
- * NOTE: caller of this function should reserve 5 units of metadata for
- * this function.
+ * This creates an orphan entry for the given inode in case something goes wrong
+ * in the middle of an unlink.
*/
int btrfs_orphan_add(struct btrfs_trans_handle *trans,
- struct btrfs_inode *inode)
+ struct btrfs_inode *inode)
{
- struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
- struct btrfs_root *root = inode->root;
- struct btrfs_block_rsv *block_rsv = NULL;
- int reserve = 0;
- bool insert = false;
int ret;
- if (!root->orphan_block_rsv) {
- block_rsv = btrfs_alloc_block_rsv(fs_info,
- BTRFS_BLOCK_RSV_TEMP);
- if (!block_rsv)
- return -ENOMEM;
- }
-
- if (!test_and_set_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
- &inode->runtime_flags))
- insert = true;
-
- if (!test_and_set_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
- &inode->runtime_flags))
- reserve = 1;
-
- spin_lock(&root->orphan_lock);
- /* If someone has created ->orphan_block_rsv, be happy to use it. */
- if (!root->orphan_block_rsv) {
- root->orphan_block_rsv = block_rsv;
- } else if (block_rsv) {
- btrfs_free_block_rsv(fs_info, block_rsv);
- block_rsv = NULL;
- }
-
- if (insert)
- atomic_inc(&root->orphan_inodes);
- spin_unlock(&root->orphan_lock);
-
- /* grab metadata reservation from transaction handle */
- if (reserve) {
- ret = btrfs_orphan_reserve_metadata(trans, inode);
- ASSERT(!ret);
- if (ret) {
- /*
- * dec doesn't need spin_lock as ->orphan_block_rsv
- * would be released only if ->orphan_inodes is
- * zero.
- */
- atomic_dec(&root->orphan_inodes);
- clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
- &inode->runtime_flags);
- if (insert)
- clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
- &inode->runtime_flags);
- return ret;
- }
- }
-
- /* insert an orphan item to track this unlinked/truncated file */
- if (insert) {
- ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode));
- if (ret) {
- if (reserve) {
- clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
- &inode->runtime_flags);
- btrfs_orphan_release_metadata(inode);
- }
- /*
- * btrfs_orphan_commit_root may race with us and set
- * ->orphan_block_rsv to zero, in order to avoid that,
- * decrease ->orphan_inodes after everything is done.
- */
- atomic_dec(&root->orphan_inodes);
- if (ret != -EEXIST) {
- clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
- &inode->runtime_flags);
- btrfs_abort_transaction(trans, ret);
- return ret;
- }
- }
- ret = 0;
+ ret = btrfs_insert_orphan_item(trans, inode->root, btrfs_ino(inode));
+ if (ret && ret != -EEXIST) {
+ btrfs_abort_transaction(trans, ret);
+ return ret;
}
return 0;
}
/*
- * We have done the truncate/delete so we can go ahead and remove the orphan
- * item for this particular inode.
+ * We have done the delete so we can go ahead and remove the orphan item for
+ * this particular inode.
*/
static int btrfs_orphan_del(struct btrfs_trans_handle *trans,
struct btrfs_inode *inode)
{
- struct btrfs_root *root = inode->root;
- int delete_item = 0;
- int ret = 0;
-
- if (test_and_clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
- &inode->runtime_flags))
- delete_item = 1;
-
- if (delete_item && trans)
- ret = btrfs_del_orphan_item(trans, root, btrfs_ino(inode));
-
- if (test_and_clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
- &inode->runtime_flags))
- btrfs_orphan_release_metadata(inode);
-
- /*
- * btrfs_orphan_commit_root may race with us and set ->orphan_block_rsv
- * to zero, in order to avoid that, decrease ->orphan_inodes after
- * everything is done.
- */
- if (delete_item)
- atomic_dec(&root->orphan_inodes);
-
- return ret;
+ return btrfs_del_orphan_item(trans, inode->root, btrfs_ino(inode));
}
/*
@@ -3478,7 +3350,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
struct btrfs_trans_handle *trans;
struct inode *inode;
u64 last_objectid = 0;
- int ret = 0, nr_unlink = 0, nr_truncate = 0;
+ int ret = 0, nr_unlink = 0;
if (cmpxchg(&root->orphan_cleanup_state, 0, ORPHAN_CLEANUP_STARTED))
return 0;
@@ -3578,12 +3450,31 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
key.offset = found_key.objectid - 1;
continue;
}
+
}
+
/*
- * Inode is already gone but the orphan item is still there,
- * kill the orphan item.
+ * If we have an inode with links, there are a couple of
+ * possibilities. Old kernels (before v3.12) used to create an
+ * orphan item for truncate indicating that there were possibly
+ * extent items past i_size that needed to be deleted. In v3.12,
+ * truncate was changed to update i_size in sync with the extent
+ * items, but the (useless) orphan item was still created. Since
+ * v4.18, we don't create the orphan item for truncate at all.
+ *
+ * So, this item could mean that we need to do a truncate, but
+ * only if this filesystem was last used on a pre-v3.12 kernel
+ * and was not cleanly unmounted. The odds of that are quite
+ * slim, and it's a pain to do the truncate now, so just delete
+ * the orphan item.
+ *
+ * It's also possible that this orphan item was supposed to be
+ * deleted but wasn't. The inode number may have been reused,
+ * but either way, we can delete the orphan item.
*/
- if (ret == -ENOENT) {
+ if (ret == -ENOENT || inode->i_nlink) {
+ if (!ret)
+ iput(inode);
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
@@ -3599,42 +3490,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
continue;
}
- /*
- * add this inode to the orphan list so btrfs_orphan_del does
- * the proper thing when we hit it
- */
- set_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
- &BTRFS_I(inode)->runtime_flags);
- atomic_inc(&root->orphan_inodes);
-
- /* if we have links, this was a truncate, lets do that */
- if (inode->i_nlink) {
- if (WARN_ON(!S_ISREG(inode->i_mode))) {
- iput(inode);
- continue;
- }
- nr_truncate++;
-
- /* 1 for the orphan item deletion. */
- trans = btrfs_start_transaction(root, 1);
- if (IS_ERR(trans)) {
- iput(inode);
- ret = PTR_ERR(trans);
- goto out;
- }
- ret = btrfs_orphan_add(trans, BTRFS_I(inode));
- btrfs_end_transaction(trans);
- if (ret) {
- iput(inode);
- goto out;
- }
-
- ret = btrfs_truncate(inode, false);
- if (ret)
- btrfs_orphan_del(NULL, BTRFS_I(inode));
- } else {
- nr_unlink++;
- }
+ nr_unlink++;
/* this will do delete_inode and everything for us */
iput(inode);
@@ -3646,12 +3502,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
root->orphan_cleanup_state = ORPHAN_CLEANUP_DONE;
- if (root->orphan_block_rsv)
- btrfs_block_rsv_release(fs_info, root->orphan_block_rsv,
- (u64)-1);
-
- if (root->orphan_block_rsv ||
- test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state)) {
+ if (test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state)) {
trans = btrfs_join_transaction(root);
if (!IS_ERR(trans))
btrfs_end_transaction(trans);
@@ -3659,8 +3510,6 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
if (nr_unlink)
btrfs_debug(fs_info, "unlinked %d orphans", nr_unlink);
- if (nr_truncate)
- btrfs_debug(fs_info, "truncated %d orphans", nr_truncate);
out:
if (ret)
@@ -3923,7 +3772,7 @@ static int btrfs_read_locked_inode(struct inode *inode)
break;
}
- btrfs_update_iflags(inode);
+ btrfs_sync_inode_flags_to_i_flags(inode);
return 0;
make_bad:
@@ -4237,7 +4086,7 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
return ret;
}
-int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
+static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct inode *dir, u64 objectid,
const char *name, int name_len)
@@ -4318,6 +4167,262 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
return ret;
}
+/*
+ * Helper to check if the subvolume references other subvolumes or if it's
+ * default.
+ */
+static noinline int may_destroy_subvol(struct btrfs_root *root)
+{
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct btrfs_path *path;
+ struct btrfs_dir_item *di;
+ struct btrfs_key key;
+ u64 dir_id;
+ int ret;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ /* Make sure this root isn't set as the default subvol */
+ dir_id = btrfs_super_root_dir(fs_info->super_copy);
+ di = btrfs_lookup_dir_item(NULL, fs_info->tree_root, path,
+ dir_id, "default", 7, 0);
+ if (di && !IS_ERR(di)) {
+ btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key);
+ if (key.objectid == root->root_key.objectid) {
+ ret = -EPERM;
+ btrfs_err(fs_info,
+ "deleting default subvolume %llu is not allowed",
+ key.objectid);
+ goto out;
+ }
+ btrfs_release_path(path);
+ }
+
+ key.objectid = root->root_key.objectid;
+ key.type = BTRFS_ROOT_REF_KEY;
+ key.offset = (u64)-1;
+
+ ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
+ if (ret < 0)
+ goto out;
+ BUG_ON(ret == 0);
+
+ ret = 0;
+ if (path->slots[0] > 0) {
+ path->slots[0]--;
+ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+ if (key.objectid == root->root_key.objectid &&
+ key.type == BTRFS_ROOT_REF_KEY)
+ ret = -ENOTEMPTY;
+ }
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
+/* Delete all dentries for inodes belonging to the root */
+static void btrfs_prune_dentries(struct btrfs_root *root)
+{
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct rb_node *node;
+ struct rb_node *prev;
+ struct btrfs_inode *entry;
+ struct inode *inode;
+ u64 objectid = 0;
+
+ if (!test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
+ WARN_ON(btrfs_root_refs(&root->root_item) != 0);
+
+ spin_lock(&root->inode_lock);
+again:
+ node = root->inode_tree.rb_node;
+ prev = NULL;
+ while (node) {
+ prev = node;
+ entry = rb_entry(node, struct btrfs_inode, rb_node);
+
+ if (objectid < btrfs_ino(BTRFS_I(&entry->vfs_inode)))
+ node = node->rb_left;
+ else if (objectid > btrfs_ino(BTRFS_I(&entry->vfs_inode)))
+ node = node->rb_right;
+ else
+ break;
+ }
+ if (!node) {
+ while (prev) {
+ entry = rb_entry(prev, struct btrfs_inode, rb_node);
+ if (objectid <= btrfs_ino(BTRFS_I(&entry->vfs_inode))) {
+ node = prev;
+ break;
+ }
+ prev = rb_next(prev);
+ }
+ }
+ while (node) {
+ entry = rb_entry(node, struct btrfs_inode, rb_node);
+ objectid = btrfs_ino(BTRFS_I(&entry->vfs_inode)) + 1;
+ inode = igrab(&entry->vfs_inode);
+ if (inode) {
+ spin_unlock(&root->inode_lock);
+ if (atomic_read(&inode->i_count) > 1)
+ d_prune_aliases(inode);
+ /*
+ * btrfs_drop_inode will have it removed from the inode
+ * cache when its usage count hits zero.
+ */
+ iput(inode);
+ cond_resched();
+ spin_lock(&root->inode_lock);
+ goto again;
+ }
+
+ if (cond_resched_lock(&root->inode_lock))
+ goto again;
+
+ node = rb_next(node);
+ }
+ spin_unlock(&root->inode_lock);
+}
+
+int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
+{
+ struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb);
+ struct btrfs_root *root = BTRFS_I(dir)->root;
+ struct inode *inode = d_inode(dentry);
+ struct btrfs_root *dest = BTRFS_I(inode)->root;
+ struct btrfs_trans_handle *trans;
+ struct btrfs_block_rsv block_rsv;
+ u64 root_flags;
+ int ret;
+ int err;
+
+ /*
+ * Don't allow to delete a subvolume with send in progress. This is
+ * inside the inode lock so the error handling that has to drop the bit
+ * again is not run concurrently.
+ */
+ spin_lock(&dest->root_item_lock);
+ root_flags = btrfs_root_flags(&dest->root_item);
+ if (dest->send_in_progress == 0) {
+ btrfs_set_root_flags(&dest->root_item,
+ root_flags | BTRFS_ROOT_SUBVOL_DEAD);
+ spin_unlock(&dest->root_item_lock);
+ } else {
+ spin_unlock(&dest->root_item_lock);
+ btrfs_warn(fs_info,
+ "attempt to delete subvolume %llu during send",
+ dest->root_key.objectid);
+ return -EPERM;
+ }
+
+ down_write(&fs_info->subvol_sem);
+
+ err = may_destroy_subvol(dest);
+ if (err)
+ goto out_up_write;
+
+ btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
+ /*
+ * One for dir inode,
+ * two for dir entries,
+ * two for root ref/backref.
+ */
+ err = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true);
+ if (err)
+ goto out_up_write;
+
+ trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans)) {
+ err = PTR_ERR(trans);
+ goto out_release;
+ }
+ trans->block_rsv = &block_rsv;
+ trans->bytes_reserved = block_rsv.size;
+
+ btrfs_record_snapshot_destroy(trans, BTRFS_I(dir));
+
+ ret = btrfs_unlink_subvol(trans, root, dir,
+ dest->root_key.objectid,
+ dentry->d_name.name,
+ dentry->d_name.len);
+ if (ret) {
+ err = ret;
+ btrfs_abort_transaction(trans, ret);
+ goto out_end_trans;
+ }
+
+ btrfs_record_root_in_trans(trans, dest);
+
+ memset(&dest->root_item.drop_progress, 0,
+ sizeof(dest->root_item.drop_progress));
+ dest->root_item.drop_level = 0;
+ btrfs_set_root_refs(&dest->root_item, 0);
+
+ if (!test_and_set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &dest->state)) {
+ ret = btrfs_insert_orphan_item(trans,
+ fs_info->tree_root,
+ dest->root_key.objectid);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ err = ret;
+ goto out_end_trans;
+ }
+ }
+
+ ret = btrfs_uuid_tree_remove(trans, dest->root_item.uuid,
+ BTRFS_UUID_KEY_SUBVOL,
+ dest->root_key.objectid);
+ if (ret && ret != -ENOENT) {
+ btrfs_abort_transaction(trans, ret);
+ err = ret;
+ goto out_end_trans;
+ }
+ if (!btrfs_is_empty_uuid(dest->root_item.received_uuid)) {
+ ret = btrfs_uuid_tree_remove(trans,
+ dest->root_item.received_uuid,
+ BTRFS_UUID_KEY_RECEIVED_SUBVOL,
+ dest->root_key.objectid);
+ if (ret && ret != -ENOENT) {
+ btrfs_abort_transaction(trans, ret);
+ err = ret;
+ goto out_end_trans;
+ }
+ }
+
+out_end_trans:
+ trans->block_rsv = NULL;
+ trans->bytes_reserved = 0;
+ ret = btrfs_end_transaction(trans);
+ if (ret && !err)
+ err = ret;
+ inode->i_flags |= S_DEAD;
+out_release:
+ btrfs_subvolume_release_metadata(fs_info, &block_rsv);
+out_up_write:
+ up_write(&fs_info->subvol_sem);
+ if (err) {
+ spin_lock(&dest->root_item_lock);
+ root_flags = btrfs_root_flags(&dest->root_item);
+ btrfs_set_root_flags(&dest->root_item,
+ root_flags & ~BTRFS_ROOT_SUBVOL_DEAD);
+ spin_unlock(&dest->root_item_lock);
+ } else {
+ d_invalidate(dentry);
+ btrfs_prune_dentries(dest);
+ ASSERT(dest->send_in_progress == 0);
+
+ /* the last ref */
+ if (dest->ino_cache_inode) {
+ iput(dest->ino_cache_inode);
+ dest->ino_cache_inode = NULL;
+ }
+ }
+
+ return err;
+}
+
static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
@@ -4329,7 +4434,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
if (inode->i_size > BTRFS_EMPTY_DIR_SIZE)
return -ENOTEMPTY;
if (btrfs_ino(BTRFS_I(inode)) == BTRFS_FIRST_FREE_OBJECTID)
- return -EPERM;
+ return btrfs_delete_subvolume(dir, dentry);
trans = __unlink_start_trans(dir);
if (IS_ERR(trans))
@@ -4441,7 +4546,6 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
int pending_del_slot = 0;
int extent_type = -1;
int ret;
- int err = 0;
u64 ino = btrfs_ino(BTRFS_I(inode));
u64 bytes_deleted = 0;
bool be_nice = false;
@@ -4493,22 +4597,19 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
* up a huge file in a single leaf. Most of the time that
* bytes_deleted is > 0, it will be huge by the time we get here
*/
- if (be_nice && bytes_deleted > SZ_32M) {
- if (btrfs_should_end_transaction(trans)) {
- err = -EAGAIN;
- goto error;
- }
- }
-
-
- path->leave_spinning = 1;
- ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
- if (ret < 0) {
- err = ret;
+ if (be_nice && bytes_deleted > SZ_32M &&
+ btrfs_should_end_transaction(trans)) {
+ ret = -EAGAIN;
goto out;
}
+ path->leave_spinning = 1;
+ ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+ if (ret < 0)
+ goto out;
+
if (ret > 0) {
+ ret = 0;
/* there are no items in the tree for us to truncate, we're
* done
*/
@@ -4619,7 +4720,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
* We have to bail so the last_size is set to
* just before this extent.
*/
- err = NEED_TRUNCATE_BLOCK;
+ ret = NEED_TRUNCATE_BLOCK;
break;
}
@@ -4658,7 +4759,10 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
extent_num_bytes, 0,
btrfs_header_owner(leaf),
ino, extent_offset);
- BUG_ON(ret);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ break;
+ }
if (btrfs_should_throttle_delayed_refs(trans, fs_info))
btrfs_async_run_delayed_refs(fs_info,
trans->delayed_ref_updates * 2,
@@ -4686,7 +4790,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
pending_del_nr);
if (ret) {
btrfs_abort_transaction(trans, ret);
- goto error;
+ break;
}
pending_del_nr = 0;
}
@@ -4697,8 +4801,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
trans->delayed_ref_updates = 0;
ret = btrfs_run_delayed_refs(trans,
updates * 2);
- if (ret && !err)
- err = ret;
+ if (ret)
+ break;
}
}
/*
@@ -4706,8 +4810,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
* and let the transaction restart
*/
if (should_end) {
- err = -EAGAIN;
- goto error;
+ ret = -EAGAIN;
+ break;
}
goto search_again;
} else {
@@ -4715,32 +4819,37 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
}
}
out:
- if (pending_del_nr) {
- ret = btrfs_del_items(trans, root, path, pending_del_slot,
+ if (ret >= 0 && pending_del_nr) {
+ int err;
+
+ err = btrfs_del_items(trans, root, path, pending_del_slot,
pending_del_nr);
- if (ret)
- btrfs_abort_transaction(trans, ret);
+ if (err) {
+ btrfs_abort_transaction(trans, err);
+ ret = err;
+ }
}
-error:
if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
ASSERT(last_size >= new_size);
- if (!err && last_size > new_size)
+ if (!ret && last_size > new_size)
last_size = new_size;
btrfs_ordered_update_i_size(inode, last_size, NULL);
}
btrfs_free_path(path);
- if (be_nice && bytes_deleted > SZ_32M) {
+ if (be_nice && bytes_deleted > SZ_32M && (ret >= 0 || ret == -EAGAIN)) {
unsigned long updates = trans->delayed_ref_updates;
+ int err;
+
if (updates) {
trans->delayed_ref_updates = 0;
- ret = btrfs_run_delayed_refs(trans, updates * 2);
- if (ret && !err)
- err = ret;
+ err = btrfs_run_delayed_refs(trans, updates * 2);
+ if (err)
+ ret = err;
}
}
- return err;
+ return ret;
}
/*
@@ -5082,30 +5191,6 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
set_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
&BTRFS_I(inode)->runtime_flags);
- /*
- * 1 for the orphan item we're going to add
- * 1 for the orphan item deletion.
- */
- trans = btrfs_start_transaction(root, 2);
- if (IS_ERR(trans))
- return PTR_ERR(trans);
-
- /*
- * We need to do this in case we fail at _any_ point during the
- * actual truncate. Once we do the truncate_setsize we could
- * invalidate pages which forces any outstanding ordered io to
- * be instantly completed which will give us extents that need
- * to be truncated. If we fail to get an orphan inode down we
- * could have left over extents that were never meant to live,
- * so we need to guarantee from this point on that everything
- * will be consistent.
- */
- ret = btrfs_orphan_add(trans, BTRFS_I(inode));
- btrfs_end_transaction(trans);
- if (ret)
- return ret;
-
- /* we don't support swapfiles, so vmtruncate shouldn't fail */
truncate_setsize(inode, newsize);
/* Disable nonlocked read DIO to avoid the end less truncate */
@@ -5117,29 +5202,16 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
if (ret && inode->i_nlink) {
int err;
- /* To get a stable disk_i_size */
- err = btrfs_wait_ordered_range(inode, 0, (u64)-1);
- if (err) {
- btrfs_orphan_del(NULL, BTRFS_I(inode));
- return err;
- }
-
/*
- * failed to truncate, disk_i_size is only adjusted down
- * as we remove extents, so it should represent the true
- * size of the inode, so reset the in memory size and
- * delete our orphan entry.
+ * Truncate failed, so fix up the in-memory size. We
+ * adjusted disk_i_size down as we removed extents, so
+ * wait for disk_i_size to be stable and then update the
+ * in-memory size to match.
*/
- trans = btrfs_join_transaction(root);
- if (IS_ERR(trans)) {
- btrfs_orphan_del(NULL, BTRFS_I(inode));
- return ret;
- }
- i_size_write(inode, BTRFS_I(inode)->disk_i_size);
- err = btrfs_orphan_del(trans, BTRFS_I(inode));
+ err = btrfs_wait_ordered_range(inode, 0, (u64)-1);
if (err)
- btrfs_abort_transaction(trans, err);
- btrfs_end_transaction(trans);
+ return err;
+ i_size_write(inode, BTRFS_I(inode)->disk_i_size);
}
}
@@ -5269,13 +5341,52 @@ static void evict_inode_truncate_pages(struct inode *inode)
spin_unlock(&io_tree->lock);
}
+static struct btrfs_trans_handle *evict_refill_and_join(struct btrfs_root *root,
+ struct btrfs_block_rsv *rsv,
+ u64 min_size)
+{
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
+ int failures = 0;
+
+ for (;;) {
+ struct btrfs_trans_handle *trans;
+ int ret;
+
+ ret = btrfs_block_rsv_refill(root, rsv, min_size,
+ BTRFS_RESERVE_FLUSH_LIMIT);
+
+ if (ret && ++failures > 2) {
+ btrfs_warn(fs_info,
+ "could not allocate space for a delete; will truncate on mount");
+ return ERR_PTR(-ENOSPC);
+ }
+
+ trans = btrfs_join_transaction(root);
+ if (IS_ERR(trans) || !ret)
+ return trans;
+
+ /*
+ * Try to steal from the global reserve if there is space for
+ * it.
+ */
+ if (!btrfs_check_space_for_delayed_refs(trans, fs_info) &&
+ !btrfs_block_rsv_migrate(global_rsv, rsv, min_size, 0))
+ return trans;
+
+ /* If not, commit and try again. */
+ ret = btrfs_commit_transaction(trans);
+ if (ret)
+ return ERR_PTR(ret);
+ }
+}
+
void btrfs_evict_inode(struct inode *inode)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(inode)->root;
- struct btrfs_block_rsv *rsv, *global_rsv;
- int steal_from_global = 0;
+ struct btrfs_block_rsv *rsv;
u64 min_size;
int ret;
@@ -5296,21 +5407,16 @@ void btrfs_evict_inode(struct inode *inode)
btrfs_is_free_space_inode(BTRFS_I(inode))))
goto no_delete;
- if (is_bad_inode(inode)) {
- btrfs_orphan_del(NULL, BTRFS_I(inode));
+ if (is_bad_inode(inode))
goto no_delete;
- }
/* do we really want it for ->i_nlink > 0 and zero btrfs_root_refs? */
if (!special_file(inode->i_mode))
btrfs_wait_ordered_range(inode, 0, (u64)-1);
btrfs_free_io_failure_record(BTRFS_I(inode), 0, (u64)-1);
- if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) {
- BUG_ON(test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
- &BTRFS_I(inode)->runtime_flags));
+ if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags))
goto no_delete;
- }
if (inode->i_nlink > 0) {
BUG_ON(btrfs_root_refs(&root->root_item) != 0 &&
@@ -5319,130 +5425,63 @@ void btrfs_evict_inode(struct inode *inode)
}
ret = btrfs_commit_inode_delayed_inode(BTRFS_I(inode));
- if (ret) {
- btrfs_orphan_del(NULL, BTRFS_I(inode));
+ if (ret)
goto no_delete;
- }
rsv = btrfs_alloc_block_rsv(fs_info, BTRFS_BLOCK_RSV_TEMP);
- if (!rsv) {
- btrfs_orphan_del(NULL, BTRFS_I(inode));
+ if (!rsv)
goto no_delete;
- }
rsv->size = min_size;
rsv->failfast = 1;
- global_rsv = &fs_info->global_block_rsv;
btrfs_i_size_write(BTRFS_I(inode), 0);
- /*
- * This is a bit simpler than btrfs_truncate since we've already
- * reserved our space for our orphan item in the unlink, so we just
- * need to reserve some slack space in case we add bytes and update
- * inode item when doing the truncate.
- */
while (1) {
- ret = btrfs_block_rsv_refill(root, rsv, min_size,
- BTRFS_RESERVE_FLUSH_LIMIT);
-
- /*
- * Try and steal from the global reserve since we will
- * likely not use this space anyway, we want to try as
- * hard as possible to get this to work.
- */
- if (ret)
- steal_from_global++;
- else
- steal_from_global = 0;
- ret = 0;
-
- /*
- * steal_from_global == 0: we reserved stuff, hooray!
- * steal_from_global == 1: we didn't reserve stuff, boo!
- * steal_from_global == 2: we've committed, still not a lot of
- * room but maybe we'll have room in the global reserve this
- * time.
- * steal_from_global == 3: abandon all hope!
- */
- if (steal_from_global > 2) {
- btrfs_warn(fs_info,
- "Could not get space for a delete, will truncate on mount %d",
- ret);
- btrfs_orphan_del(NULL, BTRFS_I(inode));
- btrfs_free_block_rsv(fs_info, rsv);
- goto no_delete;
- }
-
- trans = btrfs_join_transaction(root);
- if (IS_ERR(trans)) {
- btrfs_orphan_del(NULL, BTRFS_I(inode));
- btrfs_free_block_rsv(fs_info, rsv);
- goto no_delete;
- }
-
- /*
- * We can't just steal from the global reserve, we need to make
- * sure there is room to do it, if not we need to commit and try
- * again.
- */
- if (steal_from_global) {
- if (!btrfs_check_space_for_delayed_refs(trans, fs_info))
- ret = btrfs_block_rsv_migrate(global_rsv, rsv,
- min_size, 0);
- else
- ret = -ENOSPC;
- }
-
- /*
- * Couldn't steal from the global reserve, we have too much
- * pending stuff built up, commit the transaction and try it
- * again.
- */
- if (ret) {
- ret = btrfs_commit_transaction(trans);
- if (ret) {
- btrfs_orphan_del(NULL, BTRFS_I(inode));
- btrfs_free_block_rsv(fs_info, rsv);
- goto no_delete;
- }
- continue;
- } else {
- steal_from_global = 0;
- }
+ trans = evict_refill_and_join(root, rsv, min_size);
+ if (IS_ERR(trans))
+ goto free_rsv;
trans->block_rsv = rsv;
ret = btrfs_truncate_inode_items(trans, root, inode, 0, 0);
- if (ret != -ENOSPC && ret != -EAGAIN)
- break;
-
trans->block_rsv = &fs_info->trans_block_rsv;
btrfs_end_transaction(trans);
- trans = NULL;
btrfs_btree_balance_dirty(fs_info);
+ if (ret && ret != -ENOSPC && ret != -EAGAIN)
+ goto free_rsv;
+ else if (!ret)
+ break;
}
- btrfs_free_block_rsv(fs_info, rsv);
-
/*
- * Errors here aren't a big deal, it just means we leave orphan items
- * in the tree. They will be cleaned up on the next mount.
+ * Errors here aren't a big deal, it just means we leave orphan items in
+ * the tree. They will be cleaned up on the next mount. If the inode
+ * number gets reused, cleanup deletes the orphan item without doing
+ * anything, and unlink reuses the existing orphan item.
+ *
+ * If it turns out that we are dropping too many of these, we might want
+ * to add a mechanism for retrying these after a commit.
*/
- if (ret == 0) {
- trans->block_rsv = root->orphan_block_rsv;
+ trans = evict_refill_and_join(root, rsv, min_size);
+ if (!IS_ERR(trans)) {
+ trans->block_rsv = rsv;
btrfs_orphan_del(trans, BTRFS_I(inode));
- } else {
- btrfs_orphan_del(NULL, BTRFS_I(inode));
+ trans->block_rsv = &fs_info->trans_block_rsv;
+ btrfs_end_transaction(trans);
}
- trans->block_rsv = &fs_info->trans_block_rsv;
if (!(root == fs_info->tree_root ||
root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID))
btrfs_return_ino(root, btrfs_ino(BTRFS_I(inode)));
- btrfs_end_transaction(trans);
- btrfs_btree_balance_dirty(fs_info);
+free_rsv:
+ btrfs_free_block_rsv(fs_info, rsv);
no_delete:
+ /*
+ * If we didn't successfully delete, the orphan item will still be in
+ * the tree and we'll retry on the next mount. Again, we might also want
+ * to retry these periodically in the future.
+ */
btrfs_remove_delayed_node(BTRFS_I(inode));
clear_inode(inode);
}
@@ -5618,69 +5657,6 @@ static void inode_tree_del(struct inode *inode)
}
}
-void btrfs_invalidate_inodes(struct btrfs_root *root)
-{
- struct btrfs_fs_info *fs_info = root->fs_info;
- struct rb_node *node;
- struct rb_node *prev;
- struct btrfs_inode *entry;
- struct inode *inode;
- u64 objectid = 0;
-
- if (!test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
- WARN_ON(btrfs_root_refs(&root->root_item) != 0);
-
- spin_lock(&root->inode_lock);
-again:
- node = root->inode_tree.rb_node;
- prev = NULL;
- while (node) {
- prev = node;
- entry = rb_entry(node, struct btrfs_inode, rb_node);
-
- if (objectid < btrfs_ino(BTRFS_I(&entry->vfs_inode)))
- node = node->rb_left;
- else if (objectid > btrfs_ino(BTRFS_I(&entry->vfs_inode)))
- node = node->rb_right;
- else
- break;
- }
- if (!node) {
- while (prev) {
- entry = rb_entry(prev, struct btrfs_inode, rb_node);
- if (objectid <= btrfs_ino(BTRFS_I(&entry->vfs_inode))) {
- node = prev;
- break;
- }
- prev = rb_next(prev);
- }
- }
- while (node) {
- entry = rb_entry(node, struct btrfs_inode, rb_node);
- objectid = btrfs_ino(BTRFS_I(&entry->vfs_inode)) + 1;
- inode = igrab(&entry->vfs_inode);
- if (inode) {
- spin_unlock(&root->inode_lock);
- if (atomic_read(&inode->i_count) > 1)
- d_prune_aliases(inode);
- /*
- * btrfs_drop_inode will have it removed from
- * the inode cache when its usage count
- * hits zero.
- */
- iput(inode);
- cond_resched();
- spin_lock(&root->inode_lock);
- goto again;
- }
-
- if (cond_resched_lock(&root->inode_lock))
- goto again;
-
- node = rb_next(node);
- }
- spin_unlock(&root->inode_lock);
-}
static int btrfs_init_locked_inode(struct inode *inode, void *p)
{
@@ -5842,11 +5818,6 @@ static int btrfs_dentry_delete(const struct dentry *dentry)
return 0;
}
-static void btrfs_dentry_release(struct dentry *dentry)
-{
- kfree(dentry->d_fsdata);
-}
-
static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
@@ -5905,11 +5876,13 @@ static int btrfs_filldir(void *addr, int entries, struct dir_context *ctx)
struct dir_entry *entry = addr;
char *name = (char *)(entry + 1);
- ctx->pos = entry->offset;
- if (!dir_emit(ctx, name, entry->name_len, entry->ino,
- entry->type))
+ ctx->pos = get_unaligned(&entry->offset);
+ if (!dir_emit(ctx, name, get_unaligned(&entry->name_len),
+ get_unaligned(&entry->ino),
+ get_unaligned(&entry->type)))
return 1;
- addr += sizeof(struct dir_entry) + entry->name_len;
+ addr += sizeof(struct dir_entry) +
+ get_unaligned(&entry->name_len);
ctx->pos++;
}
return 0;
@@ -5999,14 +5972,15 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
}
entry = addr;
- entry->name_len = name_len;
+ put_unaligned(name_len, &entry->name_len);
name_ptr = (char *)(entry + 1);
read_extent_buffer(leaf, name_ptr, (unsigned long)(di + 1),
name_len);
- entry->type = btrfs_filetype_table[btrfs_dir_type(leaf, di)];
+ put_unaligned(btrfs_filetype_table[btrfs_dir_type(leaf, di)],
+ &entry->type);
btrfs_dir_item_key_to_cpu(leaf, di, &location);
- entry->ino = location.objectid;
- entry->offset = found_key.offset;
+ put_unaligned(location.objectid, &entry->ino);
+ put_unaligned(found_key.offset, &entry->offset);
entries++;
addr += sizeof(struct dir_entry) + name_len;
total_len += sizeof(struct dir_entry) + name_len;
@@ -6259,7 +6233,7 @@ static void btrfs_inherit_iflags(struct inode *inode, struct inode *dir)
BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM;
}
- btrfs_update_iflags(inode);
+ btrfs_sync_inode_flags_to_i_flags(inode);
}
static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
@@ -6575,8 +6549,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
goto out_unlock_inode;
} else {
btrfs_update_inode(trans, root, inode);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
}
out_unlock:
@@ -6652,8 +6625,7 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
goto out_unlock_inode;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
out_unlock:
btrfs_end_transaction(trans);
@@ -6696,8 +6668,9 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
* 2 items for inode and inode ref
* 2 items for dir items
* 1 item for parent inode
+ * 1 item for orphan item deletion if O_TMPFILE
*/
- trans = btrfs_start_transaction(root, 5);
+ trans = btrfs_start_transaction(root, inode->i_nlink ? 5 : 6);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
trans = NULL;
@@ -6798,12 +6771,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
if (err)
goto out_fail_inode;
- d_instantiate(dentry, inode);
- /*
- * mkdir is special. We're unlocking after we call d_instantiate
- * to avoid a race with nfsd calling d_instantiate.
- */
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
drop_on_err = 0;
out_fail:
@@ -7079,7 +7047,7 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
err = 0;
write_lock(&em_tree->lock);
- err = btrfs_add_extent_mapping(em_tree, &em, start, len);
+ err = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len);
write_unlock(&em_tree->lock);
out:
@@ -7364,6 +7332,14 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
btrfs_file_extent_other_encoding(leaf, fi))
goto out;
+ /*
+ * Do the same check as in btrfs_cross_ref_exist but without the
+ * unnecessary search.
+ */
+ if (btrfs_file_extent_generation(leaf, fi) <=
+ btrfs_root_last_snapshot(&root->root_item))
+ goto out;
+
backref_offset = btrfs_file_extent_offset(leaf, fi);
if (orig_start) {
@@ -7564,6 +7540,125 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
return em;
}
+
+static int btrfs_get_blocks_direct_read(struct extent_map *em,
+ struct buffer_head *bh_result,
+ struct inode *inode,
+ u64 start, u64 len)
+{
+ if (em->block_start == EXTENT_MAP_HOLE ||
+ test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+ return -ENOENT;
+
+ len = min(len, em->len - (start - em->start));
+
+ bh_result->b_blocknr = (em->block_start + (start - em->start)) >>
+ inode->i_blkbits;
+ bh_result->b_size = len;
+ bh_result->b_bdev = em->bdev;
+ set_buffer_mapped(bh_result);
+
+ return 0;
+}
+
+static int btrfs_get_blocks_direct_write(struct extent_map **map,
+ struct buffer_head *bh_result,
+ struct inode *inode,
+ struct btrfs_dio_data *dio_data,
+ u64 start, u64 len)
+{
+ struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+ struct extent_map *em = *map;
+ int ret = 0;
+
+ /*
+ * We don't allocate a new extent in the following cases
+ *
+ * 1) The inode is marked as NODATACOW. In this case we'll just use the
+ * existing extent.
+ * 2) The extent is marked as PREALLOC. We're good to go here and can
+ * just use the extent.
+ *
+ */
+ if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) ||
+ ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
+ em->block_start != EXTENT_MAP_HOLE)) {
+ int type;
+ u64 block_start, orig_start, orig_block_len, ram_bytes;
+
+ if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+ type = BTRFS_ORDERED_PREALLOC;
+ else
+ type = BTRFS_ORDERED_NOCOW;
+ len = min(len, em->len - (start - em->start));
+ block_start = em->block_start + (start - em->start);
+
+ if (can_nocow_extent(inode, start, &len, &orig_start,
+ &orig_block_len, &ram_bytes) == 1 &&
+ btrfs_inc_nocow_writers(fs_info, block_start)) {
+ struct extent_map *em2;
+
+ em2 = btrfs_create_dio_extent(inode, start, len,
+ orig_start, block_start,
+ len, orig_block_len,
+ ram_bytes, type);
+ btrfs_dec_nocow_writers(fs_info, block_start);
+ if (type == BTRFS_ORDERED_PREALLOC) {
+ free_extent_map(em);
+ *map = em = em2;
+ }
+
+ if (em2 && IS_ERR(em2)) {
+ ret = PTR_ERR(em2);
+ goto out;
+ }
+ /*
+ * For inode marked NODATACOW or extent marked PREALLOC,
+ * use the existing or preallocated extent, so does not
+ * need to adjust btrfs_space_info's bytes_may_use.
+ */
+ btrfs_free_reserved_data_space_noquota(inode, start,
+ len);
+ goto skip_cow;
+ }
+ }
+
+ /* this will cow the extent */
+ len = bh_result->b_size;
+ free_extent_map(em);
+ *map = em = btrfs_new_extent_direct(inode, start, len);
+ if (IS_ERR(em)) {
+ ret = PTR_ERR(em);
+ goto out;
+ }
+
+ len = min(len, em->len - (start - em->start));
+
+skip_cow:
+ bh_result->b_blocknr = (em->block_start + (start - em->start)) >>
+ inode->i_blkbits;
+ bh_result->b_size = len;
+ bh_result->b_bdev = em->bdev;
+ set_buffer_mapped(bh_result);
+
+ if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+ set_buffer_new(bh_result);
+
+ /*
+ * Need to update the i_size under the extent lock so buffered
+ * readers will get the updated i_size when we unlock.
+ */
+ if (!dio_data->overwrite && start + len > i_size_read(inode))
+ i_size_write(inode, start + len);
+
+ WARN_ON(dio_data->reserve < len);
+ dio_data->reserve -= len;
+ dio_data->unsubmitted_oe_range_end = start + len;
+ current->journal_info = dio_data;
+out:
+ return ret;
+}
+
static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
@@ -7632,116 +7727,36 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
goto unlock_err;
}
- /* Just a good old fashioned hole, return */
- if (!create && (em->block_start == EXTENT_MAP_HOLE ||
- test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
- free_extent_map(em);
- goto unlock_err;
- }
-
- /*
- * We don't allocate a new extent in the following cases
- *
- * 1) The inode is marked as NODATACOW. In this case we'll just use the
- * existing extent.
- * 2) The extent is marked as PREALLOC. We're good to go here and can
- * just use the extent.
- *
- */
- if (!create) {
- len = min(len, em->len - (start - em->start));
- lockstart = start + len;
- goto unlock;
- }
-
- if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) ||
- ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
- em->block_start != EXTENT_MAP_HOLE)) {
- int type;
- u64 block_start, orig_start, orig_block_len, ram_bytes;
-
- if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
- type = BTRFS_ORDERED_PREALLOC;
- else
- type = BTRFS_ORDERED_NOCOW;
- len = min(len, em->len - (start - em->start));
- block_start = em->block_start + (start - em->start);
-
- if (can_nocow_extent(inode, start, &len, &orig_start,
- &orig_block_len, &ram_bytes) == 1 &&
- btrfs_inc_nocow_writers(fs_info, block_start)) {
- struct extent_map *em2;
-
- em2 = btrfs_create_dio_extent(inode, start, len,
- orig_start, block_start,
- len, orig_block_len,
- ram_bytes, type);
- btrfs_dec_nocow_writers(fs_info, block_start);
- if (type == BTRFS_ORDERED_PREALLOC) {
- free_extent_map(em);
- em = em2;
- }
- if (em2 && IS_ERR(em2)) {
- ret = PTR_ERR(em2);
- goto unlock_err;
- }
- /*
- * For inode marked NODATACOW or extent marked PREALLOC,
- * use the existing or preallocated extent, so does not
- * need to adjust btrfs_space_info's bytes_may_use.
- */
- btrfs_free_reserved_data_space_noquota(inode,
- start, len);
- goto unlock;
- }
- }
-
- /*
- * this will cow the extent, reset the len in case we changed
- * it above
- */
- len = bh_result->b_size;
- free_extent_map(em);
- em = btrfs_new_extent_direct(inode, start, len);
- if (IS_ERR(em)) {
- ret = PTR_ERR(em);
- goto unlock_err;
- }
- len = min(len, em->len - (start - em->start));
-unlock:
- bh_result->b_blocknr = (em->block_start + (start - em->start)) >>
- inode->i_blkbits;
- bh_result->b_size = len;
- bh_result->b_bdev = em->bdev;
- set_buffer_mapped(bh_result);
if (create) {
- if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
- set_buffer_new(bh_result);
+ ret = btrfs_get_blocks_direct_write(&em, bh_result, inode,
+ dio_data, start, len);
+ if (ret < 0)
+ goto unlock_err;
- /*
- * Need to update the i_size under the extent lock so buffered
- * readers will get the updated i_size when we unlock.
- */
- if (!dio_data->overwrite && start + len > i_size_read(inode))
- i_size_write(inode, start + len);
-
- WARN_ON(dio_data->reserve < len);
- dio_data->reserve -= len;
- dio_data->unsubmitted_oe_range_end = start + len;
- current->journal_info = dio_data;
- }
-
- /*
- * In the case of write we need to clear and unlock the entire range,
- * in the case of read we need to unlock only the end area that we
- * aren't using if there is any left over space.
- */
- if (lockstart < lockend) {
- clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
- lockend, unlock_bits, 1, 0,
- &cached_state);
+ /* clear and unlock the entire range */
+ clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
+ unlock_bits, 1, 0, &cached_state);
} else {
- free_extent_state(cached_state);
+ ret = btrfs_get_blocks_direct_read(em, bh_result, inode,
+ start, len);
+ /* Can be negative only if we read from a hole */
+ if (ret < 0) {
+ ret = 0;
+ free_extent_map(em);
+ goto unlock_err;
+ }
+ /*
+ * We need to unlock only the end area that we aren't using.
+ * The rest is going to be unlocked by the endio routine.
+ */
+ lockstart = start + bh_result->b_size;
+ if (lockstart < lockend) {
+ clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
+ lockend, unlock_bits, 1, 0,
+ &cached_state);
+ } else {
+ free_extent_state(cached_state);
+ }
}
free_extent_map(em);
@@ -8127,7 +8142,6 @@ static void __endio_write_update_ordered(struct inode *inode,
u64 ordered_offset = offset;
u64 ordered_bytes = bytes;
u64 last_offset;
- int ret;
if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
wq = fs_info->endio_freespace_worker;
@@ -8137,32 +8151,31 @@ static void __endio_write_update_ordered(struct inode *inode,
func = btrfs_endio_write_helper;
}
-again:
- last_offset = ordered_offset;
- ret = btrfs_dec_test_first_ordered_pending(inode, &ordered,
- &ordered_offset,
- ordered_bytes,
- uptodate);
- if (!ret)
- goto out_test;
-
- btrfs_init_work(&ordered->work, func, finish_ordered_fn, NULL, NULL);
- btrfs_queue_work(wq, &ordered->work);
-out_test:
- /*
- * If btrfs_dec_test_ordered_pending does not find any ordered extent
- * in the range, we can exit.
- */
- if (ordered_offset == last_offset)
- return;
- /*
- * our bio might span multiple ordered extents. If we haven't
- * completed the accounting for the whole dio, go back and try again
- */
- if (ordered_offset < offset + bytes) {
- ordered_bytes = offset + bytes - ordered_offset;
- ordered = NULL;
- goto again;
+ while (ordered_offset < offset + bytes) {
+ last_offset = ordered_offset;
+ if (btrfs_dec_test_first_ordered_pending(inode, &ordered,
+ &ordered_offset,
+ ordered_bytes,
+ uptodate)) {
+ btrfs_init_work(&ordered->work, func,
+ finish_ordered_fn,
+ NULL, NULL);
+ btrfs_queue_work(wq, &ordered->work);
+ }
+ /*
+ * If btrfs_dec_test_ordered_pending does not find any ordered
+ * extent in the range, we can exit.
+ */
+ if (ordered_offset == last_offset)
+ return;
+ /*
+ * Our bio might span multiple ordered extents. In this case
+ * we keep goin until we have accounted the whole dio.
+ */
+ if (ordered_offset < offset + bytes) {
+ ordered_bytes = offset + bytes - ordered_offset;
+ ordered = NULL;
+ }
}
}
@@ -8701,29 +8714,19 @@ static int btrfs_writepage(struct page *page, struct writeback_control *wbc)
static int btrfs_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
- struct extent_io_tree *tree;
-
- tree = &BTRFS_I(mapping->host)->io_tree;
- return extent_writepages(tree, mapping, wbc);
+ return extent_writepages(mapping, wbc);
}
static int
btrfs_readpages(struct file *file, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
- struct extent_io_tree *tree;
- tree = &BTRFS_I(mapping->host)->io_tree;
- return extent_readpages(tree, mapping, pages, nr_pages);
+ return extent_readpages(mapping, pages, nr_pages);
}
+
static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags)
{
- struct extent_io_tree *tree;
- struct extent_map_tree *map;
- int ret;
-
- tree = &BTRFS_I(page->mapping->host)->io_tree;
- map = &BTRFS_I(page->mapping->host)->extent_tree;
- ret = try_release_extent_mapping(map, tree, page, gfp_flags);
+ int ret = try_release_extent_mapping(page, gfp_flags);
if (ret == 1) {
ClearPagePrivate(page);
set_page_private(page, 0);
@@ -8864,8 +8867,8 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
*
* We are not allowed to take the i_mutex here so we have to play games to
* protect against truncate races as the page could now be beyond EOF. Because
- * vmtruncate() writes the inode size before removing pages, once we have the
- * page lock we can determine safely if the page is beyond EOF. If it is not
+ * truncate_setsize() writes the inode size before removing pages, once we have
+ * the page lock we can determine safely if the page is beyond EOF. If it is not
* beyond EOF, then the page is guaranteed safe against truncation until we
* unlock the page.
*/
@@ -9027,8 +9030,7 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback)
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_block_rsv *rsv;
- int ret = 0;
- int err = 0;
+ int ret;
struct btrfs_trans_handle *trans;
u64 mask = fs_info->sectorsize - 1;
u64 min_size = btrfs_calc_trunc_metadata_size(fs_info, 1);
@@ -9041,39 +9043,31 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback)
}
/*
- * Yes ladies and gentlemen, this is indeed ugly. The fact is we have
- * 3 things going on here
+ * Yes ladies and gentlemen, this is indeed ugly. We have a couple of
+ * things going on here:
*
- * 1) We need to reserve space for our orphan item and the space to
- * delete our orphan item. Lord knows we don't want to have a dangling
- * orphan item because we didn't reserve space to remove it.
+ * 1) We need to reserve space to update our inode.
*
- * 2) We need to reserve space to update our inode.
- *
- * 3) We need to have something to cache all the space that is going to
+ * 2) We need to have something to cache all the space that is going to
* be free'd up by the truncate operation, but also have some slack
* space reserved in case it uses space during the truncate (thank you
* very much snapshotting).
*
- * And we need these to all be separate. The fact is we can use a lot of
+ * And we need these to be separate. The fact is we can use a lot of
* space doing the truncate, and we have no earthly idea how much space
* we will use, so we need the truncate reservation to be separate so it
- * doesn't end up using space reserved for updating the inode or
- * removing the orphan item. We also need to be able to stop the
- * transaction and start a new one, which means we need to be able to
- * update the inode several times, and we have no idea of knowing how
- * many times that will be, so we can't just reserve 1 item for the
- * entirety of the operation, so that has to be done separately as well.
- * Then there is the orphan item, which does indeed need to be held on
- * to for the whole operation, and we need nobody to touch this reserved
- * space except the orphan code.
+ * doesn't end up using space reserved for updating the inode. We also
+ * need to be able to stop the transaction and start a new one, which
+ * means we need to be able to update the inode several times, and we
+ * have no idea of knowing how many times that will be, so we can't just
+ * reserve 1 item for the entirety of the operation, so that has to be
+ * done separately as well.
*
* So that leaves us with
*
- * 1) root->orphan_block_rsv - for the orphan deletion.
- * 2) rsv - for the truncate reservation, which we will steal from the
+ * 1) rsv - for the truncate reservation, which we will steal from the
* transaction reservation.
- * 3) fs_info->trans_block_rsv - this will have 1 items worth left for
+ * 2) fs_info->trans_block_rsv - this will have 1 items worth left for
* updating the inode.
*/
rsv = btrfs_alloc_block_rsv(fs_info, BTRFS_BLOCK_RSV_TEMP);
@@ -9088,7 +9082,7 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback)
*/
trans = btrfs_start_transaction(root, 2);
if (IS_ERR(trans)) {
- err = PTR_ERR(trans);
+ ret = PTR_ERR(trans);
goto out;
}
@@ -9112,23 +9106,19 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback)
inode->i_size,
BTRFS_EXTENT_DATA_KEY);
trans->block_rsv = &fs_info->trans_block_rsv;
- if (ret != -ENOSPC && ret != -EAGAIN) {
- err = ret;
+ if (ret != -ENOSPC && ret != -EAGAIN)
break;
- }
ret = btrfs_update_inode(trans, root, inode);
- if (ret) {
- err = ret;
+ if (ret)
break;
- }
btrfs_end_transaction(trans);
btrfs_btree_balance_dirty(fs_info);
trans = btrfs_start_transaction(root, 2);
if (IS_ERR(trans)) {
- ret = err = PTR_ERR(trans);
+ ret = PTR_ERR(trans);
trans = NULL;
break;
}
@@ -9161,29 +9151,23 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback)
btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
}
- if (ret == 0 && inode->i_nlink > 0) {
- trans->block_rsv = root->orphan_block_rsv;
- ret = btrfs_orphan_del(trans, BTRFS_I(inode));
- if (ret)
- err = ret;
- }
-
if (trans) {
- trans->block_rsv = &fs_info->trans_block_rsv;
- ret = btrfs_update_inode(trans, root, inode);
- if (ret && !err)
- err = ret;
+ int ret2;
- ret = btrfs_end_transaction(trans);
+ trans->block_rsv = &fs_info->trans_block_rsv;
+ ret2 = btrfs_update_inode(trans, root, inode);
+ if (ret2 && !ret)
+ ret = ret2;
+
+ ret2 = btrfs_end_transaction(trans);
+ if (ret2 && !ret)
+ ret = ret2;
btrfs_btree_balance_dirty(fs_info);
}
out:
btrfs_free_block_rsv(fs_info, rsv);
- if (ret && !err)
- err = ret;
-
- return err;
+ return ret;
}
/*
@@ -9319,13 +9303,6 @@ void btrfs_destroy_inode(struct inode *inode)
if (!root)
goto free;
- if (test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
- &BTRFS_I(inode)->runtime_flags)) {
- btrfs_info(fs_info, "inode %llu still on the orphan list",
- btrfs_ino(BTRFS_I(inode)));
- atomic_dec(&root->orphan_inodes);
- }
-
while (1) {
ordered = btrfs_lookup_first_ordered_extent(inode, (u64)-1);
if (!ordered)
@@ -9959,6 +9936,13 @@ static int btrfs_rename2(struct inode *old_dir, struct dentry *old_dentry,
return btrfs_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
}
+struct btrfs_delalloc_work {
+ struct inode *inode;
+ struct completion completion;
+ struct list_head list;
+ struct btrfs_work work;
+};
+
static void btrfs_run_delalloc_work(struct btrfs_work *work)
{
struct btrfs_delalloc_work *delalloc_work;
@@ -9972,15 +9956,11 @@ static void btrfs_run_delalloc_work(struct btrfs_work *work)
&BTRFS_I(inode)->runtime_flags))
filemap_flush(inode->i_mapping);
- if (delalloc_work->delay_iput)
- btrfs_add_delayed_iput(inode);
- else
- iput(inode);
+ iput(inode);
complete(&delalloc_work->completion);
}
-struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
- int delay_iput)
+static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode)
{
struct btrfs_delalloc_work *work;
@@ -9991,7 +9971,6 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
init_completion(&work->completion);
INIT_LIST_HEAD(&work->list);
work->inode = inode;
- work->delay_iput = delay_iput;
WARN_ON_ONCE(!inode);
btrfs_init_work(&work->work, btrfs_flush_delalloc_helper,
btrfs_run_delalloc_work, NULL, NULL);
@@ -9999,18 +9978,11 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
return work;
}
-void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work)
-{
- wait_for_completion(&work->completion);
- kfree(work);
-}
-
/*
* some fairly slow code that needs optimization. This walks the list
* of all the inodes with pending delalloc and forces them to disk.
*/
-static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput,
- int nr)
+static int start_delalloc_inodes(struct btrfs_root *root, int nr)
{
struct btrfs_inode *binode;
struct inode *inode;
@@ -10038,12 +10010,9 @@ static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput,
}
spin_unlock(&root->delalloc_lock);
- work = btrfs_alloc_delalloc_work(inode, delay_iput);
+ work = btrfs_alloc_delalloc_work(inode);
if (!work) {
- if (delay_iput)
- btrfs_add_delayed_iput(inode);
- else
- iput(inode);
+ iput(inode);
ret = -ENOMEM;
goto out;
}
@@ -10061,10 +10030,11 @@ static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput,
out:
list_for_each_entry_safe(work, next, &works, list) {
list_del_init(&work->list);
- btrfs_wait_and_free_delalloc_work(work);
+ wait_for_completion(&work->completion);
+ kfree(work);
}
- if (!list_empty_careful(&splice)) {
+ if (!list_empty(&splice)) {
spin_lock(&root->delalloc_lock);
list_splice_tail(&splice, &root->delalloc_inodes);
spin_unlock(&root->delalloc_lock);
@@ -10073,7 +10043,7 @@ static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput,
return ret;
}
-int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
+int btrfs_start_delalloc_inodes(struct btrfs_root *root)
{
struct btrfs_fs_info *fs_info = root->fs_info;
int ret;
@@ -10081,14 +10051,13 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
return -EROFS;
- ret = __start_delalloc_inodes(root, delay_iput, -1);
+ ret = start_delalloc_inodes(root, -1);
if (ret > 0)
ret = 0;
return ret;
}
-int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput,
- int nr)
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int nr)
{
struct btrfs_root *root;
struct list_head splice;
@@ -10111,7 +10080,7 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput,
&fs_info->delalloc_roots);
spin_unlock(&fs_info->delalloc_root_lock);
- ret = __start_delalloc_inodes(root, delay_iput, nr);
+ ret = start_delalloc_inodes(root, nr);
btrfs_put_fs_root(root);
if (ret < 0)
goto out;
@@ -10126,7 +10095,7 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput,
ret = 0;
out:
- if (!list_empty_careful(&splice)) {
+ if (!list_empty(&splice)) {
spin_lock(&fs_info->delalloc_root_lock);
list_splice_tail(&splice, &fs_info->delalloc_roots);
spin_unlock(&fs_info->delalloc_root_lock);
@@ -10246,8 +10215,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
goto out_unlock_inode;
}
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
out_unlock:
btrfs_end_transaction(trans);
@@ -10665,5 +10633,4 @@ static const struct inode_operations btrfs_symlink_inode_operations = {
const struct dentry_operations btrfs_dentry_operations = {
.d_delete = btrfs_dentry_delete,
- .d_release = btrfs_dentry_release,
};
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 632e26d..d29992f 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -93,20 +93,22 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
int no_time_update);
/* Mask out flags that are inappropriate for the given type of inode. */
-static unsigned int btrfs_mask_flags(umode_t mode, unsigned int flags)
+static unsigned int btrfs_mask_fsflags_for_type(struct inode *inode,
+ unsigned int flags)
{
- if (S_ISDIR(mode))
+ if (S_ISDIR(inode->i_mode))
return flags;
- else if (S_ISREG(mode))
+ else if (S_ISREG(inode->i_mode))
return flags & ~FS_DIRSYNC_FL;
else
return flags & (FS_NODUMP_FL | FS_NOATIME_FL);
}
/*
- * Export inode flags to the format expected by the FS_IOC_GETFLAGS ioctl.
+ * Export internal inode flags to the format expected by the FS_IOC_GETFLAGS
+ * ioctl.
*/
-static unsigned int btrfs_flags_to_ioctl(unsigned int flags)
+static unsigned int btrfs_inode_flags_to_fsflags(unsigned int flags)
{
unsigned int iflags = 0;
@@ -136,20 +138,20 @@ static unsigned int btrfs_flags_to_ioctl(unsigned int flags)
/*
* Update inode->i_flags based on the btrfs internal flags.
*/
-void btrfs_update_iflags(struct inode *inode)
+void btrfs_sync_inode_flags_to_i_flags(struct inode *inode)
{
- struct btrfs_inode *ip = BTRFS_I(inode);
+ struct btrfs_inode *binode = BTRFS_I(inode);
unsigned int new_fl = 0;
- if (ip->flags & BTRFS_INODE_SYNC)
+ if (binode->flags & BTRFS_INODE_SYNC)
new_fl |= S_SYNC;
- if (ip->flags & BTRFS_INODE_IMMUTABLE)
+ if (binode->flags & BTRFS_INODE_IMMUTABLE)
new_fl |= S_IMMUTABLE;
- if (ip->flags & BTRFS_INODE_APPEND)
+ if (binode->flags & BTRFS_INODE_APPEND)
new_fl |= S_APPEND;
- if (ip->flags & BTRFS_INODE_NOATIME)
+ if (binode->flags & BTRFS_INODE_NOATIME)
new_fl |= S_NOATIME;
- if (ip->flags & BTRFS_INODE_DIRSYNC)
+ if (binode->flags & BTRFS_INODE_DIRSYNC)
new_fl |= S_DIRSYNC;
set_mask_bits(&inode->i_flags,
@@ -159,15 +161,16 @@ void btrfs_update_iflags(struct inode *inode)
static int btrfs_ioctl_getflags(struct file *file, void __user *arg)
{
- struct btrfs_inode *ip = BTRFS_I(file_inode(file));
- unsigned int flags = btrfs_flags_to_ioctl(ip->flags);
+ struct btrfs_inode *binode = BTRFS_I(file_inode(file));
+ unsigned int flags = btrfs_inode_flags_to_fsflags(binode->flags);
if (copy_to_user(arg, &flags, sizeof(flags)))
return -EFAULT;
return 0;
}
-static int check_flags(unsigned int flags)
+/* Check if @flags are a supported and valid set of FS_*_FL flags */
+static int check_fsflags(unsigned int flags)
{
if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
FS_NOATIME_FL | FS_NODUMP_FL | \
@@ -186,13 +189,13 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
{
struct inode *inode = file_inode(file);
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
- struct btrfs_inode *ip = BTRFS_I(inode);
- struct btrfs_root *root = ip->root;
+ struct btrfs_inode *binode = BTRFS_I(inode);
+ struct btrfs_root *root = binode->root;
struct btrfs_trans_handle *trans;
- unsigned int flags, oldflags;
+ unsigned int fsflags, old_fsflags;
int ret;
- u64 ip_oldflags;
- unsigned int i_oldflags;
+ u64 old_flags;
+ unsigned int old_i_flags;
umode_t mode;
if (!inode_owner_or_capable(inode))
@@ -201,10 +204,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
if (btrfs_root_readonly(root))
return -EROFS;
- if (copy_from_user(&flags, arg, sizeof(flags)))
+ if (copy_from_user(&fsflags, arg, sizeof(fsflags)))
return -EFAULT;
- ret = check_flags(flags);
+ ret = check_fsflags(fsflags);
if (ret)
return ret;
@@ -214,44 +217,44 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
inode_lock(inode);
- ip_oldflags = ip->flags;
- i_oldflags = inode->i_flags;
+ old_flags = binode->flags;
+ old_i_flags = inode->i_flags;
mode = inode->i_mode;
- flags = btrfs_mask_flags(inode->i_mode, flags);
- oldflags = btrfs_flags_to_ioctl(ip->flags);
- if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
+ fsflags = btrfs_mask_fsflags_for_type(inode, fsflags);
+ old_fsflags = btrfs_inode_flags_to_fsflags(binode->flags);
+ if ((fsflags ^ old_fsflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
if (!capable(CAP_LINUX_IMMUTABLE)) {
ret = -EPERM;
goto out_unlock;
}
}
- if (flags & FS_SYNC_FL)
- ip->flags |= BTRFS_INODE_SYNC;
+ if (fsflags & FS_SYNC_FL)
+ binode->flags |= BTRFS_INODE_SYNC;
else
- ip->flags &= ~BTRFS_INODE_SYNC;
- if (flags & FS_IMMUTABLE_FL)
- ip->flags |= BTRFS_INODE_IMMUTABLE;
+ binode->flags &= ~BTRFS_INODE_SYNC;
+ if (fsflags & FS_IMMUTABLE_FL)
+ binode->flags |= BTRFS_INODE_IMMUTABLE;
else
- ip->flags &= ~BTRFS_INODE_IMMUTABLE;
- if (flags & FS_APPEND_FL)
- ip->flags |= BTRFS_INODE_APPEND;
+ binode->flags &= ~BTRFS_INODE_IMMUTABLE;
+ if (fsflags & FS_APPEND_FL)
+ binode->flags |= BTRFS_INODE_APPEND;
else
- ip->flags &= ~BTRFS_INODE_APPEND;
- if (flags & FS_NODUMP_FL)
- ip->flags |= BTRFS_INODE_NODUMP;
+ binode->flags &= ~BTRFS_INODE_APPEND;
+ if (fsflags & FS_NODUMP_FL)
+ binode->flags |= BTRFS_INODE_NODUMP;
else
- ip->flags &= ~BTRFS_INODE_NODUMP;
- if (flags & FS_NOATIME_FL)
- ip->flags |= BTRFS_INODE_NOATIME;
+ binode->flags &= ~BTRFS_INODE_NODUMP;
+ if (fsflags & FS_NOATIME_FL)
+ binode->flags |= BTRFS_INODE_NOATIME;
else
- ip->flags &= ~BTRFS_INODE_NOATIME;
- if (flags & FS_DIRSYNC_FL)
- ip->flags |= BTRFS_INODE_DIRSYNC;
+ binode->flags &= ~BTRFS_INODE_NOATIME;
+ if (fsflags & FS_DIRSYNC_FL)
+ binode->flags |= BTRFS_INODE_DIRSYNC;
else
- ip->flags &= ~BTRFS_INODE_DIRSYNC;
- if (flags & FS_NOCOW_FL) {
+ binode->flags &= ~BTRFS_INODE_DIRSYNC;
+ if (fsflags & FS_NOCOW_FL) {
if (S_ISREG(mode)) {
/*
* It's safe to turn csums off here, no extents exist.
@@ -259,10 +262,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
* status of the file and will not set it.
*/
if (inode->i_size == 0)
- ip->flags |= BTRFS_INODE_NODATACOW
- | BTRFS_INODE_NODATASUM;
+ binode->flags |= BTRFS_INODE_NODATACOW
+ | BTRFS_INODE_NODATASUM;
} else {
- ip->flags |= BTRFS_INODE_NODATACOW;
+ binode->flags |= BTRFS_INODE_NODATACOW;
}
} else {
/*
@@ -270,10 +273,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
*/
if (S_ISREG(mode)) {
if (inode->i_size == 0)
- ip->flags &= ~(BTRFS_INODE_NODATACOW
+ binode->flags &= ~(BTRFS_INODE_NODATACOW
| BTRFS_INODE_NODATASUM);
} else {
- ip->flags &= ~BTRFS_INODE_NODATACOW;
+ binode->flags &= ~BTRFS_INODE_NODATACOW;
}
}
@@ -282,18 +285,18 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
* flag may be changed automatically if compression code won't make
* things smaller.
*/
- if (flags & FS_NOCOMP_FL) {
- ip->flags &= ~BTRFS_INODE_COMPRESS;
- ip->flags |= BTRFS_INODE_NOCOMPRESS;
+ if (fsflags & FS_NOCOMP_FL) {
+ binode->flags &= ~BTRFS_INODE_COMPRESS;
+ binode->flags |= BTRFS_INODE_NOCOMPRESS;
ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0);
if (ret && ret != -ENODATA)
goto out_drop;
- } else if (flags & FS_COMPR_FL) {
+ } else if (fsflags & FS_COMPR_FL) {
const char *comp;
- ip->flags |= BTRFS_INODE_COMPRESS;
- ip->flags &= ~BTRFS_INODE_NOCOMPRESS;
+ binode->flags |= BTRFS_INODE_COMPRESS;
+ binode->flags &= ~BTRFS_INODE_NOCOMPRESS;
comp = btrfs_compress_type2str(fs_info->compress_type);
if (!comp || comp[0] == 0)
@@ -308,7 +311,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0);
if (ret && ret != -ENODATA)
goto out_drop;
- ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
+ binode->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
}
trans = btrfs_start_transaction(root, 1);
@@ -317,7 +320,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
goto out_drop;
}
- btrfs_update_iflags(inode);
+ btrfs_sync_inode_flags_to_i_flags(inode);
inode_inc_iversion(inode);
inode->i_ctime = current_time(inode);
ret = btrfs_update_inode(trans, root, inode);
@@ -325,8 +328,8 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
btrfs_end_transaction(trans);
out_drop:
if (ret) {
- ip->flags = ip_oldflags;
- inode->i_flags = i_oldflags;
+ binode->flags = old_flags;
+ inode->i_flags = old_i_flags;
}
out_unlock:
@@ -335,6 +338,148 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
return ret;
}
+/*
+ * Translate btrfs internal inode flags to xflags as expected by the
+ * FS_IOC_FSGETXATT ioctl. Filter only the supported ones, unknown flags are
+ * silently dropped.
+ */
+static unsigned int btrfs_inode_flags_to_xflags(unsigned int flags)
+{
+ unsigned int xflags = 0;
+
+ if (flags & BTRFS_INODE_APPEND)
+ xflags |= FS_XFLAG_APPEND;
+ if (flags & BTRFS_INODE_IMMUTABLE)
+ xflags |= FS_XFLAG_IMMUTABLE;
+ if (flags & BTRFS_INODE_NOATIME)
+ xflags |= FS_XFLAG_NOATIME;
+ if (flags & BTRFS_INODE_NODUMP)
+ xflags |= FS_XFLAG_NODUMP;
+ if (flags & BTRFS_INODE_SYNC)
+ xflags |= FS_XFLAG_SYNC;
+
+ return xflags;
+}
+
+/* Check if @flags are a supported and valid set of FS_XFLAGS_* flags */
+static int check_xflags(unsigned int flags)
+{
+ if (flags & ~(FS_XFLAG_APPEND | FS_XFLAG_IMMUTABLE | FS_XFLAG_NOATIME |
+ FS_XFLAG_NODUMP | FS_XFLAG_SYNC))
+ return -EOPNOTSUPP;
+ return 0;
+}
+
+/*
+ * Set the xflags from the internal inode flags. The remaining items of fsxattr
+ * are zeroed.
+ */
+static int btrfs_ioctl_fsgetxattr(struct file *file, void __user *arg)
+{
+ struct btrfs_inode *binode = BTRFS_I(file_inode(file));
+ struct fsxattr fa;
+
+ memset(&fa, 0, sizeof(fa));
+ fa.fsx_xflags = btrfs_inode_flags_to_xflags(binode->flags);
+
+ if (copy_to_user(arg, &fa, sizeof(fa)))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int btrfs_ioctl_fssetxattr(struct file *file, void __user *arg)
+{
+ struct inode *inode = file_inode(file);
+ struct btrfs_inode *binode = BTRFS_I(inode);
+ struct btrfs_root *root = binode->root;
+ struct btrfs_trans_handle *trans;
+ struct fsxattr fa;
+ unsigned old_flags;
+ unsigned old_i_flags;
+ int ret = 0;
+
+ if (!inode_owner_or_capable(inode))
+ return -EPERM;
+
+ if (btrfs_root_readonly(root))
+ return -EROFS;
+
+ memset(&fa, 0, sizeof(fa));
+ if (copy_from_user(&fa, arg, sizeof(fa)))
+ return -EFAULT;
+
+ ret = check_xflags(fa.fsx_xflags);
+ if (ret)
+ return ret;
+
+ if (fa.fsx_extsize != 0 || fa.fsx_projid != 0 || fa.fsx_cowextsize != 0)
+ return -EOPNOTSUPP;
+
+ ret = mnt_want_write_file(file);
+ if (ret)
+ return ret;
+
+ inode_lock(inode);
+
+ old_flags = binode->flags;
+ old_i_flags = inode->i_flags;
+
+ /* We need the capabilities to change append-only or immutable inode */
+ if (((old_flags & (BTRFS_INODE_APPEND | BTRFS_INODE_IMMUTABLE)) ||
+ (fa.fsx_xflags & (FS_XFLAG_APPEND | FS_XFLAG_IMMUTABLE))) &&
+ !capable(CAP_LINUX_IMMUTABLE)) {
+ ret = -EPERM;
+ goto out_unlock;
+ }
+
+ if (fa.fsx_xflags & FS_XFLAG_SYNC)
+ binode->flags |= BTRFS_INODE_SYNC;
+ else
+ binode->flags &= ~BTRFS_INODE_SYNC;
+ if (fa.fsx_xflags & FS_XFLAG_IMMUTABLE)
+ binode->flags |= BTRFS_INODE_IMMUTABLE;
+ else
+ binode->flags &= ~BTRFS_INODE_IMMUTABLE;
+ if (fa.fsx_xflags & FS_XFLAG_APPEND)
+ binode->flags |= BTRFS_INODE_APPEND;
+ else
+ binode->flags &= ~BTRFS_INODE_APPEND;
+ if (fa.fsx_xflags & FS_XFLAG_NODUMP)
+ binode->flags |= BTRFS_INODE_NODUMP;
+ else
+ binode->flags &= ~BTRFS_INODE_NODUMP;
+ if (fa.fsx_xflags & FS_XFLAG_NOATIME)
+ binode->flags |= BTRFS_INODE_NOATIME;
+ else
+ binode->flags &= ~BTRFS_INODE_NOATIME;
+
+ /* 1 item for the inode */
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out_unlock;
+ }
+
+ btrfs_sync_inode_flags_to_i_flags(inode);
+ inode_inc_iversion(inode);
+ inode->i_ctime = current_time(inode);
+ ret = btrfs_update_inode(trans, root, inode);
+
+ btrfs_end_transaction(trans);
+
+out_unlock:
+ if (ret) {
+ binode->flags = old_flags;
+ inode->i_flags = old_i_flags;
+ }
+
+ inode_unlock(inode);
+ mnt_drop_write_file(file);
+
+ return ret;
+}
+
static int btrfs_ioctl_getversion(struct file *file, int __user *arg)
{
struct inode *inode = file_inode(file);
@@ -424,7 +569,6 @@ static noinline int create_subvol(struct inode *dir,
u64 objectid;
u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID;
u64 index = 0;
- u64 qgroup_reserved;
uuid_le new_uuid;
root_item = kzalloc(sizeof(*root_item), GFP_KERNEL);
@@ -449,8 +593,7 @@ static noinline int create_subvol(struct inode *dir,
* The same as the snapshot creation, please see the comment
* of create_snapshot().
*/
- ret = btrfs_subvolume_reserve_metadata(root, &block_rsv,
- 8, &qgroup_reserved, false);
+ ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 8, false);
if (ret)
goto fail_free;
@@ -573,7 +716,7 @@ static noinline int create_subvol(struct inode *dir,
btrfs_ino(BTRFS_I(dir)), index, name, namelen);
BUG_ON(ret);
- ret = btrfs_uuid_tree_add(trans, fs_info, root_item->uuid,
+ ret = btrfs_uuid_tree_add(trans, root_item->uuid,
BTRFS_UUID_KEY_SUBVOL, objectid);
if (ret)
btrfs_abort_transaction(trans, ret);
@@ -640,7 +783,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
wait_event(root->subv_writers->wait,
percpu_counter_sum(&root->subv_writers->counter) == 0);
- ret = btrfs_start_delalloc_inodes(root, 0);
+ ret = btrfs_start_delalloc_inodes(root);
if (ret)
goto dec_and_free;
@@ -658,7 +801,6 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
*/
ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root,
&pending_snapshot->block_rsv, 8,
- &pending_snapshot->qgroup_reserved,
false);
if (ret)
goto dec_and_free;
@@ -1457,7 +1599,6 @@ static noinline int btrfs_ioctl_resize(struct file *file,
return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
}
- mutex_lock(&fs_info->volume_mutex);
vol_args = memdup_user(arg, sizeof(*vol_args));
if (IS_ERR(vol_args)) {
ret = PTR_ERR(vol_args);
@@ -1565,7 +1706,6 @@ static noinline int btrfs_ioctl_resize(struct file *file,
out_free:
kfree(vol_args);
out:
- mutex_unlock(&fs_info->volume_mutex);
clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
mnt_drop_write_file(file);
return ret;
@@ -1832,60 +1972,6 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
return ret;
}
-/*
- * helper to check if the subvolume references other subvolumes
- */
-static noinline int may_destroy_subvol(struct btrfs_root *root)
-{
- struct btrfs_fs_info *fs_info = root->fs_info;
- struct btrfs_path *path;
- struct btrfs_dir_item *di;
- struct btrfs_key key;
- u64 dir_id;
- int ret;
-
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
- /* Make sure this root isn't set as the default subvol */
- dir_id = btrfs_super_root_dir(fs_info->super_copy);
- di = btrfs_lookup_dir_item(NULL, fs_info->tree_root, path,
- dir_id, "default", 7, 0);
- if (di && !IS_ERR(di)) {
- btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key);
- if (key.objectid == root->root_key.objectid) {
- ret = -EPERM;
- btrfs_err(fs_info,
- "deleting default subvolume %llu is not allowed",
- key.objectid);
- goto out;
- }
- btrfs_release_path(path);
- }
-
- key.objectid = root->root_key.objectid;
- key.type = BTRFS_ROOT_REF_KEY;
- key.offset = (u64)-1;
-
- ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
- if (ret < 0)
- goto out;
- BUG_ON(ret == 0);
-
- ret = 0;
- if (path->slots[0] > 0) {
- path->slots[0]--;
- btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
- if (key.objectid == root->root_key.objectid &&
- key.type == BTRFS_ROOT_REF_KEY)
- ret = -ENOTEMPTY;
- }
-out:
- btrfs_free_path(path);
- return ret;
-}
-
static noinline int key_in_sk(struct btrfs_key *key,
struct btrfs_ioctl_search_key *sk)
{
@@ -2066,7 +2152,7 @@ static noinline int search_ioctl(struct inode *inode,
root = btrfs_read_fs_root_no_name(info, &key);
if (IS_ERR(root)) {
btrfs_free_path(path);
- return -ENOENT;
+ return PTR_ERR(root);
}
}
@@ -2200,8 +2286,7 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info,
key.offset = (u64)-1;
root = btrfs_read_fs_root_no_name(info, &key);
if (IS_ERR(root)) {
- btrfs_err(info, "could not find root %llu", tree_id);
- ret = -ENOENT;
+ ret = PTR_ERR(root);
goto out;
}
@@ -2256,6 +2341,165 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info,
return ret;
}
+static int btrfs_search_path_in_tree_user(struct inode *inode,
+ struct btrfs_ioctl_ino_lookup_user_args *args)
+{
+ struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
+ struct super_block *sb = inode->i_sb;
+ struct btrfs_key upper_limit = BTRFS_I(inode)->location;
+ u64 treeid = BTRFS_I(inode)->root->root_key.objectid;
+ u64 dirid = args->dirid;
+ unsigned long item_off;
+ unsigned long item_len;
+ struct btrfs_inode_ref *iref;
+ struct btrfs_root_ref *rref;
+ struct btrfs_root *root;
+ struct btrfs_path *path;
+ struct btrfs_key key, key2;
+ struct extent_buffer *leaf;
+ struct inode *temp_inode;
+ char *ptr;
+ int slot;
+ int len;
+ int total_len = 0;
+ int ret;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ /*
+ * If the bottom subvolume does not exist directly under upper_limit,
+ * construct the path in from the bottom up.
+ */
+ if (dirid != upper_limit.objectid) {
+ ptr = &args->path[BTRFS_INO_LOOKUP_USER_PATH_MAX - 1];
+
+ key.objectid = treeid;
+ key.type = BTRFS_ROOT_ITEM_KEY;
+ key.offset = (u64)-1;
+ root = btrfs_read_fs_root_no_name(fs_info, &key);
+ if (IS_ERR(root)) {
+ ret = PTR_ERR(root);
+ goto out;
+ }
+
+ key.objectid = dirid;
+ key.type = BTRFS_INODE_REF_KEY;
+ key.offset = (u64)-1;
+ while (1) {
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0) {
+ goto out;
+ } else if (ret > 0) {
+ ret = btrfs_previous_item(root, path, dirid,
+ BTRFS_INODE_REF_KEY);
+ if (ret < 0) {
+ goto out;
+ } else if (ret > 0) {
+ ret = -ENOENT;
+ goto out;
+ }
+ }
+
+ leaf = path->nodes[0];
+ slot = path->slots[0];
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+
+ iref = btrfs_item_ptr(leaf, slot, struct btrfs_inode_ref);
+ len = btrfs_inode_ref_name_len(leaf, iref);
+ ptr -= len + 1;
+ total_len += len + 1;
+ if (ptr < args->path) {
+ ret = -ENAMETOOLONG;
+ goto out;
+ }
+
+ *(ptr + len) = '/';
+ read_extent_buffer(leaf, ptr,
+ (unsigned long)(iref + 1), len);
+
+ /* Check the read+exec permission of this directory */
+ ret = btrfs_previous_item(root, path, dirid,
+ BTRFS_INODE_ITEM_KEY);
+ if (ret < 0) {
+ goto out;
+ } else if (ret > 0) {
+ ret = -ENOENT;
+ goto out;
+ }
+
+ leaf = path->nodes[0];
+ slot = path->slots[0];
+ btrfs_item_key_to_cpu(leaf, &key2, slot);
+ if (key2.objectid != dirid) {
+ ret = -ENOENT;
+ goto out;
+ }
+
+ temp_inode = btrfs_iget(sb, &key2, root, NULL);
+ ret = inode_permission(temp_inode, MAY_READ | MAY_EXEC);
+ iput(temp_inode);
+ if (ret) {
+ ret = -EACCES;
+ goto out;
+ }
+
+ if (key.offset == upper_limit.objectid)
+ break;
+ if (key.objectid == BTRFS_FIRST_FREE_OBJECTID) {
+ ret = -EACCES;
+ goto out;
+ }
+
+ btrfs_release_path(path);
+ key.objectid = key.offset;
+ key.offset = (u64)-1;
+ dirid = key.objectid;
+ }
+
+ memmove(args->path, ptr, total_len);
+ args->path[total_len] = '\0';
+ btrfs_release_path(path);
+ }
+
+ /* Get the bottom subvolume's name from ROOT_REF */
+ root = fs_info->tree_root;
+ key.objectid = treeid;
+ key.type = BTRFS_ROOT_REF_KEY;
+ key.offset = args->treeid;
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0) {
+ goto out;
+ } else if (ret > 0) {
+ ret = -ENOENT;
+ goto out;
+ }
+
+ leaf = path->nodes[0];
+ slot = path->slots[0];
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+
+ item_off = btrfs_item_ptr_offset(leaf, slot);
+ item_len = btrfs_item_size_nr(leaf, slot);
+ /* Check if dirid in ROOT_REF corresponds to passed dirid */
+ rref = btrfs_item_ptr(leaf, slot, struct btrfs_root_ref);
+ if (args->dirid != btrfs_root_ref_dirid(leaf, rref)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* Copy subvolume's name */
+ item_off += sizeof(struct btrfs_root_ref);
+ item_len -= sizeof(struct btrfs_root_ref);
+ read_extent_buffer(leaf, args->name, item_off, item_len);
+ args->name[item_len] = 0;
+
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
static noinline int btrfs_ioctl_ino_lookup(struct file *file,
void __user *argp)
{
@@ -2298,6 +2542,265 @@ static noinline int btrfs_ioctl_ino_lookup(struct file *file,
return ret;
}
+/*
+ * Version of ino_lookup ioctl (unprivileged)
+ *
+ * The main differences from ino_lookup ioctl are:
+ *
+ * 1. Read + Exec permission will be checked using inode_permission() during
+ * path construction. -EACCES will be returned in case of failure.
+ * 2. Path construction will be stopped at the inode number which corresponds
+ * to the fd with which this ioctl is called. If constructed path does not
+ * exist under fd's inode, -EACCES will be returned.
+ * 3. The name of bottom subvolume is also searched and filled.
+ */
+static int btrfs_ioctl_ino_lookup_user(struct file *file, void __user *argp)
+{
+ struct btrfs_ioctl_ino_lookup_user_args *args;
+ struct inode *inode;
+ int ret;
+
+ args = memdup_user(argp, sizeof(*args));
+ if (IS_ERR(args))
+ return PTR_ERR(args);
+
+ inode = file_inode(file);
+
+ if (args->dirid == BTRFS_FIRST_FREE_OBJECTID &&
+ BTRFS_I(inode)->location.objectid != BTRFS_FIRST_FREE_OBJECTID) {
+ /*
+ * The subvolume does not exist under fd with which this is
+ * called
+ */
+ kfree(args);
+ return -EACCES;
+ }
+
+ ret = btrfs_search_path_in_tree_user(inode, args);
+
+ if (ret == 0 && copy_to_user(argp, args, sizeof(*args)))
+ ret = -EFAULT;
+
+ kfree(args);
+ return ret;
+}
+
+/* Get the subvolume information in BTRFS_ROOT_ITEM and BTRFS_ROOT_BACKREF */
+static int btrfs_ioctl_get_subvol_info(struct file *file, void __user *argp)
+{
+ struct btrfs_ioctl_get_subvol_info_args *subvol_info;
+ struct btrfs_fs_info *fs_info;
+ struct btrfs_root *root;
+ struct btrfs_path *path;
+ struct btrfs_key key;
+ struct btrfs_root_item *root_item;
+ struct btrfs_root_ref *rref;
+ struct extent_buffer *leaf;
+ unsigned long item_off;
+ unsigned long item_len;
+ struct inode *inode;
+ int slot;
+ int ret = 0;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ subvol_info = kzalloc(sizeof(*subvol_info), GFP_KERNEL);
+ if (!subvol_info) {
+ btrfs_free_path(path);
+ return -ENOMEM;
+ }
+
+ inode = file_inode(file);
+ fs_info = BTRFS_I(inode)->root->fs_info;
+
+ /* Get root_item of inode's subvolume */
+ key.objectid = BTRFS_I(inode)->root->root_key.objectid;
+ key.type = BTRFS_ROOT_ITEM_KEY;
+ key.offset = (u64)-1;
+ root = btrfs_read_fs_root_no_name(fs_info, &key);
+ if (IS_ERR(root)) {
+ ret = PTR_ERR(root);
+ goto out;
+ }
+ root_item = &root->root_item;
+
+ subvol_info->treeid = key.objectid;
+
+ subvol_info->generation = btrfs_root_generation(root_item);
+ subvol_info->flags = btrfs_root_flags(root_item);
+
+ memcpy(subvol_info->uuid, root_item->uuid, BTRFS_UUID_SIZE);
+ memcpy(subvol_info->parent_uuid, root_item->parent_uuid,
+ BTRFS_UUID_SIZE);
+ memcpy(subvol_info->received_uuid, root_item->received_uuid,
+ BTRFS_UUID_SIZE);
+
+ subvol_info->ctransid = btrfs_root_ctransid(root_item);
+ subvol_info->ctime.sec = btrfs_stack_timespec_sec(&root_item->ctime);
+ subvol_info->ctime.nsec = btrfs_stack_timespec_nsec(&root_item->ctime);
+
+ subvol_info->otransid = btrfs_root_otransid(root_item);
+ subvol_info->otime.sec = btrfs_stack_timespec_sec(&root_item->otime);
+ subvol_info->otime.nsec = btrfs_stack_timespec_nsec(&root_item->otime);
+
+ subvol_info->stransid = btrfs_root_stransid(root_item);
+ subvol_info->stime.sec = btrfs_stack_timespec_sec(&root_item->stime);
+ subvol_info->stime.nsec = btrfs_stack_timespec_nsec(&root_item->stime);
+
+ subvol_info->rtransid = btrfs_root_rtransid(root_item);
+ subvol_info->rtime.sec = btrfs_stack_timespec_sec(&root_item->rtime);
+ subvol_info->rtime.nsec = btrfs_stack_timespec_nsec(&root_item->rtime);
+
+ if (key.objectid != BTRFS_FS_TREE_OBJECTID) {
+ /* Search root tree for ROOT_BACKREF of this subvolume */
+ root = fs_info->tree_root;
+
+ key.type = BTRFS_ROOT_BACKREF_KEY;
+ key.offset = 0;
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0) {
+ goto out;
+ } else if (path->slots[0] >=
+ btrfs_header_nritems(path->nodes[0])) {
+ ret = btrfs_next_leaf(root, path);
+ if (ret < 0) {
+ goto out;
+ } else if (ret > 0) {
+ ret = -EUCLEAN;
+ goto out;
+ }
+ }
+
+ leaf = path->nodes[0];
+ slot = path->slots[0];
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+ if (key.objectid == subvol_info->treeid &&
+ key.type == BTRFS_ROOT_BACKREF_KEY) {
+ subvol_info->parent_id = key.offset;
+
+ rref = btrfs_item_ptr(leaf, slot, struct btrfs_root_ref);
+ subvol_info->dirid = btrfs_root_ref_dirid(leaf, rref);
+
+ item_off = btrfs_item_ptr_offset(leaf, slot)
+ + sizeof(struct btrfs_root_ref);
+ item_len = btrfs_item_size_nr(leaf, slot)
+ - sizeof(struct btrfs_root_ref);
+ read_extent_buffer(leaf, subvol_info->name,
+ item_off, item_len);
+ } else {
+ ret = -ENOENT;
+ goto out;
+ }
+ }
+
+ if (copy_to_user(argp, subvol_info, sizeof(*subvol_info)))
+ ret = -EFAULT;
+
+out:
+ btrfs_free_path(path);
+ kzfree(subvol_info);
+ return ret;
+}
+
+/*
+ * Return ROOT_REF information of the subvolume containing this inode
+ * except the subvolume name.
+ */
+static int btrfs_ioctl_get_subvol_rootref(struct file *file, void __user *argp)
+{
+ struct btrfs_ioctl_get_subvol_rootref_args *rootrefs;
+ struct btrfs_root_ref *rref;
+ struct btrfs_root *root;
+ struct btrfs_path *path;
+ struct btrfs_key key;
+ struct extent_buffer *leaf;
+ struct inode *inode;
+ u64 objectid;
+ int slot;
+ int ret;
+ u8 found;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ rootrefs = memdup_user(argp, sizeof(*rootrefs));
+ if (IS_ERR(rootrefs)) {
+ btrfs_free_path(path);
+ return PTR_ERR(rootrefs);
+ }
+
+ inode = file_inode(file);
+ root = BTRFS_I(inode)->root->fs_info->tree_root;
+ objectid = BTRFS_I(inode)->root->root_key.objectid;
+
+ key.objectid = objectid;
+ key.type = BTRFS_ROOT_REF_KEY;
+ key.offset = rootrefs->min_treeid;
+ found = 0;
+
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0) {
+ goto out;
+ } else if (path->slots[0] >=
+ btrfs_header_nritems(path->nodes[0])) {
+ ret = btrfs_next_leaf(root, path);
+ if (ret < 0) {
+ goto out;
+ } else if (ret > 0) {
+ ret = -EUCLEAN;
+ goto out;
+ }
+ }
+ while (1) {
+ leaf = path->nodes[0];
+ slot = path->slots[0];
+
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+ if (key.objectid != objectid || key.type != BTRFS_ROOT_REF_KEY) {
+ ret = 0;
+ goto out;
+ }
+
+ if (found == BTRFS_MAX_ROOTREF_BUFFER_NUM) {
+ ret = -EOVERFLOW;
+ goto out;
+ }
+
+ rref = btrfs_item_ptr(leaf, slot, struct btrfs_root_ref);
+ rootrefs->rootref[found].treeid = key.offset;
+ rootrefs->rootref[found].dirid =
+ btrfs_root_ref_dirid(leaf, rref);
+ found++;
+
+ ret = btrfs_next_item(root, path);
+ if (ret < 0) {
+ goto out;
+ } else if (ret > 0) {
+ ret = -EUCLEAN;
+ goto out;
+ }
+ }
+
+out:
+ if (!ret || ret == -EOVERFLOW) {
+ rootrefs->num_items = found;
+ /* update min_treeid for next search */
+ if (found)
+ rootrefs->min_treeid =
+ rootrefs->rootref[found - 1].treeid + 1;
+ if (copy_to_user(argp, rootrefs, sizeof(*rootrefs)))
+ ret = -EFAULT;
+ }
+
+ kfree(rootrefs);
+ btrfs_free_path(path);
+
+ return ret;
+}
+
static noinline int btrfs_ioctl_snap_destroy(struct file *file,
void __user *arg)
{
@@ -2309,12 +2812,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
struct btrfs_root *root = BTRFS_I(dir)->root;
struct btrfs_root *dest = NULL;
struct btrfs_ioctl_vol_args *vol_args;
- struct btrfs_trans_handle *trans;
- struct btrfs_block_rsv block_rsv;
- u64 root_flags;
- u64 qgroup_reserved;
int namelen;
- int ret;
int err = 0;
if (!S_ISDIR(dir->i_mode))
@@ -2398,133 +2896,11 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
}
inode_lock(inode);
-
- /*
- * Don't allow to delete a subvolume with send in progress. This is
- * inside the i_mutex so the error handling that has to drop the bit
- * again is not run concurrently.
- */
- spin_lock(&dest->root_item_lock);
- root_flags = btrfs_root_flags(&dest->root_item);
- if (dest->send_in_progress == 0) {
- btrfs_set_root_flags(&dest->root_item,
- root_flags | BTRFS_ROOT_SUBVOL_DEAD);
- spin_unlock(&dest->root_item_lock);
- } else {
- spin_unlock(&dest->root_item_lock);
- btrfs_warn(fs_info,
- "Attempt to delete subvolume %llu during send",
- dest->root_key.objectid);
- err = -EPERM;
- goto out_unlock_inode;
- }
-
- down_write(&fs_info->subvol_sem);
-
- err = may_destroy_subvol(dest);
- if (err)
- goto out_up_write;
-
- btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
- /*
- * One for dir inode, two for dir entries, two for root
- * ref/backref.
- */
- err = btrfs_subvolume_reserve_metadata(root, &block_rsv,
- 5, &qgroup_reserved, true);
- if (err)
- goto out_up_write;
-
- trans = btrfs_start_transaction(root, 0);
- if (IS_ERR(trans)) {
- err = PTR_ERR(trans);
- goto out_release;
- }
- trans->block_rsv = &block_rsv;
- trans->bytes_reserved = block_rsv.size;
-
- btrfs_record_snapshot_destroy(trans, BTRFS_I(dir));
-
- ret = btrfs_unlink_subvol(trans, root, dir,
- dest->root_key.objectid,
- dentry->d_name.name,
- dentry->d_name.len);
- if (ret) {
- err = ret;
- btrfs_abort_transaction(trans, ret);
- goto out_end_trans;
- }
-
- btrfs_record_root_in_trans(trans, dest);
-
- memset(&dest->root_item.drop_progress, 0,
- sizeof(dest->root_item.drop_progress));
- dest->root_item.drop_level = 0;
- btrfs_set_root_refs(&dest->root_item, 0);
-
- if (!test_and_set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &dest->state)) {
- ret = btrfs_insert_orphan_item(trans,
- fs_info->tree_root,
- dest->root_key.objectid);
- if (ret) {
- btrfs_abort_transaction(trans, ret);
- err = ret;
- goto out_end_trans;
- }
- }
-
- ret = btrfs_uuid_tree_rem(trans, fs_info, dest->root_item.uuid,
- BTRFS_UUID_KEY_SUBVOL,
- dest->root_key.objectid);
- if (ret && ret != -ENOENT) {
- btrfs_abort_transaction(trans, ret);
- err = ret;
- goto out_end_trans;
- }
- if (!btrfs_is_empty_uuid(dest->root_item.received_uuid)) {
- ret = btrfs_uuid_tree_rem(trans, fs_info,
- dest->root_item.received_uuid,
- BTRFS_UUID_KEY_RECEIVED_SUBVOL,
- dest->root_key.objectid);
- if (ret && ret != -ENOENT) {
- btrfs_abort_transaction(trans, ret);
- err = ret;
- goto out_end_trans;
- }
- }
-
-out_end_trans:
- trans->block_rsv = NULL;
- trans->bytes_reserved = 0;
- ret = btrfs_end_transaction(trans);
- if (ret && !err)
- err = ret;
- inode->i_flags |= S_DEAD;
-out_release:
- btrfs_subvolume_release_metadata(fs_info, &block_rsv);
-out_up_write:
- up_write(&fs_info->subvol_sem);
- if (err) {
- spin_lock(&dest->root_item_lock);
- root_flags = btrfs_root_flags(&dest->root_item);
- btrfs_set_root_flags(&dest->root_item,
- root_flags & ~BTRFS_ROOT_SUBVOL_DEAD);
- spin_unlock(&dest->root_item_lock);
- }
-out_unlock_inode:
+ err = btrfs_delete_subvolume(dir, dentry);
inode_unlock(inode);
- if (!err) {
- d_invalidate(dentry);
- btrfs_invalidate_inodes(dest);
+ if (!err)
d_delete(dentry);
- ASSERT(dest->send_in_progress == 0);
- /* the last ref */
- if (dest->ino_cache_inode) {
- iput(dest->ino_cache_inode);
- dest->ino_cache_inode = NULL;
- }
- }
out_dput:
dput(dentry);
out_unlock_dir:
@@ -2613,7 +2989,6 @@ static long btrfs_ioctl_add_dev(struct btrfs_fs_info *fs_info, void __user *arg)
if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags))
return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
- mutex_lock(&fs_info->volume_mutex);
vol_args = memdup_user(arg, sizeof(*vol_args));
if (IS_ERR(vol_args)) {
ret = PTR_ERR(vol_args);
@@ -2628,7 +3003,6 @@ static long btrfs_ioctl_add_dev(struct btrfs_fs_info *fs_info, void __user *arg)
kfree(vol_args);
out:
- mutex_unlock(&fs_info->volume_mutex);
clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
return ret;
}
@@ -2654,8 +3028,10 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
}
/* Check for compatibility reject unknown flags */
- if (vol_args->flags & ~BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED)
- return -EOPNOTSUPP;
+ if (vol_args->flags & ~BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED) {
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
@@ -2954,8 +3330,6 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp)
put_page(pg);
}
}
- kfree(cmp->src_pages);
- kfree(cmp->dst_pages);
}
static int btrfs_cmp_data_prepare(struct inode *src, u64 loff,
@@ -2964,40 +3338,14 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff,
{
int ret;
int num_pages = PAGE_ALIGN(len) >> PAGE_SHIFT;
- struct page **src_pgarr, **dst_pgarr;
- /*
- * We must gather up all the pages before we initiate our
- * extent locking. We use an array for the page pointers. Size
- * of the array is bounded by len, which is in turn bounded by
- * BTRFS_MAX_DEDUPE_LEN.
- */
- src_pgarr = kcalloc(num_pages, sizeof(struct page *), GFP_KERNEL);
- dst_pgarr = kcalloc(num_pages, sizeof(struct page *), GFP_KERNEL);
- if (!src_pgarr || !dst_pgarr) {
- kfree(src_pgarr);
- kfree(dst_pgarr);
- return -ENOMEM;
- }
cmp->num_pages = num_pages;
- cmp->src_pages = src_pgarr;
- cmp->dst_pages = dst_pgarr;
- /*
- * If deduping ranges in the same inode, locking rules make it mandatory
- * to always lock pages in ascending order to avoid deadlocks with
- * concurrent tasks (such as starting writeback/delalloc).
- */
- if (src == dst && dst_loff < loff) {
- swap(src_pgarr, dst_pgarr);
- swap(loff, dst_loff);
- }
-
- ret = gather_extent_pages(src, src_pgarr, cmp->num_pages, loff);
+ ret = gather_extent_pages(src, cmp->src_pages, num_pages, loff);
if (ret)
goto out;
- ret = gather_extent_pages(dst, dst_pgarr, cmp->num_pages, dst_loff);
+ ret = gather_extent_pages(dst, cmp->dst_pages, num_pages, dst_loff);
out:
if (ret)
@@ -3067,31 +3415,23 @@ static int extent_same_check_offsets(struct inode *inode, u64 off, u64 *plen,
return 0;
}
-static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
- struct inode *dst, u64 dst_loff)
+static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen,
+ struct inode *dst, u64 dst_loff,
+ struct cmp_pages *cmp)
{
int ret;
u64 len = olen;
- struct cmp_pages cmp;
bool same_inode = (src == dst);
u64 same_lock_start = 0;
u64 same_lock_len = 0;
- if (len == 0)
- return 0;
-
- if (same_inode)
- inode_lock(src);
- else
- btrfs_double_inode_lock(src, dst);
-
ret = extent_same_check_offsets(src, loff, &len, olen);
if (ret)
- goto out_unlock;
+ return ret;
ret = extent_same_check_offsets(dst, dst_loff, &len, olen);
if (ret)
- goto out_unlock;
+ return ret;
if (same_inode) {
/*
@@ -3108,32 +3448,21 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
* allow an unaligned length so long as it ends at
* i_size.
*/
- if (len != olen) {
- ret = -EINVAL;
- goto out_unlock;
- }
+ if (len != olen)
+ return -EINVAL;
/* Check for overlapping ranges */
- if (dst_loff + len > loff && dst_loff < loff + len) {
- ret = -EINVAL;
- goto out_unlock;
- }
+ if (dst_loff + len > loff && dst_loff < loff + len)
+ return -EINVAL;
same_lock_start = min_t(u64, loff, dst_loff);
same_lock_len = max_t(u64, loff, dst_loff) + len - same_lock_start;
}
- /* don't make the dst file partly checksummed */
- if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
- (BTRFS_I(dst)->flags & BTRFS_INODE_NODATASUM)) {
- ret = -EINVAL;
- goto out_unlock;
- }
-
again:
- ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp);
+ ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, cmp);
if (ret)
- goto out_unlock;
+ return ret;
if (same_inode)
ret = lock_extent_range(src, same_lock_start, same_lock_len,
@@ -3154,7 +3483,7 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
* Ranges in the io trees already unlocked. Now unlock all
* pages before waiting for all IO to complete.
*/
- btrfs_cmp_data_free(&cmp);
+ btrfs_cmp_data_free(cmp);
if (same_inode) {
btrfs_wait_ordered_range(src, same_lock_start,
same_lock_len);
@@ -3167,12 +3496,12 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
ASSERT(ret == 0);
if (WARN_ON(ret)) {
/* ranges in the io trees already unlocked */
- btrfs_cmp_data_free(&cmp);
+ btrfs_cmp_data_free(cmp);
return ret;
}
/* pass original length for comparison so we stay within i_size */
- ret = btrfs_cmp_data(olen, &cmp);
+ ret = btrfs_cmp_data(olen, cmp);
if (ret == 0)
ret = btrfs_clone(src, dst, loff, olen, len, dst_loff, 1);
@@ -3182,18 +3511,91 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
else
btrfs_double_extent_unlock(src, loff, dst, dst_loff, len);
- btrfs_cmp_data_free(&cmp);
+ btrfs_cmp_data_free(cmp);
+
+ return ret;
+}
+
+#define BTRFS_MAX_DEDUPE_LEN SZ_16M
+
+static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
+ struct inode *dst, u64 dst_loff)
+{
+ int ret;
+ struct cmp_pages cmp;
+ int num_pages = PAGE_ALIGN(BTRFS_MAX_DEDUPE_LEN) >> PAGE_SHIFT;
+ bool same_inode = (src == dst);
+ u64 i, tail_len, chunk_count;
+
+ if (olen == 0)
+ return 0;
+
+ if (same_inode)
+ inode_lock(src);
+ else
+ btrfs_double_inode_lock(src, dst);
+
+ /* don't make the dst file partly checksummed */
+ if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
+ (BTRFS_I(dst)->flags & BTRFS_INODE_NODATASUM)) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
+ tail_len = olen % BTRFS_MAX_DEDUPE_LEN;
+ chunk_count = div_u64(olen, BTRFS_MAX_DEDUPE_LEN);
+ if (chunk_count == 0)
+ num_pages = PAGE_ALIGN(tail_len) >> PAGE_SHIFT;
+
+ /*
+ * If deduping ranges in the same inode, locking rules make it
+ * mandatory to always lock pages in ascending order to avoid deadlocks
+ * with concurrent tasks (such as starting writeback/delalloc).
+ */
+ if (same_inode && dst_loff < loff)
+ swap(loff, dst_loff);
+
+ /*
+ * We must gather up all the pages before we initiate our extent
+ * locking. We use an array for the page pointers. Size of the array is
+ * bounded by len, which is in turn bounded by BTRFS_MAX_DEDUPE_LEN.
+ */
+ cmp.src_pages = kvmalloc_array(num_pages, sizeof(struct page *),
+ GFP_KERNEL | __GFP_ZERO);
+ cmp.dst_pages = kvmalloc_array(num_pages, sizeof(struct page *),
+ GFP_KERNEL | __GFP_ZERO);
+ if (!cmp.src_pages || !cmp.dst_pages) {
+ ret = -ENOMEM;
+ goto out_free;
+ }
+
+ for (i = 0; i < chunk_count; i++) {
+ ret = btrfs_extent_same_range(src, loff, BTRFS_MAX_DEDUPE_LEN,
+ dst, dst_loff, &cmp);
+ if (ret)
+ goto out_unlock;
+
+ loff += BTRFS_MAX_DEDUPE_LEN;
+ dst_loff += BTRFS_MAX_DEDUPE_LEN;
+ }
+
+ if (tail_len > 0)
+ ret = btrfs_extent_same_range(src, loff, tail_len, dst,
+ dst_loff, &cmp);
+
out_unlock:
if (same_inode)
inode_unlock(src);
else
btrfs_double_inode_unlock(src, dst);
+out_free:
+ kvfree(cmp.src_pages);
+ kvfree(cmp.dst_pages);
+
return ret;
}
-#define BTRFS_MAX_DEDUPE_LEN SZ_16M
-
ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
struct file *dst_file, u64 dst_loff)
{
@@ -3202,9 +3604,6 @@ ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
ssize_t res;
- if (olen > BTRFS_MAX_DEDUPE_LEN)
- olen = BTRFS_MAX_DEDUPE_LEN;
-
if (WARN_ON_ONCE(bs < PAGE_SIZE)) {
/*
* Btrfs does not support blocksize < page_size. As a
@@ -3826,11 +4225,6 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
src->i_sb != inode->i_sb)
return -EXDEV;
- /* don't make the dst file partly checksummed */
- if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
- (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
- return -EINVAL;
-
if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode))
return -EISDIR;
@@ -3840,6 +4234,13 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
inode_lock(src);
}
+ /* don't make the dst file partly checksummed */
+ if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
+ (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
/* determine range to clone */
ret = -EINVAL;
if (off + len > src->i_size || off + len < off)
@@ -4007,8 +4408,8 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp)
return ret;
}
-void btrfs_get_block_group_info(struct list_head *groups_list,
- struct btrfs_ioctl_space_info *space)
+static void get_block_group_info(struct list_head *groups_list,
+ struct btrfs_ioctl_space_info *space)
{
struct btrfs_block_group_cache *block_group;
@@ -4124,8 +4525,8 @@ static long btrfs_ioctl_space_info(struct btrfs_fs_info *fs_info,
down_read(&info->groups_sem);
for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) {
if (!list_empty(&info->block_groups[c])) {
- btrfs_get_block_group_info(
- &info->block_groups[c], &space);
+ get_block_group_info(&info->block_groups[c],
+ &space);
memcpy(dest, &space, sizeof(space));
dest++;
space_args.total_spaces++;
@@ -4490,14 +4891,14 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info,
return ret;
}
-void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
+void btrfs_update_ioctl_balance_args(struct btrfs_fs_info *fs_info,
struct btrfs_ioctl_balance_args *bargs)
{
struct btrfs_balance_control *bctl = fs_info->balance_ctl;
bargs->flags = bctl->flags;
- if (atomic_read(&fs_info->balance_running))
+ if (test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags))
bargs->state |= BTRFS_BALANCE_STATE_RUNNING;
if (atomic_read(&fs_info->balance_pause_req))
bargs->state |= BTRFS_BALANCE_STATE_PAUSE_REQ;
@@ -4508,13 +4909,9 @@ void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
memcpy(&bargs->meta, &bctl->meta, sizeof(bargs->meta));
memcpy(&bargs->sys, &bctl->sys, sizeof(bargs->sys));
- if (lock) {
- spin_lock(&fs_info->balance_lock);
- memcpy(&bargs->stat, &bctl->stat, sizeof(bargs->stat));
- spin_unlock(&fs_info->balance_lock);
- } else {
- memcpy(&bargs->stat, &bctl->stat, sizeof(bargs->stat));
- }
+ spin_lock(&fs_info->balance_lock);
+ memcpy(&bargs->stat, &bctl->stat, sizeof(bargs->stat));
+ spin_unlock(&fs_info->balance_lock);
}
static long btrfs_ioctl_balance(struct file *file, void __user *arg)
@@ -4535,7 +4932,6 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
again:
if (!test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
- mutex_lock(&fs_info->volume_mutex);
mutex_lock(&fs_info->balance_mutex);
need_unlock = true;
goto locked;
@@ -4550,21 +4946,22 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
mutex_lock(&fs_info->balance_mutex);
if (fs_info->balance_ctl) {
/* this is either (2) or (3) */
- if (!atomic_read(&fs_info->balance_running)) {
+ if (!test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)) {
mutex_unlock(&fs_info->balance_mutex);
- if (!mutex_trylock(&fs_info->volume_mutex))
- goto again;
+ /*
+ * Lock released to allow other waiters to continue,
+ * we'll reexamine the status again.
+ */
mutex_lock(&fs_info->balance_mutex);
if (fs_info->balance_ctl &&
- !atomic_read(&fs_info->balance_running)) {
+ !test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)) {
/* this is (3) */
need_unlock = false;
goto locked;
}
mutex_unlock(&fs_info->balance_mutex);
- mutex_unlock(&fs_info->volume_mutex);
goto again;
} else {
/* this is (2) */
@@ -4617,7 +5014,6 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
goto out_bargs;
}
- bctl->fs_info = fs_info;
if (arg) {
memcpy(&bctl->data, &bargs->data, sizeof(bctl->data));
memcpy(&bctl->meta, &bargs->meta, sizeof(bctl->meta));
@@ -4636,14 +5032,14 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
do_balance:
/*
- * Ownership of bctl and filesystem flag BTRFS_FS_EXCL_OP
- * goes to to btrfs_balance. bctl is freed in __cancel_balance,
- * or, if restriper was paused all the way until unmount, in
- * free_fs_info. The flag is cleared in __cancel_balance.
+ * Ownership of bctl and filesystem flag BTRFS_FS_EXCL_OP goes to
+ * btrfs_balance. bctl is freed in reset_balance_state, or, if
+ * restriper was paused all the way until unmount, in free_fs_info.
+ * The flag should be cleared after reset_balance_state.
*/
need_unlock = false;
- ret = btrfs_balance(bctl, bargs);
+ ret = btrfs_balance(fs_info, bctl, bargs);
bctl = NULL;
if (arg) {
@@ -4657,7 +5053,6 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
kfree(bargs);
out_unlock:
mutex_unlock(&fs_info->balance_mutex);
- mutex_unlock(&fs_info->volume_mutex);
if (need_unlock)
clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
out:
@@ -4701,7 +5096,7 @@ static long btrfs_ioctl_balance_progress(struct btrfs_fs_info *fs_info,
goto out;
}
- update_ioctl_balance_args(fs_info, 1, bargs);
+ btrfs_update_ioctl_balance_args(fs_info, bargs);
if (copy_to_user(arg, bargs, sizeof(*bargs)))
ret = -EFAULT;
@@ -5038,8 +5433,7 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
BTRFS_UUID_SIZE);
if (received_uuid_changed &&
!btrfs_is_empty_uuid(root_item->received_uuid)) {
- ret = btrfs_uuid_tree_rem(trans, fs_info,
- root_item->received_uuid,
+ ret = btrfs_uuid_tree_remove(trans, root_item->received_uuid,
BTRFS_UUID_KEY_RECEIVED_SUBVOL,
root->root_key.objectid);
if (ret && ret != -ENOENT) {
@@ -5063,7 +5457,7 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
goto out;
}
if (received_uuid_changed && !btrfs_is_empty_uuid(sa->uuid)) {
- ret = btrfs_uuid_tree_add(trans, fs_info, sa->uuid,
+ ret = btrfs_uuid_tree_add(trans, sa->uuid,
BTRFS_UUID_KEY_RECEIVED_SUBVOL,
root->root_key.objectid);
if (ret < 0 && ret != -EEXIST) {
@@ -5497,7 +5891,7 @@ long btrfs_ioctl(struct file *file, unsigned int
case BTRFS_IOC_SYNC: {
int ret;
- ret = btrfs_start_delalloc_roots(fs_info, 0, -1);
+ ret = btrfs_start_delalloc_roots(fs_info, -1);
if (ret)
return ret;
ret = btrfs_sync_fs(inode->i_sb, 1);
@@ -5565,6 +5959,16 @@ long btrfs_ioctl(struct file *file, unsigned int
return btrfs_ioctl_get_features(file, argp);
case BTRFS_IOC_SET_FEATURES:
return btrfs_ioctl_set_features(file, argp);
+ case FS_IOC_FSGETXATTR:
+ return btrfs_ioctl_fsgetxattr(file, argp);
+ case FS_IOC_FSSETXATTR:
+ return btrfs_ioctl_fssetxattr(file, argp);
+ case BTRFS_IOC_GET_SUBVOL_INFO:
+ return btrfs_ioctl_get_subvol_info(file, argp);
+ case BTRFS_IOC_GET_SUBVOL_ROOTREF:
+ return btrfs_ioctl_get_subvol_rootref(file, argp);
+ case BTRFS_IOC_INO_LOOKUP_USER:
+ return btrfs_ioctl_ino_lookup_user(file, argp);
}
return -ENOTTY;
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index e4faefa..1da768e 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -66,22 +66,16 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw)
write_lock(&eb->lock);
WARN_ON(atomic_read(&eb->spinning_writers));
atomic_inc(&eb->spinning_writers);
- /*
- * atomic_dec_and_test implies a barrier for waitqueue_active
- */
- if (atomic_dec_and_test(&eb->blocking_writers) &&
- waitqueue_active(&eb->write_lock_wq))
- wake_up(&eb->write_lock_wq);
+ /* atomic_dec_and_test implies a barrier */
+ if (atomic_dec_and_test(&eb->blocking_writers))
+ cond_wake_up_nomb(&eb->write_lock_wq);
} else if (rw == BTRFS_READ_LOCK_BLOCKING) {
BUG_ON(atomic_read(&eb->blocking_readers) == 0);
read_lock(&eb->lock);
atomic_inc(&eb->spinning_readers);
- /*
- * atomic_dec_and_test implies a barrier for waitqueue_active
- */
- if (atomic_dec_and_test(&eb->blocking_readers) &&
- waitqueue_active(&eb->read_lock_wq))
- wake_up(&eb->read_lock_wq);
+ /* atomic_dec_and_test implies a barrier */
+ if (atomic_dec_and_test(&eb->blocking_readers))
+ cond_wake_up_nomb(&eb->read_lock_wq);
}
}
@@ -221,12 +215,9 @@ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
}
btrfs_assert_tree_read_locked(eb);
WARN_ON(atomic_read(&eb->blocking_readers) == 0);
- /*
- * atomic_dec_and_test implies a barrier for waitqueue_active
- */
- if (atomic_dec_and_test(&eb->blocking_readers) &&
- waitqueue_active(&eb->read_lock_wq))
- wake_up(&eb->read_lock_wq);
+ /* atomic_dec_and_test implies a barrier */
+ if (atomic_dec_and_test(&eb->blocking_readers))
+ cond_wake_up_nomb(&eb->read_lock_wq);
atomic_dec(&eb->read_locks);
}
@@ -275,12 +266,9 @@ void btrfs_tree_unlock(struct extent_buffer *eb)
if (blockers) {
WARN_ON(atomic_read(&eb->spinning_writers));
atomic_dec(&eb->blocking_writers);
- /*
- * Make sure counter is updated before we wake up waiters.
- */
+ /* Use the lighter barrier after atomic */
smp_mb__after_atomic();
- if (waitqueue_active(&eb->write_lock_wq))
- wake_up(&eb->write_lock_wq);
+ cond_wake_up_nomb(&eb->write_lock_wq);
} else {
WARN_ON(atomic_read(&eb->spinning_writers) != 1);
atomic_dec(&eb->spinning_writers);
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 0667ea0..b6a4cc1 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -17,6 +17,43 @@
#define LZO_LEN 4
+/*
+ * Btrfs LZO compression format
+ *
+ * Regular and inlined LZO compressed data extents consist of:
+ *
+ * 1. Header
+ * Fixed size. LZO_LEN (4) bytes long, LE32.
+ * Records the total size (including the header) of compressed data.
+ *
+ * 2. Segment(s)
+ * Variable size. Each segment includes one segment header, followd by data
+ * payload.
+ * One regular LZO compressed extent can have one or more segments.
+ * For inlined LZO compressed extent, only one segment is allowed.
+ * One segment represents at most one page of uncompressed data.
+ *
+ * 2.1 Segment header
+ * Fixed size. LZO_LEN (4) bytes long, LE32.
+ * Records the total size of the segment (not including the header).
+ * Segment header never crosses page boundary, thus it's possible to
+ * have at most 3 padding zeros at the end of the page.
+ *
+ * 2.2 Data Payload
+ * Variable size. Size up limit should be lzo1x_worst_compress(PAGE_SIZE)
+ * which is 4419 for a 4KiB page.
+ *
+ * Example:
+ * Page 1:
+ * 0 0x2 0x4 0x6 0x8 0xa 0xc 0xe 0x10
+ * 0x0000 | Header | SegHdr 01 | Data payload 01 ... |
+ * ...
+ * 0x0ff0 | SegHdr N | Data payload N ... |00|
+ * ^^ padding zeros
+ * Page 2:
+ * 0x1000 | SegHdr N+1| Data payload N+1 ... |
+ */
+
struct workspace {
void *mem;
void *buf; /* where decompressed data goes */
@@ -258,6 +295,7 @@ static int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
unsigned long working_bytes;
size_t in_len;
size_t out_len;
+ const size_t max_segment_len = lzo1x_worst_compress(PAGE_SIZE);
unsigned long in_offset;
unsigned long in_page_bytes_left;
unsigned long tot_in;
@@ -271,10 +309,22 @@ static int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
data_in = kmap(pages_in[0]);
tot_len = read_compress_length(data_in);
+ /*
+ * Compressed data header check.
+ *
+ * The real compressed size can't exceed the maximum extent length, and
+ * all pages should be used (whole unused page with just the segment
+ * header is not possible). If this happens it means the compressed
+ * extent is corrupted.
+ */
+ if (tot_len > min_t(size_t, BTRFS_MAX_COMPRESSED, srclen) ||
+ tot_len < srclen - PAGE_SIZE) {
+ ret = -EUCLEAN;
+ goto done;
+ }
tot_in = LZO_LEN;
in_offset = LZO_LEN;
- tot_len = min_t(size_t, srclen, tot_len);
in_page_bytes_left = PAGE_SIZE - LZO_LEN;
tot_out = 0;
@@ -285,6 +335,17 @@ static int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
in_offset += LZO_LEN;
tot_in += LZO_LEN;
+ /*
+ * Segment header check.
+ *
+ * The segment length must not exceed the maximum LZO
+ * compression size, nor the total compressed size.
+ */
+ if (in_len > max_segment_len || tot_in + in_len > tot_len) {
+ ret = -EUCLEAN;
+ goto done;
+ }
+
tot_in += in_len;
working_bytes = in_len;
may_late_unmap = need_unmap = false;
@@ -335,7 +396,7 @@ static int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
}
}
- out_len = lzo1x_worst_compress(PAGE_SIZE);
+ out_len = max_segment_len;
ret = lzo1x_decompress_safe(buf, in_len, workspace->buf,
&out_len);
if (need_unmap)
@@ -369,15 +430,24 @@ static int lzo_decompress(struct list_head *ws, unsigned char *data_in,
struct workspace *workspace = list_entry(ws, struct workspace, list);
size_t in_len;
size_t out_len;
+ size_t max_segment_len = lzo1x_worst_compress(PAGE_SIZE);
int ret = 0;
char *kaddr;
unsigned long bytes;
- BUG_ON(srclen < LZO_LEN);
+ if (srclen < LZO_LEN || srclen > max_segment_len + LZO_LEN * 2)
+ return -EUCLEAN;
+ in_len = read_compress_length(data_in);
+ if (in_len != srclen)
+ return -EUCLEAN;
data_in += LZO_LEN;
in_len = read_compress_length(data_in);
+ if (in_len != srclen - LZO_LEN * 2) {
+ ret = -EUCLEAN;
+ goto out;
+ }
data_in += LZO_LEN;
out_len = PAGE_SIZE;
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 6db8bb2..2e1a169 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -343,11 +343,8 @@ int btrfs_dec_test_first_ordered_pending(struct inode *inode,
if (entry->bytes_left == 0) {
ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags);
- /*
- * Implicit memory barrier after test_and_set_bit
- */
- if (waitqueue_active(&entry->wait))
- wake_up(&entry->wait);
+ /* test_and_set_bit implies a barrier */
+ cond_wake_up_nomb(&entry->wait);
} else {
ret = 1;
}
@@ -410,11 +407,8 @@ int btrfs_dec_test_ordered_pending(struct inode *inode,
if (entry->bytes_left == 0) {
ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags);
- /*
- * Implicit memory barrier after test_and_set_bit
- */
- if (waitqueue_active(&entry->wait))
- wake_up(&entry->wait);
+ /* test_and_set_bit implies a barrier */
+ cond_wake_up_nomb(&entry->wait);
} else {
ret = 1;
}
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 124276b..a4e11cf 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -166,6 +166,25 @@ static void print_uuid_item(struct extent_buffer *l, unsigned long offset,
}
}
+/*
+ * Helper to output refs and locking status of extent buffer. Useful to debug
+ * race condition related problems.
+ */
+static void print_eb_refs_lock(struct extent_buffer *eb)
+{
+#ifdef CONFIG_BTRFS_DEBUG
+ btrfs_info(eb->fs_info,
+"refs %u lock (w:%d r:%d bw:%d br:%d sw:%d sr:%d) lock_owner %u current %u",
+ atomic_read(&eb->refs), atomic_read(&eb->write_locks),
+ atomic_read(&eb->read_locks),
+ atomic_read(&eb->blocking_writers),
+ atomic_read(&eb->blocking_readers),
+ atomic_read(&eb->spinning_writers),
+ atomic_read(&eb->spinning_readers),
+ eb->lock_owner, current->pid);
+#endif
+}
+
void btrfs_print_leaf(struct extent_buffer *l)
{
struct btrfs_fs_info *fs_info;
@@ -189,9 +208,11 @@ void btrfs_print_leaf(struct extent_buffer *l)
fs_info = l->fs_info;
nr = btrfs_header_nritems(l);
- btrfs_info(fs_info, "leaf %llu total ptrs %d free space %d",
- btrfs_header_bytenr(l), nr,
- btrfs_leaf_free_space(fs_info, l));
+ btrfs_info(fs_info,
+ "leaf %llu gen %llu total ptrs %d free space %d owner %llu",
+ btrfs_header_bytenr(l), btrfs_header_generation(l), nr,
+ btrfs_leaf_free_space(fs_info, l), btrfs_header_owner(l));
+ print_eb_refs_lock(l);
for (i = 0 ; i < nr ; i++) {
item = btrfs_item_nr(i);
btrfs_item_key_to_cpu(l, &key, i);
@@ -325,7 +346,7 @@ void btrfs_print_leaf(struct extent_buffer *l)
}
}
-void btrfs_print_tree(struct extent_buffer *c)
+void btrfs_print_tree(struct extent_buffer *c, bool follow)
{
struct btrfs_fs_info *fs_info;
int i; u32 nr;
@@ -342,15 +363,20 @@ void btrfs_print_tree(struct extent_buffer *c)
return;
}
btrfs_info(fs_info,
- "node %llu level %d total ptrs %d free spc %u",
- btrfs_header_bytenr(c), level, nr,
- (u32)BTRFS_NODEPTRS_PER_BLOCK(fs_info) - nr);
+ "node %llu level %d gen %llu total ptrs %d free spc %u owner %llu",
+ btrfs_header_bytenr(c), level, btrfs_header_generation(c),
+ nr, (u32)BTRFS_NODEPTRS_PER_BLOCK(fs_info) - nr,
+ btrfs_header_owner(c));
+ print_eb_refs_lock(c);
for (i = 0; i < nr; i++) {
btrfs_node_key_to_cpu(c, &key, i);
- pr_info("\tkey %d (%llu %u %llu) block %llu\n",
+ pr_info("\tkey %d (%llu %u %llu) block %llu gen %llu\n",
i, key.objectid, key.type, key.offset,
- btrfs_node_blockptr(c, i));
+ btrfs_node_blockptr(c, i),
+ btrfs_node_ptr_generation(c, i));
}
+ if (!follow)
+ return;
for (i = 0; i < nr; i++) {
struct btrfs_key first_key;
struct extent_buffer *next;
@@ -372,7 +398,7 @@ void btrfs_print_tree(struct extent_buffer *c)
if (btrfs_header_level(next) !=
level - 1)
BUG();
- btrfs_print_tree(next);
+ btrfs_print_tree(next, follow);
free_extent_buffer(next);
}
}
diff --git a/fs/btrfs/print-tree.h b/fs/btrfs/print-tree.h
index 4a98481..e6bb38f 100644
--- a/fs/btrfs/print-tree.h
+++ b/fs/btrfs/print-tree.h
@@ -7,6 +7,6 @@
#define BTRFS_PRINT_TREE_H
void btrfs_print_leaf(struct extent_buffer *l);
-void btrfs_print_tree(struct extent_buffer *c);
+void btrfs_print_tree(struct extent_buffer *c, bool follow);
#endif
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index 53a8c95..dc61400 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -380,6 +380,7 @@ static int prop_compression_apply(struct inode *inode,
const char *value,
size_t len)
{
+ struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
int type;
if (len == 0) {
@@ -390,14 +391,17 @@ static int prop_compression_apply(struct inode *inode,
return 0;
}
- if (!strncmp("lzo", value, 3))
+ if (!strncmp("lzo", value, 3)) {
type = BTRFS_COMPRESS_LZO;
- else if (!strncmp("zlib", value, 4))
+ btrfs_set_fs_incompat(fs_info, COMPRESS_LZO);
+ } else if (!strncmp("zlib", value, 4)) {
type = BTRFS_COMPRESS_ZLIB;
- else if (!strncmp("zstd", value, len))
+ } else if (!strncmp("zstd", value, len)) {
type = BTRFS_COMPRESS_ZSTD;
- else
+ btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD);
+ } else {
return -EINVAL;
+ }
BTRFS_I(inode)->flags &= ~BTRFS_INODE_NOCOMPRESS;
BTRFS_I(inode)->flags |= BTRFS_INODE_COMPRESS;
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 09c7e4f..1874a6d 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -11,6 +11,7 @@
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/btrfs.h>
+#include <linux/sizes.h>
#include "ctree.h"
#include "transaction.h"
@@ -1881,8 +1882,8 @@ static int qgroup_update_counters(struct btrfs_fs_info *fs_info,
cur_old_count = btrfs_qgroup_get_old_refcnt(qg, seq);
cur_new_count = btrfs_qgroup_get_new_refcnt(qg, seq);
- trace_qgroup_update_counters(fs_info, qg->qgroupid,
- cur_old_count, cur_new_count);
+ trace_qgroup_update_counters(fs_info, qg, cur_old_count,
+ cur_new_count);
/* Rfer update part */
if (cur_old_count == 0 && cur_new_count > 0) {
@@ -2013,8 +2014,8 @@ btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans,
BUG_ON(!fs_info->quota_root);
- trace_btrfs_qgroup_account_extent(fs_info, bytenr, num_bytes,
- nr_old_roots, nr_new_roots);
+ trace_btrfs_qgroup_account_extent(fs_info, trans->transid, bytenr,
+ num_bytes, nr_old_roots, nr_new_roots);
qgroups = ulist_alloc(GFP_NOFS);
if (!qgroups) {
@@ -2375,8 +2376,21 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
return ret;
}
-static bool qgroup_check_limits(const struct btrfs_qgroup *qg, u64 num_bytes)
+/*
+ * Two limits to commit transaction in advance.
+ *
+ * For RATIO, it will be 1/RATIO of the remaining limit
+ * (excluding data and prealloc meta) as threshold.
+ * For SIZE, it will be in byte unit as threshold.
+ */
+#define QGROUP_PERTRANS_RATIO 32
+#define QGROUP_PERTRANS_SIZE SZ_32M
+static bool qgroup_check_limits(struct btrfs_fs_info *fs_info,
+ const struct btrfs_qgroup *qg, u64 num_bytes)
{
+ u64 limit;
+ u64 threshold;
+
if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_RFER) &&
qgroup_rsv_total(qg) + (s64)qg->rfer + num_bytes > qg->max_rfer)
return false;
@@ -2385,6 +2399,31 @@ static bool qgroup_check_limits(const struct btrfs_qgroup *qg, u64 num_bytes)
qgroup_rsv_total(qg) + (s64)qg->excl + num_bytes > qg->max_excl)
return false;
+ /*
+ * Even if we passed the check, it's better to check if reservation
+ * for meta_pertrans is pushing us near limit.
+ * If there is too much pertrans reservation or it's near the limit,
+ * let's try commit transaction to free some, using transaction_kthread
+ */
+ if ((qg->lim_flags & (BTRFS_QGROUP_LIMIT_MAX_RFER |
+ BTRFS_QGROUP_LIMIT_MAX_EXCL))) {
+ if (qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_EXCL)
+ limit = qg->max_excl;
+ else
+ limit = qg->max_rfer;
+ threshold = (limit - qg->rsv.values[BTRFS_QGROUP_RSV_DATA] -
+ qg->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC]) /
+ QGROUP_PERTRANS_RATIO;
+ threshold = min_t(u64, threshold, QGROUP_PERTRANS_SIZE);
+
+ /*
+ * Use transaction_kthread to commit transaction, so we no
+ * longer need to bother nested transaction nor lock context.
+ */
+ if (qg->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS] > threshold)
+ btrfs_commit_transaction_locksafe(fs_info);
+ }
+
return true;
}
@@ -2434,7 +2473,7 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce,
qg = unode_aux_to_qgroup(unode);
- if (enforce && !qgroup_check_limits(qg, num_bytes)) {
+ if (enforce && !qgroup_check_limits(fs_info, qg, num_bytes)) {
ret = -EDQUOT;
goto out;
}
@@ -2541,6 +2580,21 @@ void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
}
/*
+ * Check if the leaf is the last leaf. Which means all node pointers
+ * are at their last position.
+ */
+static bool is_last_leaf(struct btrfs_path *path)
+{
+ int i;
+
+ for (i = 1; i < BTRFS_MAX_LEVEL && path->nodes[i]; i++) {
+ if (path->slots[i] != btrfs_header_nritems(path->nodes[i]) - 1)
+ return false;
+ }
+ return true;
+}
+
+/*
* returns < 0 on error, 0 when more leafs are to be scanned.
* returns 1 when done.
*/
@@ -2551,8 +2605,8 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
struct btrfs_key found;
struct extent_buffer *scratch_leaf = NULL;
struct ulist *roots = NULL;
- struct seq_list tree_mod_seq_elem = SEQ_LIST_INIT(tree_mod_seq_elem);
u64 num_bytes;
+ bool done;
int slot;
int ret;
@@ -2581,12 +2635,12 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
mutex_unlock(&fs_info->qgroup_rescan_lock);
return ret;
}
+ done = is_last_leaf(path);
btrfs_item_key_to_cpu(path->nodes[0], &found,
btrfs_header_nritems(path->nodes[0]) - 1);
fs_info->qgroup_rescan_progress.objectid = found.objectid + 1;
- btrfs_get_tree_mod_seq(fs_info, &tree_mod_seq_elem);
scratch_leaf = btrfs_clone_extent_buffer(path->nodes[0]);
if (!scratch_leaf) {
ret = -ENOMEM;
@@ -2625,8 +2679,9 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
btrfs_tree_read_unlock_blocking(scratch_leaf);
free_extent_buffer(scratch_leaf);
}
- btrfs_put_tree_mod_seq(fs_info, &tree_mod_seq_elem);
+ if (done && !ret)
+ ret = 1;
return ret;
}
@@ -2642,6 +2697,12 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
path = btrfs_alloc_path();
if (!path)
goto out;
+ /*
+ * Rescan should only search for commit root, and any later difference
+ * should be recorded by qgroup
+ */
+ path->search_commit_root = 1;
+ path->skip_locking = 1;
err = 0;
while (!err && !btrfs_fs_closing(fs_info)) {
@@ -2721,26 +2782,36 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
{
int ret = 0;
- if (!init_flags &&
- (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) ||
- !(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON))) {
- ret = -EINVAL;
- goto err;
+ if (!init_flags) {
+ /* we're resuming qgroup rescan at mount time */
+ if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN))
+ btrfs_warn(fs_info,
+ "qgroup rescan init failed, qgroup is not enabled");
+ else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON))
+ btrfs_warn(fs_info,
+ "qgroup rescan init failed, qgroup rescan is not queued");
+ return -EINVAL;
}
mutex_lock(&fs_info->qgroup_rescan_lock);
spin_lock(&fs_info->qgroup_lock);
if (init_flags) {
- if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN)
+ if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) {
+ btrfs_warn(fs_info,
+ "qgroup rescan is already in progress");
ret = -EINPROGRESS;
- else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON))
+ } else if (!(fs_info->qgroup_flags &
+ BTRFS_QGROUP_STATUS_FLAG_ON)) {
+ btrfs_warn(fs_info,
+ "qgroup rescan init failed, qgroup is not enabled");
ret = -EINVAL;
+ }
if (ret) {
spin_unlock(&fs_info->qgroup_lock);
mutex_unlock(&fs_info->qgroup_rescan_lock);
- goto err;
+ return ret;
}
fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_RESCAN;
}
@@ -2759,13 +2830,6 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
btrfs_init_work(&fs_info->qgroup_rescan_work,
btrfs_qgroup_rescan_helper,
btrfs_qgroup_rescan_worker, NULL, NULL);
-
- if (ret) {
-err:
- btrfs_info(fs_info, "qgroup_rescan_init failed with %d", ret);
- return ret;
- }
-
return 0;
}
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 9abd950..5e4ad134 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -163,6 +163,12 @@ struct btrfs_raid_bio {
* bitmap to record which horizontal stripe has data
*/
unsigned long *dbitmap;
+
+ /* allocated with real_stripes-many pointers for finish_*() calls */
+ void **finish_pointers;
+
+ /* allocated with stripe_npages-many bits for finish_*() calls */
+ unsigned long *finish_pbitmap;
};
static int __raid56_parity_recover(struct btrfs_raid_bio *rbio);
@@ -981,9 +987,14 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info,
int stripe_npages = DIV_ROUND_UP(stripe_len, PAGE_SIZE);
void *p;
- rbio = kzalloc(sizeof(*rbio) + num_pages * sizeof(struct page *) * 2 +
- DIV_ROUND_UP(stripe_npages, BITS_PER_LONG) *
- sizeof(long), GFP_NOFS);
+ rbio = kzalloc(sizeof(*rbio) +
+ sizeof(*rbio->stripe_pages) * num_pages +
+ sizeof(*rbio->bio_pages) * num_pages +
+ sizeof(*rbio->finish_pointers) * real_stripes +
+ sizeof(*rbio->dbitmap) * BITS_TO_LONGS(stripe_npages) +
+ sizeof(*rbio->finish_pbitmap) *
+ BITS_TO_LONGS(stripe_npages),
+ GFP_NOFS);
if (!rbio)
return ERR_PTR(-ENOMEM);
@@ -1005,13 +1016,20 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info,
atomic_set(&rbio->stripes_pending, 0);
/*
- * the stripe_pages and bio_pages array point to the extra
+ * the stripe_pages, bio_pages, etc arrays point to the extra
* memory we allocated past the end of the rbio
*/
p = rbio + 1;
- rbio->stripe_pages = p;
- rbio->bio_pages = p + sizeof(struct page *) * num_pages;
- rbio->dbitmap = p + sizeof(struct page *) * num_pages * 2;
+#define CONSUME_ALLOC(ptr, count) do { \
+ ptr = p; \
+ p = (unsigned char *)p + sizeof(*(ptr)) * (count); \
+ } while (0)
+ CONSUME_ALLOC(rbio->stripe_pages, num_pages);
+ CONSUME_ALLOC(rbio->bio_pages, num_pages);
+ CONSUME_ALLOC(rbio->finish_pointers, real_stripes);
+ CONSUME_ALLOC(rbio->dbitmap, BITS_TO_LONGS(stripe_npages));
+ CONSUME_ALLOC(rbio->finish_pbitmap, BITS_TO_LONGS(stripe_npages));
+#undef CONSUME_ALLOC
if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID5)
nr_data = real_stripes - 1;
@@ -1180,7 +1198,7 @@ static void index_rbio_pages(struct btrfs_raid_bio *rbio)
static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
{
struct btrfs_bio *bbio = rbio->bbio;
- void *pointers[rbio->real_stripes];
+ void **pointers = rbio->finish_pointers;
int nr_data = rbio->nr_data;
int stripe;
int pagenr;
@@ -2350,8 +2368,8 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
int need_check)
{
struct btrfs_bio *bbio = rbio->bbio;
- void *pointers[rbio->real_stripes];
- DECLARE_BITMAP(pbitmap, rbio->stripe_npages);
+ void **pointers = rbio->finish_pointers;
+ unsigned long *pbitmap = rbio->finish_pbitmap;
int nr_data = rbio->nr_data;
int stripe;
int pagenr;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 00b7d32..879b76f 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1841,7 +1841,7 @@ int replace_path(struct btrfs_trans_handle *trans,
old_bytenr = btrfs_node_blockptr(parent, slot);
blocksize = fs_info->nodesize;
old_ptr_gen = btrfs_node_ptr_generation(parent, slot);
- btrfs_node_key_to_cpu(parent, &key, slot);
+ btrfs_node_key_to_cpu(parent, &first_key, slot);
if (level <= max_level) {
eb = path->nodes[level];
@@ -4299,7 +4299,7 @@ struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info,
return inode;
}
-static struct reloc_control *alloc_reloc_control(struct btrfs_fs_info *fs_info)
+static struct reloc_control *alloc_reloc_control(void)
{
struct reloc_control *rc;
@@ -4344,7 +4344,7 @@ static void describe_relocation(struct btrfs_fs_info *fs_info,
DESCRIBE_FLAG(RAID5, "raid5");
DESCRIBE_FLAG(RAID6, "raid6");
if (flags)
- snprintf(buf, buf - bp + sizeof(buf), "|0x%llx", flags);
+ snprintf(bp, buf - bp + sizeof(buf), "|0x%llx", flags);
#undef DESCRIBE_FLAG
}
@@ -4366,7 +4366,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
int rw = 0;
int err = 0;
- rc = alloc_reloc_control(fs_info);
+ rc = alloc_reloc_control();
if (!rc)
return -ENOMEM;
@@ -4562,7 +4562,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
if (list_empty(&reloc_roots))
goto out;
- rc = alloc_reloc_control(fs_info);
+ rc = alloc_reloc_control();
if (!rc) {
err = -ENOMEM;
goto out;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 52b39a0..a590058 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3984,6 +3984,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
spin_lock(&fs_info->unused_bgs_lock);
if (list_empty(&cache->bg_list)) {
btrfs_get_block_group(cache);
+ trace_btrfs_add_unused_block_group(cache);
list_add_tail(&cache->bg_list,
&fs_info->unused_bgs);
}
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 221e5cd..c47f62b 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -235,6 +235,7 @@ struct orphan_dir_info {
struct rb_node node;
u64 ino;
u64 gen;
+ u64 last_dir_index_offset;
};
struct name_cache_entry {
@@ -2844,12 +2845,6 @@ add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino)
struct rb_node *parent = NULL;
struct orphan_dir_info *entry, *odi;
- odi = kmalloc(sizeof(*odi), GFP_KERNEL);
- if (!odi)
- return ERR_PTR(-ENOMEM);
- odi->ino = dir_ino;
- odi->gen = 0;
-
while (*p) {
parent = *p;
entry = rb_entry(parent, struct orphan_dir_info, node);
@@ -2858,11 +2853,17 @@ add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino)
} else if (dir_ino > entry->ino) {
p = &(*p)->rb_right;
} else {
- kfree(odi);
return entry;
}
}
+ odi = kmalloc(sizeof(*odi), GFP_KERNEL);
+ if (!odi)
+ return ERR_PTR(-ENOMEM);
+ odi->ino = dir_ino;
+ odi->gen = 0;
+ odi->last_dir_index_offset = 0;
+
rb_link_node(&odi->node, parent, p);
rb_insert_color(&odi->node, &sctx->orphan_dirs);
return odi;
@@ -2917,6 +2918,7 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen,
struct btrfs_key found_key;
struct btrfs_key loc;
struct btrfs_dir_item *di;
+ struct orphan_dir_info *odi = NULL;
/*
* Don't try to rmdir the top/root subvolume dir.
@@ -2931,6 +2933,11 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen,
key.objectid = dir;
key.type = BTRFS_DIR_INDEX_KEY;
key.offset = 0;
+
+ odi = get_orphan_dir_info(sctx, dir);
+ if (odi)
+ key.offset = odi->last_dir_index_offset;
+
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (ret < 0)
goto out;
@@ -2958,30 +2965,33 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen,
dm = get_waiting_dir_move(sctx, loc.objectid);
if (dm) {
- struct orphan_dir_info *odi;
-
odi = add_orphan_dir_info(sctx, dir);
if (IS_ERR(odi)) {
ret = PTR_ERR(odi);
goto out;
}
odi->gen = dir_gen;
+ odi->last_dir_index_offset = found_key.offset;
dm->rmdir_ino = dir;
ret = 0;
goto out;
}
if (loc.objectid > send_progress) {
- struct orphan_dir_info *odi;
-
- odi = get_orphan_dir_info(sctx, dir);
- free_orphan_dir_info(sctx, odi);
+ odi = add_orphan_dir_info(sctx, dir);
+ if (IS_ERR(odi)) {
+ ret = PTR_ERR(odi);
+ goto out;
+ }
+ odi->gen = dir_gen;
+ odi->last_dir_index_offset = found_key.offset;
ret = 0;
goto out;
}
path->slots[0]++;
}
+ free_orphan_dir_info(sctx, odi);
ret = 1;
@@ -3259,13 +3269,16 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
if (rmdir_ino) {
struct orphan_dir_info *odi;
+ u64 gen;
odi = get_orphan_dir_info(sctx, rmdir_ino);
if (!odi) {
/* already deleted */
goto finish;
}
- ret = can_rmdir(sctx, rmdir_ino, odi->gen, sctx->cur_ino);
+ gen = odi->gen;
+
+ ret = can_rmdir(sctx, rmdir_ino, gen, sctx->cur_ino);
if (ret < 0)
goto out;
if (!ret)
@@ -3276,13 +3289,12 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
ret = -ENOMEM;
goto out;
}
- ret = get_cur_path(sctx, rmdir_ino, odi->gen, name);
+ ret = get_cur_path(sctx, rmdir_ino, gen, name);
if (ret < 0)
goto out;
ret = send_rmdir(sctx, name);
if (ret < 0)
goto out;
- free_orphan_dir_info(sctx, odi);
}
finish:
@@ -5236,6 +5248,10 @@ static int send_write_or_clone(struct send_ctx *sctx,
len = btrfs_file_extent_num_bytes(path->nodes[0], ei);
}
+ if (offset >= sctx->cur_inode_size) {
+ ret = 0;
+ goto out;
+ }
if (offset + len > sctx->cur_inode_size)
len = sctx->cur_inode_size - offset;
if (len == 0) {
@@ -6450,7 +6466,7 @@ static void btrfs_root_dec_send_in_progress(struct btrfs_root* root)
*/
if (root->send_in_progress < 0)
btrfs_err(root->fs_info,
- "send_in_progres unbalanced %d root %llu",
+ "send_in_progress unbalanced %d root %llu",
root->send_in_progress, root->root_key.objectid);
spin_unlock(&root->root_item_lock);
}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 0628092..81107ad 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -323,6 +323,7 @@ enum {
Opt_ssd, Opt_nossd,
Opt_ssd_spread, Opt_nossd_spread,
Opt_subvol,
+ Opt_subvol_empty,
Opt_subvolid,
Opt_thread_pool,
Opt_treelog, Opt_notreelog,
@@ -388,6 +389,7 @@ static const match_table_t tokens = {
{Opt_ssd_spread, "ssd_spread"},
{Opt_nossd_spread, "nossd_spread"},
{Opt_subvol, "subvol=%s"},
+ {Opt_subvol_empty, "subvol="},
{Opt_subvolid, "subvolid=%s"},
{Opt_thread_pool, "thread_pool=%u"},
{Opt_treelog, "treelog"},
@@ -461,6 +463,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
btrfs_set_opt(info->mount_opt, DEGRADED);
break;
case Opt_subvol:
+ case Opt_subvol_empty:
case Opt_subvolid:
case Opt_subvolrootid:
case Opt_device:
@@ -1782,10 +1785,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
}
ret = btrfs_parse_options(fs_info, data, *flags);
- if (ret) {
- ret = -EINVAL;
+ if (ret)
goto restore;
- }
btrfs_remount_begin(fs_info, old_opts, *flags);
btrfs_resize_thread_pool(fs_info,
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 4848a43..4a4e960 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -210,12 +210,42 @@ static struct attribute *btrfs_supported_feature_attrs[] = {
NULL
};
+/*
+ * Features which depend on feature bits and may differ between each fs.
+ *
+ * /sys/fs/btrfs/features lists all available features of this kernel while
+ * /sys/fs/btrfs/UUID/features shows features of the fs which are enabled or
+ * can be changed online.
+ */
static const struct attribute_group btrfs_feature_attr_group = {
.name = "features",
.is_visible = btrfs_feature_visible,
.attrs = btrfs_supported_feature_attrs,
};
+static ssize_t rmdir_subvol_show(struct kobject *kobj,
+ struct kobj_attribute *ka, char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "0\n");
+}
+BTRFS_ATTR(static_feature, rmdir_subvol, rmdir_subvol_show);
+
+static struct attribute *btrfs_supported_static_feature_attrs[] = {
+ BTRFS_ATTR_PTR(static_feature, rmdir_subvol),
+ NULL
+};
+
+/*
+ * Features which only depend on kernel version.
+ *
+ * These are listed in /sys/fs/btrfs/features along with
+ * btrfs_feature_attr_group
+ */
+static const struct attribute_group btrfs_static_feature_attr_group = {
+ .name = "features",
+ .attrs = btrfs_supported_static_feature_attrs,
+};
+
static ssize_t btrfs_show_u64(u64 *value_ptr, spinlock_t *lock, char *buf)
{
u64 val;
@@ -514,10 +544,11 @@ static inline struct btrfs_fs_info *to_fs_info(struct kobject *kobj)
}
#define NUM_FEATURE_BITS 64
-static char btrfs_unknown_feature_names[3][NUM_FEATURE_BITS][13];
-static struct btrfs_feature_attr btrfs_feature_attrs[3][NUM_FEATURE_BITS];
+#define BTRFS_FEATURE_NAME_MAX 13
+static char btrfs_unknown_feature_names[FEAT_MAX][NUM_FEATURE_BITS][BTRFS_FEATURE_NAME_MAX];
+static struct btrfs_feature_attr btrfs_feature_attrs[FEAT_MAX][NUM_FEATURE_BITS];
-static const u64 supported_feature_masks[3] = {
+static const u64 supported_feature_masks[FEAT_MAX] = {
[FEAT_COMPAT] = BTRFS_FEATURE_COMPAT_SUPP,
[FEAT_COMPAT_RO] = BTRFS_FEATURE_COMPAT_RO_SUPP,
[FEAT_INCOMPAT] = BTRFS_FEATURE_INCOMPAT_SUPP,
@@ -589,7 +620,7 @@ void btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs)
return;
}
- list_for_each_entry(fs_devs, fs_uuids, list) {
+ list_for_each_entry(fs_devs, fs_uuids, fs_list) {
__btrfs_sysfs_remove_fsid(fs_devs);
}
}
@@ -609,7 +640,7 @@ void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info)
btrfs_sysfs_rm_device_link(fs_info->fs_devices, NULL);
}
-const char * const btrfs_feature_set_names[3] = {
+const char * const btrfs_feature_set_names[FEAT_MAX] = {
[FEAT_COMPAT] = "compat",
[FEAT_COMPAT_RO] = "compat_ro",
[FEAT_INCOMPAT] = "incompat",
@@ -673,7 +704,7 @@ static void init_feature_attrs(void)
if (fa->kobj_attr.attr.name)
continue;
- snprintf(name, 13, "%s:%u",
+ snprintf(name, BTRFS_FEATURE_NAME_MAX, "%s:%u",
btrfs_feature_set_names[set], i);
fa->kobj_attr.attr.name = name;
@@ -900,8 +931,15 @@ int __init btrfs_init_sysfs(void)
ret = sysfs_create_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
if (ret)
goto out2;
+ ret = sysfs_merge_group(&btrfs_kset->kobj,
+ &btrfs_static_feature_attr_group);
+ if (ret)
+ goto out_remove_group;
return 0;
+
+out_remove_group:
+ sysfs_remove_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
out2:
debugfs_remove_recursive(btrfs_debugfs_root_dentry);
out1:
@@ -912,6 +950,8 @@ int __init btrfs_init_sysfs(void)
void __cold btrfs_exit_sysfs(void)
{
+ sysfs_unmerge_group(&btrfs_kset->kobj,
+ &btrfs_static_feature_attr_group);
sysfs_remove_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
kset_unregister(btrfs_kset);
debugfs_remove_recursive(btrfs_debugfs_root_dentry);
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index b567560..c6ee600 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -9,7 +9,7 @@
extern u64 btrfs_debugfs_test;
enum btrfs_feature_set {
- FEAT_COMPAT,
+ FEAT_COMPAT = 0,
FEAT_COMPAT_RO,
FEAT_INCOMPAT,
FEAT_MAX
@@ -77,7 +77,7 @@ attr_to_btrfs_feature_attr(struct attribute *attr)
}
char *btrfs_printable_features(enum btrfs_feature_set set, u64 flags);
-extern const char * const btrfs_feature_set_names[3];
+extern const char * const btrfs_feature_set_names[FEAT_MAX];
extern struct kobj_type space_info_ktype;
extern struct kobj_type btrfs_raid_ktype;
int btrfs_sysfs_add_device_link(struct btrfs_fs_devices *fs_devices,
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index 30ed438..db72b3b 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -219,11 +219,13 @@ void btrfs_free_dummy_block_group(struct btrfs_block_group_cache *cache)
kfree(cache);
}
-void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans)
+void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info)
{
memset(trans, 0, sizeof(*trans));
trans->transid = 1;
trans->type = __TRANS_DUMMY;
+ trans->fs_info = fs_info;
}
int btrfs_run_sanity_tests(void)
diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h
index a5a0b95..70ff9f9 100644
--- a/fs/btrfs/tests/btrfs-tests.h
+++ b/fs/btrfs/tests/btrfs-tests.h
@@ -9,7 +9,8 @@
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
int btrfs_run_sanity_tests(void);
-#define test_msg(fmt, ...) pr_info("BTRFS: selftest: " fmt, ##__VA_ARGS__)
+#define test_msg(fmt, ...) pr_info("BTRFS: selftest: " fmt "\n", ##__VA_ARGS__)
+#define test_err(fmt, ...) pr_err("BTRFS: selftest: " fmt "\n", ##__VA_ARGS__)
struct btrfs_root;
struct btrfs_trans_handle;
@@ -28,7 +29,8 @@ void btrfs_free_dummy_root(struct btrfs_root *root);
struct btrfs_block_group_cache *
btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info, unsigned long length);
void btrfs_free_dummy_block_group(struct btrfs_block_group_cache *cache);
-void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans);
+void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info);
#else
static inline int btrfs_run_sanity_tests(void)
{
diff --git a/fs/btrfs/tests/extent-buffer-tests.c b/fs/btrfs/tests/extent-buffer-tests.c
index 31e8a9e..7d72eab 100644
--- a/fs/btrfs/tests/extent-buffer-tests.c
+++ b/fs/btrfs/tests/extent-buffer-tests.c
@@ -26,31 +26,31 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
u32 value_len = strlen(value);
int ret = 0;
- test_msg("Running btrfs_split_item tests\n");
+ test_msg("running btrfs_split_item tests");
fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
if (!fs_info) {
- test_msg("Could not allocate fs_info\n");
+ test_err("could not allocate fs_info");
return -ENOMEM;
}
root = btrfs_alloc_dummy_root(fs_info);
if (IS_ERR(root)) {
- test_msg("Could not allocate root\n");
+ test_err("could not allocate root");
ret = PTR_ERR(root);
goto out;
}
path = btrfs_alloc_path();
if (!path) {
- test_msg("Could not allocate path\n");
+ test_err("could not allocate path");
ret = -ENOMEM;
goto out;
}
path->nodes[0] = eb = alloc_dummy_extent_buffer(fs_info, nodesize);
if (!eb) {
- test_msg("Could not allocate dummy buffer\n");
+ test_err("could not allocate dummy buffer");
ret = -ENOMEM;
goto out;
}
@@ -75,7 +75,7 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
*/
ret = btrfs_split_item(NULL, root, path, &key, 17);
if (ret) {
- test_msg("Split item failed %d\n", ret);
+ test_err("split item failed %d", ret);
goto out;
}
@@ -86,14 +86,14 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
btrfs_item_key_to_cpu(eb, &key, 0);
if (key.objectid != 0 || key.type != BTRFS_EXTENT_CSUM_KEY ||
key.offset != 0) {
- test_msg("Invalid key at slot 0\n");
+ test_err("invalid key at slot 0");
ret = -EINVAL;
goto out;
}
item = btrfs_item_nr(0);
if (btrfs_item_size(eb, item) != strlen(split1)) {
- test_msg("Invalid len in the first split\n");
+ test_err("invalid len in the first split");
ret = -EINVAL;
goto out;
}
@@ -101,8 +101,8 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
read_extent_buffer(eb, buf, btrfs_item_ptr_offset(eb, 0),
strlen(split1));
if (memcmp(buf, split1, strlen(split1))) {
- test_msg("Data in the buffer doesn't match what it should "
- "in the first split have='%.*s' want '%s'\n",
+ test_err(
+"data in the buffer doesn't match what it should in the first split have='%.*s' want '%s'",
(int)strlen(split1), buf, split1);
ret = -EINVAL;
goto out;
@@ -111,14 +111,14 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
btrfs_item_key_to_cpu(eb, &key, 1);
if (key.objectid != 0 || key.type != BTRFS_EXTENT_CSUM_KEY ||
key.offset != 3) {
- test_msg("Invalid key at slot 1\n");
+ test_err("invalid key at slot 1");
ret = -EINVAL;
goto out;
}
item = btrfs_item_nr(1);
if (btrfs_item_size(eb, item) != strlen(split2)) {
- test_msg("Invalid len in the second split\n");
+ test_err("invalid len in the second split");
ret = -EINVAL;
goto out;
}
@@ -126,8 +126,8 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
read_extent_buffer(eb, buf, btrfs_item_ptr_offset(eb, 1),
strlen(split2));
if (memcmp(buf, split2, strlen(split2))) {
- test_msg("Data in the buffer doesn't match what it should "
- "in the second split\n");
+ test_err(
+ "data in the buffer doesn't match what it should in the second split");
ret = -EINVAL;
goto out;
}
@@ -136,21 +136,21 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
/* Do it again so we test memmoving the other items in the leaf */
ret = btrfs_split_item(NULL, root, path, &key, 4);
if (ret) {
- test_msg("Second split item failed %d\n", ret);
+ test_err("second split item failed %d", ret);
goto out;
}
btrfs_item_key_to_cpu(eb, &key, 0);
if (key.objectid != 0 || key.type != BTRFS_EXTENT_CSUM_KEY ||
key.offset != 0) {
- test_msg("Invalid key at slot 0\n");
+ test_err("invalid key at slot 0");
ret = -EINVAL;
goto out;
}
item = btrfs_item_nr(0);
if (btrfs_item_size(eb, item) != strlen(split3)) {
- test_msg("Invalid len in the first split\n");
+ test_err("invalid len in the first split");
ret = -EINVAL;
goto out;
}
@@ -158,8 +158,8 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
read_extent_buffer(eb, buf, btrfs_item_ptr_offset(eb, 0),
strlen(split3));
if (memcmp(buf, split3, strlen(split3))) {
- test_msg("Data in the buffer doesn't match what it should "
- "in the third split");
+ test_err(
+ "data in the buffer doesn't match what it should in the third split");
ret = -EINVAL;
goto out;
}
@@ -167,14 +167,14 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
btrfs_item_key_to_cpu(eb, &key, 1);
if (key.objectid != 0 || key.type != BTRFS_EXTENT_CSUM_KEY ||
key.offset != 1) {
- test_msg("Invalid key at slot 1\n");
+ test_err("invalid key at slot 1");
ret = -EINVAL;
goto out;
}
item = btrfs_item_nr(1);
if (btrfs_item_size(eb, item) != strlen(split4)) {
- test_msg("Invalid len in the second split\n");
+ test_err("invalid len in the second split");
ret = -EINVAL;
goto out;
}
@@ -182,8 +182,8 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
read_extent_buffer(eb, buf, btrfs_item_ptr_offset(eb, 1),
strlen(split4));
if (memcmp(buf, split4, strlen(split4))) {
- test_msg("Data in the buffer doesn't match what it should "
- "in the fourth split\n");
+ test_err(
+ "data in the buffer doesn't match what it should in the fourth split");
ret = -EINVAL;
goto out;
}
@@ -191,14 +191,14 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
btrfs_item_key_to_cpu(eb, &key, 2);
if (key.objectid != 0 || key.type != BTRFS_EXTENT_CSUM_KEY ||
key.offset != 3) {
- test_msg("Invalid key at slot 2\n");
+ test_err("invalid key at slot 2");
ret = -EINVAL;
goto out;
}
item = btrfs_item_nr(2);
if (btrfs_item_size(eb, item) != strlen(split2)) {
- test_msg("Invalid len in the second split\n");
+ test_err("invalid len in the second split");
ret = -EINVAL;
goto out;
}
@@ -206,8 +206,8 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
read_extent_buffer(eb, buf, btrfs_item_ptr_offset(eb, 2),
strlen(split2));
if (memcmp(buf, split2, strlen(split2))) {
- test_msg("Data in the buffer doesn't match what it should "
- "in the last chunk\n");
+ test_err(
+ "data in the buffer doesn't match what it should in the last chunk");
ret = -EINVAL;
goto out;
}
@@ -220,6 +220,6 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
int btrfs_test_extent_buffer_operations(u32 sectorsize, u32 nodesize)
{
- test_msg("Running extent buffer operation tests\n");
+ test_msg("running extent buffer operation tests");
return test_btrfs_split_item(sectorsize, nodesize);
}
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index 76aa5a6..d9269a53 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -46,7 +46,9 @@ static noinline int process_page_range(struct inode *inode, u64 start, u64 end,
cond_resched();
loops++;
if (loops > 100000) {
- printk(KERN_ERR "stuck in a loop, start %Lu, end %Lu, nr_pages %lu, ret %d\n", start, end, nr_pages, ret);
+ printk(KERN_ERR
+ "stuck in a loop, start %llu, end %llu, nr_pages %lu, ret %d\n",
+ start, end, nr_pages, ret);
break;
}
}
@@ -66,11 +68,11 @@ static int test_find_delalloc(u32 sectorsize)
u64 found;
int ret = -EINVAL;
- test_msg("Running find delalloc tests\n");
+ test_msg("running find delalloc tests");
inode = btrfs_new_test_inode();
if (!inode) {
- test_msg("Failed to allocate test inode\n");
+ test_err("failed to allocate test inode");
return -ENOMEM;
}
@@ -84,7 +86,7 @@ static int test_find_delalloc(u32 sectorsize)
for (index = 0; index < (total_dirty >> PAGE_SHIFT); index++) {
page = find_or_create_page(inode->i_mapping, index, GFP_KERNEL);
if (!page) {
- test_msg("Failed to allocate test page\n");
+ test_err("failed to allocate test page");
ret = -ENOMEM;
goto out;
}
@@ -107,11 +109,11 @@ static int test_find_delalloc(u32 sectorsize)
found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
&end, max_bytes);
if (!found) {
- test_msg("Should have found at least one delalloc\n");
+ test_err("should have found at least one delalloc");
goto out_bits;
}
if (start != 0 || end != (sectorsize - 1)) {
- test_msg("Expected start 0 end %u, got start %llu end %llu\n",
+ test_err("expected start 0 end %u, got start %llu end %llu",
sectorsize - 1, start, end);
goto out_bits;
}
@@ -129,7 +131,7 @@ static int test_find_delalloc(u32 sectorsize)
locked_page = find_lock_page(inode->i_mapping,
test_start >> PAGE_SHIFT);
if (!locked_page) {
- test_msg("Couldn't find the locked page\n");
+ test_err("couldn't find the locked page");
goto out_bits;
}
set_extent_delalloc(&tmp, sectorsize, max_bytes - 1, 0, NULL);
@@ -138,17 +140,17 @@ static int test_find_delalloc(u32 sectorsize)
found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
&end, max_bytes);
if (!found) {
- test_msg("Couldn't find delalloc in our range\n");
+ test_err("couldn't find delalloc in our range");
goto out_bits;
}
if (start != test_start || end != max_bytes - 1) {
- test_msg("Expected start %Lu end %Lu, got start %Lu, end "
- "%Lu\n", test_start, max_bytes - 1, start, end);
+ test_err("expected start %llu end %llu, got start %llu, end %llu",
+ test_start, max_bytes - 1, start, end);
goto out_bits;
}
if (process_page_range(inode, start, end,
PROCESS_TEST_LOCKED | PROCESS_UNLOCK)) {
- test_msg("There were unlocked pages in the range\n");
+ test_err("there were unlocked pages in the range");
goto out_bits;
}
unlock_extent(&tmp, start, end);
@@ -164,7 +166,7 @@ static int test_find_delalloc(u32 sectorsize)
locked_page = find_lock_page(inode->i_mapping, test_start >>
PAGE_SHIFT);
if (!locked_page) {
- test_msg("Couldn't find the locked page\n");
+ test_err("couldn't find the locked page");
goto out_bits;
}
start = test_start;
@@ -172,11 +174,11 @@ static int test_find_delalloc(u32 sectorsize)
found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
&end, max_bytes);
if (found) {
- test_msg("Found range when we shouldn't have\n");
+ test_err("found range when we shouldn't have");
goto out_bits;
}
if (end != (u64)-1) {
- test_msg("Did not return the proper end offset\n");
+ test_err("did not return the proper end offset");
goto out_bits;
}
@@ -193,17 +195,17 @@ static int test_find_delalloc(u32 sectorsize)
found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
&end, max_bytes);
if (!found) {
- test_msg("Didn't find our range\n");
+ test_err("didn't find our range");
goto out_bits;
}
if (start != test_start || end != total_dirty - 1) {
- test_msg("Expected start %Lu end %Lu, got start %Lu end %Lu\n",
+ test_err("expected start %llu end %llu, got start %llu end %llu",
test_start, total_dirty - 1, start, end);
goto out_bits;
}
if (process_page_range(inode, start, end,
PROCESS_TEST_LOCKED | PROCESS_UNLOCK)) {
- test_msg("Pages in range were not all locked\n");
+ test_err("pages in range were not all locked");
goto out_bits;
}
unlock_extent(&tmp, start, end);
@@ -215,7 +217,7 @@ static int test_find_delalloc(u32 sectorsize)
page = find_get_page(inode->i_mapping,
(max_bytes + SZ_1M) >> PAGE_SHIFT);
if (!page) {
- test_msg("Couldn't find our page\n");
+ test_err("couldn't find our page");
goto out_bits;
}
ClearPageDirty(page);
@@ -234,18 +236,17 @@ static int test_find_delalloc(u32 sectorsize)
found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
&end, max_bytes);
if (!found) {
- test_msg("Didn't find our range\n");
+ test_err("didn't find our range");
goto out_bits;
}
if (start != test_start && end != test_start + PAGE_SIZE - 1) {
- test_msg("Expected start %Lu end %Lu, got start %Lu end %Lu\n",
- test_start, test_start + PAGE_SIZE - 1, start,
- end);
+ test_err("expected start %llu end %llu, got start %llu end %llu",
+ test_start, test_start + PAGE_SIZE - 1, start, end);
goto out_bits;
}
if (process_page_range(inode, start, end, PROCESS_TEST_LOCKED |
PROCESS_UNLOCK)) {
- test_msg("Pages in range were not all locked\n");
+ test_err("pages in range were not all locked");
goto out_bits;
}
ret = 0;
@@ -271,14 +272,14 @@ static int check_eb_bitmap(unsigned long *bitmap, struct extent_buffer *eb,
bit = !!test_bit(i, bitmap);
bit1 = !!extent_buffer_test_bit(eb, 0, i);
if (bit1 != bit) {
- test_msg("Bits do not match\n");
+ test_err("bits do not match");
return -EINVAL;
}
bit1 = !!extent_buffer_test_bit(eb, i / BITS_PER_BYTE,
i % BITS_PER_BYTE);
if (bit1 != bit) {
- test_msg("Offset bits do not match\n");
+ test_err("offset bits do not match");
return -EINVAL;
}
}
@@ -295,7 +296,7 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
memset(bitmap, 0, len);
memzero_extent_buffer(eb, 0, len);
if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
- test_msg("Bitmap was not zeroed\n");
+ test_err("bitmap was not zeroed");
return -EINVAL;
}
@@ -303,7 +304,7 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
extent_buffer_bitmap_set(eb, 0, 0, len * BITS_PER_BYTE);
ret = check_eb_bitmap(bitmap, eb, len);
if (ret) {
- test_msg("Setting all bits failed\n");
+ test_err("setting all bits failed");
return ret;
}
@@ -311,7 +312,7 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
extent_buffer_bitmap_clear(eb, 0, 0, len * BITS_PER_BYTE);
ret = check_eb_bitmap(bitmap, eb, len);
if (ret) {
- test_msg("Clearing all bits failed\n");
+ test_err("clearing all bits failed");
return ret;
}
@@ -324,7 +325,7 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
sizeof(long) * BITS_PER_BYTE);
ret = check_eb_bitmap(bitmap, eb, len);
if (ret) {
- test_msg("Setting straddling pages failed\n");
+ test_err("setting straddling pages failed");
return ret;
}
@@ -337,7 +338,7 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
sizeof(long) * BITS_PER_BYTE);
ret = check_eb_bitmap(bitmap, eb, len);
if (ret) {
- test_msg("Clearing straddling pages failed\n");
+ test_err("clearing straddling pages failed");
return ret;
}
}
@@ -361,7 +362,7 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
ret = check_eb_bitmap(bitmap, eb, len);
if (ret) {
- test_msg("Random bit pattern failed\n");
+ test_err("random bit pattern failed");
return ret;
}
@@ -376,7 +377,7 @@ static int test_eb_bitmaps(u32 sectorsize, u32 nodesize)
struct extent_buffer *eb;
int ret;
- test_msg("Running extent buffer bitmap tests\n");
+ test_msg("running extent buffer bitmap tests");
/*
* In ppc64, sectorsize can be 64K, thus 4 * 64K will be larger than
@@ -389,13 +390,13 @@ static int test_eb_bitmaps(u32 sectorsize, u32 nodesize)
bitmap = kmalloc(len, GFP_KERNEL);
if (!bitmap) {
- test_msg("Couldn't allocate test bitmap\n");
+ test_err("couldn't allocate test bitmap");
return -ENOMEM;
}
eb = __alloc_dummy_extent_buffer(fs_info, 0, len);
if (!eb) {
- test_msg("Couldn't allocate test extent buffer\n");
+ test_err("couldn't allocate test extent buffer");
kfree(bitmap);
return -ENOMEM;
}
@@ -408,7 +409,7 @@ static int test_eb_bitmaps(u32 sectorsize, u32 nodesize)
free_extent_buffer(eb);
eb = __alloc_dummy_extent_buffer(NULL, nodesize / 2, len);
if (!eb) {
- test_msg("Couldn't allocate test extent buffer\n");
+ test_err("couldn't allocate test extent buffer");
kfree(bitmap);
return -ENOMEM;
}
@@ -424,7 +425,7 @@ int btrfs_test_extent_io(u32 sectorsize, u32 nodesize)
{
int ret;
- test_msg("Running extent I/O tests\n");
+ test_msg("running extent I/O tests");
ret = test_find_delalloc(sectorsize);
if (ret)
@@ -432,6 +433,6 @@ int btrfs_test_extent_io(u32 sectorsize, u32 nodesize)
ret = test_eb_bitmaps(sectorsize, nodesize);
out:
- test_msg("Extent I/O tests finished\n");
+ test_msg("extent I/O tests finished");
return ret;
}
diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c
index 79e0a5f..385a531 100644
--- a/fs/btrfs/tests/extent-map-tests.c
+++ b/fs/btrfs/tests/extent-map-tests.c
@@ -19,8 +19,8 @@ static void free_extent_map_tree(struct extent_map_tree *em_tree)
#ifdef CONFIG_BTRFS_DEBUG
if (refcount_read(&em->refs) != 1) {
- test_msg(
-"em leak: em (start 0x%llx len 0x%llx block_start 0x%llx block_len 0x%llx) refs %d\n",
+ test_err(
+"em leak: em (start 0x%llx len 0x%llx block_start 0x%llx block_len 0x%llx) refs %d",
em->start, em->len, em->block_start,
em->block_len, refcount_read(&em->refs));
@@ -47,7 +47,8 @@ static void free_extent_map_tree(struct extent_map_tree *em_tree)
* ->add_extent_mapping(0, 16K)
* -> #handle -EEXIST
*/
-static void test_case_1(struct extent_map_tree *em_tree)
+static void test_case_1(struct btrfs_fs_info *fs_info,
+ struct extent_map_tree *em_tree)
{
struct extent_map *em;
u64 start = 0;
@@ -90,14 +91,14 @@ static void test_case_1(struct extent_map_tree *em_tree)
em->len = len;
em->block_start = start;
em->block_len = len;
- ret = btrfs_add_extent_mapping(em_tree, &em, em->start, em->len);
+ ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
if (ret)
- test_msg("case1 [%llu %llu]: ret %d\n", start, start + len, ret);
+ test_err("case1 [%llu %llu]: ret %d", start, start + len, ret);
if (em &&
(em->start != 0 || extent_map_end(em) != SZ_16K ||
em->block_start != 0 || em->block_len != SZ_16K))
- test_msg(
-"case1 [%llu %llu]: ret %d return a wrong em (start %llu len %llu block_start %llu block_len %llu\n",
+ test_err(
+"case1 [%llu %llu]: ret %d return a wrong em (start %llu len %llu block_start %llu block_len %llu",
start, start + len, ret, em->start, em->len,
em->block_start, em->block_len);
free_extent_map(em);
@@ -112,7 +113,8 @@ static void test_case_1(struct extent_map_tree *em_tree)
* Reading the inline ending up with EEXIST, ie. read an inline
* extent and discard page cache and read it again.
*/
-static void test_case_2(struct extent_map_tree *em_tree)
+static void test_case_2(struct btrfs_fs_info *fs_info,
+ struct extent_map_tree *em_tree)
{
struct extent_map *em;
int ret;
@@ -153,14 +155,14 @@ static void test_case_2(struct extent_map_tree *em_tree)
em->len = SZ_1K;
em->block_start = EXTENT_MAP_INLINE;
em->block_len = (u64)-1;
- ret = btrfs_add_extent_mapping(em_tree, &em, em->start, em->len);
+ ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
if (ret)
- test_msg("case2 [0 1K]: ret %d\n", ret);
+ test_err("case2 [0 1K]: ret %d", ret);
if (em &&
(em->start != 0 || extent_map_end(em) != SZ_1K ||
em->block_start != EXTENT_MAP_INLINE || em->block_len != (u64)-1))
- test_msg(
-"case2 [0 1K]: ret %d return a wrong em (start %llu len %llu block_start %llu block_len %llu\n",
+ test_err(
+"case2 [0 1K]: ret %d return a wrong em (start %llu len %llu block_start %llu block_len %llu",
ret, em->start, em->len, em->block_start,
em->block_len);
free_extent_map(em);
@@ -169,7 +171,8 @@ static void test_case_2(struct extent_map_tree *em_tree)
free_extent_map_tree(em_tree);
}
-static void __test_case_3(struct extent_map_tree *em_tree, u64 start)
+static void __test_case_3(struct btrfs_fs_info *fs_info,
+ struct extent_map_tree *em_tree, u64 start)
{
struct extent_map *em;
u64 len = SZ_4K;
@@ -198,9 +201,9 @@ static void __test_case_3(struct extent_map_tree *em_tree, u64 start)
em->len = SZ_16K;
em->block_start = 0;
em->block_len = SZ_16K;
- ret = btrfs_add_extent_mapping(em_tree, &em, start, len);
+ ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len);
if (ret)
- test_msg("case3 [0x%llx 0x%llx): ret %d\n",
+ test_err("case3 [0x%llx 0x%llx): ret %d",
start, start + len, ret);
/*
* Since bytes within em are contiguous, em->block_start is identical to
@@ -209,8 +212,8 @@ static void __test_case_3(struct extent_map_tree *em_tree, u64 start)
if (em &&
(start < em->start || start + len > extent_map_end(em) ||
em->start != em->block_start || em->len != em->block_len))
- test_msg(
-"case3 [0x%llx 0x%llx): ret %d em (start 0x%llx len 0x%llx block_start 0x%llx block_len 0x%llx)\n",
+ test_err(
+"case3 [0x%llx 0x%llx): ret %d em (start 0x%llx len 0x%llx block_start 0x%llx block_len 0x%llx)",
start, start + len, ret, em->start, em->len,
em->block_start, em->block_len);
free_extent_map(em);
@@ -235,14 +238,16 @@ static void __test_case_3(struct extent_map_tree *em_tree, u64 start)
* -> add_extent_mapping()
* -> add_extent_mapping()
*/
-static void test_case_3(struct extent_map_tree *em_tree)
+static void test_case_3(struct btrfs_fs_info *fs_info,
+ struct extent_map_tree *em_tree)
{
- __test_case_3(em_tree, 0);
- __test_case_3(em_tree, SZ_8K);
- __test_case_3(em_tree, (12 * 1024ULL));
+ __test_case_3(fs_info, em_tree, 0);
+ __test_case_3(fs_info, em_tree, SZ_8K);
+ __test_case_3(fs_info, em_tree, (12 * 1024ULL));
}
-static void __test_case_4(struct extent_map_tree *em_tree, u64 start)
+static void __test_case_4(struct btrfs_fs_info *fs_info,
+ struct extent_map_tree *em_tree, u64 start)
{
struct extent_map *em;
u64 len = SZ_4K;
@@ -283,14 +288,14 @@ static void __test_case_4(struct extent_map_tree *em_tree, u64 start)
em->len = SZ_32K;
em->block_start = 0;
em->block_len = SZ_32K;
- ret = btrfs_add_extent_mapping(em_tree, &em, start, len);
+ ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len);
if (ret)
- test_msg("case4 [0x%llx 0x%llx): ret %d\n",
+ test_err("case4 [0x%llx 0x%llx): ret %d",
start, len, ret);
if (em &&
(start < em->start || start + len > extent_map_end(em)))
- test_msg(
-"case4 [0x%llx 0x%llx): ret %d, added wrong em (start 0x%llx len 0x%llx block_start 0x%llx block_len 0x%llx)\n",
+ test_err(
+"case4 [0x%llx 0x%llx): ret %d, added wrong em (start 0x%llx len 0x%llx block_start 0x%llx block_len 0x%llx)",
start, len, ret, em->start, em->len, em->block_start,
em->block_len);
free_extent_map(em);
@@ -324,30 +329,45 @@ static void __test_case_4(struct extent_map_tree *em_tree, u64 start)
* # handle -EEXIST when adding
* # [0, 32K)
*/
-static void test_case_4(struct extent_map_tree *em_tree)
+static void test_case_4(struct btrfs_fs_info *fs_info,
+ struct extent_map_tree *em_tree)
{
- __test_case_4(em_tree, 0);
- __test_case_4(em_tree, SZ_4K);
+ __test_case_4(fs_info, em_tree, 0);
+ __test_case_4(fs_info, em_tree, SZ_4K);
}
int btrfs_test_extent_map(void)
{
+ struct btrfs_fs_info *fs_info = NULL;
struct extent_map_tree *em_tree;
- test_msg("Running extent_map tests\n");
+ test_msg("running extent_map tests");
+
+ /*
+ * Note: the fs_info is not set up completely, we only need
+ * fs_info::fsid for the tracepoint.
+ */
+ fs_info = btrfs_alloc_dummy_fs_info(PAGE_SIZE, PAGE_SIZE);
+ if (!fs_info) {
+ test_msg("Couldn't allocate dummy fs info");
+ return -ENOMEM;
+ }
em_tree = kzalloc(sizeof(*em_tree), GFP_KERNEL);
if (!em_tree)
/* Skip the test on error. */
- return 0;
+ goto out;
extent_map_tree_init(em_tree);
- test_case_1(em_tree);
- test_case_2(em_tree);
- test_case_3(em_tree);
- test_case_4(em_tree);
+ test_case_1(fs_info, em_tree);
+ test_case_2(fs_info, em_tree);
+ test_case_3(fs_info, em_tree);
+ test_case_4(fs_info, em_tree);
kfree(em_tree);
+out:
+ btrfs_free_dummy_fs_info(fs_info);
+
return 0;
}
diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c
index d3c9f8a..5c2f77e 100644
--- a/fs/btrfs/tests/free-space-tests.c
+++ b/fs/btrfs/tests/free-space-tests.c
@@ -20,63 +20,63 @@ static int test_extents(struct btrfs_block_group_cache *cache)
{
int ret = 0;
- test_msg("Running extent only tests\n");
+ test_msg("running extent only tests");
/* First just make sure we can remove an entire entry */
ret = btrfs_add_free_space(cache, 0, SZ_4M);
if (ret) {
- test_msg("Error adding initial extents %d\n", ret);
+ test_err("error adding initial extents %d", ret);
return ret;
}
ret = btrfs_remove_free_space(cache, 0, SZ_4M);
if (ret) {
- test_msg("Error removing extent %d\n", ret);
+ test_err("error removing extent %d", ret);
return ret;
}
if (test_check_exists(cache, 0, SZ_4M)) {
- test_msg("Full remove left some lingering space\n");
+ test_err("full remove left some lingering space");
return -1;
}
/* Ok edge and middle cases now */
ret = btrfs_add_free_space(cache, 0, SZ_4M);
if (ret) {
- test_msg("Error adding half extent %d\n", ret);
+ test_err("error adding half extent %d", ret);
return ret;
}
ret = btrfs_remove_free_space(cache, 3 * SZ_1M, SZ_1M);
if (ret) {
- test_msg("Error removing tail end %d\n", ret);
+ test_err("error removing tail end %d", ret);
return ret;
}
ret = btrfs_remove_free_space(cache, 0, SZ_1M);
if (ret) {
- test_msg("Error removing front end %d\n", ret);
+ test_err("error removing front end %d", ret);
return ret;
}
ret = btrfs_remove_free_space(cache, SZ_2M, 4096);
if (ret) {
- test_msg("Error removing middle piece %d\n", ret);
+ test_err("error removing middle piece %d", ret);
return ret;
}
if (test_check_exists(cache, 0, SZ_1M)) {
- test_msg("Still have space at the front\n");
+ test_err("still have space at the front");
return -1;
}
if (test_check_exists(cache, SZ_2M, 4096)) {
- test_msg("Still have space in the middle\n");
+ test_err("still have space in the middle");
return -1;
}
if (test_check_exists(cache, 3 * SZ_1M, SZ_1M)) {
- test_msg("Still have space at the end\n");
+ test_err("still have space at the end");
return -1;
}
@@ -92,34 +92,34 @@ static int test_bitmaps(struct btrfs_block_group_cache *cache,
u64 next_bitmap_offset;
int ret;
- test_msg("Running bitmap only tests\n");
+ test_msg("running bitmap only tests");
ret = test_add_free_space_entry(cache, 0, SZ_4M, 1);
if (ret) {
- test_msg("Couldn't create a bitmap entry %d\n", ret);
+ test_err("couldn't create a bitmap entry %d", ret);
return ret;
}
ret = btrfs_remove_free_space(cache, 0, SZ_4M);
if (ret) {
- test_msg("Error removing bitmap full range %d\n", ret);
+ test_err("error removing bitmap full range %d", ret);
return ret;
}
if (test_check_exists(cache, 0, SZ_4M)) {
- test_msg("Left some space in bitmap\n");
+ test_err("left some space in bitmap");
return -1;
}
ret = test_add_free_space_entry(cache, 0, SZ_4M, 1);
if (ret) {
- test_msg("Couldn't add to our bitmap entry %d\n", ret);
+ test_err("couldn't add to our bitmap entry %d", ret);
return ret;
}
ret = btrfs_remove_free_space(cache, SZ_1M, SZ_2M);
if (ret) {
- test_msg("Couldn't remove middle chunk %d\n", ret);
+ test_err("couldn't remove middle chunk %d", ret);
return ret;
}
@@ -133,19 +133,19 @@ static int test_bitmaps(struct btrfs_block_group_cache *cache,
ret = test_add_free_space_entry(cache, next_bitmap_offset - SZ_2M,
SZ_4M, 1);
if (ret) {
- test_msg("Couldn't add space that straddles two bitmaps %d\n",
+ test_err("couldn't add space that straddles two bitmaps %d",
ret);
return ret;
}
ret = btrfs_remove_free_space(cache, next_bitmap_offset - SZ_1M, SZ_2M);
if (ret) {
- test_msg("Couldn't remove overlapping space %d\n", ret);
+ test_err("couldn't remove overlapping space %d", ret);
return ret;
}
if (test_check_exists(cache, next_bitmap_offset - SZ_1M, SZ_2M)) {
- test_msg("Left some space when removing overlapping\n");
+ test_err("left some space when removing overlapping");
return -1;
}
@@ -161,7 +161,7 @@ static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache,
u64 bitmap_offset = (u64)(BITS_PER_BITMAP * sectorsize);
int ret;
- test_msg("Running bitmap and extent tests\n");
+ test_msg("running bitmap and extent tests");
/*
* First let's do something simple, an extent at the same offset as the
@@ -170,42 +170,42 @@ static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache,
*/
ret = test_add_free_space_entry(cache, SZ_4M, SZ_1M, 1);
if (ret) {
- test_msg("Couldn't create bitmap entry %d\n", ret);
+ test_err("couldn't create bitmap entry %d", ret);
return ret;
}
ret = test_add_free_space_entry(cache, 0, SZ_1M, 0);
if (ret) {
- test_msg("Couldn't add extent entry %d\n", ret);
+ test_err("couldn't add extent entry %d", ret);
return ret;
}
ret = btrfs_remove_free_space(cache, 0, SZ_1M);
if (ret) {
- test_msg("Couldn't remove extent entry %d\n", ret);
+ test_err("couldn't remove extent entry %d", ret);
return ret;
}
if (test_check_exists(cache, 0, SZ_1M)) {
- test_msg("Left remnants after our remove\n");
+ test_err("left remnants after our remove");
return -1;
}
/* Now to add back the extent entry and remove from the bitmap */
ret = test_add_free_space_entry(cache, 0, SZ_1M, 0);
if (ret) {
- test_msg("Couldn't re-add extent entry %d\n", ret);
+ test_err("couldn't re-add extent entry %d", ret);
return ret;
}
ret = btrfs_remove_free_space(cache, SZ_4M, SZ_1M);
if (ret) {
- test_msg("Couldn't remove from bitmap %d\n", ret);
+ test_err("couldn't remove from bitmap %d", ret);
return ret;
}
if (test_check_exists(cache, SZ_4M, SZ_1M)) {
- test_msg("Left remnants in the bitmap\n");
+ test_err("left remnants in the bitmap");
return -1;
}
@@ -215,18 +215,18 @@ static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache,
*/
ret = test_add_free_space_entry(cache, SZ_1M, SZ_4M, 1);
if (ret) {
- test_msg("Couldn't add to a bitmap %d\n", ret);
+ test_err("couldn't add to a bitmap %d", ret);
return ret;
}
ret = btrfs_remove_free_space(cache, SZ_512K, 3 * SZ_1M);
if (ret) {
- test_msg("Couldn't remove overlapping space %d\n", ret);
+ test_err("couldn't remove overlapping space %d", ret);
return ret;
}
if (test_check_exists(cache, SZ_512K, 3 * SZ_1M)) {
- test_msg("Left over pieces after removing overlapping\n");
+ test_err("left over pieces after removing overlapping");
return -1;
}
@@ -235,24 +235,24 @@ static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache,
/* Now with the extent entry offset into the bitmap */
ret = test_add_free_space_entry(cache, SZ_4M, SZ_4M, 1);
if (ret) {
- test_msg("Couldn't add space to the bitmap %d\n", ret);
+ test_err("couldn't add space to the bitmap %d", ret);
return ret;
}
ret = test_add_free_space_entry(cache, SZ_2M, SZ_2M, 0);
if (ret) {
- test_msg("Couldn't add extent to the cache %d\n", ret);
+ test_err("couldn't add extent to the cache %d", ret);
return ret;
}
ret = btrfs_remove_free_space(cache, 3 * SZ_1M, SZ_4M);
if (ret) {
- test_msg("Problem removing overlapping space %d\n", ret);
+ test_err("problem removing overlapping space %d", ret);
return ret;
}
if (test_check_exists(cache, 3 * SZ_1M, SZ_4M)) {
- test_msg("Left something behind when removing space");
+ test_err("left something behind when removing space");
return -1;
}
@@ -269,25 +269,25 @@ static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache,
__btrfs_remove_free_space_cache(cache->free_space_ctl);
ret = test_add_free_space_entry(cache, bitmap_offset + SZ_4M, SZ_4M, 1);
if (ret) {
- test_msg("Couldn't add bitmap %d\n", ret);
+ test_err("couldn't add bitmap %d", ret);
return ret;
}
ret = test_add_free_space_entry(cache, bitmap_offset - SZ_1M,
5 * SZ_1M, 0);
if (ret) {
- test_msg("Couldn't add extent entry %d\n", ret);
+ test_err("couldn't add extent entry %d", ret);
return ret;
}
ret = btrfs_remove_free_space(cache, bitmap_offset + SZ_1M, 5 * SZ_1M);
if (ret) {
- test_msg("Failed to free our space %d\n", ret);
+ test_err("failed to free our space %d", ret);
return ret;
}
if (test_check_exists(cache, bitmap_offset + SZ_1M, 5 * SZ_1M)) {
- test_msg("Left stuff over\n");
+ test_err("left stuff over");
return -1;
}
@@ -301,19 +301,19 @@ static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache,
*/
ret = test_add_free_space_entry(cache, SZ_1M, SZ_2M, 1);
if (ret) {
- test_msg("Couldn't add bitmap entry %d\n", ret);
+ test_err("couldn't add bitmap entry %d", ret);
return ret;
}
ret = test_add_free_space_entry(cache, 3 * SZ_1M, SZ_1M, 0);
if (ret) {
- test_msg("Couldn't add extent entry %d\n", ret);
+ test_err("couldn't add extent entry %d", ret);
return ret;
}
ret = btrfs_remove_free_space(cache, SZ_1M, 3 * SZ_1M);
if (ret) {
- test_msg("Error removing bitmap and extent overlapping %d\n", ret);
+ test_err("error removing bitmap and extent overlapping %d", ret);
return ret;
}
@@ -335,12 +335,14 @@ check_num_extents_and_bitmaps(const struct btrfs_block_group_cache *cache,
const int num_bitmaps)
{
if (cache->free_space_ctl->free_extents != num_extents) {
- test_msg("Incorrect # of extent entries in the cache: %d, expected %d\n",
+ test_err(
+ "incorrect # of extent entries in the cache: %d, expected %d",
cache->free_space_ctl->free_extents, num_extents);
return -EINVAL;
}
if (cache->free_space_ctl->total_bitmaps != num_bitmaps) {
- test_msg("Incorrect # of extent entries in the cache: %d, expected %d\n",
+ test_err(
+ "incorrect # of extent entries in the cache: %d, expected %d",
cache->free_space_ctl->total_bitmaps, num_bitmaps);
return -EINVAL;
}
@@ -358,7 +360,7 @@ static int check_cache_empty(struct btrfs_block_group_cache *cache)
* allocate.
*/
if (cache->free_space_ctl->free_space != 0) {
- test_msg("Cache free space is not 0\n");
+ test_err("cache free space is not 0");
return -EINVAL;
}
@@ -366,7 +368,7 @@ static int check_cache_empty(struct btrfs_block_group_cache *cache)
offset = btrfs_find_space_for_alloc(cache, 0, 4096, 0,
&max_extent_size);
if (offset != 0) {
- test_msg("Space allocation did not fail, returned offset: %llu",
+ test_err("space allocation did not fail, returned offset: %llu",
offset);
return -EINVAL;
}
@@ -402,7 +404,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
};
const struct btrfs_free_space_op *orig_free_space_ops;
- test_msg("Running space stealing from bitmap to extent\n");
+ test_msg("running space stealing from bitmap to extent");
/*
* For this test, we want to ensure we end up with an extent entry
@@ -430,7 +432,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
*/
ret = test_add_free_space_entry(cache, SZ_128M - SZ_256K, SZ_128K, 0);
if (ret) {
- test_msg("Couldn't add extent entry %d\n", ret);
+ test_err("couldn't add extent entry %d", ret);
return ret;
}
@@ -438,7 +440,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
ret = test_add_free_space_entry(cache, SZ_128M + SZ_512K,
SZ_128M - SZ_512K, 1);
if (ret) {
- test_msg("Couldn't add bitmap entry %d\n", ret);
+ test_err("couldn't add bitmap entry %d", ret);
return ret;
}
@@ -457,17 +459,17 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
SZ_128M + 768 * SZ_1K,
SZ_128M - 768 * SZ_1K);
if (ret) {
- test_msg("Failed to free part of bitmap space %d\n", ret);
+ test_err("failed to free part of bitmap space %d", ret);
return ret;
}
/* Confirm that only those 2 ranges are marked as free. */
if (!test_check_exists(cache, SZ_128M - SZ_256K, SZ_128K)) {
- test_msg("Free space range missing\n");
+ test_err("free space range missing");
return -ENOENT;
}
if (!test_check_exists(cache, SZ_128M + SZ_512K, SZ_256K)) {
- test_msg("Free space range missing\n");
+ test_err("free space range missing");
return -ENOENT;
}
@@ -477,7 +479,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
*/
if (test_check_exists(cache, SZ_128M + 768 * SZ_1K,
SZ_128M - 768 * SZ_1K)) {
- test_msg("Bitmap region not removed from space cache\n");
+ test_err("bitmap region not removed from space cache");
return -EINVAL;
}
@@ -486,7 +488,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
* covered by the bitmap, isn't marked as free.
*/
if (test_check_exists(cache, SZ_128M + SZ_256K, SZ_256K)) {
- test_msg("Invalid bitmap region marked as free\n");
+ test_err("invalid bitmap region marked as free");
return -EINVAL;
}
@@ -495,7 +497,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
* by the bitmap too, isn't marked as free either.
*/
if (test_check_exists(cache, SZ_128M, SZ_256K)) {
- test_msg("Invalid bitmap region marked as free\n");
+ test_err("invalid bitmap region marked as free");
return -EINVAL;
}
@@ -506,12 +508,12 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
*/
ret = btrfs_add_free_space(cache, SZ_128M, SZ_512K);
if (ret) {
- test_msg("Error adding free space: %d\n", ret);
+ test_err("error adding free space: %d", ret);
return ret;
}
/* Confirm the region is marked as free. */
if (!test_check_exists(cache, SZ_128M, SZ_512K)) {
- test_msg("Bitmap region not marked as free\n");
+ test_err("bitmap region not marked as free");
return -ENOENT;
}
@@ -531,7 +533,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
*/
ret = btrfs_add_free_space(cache, SZ_128M + SZ_16M, sectorsize);
if (ret) {
- test_msg("Error adding free space: %d\n", ret);
+ test_err("error adding free space: %d", ret);
return ret;
}
@@ -550,12 +552,12 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
*/
ret = btrfs_add_free_space(cache, SZ_128M - SZ_128K, SZ_128K);
if (ret) {
- test_msg("Error adding free space: %d\n", ret);
+ test_err("error adding free space: %d", ret);
return ret;
}
/* Confirm the region is marked as free. */
if (!test_check_exists(cache, SZ_128M - SZ_128K, SZ_128K)) {
- test_msg("Extent region not marked as free\n");
+ test_err("extent region not marked as free");
return -ENOENT;
}
@@ -583,12 +585,12 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
* allocate the whole free space at once.
*/
if (!test_check_exists(cache, SZ_128M - SZ_256K, SZ_1M)) {
- test_msg("Expected region not marked as free\n");
+ test_err("expected region not marked as free");
return -ENOENT;
}
if (cache->free_space_ctl->free_space != (SZ_1M + sectorsize)) {
- test_msg("Cache free space is not 1Mb + %u\n", sectorsize);
+ test_err("cache free space is not 1Mb + %u", sectorsize);
return -EINVAL;
}
@@ -596,7 +598,8 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
0, SZ_1M, 0,
&max_extent_size);
if (offset != (SZ_128M - SZ_256K)) {
- test_msg("Failed to allocate 1Mb from space cache, returned offset is: %llu\n",
+ test_err(
+ "failed to allocate 1Mb from space cache, returned offset is: %llu",
offset);
return -EINVAL;
}
@@ -610,7 +613,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
return ret;
if (cache->free_space_ctl->free_space != sectorsize) {
- test_msg("Cache free space is not %u\n", sectorsize);
+ test_err("cache free space is not %u", sectorsize);
return -EINVAL;
}
@@ -618,7 +621,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
0, sectorsize, 0,
&max_extent_size);
if (offset != (SZ_128M + SZ_16M)) {
- test_msg("Failed to allocate %u, returned offset : %llu\n",
+ test_err("failed to allocate %u, returned offset : %llu",
sectorsize, offset);
return -EINVAL;
}
@@ -640,14 +643,14 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
*/
ret = test_add_free_space_entry(cache, SZ_128M + SZ_128K, SZ_128K, 0);
if (ret) {
- test_msg("Couldn't add extent entry %d\n", ret);
+ test_err("couldn't add extent entry %d", ret);
return ret;
}
/* Bitmap entry covering free space range [0, 128Mb - 512Kb[ */
ret = test_add_free_space_entry(cache, 0, SZ_128M - SZ_512K, 1);
if (ret) {
- test_msg("Couldn't add bitmap entry %d\n", ret);
+ test_err("couldn't add bitmap entry %d", ret);
return ret;
}
@@ -664,17 +667,17 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
*/
ret = btrfs_remove_free_space(cache, 0, SZ_128M - 768 * SZ_1K);
if (ret) {
- test_msg("Failed to free part of bitmap space %d\n", ret);
+ test_err("failed to free part of bitmap space %d", ret);
return ret;
}
/* Confirm that only those 2 ranges are marked as free. */
if (!test_check_exists(cache, SZ_128M + SZ_128K, SZ_128K)) {
- test_msg("Free space range missing\n");
+ test_err("free space range missing");
return -ENOENT;
}
if (!test_check_exists(cache, SZ_128M - 768 * SZ_1K, SZ_256K)) {
- test_msg("Free space range missing\n");
+ test_err("free space range missing");
return -ENOENT;
}
@@ -683,7 +686,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
* as free anymore.
*/
if (test_check_exists(cache, 0, SZ_128M - 768 * SZ_1K)) {
- test_msg("Bitmap region not removed from space cache\n");
+ test_err("bitmap region not removed from space cache");
return -EINVAL;
}
@@ -692,7 +695,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
* covered by the bitmap, isn't marked as free.
*/
if (test_check_exists(cache, SZ_128M - SZ_512K, SZ_512K)) {
- test_msg("Invalid bitmap region marked as free\n");
+ test_err("invalid bitmap region marked as free");
return -EINVAL;
}
@@ -703,12 +706,12 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
*/
ret = btrfs_add_free_space(cache, SZ_128M - SZ_512K, SZ_512K);
if (ret) {
- test_msg("Error adding free space: %d\n", ret);
+ test_err("error adding free space: %d", ret);
return ret;
}
/* Confirm the region is marked as free. */
if (!test_check_exists(cache, SZ_128M - SZ_512K, SZ_512K)) {
- test_msg("Bitmap region not marked as free\n");
+ test_err("bitmap region not marked as free");
return -ENOENT;
}
@@ -728,7 +731,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
*/
ret = btrfs_add_free_space(cache, SZ_32M, 2 * sectorsize);
if (ret) {
- test_msg("Error adding free space: %d\n", ret);
+ test_err("error adding free space: %d", ret);
return ret;
}
@@ -739,12 +742,12 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
*/
ret = btrfs_add_free_space(cache, SZ_128M, SZ_128K);
if (ret) {
- test_msg("Error adding free space: %d\n", ret);
+ test_err("error adding free space: %d", ret);
return ret;
}
/* Confirm the region is marked as free. */
if (!test_check_exists(cache, SZ_128M, SZ_128K)) {
- test_msg("Extent region not marked as free\n");
+ test_err("extent region not marked as free");
return -ENOENT;
}
@@ -772,19 +775,20 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
* allocate the whole free space at once.
*/
if (!test_check_exists(cache, SZ_128M - 768 * SZ_1K, SZ_1M)) {
- test_msg("Expected region not marked as free\n");
+ test_err("expected region not marked as free");
return -ENOENT;
}
if (cache->free_space_ctl->free_space != (SZ_1M + 2 * sectorsize)) {
- test_msg("Cache free space is not 1Mb + %u\n", 2 * sectorsize);
+ test_err("cache free space is not 1Mb + %u", 2 * sectorsize);
return -EINVAL;
}
offset = btrfs_find_space_for_alloc(cache, 0, SZ_1M, 0,
&max_extent_size);
if (offset != (SZ_128M - 768 * SZ_1K)) {
- test_msg("Failed to allocate 1Mb from space cache, returned offset is: %llu\n",
+ test_err(
+ "failed to allocate 1Mb from space cache, returned offset is: %llu",
offset);
return -EINVAL;
}
@@ -798,7 +802,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
return ret;
if (cache->free_space_ctl->free_space != 2 * sectorsize) {
- test_msg("Cache free space is not %u\n", 2 * sectorsize);
+ test_err("cache free space is not %u", 2 * sectorsize);
return -EINVAL;
}
@@ -806,9 +810,8 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
0, 2 * sectorsize, 0,
&max_extent_size);
if (offset != SZ_32M) {
- test_msg("Failed to allocate %u, offset: %llu\n",
- 2 * sectorsize,
- offset);
+ test_err("failed to allocate %u, offset: %llu",
+ 2 * sectorsize, offset);
return -EINVAL;
}
@@ -829,7 +832,7 @@ int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize)
struct btrfs_root *root = NULL;
int ret = -ENOMEM;
- test_msg("Running btrfs free space cache tests\n");
+ test_msg("running btrfs free space cache tests");
fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
if (!fs_info)
return -ENOMEM;
@@ -843,7 +846,7 @@ int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize)
cache = btrfs_alloc_dummy_block_group(fs_info,
BITS_PER_BITMAP * sectorsize + PAGE_SIZE);
if (!cache) {
- test_msg("Couldn't run the tests\n");
+ test_err("couldn't run the tests");
btrfs_free_dummy_fs_info(fs_info);
return 0;
}
@@ -871,6 +874,6 @@ int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize)
btrfs_free_dummy_block_group(cache);
btrfs_free_dummy_root(root);
btrfs_free_dummy_fs_info(fs_info);
- test_msg("Free space cache tests finished\n");
+ test_msg("free space cache tests finished");
return ret;
}
diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c
index e1f9666..89346da 100644
--- a/fs/btrfs/tests/free-space-tree-tests.c
+++ b/fs/btrfs/tests/free-space-tree-tests.c
@@ -32,7 +32,7 @@ static int __check_free_space_extents(struct btrfs_trans_handle *trans,
info = search_free_space_info(trans, fs_info, cache, path, 0);
if (IS_ERR(info)) {
- test_msg("Could not find free space info\n");
+ test_err("could not find free space info");
ret = PTR_ERR(info);
goto out;
}
@@ -40,7 +40,7 @@ static int __check_free_space_extents(struct btrfs_trans_handle *trans,
extent_count = btrfs_free_space_extent_count(path->nodes[0], info);
if (extent_count != num_extents) {
- test_msg("Extent count is wrong\n");
+ test_err("extent count is wrong");
ret = -EINVAL;
goto out;
}
@@ -99,7 +99,7 @@ static int __check_free_space_extents(struct btrfs_trans_handle *trans,
btrfs_release_path(path);
return ret;
invalid:
- test_msg("Free space tree is invalid\n");
+ test_err("free space tree is invalid");
ret = -EINVAL;
goto out;
}
@@ -117,7 +117,7 @@ static int check_free_space_extents(struct btrfs_trans_handle *trans,
info = search_free_space_info(trans, fs_info, cache, path, 0);
if (IS_ERR(info)) {
- test_msg("Could not find free space info\n");
+ test_err("could not find free space info");
btrfs_release_path(path);
return PTR_ERR(info);
}
@@ -131,15 +131,15 @@ static int check_free_space_extents(struct btrfs_trans_handle *trans,
/* Flip it to the other format and check that for good measure. */
if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) {
- ret = convert_free_space_to_extents(trans, fs_info, cache, path);
+ ret = convert_free_space_to_extents(trans, cache, path);
if (ret) {
- test_msg("Could not convert to extents\n");
+ test_err("could not convert to extents");
return ret;
}
} else {
- ret = convert_free_space_to_bitmaps(trans, fs_info, cache, path);
+ ret = convert_free_space_to_bitmaps(trans, cache, path);
if (ret) {
- test_msg("Could not convert to bitmaps\n");
+ test_err("could not convert to bitmaps");
return ret;
}
}
@@ -170,11 +170,11 @@ static int test_remove_all(struct btrfs_trans_handle *trans,
const struct free_space_extent extents[] = {};
int ret;
- ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+ ret = __remove_from_free_space_tree(trans, cache, path,
cache->key.objectid,
cache->key.offset);
if (ret) {
- test_msg("Could not remove free space\n");
+ test_err("could not remove free space");
return ret;
}
@@ -194,10 +194,10 @@ static int test_remove_beginning(struct btrfs_trans_handle *trans,
};
int ret;
- ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+ ret = __remove_from_free_space_tree(trans, cache, path,
cache->key.objectid, alignment);
if (ret) {
- test_msg("Could not remove free space\n");
+ test_err("could not remove free space");
return ret;
}
@@ -217,12 +217,12 @@ static int test_remove_end(struct btrfs_trans_handle *trans,
};
int ret;
- ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+ ret = __remove_from_free_space_tree(trans, cache, path,
cache->key.objectid +
cache->key.offset - alignment,
alignment);
if (ret) {
- test_msg("Could not remove free space\n");
+ test_err("could not remove free space");
return ret;
}
@@ -243,11 +243,11 @@ static int test_remove_middle(struct btrfs_trans_handle *trans,
};
int ret;
- ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+ ret = __remove_from_free_space_tree(trans, cache, path,
cache->key.objectid + alignment,
alignment);
if (ret) {
- test_msg("Could not remove free space\n");
+ test_err("could not remove free space");
return ret;
}
@@ -266,26 +266,26 @@ static int test_merge_left(struct btrfs_trans_handle *trans,
};
int ret;
- ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+ ret = __remove_from_free_space_tree(trans, cache, path,
cache->key.objectid,
cache->key.offset);
if (ret) {
- test_msg("Could not remove free space\n");
+ test_err("could not remove free space");
return ret;
}
- ret = __add_to_free_space_tree(trans, fs_info, cache, path,
- cache->key.objectid, alignment);
+ ret = __add_to_free_space_tree(trans, cache, path, cache->key.objectid,
+ alignment);
if (ret) {
- test_msg("Could not add free space\n");
+ test_err("could not add free space");
return ret;
}
- ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+ ret = __add_to_free_space_tree(trans, cache, path,
cache->key.objectid + alignment,
alignment);
if (ret) {
- test_msg("Could not add free space\n");
+ test_err("could not add free space");
return ret;
}
@@ -304,27 +304,27 @@ static int test_merge_right(struct btrfs_trans_handle *trans,
};
int ret;
- ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+ ret = __remove_from_free_space_tree(trans, cache, path,
cache->key.objectid,
cache->key.offset);
if (ret) {
- test_msg("Could not remove free space\n");
+ test_err("could not remove free space");
return ret;
}
- ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+ ret = __add_to_free_space_tree(trans, cache, path,
cache->key.objectid + 2 * alignment,
alignment);
if (ret) {
- test_msg("Could not add free space\n");
+ test_err("could not add free space");
return ret;
}
- ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+ ret = __add_to_free_space_tree(trans, cache, path,
cache->key.objectid + alignment,
alignment);
if (ret) {
- test_msg("Could not add free space\n");
+ test_err("could not add free space");
return ret;
}
@@ -343,34 +343,34 @@ static int test_merge_both(struct btrfs_trans_handle *trans,
};
int ret;
- ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+ ret = __remove_from_free_space_tree(trans, cache, path,
cache->key.objectid,
cache->key.offset);
if (ret) {
- test_msg("Could not remove free space\n");
+ test_err("could not remove free space");
return ret;
}
- ret = __add_to_free_space_tree(trans, fs_info, cache, path,
- cache->key.objectid, alignment);
+ ret = __add_to_free_space_tree(trans, cache, path, cache->key.objectid,
+ alignment);
if (ret) {
- test_msg("Could not add free space\n");
+ test_err("could not add free space");
return ret;
}
- ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+ ret = __add_to_free_space_tree(trans, cache, path,
cache->key.objectid + 2 * alignment,
alignment);
if (ret) {
- test_msg("Could not add free space\n");
+ test_err("could not add free space");
return ret;
}
- ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+ ret = __add_to_free_space_tree(trans, cache, path,
cache->key.objectid + alignment,
alignment);
if (ret) {
- test_msg("Could not add free space\n");
+ test_err("could not add free space");
return ret;
}
@@ -391,34 +391,34 @@ static int test_merge_none(struct btrfs_trans_handle *trans,
};
int ret;
- ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
+ ret = __remove_from_free_space_tree(trans, cache, path,
cache->key.objectid,
cache->key.offset);
if (ret) {
- test_msg("Could not remove free space\n");
+ test_err("could not remove free space");
return ret;
}
- ret = __add_to_free_space_tree(trans, fs_info, cache, path,
- cache->key.objectid, alignment);
+ ret = __add_to_free_space_tree(trans, cache, path, cache->key.objectid,
+ alignment);
if (ret) {
- test_msg("Could not add free space\n");
+ test_err("could not add free space");
return ret;
}
- ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+ ret = __add_to_free_space_tree(trans, cache, path,
cache->key.objectid + 4 * alignment,
alignment);
if (ret) {
- test_msg("Could not add free space\n");
+ test_err("could not add free space");
return ret;
}
- ret = __add_to_free_space_tree(trans, fs_info, cache, path,
+ ret = __add_to_free_space_tree(trans, cache, path,
cache->key.objectid + 2 * alignment,
alignment);
if (ret) {
- test_msg("Could not add free space\n");
+ test_err("could not add free space");
return ret;
}
@@ -444,14 +444,14 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize,
fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
if (!fs_info) {
- test_msg("Couldn't allocate dummy fs info\n");
+ test_err("couldn't allocate dummy fs info");
ret = -ENOMEM;
goto out;
}
root = btrfs_alloc_dummy_root(fs_info);
if (IS_ERR(root)) {
- test_msg("Couldn't allocate dummy root\n");
+ test_err("couldn't allocate dummy root");
ret = PTR_ERR(root);
goto out;
}
@@ -463,7 +463,7 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize,
root->node = alloc_test_extent_buffer(root->fs_info, nodesize);
if (!root->node) {
- test_msg("Couldn't allocate dummy buffer\n");
+ test_err("couldn't allocate dummy buffer");
ret = -ENOMEM;
goto out;
}
@@ -473,7 +473,7 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize,
cache = btrfs_alloc_dummy_block_group(fs_info, 8 * alignment);
if (!cache) {
- test_msg("Couldn't allocate dummy block group cache\n");
+ test_err("couldn't allocate dummy block group cache");
ret = -ENOMEM;
goto out;
}
@@ -482,26 +482,25 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize,
cache->needs_free_space = 1;
cache->fs_info = root->fs_info;
- btrfs_init_dummy_trans(&trans);
+ btrfs_init_dummy_trans(&trans, root->fs_info);
path = btrfs_alloc_path();
if (!path) {
- test_msg("Couldn't allocate path\n");
+ test_err("couldn't allocate path");
ret = -ENOMEM;
goto out;
}
- ret = add_block_group_free_space(&trans, root->fs_info, cache);
+ ret = add_block_group_free_space(&trans, cache);
if (ret) {
- test_msg("Could not add block group free space\n");
+ test_err("could not add block group free space");
goto out;
}
if (bitmaps) {
- ret = convert_free_space_to_bitmaps(&trans, root->fs_info,
- cache, path);
+ ret = convert_free_space_to_bitmaps(&trans, cache, path);
if (ret) {
- test_msg("Could not convert block group to bitmaps\n");
+ test_err("could not convert block group to bitmaps");
goto out;
}
}
@@ -510,14 +509,14 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize,
if (ret)
goto out;
- ret = remove_block_group_free_space(&trans, root->fs_info, cache);
+ ret = remove_block_group_free_space(&trans, cache);
if (ret) {
- test_msg("Could not remove block group free space\n");
+ test_err("could not remove block group free space");
goto out;
}
if (btrfs_header_nritems(root->node) != 0) {
- test_msg("Free space tree has leftover items\n");
+ test_err("free space tree has leftover items");
ret = -EINVAL;
goto out;
}
@@ -539,14 +538,16 @@ static int run_test_both_formats(test_func_t test_func, u32 sectorsize,
ret = run_test(test_func, 0, sectorsize, nodesize, alignment);
if (ret) {
- test_msg("%pf failed with extents, sectorsize=%u, nodesize=%u, alignment=%u\n",
+ test_err(
+ "%pf failed with extents, sectorsize=%u, nodesize=%u, alignment=%u",
test_func, sectorsize, nodesize, alignment);
test_ret = ret;
}
ret = run_test(test_func, 1, sectorsize, nodesize, alignment);
if (ret) {
- test_msg("%pf failed with bitmaps, sectorsize=%u, nodesize=%u, alignment=%u\n",
+ test_err(
+ "%pf failed with bitmaps, sectorsize=%u, nodesize=%u, alignment=%u",
test_func, sectorsize, nodesize, alignment);
test_ret = ret;
}
@@ -577,7 +578,7 @@ int btrfs_test_free_space_tree(u32 sectorsize, u32 nodesize)
*/
bitmap_alignment = BTRFS_FREE_SPACE_BITMAP_BITS * PAGE_SIZE;
- test_msg("Running free space tree tests\n");
+ test_msg("running free space tree tests");
for (i = 0; i < ARRAY_SIZE(tests); i++) {
int ret;
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index e0ba799..64043f0 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -228,7 +228,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
inode = btrfs_new_test_inode();
if (!inode) {
- test_msg("Couldn't allocate inode\n");
+ test_err("couldn't allocate inode");
return ret;
}
@@ -238,19 +238,19 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
if (!fs_info) {
- test_msg("Couldn't allocate dummy fs info\n");
+ test_err("couldn't allocate dummy fs info");
goto out;
}
root = btrfs_alloc_dummy_root(fs_info);
if (IS_ERR(root)) {
- test_msg("Couldn't allocate root\n");
+ test_err("couldn't allocate root");
goto out;
}
root->node = alloc_dummy_extent_buffer(fs_info, nodesize);
if (!root->node) {
- test_msg("Couldn't allocate dummy buffer\n");
+ test_err("couldn't allocate dummy buffer");
goto out;
}
@@ -268,11 +268,11 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, sectorsize, 0);
if (IS_ERR(em)) {
em = NULL;
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start != EXTENT_MAP_HOLE) {
- test_msg("Expected a hole, got %llu\n", em->block_start);
+ test_err("expected a hole, got %llu", em->block_start);
goto out;
}
free_extent_map(em);
@@ -287,20 +287,21 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, (u64)-1, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start != EXTENT_MAP_HOLE) {
- test_msg("Expected a hole, got %llu\n", em->block_start);
+ test_err("expected a hole, got %llu", em->block_start);
goto out;
}
if (em->start != 0 || em->len != 5) {
- test_msg("Unexpected extent wanted start 0 len 5, got start "
- "%llu len %llu\n", em->start, em->len);
+ test_err(
+ "unexpected extent wanted start 0 len 5, got start %llu len %llu",
+ em->start, em->len);
goto out;
}
if (em->flags != 0) {
- test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+ test_err("unexpected flags set, want 0 have %lu", em->flags);
goto out;
}
offset = em->start + em->len;
@@ -308,21 +309,22 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start != EXTENT_MAP_INLINE) {
- test_msg("Expected an inline, got %llu\n", em->block_start);
+ test_err("expected an inline, got %llu", em->block_start);
goto out;
}
if (em->start != offset || em->len != (sectorsize - 5)) {
- test_msg("Unexpected extent wanted start %llu len 1, got start "
- "%llu len %llu\n", offset, em->start, em->len);
+ test_err(
+ "unexpected extent wanted start %llu len 1, got start %llu len %llu",
+ offset, em->start, em->len);
goto out;
}
if (em->flags != 0) {
- test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+ test_err("unexpected flags set, want 0 have %lu", em->flags);
goto out;
}
/*
@@ -335,20 +337,21 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start != EXTENT_MAP_HOLE) {
- test_msg("Expected a hole, got %llu\n", em->block_start);
+ test_err("expected a hole, got %llu", em->block_start);
goto out;
}
if (em->start != offset || em->len != 4) {
- test_msg("Unexpected extent wanted start %llu len 4, got start "
- "%llu len %llu\n", offset, em->start, em->len);
+ test_err(
+ "unexpected extent wanted start %llu len 4, got start %llu len %llu",
+ offset, em->start, em->len);
goto out;
}
if (em->flags != 0) {
- test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+ test_err("unexpected flags set, want 0 have %lu", em->flags);
goto out;
}
offset = em->start + em->len;
@@ -357,24 +360,25 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
/* Regular extent */
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
- test_msg("Expected a real extent, got %llu\n", em->block_start);
+ test_err("expected a real extent, got %llu", em->block_start);
goto out;
}
if (em->start != offset || em->len != sectorsize - 1) {
- test_msg("Unexpected extent wanted start %llu len 4095, got "
- "start %llu len %llu\n", offset, em->start, em->len);
+ test_err(
+ "unexpected extent wanted start %llu len 4095, got start %llu len %llu",
+ offset, em->start, em->len);
goto out;
}
if (em->flags != 0) {
- test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+ test_err("unexpected flags set, want 0 have %lu", em->flags);
goto out;
}
if (em->orig_start != em->start) {
- test_msg("Wrong orig offset, want %llu, have %llu\n", em->start,
+ test_err("wrong orig offset, want %llu, have %llu", em->start,
em->orig_start);
goto out;
}
@@ -384,25 +388,25 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
/* The next 3 are split extents */
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
- test_msg("Expected a real extent, got %llu\n", em->block_start);
+ test_err("expected a real extent, got %llu", em->block_start);
goto out;
}
if (em->start != offset || em->len != sectorsize) {
- test_msg("Unexpected extent start %llu len %u, "
- "got start %llu len %llu\n",
+ test_err(
+ "unexpected extent start %llu len %u, got start %llu len %llu",
offset, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != 0) {
- test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+ test_err("unexpected flags set, want 0 have %lu", em->flags);
goto out;
}
if (em->orig_start != em->start) {
- test_msg("Wrong orig offset, want %llu, have %llu\n", em->start,
+ test_err("wrong orig offset, want %llu, have %llu", em->start,
em->orig_start);
goto out;
}
@@ -413,21 +417,21 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start != EXTENT_MAP_HOLE) {
- test_msg("Expected a hole, got %llu\n", em->block_start);
+ test_err("expected a hole, got %llu", em->block_start);
goto out;
}
if (em->start != offset || em->len != sectorsize) {
- test_msg("Unexpected extent wanted start %llu len %u, "
- "got start %llu len %llu\n",
+ test_err(
+ "unexpected extent wanted start %llu len %u, got start %llu len %llu",
offset, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != 0) {
- test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+ test_err("unexpected flags set, want 0 have %lu", em->flags);
goto out;
}
offset = em->start + em->len;
@@ -435,31 +439,31 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
- test_msg("Expected a real extent, got %llu\n", em->block_start);
+ test_err("expected a real extent, got %llu", em->block_start);
goto out;
}
if (em->start != offset || em->len != 2 * sectorsize) {
- test_msg("Unexpected extent wanted start %llu len %u, "
- "got start %llu len %llu\n",
+ test_err(
+ "unexpected extent wanted start %llu len %u, got start %llu len %llu",
offset, 2 * sectorsize, em->start, em->len);
goto out;
}
if (em->flags != 0) {
- test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+ test_err("unexpected flags set, want 0 have %lu", em->flags);
goto out;
}
if (em->orig_start != orig_start) {
- test_msg("Wrong orig offset, want %llu, have %llu\n",
+ test_err("wrong orig offset, want %llu, have %llu",
orig_start, em->orig_start);
goto out;
}
disk_bytenr += (em->start - orig_start);
if (em->block_start != disk_bytenr) {
- test_msg("Wrong block start, want %llu, have %llu\n",
+ test_err("wrong block start, want %llu, have %llu",
disk_bytenr, em->block_start);
goto out;
}
@@ -469,26 +473,26 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
/* Prealloc extent */
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
- test_msg("Expected a real extent, got %llu\n", em->block_start);
+ test_err("expected a real extent, got %llu", em->block_start);
goto out;
}
if (em->start != offset || em->len != sectorsize) {
- test_msg("Unexpected extent wanted start %llu len %u, "
- "got start %llu len %llu\n",
+ test_err(
+ "unexpected extent wanted start %llu len %u, got start %llu len %llu",
offset, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != prealloc_only) {
- test_msg("Unexpected flags set, want %lu have %lu\n",
+ test_err("unexpected flags set, want %lu have %lu",
prealloc_only, em->flags);
goto out;
}
if (em->orig_start != em->start) {
- test_msg("Wrong orig offset, want %llu, have %llu\n", em->start,
+ test_err("wrong orig offset, want %llu, have %llu", em->start,
em->orig_start);
goto out;
}
@@ -498,26 +502,26 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
/* The next 3 are a half written prealloc extent */
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
- test_msg("Expected a real extent, got %llu\n", em->block_start);
+ test_err("expected a real extent, got %llu", em->block_start);
goto out;
}
if (em->start != offset || em->len != sectorsize) {
- test_msg("Unexpected extent wanted start %llu len %u, "
- "got start %llu len %llu\n",
+ test_err(
+ "unexpected extent wanted start %llu len %u, got start %llu len %llu",
offset, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != prealloc_only) {
- test_msg("Unexpected flags set, want %lu have %lu\n",
+ test_err("unexpected flags set, want %lu have %lu",
prealloc_only, em->flags);
goto out;
}
if (em->orig_start != em->start) {
- test_msg("Wrong orig offset, want %llu, have %llu\n", em->start,
+ test_err("wrong orig offset, want %llu, have %llu", em->start,
em->orig_start);
goto out;
}
@@ -528,30 +532,30 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start >= EXTENT_MAP_HOLE) {
- test_msg("Expected a real extent, got %llu\n", em->block_start);
+ test_err("expected a real extent, got %llu", em->block_start);
goto out;
}
if (em->start != offset || em->len != sectorsize) {
- test_msg("Unexpected extent wanted start %llu len %u, "
- "got start %llu len %llu\n",
+ test_err(
+ "unexpected extent wanted start %llu len %u, got start %llu len %llu",
offset, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != 0) {
- test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+ test_err("unexpected flags set, want 0 have %lu", em->flags);
goto out;
}
if (em->orig_start != orig_start) {
- test_msg("Unexpected orig offset, wanted %llu, have %llu\n",
+ test_err("unexpected orig offset, wanted %llu, have %llu",
orig_start, em->orig_start);
goto out;
}
if (em->block_start != (disk_bytenr + (em->start - em->orig_start))) {
- test_msg("Unexpected block start, wanted %llu, have %llu\n",
+ test_err("unexpected block start, wanted %llu, have %llu",
disk_bytenr + (em->start - em->orig_start),
em->block_start);
goto out;
@@ -561,31 +565,31 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
- test_msg("Expected a real extent, got %llu\n", em->block_start);
+ test_err("expected a real extent, got %llu", em->block_start);
goto out;
}
if (em->start != offset || em->len != 2 * sectorsize) {
- test_msg("Unexpected extent wanted start %llu len %u, "
- "got start %llu len %llu\n",
+ test_err(
+ "unexpected extent wanted start %llu len %u, got start %llu len %llu",
offset, 2 * sectorsize, em->start, em->len);
goto out;
}
if (em->flags != prealloc_only) {
- test_msg("Unexpected flags set, want %lu have %lu\n",
+ test_err("unexpected flags set, want %lu have %lu",
prealloc_only, em->flags);
goto out;
}
if (em->orig_start != orig_start) {
- test_msg("Wrong orig offset, want %llu, have %llu\n", orig_start,
+ test_err("wrong orig offset, want %llu, have %llu", orig_start,
em->orig_start);
goto out;
}
if (em->block_start != (disk_bytenr + (em->start - em->orig_start))) {
- test_msg("Unexpected block start, wanted %llu, have %llu\n",
+ test_err("unexpected block start, wanted %llu, have %llu",
disk_bytenr + (em->start - em->orig_start),
em->block_start);
goto out;
@@ -596,31 +600,31 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
/* Now for the compressed extent */
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
- test_msg("Expected a real extent, got %llu\n", em->block_start);
+ test_err("expected a real extent, got %llu", em->block_start);
goto out;
}
if (em->start != offset || em->len != 2 * sectorsize) {
- test_msg("Unexpected extent wanted start %llu len %u,"
- "got start %llu len %llu\n",
+ test_err(
+ "unexpected extent wanted start %llu len %u, got start %llu len %llu",
offset, 2 * sectorsize, em->start, em->len);
goto out;
}
if (em->flags != compressed_only) {
- test_msg("Unexpected flags set, want %lu have %lu\n",
+ test_err("unexpected flags set, want %lu have %lu",
compressed_only, em->flags);
goto out;
}
if (em->orig_start != em->start) {
- test_msg("Wrong orig offset, want %llu, have %llu\n",
+ test_err("wrong orig offset, want %llu, have %llu",
em->start, em->orig_start);
goto out;
}
if (em->compress_type != BTRFS_COMPRESS_ZLIB) {
- test_msg("Unexpected compress type, wanted %d, got %d\n",
+ test_err("unexpected compress type, wanted %d, got %d",
BTRFS_COMPRESS_ZLIB, em->compress_type);
goto out;
}
@@ -630,31 +634,31 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
/* Split compressed extent */
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
- test_msg("Expected a real extent, got %llu\n", em->block_start);
+ test_err("expected a real extent, got %llu", em->block_start);
goto out;
}
if (em->start != offset || em->len != sectorsize) {
- test_msg("Unexpected extent wanted start %llu len %u,"
- "got start %llu len %llu\n",
+ test_err(
+ "unexpected extent wanted start %llu len %u, got start %llu len %llu",
offset, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != compressed_only) {
- test_msg("Unexpected flags set, want %lu have %lu\n",
+ test_err("unexpected flags set, want %lu have %lu",
compressed_only, em->flags);
goto out;
}
if (em->orig_start != em->start) {
- test_msg("Wrong orig offset, want %llu, have %llu\n",
+ test_err("wrong orig offset, want %llu, have %llu",
em->start, em->orig_start);
goto out;
}
if (em->compress_type != BTRFS_COMPRESS_ZLIB) {
- test_msg("Unexpected compress type, wanted %d, got %d\n",
+ test_err("unexpected compress type, wanted %d, got %d",
BTRFS_COMPRESS_ZLIB, em->compress_type);
goto out;
}
@@ -665,25 +669,25 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
- test_msg("Expected a real extent, got %llu\n", em->block_start);
+ test_err("expected a real extent, got %llu", em->block_start);
goto out;
}
if (em->start != offset || em->len != sectorsize) {
- test_msg("Unexpected extent wanted start %llu len %u, "
- "got start %llu len %llu\n",
+ test_err(
+ "unexpected extent wanted start %llu len %u, got start %llu len %llu",
offset, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != 0) {
- test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+ test_err("unexpected flags set, want 0 have %lu", em->flags);
goto out;
}
if (em->orig_start != em->start) {
- test_msg("Wrong orig offset, want %llu, have %llu\n", em->start,
+ test_err("wrong orig offset, want %llu, have %llu", em->start,
em->orig_start);
goto out;
}
@@ -692,32 +696,32 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start != disk_bytenr) {
- test_msg("Block start does not match, want %llu got %llu\n",
+ test_err("block start does not match, want %llu got %llu",
disk_bytenr, em->block_start);
goto out;
}
if (em->start != offset || em->len != 2 * sectorsize) {
- test_msg("Unexpected extent wanted start %llu len %u, "
- "got start %llu len %llu\n",
+ test_err(
+ "unexpected extent wanted start %llu len %u, got start %llu len %llu",
offset, 2 * sectorsize, em->start, em->len);
goto out;
}
if (em->flags != compressed_only) {
- test_msg("Unexpected flags set, want %lu have %lu\n",
+ test_err("unexpected flags set, want %lu have %lu",
compressed_only, em->flags);
goto out;
}
if (em->orig_start != orig_start) {
- test_msg("Wrong orig offset, want %llu, have %llu\n",
+ test_err("wrong orig offset, want %llu, have %llu",
em->start, orig_start);
goto out;
}
if (em->compress_type != BTRFS_COMPRESS_ZLIB) {
- test_msg("Unexpected compress type, wanted %d, got %d\n",
+ test_err("unexpected compress type, wanted %d, got %d",
BTRFS_COMPRESS_ZLIB, em->compress_type);
goto out;
}
@@ -728,25 +732,25 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset + 6,
sectorsize, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
- test_msg("Expected a real extent, got %llu\n", em->block_start);
+ test_err("expected a real extent, got %llu", em->block_start);
goto out;
}
if (em->start != offset || em->len != sectorsize) {
- test_msg("Unexpected extent wanted start %llu len %u, "
- "got start %llu len %llu\n",
+ test_err(
+ "unexpected extent wanted start %llu len %u, got start %llu len %llu",
offset, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != 0) {
- test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+ test_err("unexpected flags set, want 0 have %lu", em->flags);
goto out;
}
if (em->orig_start != em->start) {
- test_msg("Wrong orig offset, want %llu, have %llu\n", em->start,
+ test_err("wrong orig offset, want %llu, have %llu", em->start,
em->orig_start);
goto out;
}
@@ -755,11 +759,11 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, SZ_4M, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start != EXTENT_MAP_HOLE) {
- test_msg("Expected a hole extent, got %llu\n", em->block_start);
+ test_err("expected a hole extent, got %llu", em->block_start);
goto out;
}
/*
@@ -768,18 +772,18 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
* test.
*/
if (em->start != offset || em->len != 3 * sectorsize) {
- test_msg("Unexpected extent wanted start %llu len %u, "
- "got start %llu len %llu\n",
+ test_err(
+ "unexpected extent wanted start %llu len %u, got start %llu len %llu",
offset, 3 * sectorsize, em->start, em->len);
goto out;
}
if (em->flags != vacancy_only) {
- test_msg("Unexpected flags set, want %lu have %lu\n",
+ test_err("unexpected flags set, want %lu have %lu",
vacancy_only, em->flags);
goto out;
}
if (em->orig_start != em->start) {
- test_msg("Wrong orig offset, want %llu, have %llu\n", em->start,
+ test_err("wrong orig offset, want %llu, have %llu", em->start,
em->orig_start);
goto out;
}
@@ -788,25 +792,25 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
- test_msg("Expected a real extent, got %llu\n", em->block_start);
+ test_err("expected a real extent, got %llu", em->block_start);
goto out;
}
if (em->start != offset || em->len != sectorsize) {
- test_msg("Unexpected extent wanted start %llu len %u,"
- "got start %llu len %llu\n",
+ test_err(
+ "unexpected extent wanted start %llu len %u, got start %llu len %llu",
offset, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != 0) {
- test_msg("Unexpected flags set, want 0 have %lu\n", em->flags);
+ test_err("unexpected flags set, want 0 have %lu", em->flags);
goto out;
}
if (em->orig_start != em->start) {
- test_msg("Wrong orig offset, want %llu, have %llu\n", em->start,
+ test_err("wrong orig offset, want %llu, have %llu", em->start,
em->orig_start);
goto out;
}
@@ -830,7 +834,7 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
inode = btrfs_new_test_inode();
if (!inode) {
- test_msg("Couldn't allocate inode\n");
+ test_err("couldn't allocate inode");
return ret;
}
@@ -840,19 +844,19 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
if (!fs_info) {
- test_msg("Couldn't allocate dummy fs info\n");
+ test_err("couldn't allocate dummy fs info");
goto out;
}
root = btrfs_alloc_dummy_root(fs_info);
if (IS_ERR(root)) {
- test_msg("Couldn't allocate root\n");
+ test_err("couldn't allocate root");
goto out;
}
root->node = alloc_dummy_extent_buffer(fs_info, nodesize);
if (!root->node) {
- test_msg("Couldn't allocate dummy buffer\n");
+ test_err("couldn't allocate dummy buffer");
goto out;
}
@@ -871,21 +875,21 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
sectorsize, BTRFS_FILE_EXTENT_REG, 0, 1);
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, 2 * sectorsize, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start != EXTENT_MAP_HOLE) {
- test_msg("Expected a hole, got %llu\n", em->block_start);
+ test_err("expected a hole, got %llu", em->block_start);
goto out;
}
if (em->start != 0 || em->len != sectorsize) {
- test_msg("Unexpected extent wanted start 0 len %u, "
- "got start %llu len %llu\n",
+ test_err(
+ "unexpected extent wanted start 0 len %u, got start %llu len %llu",
sectorsize, em->start, em->len);
goto out;
}
if (em->flags != vacancy_only) {
- test_msg("Wrong flags, wanted %lu, have %lu\n", vacancy_only,
+ test_err("wrong flags, wanted %lu, have %lu", vacancy_only,
em->flags);
goto out;
}
@@ -894,21 +898,21 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, sectorsize,
2 * sectorsize, 0);
if (IS_ERR(em)) {
- test_msg("Got an error when we shouldn't have\n");
+ test_err("got an error when we shouldn't have");
goto out;
}
if (em->block_start != sectorsize) {
- test_msg("Expected a real extent, got %llu\n", em->block_start);
+ test_err("expected a real extent, got %llu", em->block_start);
goto out;
}
if (em->start != sectorsize || em->len != sectorsize) {
- test_msg("Unexpected extent wanted start %u len %u, "
- "got start %llu len %llu\n",
+ test_err(
+ "unexpected extent wanted start %u len %u, got start %llu len %llu",
sectorsize, sectorsize, em->start, em->len);
goto out;
}
if (em->flags != 0) {
- test_msg("Unexpected flags set, wanted 0 got %lu\n",
+ test_err("unexpected flags set, wanted 0 got %lu",
em->flags);
goto out;
}
@@ -931,19 +935,19 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
inode = btrfs_new_test_inode();
if (!inode) {
- test_msg("Couldn't allocate inode\n");
+ test_err("couldn't allocate inode");
return ret;
}
fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
if (!fs_info) {
- test_msg("Couldn't allocate dummy fs info\n");
+ test_err("couldn't allocate dummy fs info");
goto out;
}
root = btrfs_alloc_dummy_root(fs_info);
if (IS_ERR(root)) {
- test_msg("Couldn't allocate root\n");
+ test_err("couldn't allocate root");
goto out;
}
@@ -954,12 +958,12 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
ret = btrfs_set_extent_delalloc(inode, 0, BTRFS_MAX_EXTENT_SIZE - 1, 0,
NULL, 0);
if (ret) {
- test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+ test_err("btrfs_set_extent_delalloc returned %d", ret);
goto out;
}
if (BTRFS_I(inode)->outstanding_extents != 1) {
ret = -EINVAL;
- test_msg("Miscount, wanted 1, got %u\n",
+ test_err("miscount, wanted 1, got %u",
BTRFS_I(inode)->outstanding_extents);
goto out;
}
@@ -969,12 +973,12 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
BTRFS_MAX_EXTENT_SIZE + sectorsize - 1,
0, NULL, 0);
if (ret) {
- test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+ test_err("btrfs_set_extent_delalloc returned %d", ret);
goto out;
}
if (BTRFS_I(inode)->outstanding_extents != 2) {
ret = -EINVAL;
- test_msg("Miscount, wanted 2, got %u\n",
+ test_err("miscount, wanted 2, got %u",
BTRFS_I(inode)->outstanding_extents);
goto out;
}
@@ -986,12 +990,12 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
EXTENT_DELALLOC | EXTENT_DIRTY |
EXTENT_UPTODATE, 0, 0, NULL);
if (ret) {
- test_msg("clear_extent_bit returned %d\n", ret);
+ test_err("clear_extent_bit returned %d", ret);
goto out;
}
if (BTRFS_I(inode)->outstanding_extents != 2) {
ret = -EINVAL;
- test_msg("Miscount, wanted 2, got %u\n",
+ test_err("miscount, wanted 2, got %u",
BTRFS_I(inode)->outstanding_extents);
goto out;
}
@@ -1002,12 +1006,12 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
+ sectorsize - 1,
0, NULL, 0);
if (ret) {
- test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+ test_err("btrfs_set_extent_delalloc returned %d", ret);
goto out;
}
if (BTRFS_I(inode)->outstanding_extents != 2) {
ret = -EINVAL;
- test_msg("Miscount, wanted 2, got %u\n",
+ test_err("miscount, wanted 2, got %u",
BTRFS_I(inode)->outstanding_extents);
goto out;
}
@@ -1020,12 +1024,12 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
(BTRFS_MAX_EXTENT_SIZE << 1) + 3 * sectorsize - 1,
0, NULL, 0);
if (ret) {
- test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+ test_err("btrfs_set_extent_delalloc returned %d", ret);
goto out;
}
if (BTRFS_I(inode)->outstanding_extents != 4) {
ret = -EINVAL;
- test_msg("Miscount, wanted 4, got %u\n",
+ test_err("miscount, wanted 4, got %u",
BTRFS_I(inode)->outstanding_extents);
goto out;
}
@@ -1037,12 +1041,12 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
BTRFS_MAX_EXTENT_SIZE + sectorsize,
BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, 0, NULL, 0);
if (ret) {
- test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+ test_err("btrfs_set_extent_delalloc returned %d", ret);
goto out;
}
if (BTRFS_I(inode)->outstanding_extents != 3) {
ret = -EINVAL;
- test_msg("Miscount, wanted 3, got %u\n",
+ test_err("miscount, wanted 3, got %u",
BTRFS_I(inode)->outstanding_extents);
goto out;
}
@@ -1054,12 +1058,12 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_UPTODATE, 0, 0, NULL);
if (ret) {
- test_msg("clear_extent_bit returned %d\n", ret);
+ test_err("clear_extent_bit returned %d", ret);
goto out;
}
if (BTRFS_I(inode)->outstanding_extents != 4) {
ret = -EINVAL;
- test_msg("Miscount, wanted 4, got %u\n",
+ test_err("miscount, wanted 4, got %u",
BTRFS_I(inode)->outstanding_extents);
goto out;
}
@@ -1072,12 +1076,12 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
BTRFS_MAX_EXTENT_SIZE + sectorsize,
BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, 0, NULL, 0);
if (ret) {
- test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+ test_err("btrfs_set_extent_delalloc returned %d", ret);
goto out;
}
if (BTRFS_I(inode)->outstanding_extents != 3) {
ret = -EINVAL;
- test_msg("Miscount, wanted 3, got %u\n",
+ test_err("miscount, wanted 3, got %u",
BTRFS_I(inode)->outstanding_extents);
goto out;
}
@@ -1087,12 +1091,12 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_UPTODATE, 0, 0, NULL);
if (ret) {
- test_msg("clear_extent_bit returned %d\n", ret);
+ test_err("clear_extent_bit returned %d", ret);
goto out;
}
if (BTRFS_I(inode)->outstanding_extents) {
ret = -EINVAL;
- test_msg("Miscount, wanted 0, got %u\n",
+ test_err("miscount, wanted 0, got %u",
BTRFS_I(inode)->outstanding_extents);
goto out;
}
@@ -1115,14 +1119,14 @@ int btrfs_test_inodes(u32 sectorsize, u32 nodesize)
set_bit(EXTENT_FLAG_COMPRESSED, &compressed_only);
set_bit(EXTENT_FLAG_PREALLOC, &prealloc_only);
- test_msg("Running btrfs_get_extent tests\n");
+ test_msg("running btrfs_get_extent tests");
ret = test_btrfs_get_extent(sectorsize, nodesize);
if (ret)
return ret;
- test_msg("Running hole first btrfs_get_extent test\n");
+ test_msg("running hole first btrfs_get_extent test");
ret = test_hole_first(sectorsize, nodesize);
if (ret)
return ret;
- test_msg("Running outstanding_extents tests\n");
+ test_msg("running outstanding_extents tests");
return test_extent_accounting(sectorsize, nodesize);
}
diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c
index 39b9578..ace94db 100644
--- a/fs/btrfs/tests/qgroup-tests.c
+++ b/fs/btrfs/tests/qgroup-tests.c
@@ -24,7 +24,7 @@ static int insert_normal_tree_ref(struct btrfs_root *root, u64 bytenr,
u32 size = sizeof(*item) + sizeof(*iref) + sizeof(*block_info);
int ret;
- btrfs_init_dummy_trans(&trans);
+ btrfs_init_dummy_trans(&trans, NULL);
ins.objectid = bytenr;
ins.type = BTRFS_EXTENT_ITEM_KEY;
@@ -32,14 +32,14 @@ static int insert_normal_tree_ref(struct btrfs_root *root, u64 bytenr,
path = btrfs_alloc_path();
if (!path) {
- test_msg("Couldn't allocate path\n");
+ test_err("couldn't allocate path");
return -ENOMEM;
}
path->leave_spinning = 1;
ret = btrfs_insert_empty_item(&trans, root, path, &ins, size);
if (ret) {
- test_msg("Couldn't insert ref %d\n", ret);
+ test_err("couldn't insert ref %d", ret);
btrfs_free_path(path);
return ret;
}
@@ -74,7 +74,7 @@ static int add_tree_ref(struct btrfs_root *root, u64 bytenr, u64 num_bytes,
u64 refs;
int ret;
- btrfs_init_dummy_trans(&trans);
+ btrfs_init_dummy_trans(&trans, NULL);
key.objectid = bytenr;
key.type = BTRFS_EXTENT_ITEM_KEY;
@@ -82,14 +82,14 @@ static int add_tree_ref(struct btrfs_root *root, u64 bytenr, u64 num_bytes,
path = btrfs_alloc_path();
if (!path) {
- test_msg("Couldn't allocate path\n");
+ test_err("couldn't allocate path");
return -ENOMEM;
}
path->leave_spinning = 1;
ret = btrfs_search_slot(&trans, root, &key, path, 0, 1);
if (ret) {
- test_msg("Couldn't find extent ref\n");
+ test_err("couldn't find extent ref");
btrfs_free_path(path);
return ret;
}
@@ -111,7 +111,7 @@ static int add_tree_ref(struct btrfs_root *root, u64 bytenr, u64 num_bytes,
ret = btrfs_insert_empty_item(&trans, root, path, &key, 0);
if (ret)
- test_msg("Failed to insert backref\n");
+ test_err("failed to insert backref");
btrfs_free_path(path);
return ret;
}
@@ -124,7 +124,7 @@ static int remove_extent_item(struct btrfs_root *root, u64 bytenr,
struct btrfs_path *path;
int ret;
- btrfs_init_dummy_trans(&trans);
+ btrfs_init_dummy_trans(&trans, NULL);
key.objectid = bytenr;
key.type = BTRFS_EXTENT_ITEM_KEY;
@@ -132,14 +132,14 @@ static int remove_extent_item(struct btrfs_root *root, u64 bytenr,
path = btrfs_alloc_path();
if (!path) {
- test_msg("Couldn't allocate path\n");
+ test_err("couldn't allocate path");
return -ENOMEM;
}
path->leave_spinning = 1;
ret = btrfs_search_slot(&trans, root, &key, path, -1, 1);
if (ret) {
- test_msg("Didn't find our key %d\n", ret);
+ test_err("didn't find our key %d", ret);
btrfs_free_path(path);
return ret;
}
@@ -158,7 +158,7 @@ static int remove_extent_ref(struct btrfs_root *root, u64 bytenr,
u64 refs;
int ret;
- btrfs_init_dummy_trans(&trans);
+ btrfs_init_dummy_trans(&trans, NULL);
key.objectid = bytenr;
key.type = BTRFS_EXTENT_ITEM_KEY;
@@ -166,14 +166,14 @@ static int remove_extent_ref(struct btrfs_root *root, u64 bytenr,
path = btrfs_alloc_path();
if (!path) {
- test_msg("Couldn't allocate path\n");
+ test_err("couldn't allocate path");
return -ENOMEM;
}
path->leave_spinning = 1;
ret = btrfs_search_slot(&trans, root, &key, path, 0, 1);
if (ret) {
- test_msg("Couldn't find extent ref\n");
+ test_err("couldn't find extent ref");
btrfs_free_path(path);
return ret;
}
@@ -195,7 +195,7 @@ static int remove_extent_ref(struct btrfs_root *root, u64 bytenr,
ret = btrfs_search_slot(&trans, root, &key, path, -1, 1);
if (ret) {
- test_msg("Couldn't find backref %d\n", ret);
+ test_err("couldn't find backref %d", ret);
btrfs_free_path(path);
return ret;
}
@@ -213,12 +213,12 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
struct ulist *new_roots = NULL;
int ret;
- btrfs_init_dummy_trans(&trans);
+ btrfs_init_dummy_trans(&trans, fs_info);
- test_msg("Qgroup basic add\n");
+ test_msg("qgroup basic add");
ret = btrfs_create_qgroup(NULL, fs_info, BTRFS_FS_TREE_OBJECTID);
if (ret) {
- test_msg("Couldn't create a qgroup %d\n", ret);
+ test_err("couldn't create a qgroup %d", ret);
return ret;
}
@@ -231,7 +231,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
false);
if (ret) {
ulist_free(old_roots);
- test_msg("Couldn't find old roots: %d\n", ret);
+ test_err("couldn't find old roots: %d", ret);
return ret;
}
@@ -245,20 +245,20 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
- test_msg("Couldn't find old roots: %d\n", ret);
+ test_err("couldn't find old roots: %d", ret);
return ret;
}
ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
nodesize, old_roots, new_roots);
if (ret) {
- test_msg("Couldn't account space for a qgroup %d\n", ret);
+ test_err("couldn't account space for a qgroup %d", ret);
return ret;
}
if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
nodesize, nodesize)) {
- test_msg("Qgroup counts didn't match expected values\n");
+ test_err("qgroup counts didn't match expected values");
return -EINVAL;
}
old_roots = NULL;
@@ -268,7 +268,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
false);
if (ret) {
ulist_free(old_roots);
- test_msg("Couldn't find old roots: %d\n", ret);
+ test_err("couldn't find old roots: %d", ret);
return ret;
}
@@ -281,19 +281,19 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
- test_msg("Couldn't find old roots: %d\n", ret);
+ test_err("couldn't find old roots: %d", ret);
return ret;
}
ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
nodesize, old_roots, new_roots);
if (ret) {
- test_msg("Couldn't account space for a qgroup %d\n", ret);
+ test_err("couldn't account space for a qgroup %d", ret);
return -EINVAL;
}
if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID, 0, 0)) {
- test_msg("Qgroup counts didn't match expected values\n");
+ test_err("qgroup counts didn't match expected values");
return -EINVAL;
}
@@ -314,9 +314,9 @@ static int test_multiple_refs(struct btrfs_root *root,
struct ulist *new_roots = NULL;
int ret;
- btrfs_init_dummy_trans(&trans);
+ btrfs_init_dummy_trans(&trans, fs_info);
- test_msg("Qgroup multiple refs test\n");
+ test_msg("qgroup multiple refs test");
/*
* We have BTRFS_FS_TREE_OBJECTID created already from the
@@ -324,7 +324,7 @@ static int test_multiple_refs(struct btrfs_root *root,
*/
ret = btrfs_create_qgroup(NULL, fs_info, BTRFS_FIRST_FREE_OBJECTID);
if (ret) {
- test_msg("Couldn't create a qgroup %d\n", ret);
+ test_err("couldn't create a qgroup %d", ret);
return ret;
}
@@ -332,7 +332,7 @@ static int test_multiple_refs(struct btrfs_root *root,
false);
if (ret) {
ulist_free(old_roots);
- test_msg("Couldn't find old roots: %d\n", ret);
+ test_err("couldn't find old roots: %d", ret);
return ret;
}
@@ -346,20 +346,20 @@ static int test_multiple_refs(struct btrfs_root *root,
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
- test_msg("Couldn't find old roots: %d\n", ret);
+ test_err("couldn't find old roots: %d", ret);
return ret;
}
ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
nodesize, old_roots, new_roots);
if (ret) {
- test_msg("Couldn't account space for a qgroup %d\n", ret);
+ test_err("couldn't account space for a qgroup %d", ret);
return ret;
}
if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
nodesize, nodesize)) {
- test_msg("Qgroup counts didn't match expected values\n");
+ test_err("qgroup counts didn't match expected values");
return -EINVAL;
}
@@ -367,7 +367,7 @@ static int test_multiple_refs(struct btrfs_root *root,
false);
if (ret) {
ulist_free(old_roots);
- test_msg("Couldn't find old roots: %d\n", ret);
+ test_err("couldn't find old roots: %d", ret);
return ret;
}
@@ -381,26 +381,26 @@ static int test_multiple_refs(struct btrfs_root *root,
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
- test_msg("Couldn't find old roots: %d\n", ret);
+ test_err("couldn't find old roots: %d", ret);
return ret;
}
ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
nodesize, old_roots, new_roots);
if (ret) {
- test_msg("Couldn't account space for a qgroup %d\n", ret);
+ test_err("couldn't account space for a qgroup %d", ret);
return ret;
}
if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
nodesize, 0)) {
- test_msg("Qgroup counts didn't match expected values\n");
+ test_err("qgroup counts didn't match expected values");
return -EINVAL;
}
if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FIRST_FREE_OBJECTID,
nodesize, 0)) {
- test_msg("Qgroup counts didn't match expected values\n");
+ test_err("qgroup counts didn't match expected values");
return -EINVAL;
}
@@ -408,7 +408,7 @@ static int test_multiple_refs(struct btrfs_root *root,
false);
if (ret) {
ulist_free(old_roots);
- test_msg("Couldn't find old roots: %d\n", ret);
+ test_err("couldn't find old roots: %d", ret);
return ret;
}
@@ -422,26 +422,26 @@ static int test_multiple_refs(struct btrfs_root *root,
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
- test_msg("Couldn't find old roots: %d\n", ret);
+ test_err("couldn't find old roots: %d", ret);
return ret;
}
ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
nodesize, old_roots, new_roots);
if (ret) {
- test_msg("Couldn't account space for a qgroup %d\n", ret);
+ test_err("couldn't account space for a qgroup %d", ret);
return ret;
}
if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FIRST_FREE_OBJECTID,
0, 0)) {
- test_msg("Qgroup counts didn't match expected values\n");
+ test_err("qgroup counts didn't match expected values");
return -EINVAL;
}
if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
nodesize, nodesize)) {
- test_msg("Qgroup counts didn't match expected values\n");
+ test_err("qgroup counts didn't match expected values");
return -EINVAL;
}
@@ -457,13 +457,13 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize)
fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
if (!fs_info) {
- test_msg("Couldn't allocate dummy fs info\n");
+ test_err("couldn't allocate dummy fs info");
return -ENOMEM;
}
root = btrfs_alloc_dummy_root(fs_info);
if (IS_ERR(root)) {
- test_msg("Couldn't allocate root\n");
+ test_err("couldn't allocate root");
ret = PTR_ERR(root);
goto out;
}
@@ -485,7 +485,7 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize)
*/
root->node = alloc_test_extent_buffer(root->fs_info, nodesize);
if (!root->node) {
- test_msg("Couldn't allocate dummy buffer\n");
+ test_err("couldn't allocate dummy buffer");
ret = -ENOMEM;
goto out;
}
@@ -495,7 +495,7 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize)
tmp_root = btrfs_alloc_dummy_root(fs_info);
if (IS_ERR(tmp_root)) {
- test_msg("Couldn't allocate a fs root\n");
+ test_err("couldn't allocate a fs root");
ret = PTR_ERR(tmp_root);
goto out;
}
@@ -504,13 +504,13 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize)
root->fs_info->fs_root = tmp_root;
ret = btrfs_insert_fs_root(root->fs_info, tmp_root);
if (ret) {
- test_msg("Couldn't insert fs root %d\n", ret);
+ test_err("couldn't insert fs root %d", ret);
goto out;
}
tmp_root = btrfs_alloc_dummy_root(fs_info);
if (IS_ERR(tmp_root)) {
- test_msg("Couldn't allocate a fs root\n");
+ test_err("couldn't allocate a fs root");
ret = PTR_ERR(tmp_root);
goto out;
}
@@ -518,11 +518,11 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize)
tmp_root->root_key.objectid = BTRFS_FIRST_FREE_OBJECTID;
ret = btrfs_insert_fs_root(root->fs_info, tmp_root);
if (ret) {
- test_msg("Couldn't insert fs root %d\n", ret);
+ test_err("couldn't insert fs root %d", ret);
goto out;
}
- test_msg("Running qgroup tests\n");
+ test_msg("running qgroup tests");
ret = test_no_shared_qgroup(root, sectorsize, nodesize);
if (ret)
goto out;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 63fdcab..4485eae 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -877,12 +877,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
atomic_dec(&cur_trans->num_writers);
extwriter_counter_dec(cur_trans, trans->type);
- /*
- * Make sure counter is updated before we wake up waiters.
- */
- smp_mb();
- if (waitqueue_active(&cur_trans->writer_wait))
- wake_up(&cur_trans->writer_wait);
+ cond_wake_up(&cur_trans->writer_wait);
btrfs_put_transaction(cur_trans);
if (current->journal_info == trans)
@@ -1250,7 +1245,6 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans)
btrfs_free_log(trans, root);
btrfs_update_reloc_root(trans, root);
- btrfs_orphan_commit_root(trans, root);
btrfs_save_ino_cache(root, trans);
@@ -1640,15 +1634,14 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
btrfs_abort_transaction(trans, ret);
goto fail;
}
- ret = btrfs_uuid_tree_add(trans, fs_info, new_uuid.b,
- BTRFS_UUID_KEY_SUBVOL, objectid);
+ ret = btrfs_uuid_tree_add(trans, new_uuid.b, BTRFS_UUID_KEY_SUBVOL,
+ objectid);
if (ret) {
btrfs_abort_transaction(trans, ret);
goto fail;
}
if (!btrfs_is_empty_uuid(new_root_item->received_uuid)) {
- ret = btrfs_uuid_tree_add(trans, fs_info,
- new_root_item->received_uuid,
+ ret = btrfs_uuid_tree_add(trans, new_root_item->received_uuid,
BTRFS_UUID_KEY_RECEIVED_SUBVOL,
objectid);
if (ret && ret != -EEXIST) {
@@ -2267,6 +2260,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
*/
cur_trans->state = TRANS_STATE_COMPLETED;
wake_up(&cur_trans->commit_wait);
+ clear_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags);
spin_lock(&fs_info->trans_lock);
list_del_init(&cur_trans->list);
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index c88fccd..9443948 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -139,7 +139,6 @@ struct btrfs_pending_snapshot {
struct btrfs_path *path;
/* block reservation for the operation */
struct btrfs_block_rsv block_rsv;
- u64 qgroup_reserved;
/* extra metadata reservation for relocation */
int error;
bool readonly;
@@ -199,6 +198,20 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root);
int btrfs_commit_transaction(struct btrfs_trans_handle *trans);
int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
int wait_for_unblock);
+
+/*
+ * Try to commit transaction asynchronously, so this is safe to call
+ * even holding a spinlock.
+ *
+ * It's done by informing transaction_kthread to commit transaction without
+ * waiting for commit interval.
+ */
+static inline void btrfs_commit_transaction_locksafe(
+ struct btrfs_fs_info *fs_info)
+{
+ set_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags);
+ wake_up_process(fs_info->transaction_kthread);
+}
int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans);
int btrfs_should_end_transaction(struct btrfs_trans_handle *trans);
void btrfs_throttle(struct btrfs_fs_info *fs_info);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 43758e3..f8220ec 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -222,11 +222,8 @@ int btrfs_pin_log_trans(struct btrfs_root *root)
void btrfs_end_log_trans(struct btrfs_root *root)
{
if (atomic_dec_and_test(&root->log_writers)) {
- /*
- * Implicit memory barrier after atomic_dec_and_test
- */
- if (waitqueue_active(&root->log_writer_wait))
- wake_up(&root->log_writer_wait);
+ /* atomic_dec_and_test implies a barrier */
+ cond_wake_up_nomb(&root->log_writer_wait);
}
}
@@ -2988,11 +2985,8 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
mutex_lock(&log_root_tree->log_mutex);
if (atomic_dec_and_test(&log_root_tree->log_writers)) {
- /*
- * Implicit memory barrier after atomic_dec_and_test
- */
- if (waitqueue_active(&log_root_tree->log_writer_wait))
- wake_up(&log_root_tree->log_writer_wait);
+ /* atomic_dec_and_test implies a barrier */
+ cond_wake_up_nomb(&log_root_tree->log_writer_wait);
}
if (ret) {
@@ -3116,10 +3110,11 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
mutex_unlock(&log_root_tree->log_mutex);
/*
- * The barrier before waitqueue_active is implied by mutex_unlock
+ * The barrier before waitqueue_active (in cond_wake_up) is needed so
+ * all the updates above are seen by the woken threads. It might not be
+ * necessary, but proving that seems to be hard.
*/
- if (waitqueue_active(&log_root_tree->log_commit_wait[index2]))
- wake_up(&log_root_tree->log_commit_wait[index2]);
+ cond_wake_up(&log_root_tree->log_commit_wait[index2]);
out:
mutex_lock(&root->log_mutex);
btrfs_remove_all_log_ctxs(root, index1, ret);
@@ -3128,10 +3123,11 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
mutex_unlock(&root->log_mutex);
/*
- * The barrier before waitqueue_active is implied by mutex_unlock
+ * The barrier before waitqueue_active (in cond_wake_up) is needed so
+ * all the updates above are seen by the woken threads. It might not be
+ * necessary, but proving that seems to be hard.
*/
- if (waitqueue_active(&root->log_commit_wait[index1]))
- wake_up(&root->log_commit_wait[index1]);
+ cond_wake_up(&root->log_commit_wait[index1]);
return ret;
}
@@ -4320,6 +4316,110 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
return ret;
}
+/*
+ * Log all prealloc extents beyond the inode's i_size to make sure we do not
+ * lose them after doing a fast fsync and replaying the log. We scan the
+ * subvolume's root instead of iterating the inode's extent map tree because
+ * otherwise we can log incorrect extent items based on extent map conversion.
+ * That can happen due to the fact that extent maps are merged when they
+ * are not in the extent map tree's list of modified extents.
+ */
+static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
+ struct btrfs_inode *inode,
+ struct btrfs_path *path)
+{
+ struct btrfs_root *root = inode->root;
+ struct btrfs_key key;
+ const u64 i_size = i_size_read(&inode->vfs_inode);
+ const u64 ino = btrfs_ino(inode);
+ struct btrfs_path *dst_path = NULL;
+ u64 last_extent = (u64)-1;
+ int ins_nr = 0;
+ int start_slot;
+ int ret;
+
+ if (!(inode->flags & BTRFS_INODE_PREALLOC))
+ return 0;
+
+ key.objectid = ino;
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = i_size;
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0)
+ goto out;
+
+ while (true) {
+ struct extent_buffer *leaf = path->nodes[0];
+ int slot = path->slots[0];
+
+ if (slot >= btrfs_header_nritems(leaf)) {
+ if (ins_nr > 0) {
+ ret = copy_items(trans, inode, dst_path, path,
+ &last_extent, start_slot,
+ ins_nr, 1, 0);
+ if (ret < 0)
+ goto out;
+ ins_nr = 0;
+ }
+ ret = btrfs_next_leaf(root, path);
+ if (ret < 0)
+ goto out;
+ if (ret > 0) {
+ ret = 0;
+ break;
+ }
+ continue;
+ }
+
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+ if (key.objectid > ino)
+ break;
+ if (WARN_ON_ONCE(key.objectid < ino) ||
+ key.type < BTRFS_EXTENT_DATA_KEY ||
+ key.offset < i_size) {
+ path->slots[0]++;
+ continue;
+ }
+ if (last_extent == (u64)-1) {
+ last_extent = key.offset;
+ /*
+ * Avoid logging extent items logged in past fsync calls
+ * and leading to duplicate keys in the log tree.
+ */
+ do {
+ ret = btrfs_truncate_inode_items(trans,
+ root->log_root,
+ &inode->vfs_inode,
+ i_size,
+ BTRFS_EXTENT_DATA_KEY);
+ } while (ret == -EAGAIN);
+ if (ret)
+ goto out;
+ }
+ if (ins_nr == 0)
+ start_slot = slot;
+ ins_nr++;
+ path->slots[0]++;
+ if (!dst_path) {
+ dst_path = btrfs_alloc_path();
+ if (!dst_path) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ }
+ }
+ if (ins_nr > 0) {
+ ret = copy_items(trans, inode, dst_path, path, &last_extent,
+ start_slot, ins_nr, 1, 0);
+ if (ret > 0)
+ ret = 0;
+ }
+out:
+ btrfs_release_path(path);
+ btrfs_free_path(dst_path);
+ return ret;
+}
+
static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_inode *inode,
@@ -4362,6 +4462,11 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
if (em->generation <= test_gen)
continue;
+ /* We log prealloc extents beyond eof later. */
+ if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) &&
+ em->start >= i_size_read(&inode->vfs_inode))
+ continue;
+
if (em->start < logged_start)
logged_start = em->start;
if ((em->start + em->len - 1) > logged_end)
@@ -4374,31 +4479,6 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
num++;
}
- /*
- * Add all prealloc extents beyond the inode's i_size to make sure we
- * don't lose them after doing a fast fsync and replaying the log.
- */
- if (inode->flags & BTRFS_INODE_PREALLOC) {
- struct rb_node *node;
-
- for (node = rb_last(&tree->map); node; node = rb_prev(node)) {
- em = rb_entry(node, struct extent_map, rb_node);
- if (em->start < i_size_read(&inode->vfs_inode))
- break;
- if (!list_empty(&em->list))
- continue;
- /* Same as above loop. */
- if (++num > 32768) {
- list_del_init(&tree->modified_extents);
- ret = -EFBIG;
- goto process;
- }
- refcount_inc(&em->refs);
- set_bit(EXTENT_FLAG_LOGGING, &em->flags);
- list_add_tail(&em->list, &extents);
- }
- }
-
list_sort(NULL, &extents, extent_cmp);
btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end);
/*
@@ -4443,6 +4523,9 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
up_write(&inode->dio_sem);
btrfs_release_path(path);
+ if (!ret)
+ ret = btrfs_log_prealloc_extents(trans, inode, path);
+
return ret;
}
@@ -4827,6 +4910,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
struct extent_map_tree *em_tree = &inode->extent_tree;
u64 logged_isize = 0;
bool need_log_inode_item = true;
+ bool xattrs_logged = false;
path = btrfs_alloc_path();
if (!path)
@@ -5128,6 +5212,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
err = btrfs_log_all_xattrs(trans, root, inode, path, dst_path);
if (err)
goto out_unlock;
+ xattrs_logged = true;
if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) {
btrfs_release_path(path);
btrfs_release_path(dst_path);
@@ -5140,6 +5225,11 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
btrfs_release_path(dst_path);
if (need_log_inode_item) {
err = log_inode_item(trans, log, dst_path, inode);
+ if (!err && !xattrs_logged) {
+ err = btrfs_log_all_xattrs(trans, root, inode, path,
+ dst_path);
+ btrfs_release_path(path);
+ }
if (err)
goto out_unlock;
}
diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c
index 1ba7ca2..3b2ae34 100644
--- a/fs/btrfs/uuid-tree.c
+++ b/fs/btrfs/uuid-tree.c
@@ -79,10 +79,10 @@ static int btrfs_uuid_tree_lookup(struct btrfs_root *uuid_root, u8 *uuid,
return ret;
}
-int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info, u8 *uuid, u8 type,
+int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
u64 subid_cpu)
{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_root *uuid_root = fs_info->uuid_root;
int ret;
struct btrfs_path *path = NULL;
@@ -144,10 +144,10 @@ int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans,
return ret;
}
-int btrfs_uuid_tree_rem(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info, u8 *uuid, u8 type,
+int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
u64 subid)
{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_root *uuid_root = fs_info->uuid_root;
int ret;
struct btrfs_path *path = NULL;
@@ -239,7 +239,7 @@ static int btrfs_uuid_iter_rem(struct btrfs_root *uuid_root, u8 *uuid, u8 type,
goto out;
}
- ret = btrfs_uuid_tree_rem(trans, uuid_root->fs_info, uuid, type, subid);
+ ret = btrfs_uuid_tree_remove(trans, uuid, type, subid);
btrfs_end_transaction(trans);
out:
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 292266f..e034ad9 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -40,6 +40,9 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
.tolerated_failures = 1,
.devs_increment = 2,
.ncopies = 2,
+ .raid_name = "raid10",
+ .bg_flag = BTRFS_BLOCK_GROUP_RAID10,
+ .mindev_error = BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET,
},
[BTRFS_RAID_RAID1] = {
.sub_stripes = 1,
@@ -49,6 +52,9 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
.tolerated_failures = 1,
.devs_increment = 2,
.ncopies = 2,
+ .raid_name = "raid1",
+ .bg_flag = BTRFS_BLOCK_GROUP_RAID1,
+ .mindev_error = BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET,
},
[BTRFS_RAID_DUP] = {
.sub_stripes = 1,
@@ -58,6 +64,9 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
.tolerated_failures = 0,
.devs_increment = 1,
.ncopies = 2,
+ .raid_name = "dup",
+ .bg_flag = BTRFS_BLOCK_GROUP_DUP,
+ .mindev_error = 0,
},
[BTRFS_RAID_RAID0] = {
.sub_stripes = 1,
@@ -67,6 +76,9 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
.tolerated_failures = 0,
.devs_increment = 1,
.ncopies = 1,
+ .raid_name = "raid0",
+ .bg_flag = BTRFS_BLOCK_GROUP_RAID0,
+ .mindev_error = 0,
},
[BTRFS_RAID_SINGLE] = {
.sub_stripes = 1,
@@ -76,6 +88,9 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
.tolerated_failures = 0,
.devs_increment = 1,
.ncopies = 1,
+ .raid_name = "single",
+ .bg_flag = 0,
+ .mindev_error = 0,
},
[BTRFS_RAID_RAID5] = {
.sub_stripes = 1,
@@ -85,6 +100,9 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
.tolerated_failures = 1,
.devs_increment = 1,
.ncopies = 2,
+ .raid_name = "raid5",
+ .bg_flag = BTRFS_BLOCK_GROUP_RAID5,
+ .mindev_error = BTRFS_ERROR_DEV_RAID5_MIN_NOT_MET,
},
[BTRFS_RAID_RAID6] = {
.sub_stripes = 1,
@@ -94,33 +112,19 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
.tolerated_failures = 2,
.devs_increment = 1,
.ncopies = 3,
+ .raid_name = "raid6",
+ .bg_flag = BTRFS_BLOCK_GROUP_RAID6,
+ .mindev_error = BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET,
},
};
-const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
- [BTRFS_RAID_RAID10] = BTRFS_BLOCK_GROUP_RAID10,
- [BTRFS_RAID_RAID1] = BTRFS_BLOCK_GROUP_RAID1,
- [BTRFS_RAID_DUP] = BTRFS_BLOCK_GROUP_DUP,
- [BTRFS_RAID_RAID0] = BTRFS_BLOCK_GROUP_RAID0,
- [BTRFS_RAID_SINGLE] = 0,
- [BTRFS_RAID_RAID5] = BTRFS_BLOCK_GROUP_RAID5,
- [BTRFS_RAID_RAID6] = BTRFS_BLOCK_GROUP_RAID6,
-};
+const char *get_raid_name(enum btrfs_raid_types type)
+{
+ if (type >= BTRFS_NR_RAID_TYPES)
+ return NULL;
-/*
- * Table to convert BTRFS_RAID_* to the error code if minimum number of devices
- * condition is not met. Zero means there's no corresponding
- * BTRFS_ERROR_DEV_*_NOT_MET value.
- */
-const int btrfs_raid_mindev_error[BTRFS_NR_RAID_TYPES] = {
- [BTRFS_RAID_RAID10] = BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET,
- [BTRFS_RAID_RAID1] = BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET,
- [BTRFS_RAID_DUP] = 0,
- [BTRFS_RAID_RAID0] = 0,
- [BTRFS_RAID_SINGLE] = 0,
- [BTRFS_RAID_RAID5] = BTRFS_ERROR_DEV_RAID5_MIN_NOT_MET,
- [BTRFS_RAID_RAID6] = BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET,
-};
+ return btrfs_raid_array[type].raid_name;
+}
static int init_first_rw_device(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
@@ -167,12 +171,6 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
* may be used to exclude some operations from running concurrently without any
* modifications to the list (see write_all_supers)
*
- * volume_mutex
- * ------------
- * coarse lock owned by a mounted filesystem; used to exclude some operations
- * that cannot run in parallel and affect the higher-level properties of the
- * filesystem like: device add/deleting/resize/replace, or balance
- *
* balance_mutex
* -------------
* protects balance structures (status, state) and context accessed from
@@ -197,6 +195,41 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
* device_list_mutex
* chunk_mutex
* balance_mutex
+ *
+ *
+ * Exclusive operations, BTRFS_FS_EXCL_OP
+ * ======================================
+ *
+ * Maintains the exclusivity of the following operations that apply to the
+ * whole filesystem and cannot run in parallel.
+ *
+ * - Balance (*)
+ * - Device add
+ * - Device remove
+ * - Device replace (*)
+ * - Resize
+ *
+ * The device operations (as above) can be in one of the following states:
+ *
+ * - Running state
+ * - Paused state
+ * - Completed state
+ *
+ * Only device operations marked with (*) can go into the Paused state for the
+ * following reasons:
+ *
+ * - ioctl (only Balance can be Paused through ioctl)
+ * - filesystem remounted as read-only
+ * - filesystem unmounted and mounted as read-only
+ * - system power-cycle and filesystem mounted as read-only
+ * - filesystem or device errors leading to forced read-only
+ *
+ * BTRFS_FS_EXCL_OP flag is set and cleared using atomic operations.
+ * During the course of Paused state, the BTRFS_FS_EXCL_OP remains set.
+ * A device operation in Paused or Running state can be canceled or resumed
+ * either by ioctl (Balance only) or when remounted as read-write.
+ * BTRFS_FS_EXCL_OP flag is cleared when the device operation is canceled or
+ * completed.
*/
DEFINE_MUTEX(uuid_mutex);
@@ -227,14 +260,14 @@ static struct btrfs_fs_devices *alloc_fs_devices(const u8 *fsid)
INIT_LIST_HEAD(&fs_devs->devices);
INIT_LIST_HEAD(&fs_devs->resized_devices);
INIT_LIST_HEAD(&fs_devs->alloc_list);
- INIT_LIST_HEAD(&fs_devs->list);
+ INIT_LIST_HEAD(&fs_devs->fs_list);
if (fsid)
memcpy(fs_devs->fsid, fsid, BTRFS_FSID_SIZE);
return fs_devs;
}
-static void free_device(struct btrfs_device *device)
+void btrfs_free_device(struct btrfs_device *device)
{
rcu_string_free(device->name);
bio_put(device->flush_bio);
@@ -249,7 +282,7 @@ static void free_fs_devices(struct btrfs_fs_devices *fs_devices)
device = list_entry(fs_devices->devices.next,
struct btrfs_device, dev_list);
list_del(&device->dev_list);
- free_device(device);
+ btrfs_free_device(device);
}
kfree(fs_devices);
}
@@ -273,8 +306,8 @@ void __exit btrfs_cleanup_fs_uuids(void)
while (!list_empty(&fs_uuids)) {
fs_devices = list_entry(fs_uuids.next,
- struct btrfs_fs_devices, list);
- list_del(&fs_devices->list);
+ struct btrfs_fs_devices, fs_list);
+ list_del(&fs_devices->fs_list);
free_fs_devices(fs_devices);
}
}
@@ -282,7 +315,7 @@ void __exit btrfs_cleanup_fs_uuids(void)
/*
* Returns a pointer to a new btrfs_device on success; ERR_PTR() on error.
* Returned struct is not linked onto any lists and must be destroyed using
- * free_device.
+ * btrfs_free_device.
*/
static struct btrfs_device *__alloc_device(void)
{
@@ -327,10 +360,9 @@ static struct btrfs_device *__alloc_device(void)
static struct btrfs_device *find_device(struct btrfs_fs_devices *fs_devices,
u64 devid, const u8 *uuid)
{
- struct list_head *head = &fs_devices->devices;
struct btrfs_device *dev;
- list_for_each_entry(dev, head, dev_list) {
+ list_for_each_entry(dev, &fs_devices->devices, dev_list) {
if (dev->devid == devid &&
(!uuid || !memcmp(dev->uuid, uuid, BTRFS_UUID_SIZE))) {
return dev;
@@ -343,7 +375,7 @@ static noinline struct btrfs_fs_devices *find_fsid(u8 *fsid)
{
struct btrfs_fs_devices *fs_devices;
- list_for_each_entry(fs_devices, &fs_uuids, list) {
+ list_for_each_entry(fs_devices, &fs_uuids, fs_list) {
if (memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE) == 0)
return fs_devices;
}
@@ -607,7 +639,7 @@ static void btrfs_free_stale_devices(const char *path,
struct btrfs_fs_devices *fs_devs, *tmp_fs_devs;
struct btrfs_device *dev, *tmp_dev;
- list_for_each_entry_safe(fs_devs, tmp_fs_devs, &fs_uuids, list) {
+ list_for_each_entry_safe(fs_devs, tmp_fs_devs, &fs_uuids, fs_list) {
if (fs_devs->opened)
continue;
@@ -632,13 +664,13 @@ static void btrfs_free_stale_devices(const char *path,
/* delete the stale device */
if (fs_devs->num_devices == 1) {
btrfs_sysfs_remove_fsid(fs_devs);
- list_del(&fs_devs->list);
+ list_del(&fs_devs->fs_list);
free_fs_devices(fs_devs);
break;
} else {
fs_devs->num_devices--;
list_del(&dev->dev_list);
- free_device(dev);
+ btrfs_free_device(dev);
}
}
}
@@ -732,7 +764,7 @@ static noinline struct btrfs_device *device_list_add(const char *path,
if (IS_ERR(fs_devices))
return ERR_CAST(fs_devices);
- list_add(&fs_devices->list, &fs_uuids);
+ list_add(&fs_devices->fs_list, &fs_uuids);
device = NULL;
} else {
@@ -753,7 +785,7 @@ static noinline struct btrfs_device *device_list_add(const char *path,
name = rcu_string_strdup(path, GFP_NOFS);
if (!name) {
- free_device(device);
+ btrfs_free_device(device);
return ERR_PTR(-ENOMEM);
}
rcu_assign_pointer(device->name, name);
@@ -866,7 +898,7 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
name = rcu_string_strdup(orig_dev->name->str,
GFP_KERNEL);
if (!name) {
- free_device(device);
+ btrfs_free_device(device);
goto error;
}
rcu_assign_pointer(device->name, name);
@@ -938,7 +970,7 @@ void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, int step)
}
list_del_init(&device->dev_list);
fs_devices->num_devices--;
- free_device(device);
+ btrfs_free_device(device);
}
if (fs_devices->seed) {
@@ -956,7 +988,7 @@ static void free_device_rcu(struct rcu_head *head)
struct btrfs_device *device;
device = container_of(head, struct btrfs_device, rcu);
- free_device(device);
+ btrfs_free_device(device);
}
static void btrfs_close_bdev(struct btrfs_device *device)
@@ -1005,7 +1037,7 @@ static void btrfs_prepare_close_one_device(struct btrfs_device *device)
new_device->fs_devices = device->fs_devices;
}
-static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
+static int close_fs_devices(struct btrfs_fs_devices *fs_devices)
{
struct btrfs_device *device, *tmp;
struct list_head pending_put;
@@ -1050,7 +1082,7 @@ int btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
int ret;
mutex_lock(&uuid_mutex);
- ret = __btrfs_close_devices(fs_devices);
+ ret = close_fs_devices(fs_devices);
if (!fs_devices->opened) {
seed_devices = fs_devices->seed;
fs_devices->seed = NULL;
@@ -1060,23 +1092,22 @@ int btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
while (seed_devices) {
fs_devices = seed_devices;
seed_devices = fs_devices->seed;
- __btrfs_close_devices(fs_devices);
+ close_fs_devices(fs_devices);
free_fs_devices(fs_devices);
}
return ret;
}
-static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
+static int open_fs_devices(struct btrfs_fs_devices *fs_devices,
fmode_t flags, void *holder)
{
- struct list_head *head = &fs_devices->devices;
struct btrfs_device *device;
struct btrfs_device *latest_dev = NULL;
int ret = 0;
flags |= FMODE_EXCL;
- list_for_each_entry(device, head, dev_list) {
+ list_for_each_entry(device, &fs_devices->devices, dev_list) {
/* Just open everything we can; ignore failures here */
if (btrfs_open_one_device(fs_devices, device, flags, holder))
continue;
@@ -1115,15 +1146,16 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
{
int ret;
- mutex_lock(&uuid_mutex);
+ mutex_lock(&fs_devices->device_list_mutex);
if (fs_devices->opened) {
fs_devices->opened++;
ret = 0;
} else {
list_sort(NULL, &fs_devices->devices, devid_cmp);
- ret = __btrfs_open_devices(fs_devices, flags, holder);
+ ret = open_fs_devices(fs_devices, flags, holder);
}
- mutex_unlock(&uuid_mutex);
+ mutex_unlock(&fs_devices->device_list_mutex);
+
return ret;
}
@@ -1201,31 +1233,29 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
*/
bytenr = btrfs_sb_offset(0);
flags |= FMODE_EXCL;
- mutex_lock(&uuid_mutex);
bdev = blkdev_get_by_path(path, flags, holder);
- if (IS_ERR(bdev)) {
- ret = PTR_ERR(bdev);
- goto error;
- }
+ if (IS_ERR(bdev))
+ return PTR_ERR(bdev);
if (btrfs_read_disk_super(bdev, bytenr, &page, &disk_super)) {
ret = -EINVAL;
goto error_bdev_put;
}
+ mutex_lock(&uuid_mutex);
device = device_list_add(path, disk_super);
if (IS_ERR(device))
ret = PTR_ERR(device);
else
*fs_devices_ret = device->fs_devices;
+ mutex_unlock(&uuid_mutex);
btrfs_release_disk_super(page);
error_bdev_put:
blkdev_put(bdev, flags);
-error:
- mutex_unlock(&uuid_mutex);
+
return ret;
}
@@ -1857,11 +1887,11 @@ static int btrfs_check_raid_min_devices(struct btrfs_fs_info *fs_info,
} while (read_seqretry(&fs_info->profiles_lock, seq));
for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
- if (!(all_avail & btrfs_raid_group[i]))
+ if (!(all_avail & btrfs_raid_array[i].bg_flag))
continue;
if (num_devices < btrfs_raid_array[i].devs_min) {
- int ret = btrfs_raid_mindev_error[i];
+ int ret = btrfs_raid_array[i].mindev_error;
if (ret)
return ret;
@@ -1917,13 +1947,13 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
{
struct btrfs_device *device;
struct btrfs_fs_devices *cur_devices;
+ struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
u64 num_devices;
int ret = 0;
- mutex_lock(&fs_info->volume_mutex);
mutex_lock(&uuid_mutex);
- num_devices = fs_info->fs_devices->num_devices;
+ num_devices = fs_devices->num_devices;
btrfs_dev_replace_read_lock(&fs_info->dev_replace);
if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace)) {
WARN_ON(num_devices < 1);
@@ -1986,27 +2016,32 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
* (super_copy) should hold the device list mutex.
*/
+ /*
+ * In normal cases the cur_devices == fs_devices. But in case
+ * of deleting a seed device, the cur_devices should point to
+ * its own fs_devices listed under the fs_devices->seed.
+ */
cur_devices = device->fs_devices;
- mutex_lock(&fs_info->fs_devices->device_list_mutex);
+ mutex_lock(&fs_devices->device_list_mutex);
list_del_rcu(&device->dev_list);
- device->fs_devices->num_devices--;
- device->fs_devices->total_devices--;
+ cur_devices->num_devices--;
+ cur_devices->total_devices--;
if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state))
- device->fs_devices->missing_devices--;
+ cur_devices->missing_devices--;
btrfs_assign_next_active_device(fs_info, device, NULL);
if (device->bdev) {
- device->fs_devices->open_devices--;
+ cur_devices->open_devices--;
/* remove sysfs entry */
- btrfs_sysfs_rm_device_link(fs_info->fs_devices, device);
+ btrfs_sysfs_rm_device_link(fs_devices, device);
}
num_devices = btrfs_super_num_devices(fs_info->super_copy) - 1;
btrfs_set_super_num_devices(fs_info->super_copy, num_devices);
- mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+ mutex_unlock(&fs_devices->device_list_mutex);
/*
* at this point, the device is zero sized and detached from
@@ -2020,8 +2055,6 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
call_rcu(&device->rcu, free_device_rcu);
if (cur_devices->open_devices == 0) {
- struct btrfs_fs_devices *fs_devices;
- fs_devices = fs_info->fs_devices;
while (fs_devices) {
if (fs_devices->seed == cur_devices) {
fs_devices->seed = cur_devices->seed;
@@ -2030,20 +2063,19 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
fs_devices = fs_devices->seed;
}
cur_devices->seed = NULL;
- __btrfs_close_devices(cur_devices);
+ close_fs_devices(cur_devices);
free_fs_devices(cur_devices);
}
out:
mutex_unlock(&uuid_mutex);
- mutex_unlock(&fs_info->volume_mutex);
return ret;
error_undo:
if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
mutex_lock(&fs_info->chunk_mutex);
list_add(&device->dev_alloc_list,
- &fs_info->fs_devices->alloc_list);
+ &fs_devices->alloc_list);
device->fs_devices->rw_devices++;
mutex_unlock(&fs_info->chunk_mutex);
}
@@ -2112,7 +2144,7 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
tmp_fs_devices = tmp_fs_devices->seed;
}
fs_devices->seed = NULL;
- __btrfs_close_devices(fs_devices);
+ close_fs_devices(fs_devices);
free_fs_devices(fs_devices);
}
}
@@ -2120,23 +2152,23 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
struct btrfs_device *tgtdev)
{
- mutex_lock(&uuid_mutex);
- WARN_ON(!tgtdev);
- mutex_lock(&fs_info->fs_devices->device_list_mutex);
+ struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
- btrfs_sysfs_rm_device_link(fs_info->fs_devices, tgtdev);
+ WARN_ON(!tgtdev);
+ mutex_lock(&fs_devices->device_list_mutex);
+
+ btrfs_sysfs_rm_device_link(fs_devices, tgtdev);
if (tgtdev->bdev)
- fs_info->fs_devices->open_devices--;
+ fs_devices->open_devices--;
- fs_info->fs_devices->num_devices--;
+ fs_devices->num_devices--;
btrfs_assign_next_active_device(fs_info, tgtdev, NULL);
list_del_rcu(&tgtdev->dev_list);
- mutex_unlock(&fs_info->fs_devices->device_list_mutex);
- mutex_unlock(&uuid_mutex);
+ mutex_unlock(&fs_devices->device_list_mutex);
/*
* The update_dev_time() with in btrfs_scratch_superblocks()
@@ -2188,10 +2220,6 @@ int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info,
struct btrfs_device *tmp;
devices = &fs_info->fs_devices->devices;
- /*
- * It is safe to read the devices since the volume_mutex
- * is held by the caller.
- */
list_for_each_entry(tmp, devices, dev_list) {
if (test_bit(BTRFS_DEV_STATE_IN_FS_METADATA,
&tmp->dev_state) && !tmp->bdev) {
@@ -2259,7 +2287,7 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
return PTR_ERR(old_devices);
}
- list_add(&old_devices->list, &fs_uuids);
+ list_add(&old_devices->fs_list, &fs_uuids);
memcpy(seed_devices, fs_devices, sizeof(*seed_devices));
seed_devices->opened = 1;
@@ -2570,7 +2598,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
if (trans)
btrfs_end_transaction(trans);
error_free_device:
- free_device(device);
+ btrfs_free_device(device);
error:
blkdev_put(bdev, FMODE_EXCL);
if (seeding_dev && !unlocked) {
@@ -2580,99 +2608,6 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
return ret;
}
-int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
- const char *device_path,
- struct btrfs_device *srcdev,
- struct btrfs_device **device_out)
-{
- struct btrfs_device *device;
- struct block_device *bdev;
- struct list_head *devices;
- struct rcu_string *name;
- u64 devid = BTRFS_DEV_REPLACE_DEVID;
- int ret = 0;
-
- *device_out = NULL;
- if (fs_info->fs_devices->seeding) {
- btrfs_err(fs_info, "the filesystem is a seed filesystem!");
- return -EINVAL;
- }
-
- bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
- fs_info->bdev_holder);
- if (IS_ERR(bdev)) {
- btrfs_err(fs_info, "target device %s is invalid!", device_path);
- return PTR_ERR(bdev);
- }
-
- filemap_write_and_wait(bdev->bd_inode->i_mapping);
-
- devices = &fs_info->fs_devices->devices;
- list_for_each_entry(device, devices, dev_list) {
- if (device->bdev == bdev) {
- btrfs_err(fs_info,
- "target device is in the filesystem!");
- ret = -EEXIST;
- goto error;
- }
- }
-
-
- if (i_size_read(bdev->bd_inode) <
- btrfs_device_get_total_bytes(srcdev)) {
- btrfs_err(fs_info,
- "target device is smaller than source device!");
- ret = -EINVAL;
- goto error;
- }
-
-
- device = btrfs_alloc_device(NULL, &devid, NULL);
- if (IS_ERR(device)) {
- ret = PTR_ERR(device);
- goto error;
- }
-
- name = rcu_string_strdup(device_path, GFP_KERNEL);
- if (!name) {
- free_device(device);
- ret = -ENOMEM;
- goto error;
- }
- rcu_assign_pointer(device->name, name);
-
- mutex_lock(&fs_info->fs_devices->device_list_mutex);
- set_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
- device->generation = 0;
- device->io_width = fs_info->sectorsize;
- device->io_align = fs_info->sectorsize;
- device->sector_size = fs_info->sectorsize;
- device->total_bytes = btrfs_device_get_total_bytes(srcdev);
- device->disk_total_bytes = btrfs_device_get_disk_total_bytes(srcdev);
- device->bytes_used = btrfs_device_get_bytes_used(srcdev);
- device->commit_total_bytes = srcdev->commit_total_bytes;
- device->commit_bytes_used = device->bytes_used;
- device->fs_info = fs_info;
- device->bdev = bdev;
- set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
- set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
- device->mode = FMODE_EXCL;
- device->dev_stats_valid = 1;
- set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
- device->fs_devices = fs_info->fs_devices;
- list_add(&device->dev_list, &fs_info->fs_devices->devices);
- fs_info->fs_devices->num_devices++;
- fs_info->fs_devices->open_devices++;
- mutex_unlock(&fs_info->fs_devices->device_list_mutex);
-
- *device_out = device;
- return ret;
-
-error:
- blkdev_put(bdev, FMODE_EXCL);
- return ret;
-}
-
static noinline int btrfs_update_device(struct btrfs_trans_handle *trans,
struct btrfs_device *device)
{
@@ -3273,24 +3208,12 @@ static void update_balance_args(struct btrfs_balance_control *bctl)
}
/*
- * Should be called with both balance and volume mutexes held to
- * serialize other volume operations (add_dev/rm_dev/resize) with
- * restriper. Same goes for unset_balance_control.
+ * Clear the balance status in fs_info and delete the balance item from disk.
*/
-static void set_balance_control(struct btrfs_balance_control *bctl)
-{
- struct btrfs_fs_info *fs_info = bctl->fs_info;
-
- BUG_ON(fs_info->balance_ctl);
-
- spin_lock(&fs_info->balance_lock);
- fs_info->balance_ctl = bctl;
- spin_unlock(&fs_info->balance_lock);
-}
-
-static void unset_balance_control(struct btrfs_fs_info *fs_info)
+static void reset_balance_state(struct btrfs_fs_info *fs_info)
{
struct btrfs_balance_control *bctl = fs_info->balance_ctl;
+ int ret;
BUG_ON(!fs_info->balance_ctl);
@@ -3299,6 +3222,9 @@ static void unset_balance_control(struct btrfs_fs_info *fs_info)
spin_unlock(&fs_info->balance_lock);
kfree(bctl);
+ ret = del_balance_item(fs_info);
+ if (ret)
+ btrfs_handle_fs_error(fs_info, ret, NULL);
}
/*
@@ -3835,18 +3761,6 @@ static inline int balance_need_close(struct btrfs_fs_info *fs_info)
atomic_read(&fs_info->balance_cancel_req) == 0);
}
-static void __cancel_balance(struct btrfs_fs_info *fs_info)
-{
- int ret;
-
- unset_balance_control(fs_info);
- ret = del_balance_item(fs_info);
- if (ret)
- btrfs_handle_fs_error(fs_info, ret, NULL);
-
- clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
-}
-
/* Non-zero return value signifies invalidity */
static inline int validate_convert_profile(struct btrfs_balance_args *bctl_arg,
u64 allowed)
@@ -3857,12 +3771,12 @@ static inline int validate_convert_profile(struct btrfs_balance_args *bctl_arg,
}
/*
- * Should be called with both balance and volume mutexes held
+ * Should be called with balance mutexe held
*/
-int btrfs_balance(struct btrfs_balance_control *bctl,
+int btrfs_balance(struct btrfs_fs_info *fs_info,
+ struct btrfs_balance_control *bctl,
struct btrfs_ioctl_balance_args *bargs)
{
- struct btrfs_fs_info *fs_info = bctl->fs_info;
u64 meta_target, data_target;
u64 allowed;
int mixed = 0;
@@ -3891,7 +3805,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
!(bctl->flags & BTRFS_BALANCE_METADATA) ||
memcmp(&bctl->data, &bctl->meta, sizeof(bctl->data))) {
btrfs_err(fs_info,
- "with mixed groups data and metadata balance options must be the same");
+ "balance: mixed groups data and metadata options must be the same");
ret = -EINVAL;
goto out;
}
@@ -3913,23 +3827,29 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
allowed |= (BTRFS_BLOCK_GROUP_RAID10 |
BTRFS_BLOCK_GROUP_RAID6);
if (validate_convert_profile(&bctl->data, allowed)) {
+ int index = btrfs_bg_flags_to_raid_index(bctl->data.target);
+
btrfs_err(fs_info,
- "unable to start balance with target data profile %llu",
- bctl->data.target);
+ "balance: invalid convert data profile %s",
+ get_raid_name(index));
ret = -EINVAL;
goto out;
}
if (validate_convert_profile(&bctl->meta, allowed)) {
+ int index = btrfs_bg_flags_to_raid_index(bctl->meta.target);
+
btrfs_err(fs_info,
- "unable to start balance with target metadata profile %llu",
- bctl->meta.target);
+ "balance: invalid convert metadata profile %s",
+ get_raid_name(index));
ret = -EINVAL;
goto out;
}
if (validate_convert_profile(&bctl->sys, allowed)) {
+ int index = btrfs_bg_flags_to_raid_index(bctl->sys.target);
+
btrfs_err(fs_info,
- "unable to start balance with target system profile %llu",
- bctl->sys.target);
+ "balance: invalid convert system profile %s",
+ get_raid_name(index));
ret = -EINVAL;
goto out;
}
@@ -3950,10 +3870,10 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
!(bctl->meta.target & allowed))) {
if (bctl->flags & BTRFS_BALANCE_FORCE) {
btrfs_info(fs_info,
- "force reducing metadata integrity");
+ "balance: force reducing metadata integrity");
} else {
btrfs_err(fs_info,
- "balance will reduce metadata integrity, use force if you want this");
+ "balance: reduces metadata integrity, use --force if you want this");
ret = -EINVAL;
goto out;
}
@@ -3967,9 +3887,12 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
bctl->data.target : fs_info->avail_data_alloc_bits;
if (btrfs_get_num_tolerated_disk_barrier_failures(meta_target) <
btrfs_get_num_tolerated_disk_barrier_failures(data_target)) {
+ int meta_index = btrfs_bg_flags_to_raid_index(meta_target);
+ int data_index = btrfs_bg_flags_to_raid_index(data_target);
+
btrfs_warn(fs_info,
- "metadata profile 0x%llx has lower redundancy than data profile 0x%llx",
- meta_target, data_target);
+ "balance: metadata profile %s has lower redundancy than data profile %s",
+ get_raid_name(meta_index), get_raid_name(data_index));
}
ret = insert_balance_item(fs_info, bctl);
@@ -3978,7 +3901,10 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
if (!(bctl->flags & BTRFS_BALANCE_RESUME)) {
BUG_ON(ret == -EEXIST);
- set_balance_control(bctl);
+ BUG_ON(fs_info->balance_ctl);
+ spin_lock(&fs_info->balance_lock);
+ fs_info->balance_ctl = bctl;
+ spin_unlock(&fs_info->balance_lock);
} else {
BUG_ON(ret != -EEXIST);
spin_lock(&fs_info->balance_lock);
@@ -3986,22 +3912,24 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
spin_unlock(&fs_info->balance_lock);
}
- atomic_inc(&fs_info->balance_running);
+ ASSERT(!test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags));
+ set_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags);
mutex_unlock(&fs_info->balance_mutex);
ret = __btrfs_balance(fs_info);
mutex_lock(&fs_info->balance_mutex);
- atomic_dec(&fs_info->balance_running);
+ clear_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags);
if (bargs) {
memset(bargs, 0, sizeof(*bargs));
- update_ioctl_balance_args(fs_info, 0, bargs);
+ btrfs_update_ioctl_balance_args(fs_info, bargs);
}
if ((ret && ret != -ECANCELED && ret != -ENOSPC) ||
balance_need_close(fs_info)) {
- __cancel_balance(fs_info);
+ reset_balance_state(fs_info);
+ clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
}
wake_up(&fs_info->balance_wait_q);
@@ -4009,11 +3937,11 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
return ret;
out:
if (bctl->flags & BTRFS_BALANCE_RESUME)
- __cancel_balance(fs_info);
- else {
+ reset_balance_state(fs_info);
+ else
kfree(bctl);
- clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
- }
+ clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
+
return ret;
}
@@ -4022,16 +3950,12 @@ static int balance_kthread(void *data)
struct btrfs_fs_info *fs_info = data;
int ret = 0;
- mutex_lock(&fs_info->volume_mutex);
mutex_lock(&fs_info->balance_mutex);
-
if (fs_info->balance_ctl) {
- btrfs_info(fs_info, "continuing balance");
- ret = btrfs_balance(fs_info->balance_ctl, NULL);
+ btrfs_info(fs_info, "balance: resuming");
+ ret = btrfs_balance(fs_info, fs_info->balance_ctl, NULL);
}
-
mutex_unlock(&fs_info->balance_mutex);
- mutex_unlock(&fs_info->volume_mutex);
return ret;
}
@@ -4040,18 +3964,27 @@ int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info)
{
struct task_struct *tsk;
- spin_lock(&fs_info->balance_lock);
+ mutex_lock(&fs_info->balance_mutex);
if (!fs_info->balance_ctl) {
- spin_unlock(&fs_info->balance_lock);
+ mutex_unlock(&fs_info->balance_mutex);
return 0;
}
- spin_unlock(&fs_info->balance_lock);
+ mutex_unlock(&fs_info->balance_mutex);
if (btrfs_test_opt(fs_info, SKIP_BALANCE)) {
- btrfs_info(fs_info, "force skipping balance");
+ btrfs_info(fs_info, "balance: resume skipped");
return 0;
}
+ /*
+ * A ro->rw remount sequence should continue with the paused balance
+ * regardless of who pauses it, system or the user as of now, so set
+ * the resume flag.
+ */
+ spin_lock(&fs_info->balance_lock);
+ fs_info->balance_ctl->flags |= BTRFS_BALANCE_RESUME;
+ spin_unlock(&fs_info->balance_lock);
+
tsk = kthread_run(balance_kthread, fs_info, "btrfs-balance");
return PTR_ERR_OR_ZERO(tsk);
}
@@ -4091,7 +4024,6 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info)
leaf = path->nodes[0];
item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_balance_item);
- bctl->fs_info = fs_info;
bctl->flags = btrfs_balance_flags(leaf, item);
bctl->flags |= BTRFS_BALANCE_RESUME;
@@ -4102,15 +4034,26 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info)
btrfs_balance_sys(leaf, item, &disk_bargs);
btrfs_disk_balance_args_to_cpu(&bctl->sys, &disk_bargs);
- WARN_ON(test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags));
+ /*
+ * This should never happen, as the paused balance state is recovered
+ * during mount without any chance of other exclusive ops to collide.
+ *
+ * This gives the exclusive op status to balance and keeps in paused
+ * state until user intervention (cancel or umount). If the ownership
+ * cannot be assigned, show a message but do not fail. The balance
+ * is in a paused state and must have fs_info::balance_ctl properly
+ * set up.
+ */
+ if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags))
+ btrfs_warn(fs_info,
+ "balance: cannot set exclusive op status, resume manually");
- mutex_lock(&fs_info->volume_mutex);
mutex_lock(&fs_info->balance_mutex);
-
- set_balance_control(bctl);
-
+ BUG_ON(fs_info->balance_ctl);
+ spin_lock(&fs_info->balance_lock);
+ fs_info->balance_ctl = bctl;
+ spin_unlock(&fs_info->balance_lock);
mutex_unlock(&fs_info->balance_mutex);
- mutex_unlock(&fs_info->volume_mutex);
out:
btrfs_free_path(path);
return ret;
@@ -4126,16 +4069,16 @@ int btrfs_pause_balance(struct btrfs_fs_info *fs_info)
return -ENOTCONN;
}
- if (atomic_read(&fs_info->balance_running)) {
+ if (test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)) {
atomic_inc(&fs_info->balance_pause_req);
mutex_unlock(&fs_info->balance_mutex);
wait_event(fs_info->balance_wait_q,
- atomic_read(&fs_info->balance_running) == 0);
+ !test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags));
mutex_lock(&fs_info->balance_mutex);
/* we are good with balance_ctl ripped off from under us */
- BUG_ON(atomic_read(&fs_info->balance_running));
+ BUG_ON(test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags));
atomic_dec(&fs_info->balance_pause_req);
} else {
ret = -ENOTCONN;
@@ -4147,38 +4090,49 @@ int btrfs_pause_balance(struct btrfs_fs_info *fs_info)
int btrfs_cancel_balance(struct btrfs_fs_info *fs_info)
{
- if (sb_rdonly(fs_info->sb))
- return -EROFS;
-
mutex_lock(&fs_info->balance_mutex);
if (!fs_info->balance_ctl) {
mutex_unlock(&fs_info->balance_mutex);
return -ENOTCONN;
}
+ /*
+ * A paused balance with the item stored on disk can be resumed at
+ * mount time if the mount is read-write. Otherwise it's still paused
+ * and we must not allow cancelling as it deletes the item.
+ */
+ if (sb_rdonly(fs_info->sb)) {
+ mutex_unlock(&fs_info->balance_mutex);
+ return -EROFS;
+ }
+
atomic_inc(&fs_info->balance_cancel_req);
/*
* if we are running just wait and return, balance item is
* deleted in btrfs_balance in this case
*/
- if (atomic_read(&fs_info->balance_running)) {
+ if (test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)) {
mutex_unlock(&fs_info->balance_mutex);
wait_event(fs_info->balance_wait_q,
- atomic_read(&fs_info->balance_running) == 0);
+ !test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags));
mutex_lock(&fs_info->balance_mutex);
} else {
- /* __cancel_balance needs volume_mutex */
mutex_unlock(&fs_info->balance_mutex);
- mutex_lock(&fs_info->volume_mutex);
+ /*
+ * Lock released to allow other waiters to continue, we'll
+ * reexamine the status again.
+ */
mutex_lock(&fs_info->balance_mutex);
- if (fs_info->balance_ctl)
- __cancel_balance(fs_info);
-
- mutex_unlock(&fs_info->volume_mutex);
+ if (fs_info->balance_ctl) {
+ reset_balance_state(fs_info);
+ clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
+ btrfs_info(fs_info, "balance: canceled");
+ }
}
- BUG_ON(fs_info->balance_ctl || atomic_read(&fs_info->balance_running));
+ BUG_ON(fs_info->balance_ctl ||
+ test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags));
atomic_dec(&fs_info->balance_cancel_req);
mutex_unlock(&fs_info->balance_mutex);
return 0;
@@ -4255,8 +4209,7 @@ static int btrfs_uuid_scan_kthread(void *data)
}
update_tree:
if (!btrfs_is_empty_uuid(root_item.uuid)) {
- ret = btrfs_uuid_tree_add(trans, fs_info,
- root_item.uuid,
+ ret = btrfs_uuid_tree_add(trans, root_item.uuid,
BTRFS_UUID_KEY_SUBVOL,
key.objectid);
if (ret < 0) {
@@ -4267,7 +4220,7 @@ static int btrfs_uuid_scan_kthread(void *data)
}
if (!btrfs_is_empty_uuid(root_item.received_uuid)) {
- ret = btrfs_uuid_tree_add(trans, fs_info,
+ ret = btrfs_uuid_tree_add(trans,
root_item.received_uuid,
BTRFS_UUID_KEY_RECEIVED_SUBVOL,
key.objectid);
@@ -4473,7 +4426,7 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size)
if (!path)
return -ENOMEM;
- path->reada = READA_FORWARD;
+ path->reada = READA_BACK;
mutex_lock(&fs_info->chunk_mutex);
@@ -6034,9 +5987,8 @@ int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
return __btrfs_map_block(fs_info, op, logical, length, bbio_ret, 0, 1);
}
-int btrfs_rmap_block(struct btrfs_fs_info *fs_info,
- u64 chunk_start, u64 physical, u64 devid,
- u64 **logical, int *naddrs, int *stripe_len)
+int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
+ u64 physical, u64 **logical, int *naddrs, int *stripe_len)
{
struct extent_map *em;
struct map_lookup *map;
@@ -6068,8 +6020,6 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info,
BUG_ON(!buf); /* -ENOMEM */
for (i = 0; i < map->num_stripes; i++) {
- if (devid && map->stripes[i].dev->devid != devid)
- continue;
if (map->stripes[i].physical > physical ||
map->stripes[i].physical + length <= physical)
continue;
@@ -6401,7 +6351,7 @@ static struct btrfs_device *add_missing_dev(struct btrfs_fs_devices *fs_devices,
*
* Return: a pointer to a new &struct btrfs_device on success; ERR_PTR()
* on error. Returned struct is not linked onto any lists and must be
- * destroyed with free_device.
+ * destroyed with btrfs_free_device.
*/
struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
const u64 *devid,
@@ -6424,7 +6374,7 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
ret = find_next_devid(fs_info, &tmp);
if (ret) {
- free_device(dev);
+ btrfs_free_device(dev);
return ERR_PTR(ret);
}
}
@@ -6675,8 +6625,7 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info,
if (IS_ERR(fs_devices))
return fs_devices;
- ret = __btrfs_open_devices(fs_devices, FMODE_READ,
- fs_info->bdev_holder);
+ ret = open_fs_devices(fs_devices, FMODE_READ, fs_info->bdev_holder);
if (ret) {
free_fs_devices(fs_devices);
fs_devices = ERR_PTR(ret);
@@ -6684,7 +6633,7 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info,
}
if (!fs_devices->seeding) {
- __btrfs_close_devices(fs_devices);
+ close_fs_devices(fs_devices);
free_fs_devices(fs_devices);
fs_devices = ERR_PTR(-EINVAL);
goto out;
@@ -6993,6 +6942,10 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
if (!path)
return -ENOMEM;
+ /*
+ * uuid_mutex is needed only if we are mounting a sprout FS
+ * otherwise we don't need it.
+ */
mutex_lock(&uuid_mutex);
mutex_lock(&fs_info->chunk_mutex);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 7909688..5139ec8 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -208,6 +208,7 @@ BTRFS_DEVICE_GETSET_FUNCS(bytes_used);
struct btrfs_fs_devices {
u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */
+ struct list_head fs_list;
u64 num_devices;
u64 open_devices;
@@ -229,7 +230,6 @@ struct btrfs_fs_devices {
struct list_head resized_devices;
/* devices not currently being allocated */
struct list_head alloc_list;
- struct list_head list;
struct btrfs_fs_devices *seed;
int seeding;
@@ -329,11 +329,12 @@ struct btrfs_raid_attr {
int tolerated_failures; /* max tolerated fail devs */
int devs_increment; /* ndevs has to be a multiple of this */
int ncopies; /* how many copies to data has */
+ int mindev_error; /* error code if min devs requisite is unmet */
+ const char raid_name[8]; /* name of the raid */
+ u64 bg_flag; /* block group flag of the raid */
};
extern const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES];
-extern const int btrfs_raid_mindev_error[BTRFS_NR_RAID_TYPES];
-extern const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES];
struct map_lookup {
u64 type;
@@ -351,8 +352,6 @@ struct map_lookup {
struct btrfs_balance_args;
struct btrfs_balance_progress;
struct btrfs_balance_control {
- struct btrfs_fs_info *fs_info;
-
struct btrfs_balance_args data;
struct btrfs_balance_args meta;
struct btrfs_balance_args sys;
@@ -393,9 +392,8 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
u64 logical, u64 *length,
struct btrfs_bio **bbio_ret);
-int btrfs_rmap_block(struct btrfs_fs_info *fs_info,
- u64 chunk_start, u64 physical, u64 devid,
- u64 **logical, int *naddrs, int *stripe_len);
+int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
+ u64 physical, u64 **logical, int *naddrs, int *stripe_len);
int btrfs_read_sys_array(struct btrfs_fs_info *fs_info);
int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info);
int btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
@@ -421,6 +419,7 @@ int btrfs_find_device_by_devspec(struct btrfs_fs_info *fs_info, u64 devid,
struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
const u64 *devid,
const u8 *uuid);
+void btrfs_free_device(struct btrfs_device *device);
int btrfs_rm_device(struct btrfs_fs_info *fs_info,
const char *device_path, u64 devid);
void __exit btrfs_cleanup_fs_uuids(void);
@@ -431,11 +430,8 @@ struct btrfs_device *btrfs_find_device(struct btrfs_fs_info *fs_info, u64 devid,
u8 *uuid, u8 *fsid);
int btrfs_shrink_device(struct btrfs_device *device, u64 new_size);
int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *path);
-int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
- const char *device_path,
- struct btrfs_device *srcdev,
- struct btrfs_device **device_out);
-int btrfs_balance(struct btrfs_balance_control *bctl,
+int btrfs_balance(struct btrfs_fs_info *fs_info,
+ struct btrfs_balance_control *bctl,
struct btrfs_ioctl_balance_args *bargs);
int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info);
int btrfs_recover_balance(struct btrfs_fs_info *fs_info);
@@ -553,6 +549,8 @@ static inline enum btrfs_raid_types btrfs_bg_flags_to_raid_index(u64 flags)
return BTRFS_RAID_SINGLE; /* BTRFS_BLOCK_GROUP_SINGLE */
}
+const char *get_raid_name(enum btrfs_raid_types type);
+
void btrfs_update_commit_device_size(struct btrfs_fs_info *fs_info);
void btrfs_update_commit_device_bytes_used(struct btrfs_transaction *trans);
diff --git a/fs/buffer.c b/fs/buffer.c
index 249b83f..cabc045 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3427,120 +3427,6 @@ int bh_submit_read(struct buffer_head *bh)
}
EXPORT_SYMBOL(bh_submit_read);
-/*
- * Seek for SEEK_DATA / SEEK_HOLE within @page, starting at @lastoff.
- *
- * Returns the offset within the file on success, and -ENOENT otherwise.
- */
-static loff_t
-page_seek_hole_data(struct page *page, loff_t lastoff, int whence)
-{
- loff_t offset = page_offset(page);
- struct buffer_head *bh, *head;
- bool seek_data = whence == SEEK_DATA;
-
- if (lastoff < offset)
- lastoff = offset;
-
- bh = head = page_buffers(page);
- do {
- offset += bh->b_size;
- if (lastoff >= offset)
- continue;
-
- /*
- * Unwritten extents that have data in the page cache covering
- * them can be identified by the BH_Unwritten state flag.
- * Pages with multiple buffers might have a mix of holes, data
- * and unwritten extents - any buffer with valid data in it
- * should have BH_Uptodate flag set on it.
- */
-
- if ((buffer_unwritten(bh) || buffer_uptodate(bh)) == seek_data)
- return lastoff;
-
- lastoff = offset;
- } while ((bh = bh->b_this_page) != head);
- return -ENOENT;
-}
-
-/*
- * Seek for SEEK_DATA / SEEK_HOLE in the page cache.
- *
- * Within unwritten extents, the page cache determines which parts are holes
- * and which are data: unwritten and uptodate buffer heads count as data;
- * everything else counts as a hole.
- *
- * Returns the resulting offset on successs, and -ENOENT otherwise.
- */
-loff_t
-page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length,
- int whence)
-{
- pgoff_t index = offset >> PAGE_SHIFT;
- pgoff_t end = DIV_ROUND_UP(offset + length, PAGE_SIZE);
- loff_t lastoff = offset;
- struct pagevec pvec;
-
- if (length <= 0)
- return -ENOENT;
-
- pagevec_init(&pvec);
-
- do {
- unsigned nr_pages, i;
-
- nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping, &index,
- end - 1);
- if (nr_pages == 0)
- break;
-
- for (i = 0; i < nr_pages; i++) {
- struct page *page = pvec.pages[i];
-
- /*
- * At this point, the page may be truncated or
- * invalidated (changing page->mapping to NULL), or
- * even swizzled back from swapper_space to tmpfs file
- * mapping. However, page->index will not change
- * because we have a reference on the page.
- *
- * If current page offset is beyond where we've ended,
- * we've found a hole.
- */
- if (whence == SEEK_HOLE &&
- lastoff < page_offset(page))
- goto check_range;
-
- lock_page(page);
- if (likely(page->mapping == inode->i_mapping) &&
- page_has_buffers(page)) {
- lastoff = page_seek_hole_data(page, lastoff, whence);
- if (lastoff >= 0) {
- unlock_page(page);
- goto check_range;
- }
- }
- unlock_page(page);
- lastoff = page_offset(page) + PAGE_SIZE;
- }
- pagevec_release(&pvec);
- } while (index < end);
-
- /* When no page at lastoff and we are not done, we found a hole. */
- if (whence != SEEK_HOLE)
- goto not_found;
-
-check_range:
- if (lastoff < offset + length)
- goto out;
-not_found:
- lastoff = -ENOENT;
-out:
- pagevec_release(&pvec);
- return lastoff;
-}
-
void __init buffer_init(void)
{
unsigned long nrpages;
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 0daa1e3..ab0bbe9 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -572,6 +572,11 @@ int cachefiles_walk_to_object(struct cachefiles_object *parent,
if (ret < 0)
goto create_error;
+ if (unlikely(d_unhashed(next))) {
+ dput(next);
+ inode_unlock(d_inode(dir));
+ goto lookup_again;
+ }
ASSERT(d_backing_inode(next));
_debug("mkdir -> %p{%p{ino=%lu}}",
@@ -764,6 +769,7 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
/* search the current directory for the element name */
inode_lock(d_inode(dir));
+retry:
start = jiffies;
subdir = lookup_one_len(dirname, dir, strlen(dirname));
cachefiles_hist(cachefiles_lookup_histogram, start);
@@ -793,6 +799,10 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
if (ret < 0)
goto mkdir_error;
+ if (unlikely(d_unhashed(subdir))) {
+ dput(subdir);
+ goto retry;
+ }
ASSERT(d_backing_inode(subdir));
_debug("mkdir -> %p{%p{ino=%lu}}",
diff --git a/fs/cachefiles/proc.c b/fs/cachefiles/proc.c
index 125b90f6..0ce1aa5 100644
--- a/fs/cachefiles/proc.c
+++ b/fs/cachefiles/proc.c
@@ -85,21 +85,6 @@ static const struct seq_operations cachefiles_histogram_ops = {
};
/*
- * open "/proc/fs/cachefiles/XXX" which provide statistics summaries
- */
-static int cachefiles_histogram_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &cachefiles_histogram_ops);
-}
-
-static const struct file_operations cachefiles_histogram_fops = {
- .open = cachefiles_histogram_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-/*
* initialise the /proc/fs/cachefiles/ directory
*/
int __init cachefiles_proc_init(void)
@@ -109,8 +94,8 @@ int __init cachefiles_proc_init(void)
if (!proc_mkdir("fs/cachefiles", NULL))
goto error_dir;
- if (!proc_create("fs/cachefiles/histogram", S_IFREG | 0444, NULL,
- &cachefiles_histogram_fops))
+ if (!proc_create_seq("fs/cachefiles/histogram", S_IFREG | 0444, NULL,
+ &cachefiles_histogram_ops))
goto error_histogram;
_leave(" = 0");
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index f85040d..cf0e45b 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -70,69 +70,104 @@ static __le32 ceph_flags_sys2wire(u32 flags)
*/
/*
- * Calculate the length sum of direct io vectors that can
- * be combined into one page vector.
+ * How many pages to get in one call to iov_iter_get_pages(). This
+ * determines the size of the on-stack array used as a buffer.
*/
-static size_t dio_get_pagev_size(const struct iov_iter *it)
-{
- const struct iovec *iov = it->iov;
- const struct iovec *iovend = iov + it->nr_segs;
- size_t size;
+#define ITER_GET_BVECS_PAGES 64
- size = iov->iov_len - it->iov_offset;
- /*
- * An iov can be page vectored when both the current tail
- * and the next base are page aligned.
- */
- while (PAGE_ALIGNED((iov->iov_base + iov->iov_len)) &&
- (++iov < iovend && PAGE_ALIGNED((iov->iov_base)))) {
- size += iov->iov_len;
- }
- dout("dio_get_pagevlen len = %zu\n", size);
- return size;
+static ssize_t __iter_get_bvecs(struct iov_iter *iter, size_t maxsize,
+ struct bio_vec *bvecs)
+{
+ size_t size = 0;
+ int bvec_idx = 0;
+
+ if (maxsize > iov_iter_count(iter))
+ maxsize = iov_iter_count(iter);
+
+ while (size < maxsize) {
+ struct page *pages[ITER_GET_BVECS_PAGES];
+ ssize_t bytes;
+ size_t start;
+ int idx = 0;
+
+ bytes = iov_iter_get_pages(iter, pages, maxsize - size,
+ ITER_GET_BVECS_PAGES, &start);
+ if (bytes < 0)
+ return size ?: bytes;
+
+ iov_iter_advance(iter, bytes);
+ size += bytes;
+
+ for ( ; bytes; idx++, bvec_idx++) {
+ struct bio_vec bv = {
+ .bv_page = pages[idx],
+ .bv_len = min_t(int, bytes, PAGE_SIZE - start),
+ .bv_offset = start,
+ };
+
+ bvecs[bvec_idx] = bv;
+ bytes -= bv.bv_len;
+ start = 0;
+ }
+ }
+
+ return size;
}
/*
- * Allocate a page vector based on (@it, @nbytes).
- * The return value is the tuple describing a page vector,
- * that is (@pages, @page_align, @num_pages).
+ * iov_iter_get_pages() only considers one iov_iter segment, no matter
+ * what maxsize or maxpages are given. For ITER_BVEC that is a single
+ * page.
+ *
+ * Attempt to get up to @maxsize bytes worth of pages from @iter.
+ * Return the number of bytes in the created bio_vec array, or an error.
*/
-static struct page **
-dio_get_pages_alloc(const struct iov_iter *it, size_t nbytes,
- size_t *page_align, int *num_pages)
+static ssize_t iter_get_bvecs_alloc(struct iov_iter *iter, size_t maxsize,
+ struct bio_vec **bvecs, int *num_bvecs)
{
- struct iov_iter tmp_it = *it;
- size_t align;
- struct page **pages;
- int ret = 0, idx, npages;
+ struct bio_vec *bv;
+ size_t orig_count = iov_iter_count(iter);
+ ssize_t bytes;
+ int npages;
- align = (unsigned long)(it->iov->iov_base + it->iov_offset) &
- (PAGE_SIZE - 1);
- npages = calc_pages_for(align, nbytes);
- pages = kvmalloc(sizeof(*pages) * npages, GFP_KERNEL);
- if (!pages)
- return ERR_PTR(-ENOMEM);
+ iov_iter_truncate(iter, maxsize);
+ npages = iov_iter_npages(iter, INT_MAX);
+ iov_iter_reexpand(iter, orig_count);
- for (idx = 0; idx < npages; ) {
- size_t start;
- ret = iov_iter_get_pages(&tmp_it, pages + idx, nbytes,
- npages - idx, &start);
- if (ret < 0)
- goto fail;
+ /*
+ * __iter_get_bvecs() may populate only part of the array -- zero it
+ * out.
+ */
+ bv = kvmalloc_array(npages, sizeof(*bv), GFP_KERNEL | __GFP_ZERO);
+ if (!bv)
+ return -ENOMEM;
- iov_iter_advance(&tmp_it, ret);
- nbytes -= ret;
- idx += (ret + start + PAGE_SIZE - 1) / PAGE_SIZE;
+ bytes = __iter_get_bvecs(iter, maxsize, bv);
+ if (bytes < 0) {
+ /*
+ * No pages were pinned -- just free the array.
+ */
+ kvfree(bv);
+ return bytes;
}
- BUG_ON(nbytes != 0);
- *num_pages = npages;
- *page_align = align;
- dout("dio_get_pages_alloc: got %d pages align %zu\n", npages, align);
- return pages;
-fail:
- ceph_put_page_vector(pages, idx, false);
- return ERR_PTR(ret);
+ *bvecs = bv;
+ *num_bvecs = npages;
+ return bytes;
+}
+
+static void put_bvecs(struct bio_vec *bvecs, int num_bvecs, bool should_dirty)
+{
+ int i;
+
+ for (i = 0; i < num_bvecs; i++) {
+ if (bvecs[i].bv_page) {
+ if (should_dirty)
+ set_page_dirty_lock(bvecs[i].bv_page);
+ put_page(bvecs[i].bv_page);
+ }
+ }
+ kvfree(bvecs);
}
/*
@@ -746,11 +781,12 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req)
struct inode *inode = req->r_inode;
struct ceph_aio_request *aio_req = req->r_priv;
struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
- int num_pages = calc_pages_for((u64)osd_data->alignment,
- osd_data->length);
- dout("ceph_aio_complete_req %p rc %d bytes %llu\n",
- inode, rc, osd_data->length);
+ BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_BVECS);
+ BUG_ON(!osd_data->num_bvecs);
+
+ dout("ceph_aio_complete_req %p rc %d bytes %u\n",
+ inode, rc, osd_data->bvec_pos.iter.bi_size);
if (rc == -EOLDSNAPC) {
struct ceph_aio_work *aio_work;
@@ -768,9 +804,10 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req)
} else if (!aio_req->write) {
if (rc == -ENOENT)
rc = 0;
- if (rc >= 0 && osd_data->length > rc) {
- int zoff = osd_data->alignment + rc;
- int zlen = osd_data->length - rc;
+ if (rc >= 0 && osd_data->bvec_pos.iter.bi_size > rc) {
+ struct iov_iter i;
+ int zlen = osd_data->bvec_pos.iter.bi_size - rc;
+
/*
* If read is satisfied by single OSD request,
* it can pass EOF. Otherwise read is within
@@ -785,13 +822,16 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req)
aio_req->total_len = rc + zlen;
}
- if (zlen > 0)
- ceph_zero_page_vector_range(zoff, zlen,
- osd_data->pages);
+ iov_iter_bvec(&i, ITER_BVEC, osd_data->bvec_pos.bvecs,
+ osd_data->num_bvecs,
+ osd_data->bvec_pos.iter.bi_size);
+ iov_iter_advance(&i, rc);
+ iov_iter_zero(zlen, &i);
}
}
- ceph_put_page_vector(osd_data->pages, num_pages, aio_req->should_dirty);
+ put_bvecs(osd_data->bvec_pos.bvecs, osd_data->num_bvecs,
+ aio_req->should_dirty);
ceph_osdc_put_request(req);
if (rc < 0)
@@ -879,7 +919,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_vino vino;
struct ceph_osd_request *req;
- struct page **pages;
+ struct bio_vec *bvecs;
struct ceph_aio_request *aio_req = NULL;
int num_pages = 0;
int flags;
@@ -914,10 +954,14 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
}
while (iov_iter_count(iter) > 0) {
- u64 size = dio_get_pagev_size(iter);
- size_t start = 0;
+ u64 size = iov_iter_count(iter);
ssize_t len;
+ if (write)
+ size = min_t(u64, size, fsc->mount_options->wsize);
+ else
+ size = min_t(u64, size, fsc->mount_options->rsize);
+
vino = ceph_vino(inode);
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
vino, pos, &size, 0,
@@ -933,18 +977,14 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
break;
}
- if (write)
- size = min_t(u64, size, fsc->mount_options->wsize);
- else
- size = min_t(u64, size, fsc->mount_options->rsize);
-
- len = size;
- pages = dio_get_pages_alloc(iter, len, &start, &num_pages);
- if (IS_ERR(pages)) {
+ len = iter_get_bvecs_alloc(iter, size, &bvecs, &num_pages);
+ if (len < 0) {
ceph_osdc_put_request(req);
- ret = PTR_ERR(pages);
+ ret = len;
break;
}
+ if (len != size)
+ osd_req_op_extent_update(req, 0, len);
/*
* To simplify error handling, allow AIO when IO within i_size
@@ -977,8 +1017,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
req->r_mtime = mtime;
}
- osd_req_op_extent_osd_data_pages(req, 0, pages, len, start,
- false, false);
+ osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len);
if (aio_req) {
aio_req->total_len += len;
@@ -991,7 +1030,6 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
list_add_tail(&req->r_unsafe_item, &aio_req->osd_reqs);
pos += len;
- iov_iter_advance(iter, len);
continue;
}
@@ -1004,25 +1042,26 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
if (ret == -ENOENT)
ret = 0;
if (ret >= 0 && ret < len && pos + ret < size) {
+ struct iov_iter i;
int zlen = min_t(size_t, len - ret,
size - pos - ret);
- ceph_zero_page_vector_range(start + ret, zlen,
- pages);
+
+ iov_iter_bvec(&i, ITER_BVEC, bvecs, num_pages,
+ len);
+ iov_iter_advance(&i, ret);
+ iov_iter_zero(zlen, &i);
ret += zlen;
}
if (ret >= 0)
len = ret;
}
- ceph_put_page_vector(pages, num_pages, should_dirty);
-
+ put_bvecs(bvecs, num_pages, should_dirty);
ceph_osdc_put_request(req);
if (ret < 0)
break;
pos += len;
- iov_iter_advance(iter, len);
-
if (!write && pos >= size)
break;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 8bf6025..ae05692 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -669,13 +669,15 @@ void ceph_fill_file_time(struct inode *inode, int issued,
CEPH_CAP_FILE_BUFFER|
CEPH_CAP_AUTH_EXCL|
CEPH_CAP_XATTR_EXCL)) {
- if (timespec_compare(ctime, &inode->i_ctime) > 0) {
+ if (ci->i_version == 0 ||
+ timespec_compare(ctime, &inode->i_ctime) > 0) {
dout("ctime %ld.%09ld -> %ld.%09ld inc w/ cap\n",
inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec,
ctime->tv_sec, ctime->tv_nsec);
inode->i_ctime = *ctime;
}
- if (ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) > 0) {
+ if (ci->i_version == 0 ||
+ ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) > 0) {
/* the MDS did a utimes() */
dout("mtime %ld.%09ld -> %ld.%09ld "
"tw %d -> %d\n",
@@ -795,7 +797,6 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
new_issued = ~issued & le32_to_cpu(info->cap.caps);
/* update inode */
- ci->i_version = le64_to_cpu(info->version);
inode->i_rdev = le32_to_cpu(info->rdev);
inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
@@ -868,6 +869,9 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
xattr_blob = NULL;
}
+ /* finally update i_version */
+ ci->i_version = le64_to_cpu(info->version);
+
inode->i_mapping->a_ops = &ceph_aops;
switch (inode->i_mode & S_IFMT) {
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 7e72348..315f7e6 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -228,7 +228,15 @@ static size_t ceph_vxattrcb_dir_rctime(struct ceph_inode_info *ci, char *val,
static bool ceph_vxattrcb_quota_exists(struct ceph_inode_info *ci)
{
- return (ci->i_max_files || ci->i_max_bytes);
+ bool ret = false;
+ spin_lock(&ci->i_ceph_lock);
+ if ((ci->i_max_files || ci->i_max_bytes) &&
+ ci->i_vino.snap == CEPH_NOSNAP &&
+ ci->i_snap_realm &&
+ ci->i_snap_realm->ino == ci->i_vino.ino)
+ ret = true;
+ spin_unlock(&ci->i_ceph_lock);
+ return ret;
}
static size_t ceph_vxattrcb_quota(struct ceph_inode_info *ci, char *val,
@@ -1008,14 +1016,19 @@ int __ceph_setxattr(struct inode *inode, const char *name,
char *newval = NULL;
struct ceph_inode_xattr *xattr = NULL;
int required_blob_size;
+ bool check_realm = false;
bool lock_snap_rwsem = false;
if (ceph_snap(inode) != CEPH_NOSNAP)
return -EROFS;
vxattr = ceph_match_vxattr(inode, name);
- if (vxattr && vxattr->readonly)
- return -EOPNOTSUPP;
+ if (vxattr) {
+ if (vxattr->readonly)
+ return -EOPNOTSUPP;
+ if (value && !strncmp(vxattr->name, "ceph.quota", 10))
+ check_realm = true;
+ }
/* pass any unhandled ceph.* xattrs through to the MDS */
if (!strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN))
@@ -1109,6 +1122,15 @@ int __ceph_setxattr(struct inode *inode, const char *name,
err = -EBUSY;
} else {
err = ceph_sync_setxattr(inode, name, value, size, flags);
+ if (err >= 0 && check_realm) {
+ /* check if snaprealm was created for quota inode */
+ spin_lock(&ci->i_ceph_lock);
+ if ((ci->i_max_files || ci->i_max_bytes) &&
+ !(ci->i_snap_realm &&
+ ci->i_snap_realm->ino == ci->i_vino.ino))
+ err = -EOPNOTSUPP;
+ spin_unlock(&ci->i_ceph_lock);
+ }
}
out:
ceph_free_cap_flush(prealloc_cf);
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index 741749a..5f132d5 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -197,7 +197,7 @@
config CIFS_SMB_DIRECT
bool "SMB Direct support (Experimental)"
- depends on CIFS=m && INFINIBAND || CIFS=y && INFINIBAND=y
+ depends on CIFS=m && INFINIBAND && INFINIBAND_ADDR_TRANS || CIFS=y && INFINIBAND=y && INFINIBAND_ADDR_TRANS=y
help
Enables SMB Direct experimental support for SMB 3.0, 3.02 and 3.1.1.
SMB Direct allows transferring SMB packets over RDMA. If unsure,
diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile
index 7e4a1e2..8581799 100644
--- a/fs/cifs/Makefile
+++ b/fs/cifs/Makefile
@@ -1,11 +1,12 @@
# SPDX-License-Identifier: GPL-2.0
#
-# Makefile for Linux CIFS VFS client
+# Makefile for Linux CIFS/SMB2/SMB3 VFS client
#
+ccflags-y += -I$(src) # needed for trace events
obj-$(CONFIG_CIFS) += cifs.o
-cifs-y := cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o inode.o \
- link.o misc.o netmisc.o smbencrypt.o transport.o asn1.o \
+cifs-y := trace.o cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o \
+ inode.o link.o misc.o netmisc.o smbencrypt.o transport.o asn1.o \
cifs_unicode.o nterr.o cifsencrypt.o \
readdir.o ioctl.o sess.o export.o smb1ops.o winucase.o \
smb2ops.o smb2maperror.o smb2transport.o \
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 9d69ea4..1161460 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -42,7 +42,7 @@ cifs_dump_mem(char *label, void *data, int length)
data, length, true);
}
-void cifs_dump_detail(void *buf)
+void cifs_dump_detail(void *buf, struct TCP_Server_Info *server)
{
#ifdef CONFIG_CIFS_DEBUG2
struct smb_hdr *smb = (struct smb_hdr *)buf;
@@ -50,7 +50,8 @@ void cifs_dump_detail(void *buf)
cifs_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d\n",
smb->Command, smb->Status.CifsError,
smb->Flags, smb->Flags2, smb->Mid, smb->Pid);
- cifs_dbg(VFS, "smb buf %p len %u\n", smb, smbCalcSize(smb));
+ cifs_dbg(VFS, "smb buf %p len %u\n", smb,
+ server->ops->calc_smb_size(smb, server));
#endif /* CONFIG_CIFS_DEBUG2 */
}
@@ -83,7 +84,7 @@ void cifs_dump_mids(struct TCP_Server_Info *server)
cifs_dbg(VFS, "IsMult: %d IsEnd: %d\n",
mid_entry->multiRsp, mid_entry->multiEnd);
if (mid_entry->resp_buf) {
- cifs_dump_detail(mid_entry->resp_buf);
+ cifs_dump_detail(mid_entry->resp_buf, server);
cifs_dump_mem("existing buf: ",
mid_entry->resp_buf, 62);
}
@@ -113,6 +114,8 @@ static void cifs_debug_tcon(struct seq_file *m, struct cifs_tcon *tcon)
seq_printf(m, " type: %d ", dev_type);
if (tcon->seal)
seq_printf(m, " Encrypted");
+ if (tcon->nocase)
+ seq_printf(m, " nocase");
if (tcon->unix_ext)
seq_printf(m, " POSIX Extensions");
if (tcon->ses->server->ops->dump_share_caps)
@@ -237,6 +240,10 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
server->credits, server->dialect);
if (server->sign)
seq_printf(m, " signed");
+#ifdef CONFIG_CIFS_SMB311
+ if (server->posix_ext_supported)
+ seq_printf(m, " posix");
+#endif /* 3.1.1 */
i++;
list_for_each(tmp2, &server->smb_ses_list) {
ses = list_entry(tmp2, struct cifs_ses,
@@ -314,18 +321,6 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int cifs_debug_data_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, cifs_debug_data_proc_show, NULL);
-}
-
-static const struct file_operations cifs_debug_data_proc_fops = {
- .open = cifs_debug_data_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
#ifdef CONFIG_CIFS_STATS
static ssize_t cifs_stats_proc_write(struct file *file,
const char __user *buffer, size_t count, loff_t *ppos)
@@ -497,35 +492,36 @@ cifs_proc_init(void)
if (proc_fs_cifs == NULL)
return;
- proc_create("DebugData", 0, proc_fs_cifs, &cifs_debug_data_proc_fops);
+ proc_create_single("DebugData", 0, proc_fs_cifs,
+ cifs_debug_data_proc_show);
#ifdef CONFIG_CIFS_STATS
- proc_create("Stats", 0, proc_fs_cifs, &cifs_stats_proc_fops);
+ proc_create("Stats", 0644, proc_fs_cifs, &cifs_stats_proc_fops);
#endif /* STATS */
- proc_create("cifsFYI", 0, proc_fs_cifs, &cifsFYI_proc_fops);
- proc_create("traceSMB", 0, proc_fs_cifs, &traceSMB_proc_fops);
- proc_create("LinuxExtensionsEnabled", 0, proc_fs_cifs,
+ proc_create("cifsFYI", 0644, proc_fs_cifs, &cifsFYI_proc_fops);
+ proc_create("traceSMB", 0644, proc_fs_cifs, &traceSMB_proc_fops);
+ proc_create("LinuxExtensionsEnabled", 0644, proc_fs_cifs,
&cifs_linux_ext_proc_fops);
- proc_create("SecurityFlags", 0, proc_fs_cifs,
+ proc_create("SecurityFlags", 0644, proc_fs_cifs,
&cifs_security_flags_proc_fops);
- proc_create("LookupCacheEnabled", 0, proc_fs_cifs,
+ proc_create("LookupCacheEnabled", 0644, proc_fs_cifs,
&cifs_lookup_cache_proc_fops);
#ifdef CONFIG_CIFS_SMB_DIRECT
- proc_create("rdma_readwrite_threshold", 0, proc_fs_cifs,
+ proc_create("rdma_readwrite_threshold", 0644, proc_fs_cifs,
&cifs_rdma_readwrite_threshold_proc_fops);
- proc_create("smbd_max_frmr_depth", 0, proc_fs_cifs,
+ proc_create("smbd_max_frmr_depth", 0644, proc_fs_cifs,
&cifs_smbd_max_frmr_depth_proc_fops);
- proc_create("smbd_keep_alive_interval", 0, proc_fs_cifs,
+ proc_create("smbd_keep_alive_interval", 0644, proc_fs_cifs,
&cifs_smbd_keep_alive_interval_proc_fops);
- proc_create("smbd_max_receive_size", 0, proc_fs_cifs,
+ proc_create("smbd_max_receive_size", 0644, proc_fs_cifs,
&cifs_smbd_max_receive_size_proc_fops);
- proc_create("smbd_max_fragmented_recv_size", 0, proc_fs_cifs,
+ proc_create("smbd_max_fragmented_recv_size", 0644, proc_fs_cifs,
&cifs_smbd_max_fragmented_recv_size_proc_fops);
- proc_create("smbd_max_send_size", 0, proc_fs_cifs,
+ proc_create("smbd_max_send_size", 0644, proc_fs_cifs,
&cifs_smbd_max_send_size_proc_fops);
- proc_create("smbd_send_credit_target", 0, proc_fs_cifs,
+ proc_create("smbd_send_credit_target", 0644, proc_fs_cifs,
&cifs_smbd_send_credit_target_proc_fops);
- proc_create("smbd_receive_credit_max", 0, proc_fs_cifs,
+ proc_create("smbd_receive_credit_max", 0644, proc_fs_cifs,
&cifs_smbd_receive_credit_max_proc_fops);
#endif
}
@@ -583,6 +579,8 @@ static ssize_t cifsFYI_proc_write(struct file *file, const char __user *buffer,
cifsFYI = bv;
else if ((c[0] > '1') && (c[0] <= '9'))
cifsFYI = (int) (c[0] - '0'); /* see cifs_debug.h for meanings */
+ else
+ return -EINVAL;
return count;
}
diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h
index fe55676..f4f3f08 100644
--- a/fs/cifs/cifs_debug.h
+++ b/fs/cifs/cifs_debug.h
@@ -23,7 +23,7 @@
#define _H_CIFS_DEBUG
void cifs_dump_mem(char *label, void *data, int length);
-void cifs_dump_detail(void *);
+void cifs_dump_detail(void *buf, struct TCP_Server_Info *ptcp_info);
void cifs_dump_mids(struct TCP_Server_Info *);
extern bool traceSMB; /* flag which enables the function below */
void dump_smb(void *, int);
@@ -54,7 +54,7 @@ do { \
pr_debug_ ## ratefunc("%s: " \
fmt, __FILE__, ##__VA_ARGS__); \
} else if ((type) & VFS) { \
- pr_err_ ## ratefunc("CuIFS VFS: " \
+ pr_err_ ## ratefunc("CIFS VFS: " \
fmt, ##__VA_ARGS__); \
} else if ((type) & NOISY && (NOISY != 0)) { \
pr_debug_ ## ratefunc(fmt, ##__VA_ARGS__); \
diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h
index 350fa55..9731d0d 100644
--- a/fs/cifs/cifs_fs_sb.h
+++ b/fs/cifs/cifs_fs_sb.h
@@ -50,6 +50,7 @@
* root mountable
*/
#define CIFS_MOUNT_UID_FROM_ACL 0x2000000 /* try to get UID via special SID */
+#define CIFS_MOUNT_NO_HANDLE_CACHE 0x4000000 /* disable caching dir handles */
struct cifs_sb_info {
struct rb_root tlink_tree;
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index f715609..eb7b657 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -58,13 +58,15 @@ bool traceSMB;
bool enable_oplocks = true;
bool linuxExtEnabled = true;
bool lookupCacheEnabled = true;
+bool disable_legacy_dialects; /* false by default */
unsigned int global_secflags = CIFSSEC_DEF;
/* unsigned int ntlmv2_support = 0; */
unsigned int sign_CIFS_PDUs = 1;
static const struct super_operations cifs_super_ops;
unsigned int CIFSMaxBufSize = CIFS_MAX_MSGSIZE;
module_param(CIFSMaxBufSize, uint, 0444);
-MODULE_PARM_DESC(CIFSMaxBufSize, "Network buffer size (not including header). "
+MODULE_PARM_DESC(CIFSMaxBufSize, "Network buffer size (not including header) "
+ "for CIFS requests. "
"Default: 16384 Range: 8192 to 130048");
unsigned int cifs_min_rcv = CIFS_MIN_RCV_POOL;
module_param(cifs_min_rcv, uint, 0444);
@@ -76,11 +78,21 @@ MODULE_PARM_DESC(cifs_min_small, "Small network buffers in pool. Default: 30 "
"Range: 2 to 256");
unsigned int cifs_max_pending = CIFS_MAX_REQ;
module_param(cifs_max_pending, uint, 0444);
-MODULE_PARM_DESC(cifs_max_pending, "Simultaneous requests to server. "
+MODULE_PARM_DESC(cifs_max_pending, "Simultaneous requests to server for "
+ "CIFS/SMB1 dialect (N/A for SMB3) "
"Default: 32767 Range: 2 to 32767.");
module_param(enable_oplocks, bool, 0644);
MODULE_PARM_DESC(enable_oplocks, "Enable or disable oplocks. Default: y/Y/1");
+module_param(disable_legacy_dialects, bool, 0644);
+MODULE_PARM_DESC(disable_legacy_dialects, "To improve security it may be "
+ "helpful to restrict the ability to "
+ "override the default dialects (SMB2.1, "
+ "SMB3 and SMB3.02) on mount with old "
+ "dialects (CIFS/SMB1 and SMB2) since "
+ "vers=1.0 (CIFS/SMB1) and vers=2.0 are weaker"
+ " and less secure. Default: n/N/0");
+
extern mempool_t *cifs_sm_req_poolp;
extern mempool_t *cifs_req_poolp;
extern mempool_t *cifs_mid_poolp;
@@ -469,10 +481,20 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
seq_puts(s, ",persistenthandles");
else if (tcon->use_resilient)
seq_puts(s, ",resilienthandles");
+
+#ifdef CONFIG_CIFS_SMB311
+ if (tcon->posix_extensions)
+ seq_puts(s, ",posix");
+ else if (tcon->unix_ext)
+ seq_puts(s, ",unix");
+ else
+ seq_puts(s, ",nounix");
+#else
if (tcon->unix_ext)
seq_puts(s, ",unix");
else
seq_puts(s, ",nounix");
+#endif /* SMB311 */
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
seq_puts(s, ",posixpaths");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)
@@ -495,6 +517,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
seq_puts(s, ",sfu");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
seq_puts(s, ",nobrl");
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_HANDLE_CACHE)
+ seq_puts(s, ",nohandlecache");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL)
seq_puts(s, ",cifsacl");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
@@ -897,6 +921,17 @@ struct file_system_type cifs_fs_type = {
/* .fs_flags */
};
MODULE_ALIAS_FS("cifs");
+
+static struct file_system_type smb3_fs_type = {
+ .owner = THIS_MODULE,
+ .name = "smb3",
+ .mount = cifs_do_mount,
+ .kill_sb = cifs_kill_sb,
+ /* .fs_flags */
+};
+MODULE_ALIAS_FS("smb3");
+MODULE_ALIAS("smb3");
+
const struct inode_operations cifs_dir_inode_ops = {
.create = cifs_create,
.atomic_open = cifs_atomic_open,
@@ -1047,6 +1082,18 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
return rc;
}
+/*
+ * Directory operations under CIFS/SMB2/SMB3 are synchronous, so fsync()
+ * is a dummy operation.
+ */
+static int cifs_dir_fsync(struct file *file, loff_t start, loff_t end, int datasync)
+{
+ cifs_dbg(FYI, "Sync directory - name: %pD datasync: 0x%x\n",
+ file, datasync);
+
+ return 0;
+}
+
static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off,
struct file *dst_file, loff_t destoff,
size_t len, unsigned int flags)
@@ -1181,6 +1228,7 @@ const struct file_operations cifs_dir_ops = {
.copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.llseek = generic_file_llseek,
+ .fsync = cifs_dir_fsync,
};
static void
@@ -1422,6 +1470,12 @@ init_cifs(void)
if (rc)
goto out_init_cifs_idmap;
+ rc = register_filesystem(&smb3_fs_type);
+ if (rc) {
+ unregister_filesystem(&cifs_fs_type);
+ goto out_init_cifs_idmap;
+ }
+
return 0;
out_init_cifs_idmap:
@@ -1452,8 +1506,9 @@ init_cifs(void)
static void __exit
exit_cifs(void)
{
- cifs_dbg(NOISY, "exit_cifs\n");
+ cifs_dbg(NOISY, "exit_smb3\n");
unregister_filesystem(&cifs_fs_type);
+ unregister_filesystem(&smb3_fs_type);
cifs_dfs_release_automount_timer();
#ifdef CONFIG_CIFS_ACL
exit_cifs_idmap();
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 013ba2a..5f02318 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -149,5 +149,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
extern const struct export_operations cifs_export_ops;
#endif /* CONFIG_CIFS_NFSD_EXPORT */
-#define CIFS_VERSION "2.11"
+#define CIFS_VERSION "2.12"
#endif /* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index cb950a5..08d1cdd 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -176,6 +176,7 @@ struct smb_rqst {
struct kvec *rq_iov; /* array of kvecs */
unsigned int rq_nvec; /* number of kvecs in array */
struct page **rq_pages; /* pointer to array of page ptrs */
+ unsigned int rq_offset; /* the offset to the 1st page */
unsigned int rq_npages; /* number pages in array */
unsigned int rq_pagesz; /* page size to use */
unsigned int rq_tailsz; /* length of last page */
@@ -244,7 +245,7 @@ struct smb_version_operations {
int (*map_error)(char *, bool);
/* find mid corresponding to the response message */
struct mid_q_entry * (*find_mid)(struct TCP_Server_Info *, char *);
- void (*dump_detail)(void *);
+ void (*dump_detail)(void *buf, struct TCP_Server_Info *ptcp_info);
void (*clear_stats)(struct cifs_tcon *);
void (*print_stats)(struct seq_file *m, struct cifs_tcon *);
void (*dump_share_caps)(struct seq_file *, struct cifs_tcon *);
@@ -372,7 +373,7 @@ struct smb_version_operations {
int (*close_dir)(const unsigned int, struct cifs_tcon *,
struct cifs_fid *);
/* calculate a size of SMB message */
- unsigned int (*calc_smb_size)(void *);
+ unsigned int (*calc_smb_size)(void *buf, struct TCP_Server_Info *ptcpi);
/* check for STATUS_PENDING and process it in a positive case */
bool (*is_status_pending)(char *, struct TCP_Server_Info *, int);
/* check for STATUS_NETWORK_SESSION_EXPIRED */
@@ -417,7 +418,7 @@ struct smb_version_operations {
/* create lease context buffer for CREATE request */
char * (*create_lease_buf)(u8 *, u8);
/* parse lease context buffer and return oplock/epoch info */
- __u8 (*parse_lease_buf)(void *, unsigned int *);
+ __u8 (*parse_lease_buf)(void *buf, unsigned int *epoch, char *lkey);
ssize_t (*copychunk_range)(const unsigned int,
struct cifsFileInfo *src_file,
struct cifsFileInfo *target_file,
@@ -457,7 +458,7 @@ struct smb_version_operations {
struct mid_q_entry **);
enum securityEnum (*select_sectype)(struct TCP_Server_Info *,
enum securityEnum);
-
+ int (*next_header)(char *);
};
struct smb_version_values {
@@ -521,10 +522,12 @@ struct smb_vol {
bool sfu_remap:1; /* remap seven reserved chars ala SFU */
bool posix_paths:1; /* unset to not ask for posix pathnames. */
bool no_linux_ext:1;
+ bool linux_ext:1;
bool sfu_emul:1;
bool nullauth:1; /* attempt to authenticate with null user */
bool nocase:1; /* request case insensitive filenames */
bool nobrl:1; /* disable sending byte range locks to srv */
+ bool nohandlecache:1; /* disable caching dir handles if srvr probs */
bool mand_lock:1; /* send mandatory not posix byte range lock reqs */
bool seal:1; /* request transport encryption on share */
bool nodfs:1; /* Do not request DFS, even if available */
@@ -630,7 +633,7 @@ struct TCP_Server_Info {
bool oplocks:1; /* enable oplocks */
unsigned int maxReq; /* Clients should submit no more */
/* than maxReq distinct unanswered SMBs to the server when using */
- /* multiplexed reads or writes */
+ /* multiplexed reads or writes (for SMB1/CIFS only, not SMB2/SMB3) */
unsigned int maxBuf; /* maxBuf specifies the maximum */
/* message size the server can send or receive for non-raw SMBs */
/* maxBuf is returned by SMB NegotiateProtocol so maxBuf is only 0 */
@@ -681,6 +684,7 @@ struct TCP_Server_Info {
__le16 cipher_type;
/* save initital negprot hash */
__u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
+ bool posix_ext_supported;
#endif /* 3.1.1 */
struct delayed_work reconnect; /* reconnect workqueue job */
struct mutex reconnect_mutex; /* prevent simultaneous reconnects */
@@ -953,9 +957,13 @@ struct cifs_tcon {
bool print:1; /* set if connection to printer share */
bool retry:1;
bool nocase:1;
+ bool nohandlecache:1; /* if strange server resource prob can turn off */
bool seal:1; /* transport encryption for this mounted share */
bool unix_ext:1; /* if false disable Linux extensions to CIFS protocol
for this mount even if server would support */
+#ifdef CONFIG_CIFS_SMB311
+ bool posix_extensions; /* if true SMB3.11 posix extensions enabled */
+#endif /* CIFS_311 */
bool local_lease:1; /* check leases (only) on local system not remote */
bool broken_posix_open; /* e.g. Samba server versions < 3.3.2, 3.2.9 */
bool broken_sparse_sup; /* if server or share does not support sparse */
@@ -979,6 +987,9 @@ struct cifs_tcon {
struct fscache_cookie *fscache; /* cookie for share */
#endif
struct list_head pending_opens; /* list of incomplete opens */
+ bool valid_root_fid:1; /* Do we have a useable root fid */
+ struct mutex prfid_mutex; /* prevents reopen race after dead ses*/
+ struct cifs_fid *prfid; /* handle to the directory at top of share */
/* BB add field for back pointer to sb struct(s)? */
};
@@ -1071,6 +1082,7 @@ struct cifs_open_parms {
int create_options;
const char *path;
struct cifs_fid *fid;
+ umode_t mode;
bool reconnect:1;
};
@@ -1169,10 +1181,11 @@ struct cifs_readdata {
struct smbd_mr *mr;
#endif
unsigned int pagesz;
+ unsigned int page_offset;
unsigned int tailsz;
unsigned int credits;
unsigned int nr_pages;
- struct page *pages[];
+ struct page **pages;
};
struct cifs_writedata;
@@ -1194,10 +1207,11 @@ struct cifs_writedata {
struct smbd_mr *mr;
#endif
unsigned int pagesz;
+ unsigned int page_offset;
unsigned int tailsz;
unsigned int credits;
unsigned int nr_pages;
- struct page *pages[];
+ struct page **pages;
};
/*
@@ -1692,16 +1706,17 @@ GLOBAL_EXTERN atomic_t smBufAllocCount;
GLOBAL_EXTERN atomic_t midCount;
/* Misc globals */
-GLOBAL_EXTERN bool enable_oplocks; /* enable or disable oplocks */
-GLOBAL_EXTERN bool lookupCacheEnabled;
-GLOBAL_EXTERN unsigned int global_secflags; /* if on, session setup sent
+extern bool enable_oplocks; /* enable or disable oplocks */
+extern bool lookupCacheEnabled;
+extern unsigned int global_secflags; /* if on, session setup sent
with more secure ntlmssp2 challenge/resp */
-GLOBAL_EXTERN unsigned int sign_CIFS_PDUs; /* enable smb packet signing */
-GLOBAL_EXTERN bool linuxExtEnabled;/*enable Linux/Unix CIFS extensions*/
-GLOBAL_EXTERN unsigned int CIFSMaxBufSize; /* max size not including hdr */
-GLOBAL_EXTERN unsigned int cifs_min_rcv; /* min size of big ntwrk buf pool */
-GLOBAL_EXTERN unsigned int cifs_min_small; /* min size of small buf pool */
-GLOBAL_EXTERN unsigned int cifs_max_pending; /* MAX requests at once to server*/
+extern unsigned int sign_CIFS_PDUs; /* enable smb packet signing */
+extern bool linuxExtEnabled;/*enable Linux/Unix CIFS extensions*/
+extern unsigned int CIFSMaxBufSize; /* max size not including hdr */
+extern unsigned int cifs_min_rcv; /* min size of big ntwrk buf pool */
+extern unsigned int cifs_min_small; /* min size of small buf pool */
+extern unsigned int cifs_max_pending; /* MAX requests at once to server*/
+extern bool disable_legacy_dialects; /* forbid vers=1.0 and vers=2.0 mounts */
#ifdef CONFIG_CIFS_ACL
GLOBAL_EXTERN struct rb_root uidtree;
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 365a414..7933c5f 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -21,6 +21,7 @@
#ifndef _CIFSPROTO_H
#define _CIFSPROTO_H
#include <linux/nls.h>
+#include "trace.h"
struct statfs;
struct smb_vol;
@@ -47,6 +48,7 @@ extern void _free_xid(unsigned int);
cifs_dbg(FYI, "CIFS VFS: in %s as Xid: %u with uid: %d\n", \
__func__, __xid, \
from_kuid(&init_user_ns, current_fsuid())); \
+ trace_smb3_enter(__xid, __func__); \
__xid; \
})
@@ -54,7 +56,11 @@ extern void _free_xid(unsigned int);
do { \
_free_xid(curr_xid); \
cifs_dbg(FYI, "CIFS VFS: leaving %s (xid = %u) rc = %d\n", \
- __func__, curr_xid, (int)rc); \
+ __func__, curr_xid, (int)rc); \
+ if (rc) \
+ trace_smb3_exit_err(curr_xid, __func__, (int)rc); \
+ else \
+ trace_smb3_exit_done(curr_xid, __func__); \
} while (0)
extern int init_cifs_idmap(void);
extern void exit_cifs_idmap(void);
@@ -124,7 +130,7 @@ extern void cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset,
unsigned int bytes_written);
extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *, bool);
extern struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *, bool);
-extern unsigned int smbCalcSize(void *buf);
+extern unsigned int smbCalcSize(void *buf, struct TCP_Server_Info *server);
extern int decode_negTokenInit(unsigned char *security_blob, int length,
struct TCP_Server_Info *server);
extern int cifs_convert_address(struct sockaddr *dst, const char *src, int len);
@@ -197,7 +203,9 @@ extern void dequeue_mid(struct mid_q_entry *mid, bool malformed);
extern int cifs_read_from_socket(struct TCP_Server_Info *server, char *buf,
unsigned int to_read);
extern int cifs_read_page_from_socket(struct TCP_Server_Info *server,
- struct page *page, unsigned int to_read);
+ struct page *page,
+ unsigned int page_offset,
+ unsigned int to_read);
extern int cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
struct cifs_sb_info *cifs_sb);
extern int cifs_match_super(struct super_block *, void *);
@@ -525,6 +533,8 @@ int cifs_async_writev(struct cifs_writedata *wdata,
void cifs_writev_complete(struct work_struct *work);
struct cifs_writedata *cifs_writedata_alloc(unsigned int nr_pages,
work_func_t complete);
+struct cifs_writedata *cifs_writedata_direct_alloc(struct page **pages,
+ work_func_t complete);
void cifs_writedata_release(struct kref *refcount);
int cifs_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
struct cifs_sb_info *cifs_sb,
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 6d3e40d..5aca336 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -106,6 +106,12 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon)
open_file->oplock_break_cancelled = true;
}
spin_unlock(&tcon->open_file_lock);
+
+ mutex_lock(&tcon->prfid_mutex);
+ tcon->valid_root_fid = false;
+ memset(tcon->prfid, 0, sizeof(struct cifs_fid));
+ mutex_unlock(&tcon->prfid_mutex);
+
/*
* BB Add call to invalidate_inodes(sb) for all superblocks mounted
* to this tcon.
@@ -455,6 +461,9 @@ cifs_enable_signing(struct TCP_Server_Info *server, bool mnt_sign_required)
server->sign = true;
}
+ if (cifs_rdma_enabled(server) && server->sign)
+ cifs_dbg(VFS, "Signing is enabled, and RDMA read/write will be disabled");
+
return 0;
}
@@ -1943,6 +1952,7 @@ cifs_writedata_release(struct kref *refcount)
if (wdata->cfile)
cifsFileInfo_put(wdata->cfile);
+ kvfree(wdata->pages);
kfree(wdata);
}
@@ -2066,12 +2076,22 @@ cifs_writev_complete(struct work_struct *work)
struct cifs_writedata *
cifs_writedata_alloc(unsigned int nr_pages, work_func_t complete)
{
+ struct page **pages =
+ kzalloc(sizeof(struct page *) * nr_pages, GFP_NOFS);
+ if (pages)
+ return cifs_writedata_direct_alloc(pages, complete);
+
+ return NULL;
+}
+
+struct cifs_writedata *
+cifs_writedata_direct_alloc(struct page **pages, work_func_t complete)
+{
struct cifs_writedata *wdata;
- /* writedata + number of page pointers */
- wdata = kzalloc(sizeof(*wdata) +
- sizeof(struct page *) * nr_pages, GFP_NOFS);
+ wdata = kzalloc(sizeof(*wdata), GFP_NOFS);
if (wdata != NULL) {
+ wdata->pages = pages;
kref_init(&wdata->refcount);
INIT_LIST_HEAD(&wdata->list);
init_completion(&wdata->done);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index e8830f0..e5a2fe7f 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -61,6 +61,7 @@
#define RFC1001_PORT 139
extern mempool_t *cifs_req_poolp;
+extern bool disable_legacy_dialects;
/* FIXME: should these be tunable? */
#define TLINK_ERROR_EXPIRE (1 * HZ)
@@ -76,9 +77,10 @@ enum {
Opt_mapposix, Opt_nomapposix,
Opt_mapchars, Opt_nomapchars, Opt_sfu,
Opt_nosfu, Opt_nodfs, Opt_posixpaths,
- Opt_noposixpaths, Opt_nounix,
+ Opt_noposixpaths, Opt_nounix, Opt_unix,
Opt_nocase,
Opt_brl, Opt_nobrl,
+ Opt_handlecache, Opt_nohandlecache,
Opt_forcemandatorylock, Opt_setuidfromacl, Opt_setuids,
Opt_nosetuids, Opt_dynperm, Opt_nodynperm,
Opt_nohard, Opt_nosoft,
@@ -144,10 +146,16 @@ static const match_table_t cifs_mount_option_tokens = {
{ Opt_noposixpaths, "noposixpaths" },
{ Opt_nounix, "nounix" },
{ Opt_nounix, "nolinux" },
+ { Opt_nounix, "noposix" },
+ { Opt_unix, "unix" },
+ { Opt_unix, "linux" },
+ { Opt_unix, "posix" },
{ Opt_nocase, "nocase" },
{ Opt_nocase, "ignorecase" },
{ Opt_brl, "brl" },
{ Opt_nobrl, "nobrl" },
+ { Opt_handlecache, "handlecache" },
+ { Opt_nohandlecache, "nohandlecache" },
{ Opt_nobrl, "nolock" },
{ Opt_forcemandatorylock, "forcemandatorylock" },
{ Opt_forcemandatorylock, "forcemand" },
@@ -591,10 +599,11 @@ cifs_read_from_socket(struct TCP_Server_Info *server, char *buf,
int
cifs_read_page_from_socket(struct TCP_Server_Info *server, struct page *page,
- unsigned int to_read)
+ unsigned int page_offset, unsigned int to_read)
{
struct msghdr smb_msg;
- struct bio_vec bv = {.bv_page = page, .bv_len = to_read};
+ struct bio_vec bv = {
+ .bv_page = page, .bv_len = to_read, .bv_offset = page_offset};
iov_iter_bvec(&smb_msg.msg_iter, READ | ITER_BVEC, &bv, 1, to_read);
return cifs_readv_from_socket(server, &smb_msg);
}
@@ -848,6 +857,7 @@ cifs_demultiplex_thread(void *p)
int length;
struct TCP_Server_Info *server = p;
unsigned int pdu_length;
+ unsigned int next_offset;
char *buf = NULL;
struct task_struct *task_to_wake = NULL;
struct mid_q_entry *mid_entry;
@@ -874,24 +884,29 @@ cifs_demultiplex_thread(void *p)
length = cifs_read_from_socket(server, buf, pdu_length);
if (length < 0)
continue;
- server->total_read = length;
+
+ if (server->vals->header_preamble_size == 0)
+ server->total_read = 0;
+ else
+ server->total_read = length;
/*
* The right amount was read from socket - 4 bytes,
* so we can now interpret the length field.
*/
pdu_length = get_rfc1002_length(buf);
- server->pdu_size = pdu_length;
cifs_dbg(FYI, "RFC1002 header 0x%x\n", pdu_length);
if (!is_smb_response(server, buf[0]))
continue;
+next_pdu:
+ server->pdu_size = pdu_length;
/* make sure we have enough to get to the MID */
- if (pdu_length < HEADER_SIZE(server) - 1 -
+ if (server->pdu_size < HEADER_SIZE(server) - 1 -
server->vals->header_preamble_size) {
cifs_dbg(VFS, "SMB response too short (%u bytes)\n",
- pdu_length);
+ server->pdu_size);
cifs_reconnect(server);
wake_up(&server->response_q);
continue;
@@ -906,6 +921,12 @@ cifs_demultiplex_thread(void *p)
continue;
server->total_read += length;
+ if (server->ops->next_header) {
+ next_offset = server->ops->next_header(buf);
+ if (next_offset)
+ server->pdu_size = next_offset;
+ }
+
if (server->ops->is_transform_hdr &&
server->ops->receive_transform &&
server->ops->is_transform_hdr(buf)) {
@@ -948,10 +969,18 @@ cifs_demultiplex_thread(void *p)
HEADER_SIZE(server));
#ifdef CONFIG_CIFS_DEBUG2
if (server->ops->dump_detail)
- server->ops->dump_detail(buf);
+ server->ops->dump_detail(buf, server);
cifs_dump_mids(server);
#endif /* CIFS_DEBUG2 */
-
+ }
+ if (pdu_length > server->pdu_size) {
+ if (!allocate_buffers(server))
+ continue;
+ pdu_length -= server->pdu_size;
+ server->total_read = 0;
+ server->large_buf = false;
+ buf = server->smallbuf;
+ goto next_pdu;
}
} /* end while !EXITING */
@@ -1143,10 +1172,18 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol)
switch (match_token(value, cifs_smb_version_tokens, args)) {
case Smb_1:
+ if (disable_legacy_dialects) {
+ cifs_dbg(VFS, "mount with legacy dialect disabled\n");
+ return 1;
+ }
vol->ops = &smb1_operations;
vol->vals = &smb1_values;
break;
case Smb_20:
+ if (disable_legacy_dialects) {
+ cifs_dbg(VFS, "mount with legacy dialect disabled\n");
+ return 1;
+ }
vol->ops = &smb20_operations;
vol->vals = &smb20_values;
break;
@@ -1426,8 +1463,17 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
vol->posix_paths = 0;
break;
case Opt_nounix:
+ if (vol->linux_ext)
+ cifs_dbg(VFS,
+ "conflicting unix mount options\n");
vol->no_linux_ext = 1;
break;
+ case Opt_unix:
+ if (vol->no_linux_ext)
+ cifs_dbg(VFS,
+ "conflicting unix mount options\n");
+ vol->linux_ext = 1;
+ break;
case Opt_nocase:
vol->nocase = 1;
break;
@@ -1445,6 +1491,12 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
(S_IALLUGO & ~(S_ISUID | S_IXGRP)))
vol->file_mode = S_IALLUGO;
break;
+ case Opt_nohandlecache:
+ vol->nohandlecache = 1;
+ break;
+ case Opt_handlecache:
+ vol->nohandlecache = 0;
+ break;
case Opt_forcemandatorylock:
vol->mand_lock = 1;
break;
@@ -1977,14 +2029,6 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
goto cifs_parse_mount_err;
}
-#ifdef CONFIG_CIFS_SMB_DIRECT
- if (vol->rdma && vol->sign) {
- cifs_dbg(VFS, "Currently SMB direct doesn't support signing."
- " This is being fixed\n");
- goto cifs_parse_mount_err;
- }
-#endif
-
#ifndef CONFIG_KEYS
/* Muliuser mounts require CONFIG_KEYS support */
if (vol->multiuser) {
@@ -2959,6 +3003,29 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
}
}
+ if (volume_info->seal) {
+ if (ses->server->vals->protocol_id == 0) {
+ cifs_dbg(VFS,
+ "SMB3 or later required for encryption\n");
+ rc = -EOPNOTSUPP;
+ goto out_fail;
+ } else if (tcon->ses->server->capabilities &
+ SMB2_GLOBAL_CAP_ENCRYPTION)
+ tcon->seal = true;
+ else {
+ cifs_dbg(VFS, "Encryption is not supported on share\n");
+ rc = -EOPNOTSUPP;
+ goto out_fail;
+ }
+ }
+
+#ifdef CONFIG_CIFS_SMB311
+ if ((volume_info->linux_ext) && (ses->server->posix_ext_supported)) {
+ if (ses->server->vals->protocol_id == SMB311_PROT_ID)
+ tcon->posix_extensions = true;
+ }
+#endif /* 311 */
+
/*
* BB Do we need to wrap session_mutex around this TCon call and Unix
* SetFS as we do on SessSetup and reconnect?
@@ -3007,22 +3074,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
tcon->use_resilient = true;
}
- if (volume_info->seal) {
- if (ses->server->vals->protocol_id == 0) {
- cifs_dbg(VFS,
- "SMB3 or later required for encryption\n");
- rc = -EOPNOTSUPP;
- goto out_fail;
- } else if (tcon->ses->server->capabilities &
- SMB2_GLOBAL_CAP_ENCRYPTION)
- tcon->seal = true;
- else {
- cifs_dbg(VFS, "Encryption is not supported on share\n");
- rc = -EOPNOTSUPP;
- goto out_fail;
- }
- }
-
/*
* We can have only one retry value for a connection to a share so for
* resources mounted more than once to the same server share the last
@@ -3030,6 +3081,7 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
*/
tcon->retry = volume_info->retry;
tcon->nocase = volume_info->nocase;
+ tcon->nohandlecache = volume_info->nohandlecache;
tcon->local_lease = volume_info->local_lease;
INIT_LIST_HEAD(&tcon->pending_opens);
@@ -3588,6 +3640,8 @@ int cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_UNX_EMUL;
if (pvolume_info->nobrl)
cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_BRL;
+ if (pvolume_info->nohandlecache)
+ cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_HANDLE_CACHE;
if (pvolume_info->nostrictsync)
cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NOSSYNC;
if (pvolume_info->mand_lock)
@@ -3930,6 +3984,12 @@ cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info)
goto remote_path_check;
}
+#ifdef CONFIG_CIFS_SMB311
+ /* if new SMB3.11 POSIX extensions are supported do not remap / and \ */
+ if (tcon->posix_extensions)
+ cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
+#endif /* SMB3.11 */
+
/* tell server which Unix caps we support */
if (cap_unix(tcon->ses)) {
/* reset of caps checks mount to see if unix extensions
@@ -4361,6 +4421,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
vol_info->UNC = master_tcon->treeName;
vol_info->retry = master_tcon->retry;
vol_info->nocase = master_tcon->nocase;
+ vol_info->nohandlecache = master_tcon->nohandlecache;
vol_info->local_lease = master_tcon->local_lease;
vol_info->no_linux_ext = !master_tcon->unix_ext;
vol_info->sectype = master_tcon->ses->sectype;
@@ -4390,8 +4451,14 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
goto out;
}
+#ifdef CONFIG_CIFS_SMB311
+ /* if new SMB3.11 POSIX extensions are supported do not remap / and \ */
+ if (tcon->posix_extensions)
+ cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
+#endif /* SMB3.11 */
if (cap_unix(ses))
reset_cifs_unix_caps(0, tcon, NULL, vol_info);
+
out:
kfree(vol_info->username);
kzfree(vol_info->password);
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 81ba6e0..ddae52b 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -369,7 +369,7 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid,
oparms.path = full_path;
oparms.fid = fid;
oparms.reconnect = false;
-
+ oparms.mode = mode;
rc = server->ops->open(xid, &oparms, oplock, buf);
if (rc) {
cifs_dbg(FYI, "cifs_create returned 0x%x\n", rc);
@@ -684,6 +684,9 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode,
goto mknod_out;
}
+ if (!S_ISCHR(mode) && !S_ISBLK(mode))
+ goto mknod_out;
+
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL))
goto mknod_out;
@@ -692,10 +695,8 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode,
buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
if (buf == NULL) {
- kfree(full_path);
rc = -ENOMEM;
- free_xid(xid);
- return rc;
+ goto mknod_out;
}
if (backup_cred(cifs_sb))
@@ -742,7 +743,7 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode,
pdev->minor = cpu_to_le64(MINOR(device_number));
rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms,
&bytes_written, iov, 1);
- } /* else if (S_ISFIFO) */
+ }
tcon->ses->server->ops->close(xid, tcon, &fid);
d_drop(direntry);
@@ -779,21 +780,25 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink)) {
free_xid(xid);
- return (struct dentry *)tlink;
+ return ERR_CAST(tlink);
}
pTcon = tlink_tcon(tlink);
rc = check_name(direntry, pTcon);
- if (rc)
- goto lookup_out;
+ if (unlikely(rc)) {
+ cifs_put_tlink(tlink);
+ free_xid(xid);
+ return ERR_PTR(rc);
+ }
/* can not grab the rename sem here since it would
deadlock in the cases (beginning of sys_rename itself)
in which we already have the sb rename sem */
full_path = build_path_from_dentry(direntry);
if (full_path == NULL) {
- rc = -ENOMEM;
- goto lookup_out;
+ cifs_put_tlink(tlink);
+ free_xid(xid);
+ return ERR_PTR(-ENOMEM);
}
if (d_really_is_positive(direntry)) {
@@ -812,29 +817,25 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
parent_dir_inode->i_sb, xid, NULL);
}
- if ((rc == 0) && (newInode != NULL)) {
- d_add(direntry, newInode);
+ if (rc == 0) {
/* since paths are not looked up by component - the parent
directories are presumed to be good here */
renew_parental_timestamps(direntry);
-
} else if (rc == -ENOENT) {
- rc = 0;
cifs_set_time(direntry, jiffies);
- d_add(direntry, NULL);
- /* if it was once a directory (but how can we tell?) we could do
- shrink_dcache_parent(direntry); */
- } else if (rc != -EACCES) {
- cifs_dbg(FYI, "Unexpected lookup error %d\n", rc);
- /* We special case check for Access Denied - since that
- is a common return code */
+ newInode = NULL;
+ } else {
+ if (rc != -EACCES) {
+ cifs_dbg(FYI, "Unexpected lookup error %d\n", rc);
+ /* We special case check for Access Denied - since that
+ is a common return code */
+ }
+ newInode = ERR_PTR(rc);
}
-
-lookup_out:
kfree(full_path);
cifs_put_tlink(tlink);
free_xid(xid);
- return ERR_PTR(rc);
+ return d_splice_alias(newInode, direntry);
}
static int
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 4bcd4e8..87eece6 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2880,13 +2880,13 @@ cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from)
}
static struct cifs_readdata *
-cifs_readdata_alloc(unsigned int nr_pages, work_func_t complete)
+cifs_readdata_direct_alloc(struct page **pages, work_func_t complete)
{
struct cifs_readdata *rdata;
- rdata = kzalloc(sizeof(*rdata) + (sizeof(struct page *) * nr_pages),
- GFP_KERNEL);
+ rdata = kzalloc(sizeof(*rdata), GFP_KERNEL);
if (rdata != NULL) {
+ rdata->pages = pages;
kref_init(&rdata->refcount);
INIT_LIST_HEAD(&rdata->list);
init_completion(&rdata->done);
@@ -2896,6 +2896,22 @@ cifs_readdata_alloc(unsigned int nr_pages, work_func_t complete)
return rdata;
}
+static struct cifs_readdata *
+cifs_readdata_alloc(unsigned int nr_pages, work_func_t complete)
+{
+ struct page **pages =
+ kzalloc(sizeof(struct page *) * nr_pages, GFP_KERNEL);
+ struct cifs_readdata *ret = NULL;
+
+ if (pages) {
+ ret = cifs_readdata_direct_alloc(pages, complete);
+ if (!ret)
+ kfree(pages);
+ }
+
+ return ret;
+}
+
void
cifs_readdata_release(struct kref *refcount)
{
@@ -2910,6 +2926,7 @@ cifs_readdata_release(struct kref *refcount)
if (rdata->cfile)
cifsFileInfo_put(rdata->cfile);
+ kvfree(rdata->pages);
kfree(rdata);
}
@@ -3009,12 +3026,20 @@ uncached_fill_pages(struct TCP_Server_Info *server,
int result = 0;
unsigned int i;
unsigned int nr_pages = rdata->nr_pages;
+ unsigned int page_offset = rdata->page_offset;
rdata->got_bytes = 0;
rdata->tailsz = PAGE_SIZE;
for (i = 0; i < nr_pages; i++) {
struct page *page = rdata->pages[i];
size_t n;
+ unsigned int segment_size = rdata->pagesz;
+
+ if (i == 0)
+ segment_size -= page_offset;
+ else
+ page_offset = 0;
+
if (len <= 0) {
/* no need to hold page hostage */
@@ -3023,24 +3048,25 @@ uncached_fill_pages(struct TCP_Server_Info *server,
put_page(page);
continue;
}
+
n = len;
- if (len >= PAGE_SIZE) {
+ if (len >= segment_size)
/* enough data to fill the page */
- n = PAGE_SIZE;
- len -= n;
- } else {
- zero_user(page, len, PAGE_SIZE - len);
+ n = segment_size;
+ else
rdata->tailsz = len;
- len = 0;
- }
+ len -= n;
+
if (iter)
- result = copy_page_from_iter(page, 0, n, iter);
+ result = copy_page_from_iter(
+ page, page_offset, n, iter);
#ifdef CONFIG_CIFS_SMB_DIRECT
else if (rdata->mr)
result = n;
#endif
else
- result = cifs_read_page_from_socket(server, page, n);
+ result = cifs_read_page_from_socket(
+ server, page, page_offset, n);
if (result < 0)
break;
@@ -3113,6 +3139,7 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
rdata->bytes = cur_len;
rdata->pid = pid;
rdata->pagesz = PAGE_SIZE;
+ rdata->tailsz = PAGE_SIZE;
rdata->read_into_pages = cifs_uncached_read_into_pages;
rdata->copy_into_pages = cifs_uncached_copy_into_pages;
rdata->credits = credits;
@@ -3462,7 +3489,7 @@ cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset)
* If the page is mmap'ed into a process' page tables, then we need to make
* sure that it doesn't change while being written back.
*/
-static int
+static vm_fault_t
cifs_page_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
@@ -3557,6 +3584,7 @@ readpages_fill_pages(struct TCP_Server_Info *server,
u64 eof;
pgoff_t eof_index;
unsigned int nr_pages = rdata->nr_pages;
+ unsigned int page_offset = rdata->page_offset;
/* determine the eof that the server (probably) has */
eof = CIFS_I(rdata->mapping->host)->server_eof;
@@ -3567,13 +3595,21 @@ readpages_fill_pages(struct TCP_Server_Info *server,
rdata->tailsz = PAGE_SIZE;
for (i = 0; i < nr_pages; i++) {
struct page *page = rdata->pages[i];
- size_t n = PAGE_SIZE;
+ unsigned int to_read = rdata->pagesz;
+ size_t n;
- if (len >= PAGE_SIZE) {
- len -= PAGE_SIZE;
+ if (i == 0)
+ to_read -= page_offset;
+ else
+ page_offset = 0;
+
+ n = to_read;
+
+ if (len >= to_read) {
+ len -= to_read;
} else if (len > 0) {
/* enough for partial page, fill and zero the rest */
- zero_user(page, len, PAGE_SIZE - len);
+ zero_user(page, len + page_offset, to_read - len);
n = rdata->tailsz = len;
len = 0;
} else if (page->index > eof_index) {
@@ -3605,13 +3641,15 @@ readpages_fill_pages(struct TCP_Server_Info *server,
}
if (iter)
- result = copy_page_from_iter(page, 0, n, iter);
+ result = copy_page_from_iter(
+ page, page_offset, n, iter);
#ifdef CONFIG_CIFS_SMB_DIRECT
else if (rdata->mr)
result = n;
#endif
else
- result = cifs_read_page_from_socket(server, page, n);
+ result = cifs_read_page_from_socket(
+ server, page, page_offset, n);
if (result < 0)
break;
@@ -3790,6 +3828,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
rdata->bytes = bytes;
rdata->pid = pid;
rdata->pagesz = PAGE_SIZE;
+ rdata->tailsz = PAGE_SIZE;
rdata->read_into_pages = cifs_readpages_read_into_pages;
rdata->copy_into_pages = cifs_readpages_copy_into_pages;
rdata->credits = credits;
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 3c371f7..745fd7f 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -746,7 +746,8 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
cifs_dbg(FYI, "Getting info on %s\n", full_path);
if ((data == NULL) && (*inode != NULL)) {
- if (CIFS_CACHE_READ(CIFS_I(*inode))) {
+ if (CIFS_CACHE_READ(CIFS_I(*inode)) &&
+ CIFS_I(*inode)->time != 0) {
cifs_dbg(FYI, "No need to revalidate cached inode sizes\n");
goto cgii_exit;
}
@@ -1857,15 +1858,15 @@ cifs_inode_needs_reval(struct inode *inode)
struct cifsInodeInfo *cifs_i = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+ if (cifs_i->time == 0)
+ return true;
+
if (CIFS_CACHE_READ(cifs_i))
return false;
if (!lookupCacheEnabled)
return true;
- if (cifs_i->time == 0)
- return true;
-
if (!cifs_sb->actimeo)
return true;
@@ -2104,10 +2105,14 @@ static int cifs_truncate_page(struct address_space *mapping, loff_t from)
static void cifs_setsize(struct inode *inode, loff_t offset)
{
+ struct cifsInodeInfo *cifs_i = CIFS_I(inode);
+
spin_lock(&inode->i_lock);
i_size_write(inode, offset);
spin_unlock(&inode->i_lock);
+ /* Cached inode must be refreshed on truncate */
+ cifs_i->time = 0;
truncate_pagecache(inode, offset);
}
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 460084a..aba3fc3 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -117,6 +117,8 @@ tconInfoAlloc(void)
INIT_LIST_HEAD(&ret_buf->openFileList);
INIT_LIST_HEAD(&ret_buf->tcon_list);
spin_lock_init(&ret_buf->open_file_lock);
+ mutex_init(&ret_buf->prfid_mutex);
+ ret_buf->prfid = kzalloc(sizeof(struct cifs_fid), GFP_KERNEL);
#ifdef CONFIG_CIFS_STATS
spin_lock_init(&ret_buf->stat_lock);
#endif
@@ -134,6 +136,7 @@ tconInfoFree(struct cifs_tcon *buf_to_free)
atomic_dec(&tconInfoAllocCount);
kfree(buf_to_free->nativeFileSystem);
kzfree(buf_to_free->password);
+ kfree(buf_to_free->prfid);
kfree(buf_to_free);
}
@@ -145,7 +148,7 @@ cifs_buf_get(void)
* SMB2 header is bigger than CIFS one - no problems to clean some
* more bytes for CIFS.
*/
- size_t buf_size = sizeof(struct smb2_hdr);
+ size_t buf_size = sizeof(struct smb2_sync_hdr);
/*
* We could use negotiated size instead of max_msgsize -
@@ -339,7 +342,7 @@ checkSMB(char *buf, unsigned int total_read, struct TCP_Server_Info *server)
/* otherwise, there is enough to get to the BCC */
if (check_smb_hdr(smb))
return -EIO;
- clc_len = smbCalcSize(smb);
+ clc_len = smbCalcSize(smb, server);
if (4 + rfclen != total_read) {
cifs_dbg(VFS, "Length read does not match RFC1001 length %d\n",
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index cc88f4f..d7ad0df 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -903,7 +903,7 @@ map_smb_to_linux_error(char *buf, bool logErr)
* portion, the number of word parameters and the data portion of the message
*/
unsigned int
-smbCalcSize(void *buf)
+smbCalcSize(void *buf, struct TCP_Server_Info *server)
{
struct smb_hdr *ptr = (struct smb_hdr *)buf;
return (sizeof(struct smb_hdr) + (2 * ptr->WordCount) +
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index a27fc87..eeab81c 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -650,7 +650,8 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos,
char *cur_ent;
char *end_of_smb = cfile->srch_inf.ntwrk_buf_start +
server->ops->calc_smb_size(
- cfile->srch_inf.ntwrk_buf_start);
+ cfile->srch_inf.ntwrk_buf_start,
+ server);
cur_ent = cfile->srch_inf.srch_entries_start;
first_entry_in_buffer = cfile->srch_inf.index_of_last_entry
@@ -831,7 +832,8 @@ int cifs_readdir(struct file *file, struct dir_context *ctx)
cifs_dbg(FYI, "loop through %d times filling dir for net buf %p\n",
num_to_fill, cifsFile->srch_inf.ntwrk_buf_start);
max_len = tcon->ses->server->ops->calc_smb_size(
- cifsFile->srch_inf.ntwrk_buf_start);
+ cifsFile->srch_inf.ntwrk_buf_start,
+ tcon->ses->server);
end_of_smb = cifsFile->srch_inf.ntwrk_buf_start + max_len;
tmp_buf = kmalloc(UNICODE_NAME_MAX, GFP_KERNEL);
diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h
index 401a5d8..0ffa180 100644
--- a/fs/cifs/smb2glob.h
+++ b/fs/cifs/smb2glob.h
@@ -61,9 +61,4 @@
/* Maximum buffer size value we can send with 1 credit */
#define SMB2_MAX_BUFFER_SIZE 65536
-static inline struct smb2_sync_hdr *get_sync_hdr(void *buf)
-{
- return &(((struct smb2_hdr *)buf)->sync_hdr);
-}
-
#endif /* _SMB2_GLOB_H */
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index 1238cd3..a6e786e 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -44,26 +44,38 @@ smb2_open_op_close(const unsigned int xid, struct cifs_tcon *tcon,
__u32 create_options, void *data, int command)
{
int rc, tmprc = 0;
- __le16 *utf16_path;
+ __le16 *utf16_path = NULL;
__u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
struct cifs_open_parms oparms;
struct cifs_fid fid;
+ bool use_cached_root_handle = false;
- utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb);
- if (!utf16_path)
- return -ENOMEM;
+ if ((strcmp(full_path, "") == 0) && (create_options == 0) &&
+ (desired_access == FILE_READ_ATTRIBUTES) &&
+ (create_disposition == FILE_OPEN) &&
+ (tcon->nohandlecache == false)) {
+ rc = open_shroot(xid, tcon, &fid);
+ if (rc == 0)
+ use_cached_root_handle = true;
+ }
- oparms.tcon = tcon;
- oparms.desired_access = desired_access;
- oparms.disposition = create_disposition;
- oparms.create_options = create_options;
- oparms.fid = &fid;
- oparms.reconnect = false;
+ if (use_cached_root_handle == false) {
+ utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb);
+ if (!utf16_path)
+ return -ENOMEM;
- rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL);
- if (rc) {
- kfree(utf16_path);
- return rc;
+ oparms.tcon = tcon;
+ oparms.desired_access = desired_access;
+ oparms.disposition = create_disposition;
+ oparms.create_options = create_options;
+ oparms.fid = &fid;
+ oparms.reconnect = false;
+
+ rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL);
+ if (rc) {
+ kfree(utf16_path);
+ return rc;
+ }
}
switch (command) {
@@ -107,7 +119,8 @@ smb2_open_op_close(const unsigned int xid, struct cifs_tcon *tcon,
break;
}
- rc = SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
+ if (use_cached_root_handle == false)
+ rc = SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
if (tmprc)
rc = tmprc;
kfree(utf16_path);
diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c
index 3bfc9c9..20a2d30 100644
--- a/fs/cifs/smb2maperror.c
+++ b/fs/cifs/smb2maperror.c
@@ -27,6 +27,7 @@
#include "smb2proto.h"
#include "smb2status.h"
#include "smb2glob.h"
+#include "trace.h"
struct status_to_posix_error {
__le32 smb2_status;
@@ -2450,13 +2451,16 @@ smb2_print_status(__le32 status)
int
map_smb2_to_linux_error(char *buf, bool log_err)
{
- struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+ struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
unsigned int i;
int rc = -EIO;
__le32 smb2err = shdr->Status;
- if (smb2err == 0)
+ if (smb2err == 0) {
+ trace_smb3_cmd_done(shdr->TreeId, shdr->SessionId,
+ le16_to_cpu(shdr->Command), le64_to_cpu(shdr->MessageId));
return 0;
+ }
/* mask facility */
if (log_err && (smb2err != STATUS_MORE_PROCESSING_REQUIRED) &&
@@ -2478,5 +2482,8 @@ map_smb2_to_linux_error(char *buf, bool log_err)
cifs_dbg(FYI, "Mapping SMB2 status code 0x%08x to POSIX err %d\n",
__le32_to_cpu(smb2err), rc);
+ trace_smb3_cmd_err(shdr->TreeId, shdr->SessionId,
+ le16_to_cpu(shdr->Command),
+ le64_to_cpu(shdr->MessageId), le32_to_cpu(smb2err), rc);
return rc;
}
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 68ea849..cb5728e 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -94,8 +94,8 @@ static const __le16 smb2_rsp_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
};
#ifdef CONFIG_CIFS_SMB311
-static __u32 get_neg_ctxt_len(struct smb2_hdr *hdr, __u32 len, __u32 non_ctxlen,
- size_t hdr_preamble_size)
+static __u32 get_neg_ctxt_len(struct smb2_sync_hdr *hdr, __u32 len,
+ __u32 non_ctxlen)
{
__u16 neg_count;
__u32 nc_offset, size_of_pad_before_neg_ctxts;
@@ -109,12 +109,11 @@ static __u32 get_neg_ctxt_len(struct smb2_hdr *hdr, __u32 len, __u32 non_ctxlen,
/* Make sure that negotiate contexts start after gss security blob */
nc_offset = le32_to_cpu(pneg_rsp->NegotiateContextOffset);
- if (nc_offset < non_ctxlen - hdr_preamble_size /* RFC1001 len */) {
+ if (nc_offset < non_ctxlen) {
printk_once(KERN_WARNING "invalid negotiate context offset\n");
return 0;
}
- size_of_pad_before_neg_ctxts = nc_offset -
- (non_ctxlen - hdr_preamble_size);
+ size_of_pad_before_neg_ctxts = nc_offset - non_ctxlen;
/* Verify that at least minimal negotiate contexts fit within frame */
if (len < nc_offset + (neg_count * sizeof(struct smb2_neg_context))) {
@@ -131,25 +130,20 @@ static __u32 get_neg_ctxt_len(struct smb2_hdr *hdr, __u32 len, __u32 non_ctxlen,
#endif /* CIFS_SMB311 */
int
-smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
+smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr)
{
- struct smb2_pdu *pdu = (struct smb2_pdu *)buf;
- struct smb2_hdr *hdr = &pdu->hdr;
- struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+ struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
+ struct smb2_sync_pdu *pdu = (struct smb2_sync_pdu *)shdr;
__u64 mid;
- __u32 len = get_rfc1002_length(buf);
__u32 clc_len; /* calculated length */
int command;
-
- /* BB disable following printk later */
- cifs_dbg(FYI, "%s length: 0x%x, smb_buf_length: 0x%x\n",
- __func__, length, len);
+ int pdu_size = sizeof(struct smb2_sync_pdu);
+ int hdr_size = sizeof(struct smb2_sync_hdr);
/*
* Add function to do table lookup of StructureSize by command
* ie Validate the wct via smb2_struct_sizes table above
*/
-
if (shdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) {
struct smb2_transform_hdr *thdr =
(struct smb2_transform_hdr *)buf;
@@ -173,8 +167,8 @@ smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
}
mid = le64_to_cpu(shdr->MessageId);
- if (length < sizeof(struct smb2_pdu)) {
- if ((length >= sizeof(struct smb2_hdr))
+ if (len < pdu_size) {
+ if ((len >= hdr_size)
&& (shdr->Status != 0)) {
pdu->StructureSize2 = 0;
/*
@@ -187,8 +181,7 @@ smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
}
return 1;
}
- if (len > CIFSMaxBufSize + MAX_SMB2_HDR_SIZE -
- srvr->vals->header_preamble_size) {
+ if (len > CIFSMaxBufSize + MAX_SMB2_HDR_SIZE) {
cifs_dbg(VFS, "SMB length greater than maximum, mid=%llu\n",
mid);
return 1;
@@ -227,44 +220,38 @@ smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
}
}
- if (srvr->vals->header_preamble_size + len != length) {
- cifs_dbg(VFS, "Total length %u RFC1002 length %zu mismatch mid %llu\n",
- length, srvr->vals->header_preamble_size + len, mid);
- return 1;
- }
-
- clc_len = smb2_calc_size(hdr);
+ clc_len = smb2_calc_size(buf, srvr);
#ifdef CONFIG_CIFS_SMB311
if (shdr->Command == SMB2_NEGOTIATE)
- clc_len += get_neg_ctxt_len(hdr, len, clc_len,
- srvr->vals->header_preamble_size);
+ clc_len += get_neg_ctxt_len(shdr, len, clc_len);
#endif /* SMB311 */
- if (srvr->vals->header_preamble_size + len != clc_len) {
- cifs_dbg(FYI, "Calculated size %u length %zu mismatch mid %llu\n",
- clc_len, srvr->vals->header_preamble_size + len, mid);
+ if (len != clc_len) {
+ cifs_dbg(FYI, "Calculated size %u length %u mismatch mid %llu\n",
+ clc_len, len, mid);
/* create failed on symlink */
if (command == SMB2_CREATE_HE &&
shdr->Status == STATUS_STOPPED_ON_SYMLINK)
return 0;
/* Windows 7 server returns 24 bytes more */
- if (clc_len + 24 - srvr->vals->header_preamble_size == len && command == SMB2_OPLOCK_BREAK_HE)
+ if (clc_len + 24 == len && command == SMB2_OPLOCK_BREAK_HE)
return 0;
/* server can return one byte more due to implied bcc[0] */
- if (clc_len == srvr->vals->header_preamble_size + len + 1)
+ if (clc_len == len + 1)
return 0;
/*
* MacOS server pads after SMB2.1 write response with 3 bytes
* of junk. Other servers match RFC1001 len to actual
* SMB2/SMB3 frame length (header + smb2 response specific data)
+ * Some windows servers do too when compounding is used.
* Log the server error (once), but allow it and continue
* since the frame is parseable.
*/
- if (clc_len < srvr->vals->header_preamble_size /* RFC1001 header size */ + len) {
+ if (clc_len < len) {
printk_once(KERN_WARNING
- "SMB2 server sent bad RFC1001 len %d not %zu\n",
- len, clc_len - srvr->vals->header_preamble_size);
+ "SMB2 server sent bad RFC1001 len %d not %d\n",
+ len, clc_len);
return 0;
}
@@ -305,15 +292,14 @@ static const bool has_smb2_data_area[NUMBER_OF_SMB2_COMMANDS] = {
* area and the offset to it (from the beginning of the smb are also returned.
*/
char *
-smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr)
+smb2_get_data_area_len(int *off, int *len, struct smb2_sync_hdr *shdr)
{
- struct smb2_sync_hdr *shdr = get_sync_hdr(hdr);
*off = 0;
*len = 0;
/* error responses do not have data area */
if (shdr->Status && shdr->Status != STATUS_MORE_PROCESSING_REQUIRED &&
- (((struct smb2_err_rsp *)hdr)->StructureSize) ==
+ (((struct smb2_err_rsp *)shdr)->StructureSize) ==
SMB2_ERROR_STRUCTURE_SIZE2)
return NULL;
@@ -325,42 +311,44 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr)
switch (shdr->Command) {
case SMB2_NEGOTIATE:
*off = le16_to_cpu(
- ((struct smb2_negotiate_rsp *)hdr)->SecurityBufferOffset);
+ ((struct smb2_negotiate_rsp *)shdr)->SecurityBufferOffset);
*len = le16_to_cpu(
- ((struct smb2_negotiate_rsp *)hdr)->SecurityBufferLength);
+ ((struct smb2_negotiate_rsp *)shdr)->SecurityBufferLength);
break;
case SMB2_SESSION_SETUP:
*off = le16_to_cpu(
- ((struct smb2_sess_setup_rsp *)hdr)->SecurityBufferOffset);
+ ((struct smb2_sess_setup_rsp *)shdr)->SecurityBufferOffset);
*len = le16_to_cpu(
- ((struct smb2_sess_setup_rsp *)hdr)->SecurityBufferLength);
+ ((struct smb2_sess_setup_rsp *)shdr)->SecurityBufferLength);
break;
case SMB2_CREATE:
*off = le32_to_cpu(
- ((struct smb2_create_rsp *)hdr)->CreateContextsOffset);
+ ((struct smb2_create_rsp *)shdr)->CreateContextsOffset);
*len = le32_to_cpu(
- ((struct smb2_create_rsp *)hdr)->CreateContextsLength);
+ ((struct smb2_create_rsp *)shdr)->CreateContextsLength);
break;
case SMB2_QUERY_INFO:
*off = le16_to_cpu(
- ((struct smb2_query_info_rsp *)hdr)->OutputBufferOffset);
+ ((struct smb2_query_info_rsp *)shdr)->OutputBufferOffset);
*len = le32_to_cpu(
- ((struct smb2_query_info_rsp *)hdr)->OutputBufferLength);
+ ((struct smb2_query_info_rsp *)shdr)->OutputBufferLength);
break;
case SMB2_READ:
- *off = ((struct smb2_read_rsp *)hdr)->DataOffset;
- *len = le32_to_cpu(((struct smb2_read_rsp *)hdr)->DataLength);
+ /* TODO: is this a bug ? */
+ *off = ((struct smb2_read_rsp *)shdr)->DataOffset;
+ *len = le32_to_cpu(((struct smb2_read_rsp *)shdr)->DataLength);
break;
case SMB2_QUERY_DIRECTORY:
*off = le16_to_cpu(
- ((struct smb2_query_directory_rsp *)hdr)->OutputBufferOffset);
+ ((struct smb2_query_directory_rsp *)shdr)->OutputBufferOffset);
*len = le32_to_cpu(
- ((struct smb2_query_directory_rsp *)hdr)->OutputBufferLength);
+ ((struct smb2_query_directory_rsp *)shdr)->OutputBufferLength);
break;
case SMB2_IOCTL:
*off = le32_to_cpu(
- ((struct smb2_ioctl_rsp *)hdr)->OutputOffset);
- *len = le32_to_cpu(((struct smb2_ioctl_rsp *)hdr)->OutputCount);
+ ((struct smb2_ioctl_rsp *)shdr)->OutputOffset);
+ *len = le32_to_cpu(
+ ((struct smb2_ioctl_rsp *)shdr)->OutputCount);
break;
case SMB2_CHANGE_NOTIFY:
default:
@@ -403,15 +391,14 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr)
* portion, the number of word parameters and the data portion of the message.
*/
unsigned int
-smb2_calc_size(void *buf)
+smb2_calc_size(void *buf, struct TCP_Server_Info *srvr)
{
- struct smb2_pdu *pdu = (struct smb2_pdu *)buf;
- struct smb2_hdr *hdr = &pdu->hdr;
- struct smb2_sync_hdr *shdr = get_sync_hdr(hdr);
+ struct smb2_sync_pdu *pdu = (struct smb2_sync_pdu *)buf;
+ struct smb2_sync_hdr *shdr = &pdu->sync_hdr;
int offset; /* the offset from the beginning of SMB to data area */
int data_length; /* the length of the variable length data area */
/* Structure Size has already been checked to make sure it is 64 */
- int len = 4 + le16_to_cpu(shdr->StructureSize);
+ int len = le16_to_cpu(shdr->StructureSize);
/*
* StructureSize2, ie length of fixed parameter area has already
@@ -422,7 +409,7 @@ smb2_calc_size(void *buf)
if (has_smb2_data_area[le16_to_cpu(shdr->Command)] == false)
goto calc_size_exit;
- smb2_get_data_area_len(&offset, &data_length, hdr);
+ smb2_get_data_area_len(&offset, &data_length, shdr);
cifs_dbg(FYI, "SMB2 data length %d offset %d\n", data_length, offset);
if (data_length > 0) {
@@ -430,15 +417,14 @@ smb2_calc_size(void *buf)
* Check to make sure that data area begins after fixed area,
* Note that last byte of the fixed area is part of data area
* for some commands, typically those with odd StructureSize,
- * so we must add one to the calculation (and 4 to account for
- * the size of the RFC1001 hdr.
+ * so we must add one to the calculation.
*/
- if (offset + 4 + 1 < len) {
+ if (offset + 1 < len) {
cifs_dbg(VFS, "data area offset %d overlaps SMB2 header %d\n",
- offset + 4 + 1, len);
+ offset + 1, len);
data_length = 0;
} else {
- len = 4 + offset + data_length;
+ len = offset + data_length;
}
}
calc_size_exit:
@@ -465,8 +451,14 @@ cifs_convert_path_to_utf16(const char *from, struct cifs_sb_info *cifs_sb)
/* Windows doesn't allow paths beginning with \ */
if (from[0] == '\\')
start_of_path = from + 1;
+#ifdef CONFIG_CIFS_SMB311
+ /* SMB311 POSIX extensions paths do not include leading slash */
+ else if (cifs_sb_master_tcon(cifs_sb)->posix_extensions)
+ start_of_path = from + 1;
+#endif /* 311 */
else
start_of_path = from;
+
to = cifs_strndup_to_utf16(start_of_path, PATH_MAX, &len,
cifs_sb->local_nls, map_type);
return to;
@@ -621,7 +613,7 @@ smb2_is_valid_lease_break(char *buffer)
bool
smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
{
- struct smb2_oplock_break_rsp *rsp = (struct smb2_oplock_break_rsp *)buffer;
+ struct smb2_oplock_break *rsp = (struct smb2_oplock_break *)buffer;
struct list_head *tmp, *tmp1, *tmp2;
struct cifs_ses *ses;
struct cifs_tcon *tcon;
@@ -630,7 +622,7 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
cifs_dbg(FYI, "Checking for oplock break\n");
- if (rsp->hdr.sync_hdr.Command != SMB2_OPLOCK_BREAK)
+ if (rsp->sync_hdr.Command != SMB2_OPLOCK_BREAK)
return false;
if (rsp->StructureSize !=
@@ -721,7 +713,7 @@ smb2_cancelled_close_fid(struct work_struct *work)
int
smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server)
{
- struct smb2_sync_hdr *sync_hdr = get_sync_hdr(buffer);
+ struct smb2_sync_hdr *sync_hdr = (struct smb2_sync_hdr *)buffer;
struct smb2_create_rsp *rsp = (struct smb2_create_rsp *)buffer;
struct cifs_tcon *tcon;
struct close_cancelled_open *cancelled;
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index b4ae932..950d0ab2 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -123,7 +123,7 @@ smb2_get_credits_field(struct TCP_Server_Info *server, const int optype)
static unsigned int
smb2_get_credits(struct mid_q_entry *mid)
{
- struct smb2_sync_hdr *shdr = get_sync_hdr(mid->resp_buf);
+ struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)mid->resp_buf;
return le16_to_cpu(shdr->CreditRequest);
}
@@ -190,7 +190,7 @@ static struct mid_q_entry *
smb2_find_mid(struct TCP_Server_Info *server, char *buf)
{
struct mid_q_entry *mid;
- struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+ struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
__u64 wire_mid = le64_to_cpu(shdr->MessageId);
if (shdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) {
@@ -212,15 +212,16 @@ smb2_find_mid(struct TCP_Server_Info *server, char *buf)
}
static void
-smb2_dump_detail(void *buf)
+smb2_dump_detail(void *buf, struct TCP_Server_Info *server)
{
#ifdef CONFIG_CIFS_DEBUG2
- struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+ struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
cifs_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Mid: %llu Pid: %d\n",
shdr->Command, shdr->Status, shdr->Flags, shdr->MessageId,
shdr->ProcessId);
- cifs_dbg(VFS, "smb buf %p len %u\n", buf, smb2_calc_size(buf));
+ cifs_dbg(VFS, "smb buf %p len %u\n", buf,
+ server->ops->calc_smb_size(buf, server));
#endif
}
@@ -252,9 +253,14 @@ smb2_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *volume_info)
wsize = volume_info->wsize ? volume_info->wsize : CIFS_DEFAULT_IOSIZE;
wsize = min_t(unsigned int, wsize, server->max_write);
#ifdef CONFIG_CIFS_SMB_DIRECT
- if (server->rdma)
- wsize = min_t(unsigned int,
+ if (server->rdma) {
+ if (server->sign)
+ wsize = min_t(unsigned int,
+ wsize, server->smbd_conn->max_fragmented_send_size);
+ else
+ wsize = min_t(unsigned int,
wsize, server->smbd_conn->max_readwrite_size);
+ }
#endif
if (!(server->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU))
wsize = min_t(unsigned int, wsize, SMB2_MAX_BUFFER_SIZE);
@@ -272,9 +278,14 @@ smb2_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *volume_info)
rsize = volume_info->rsize ? volume_info->rsize : CIFS_DEFAULT_IOSIZE;
rsize = min_t(unsigned int, rsize, server->max_read);
#ifdef CONFIG_CIFS_SMB_DIRECT
- if (server->rdma)
- rsize = min_t(unsigned int,
+ if (server->rdma) {
+ if (server->sign)
+ rsize = min_t(unsigned int,
+ rsize, server->smbd_conn->max_fragmented_recv_size);
+ else
+ rsize = min_t(unsigned int,
rsize, server->smbd_conn->max_readwrite_size);
+ }
#endif
if (!(server->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU))
@@ -312,6 +323,40 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon)
}
#endif /* STATS2 */
+/*
+ * Open the directory at the root of a share
+ */
+int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid)
+{
+ struct cifs_open_parms oparams;
+ int rc;
+ __le16 srch_path = 0; /* Null - since an open of top of share */
+ u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
+
+ mutex_lock(&tcon->prfid_mutex);
+ if (tcon->valid_root_fid) {
+ cifs_dbg(FYI, "found a cached root file handle\n");
+ memcpy(pfid, tcon->prfid, sizeof(struct cifs_fid));
+ mutex_unlock(&tcon->prfid_mutex);
+ return 0;
+ }
+
+ oparams.tcon = tcon;
+ oparams.create_options = 0;
+ oparams.desired_access = FILE_READ_ATTRIBUTES;
+ oparams.disposition = FILE_OPEN;
+ oparams.fid = pfid;
+ oparams.reconnect = false;
+
+ rc = SMB2_open(xid, &oparams, &srch_path, &oplock, NULL, NULL);
+ if (rc == 0) {
+ memcpy(tcon->prfid, pfid, sizeof(struct cifs_fid));
+ tcon->valid_root_fid = true;
+ }
+ mutex_unlock(&tcon->prfid_mutex);
+ return rc;
+}
+
static void
smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon)
{
@@ -320,6 +365,7 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon)
u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
struct cifs_open_parms oparms;
struct cifs_fid fid;
+ bool no_cached_open = tcon->nohandlecache;
oparms.tcon = tcon;
oparms.desired_access = FILE_READ_ATTRIBUTES;
@@ -328,7 +374,11 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon)
oparms.fid = &fid;
oparms.reconnect = false;
- rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL);
+ if (no_cached_open)
+ rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL);
+ else
+ rc = open_shroot(xid, tcon, &fid);
+
if (rc)
return;
@@ -342,7 +392,8 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon)
FS_DEVICE_INFORMATION);
SMB2_QFS_attr(xid, tcon, fid.persistent_fid, fid.volatile_fid,
FS_SECTOR_SIZE_INFORMATION); /* SMB3 specific */
- SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
+ if (no_cached_open)
+ SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
return;
}
@@ -384,6 +435,9 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon,
struct cifs_open_parms oparms;
struct cifs_fid fid;
+ if ((*full_path == 0) && tcon->valid_root_fid)
+ return 0;
+
utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb);
if (!utf16_path)
return -ENOMEM;
@@ -579,9 +633,15 @@ smb2_query_eas(const unsigned int xid, struct cifs_tcon *tcon,
SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
+ /*
+ * If ea_name is NULL (listxattr) and there are no EAs, return 0 as it's
+ * not an error. Otherwise, the specified ea_name was not found.
+ */
if (!rc)
rc = move_smb2_ea_to_cifs(ea_data, buf_size, smb2_data,
SMB2_MAX_EA_BUF, ea_name);
+ else if (!ea_name && rc == -ENODATA)
+ rc = 0;
kfree(smb2_data);
return rc;
@@ -688,9 +748,11 @@ smb2_dump_share_caps(struct seq_file *m, struct cifs_tcon *tcon)
seq_puts(m, " TRIM-support,");
seq_printf(m, "\tShare Flags: 0x%x", tcon->share_flags);
+ seq_printf(m, "\n\ttid: 0x%x", tcon->tid);
if (tcon->perf_sector_size)
seq_printf(m, "\tOptimal sector size: 0x%x",
tcon->perf_sector_size);
+ seq_printf(m, "\tMaximal Access: 0x%x", tcon->maximal_access);
}
static void
@@ -1241,7 +1303,7 @@ smb2_close_dir(const unsigned int xid, struct cifs_tcon *tcon,
static bool
smb2_is_status_pending(char *buf, struct TCP_Server_Info *server, int length)
{
- struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+ struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
if (shdr->Status != STATUS_PENDING)
return false;
@@ -1259,12 +1321,13 @@ smb2_is_status_pending(char *buf, struct TCP_Server_Info *server, int length)
static bool
smb2_is_session_expired(char *buf)
{
- struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+ struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
- if (shdr->Status != STATUS_NETWORK_SESSION_EXPIRED)
+ if (shdr->Status != STATUS_NETWORK_SESSION_EXPIRED &&
+ shdr->Status != STATUS_USER_SESSION_DELETED)
return false;
- cifs_dbg(FYI, "Session expired\n");
+ cifs_dbg(FYI, "Session expired or deleted\n");
return true;
}
@@ -1452,14 +1515,12 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
struct cifs_open_parms oparms;
struct cifs_fid fid;
struct kvec err_iov = {NULL, 0};
- struct smb2_err_rsp *err_buf = NULL;
+ struct smb2_err_rsp *err_buf;
struct smb2_symlink_err_rsp *symlink;
unsigned int sub_len;
unsigned int sub_offset;
unsigned int print_len;
unsigned int print_offset;
- struct cifs_ses *ses = tcon->ses;
- struct TCP_Server_Info *server = ses->server;
cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path);
@@ -1476,14 +1537,14 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, &err_iov);
- if (!rc || !err_buf) {
+ if (!rc || !err_iov.iov_base) {
kfree(utf16_path);
return -ENOENT;
}
err_buf = err_iov.iov_base;
if (le32_to_cpu(err_buf->ByteCount) < sizeof(struct smb2_symlink_err_rsp) ||
- err_iov.iov_len + server->vals->header_preamble_size < SMB2_SYMLINK_STRUCT_SIZE) {
+ err_iov.iov_len < SMB2_SYMLINK_STRUCT_SIZE) {
kfree(utf16_path);
return -ENOENT;
}
@@ -1496,14 +1557,13 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
print_len = le16_to_cpu(symlink->PrintNameLength);
print_offset = le16_to_cpu(symlink->PrintNameOffset);
- if (err_iov.iov_len + server->vals->header_preamble_size <
- SMB2_SYMLINK_STRUCT_SIZE + sub_offset + sub_len) {
+ if (err_iov.iov_len < SMB2_SYMLINK_STRUCT_SIZE + sub_offset + sub_len) {
kfree(utf16_path);
return -ENOENT;
}
- if (err_iov.iov_len + server->vals->header_preamble_size <
- SMB2_SYMLINK_STRUCT_SIZE + print_offset + print_len) {
+ if (err_iov.iov_len <
+ SMB2_SYMLINK_STRUCT_SIZE + print_offset + print_len) {
kfree(utf16_path);
return -ENOENT;
}
@@ -1577,8 +1637,11 @@ get_smb2_acl_by_path(struct cifs_sb_info *cifs_sb,
oparms.create_options = 0;
utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
- if (!utf16_path)
- return ERR_PTR(-ENOMEM);
+ if (!utf16_path) {
+ rc = -ENOMEM;
+ free_xid(xid);
+ return ERR_PTR(rc);
+ }
oparms.tcon = tcon;
oparms.desired_access = READ_CONTROL;
@@ -1636,8 +1699,11 @@ set_smb2_acl(struct cifs_ntsd *pnntsd, __u32 acllen,
access_flags = WRITE_DAC;
utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
- if (!utf16_path)
- return -ENOMEM;
+ if (!utf16_path) {
+ rc = -ENOMEM;
+ free_xid(xid);
+ return rc;
+ }
oparms.tcon = tcon;
oparms.desired_access = access_flags;
@@ -1697,15 +1763,21 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
/* if file not oplocked can't be sure whether asking to extend size */
if (!CIFS_CACHE_READ(cifsi))
- if (keep_size == false)
- return -EOPNOTSUPP;
+ if (keep_size == false) {
+ rc = -EOPNOTSUPP;
+ free_xid(xid);
+ return rc;
+ }
/*
* Must check if file sparse since fallocate -z (zero range) assumes
* non-sparse allocation
*/
- if (!(cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE))
- return -EOPNOTSUPP;
+ if (!(cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE)) {
+ rc = -EOPNOTSUPP;
+ free_xid(xid);
+ return rc;
+ }
/*
* need to make sure we are not asked to extend the file since the SMB3
@@ -1714,8 +1786,11 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
* which for a non sparse file would zero the newly extended range
*/
if (keep_size == false)
- if (i_size_read(inode) < offset + len)
- return -EOPNOTSUPP;
+ if (i_size_read(inode) < offset + len) {
+ rc = -EOPNOTSUPP;
+ free_xid(xid);
+ return rc;
+ }
cifs_dbg(FYI, "offset %lld len %lld", offset, len);
@@ -1748,8 +1823,11 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
/* Need to make file sparse, if not already, before freeing range. */
/* Consider adding equivalent for compressed since it could also work */
- if (!smb2_set_sparse(xid, tcon, cfile, inode, set_sparse))
- return -EOPNOTSUPP;
+ if (!smb2_set_sparse(xid, tcon, cfile, inode, set_sparse)) {
+ rc = -EOPNOTSUPP;
+ free_xid(xid);
+ return rc;
+ }
cifs_dbg(FYI, "offset %lld len %lld", offset, len);
@@ -1780,8 +1858,10 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
/* if file not oplocked can't be sure whether asking to extend size */
if (!CIFS_CACHE_READ(cifsi))
- if (keep_size == false)
- return -EOPNOTSUPP;
+ if (keep_size == false) {
+ free_xid(xid);
+ return rc;
+ }
/*
* Files are non-sparse by default so falloc may be a no-op
@@ -1790,14 +1870,16 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
*/
if ((cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE) == 0) {
if (keep_size == true)
- return 0;
+ rc = 0;
/* check if extending file */
else if (i_size_read(inode) >= off + len)
/* not extending file and already not sparse */
- return 0;
+ rc = 0;
/* BB: in future add else clause to extend file */
else
- return -EOPNOTSUPP;
+ rc = -EOPNOTSUPP;
+ free_xid(xid);
+ return rc;
}
if ((keep_size == true) || (i_size_read(inode) >= off + len)) {
@@ -1809,8 +1891,11 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
* ie potentially making a few extra pages at the beginning
* or end of the file non-sparse via set_sparse is harmless.
*/
- if ((off > 8192) || (off + len + 8192 < i_size_read(inode)))
- return -EOPNOTSUPP;
+ if ((off > 8192) || (off + len + 8192 < i_size_read(inode))) {
+ rc = -EOPNOTSUPP;
+ free_xid(xid);
+ return rc;
+ }
rc = smb2_set_sparse(xid, tcon, cfile, inode, false);
}
@@ -2019,7 +2104,7 @@ smb3_create_lease_buf(u8 *lease_key, u8 oplock)
}
static __u8
-smb2_parse_lease_buf(void *buf, unsigned int *epoch)
+smb2_parse_lease_buf(void *buf, unsigned int *epoch, char *lease_key)
{
struct create_lease *lc = (struct create_lease *)buf;
@@ -2030,13 +2115,16 @@ smb2_parse_lease_buf(void *buf, unsigned int *epoch)
}
static __u8
-smb3_parse_lease_buf(void *buf, unsigned int *epoch)
+smb3_parse_lease_buf(void *buf, unsigned int *epoch, char *lease_key)
{
struct create_lease_v2 *lc = (struct create_lease_v2 *)buf;
*epoch = le16_to_cpu(lc->lcontext.Epoch);
if (lc->lcontext.LeaseFlags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS)
return SMB2_OPLOCK_LEVEL_NOCHANGE;
+ if (lease_key)
+ memcpy(lease_key, &lc->lcontext.LeaseKeyLow,
+ SMB2_LEASE_KEY_SIZE);
return le32_to_cpu(lc->lcontext.LeaseState);
}
@@ -2054,12 +2142,11 @@ smb2_dir_needs_close(struct cifsFileInfo *cfile)
}
static void
-fill_transform_hdr(struct TCP_Server_Info *server,
- struct smb2_transform_hdr *tr_hdr, struct smb_rqst *old_rq)
+fill_transform_hdr(struct smb2_transform_hdr *tr_hdr, unsigned int orig_len,
+ struct smb_rqst *old_rq)
{
struct smb2_sync_hdr *shdr =
(struct smb2_sync_hdr *)old_rq->rq_iov[1].iov_base;
- unsigned int orig_len = get_rfc1002_length(old_rq->rq_iov[0].iov_base);
memset(tr_hdr, 0, sizeof(struct smb2_transform_hdr));
tr_hdr->ProtocolId = SMB2_TRANSFORM_PROTO_NUM;
@@ -2067,8 +2154,6 @@ fill_transform_hdr(struct TCP_Server_Info *server,
tr_hdr->Flags = cpu_to_le16(0x01);
get_random_bytes(&tr_hdr->Nonce, SMB3_AES128CMM_NONCE);
memcpy(&tr_hdr->SessionId, &shdr->SessionId, 8);
- inc_rfc1001_len(tr_hdr, sizeof(struct smb2_transform_hdr) - server->vals->header_preamble_size);
- inc_rfc1001_len(tr_hdr, orig_len);
}
/* We can not use the normal sg_set_buf() as we will sometimes pass a
@@ -2080,11 +2165,16 @@ static inline void smb2_sg_set_buf(struct scatterlist *sg, const void *buf,
sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf));
}
+/* Assumes:
+ * rqst->rq_iov[0] is rfc1002 length
+ * rqst->rq_iov[1] is tranform header
+ * rqst->rq_iov[2+] data to be encrypted/decrypted
+ */
static struct scatterlist *
init_sg(struct smb_rqst *rqst, u8 *sign)
{
- unsigned int sg_len = rqst->rq_nvec + rqst->rq_npages + 1;
- unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 24;
+ unsigned int sg_len = rqst->rq_nvec + rqst->rq_npages;
+ unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20;
struct scatterlist *sg;
unsigned int i;
unsigned int j;
@@ -2094,10 +2184,10 @@ init_sg(struct smb_rqst *rqst, u8 *sign)
return NULL;
sg_init_table(sg, sg_len);
- smb2_sg_set_buf(&sg[0], rqst->rq_iov[0].iov_base + 24, assoc_data_len);
- for (i = 1; i < rqst->rq_nvec; i++)
- smb2_sg_set_buf(&sg[i], rqst->rq_iov[i].iov_base,
- rqst->rq_iov[i].iov_len);
+ smb2_sg_set_buf(&sg[0], rqst->rq_iov[1].iov_base + 20, assoc_data_len);
+ for (i = 1; i < rqst->rq_nvec - 1; i++)
+ smb2_sg_set_buf(&sg[i], rqst->rq_iov[i+1].iov_base,
+ rqst->rq_iov[i+1].iov_len);
for (j = 0; i < sg_len - 1; i++, j++) {
unsigned int len = (j < rqst->rq_npages - 1) ? rqst->rq_pagesz
: rqst->rq_tailsz;
@@ -2129,9 +2219,10 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key)
}
/*
* Encrypt or decrypt @rqst message. @rqst has the following format:
- * iov[0] - transform header (associate data),
- * iov[1-N] and pages - data to encrypt.
- * On success return encrypted data in iov[1-N] and pages, leave iov[0]
+ * iov[0] - rfc1002 length
+ * iov[1] - transform header (associate data),
+ * iov[2-N] and pages - data to encrypt.
+ * On success return encrypted data in iov[2-N] and pages, leave iov[0-1]
* untouched.
*/
static int
@@ -2139,7 +2230,7 @@ crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc)
{
struct smb2_transform_hdr *tr_hdr =
(struct smb2_transform_hdr *)rqst->rq_iov[0].iov_base;
- unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20 - server->vals->header_preamble_size;
+ unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20;
int rc = 0;
struct scatterlist *sg;
u8 sign[SMB2_SIGNATURE_SIZE] = {};
@@ -2226,6 +2317,10 @@ crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc)
return rc;
}
+/*
+ * This is called from smb_send_rqst. At this point we have the rfc1002
+ * header as the first element in the vector.
+ */
static int
smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq,
struct smb_rqst *old_rq)
@@ -2234,6 +2329,7 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq,
struct page **pages;
struct smb2_transform_hdr *tr_hdr;
unsigned int npages = old_rq->rq_npages;
+ unsigned int orig_len = get_rfc1002_length(old_rq->rq_iov[0].iov_base);
int i;
int rc = -ENOMEM;
@@ -2252,24 +2348,34 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq,
goto err_free_pages;
}
- iov = kmalloc_array(old_rq->rq_nvec, sizeof(struct kvec), GFP_KERNEL);
+ /* Make space for one extra iov to hold the transform header */
+ iov = kmalloc_array(old_rq->rq_nvec + 1, sizeof(struct kvec),
+ GFP_KERNEL);
if (!iov)
goto err_free_pages;
/* copy all iovs from the old except the 1st one (rfc1002 length) */
- memcpy(&iov[1], &old_rq->rq_iov[1],
+ memcpy(&iov[2], &old_rq->rq_iov[1],
sizeof(struct kvec) * (old_rq->rq_nvec - 1));
+ /* copy the rfc1002 iov */
+ iov[0].iov_base = old_rq->rq_iov[0].iov_base;
+ iov[0].iov_len = old_rq->rq_iov[0].iov_len;
+
new_rq->rq_iov = iov;
- new_rq->rq_nvec = old_rq->rq_nvec;
+ new_rq->rq_nvec = old_rq->rq_nvec + 1;
tr_hdr = kmalloc(sizeof(struct smb2_transform_hdr), GFP_KERNEL);
if (!tr_hdr)
goto err_free_iov;
- /* fill the 1st iov with a transform header */
- fill_transform_hdr(server, tr_hdr, old_rq);
- new_rq->rq_iov[0].iov_base = tr_hdr;
- new_rq->rq_iov[0].iov_len = sizeof(struct smb2_transform_hdr);
+ /* fill the 2nd iov with a transform header */
+ fill_transform_hdr(tr_hdr, orig_len, old_rq);
+ new_rq->rq_iov[1].iov_base = tr_hdr;
+ new_rq->rq_iov[1].iov_len = sizeof(struct smb2_transform_hdr);
+
+ /* Update rfc1002 header */
+ inc_rfc1001_len(new_rq->rq_iov[0].iov_base,
+ sizeof(struct smb2_transform_hdr));
/* copy pages form the old */
for (i = 0; i < npages; i++) {
@@ -2309,7 +2415,7 @@ smb3_free_transform_rq(struct smb_rqst *rqst)
put_page(rqst->rq_pages[i]);
kfree(rqst->rq_pages);
/* free transform header */
- kfree(rqst->rq_iov[0].iov_base);
+ kfree(rqst->rq_iov[1].iov_base);
kfree(rqst->rq_iov);
}
@@ -2326,18 +2432,19 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf,
unsigned int buf_data_size, struct page **pages,
unsigned int npages, unsigned int page_data_size)
{
- struct kvec iov[2];
+ struct kvec iov[3];
struct smb_rqst rqst = {NULL};
- struct smb2_hdr *hdr;
int rc;
- iov[0].iov_base = buf;
- iov[0].iov_len = sizeof(struct smb2_transform_hdr);
- iov[1].iov_base = buf + sizeof(struct smb2_transform_hdr);
- iov[1].iov_len = buf_data_size;
+ iov[0].iov_base = NULL;
+ iov[0].iov_len = 0;
+ iov[1].iov_base = buf;
+ iov[1].iov_len = sizeof(struct smb2_transform_hdr);
+ iov[2].iov_base = buf + sizeof(struct smb2_transform_hdr);
+ iov[2].iov_len = buf_data_size;
rqst.rq_iov = iov;
- rqst.rq_nvec = 2;
+ rqst.rq_nvec = 3;
rqst.rq_pages = pages;
rqst.rq_npages = npages;
rqst.rq_pagesz = PAGE_SIZE;
@@ -2349,10 +2456,9 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf,
if (rc)
return rc;
- memmove(buf + server->vals->header_preamble_size, iov[1].iov_base, buf_data_size);
- hdr = (struct smb2_hdr *)buf;
- hdr->smb2_buf_length = cpu_to_be32(buf_data_size + page_data_size);
- server->total_read = buf_data_size + page_data_size + server->vals->header_preamble_size;
+ memmove(buf, iov[2].iov_base, buf_data_size);
+
+ server->total_read = buf_data_size + page_data_size;
return rc;
}
@@ -2377,7 +2483,7 @@ read_data_into_pages(struct TCP_Server_Info *server, struct page **pages,
zero_user(page, len, PAGE_SIZE - len);
len = 0;
}
- length = cifs_read_page_from_socket(server, page, n);
+ length = cifs_read_page_from_socket(server, page, 0, n);
if (length < 0)
return length;
server->total_read += length;
@@ -2425,7 +2531,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid,
unsigned int cur_page_idx;
unsigned int pad_len;
struct cifs_readdata *rdata = mid->callback_data;
- struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+ struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
struct bio_vec *bvec = NULL;
struct iov_iter iter;
struct kvec iov;
@@ -2456,7 +2562,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid,
return 0;
}
- data_offset = server->ops->read_data_offset(buf) + server->vals->header_preamble_size;
+ data_offset = server->ops->read_data_offset(buf);
#ifdef CONFIG_CIFS_SMB_DIRECT
use_rdma_mr = rdata->mr;
#endif
@@ -2552,12 +2658,11 @@ receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid)
unsigned int npages;
struct page **pages;
unsigned int len;
- unsigned int buflen = server->pdu_size + server->vals->header_preamble_size;
+ unsigned int buflen = server->pdu_size;
int rc;
int i = 0;
- len = min_t(unsigned int, buflen, server->vals->read_rsp_size -
- server->vals->header_preamble_size +
+ len = min_t(unsigned int, buflen, server->vals->read_rsp_size +
sizeof(struct smb2_transform_hdr)) - HEADER_SIZE(server) + 1;
rc = cifs_read_from_socket(server, buf + HEADER_SIZE(server) - 1, len);
@@ -2565,8 +2670,7 @@ receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid)
return rc;
server->total_read += rc;
- len = le32_to_cpu(tr_hdr->OriginalMessageSize) +
- server->vals->header_preamble_size -
+ len = le32_to_cpu(tr_hdr->OriginalMessageSize) -
server->vals->read_rsp_size;
npages = DIV_ROUND_UP(len, PAGE_SIZE);
@@ -2593,8 +2697,7 @@ receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid)
if (rc)
goto free_pages;
- rc = decrypt_raw_data(server, buf, server->vals->read_rsp_size -
- server->vals->header_preamble_size,
+ rc = decrypt_raw_data(server, buf, server->vals->read_rsp_size,
pages, npages, len);
if (rc)
goto free_pages;
@@ -2631,7 +2734,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server,
struct mid_q_entry *mid_entry;
/* switch to large buffer if too big for a small one */
- if (pdu_length + server->vals->header_preamble_size > MAX_CIFS_SMALL_BUFFER_SIZE) {
+ if (pdu_length > MAX_CIFS_SMALL_BUFFER_SIZE) {
server->large_buf = true;
memcpy(server->bigbuf, buf, server->total_read);
buf = server->bigbuf;
@@ -2639,13 +2742,12 @@ receive_encrypted_standard(struct TCP_Server_Info *server,
/* now read the rest */
length = cifs_read_from_socket(server, buf + HEADER_SIZE(server) - 1,
- pdu_length - HEADER_SIZE(server) + 1 +
- server->vals->header_preamble_size);
+ pdu_length - HEADER_SIZE(server) + 1);
if (length < 0)
return length;
server->total_read += length;
- buf_size = pdu_length + server->vals->header_preamble_size - sizeof(struct smb2_transform_hdr);
+ buf_size = pdu_length - sizeof(struct smb2_transform_hdr);
length = decrypt_raw_data(server, buf, buf_size, NULL, 0, 0);
if (length)
return length;
@@ -2674,7 +2776,7 @@ smb3_receive_transform(struct TCP_Server_Info *server, struct mid_q_entry **mid)
struct smb2_transform_hdr *tr_hdr = (struct smb2_transform_hdr *)buf;
unsigned int orig_len = le32_to_cpu(tr_hdr->OriginalMessageSize);
- if (pdu_length + server->vals->header_preamble_size < sizeof(struct smb2_transform_hdr) +
+ if (pdu_length < sizeof(struct smb2_transform_hdr) +
sizeof(struct smb2_sync_hdr)) {
cifs_dbg(VFS, "Transform message is too small (%u)\n",
pdu_length);
@@ -2683,14 +2785,14 @@ smb3_receive_transform(struct TCP_Server_Info *server, struct mid_q_entry **mid)
return -ECONNABORTED;
}
- if (pdu_length + server->vals->header_preamble_size < orig_len + sizeof(struct smb2_transform_hdr)) {
+ if (pdu_length < orig_len + sizeof(struct smb2_transform_hdr)) {
cifs_dbg(VFS, "Transform message is broken\n");
cifs_reconnect(server);
wake_up(&server->response_q);
return -ECONNABORTED;
}
- if (pdu_length + server->vals->header_preamble_size > CIFSMaxBufSize + MAX_HEADER_SIZE(server))
+ if (pdu_length > CIFSMaxBufSize + MAX_HEADER_SIZE(server))
return receive_encrypted_read(server, mid);
return receive_encrypted_standard(server, mid);
@@ -2701,11 +2803,23 @@ smb3_handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid)
{
char *buf = server->large_buf ? server->bigbuf : server->smallbuf;
- return handle_read_data(server, mid, buf, server->pdu_size +
- server->vals->header_preamble_size,
+ return handle_read_data(server, mid, buf, server->pdu_size,
NULL, 0, 0);
}
+static int
+smb2_next_header(char *buf)
+{
+ struct smb2_sync_hdr *hdr = (struct smb2_sync_hdr *)buf;
+ struct smb2_transform_hdr *t_hdr = (struct smb2_transform_hdr *)buf;
+
+ if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM)
+ return sizeof(struct smb2_transform_hdr) +
+ le32_to_cpu(t_hdr->OriginalMessageSize);
+
+ return le32_to_cpu(hdr->NextCommand);
+}
+
struct smb_version_operations smb20_operations = {
.compare_fids = smb2_compare_fids,
.setup_request = smb2_setup_request,
@@ -2797,6 +2911,7 @@ struct smb_version_operations smb20_operations = {
.get_acl_by_fid = get_smb2_acl_by_fid,
.set_acl = set_smb2_acl,
#endif /* CIFS_ACL */
+ .next_header = smb2_next_header,
};
struct smb_version_operations smb21_operations = {
@@ -2891,6 +3006,7 @@ struct smb_version_operations smb21_operations = {
.get_acl_by_fid = get_smb2_acl_by_fid,
.set_acl = set_smb2_acl,
#endif /* CIFS_ACL */
+ .next_header = smb2_next_header,
};
struct smb_version_operations smb30_operations = {
@@ -2995,6 +3111,7 @@ struct smb_version_operations smb30_operations = {
.get_acl_by_fid = get_smb2_acl_by_fid,
.set_acl = set_smb2_acl,
#endif /* CIFS_ACL */
+ .next_header = smb2_next_header,
};
#ifdef CONFIG_CIFS_SMB311
@@ -3095,6 +3212,7 @@ struct smb_version_operations smb311_operations = {
.query_all_EAs = smb2_query_eas,
.set_EA = smb2_set_ea,
#endif /* CIFS_XATTR */
+ .next_header = smb2_next_header,
};
#endif /* CIFS_SMB311 */
@@ -3106,8 +3224,8 @@ struct smb_version_values smb20_values = {
.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
- .header_size = sizeof(struct smb2_hdr),
- .header_preamble_size = 4,
+ .header_size = sizeof(struct smb2_sync_hdr),
+ .header_preamble_size = 0,
.max_header_size = MAX_SMB2_HDR_SIZE,
.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
.lock_cmd = SMB2_LOCK,
@@ -3127,8 +3245,8 @@ struct smb_version_values smb21_values = {
.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
- .header_size = sizeof(struct smb2_hdr),
- .header_preamble_size = 4,
+ .header_size = sizeof(struct smb2_sync_hdr),
+ .header_preamble_size = 0,
.max_header_size = MAX_SMB2_HDR_SIZE,
.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
.lock_cmd = SMB2_LOCK,
@@ -3148,8 +3266,8 @@ struct smb_version_values smb3any_values = {
.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
- .header_size = sizeof(struct smb2_hdr),
- .header_preamble_size = 4,
+ .header_size = sizeof(struct smb2_sync_hdr),
+ .header_preamble_size = 0,
.max_header_size = MAX_SMB2_HDR_SIZE,
.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
.lock_cmd = SMB2_LOCK,
@@ -3169,8 +3287,8 @@ struct smb_version_values smbdefault_values = {
.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
- .header_size = sizeof(struct smb2_hdr),
- .header_preamble_size = 4,
+ .header_size = sizeof(struct smb2_sync_hdr),
+ .header_preamble_size = 0,
.max_header_size = MAX_SMB2_HDR_SIZE,
.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
.lock_cmd = SMB2_LOCK,
@@ -3190,8 +3308,8 @@ struct smb_version_values smb30_values = {
.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
- .header_size = sizeof(struct smb2_hdr),
- .header_preamble_size = 4,
+ .header_size = sizeof(struct smb2_sync_hdr),
+ .header_preamble_size = 0,
.max_header_size = MAX_SMB2_HDR_SIZE,
.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
.lock_cmd = SMB2_LOCK,
@@ -3211,8 +3329,8 @@ struct smb_version_values smb302_values = {
.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
- .header_size = sizeof(struct smb2_hdr),
- .header_preamble_size = 4,
+ .header_size = sizeof(struct smb2_sync_hdr),
+ .header_preamble_size = 0,
.max_header_size = MAX_SMB2_HDR_SIZE,
.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
.lock_cmd = SMB2_LOCK,
@@ -3233,8 +3351,8 @@ struct smb_version_values smb311_values = {
.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
.unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
- .header_size = sizeof(struct smb2_hdr),
- .header_preamble_size = 4,
+ .header_size = sizeof(struct smb2_sync_hdr),
+ .header_preamble_size = 0,
.max_header_size = MAX_SMB2_HDR_SIZE,
.read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
.lock_cmd = SMB2_LOCK,
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 0f044c4..281fbc1 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -49,6 +49,7 @@
#include "cifspdu.h"
#include "cifs_spnego.h"
#include "smbdirect.h"
+#include "trace.h"
/*
* The following table defines the expected "StructureSize" of SMB2 requests
@@ -79,7 +80,7 @@ static const int smb2_req_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
/* SMB2_OPLOCK_BREAK */ 24 /* BB this is 36 for LEASE_BREAK variant */
};
-static int encryption_required(const struct cifs_tcon *tcon)
+static int smb3_encryption_required(const struct cifs_tcon *tcon)
{
if (!tcon)
return 0;
@@ -145,7 +146,7 @@ smb2_hdr_assemble(struct smb2_sync_hdr *shdr, __le16 smb2_cmd,
shdr->Flags |= SMB2_FLAGS_DFS_OPERATIONS; */
if (tcon->ses && tcon->ses->server && tcon->ses->server->sign &&
- !encryption_required(tcon))
+ !smb3_encryption_required(tcon))
shdr->Flags |= SMB2_FLAGS_SIGNED;
out:
return;
@@ -367,6 +368,7 @@ smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
#define SMB2_PREAUTH_INTEGRITY_CAPABILITIES cpu_to_le16(1)
#define SMB2_ENCRYPTION_CAPABILITIES cpu_to_le16(2)
+#define SMB2_POSIX_EXTENSIONS_AVAILABLE cpu_to_le16(0x100)
static void
build_preauth_ctxt(struct smb2_preauth_neg_context *pneg_ctxt)
@@ -383,10 +385,17 @@ static void
build_encrypt_ctxt(struct smb2_encryption_neg_context *pneg_ctxt)
{
pneg_ctxt->ContextType = SMB2_ENCRYPTION_CAPABILITIES;
- pneg_ctxt->DataLength = cpu_to_le16(6);
- pneg_ctxt->CipherCount = cpu_to_le16(2);
- pneg_ctxt->Ciphers[0] = SMB2_ENCRYPTION_AES128_GCM;
- pneg_ctxt->Ciphers[1] = SMB2_ENCRYPTION_AES128_CCM;
+ pneg_ctxt->DataLength = cpu_to_le16(4); /* Cipher Count + le16 cipher */
+ pneg_ctxt->CipherCount = cpu_to_le16(1);
+/* pneg_ctxt->Ciphers[0] = SMB2_ENCRYPTION_AES128_GCM;*/ /* not supported yet */
+ pneg_ctxt->Ciphers[0] = SMB2_ENCRYPTION_AES128_CCM;
+}
+
+static void
+build_posix_ctxt(struct smb2_posix_neg_context *pneg_ctxt)
+{
+ pneg_ctxt->ContextType = SMB2_POSIX_EXTENSIONS_AVAILABLE;
+ pneg_ctxt->DataLength = cpu_to_le16(POSIX_CTXT_DATA_LEN);
}
static void
@@ -394,17 +403,24 @@ assemble_neg_contexts(struct smb2_negotiate_req *req,
unsigned int *total_len)
{
char *pneg_ctxt = (char *)req + OFFSET_OF_NEG_CONTEXT;
+ unsigned int ctxt_len;
+ *total_len += 2; /* Add 2 due to round to 8 byte boundary for 1st ctxt */
build_preauth_ctxt((struct smb2_preauth_neg_context *)pneg_ctxt);
- /* Add 2 to size to round to 8 byte boundary */
+ ctxt_len = DIV_ROUND_UP(sizeof(struct smb2_preauth_neg_context), 8) * 8;
+ *total_len += ctxt_len;
+ pneg_ctxt += ctxt_len;
- pneg_ctxt += 2 + sizeof(struct smb2_preauth_neg_context);
build_encrypt_ctxt((struct smb2_encryption_neg_context *)pneg_ctxt);
- req->NegotiateContextOffset = cpu_to_le32(OFFSET_OF_NEG_CONTEXT);
- req->NegotiateContextCount = cpu_to_le16(2);
+ ctxt_len = DIV_ROUND_UP(sizeof(struct smb2_encryption_neg_context), 8) * 8;
+ *total_len += ctxt_len;
+ pneg_ctxt += ctxt_len;
- *total_len += 4 + sizeof(struct smb2_preauth_neg_context)
- + sizeof(struct smb2_encryption_neg_context);
+ build_posix_ctxt((struct smb2_posix_neg_context *)pneg_ctxt);
+ *total_len += sizeof(struct smb2_posix_neg_context);
+
+ req->NegotiateContextOffset = cpu_to_le32(OFFSET_OF_NEG_CONTEXT);
+ req->NegotiateContextCount = cpu_to_le16(3);
}
static void decode_preauth_context(struct smb2_preauth_neg_context *ctxt)
@@ -444,16 +460,17 @@ static int decode_encrypt_ctx(struct TCP_Server_Info *server,
return -EINVAL;
}
server->cipher_type = ctxt->Ciphers[0];
+ server->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION;
return 0;
}
static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp,
- struct TCP_Server_Info *server)
+ struct TCP_Server_Info *server,
+ unsigned int len_of_smb)
{
struct smb2_neg_context *pctx;
unsigned int offset = le32_to_cpu(rsp->NegotiateContextOffset);
unsigned int ctxt_cnt = le16_to_cpu(rsp->NegotiateContextCount);
- unsigned int len_of_smb = be32_to_cpu(rsp->hdr.smb2_buf_length);
unsigned int len_of_ctxts, i;
int rc = 0;
@@ -474,8 +491,7 @@ static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp,
if (len_of_ctxts < sizeof(struct smb2_neg_context))
break;
- pctx = (struct smb2_neg_context *)(offset +
- server->vals->header_preamble_size + (char *)rsp);
+ pctx = (struct smb2_neg_context *)(offset + (char *)rsp);
clen = le16_to_cpu(pctx->DataLength);
if (clen > len_of_ctxts)
break;
@@ -486,6 +502,8 @@ static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp,
else if (pctx->ContextType == SMB2_ENCRYPTION_CAPABILITIES)
rc = decode_encrypt_ctx(server,
(struct smb2_encryption_neg_context *)pctx);
+ else if (pctx->ContextType == SMB2_POSIX_EXTENSIONS_AVAILABLE)
+ server->posix_ext_supported = true;
else
cifs_dbg(VFS, "unknown negcontext of type %d ignored\n",
le16_to_cpu(pctx->ContextType));
@@ -500,6 +518,64 @@ static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp,
return rc;
}
+static struct create_posix *
+create_posix_buf(umode_t mode)
+{
+ struct create_posix *buf;
+
+ buf = kzalloc(sizeof(struct create_posix),
+ GFP_KERNEL);
+ if (!buf)
+ return NULL;
+
+ buf->ccontext.DataOffset =
+ cpu_to_le16(offsetof(struct create_posix, Mode));
+ buf->ccontext.DataLength = cpu_to_le32(4);
+ buf->ccontext.NameOffset =
+ cpu_to_le16(offsetof(struct create_posix, Name));
+ buf->ccontext.NameLength = cpu_to_le16(16);
+
+ /* SMB2_CREATE_TAG_POSIX is "0x93AD25509CB411E7B42383DE968BCD7C" */
+ buf->Name[0] = 0x93;
+ buf->Name[1] = 0xAD;
+ buf->Name[2] = 0x25;
+ buf->Name[3] = 0x50;
+ buf->Name[4] = 0x9C;
+ buf->Name[5] = 0xB4;
+ buf->Name[6] = 0x11;
+ buf->Name[7] = 0xE7;
+ buf->Name[8] = 0xB4;
+ buf->Name[9] = 0x23;
+ buf->Name[10] = 0x83;
+ buf->Name[11] = 0xDE;
+ buf->Name[12] = 0x96;
+ buf->Name[13] = 0x8B;
+ buf->Name[14] = 0xCD;
+ buf->Name[15] = 0x7C;
+ buf->Mode = cpu_to_le32(mode);
+ cifs_dbg(FYI, "mode on posix create 0%o", mode);
+ return buf;
+}
+
+static int
+add_posix_context(struct kvec *iov, unsigned int *num_iovec, umode_t mode)
+{
+ struct smb2_create_req *req = iov[0].iov_base;
+ unsigned int num = *num_iovec;
+
+ iov[num].iov_base = create_posix_buf(mode);
+ if (iov[num].iov_base == NULL)
+ return -ENOMEM;
+ iov[num].iov_len = sizeof(struct create_posix);
+ if (!req->CreateContextsOffset)
+ req->CreateContextsOffset = cpu_to_le32(
+ sizeof(struct smb2_create_req) +
+ iov[num - 1].iov_len);
+ le32_add_cpu(&req->CreateContextsLength, sizeof(struct create_posix));
+ *num_iovec = num + 1;
+ return 0;
+}
+
#else
static void assemble_neg_contexts(struct smb2_negotiate_req *req,
unsigned int *total_len)
@@ -690,7 +766,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
server->capabilities |= SMB2_NT_FIND | SMB2_LARGE_FILES;
security_blob = smb2_get_data_area_len(&blob_offset, &blob_length,
- &rsp->hdr);
+ (struct smb2_sync_hdr *)rsp);
/*
* See MS-SMB2 section 2.2.4: if no blob, client picks default which
* for us will be
@@ -717,7 +793,8 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
#ifdef CONFIG_CIFS_SMB311
if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) {
if (rsp->NegotiateContextCount)
- rc = smb311_decode_neg_context(rsp, server);
+ rc = smb311_decode_neg_context(rsp, server,
+ rsp_iov.iov_len);
else
cifs_dbg(VFS, "Missing expected negotiate contexts\n");
}
@@ -729,19 +806,14 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
{
- int rc = 0;
- struct validate_negotiate_info_req vneg_inbuf;
+ int rc;
+ struct validate_negotiate_info_req *pneg_inbuf;
struct validate_negotiate_info_rsp *pneg_rsp = NULL;
u32 rsplen;
u32 inbuflen; /* max of 4 dialects */
cifs_dbg(FYI, "validate negotiate\n");
-#ifdef CONFIG_CIFS_SMB_DIRECT
- if (tcon->ses->server->rdma)
- return 0;
-#endif
-
/* In SMB3.11 preauth integrity supersedes validate negotiate */
if (tcon->ses->server->dialect == SMB311_PROT_ID)
return 0;
@@ -764,63 +836,69 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
if (tcon->ses->session_flags & SMB2_SESSION_FLAG_IS_NULL)
cifs_dbg(VFS, "Unexpected null user (anonymous) auth flag sent by server\n");
- vneg_inbuf.Capabilities =
+ pneg_inbuf = kmalloc(sizeof(*pneg_inbuf), GFP_NOFS);
+ if (!pneg_inbuf)
+ return -ENOMEM;
+
+ pneg_inbuf->Capabilities =
cpu_to_le32(tcon->ses->server->vals->req_capabilities);
- memcpy(vneg_inbuf.Guid, tcon->ses->server->client_guid,
+ memcpy(pneg_inbuf->Guid, tcon->ses->server->client_guid,
SMB2_CLIENT_GUID_SIZE);
if (tcon->ses->sign)
- vneg_inbuf.SecurityMode =
+ pneg_inbuf->SecurityMode =
cpu_to_le16(SMB2_NEGOTIATE_SIGNING_REQUIRED);
else if (global_secflags & CIFSSEC_MAY_SIGN)
- vneg_inbuf.SecurityMode =
+ pneg_inbuf->SecurityMode =
cpu_to_le16(SMB2_NEGOTIATE_SIGNING_ENABLED);
else
- vneg_inbuf.SecurityMode = 0;
+ pneg_inbuf->SecurityMode = 0;
if (strcmp(tcon->ses->server->vals->version_string,
SMB3ANY_VERSION_STRING) == 0) {
- vneg_inbuf.Dialects[0] = cpu_to_le16(SMB30_PROT_ID);
- vneg_inbuf.Dialects[1] = cpu_to_le16(SMB302_PROT_ID);
- vneg_inbuf.DialectCount = cpu_to_le16(2);
+ pneg_inbuf->Dialects[0] = cpu_to_le16(SMB30_PROT_ID);
+ pneg_inbuf->Dialects[1] = cpu_to_le16(SMB302_PROT_ID);
+ pneg_inbuf->DialectCount = cpu_to_le16(2);
/* structure is big enough for 3 dialects, sending only 2 */
- inbuflen = sizeof(struct validate_negotiate_info_req) - 2;
+ inbuflen = sizeof(*pneg_inbuf) -
+ sizeof(pneg_inbuf->Dialects[0]);
} else if (strcmp(tcon->ses->server->vals->version_string,
SMBDEFAULT_VERSION_STRING) == 0) {
- vneg_inbuf.Dialects[0] = cpu_to_le16(SMB21_PROT_ID);
- vneg_inbuf.Dialects[1] = cpu_to_le16(SMB30_PROT_ID);
- vneg_inbuf.Dialects[2] = cpu_to_le16(SMB302_PROT_ID);
- vneg_inbuf.DialectCount = cpu_to_le16(3);
+ pneg_inbuf->Dialects[0] = cpu_to_le16(SMB21_PROT_ID);
+ pneg_inbuf->Dialects[1] = cpu_to_le16(SMB30_PROT_ID);
+ pneg_inbuf->Dialects[2] = cpu_to_le16(SMB302_PROT_ID);
+ pneg_inbuf->DialectCount = cpu_to_le16(3);
/* structure is big enough for 3 dialects */
- inbuflen = sizeof(struct validate_negotiate_info_req);
+ inbuflen = sizeof(*pneg_inbuf);
} else {
/* otherwise specific dialect was requested */
- vneg_inbuf.Dialects[0] =
+ pneg_inbuf->Dialects[0] =
cpu_to_le16(tcon->ses->server->vals->protocol_id);
- vneg_inbuf.DialectCount = cpu_to_le16(1);
+ pneg_inbuf->DialectCount = cpu_to_le16(1);
/* structure is big enough for 3 dialects, sending only 1 */
- inbuflen = sizeof(struct validate_negotiate_info_req) - 4;
+ inbuflen = sizeof(*pneg_inbuf) -
+ sizeof(pneg_inbuf->Dialects[0]) * 2;
}
rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */,
- (char *)&vneg_inbuf, sizeof(struct validate_negotiate_info_req),
- (char **)&pneg_rsp, &rsplen);
+ (char *)pneg_inbuf, inbuflen, (char **)&pneg_rsp, &rsplen);
if (rc != 0) {
cifs_dbg(VFS, "validate protocol negotiate failed: %d\n", rc);
- return -EIO;
+ rc = -EIO;
+ goto out_free_inbuf;
}
- if (rsplen != sizeof(struct validate_negotiate_info_rsp)) {
+ rc = -EIO;
+ if (rsplen != sizeof(*pneg_rsp)) {
cifs_dbg(VFS, "invalid protocol negotiate response size: %d\n",
rsplen);
/* relax check since Mac returns max bufsize allowed on ioctl */
- if ((rsplen > CIFSMaxBufSize)
- || (rsplen < sizeof(struct validate_negotiate_info_rsp)))
- goto err_rsp_free;
+ if (rsplen > CIFSMaxBufSize || rsplen < sizeof(*pneg_rsp))
+ goto out_free_rsp;
}
/* check validate negotiate info response matches what we got earlier */
@@ -837,15 +915,17 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
goto vneg_out;
/* validate negotiate successful */
+ rc = 0;
cifs_dbg(FYI, "validate negotiate info successful\n");
- kfree(pneg_rsp);
- return 0;
+ goto out_free_rsp;
vneg_out:
cifs_dbg(VFS, "protocol revalidation - security settings mismatch\n");
-err_rsp_free:
+out_free_rsp:
kfree(pneg_rsp);
- return -EIO;
+out_free_inbuf:
+ kfree(pneg_inbuf);
+ return rc;
}
enum securityEnum
@@ -1050,7 +1130,7 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data)
goto out_put_spnego_key;
rsp = (struct smb2_sess_setup_rsp *)sess_data->iov[0].iov_base;
- ses->Suid = rsp->hdr.sync_hdr.SessionId;
+ ses->Suid = rsp->sync_hdr.SessionId;
ses->session_flags = le16_to_cpu(rsp->SessionFlags);
@@ -1126,13 +1206,13 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data)
/* If true, rc here is expected and not an error */
if (sess_data->buf0_type != CIFS_NO_BUFFER &&
- rsp->hdr.sync_hdr.Status == STATUS_MORE_PROCESSING_REQUIRED)
+ rsp->sync_hdr.Status == STATUS_MORE_PROCESSING_REQUIRED)
rc = 0;
if (rc)
goto out;
- if (offsetof(struct smb2_sess_setup_rsp, Buffer) - ses->server->vals->header_preamble_size !=
+ if (offsetof(struct smb2_sess_setup_rsp, Buffer) !=
le16_to_cpu(rsp->SecurityBufferOffset)) {
cifs_dbg(VFS, "Invalid security buffer offset %d\n",
le16_to_cpu(rsp->SecurityBufferOffset));
@@ -1147,7 +1227,7 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data)
cifs_dbg(FYI, "rawntlmssp session setup challenge phase\n");
- ses->Suid = rsp->hdr.sync_hdr.SessionId;
+ ses->Suid = rsp->sync_hdr.SessionId;
ses->session_flags = le16_to_cpu(rsp->SessionFlags);
out:
@@ -1205,7 +1285,7 @@ SMB2_sess_auth_rawntlmssp_authenticate(struct SMB2_sess_data *sess_data)
rsp = (struct smb2_sess_setup_rsp *)sess_data->iov[0].iov_base;
- ses->Suid = rsp->hdr.sync_hdr.SessionId;
+ ses->Suid = rsp->sync_hdr.SessionId;
ses->session_flags = le16_to_cpu(rsp->SessionFlags);
rc = SMB2_sess_establish_session(sess_data);
@@ -1272,6 +1352,7 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
sess_data->ses = ses;
sess_data->buf0_type = CIFS_NO_BUFFER;
sess_data->nls_cp = (struct nls_table *) nls_cp;
+ sess_data->previous_session = ses->Suid;
#ifdef CONFIG_CIFS_SMB311
/*
@@ -1399,7 +1480,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
return rc;
}
- if (encryption_required(tcon))
+ if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
iov[0].iov_base = (char *)req;
@@ -1415,7 +1496,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
/* 3.11 tcon req must be signed if not encrypted. See MS-SMB2 3.2.4.1.1 */
if ((ses->server->dialect == SMB311_PROT_ID) &&
- !encryption_required(tcon))
+ !smb3_encryption_required(tcon))
req->sync_hdr.Flags |= SMB2_FLAGS_SIGNED;
rc = smb2_send_recv(xid, ses, iov, 2, &resp_buftype, flags, &rsp_iov);
@@ -1453,7 +1534,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
tcon->maximal_access = le32_to_cpu(rsp->MaximalAccess);
tcon->tidStatus = CifsGood;
tcon->need_reconnect = false;
- tcon->tid = rsp->hdr.sync_hdr.TreeId;
+ tcon->tid = rsp->sync_hdr.TreeId;
strlcpy(tcon->treeName, tree, sizeof(tcon->treeName));
if ((rsp->Capabilities & SMB2_SHARE_CAP_DFS) &&
@@ -1473,7 +1554,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
return rc;
tcon_error_exit:
- if (rsp && rsp->hdr.sync_hdr.Status == STATUS_BAD_NETWORK_NAME) {
+ if (rsp && rsp->sync_hdr.Status == STATUS_BAD_NETWORK_NAME) {
cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree);
}
goto tcon_exit;
@@ -1504,7 +1585,7 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon)
if (rc)
return rc;
- if (encryption_required(tcon))
+ if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
flags |= CIFS_NO_RESP;
@@ -1571,7 +1652,7 @@ create_reconnect_durable_buf(struct cifs_fid *fid)
static __u8
parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp,
- unsigned int *epoch)
+ unsigned int *epoch, char *lease_key)
{
char *data_offset;
struct create_context *cc;
@@ -1579,14 +1660,15 @@ parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp,
unsigned int remaining;
char *name;
- data_offset = (char *)rsp + server->vals->header_preamble_size + le32_to_cpu(rsp->CreateContextsOffset);
+ data_offset = (char *)rsp + le32_to_cpu(rsp->CreateContextsOffset);
remaining = le32_to_cpu(rsp->CreateContextsLength);
cc = (struct create_context *)data_offset;
while (remaining >= sizeof(struct create_context)) {
name = le16_to_cpu(cc->NameOffset) + (char *)cc;
if (le16_to_cpu(cc->NameLength) == 4 &&
strncmp(name, "RqLs", 4) == 0)
- return server->ops->parse_lease_buf(cc, epoch);
+ return server->ops->parse_lease_buf(cc, epoch,
+ lease_key);
next = le32_to_cpu(cc->Next);
if (!next)
@@ -1814,7 +1896,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
struct TCP_Server_Info *server;
struct cifs_tcon *tcon = oparms->tcon;
struct cifs_ses *ses = tcon->ses;
- struct kvec iov[4];
+ struct kvec iov[5]; /* make sure at least one for each open context */
struct kvec rsp_iov = {NULL, 0};
int resp_buftype;
int uni_path_len;
@@ -1823,7 +1905,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
int rc = 0;
unsigned int n_iov = 2;
__u32 file_attributes = 0;
- char *dhc_buf = NULL, *lc_buf = NULL;
+ char *dhc_buf = NULL, *lc_buf = NULL, *pc_buf = NULL;
int flags = 0;
unsigned int total_len;
@@ -1839,7 +1921,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
if (rc)
return rc;
- if (encryption_required(tcon))
+ if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
if (oparms->create_options & CREATE_OPTION_READONLY)
@@ -1940,6 +2022,27 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
dhc_buf = iov[n_iov-1].iov_base;
}
+#ifdef CONFIG_CIFS_SMB311
+ if (tcon->posix_extensions) {
+ if (n_iov > 2) {
+ struct create_context *ccontext =
+ (struct create_context *)iov[n_iov-1].iov_base;
+ ccontext->Next =
+ cpu_to_le32(iov[n_iov-1].iov_len);
+ }
+
+ rc = add_posix_context(iov, &n_iov, oparms->mode);
+ if (rc) {
+ cifs_small_buf_release(req);
+ kfree(copy_path);
+ kfree(lc_buf);
+ kfree(dhc_buf);
+ return rc;
+ }
+ pc_buf = iov[n_iov-1].iov_base;
+ }
+#endif /* SMB311 */
+
rc = smb2_send_recv(xid, ses, iov, n_iov, &resp_buftype, flags,
&rsp_iov);
cifs_small_buf_release(req);
@@ -1952,8 +2055,13 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
resp_buftype = CIFS_NO_BUFFER;
rsp = NULL;
}
+ trace_smb3_open_err(xid, tcon->tid, ses->Suid,
+ oparms->create_options, oparms->desired_access, rc);
goto creat_exit;
- }
+ } else
+ trace_smb3_open_done(xid, rsp->PersistentFileId, tcon->tid,
+ ses->Suid, oparms->create_options,
+ oparms->desired_access);
oparms->fid->persistent_fid = rsp->PersistentFileId;
oparms->fid->volatile_fid = rsp->VolatileFileId;
@@ -1968,13 +2076,15 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
}
if (rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE)
- *oplock = parse_lease_state(server, rsp, &oparms->fid->epoch);
+ *oplock = parse_lease_state(server, rsp, &oparms->fid->epoch,
+ oparms->fid->lease_key);
else
*oplock = rsp->OplockLevel;
creat_exit:
kfree(copy_path);
kfree(lc_buf);
kfree(dhc_buf);
+ kfree(pc_buf);
free_rsp_buf(resp_buftype, rsp);
return rc;
}
@@ -1990,7 +2100,6 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
{
struct smb2_ioctl_req *req;
struct smb2_ioctl_rsp *rsp;
- struct smb2_sync_hdr *shdr;
struct cifs_ses *ses;
struct kvec iov[2];
struct kvec rsp_iov;
@@ -2021,7 +2130,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
if (rc)
return rc;
- if (encryption_required(tcon))
+ if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
req->CtlCode = cpu_to_le32(opcode);
@@ -2084,6 +2193,10 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
cifs_small_buf_release(req);
rsp = (struct smb2_ioctl_rsp *)rsp_iov.iov_base;
+ if (rc != 0)
+ trace_smb3_fsctl_err(xid, persistent_fid, tcon->tid,
+ ses->Suid, 0, opcode, rc);
+
if ((rc != 0) && (rc != -EINVAL)) {
cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE);
goto ioctl_exit;
@@ -2111,7 +2224,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
goto ioctl_exit;
}
- if (get_rfc1002_length(rsp) < le32_to_cpu(rsp->OutputOffset) + *plen) {
+ if (rsp_iov.iov_len < le32_to_cpu(rsp->OutputOffset) + *plen) {
cifs_dbg(VFS, "Malformed ioctl resp: len %d offset %d\n", *plen,
le32_to_cpu(rsp->OutputOffset));
*plen = 0;
@@ -2125,8 +2238,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
goto ioctl_exit;
}
- shdr = get_sync_hdr(rsp);
- memcpy(*out_data, (char *)shdr + le32_to_cpu(rsp->OutputOffset), *plen);
+ memcpy(*out_data, (char *)rsp + le32_to_cpu(rsp->OutputOffset), *plen);
ioctl_exit:
free_rsp_buf(resp_buftype, rsp);
return rc;
@@ -2158,8 +2270,8 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
}
int
-SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
- u64 persistent_fid, u64 volatile_fid)
+SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon,
+ u64 persistent_fid, u64 volatile_fid, int flags)
{
struct smb2_close_req *req;
struct smb2_close_rsp *rsp;
@@ -2168,7 +2280,6 @@ SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
struct kvec rsp_iov;
int resp_buftype;
int rc = 0;
- int flags = 0;
unsigned int total_len;
cifs_dbg(FYI, "Close\n");
@@ -2180,7 +2291,7 @@ SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
if (rc)
return rc;
- if (encryption_required(tcon))
+ if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
req->PersistentFileId = persistent_fid;
@@ -2195,6 +2306,8 @@ SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
if (rc != 0) {
cifs_stats_fail_inc(tcon, SMB2_CLOSE_HE);
+ trace_smb3_close_err(xid, persistent_fid, tcon->tid, ses->Suid,
+ rc);
goto close_exit;
}
@@ -2205,14 +2318,20 @@ SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
return rc;
}
+int
+SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
+ u64 persistent_fid, u64 volatile_fid)
+{
+ return SMB2_close_flags(xid, tcon, persistent_fid, volatile_fid, 0);
+}
+
static int
-validate_iov(struct TCP_Server_Info *server,
- unsigned int offset, unsigned int buffer_length,
+validate_iov(unsigned int offset, unsigned int buffer_length,
struct kvec *iov, unsigned int min_buf_size)
{
unsigned int smb_len = iov->iov_len;
- char *end_of_smb = smb_len + server->vals->header_preamble_size + (char *)iov->iov_base;
- char *begin_of_buf = server->vals->header_preamble_size + offset + (char *)iov->iov_base;
+ char *end_of_smb = smb_len + (char *)iov->iov_base;
+ char *begin_of_buf = offset + (char *)iov->iov_base;
char *end_of_buf = begin_of_buf + buffer_length;
@@ -2242,18 +2361,17 @@ validate_iov(struct TCP_Server_Info *server,
* Caller must free buffer.
*/
static int
-validate_and_copy_iov(struct TCP_Server_Info *server,
- unsigned int offset, unsigned int buffer_length,
+validate_and_copy_iov(unsigned int offset, unsigned int buffer_length,
struct kvec *iov, unsigned int minbufsize,
char *data)
{
- char *begin_of_buf = server->vals->header_preamble_size + offset + (char *)(iov->iov_base);
+ char *begin_of_buf = offset + (char *)iov->iov_base;
int rc;
if (!data)
return -EINVAL;
- rc = validate_iov(server, offset, buffer_length, iov, minbufsize);
+ rc = validate_iov(offset, buffer_length, iov, minbufsize);
if (rc)
return rc;
@@ -2288,7 +2406,7 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
if (rc)
return rc;
- if (encryption_required(tcon))
+ if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
req->InfoType = info_type;
@@ -2314,6 +2432,8 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
if (rc) {
cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
+ trace_smb3_query_info_err(xid, persistent_fid, tcon->tid,
+ ses->Suid, info_class, (__u32)info_type, rc);
goto qinf_exit;
}
@@ -2331,8 +2451,7 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
}
}
- rc = validate_and_copy_iov(ses->server,
- le16_to_cpu(rsp->OutputBufferOffset),
+ rc = validate_and_copy_iov(le16_to_cpu(rsp->OutputBufferOffset),
le32_to_cpu(rsp->OutputBufferLength),
&rsp_iov, min_len, *data);
@@ -2403,7 +2522,7 @@ smb2_echo_callback(struct mid_q_entry *mid)
unsigned int credits_received = 1;
if (mid->mid_state == MID_RESPONSE_RECEIVED)
- credits_received = le16_to_cpu(rsp->hdr.sync_hdr.CreditRequest);
+ credits_received = le16_to_cpu(rsp->sync_hdr.CreditRequest);
DeleteMidQEntry(mid);
add_credits(server, credits_received, CIFS_ECHO_OP);
@@ -2532,7 +2651,7 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
if (rc)
return rc;
- if (encryption_required(tcon))
+ if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
req->PersistentFileId = persistent_fid;
@@ -2544,8 +2663,11 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
rc = smb2_send_recv(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
cifs_small_buf_release(req);
- if (rc != 0)
+ if (rc != 0) {
cifs_stats_fail_inc(tcon, SMB2_FLUSH_HE);
+ trace_smb3_flush_err(xid, persistent_fid, tcon->tid, ses->Suid,
+ rc);
+ }
free_rsp_buf(resp_buftype, rsp_iov.iov_base);
return rc;
@@ -2590,7 +2712,7 @@ smb2_new_read_req(void **buf, unsigned int *total_len,
* If we want to do a RDMA write, fill in and append
* smbd_buffer_descriptor_v1 to the end of read request
*/
- if (server->rdma && rdata &&
+ if (server->rdma && rdata && !server->sign &&
rdata->bytes >= server->smbd_conn->rdma_readwrite_threshold) {
struct smbd_buffer_descriptor_v1 *v1;
@@ -2654,11 +2776,12 @@ smb2_readv_callback(struct mid_q_entry *mid)
struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink);
struct TCP_Server_Info *server = tcon->ses->server;
struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)rdata->iov[1].iov_base;
+ (struct smb2_sync_hdr *)rdata->iov[0].iov_base;
unsigned int credits_received = 1;
struct smb_rqst rqst = { .rq_iov = rdata->iov,
.rq_nvec = 2,
.rq_pages = rdata->pages,
+ .rq_offset = rdata->page_offset,
.rq_npages = rdata->nr_pages,
.rq_pagesz = rdata->pagesz,
.rq_tailsz = rdata->tailsz };
@@ -2756,7 +2879,7 @@ smb2_async_readv(struct cifs_readdata *rdata)
return rc;
}
- if (encryption_required(io_parms.tcon))
+ if (smb3_encryption_required(io_parms.tcon))
flags |= CIFS_TRANSFORM_REQ;
req_len = cpu_to_be32(total_len);
@@ -2787,7 +2910,13 @@ smb2_async_readv(struct cifs_readdata *rdata)
if (rc) {
kref_put(&rdata->refcount, cifs_readdata_release);
cifs_stats_fail_inc(io_parms.tcon, SMB2_READ_HE);
- }
+ trace_smb3_read_err(rc, 0 /* xid */, io_parms.persistent_fid,
+ io_parms.tcon->tid, io_parms.tcon->ses->Suid,
+ io_parms.offset, io_parms.length);
+ } else
+ trace_smb3_read_done(0 /* xid */, io_parms.persistent_fid,
+ io_parms.tcon->tid, io_parms.tcon->ses->Suid,
+ io_parms.offset, io_parms.length);
cifs_small_buf_release(buf);
return rc;
@@ -2800,7 +2929,6 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
int resp_buftype, rc = -EACCES;
struct smb2_read_plain_req *req = NULL;
struct smb2_read_rsp *rsp = NULL;
- struct smb2_sync_hdr *shdr;
struct kvec iov[1];
struct kvec rsp_iov;
unsigned int total_len;
@@ -2812,7 +2940,7 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
if (rc)
return rc;
- if (encryption_required(io_parms->tcon))
+ if (smb3_encryption_required(io_parms->tcon))
flags |= CIFS_TRANSFORM_REQ;
iov[0].iov_base = (char *)req;
@@ -2828,9 +2956,15 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
cifs_stats_fail_inc(io_parms->tcon, SMB2_READ_HE);
cifs_dbg(VFS, "Send error in read = %d\n", rc);
}
+ trace_smb3_read_err(rc, xid, req->PersistentFileId,
+ io_parms->tcon->tid, ses->Suid,
+ io_parms->offset, io_parms->length);
free_rsp_buf(resp_buftype, rsp_iov.iov_base);
return rc == -ENODATA ? 0 : rc;
- }
+ } else
+ trace_smb3_read_done(xid, req->PersistentFileId,
+ io_parms->tcon->tid, ses->Suid,
+ io_parms->offset, io_parms->length);
*nbytes = le32_to_cpu(rsp->DataLength);
if ((*nbytes > CIFS_MAX_MSGSIZE) ||
@@ -2841,10 +2975,8 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
*nbytes = 0;
}
- shdr = get_sync_hdr(rsp);
-
if (*buf) {
- memcpy(*buf, (char *)shdr + rsp->DataOffset, *nbytes);
+ memcpy(*buf, (char *)rsp + rsp->DataOffset, *nbytes);
free_rsp_buf(resp_buftype, rsp_iov.iov_base);
} else if (resp_buftype != CIFS_NO_BUFFER) {
*buf = rsp_iov.iov_base;
@@ -2871,7 +3003,7 @@ smb2_writev_callback(struct mid_q_entry *mid)
switch (mid->mid_state) {
case MID_RESPONSE_RECEIVED:
- credits_received = le16_to_cpu(rsp->hdr.sync_hdr.CreditRequest);
+ credits_received = le16_to_cpu(rsp->sync_hdr.CreditRequest);
wdata->result = smb2_check_receive(mid, tcon->ses->server, 0);
if (wdata->result != 0)
break;
@@ -2948,7 +3080,7 @@ smb2_async_writev(struct cifs_writedata *wdata,
goto async_writev_out;
}
- if (encryption_required(tcon))
+ if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
shdr = (struct smb2_sync_hdr *)req;
@@ -2968,7 +3100,7 @@ smb2_async_writev(struct cifs_writedata *wdata,
* If we want to do a server RDMA read, fill in and append
* smbd_buffer_descriptor_v1 to the end of write request
*/
- if (server->rdma && wdata->bytes >=
+ if (server->rdma && !server->sign && wdata->bytes >=
server->smbd_conn->rdma_readwrite_threshold) {
struct smbd_buffer_descriptor_v1 *v1;
@@ -3009,6 +3141,7 @@ smb2_async_writev(struct cifs_writedata *wdata,
rqst.rq_iov = iov;
rqst.rq_nvec = 2;
rqst.rq_pages = wdata->pages;
+ rqst.rq_offset = wdata->page_offset;
rqst.rq_npages = wdata->nr_pages;
rqst.rq_pagesz = wdata->pagesz;
rqst.rq_tailsz = wdata->tailsz;
@@ -3046,9 +3179,15 @@ smb2_async_writev(struct cifs_writedata *wdata,
wdata, flags);
if (rc) {
+ trace_smb3_write_err(0 /* no xid */, req->PersistentFileId,
+ tcon->tid, tcon->ses->Suid, wdata->offset,
+ wdata->bytes, rc);
kref_put(&wdata->refcount, release);
cifs_stats_fail_inc(tcon, SMB2_WRITE_HE);
- }
+ } else
+ trace_smb3_write_done(0 /* no xid */, req->PersistentFileId,
+ tcon->tid, tcon->ses->Suid, wdata->offset,
+ wdata->bytes);
async_writev_out:
cifs_small_buf_release(req);
@@ -3086,7 +3225,7 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
if (io_parms->tcon->ses->server == NULL)
return -ECONNABORTED;
- if (encryption_required(io_parms->tcon))
+ if (smb3_encryption_required(io_parms->tcon))
flags |= CIFS_TRANSFORM_REQ;
req->sync_hdr.ProcessId = cpu_to_le32(io_parms->pid);
@@ -3112,10 +3251,19 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
rsp = (struct smb2_write_rsp *)rsp_iov.iov_base;
if (rc) {
+ trace_smb3_write_err(xid, req->PersistentFileId,
+ io_parms->tcon->tid,
+ io_parms->tcon->ses->Suid,
+ io_parms->offset, io_parms->length, rc);
cifs_stats_fail_inc(io_parms->tcon, SMB2_WRITE_HE);
cifs_dbg(VFS, "Send error in write = %d\n", rc);
- } else
+ } else {
*nbytes = le32_to_cpu(rsp->DataLength);
+ trace_smb3_write_done(xid, req->PersistentFileId,
+ io_parms->tcon->tid,
+ io_parms->tcon->ses->Suid,
+ io_parms->offset, *nbytes);
+ }
free_rsp_buf(resp_buftype, rsp);
return rc;
@@ -3196,7 +3344,7 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
if (rc)
return rc;
- if (encryption_required(tcon))
+ if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
switch (srch_inf->info_level) {
@@ -3247,7 +3395,7 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
if (rc) {
if (rc == -ENODATA &&
- rsp->hdr.sync_hdr.Status == STATUS_NO_MORE_FILES) {
+ rsp->sync_hdr.Status == STATUS_NO_MORE_FILES) {
srch_inf->endOfSearch = true;
rc = 0;
}
@@ -3255,8 +3403,7 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
goto qdir_exit;
}
- rc = validate_iov(server,
- le16_to_cpu(rsp->OutputBufferOffset),
+ rc = validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
info_buf_size);
if (rc)
@@ -3271,10 +3418,9 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
cifs_buf_release(srch_inf->ntwrk_buf_start);
}
srch_inf->ntwrk_buf_start = (char *)rsp;
- srch_inf->srch_entries_start = srch_inf->last_entry = 4 /* rfclen */ +
- (char *)&rsp->hdr + le16_to_cpu(rsp->OutputBufferOffset);
- /* 4 for rfc1002 length field */
- end_of_smb = get_rfc1002_length(rsp) + 4 + (char *)&rsp->hdr;
+ srch_inf->srch_entries_start = srch_inf->last_entry =
+ (char *)rsp + le16_to_cpu(rsp->OutputBufferOffset);
+ end_of_smb = rsp_iov.iov_len + (char *)rsp;
srch_inf->entries_in_buffer =
num_entries(srch_inf->srch_entries_start, end_of_smb,
&srch_inf->last_entry, info_buf_size);
@@ -3329,7 +3475,7 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
return rc;
}
- if (encryption_required(tcon))
+ if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
req->sync_hdr.ProcessId = cpu_to_le32(pid);
@@ -3362,8 +3508,11 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
cifs_small_buf_release(req);
rsp = (struct smb2_set_info_rsp *)rsp_iov.iov_base;
- if (rc != 0)
+ if (rc != 0) {
cifs_stats_fail_inc(tcon, SMB2_SET_INFO_HE);
+ trace_smb3_set_info_err(xid, persistent_fid, tcon->tid,
+ ses->Suid, info_class, (__u32)info_type, rc);
+ }
free_rsp_buf(resp_buftype, rsp);
kfree(iov);
@@ -3510,7 +3659,7 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
__u8 oplock_level)
{
int rc;
- struct smb2_oplock_break_req *req = NULL;
+ struct smb2_oplock_break *req = NULL;
struct cifs_ses *ses = tcon->ses;
int flags = CIFS_OBREAK_OP;
unsigned int total_len;
@@ -3524,7 +3673,7 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
if (rc)
return rc;
- if (encryption_required(tcon))
+ if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
req->VolatileFid = volatile_fid;
@@ -3589,7 +3738,7 @@ build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, int level,
req->InputBufferOffset =
cpu_to_le16(sizeof(struct smb2_query_info_req) - 1);
req->OutputBufferLength = cpu_to_le32(
- outbuf_len + sizeof(struct smb2_query_info_rsp) - 1 - server->vals->header_preamble_size);
+ outbuf_len + sizeof(struct smb2_query_info_rsp) - 1);
iov->iov_base = (char *)req;
iov->iov_len = total_len;
@@ -3606,7 +3755,6 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
int rc = 0;
int resp_buftype;
struct cifs_ses *ses = tcon->ses;
- struct TCP_Server_Info *server = ses->server;
struct smb2_fs_full_size_info *info = NULL;
int flags = 0;
@@ -3616,7 +3764,7 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
if (rc)
return rc;
- if (encryption_required(tcon))
+ if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
rc = smb2_send_recv(xid, ses, &iov, 1, &resp_buftype, flags, &rsp_iov);
@@ -3627,10 +3775,9 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
}
rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
- info = (struct smb2_fs_full_size_info *)(server->vals->header_preamble_size +
- le16_to_cpu(rsp->OutputBufferOffset) + (char *)&rsp->hdr);
- rc = validate_iov(server,
- le16_to_cpu(rsp->OutputBufferOffset),
+ info = (struct smb2_fs_full_size_info *)(
+ le16_to_cpu(rsp->OutputBufferOffset) + (char *)rsp);
+ rc = validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
sizeof(struct smb2_fs_full_size_info));
if (!rc)
@@ -3651,7 +3798,6 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
int rc = 0;
int resp_buftype, max_len, min_len;
struct cifs_ses *ses = tcon->ses;
- struct TCP_Server_Info *server = ses->server;
unsigned int rsp_len, offset;
int flags = 0;
@@ -3674,7 +3820,7 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
if (rc)
return rc;
- if (encryption_required(tcon))
+ if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
rc = smb2_send_recv(xid, ses, &iov, 1, &resp_buftype, flags, &rsp_iov);
@@ -3687,20 +3833,20 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
rsp_len = le32_to_cpu(rsp->OutputBufferLength);
offset = le16_to_cpu(rsp->OutputBufferOffset);
- rc = validate_iov(server, offset, rsp_len, &rsp_iov, min_len);
+ rc = validate_iov(offset, rsp_len, &rsp_iov, min_len);
if (rc)
goto qfsattr_exit;
if (level == FS_ATTRIBUTE_INFORMATION)
- memcpy(&tcon->fsAttrInfo, server->vals->header_preamble_size + offset
- + (char *)&rsp->hdr, min_t(unsigned int,
+ memcpy(&tcon->fsAttrInfo, offset
+ + (char *)rsp, min_t(unsigned int,
rsp_len, max_len));
else if (level == FS_DEVICE_INFORMATION)
- memcpy(&tcon->fsDevInfo, server->vals->header_preamble_size + offset
- + (char *)&rsp->hdr, sizeof(FILE_SYSTEM_DEVICE_INFO));
+ memcpy(&tcon->fsDevInfo, offset
+ + (char *)rsp, sizeof(FILE_SYSTEM_DEVICE_INFO));
else if (level == FS_SECTOR_SIZE_INFORMATION) {
struct smb3_fs_ss_info *ss_info = (struct smb3_fs_ss_info *)
- (server->vals->header_preamble_size + offset + (char *)&rsp->hdr);
+ (offset + (char *)rsp);
tcon->ss_flags = le32_to_cpu(ss_info->Flags);
tcon->perf_sector_size =
le32_to_cpu(ss_info->PhysicalBytesPerSectorForPerf);
@@ -3731,7 +3877,7 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
if (rc)
return rc;
- if (encryption_required(tcon))
+ if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
req->sync_hdr.ProcessId = cpu_to_le32(pid);
@@ -3754,6 +3900,8 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
if (rc) {
cifs_dbg(FYI, "Send error in smb2_lockv = %d\n", rc);
cifs_stats_fail_inc(tcon, SMB2_LOCK_HE);
+ trace_smb3_lock_err(xid, persist_fid, tcon->tid,
+ tcon->ses->Suid, rc);
}
return rc;
@@ -3795,7 +3943,7 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon,
if (rc)
return rc;
- if (encryption_required(tcon))
+ if (smb3_encryption_required(tcon))
flags |= CIFS_TRANSFORM_REQ;
req->sync_hdr.CreditRequest = cpu_to_le16(1);
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 6093e51..a345560 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -122,25 +122,10 @@ struct smb2_sync_pdu {
__le16 StructureSize2; /* size of wct area (varies, request specific) */
} __packed;
-struct smb2_hdr {
- __be32 smb2_buf_length; /* big endian on wire */
- /* length is only two or three bytes - with */
- /* one or two byte type preceding it that MBZ */
- struct smb2_sync_hdr sync_hdr;
-} __packed;
-
-struct smb2_pdu {
- struct smb2_hdr hdr;
- __le16 StructureSize2; /* size of wct area (varies, request specific) */
-} __packed;
-
#define SMB3_AES128CMM_NONCE 11
#define SMB3_AES128GCM_NONCE 12
struct smb2_transform_hdr {
- __be32 smb2_buf_length; /* big endian on wire */
- /* length is only two or three bytes - with
- one or two byte type preceding it that MBZ */
__le32 ProtocolId; /* 0xFD 'S' 'M' 'B' */
__u8 Signature[16];
__u8 Nonce[16];
@@ -171,7 +156,7 @@ struct smb2_transform_hdr {
#define SMB2_ERROR_STRUCTURE_SIZE2 cpu_to_le16(9)
struct smb2_err_rsp {
- struct smb2_hdr hdr;
+ struct smb2_sync_hdr sync_hdr;
__le16 StructureSize;
__le16 Reserved; /* MBZ */
__le32 ByteCount; /* even if zero, at least one byte follows */
@@ -297,11 +282,19 @@ struct smb2_encryption_neg_context {
__le16 DataLength;
__le32 Reserved;
__le16 CipherCount; /* AES-128-GCM and AES-128-CCM */
- __le16 Ciphers[2]; /* Ciphers[0] since only one used now */
+ __le16 Ciphers[1]; /* Ciphers[0] since only one used now */
+} __packed;
+
+#define POSIX_CTXT_DATA_LEN 8
+struct smb2_posix_neg_context {
+ __le16 ContextType; /* 0x100 */
+ __le16 DataLength;
+ __le32 Reserved;
+ __le64 Reserved1; /* In case needed for future (eg version or caps) */
} __packed;
struct smb2_negotiate_rsp {
- struct smb2_hdr hdr;
+ struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 65 */
__le16 SecurityMode;
__le16 DialectRevision;
@@ -341,7 +334,7 @@ struct smb2_sess_setup_req {
#define SMB2_SESSION_FLAG_IS_NULL 0x0002
#define SMB2_SESSION_FLAG_ENCRYPT_DATA 0x0004
struct smb2_sess_setup_rsp {
- struct smb2_hdr hdr;
+ struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 9 */
__le16 SessionFlags;
__le16 SecurityBufferOffset;
@@ -356,7 +349,7 @@ struct smb2_logoff_req {
} __packed;
struct smb2_logoff_rsp {
- struct smb2_hdr hdr;
+ struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 4 */
__le16 Reserved;
} __packed;
@@ -452,7 +445,7 @@ struct smb2_tree_connect_req_extension {
} __packed;
struct smb2_tree_connect_rsp {
- struct smb2_hdr hdr;
+ struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 16 */
__u8 ShareType; /* see below */
__u8 Reserved;
@@ -503,7 +496,7 @@ struct smb2_tree_disconnect_req {
} __packed;
struct smb2_tree_disconnect_rsp {
- struct smb2_hdr hdr;
+ struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 4 */
__le16 Reserved;
} __packed;
@@ -615,7 +608,9 @@ struct smb2_tree_disconnect_rsp {
#define SMB2_CREATE_DURABLE_HANDLE_REQUEST_V2 "DH2Q"
#define SMB2_CREATE_DURABLE_HANDLE_RECONNECT_V2 "DH2C"
#define SMB2_CREATE_APP_INSTANCE_ID 0x45BCA66AEFA7F74A9008FA462E144D74
-#define SVHDX_OPEN_DEVICE_CONTEXT 0x83CE6F1AD851E0986E34401CC9BCFCE9
+#define SVHDX_OPEN_DEVICE_CONTEX 0x9CCBCF9E04C1E643980E158DA1F6EC83
+#define SMB2_CREATE_TAG_POSIX 0x93AD25509CB411E7B42383DE968BCD7C
+
struct smb2_create_req {
struct smb2_sync_hdr sync_hdr;
@@ -638,7 +633,7 @@ struct smb2_create_req {
} __packed;
struct smb2_create_rsp {
- struct smb2_hdr hdr;
+ struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 89 */
__u8 OplockLevel;
__u8 Reserved;
@@ -727,6 +722,13 @@ struct create_durable {
} Data;
} __packed;
+struct create_posix {
+ struct create_context ccontext;
+ __u8 Name[16];
+ __le32 Mode;
+ __u32 Reserved;
+} __packed;
+
/* See MS-SMB2 2.2.13.2.11 */
/* Flags */
#define SMB2_DHANDLE_FLAG_PERSISTENT 0x00000002
@@ -894,7 +896,7 @@ struct smb2_ioctl_req {
} __packed;
struct smb2_ioctl_rsp {
- struct smb2_hdr hdr;
+ struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 57 */
__u16 Reserved;
__le32 CtlCode;
@@ -921,7 +923,7 @@ struct smb2_close_req {
} __packed;
struct smb2_close_rsp {
- struct smb2_hdr hdr;
+ struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* 60 */
__le16 Flags;
__le32 Reserved;
@@ -944,7 +946,7 @@ struct smb2_flush_req {
} __packed;
struct smb2_flush_rsp {
- struct smb2_hdr hdr;
+ struct smb2_sync_hdr sync_hdr;
__le16 StructureSize;
__le16 Reserved;
} __packed;
@@ -976,7 +978,7 @@ struct smb2_read_plain_req {
} __packed;
struct smb2_read_rsp {
- struct smb2_hdr hdr;
+ struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 17 */
__u8 DataOffset;
__u8 Reserved;
@@ -1007,7 +1009,7 @@ struct smb2_write_req {
} __packed;
struct smb2_write_rsp {
- struct smb2_hdr hdr;
+ struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 17 */
__u8 DataOffset;
__u8 Reserved;
@@ -1041,7 +1043,7 @@ struct smb2_lock_req {
} __packed;
struct smb2_lock_rsp {
- struct smb2_hdr hdr;
+ struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 4 */
__le16 Reserved;
} __packed;
@@ -1053,7 +1055,7 @@ struct smb2_echo_req {
} __packed;
struct smb2_echo_rsp {
- struct smb2_hdr hdr;
+ struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 4 */
__u16 Reserved;
} __packed;
@@ -1079,7 +1081,7 @@ struct smb2_query_directory_req {
} __packed;
struct smb2_query_directory_rsp {
- struct smb2_hdr hdr;
+ struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 9 */
__le16 OutputBufferOffset;
__le32 OutputBufferLength;
@@ -1128,7 +1130,7 @@ struct smb2_query_info_req {
} __packed;
struct smb2_query_info_rsp {
- struct smb2_hdr hdr;
+ struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 9 */
__le16 OutputBufferOffset;
__le32 OutputBufferLength;
@@ -1150,12 +1152,11 @@ struct smb2_set_info_req {
} __packed;
struct smb2_set_info_rsp {
- struct smb2_hdr hdr;
+ struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 2 */
} __packed;
-/* oplock break without an rfc1002 header */
-struct smb2_oplock_break_req {
+struct smb2_oplock_break {
struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 24 */
__u8 OplockLevel;
@@ -1165,21 +1166,10 @@ struct smb2_oplock_break_req {
__u64 VolatileFid;
} __packed;
-/* oplock break with an rfc1002 header */
-struct smb2_oplock_break_rsp {
- struct smb2_hdr hdr;
- __le16 StructureSize; /* Must be 24 */
- __u8 OplockLevel;
- __u8 Reserved;
- __le32 Reserved2;
- __u64 PersistentFid;
- __u64 VolatileFid;
-} __packed;
-
#define SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED cpu_to_le32(0x01)
struct smb2_lease_break {
- struct smb2_hdr hdr;
+ struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 44 */
__le16 Reserved;
__le32 Flags;
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 8ba24a9..908555b 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -36,8 +36,9 @@ struct smb_rqst;
extern int map_smb2_to_linux_error(char *buf, bool log_err);
extern int smb2_check_message(char *buf, unsigned int length,
struct TCP_Server_Info *server);
-extern unsigned int smb2_calc_size(void *buf);
-extern char *smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr);
+extern unsigned int smb2_calc_size(void *buf, struct TCP_Server_Info *server);
+extern char *smb2_get_data_area_len(int *off, int *len,
+ struct smb2_sync_hdr *shdr);
extern __le16 *cifs_convert_path_to_utf16(const char *from,
struct cifs_sb_info *cifs_sb);
@@ -65,6 +66,8 @@ extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server,
extern int smb3_handle_read_data(struct TCP_Server_Info *server,
struct mid_q_entry *mid);
+extern int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
+ struct cifs_fid *pfid);
extern void move_smb2_info_to_cifs(FILE_ALL_INFO *dst,
struct smb2_file_all_info *src);
extern int smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
@@ -129,6 +132,8 @@ extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon,
char **out_data, u32 *plen /* returned data len */);
extern int SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_file_id, u64 volatile_file_id);
+extern int SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon,
+ u64 persistent_fid, u64 volatile_fid, int flags);
extern int SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_file_id, u64 volatile_file_id);
extern int SMB2_query_eas(const unsigned int xid, struct cifs_tcon *tcon,
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index 8806f3f..2c67112 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -480,7 +480,7 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
unsigned int rc;
char server_response_sig[16];
struct smb2_sync_hdr *shdr =
- (struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base;
+ (struct smb2_sync_hdr *)rqst->rq_iov[0].iov_base;
if ((shdr->Command == SMB2_NEGOTIATE) ||
(shdr->Command == SMB2_SESSION_SETUP) ||
@@ -605,14 +605,12 @@ smb2_check_receive(struct mid_q_entry *mid, struct TCP_Server_Info *server,
bool log_error)
{
unsigned int len = mid->resp_buf_size;
- struct kvec iov[2];
+ struct kvec iov[1];
struct smb_rqst rqst = { .rq_iov = iov,
- .rq_nvec = 2 };
+ .rq_nvec = 1 };
iov[0].iov_base = (char *)mid->resp_buf;
- iov[0].iov_len = 4;
- iov[1].iov_base = (char *)mid->resp_buf + 4;
- iov[1].iov_len = len;
+ iov[0].iov_len = len;
dump_smb(mid->resp_buf, min_t(u32, 80, len));
/* convert the length into a more usable form */
diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c
index 5008af5..c62f7c9 100644
--- a/fs/cifs/smbdirect.c
+++ b/fs/cifs/smbdirect.c
@@ -1028,7 +1028,7 @@ static int smbd_post_send(struct smbd_connection *info,
for (i = 0; i < request->num_sge; i++) {
log_rdma_send(INFO,
"rdma_request sge[%d] addr=%llu length=%u\n",
- i, request->sge[0].addr, request->sge[0].length);
+ i, request->sge[i].addr, request->sge[i].length);
ib_dma_sync_single_for_device(
info->id->device,
request->sge[i].addr,
@@ -2086,7 +2086,7 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst)
int start, i, j;
int max_iov_size =
info->max_send_size - sizeof(struct smbd_data_transfer);
- struct kvec iov[SMBDIRECT_MAX_SGE];
+ struct kvec *iov;
int rc;
info->smbd_send_pending++;
@@ -2096,32 +2096,20 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst)
}
/*
- * This usually means a configuration error
- * We use RDMA read/write for packet size > rdma_readwrite_threshold
- * as long as it's properly configured we should never get into this
- * situation
- */
- if (rqst->rq_nvec + rqst->rq_npages > SMBDIRECT_MAX_SGE) {
- log_write(ERR, "maximum send segment %x exceeding %x\n",
- rqst->rq_nvec + rqst->rq_npages, SMBDIRECT_MAX_SGE);
- rc = -EINVAL;
- goto done;
- }
-
- /*
- * Remove the RFC1002 length defined in MS-SMB2 section 2.1
- * It is used only for TCP transport
+ * Skip the RFC1002 length defined in MS-SMB2 section 2.1
+ * It is used only for TCP transport in the iov[0]
* In future we may want to add a transport layer under protocol
* layer so this will only be issued to TCP transport
*/
- iov[0].iov_base = (char *)rqst->rq_iov[0].iov_base + 4;
- iov[0].iov_len = rqst->rq_iov[0].iov_len - 4;
- buflen += iov[0].iov_len;
+
+ if (rqst->rq_iov[0].iov_len != 4) {
+ log_write(ERR, "expected the pdu length in 1st iov, but got %zu\n", rqst->rq_iov[0].iov_len);
+ return -EINVAL;
+ }
+ iov = &rqst->rq_iov[1];
/* total up iov array first */
- for (i = 1; i < rqst->rq_nvec; i++) {
- iov[i].iov_base = rqst->rq_iov[i].iov_base;
- iov[i].iov_len = rqst->rq_iov[i].iov_len;
+ for (i = 0; i < rqst->rq_nvec-1; i++) {
buflen += iov[i].iov_len;
}
@@ -2139,6 +2127,10 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst)
goto done;
}
+ cifs_dbg(FYI, "Sending smb (RDMA): smb_len=%u\n", buflen);
+ for (i = 0; i < rqst->rq_nvec-1; i++)
+ dump_smb(iov[i].iov_base, iov[i].iov_len);
+
remaining_data_length = buflen;
log_write(INFO, "rqst->rq_nvec=%d rqst->rq_npages=%d rq_pagesz=%d "
@@ -2194,12 +2186,14 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst)
goto done;
}
i++;
+ if (i == rqst->rq_nvec-1)
+ break;
}
start = i;
buflen = 0;
} else {
i++;
- if (i == rqst->rq_nvec) {
+ if (i == rqst->rq_nvec-1) {
/* send out all remaining vecs */
remaining_data_length -= buflen;
log_write(INFO,
diff --git a/fs/cifs/trace.c b/fs/cifs/trace.c
new file mode 100644
index 0000000..bd4a546f
--- /dev/null
+++ b/fs/cifs/trace.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018, Microsoft Corporation.
+ *
+ * Author(s): Steve French <stfrench@microsoft.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
+ * the GNU General Public License for more details.
+ */
+#define CREATE_TRACE_POINTS
+#include "trace.h"
diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h
new file mode 100644
index 0000000..61e74d4
--- /dev/null
+++ b/fs/cifs/trace.h
@@ -0,0 +1,429 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018, Microsoft Corporation.
+ *
+ * Author(s): Steve French <stfrench@microsoft.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
+ * the GNU General Public License for more details.
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM cifs
+
+#if !defined(_CIFS_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _CIFS_TRACE_H
+
+#include <linux/tracepoint.h>
+
+/* For logging errors in read or write */
+DECLARE_EVENT_CLASS(smb3_rw_err_class,
+ TP_PROTO(unsigned int xid,
+ __u64 fid,
+ __u32 tid,
+ __u64 sesid,
+ __u64 offset,
+ __u32 len,
+ int rc),
+ TP_ARGS(xid, fid, tid, sesid, offset, len, rc),
+ TP_STRUCT__entry(
+ __field(unsigned int, xid)
+ __field(__u64, fid)
+ __field(__u32, tid)
+ __field(__u64, sesid)
+ __field(__u64, offset)
+ __field(__u32, len)
+ __field(int, rc)
+ ),
+ TP_fast_assign(
+ __entry->xid = xid;
+ __entry->fid = fid;
+ __entry->tid = tid;
+ __entry->sesid = sesid;
+ __entry->offset = offset;
+ __entry->len = len;
+ __entry->rc = rc;
+ ),
+ TP_printk("\txid=%u sid=0x%llx tid=0x%x fid=0x%llx offset=0x%llx len=0x%x rc=%d",
+ __entry->xid, __entry->sesid, __entry->tid, __entry->fid,
+ __entry->offset, __entry->len, __entry->rc)
+)
+
+#define DEFINE_SMB3_RW_ERR_EVENT(name) \
+DEFINE_EVENT(smb3_rw_err_class, smb3_##name, \
+ TP_PROTO(unsigned int xid, \
+ __u64 fid, \
+ __u32 tid, \
+ __u64 sesid, \
+ __u64 offset, \
+ __u32 len, \
+ int rc), \
+ TP_ARGS(xid, fid, tid, sesid, offset, len, rc))
+
+DEFINE_SMB3_RW_ERR_EVENT(write_err);
+DEFINE_SMB3_RW_ERR_EVENT(read_err);
+
+
+/* For logging successful read or write */
+DECLARE_EVENT_CLASS(smb3_rw_done_class,
+ TP_PROTO(unsigned int xid,
+ __u64 fid,
+ __u32 tid,
+ __u64 sesid,
+ __u64 offset,
+ __u32 len),
+ TP_ARGS(xid, fid, tid, sesid, offset, len),
+ TP_STRUCT__entry(
+ __field(unsigned int, xid)
+ __field(__u64, fid)
+ __field(__u32, tid)
+ __field(__u64, sesid)
+ __field(__u64, offset)
+ __field(__u32, len)
+ ),
+ TP_fast_assign(
+ __entry->xid = xid;
+ __entry->fid = fid;
+ __entry->tid = tid;
+ __entry->sesid = sesid;
+ __entry->offset = offset;
+ __entry->len = len;
+ ),
+ TP_printk("xid=%u sid=0x%llx tid=0x%x fid=0x%llx offset=0x%llx len=0x%x",
+ __entry->xid, __entry->sesid, __entry->tid, __entry->fid,
+ __entry->offset, __entry->len)
+)
+
+#define DEFINE_SMB3_RW_DONE_EVENT(name) \
+DEFINE_EVENT(smb3_rw_done_class, smb3_##name, \
+ TP_PROTO(unsigned int xid, \
+ __u64 fid, \
+ __u32 tid, \
+ __u64 sesid, \
+ __u64 offset, \
+ __u32 len), \
+ TP_ARGS(xid, fid, tid, sesid, offset, len))
+
+DEFINE_SMB3_RW_DONE_EVENT(write_done);
+DEFINE_SMB3_RW_DONE_EVENT(read_done);
+
+/*
+ * For handle based calls other than read and write, and get/set info
+ */
+DECLARE_EVENT_CLASS(smb3_fd_err_class,
+ TP_PROTO(unsigned int xid,
+ __u64 fid,
+ __u32 tid,
+ __u64 sesid,
+ int rc),
+ TP_ARGS(xid, fid, tid, sesid, rc),
+ TP_STRUCT__entry(
+ __field(unsigned int, xid)
+ __field(__u64, fid)
+ __field(__u32, tid)
+ __field(__u64, sesid)
+ __field(int, rc)
+ ),
+ TP_fast_assign(
+ __entry->xid = xid;
+ __entry->fid = fid;
+ __entry->tid = tid;
+ __entry->sesid = sesid;
+ __entry->rc = rc;
+ ),
+ TP_printk("\txid=%u sid=0x%llx tid=0x%x fid=0x%llx rc=%d",
+ __entry->xid, __entry->sesid, __entry->tid, __entry->fid,
+ __entry->rc)
+)
+
+#define DEFINE_SMB3_FD_ERR_EVENT(name) \
+DEFINE_EVENT(smb3_fd_err_class, smb3_##name, \
+ TP_PROTO(unsigned int xid, \
+ __u64 fid, \
+ __u32 tid, \
+ __u64 sesid, \
+ int rc), \
+ TP_ARGS(xid, fid, tid, sesid, rc))
+
+DEFINE_SMB3_FD_ERR_EVENT(flush_err);
+DEFINE_SMB3_FD_ERR_EVENT(lock_err);
+DEFINE_SMB3_FD_ERR_EVENT(close_err);
+
+/*
+ * For handle based query/set info calls
+ */
+DECLARE_EVENT_CLASS(smb3_inf_err_class,
+ TP_PROTO(unsigned int xid,
+ __u64 fid,
+ __u32 tid,
+ __u64 sesid,
+ __u8 infclass,
+ __u32 type,
+ int rc),
+ TP_ARGS(xid, fid, tid, sesid, infclass, type, rc),
+ TP_STRUCT__entry(
+ __field(unsigned int, xid)
+ __field(__u64, fid)
+ __field(__u32, tid)
+ __field(__u64, sesid)
+ __field(__u8, infclass)
+ __field(__u32, type)
+ __field(int, rc)
+ ),
+ TP_fast_assign(
+ __entry->xid = xid;
+ __entry->fid = fid;
+ __entry->tid = tid;
+ __entry->sesid = sesid;
+ __entry->infclass = infclass;
+ __entry->type = type;
+ __entry->rc = rc;
+ ),
+ TP_printk("xid=%u sid=0x%llx tid=0x%x fid=0x%llx class=%u type=0x%x rc=%d",
+ __entry->xid, __entry->sesid, __entry->tid, __entry->fid,
+ __entry->infclass, __entry->type, __entry->rc)
+)
+
+#define DEFINE_SMB3_INF_ERR_EVENT(name) \
+DEFINE_EVENT(smb3_inf_err_class, smb3_##name, \
+ TP_PROTO(unsigned int xid, \
+ __u64 fid, \
+ __u32 tid, \
+ __u64 sesid, \
+ __u8 infclass, \
+ __u32 type, \
+ int rc), \
+ TP_ARGS(xid, fid, tid, sesid, infclass, type, rc))
+
+DEFINE_SMB3_INF_ERR_EVENT(query_info_err);
+DEFINE_SMB3_INF_ERR_EVENT(set_info_err);
+DEFINE_SMB3_INF_ERR_EVENT(fsctl_err);
+
+/*
+ * For logging SMB3 Status code and Command for responses which return errors
+ */
+DECLARE_EVENT_CLASS(smb3_cmd_err_class,
+ TP_PROTO(__u32 tid,
+ __u64 sesid,
+ __u16 cmd,
+ __u64 mid,
+ __u32 status,
+ int rc),
+ TP_ARGS(tid, sesid, cmd, mid, status, rc),
+ TP_STRUCT__entry(
+ __field(__u32, tid)
+ __field(__u64, sesid)
+ __field(__u16, cmd)
+ __field(__u64, mid)
+ __field(__u32, status)
+ __field(int, rc)
+ ),
+ TP_fast_assign(
+ __entry->tid = tid;
+ __entry->sesid = sesid;
+ __entry->cmd = cmd;
+ __entry->mid = mid;
+ __entry->status = status;
+ __entry->rc = rc;
+ ),
+ TP_printk("\tsid=0x%llx tid=0x%x cmd=%u mid=%llu status=0x%x rc=%d",
+ __entry->sesid, __entry->tid, __entry->cmd, __entry->mid,
+ __entry->status, __entry->rc)
+)
+
+#define DEFINE_SMB3_CMD_ERR_EVENT(name) \
+DEFINE_EVENT(smb3_cmd_err_class, smb3_##name, \
+ TP_PROTO(__u32 tid, \
+ __u64 sesid, \
+ __u16 cmd, \
+ __u64 mid, \
+ __u32 status, \
+ int rc), \
+ TP_ARGS(tid, sesid, cmd, mid, status, rc))
+
+DEFINE_SMB3_CMD_ERR_EVENT(cmd_err);
+
+DECLARE_EVENT_CLASS(smb3_cmd_done_class,
+ TP_PROTO(__u32 tid,
+ __u64 sesid,
+ __u16 cmd,
+ __u64 mid),
+ TP_ARGS(tid, sesid, cmd, mid),
+ TP_STRUCT__entry(
+ __field(__u32, tid)
+ __field(__u64, sesid)
+ __field(__u16, cmd)
+ __field(__u64, mid)
+ ),
+ TP_fast_assign(
+ __entry->tid = tid;
+ __entry->sesid = sesid;
+ __entry->cmd = cmd;
+ __entry->mid = mid;
+ ),
+ TP_printk("\tsid=0x%llx tid=0x%x cmd=%u mid=%llu",
+ __entry->sesid, __entry->tid,
+ __entry->cmd, __entry->mid)
+)
+
+#define DEFINE_SMB3_CMD_DONE_EVENT(name) \
+DEFINE_EVENT(smb3_cmd_done_class, smb3_##name, \
+ TP_PROTO(__u32 tid, \
+ __u64 sesid, \
+ __u16 cmd, \
+ __u64 mid), \
+ TP_ARGS(tid, sesid, cmd, mid))
+
+DEFINE_SMB3_CMD_DONE_EVENT(cmd_done);
+
+DECLARE_EVENT_CLASS(smb3_exit_err_class,
+ TP_PROTO(unsigned int xid,
+ const char *func_name,
+ int rc),
+ TP_ARGS(xid, func_name, rc),
+ TP_STRUCT__entry(
+ __field(unsigned int, xid)
+ __field(const char *, func_name)
+ __field(int, rc)
+ ),
+ TP_fast_assign(
+ __entry->xid = xid;
+ __entry->func_name = func_name;
+ __entry->rc = rc;
+ ),
+ TP_printk("\t%s: xid=%u rc=%d",
+ __entry->func_name, __entry->xid, __entry->rc)
+)
+
+#define DEFINE_SMB3_EXIT_ERR_EVENT(name) \
+DEFINE_EVENT(smb3_exit_err_class, smb3_##name, \
+ TP_PROTO(unsigned int xid, \
+ const char *func_name, \
+ int rc), \
+ TP_ARGS(xid, func_name, rc))
+
+DEFINE_SMB3_EXIT_ERR_EVENT(exit_err);
+
+DECLARE_EVENT_CLASS(smb3_enter_exit_class,
+ TP_PROTO(unsigned int xid,
+ const char *func_name),
+ TP_ARGS(xid, func_name),
+ TP_STRUCT__entry(
+ __field(unsigned int, xid)
+ __field(const char *, func_name)
+ ),
+ TP_fast_assign(
+ __entry->xid = xid;
+ __entry->func_name = func_name;
+ ),
+ TP_printk("\t%s: xid=%u",
+ __entry->func_name, __entry->xid)
+)
+
+#define DEFINE_SMB3_ENTER_EXIT_EVENT(name) \
+DEFINE_EVENT(smb3_enter_exit_class, smb3_##name, \
+ TP_PROTO(unsigned int xid, \
+ const char *func_name), \
+ TP_ARGS(xid, func_name))
+
+DEFINE_SMB3_ENTER_EXIT_EVENT(enter);
+DEFINE_SMB3_ENTER_EXIT_EVENT(exit_done);
+
+/*
+ * For smb2/smb3 open call
+ */
+DECLARE_EVENT_CLASS(smb3_open_err_class,
+ TP_PROTO(unsigned int xid,
+ __u32 tid,
+ __u64 sesid,
+ int create_options,
+ int desired_access,
+ int rc),
+ TP_ARGS(xid, tid, sesid, create_options, desired_access, rc),
+ TP_STRUCT__entry(
+ __field(unsigned int, xid)
+ __field(__u32, tid)
+ __field(__u64, sesid)
+ __field(int, create_options)
+ __field(int, desired_access)
+ __field(int, rc)
+ ),
+ TP_fast_assign(
+ __entry->xid = xid;
+ __entry->tid = tid;
+ __entry->sesid = sesid;
+ __entry->create_options = create_options;
+ __entry->desired_access = desired_access;
+ __entry->rc = rc;
+ ),
+ TP_printk("xid=%u sid=0x%llx tid=0x%x cr_opts=0x%x des_access=0x%x rc=%d",
+ __entry->xid, __entry->sesid, __entry->tid,
+ __entry->create_options, __entry->desired_access, __entry->rc)
+)
+
+#define DEFINE_SMB3_OPEN_ERR_EVENT(name) \
+DEFINE_EVENT(smb3_open_err_class, smb3_##name, \
+ TP_PROTO(unsigned int xid, \
+ __u32 tid, \
+ __u64 sesid, \
+ int create_options, \
+ int desired_access, \
+ int rc), \
+ TP_ARGS(xid, tid, sesid, create_options, desired_access, rc))
+
+DEFINE_SMB3_OPEN_ERR_EVENT(open_err);
+
+
+DECLARE_EVENT_CLASS(smb3_open_done_class,
+ TP_PROTO(unsigned int xid,
+ __u64 fid,
+ __u32 tid,
+ __u64 sesid,
+ int create_options,
+ int desired_access),
+ TP_ARGS(xid, fid, tid, sesid, create_options, desired_access),
+ TP_STRUCT__entry(
+ __field(unsigned int, xid)
+ __field(__u64, fid)
+ __field(__u32, tid)
+ __field(__u64, sesid)
+ __field(int, create_options)
+ __field(int, desired_access)
+ ),
+ TP_fast_assign(
+ __entry->xid = xid;
+ __entry->fid = fid;
+ __entry->tid = tid;
+ __entry->sesid = sesid;
+ __entry->create_options = create_options;
+ __entry->desired_access = desired_access;
+ ),
+ TP_printk("xid=%u sid=0x%llx tid=0x%x fid=0x%llx cr_opts=0x%x des_access=0x%x",
+ __entry->xid, __entry->sesid, __entry->tid, __entry->fid,
+ __entry->create_options, __entry->desired_access)
+)
+
+#define DEFINE_SMB3_OPEN_DONE_EVENT(name) \
+DEFINE_EVENT(smb3_open_done_class, smb3_##name, \
+ TP_PROTO(unsigned int xid, \
+ __u64 fid, \
+ __u32 tid, \
+ __u64 sesid, \
+ int create_options, \
+ int desired_access), \
+ TP_ARGS(xid, fid, tid, sesid, create_options, desired_access))
+
+DEFINE_SMB3_OPEN_DONE_EVENT(open_done);
+
+#endif /* _CIFS_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace
+#include <trace/define_trace.h>
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 8f6f259..e7254e3 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -753,7 +753,7 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
goto out;
#ifdef CONFIG_CIFS_SMB311
- if (ses->status == CifsNew)
+ if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP))
smb311_update_preauth_hash(ses, rqst->rq_iov+1,
rqst->rq_nvec-1);
#endif
@@ -798,10 +798,10 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
*resp_buf_type = CIFS_SMALL_BUFFER;
#ifdef CONFIG_CIFS_SMB311
- if (ses->status == CifsNew) {
+ if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP)) {
struct kvec iov = {
- .iov_base = buf + 4,
- .iov_len = get_rfc1002_length(buf)
+ .iov_base = buf,
+ .iov_len = midQ->resp_buf_size
};
smb311_update_preauth_hash(ses, &iov, 1);
}
@@ -834,8 +834,11 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
if (n_vec + 1 > CIFS_MAX_IOV_SIZE) {
new_iov = kmalloc(sizeof(struct kvec) * (n_vec + 1),
GFP_KERNEL);
- if (!new_iov)
+ if (!new_iov) {
+ /* otherwise cifs_send_recv below sets resp_buf_type */
+ *resp_buf_type = CIFS_NO_BUFFER;
return -ENOMEM;
+ }
} else
new_iov = s_iov;
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 017b0ab..c4fb9ad 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -492,7 +492,7 @@ static void cramfs_kill_sb(struct super_block *sb)
{
struct cramfs_sb_info *sbi = CRAMFS_SB(sb);
- if (IS_ENABLED(CCONFIG_CRAMFS_MTD) && sb->s_mtd) {
+ if (IS_ENABLED(CONFIG_CRAMFS_MTD) && sb->s_mtd) {
if (sbi && sbi->mtd_point_size)
mtd_unpoint(sb->s_mtd, 0, sbi->mtd_point_size);
kill_mtd_super(sb);
@@ -808,10 +808,7 @@ static struct dentry *cramfs_lookup(struct inode *dir, struct dentry *dentry, un
}
out:
mutex_unlock(&read_mutex);
- if (IS_ERR(inode))
- return ERR_CAST(inode);
- d_add(dentry, inode);
- return NULL;
+ return d_splice_alias(inode, dentry);
}
static int cramfs_readpage(struct file *file, struct page *page)
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index ce65452..243a269 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -156,12 +156,8 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw,
}
req = skcipher_request_alloc(tfm, gfp_flags);
- if (!req) {
- printk_ratelimited(KERN_ERR
- "%s: crypto_request_alloc() failed\n",
- __func__);
+ if (!req)
return -ENOMEM;
- }
skcipher_request_set_callback(
req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
@@ -178,9 +174,10 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw,
res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
skcipher_request_free(req);
if (res) {
- printk_ratelimited(KERN_ERR
- "%s: crypto_skcipher_encrypt() returned %d\n",
- __func__, res);
+ fscrypt_err(inode->i_sb,
+ "%scryption failed for inode %lu, block %llu: %d",
+ (rw == FS_DECRYPT ? "de" : "en"),
+ inode->i_ino, lblk_num, res);
return res;
}
return 0;
@@ -326,7 +323,6 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
return 0;
}
- /* this should eventually be an flag in d_flags */
spin_lock(&dentry->d_lock);
cached_with_key = dentry->d_flags & DCACHE_ENCRYPTED_WITH_KEY;
spin_unlock(&dentry->d_lock);
@@ -353,7 +349,6 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
const struct dentry_operations fscrypt_d_ops = {
.d_revalidate = fscrypt_d_revalidate,
};
-EXPORT_SYMBOL(fscrypt_d_ops);
void fscrypt_restore_control_page(struct page *page)
{
@@ -422,13 +417,43 @@ int fscrypt_initialize(unsigned int cop_flags)
return res;
}
+void fscrypt_msg(struct super_block *sb, const char *level,
+ const char *fmt, ...)
+{
+ static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
+ DEFAULT_RATELIMIT_BURST);
+ struct va_format vaf;
+ va_list args;
+
+ if (!__ratelimit(&rs))
+ return;
+
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ if (sb)
+ printk("%sfscrypt (%s): %pV\n", level, sb->s_id, &vaf);
+ else
+ printk("%sfscrypt: %pV\n", level, &vaf);
+ va_end(args);
+}
+
/**
* fscrypt_init() - Set up for fs encryption.
*/
static int __init fscrypt_init(void)
{
+ /*
+ * Use an unbound workqueue to allow bios to be decrypted in parallel
+ * even when they happen to complete on the same CPU. This sacrifices
+ * locality, but it's worthwhile since decryption is CPU-intensive.
+ *
+ * Also use a high-priority workqueue to prioritize decryption work,
+ * which blocks reads from completing, over regular application tasks.
+ */
fscrypt_read_workqueue = alloc_workqueue("fscrypt_read_queue",
- WQ_HIGHPRI, 0);
+ WQ_UNBOUND | WQ_HIGHPRI,
+ num_online_cpus());
if (!fscrypt_read_workqueue)
goto fail;
diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index e33f3d3..d7a0f68 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -59,11 +59,8 @@ int fname_encrypt(struct inode *inode, const struct qstr *iname,
/* Set up the encryption request */
req = skcipher_request_alloc(tfm, GFP_NOFS);
- if (!req) {
- printk_ratelimited(KERN_ERR
- "%s: skcipher_request_alloc() failed\n", __func__);
+ if (!req)
return -ENOMEM;
- }
skcipher_request_set_callback(req,
CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
crypto_req_done, &wait);
@@ -74,8 +71,9 @@ int fname_encrypt(struct inode *inode, const struct qstr *iname,
res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
skcipher_request_free(req);
if (res < 0) {
- printk_ratelimited(KERN_ERR
- "%s: Error (error code %d)\n", __func__, res);
+ fscrypt_err(inode->i_sb,
+ "Filename encryption failed for inode %lu: %d",
+ inode->i_ino, res);
return res;
}
@@ -96,23 +94,14 @@ static int fname_decrypt(struct inode *inode,
struct skcipher_request *req = NULL;
DECLARE_CRYPTO_WAIT(wait);
struct scatterlist src_sg, dst_sg;
- struct fscrypt_info *ci = inode->i_crypt_info;
- struct crypto_skcipher *tfm = ci->ci_ctfm;
+ struct crypto_skcipher *tfm = inode->i_crypt_info->ci_ctfm;
int res = 0;
char iv[FS_CRYPTO_BLOCK_SIZE];
- unsigned lim;
-
- lim = inode->i_sb->s_cop->max_namelen(inode);
- if (iname->len <= 0 || iname->len > lim)
- return -EIO;
/* Allocate request */
req = skcipher_request_alloc(tfm, GFP_NOFS);
- if (!req) {
- printk_ratelimited(KERN_ERR
- "%s: crypto_request_alloc() failed\n", __func__);
+ if (!req)
return -ENOMEM;
- }
skcipher_request_set_callback(req,
CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
crypto_req_done, &wait);
@@ -127,8 +116,9 @@ static int fname_decrypt(struct inode *inode,
res = crypto_wait_req(crypto_skcipher_decrypt(req), &wait);
skcipher_request_free(req);
if (res < 0) {
- printk_ratelimited(KERN_ERR
- "%s: Error (error code %d)\n", __func__, res);
+ fscrypt_err(inode->i_sb,
+ "Filename decryption failed for inode %lu: %d",
+ inode->i_ino, res);
return res;
}
@@ -341,12 +331,12 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
return 0;
}
ret = fscrypt_get_encryption_info(dir);
- if (ret && ret != -EOPNOTSUPP)
+ if (ret)
return ret;
if (dir->i_crypt_info) {
if (!fscrypt_fname_encrypted_size(dir, iname->len,
- dir->i_sb->s_cop->max_namelen(dir),
+ dir->i_sb->s_cop->max_namelen,
&fname->crypto_buf.len))
return -ENAMETOOLONG;
fname->crypto_buf.name = kmalloc(fname->crypto_buf.len,
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index ad6722b..3756239 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -18,15 +18,7 @@
/* Encryption parameters */
#define FS_IV_SIZE 16
-#define FS_AES_128_ECB_KEY_SIZE 16
-#define FS_AES_128_CBC_KEY_SIZE 16
-#define FS_AES_128_CTS_KEY_SIZE 16
-#define FS_AES_256_GCM_KEY_SIZE 32
-#define FS_AES_256_CBC_KEY_SIZE 32
-#define FS_AES_256_CTS_KEY_SIZE 32
-#define FS_AES_256_XTS_KEY_SIZE 64
-
-#define FS_KEY_DERIVATION_NONCE_SIZE 16
+#define FS_KEY_DERIVATION_NONCE_SIZE 16
/**
* Encryption context for inode
@@ -91,6 +83,10 @@ static inline bool fscrypt_valid_enc_modes(u32 contents_mode,
filenames_mode == FS_ENCRYPTION_MODE_AES_256_CTS)
return true;
+ if (contents_mode == FS_ENCRYPTION_MODE_SPECK128_256_XTS &&
+ filenames_mode == FS_ENCRYPTION_MODE_SPECK128_256_CTS)
+ return true;
+
return false;
}
@@ -106,6 +102,15 @@ extern int fscrypt_do_page_crypto(const struct inode *inode,
gfp_t gfp_flags);
extern struct page *fscrypt_alloc_bounce_page(struct fscrypt_ctx *ctx,
gfp_t gfp_flags);
+extern const struct dentry_operations fscrypt_d_ops;
+
+extern void __printf(3, 4) __cold
+fscrypt_msg(struct super_block *sb, const char *level, const char *fmt, ...);
+
+#define fscrypt_warn(sb, fmt, ...) \
+ fscrypt_msg(sb, KERN_WARNING, fmt, ##__VA_ARGS__)
+#define fscrypt_err(sb, fmt, ...) \
+ fscrypt_msg(sb, KERN_ERR, fmt, ##__VA_ARGS__)
/* fname.c */
extern int fname_encrypt(struct inode *inode, const struct qstr *iname,
diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index bec0649..926e5df 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -39,8 +39,9 @@ int fscrypt_file_open(struct inode *inode, struct file *filp)
dir = dget_parent(file_dentry(filp));
if (IS_ENCRYPTED(d_inode(dir)) &&
!fscrypt_has_permitted_context(d_inode(dir), inode)) {
- pr_warn_ratelimited("fscrypt: inconsistent encryption contexts: %lu/%lu",
- d_inode(dir)->i_ino, inode->i_ino);
+ fscrypt_warn(inode->i_sb,
+ "inconsistent encryption contexts: %lu/%lu",
+ d_inode(dir)->i_ino, inode->i_ino);
err = -EPERM;
}
dput(dir);
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
index 05f5ee1..e997ca5 100644
--- a/fs/crypto/keyinfo.c
+++ b/fs/crypto/keyinfo.c
@@ -19,17 +19,16 @@
static struct crypto_shash *essiv_hash_tfm;
-/**
- * derive_key_aes() - Derive a key using AES-128-ECB
- * @deriving_key: Encryption key used for derivation.
- * @source_key: Source key to which to apply derivation.
- * @derived_raw_key: Derived raw key.
+/*
+ * Key derivation function. This generates the derived key by encrypting the
+ * master key with AES-128-ECB using the inode's nonce as the AES key.
*
- * Return: Zero on success; non-zero otherwise.
+ * The master key must be at least as long as the derived key. If the master
+ * key is longer, then only the first 'derived_keysize' bytes are used.
*/
-static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE],
- const struct fscrypt_key *source_key,
- u8 derived_raw_key[FS_MAX_KEY_SIZE])
+static int derive_key_aes(const u8 *master_key,
+ const struct fscrypt_context *ctx,
+ u8 *derived_key, unsigned int derived_keysize)
{
int res = 0;
struct skcipher_request *req = NULL;
@@ -51,14 +50,13 @@ static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE],
skcipher_request_set_callback(req,
CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
crypto_req_done, &wait);
- res = crypto_skcipher_setkey(tfm, deriving_key,
- FS_AES_128_ECB_KEY_SIZE);
+ res = crypto_skcipher_setkey(tfm, ctx->nonce, sizeof(ctx->nonce));
if (res < 0)
goto out;
- sg_init_one(&src_sg, source_key->raw, source_key->size);
- sg_init_one(&dst_sg, derived_raw_key, source_key->size);
- skcipher_request_set_crypt(req, &src_sg, &dst_sg, source_key->size,
+ sg_init_one(&src_sg, master_key, derived_keysize);
+ sg_init_one(&dst_sg, derived_key, derived_keysize);
+ skcipher_request_set_crypt(req, &src_sg, &dst_sg, derived_keysize,
NULL);
res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
out:
@@ -67,101 +65,147 @@ static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE],
return res;
}
-static int validate_user_key(struct fscrypt_info *crypt_info,
- struct fscrypt_context *ctx, u8 *raw_key,
- const char *prefix, int min_keysize)
+/*
+ * Search the current task's subscribed keyrings for a "logon" key with
+ * description prefix:descriptor, and if found acquire a read lock on it and
+ * return a pointer to its validated payload in *payload_ret.
+ */
+static struct key *
+find_and_lock_process_key(const char *prefix,
+ const u8 descriptor[FS_KEY_DESCRIPTOR_SIZE],
+ unsigned int min_keysize,
+ const struct fscrypt_key **payload_ret)
{
char *description;
- struct key *keyring_key;
- struct fscrypt_key *master_key;
+ struct key *key;
const struct user_key_payload *ukp;
- int res;
+ const struct fscrypt_key *payload;
description = kasprintf(GFP_NOFS, "%s%*phN", prefix,
- FS_KEY_DESCRIPTOR_SIZE,
- ctx->master_key_descriptor);
+ FS_KEY_DESCRIPTOR_SIZE, descriptor);
if (!description)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
- keyring_key = request_key(&key_type_logon, description, NULL);
+ key = request_key(&key_type_logon, description, NULL);
kfree(description);
- if (IS_ERR(keyring_key))
- return PTR_ERR(keyring_key);
- down_read(&keyring_key->sem);
+ if (IS_ERR(key))
+ return key;
- if (keyring_key->type != &key_type_logon) {
- printk_once(KERN_WARNING
- "%s: key type must be logon\n", __func__);
- res = -ENOKEY;
- goto out;
- }
- ukp = user_key_payload_locked(keyring_key);
- if (!ukp) {
- /* key was revoked before we acquired its semaphore */
- res = -EKEYREVOKED;
- goto out;
- }
- if (ukp->datalen != sizeof(struct fscrypt_key)) {
- res = -EINVAL;
- goto out;
- }
- master_key = (struct fscrypt_key *)ukp->data;
- BUILD_BUG_ON(FS_AES_128_ECB_KEY_SIZE != FS_KEY_DERIVATION_NONCE_SIZE);
+ down_read(&key->sem);
+ ukp = user_key_payload_locked(key);
- if (master_key->size < min_keysize || master_key->size > FS_MAX_KEY_SIZE
- || master_key->size % AES_BLOCK_SIZE != 0) {
- printk_once(KERN_WARNING
- "%s: key size incorrect: %d\n",
- __func__, master_key->size);
- res = -ENOKEY;
- goto out;
+ if (!ukp) /* was the key revoked before we acquired its semaphore? */
+ goto invalid;
+
+ payload = (const struct fscrypt_key *)ukp->data;
+
+ if (ukp->datalen != sizeof(struct fscrypt_key) ||
+ payload->size < 1 || payload->size > FS_MAX_KEY_SIZE) {
+ fscrypt_warn(NULL,
+ "key with description '%s' has invalid payload",
+ key->description);
+ goto invalid;
}
- res = derive_key_aes(ctx->nonce, master_key, raw_key);
-out:
- up_read(&keyring_key->sem);
- key_put(keyring_key);
- return res;
+
+ if (payload->size < min_keysize) {
+ fscrypt_warn(NULL,
+ "key with description '%s' is too short (got %u bytes, need %u+ bytes)",
+ key->description, payload->size, min_keysize);
+ goto invalid;
+ }
+
+ *payload_ret = payload;
+ return key;
+
+invalid:
+ up_read(&key->sem);
+ key_put(key);
+ return ERR_PTR(-ENOKEY);
}
-static const struct {
+/* Find the master key, then derive the inode's actual encryption key */
+static int find_and_derive_key(const struct inode *inode,
+ const struct fscrypt_context *ctx,
+ u8 *derived_key, unsigned int derived_keysize)
+{
+ struct key *key;
+ const struct fscrypt_key *payload;
+ int err;
+
+ key = find_and_lock_process_key(FS_KEY_DESC_PREFIX,
+ ctx->master_key_descriptor,
+ derived_keysize, &payload);
+ if (key == ERR_PTR(-ENOKEY) && inode->i_sb->s_cop->key_prefix) {
+ key = find_and_lock_process_key(inode->i_sb->s_cop->key_prefix,
+ ctx->master_key_descriptor,
+ derived_keysize, &payload);
+ }
+ if (IS_ERR(key))
+ return PTR_ERR(key);
+ err = derive_key_aes(payload->raw, ctx, derived_key, derived_keysize);
+ up_read(&key->sem);
+ key_put(key);
+ return err;
+}
+
+static struct fscrypt_mode {
+ const char *friendly_name;
const char *cipher_str;
int keysize;
+ bool logged_impl_name;
} available_modes[] = {
- [FS_ENCRYPTION_MODE_AES_256_XTS] = { "xts(aes)",
- FS_AES_256_XTS_KEY_SIZE },
- [FS_ENCRYPTION_MODE_AES_256_CTS] = { "cts(cbc(aes))",
- FS_AES_256_CTS_KEY_SIZE },
- [FS_ENCRYPTION_MODE_AES_128_CBC] = { "cbc(aes)",
- FS_AES_128_CBC_KEY_SIZE },
- [FS_ENCRYPTION_MODE_AES_128_CTS] = { "cts(cbc(aes))",
- FS_AES_128_CTS_KEY_SIZE },
+ [FS_ENCRYPTION_MODE_AES_256_XTS] = {
+ .friendly_name = "AES-256-XTS",
+ .cipher_str = "xts(aes)",
+ .keysize = 64,
+ },
+ [FS_ENCRYPTION_MODE_AES_256_CTS] = {
+ .friendly_name = "AES-256-CTS-CBC",
+ .cipher_str = "cts(cbc(aes))",
+ .keysize = 32,
+ },
+ [FS_ENCRYPTION_MODE_AES_128_CBC] = {
+ .friendly_name = "AES-128-CBC",
+ .cipher_str = "cbc(aes)",
+ .keysize = 16,
+ },
+ [FS_ENCRYPTION_MODE_AES_128_CTS] = {
+ .friendly_name = "AES-128-CTS-CBC",
+ .cipher_str = "cts(cbc(aes))",
+ .keysize = 16,
+ },
+ [FS_ENCRYPTION_MODE_SPECK128_256_XTS] = {
+ .friendly_name = "Speck128/256-XTS",
+ .cipher_str = "xts(speck128)",
+ .keysize = 64,
+ },
+ [FS_ENCRYPTION_MODE_SPECK128_256_CTS] = {
+ .friendly_name = "Speck128/256-CTS-CBC",
+ .cipher_str = "cts(cbc(speck128))",
+ .keysize = 32,
+ },
};
-static int determine_cipher_type(struct fscrypt_info *ci, struct inode *inode,
- const char **cipher_str_ret, int *keysize_ret)
+static struct fscrypt_mode *
+select_encryption_mode(const struct fscrypt_info *ci, const struct inode *inode)
{
- u32 mode;
-
if (!fscrypt_valid_enc_modes(ci->ci_data_mode, ci->ci_filename_mode)) {
- pr_warn_ratelimited("fscrypt: inode %lu uses unsupported encryption modes (contents mode %d, filenames mode %d)\n",
- inode->i_ino,
- ci->ci_data_mode, ci->ci_filename_mode);
- return -EINVAL;
+ fscrypt_warn(inode->i_sb,
+ "inode %lu uses unsupported encryption modes (contents mode %d, filenames mode %d)",
+ inode->i_ino, ci->ci_data_mode,
+ ci->ci_filename_mode);
+ return ERR_PTR(-EINVAL);
}
- if (S_ISREG(inode->i_mode)) {
- mode = ci->ci_data_mode;
- } else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) {
- mode = ci->ci_filename_mode;
- } else {
- WARN_ONCE(1, "fscrypt: filesystem tried to load encryption info for inode %lu, which is not encryptable (file type %d)\n",
- inode->i_ino, (inode->i_mode & S_IFMT));
- return -EINVAL;
- }
+ if (S_ISREG(inode->i_mode))
+ return &available_modes[ci->ci_data_mode];
- *cipher_str_ret = available_modes[mode].cipher_str;
- *keysize_ret = available_modes[mode].keysize;
- return 0;
+ if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+ return &available_modes[ci->ci_filename_mode];
+
+ WARN_ONCE(1, "fscrypt: filesystem tried to load encryption info for inode %lu, which is not encryptable (file type %d)\n",
+ inode->i_ino, (inode->i_mode & S_IFMT));
+ return ERR_PTR(-EINVAL);
}
static void put_crypt_info(struct fscrypt_info *ci)
@@ -184,8 +228,9 @@ static int derive_essiv_salt(const u8 *key, int keysize, u8 *salt)
tfm = crypto_alloc_shash("sha256", 0, 0);
if (IS_ERR(tfm)) {
- pr_warn_ratelimited("fscrypt: error allocating SHA-256 transform: %ld\n",
- PTR_ERR(tfm));
+ fscrypt_warn(NULL,
+ "error allocating SHA-256 transform: %ld",
+ PTR_ERR(tfm));
return PTR_ERR(tfm);
}
prev_tfm = cmpxchg(&essiv_hash_tfm, NULL, tfm);
@@ -245,8 +290,7 @@ int fscrypt_get_encryption_info(struct inode *inode)
struct fscrypt_info *crypt_info;
struct fscrypt_context ctx;
struct crypto_skcipher *ctfm;
- const char *cipher_str;
- int keysize;
+ struct fscrypt_mode *mode;
u8 *raw_key = NULL;
int res;
@@ -290,57 +334,59 @@ int fscrypt_get_encryption_info(struct inode *inode)
memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
sizeof(crypt_info->ci_master_key));
- res = determine_cipher_type(crypt_info, inode, &cipher_str, &keysize);
- if (res)
+ mode = select_encryption_mode(crypt_info, inode);
+ if (IS_ERR(mode)) {
+ res = PTR_ERR(mode);
goto out;
+ }
/*
* This cannot be a stack buffer because it is passed to the scatterlist
* crypto API as part of key derivation.
*/
res = -ENOMEM;
- raw_key = kmalloc(FS_MAX_KEY_SIZE, GFP_NOFS);
+ raw_key = kmalloc(mode->keysize, GFP_NOFS);
if (!raw_key)
goto out;
- res = validate_user_key(crypt_info, &ctx, raw_key, FS_KEY_DESC_PREFIX,
- keysize);
- if (res && inode->i_sb->s_cop->key_prefix) {
- int res2 = validate_user_key(crypt_info, &ctx, raw_key,
- inode->i_sb->s_cop->key_prefix,
- keysize);
- if (res2) {
- if (res2 == -ENOKEY)
- res = -ENOKEY;
- goto out;
- }
- } else if (res) {
+ res = find_and_derive_key(inode, &ctx, raw_key, mode->keysize);
+ if (res)
+ goto out;
+
+ ctfm = crypto_alloc_skcipher(mode->cipher_str, 0, 0);
+ if (IS_ERR(ctfm)) {
+ res = PTR_ERR(ctfm);
+ fscrypt_warn(inode->i_sb,
+ "error allocating '%s' transform for inode %lu: %d",
+ mode->cipher_str, inode->i_ino, res);
goto out;
}
- ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
- if (!ctfm || IS_ERR(ctfm)) {
- res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
- pr_debug("%s: error %d (inode %lu) allocating crypto tfm\n",
- __func__, res, inode->i_ino);
- goto out;
+ if (unlikely(!mode->logged_impl_name)) {
+ /*
+ * fscrypt performance can vary greatly depending on which
+ * crypto algorithm implementation is used. Help people debug
+ * performance problems by logging the ->cra_driver_name the
+ * first time a mode is used. Note that multiple threads can
+ * race here, but it doesn't really matter.
+ */
+ mode->logged_impl_name = true;
+ pr_info("fscrypt: %s using implementation \"%s\"\n",
+ mode->friendly_name,
+ crypto_skcipher_alg(ctfm)->base.cra_driver_name);
}
crypt_info->ci_ctfm = ctfm;
- crypto_skcipher_clear_flags(ctfm, ~0);
crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_REQ_WEAK_KEY);
- /*
- * if the provided key is longer than keysize, we use the first
- * keysize bytes of the derived key only
- */
- res = crypto_skcipher_setkey(ctfm, raw_key, keysize);
+ res = crypto_skcipher_setkey(ctfm, raw_key, mode->keysize);
if (res)
goto out;
if (S_ISREG(inode->i_mode) &&
crypt_info->ci_data_mode == FS_ENCRYPTION_MODE_AES_128_CBC) {
- res = init_essiv_generator(crypt_info, raw_key, keysize);
+ res = init_essiv_generator(crypt_info, raw_key, mode->keysize);
if (res) {
- pr_debug("%s: error %d (inode %lu) allocating essiv tfm\n",
- __func__, res, inode->i_ino);
+ fscrypt_warn(inode->i_sb,
+ "error initializing ESSIV generator for inode %lu: %d",
+ inode->i_ino, res);
goto out;
}
}
diff --git a/fs/dax.c b/fs/dax.c
index aaec72de..aa86d9f 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -677,7 +677,7 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping,
* downgrading page table protection not changing it to point
* to a new page.
*
- * See Documentation/vm/mmu_notifier.txt
+ * See Documentation/vm/mmu_notifier.rst
*/
if (pmdp) {
#ifdef CONFIG_FS_DAX_PMD
diff --git a/fs/dcache.c b/fs/dcache.c
index 86d2de6..0e8e5de 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -580,6 +580,7 @@ static void __dentry_kill(struct dentry *dentry)
spin_unlock(&dentry->d_lock);
if (likely(can_free))
dentry_free(dentry);
+ cond_resched();
}
static struct dentry *__lock_parent(struct dentry *dentry)
@@ -827,30 +828,24 @@ static inline bool fast_dput(struct dentry *dentry)
*/
void dput(struct dentry *dentry)
{
- if (unlikely(!dentry))
- return;
+ while (dentry) {
+ might_sleep();
-repeat:
- might_sleep();
+ rcu_read_lock();
+ if (likely(fast_dput(dentry))) {
+ rcu_read_unlock();
+ return;
+ }
- rcu_read_lock();
- if (likely(fast_dput(dentry))) {
+ /* Slow case: now with the dentry lock held */
rcu_read_unlock();
- return;
- }
- /* Slow case: now with the dentry lock held */
- rcu_read_unlock();
+ if (likely(retain_dentry(dentry))) {
+ spin_unlock(&dentry->d_lock);
+ return;
+ }
- if (likely(retain_dentry(dentry))) {
- spin_unlock(&dentry->d_lock);
- return;
- }
-
- dentry = dentry_kill(dentry);
- if (dentry) {
- cond_resched();
- goto repeat;
+ dentry = dentry_kill(dentry);
}
}
EXPORT_SYMBOL(dput);
@@ -907,6 +902,35 @@ struct dentry *dget_parent(struct dentry *dentry)
}
EXPORT_SYMBOL(dget_parent);
+static struct dentry * __d_find_any_alias(struct inode *inode)
+{
+ struct dentry *alias;
+
+ if (hlist_empty(&inode->i_dentry))
+ return NULL;
+ alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
+ __dget(alias);
+ return alias;
+}
+
+/**
+ * d_find_any_alias - find any alias for a given inode
+ * @inode: inode to find an alias for
+ *
+ * If any aliases exist for the given inode, take and return a
+ * reference for one of them. If no aliases exist, return %NULL.
+ */
+struct dentry *d_find_any_alias(struct inode *inode)
+{
+ struct dentry *de;
+
+ spin_lock(&inode->i_lock);
+ de = __d_find_any_alias(inode);
+ spin_unlock(&inode->i_lock);
+ return de;
+}
+EXPORT_SYMBOL(d_find_any_alias);
+
/**
* d_find_alias - grab a hashed alias of inode
* @inode: inode in question
@@ -923,34 +947,19 @@ EXPORT_SYMBOL(dget_parent);
*/
static struct dentry *__d_find_alias(struct inode *inode)
{
- struct dentry *alias, *discon_alias;
+ struct dentry *alias;
-again:
- discon_alias = NULL;
+ if (S_ISDIR(inode->i_mode))
+ return __d_find_any_alias(inode);
+
hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
spin_lock(&alias->d_lock);
- if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
- if (IS_ROOT(alias) &&
- (alias->d_flags & DCACHE_DISCONNECTED)) {
- discon_alias = alias;
- } else {
- __dget_dlock(alias);
- spin_unlock(&alias->d_lock);
- return alias;
- }
- }
- spin_unlock(&alias->d_lock);
- }
- if (discon_alias) {
- alias = discon_alias;
- spin_lock(&alias->d_lock);
- if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
+ if (!d_unhashed(alias)) {
__dget_dlock(alias);
spin_unlock(&alias->d_lock);
return alias;
}
spin_unlock(&alias->d_lock);
- goto again;
}
return NULL;
}
@@ -1052,8 +1061,6 @@ static void shrink_dentry_list(struct list_head *list)
while (!list_empty(list)) {
struct dentry *dentry, *parent;
- cond_resched();
-
dentry = list_entry(list->prev, struct dentry, d_lru);
spin_lock(&dentry->d_lock);
rcu_read_lock();
@@ -1230,13 +1237,11 @@ enum d_walk_ret {
* @parent: start of walk
* @data: data passed to @enter() and @finish()
* @enter: callback when first entering the dentry
- * @finish: callback when successfully finished the walk
*
- * The @enter() and @finish() callbacks are called with d_lock held.
+ * The @enter() callbacks are called with d_lock held.
*/
static void d_walk(struct dentry *parent, void *data,
- enum d_walk_ret (*enter)(void *, struct dentry *),
- void (*finish)(void *))
+ enum d_walk_ret (*enter)(void *, struct dentry *))
{
struct dentry *this_parent;
struct list_head *next;
@@ -1325,8 +1330,6 @@ static void d_walk(struct dentry *parent, void *data,
if (need_seqretry(&rename_lock, seq))
goto rename_retry;
rcu_read_unlock();
- if (finish)
- finish(data);
out_unlock:
spin_unlock(&this_parent->d_lock);
@@ -1375,7 +1378,7 @@ int path_has_submounts(const struct path *parent)
struct check_mount data = { .mnt = parent->mnt, .mounted = 0 };
read_seqlock_excl(&mount_lock);
- d_walk(parent->dentry, &data, path_check_mount, NULL);
+ d_walk(parent->dentry, &data, path_check_mount);
read_sequnlock_excl(&mount_lock);
return data.mounted;
@@ -1483,11 +1486,16 @@ void shrink_dcache_parent(struct dentry *parent)
data.start = parent;
data.found = 0;
- d_walk(parent, &data, select_collect, NULL);
+ d_walk(parent, &data, select_collect);
+
+ if (!list_empty(&data.dispose)) {
+ shrink_dentry_list(&data.dispose);
+ continue;
+ }
+
+ cond_resched();
if (!data.found)
break;
-
- shrink_dentry_list(&data.dispose);
}
}
EXPORT_SYMBOL(shrink_dcache_parent);
@@ -1518,7 +1526,7 @@ static enum d_walk_ret umount_check(void *_data, struct dentry *dentry)
static void do_one_tree(struct dentry *dentry)
{
shrink_dcache_parent(dentry);
- d_walk(dentry, dentry, umount_check, NULL);
+ d_walk(dentry, dentry, umount_check);
d_drop(dentry);
dput(dentry);
}
@@ -1542,78 +1550,48 @@ void shrink_dcache_for_umount(struct super_block *sb)
}
}
-struct detach_data {
- struct select_data select;
- struct dentry *mountpoint;
-};
-static enum d_walk_ret detach_and_collect(void *_data, struct dentry *dentry)
+static enum d_walk_ret find_submount(void *_data, struct dentry *dentry)
{
- struct detach_data *data = _data;
-
+ struct dentry **victim = _data;
if (d_mountpoint(dentry)) {
__dget_dlock(dentry);
- data->mountpoint = dentry;
+ *victim = dentry;
return D_WALK_QUIT;
}
-
- return select_collect(&data->select, dentry);
-}
-
-static void check_and_drop(void *_data)
-{
- struct detach_data *data = _data;
-
- if (!data->mountpoint && list_empty(&data->select.dispose))
- __d_drop(data->select.start);
+ return D_WALK_CONTINUE;
}
/**
* d_invalidate - detach submounts, prune dcache, and drop
* @dentry: dentry to invalidate (aka detach, prune and drop)
- *
- * no dcache lock.
- *
- * The final d_drop is done as an atomic operation relative to
- * rename_lock ensuring there are no races with d_set_mounted. This
- * ensures there are no unhashed dentries on the path to a mountpoint.
*/
void d_invalidate(struct dentry *dentry)
{
- /*
- * If it's already been dropped, return OK.
- */
+ bool had_submounts = false;
spin_lock(&dentry->d_lock);
if (d_unhashed(dentry)) {
spin_unlock(&dentry->d_lock);
return;
}
+ __d_drop(dentry);
spin_unlock(&dentry->d_lock);
/* Negative dentries can be dropped without further checks */
- if (!dentry->d_inode) {
- d_drop(dentry);
+ if (!dentry->d_inode)
return;
- }
+ shrink_dcache_parent(dentry);
for (;;) {
- struct detach_data data;
-
- data.mountpoint = NULL;
- INIT_LIST_HEAD(&data.select.dispose);
- data.select.start = dentry;
- data.select.found = 0;
-
- d_walk(dentry, &data, detach_and_collect, check_and_drop);
-
- if (!list_empty(&data.select.dispose))
- shrink_dentry_list(&data.select.dispose);
- else if (!data.mountpoint)
+ struct dentry *victim = NULL;
+ d_walk(dentry, &victim, find_submount);
+ if (!victim) {
+ if (had_submounts)
+ shrink_dcache_parent(dentry);
return;
-
- if (data.mountpoint) {
- detach_mounts(data.mountpoint);
- dput(data.mountpoint);
}
+ had_submounts = true;
+ detach_mounts(victim);
+ dput(victim);
}
}
EXPORT_SYMBOL(d_invalidate);
@@ -1899,6 +1877,28 @@ void d_instantiate(struct dentry *entry, struct inode * inode)
}
EXPORT_SYMBOL(d_instantiate);
+/*
+ * This should be equivalent to d_instantiate() + unlock_new_inode(),
+ * with lockdep-related part of unlock_new_inode() done before
+ * anything else. Use that instead of open-coding d_instantiate()/
+ * unlock_new_inode() combinations.
+ */
+void d_instantiate_new(struct dentry *entry, struct inode *inode)
+{
+ BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
+ BUG_ON(!inode);
+ lockdep_annotate_inode_mutex_key(inode);
+ security_d_instantiate(entry, inode);
+ spin_lock(&inode->i_lock);
+ __d_instantiate(entry, inode);
+ WARN_ON(!(inode->i_state & I_NEW));
+ inode->i_state &= ~I_NEW;
+ smp_mb();
+ wake_up_bit(&inode->i_state, __I_NEW);
+ spin_unlock(&inode->i_lock);
+}
+EXPORT_SYMBOL(d_instantiate_new);
+
/**
* d_instantiate_no_diralias - instantiate a non-aliased dentry
* @entry: dentry to complete
@@ -1941,35 +1941,6 @@ struct dentry *d_make_root(struct inode *root_inode)
}
EXPORT_SYMBOL(d_make_root);
-static struct dentry * __d_find_any_alias(struct inode *inode)
-{
- struct dentry *alias;
-
- if (hlist_empty(&inode->i_dentry))
- return NULL;
- alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
- __dget(alias);
- return alias;
-}
-
-/**
- * d_find_any_alias - find any alias for a given inode
- * @inode: inode to find an alias for
- *
- * If any aliases exist for the given inode, take and return a
- * reference for one of them. If no aliases exist, return %NULL.
- */
-struct dentry *d_find_any_alias(struct inode *inode)
-{
- struct dentry *de;
-
- spin_lock(&inode->i_lock);
- de = __d_find_any_alias(inode);
- spin_unlock(&inode->i_lock);
- return de;
-}
-EXPORT_SYMBOL(d_find_any_alias);
-
static struct dentry *__d_instantiate_anon(struct dentry *dentry,
struct inode *inode,
bool disconnected)
@@ -3112,7 +3083,7 @@ static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry)
void d_genocide(struct dentry *parent)
{
- d_walk(parent, parent, d_genocide_kill, NULL);
+ d_walk(parent, parent, d_genocide_kill);
}
EXPORT_SYMBOL(d_genocide);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 874607b..093fb54 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -432,8 +432,8 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
struct bio *bio;
/*
- * bio_alloc() is guaranteed to return a bio when called with
- * __GFP_RECLAIM and we request a valid number of vectors.
+ * bio_alloc() is guaranteed to return a bio when allowed to sleep and
+ * we request a valid number of vectors.
*/
bio = bio_alloc(GFP_KERNEL, nr_vecs);
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 5243989..a5e4a22 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -1037,6 +1037,7 @@ static void sctp_connect_to_sock(struct connection *con)
int result;
int addr_len;
struct socket *sock;
+ struct timeval tv = { .tv_sec = 5, .tv_usec = 0 };
if (con->nodeid == 0) {
log_print("attempt to connect sock 0 foiled");
@@ -1080,11 +1081,22 @@ static void sctp_connect_to_sock(struct connection *con)
log_print("connecting to %d", con->nodeid);
/* Turn off Nagle's algorithm */
- kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one,
+ kernel_setsockopt(sock, SOL_SCTP, SCTP_NODELAY, (char *)&one,
sizeof(one));
+ /*
+ * Make sock->ops->connect() function return in specified time,
+ * since O_NONBLOCK argument in connect() function does not work here,
+ * then, we should restore the default value of this attribute.
+ */
+ kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO, (char *)&tv,
+ sizeof(tv));
result = sock->ops->connect(sock, (struct sockaddr *)&daddr, addr_len,
- O_NONBLOCK);
+ 0);
+ memset(&tv, 0, sizeof(tv));
+ kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO, (char *)&tv,
+ sizeof(tv));
+
if (result == -EINPROGRESS)
result = 0;
if (result == 0)
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 846ca15..4dd842f7 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1997,6 +1997,16 @@ int ecryptfs_encrypt_and_encode_filename(
return rc;
}
+static bool is_dot_dotdot(const char *name, size_t name_size)
+{
+ if (name_size == 1 && name[0] == '.')
+ return true;
+ else if (name_size == 2 && name[0] == '.' && name[1] == '.')
+ return true;
+
+ return false;
+}
+
/**
* ecryptfs_decode_and_decrypt_filename - converts the encoded cipher text name to decoded plaintext
* @plaintext_name: The plaintext name
@@ -2021,13 +2031,21 @@ int ecryptfs_decode_and_decrypt_filename(char **plaintext_name,
size_t packet_size;
int rc = 0;
- if ((mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)
- && !(mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
- && (name_size > ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE)
- && (strncmp(name, ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX,
- ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE) == 0)) {
- const char *orig_name = name;
- size_t orig_name_size = name_size;
+ if ((mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) &&
+ !(mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)) {
+ if (is_dot_dotdot(name, name_size)) {
+ rc = ecryptfs_copy_filename(plaintext_name,
+ plaintext_name_size,
+ name, name_size);
+ goto out;
+ }
+
+ if (name_size <= ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE ||
+ strncmp(name, ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX,
+ ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE)) {
+ rc = -EINVAL;
+ goto out;
+ }
name += ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE;
name_size -= ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE;
@@ -2047,12 +2065,9 @@ int ecryptfs_decode_and_decrypt_filename(char **plaintext_name,
decoded_name,
decoded_name_size);
if (rc) {
- printk(KERN_INFO "%s: Could not parse tag 70 packet "
- "from filename; copying through filename "
- "as-is\n", __func__);
- rc = ecryptfs_copy_filename(plaintext_name,
- plaintext_name_size,
- orig_name, orig_name_size);
+ ecryptfs_printk(KERN_DEBUG,
+ "%s: Could not parse tag 70 packet from filename\n",
+ __func__);
goto out_free;
}
} else {
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index c74ed3c..b76a985 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -82,17 +82,28 @@ ecryptfs_filldir(struct dir_context *ctx, const char *lower_name,
buf->sb, lower_name,
lower_namelen);
if (rc) {
- printk(KERN_ERR "%s: Error attempting to decode and decrypt "
- "filename [%s]; rc = [%d]\n", __func__, lower_name,
- rc);
- goto out;
+ if (rc != -EINVAL) {
+ ecryptfs_printk(KERN_DEBUG,
+ "%s: Error attempting to decode and decrypt filename [%s]; rc = [%d]\n",
+ __func__, lower_name, rc);
+ return rc;
+ }
+
+ /* Mask -EINVAL errors as these are most likely due a plaintext
+ * filename present in the lower filesystem despite filename
+ * encryption being enabled. One unavoidable example would be
+ * the "lost+found" dentry in the root directory of an Ext4
+ * filesystem.
+ */
+ return 0;
}
+
buf->caller->pos = buf->ctx.pos;
rc = !dir_emit(buf->caller, name, name_size, ino, d_type);
kfree(name);
if (!rc)
buf->entries_written++;
-out:
+
return rc;
}
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 847904a..49121e5 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -283,8 +283,7 @@ ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
iget_failed(ecryptfs_inode);
goto out;
}
- unlock_new_inode(ecryptfs_inode);
- d_instantiate(ecryptfs_dentry, ecryptfs_inode);
+ d_instantiate_new(ecryptfs_dentry, ecryptfs_inode);
out:
return rc;
}
@@ -395,8 +394,7 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
mount_crypt_stat = &ecryptfs_superblock_to_private(
ecryptfs_dentry->d_sb)->mount_crypt_stat;
- if (mount_crypt_stat
- && (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)) {
+ if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) {
rc = ecryptfs_encrypt_and_encode_filename(
&encrypted_and_encoded_name, &len,
mount_crypt_stat, name, len);
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index c89a58cf..e74fe84 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -1880,7 +1880,7 @@ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat,
candidate_auth_tok = &auth_tok_list_item->auth_tok;
if (unlikely(ecryptfs_verbosity > 0)) {
ecryptfs_printk(KERN_DEBUG,
- "Considering cadidate auth tok:\n");
+ "Considering candidate auth tok:\n");
ecryptfs_dump_auth_tok(candidate_auth_tok);
}
rc = ecryptfs_get_auth_tok_sig(&candidate_auth_tok_sig,
diff --git a/fs/eventfd.c b/fs/eventfd.c
index 08d3bd6..61c9514 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -101,14 +101,20 @@ static int eventfd_release(struct inode *inode, struct file *file)
return 0;
}
-static __poll_t eventfd_poll(struct file *file, poll_table *wait)
+static struct wait_queue_head *
+eventfd_get_poll_head(struct file *file, __poll_t events)
+{
+ struct eventfd_ctx *ctx = file->private_data;
+
+ return &ctx->wqh;
+}
+
+static __poll_t eventfd_poll_mask(struct file *file, __poll_t eventmask)
{
struct eventfd_ctx *ctx = file->private_data;
__poll_t events = 0;
u64 count;
- poll_wait(file, &ctx->wqh, wait);
-
/*
* All writes to ctx->count occur within ctx->wqh.lock. This read
* can be done outside ctx->wqh.lock because we know that poll_wait
@@ -305,7 +311,8 @@ static const struct file_operations eventfd_fops = {
.show_fdinfo = eventfd_show_fdinfo,
#endif
.release = eventfd_release,
- .poll = eventfd_poll,
+ .get_poll_head = eventfd_get_poll_head,
+ .poll_mask = eventfd_poll_mask,
.read = eventfd_read,
.write = eventfd_write,
.llseek = noop_llseek,
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 602ca42..67db22f 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -884,8 +884,7 @@ static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt,
pt->_key = epi->event.events;
if (!is_file_epoll(epi->ffd.file))
- return epi->ffd.file->f_op->poll(epi->ffd.file, pt) &
- epi->event.events;
+ return vfs_poll(epi->ffd.file, pt) & epi->event.events;
ep = epi->ffd.file->private_data;
poll_wait(epi->ffd.file, &ep->poll_wait, pt);
@@ -2025,7 +2024,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
/* The target file descriptor must support poll */
error = -EPERM;
- if (!tf.file->f_op->poll)
+ if (!file_can_poll(tf.file))
goto error_tgt_fput;
/* Check if EPOLLWAKEUP is allowed */
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index 3c6a9c1..ddbf872 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -790,7 +790,7 @@ int ore_create(struct ore_io_state *ios)
for (i = 0; i < ios->oc->numdevs; i++) {
struct osd_request *or;
- or = osd_start_request(_ios_od(ios, i), GFP_KERNEL);
+ or = osd_start_request(_ios_od(ios, i));
if (unlikely(!or)) {
ORE_ERR("%s: osd_start_request failed\n", __func__);
ret = -ENOMEM;
@@ -815,7 +815,7 @@ int ore_remove(struct ore_io_state *ios)
for (i = 0; i < ios->oc->numdevs; i++) {
struct osd_request *or;
- or = osd_start_request(_ios_od(ios, i), GFP_KERNEL);
+ or = osd_start_request(_ios_od(ios, i));
if (unlikely(!or)) {
ORE_ERR("%s: osd_start_request failed\n", __func__);
ret = -ENOMEM;
@@ -847,7 +847,7 @@ static int _write_mirror(struct ore_io_state *ios, int cur_comp)
struct ore_per_dev_state *per_dev = &ios->per_dev[cur_comp];
struct osd_request *or;
- or = osd_start_request(_ios_od(ios, dev), GFP_KERNEL);
+ or = osd_start_request(_ios_od(ios, dev));
if (unlikely(!or)) {
ORE_ERR("%s: osd_start_request failed\n", __func__);
ret = -ENOMEM;
@@ -966,7 +966,7 @@ int _ore_read_mirror(struct ore_io_state *ios, unsigned cur_comp)
return 0; /* Just an empty slot */
first_dev = per_dev->dev + first_dev % ios->layout->mirrors_p1;
- or = osd_start_request(_ios_od(ios, first_dev), GFP_KERNEL);
+ or = osd_start_request(_ios_od(ios, first_dev));
if (unlikely(!or)) {
ORE_ERR("%s: osd_start_request failed\n", __func__);
return -ENOMEM;
@@ -1060,7 +1060,7 @@ static int _truncate_mirrors(struct ore_io_state *ios, unsigned cur_comp,
struct ore_per_dev_state *per_dev = &ios->per_dev[cur_comp];
struct osd_request *or;
- or = osd_start_request(_ios_od(ios, cur_comp), GFP_KERNEL);
+ or = osd_start_request(_ios_od(ios, cur_comp));
if (unlikely(!or)) {
ORE_ERR("%s: osd_start_request failed\n", __func__);
return -ENOMEM;
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 179cd5c..719a315 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -229,7 +229,7 @@ void exofs_make_credential(u8 cred_a[OSD_CAP_LEN], const struct osd_obj_id *obj)
static int exofs_read_kern(struct osd_dev *od, u8 *cred, struct osd_obj_id *obj,
u64 offset, void *p, unsigned length)
{
- struct osd_request *or = osd_start_request(od, GFP_KERNEL);
+ struct osd_request *or = osd_start_request(od);
/* struct osd_sense_info osi = {.key = 0};*/
int ret;
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 0964022..047c327 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -88,11 +88,11 @@ static ssize_t ext2_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
* The default page_lock and i_size verification done by non-DAX fault paths
* is sufficient because ext2 doesn't support hole punching.
*/
-static int ext2_dax_fault(struct vm_fault *vmf)
+static vm_fault_t ext2_dax_fault(struct vm_fault *vmf)
{
struct inode *inode = file_inode(vmf->vma->vm_file);
struct ext2_inode_info *ei = EXT2_I(inode);
- int ret;
+ vm_fault_t ret;
if (vmf->flags & FAULT_FLAG_WRITE) {
sb_start_pagefault(inode->i_sb);
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 1e01fab..7163590 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -1264,21 +1264,11 @@ static void __ext2_truncate_blocks(struct inode *inode, loff_t offset)
static void ext2_truncate_blocks(struct inode *inode, loff_t offset)
{
- /*
- * XXX: it seems like a bug here that we don't allow
- * IS_APPEND inode to have blocks-past-i_size trimmed off.
- * review and fix this.
- *
- * Also would be nice to be able to handle IO errors and such,
- * but that's probably too much to ask.
- */
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode)))
return;
if (ext2_inode_is_fast_symlink(inode))
return;
- if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
- return;
dax_sem_down_write(EXT2_I(inode));
__ext2_truncate_blocks(inode, offset);
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 55f7caa..152453a 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -41,8 +41,7 @@ static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
{
int err = ext2_add_link(dentry, inode);
if (!err) {
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
}
inode_dec_link_count(inode);
@@ -255,8 +254,7 @@ static int ext2_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
if (err)
goto out_fail;
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
out:
return err;
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index de16945..c09289a 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -961,8 +961,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
if (sbi->s_mount_opt & EXT2_MOUNT_DAX) {
- err = bdev_dax_supported(sb, blocksize);
- if (err) {
+ if (!bdev_dax_supported(sb->s_bdev, blocksize)) {
ext2_msg(sb, KERN_ERR,
"DAX unsupported by block device. Turning off DAX.");
sbi->s_mount_opt &= ~EXT2_MOUNT_DAX;
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index a33d8fb..b00481c 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -185,25 +185,15 @@ static int ext4_init_block_bitmap(struct super_block *sb,
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_fsblk_t start, tmp;
int flex_bg = 0;
- struct ext4_group_info *grp;
J_ASSERT_BH(bh, buffer_locked(bh));
/* If checksum is bad mark all blocks used to prevent allocation
* essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
- grp = ext4_get_group_info(sb, block_group);
- if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
- percpu_counter_sub(&sbi->s_freeclusters_counter,
- grp->bb_free);
- set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
- if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
- int count;
- count = ext4_free_inodes_count(sb, gdp);
- percpu_counter_sub(&sbi->s_freeinodes_counter,
- count);
- }
- set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
+ ext4_mark_group_bitmap_corrupted(sb, block_group,
+ EXT4_GROUP_INFO_BBITMAP_CORRUPT |
+ EXT4_GROUP_INFO_IBITMAP_CORRUPT);
return -EFSBADCRC;
}
memset(bh->b_data, 0, sb->s_blocksize);
@@ -321,6 +311,7 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_grpblk_t offset;
ext4_grpblk_t next_zero_bit;
+ ext4_grpblk_t max_bit = EXT4_CLUSTERS_PER_GROUP(sb);
ext4_fsblk_t blk;
ext4_fsblk_t group_first_block;
@@ -338,7 +329,7 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
/* check whether block bitmap block number is set */
blk = ext4_block_bitmap(sb, desc);
offset = blk - group_first_block;
- if (offset < 0 || EXT4_B2C(sbi, offset) >= sb->s_blocksize ||
+ if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit ||
!ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
/* bad block bitmap */
return blk;
@@ -346,7 +337,7 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
/* check whether the inode bitmap block number is set */
blk = ext4_inode_bitmap(sb, desc);
offset = blk - group_first_block;
- if (offset < 0 || EXT4_B2C(sbi, offset) >= sb->s_blocksize ||
+ if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit ||
!ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
/* bad block bitmap */
return blk;
@@ -354,8 +345,8 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
/* check whether the inode table block number is set */
blk = ext4_inode_table(sb, desc);
offset = blk - group_first_block;
- if (offset < 0 || EXT4_B2C(sbi, offset) >= sb->s_blocksize ||
- EXT4_B2C(sbi, offset + sbi->s_itb_per_group) >= sb->s_blocksize)
+ if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit ||
+ EXT4_B2C(sbi, offset + sbi->s_itb_per_group) >= max_bit)
return blk;
next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
EXT4_B2C(sbi, offset + sbi->s_itb_per_group),
@@ -374,7 +365,6 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
{
ext4_fsblk_t blk;
struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
- struct ext4_sb_info *sbi = EXT4_SB(sb);
if (buffer_verified(bh))
return 0;
@@ -386,10 +376,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
desc, bh))) {
ext4_unlock_group(sb, block_group);
ext4_error(sb, "bg %u: bad block bitmap checksum", block_group);
- if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
- percpu_counter_sub(&sbi->s_freeclusters_counter,
- grp->bb_free);
- set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+ ext4_mark_group_bitmap_corrupted(sb, block_group,
+ EXT4_GROUP_INFO_BBITMAP_CORRUPT);
return -EFSBADCRC;
}
blk = ext4_valid_block_bitmap(sb, desc, block_group, bh);
@@ -397,10 +385,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
ext4_unlock_group(sb, block_group);
ext4_error(sb, "bg %u: block %llu: invalid block bitmap",
block_group, blk);
- if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
- percpu_counter_sub(&sbi->s_freeclusters_counter,
- grp->bb_free);
- set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+ ext4_mark_group_bitmap_corrupted(sb, block_group,
+ EXT4_GROUP_INFO_BBITMAP_CORRUPT);
return -EFSCORRUPTED;
}
set_buffer_verified(bh);
@@ -435,6 +421,8 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
(bitmap_blk >= ext4_blocks_count(sbi->s_es))) {
ext4_error(sb, "Invalid block bitmap block %llu in "
"block_group %u", bitmap_blk, block_group);
+ ext4_mark_group_bitmap_corrupted(sb, block_group,
+ EXT4_GROUP_INFO_BBITMAP_CORRUPT);
return ERR_PTR(-EFSCORRUPTED);
}
bh = sb_getblk(sb, bitmap_blk);
@@ -513,6 +501,8 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group,
ext4_error(sb, "Cannot read block bitmap - "
"block_group = %u, block_bitmap = %llu",
block_group, (unsigned long long) bh->b_blocknr);
+ ext4_mark_group_bitmap_corrupted(sb, block_group,
+ EXT4_GROUP_INFO_BBITMAP_CORRUPT);
return -EIO;
}
clear_buffer_new(bh);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index a42e712..df95412 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2390,7 +2390,7 @@ extern int ext4_init_inode_table(struct super_block *sb,
extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
/* mballoc.c */
-extern const struct file_operations ext4_seq_mb_groups_fops;
+extern const struct seq_operations ext4_mb_seq_groups_ops;
extern long ext4_mb_stats;
extern long ext4_mb_max_to_scan;
extern int ext4_mb_init(struct super_block *);
@@ -2530,6 +2530,9 @@ extern int ext4_alloc_flex_bg_array(struct super_block *sb,
ext4_group_t ngroup);
extern const char *ext4_decode_error(struct super_block *sb, int errno,
char nbuf[16]);
+extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
+ ext4_group_t block_group,
+ unsigned int flags);
extern __printf(4, 5)
void __ext4_error(struct super_block *, const char *, unsigned int,
@@ -2857,6 +2860,10 @@ struct ext4_group_info {
#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT 1
#define EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT 2
#define EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT 3
+#define EXT4_GROUP_INFO_BBITMAP_CORRUPT \
+ (1 << EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT)
+#define EXT4_GROUP_INFO_IBITMAP_CORRUPT \
+ (1 << EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT)
#define EXT4_MB_GRP_NEED_INIT(grp) \
(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 0a73159..c969275 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -5329,8 +5329,9 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
stop = le32_to_cpu(extent->ee_block);
/*
- * In case of left shift, Don't start shifting extents until we make
- * sure the hole is big enough to accommodate the shift.
+ * For left shifts, make sure the hole on the left is big enough to
+ * accommodate the shift. For right shifts, make sure the last extent
+ * won't be shifted beyond EXT_MAX_BLOCKS.
*/
if (SHIFT == SHIFT_LEFT) {
path = ext4_find_extent(inode, start - 1, &path,
@@ -5350,9 +5351,14 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
if ((start == ex_start && shift > ex_start) ||
(shift > start - ex_end)) {
- ext4_ext_drop_refs(path);
- kfree(path);
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
+ }
+ } else {
+ if (shift > EXT_MAX_BLOCKS -
+ (stop + ext4_ext_get_actual_len(extent))) {
+ ret = -EINVAL;
+ goto out;
}
}
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 763ef18..c4e6fb1 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -162,8 +162,7 @@ int __init ext4_init_es(void)
void ext4_exit_es(void)
{
- if (ext4_es_cachep)
- kmem_cache_destroy(ext4_es_cachep);
+ kmem_cache_destroy(ext4_es_cachep);
}
void ext4_es_init_tree(struct ext4_es_tree *tree)
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index fb6f023..7f80233 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -277,10 +277,11 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
}
#ifdef CONFIG_FS_DAX
-static int ext4_dax_huge_fault(struct vm_fault *vmf,
+static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf,
enum page_entry_size pe_size)
{
- int result, error = 0;
+ int error = 0;
+ vm_fault_t result;
int retries = 0;
handle_t *handle = NULL;
struct inode *inode = file_inode(vmf->vma->vm_file);
@@ -335,7 +336,7 @@ static int ext4_dax_huge_fault(struct vm_fault *vmf,
return result;
}
-static int ext4_dax_fault(struct vm_fault *vmf)
+static vm_fault_t ext4_dax_fault(struct vm_fault *vmf)
{
return ext4_dax_huge_fault(vmf, PE_SIZE_PTE);
}
@@ -380,50 +381,64 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
return 0;
}
-static int ext4_file_open(struct inode * inode, struct file * filp)
+static int ext4_sample_last_mounted(struct super_block *sb,
+ struct vfsmount *mnt)
{
- struct super_block *sb = inode->i_sb;
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- struct vfsmount *mnt = filp->f_path.mnt;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
struct path path;
char buf[64], *cp;
+ handle_t *handle;
+ int err;
+
+ if (likely(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED))
+ return 0;
+
+ if (sb_rdonly(sb) || !sb_start_intwrite_trylock(sb))
+ return 0;
+
+ sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
+ /*
+ * Sample where the filesystem has been mounted and
+ * store it in the superblock for sysadmin convenience
+ * when trying to sort through large numbers of block
+ * devices or filesystem images.
+ */
+ memset(buf, 0, sizeof(buf));
+ path.mnt = mnt;
+ path.dentry = mnt->mnt_root;
+ cp = d_path(&path, buf, sizeof(buf));
+ err = 0;
+ if (IS_ERR(cp))
+ goto out;
+
+ handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
+ err = PTR_ERR(handle);
+ if (IS_ERR(handle))
+ goto out;
+ BUFFER_TRACE(sbi->s_sbh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, sbi->s_sbh);
+ if (err)
+ goto out_journal;
+ strlcpy(sbi->s_es->s_last_mounted, cp,
+ sizeof(sbi->s_es->s_last_mounted));
+ ext4_handle_dirty_super(handle, sb);
+out_journal:
+ ext4_journal_stop(handle);
+out:
+ sb_end_intwrite(sb);
+ return err;
+}
+
+static int ext4_file_open(struct inode * inode, struct file * filp)
+{
int ret;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
- if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
- !sb_rdonly(sb))) {
- sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
- /*
- * Sample where the filesystem has been mounted and
- * store it in the superblock for sysadmin convenience
- * when trying to sort through large numbers of block
- * devices or filesystem images.
- */
- memset(buf, 0, sizeof(buf));
- path.mnt = mnt;
- path.dentry = mnt->mnt_root;
- cp = d_path(&path, buf, sizeof(buf));
- if (!IS_ERR(cp)) {
- handle_t *handle;
- int err;
-
- handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
- if (IS_ERR(handle))
- return PTR_ERR(handle);
- BUFFER_TRACE(sbi->s_sbh, "get_write_access");
- err = ext4_journal_get_write_access(handle, sbi->s_sbh);
- if (err) {
- ext4_journal_stop(handle);
- return err;
- }
- strlcpy(sbi->s_es->s_last_mounted, cp,
- sizeof(sbi->s_es->s_last_mounted));
- ext4_handle_dirty_super(handle, sb);
- ext4_journal_stop(handle);
- }
- }
+ ret = ext4_sample_last_mounted(inode->i_sb, filp->f_path.mnt);
+ if (ret)
+ return ret;
ret = fscrypt_file_open(inode, filp);
if (ret)
diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c
index e871c4b..4b99e2db 100644
--- a/fs/ext4/fsmap.c
+++ b/fs/ext4/fsmap.c
@@ -402,8 +402,8 @@ static void ext4_getfsmap_free_fixed_metadata(struct list_head *meta_list)
}
/* Find all the fixed metadata in the filesystem. */
-int ext4_getfsmap_find_fixed_metadata(struct super_block *sb,
- struct list_head *meta_list)
+static int ext4_getfsmap_find_fixed_metadata(struct super_block *sb,
+ struct list_head *meta_list)
{
struct ext4_group_desc *gdp;
ext4_group_t agno;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index df92e3e..4d6e007 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -83,7 +83,6 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
{
ext4_fsblk_t blk;
struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
- struct ext4_sb_info *sbi = EXT4_SB(sb);
if (buffer_verified(bh))
return 0;
@@ -97,14 +96,8 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
ext4_unlock_group(sb, block_group);
ext4_error(sb, "Corrupt inode bitmap - block_group = %u, "
"inode_bitmap = %llu", block_group, blk);
- grp = ext4_get_group_info(sb, block_group);
- if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
- int count;
- count = ext4_free_inodes_count(sb, desc);
- percpu_counter_sub(&sbi->s_freeinodes_counter,
- count);
- }
- set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
+ ext4_mark_group_bitmap_corrupted(sb, block_group,
+ EXT4_GROUP_INFO_IBITMAP_CORRUPT);
return -EFSBADCRC;
}
set_buffer_verified(bh);
@@ -136,6 +129,8 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
(bitmap_blk >= ext4_blocks_count(sbi->s_es))) {
ext4_error(sb, "Invalid inode bitmap blk %llu in "
"block_group %u", bitmap_blk, block_group);
+ ext4_mark_group_bitmap_corrupted(sb, block_group,
+ EXT4_GROUP_INFO_IBITMAP_CORRUPT);
return ERR_PTR(-EFSCORRUPTED);
}
bh = sb_getblk(sb, bitmap_blk);
@@ -143,7 +138,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
ext4_error(sb, "Cannot read inode bitmap - "
"block_group = %u, inode_bitmap = %llu",
block_group, bitmap_blk);
- return ERR_PTR(-EIO);
+ return ERR_PTR(-ENOMEM);
}
if (bitmap_uptodate(bh))
goto verify;
@@ -190,6 +185,8 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
ext4_error(sb, "Cannot read inode bitmap - "
"block_group = %u, inode_bitmap = %llu",
block_group, bitmap_blk);
+ ext4_mark_group_bitmap_corrupted(sb, block_group,
+ EXT4_GROUP_INFO_IBITMAP_CORRUPT);
return ERR_PTR(-EIO);
}
@@ -337,13 +334,8 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
fatal = err;
} else {
ext4_error(sb, "bit already cleared for inode %lu", ino);
- if (gdp && !EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
- int count;
- count = ext4_free_inodes_count(sb, gdp);
- percpu_counter_sub(&sbi->s_freeinodes_counter,
- count);
- }
- set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
+ ext4_mark_group_bitmap_corrupted(sb, block_group,
+ EXT4_GROUP_INFO_IBITMAP_CORRUPT);
}
error_return:
@@ -914,6 +906,8 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
if (group == 0 && (ino + 1) < EXT4_FIRST_INO(sb)) {
ext4_error(sb, "reserved inode found cleared - "
"inode=%lu", ino + 1);
+ ext4_mark_group_bitmap_corrupted(sb, group,
+ EXT4_GROUP_INFO_IBITMAP_CORRUPT);
goto next_group;
}
@@ -1105,6 +1099,8 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
err = -EIO;
ext4_error(sb, "failed to insert inode %lu: doubly allocated?",
inode->i_ino);
+ ext4_mark_group_bitmap_corrupted(sb, group,
+ EXT4_GROUP_INFO_IBITMAP_CORRUPT);
goto out;
}
inode->i_generation = prandom_u32();
@@ -1206,11 +1202,8 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
- if (IS_ERR(bitmap_bh)) {
- ext4_error(sb, "inode bitmap error %ld for orphan %lu",
- ino, PTR_ERR(bitmap_bh));
+ if (IS_ERR(bitmap_bh))
return (struct inode *) bitmap_bh;
- }
/* Having the inode bit set should be a 100% indicator that this
* is a valid orphan (no e2fsck run on fs). Orphans also include
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index c32802c..bf7fa150 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -561,10 +561,16 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
unsigned epb = inode->i_sb->s_blocksize / sizeof(u32);
int i;
- /* Count number blocks in a subtree under 'partial' */
- count = 1;
- for (i = 0; partial + i != chain + depth - 1; i++)
- count *= epb;
+ /*
+ * Count number blocks in a subtree under 'partial'. At each
+ * level we count number of complete empty subtrees beyond
+ * current offset and then descend into the subtree only
+ * partially beyond current offset.
+ */
+ count = 0;
+ for (i = partial - chain + 1; i < depth; i++)
+ count = count * epb + (epb - offsets[i] - 1);
+ count++;
/* Fill in size of a hole we found */
map->m_pblk = 0;
map->m_len = min_t(unsigned int, map->m_len, count);
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 70cf4c7..285ed15 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -144,6 +144,12 @@ int ext4_find_inline_data_nolock(struct inode *inode)
goto out;
if (!is.s.not_found) {
+ if (is.s.here->e_value_inum) {
+ EXT4_ERROR_INODE(inode, "inline data xattr refers "
+ "to an external xattr inode");
+ error = -EFSCORRUPTED;
+ goto out;
+ }
EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here -
(void *)ext4_raw_inode(&is.iloc));
EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE +
@@ -1835,8 +1841,8 @@ int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap)
iomap->offset = 0;
iomap->length = min_t(loff_t, ext4_get_inline_size(inode),
i_size_read(inode));
- iomap->type = 0;
- iomap->flags = IOMAP_F_DATA_INLINE;
+ iomap->type = IOMAP_INLINE;
+ iomap->flags = 0;
out:
up_read(&EXT4_I(inode)->xattr_sem);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 1e50c5e..2ea07ef 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4298,28 +4298,28 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
EXT4_BLOCK_SIZE_BITS(sb);
stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
- /* If there are no blocks to remove, return now */
- if (first_block >= stop_block)
- goto out_stop;
+ /* If there are blocks to remove, do it */
+ if (stop_block > first_block) {
- down_write(&EXT4_I(inode)->i_data_sem);
- ext4_discard_preallocations(inode);
+ down_write(&EXT4_I(inode)->i_data_sem);
+ ext4_discard_preallocations(inode);
- ret = ext4_es_remove_extent(inode, first_block,
- stop_block - first_block);
- if (ret) {
+ ret = ext4_es_remove_extent(inode, first_block,
+ stop_block - first_block);
+ if (ret) {
+ up_write(&EXT4_I(inode)->i_data_sem);
+ goto out_stop;
+ }
+
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ ret = ext4_ext_remove_space(inode, first_block,
+ stop_block - 1);
+ else
+ ret = ext4_ind_remove_space(handle, inode, first_block,
+ stop_block);
+
up_write(&EXT4_I(inode)->i_data_sem);
- goto out_stop;
}
-
- if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
- ret = ext4_ext_remove_space(inode, first_block,
- stop_block - 1);
- else
- ret = ext4_ind_remove_space(handle, inode, first_block,
- stop_block);
-
- up_write(&EXT4_I(inode)->i_data_sem);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
@@ -4701,19 +4701,21 @@ static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode,
}
}
-static inline void ext4_iget_extra_inode(struct inode *inode,
+static inline int ext4_iget_extra_inode(struct inode *inode,
struct ext4_inode *raw_inode,
struct ext4_inode_info *ei)
{
__le32 *magic = (void *)raw_inode +
EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize;
+
if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize + sizeof(__le32) <=
EXT4_INODE_SIZE(inode->i_sb) &&
*magic == cpu_to_le32(EXT4_XATTR_MAGIC)) {
ext4_set_inode_state(inode, EXT4_STATE_XATTR);
- ext4_find_inline_data_nolock(inode);
+ return ext4_find_inline_data_nolock(inode);
} else
EXT4_I(inode)->i_inline_off = 0;
+ return 0;
}
int ext4_get_projid(struct inode *inode, kprojid_t *projid)
@@ -4724,6 +4726,26 @@ int ext4_get_projid(struct inode *inode, kprojid_t *projid)
return 0;
}
+/*
+ * ext4 has self-managed i_version for ea inodes, it stores the lower 32bit of
+ * refcount in i_version, so use raw values if inode has EXT4_EA_INODE_FL flag
+ * set.
+ */
+static inline void ext4_inode_set_iversion_queried(struct inode *inode, u64 val)
+{
+ if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
+ inode_set_iversion_raw(inode, val);
+ else
+ inode_set_iversion_queried(inode, val);
+}
+static inline u64 ext4_inode_peek_iversion(const struct inode *inode)
+{
+ if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
+ return inode_peek_iversion_raw(inode);
+ else
+ return inode_peek_iversion(inode);
+}
+
struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
{
struct ext4_iloc iloc;
@@ -4893,7 +4915,9 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
ei->i_extra_isize = sizeof(struct ext4_inode) -
EXT4_GOOD_OLD_INODE_SIZE;
} else {
- ext4_iget_extra_inode(inode, raw_inode, ei);
+ ret = ext4_iget_extra_inode(inode, raw_inode, ei);
+ if (ret)
+ goto bad_inode;
}
}
@@ -4910,7 +4934,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
ivers |=
(__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
}
- inode_set_iversion_queried(inode, ivers);
+ ext4_inode_set_iversion_queried(inode, ivers);
}
ret = 0;
@@ -4945,6 +4969,13 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
inode->i_op = &ext4_dir_inode_operations;
inode->i_fop = &ext4_dir_operations;
} else if (S_ISLNK(inode->i_mode)) {
+ /* VFS does not allow setting these so must be corruption */
+ if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
+ EXT4_ERROR_INODE(inode,
+ "immutable or append flags not allowed on symlinks");
+ ret = -EFSCORRUPTED;
+ goto bad_inode;
+ }
if (ext4_encrypted_inode(inode)) {
inode->i_op = &ext4_encrypted_symlink_inode_operations;
ext4_set_aops(inode);
@@ -5196,7 +5227,7 @@ static int ext4_do_update_inode(handle_t *handle,
}
if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
- u64 ivers = inode_peek_iversion(inode);
+ u64 ivers = ext4_inode_peek_iversion(inode);
raw_inode->i_disk_version = cpu_to_le32(ivers);
if (ei->i_extra_isize) {
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 769a627..6eae2b9 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -470,6 +470,8 @@ static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b,
"freeing block already freed "
"(bit %u)",
first + i);
+ ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+ EXT4_GROUP_INFO_BBITMAP_CORRUPT);
}
mb_clear_bit(first + i, e4b->bd_info->bb_bitmap);
}
@@ -747,10 +749,8 @@ void ext4_mb_generate_buddy(struct super_block *sb,
* corrupt and update bb_free using bitmap value
*/
grp->bb_free = free;
- if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
- percpu_counter_sub(&sbi->s_freeclusters_counter,
- grp->bb_free);
- set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+ ext4_mark_group_bitmap_corrupted(sb, group,
+ EXT4_GROUP_INFO_BBITMAP_CORRUPT);
}
mb_set_largest_free_order(sb, grp);
@@ -1454,12 +1454,8 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
"freeing already freed block "
"(bit %u); block bitmap corrupt.",
block);
- if (!EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))
- percpu_counter_sub(&sbi->s_freeclusters_counter,
- e4b->bd_info->bb_free);
- /* Mark the block group as corrupt. */
- set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
- &e4b->bd_info->bb_state);
+ ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+ EXT4_GROUP_INFO_BBITMAP_CORRUPT);
mb_regenerate_buddy(e4b);
goto done;
}
@@ -1956,6 +1952,8 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
"%d free clusters as per "
"group info. But bitmap says 0",
free);
+ ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+ EXT4_GROUP_INFO_BBITMAP_CORRUPT);
break;
}
@@ -1966,6 +1964,8 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
"%d free clusters as per "
"group info. But got %d blocks",
free, ex.fe_len);
+ ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+ EXT4_GROUP_INFO_BBITMAP_CORRUPT);
/*
* The number of free blocks differs. This mostly
* indicate that the bitmap is corrupt. So exit
@@ -2254,7 +2254,7 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos)
{
- struct super_block *sb = seq->private;
+ struct super_block *sb = PDE_DATA(file_inode(seq->file));
ext4_group_t group;
if (*pos < 0 || *pos >= ext4_get_groups_count(sb))
@@ -2265,7 +2265,7 @@ static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos)
static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct super_block *sb = seq->private;
+ struct super_block *sb = PDE_DATA(file_inode(seq->file));
ext4_group_t group;
++*pos;
@@ -2277,7 +2277,7 @@ static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos)
static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
{
- struct super_block *sb = seq->private;
+ struct super_block *sb = PDE_DATA(file_inode(seq->file));
ext4_group_t group = (ext4_group_t) ((unsigned long) v);
int i;
int err, buddy_loaded = 0;
@@ -2330,34 +2330,13 @@ static void ext4_mb_seq_groups_stop(struct seq_file *seq, void *v)
{
}
-static const struct seq_operations ext4_mb_seq_groups_ops = {
+const struct seq_operations ext4_mb_seq_groups_ops = {
.start = ext4_mb_seq_groups_start,
.next = ext4_mb_seq_groups_next,
.stop = ext4_mb_seq_groups_stop,
.show = ext4_mb_seq_groups_show,
};
-static int ext4_mb_seq_groups_open(struct inode *inode, struct file *file)
-{
- struct super_block *sb = PDE_DATA(inode);
- int rc;
-
- rc = seq_open(file, &ext4_mb_seq_groups_ops);
- if (rc == 0) {
- struct seq_file *m = file->private_data;
- m->private = sb;
- }
- return rc;
-
-}
-
-const struct file_operations ext4_seq_mb_groups_fops = {
- .open = ext4_mb_seq_groups_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static struct kmem_cache *get_groupinfo_cache(int blocksize_bits)
{
int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE;
@@ -2537,8 +2516,7 @@ static void ext4_groupinfo_destroy_slabs(void)
int i;
for (i = 0; i < NR_GRPINFO_CACHES; i++) {
- if (ext4_groupinfo_caches[i])
- kmem_cache_destroy(ext4_groupinfo_caches[i]);
+ kmem_cache_destroy(ext4_groupinfo_caches[i]);
ext4_groupinfo_caches[i] = NULL;
}
}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index b1f21e3..4a09063 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2411,8 +2411,7 @@ static int ext4_add_nondir(handle_t *handle,
int err = ext4_add_entry(handle, dentry, inode);
if (!err) {
ext4_mark_inode_dirty(handle, inode);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
}
drop_nlink(inode);
@@ -2651,8 +2650,7 @@ static int ext4_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
err = ext4_mark_inode_dirty(handle, dir);
if (err)
goto out_clear_inode;
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
if (IS_DIRSYNC(dir))
ext4_handle_sync(handle);
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index b6bec27..d792b76 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1933,7 +1933,7 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
return 0;
n_group = ext4_get_group_number(sb, n_blocks_count - 1);
- if (n_group > (0xFFFFFFFFUL / EXT4_INODES_PER_GROUP(sb))) {
+ if (n_group >= (0xFFFFFFFFUL / EXT4_INODES_PER_GROUP(sb))) {
ext4_warning(sb, "resize would cause inodes_count overflow");
return -EINVAL;
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 185f7e6..00fe75a 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -763,6 +763,36 @@ __acquires(bitlock)
return;
}
+void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
+ ext4_group_t group,
+ unsigned int flags)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+ struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
+
+ if ((flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) &&
+ !EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) {
+ percpu_counter_sub(&sbi->s_freeclusters_counter,
+ grp->bb_free);
+ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
+ &grp->bb_state);
+ }
+
+ if ((flags & EXT4_GROUP_INFO_IBITMAP_CORRUPT) &&
+ !EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+ if (gdp) {
+ int count;
+
+ count = ext4_free_inodes_count(sb, gdp);
+ percpu_counter_sub(&sbi->s_freeinodes_counter,
+ count);
+ }
+ set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT,
+ &grp->bb_state);
+ }
+}
+
void ext4_update_dynamic_rev(struct super_block *sb)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
@@ -1237,19 +1267,13 @@ static bool ext4_dummy_context(struct inode *inode)
return DUMMY_ENCRYPTION_ENABLED(EXT4_SB(inode->i_sb));
}
-static unsigned ext4_max_namelen(struct inode *inode)
-{
- return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize :
- EXT4_NAME_LEN;
-}
-
static const struct fscrypt_operations ext4_cryptops = {
.key_prefix = "ext4:",
.get_context = ext4_get_context,
.set_context = ext4_set_context,
.dummy_context = ext4_dummy_context,
.empty_dir = ext4_empty_dir,
- .max_namelen = ext4_max_namelen,
+ .max_namelen = EXT4_NAME_LEN,
};
#endif
@@ -2116,12 +2140,12 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
int read_only)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- int res = 0;
+ int err = 0;
if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) {
ext4_msg(sb, KERN_ERR, "revision level too high, "
"forcing read-only mode");
- res = SB_RDONLY;
+ err = -EROFS;
}
if (read_only)
goto done;
@@ -2154,7 +2178,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
if (sbi->s_journal)
ext4_set_feature_journal_needs_recovery(sb);
- ext4_commit_super(sb, 1);
+ err = ext4_commit_super(sb, 1);
done:
if (test_opt(sb, DEBUG))
printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
@@ -2166,7 +2190,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
sbi->s_mount_opt, sbi->s_mount_opt2);
cleancache_init_fs(sb);
- return res;
+ return err;
}
int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup)
@@ -3732,8 +3756,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
" that may contain inline data");
sbi->s_mount_opt &= ~EXT4_MOUNT_DAX;
}
- err = bdev_dax_supported(sb, blocksize);
- if (err) {
+ if (!bdev_dax_supported(sb->s_bdev, blocksize)) {
ext4_msg(sb, KERN_ERR,
"DAX unsupported by block device. Turning off DAX.");
sbi->s_mount_opt &= ~EXT4_MOUNT_DAX;
@@ -4224,8 +4247,12 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount4;
}
- if (ext4_setup_super(sb, es, sb_rdonly(sb)))
+ ret = ext4_setup_super(sb, es, sb_rdonly(sb));
+ if (ret == -EROFS) {
sb->s_flags |= SB_RDONLY;
+ ret = 0;
+ } else if (ret)
+ goto failed_mount4a;
/* determine the minimum size of new large inodes, if present */
if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE &&
@@ -4760,11 +4787,7 @@ static int ext4_commit_super(struct super_block *sb, int sync)
unlock_buffer(sbh);
error = __sync_dirty_buffer(sbh,
REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0));
- if (error)
- return error;
-
- error = buffer_write_io_error(sbh);
- if (error) {
+ if (buffer_write_io_error(sbh)) {
ext4_msg(sb, KERN_ERR, "I/O error while writing "
"superblock");
clear_buffer_write_io_error(sbh);
@@ -5165,8 +5188,12 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
if (sbi->s_journal)
ext4_clear_journal_err(sb, es);
sbi->s_mount_state = le16_to_cpu(es->s_state);
- if (!ext4_setup_super(sb, es, 0))
- sb->s_flags &= ~SB_RDONLY;
+
+ err = ext4_setup_super(sb, es, 0);
+ if (err)
+ goto restore_opts;
+
+ sb->s_flags &= ~SB_RDONLY;
if (ext4_has_feature_mmp(sb))
if (ext4_multi_mount_protect(sb,
le64_to_cpu(es->s_mmp_block))) {
@@ -5190,8 +5217,11 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
}
ext4_setup_system_zone(sb);
- if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY))
- ext4_commit_super(sb, 1);
+ if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) {
+ err = ext4_commit_super(sb, 1);
+ if (err)
+ goto restore_opts;
+ }
#ifdef CONFIG_QUOTA
/* Release old quota file names */
@@ -5252,7 +5282,8 @@ static int ext4_statfs_project(struct super_block *sb,
dquot->dq_dqb.dqb_bsoftlimit :
dquot->dq_dqb.dqb_bhardlimit) >> sb->s_blocksize_bits;
if (limit && buf->f_blocks > limit) {
- curblock = dquot->dq_dqb.dqb_curspace >> sb->s_blocksize_bits;
+ curblock = (dquot->dq_dqb.dqb_curspace +
+ dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits;
buf->f_blocks = limit;
buf->f_bfree = buf->f_bavail =
(buf->f_blocks > curblock) ?
@@ -5886,5 +5917,6 @@ static void __exit ext4_exit_fs(void)
MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
MODULE_DESCRIPTION("Fourth Extended Filesystem");
MODULE_LICENSE("GPL");
+MODULE_SOFTDEP("pre: crc32c");
module_init(ext4_init_fs)
module_exit(ext4_exit_fs)
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 9ebd26c..f34da0b 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -346,39 +346,9 @@ static struct kobject *ext4_root;
static struct kobject *ext4_feat;
-#define PROC_FILE_SHOW_DEFN(name) \
-static int name##_open(struct inode *inode, struct file *file) \
-{ \
- return single_open(file, ext4_seq_##name##_show, PDE_DATA(inode)); \
-} \
-\
-static const struct file_operations ext4_seq_##name##_fops = { \
- .open = name##_open, \
- .read = seq_read, \
- .llseek = seq_lseek, \
- .release = single_release, \
-}
-
-#define PROC_FILE_LIST(name) \
- { __stringify(name), &ext4_seq_##name##_fops }
-
-PROC_FILE_SHOW_DEFN(es_shrinker_info);
-PROC_FILE_SHOW_DEFN(options);
-
-static const struct ext4_proc_files {
- const char *name;
- const struct file_operations *fops;
-} proc_files[] = {
- PROC_FILE_LIST(options),
- PROC_FILE_LIST(es_shrinker_info),
- PROC_FILE_LIST(mb_groups),
- { NULL, NULL },
-};
-
int ext4_register_sysfs(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- const struct ext4_proc_files *p;
int err;
init_completion(&sbi->s_kobj_unregister);
@@ -392,11 +362,14 @@ int ext4_register_sysfs(struct super_block *sb)
if (ext4_proc_root)
sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root);
-
if (sbi->s_proc) {
- for (p = proc_files; p->name; p++)
- proc_create_data(p->name, S_IRUGO, sbi->s_proc,
- p->fops, sb);
+ proc_create_single_data("options", S_IRUGO, sbi->s_proc,
+ ext4_seq_options_show, sb);
+ proc_create_single_data("es_shrinker_info", S_IRUGO,
+ sbi->s_proc, ext4_seq_es_shrinker_info_show,
+ sb);
+ proc_create_seq_data("mb_groups", S_IRUGO, sbi->s_proc,
+ &ext4_mb_seq_groups_ops, sb);
}
return 0;
}
@@ -404,13 +377,9 @@ int ext4_register_sysfs(struct super_block *sb)
void ext4_unregister_sysfs(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- const struct ext4_proc_files *p;
- if (sbi->s_proc) {
- for (p = proc_files; p->name; p++)
- remove_proc_entry(p->name, sbi->s_proc);
- remove_proc_entry(sb->s_id, ext4_proc_root);
- }
+ if (sbi->s_proc)
+ remove_proc_subtree(sb->s_id, ext4_proc_root);
kobject_del(&sbi->s_kobj);
}
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 499cb4b..fc4ced5 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1688,7 +1688,7 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
/* No failures allowed past this point. */
- if (!s->not_found && here->e_value_offs) {
+ if (!s->not_found && here->e_value_size && here->e_value_offs) {
/* Remove the old value. */
void *first_val = s->base + min_offs;
size_t offs = le16_to_cpu(here->e_value_offs);
diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c
index 629001b..197a9d8 100644
--- a/fs/ext4/xattr_security.c
+++ b/fs/ext4/xattr_security.c
@@ -43,7 +43,7 @@ ext4_initxattrs(struct inode *inode, const struct xattr *xattr_array,
err = ext4_xattr_set_handle(handle, inode,
EXT4_XATTR_INDEX_SECURITY,
xattr->name, xattr->value,
- xattr->value_len, 0);
+ xattr->value_len, XATTR_CREATE);
if (err < 0)
break;
}
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index d5098ef..75e37fd 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -294,8 +294,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
alloc_nid_done(sbi, ino);
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
@@ -597,8 +596,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
err = page_symlink(inode, disk_link.name, disk_link.len);
err_out:
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
/*
* Let's flush symlink data in order to avoid broken symlink as much as
@@ -661,8 +659,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
alloc_nid_done(sbi, inode->i_ino);
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
@@ -713,8 +710,7 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
alloc_nid_done(sbi, inode->i_ino);
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 42d564c..970ae27 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1930,19 +1930,13 @@ static bool f2fs_dummy_context(struct inode *inode)
return DUMMY_ENCRYPTION_ENABLED(F2FS_I_SB(inode));
}
-static unsigned f2fs_max_namelen(struct inode *inode)
-{
- return S_ISLNK(inode->i_mode) ?
- inode->i_sb->s_blocksize : F2FS_NAME_LEN;
-}
-
static const struct fscrypt_operations f2fs_cryptops = {
.key_prefix = "f2fs:",
.get_context = f2fs_get_context,
.set_context = f2fs_set_context,
.dummy_context = f2fs_dummy_context,
.empty_dir = f2fs_empty_dir,
- .max_namelen = f2fs_max_namelen,
+ .max_namelen = F2FS_NAME_LEN,
};
#endif
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index f33a56d..4b47ca6 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -572,23 +572,6 @@ static int iostat_info_seq_show(struct seq_file *seq, void *offset)
return 0;
}
-#define F2FS_PROC_FILE_DEF(_name) \
-static int _name##_open_fs(struct inode *inode, struct file *file) \
-{ \
- return single_open(file, _name##_seq_show, PDE_DATA(inode)); \
-} \
- \
-static const struct file_operations f2fs_seq_##_name##_fops = { \
- .open = _name##_open_fs, \
- .read = seq_read, \
- .llseek = seq_lseek, \
- .release = single_release, \
-};
-
-F2FS_PROC_FILE_DEF(segment_info);
-F2FS_PROC_FILE_DEF(segment_bits);
-F2FS_PROC_FILE_DEF(iostat_info);
-
int __init f2fs_init_sysfs(void)
{
int ret;
@@ -632,12 +615,12 @@ int f2fs_register_sysfs(struct f2fs_sb_info *sbi)
sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
if (sbi->s_proc) {
- proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
- &f2fs_seq_segment_info_fops, sb);
- proc_create_data("segment_bits", S_IRUGO, sbi->s_proc,
- &f2fs_seq_segment_bits_fops, sb);
- proc_create_data("iostat_info", S_IRUGO, sbi->s_proc,
- &f2fs_seq_iostat_info_fops, sb);
+ proc_create_single_data("segment_info", S_IRUGO, sbi->s_proc,
+ segment_info_seq_show, sb);
+ proc_create_single_data("segment_bits", S_IRUGO, sbi->s_proc,
+ segment_bits_seq_show, sb);
+ proc_create_single_data("iostat_info", S_IRUGO, sbi->s_proc,
+ iostat_info_seq_show, sb);
}
return 0;
}
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index 582ca73..484ce67 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -314,10 +314,6 @@ static int msdos_rmdir(struct inode *dir, struct dentry *dentry)
int err;
mutex_lock(&MSDOS_SB(sb)->s_lock);
- /*
- * Check whether the directory is not in use, then check
- * whether it is empty.
- */
err = fat_dir_empty(inode);
if (err)
goto out;
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index 2649759..4f4362d 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -697,15 +697,6 @@ static int vfat_find(struct inode *dir, const struct qstr *qname,
return fat_search_long(dir, qname->name, len, sinfo);
}
-/*
- * (nfsd's) anonymous disconnected dentry?
- * NOTE: !IS_ROOT() is not anonymous (I.e. d_splice_alias() did the job).
- */
-static int vfat_d_anon_disconn(struct dentry *dentry)
-{
- return IS_ROOT(dentry) && (dentry->d_flags & DCACHE_DISCONNECTED);
-}
-
static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
@@ -738,8 +729,7 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
* Checking "alias->d_parent == dentry->d_parent" to make sure
* FS is not corrupted (especially double linked dir).
*/
- if (alias && alias->d_parent == dentry->d_parent &&
- !vfat_d_anon_disconn(alias)) {
+ if (alias && alias->d_parent == dentry->d_parent) {
/*
* This inode has non anonymous-DCACHE_DISCONNECTED
* dentry. This means, the user did ->lookup() by an
@@ -747,7 +737,6 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
*
* Switch to new one for reason of locality if possible.
*/
- BUG_ON(d_unhashed(alias));
if (!S_ISDIR(inode->i_mode))
d_move(alias, dentry);
iput(inode);
diff --git a/fs/fcntl.c b/fs/fcntl.c
index d737ff0..c421694 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -871,9 +871,9 @@ int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp)
if (fa->fa_file != filp)
continue;
- spin_lock_irq(&fa->fa_lock);
+ write_lock_irq(&fa->fa_lock);
fa->fa_file = NULL;
- spin_unlock_irq(&fa->fa_lock);
+ write_unlock_irq(&fa->fa_lock);
*fp = fa->fa_next;
call_rcu(&fa->fa_rcu, fasync_free_rcu);
@@ -918,13 +918,13 @@ struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasy
if (fa->fa_file != filp)
continue;
- spin_lock_irq(&fa->fa_lock);
+ write_lock_irq(&fa->fa_lock);
fa->fa_fd = fd;
- spin_unlock_irq(&fa->fa_lock);
+ write_unlock_irq(&fa->fa_lock);
goto out;
}
- spin_lock_init(&new->fa_lock);
+ rwlock_init(&new->fa_lock);
new->magic = FASYNC_MAGIC;
new->fa_file = filp;
new->fa_fd = fd;
@@ -987,14 +987,13 @@ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band)
{
while (fa) {
struct fown_struct *fown;
- unsigned long flags;
if (fa->magic != FASYNC_MAGIC) {
printk(KERN_ERR "kill_fasync: bad magic number in "
"fasync_struct!\n");
return;
}
- spin_lock_irqsave(&fa->fa_lock, flags);
+ read_lock(&fa->fa_lock);
if (fa->fa_file) {
fown = &fa->fa_file->f_owner;
/* Don't send SIGURG to processes which have not set a
@@ -1003,7 +1002,7 @@ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band)
if (!(sig == SIGURG && fown->signum == 0))
send_sigio(fown, fa->fa_fd, band);
}
- spin_unlock_irqrestore(&fa->fa_lock, flags);
+ read_unlock(&fa->fa_lock);
fa = rcu_dereference(fa->fa_next);
}
}
diff --git a/fs/filesystems.c b/fs/filesystems.c
index f2728a4..b03f57b 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -238,21 +238,9 @@ static int filesystems_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int filesystems_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, filesystems_proc_show, NULL);
-}
-
-static const struct file_operations filesystems_proc_fops = {
- .open = filesystems_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __init proc_filesystems_init(void)
{
- proc_create("filesystems", 0, NULL, &filesystems_proc_fops);
+ proc_create_single("filesystems", 0, NULL, filesystems_proc_show);
return 0;
}
module_init(proc_filesystems_init);
diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c
index ce4785f..a514256 100644
--- a/fs/freevxfs/vxfs_lookup.c
+++ b/fs/freevxfs/vxfs_lookup.c
@@ -193,13 +193,9 @@ vxfs_lookup(struct inode *dip, struct dentry *dp, unsigned int flags)
return ERR_PTR(-ENAMETOOLONG);
ino = vxfs_inode_by_name(dip, dp);
- if (ino) {
+ if (ino)
ip = vxfs_iget(dip->i_sb, ino);
- if (IS_ERR(ip))
- return ERR_CAST(ip);
- }
- d_add(dp, ip);
- return NULL;
+ return d_splice_alias(ip, dp);
}
/**
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 4b12ba7..471d863 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -745,11 +745,12 @@ int inode_congested(struct inode *inode, int cong_bits)
*/
if (inode && inode_to_wb_is_valid(inode)) {
struct bdi_writeback *wb;
- bool locked, congested;
+ struct wb_lock_cookie lock_cookie = {};
+ bool congested;
- wb = unlocked_inode_to_wb_begin(inode, &locked);
+ wb = unlocked_inode_to_wb_begin(inode, &lock_cookie);
congested = wb_congested(wb, cong_bits);
- unlocked_inode_to_wb_end(inode, locked);
+ unlocked_inode_to_wb_end(inode, &lock_cookie);
return congested;
}
@@ -1960,7 +1961,7 @@ void wb_workfn(struct work_struct *work)
}
if (!list_empty(&wb->work_list))
- mod_delayed_work(bdi_wq, &wb->dwork, 0);
+ wb_wakeup(wb);
else if (wb_has_dirty_io(wb) && dirty_writeback_interval)
wb_wakeup_delayed(wb);
diff --git a/fs/fscache/histogram.c b/fs/fscache/histogram.c
index 15a3d04..9a13e9e 100644
--- a/fs/fscache/histogram.c
+++ b/fs/fscache/histogram.c
@@ -83,24 +83,9 @@ static void fscache_histogram_stop(struct seq_file *m, void *v)
{
}
-static const struct seq_operations fscache_histogram_ops = {
+const struct seq_operations fscache_histogram_ops = {
.start = fscache_histogram_start,
.stop = fscache_histogram_stop,
.next = fscache_histogram_next,
.show = fscache_histogram_show,
};
-
-/*
- * open "/proc/fs/fscache/histogram" to provide latency data
- */
-static int fscache_histogram_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &fscache_histogram_ops);
-}
-
-const struct file_operations fscache_histogram_fops = {
- .open = fscache_histogram_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
index 500650f..f83328a 100644
--- a/fs/fscache/internal.h
+++ b/fs/fscache/internal.h
@@ -31,6 +31,7 @@
#include <linux/fscache-cache.h>
#include <trace/events/fscache.h>
#include <linux/sched.h>
+#include <linux/seq_file.h>
#define FSCACHE_MIN_THREADS 4
#define FSCACHE_MAX_THREADS 32
@@ -84,7 +85,7 @@ static inline void fscache_hist(atomic_t histogram[], unsigned long start_jif)
atomic_inc(&histogram[jif]);
}
-extern const struct file_operations fscache_histogram_fops;
+extern const struct seq_operations fscache_histogram_ops;
#else
#define fscache_hist(hist, start_jif) do {} while (0)
@@ -294,7 +295,7 @@ static inline void fscache_stat_d(atomic_t *stat)
#define __fscache_stat(stat) (stat)
-extern const struct file_operations fscache_stats_fops;
+int fscache_stats_show(struct seq_file *m, void *v);
#else
#define __fscache_stat(stat) (NULL)
diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c
index 1d9e495..49a8c90 100644
--- a/fs/fscache/proc.c
+++ b/fs/fscache/proc.c
@@ -26,14 +26,14 @@ int __init fscache_proc_init(void)
goto error_dir;
#ifdef CONFIG_FSCACHE_STATS
- if (!proc_create("fs/fscache/stats", S_IFREG | 0444, NULL,
- &fscache_stats_fops))
+ if (!proc_create_single("fs/fscache/stats", S_IFREG | 0444, NULL,
+ fscache_stats_show))
goto error_stats;
#endif
#ifdef CONFIG_FSCACHE_HISTOGRAM
- if (!proc_create("fs/fscache/histogram", S_IFREG | 0444, NULL,
- &fscache_histogram_fops))
+ if (!proc_create_seq("fs/fscache/histogram", S_IFREG | 0444, NULL,
+ &fscache_histogram_ops))
goto error_histogram;
#endif
diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
index fcc8c2f..00564a1 100644
--- a/fs/fscache/stats.c
+++ b/fs/fscache/stats.c
@@ -138,7 +138,7 @@ atomic_t fscache_n_cache_culled_objects;
/*
* display the general statistics
*/
-static int fscache_stats_show(struct seq_file *m, void *v)
+int fscache_stats_show(struct seq_file *m, void *v)
{
seq_puts(m, "FS-Cache statistics\n");
@@ -284,18 +284,3 @@ static int fscache_stats_show(struct seq_file *m, void *v)
atomic_read(&fscache_n_cache_culled_objects));
return 0;
}
-
-/*
- * open "/proc/fs/fscache/stats" allowing provision of a statistical summary
- */
-static int fscache_stats_open(struct inode *inode, struct file *file)
-{
- return single_open(file, fscache_stats_show, NULL);
-}
-
-const struct file_operations fscache_stats_fops = {
- .open = fscache_stats_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index f587165..35f5ee2 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -54,8 +54,7 @@ static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
continue;
if (start >= to)
break;
- if (gfs2_is_jdata(ip))
- set_buffer_uptodate(bh);
+ set_buffer_uptodate(bh);
gfs2_trans_add_data(ip->i_gl, bh);
}
}
@@ -747,18 +746,21 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
put_page(page);
gfs2_trans_end(sdp);
- if (pos + len > ip->i_inode.i_size)
- gfs2_trim_blocks(&ip->i_inode);
- goto out_trans_fail;
+ if (alloc_required) {
+ gfs2_inplace_release(ip);
+ if (pos + len > ip->i_inode.i_size)
+ gfs2_trim_blocks(&ip->i_inode);
+ }
+ goto out_qunlock;
out_endtrans:
gfs2_trans_end(sdp);
out_trans_fail:
- if (alloc_required) {
+ if (alloc_required)
gfs2_inplace_release(ip);
out_qunlock:
+ if (alloc_required)
gfs2_quota_unlock(ip);
- }
out_unlock:
if (&ip->i_inode == sdp->sd_rindex) {
gfs2_glock_dq(&m_ip->i_gh);
@@ -814,7 +816,6 @@ static void adjust_fs_space(struct inode *inode)
* @inode: The inode
* @dibh: The buffer_head containing the on-disk inode
* @pos: The file position
- * @len: The length of the write
* @copied: How much was actually copied by the VFS
* @page: The page
*
@@ -824,17 +825,15 @@ static void adjust_fs_space(struct inode *inode)
* Returns: errno
*/
static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
- loff_t pos, unsigned len, unsigned copied,
+ loff_t pos, unsigned copied,
struct page *page)
{
struct gfs2_inode *ip = GFS2_I(inode);
- struct gfs2_sbd *sdp = GFS2_SB(inode);
- struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
u64 to = pos + copied;
void *kaddr;
unsigned char *buf = dibh->b_data + sizeof(struct gfs2_dinode);
- BUG_ON(pos + len > gfs2_max_stuffed_size(ip));
+ BUG_ON(pos + copied > gfs2_max_stuffed_size(ip));
kaddr = kmap_atomic(page);
memcpy(buf + pos, kaddr + pos, copied);
@@ -850,20 +849,6 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
i_size_write(inode, to);
mark_inode_dirty(inode);
}
-
- if (inode == sdp->sd_rindex) {
- adjust_fs_space(inode);
- sdp->sd_rindex_uptodate = 0;
- }
-
- brelse(dibh);
- gfs2_trans_end(sdp);
- if (inode == sdp->sd_rindex) {
- gfs2_glock_dq(&m_ip->i_gh);
- gfs2_holder_uninit(&m_ip->i_gh);
- }
- gfs2_glock_dq(&ip->i_gh);
- gfs2_holder_uninit(&ip->i_gh);
return copied;
}
@@ -877,9 +862,8 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
* @page: The page that has been written
* @fsdata: The fsdata (unused in GFS2)
*
- * The main write_end function for GFS2. We have a separate one for
- * stuffed files as they are slightly different, otherwise we just
- * put our locking around the VFS provided functions.
+ * The main write_end function for GFS2. We just put our locking around the VFS
+ * provided functions.
*
* Returns: errno
*/
@@ -900,32 +884,39 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
BUG_ON(gfs2_glock_is_locked_by_me(ip->i_gl) == NULL);
ret = gfs2_meta_inode_buffer(ip, &dibh);
- if (unlikely(ret)) {
- unlock_page(page);
- put_page(page);
- goto failed;
+ if (unlikely(ret))
+ goto out;
+
+ if (gfs2_is_stuffed(ip)) {
+ ret = gfs2_stuffed_write_end(inode, dibh, pos, copied, page);
+ page = NULL;
+ goto out2;
}
- if (gfs2_is_stuffed(ip))
- return gfs2_stuffed_write_end(inode, dibh, pos, len, copied, page);
-
- if (!gfs2_is_writeback(ip))
+ if (gfs2_is_jdata(ip))
gfs2_page_add_databufs(ip, page, pos & ~PAGE_MASK, len);
+ else
+ gfs2_ordered_add_inode(ip);
ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
+ page = NULL;
if (tr->tr_num_buf_new)
__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
else
gfs2_trans_add_meta(ip->i_gl, dibh);
-
+out2:
if (inode == sdp->sd_rindex) {
adjust_fs_space(inode);
sdp->sd_rindex_uptodate = 0;
}
brelse(dibh);
-failed:
+out:
+ if (page) {
+ unlock_page(page);
+ put_page(page);
+ }
gfs2_trans_end(sdp);
gfs2_inplace_release(ip);
if (ip->i_qadata && ip->i_qadata->qa_qd_num)
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 278ed08..ed66997 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -89,10 +89,12 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
map_bh(bh, inode->i_sb, block);
set_buffer_uptodate(bh);
- if (!gfs2_is_jdata(ip))
- mark_buffer_dirty(bh);
- if (!gfs2_is_writeback(ip))
+ if (gfs2_is_jdata(ip))
gfs2_trans_add_data(ip->i_gl, bh);
+ else {
+ mark_buffer_dirty(bh);
+ gfs2_ordered_add_inode(ip);
+ }
if (release) {
unlock_page(page);
@@ -176,8 +178,8 @@ int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page)
/**
* find_metapath - Find path through the metadata tree
* @sdp: The superblock
- * @mp: The metapath to return the result in
* @block: The disk block to look up
+ * @mp: The metapath to return the result in
* @height: The pre-calculated height of the metadata tree
*
* This routine returns a struct metapath structure that defines a path
@@ -188,8 +190,7 @@ int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page)
* filesystem with a blocksize of 4096.
*
* find_metapath() would return a struct metapath structure set to:
- * mp_offset = 101342453, mp_height = 3, mp_list[0] = 0, mp_list[1] = 48,
- * and mp_list[2] = 165.
+ * mp_fheight = 3, mp_list[0] = 0, mp_list[1] = 48, and mp_list[2] = 165.
*
* That means that in order to get to the block containing the byte at
* offset 101342453, we would load the indirect block pointed to by pointer
@@ -279,6 +280,21 @@ static inline __be64 *metapointer(unsigned int height, const struct metapath *mp
return p + mp->mp_list[height];
}
+static inline const __be64 *metaend(unsigned int height, const struct metapath *mp)
+{
+ const struct buffer_head *bh = mp->mp_bh[height];
+ return (const __be64 *)(bh->b_data + bh->b_size);
+}
+
+static void clone_metapath(struct metapath *clone, struct metapath *mp)
+{
+ unsigned int hgt;
+
+ *clone = *mp;
+ for (hgt = 0; hgt < mp->mp_aheight; hgt++)
+ get_bh(clone->mp_bh[hgt]);
+}
+
static void gfs2_metapath_ra(struct gfs2_glock *gl, __be64 *start, __be64 *end)
{
const __be64 *t;
@@ -420,20 +436,140 @@ static inline unsigned int gfs2_extent_length(void *start, unsigned int len, __b
return (ptr - first);
}
-static inline void bmap_lock(struct gfs2_inode *ip, int create)
+typedef const __be64 *(*gfs2_metadata_walker)(
+ struct metapath *mp,
+ const __be64 *start, const __be64 *end,
+ u64 factor, void *data);
+
+#define WALK_STOP ((__be64 *)0)
+#define WALK_NEXT ((__be64 *)1)
+
+static int gfs2_walk_metadata(struct inode *inode, sector_t lblock,
+ u64 len, struct metapath *mp, gfs2_metadata_walker walker,
+ void *data)
{
- if (create)
- down_write(&ip->i_rw_mutex);
- else
- down_read(&ip->i_rw_mutex);
+ struct metapath clone;
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
+ const __be64 *start, *end, *ptr;
+ u64 factor = 1;
+ unsigned int hgt;
+ int ret = 0;
+
+ for (hgt = ip->i_height - 1; hgt >= mp->mp_aheight; hgt--)
+ factor *= sdp->sd_inptrs;
+
+ for (;;) {
+ u64 step;
+
+ /* Walk indirect block. */
+ start = metapointer(hgt, mp);
+ end = metaend(hgt, mp);
+
+ step = (end - start) * factor;
+ if (step > len)
+ end = start + DIV_ROUND_UP_ULL(len, factor);
+
+ ptr = walker(mp, start, end, factor, data);
+ if (ptr == WALK_STOP)
+ break;
+ if (step >= len)
+ break;
+ len -= step;
+ if (ptr != WALK_NEXT) {
+ BUG_ON(!*ptr);
+ mp->mp_list[hgt] += ptr - start;
+ goto fill_up_metapath;
+ }
+
+lower_metapath:
+ /* Decrease height of metapath. */
+ if (mp != &clone) {
+ clone_metapath(&clone, mp);
+ mp = &clone;
+ }
+ brelse(mp->mp_bh[hgt]);
+ mp->mp_bh[hgt] = NULL;
+ if (!hgt)
+ break;
+ hgt--;
+ factor *= sdp->sd_inptrs;
+
+ /* Advance in metadata tree. */
+ (mp->mp_list[hgt])++;
+ start = metapointer(hgt, mp);
+ end = metaend(hgt, mp);
+ if (start >= end) {
+ mp->mp_list[hgt] = 0;
+ if (!hgt)
+ break;
+ goto lower_metapath;
+ }
+
+fill_up_metapath:
+ /* Increase height of metapath. */
+ if (mp != &clone) {
+ clone_metapath(&clone, mp);
+ mp = &clone;
+ }
+ ret = fillup_metapath(ip, mp, ip->i_height - 1);
+ if (ret < 0)
+ break;
+ hgt += ret;
+ for (; ret; ret--)
+ do_div(factor, sdp->sd_inptrs);
+ mp->mp_aheight = hgt + 1;
+ }
+ if (mp == &clone)
+ release_metapath(mp);
+ return ret;
}
-static inline void bmap_unlock(struct gfs2_inode *ip, int create)
+struct gfs2_hole_walker_args {
+ u64 blocks;
+};
+
+static const __be64 *gfs2_hole_walker(struct metapath *mp,
+ const __be64 *start, const __be64 *end,
+ u64 factor, void *data)
{
- if (create)
- up_write(&ip->i_rw_mutex);
- else
- up_read(&ip->i_rw_mutex);
+ struct gfs2_hole_walker_args *args = data;
+ const __be64 *ptr;
+
+ for (ptr = start; ptr < end; ptr++) {
+ if (*ptr) {
+ args->blocks += (ptr - start) * factor;
+ if (mp->mp_aheight == mp->mp_fheight)
+ return WALK_STOP;
+ return ptr; /* increase height */
+ }
+ }
+ args->blocks += (end - start) * factor;
+ return WALK_NEXT;
+}
+
+/**
+ * gfs2_hole_size - figure out the size of a hole
+ * @inode: The inode
+ * @lblock: The logical starting block number
+ * @len: How far to look (in blocks)
+ * @mp: The metapath at lblock
+ * @iomap: The iomap to store the hole size in
+ *
+ * This function modifies @mp.
+ *
+ * Returns: errno on error
+ */
+static int gfs2_hole_size(struct inode *inode, sector_t lblock, u64 len,
+ struct metapath *mp, struct iomap *iomap)
+{
+ struct gfs2_hole_walker_args args = { };
+ int ret = 0;
+
+ ret = gfs2_walk_metadata(inode, lblock, len, mp, gfs2_hole_walker, &args);
+ if (!ret)
+ iomap->length = args.blocks << inode->i_blkbits;
+ return ret;
}
static inline __be64 *gfs2_indirect_init(struct metapath *mp,
@@ -462,15 +598,11 @@ enum alloc_state {
};
/**
- * gfs2_bmap_alloc - Build a metadata tree of the requested height
+ * gfs2_iomap_alloc - Build a metadata tree of the requested height
* @inode: The GFS2 inode
- * @lblock: The logical starting block of the extent
- * @bh_map: This is used to return the mapping details
- * @zero_new: True if newly allocated blocks should be zeroed
+ * @iomap: The iomap structure
+ * @flags: iomap flags
* @mp: The metapath, with proper height information calculated
- * @maxlen: The max number of data blocks to alloc
- * @dblock: Pointer to return the resulting new block
- * @dblks: Pointer to return the number of blocks allocated
*
* In this routine we may have to alloc:
* i) Indirect blocks to grow the metadata tree height
@@ -483,6 +615,13 @@ enum alloc_state {
* blocks are available, there will only be one request per bmap call)
* and uses the state machine to initialise the blocks in order.
*
+ * Right now, this function will allocate at most one indirect block
+ * worth of data -- with a default block size of 4K, that's slightly
+ * less than 2M. If this limitation is ever removed to allow huge
+ * allocations, we would probably still want to limit the iomap size we
+ * return to avoid stalling other tasks during huge writes; the next
+ * iomap iteration would then find the blocks already allocated.
+ *
* Returns: errno on error
*/
@@ -497,6 +636,7 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
unsigned dblks = 0;
unsigned ptrs_per_blk;
const unsigned end_of_metadata = mp->mp_fheight - 1;
+ int ret;
enum alloc_state state;
__be64 *ptr;
__be64 zero_bn = 0;
@@ -507,6 +647,8 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
gfs2_trans_add_meta(ip->i_gl, dibh);
+ down_write(&ip->i_rw_mutex);
+
if (mp->mp_fheight == mp->mp_aheight) {
struct buffer_head *bh;
int eob;
@@ -542,11 +684,10 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
blks = dblks + iblks;
i = mp->mp_aheight;
do {
- int error;
n = blks - alloced;
- error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL);
- if (error)
- return error;
+ ret = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL);
+ if (ret)
+ goto out;
alloced += n;
if (state != ALLOC_DATA || gfs2_is_jdata(ip))
gfs2_trans_add_unrevoke(sdp, bn, n);
@@ -602,7 +743,7 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
dblks = n;
ptr = metapointer(end_of_metadata, mp);
iomap->addr = bn << inode->i_blkbits;
- iomap->flags |= IOMAP_F_NEW;
+ iomap->flags |= IOMAP_F_MERGED | IOMAP_F_NEW;
while (n-- > 0)
*ptr++ = cpu_to_be64(bn++);
break;
@@ -612,64 +753,10 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
iomap->length = (u64)dblks << inode->i_blkbits;
ip->i_height = mp->mp_fheight;
gfs2_add_inode_blocks(&ip->i_inode, alloced);
- gfs2_dinode_out(ip, mp->mp_bh[0]->b_data);
- return 0;
-}
-
-/**
- * hole_size - figure out the size of a hole
- * @inode: The inode
- * @lblock: The logical starting block number
- * @mp: The metapath
- *
- * Returns: The hole size in bytes
- *
- */
-static u64 hole_size(struct inode *inode, sector_t lblock, struct metapath *mp)
-{
- struct gfs2_inode *ip = GFS2_I(inode);
- struct gfs2_sbd *sdp = GFS2_SB(inode);
- struct metapath mp_eof;
- u64 factor = 1;
- int hgt;
- u64 holesz = 0;
- const __be64 *first, *end, *ptr;
- const struct buffer_head *bh;
- u64 lblock_stop = (i_size_read(inode) - 1) >> inode->i_blkbits;
- int zeroptrs;
- bool done = false;
-
- /* Get another metapath, to the very last byte */
- find_metapath(sdp, lblock_stop, &mp_eof, ip->i_height);
- for (hgt = ip->i_height - 1; hgt >= 0 && !done; hgt--) {
- bh = mp->mp_bh[hgt];
- if (bh) {
- zeroptrs = 0;
- first = metapointer(hgt, mp);
- end = (const __be64 *)(bh->b_data + bh->b_size);
-
- for (ptr = first; ptr < end; ptr++) {
- if (*ptr) {
- done = true;
- break;
- } else {
- zeroptrs++;
- }
- }
- } else {
- zeroptrs = sdp->sd_inptrs;
- }
- if (factor * zeroptrs >= lblock_stop - lblock + 1) {
- holesz = lblock_stop - lblock + 1;
- break;
- }
- holesz += factor * zeroptrs;
-
- factor *= sdp->sd_inptrs;
- if (hgt && (mp->mp_list[hgt - 1] < mp_eof.mp_list[hgt - 1]))
- (mp->mp_list[hgt - 1])++;
- }
- return holesz << inode->i_blkbits;
+ gfs2_dinode_out(ip, dibh->b_data);
+out:
+ up_write(&ip->i_rw_mutex);
+ return ret;
}
static void gfs2_stuffed_iomap(struct inode *inode, struct iomap *iomap)
@@ -680,126 +767,136 @@ static void gfs2_stuffed_iomap(struct inode *inode, struct iomap *iomap)
sizeof(struct gfs2_dinode);
iomap->offset = 0;
iomap->length = i_size_read(inode);
- iomap->type = IOMAP_MAPPED;
- iomap->flags = IOMAP_F_DATA_INLINE;
+ iomap->type = IOMAP_INLINE;
}
+#define IOMAP_F_GFS2_BOUNDARY IOMAP_F_PRIVATE
+
/**
- * gfs2_iomap_begin - Map blocks from an inode to disk blocks
+ * gfs2_iomap_get - Map blocks from an inode to disk blocks
* @inode: The inode
* @pos: Starting position in bytes
* @length: Length to map, in bytes
* @flags: iomap flags
* @iomap: The iomap structure
+ * @mp: The metapath
*
* Returns: errno
*/
-int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
- unsigned flags, struct iomap *iomap)
+static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
+ unsigned flags, struct iomap *iomap,
+ struct metapath *mp)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
- struct metapath mp = { .mp_aheight = 1, };
- unsigned int factor = sdp->sd_sb.sb_bsize;
- const u64 *arr = sdp->sd_heightsize;
__be64 *ptr;
sector_t lblock;
- sector_t lend;
- int ret = 0;
+ sector_t lblock_stop;
+ int ret;
int eob;
- unsigned int len;
+ u64 len;
struct buffer_head *bh;
u8 height;
- trace_gfs2_iomap_start(ip, pos, length, flags);
- if (!length) {
- ret = -EINVAL;
- goto out;
- }
+ if (!length)
+ return -EINVAL;
if (gfs2_is_stuffed(ip)) {
if (flags & IOMAP_REPORT) {
+ if (pos >= i_size_read(inode))
+ return -ENOENT;
gfs2_stuffed_iomap(inode, iomap);
- if (pos >= iomap->length)
- ret = -ENOENT;
- goto out;
+ return 0;
}
BUG_ON(!(flags & IOMAP_WRITE));
}
-
lblock = pos >> inode->i_blkbits;
- lend = (pos + length + sdp->sd_sb.sb_bsize - 1) >> inode->i_blkbits;
-
iomap->offset = lblock << inode->i_blkbits;
- iomap->addr = IOMAP_NULL_ADDR;
- iomap->type = IOMAP_HOLE;
- iomap->length = (u64)(lend - lblock) << inode->i_blkbits;
- iomap->flags = IOMAP_F_MERGED;
- bmap_lock(ip, flags & IOMAP_WRITE);
+ lblock_stop = (pos + length - 1) >> inode->i_blkbits;
+ len = lblock_stop - lblock + 1;
- /*
- * Directory data blocks have a struct gfs2_meta_header header, so the
- * remaining size is smaller than the filesystem block size. Logical
- * block numbers for directories are in units of this remaining size!
- */
- if (gfs2_is_dir(ip)) {
- factor = sdp->sd_jbsize;
- arr = sdp->sd_jheightsize;
- }
+ down_read(&ip->i_rw_mutex);
- ret = gfs2_meta_inode_buffer(ip, &mp.mp_bh[0]);
+ ret = gfs2_meta_inode_buffer(ip, &mp->mp_bh[0]);
if (ret)
- goto out_release;
+ goto unlock;
height = ip->i_height;
- while ((lblock + 1) * factor > arr[height])
+ while ((lblock + 1) * sdp->sd_sb.sb_bsize > sdp->sd_heightsize[height])
height++;
- find_metapath(sdp, lblock, &mp, height);
+ find_metapath(sdp, lblock, mp, height);
if (height > ip->i_height || gfs2_is_stuffed(ip))
goto do_alloc;
- ret = lookup_metapath(ip, &mp);
+ ret = lookup_metapath(ip, mp);
if (ret)
- goto out_release;
+ goto unlock;
- if (mp.mp_aheight != ip->i_height)
+ if (mp->mp_aheight != ip->i_height)
goto do_alloc;
- ptr = metapointer(ip->i_height - 1, &mp);
+ ptr = metapointer(ip->i_height - 1, mp);
if (*ptr == 0)
goto do_alloc;
- iomap->type = IOMAP_MAPPED;
+ bh = mp->mp_bh[ip->i_height - 1];
+ len = gfs2_extent_length(bh->b_data, bh->b_size, ptr, len, &eob);
+
iomap->addr = be64_to_cpu(*ptr) << inode->i_blkbits;
-
- bh = mp.mp_bh[ip->i_height - 1];
- len = gfs2_extent_length(bh->b_data, bh->b_size, ptr, lend - lblock, &eob);
+ iomap->length = len << inode->i_blkbits;
+ iomap->type = IOMAP_MAPPED;
+ iomap->flags = IOMAP_F_MERGED;
if (eob)
- iomap->flags |= IOMAP_F_BOUNDARY;
- iomap->length = (u64)len << inode->i_blkbits;
+ iomap->flags |= IOMAP_F_GFS2_BOUNDARY;
-out_release:
- release_metapath(&mp);
- bmap_unlock(ip, flags & IOMAP_WRITE);
out:
- trace_gfs2_iomap_end(ip, iomap, ret);
+ iomap->bdev = inode->i_sb->s_bdev;
+unlock:
+ up_read(&ip->i_rw_mutex);
return ret;
do_alloc:
- if (flags & IOMAP_WRITE) {
- ret = gfs2_iomap_alloc(inode, iomap, flags, &mp);
- } else if (flags & IOMAP_REPORT) {
+ iomap->addr = IOMAP_NULL_ADDR;
+ iomap->length = len << inode->i_blkbits;
+ iomap->type = IOMAP_HOLE;
+ iomap->flags = 0;
+ if (flags & IOMAP_REPORT) {
loff_t size = i_size_read(inode);
if (pos >= size)
ret = -ENOENT;
- else if (height <= ip->i_height)
- iomap->length = hole_size(inode, lblock, &mp);
+ else if (height == ip->i_height)
+ ret = gfs2_hole_size(inode, lblock, len, mp, iomap);
else
iomap->length = size - pos;
}
- goto out_release;
+ goto out;
}
+static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
+ unsigned flags, struct iomap *iomap)
+{
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct metapath mp = { .mp_aheight = 1, };
+ int ret;
+
+ trace_gfs2_iomap_start(ip, pos, length, flags);
+ if (flags & IOMAP_WRITE) {
+ ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
+ if (!ret && iomap->type == IOMAP_HOLE)
+ ret = gfs2_iomap_alloc(inode, iomap, flags, &mp);
+ release_metapath(&mp);
+ } else {
+ ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
+ release_metapath(&mp);
+ }
+ trace_gfs2_iomap_end(ip, iomap, ret);
+ return ret;
+}
+
+const struct iomap_ops gfs2_iomap_ops = {
+ .iomap_begin = gfs2_iomap_begin,
+};
+
/**
* gfs2_block_map - Map one or more blocks of an inode to a disk block
* @inode: The inode
@@ -825,34 +922,43 @@ int gfs2_block_map(struct inode *inode, sector_t lblock,
struct buffer_head *bh_map, int create)
{
struct gfs2_inode *ip = GFS2_I(inode);
- struct iomap iomap;
- int ret, flags = 0;
+ loff_t pos = (loff_t)lblock << inode->i_blkbits;
+ loff_t length = bh_map->b_size;
+ struct metapath mp = { .mp_aheight = 1, };
+ struct iomap iomap = { };
+ int ret;
clear_buffer_mapped(bh_map);
clear_buffer_new(bh_map);
clear_buffer_boundary(bh_map);
trace_gfs2_bmap(ip, bh_map, lblock, create, 1);
- if (create)
- flags |= IOMAP_WRITE;
- ret = gfs2_iomap_begin(inode, (loff_t)lblock << inode->i_blkbits,
- bh_map->b_size, flags, &iomap);
- if (ret) {
- if (!create && ret == -ENOENT) {
- /* Return unmapped buffer beyond the end of file. */
+ if (create) {
+ ret = gfs2_iomap_get(inode, pos, length, IOMAP_WRITE, &iomap, &mp);
+ if (!ret && iomap.type == IOMAP_HOLE)
+ ret = gfs2_iomap_alloc(inode, &iomap, IOMAP_WRITE, &mp);
+ release_metapath(&mp);
+ } else {
+ ret = gfs2_iomap_get(inode, pos, length, 0, &iomap, &mp);
+ release_metapath(&mp);
+
+ /* Return unmapped buffer beyond the end of file. */
+ if (ret == -ENOENT) {
ret = 0;
+ goto out;
}
- goto out;
}
+ if (ret)
+ goto out;
if (iomap.length > bh_map->b_size) {
iomap.length = bh_map->b_size;
- iomap.flags &= ~IOMAP_F_BOUNDARY;
+ iomap.flags &= ~IOMAP_F_GFS2_BOUNDARY;
}
if (iomap.addr != IOMAP_NULL_ADDR)
map_bh(bh_map, inode->i_sb, iomap.addr >> inode->i_blkbits);
bh_map->b_size = iomap.length;
- if (iomap.flags & IOMAP_F_BOUNDARY)
+ if (iomap.flags & IOMAP_F_GFS2_BOUNDARY)
set_buffer_boundary(bh_map);
if (iomap.flags & IOMAP_F_NEW)
set_buffer_new(bh_map);
@@ -945,8 +1051,10 @@ static int gfs2_block_zero_range(struct inode *inode, loff_t from,
err = 0;
}
- if (!gfs2_is_writeback(ip))
+ if (gfs2_is_jdata(ip))
gfs2_trans_add_data(ip->i_gl, bh);
+ else
+ gfs2_ordered_add_inode(ip);
zero_user(page, offset, length);
mark_buffer_dirty(bh);
@@ -1056,6 +1164,19 @@ static int trunc_start(struct inode *inode, u64 newsize)
return error;
}
+int gfs2_iomap_get_alloc(struct inode *inode, loff_t pos, loff_t length,
+ struct iomap *iomap)
+{
+ struct metapath mp = { .mp_aheight = 1, };
+ int ret;
+
+ ret = gfs2_iomap_get(inode, pos, length, IOMAP_WRITE, iomap, &mp);
+ if (!ret && iomap->type == IOMAP_HOLE)
+ ret = gfs2_iomap_alloc(inode, iomap, IOMAP_WRITE, &mp);
+ release_metapath(&mp);
+ return ret;
+}
+
/**
* sweep_bh_for_rgrps - find an rgrp in a meta buffer and free blocks therein
* @ip: inode
diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h
index c3402fe..6b18fb3 100644
--- a/fs/gfs2/bmap.h
+++ b/fs/gfs2/bmap.h
@@ -46,11 +46,13 @@ static inline void gfs2_write_calc_reserv(const struct gfs2_inode *ip,
}
}
+extern const struct iomap_ops gfs2_iomap_ops;
+
extern int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page);
extern int gfs2_block_map(struct inode *inode, sector_t lblock,
struct buffer_head *bh, int create);
-extern int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
- unsigned flags, struct iomap *iomap);
+extern int gfs2_iomap_get_alloc(struct inode *inode, loff_t pos, loff_t length,
+ struct iomap *iomap);
extern int gfs2_extent_map(struct inode *inode, u64 lblock, int *new,
u64 *dblock, unsigned *extlen);
extern int gfs2_setattr_size(struct inode *inode, u64 size);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 4b71f021..7137db7 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -733,7 +733,7 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
struct gfs2_inode *ip = GFS2_I(inode);
loff_t end = offset + len;
struct buffer_head *dibh;
- struct iomap iomap;
+ struct iomap iomap = { };
int error;
error = gfs2_meta_inode_buffer(ip, &dibh);
@@ -749,8 +749,8 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
}
while (offset < end) {
- error = gfs2_iomap_begin(inode, offset, end - offset,
- IOMAP_WRITE, &iomap);
+ error = gfs2_iomap_get_alloc(inode, offset, end - offset,
+ &iomap);
if (error)
goto out;
offset = iomap.offset + iomap.length;
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 1b6b1e3..d2ad817 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -116,6 +116,7 @@ static inline struct gfs2_bitmap *rbm_bi(const struct gfs2_rbm *rbm)
static inline u64 gfs2_rbm_to_block(const struct gfs2_rbm *rbm)
{
+ BUG_ON(rbm->offset >= rbm->rgd->rd_data);
return rbm->rgd->rd_data0 + (rbm_bi(rbm)->bi_start * GFS2_NBBY) +
rbm->offset;
}
@@ -696,8 +697,6 @@ struct gfs2_sbd {
u32 sd_max_dirres; /* Max blocks needed to add a directory entry */
u32 sd_max_height; /* Max height of a file's metadata tree */
u64 sd_heightsize[GFS2_MAX_META_HEIGHT + 1];
- u32 sd_max_jheight; /* Max height of journaled file's meta tree */
- u64 sd_jheightsize[GFS2_MAX_META_HEIGHT + 1];
u32 sd_max_dents_per_leaf; /* Max number of dirents in a leaf block */
struct gfs2_args sd_args; /* Mount arguments */
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 8700eb8..feda55f 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -2006,10 +2006,6 @@ static int gfs2_getattr(const struct path *path, struct kstat *stat,
return 0;
}
-const struct iomap_ops gfs2_iomap_ops = {
- .iomap_begin = gfs2_iomap_begin,
-};
-
static int gfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index 1862e31..20241436 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -14,6 +14,7 @@
#include <linux/spinlock.h>
#include <linux/writeback.h>
#include "incore.h"
+#include "inode.h"
/**
* gfs2_log_lock - acquire the right to mess with the log manager
@@ -50,8 +51,12 @@ static inline void gfs2_log_pointers_init(struct gfs2_sbd *sdp,
static inline void gfs2_ordered_add_inode(struct gfs2_inode *ip)
{
- struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+ struct gfs2_sbd *sdp;
+ if (!gfs2_is_ordered(ip))
+ return;
+
+ sdp = GFS2_SB(&ip->i_inode);
if (!test_bit(GIF_ORDERED, &ip->i_flags)) {
spin_lock(&sdp->sd_ordered_lock);
if (!test_and_set_bit(GIF_ORDERED, &ip->i_flags))
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 3ba3f16..c2469833b 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -335,25 +335,6 @@ static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent)
sdp->sd_heightsize[x] = ~0;
gfs2_assert(sdp, sdp->sd_max_height <= GFS2_MAX_META_HEIGHT);
- sdp->sd_jheightsize[0] = sdp->sd_sb.sb_bsize -
- sizeof(struct gfs2_dinode);
- sdp->sd_jheightsize[1] = sdp->sd_jbsize * sdp->sd_diptrs;
- for (x = 2;; x++) {
- u64 space, d;
- u32 m;
-
- space = sdp->sd_jheightsize[x - 1] * sdp->sd_inptrs;
- d = space;
- m = do_div(d, sdp->sd_inptrs);
-
- if (d != sdp->sd_jheightsize[x - 1] || m)
- break;
- sdp->sd_jheightsize[x] = space;
- }
- sdp->sd_max_jheight = x;
- sdp->sd_jheightsize[x] = ~0;
- gfs2_assert(sdp, sdp->sd_max_jheight <= GFS2_MAX_META_HEIGHT);
-
sdp->sd_max_dents_per_leaf = (sdp->sd_sb.sb_bsize -
sizeof(struct gfs2_leaf)) /
GFS2_MIN_DIRENT_SIZE;
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 7a98abd..e8585df 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -735,7 +735,10 @@ static int gfs2_write_buf_to_page(struct gfs2_inode *ip, unsigned long index,
if (!buffer_uptodate(bh))
goto unlock_out;
}
- gfs2_trans_add_data(ip->i_gl, bh);
+ if (gfs2_is_jdata(ip))
+ gfs2_trans_add_data(ip->i_gl, bh);
+ else
+ gfs2_ordered_add_inode(ip);
/* If we need to write to the next block as well */
if (to_write > (bsize - boff)) {
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 8b68391..6bc5cfe 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -372,8 +372,8 @@ static u32 gfs2_free_extlen(const struct gfs2_rbm *rrbm, u32 len)
start = bi->bi_bh->b_data;
if (bi->bi_clone)
start = bi->bi_clone;
- end = start + bi->bi_bh->b_size;
start += bi->bi_offset;
+ end = start + bi->bi_len;
BUG_ON(rbm.offset & 3);
start += (rbm.offset / GFS2_NBBY);
bytes = min_t(u32, len / GFS2_NBBY, (end - start));
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index c75caca..064c9a0 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -143,32 +143,21 @@ static struct gfs2_bufdata *gfs2_alloc_bufdata(struct gfs2_glock *gl,
* @gl: The inode glock associated with the buffer
* @bh: The buffer to add
*
- * This is used in two distinct cases:
- * i) In ordered write mode
- * We put the data buffer on a list so that we can ensure that it's
- * synced to disk at the right time
- * ii) In journaled data mode
- * We need to journal the data block in the same way as metadata in
- * the functions above. The difference is that here we have a tag
- * which is two __be64's being the block number (as per meta data)
- * and a flag which says whether the data block needs escaping or
- * not. This means we need a new log entry for each 251 or so data
- * blocks, which isn't an enormous overhead but twice as much as
- * for normal metadata blocks.
+ * This is used in journaled data mode.
+ * We need to journal the data block in the same way as metadata in
+ * the functions above. The difference is that here we have a tag
+ * which is two __be64's being the block number (as per meta data)
+ * and a flag which says whether the data block needs escaping or
+ * not. This means we need a new log entry for each 251 or so data
+ * blocks, which isn't an enormous overhead but twice as much as
+ * for normal metadata blocks.
*/
void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh)
{
struct gfs2_trans *tr = current->journal_info;
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
- struct address_space *mapping = bh->b_page->mapping;
- struct gfs2_inode *ip = GFS2_I(mapping->host);
struct gfs2_bufdata *bd;
- if (!gfs2_is_jdata(ip)) {
- gfs2_ordered_add_inode(ip);
- return;
- }
-
lock_buffer(bh);
if (buffer_pinned(bh)) {
set_bit(TR_TOUCHED, &tr->tr_flags);
diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index 75b2542..3bf2ae0 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -31,21 +31,15 @@ static struct dentry *hfs_lookup(struct inode *dir, struct dentry *dentry,
hfs_cat_build_key(dir->i_sb, fd.search_key, dir->i_ino, &dentry->d_name);
res = hfs_brec_read(&fd, &rec, sizeof(rec));
if (res) {
- hfs_find_exit(&fd);
- if (res == -ENOENT) {
- /* No such entry */
- inode = NULL;
- goto done;
- }
- return ERR_PTR(res);
+ if (res != -ENOENT)
+ inode = ERR_PTR(res);
+ } else {
+ inode = hfs_iget(dir->i_sb, &fd.search_key->cat, &rec);
+ if (!inode)
+ inode = ERR_PTR(-EACCES);
}
- inode = hfs_iget(dir->i_sb, &fd.search_key->cat, &rec);
hfs_find_exit(&fd);
- if (!inode)
- return ERR_PTR(-EACCES);
-done:
- d_add(dentry, inode);
- return NULL;
+ return d_splice_alias(inode, dentry);
}
/*
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 2538b49..b3309b8 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -543,9 +543,9 @@ static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry,
igrab(dir);
hlist_add_fake(&inode->i_hash);
mark_inode_dirty(inode);
+ dont_mount(dentry);
out:
- d_add(dentry, inode);
- return NULL;
+ return d_splice_alias(inode, dentry);
}
void hfs_evict_inode(struct inode *inode)
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 15e06fb..b525437 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -122,8 +122,7 @@ static struct dentry *hfsplus_lookup(struct inode *dir, struct dentry *dentry,
if (S_ISREG(inode->i_mode))
HFSPLUS_I(inode)->linkid = linkid;
out:
- d_add(dentry, inode);
- return NULL;
+ return d_splice_alias(inode, dentry);
fail:
hfs_find_exit(&fd);
return ERR_PTR(err);
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 513c357..a6c0f54 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -588,6 +588,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
return 0;
out_put_hidden_dir:
+ cancel_delayed_work_sync(&sbi->sync_work);
iput(sbi->hidden_dir);
out_put_root:
dput(sb->s_root);
diff --git a/fs/inode.c b/fs/inode.c
index 13ceb98..3b55391 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -178,6 +178,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
mapping->a_ops = &empty_aops;
mapping->host = inode;
mapping->flags = 0;
+ mapping->wb_err = 0;
atomic_set(&mapping->i_mmap_writable, 0);
mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
mapping->private_data = NULL;
diff --git a/fs/internal.h b/fs/internal.h
index e08972d..980d005 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -125,6 +125,7 @@ int do_fchmodat(int dfd, const char __user *filename, umode_t mode);
int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
int flag);
+extern int open_check_o_direct(struct file *f);
extern int vfs_open(const struct path *, struct file *, const struct cred *);
extern struct file *filp_clone_open(struct file *);
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 4823431..b445b13 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -549,7 +549,7 @@ static int ioctl_fsfreeze(struct file *filp)
{
struct super_block *sb = file_inode(filp)->i_sb;
- if (!capable(CAP_SYS_ADMIN))
+ if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN))
return -EPERM;
/* If filesystem doesn't support freeze feature, return. */
@@ -566,7 +566,7 @@ static int ioctl_fsthaw(struct file *filp)
{
struct super_block *sb = file_inode(filp)->i_sb;
- if (!capable(CAP_SYS_ADMIN))
+ if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN))
return -EPERM;
/* Thaw */
diff --git a/fs/iomap.c b/fs/iomap.c
index afd1635..206539d3 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -20,6 +20,7 @@
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
+#include <linux/pagevec.h>
#include <linux/file.h>
#include <linux/uio.h>
#include <linux/backing-dev.h>
@@ -27,6 +28,7 @@
#include <linux/task_io_accounting_ops.h>
#include <linux/dax.h>
#include <linux/sched/signal.h>
+#include <linux/swap.h>
#include "internal.h"
@@ -95,6 +97,12 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags,
return written ? written : ret;
}
+static sector_t
+iomap_sector(struct iomap *iomap, loff_t pos)
+{
+ return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT;
+}
+
static void
iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
{
@@ -352,11 +360,8 @@ static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,
struct iomap *iomap)
{
- sector_t sector = (iomap->addr +
- (pos & PAGE_MASK) - iomap->offset) >> 9;
-
- return __dax_zero_page_range(iomap->bdev, iomap->dax_dev, sector,
- offset, bytes);
+ return __dax_zero_page_range(iomap->bdev, iomap->dax_dev,
+ iomap_sector(iomap, pos & PAGE_MASK), offset, bytes);
}
static loff_t
@@ -501,10 +506,13 @@ static int iomap_to_fiemap(struct fiemap_extent_info *fi,
case IOMAP_DELALLOC:
flags |= FIEMAP_EXTENT_DELALLOC | FIEMAP_EXTENT_UNKNOWN;
break;
+ case IOMAP_MAPPED:
+ break;
case IOMAP_UNWRITTEN:
flags |= FIEMAP_EXTENT_UNWRITTEN;
break;
- case IOMAP_MAPPED:
+ case IOMAP_INLINE:
+ flags |= FIEMAP_EXTENT_DATA_INLINE;
break;
}
@@ -512,8 +520,6 @@ static int iomap_to_fiemap(struct fiemap_extent_info *fi,
flags |= FIEMAP_EXTENT_MERGED;
if (iomap->flags & IOMAP_F_SHARED)
flags |= FIEMAP_EXTENT_SHARED;
- if (iomap->flags & IOMAP_F_DATA_INLINE)
- flags |= FIEMAP_EXTENT_DATA_INLINE;
return fiemap_fill_next_extent(fi, iomap->offset,
iomap->addr != IOMAP_NULL_ADDR ? iomap->addr : 0,
@@ -587,6 +593,113 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
}
EXPORT_SYMBOL_GPL(iomap_fiemap);
+/*
+ * Seek for SEEK_DATA / SEEK_HOLE within @page, starting at @lastoff.
+ * Returns true if found and updates @lastoff to the offset in file.
+ */
+static bool
+page_seek_hole_data(struct inode *inode, struct page *page, loff_t *lastoff,
+ int whence)
+{
+ const struct address_space_operations *ops = inode->i_mapping->a_ops;
+ unsigned int bsize = i_blocksize(inode), off;
+ bool seek_data = whence == SEEK_DATA;
+ loff_t poff = page_offset(page);
+
+ if (WARN_ON_ONCE(*lastoff >= poff + PAGE_SIZE))
+ return false;
+
+ if (*lastoff < poff) {
+ /*
+ * Last offset smaller than the start of the page means we found
+ * a hole:
+ */
+ if (whence == SEEK_HOLE)
+ return true;
+ *lastoff = poff;
+ }
+
+ /*
+ * Just check the page unless we can and should check block ranges:
+ */
+ if (bsize == PAGE_SIZE || !ops->is_partially_uptodate)
+ return PageUptodate(page) == seek_data;
+
+ lock_page(page);
+ if (unlikely(page->mapping != inode->i_mapping))
+ goto out_unlock_not_found;
+
+ for (off = 0; off < PAGE_SIZE; off += bsize) {
+ if ((*lastoff & ~PAGE_MASK) >= off + bsize)
+ continue;
+ if (ops->is_partially_uptodate(page, off, bsize) == seek_data) {
+ unlock_page(page);
+ return true;
+ }
+ *lastoff = poff + off + bsize;
+ }
+
+out_unlock_not_found:
+ unlock_page(page);
+ return false;
+}
+
+/*
+ * Seek for SEEK_DATA / SEEK_HOLE in the page cache.
+ *
+ * Within unwritten extents, the page cache determines which parts are holes
+ * and which are data: uptodate buffer heads count as data; everything else
+ * counts as a hole.
+ *
+ * Returns the resulting offset on successs, and -ENOENT otherwise.
+ */
+static loff_t
+page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length,
+ int whence)
+{
+ pgoff_t index = offset >> PAGE_SHIFT;
+ pgoff_t end = DIV_ROUND_UP(offset + length, PAGE_SIZE);
+ loff_t lastoff = offset;
+ struct pagevec pvec;
+
+ if (length <= 0)
+ return -ENOENT;
+
+ pagevec_init(&pvec);
+
+ do {
+ unsigned nr_pages, i;
+
+ nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping, &index,
+ end - 1);
+ if (nr_pages == 0)
+ break;
+
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
+
+ if (page_seek_hole_data(inode, page, &lastoff, whence))
+ goto check_range;
+ lastoff = page_offset(page) + PAGE_SIZE;
+ }
+ pagevec_release(&pvec);
+ } while (index < end);
+
+ /* When no page at lastoff and we are not done, we found a hole. */
+ if (whence != SEEK_HOLE)
+ goto not_found;
+
+check_range:
+ if (lastoff < offset + length)
+ goto out;
+not_found:
+ lastoff = -ENOENT;
+out:
+ pagevec_release(&pvec);
+ return lastoff;
+}
+
+
static loff_t
iomap_seek_hole_actor(struct inode *inode, loff_t offset, loff_t length,
void *data, struct iomap *iomap)
@@ -685,6 +798,8 @@ EXPORT_SYMBOL_GPL(iomap_seek_data);
* Private flags for iomap_dio, must not overlap with the public ones in
* iomap.h:
*/
+#define IOMAP_DIO_WRITE_FUA (1 << 28)
+#define IOMAP_DIO_NEED_SYNC (1 << 29)
#define IOMAP_DIO_WRITE (1 << 30)
#define IOMAP_DIO_DIRTY (1 << 31)
@@ -759,6 +874,13 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
dio_warn_stale_pagecache(iocb->ki_filp);
}
+ /*
+ * If this is a DSYNC write, make sure we push it to stable storage now
+ * that we've written data.
+ */
+ if (ret > 0 && (dio->flags & IOMAP_DIO_NEED_SYNC))
+ ret = generic_write_sync(iocb, ret);
+
inode_dio_end(file_inode(iocb->ki_filp));
kfree(dio);
@@ -769,13 +891,8 @@ static void iomap_dio_complete_work(struct work_struct *work)
{
struct iomap_dio *dio = container_of(work, struct iomap_dio, aio.work);
struct kiocb *iocb = dio->iocb;
- bool is_write = (dio->flags & IOMAP_DIO_WRITE);
- ssize_t ret;
- ret = iomap_dio_complete(dio);
- if (is_write && ret > 0)
- ret = generic_write_sync(iocb, ret);
- iocb->ki_complete(iocb, ret, 0);
+ iocb->ki_complete(iocb, iomap_dio_complete(dio), 0);
}
/*
@@ -833,14 +950,12 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
bio = bio_alloc(GFP_KERNEL, 1);
bio_set_dev(bio, iomap->bdev);
- bio->bi_iter.bi_sector =
- (iomap->addr + pos - iomap->offset) >> 9;
+ bio->bi_iter.bi_sector = iomap_sector(iomap, pos);
bio->bi_private = dio;
bio->bi_end_io = iomap_dio_bio_end_io;
get_page(page);
- if (bio_add_page(bio, page, len, 0) != len)
- BUG();
+ __bio_add_page(bio, page, len, 0);
bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_SYNC | REQ_IDLE);
atomic_inc(&dio->ref);
@@ -858,6 +973,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
struct iov_iter iter;
struct bio *bio;
bool need_zeroout = false;
+ bool use_fua = false;
int nr_pages, ret;
size_t copied = 0;
@@ -881,8 +997,20 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
case IOMAP_MAPPED:
if (iomap->flags & IOMAP_F_SHARED)
dio->flags |= IOMAP_DIO_COW;
- if (iomap->flags & IOMAP_F_NEW)
+ if (iomap->flags & IOMAP_F_NEW) {
need_zeroout = true;
+ } else {
+ /*
+ * Use a FUA write if we need datasync semantics, this
+ * is a pure data IO that doesn't require any metadata
+ * updates and the underlying device supports FUA. This
+ * allows us to avoid cache flushes on IO completion.
+ */
+ if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) &&
+ (dio->flags & IOMAP_DIO_WRITE_FUA) &&
+ blk_queue_fua(bdev_get_queue(iomap->bdev)))
+ use_fua = true;
+ }
break;
default:
WARN_ON_ONCE(1);
@@ -916,8 +1044,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
bio = bio_alloc(GFP_KERNEL, nr_pages);
bio_set_dev(bio, iomap->bdev);
- bio->bi_iter.bi_sector =
- (iomap->addr + pos - iomap->offset) >> 9;
+ bio->bi_iter.bi_sector = iomap_sector(iomap, pos);
bio->bi_write_hint = dio->iocb->ki_hint;
bio->bi_private = dio;
bio->bi_end_io = iomap_dio_bio_end_io;
@@ -930,10 +1057,14 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
n = bio->bi_iter.bi_size;
if (dio->flags & IOMAP_DIO_WRITE) {
- bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_SYNC | REQ_IDLE);
+ bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
+ if (use_fua)
+ bio->bi_opf |= REQ_FUA;
+ else
+ dio->flags &= ~IOMAP_DIO_WRITE_FUA;
task_io_account_write(n);
} else {
- bio_set_op_attrs(bio, REQ_OP_READ, 0);
+ bio->bi_opf = REQ_OP_READ;
if (dio->flags & IOMAP_DIO_DIRTY)
bio_set_pages_dirty(bio);
}
@@ -961,6 +1092,15 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
return copied;
}
+/*
+ * iomap_dio_rw() always completes O_[D]SYNC writes regardless of whether the IO
+ * is being issued as AIO or not. This allows us to optimise pure data writes
+ * to use REQ_FUA rather than requiring generic_write_sync() to issue a
+ * REQ_FLUSH post write. This is slightly tricky because a single request here
+ * can be mapped into multiple disjoint IOs and only a subset of the IOs issued
+ * may be pure data writes. In that case, we still need to do a full data sync
+ * completion.
+ */
ssize_t
iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
const struct iomap_ops *ops, iomap_dio_end_io_t end_io)
@@ -1005,8 +1145,21 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
if (iter->type == ITER_IOVEC)
dio->flags |= IOMAP_DIO_DIRTY;
} else {
- dio->flags |= IOMAP_DIO_WRITE;
flags |= IOMAP_WRITE;
+ dio->flags |= IOMAP_DIO_WRITE;
+
+ /* for data sync or sync, we need sync completion processing */
+ if (iocb->ki_flags & IOCB_DSYNC)
+ dio->flags |= IOMAP_DIO_NEED_SYNC;
+
+ /*
+ * For datasync only writes, we optimistically try using FUA for
+ * this IO. Any non-FUA write that occurs will clear this flag,
+ * hence we know before completion whether a cache flush is
+ * necessary.
+ */
+ if ((iocb->ki_flags & (IOCB_DSYNC | IOCB_SYNC)) == IOCB_DSYNC)
+ dio->flags |= IOMAP_DIO_WRITE_FUA;
}
if (iocb->ki_flags & IOCB_NOWAIT) {
@@ -1062,6 +1215,13 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
if (ret < 0)
iomap_dio_set_error(dio, ret);
+ /*
+ * If all the writes we issued were FUA, we don't need to flush the
+ * cache on IO completion. Clear the sync flag for this case.
+ */
+ if (dio->flags & IOMAP_DIO_WRITE_FUA)
+ dio->flags &= ~IOMAP_DIO_NEED_SYNC;
+
if (!atomic_dec_and_test(&dio->ref)) {
if (!is_sync_kiocb(iocb))
return -EIOCBQUEUED;
@@ -1089,3 +1249,203 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
return ret;
}
EXPORT_SYMBOL_GPL(iomap_dio_rw);
+
+/* Swapfile activation */
+
+#ifdef CONFIG_SWAP
+struct iomap_swapfile_info {
+ struct iomap iomap; /* accumulated iomap */
+ struct swap_info_struct *sis;
+ uint64_t lowest_ppage; /* lowest physical addr seen (pages) */
+ uint64_t highest_ppage; /* highest physical addr seen (pages) */
+ unsigned long nr_pages; /* number of pages collected */
+ int nr_extents; /* extent count */
+};
+
+/*
+ * Collect physical extents for this swap file. Physical extents reported to
+ * the swap code must be trimmed to align to a page boundary. The logical
+ * offset within the file is irrelevant since the swapfile code maps logical
+ * page numbers of the swap device to the physical page-aligned extents.
+ */
+static int iomap_swapfile_add_extent(struct iomap_swapfile_info *isi)
+{
+ struct iomap *iomap = &isi->iomap;
+ unsigned long nr_pages;
+ uint64_t first_ppage;
+ uint64_t first_ppage_reported;
+ uint64_t next_ppage;
+ int error;
+
+ /*
+ * Round the start up and the end down so that the physical
+ * extent aligns to a page boundary.
+ */
+ first_ppage = ALIGN(iomap->addr, PAGE_SIZE) >> PAGE_SHIFT;
+ next_ppage = ALIGN_DOWN(iomap->addr + iomap->length, PAGE_SIZE) >>
+ PAGE_SHIFT;
+
+ /* Skip too-short physical extents. */
+ if (first_ppage >= next_ppage)
+ return 0;
+ nr_pages = next_ppage - first_ppage;
+
+ /*
+ * Calculate how much swap space we're adding; the first page contains
+ * the swap header and doesn't count. The mm still wants that first
+ * page fed to add_swap_extent, however.
+ */
+ first_ppage_reported = first_ppage;
+ if (iomap->offset == 0)
+ first_ppage_reported++;
+ if (isi->lowest_ppage > first_ppage_reported)
+ isi->lowest_ppage = first_ppage_reported;
+ if (isi->highest_ppage < (next_ppage - 1))
+ isi->highest_ppage = next_ppage - 1;
+
+ /* Add extent, set up for the next call. */
+ error = add_swap_extent(isi->sis, isi->nr_pages, nr_pages, first_ppage);
+ if (error < 0)
+ return error;
+ isi->nr_extents += error;
+ isi->nr_pages += nr_pages;
+ return 0;
+}
+
+/*
+ * Accumulate iomaps for this swap file. We have to accumulate iomaps because
+ * swap only cares about contiguous page-aligned physical extents and makes no
+ * distinction between written and unwritten extents.
+ */
+static loff_t iomap_swapfile_activate_actor(struct inode *inode, loff_t pos,
+ loff_t count, void *data, struct iomap *iomap)
+{
+ struct iomap_swapfile_info *isi = data;
+ int error;
+
+ switch (iomap->type) {
+ case IOMAP_MAPPED:
+ case IOMAP_UNWRITTEN:
+ /* Only real or unwritten extents. */
+ break;
+ case IOMAP_INLINE:
+ /* No inline data. */
+ pr_err("swapon: file is inline\n");
+ return -EINVAL;
+ default:
+ pr_err("swapon: file has unallocated extents\n");
+ return -EINVAL;
+ }
+
+ /* No uncommitted metadata or shared blocks. */
+ if (iomap->flags & IOMAP_F_DIRTY) {
+ pr_err("swapon: file is not committed\n");
+ return -EINVAL;
+ }
+ if (iomap->flags & IOMAP_F_SHARED) {
+ pr_err("swapon: file has shared extents\n");
+ return -EINVAL;
+ }
+
+ /* Only one bdev per swap file. */
+ if (iomap->bdev != isi->sis->bdev) {
+ pr_err("swapon: file is on multiple devices\n");
+ return -EINVAL;
+ }
+
+ if (isi->iomap.length == 0) {
+ /* No accumulated extent, so just store it. */
+ memcpy(&isi->iomap, iomap, sizeof(isi->iomap));
+ } else if (isi->iomap.addr + isi->iomap.length == iomap->addr) {
+ /* Append this to the accumulated extent. */
+ isi->iomap.length += iomap->length;
+ } else {
+ /* Otherwise, add the retained iomap and store this one. */
+ error = iomap_swapfile_add_extent(isi);
+ if (error)
+ return error;
+ memcpy(&isi->iomap, iomap, sizeof(isi->iomap));
+ }
+ return count;
+}
+
+/*
+ * Iterate a swap file's iomaps to construct physical extents that can be
+ * passed to the swapfile subsystem.
+ */
+int iomap_swapfile_activate(struct swap_info_struct *sis,
+ struct file *swap_file, sector_t *pagespan,
+ const struct iomap_ops *ops)
+{
+ struct iomap_swapfile_info isi = {
+ .sis = sis,
+ .lowest_ppage = (sector_t)-1ULL,
+ };
+ struct address_space *mapping = swap_file->f_mapping;
+ struct inode *inode = mapping->host;
+ loff_t pos = 0;
+ loff_t len = ALIGN_DOWN(i_size_read(inode), PAGE_SIZE);
+ loff_t ret;
+
+ ret = filemap_write_and_wait(inode->i_mapping);
+ if (ret)
+ return ret;
+
+ while (len > 0) {
+ ret = iomap_apply(inode, pos, len, IOMAP_REPORT,
+ ops, &isi, iomap_swapfile_activate_actor);
+ if (ret <= 0)
+ return ret;
+
+ pos += ret;
+ len -= ret;
+ }
+
+ if (isi.iomap.length) {
+ ret = iomap_swapfile_add_extent(&isi);
+ if (ret)
+ return ret;
+ }
+
+ *pagespan = 1 + isi.highest_ppage - isi.lowest_ppage;
+ sis->max = isi.nr_pages;
+ sis->pages = isi.nr_pages - 1;
+ sis->highest_bit = isi.nr_pages - 1;
+ return isi.nr_extents;
+}
+EXPORT_SYMBOL_GPL(iomap_swapfile_activate);
+#endif /* CONFIG_SWAP */
+
+static loff_t
+iomap_bmap_actor(struct inode *inode, loff_t pos, loff_t length,
+ void *data, struct iomap *iomap)
+{
+ sector_t *bno = data, addr;
+
+ if (iomap->type == IOMAP_MAPPED) {
+ addr = (pos - iomap->offset + iomap->addr) >> inode->i_blkbits;
+ if (addr > INT_MAX)
+ WARN(1, "would truncate bmap result\n");
+ else
+ *bno = addr;
+ }
+ return 0;
+}
+
+/* legacy ->bmap interface. 0 is the error return (!) */
+sector_t
+iomap_bmap(struct address_space *mapping, sector_t bno,
+ const struct iomap_ops *ops)
+{
+ struct inode *inode = mapping->host;
+ loff_t pos = bno >> inode->i_blkbits;
+ unsigned blocksize = i_blocksize(inode);
+
+ if (filemap_write_and_wait(mapping))
+ return 0;
+
+ bno = 0;
+ iomap_apply(inode, pos, blocksize, 0, ops, &bno, iomap_bmap_actor);
+ return bno;
+}
+EXPORT_SYMBOL_GPL(iomap_bmap);
diff --git a/fs/isofs/compress.c b/fs/isofs/compress.c
index 9bb2fe3..10205ec 100644
--- a/fs/isofs/compress.c
+++ b/fs/isofs/compress.c
@@ -20,6 +20,7 @@
#include <linux/init.h>
#include <linux/bio.h>
+#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/zlib.h>
@@ -59,7 +60,7 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
>> bufshift;
int haveblocks;
blkcnt_t blocknum;
- struct buffer_head *bhs[needblocks + 1];
+ struct buffer_head **bhs;
int curbh, curpage;
if (block_size > deflateBound(1UL << zisofs_block_shift)) {
@@ -80,7 +81,11 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
/* Because zlib is not thread-safe, do all the I/O at the top. */
blocknum = block_start >> bufshift;
- memset(bhs, 0, (needblocks + 1) * sizeof(struct buffer_head *));
+ bhs = kcalloc(needblocks + 1, sizeof(*bhs), GFP_KERNEL);
+ if (!bhs) {
+ *errp = -ENOMEM;
+ return 0;
+ }
haveblocks = isofs_get_blocks(inode, blocknum, bhs, needblocks);
ll_rw_block(REQ_OP_READ, 0, haveblocks, bhs);
@@ -190,6 +195,7 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
b_eio:
for (i = 0; i < haveblocks; i++)
brelse(bhs[i]);
+ kfree(bhs);
return stream.total_out;
}
@@ -305,7 +311,7 @@ static int zisofs_readpage(struct file *file, struct page *page)
unsigned int zisofs_pages_per_cblock =
PAGE_SHIFT <= zisofs_block_shift ?
(1 << (zisofs_block_shift - PAGE_SHIFT)) : 0;
- struct page *pages[max_t(unsigned, zisofs_pages_per_cblock, 1)];
+ struct page **pages;
pgoff_t index = page->index, end_index;
end_index = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT;
@@ -330,6 +336,12 @@ static int zisofs_readpage(struct file *file, struct page *page)
full_page = 0;
pcount = 1;
}
+ pages = kcalloc(max_t(unsigned int, zisofs_pages_per_cblock, 1),
+ sizeof(*pages), GFP_KERNEL);
+ if (!pages) {
+ unlock_page(page);
+ return -ENOMEM;
+ }
pages[full_page] = page;
for (i = 0; i < pcount; i++, index++) {
@@ -357,6 +369,7 @@ static int zisofs_readpage(struct file *file, struct page *page)
}
/* At this point, err contains 0 or -EIO depending on the "critical" page */
+ kfree(pages);
return err;
}
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index bc258a4..ec3fba7 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -394,7 +394,10 @@ static int parse_options(char *options, struct iso9660_options *popt)
break;
#ifdef CONFIG_JOLIET
case Opt_iocharset:
+ kfree(popt->iocharset);
popt->iocharset = match_strdup(&args[0]);
+ if (!popt->iocharset)
+ return 0;
break;
#endif
case Opt_map_a:
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index dfb0579..8ef6b6d 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -114,7 +114,7 @@ void __jbd2_debug(int level, const char *file, const char *func,
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
- printk(KERN_DEBUG "%s: (%s, %u): %pV\n", file, func, line, &vaf);
+ printk(KERN_DEBUG "%s: (%s, %u): %pV", file, func, line, &vaf);
va_end(args);
}
EXPORT_SYMBOL(__jbd2_debug);
@@ -2302,8 +2302,7 @@ static void jbd2_journal_destroy_slabs(void)
int i;
for (i = 0; i < JBD2_MAX_SLABS; i++) {
- if (jbd2_slab[i])
- kmem_cache_destroy(jbd2_slab[i]);
+ kmem_cache_destroy(jbd2_slab[i]);
jbd2_slab[i] = NULL;
}
}
@@ -2404,10 +2403,8 @@ static int jbd2_journal_init_journal_head_cache(void)
static void jbd2_journal_destroy_journal_head_cache(void)
{
- if (jbd2_journal_head_cache) {
- kmem_cache_destroy(jbd2_journal_head_cache);
- jbd2_journal_head_cache = NULL;
- }
+ kmem_cache_destroy(jbd2_journal_head_cache);
+ jbd2_journal_head_cache = NULL;
}
/*
@@ -2665,11 +2662,10 @@ static int __init jbd2_journal_init_handle_cache(void)
static void jbd2_journal_destroy_handle_cache(void)
{
- if (jbd2_handle_cache)
- kmem_cache_destroy(jbd2_handle_cache);
- if (jbd2_inode_cache)
- kmem_cache_destroy(jbd2_inode_cache);
-
+ kmem_cache_destroy(jbd2_handle_cache);
+ jbd2_handle_cache = NULL;
+ kmem_cache_destroy(jbd2_inode_cache);
+ jbd2_inode_cache = NULL;
}
/*
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index 696ef15..240779e 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -180,14 +180,10 @@ static struct jbd2_revoke_record_s *find_revoke_record(journal_t *journal,
void jbd2_journal_destroy_revoke_caches(void)
{
- if (jbd2_revoke_record_cache) {
- kmem_cache_destroy(jbd2_revoke_record_cache);
- jbd2_revoke_record_cache = NULL;
- }
- if (jbd2_revoke_table_cache) {
- kmem_cache_destroy(jbd2_revoke_table_cache);
- jbd2_revoke_table_cache = NULL;
- }
+ kmem_cache_destroy(jbd2_revoke_record_cache);
+ jbd2_revoke_record_cache = NULL;
+ kmem_cache_destroy(jbd2_revoke_table_cache);
+ jbd2_revoke_table_cache = NULL;
}
int __init jbd2_journal_init_revoke_caches(void)
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index ac31103..51dd68e 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -49,10 +49,8 @@ int __init jbd2_journal_init_transaction_cache(void)
void jbd2_journal_destroy_transaction_cache(void)
{
- if (transaction_cache) {
- kmem_cache_destroy(transaction_cache);
- transaction_cache = NULL;
- }
+ kmem_cache_destroy(transaction_cache);
+ transaction_cache = NULL;
}
void jbd2_journal_free_transaction(transaction_t *transaction)
@@ -532,6 +530,7 @@ int jbd2_journal_start_reserved(handle_t *handle, unsigned int type,
*/
ret = start_this_handle(journal, handle, GFP_NOFS);
if (ret < 0) {
+ handle->h_journal = journal;
jbd2_journal_free_reserved(handle);
return ret;
}
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index 0a754f3..e5a6deb 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -209,8 +209,7 @@ static int jffs2_create(struct inode *dir_i, struct dentry *dentry,
__func__, inode->i_ino, inode->i_mode, inode->i_nlink,
f->inocache->pino_nlink, inode->i_mapping->nrpages);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
fail:
@@ -430,8 +429,7 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
mutex_unlock(&dir_f->sem);
jffs2_complete_reservation(c);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
fail:
@@ -575,8 +573,7 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, umode_t mode
mutex_unlock(&dir_f->sem);
jffs2_complete_reservation(c);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
fail:
@@ -747,8 +744,7 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, umode_t mode
mutex_unlock(&dir_f->sem);
jffs2_complete_reservation(c);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
fail:
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index f60dee7..87bdf0f 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -342,7 +342,7 @@ static void jffs2_put_super (struct super_block *sb)
static void jffs2_kill_sb(struct super_block *sb)
{
struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);
- if (!sb_rdonly(sb))
+ if (c && !sb_rdonly(sb))
jffs2_stop_garbage_collect_thread(c);
kill_mtd_super(sb);
kfree(c);
diff --git a/fs/jfs/jfs_debug.c b/fs/jfs/jfs_debug.c
index a709076..35a5b2a 100644
--- a/fs/jfs/jfs_debug.c
+++ b/fs/jfs/jfs_debug.c
@@ -29,7 +29,6 @@
#ifdef PROC_FS_JFS /* see jfs_debug.h */
-static struct proc_dir_entry *base;
#ifdef CONFIG_JFS_DEBUG
static int jfs_loglevel_proc_show(struct seq_file *m, void *v)
{
@@ -66,43 +65,29 @@ static const struct file_operations jfs_loglevel_proc_fops = {
};
#endif
-static struct {
- const char *name;
- const struct file_operations *proc_fops;
-} Entries[] = {
-#ifdef CONFIG_JFS_STATISTICS
- { "lmstats", &jfs_lmstats_proc_fops, },
- { "txstats", &jfs_txstats_proc_fops, },
- { "xtstat", &jfs_xtstat_proc_fops, },
- { "mpstat", &jfs_mpstat_proc_fops, },
-#endif
-#ifdef CONFIG_JFS_DEBUG
- { "TxAnchor", &jfs_txanchor_proc_fops, },
- { "loglevel", &jfs_loglevel_proc_fops }
-#endif
-};
-#define NPROCENT ARRAY_SIZE(Entries)
-
void jfs_proc_init(void)
{
- int i;
+ struct proc_dir_entry *base;
- if (!(base = proc_mkdir("fs/jfs", NULL)))
+ base = proc_mkdir("fs/jfs", NULL);
+ if (!base)
return;
- for (i = 0; i < NPROCENT; i++)
- proc_create(Entries[i].name, 0, base, Entries[i].proc_fops);
+#ifdef CONFIG_JFS_STATISTICS
+ proc_create_single("lmstats", 0, base, jfs_lmstats_proc_show);
+ proc_create_single("txstats", 0, base, jfs_txstats_proc_show);
+ proc_create_single("xtstat", 0, base, jfs_xtstat_proc_show);
+ proc_create_single("mpstat", 0, base, jfs_mpstat_proc_show);
+#endif
+#ifdef CONFIG_JFS_DEBUG
+ proc_create_single("TxAnchor", 0, base, jfs_txanchor_proc_show);
+ proc_create("loglevel", 0, base, &jfs_loglevel_proc_fops);
+#endif
}
void jfs_proc_clean(void)
{
- int i;
-
- if (base) {
- for (i = 0; i < NPROCENT; i++)
- remove_proc_entry(Entries[i].name, base);
- remove_proc_entry("fs/jfs", NULL);
- }
+ remove_proc_subtree("fs/jfs", NULL);
}
#endif /* PROC_FS_JFS */
diff --git a/fs/jfs/jfs_debug.h b/fs/jfs/jfs_debug.h
index eafd130..0d9e35d 100644
--- a/fs/jfs/jfs_debug.h
+++ b/fs/jfs/jfs_debug.h
@@ -62,7 +62,7 @@ extern void jfs_proc_clean(void);
extern int jfsloglevel;
-extern const struct file_operations jfs_txanchor_proc_fops;
+int jfs_txanchor_proc_show(struct seq_file *m, void *v);
/* information message: e.g., configuration, major event */
#define jfs_info(fmt, arg...) do { \
@@ -105,10 +105,10 @@ extern const struct file_operations jfs_txanchor_proc_fops;
* ----------
*/
#ifdef CONFIG_JFS_STATISTICS
-extern const struct file_operations jfs_lmstats_proc_fops;
-extern const struct file_operations jfs_txstats_proc_fops;
-extern const struct file_operations jfs_mpstat_proc_fops;
-extern const struct file_operations jfs_xtstat_proc_fops;
+int jfs_lmstats_proc_show(struct seq_file *m, void *v);
+int jfs_txstats_proc_show(struct seq_file *m, void *v);
+int jfs_mpstat_proc_show(struct seq_file *m, void *v);
+int jfs_xtstat_proc_show(struct seq_file *m, void *v);
#define INCREMENT(x) ((x)++)
#define DECREMENT(x) ((x)--)
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index 0e5d412..6b68df3 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -2493,7 +2493,7 @@ int lmLogFormat(struct jfs_log *log, s64 logAddress, int logSize)
}
#ifdef CONFIG_JFS_STATISTICS
-static int jfs_lmstats_proc_show(struct seq_file *m, void *v)
+int jfs_lmstats_proc_show(struct seq_file *m, void *v)
{
seq_printf(m,
"JFS Logmgr stats\n"
@@ -2510,16 +2510,4 @@ static int jfs_lmstats_proc_show(struct seq_file *m, void *v)
lmStat.partial_page);
return 0;
}
-
-static int jfs_lmstats_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, jfs_lmstats_proc_show, NULL);
-}
-
-const struct file_operations jfs_lmstats_proc_fops = {
- .open = jfs_lmstats_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif /* CONFIG_JFS_STATISTICS */
diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index 1a3b0cc..fa2c682 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -815,7 +815,7 @@ void __invalidate_metapages(struct inode *ip, s64 addr, int len)
}
#ifdef CONFIG_JFS_STATISTICS
-static int jfs_mpstat_proc_show(struct seq_file *m, void *v)
+int jfs_mpstat_proc_show(struct seq_file *m, void *v)
{
seq_printf(m,
"JFS Metapage statistics\n"
@@ -828,16 +828,4 @@ static int jfs_mpstat_proc_show(struct seq_file *m, void *v)
mpStat.lockwait);
return 0;
}
-
-static int jfs_mpstat_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, jfs_mpstat_proc_show, NULL);
-}
-
-const struct file_operations jfs_mpstat_proc_fops = {
- .open = jfs_mpstat_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif
diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c
index 4d973524..a5663cb 100644
--- a/fs/jfs/jfs_txnmgr.c
+++ b/fs/jfs/jfs_txnmgr.c
@@ -2998,7 +2998,7 @@ int jfs_sync(void *arg)
}
#if defined(CONFIG_PROC_FS) && defined(CONFIG_JFS_DEBUG)
-static int jfs_txanchor_proc_show(struct seq_file *m, void *v)
+int jfs_txanchor_proc_show(struct seq_file *m, void *v)
{
char *freewait;
char *freelockwait;
@@ -3032,22 +3032,10 @@ static int jfs_txanchor_proc_show(struct seq_file *m, void *v)
list_empty(&TxAnchor.unlock_queue) ? "" : "not ");
return 0;
}
-
-static int jfs_txanchor_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, jfs_txanchor_proc_show, NULL);
-}
-
-const struct file_operations jfs_txanchor_proc_fops = {
- .open = jfs_txanchor_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif
#if defined(CONFIG_PROC_FS) && defined(CONFIG_JFS_STATISTICS)
-static int jfs_txstats_proc_show(struct seq_file *m, void *v)
+int jfs_txstats_proc_show(struct seq_file *m, void *v)
{
seq_printf(m,
"JFS TxStats\n"
@@ -3072,16 +3060,4 @@ static int jfs_txstats_proc_show(struct seq_file *m, void *v)
TxStat.txLockAlloc_freelock);
return 0;
}
-
-static int jfs_txstats_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, jfs_txstats_proc_show, NULL);
-}
-
-const struct file_operations jfs_txstats_proc_fops = {
- .open = jfs_txstats_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif
diff --git a/fs/jfs/jfs_xtree.c b/fs/jfs/jfs_xtree.c
index 5cde6d2..2c200b5 100644
--- a/fs/jfs/jfs_xtree.c
+++ b/fs/jfs/jfs_xtree.c
@@ -3874,7 +3874,7 @@ s64 xtTruncate_pmap(tid_t tid, struct inode *ip, s64 committed_size)
}
#ifdef CONFIG_JFS_STATISTICS
-static int jfs_xtstat_proc_show(struct seq_file *m, void *v)
+int jfs_xtstat_proc_show(struct seq_file *m, void *v)
{
seq_printf(m,
"JFS Xtree statistics\n"
@@ -3887,16 +3887,4 @@ static int jfs_xtstat_proc_show(struct seq_file *m, void *v)
xtStat.split);
return 0;
}
-
-static int jfs_xtstat_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, jfs_xtstat_proc_show, NULL);
-}
-
-const struct file_operations jfs_xtstat_proc_fops = {
- .open = jfs_xtstat_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index b41596d..56c3fcb 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -178,8 +178,7 @@ static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode,
unlock_new_inode(ip);
iput(ip);
} else {
- unlock_new_inode(ip);
- d_instantiate(dentry, ip);
+ d_instantiate_new(dentry, ip);
}
out2:
@@ -313,8 +312,7 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, umode_t mode)
unlock_new_inode(ip);
iput(ip);
} else {
- unlock_new_inode(ip);
- d_instantiate(dentry, ip);
+ d_instantiate_new(dentry, ip);
}
out2:
@@ -1059,8 +1057,7 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry,
unlock_new_inode(ip);
iput(ip);
} else {
- unlock_new_inode(ip);
- d_instantiate(dentry, ip);
+ d_instantiate_new(dentry, ip);
}
out2:
@@ -1447,8 +1444,7 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry,
unlock_new_inode(ip);
iput(ip);
} else {
- unlock_new_inode(ip);
- d_instantiate(dentry, ip);
+ d_instantiate_new(dentry, ip);
}
out1:
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 26dd9a5..ff2716f 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -316,6 +316,7 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
info->root = root;
info->ns = ns;
+ INIT_LIST_HEAD(&info->node);
sb = sget_userns(fs_type, kernfs_test_super, kernfs_set_super, flags,
&init_user_ns, info);
diff --git a/fs/locks.c b/fs/locks.c
index 62bbe8b..05e211be 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2788,22 +2788,10 @@ static const struct seq_operations locks_seq_operations = {
.show = locks_show,
};
-static int locks_open(struct inode *inode, struct file *filp)
-{
- return seq_open_private(filp, &locks_seq_operations,
- sizeof(struct locks_iterator));
-}
-
-static const struct file_operations proc_locks_operations = {
- .open = locks_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_private,
-};
-
static int __init proc_locks_init(void)
{
- proc_create("locks", 0, NULL, &proc_locks_operations);
+ proc_create_seq_private("locks", 0, NULL, &locks_seq_operations,
+ sizeof(struct locks_iterator), NULL);
return 0;
}
fs_initcall(proc_locks_init);
diff --git a/fs/minix/namei.c b/fs/minix/namei.c
index ccf0f00..1a6084d 100644
--- a/fs/minix/namei.c
+++ b/fs/minix/namei.c
@@ -28,13 +28,9 @@ static struct dentry *minix_lookup(struct inode * dir, struct dentry *dentry, un
return ERR_PTR(-ENAMETOOLONG);
ino = minix_inode_by_name(dentry);
- if (ino) {
+ if (ino)
inode = minix_iget(dir->i_sb, ino);
- if (IS_ERR(inode))
- return ERR_CAST(inode);
- }
- d_add(dentry, inode);
- return NULL;
+ return d_splice_alias(inode, dentry);
}
static int minix_mknod(struct inode * dir, struct dentry *dentry, umode_t mode, dev_t rdev)
diff --git a/fs/namei.c b/fs/namei.c
index 186bd24..6df1f61 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -984,13 +984,15 @@ static bool safe_hardlink_source(struct inode *inode)
*/
static int may_linkat(struct path *link)
{
- struct inode *inode;
+ struct inode *inode = link->dentry->d_inode;
+
+ /* Inode writeback is not safe when the uid or gid are invalid. */
+ if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid))
+ return -EOVERFLOW;
if (!sysctl_protected_hardlinks)
return 0;
- inode = link->dentry->d_inode;
-
/* Source inode owner (or CAP_FOWNER) can hardlink all they like,
* otherwise, it must be a safe source.
*/
@@ -1438,10 +1440,8 @@ static int path_parent_directory(struct path *path)
static int follow_dotdot(struct nameidata *nd)
{
while(1) {
- if (nd->path.dentry == nd->root.dentry &&
- nd->path.mnt == nd->root.mnt) {
+ if (path_equal(&nd->path, &nd->root))
break;
- }
if (nd->path.dentry != nd->path.mnt->mnt_root) {
int ret = path_parent_directory(&nd->path);
if (ret)
@@ -2749,6 +2749,11 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
BUG_ON(!inode);
BUG_ON(victim->d_parent->d_inode != dir);
+
+ /* Inode writeback is not safe when the uid or gid are invalid. */
+ if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid))
+ return -EOVERFLOW;
+
audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
@@ -3367,7 +3372,9 @@ static int do_last(struct nameidata *nd,
goto out;
*opened |= FILE_OPENED;
opened:
- error = ima_file_check(file, op->acc_mode, *opened);
+ error = open_check_o_direct(file);
+ if (!error)
+ error = ima_file_check(file, op->acc_mode, *opened);
if (!error && will_truncate)
error = handle_truncate(file);
out:
@@ -3447,6 +3454,9 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
error = finish_open(file, child, NULL, opened);
if (error)
goto out2;
+ error = open_check_o_direct(file);
+ if (error)
+ fput(file);
out2:
mnt_drop_write(path.mnt);
out:
@@ -3672,7 +3682,8 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
if (error)
return error;
- if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD))
+ if ((S_ISCHR(mode) || S_ISBLK(mode)) &&
+ !ns_capable(dentry->d_sb->s_user_ns, CAP_MKNOD))
return -EPERM;
if (!dir->i_op->mknod)
@@ -3847,11 +3858,11 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
if (error)
goto out;
- shrink_dcache_parent(dentry);
error = dir->i_op->rmdir(dir, dentry);
if (error)
goto out;
+ shrink_dcache_parent(dentry);
dentry->d_inode->i_flags |= S_DEAD;
dont_mount(dentry);
detach_mounts(dentry);
@@ -4434,8 +4445,6 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
old_dir->i_nlink >= max_links)
goto out;
}
- if (is_dir && !(flags & RENAME_EXCHANGE) && target)
- shrink_dcache_parent(new_dentry);
if (!is_dir) {
error = try_break_deleg(source, delegated_inode);
if (error)
@@ -4452,8 +4461,10 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
goto out;
if (!(flags & RENAME_EXCHANGE) && target) {
- if (is_dir)
+ if (is_dir) {
+ shrink_dcache_parent(new_dentry);
target->i_flags |= S_DEAD;
+ }
dont_mount(new_dentry);
detach_mounts(new_dentry);
}
diff --git a/fs/namespace.c b/fs/namespace.c
index e398f32..8ddd148 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1089,7 +1089,8 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
goto out_free;
}
- mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~(MNT_WRITE_HOLD|MNT_MARKED);
+ mnt->mnt.mnt_flags = old->mnt.mnt_flags;
+ mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL);
/* Don't allow unprivileged users to change mount flags */
if (flag & CL_UNPRIVILEGED) {
mnt->mnt.mnt_flags |= MNT_LOCK_ATIME;
@@ -1589,7 +1590,7 @@ static int do_umount(struct mount *mnt, int flags)
* Special case for "unmounting" root ...
* we just try to remount it readonly.
*/
- if (!capable(CAP_SYS_ADMIN))
+ if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN))
return -EPERM;
down_write(&sb->s_umount);
if (!sb_rdonly(sb))
@@ -2332,7 +2333,7 @@ static int do_remount(struct path *path, int ms_flags, int sb_flags,
down_write(&sb->s_umount);
if (ms_flags & MS_BIND)
err = change_mount_flags(path->mnt, ms_flags);
- else if (!capable(CAP_SYS_ADMIN))
+ else if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN))
err = -EPERM;
else
err = do_remount_sb(sb, sb_flags, data, 0);
@@ -2814,7 +2815,7 @@ long do_mount(const char *dev_name, const char __user *dir_name,
mnt_flags |= MNT_NODIRATIME;
if (flags & MS_STRICTATIME)
mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME);
- if (flags & SB_RDONLY)
+ if (flags & MS_RDONLY)
mnt_flags |= MNT_READONLY;
/* The default atime for remount is preservation */
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index b9129e2..bbc91d7 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -1067,7 +1067,6 @@ void nfs_clients_init(struct net *net)
}
#ifdef CONFIG_PROC_FS
-static int nfs_server_list_open(struct inode *inode, struct file *file);
static void *nfs_server_list_start(struct seq_file *p, loff_t *pos);
static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos);
static void nfs_server_list_stop(struct seq_file *p, void *v);
@@ -1080,14 +1079,6 @@ static const struct seq_operations nfs_server_list_ops = {
.show = nfs_server_list_show,
};
-static const struct file_operations nfs_server_list_fops = {
- .open = nfs_server_list_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
-static int nfs_volume_list_open(struct inode *inode, struct file *file);
static void *nfs_volume_list_start(struct seq_file *p, loff_t *pos);
static void *nfs_volume_list_next(struct seq_file *p, void *v, loff_t *pos);
static void nfs_volume_list_stop(struct seq_file *p, void *v);
@@ -1100,23 +1091,6 @@ static const struct seq_operations nfs_volume_list_ops = {
.show = nfs_volume_list_show,
};
-static const struct file_operations nfs_volume_list_fops = {
- .open = nfs_volume_list_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
-/*
- * open "/proc/fs/nfsfs/servers" which provides a summary of servers with which
- * we're dealing
- */
-static int nfs_server_list_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &nfs_server_list_ops,
- sizeof(struct seq_net_private));
-}
-
/*
* set up the iterator to start reading from the server list and return the first item
*/
@@ -1185,15 +1159,6 @@ static int nfs_server_list_show(struct seq_file *m, void *v)
}
/*
- * open "/proc/fs/nfsfs/volumes" which provides a summary of extant volumes
- */
-static int nfs_volume_list_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &nfs_volume_list_ops,
- sizeof(struct seq_net_private));
-}
-
-/*
* set up the iterator to start reading from the volume list and return the first item
*/
static void *nfs_volume_list_start(struct seq_file *m, loff_t *_pos)
@@ -1278,14 +1243,14 @@ int nfs_fs_proc_net_init(struct net *net)
goto error_0;
/* a file of servers with which we're dealing */
- p = proc_create("servers", S_IFREG|S_IRUGO,
- nn->proc_nfsfs, &nfs_server_list_fops);
+ p = proc_create_net("servers", S_IFREG|S_IRUGO, nn->proc_nfsfs,
+ &nfs_server_list_ops, sizeof(struct seq_net_private));
if (!p)
goto error_1;
/* a file of volumes that we have mounted */
- p = proc_create("volumes", S_IFREG|S_IRUGO,
- nn->proc_nfsfs, &nfs_volume_list_fops);
+ p = proc_create_net("volumes", S_IFREG|S_IRUGO, nn->proc_nfsfs,
+ &nfs_volume_list_ops, sizeof(struct seq_net_private));
if (!p)
goto error_1;
return 0;
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index 70b8bf7..a43dfed 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -227,7 +227,7 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev,
if (!buf)
return -ENOMEM;
- rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL);
+ rq = blk_get_request(q, REQ_OP_SCSI_IN, 0);
if (IS_ERR(rq)) {
error = -ENOMEM;
goto out_free_buf;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 2410b09..b0555d7 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1201,6 +1201,28 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
break;
case S_IFDIR:
host_err = vfs_mkdir(dirp, dchild, iap->ia_mode);
+ if (!host_err && unlikely(d_unhashed(dchild))) {
+ struct dentry *d;
+ d = lookup_one_len(dchild->d_name.name,
+ dchild->d_parent,
+ dchild->d_name.len);
+ if (IS_ERR(d)) {
+ host_err = PTR_ERR(d);
+ break;
+ }
+ if (unlikely(d_is_negative(d))) {
+ dput(d);
+ err = nfserr_serverfault;
+ goto out;
+ }
+ dput(resfhp->fh_dentry);
+ resfhp->fh_dentry = dget(d);
+ err = fh_update(resfhp);
+ dput(dchild);
+ dchild = d;
+ if (err)
+ goto out;
+ }
break;
case S_IFCHR:
case S_IFBLK:
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 1a2894a..dd52d3f 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -46,8 +46,7 @@ static inline int nilfs_add_nondir(struct dentry *dentry, struct inode *inode)
int err = nilfs_add_link(dentry, inode);
if (!err) {
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
return 0;
}
inode_dec_link_count(inode);
@@ -243,8 +242,7 @@ static int nilfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
goto out_fail;
nilfs_mark_inode_dirty(inode);
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
out:
if (!err)
err = nilfs_transaction_commit(dir->i_sb);
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index d51e1bb..d94e803 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -92,7 +92,7 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark,
u32 event_mask,
const void *data, int data_type)
{
- __u32 marks_mask, marks_ignored_mask;
+ __u32 marks_mask = 0, marks_ignored_mask = 0;
const struct path *path = data;
pr_debug("%s: inode_mark=%p vfsmnt_mark=%p mask=%x data=%p"
@@ -108,24 +108,20 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark,
!d_can_lookup(path->dentry))
return false;
- if (inode_mark && vfsmnt_mark) {
- marks_mask = (vfsmnt_mark->mask | inode_mark->mask);
- marks_ignored_mask = (vfsmnt_mark->ignored_mask | inode_mark->ignored_mask);
- } else if (inode_mark) {
- /*
- * if the event is for a child and this inode doesn't care about
- * events on the child, don't send it!
- */
- if ((event_mask & FS_EVENT_ON_CHILD) &&
- !(inode_mark->mask & FS_EVENT_ON_CHILD))
- return false;
- marks_mask = inode_mark->mask;
- marks_ignored_mask = inode_mark->ignored_mask;
- } else if (vfsmnt_mark) {
- marks_mask = vfsmnt_mark->mask;
- marks_ignored_mask = vfsmnt_mark->ignored_mask;
- } else {
- BUG();
+ /*
+ * if the event is for a child and this inode doesn't care about
+ * events on the child, don't send it!
+ */
+ if (inode_mark &&
+ (!(event_mask & FS_EVENT_ON_CHILD) ||
+ (inode_mark->mask & FS_EVENT_ON_CHILD))) {
+ marks_mask |= inode_mark->mask;
+ marks_ignored_mask |= inode_mark->ignored_mask;
+ }
+
+ if (vfsmnt_mark) {
+ marks_mask |= vfsmnt_mark->mask;
+ marks_ignored_mask |= vfsmnt_mark->ignored_mask;
}
if (d_is_dir(path->dentry) &&
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 219b269..613ec7e 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -192,8 +192,9 @@ static int send_to_group(struct inode *to_tell,
struct fsnotify_iter_info *iter_info)
{
struct fsnotify_group *group = NULL;
- __u32 inode_test_mask = 0;
- __u32 vfsmount_test_mask = 0;
+ __u32 test_mask = (mask & ~FS_EVENT_ON_CHILD);
+ __u32 marks_mask = 0;
+ __u32 marks_ignored_mask = 0;
if (unlikely(!inode_mark && !vfsmount_mark)) {
BUG();
@@ -213,29 +214,25 @@ static int send_to_group(struct inode *to_tell,
/* does the inode mark tell us to do something? */
if (inode_mark) {
group = inode_mark->group;
- inode_test_mask = (mask & ~FS_EVENT_ON_CHILD);
- inode_test_mask &= inode_mark->mask;
- inode_test_mask &= ~inode_mark->ignored_mask;
+ marks_mask |= inode_mark->mask;
+ marks_ignored_mask |= inode_mark->ignored_mask;
}
/* does the vfsmount_mark tell us to do something? */
if (vfsmount_mark) {
- vfsmount_test_mask = (mask & ~FS_EVENT_ON_CHILD);
group = vfsmount_mark->group;
- vfsmount_test_mask &= vfsmount_mark->mask;
- vfsmount_test_mask &= ~vfsmount_mark->ignored_mask;
- if (inode_mark)
- vfsmount_test_mask &= ~inode_mark->ignored_mask;
+ marks_mask |= vfsmount_mark->mask;
+ marks_ignored_mask |= vfsmount_mark->ignored_mask;
}
pr_debug("%s: group=%p to_tell=%p mask=%x inode_mark=%p"
- " inode_test_mask=%x vfsmount_mark=%p vfsmount_test_mask=%x"
+ " vfsmount_mark=%p marks_mask=%x marks_ignored_mask=%x"
" data=%p data_is=%d cookie=%d\n",
- __func__, group, to_tell, mask, inode_mark,
- inode_test_mask, vfsmount_mark, vfsmount_test_mask, data,
+ __func__, group, to_tell, mask, inode_mark, vfsmount_mark,
+ marks_mask, marks_ignored_mask, data,
data_is, cookie);
- if (!inode_test_mask && !vfsmount_test_mask)
+ if (!(test_mask & marks_mask & ~marks_ignored_mask))
return 0;
return group->ops->handle_event(group, to_tell, inode_mark,
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 91a8889..ea8c551 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -570,16 +570,7 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
current_page, vec_len, vec_start);
len = bio_add_page(bio, page, vec_len, vec_start);
- if (len != vec_len) {
- mlog(ML_ERROR, "Adding page[%d] to bio failed, "
- "page %p, len %d, vec_len %u, vec_start %u, "
- "bi_sector %llu\n", current_page, page, len,
- vec_len, vec_start,
- (unsigned long long)bio->bi_iter.bi_sector);
- bio_put(bio);
- bio = ERR_PTR(-EIO);
- return bio;
- }
+ if (len != vec_len) break;
cs += vec_len / (PAGE_SIZE/spp);
vec_start = 0;
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 01c6b38..7869622 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4250,10 +4250,11 @@ static int __ocfs2_reflink(struct dentry *old_dentry,
static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
struct dentry *new_dentry, bool preserve)
{
- int error;
+ int error, had_lock;
struct inode *inode = d_inode(old_dentry);
struct buffer_head *old_bh = NULL;
struct inode *new_orphan_inode = NULL;
+ struct ocfs2_lock_holder oh;
if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb)))
return -EOPNOTSUPP;
@@ -4295,6 +4296,14 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
goto out;
}
+ had_lock = ocfs2_inode_lock_tracker(new_orphan_inode, NULL, 1,
+ &oh);
+ if (had_lock < 0) {
+ error = had_lock;
+ mlog_errno(error);
+ goto out;
+ }
+
/* If the security isn't preserved, we need to re-initialize them. */
if (!preserve) {
error = ocfs2_init_security_and_acl(dir, new_orphan_inode,
@@ -4302,14 +4311,15 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
if (error)
mlog_errno(error);
}
-out:
if (!error) {
error = ocfs2_mv_orphaned_inode_to_new(dir, new_orphan_inode,
new_dentry);
if (error)
mlog_errno(error);
}
+ ocfs2_inode_unlock_tracker(new_orphan_inode, 1, &oh, had_lock);
+out:
if (new_orphan_inode) {
/*
* We need to open_unlock the inode no matter whether we
diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c
index b714652..4bee3a7 100644
--- a/fs/omfs/dir.c
+++ b/fs/omfs/dir.c
@@ -305,11 +305,10 @@ static struct dentry *omfs_lookup(struct inode *dir, struct dentry *dentry,
ino_t ino = be64_to_cpu(oi->i_head.h_self);
brelse(bh);
inode = omfs_iget(dir->i_sb, ino);
- if (IS_ERR(inode))
- return ERR_CAST(inode);
+ } else if (bh != ERR_PTR(-ENOENT)) {
+ inode = ERR_CAST(bh);
}
- d_add(dentry, inode);
- return NULL;
+ return d_splice_alias(inode, dentry);
}
/* sanity check block's self pointer */
diff --git a/fs/open.c b/fs/open.c
index c5ee7cd..d0e955b 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -724,6 +724,16 @@ SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
return ksys_fchown(fd, user, group);
}
+int open_check_o_direct(struct file *f)
+{
+ /* NB: we're sure to have correct a_ops only after f_op->open */
+ if (f->f_flags & O_DIRECT) {
+ if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
+ return -EINVAL;
+ }
+ return 0;
+}
+
static int do_dentry_open(struct file *f,
struct inode *inode,
int (*open)(struct inode *, struct file *),
@@ -745,7 +755,7 @@ static int do_dentry_open(struct file *f,
if (unlikely(f->f_flags & O_PATH)) {
f->f_mode = FMODE_PATH;
f->f_op = &empty_fops;
- goto done;
+ return 0;
}
if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) {
@@ -798,12 +808,7 @@ static int do_dentry_open(struct file *f,
f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
-done:
- /* NB: we're sure to have correct a_ops only after f_op->open */
- error = -EINVAL;
- if ((f->f_flags & O_DIRECT) &&
- (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO))
- goto out_fput;
+
return 0;
cleanup_all:
@@ -818,9 +823,6 @@ static int do_dentry_open(struct file *f,
f->f_path.dentry = NULL;
f->f_inode = NULL;
return error;
-out_fput:
- fput(f);
- return error;
}
/**
@@ -918,14 +920,20 @@ struct file *dentry_open(const struct path *path, int flags,
BUG_ON(!path->mnt);
f = get_empty_filp();
- if (IS_ERR(f))
- return f;
-
- f->f_flags = flags;
- error = vfs_open(path, f, cred);
- if (error) {
- put_filp(f);
- return ERR_PTR(error);
+ if (!IS_ERR(f)) {
+ f->f_flags = flags;
+ error = vfs_open(path, f, cred);
+ if (!error) {
+ /* from now on we need fput() to dispose of f */
+ error = open_check_o_direct(f);
+ if (error) {
+ fput(f);
+ f = ERR_PTR(error);
+ }
+ } else {
+ put_filp(f);
+ f = ERR_PTR(error);
+ }
}
return f;
}
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index 2200662..607092f 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -256,8 +256,7 @@ static struct dentry *openpromfs_lookup(struct inode *dir, struct dentry *dentry
break;
}
- d_add(dentry, inode);
- return NULL;
+ return d_splice_alias(inode, dentry);
}
static int openpromfs_readdir(struct file *file, struct dir_context *ctx)
diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c
index 6e3134e..365cd73 100644
--- a/fs/orangefs/namei.c
+++ b/fs/orangefs/namei.c
@@ -75,8 +75,7 @@ static int orangefs_create(struct inode *dir,
get_khandle_from_ino(inode),
dentry);
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
orangefs_set_timeout(dentry);
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
ORANGEFS_I(inode)->getattr_mask = STATX_BASIC_STATS;
@@ -111,7 +110,6 @@ static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry,
struct orangefs_inode_s *parent = ORANGEFS_I(dir);
struct orangefs_kernel_op_s *new_op;
struct inode *inode;
- struct dentry *res;
int ret = -EINVAL;
/*
@@ -159,65 +157,18 @@ static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry,
new_op->downcall.resp.lookup.refn.fs_id,
ret);
- if (ret < 0) {
- if (ret == -ENOENT) {
- /*
- * if no inode was found, add a negative dentry to
- * dcache anyway; if we don't, we don't hold expected
- * lookup semantics and we most noticeably break
- * during directory renames.
- *
- * however, if the operation failed or exited, do not
- * add the dentry (e.g. in the case that a touch is
- * issued on a file that already exists that was
- * interrupted during this lookup -- no need to add
- * another negative dentry for an existing file)
- */
-
- gossip_debug(GOSSIP_NAME_DEBUG,
- "orangefs_lookup: Adding *negative* dentry "
- "%p for %pd\n",
- dentry,
- dentry);
-
- d_add(dentry, NULL);
- res = NULL;
- goto out;
- }
-
+ if (ret >= 0) {
+ orangefs_set_timeout(dentry);
+ inode = orangefs_iget(dir->i_sb, &new_op->downcall.resp.lookup.refn);
+ } else if (ret == -ENOENT) {
+ inode = NULL;
+ } else {
/* must be a non-recoverable error */
- res = ERR_PTR(ret);
- goto out;
+ inode = ERR_PTR(ret);
}
- orangefs_set_timeout(dentry);
-
- inode = orangefs_iget(dir->i_sb, &new_op->downcall.resp.lookup.refn);
- if (IS_ERR(inode)) {
- gossip_debug(GOSSIP_NAME_DEBUG,
- "error %ld from iget\n", PTR_ERR(inode));
- res = ERR_CAST(inode);
- goto out;
- }
-
- gossip_debug(GOSSIP_NAME_DEBUG,
- "%s:%s:%d "
- "Found good inode [%lu] with count [%d]\n",
- __FILE__,
- __func__,
- __LINE__,
- inode->i_ino,
- (int)atomic_read(&inode->i_count));
-
- /* update dentry/inode pair into dcache */
- res = d_splice_alias(inode, dentry);
-
- gossip_debug(GOSSIP_NAME_DEBUG,
- "Lookup success (inode ct = %d)\n",
- (int)atomic_read(&inode->i_count));
-out:
op_release(new_op);
- return res;
+ return d_splice_alias(inode, dentry);
}
/* return 0 on success; non-zero otherwise */
@@ -332,8 +283,7 @@ static int orangefs_symlink(struct inode *dir,
"Assigned symlink inode new number of %pU\n",
get_khandle_from_ino(inode));
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
orangefs_set_timeout(dentry);
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
ORANGEFS_I(inode)->getattr_mask = STATX_BASIC_STATS;
@@ -402,8 +352,7 @@ static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
"Assigned dir inode new number of %pU\n",
get_khandle_from_ino(inode));
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
orangefs_set_timeout(dentry);
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
ORANGEFS_I(inode)->getattr_mask = STATX_BASIC_STATS;
diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c
index 3ae5fdb..10796d3 100644
--- a/fs/orangefs/super.c
+++ b/fs/orangefs/super.c
@@ -579,6 +579,11 @@ void orangefs_kill_sb(struct super_block *sb)
/* provided sb cleanup */
kill_anon_super(sb);
+ if (!ORANGEFS_SB(sb)) {
+ mutex_lock(&orangefs_request_mutex);
+ mutex_unlock(&orangefs_request_mutex);
+ return;
+ }
/*
* issue the unmount to userspace to tell it to remove the
* dynamic mount info it has for this superblock
diff --git a/fs/pipe.c b/fs/pipe.c
index 39d6f43..bb0840e 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -509,19 +509,22 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
}
}
-/* No kernel lock held - fine */
-static __poll_t
-pipe_poll(struct file *filp, poll_table *wait)
+static struct wait_queue_head *
+pipe_get_poll_head(struct file *filp, __poll_t events)
{
- __poll_t mask;
struct pipe_inode_info *pipe = filp->private_data;
- int nrbufs;
- poll_wait(filp, &pipe->wait, wait);
+ return &pipe->wait;
+}
+
+/* No kernel lock held - fine */
+static __poll_t pipe_poll_mask(struct file *filp, __poll_t events)
+{
+ struct pipe_inode_info *pipe = filp->private_data;
+ int nrbufs = pipe->nrbufs;
+ __poll_t mask = 0;
/* Reading only -- no need for acquiring the semaphore. */
- nrbufs = pipe->nrbufs;
- mask = 0;
if (filp->f_mode & FMODE_READ) {
mask = (nrbufs > 0) ? EPOLLIN | EPOLLRDNORM : 0;
if (!pipe->writers && filp->f_version != pipe->w_counter)
@@ -1020,7 +1023,8 @@ const struct file_operations pipefifo_fops = {
.llseek = no_llseek,
.read_iter = pipe_read,
.write_iter = pipe_write,
- .poll = pipe_poll,
+ .get_poll_head = pipe_get_poll_head,
+ .poll_mask = pipe_poll_mask,
.unlocked_ioctl = pipe_ioctl,
.release = pipe_release,
.fasync = pipe_fasync,
diff --git a/fs/proc/array.c b/fs/proc/array.c
index ae2c807..e6d7f41 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -85,6 +85,7 @@
#include <linux/delayacct.h>
#include <linux/seq_file.h>
#include <linux/pid_namespace.h>
+#include <linux/prctl.h>
#include <linux/ptrace.h>
#include <linux/tracehook.h>
#include <linux/string_helpers.h>
@@ -335,6 +336,30 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p)
#ifdef CONFIG_SECCOMP
seq_put_decimal_ull(m, "\nSeccomp:\t", p->seccomp.mode);
#endif
+ seq_printf(m, "\nSpeculation_Store_Bypass:\t");
+ switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) {
+ case -EINVAL:
+ seq_printf(m, "unknown");
+ break;
+ case PR_SPEC_NOT_AFFECTED:
+ seq_printf(m, "not vulnerable");
+ break;
+ case PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE:
+ seq_printf(m, "thread force mitigated");
+ break;
+ case PR_SPEC_PRCTL | PR_SPEC_DISABLE:
+ seq_printf(m, "thread mitigated");
+ break;
+ case PR_SPEC_PRCTL | PR_SPEC_ENABLE:
+ seq_printf(m, "thread vulnerable");
+ break;
+ case PR_SPEC_DISABLE:
+ seq_printf(m, "globally mitigated");
+ break;
+ default:
+ seq_printf(m, "vulnerable");
+ break;
+ }
seq_putc(m, '\n');
}
@@ -677,25 +702,22 @@ get_children_pid(struct inode *inode, struct pid *pid_prev, loff_t pos)
static int children_seq_show(struct seq_file *seq, void *v)
{
- struct inode *inode = seq->private;
- pid_t pid;
+ struct inode *inode = file_inode(seq->file);
- pid = pid_nr_ns(v, inode->i_sb->s_fs_info);
- seq_printf(seq, "%d ", pid);
-
+ seq_printf(seq, "%d ", pid_nr_ns(v, proc_pid_ns(inode)));
return 0;
}
static void *children_seq_start(struct seq_file *seq, loff_t *pos)
{
- return get_children_pid(seq->private, NULL, *pos);
+ return get_children_pid(file_inode(seq->file), NULL, *pos);
}
static void *children_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct pid *pid;
- pid = get_children_pid(seq->private, v, *pos + 1);
+ pid = get_children_pid(file_inode(seq->file), v, *pos + 1);
put_pid(v);
++*pos;
@@ -716,17 +738,7 @@ static const struct seq_operations children_seq_ops = {
static int children_seq_open(struct inode *inode, struct file *file)
{
- struct seq_file *m;
- int ret;
-
- ret = seq_open(file, &children_seq_ops);
- if (ret)
- return ret;
-
- m = file->private_data;
- m->private = inode;
-
- return ret;
+ return seq_open(file, &children_seq_ops);
}
const struct file_operations proc_tid_children_operations = {
diff --git a/fs/proc/base.c b/fs/proc/base.c
index eafa39a..33ed1746 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -261,7 +261,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
* Inherently racy -- command line shares address space
* with code and data.
*/
- rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0);
+ rv = access_remote_vm(mm, arg_end - 1, &c, 1, FOLL_ANON);
if (rv <= 0)
goto out_free_page;
@@ -279,7 +279,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
int nr_read;
_count = min3(count, len, PAGE_SIZE);
- nr_read = access_remote_vm(mm, p, page, _count, 0);
+ nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON);
if (nr_read < 0)
rv = nr_read;
if (nr_read <= 0)
@@ -325,7 +325,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
bool final;
_count = min3(count, len, PAGE_SIZE);
- nr_read = access_remote_vm(mm, p, page, _count, 0);
+ nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON);
if (nr_read < 0)
rv = nr_read;
if (nr_read <= 0)
@@ -698,7 +698,7 @@ static bool has_pid_permissions(struct pid_namespace *pid,
static int proc_pid_permission(struct inode *inode, int mask)
{
- struct pid_namespace *pid = inode->i_sb->s_fs_info;
+ struct pid_namespace *pid = proc_pid_ns(inode);
struct task_struct *task;
bool has_perms;
@@ -733,13 +733,11 @@ static const struct inode_operations proc_def_inode_operations = {
static int proc_single_show(struct seq_file *m, void *v)
{
struct inode *inode = m->private;
- struct pid_namespace *ns;
- struct pid *pid;
+ struct pid_namespace *ns = proc_pid_ns(inode);
+ struct pid *pid = proc_pid(inode);
struct task_struct *task;
int ret;
- ns = inode->i_sb->s_fs_info;
- pid = proc_pid(inode);
task = get_pid_task(pid, PIDTYPE_PID);
if (!task)
return -ESRCH;
@@ -946,7 +944,7 @@ static ssize_t environ_read(struct file *file, char __user *buf,
max_len = min_t(size_t, PAGE_SIZE, count);
this_len = min(max_len, this_len);
- retval = access_remote_vm(mm, (env_start + src), page, this_len, 0);
+ retval = access_remote_vm(mm, (env_start + src), page, this_len, FOLL_ANON);
if (retval <= 0) {
ret = retval;
@@ -1410,7 +1408,7 @@ static const struct file_operations proc_fail_nth_operations = {
static int sched_show(struct seq_file *m, void *v)
{
struct inode *inode = m->private;
- struct pid_namespace *ns = inode->i_sb->s_fs_info;
+ struct pid_namespace *ns = proc_pid_ns(inode);
struct task_struct *p;
p = get_proc_task(inode);
@@ -1693,6 +1691,12 @@ void task_dump_owner(struct task_struct *task, umode_t mode,
kuid_t uid;
kgid_t gid;
+ if (unlikely(task->flags & PF_KTHREAD)) {
+ *ruid = GLOBAL_ROOT_UID;
+ *rgid = GLOBAL_ROOT_GID;
+ return;
+ }
+
/* Default to the tasks effective ownership */
rcu_read_lock();
cred = __task_cred(task);
@@ -1776,8 +1780,8 @@ int pid_getattr(const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
+ struct pid_namespace *pid = proc_pid_ns(inode);
struct task_struct *task;
- struct pid_namespace *pid = path->dentry->d_sb->s_fs_info;
generic_fillattr(inode, stat);
@@ -1803,15 +1807,22 @@ int pid_getattr(const struct path *path, struct kstat *stat,
/* dentry stuff */
/*
- * Exceptional case: normally we are not allowed to unhash a busy
- * directory. In this case, however, we can do it - no aliasing problems
- * due to the way we treat inodes.
- *
+ * Set <pid>/... inode ownership (can change due to setuid(), etc.)
+ */
+void pid_update_inode(struct task_struct *task, struct inode *inode)
+{
+ task_dump_owner(task, inode->i_mode, &inode->i_uid, &inode->i_gid);
+
+ inode->i_mode &= ~(S_ISUID | S_ISGID);
+ security_task_to_inode(task, inode);
+}
+
+/*
* Rewrite the inode's ownerships here because the owning task may have
* performed a setuid(), etc.
*
*/
-int pid_revalidate(struct dentry *dentry, unsigned int flags)
+static int pid_revalidate(struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
struct task_struct *task;
@@ -1823,10 +1834,7 @@ int pid_revalidate(struct dentry *dentry, unsigned int flags)
task = get_proc_task(inode);
if (task) {
- task_dump_owner(task, inode->i_mode, &inode->i_uid, &inode->i_gid);
-
- inode->i_mode &= ~(S_ISUID | S_ISGID);
- security_task_to_inode(task, inode);
+ pid_update_inode(task, inode);
put_task_struct(task);
return 1;
}
@@ -1874,8 +1882,8 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx,
struct dentry *child, *dir = file->f_path.dentry;
struct qstr qname = QSTR_INIT(name, len);
struct inode *inode;
- unsigned type;
- ino_t ino;
+ unsigned type = DT_UNKNOWN;
+ ino_t ino = 1;
child = d_hash_and_lookup(dir, &qname);
if (!child) {
@@ -1884,22 +1892,23 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx,
if (IS_ERR(child))
goto end_instantiate;
if (d_in_lookup(child)) {
- int err = instantiate(d_inode(dir), child, task, ptr);
+ struct dentry *res;
+ res = instantiate(child, task, ptr);
d_lookup_done(child);
- if (err < 0) {
- dput(child);
+ if (IS_ERR(res))
goto end_instantiate;
+ if (unlikely(res)) {
+ dput(child);
+ child = res;
}
}
}
inode = d_inode(child);
ino = inode->i_ino;
type = inode->i_mode >> 12;
+end_instantiate:
dput(child);
return dir_emit(ctx, name, len, ino, type);
-
-end_instantiate:
- return dir_emit(ctx, name, len, 1, DT_UNKNOWN);
}
/*
@@ -2061,19 +2070,19 @@ static const struct inode_operations proc_map_files_link_inode_operations = {
.setattr = proc_setattr,
};
-static int
-proc_map_files_instantiate(struct inode *dir, struct dentry *dentry,
+static struct dentry *
+proc_map_files_instantiate(struct dentry *dentry,
struct task_struct *task, const void *ptr)
{
fmode_t mode = (fmode_t)(unsigned long)ptr;
struct proc_inode *ei;
struct inode *inode;
- inode = proc_pid_make_inode(dir->i_sb, task, S_IFLNK |
+ inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK |
((mode & FMODE_READ ) ? S_IRUSR : 0) |
((mode & FMODE_WRITE) ? S_IWUSR : 0));
if (!inode)
- return -ENOENT;
+ return ERR_PTR(-ENOENT);
ei = PROC_I(inode);
ei->op.proc_get_link = map_files_get_link;
@@ -2082,9 +2091,7 @@ proc_map_files_instantiate(struct inode *dir, struct dentry *dentry,
inode->i_size = 64;
d_set_d_op(dentry, &tid_map_files_dentry_operations);
- d_add(dentry, inode);
-
- return 0;
+ return d_splice_alias(inode, dentry);
}
static struct dentry *proc_map_files_lookup(struct inode *dir,
@@ -2093,19 +2100,19 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
unsigned long vm_start, vm_end;
struct vm_area_struct *vma;
struct task_struct *task;
- int result;
+ struct dentry *result;
struct mm_struct *mm;
- result = -ENOENT;
+ result = ERR_PTR(-ENOENT);
task = get_proc_task(dir);
if (!task)
goto out;
- result = -EACCES;
+ result = ERR_PTR(-EACCES);
if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
goto out_put_task;
- result = -ENOENT;
+ result = ERR_PTR(-ENOENT);
if (dname_to_vma_addr(dentry, &vm_start, &vm_end))
goto out_put_task;
@@ -2119,7 +2126,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
goto out_no_vma;
if (vma->vm_file)
- result = proc_map_files_instantiate(dir, dentry, task,
+ result = proc_map_files_instantiate(dentry, task,
(void *)(unsigned long)vma->vm_file->f_mode);
out_no_vma:
@@ -2128,7 +2135,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
out_put_task:
put_task_struct(task);
out:
- return ERR_PTR(result);
+ return result;
}
static const struct inode_operations proc_map_files_inode_operations = {
@@ -2331,7 +2338,7 @@ static int proc_timers_open(struct inode *inode, struct file *file)
return -ENOMEM;
tp->pid = proc_pid(inode);
- tp->ns = inode->i_sb->s_fs_info;
+ tp->ns = proc_pid_ns(inode);
return 0;
}
@@ -2429,16 +2436,16 @@ static const struct file_operations proc_pid_set_timerslack_ns_operations = {
.release = single_release,
};
-static int proc_pident_instantiate(struct inode *dir,
- struct dentry *dentry, struct task_struct *task, const void *ptr)
+static struct dentry *proc_pident_instantiate(struct dentry *dentry,
+ struct task_struct *task, const void *ptr)
{
const struct pid_entry *p = ptr;
struct inode *inode;
struct proc_inode *ei;
- inode = proc_pid_make_inode(dir->i_sb, task, p->mode);
+ inode = proc_pid_make_inode(dentry->d_sb, task, p->mode);
if (!inode)
- goto out;
+ return ERR_PTR(-ENOENT);
ei = PROC_I(inode);
if (S_ISDIR(inode->i_mode))
@@ -2448,13 +2455,9 @@ static int proc_pident_instantiate(struct inode *dir,
if (p->fop)
inode->i_fop = p->fop;
ei->op = p->op;
+ pid_update_inode(task, inode);
d_set_d_op(dentry, &pid_dentry_operations);
- d_add(dentry, inode);
- /* Close the race of the process dying before we return the dentry */
- if (pid_revalidate(dentry, 0))
- return 0;
-out:
- return -ENOENT;
+ return d_splice_alias(inode, dentry);
}
static struct dentry *proc_pident_lookup(struct inode *dir,
@@ -2462,11 +2465,9 @@ static struct dentry *proc_pident_lookup(struct inode *dir,
const struct pid_entry *ents,
unsigned int nents)
{
- int error;
struct task_struct *task = get_proc_task(dir);
const struct pid_entry *p, *last;
-
- error = -ENOENT;
+ struct dentry *res = ERR_PTR(-ENOENT);
if (!task)
goto out_no_task;
@@ -2485,11 +2486,11 @@ static struct dentry *proc_pident_lookup(struct inode *dir,
if (p >= last)
goto out;
- error = proc_pident_instantiate(dir, dentry, task, p);
+ res = proc_pident_instantiate(dentry, task, p);
out:
put_task_struct(task);
out_no_task:
- return ERR_PTR(error);
+ return res;
}
static int proc_pident_readdir(struct file *file, struct dir_context *ctx,
@@ -3132,38 +3133,32 @@ void proc_flush_task(struct task_struct *task)
}
}
-static int proc_pid_instantiate(struct inode *dir,
- struct dentry * dentry,
+static struct dentry *proc_pid_instantiate(struct dentry * dentry,
struct task_struct *task, const void *ptr)
{
struct inode *inode;
- inode = proc_pid_make_inode(dir->i_sb, task, S_IFDIR | S_IRUGO | S_IXUGO);
+ inode = proc_pid_make_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO);
if (!inode)
- goto out;
+ return ERR_PTR(-ENOENT);
inode->i_op = &proc_tgid_base_inode_operations;
inode->i_fop = &proc_tgid_base_operations;
inode->i_flags|=S_IMMUTABLE;
set_nlink(inode, nlink_tgid);
+ pid_update_inode(task, inode);
d_set_d_op(dentry, &pid_dentry_operations);
-
- d_add(dentry, inode);
- /* Close the race of the process dying before we return the dentry */
- if (pid_revalidate(dentry, 0))
- return 0;
-out:
- return -ENOENT;
+ return d_splice_alias(inode, dentry);
}
struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
{
- int result = -ENOENT;
struct task_struct *task;
unsigned tgid;
struct pid_namespace *ns;
+ struct dentry *result = ERR_PTR(-ENOENT);
tgid = name_to_int(&dentry->d_name);
if (tgid == ~0U)
@@ -3178,10 +3173,10 @@ struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsign
if (!task)
goto out;
- result = proc_pid_instantiate(dir, dentry, task, NULL);
+ result = proc_pid_instantiate(dentry, task, NULL);
put_task_struct(task);
out:
- return ERR_PTR(result);
+ return result;
}
/*
@@ -3233,7 +3228,7 @@ static struct tgid_iter next_tgid(struct pid_namespace *ns, struct tgid_iter ite
int proc_pid_readdir(struct file *file, struct dir_context *ctx)
{
struct tgid_iter iter;
- struct pid_namespace *ns = file_inode(file)->i_sb->s_fs_info;
+ struct pid_namespace *ns = proc_pid_ns(file_inode(file));
loff_t pos = ctx->pos;
if (pos >= PID_MAX_LIMIT + TGID_OFFSET)
@@ -3429,37 +3424,32 @@ static const struct inode_operations proc_tid_base_inode_operations = {
.setattr = proc_setattr,
};
-static int proc_task_instantiate(struct inode *dir,
- struct dentry *dentry, struct task_struct *task, const void *ptr)
+static struct dentry *proc_task_instantiate(struct dentry *dentry,
+ struct task_struct *task, const void *ptr)
{
struct inode *inode;
- inode = proc_pid_make_inode(dir->i_sb, task, S_IFDIR | S_IRUGO | S_IXUGO);
-
+ inode = proc_pid_make_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO);
if (!inode)
- goto out;
+ return ERR_PTR(-ENOENT);
+
inode->i_op = &proc_tid_base_inode_operations;
inode->i_fop = &proc_tid_base_operations;
- inode->i_flags|=S_IMMUTABLE;
+ inode->i_flags |= S_IMMUTABLE;
set_nlink(inode, nlink_tid);
+ pid_update_inode(task, inode);
d_set_d_op(dentry, &pid_dentry_operations);
-
- d_add(dentry, inode);
- /* Close the race of the process dying before we return the dentry */
- if (pid_revalidate(dentry, 0))
- return 0;
-out:
- return -ENOENT;
+ return d_splice_alias(inode, dentry);
}
static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
{
- int result = -ENOENT;
struct task_struct *task;
struct task_struct *leader = get_proc_task(dir);
unsigned tid;
struct pid_namespace *ns;
+ struct dentry *result = ERR_PTR(-ENOENT);
if (!leader)
goto out_no_task;
@@ -3479,13 +3469,13 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry
if (!same_thread_group(leader, task))
goto out_drop_task;
- result = proc_task_instantiate(dir, dentry, task, NULL);
+ result = proc_task_instantiate(dentry, task, NULL);
out_drop_task:
put_task_struct(task);
out:
put_task_struct(leader);
out_no_task:
- return ERR_PTR(result);
+ return result;
}
/*
@@ -3582,7 +3572,7 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx)
/* f_version caches the tgid value that the last readdir call couldn't
* return. lseek aka telldir automagically resets f_version to 0.
*/
- ns = inode->i_sb->s_fs_info;
+ ns = proc_pid_ns(inode);
tid = (int)file->f_version;
file->f_version = 0;
for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns);
diff --git a/fs/proc/cmdline.c b/fs/proc/cmdline.c
index 8233e7a..fa762c5 100644
--- a/fs/proc/cmdline.c
+++ b/fs/proc/cmdline.c
@@ -11,21 +11,9 @@ static int cmdline_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int cmdline_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, cmdline_proc_show, NULL);
-}
-
-static const struct file_operations cmdline_proc_fops = {
- .open = cmdline_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __init proc_cmdline_init(void)
{
- proc_create("cmdline", 0, NULL, &cmdline_proc_fops);
+ proc_create_single("cmdline", 0, NULL, cmdline_proc_show);
return 0;
}
fs_initcall(proc_cmdline_init);
diff --git a/fs/proc/consoles.c b/fs/proc/consoles.c
index a8ac48a..954caf0 100644
--- a/fs/proc/consoles.c
+++ b/fs/proc/consoles.c
@@ -91,21 +91,9 @@ static const struct seq_operations consoles_op = {
.show = show_console_dev
};
-static int consoles_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &consoles_op);
-}
-
-static const struct file_operations proc_consoles_operations = {
- .open = consoles_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static int __init proc_consoles_init(void)
{
- proc_create("consoles", 0, NULL, &proc_consoles_operations);
+ proc_create_seq("consoles", 0, NULL, &consoles_op);
return 0;
}
fs_initcall(proc_consoles_init);
diff --git a/fs/proc/devices.c b/fs/proc/devices.c
index 2c7f22b..37d38697 100644
--- a/fs/proc/devices.c
+++ b/fs/proc/devices.c
@@ -51,21 +51,9 @@ static const struct seq_operations devinfo_ops = {
.show = devinfo_show
};
-static int devinfo_open(struct inode *inode, struct file *filp)
-{
- return seq_open(filp, &devinfo_ops);
-}
-
-static const struct file_operations proc_devinfo_operations = {
- .open = devinfo_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static int __init proc_devices_init(void)
{
- proc_create("devices", 0, NULL, &proc_devinfo_operations);
+ proc_create_seq("devices", 0, NULL, &devinfo_ops);
return 0;
}
fs_initcall(proc_devices_init);
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 6b80cd1..05b9893 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -81,9 +81,41 @@ static const struct file_operations proc_fdinfo_file_operations = {
.release = single_release,
};
+static bool tid_fd_mode(struct task_struct *task, unsigned fd, fmode_t *mode)
+{
+ struct files_struct *files = get_files_struct(task);
+ struct file *file;
+
+ if (!files)
+ return false;
+
+ rcu_read_lock();
+ file = fcheck_files(files, fd);
+ if (file)
+ *mode = file->f_mode;
+ rcu_read_unlock();
+ put_files_struct(files);
+ return !!file;
+}
+
+static void tid_fd_update_inode(struct task_struct *task, struct inode *inode,
+ fmode_t f_mode)
+{
+ task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid);
+
+ if (S_ISLNK(inode->i_mode)) {
+ unsigned i_mode = S_IFLNK;
+ if (f_mode & FMODE_READ)
+ i_mode |= S_IRUSR | S_IXUSR;
+ if (f_mode & FMODE_WRITE)
+ i_mode |= S_IWUSR | S_IXUSR;
+ inode->i_mode = i_mode;
+ }
+ security_task_to_inode(task, inode);
+}
+
static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
{
- struct files_struct *files;
struct task_struct *task;
struct inode *inode;
unsigned int fd;
@@ -96,35 +128,11 @@ static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
fd = proc_fd(inode);
if (task) {
- files = get_files_struct(task);
- if (files) {
- struct file *file;
-
- rcu_read_lock();
- file = fcheck_files(files, fd);
- if (file) {
- unsigned f_mode = file->f_mode;
-
- rcu_read_unlock();
- put_files_struct(files);
-
- task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid);
-
- if (S_ISLNK(inode->i_mode)) {
- unsigned i_mode = S_IFLNK;
- if (f_mode & FMODE_READ)
- i_mode |= S_IRUSR | S_IXUSR;
- if (f_mode & FMODE_WRITE)
- i_mode |= S_IWUSR | S_IXUSR;
- inode->i_mode = i_mode;
- }
-
- security_task_to_inode(task, inode);
- put_task_struct(task);
- return 1;
- }
- rcu_read_unlock();
- put_files_struct(files);
+ fmode_t f_mode;
+ if (tid_fd_mode(task, fd, &f_mode)) {
+ tid_fd_update_inode(task, inode, f_mode);
+ put_task_struct(task);
+ return 1;
}
put_task_struct(task);
}
@@ -166,34 +174,33 @@ static int proc_fd_link(struct dentry *dentry, struct path *path)
return ret;
}
-static int
-proc_fd_instantiate(struct inode *dir, struct dentry *dentry,
- struct task_struct *task, const void *ptr)
+struct fd_data {
+ fmode_t mode;
+ unsigned fd;
+};
+
+static struct dentry *proc_fd_instantiate(struct dentry *dentry,
+ struct task_struct *task, const void *ptr)
{
- unsigned fd = (unsigned long)ptr;
+ const struct fd_data *data = ptr;
struct proc_inode *ei;
struct inode *inode;
- inode = proc_pid_make_inode(dir->i_sb, task, S_IFLNK);
+ inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK);
if (!inode)
- goto out;
+ return ERR_PTR(-ENOENT);
ei = PROC_I(inode);
- ei->fd = fd;
+ ei->fd = data->fd;
inode->i_op = &proc_pid_link_inode_operations;
inode->i_size = 64;
ei->op.proc_get_link = proc_fd_link;
+ tid_fd_update_inode(task, inode, data->mode);
d_set_d_op(dentry, &tid_fd_dentry_operations);
- d_add(dentry, inode);
-
- /* Close the race of the process dying before we return the dentry */
- if (tid_fd_revalidate(dentry, 0))
- return 0;
- out:
- return -ENOENT;
+ return d_splice_alias(inode, dentry);
}
static struct dentry *proc_lookupfd_common(struct inode *dir,
@@ -201,19 +208,21 @@ static struct dentry *proc_lookupfd_common(struct inode *dir,
instantiate_t instantiate)
{
struct task_struct *task = get_proc_task(dir);
- int result = -ENOENT;
- unsigned fd = name_to_int(&dentry->d_name);
+ struct fd_data data = {.fd = name_to_int(&dentry->d_name)};
+ struct dentry *result = ERR_PTR(-ENOENT);
if (!task)
goto out_no_task;
- if (fd == ~0U)
+ if (data.fd == ~0U)
+ goto out;
+ if (!tid_fd_mode(task, data.fd, &data.mode))
goto out;
- result = instantiate(dir, dentry, task, (void *)(unsigned long)fd);
+ result = instantiate(dentry, task, &data);
out:
put_task_struct(task);
out_no_task:
- return ERR_PTR(result);
+ return result;
}
static int proc_readfd_common(struct file *file, struct dir_context *ctx,
@@ -236,17 +245,22 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx,
for (fd = ctx->pos - 2;
fd < files_fdtable(files)->max_fds;
fd++, ctx->pos++) {
+ struct file *f;
+ struct fd_data data;
char name[10 + 1];
int len;
- if (!fcheck_files(files, fd))
+ f = fcheck_files(files, fd);
+ if (!f)
continue;
+ data.mode = f->f_mode;
rcu_read_unlock();
+ data.fd = fd;
len = snprintf(name, sizeof(name), "%u", fd);
if (!proc_fill_cache(file, ctx,
name, len, instantiate, p,
- (void *)(unsigned long)fd))
+ &data))
goto out_fd_loop;
cond_resched();
rcu_read_lock();
@@ -304,31 +318,25 @@ const struct inode_operations proc_fd_inode_operations = {
.setattr = proc_setattr,
};
-static int
-proc_fdinfo_instantiate(struct inode *dir, struct dentry *dentry,
- struct task_struct *task, const void *ptr)
+static struct dentry *proc_fdinfo_instantiate(struct dentry *dentry,
+ struct task_struct *task, const void *ptr)
{
- unsigned fd = (unsigned long)ptr;
+ const struct fd_data *data = ptr;
struct proc_inode *ei;
struct inode *inode;
- inode = proc_pid_make_inode(dir->i_sb, task, S_IFREG | S_IRUSR);
+ inode = proc_pid_make_inode(dentry->d_sb, task, S_IFREG | S_IRUSR);
if (!inode)
- goto out;
+ return ERR_PTR(-ENOENT);
ei = PROC_I(inode);
- ei->fd = fd;
+ ei->fd = data->fd;
inode->i_fop = &proc_fdinfo_file_operations;
+ tid_fd_update_inode(task, inode, 0);
d_set_d_op(dentry, &tid_fd_dentry_operations);
- d_add(dentry, inode);
-
- /* Close the race of the process dying before we return the dentry */
- if (tid_fd_revalidate(dentry, 0))
- return 0;
- out:
- return -ENOENT;
+ return d_splice_alias(inode, dentry);
}
static struct dentry *
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 2078e70..7b4d971 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -25,6 +25,7 @@
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/uaccess.h>
+#include <linux/seq_file.h>
#include "internal.h"
@@ -256,8 +257,7 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry,
if (!inode)
return ERR_PTR(-ENOMEM);
d_set_d_op(dentry, &proc_misc_dentry_ops);
- d_add(dentry, inode);
- return NULL;
+ return d_splice_alias(inode, dentry);
}
read_unlock(&proc_subdir_lock);
return ERR_PTR(-ENOENT);
@@ -346,13 +346,12 @@ static const struct inode_operations proc_dir_inode_operations = {
.setattr = proc_notify_change,
};
-static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp)
+/* returns the registered entry, or frees dp and returns NULL on failure */
+struct proc_dir_entry *proc_register(struct proc_dir_entry *dir,
+ struct proc_dir_entry *dp)
{
- int ret;
-
- ret = proc_alloc_inum(&dp->low_ino);
- if (ret)
- return ret;
+ if (proc_alloc_inum(&dp->low_ino))
+ goto out_free_entry;
write_lock(&proc_subdir_lock);
dp->parent = dir;
@@ -360,12 +359,16 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp
WARN(1, "proc_dir_entry '%s/%s' already registered\n",
dir->name, dp->name);
write_unlock(&proc_subdir_lock);
- proc_free_inum(dp->low_ino);
- return -EEXIST;
+ goto out_free_inum;
}
write_unlock(&proc_subdir_lock);
- return 0;
+ return dp;
+out_free_inum:
+ proc_free_inum(dp->low_ino);
+out_free_entry:
+ pde_free(dp);
+ return NULL;
}
static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
@@ -443,10 +446,7 @@ struct proc_dir_entry *proc_symlink(const char *name,
if (ent->data) {
strcpy((char*)ent->data,dest);
ent->proc_iops = &proc_link_inode_operations;
- if (proc_register(parent, ent) < 0) {
- pde_free(ent);
- ent = NULL;
- }
+ ent = proc_register(parent, ent);
} else {
pde_free(ent);
ent = NULL;
@@ -470,11 +470,9 @@ struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode,
ent->proc_fops = &proc_dir_operations;
ent->proc_iops = &proc_dir_inode_operations;
parent->nlink++;
- if (proc_register(parent, ent) < 0) {
- pde_free(ent);
+ ent = proc_register(parent, ent);
+ if (!ent)
parent->nlink--;
- ent = NULL;
- }
}
return ent;
}
@@ -505,47 +503,47 @@ struct proc_dir_entry *proc_create_mount_point(const char *name)
ent->proc_fops = NULL;
ent->proc_iops = NULL;
parent->nlink++;
- if (proc_register(parent, ent) < 0) {
- pde_free(ent);
+ ent = proc_register(parent, ent);
+ if (!ent)
parent->nlink--;
- ent = NULL;
- }
}
return ent;
}
EXPORT_SYMBOL(proc_create_mount_point);
-struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
- struct proc_dir_entry *parent,
- const struct file_operations *proc_fops,
- void *data)
+struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode,
+ struct proc_dir_entry **parent, void *data)
{
- struct proc_dir_entry *pde;
+ struct proc_dir_entry *p;
+
if ((mode & S_IFMT) == 0)
mode |= S_IFREG;
-
- if (!S_ISREG(mode)) {
- WARN_ON(1); /* use proc_mkdir() */
+ if ((mode & S_IALLUGO) == 0)
+ mode |= S_IRUGO;
+ if (WARN_ON_ONCE(!S_ISREG(mode)))
return NULL;
+
+ p = __proc_create(parent, name, mode, 1);
+ if (p) {
+ p->proc_iops = &proc_file_inode_operations;
+ p->data = data;
}
+ return p;
+}
+
+struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
+ struct proc_dir_entry *parent,
+ const struct file_operations *proc_fops, void *data)
+{
+ struct proc_dir_entry *p;
BUG_ON(proc_fops == NULL);
- if ((mode & S_IALLUGO) == 0)
- mode |= S_IRUGO;
- pde = __proc_create(&parent, name, mode, 1);
- if (!pde)
- goto out;
- pde->proc_fops = proc_fops;
- pde->data = data;
- pde->proc_iops = &proc_file_inode_operations;
- if (proc_register(parent, pde) < 0)
- goto out_free;
- return pde;
-out_free:
- pde_free(pde);
-out:
- return NULL;
+ p = proc_create_reg(name, mode, &parent, data);
+ if (!p)
+ return NULL;
+ p->proc_fops = proc_fops;
+ return proc_register(parent, p);
}
EXPORT_SYMBOL(proc_create_data);
@@ -557,6 +555,67 @@ struct proc_dir_entry *proc_create(const char *name, umode_t mode,
}
EXPORT_SYMBOL(proc_create);
+static int proc_seq_open(struct inode *inode, struct file *file)
+{
+ struct proc_dir_entry *de = PDE(inode);
+
+ if (de->state_size)
+ return seq_open_private(file, de->seq_ops, de->state_size);
+ return seq_open(file, de->seq_ops);
+}
+
+static const struct file_operations proc_seq_fops = {
+ .open = proc_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
+ struct proc_dir_entry *parent, const struct seq_operations *ops,
+ unsigned int state_size, void *data)
+{
+ struct proc_dir_entry *p;
+
+ p = proc_create_reg(name, mode, &parent, data);
+ if (!p)
+ return NULL;
+ p->proc_fops = &proc_seq_fops;
+ p->seq_ops = ops;
+ p->state_size = state_size;
+ return proc_register(parent, p);
+}
+EXPORT_SYMBOL(proc_create_seq_private);
+
+static int proc_single_open(struct inode *inode, struct file *file)
+{
+ struct proc_dir_entry *de = PDE(inode);
+
+ return single_open(file, de->single_show, de->data);
+}
+
+static const struct file_operations proc_single_fops = {
+ .open = proc_single_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode,
+ struct proc_dir_entry *parent,
+ int (*show)(struct seq_file *, void *), void *data)
+{
+ struct proc_dir_entry *p;
+
+ p = proc_create_reg(name, mode, &parent, data);
+ if (!p)
+ return NULL;
+ p->proc_fops = &proc_single_fops;
+ p->single_show = show;
+ return proc_register(parent, p);
+}
+EXPORT_SYMBOL(proc_create_single_data);
+
void proc_set_size(struct proc_dir_entry *de, loff_t size)
{
de->size = size;
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 0f1692e..43c70c9 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -44,7 +44,12 @@ struct proc_dir_entry {
struct completion *pde_unload_completion;
const struct inode_operations *proc_iops;
const struct file_operations *proc_fops;
+ union {
+ const struct seq_operations *seq_ops;
+ int (*single_show)(struct seq_file *, void *);
+ };
void *data;
+ unsigned int state_size;
unsigned int low_ino;
nlink_t nlink;
kuid_t uid;
@@ -57,9 +62,9 @@ struct proc_dir_entry {
umode_t mode;
u8 namelen;
#ifdef CONFIG_64BIT
-#define SIZEOF_PDE_INLINE_NAME (192-139)
+#define SIZEOF_PDE_INLINE_NAME (192-155)
#else
-#define SIZEOF_PDE_INLINE_NAME (128-87)
+#define SIZEOF_PDE_INLINE_NAME (128-95)
#endif
char inline_name[SIZEOF_PDE_INLINE_NAME];
} __randomize_layout;
@@ -147,14 +152,14 @@ extern const struct dentry_operations pid_dentry_operations;
extern int pid_getattr(const struct path *, struct kstat *, u32, unsigned int);
extern int proc_setattr(struct dentry *, struct iattr *);
extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *, umode_t);
-extern int pid_revalidate(struct dentry *, unsigned int);
+extern void pid_update_inode(struct task_struct *, struct inode *);
extern int pid_delete_dentry(const struct dentry *);
extern int proc_pid_readdir(struct file *, struct dir_context *);
extern struct dentry *proc_pid_lookup(struct inode *, struct dentry *, unsigned int);
extern loff_t mem_lseek(struct file *, loff_t, int);
/* Lookups */
-typedef int instantiate_t(struct inode *, struct dentry *,
+typedef struct dentry *instantiate_t(struct dentry *,
struct task_struct *, const void *);
extern bool proc_fill_cache(struct file *, struct dir_context *, const char *, int,
instantiate_t, struct task_struct *, const void *);
@@ -162,6 +167,10 @@ extern bool proc_fill_cache(struct file *, struct dir_context *, const char *, i
/*
* generic.c
*/
+struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode,
+ struct proc_dir_entry **parent, void *data);
+struct proc_dir_entry *proc_register(struct proc_dir_entry *dir,
+ struct proc_dir_entry *dp);
extern struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int);
struct dentry *proc_lookup_de(struct inode *, struct dentry *, struct proc_dir_entry *);
extern int proc_readdir(struct file *, struct dir_context *);
diff --git a/fs/proc/interrupts.c b/fs/proc/interrupts.c
index 6a6bee9..cb0edc7 100644
--- a/fs/proc/interrupts.c
+++ b/fs/proc/interrupts.c
@@ -34,21 +34,9 @@ static const struct seq_operations int_seq_ops = {
.show = show_interrupts
};
-static int interrupts_open(struct inode *inode, struct file *filp)
-{
- return seq_open(filp, &int_seq_ops);
-}
-
-static const struct file_operations proc_interrupts_operations = {
- .open = interrupts_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static int __init proc_interrupts_init(void)
{
- proc_create("interrupts", 0, NULL, &proc_interrupts_operations);
+ proc_create_seq("interrupts", 0, NULL, &int_seq_ops);
return 0;
}
fs_initcall(proc_interrupts_init);
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index d1e8276..e64ecb9 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -209,25 +209,34 @@ kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg)
{
struct list_head *head = (struct list_head *)arg;
struct kcore_list *ent;
+ struct page *p;
+
+ if (!pfn_valid(pfn))
+ return 1;
+
+ p = pfn_to_page(pfn);
+ if (!memmap_valid_within(pfn, p, page_zone(p)))
+ return 1;
ent = kmalloc(sizeof(*ent), GFP_KERNEL);
if (!ent)
return -ENOMEM;
- ent->addr = (unsigned long)__va((pfn << PAGE_SHIFT));
+ ent->addr = (unsigned long)page_to_virt(p);
ent->size = nr_pages << PAGE_SHIFT;
- /* Sanity check: Can happen in 32bit arch...maybe */
- if (ent->addr < (unsigned long) __va(0))
+ if (!virt_addr_valid(ent->addr))
goto free_out;
/* cut not-mapped area. ....from ppc-32 code. */
if (ULONG_MAX - ent->addr < ent->size)
ent->size = ULONG_MAX - ent->addr;
- /* cut when vmalloc() area is higher than direct-map area */
- if (VMALLOC_START > (unsigned long)__va(0)) {
- if (ent->addr > VMALLOC_START)
- goto free_out;
+ /*
+ * We've already checked virt_addr_valid so we know this address
+ * is a valid pointer, therefore we can check against it to determine
+ * if we need to trim
+ */
+ if (VMALLOC_START > ent->addr) {
if (VMALLOC_START - ent->addr < ent->size)
ent->size = VMALLOC_START - ent->addr;
}
diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c
index a000d75..d066947 100644
--- a/fs/proc/loadavg.c
+++ b/fs/proc/loadavg.c
@@ -24,25 +24,13 @@ static int loadavg_proc_show(struct seq_file *m, void *v)
LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]),
LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]),
nr_running(), nr_threads,
- idr_get_cursor(&task_active_pid_ns(current)->idr));
+ idr_get_cursor(&task_active_pid_ns(current)->idr) - 1);
return 0;
}
-static int loadavg_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, loadavg_proc_show, NULL);
-}
-
-static const struct file_operations loadavg_proc_fops = {
- .open = loadavg_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __init proc_loadavg_init(void)
{
- proc_create("loadavg", 0, NULL, &loadavg_proc_fops);
+ proc_create_single("loadavg", 0, NULL, loadavg_proc_show);
return 0;
}
fs_initcall(proc_loadavg_init);
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 65a72ab..2fb0484 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -149,21 +149,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int meminfo_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, meminfo_proc_show, NULL);
-}
-
-static const struct file_operations meminfo_proc_fops = {
- .open = meminfo_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __init proc_meminfo_init(void)
{
- proc_create("meminfo", 0, NULL, &meminfo_proc_fops);
+ proc_create_single("meminfo", 0, NULL, meminfo_proc_show);
return 0;
}
fs_initcall(proc_meminfo_init);
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 59b17e5..dd2b35f 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -87,28 +87,24 @@ static const struct inode_operations proc_ns_link_inode_operations = {
.setattr = proc_setattr,
};
-static int proc_ns_instantiate(struct inode *dir,
- struct dentry *dentry, struct task_struct *task, const void *ptr)
+static struct dentry *proc_ns_instantiate(struct dentry *dentry,
+ struct task_struct *task, const void *ptr)
{
const struct proc_ns_operations *ns_ops = ptr;
struct inode *inode;
struct proc_inode *ei;
- inode = proc_pid_make_inode(dir->i_sb, task, S_IFLNK | S_IRWXUGO);
+ inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK | S_IRWXUGO);
if (!inode)
- goto out;
+ return ERR_PTR(-ENOENT);
ei = PROC_I(inode);
inode->i_op = &proc_ns_link_inode_operations;
ei->ns_ops = ns_ops;
+ pid_update_inode(task, inode);
d_set_d_op(dentry, &pid_dentry_operations);
- d_add(dentry, inode);
- /* Close the race of the process dying before we return the dentry */
- if (pid_revalidate(dentry, 0))
- return 0;
-out:
- return -ENOENT;
+ return d_splice_alias(inode, dentry);
}
static int proc_ns_dir_readdir(struct file *file, struct dir_context *ctx)
@@ -147,12 +143,10 @@ const struct file_operations proc_ns_dir_operations = {
static struct dentry *proc_ns_dir_lookup(struct inode *dir,
struct dentry *dentry, unsigned int flags)
{
- int error;
struct task_struct *task = get_proc_task(dir);
const struct proc_ns_operations **entry, **last;
unsigned int len = dentry->d_name.len;
-
- error = -ENOENT;
+ struct dentry *res = ERR_PTR(-ENOENT);
if (!task)
goto out_no_task;
@@ -167,11 +161,11 @@ static struct dentry *proc_ns_dir_lookup(struct inode *dir,
if (entry == last)
goto out;
- error = proc_ns_instantiate(dir, dentry, task, *entry);
+ res = proc_ns_instantiate(dentry, task, *entry);
out:
put_task_struct(task);
out_no_task:
- return ERR_PTR(error);
+ return res;
}
const struct inode_operations proc_ns_dir_inode_operations = {
diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
index 7563437..3b63be6 100644
--- a/fs/proc/nommu.c
+++ b/fs/proc/nommu.c
@@ -113,21 +113,9 @@ static const struct seq_operations proc_nommu_region_list_seqop = {
.show = nommu_region_list_show
};
-static int proc_nommu_region_list_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &proc_nommu_region_list_seqop);
-}
-
-static const struct file_operations proc_nommu_region_list_operations = {
- .open = proc_nommu_region_list_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static int __init proc_nommu_init(void)
{
- proc_create("maps", S_IRUGO, NULL, &proc_nommu_region_list_operations);
+ proc_create_seq("maps", S_IRUGO, NULL, &proc_nommu_region_list_seqop);
return 0;
}
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 1763f37..7d94fa0 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -38,20 +38,20 @@ static struct net *get_proc_net(const struct inode *inode)
return maybe_get_net(PDE_NET(PDE(inode)));
}
-int seq_open_net(struct inode *ino, struct file *f,
- const struct seq_operations *ops, int size)
+static int seq_open_net(struct inode *inode, struct file *file)
{
- struct net *net;
+ unsigned int state_size = PDE(inode)->state_size;
struct seq_net_private *p;
+ struct net *net;
- BUG_ON(size < sizeof(*p));
+ WARN_ON_ONCE(state_size < sizeof(*p));
- net = get_proc_net(ino);
- if (net == NULL)
+ net = get_proc_net(inode);
+ if (!net)
return -ENXIO;
- p = __seq_open_private(f, ops, size);
- if (p == NULL) {
+ p = __seq_open_private(file, PDE(inode)->seq_ops, state_size);
+ if (!p) {
put_net(net);
return -ENOMEM;
}
@@ -60,51 +60,83 @@ int seq_open_net(struct inode *ino, struct file *f,
#endif
return 0;
}
-EXPORT_SYMBOL_GPL(seq_open_net);
-int single_open_net(struct inode *inode, struct file *file,
- int (*show)(struct seq_file *, void *))
+static int seq_release_net(struct inode *ino, struct file *f)
{
- int err;
- struct net *net;
-
- err = -ENXIO;
- net = get_proc_net(inode);
- if (net == NULL)
- goto err_net;
-
- err = single_open(file, show, net);
- if (err < 0)
- goto err_open;
-
- return 0;
-
-err_open:
- put_net(net);
-err_net:
- return err;
-}
-EXPORT_SYMBOL_GPL(single_open_net);
-
-int seq_release_net(struct inode *ino, struct file *f)
-{
- struct seq_file *seq;
-
- seq = f->private_data;
+ struct seq_file *seq = f->private_data;
put_net(seq_file_net(seq));
seq_release_private(ino, f);
return 0;
}
-EXPORT_SYMBOL_GPL(seq_release_net);
-int single_release_net(struct inode *ino, struct file *f)
+static const struct file_operations proc_net_seq_fops = {
+ .open = seq_open_net,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_net,
+};
+
+struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode,
+ struct proc_dir_entry *parent, const struct seq_operations *ops,
+ unsigned int state_size, void *data)
+{
+ struct proc_dir_entry *p;
+
+ p = proc_create_reg(name, mode, &parent, data);
+ if (!p)
+ return NULL;
+ p->proc_fops = &proc_net_seq_fops;
+ p->seq_ops = ops;
+ p->state_size = state_size;
+ return proc_register(parent, p);
+}
+EXPORT_SYMBOL_GPL(proc_create_net_data);
+
+static int single_open_net(struct inode *inode, struct file *file)
+{
+ struct proc_dir_entry *de = PDE(inode);
+ struct net *net;
+ int err;
+
+ net = get_proc_net(inode);
+ if (!net)
+ return -ENXIO;
+
+ err = single_open(file, de->single_show, net);
+ if (err)
+ put_net(net);
+ return err;
+}
+
+static int single_release_net(struct inode *ino, struct file *f)
{
struct seq_file *seq = f->private_data;
put_net(seq->private);
return single_release(ino, f);
}
-EXPORT_SYMBOL_GPL(single_release_net);
+
+static const struct file_operations proc_net_single_fops = {
+ .open = single_open_net,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release_net,
+};
+
+struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode,
+ struct proc_dir_entry *parent,
+ int (*show)(struct seq_file *, void *), void *data)
+{
+ struct proc_dir_entry *p;
+
+ p = proc_create_reg(name, mode, &parent, data);
+ if (!p)
+ return NULL;
+ p->proc_fops = &proc_net_single_fops;
+ p->single_show = show;
+ return proc_register(parent, p);
+}
+EXPORT_SYMBOL_GPL(proc_create_net_single);
static struct net *get_proc_task_net(struct inode *dir)
{
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 8989936..4d765e5 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -554,9 +554,8 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
if (!inode)
goto out;
- err = NULL;
d_set_d_op(dentry, &proc_sys_dentry_operations);
- d_add(dentry, inode);
+ err = d_splice_alias(inode, dentry);
out:
if (h)
@@ -684,6 +683,7 @@ static bool proc_sys_fill_cache(struct file *file,
if (IS_ERR(child))
return false;
if (d_in_lookup(child)) {
+ struct dentry *res;
inode = proc_sys_make_inode(dir->d_sb, head, table);
if (!inode) {
d_lookup_done(child);
@@ -691,7 +691,16 @@ static bool proc_sys_fill_cache(struct file *file,
return false;
}
d_set_d_op(child, &proc_sys_dentry_operations);
- d_add(child, inode);
+ res = d_splice_alias(inode, child);
+ d_lookup_done(child);
+ if (unlikely(res)) {
+ if (IS_ERR(res)) {
+ dput(child);
+ return false;
+ }
+ dput(child);
+ child = res;
+ }
}
}
inode = d_inode(child);
diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c
index d0cf1c5..c69ff19 100644
--- a/fs/proc/proc_tty.c
+++ b/fs/proc/proc_tty.c
@@ -126,18 +126,6 @@ static const struct seq_operations tty_drivers_op = {
.show = show_tty_driver
};
-static int tty_drivers_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &tty_drivers_op);
-}
-
-static const struct file_operations proc_tty_drivers_operations = {
- .open = tty_drivers_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
/*
* This function is called by tty_register_driver() to handle
* registering the driver's /proc handler into /proc/tty/driver/<foo>
@@ -147,11 +135,11 @@ void proc_tty_register_driver(struct tty_driver *driver)
struct proc_dir_entry *ent;
if (!driver->driver_name || driver->proc_entry ||
- !driver->ops->proc_fops)
+ !driver->ops->proc_show)
return;
- ent = proc_create_data(driver->driver_name, 0, proc_tty_driver,
- driver->ops->proc_fops, driver);
+ ent = proc_create_single_data(driver->driver_name, 0, proc_tty_driver,
+ driver->ops->proc_show, driver);
driver->proc_entry = ent;
}
@@ -186,6 +174,6 @@ void __init proc_tty_init(void)
* entry.
*/
proc_tty_driver = proc_mkdir_mode("tty/driver", S_IRUSR|S_IXUSR, NULL);
- proc_create("tty/ldiscs", 0, NULL, &tty_ldiscs_proc_fops);
- proc_create("tty/drivers", 0, NULL, &proc_tty_drivers_operations);
+ proc_create_seq("tty/ldiscs", 0, NULL, &tty_ldiscs_seq_ops);
+ proc_create_seq("tty/drivers", 0, NULL, &tty_drivers_op);
}
diff --git a/fs/proc/self.c b/fs/proc/self.c
index 4d7d061..127265e 100644
--- a/fs/proc/self.c
+++ b/fs/proc/self.c
@@ -12,7 +12,7 @@ static const char *proc_self_get_link(struct dentry *dentry,
struct inode *inode,
struct delayed_call *done)
{
- struct pid_namespace *ns = inode->i_sb->s_fs_info;
+ struct pid_namespace *ns = proc_pid_ns(inode);
pid_t tgid = task_tgid_nr_ns(current, ns);
char *name;
@@ -36,7 +36,7 @@ static unsigned self_inum __ro_after_init;
int proc_setup_self(struct super_block *s)
{
struct inode *root_inode = d_inode(s->s_root);
- struct pid_namespace *ns = s->s_fs_info;
+ struct pid_namespace *ns = proc_pid_ns(root_inode);
struct dentry *self;
inode_lock(root_inode);
diff --git a/fs/proc/softirqs.c b/fs/proc/softirqs.c
index 24072cc..12901dc 100644
--- a/fs/proc/softirqs.c
+++ b/fs/proc/softirqs.c
@@ -25,21 +25,9 @@ static int show_softirqs(struct seq_file *p, void *v)
return 0;
}
-static int softirqs_open(struct inode *inode, struct file *file)
-{
- return single_open(file, show_softirqs, NULL);
-}
-
-static const struct file_operations proc_softirqs_operations = {
- .open = softirqs_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __init proc_softirqs_init(void)
{
- proc_create("softirqs", 0, NULL, &proc_softirqs_operations);
+ proc_create_single("softirqs", 0, NULL, show_softirqs);
return 0;
}
fs_initcall(proc_softirqs_init);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 65ae546..a20c6e4 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -937,7 +937,7 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
/*
* The soft-dirty tracker uses #PF-s to catch writes
* to pages, so write-protect the pte as well. See the
- * Documentation/vm/soft-dirty.txt for full description
+ * Documentation/admin-guide/mm/soft-dirty.rst for full description
* of how soft-dirty works.
*/
pte_t ptent = *pte;
@@ -1310,9 +1310,11 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
else if (is_swap_pmd(pmd)) {
swp_entry_t entry = pmd_to_swp_entry(pmd);
+ unsigned long offset = swp_offset(entry);
+ offset += (addr & ~PMD_MASK) >> PAGE_SHIFT;
frame = swp_type(entry) |
- (swp_offset(entry) << MAX_SWAPFILES_SHIFT);
+ (offset << MAX_SWAPFILES_SHIFT);
flags |= PM_SWAP;
if (pmd_swp_soft_dirty(pmd))
flags |= PM_SOFT_DIRTY;
@@ -1332,6 +1334,8 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
break;
if (pm->show_pfn && (flags & PM_PRESENT))
frame++;
+ else if (flags & PM_SWAP)
+ frame += (1 << MAX_SWAPFILES_SHIFT);
}
spin_unlock(ptl);
return err;
@@ -1417,7 +1421,7 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask,
* Bits 0-54 page frame number (PFN) if present
* Bits 0-4 swap type if swapped
* Bits 5-54 swap offset if swapped
- * Bit 55 pte is soft-dirty (see Documentation/vm/soft-dirty.txt)
+ * Bit 55 pte is soft-dirty (see Documentation/admin-guide/mm/soft-dirty.rst)
* Bit 56 page exclusively mapped
* Bits 57-60 zero
* Bit 61 page is file-page or shared-anon
diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c
index 9d2efac..b905010 100644
--- a/fs/proc/thread_self.c
+++ b/fs/proc/thread_self.c
@@ -12,7 +12,7 @@ static const char *proc_thread_self_get_link(struct dentry *dentry,
struct inode *inode,
struct delayed_call *done)
{
- struct pid_namespace *ns = inode->i_sb->s_fs_info;
+ struct pid_namespace *ns = proc_pid_ns(inode);
pid_t tgid = task_tgid_nr_ns(current, ns);
pid_t pid = task_pid_nr_ns(current, ns);
char *name;
@@ -36,7 +36,7 @@ static unsigned thread_self_inum __ro_after_init;
int proc_setup_thread_self(struct super_block *s)
{
struct inode *root_inode = d_inode(s->s_root);
- struct pid_namespace *ns = s->s_fs_info;
+ struct pid_namespace *ns = proc_pid_ns(root_inode);
struct dentry *thread_self;
inode_lock(root_inode);
diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c
index 95a708d..3bd12f9 100644
--- a/fs/proc/uptime.c
+++ b/fs/proc/uptime.c
@@ -30,21 +30,9 @@ static int uptime_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int uptime_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, uptime_proc_show, NULL);
-}
-
-static const struct file_operations uptime_proc_fops = {
- .open = uptime_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __init proc_uptime_init(void)
{
- proc_create("uptime", 0, NULL, &uptime_proc_fops);
+ proc_create_single("uptime", 0, NULL, uptime_proc_show);
return 0;
}
fs_initcall(proc_uptime_init);
diff --git a/fs/proc/version.c b/fs/proc/version.c
index 94901e8..b449f18 100644
--- a/fs/proc/version.c
+++ b/fs/proc/version.c
@@ -15,21 +15,9 @@ static int version_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int version_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, version_proc_show, NULL);
-}
-
-static const struct file_operations version_proc_fops = {
- .open = version_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __init proc_version_init(void)
{
- proc_create("version", 0, NULL, &version_proc_fops);
+ proc_create_single("version", 0, NULL, version_proc_show);
return 0;
}
fs_initcall(proc_version_init);
diff --git a/fs/qnx4/namei.c b/fs/qnx4/namei.c
index eca2787..8d72221 100644
--- a/fs/qnx4/namei.c
+++ b/fs/qnx4/namei.c
@@ -114,13 +114,9 @@ struct dentry * qnx4_lookup(struct inode *dir, struct dentry *dentry, unsigned i
brelse(bh);
foundinode = qnx4_iget(dir->i_sb, ino);
- if (IS_ERR(foundinode)) {
+ if (IS_ERR(foundinode))
QNX4DEBUG((KERN_ERR "qnx4: lookup->iget -> error %ld\n",
PTR_ERR(foundinode)));
- return ERR_CAST(foundinode);
- }
out:
- d_add(dentry, foundinode);
-
- return NULL;
+ return d_splice_alias(foundinode, dentry);
}
diff --git a/fs/qnx6/namei.c b/fs/qnx6/namei.c
index 72c2770..e2e98e6 100644
--- a/fs/qnx6/namei.c
+++ b/fs/qnx6/namei.c
@@ -29,15 +29,11 @@ struct dentry *qnx6_lookup(struct inode *dir, struct dentry *dentry,
if (ino) {
foundinode = qnx6_iget(dir->i_sb, ino);
qnx6_put_page(page);
- if (IS_ERR(foundinode)) {
+ if (IS_ERR(foundinode))
pr_debug("lookup->iget -> error %ld\n",
PTR_ERR(foundinode));
- return ERR_CAST(foundinode);
- }
} else {
pr_debug("%s(): not found %s\n", __func__, name);
- return NULL;
}
- d_add(dentry, foundinode);
- return NULL;
+ return d_splice_alias(foundinode, dentry);
}
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 020c597..d88231e 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2966,7 +2966,7 @@ static int __init dquot_init(void)
NULL);
order = 0;
- dquot_hash = (struct hlist_head *)__get_free_pages(GFP_ATOMIC, order);
+ dquot_hash = (struct hlist_head *)__get_free_pages(GFP_KERNEL, order);
if (!dquot_hash)
panic("Cannot create dquot hash table");
diff --git a/fs/read_write.c b/fs/read_write.c
index c4eabbf..e83bd97 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -2023,7 +2023,7 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
ret = mnt_want_write_file(dst_file);
if (ret) {
info->status = ret;
- goto next_loop;
+ goto next_fdput;
}
dst_off = info->dest_offset;
@@ -2058,9 +2058,9 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
next_file:
mnt_drop_write_file(dst_file);
-next_loop:
+next_fdput:
fdput(dst_fd);
-
+next_loop:
if (fatal_signal_pending(current))
goto out;
}
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index bd39a99..5089dac 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -687,8 +687,7 @@ static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mod
reiserfs_update_inode_transaction(inode);
reiserfs_update_inode_transaction(dir);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
retval = journal_end(&th);
out_failed:
@@ -771,8 +770,7 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode
goto out_failed;
}
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
retval = journal_end(&th);
out_failed:
@@ -871,8 +869,7 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
/* the above add_entry did not update dir's stat data */
reiserfs_update_sd(&th, dir);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
retval = journal_end(&th);
out_failed:
reiserfs_write_unlock(dir->i_sb);
@@ -1187,8 +1184,7 @@ static int reiserfs_symlink(struct inode *parent_dir,
goto out_failed;
}
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
retval = journal_end(&th);
out_failed:
reiserfs_write_unlock(parent_dir->i_sb);
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index fe99915..e39b391 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -389,27 +389,13 @@ static int show_journal(struct seq_file *m, void *unused)
return 0;
}
-static int r_open(struct inode *inode, struct file *file)
-{
- return single_open(file, PDE_DATA(inode),
- proc_get_parent_data(inode));
-}
-
-static const struct file_operations r_file_operations = {
- .open = r_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static struct proc_dir_entry *proc_info_root = NULL;
static const char proc_info_root_name[] = "fs/reiserfs";
static void add_file(struct super_block *sb, char *name,
int (*func) (struct seq_file *, void *))
{
- proc_create_data(name, 0, REISERFS_SB(sb)->procdir,
- &r_file_operations, func);
+ proc_create_single_data(name, 0, REISERFS_SB(sb)->procdir, func, sb);
}
int reiserfs_proc_info_init(struct super_block *sb)
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 8f06fd1..6ccb519 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -213,7 +213,7 @@ static struct dentry *romfs_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
unsigned long offset, maxoff;
- struct inode *inode;
+ struct inode *inode = NULL;
struct romfs_inode ri;
const char *name; /* got from dentry */
int len, ret;
@@ -233,7 +233,7 @@ static struct dentry *romfs_lookup(struct inode *dir, struct dentry *dentry,
for (;;) {
if (!offset || offset >= maxoff)
- goto out0;
+ break;
ret = romfs_dev_read(dir->i_sb, offset, &ri, sizeof(ri));
if (ret < 0)
@@ -244,37 +244,19 @@ static struct dentry *romfs_lookup(struct inode *dir, struct dentry *dentry,
len);
if (ret < 0)
goto error;
- if (ret == 1)
+ if (ret == 1) {
+ /* Hard link handling */
+ if ((be32_to_cpu(ri.next) & ROMFH_TYPE) == ROMFH_HRD)
+ offset = be32_to_cpu(ri.spec) & ROMFH_MASK;
+ inode = romfs_iget(dir->i_sb, offset);
break;
+ }
/* next entry */
offset = be32_to_cpu(ri.next) & ROMFH_MASK;
}
- /* Hard link handling */
- if ((be32_to_cpu(ri.next) & ROMFH_TYPE) == ROMFH_HRD)
- offset = be32_to_cpu(ri.spec) & ROMFH_MASK;
-
- inode = romfs_iget(dir->i_sb, offset);
- if (IS_ERR(inode)) {
- ret = PTR_ERR(inode);
- goto error;
- }
- goto outi;
-
- /*
- * it's a bit funky, _lookup needs to return an error code
- * (negative) or a NULL, both as a dentry. ENOENT should not
- * be returned, instead we need to create a negative dentry by
- * d_add(dentry, NULL); and return 0 as no error.
- * (Although as I see, it only matters on writable file
- * systems).
- */
-out0:
- inode = NULL;
-outi:
- d_add(dentry, inode);
- ret = 0;
+ return d_splice_alias(inode, dentry);
error:
return ERR_PTR(ret);
}
diff --git a/fs/select.c b/fs/select.c
index ba879c5..bc3cc0f 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -34,6 +34,29 @@
#include <linux/uaccess.h>
+__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
+{
+ if (file->f_op->poll) {
+ return file->f_op->poll(file, pt);
+ } else if (file_has_poll_mask(file)) {
+ unsigned int events = poll_requested_events(pt);
+ struct wait_queue_head *head;
+
+ if (pt && pt->_qproc) {
+ head = file->f_op->get_poll_head(file, events);
+ if (!head)
+ return DEFAULT_POLLMASK;
+ if (IS_ERR(head))
+ return EPOLLERR;
+ pt->_qproc(file, head, pt);
+ }
+
+ return file->f_op->poll_mask(file, events);
+ } else {
+ return DEFAULT_POLLMASK;
+ }
+}
+EXPORT_SYMBOL_GPL(vfs_poll);
/*
* Estimate expected accuracy in ns from a timeval.
@@ -233,7 +256,7 @@ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
add_wait_queue(wait_address, &entry->wait);
}
-int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
+static int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
ktime_t *expires, unsigned long slack)
{
int rc = -EINTR;
@@ -258,7 +281,6 @@ int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
return rc;
}
-EXPORT_SYMBOL(poll_schedule_timeout);
/**
* poll_select_set_timeout - helper function to setup the timeout value
@@ -503,14 +525,10 @@ static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
continue;
f = fdget(i);
if (f.file) {
- const struct file_operations *f_op;
- f_op = f.file->f_op;
- mask = DEFAULT_POLLMASK;
- if (f_op->poll) {
- wait_key_set(wait, in, out,
- bit, busy_flag);
- mask = (*f_op->poll)(f.file, wait);
- }
+ wait_key_set(wait, in, out, bit,
+ busy_flag);
+ mask = vfs_poll(f.file, wait);
+
fdput(f);
if ((mask & POLLIN_SET) && (in & bit)) {
res_in |= bit;
@@ -813,34 +831,29 @@ static inline __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait,
bool *can_busy_poll,
__poll_t busy_flag)
{
- __poll_t mask;
- int fd;
+ int fd = pollfd->fd;
+ __poll_t mask = 0, filter;
+ struct fd f;
- mask = 0;
- fd = pollfd->fd;
- if (fd >= 0) {
- struct fd f = fdget(fd);
- mask = EPOLLNVAL;
- if (f.file) {
- /* userland u16 ->events contains POLL... bitmap */
- __poll_t filter = demangle_poll(pollfd->events) |
- EPOLLERR | EPOLLHUP;
- mask = DEFAULT_POLLMASK;
- if (f.file->f_op->poll) {
- pwait->_key = filter;
- pwait->_key |= busy_flag;
- mask = f.file->f_op->poll(f.file, pwait);
- if (mask & busy_flag)
- *can_busy_poll = true;
- }
- /* Mask out unneeded events. */
- mask &= filter;
- fdput(f);
- }
- }
+ if (fd < 0)
+ goto out;
+ mask = EPOLLNVAL;
+ f = fdget(fd);
+ if (!f.file)
+ goto out;
+
+ /* userland u16 ->events contains POLL... bitmap */
+ filter = demangle_poll(pollfd->events) | EPOLLERR | EPOLLHUP;
+ pwait->_key = filter | busy_flag;
+ mask = vfs_poll(f.file, pwait);
+ if (mask & busy_flag)
+ *can_busy_poll = true;
+ mask &= filter; /* Mask out unneeded events. */
+ fdput(f);
+
+out:
/* ... and so does ->revents */
pollfd->revents = mangle_poll(mask);
-
return mask;
}
diff --git a/fs/seq_file.c b/fs/seq_file.c
index c6c27f1..4cc090b 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -709,11 +709,6 @@ void seq_put_decimal_ull_width(struct seq_file *m, const char *delimiter,
if (m->count + width >= m->size)
goto overflow;
- if (num < 10) {
- m->buf[m->count++] = num + '0';
- return;
- }
-
len = num_to_str(m->buf + m->count, m->size - m->count, num, width);
if (!len)
goto overflow;
diff --git a/fs/signalfd.c b/fs/signalfd.c
index d2187a8..cbb42f7 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -81,83 +81,86 @@ static __poll_t signalfd_poll(struct file *file, poll_table *wait)
static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
siginfo_t const *kinfo)
{
- long err;
+ struct signalfd_siginfo new;
BUILD_BUG_ON(sizeof(struct signalfd_siginfo) != 128);
/*
* Unused members should be zero ...
*/
- err = __clear_user(uinfo, sizeof(*uinfo));
+ memset(&new, 0, sizeof(new));
/*
* If you change siginfo_t structure, please be sure
* this code is fixed accordingly.
*/
- err |= __put_user(kinfo->si_signo, &uinfo->ssi_signo);
- err |= __put_user(kinfo->si_errno, &uinfo->ssi_errno);
- err |= __put_user(kinfo->si_code, &uinfo->ssi_code);
+ new.ssi_signo = kinfo->si_signo;
+ new.ssi_errno = kinfo->si_errno;
+ new.ssi_code = kinfo->si_code;
switch (siginfo_layout(kinfo->si_signo, kinfo->si_code)) {
case SIL_KILL:
- err |= __put_user(kinfo->si_pid, &uinfo->ssi_pid);
- err |= __put_user(kinfo->si_uid, &uinfo->ssi_uid);
+ new.ssi_pid = kinfo->si_pid;
+ new.ssi_uid = kinfo->si_uid;
break;
case SIL_TIMER:
- err |= __put_user(kinfo->si_tid, &uinfo->ssi_tid);
- err |= __put_user(kinfo->si_overrun, &uinfo->ssi_overrun);
- err |= __put_user((long) kinfo->si_ptr, &uinfo->ssi_ptr);
- err |= __put_user(kinfo->si_int, &uinfo->ssi_int);
+ new.ssi_tid = kinfo->si_tid;
+ new.ssi_overrun = kinfo->si_overrun;
+ new.ssi_ptr = (long) kinfo->si_ptr;
+ new.ssi_int = kinfo->si_int;
break;
case SIL_POLL:
- err |= __put_user(kinfo->si_band, &uinfo->ssi_band);
- err |= __put_user(kinfo->si_fd, &uinfo->ssi_fd);
+ new.ssi_band = kinfo->si_band;
+ new.ssi_fd = kinfo->si_fd;
break;
+ case SIL_FAULT_BNDERR:
+ case SIL_FAULT_PKUERR:
+ /*
+ * Fall through to the SIL_FAULT case. Both SIL_FAULT_BNDERR
+ * and SIL_FAULT_PKUERR are only generated by faults that
+ * deliver them synchronously to userspace. In case someone
+ * injects one of these signals and signalfd catches it treat
+ * it as SIL_FAULT.
+ */
case SIL_FAULT:
- err |= __put_user((long) kinfo->si_addr, &uinfo->ssi_addr);
+ new.ssi_addr = (long) kinfo->si_addr;
#ifdef __ARCH_SI_TRAPNO
- err |= __put_user(kinfo->si_trapno, &uinfo->ssi_trapno);
+ new.ssi_trapno = kinfo->si_trapno;
#endif
-#ifdef BUS_MCEERR_AO
- /*
- * Other callers might not initialize the si_lsb field,
- * so check explicitly for the right codes here.
- */
- if (kinfo->si_signo == SIGBUS &&
- kinfo->si_code == BUS_MCEERR_AO)
- err |= __put_user((short) kinfo->si_addr_lsb,
- &uinfo->ssi_addr_lsb);
+ break;
+ case SIL_FAULT_MCEERR:
+ new.ssi_addr = (long) kinfo->si_addr;
+#ifdef __ARCH_SI_TRAPNO
+ new.ssi_trapno = kinfo->si_trapno;
#endif
-#ifdef BUS_MCEERR_AR
- /*
- * Other callers might not initialize the si_lsb field,
- * so check explicitly for the right codes here.
- */
- if (kinfo->si_signo == SIGBUS &&
- kinfo->si_code == BUS_MCEERR_AR)
- err |= __put_user((short) kinfo->si_addr_lsb,
- &uinfo->ssi_addr_lsb);
-#endif
+ new.ssi_addr_lsb = (short) kinfo->si_addr_lsb;
break;
case SIL_CHLD:
- err |= __put_user(kinfo->si_pid, &uinfo->ssi_pid);
- err |= __put_user(kinfo->si_uid, &uinfo->ssi_uid);
- err |= __put_user(kinfo->si_status, &uinfo->ssi_status);
- err |= __put_user(kinfo->si_utime, &uinfo->ssi_utime);
- err |= __put_user(kinfo->si_stime, &uinfo->ssi_stime);
+ new.ssi_pid = kinfo->si_pid;
+ new.ssi_uid = kinfo->si_uid;
+ new.ssi_status = kinfo->si_status;
+ new.ssi_utime = kinfo->si_utime;
+ new.ssi_stime = kinfo->si_stime;
break;
case SIL_RT:
- default:
/*
* This case catches also the signals queued by sigqueue().
*/
- err |= __put_user(kinfo->si_pid, &uinfo->ssi_pid);
- err |= __put_user(kinfo->si_uid, &uinfo->ssi_uid);
- err |= __put_user((long) kinfo->si_ptr, &uinfo->ssi_ptr);
- err |= __put_user(kinfo->si_int, &uinfo->ssi_int);
+ new.ssi_pid = kinfo->si_pid;
+ new.ssi_uid = kinfo->si_uid;
+ new.ssi_ptr = (long) kinfo->si_ptr;
+ new.ssi_int = kinfo->si_int;
+ break;
+ case SIL_SYS:
+ new.ssi_call_addr = (long) kinfo->si_call_addr;
+ new.ssi_syscall = kinfo->si_syscall;
+ new.ssi_arch = kinfo->si_arch;
break;
}
- return err ? -EFAULT: sizeof(*uinfo);
+ if (copy_to_user(uinfo, &new, sizeof(struct signalfd_siginfo)))
+ return -EFAULT;
+
+ return sizeof(*uinfo);
}
static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, siginfo_t *info,
diff --git a/fs/super.c b/fs/super.c
index 5fa9a8d..50728d9 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -121,13 +121,23 @@ static unsigned long super_cache_count(struct shrinker *shrink,
sb = container_of(shrink, struct super_block, s_shrink);
/*
- * Don't call trylock_super as it is a potential
- * scalability bottleneck. The counts could get updated
- * between super_cache_count and super_cache_scan anyway.
- * Call to super_cache_count with shrinker_rwsem held
- * ensures the safety of call to list_lru_shrink_count() and
- * s_op->nr_cached_objects().
+ * We don't call trylock_super() here as it is a scalability bottleneck,
+ * so we're exposed to partial setup state. The shrinker rwsem does not
+ * protect filesystem operations backing list_lru_shrink_count() or
+ * s_op->nr_cached_objects(). Counts can change between
+ * super_cache_count and super_cache_scan, so we really don't need locks
+ * here.
+ *
+ * However, if we are currently mounting the superblock, the underlying
+ * filesystem might be in a state of partial construction and hence it
+ * is dangerous to access it. trylock_super() uses a SB_BORN check to
+ * avoid this situation, so do the same here. The memory barrier is
+ * matched with the one in mount_fs() as we don't hold locks here.
*/
+ if (!(sb->s_flags & SB_BORN))
+ return 0;
+ smp_rmb();
+
if (sb->s_op && sb->s_op->nr_cached_objects)
total_objects = sb->s_op->nr_cached_objects(sb, sc);
@@ -167,6 +177,7 @@ static void destroy_unused_super(struct super_block *s)
security_sb_free(s);
put_user_ns(s->s_user_ns);
kfree(s->s_subtype);
+ free_prealloced_shrinker(&s->s_shrink);
/* no delays needed */
destroy_super_work(&s->destroy_work);
}
@@ -252,6 +263,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags,
s->s_shrink.count_objects = super_cache_count;
s->s_shrink.batch = 1024;
s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE;
+ if (prealloc_shrinker(&s->s_shrink))
+ goto fail;
return s;
fail:
@@ -518,11 +531,7 @@ struct super_block *sget_userns(struct file_system_type *type,
hlist_add_head(&s->s_instances, &type->fs_supers);
spin_unlock(&sb_lock);
get_filesystem(type);
- err = register_shrinker(&s->s_shrink);
- if (err) {
- deactivate_locked_super(s);
- s = ERR_PTR(err);
- }
+ register_shrinker_prepared(&s->s_shrink);
return s;
}
@@ -938,7 +947,7 @@ void emergency_remount(void)
static void do_thaw_all_callback(struct super_block *sb)
{
down_write(&sb->s_umount);
- if (sb->s_root && sb->s_flags & MS_BORN) {
+ if (sb->s_root && sb->s_flags & SB_BORN) {
emergency_thaw_bdev(sb);
thaw_super_locked(sb);
} else {
@@ -1273,6 +1282,14 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data)
sb = root->d_sb;
BUG_ON(!sb);
WARN_ON(!sb->s_bdi);
+
+ /*
+ * Write barrier is for super_cache_count(). We place it before setting
+ * SB_BORN as the data dependency between the two functions is the
+ * superblock structure contents that we just set up, not the SB_BORN
+ * flag.
+ */
+ smp_wmb();
sb->s_flags |= SB_BORN;
error = security_sb_kern_mount(sb, flags, secdata);
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index b428d31..92682fc 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -25,7 +25,7 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
{
struct dentry *root;
void *ns;
- bool new_sb;
+ bool new_sb = false;
if (!(flags & SB_KERNMOUNT)) {
if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET))
@@ -35,9 +35,9 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
root = kernfs_mount_ns(fs_type, flags, sysfs_root,
SYSFS_MAGIC, &new_sb, ns);
- if (IS_ERR(root) || !new_sb)
+ if (!new_sb)
kobj_ns_drop(KOBJ_NS_TYPE_NET, ns);
- else if (new_sb)
+ else if (!IS_ERR(root))
root->d_sb->s_iflags |= SB_I_USERNS_VISIBLE;
return root;
diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c
index 250b075..4d5d204 100644
--- a/fs/sysv/namei.c
+++ b/fs/sysv/namei.c
@@ -51,14 +51,9 @@ static struct dentry *sysv_lookup(struct inode * dir, struct dentry * dentry, un
if (dentry->d_name.len > SYSV_NAMELEN)
return ERR_PTR(-ENAMETOOLONG);
ino = sysv_inode_by_name(dentry);
-
- if (ino) {
+ if (ino)
inode = sysv_iget(dir->i_sb, ino);
- if (IS_ERR(inode))
- return ERR_CAST(inode);
- }
- d_add(dentry, inode);
- return NULL;
+ return d_splice_alias(inode, dentry);
}
static int sysv_mknod(struct inode * dir, struct dentry * dentry, umode_t mode, dev_t rdev)
diff --git a/fs/timerfd.c b/fs/timerfd.c
index cdad49d..d84a2be 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -226,21 +226,20 @@ static int timerfd_release(struct inode *inode, struct file *file)
kfree_rcu(ctx, rcu);
return 0;
}
-
-static __poll_t timerfd_poll(struct file *file, poll_table *wait)
+
+static struct wait_queue_head *timerfd_get_poll_head(struct file *file,
+ __poll_t eventmask)
{
struct timerfd_ctx *ctx = file->private_data;
- __poll_t events = 0;
- unsigned long flags;
- poll_wait(file, &ctx->wqh, wait);
+ return &ctx->wqh;
+}
- spin_lock_irqsave(&ctx->wqh.lock, flags);
- if (ctx->ticks)
- events |= EPOLLIN;
- spin_unlock_irqrestore(&ctx->wqh.lock, flags);
+static __poll_t timerfd_poll_mask(struct file *file, __poll_t eventmask)
+{
+ struct timerfd_ctx *ctx = file->private_data;
- return events;
+ return ctx->ticks ? EPOLLIN : 0;
}
static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count,
@@ -364,7 +363,8 @@ static long timerfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg
static const struct file_operations timerfd_fops = {
.release = timerfd_release,
- .poll = timerfd_poll,
+ .get_poll_head = timerfd_get_poll_head,
+ .poll_mask = timerfd_poll_mask,
.read = timerfd_read,
.llseek = noop_llseek,
.show_fdinfo = timerfd_show,
diff --git a/fs/ubifs/crypto.c b/fs/ubifs/crypto.c
index 616a688..55c508f 100644
--- a/fs/ubifs/crypto.c
+++ b/fs/ubifs/crypto.c
@@ -24,14 +24,6 @@ static bool ubifs_crypt_empty_dir(struct inode *inode)
return ubifs_check_dir_empty(inode) == 0;
}
-static unsigned int ubifs_crypt_max_namelen(struct inode *inode)
-{
- if (S_ISLNK(inode->i_mode))
- return UBIFS_MAX_INO_DATA;
- else
- return UBIFS_MAX_NLEN;
-}
-
int ubifs_encrypt(const struct inode *inode, struct ubifs_data_node *dn,
unsigned int in_len, unsigned int *out_len, int block)
{
@@ -89,5 +81,5 @@ const struct fscrypt_operations ubifs_crypt_operations = {
.get_context = ubifs_crypt_get_context,
.set_context = ubifs_crypt_set_context,
.empty_dir = ubifs_crypt_empty_dir,
- .max_namelen = ubifs_crypt_max_namelen,
+ .max_namelen = UBIFS_MAX_NLEN,
};
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 9d7fb88..4e267cc 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -214,7 +214,7 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
int err;
union ubifs_key key;
struct inode *inode = NULL;
- struct ubifs_dent_node *dent;
+ struct ubifs_dent_node *dent = NULL;
struct ubifs_info *c = dir->i_sb->s_fs_info;
struct fscrypt_name nm;
@@ -229,14 +229,14 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
return ERR_PTR(err);
if (fname_len(&nm) > UBIFS_MAX_NLEN) {
- err = -ENAMETOOLONG;
- goto out_fname;
+ inode = ERR_PTR(-ENAMETOOLONG);
+ goto done;
}
dent = kmalloc(UBIFS_MAX_DENT_NODE_SZ, GFP_NOFS);
if (!dent) {
- err = -ENOMEM;
- goto out_fname;
+ inode = ERR_PTR(-ENOMEM);
+ goto done;
}
if (nm.hash) {
@@ -250,16 +250,16 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
}
if (err) {
- if (err == -ENOENT) {
+ if (err == -ENOENT)
dbg_gen("not found");
- goto done;
- }
- goto out_dent;
+ else
+ inode = ERR_PTR(err);
+ goto done;
}
if (dbg_check_name(c, dent, &nm)) {
- err = -EINVAL;
- goto out_dent;
+ inode = ERR_PTR(-EINVAL);
+ goto done;
}
inode = ubifs_iget(dir->i_sb, le64_to_cpu(dent->inum));
@@ -272,7 +272,7 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
ubifs_err(c, "dead directory entry '%pd', error %d",
dentry, err);
ubifs_ro_mode(c, err);
- goto out_dent;
+ goto done;
}
if (ubifs_crypt_is_encrypted(dir) &&
@@ -280,27 +280,14 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
!fscrypt_has_permitted_context(dir, inode)) {
ubifs_warn(c, "Inconsistent encryption contexts: %lu/%lu",
dir->i_ino, inode->i_ino);
- err = -EPERM;
- goto out_inode;
+ iput(inode);
+ inode = ERR_PTR(-EPERM);
}
done:
kfree(dent);
fscrypt_free_filename(&nm);
- /*
- * Note, d_splice_alias() would be required instead if we supported
- * NFS.
- */
- d_add(dentry, inode);
- return NULL;
-
-out_inode:
- iput(inode);
-out_dent:
- kfree(dent);
-out_fname:
- fscrypt_free_filename(&nm);
- return ERR_PTR(err);
+ return d_splice_alias(inode, dentry);
}
static int ubifs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index 0458dd4..c586026 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -622,8 +622,7 @@ static int udf_add_nondir(struct dentry *dentry, struct inode *inode)
if (fibh.sbh != fibh.ebh)
brelse(fibh.ebh);
brelse(fibh.sbh);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
}
@@ -733,8 +732,7 @@ static int udf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
inc_nlink(dir);
dir->i_ctime = dir->i_mtime = current_time(dir);
mark_inode_dirty(dir);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
if (fibh.sbh != fibh.ebh)
brelse(fibh.ebh);
brelse(fibh.sbh);
diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c
index f897e55..16a8ad2 100644
--- a/fs/udf/unicode.c
+++ b/fs/udf/unicode.c
@@ -28,6 +28,9 @@
#include "udf_sb.h"
+#define SURROGATE_MASK 0xfffff800
+#define SURROGATE_PAIR 0x0000d800
+
static int udf_uni2char_utf8(wchar_t uni,
unsigned char *out,
int boundlen)
@@ -37,6 +40,9 @@ static int udf_uni2char_utf8(wchar_t uni,
if (boundlen <= 0)
return -ENAMETOOLONG;
+ if ((uni & SURROGATE_MASK) == SURROGATE_PAIR)
+ return -EINVAL;
+
if (uni < 0x80) {
out[u_len++] = (unsigned char)uni;
} else if (uni < 0x800) {
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index 32545cd..d5f43ba 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -39,8 +39,7 @@ static inline int ufs_add_nondir(struct dentry *dentry, struct inode *inode)
{
int err = ufs_add_link(dentry, inode);
if (!err) {
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
}
inode_dec_link_count(inode);
@@ -193,8 +192,7 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
if (err)
goto out_fail;
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
out_fail:
diff --git a/fs/xattr.c b/fs/xattr.c
index 61cd28b..f9cb1db 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -229,7 +229,7 @@ vfs_setxattr(struct dentry *dentry, const char *name, const void *value,
}
EXPORT_SYMBOL_GPL(vfs_setxattr);
-ssize_t
+static ssize_t
xattr_getsecurity(struct inode *inode, const char *name, void *value,
size_t size)
{
@@ -254,7 +254,6 @@ xattr_getsecurity(struct inode *inode, const char *name, void *value,
out_noalloc:
return len;
}
-EXPORT_SYMBOL_GPL(xattr_getsecurity);
/*
* vfs_getxattr_alloc - allocate memory, if necessary, before calling getxattr
@@ -354,7 +353,6 @@ vfs_listxattr(struct dentry *dentry, char *list, size_t size)
if (error)
return error;
if (inode->i_op->listxattr && (inode->i_opflags & IOP_XATTR)) {
- error = -EOPNOTSUPP;
error = inode->i_op->listxattr(dentry, list, size);
} else {
error = security_inode_listsecurity(inode, list, size);
diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index 46bcf0e6..457ac9f 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -85,6 +85,24 @@
If unsure, say N.
+config XFS_ONLINE_REPAIR
+ bool "XFS online metadata repair support"
+ default n
+ depends on XFS_FS && XFS_ONLINE_SCRUB
+ help
+ If you say Y here you will be able to repair metadata on a
+ mounted XFS filesystem. This feature is intended to reduce
+ filesystem downtime by fixing minor problems before they cause the
+ filesystem to go down. However, it requires that the filesystem be
+ formatted with secondary metadata, such as reverse mappings and inode
+ parent pointers.
+
+ This feature is considered EXPERIMENTAL. Use with caution!
+
+ See the xfs_scrub man page in section 8 for additional information.
+
+ If unsure, say N.
+
config XFS_WARN
bool "XFS Verbose Warnings"
depends on XFS_FS && !XFS_DEBUG
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 7ceb41a..e8d67a4 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -28,6 +28,7 @@
# build the libxfs code first
xfs-y += $(addprefix libxfs/, \
+ xfs_ag.o \
xfs_alloc.o \
xfs_alloc_btree.o \
xfs_attr.o \
@@ -163,4 +164,12 @@
xfs-$(CONFIG_XFS_RT) += scrub/rtbitmap.o
xfs-$(CONFIG_XFS_QUOTA) += scrub/quota.o
+
+# online repair
+ifeq ($(CONFIG_XFS_ONLINE_REPAIR),y)
+xfs-y += $(addprefix scrub/, \
+ agheader_repair.o \
+ repair.o \
+ )
+endif
endif
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
new file mode 100644
index 0000000..9345802
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -0,0 +1,464 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * Copyright (c) 2018 Red Hat, Inc.
+ * All rights reserved.
+ */
+
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_sb.h"
+#include "xfs_mount.h"
+#include "xfs_btree.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_alloc.h"
+#include "xfs_ialloc.h"
+#include "xfs_rmap.h"
+#include "xfs_ag.h"
+
+static struct xfs_buf *
+xfs_get_aghdr_buf(
+ struct xfs_mount *mp,
+ xfs_daddr_t blkno,
+ size_t numblks,
+ int flags,
+ const struct xfs_buf_ops *ops)
+{
+ struct xfs_buf *bp;
+
+ bp = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, flags);
+ if (!bp)
+ return NULL;
+
+ xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
+ bp->b_bn = blkno;
+ bp->b_maps[0].bm_bn = blkno;
+ bp->b_ops = ops;
+
+ return bp;
+}
+
+/*
+ * Generic btree root block init function
+ */
+static void
+xfs_btroot_init(
+ struct xfs_mount *mp,
+ struct xfs_buf *bp,
+ struct aghdr_init_data *id)
+{
+ xfs_btree_init_block(mp, bp, id->type, 0, 0, id->agno, 0);
+}
+
+/*
+ * Alloc btree root block init functions
+ */
+static void
+xfs_bnoroot_init(
+ struct xfs_mount *mp,
+ struct xfs_buf *bp,
+ struct aghdr_init_data *id)
+{
+ struct xfs_alloc_rec *arec;
+
+ xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 1, id->agno, 0);
+ arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
+ arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks);
+ arec->ar_blockcount = cpu_to_be32(id->agsize -
+ be32_to_cpu(arec->ar_startblock));
+}
+
+static void
+xfs_cntroot_init(
+ struct xfs_mount *mp,
+ struct xfs_buf *bp,
+ struct aghdr_init_data *id)
+{
+ struct xfs_alloc_rec *arec;
+
+ xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 1, id->agno, 0);
+ arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
+ arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks);
+ arec->ar_blockcount = cpu_to_be32(id->agsize -
+ be32_to_cpu(arec->ar_startblock));
+}
+
+/*
+ * Reverse map root block init
+ */
+static void
+xfs_rmaproot_init(
+ struct xfs_mount *mp,
+ struct xfs_buf *bp,
+ struct aghdr_init_data *id)
+{
+ struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
+ struct xfs_rmap_rec *rrec;
+
+ xfs_btree_init_block(mp, bp, XFS_BTNUM_RMAP, 0, 4, id->agno, 0);
+
+ /*
+ * mark the AG header regions as static metadata The BNO
+ * btree block is the first block after the headers, so
+ * it's location defines the size of region the static
+ * metadata consumes.
+ *
+ * Note: unlike mkfs, we never have to account for log
+ * space when growing the data regions
+ */
+ rrec = XFS_RMAP_REC_ADDR(block, 1);
+ rrec->rm_startblock = 0;
+ rrec->rm_blockcount = cpu_to_be32(XFS_BNO_BLOCK(mp));
+ rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_FS);
+ rrec->rm_offset = 0;
+
+ /* account freespace btree root blocks */
+ rrec = XFS_RMAP_REC_ADDR(block, 2);
+ rrec->rm_startblock = cpu_to_be32(XFS_BNO_BLOCK(mp));
+ rrec->rm_blockcount = cpu_to_be32(2);
+ rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_AG);
+ rrec->rm_offset = 0;
+
+ /* account inode btree root blocks */
+ rrec = XFS_RMAP_REC_ADDR(block, 3);
+ rrec->rm_startblock = cpu_to_be32(XFS_IBT_BLOCK(mp));
+ rrec->rm_blockcount = cpu_to_be32(XFS_RMAP_BLOCK(mp) -
+ XFS_IBT_BLOCK(mp));
+ rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_INOBT);
+ rrec->rm_offset = 0;
+
+ /* account for rmap btree root */
+ rrec = XFS_RMAP_REC_ADDR(block, 4);
+ rrec->rm_startblock = cpu_to_be32(XFS_RMAP_BLOCK(mp));
+ rrec->rm_blockcount = cpu_to_be32(1);
+ rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_AG);
+ rrec->rm_offset = 0;
+
+ /* account for refc btree root */
+ if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+ rrec = XFS_RMAP_REC_ADDR(block, 5);
+ rrec->rm_startblock = cpu_to_be32(xfs_refc_block(mp));
+ rrec->rm_blockcount = cpu_to_be32(1);
+ rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_REFC);
+ rrec->rm_offset = 0;
+ be16_add_cpu(&block->bb_numrecs, 1);
+ }
+}
+
+/*
+ * Initialise new secondary superblocks with the pre-grow geometry, but mark
+ * them as "in progress" so we know they haven't yet been activated. This will
+ * get cleared when the update with the new geometry information is done after
+ * changes to the primary are committed. This isn't strictly necessary, but we
+ * get it for free with the delayed buffer write lists and it means we can tell
+ * if a grow operation didn't complete properly after the fact.
+ */
+static void
+xfs_sbblock_init(
+ struct xfs_mount *mp,
+ struct xfs_buf *bp,
+ struct aghdr_init_data *id)
+{
+ struct xfs_dsb *dsb = XFS_BUF_TO_SBP(bp);
+
+ xfs_sb_to_disk(dsb, &mp->m_sb);
+ dsb->sb_inprogress = 1;
+}
+
+static void
+xfs_agfblock_init(
+ struct xfs_mount *mp,
+ struct xfs_buf *bp,
+ struct aghdr_init_data *id)
+{
+ struct xfs_agf *agf = XFS_BUF_TO_AGF(bp);
+ xfs_extlen_t tmpsize;
+
+ agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC);
+ agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION);
+ agf->agf_seqno = cpu_to_be32(id->agno);
+ agf->agf_length = cpu_to_be32(id->agsize);
+ agf->agf_roots[XFS_BTNUM_BNOi] = cpu_to_be32(XFS_BNO_BLOCK(mp));
+ agf->agf_roots[XFS_BTNUM_CNTi] = cpu_to_be32(XFS_CNT_BLOCK(mp));
+ agf->agf_levels[XFS_BTNUM_BNOi] = cpu_to_be32(1);
+ agf->agf_levels[XFS_BTNUM_CNTi] = cpu_to_be32(1);
+ if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
+ agf->agf_roots[XFS_BTNUM_RMAPi] =
+ cpu_to_be32(XFS_RMAP_BLOCK(mp));
+ agf->agf_levels[XFS_BTNUM_RMAPi] = cpu_to_be32(1);
+ agf->agf_rmap_blocks = cpu_to_be32(1);
+ }
+
+ agf->agf_flfirst = cpu_to_be32(1);
+ agf->agf_fllast = 0;
+ agf->agf_flcount = 0;
+ tmpsize = id->agsize - mp->m_ag_prealloc_blocks;
+ agf->agf_freeblks = cpu_to_be32(tmpsize);
+ agf->agf_longest = cpu_to_be32(tmpsize);
+ if (xfs_sb_version_hascrc(&mp->m_sb))
+ uuid_copy(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid);
+ if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+ agf->agf_refcount_root = cpu_to_be32(
+ xfs_refc_block(mp));
+ agf->agf_refcount_level = cpu_to_be32(1);
+ agf->agf_refcount_blocks = cpu_to_be32(1);
+ }
+}
+
+static void
+xfs_agflblock_init(
+ struct xfs_mount *mp,
+ struct xfs_buf *bp,
+ struct aghdr_init_data *id)
+{
+ struct xfs_agfl *agfl = XFS_BUF_TO_AGFL(bp);
+ __be32 *agfl_bno;
+ int bucket;
+
+ if (xfs_sb_version_hascrc(&mp->m_sb)) {
+ agfl->agfl_magicnum = cpu_to_be32(XFS_AGFL_MAGIC);
+ agfl->agfl_seqno = cpu_to_be32(id->agno);
+ uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid);
+ }
+
+ agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, bp);
+ for (bucket = 0; bucket < xfs_agfl_size(mp); bucket++)
+ agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK);
+}
+
+static void
+xfs_agiblock_init(
+ struct xfs_mount *mp,
+ struct xfs_buf *bp,
+ struct aghdr_init_data *id)
+{
+ struct xfs_agi *agi = XFS_BUF_TO_AGI(bp);
+ int bucket;
+
+ agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC);
+ agi->agi_versionnum = cpu_to_be32(XFS_AGI_VERSION);
+ agi->agi_seqno = cpu_to_be32(id->agno);
+ agi->agi_length = cpu_to_be32(id->agsize);
+ agi->agi_count = 0;
+ agi->agi_root = cpu_to_be32(XFS_IBT_BLOCK(mp));
+ agi->agi_level = cpu_to_be32(1);
+ agi->agi_freecount = 0;
+ agi->agi_newino = cpu_to_be32(NULLAGINO);
+ agi->agi_dirino = cpu_to_be32(NULLAGINO);
+ if (xfs_sb_version_hascrc(&mp->m_sb))
+ uuid_copy(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid);
+ if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
+ agi->agi_free_root = cpu_to_be32(XFS_FIBT_BLOCK(mp));
+ agi->agi_free_level = cpu_to_be32(1);
+ }
+ for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++)
+ agi->agi_unlinked[bucket] = cpu_to_be32(NULLAGINO);
+}
+
+typedef void (*aghdr_init_work_f)(struct xfs_mount *mp, struct xfs_buf *bp,
+ struct aghdr_init_data *id);
+static int
+xfs_ag_init_hdr(
+ struct xfs_mount *mp,
+ struct aghdr_init_data *id,
+ aghdr_init_work_f work,
+ const struct xfs_buf_ops *ops)
+
+{
+ struct xfs_buf *bp;
+
+ bp = xfs_get_aghdr_buf(mp, id->daddr, id->numblks, 0, ops);
+ if (!bp)
+ return -ENOMEM;
+
+ (*work)(mp, bp, id);
+
+ xfs_buf_delwri_queue(bp, &id->buffer_list);
+ xfs_buf_relse(bp);
+ return 0;
+}
+
+struct xfs_aghdr_grow_data {
+ xfs_daddr_t daddr;
+ size_t numblks;
+ const struct xfs_buf_ops *ops;
+ aghdr_init_work_f work;
+ xfs_btnum_t type;
+ bool need_init;
+};
+
+/*
+ * Prepare new AG headers to be written to disk. We use uncached buffers here,
+ * as it is assumed these new AG headers are currently beyond the currently
+ * valid filesystem address space. Using cached buffers would trip over EOFS
+ * corruption detection alogrithms in the buffer cache lookup routines.
+ *
+ * This is a non-transactional function, but the prepared buffers are added to a
+ * delayed write buffer list supplied by the caller so they can submit them to
+ * disk and wait on them as required.
+ */
+int
+xfs_ag_init_headers(
+ struct xfs_mount *mp,
+ struct aghdr_init_data *id)
+
+{
+ struct xfs_aghdr_grow_data aghdr_data[] = {
+ { /* SB */
+ .daddr = XFS_AG_DADDR(mp, id->agno, XFS_SB_DADDR),
+ .numblks = XFS_FSS_TO_BB(mp, 1),
+ .ops = &xfs_sb_buf_ops,
+ .work = &xfs_sbblock_init,
+ .need_init = true
+ },
+ { /* AGF */
+ .daddr = XFS_AG_DADDR(mp, id->agno, XFS_AGF_DADDR(mp)),
+ .numblks = XFS_FSS_TO_BB(mp, 1),
+ .ops = &xfs_agf_buf_ops,
+ .work = &xfs_agfblock_init,
+ .need_init = true
+ },
+ { /* AGFL */
+ .daddr = XFS_AG_DADDR(mp, id->agno, XFS_AGFL_DADDR(mp)),
+ .numblks = XFS_FSS_TO_BB(mp, 1),
+ .ops = &xfs_agfl_buf_ops,
+ .work = &xfs_agflblock_init,
+ .need_init = true
+ },
+ { /* AGI */
+ .daddr = XFS_AG_DADDR(mp, id->agno, XFS_AGI_DADDR(mp)),
+ .numblks = XFS_FSS_TO_BB(mp, 1),
+ .ops = &xfs_agi_buf_ops,
+ .work = &xfs_agiblock_init,
+ .need_init = true
+ },
+ { /* BNO root block */
+ .daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_BNO_BLOCK(mp)),
+ .numblks = BTOBB(mp->m_sb.sb_blocksize),
+ .ops = &xfs_allocbt_buf_ops,
+ .work = &xfs_bnoroot_init,
+ .need_init = true
+ },
+ { /* CNT root block */
+ .daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_CNT_BLOCK(mp)),
+ .numblks = BTOBB(mp->m_sb.sb_blocksize),
+ .ops = &xfs_allocbt_buf_ops,
+ .work = &xfs_cntroot_init,
+ .need_init = true
+ },
+ { /* INO root block */
+ .daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_IBT_BLOCK(mp)),
+ .numblks = BTOBB(mp->m_sb.sb_blocksize),
+ .ops = &xfs_inobt_buf_ops,
+ .work = &xfs_btroot_init,
+ .type = XFS_BTNUM_INO,
+ .need_init = true
+ },
+ { /* FINO root block */
+ .daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_FIBT_BLOCK(mp)),
+ .numblks = BTOBB(mp->m_sb.sb_blocksize),
+ .ops = &xfs_inobt_buf_ops,
+ .work = &xfs_btroot_init,
+ .type = XFS_BTNUM_FINO,
+ .need_init = xfs_sb_version_hasfinobt(&mp->m_sb)
+ },
+ { /* RMAP root block */
+ .daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_RMAP_BLOCK(mp)),
+ .numblks = BTOBB(mp->m_sb.sb_blocksize),
+ .ops = &xfs_rmapbt_buf_ops,
+ .work = &xfs_rmaproot_init,
+ .need_init = xfs_sb_version_hasrmapbt(&mp->m_sb)
+ },
+ { /* REFC root block */
+ .daddr = XFS_AGB_TO_DADDR(mp, id->agno, xfs_refc_block(mp)),
+ .numblks = BTOBB(mp->m_sb.sb_blocksize),
+ .ops = &xfs_refcountbt_buf_ops,
+ .work = &xfs_btroot_init,
+ .type = XFS_BTNUM_REFC,
+ .need_init = xfs_sb_version_hasreflink(&mp->m_sb)
+ },
+ { /* NULL terminating block */
+ .daddr = XFS_BUF_DADDR_NULL,
+ }
+ };
+ struct xfs_aghdr_grow_data *dp;
+ int error = 0;
+
+ /* Account for AG free space in new AG */
+ id->nfree += id->agsize - mp->m_ag_prealloc_blocks;
+ for (dp = &aghdr_data[0]; dp->daddr != XFS_BUF_DADDR_NULL; dp++) {
+ if (!dp->need_init)
+ continue;
+
+ id->daddr = dp->daddr;
+ id->numblks = dp->numblks;
+ id->type = dp->type;
+ error = xfs_ag_init_hdr(mp, id, dp->work, dp->ops);
+ if (error)
+ break;
+ }
+ return error;
+}
+
+/*
+ * Extent the AG indicated by the @id by the length passed in
+ */
+int
+xfs_ag_extend_space(
+ struct xfs_mount *mp,
+ struct xfs_trans *tp,
+ struct aghdr_init_data *id,
+ xfs_extlen_t len)
+{
+ struct xfs_owner_info oinfo;
+ struct xfs_buf *bp;
+ struct xfs_agi *agi;
+ struct xfs_agf *agf;
+ int error;
+
+ /*
+ * Change the agi length.
+ */
+ error = xfs_ialloc_read_agi(mp, tp, id->agno, &bp);
+ if (error)
+ return error;
+
+ agi = XFS_BUF_TO_AGI(bp);
+ be32_add_cpu(&agi->agi_length, len);
+ ASSERT(id->agno == mp->m_sb.sb_agcount - 1 ||
+ be32_to_cpu(agi->agi_length) == mp->m_sb.sb_agblocks);
+ xfs_ialloc_log_agi(tp, bp, XFS_AGI_LENGTH);
+
+ /*
+ * Change agf length.
+ */
+ error = xfs_alloc_read_agf(mp, tp, id->agno, 0, &bp);
+ if (error)
+ return error;
+
+ agf = XFS_BUF_TO_AGF(bp);
+ be32_add_cpu(&agf->agf_length, len);
+ ASSERT(agf->agf_length == agi->agi_length);
+ xfs_alloc_log_agf(tp, bp, XFS_AGF_LENGTH);
+
+ /*
+ * Free the new space.
+ *
+ * XFS_RMAP_OWN_NULL is used here to tell the rmap btree that
+ * this doesn't actually exist in the rmap btree.
+ */
+ xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_NULL);
+ error = xfs_rmap_free(tp, bp, id->agno,
+ be32_to_cpu(agf->agf_length) - len,
+ len, &oinfo);
+ if (error)
+ return error;
+
+ return xfs_free_extent(tp, XFS_AGB_TO_FSB(mp, id->agno,
+ be32_to_cpu(agf->agf_length) - len),
+ len, &oinfo, XFS_AG_RESV_NONE);
+}
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
new file mode 100644
index 0000000..412702e
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018 Red Hat, Inc.
+ * All rights reserved.
+ */
+
+#ifndef __LIBXFS_AG_H
+#define __LIBXFS_AG_H 1
+
+struct xfs_mount;
+struct xfs_trans;
+
+struct aghdr_init_data {
+ /* per ag data */
+ xfs_agblock_t agno; /* ag to init */
+ xfs_extlen_t agsize; /* new AG size */
+ struct list_head buffer_list; /* buffer writeback list */
+ xfs_rfsblock_t nfree; /* cumulative new free space */
+
+ /* per header data */
+ xfs_daddr_t daddr; /* header location */
+ size_t numblks; /* size of header */
+ xfs_btnum_t type; /* type of btree root block */
+};
+
+int xfs_ag_init_headers(struct xfs_mount *mp, struct aghdr_init_data *id);
+int xfs_ag_extend_space(struct xfs_mount *mp, struct xfs_trans *tp,
+ struct aghdr_init_data *id, xfs_extlen_t len);
+
+#endif /* __LIBXFS_AG_H */
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 4bcc095..dc9dd38 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -39,6 +39,9 @@
#include "xfs_buf_item.h"
#include "xfs_log.h"
#include "xfs_ag_resv.h"
+#include "xfs_bmap.h"
+
+extern kmem_zone_t *xfs_bmap_free_item_zone;
struct workqueue_struct *xfs_alloc_wq;
@@ -2060,6 +2063,30 @@ xfs_alloc_space_available(
return true;
}
+int
+xfs_free_agfl_block(
+ struct xfs_trans *tp,
+ xfs_agnumber_t agno,
+ xfs_agblock_t agbno,
+ struct xfs_buf *agbp,
+ struct xfs_owner_info *oinfo)
+{
+ int error;
+ struct xfs_buf *bp;
+
+ error = xfs_free_ag_extent(tp, agbp, agno, agbno, 1, oinfo,
+ XFS_AG_RESV_AGFL);
+ if (error)
+ return error;
+
+ bp = xfs_btree_get_bufs(tp->t_mountp, tp, agno, agbno, 0);
+ if (!bp)
+ return -EFSCORRUPTED;
+ xfs_trans_binval(tp, bp);
+
+ return 0;
+}
+
/*
* Check the agfl fields of the agf for inconsistency or corruption. The purpose
* is to detect an agfl header padding mismatch between current and early v5
@@ -2148,6 +2175,40 @@ xfs_agfl_reset(
}
/*
+ * Defer an AGFL block free. This is effectively equivalent to
+ * xfs_bmap_add_free() with some special handling particular to AGFL blocks.
+ *
+ * Deferring AGFL frees helps prevent log reservation overruns due to too many
+ * allocation operations in a transaction. AGFL frees are prone to this problem
+ * because for one they are always freed one at a time. Further, an immediate
+ * AGFL block free can cause a btree join and require another block free before
+ * the real allocation can proceed. Deferring the free disconnects freeing up
+ * the AGFL slot from freeing the block.
+ */
+STATIC void
+xfs_defer_agfl_block(
+ struct xfs_mount *mp,
+ struct xfs_defer_ops *dfops,
+ xfs_agnumber_t agno,
+ xfs_fsblock_t agbno,
+ struct xfs_owner_info *oinfo)
+{
+ struct xfs_extent_free_item *new; /* new element */
+
+ ASSERT(xfs_bmap_free_item_zone != NULL);
+ ASSERT(oinfo != NULL);
+
+ new = kmem_zone_alloc(xfs_bmap_free_item_zone, KM_SLEEP);
+ new->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno);
+ new->xefi_blockcount = 1;
+ new->xefi_oinfo = *oinfo;
+
+ trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
+
+ xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_AGFL_FREE, &new->xefi_list);
+}
+
+/*
* Decide whether to use this allocation group for this allocation.
* If so, fix up the btree freelist's size.
*/
@@ -2247,21 +2308,20 @@ xfs_alloc_fix_freelist(
else
xfs_rmap_ag_owner(&targs.oinfo, XFS_RMAP_OWN_AG);
while (!(flags & XFS_ALLOC_FLAG_NOSHRINK) && pag->pagf_flcount > need) {
- struct xfs_buf *bp;
-
error = xfs_alloc_get_freelist(tp, agbp, &bno, 0);
if (error)
goto out_agbp_relse;
- error = xfs_free_ag_extent(tp, agbp, args->agno, bno, 1,
- &targs.oinfo, XFS_AG_RESV_AGFL);
- if (error)
- goto out_agbp_relse;
- bp = xfs_btree_get_bufs(mp, tp, args->agno, bno, 0);
- if (!bp) {
- error = -EFSCORRUPTED;
- goto out_agbp_relse;
+
+ /* defer agfl frees if dfops is provided */
+ if (tp->t_agfl_dfops) {
+ xfs_defer_agfl_block(mp, tp->t_agfl_dfops, args->agno,
+ bno, &targs.oinfo);
+ } else {
+ error = xfs_free_agfl_block(tp, args->agno, bno, agbp,
+ &targs.oinfo);
+ if (error)
+ goto out_agbp_relse;
}
- xfs_trans_binval(tp, bp);
}
targs.tp = tp;
@@ -2949,18 +3009,20 @@ xfs_free_extent_fix_freelist(
* after fixing up the freelist.
*/
int /* error */
-xfs_free_extent(
+__xfs_free_extent(
struct xfs_trans *tp, /* transaction pointer */
xfs_fsblock_t bno, /* starting block number of extent */
xfs_extlen_t len, /* length of extent */
struct xfs_owner_info *oinfo, /* extent owner */
- enum xfs_ag_resv_type type) /* block reservation type */
+ enum xfs_ag_resv_type type, /* block reservation type */
+ bool skip_discard)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_buf *agbp;
xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, bno);
xfs_agblock_t agbno = XFS_FSB_TO_AGBNO(mp, bno);
int error;
+ unsigned int busy_flags = 0;
ASSERT(len != 0);
ASSERT(type != XFS_AG_RESV_AGFL);
@@ -2984,7 +3046,9 @@ xfs_free_extent(
if (error)
goto err;
- xfs_extent_busy_insert(tp, agno, agbno, len, 0);
+ if (skip_discard)
+ busy_flags |= XFS_EXTENT_BUSY_SKIP_DISCARD;
+ xfs_extent_busy_insert(tp, agno, agbno, len, busy_flags);
return 0;
err:
@@ -3116,3 +3180,40 @@ xfs_alloc_has_record(
return xfs_btree_has_record(cur, &low, &high, exists);
}
+
+/*
+ * Walk all the blocks in the AGFL. The @walk_fn can return any negative
+ * error code or XFS_BTREE_QUERY_RANGE_ABORT.
+ */
+int
+xfs_agfl_walk(
+ struct xfs_mount *mp,
+ struct xfs_agf *agf,
+ struct xfs_buf *agflbp,
+ xfs_agfl_walk_fn walk_fn,
+ void *priv)
+{
+ __be32 *agfl_bno;
+ unsigned int i;
+ int error;
+
+ agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, agflbp);
+ i = be32_to_cpu(agf->agf_flfirst);
+
+ /* Nothing to walk in an empty AGFL. */
+ if (agf->agf_flcount == cpu_to_be32(0))
+ return 0;
+
+ /* Otherwise, walk from first to last, wrapping as needed. */
+ for (;;) {
+ error = walk_fn(mp, be32_to_cpu(agfl_bno[i]), priv);
+ if (error)
+ return error;
+ if (i == be32_to_cpu(agf->agf_fllast))
+ break;
+ if (++i == xfs_agfl_size(mp))
+ i = 0;
+ }
+
+ return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index cbf789e..0747adc 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -191,12 +191,24 @@ xfs_alloc_vextent(
* Free an extent.
*/
int /* error */
-xfs_free_extent(
+__xfs_free_extent(
struct xfs_trans *tp, /* transaction pointer */
xfs_fsblock_t bno, /* starting block number of extent */
xfs_extlen_t len, /* length of extent */
struct xfs_owner_info *oinfo, /* extent owner */
- enum xfs_ag_resv_type type); /* block reservation type */
+ enum xfs_ag_resv_type type, /* block reservation type */
+ bool skip_discard);
+
+static inline int
+xfs_free_extent(
+ struct xfs_trans *tp,
+ xfs_fsblock_t bno,
+ xfs_extlen_t len,
+ struct xfs_owner_info *oinfo,
+ enum xfs_ag_resv_type type)
+{
+ return __xfs_free_extent(tp, bno, len, oinfo, type, false);
+}
int /* error */
xfs_alloc_lookup_le(
@@ -223,6 +235,8 @@ int xfs_read_agf(struct xfs_mount *mp, struct xfs_trans *tp,
xfs_agnumber_t agno, int flags, struct xfs_buf **bpp);
int xfs_alloc_read_agfl(struct xfs_mount *mp, struct xfs_trans *tp,
xfs_agnumber_t agno, struct xfs_buf **bpp);
+int xfs_free_agfl_block(struct xfs_trans *, xfs_agnumber_t, xfs_agblock_t,
+ struct xfs_buf *, struct xfs_owner_info *);
int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, int flags);
int xfs_free_extent_fix_freelist(struct xfs_trans *tp, xfs_agnumber_t agno,
struct xfs_buf **agbp);
@@ -248,4 +262,9 @@ bool xfs_verify_fsbno(struct xfs_mount *mp, xfs_fsblock_t fsbno);
int xfs_alloc_has_record(struct xfs_btree_cur *cur, xfs_agblock_t bno,
xfs_extlen_t len, bool *exist);
+typedef int (*xfs_agfl_walk_fn)(struct xfs_mount *mp, xfs_agblock_t bno,
+ void *priv);
+int xfs_agfl_walk(struct xfs_mount *mp, struct xfs_agf *agf,
+ struct xfs_buf *agflbp, xfs_agfl_walk_fn walk_fn, void *priv);
+
#endif /* __XFS_ALLOC_H__ */
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index b451649b..18aec7a 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -547,3 +547,12 @@ xfs_allocbt_maxrecs(
return blocklen / sizeof(xfs_alloc_rec_t);
return blocklen / (sizeof(xfs_alloc_key_t) + sizeof(xfs_alloc_ptr_t));
}
+
+/* Calculate the freespace btree size for some records. */
+xfs_extlen_t
+xfs_allocbt_calc_size(
+ struct xfs_mount *mp,
+ unsigned long long len)
+{
+ return xfs_btree_calc_size(mp->m_alloc_mnr, len);
+}
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.h b/fs/xfs/libxfs/xfs_alloc_btree.h
index 45e189e..2fd5472 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.h
+++ b/fs/xfs/libxfs/xfs_alloc_btree.h
@@ -61,5 +61,7 @@ extern struct xfs_btree_cur *xfs_allocbt_init_cursor(struct xfs_mount *,
struct xfs_trans *, struct xfs_buf *,
xfs_agnumber_t, xfs_btnum_t);
extern int xfs_allocbt_maxrecs(struct xfs_mount *, int, int);
+extern xfs_extlen_t xfs_allocbt_calc_size(struct xfs_mount *mp,
+ unsigned long long len);
#endif /* __XFS_ALLOC_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index ce4a34a..c3d02a6 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -236,7 +236,7 @@ xfs_attr_set(
args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
args.total = xfs_attr_calc_size(&args, &local);
- error = xfs_qm_dqattach(dp, 0);
+ error = xfs_qm_dqattach(dp);
if (error)
return error;
@@ -427,7 +427,7 @@ xfs_attr_remove(
*/
args.op_flags = XFS_DA_OP_OKNOENT;
- error = xfs_qm_dqattach(dp, 0);
+ error = xfs_qm_dqattach(dp);
if (error)
return error;
@@ -511,7 +511,14 @@ xfs_attr_shortform_addname(xfs_da_args_t *args)
if (args->flags & ATTR_CREATE)
return retval;
retval = xfs_attr_shortform_remove(args);
- ASSERT(retval == 0);
+ if (retval)
+ return retval;
+ /*
+ * Since we have removed the old attr, clear ATTR_REPLACE so
+ * that the leaf format add routine won't trip over the attr
+ * not being around.
+ */
+ args->flags &= ~ATTR_REPLACE;
}
if (args->namelen >= XFS_ATTR_SF_ENTSIZE_MAX ||
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 21be186..83a6d3c 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -620,7 +620,7 @@ xfs_attr_rmtval_remove(
/*
* If the "remote" value is in the cache, remove it.
*/
- bp = xfs_incore(mp->m_ddev_targp, dblkno, dblkcnt, XBF_TRYLOCK);
+ bp = xfs_buf_incore(mp->m_ddev_targp, dblkno, dblkcnt, XBF_TRYLOCK);
if (bp) {
xfs_buf_stale(bp);
xfs_buf_relse(bp);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 6a7c2f0..7b0e2b5 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -246,7 +246,7 @@ xfs_bmap_get_bp(
struct xfs_btree_cur *cur,
xfs_fsblock_t bno)
{
- struct xfs_log_item_desc *lidp;
+ struct xfs_log_item *lip;
int i;
if (!cur)
@@ -260,9 +260,9 @@ xfs_bmap_get_bp(
}
/* Chase down all the log items to see if the bp is there */
- list_for_each_entry(lidp, &cur->bc_tp->t_items, lid_trans) {
- struct xfs_buf_log_item *bip;
- bip = (struct xfs_buf_log_item *)lidp->lid_item;
+ list_for_each_entry(lip, &cur->bc_tp->t_items, li_trans) {
+ struct xfs_buf_log_item *bip = (struct xfs_buf_log_item *)lip;
+
if (bip->bli_item.li_type == XFS_LI_BUF &&
XFS_BUF_ADDR(bip->bli_buf) == bno)
return bip->bli_buf;
@@ -312,8 +312,9 @@ xfs_check_block(
xfs_warn(mp, "%s: thispa(%d) == pp(%d) %Ld",
__func__, j, i,
(unsigned long long)be64_to_cpu(*thispa));
- panic("%s: ptrs are equal in node\n",
+ xfs_err(mp, "%s: ptrs are equal in node\n",
__func__);
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
}
}
}
@@ -483,7 +484,8 @@ xfs_bmap_check_leaf_extents(
error_norelse:
xfs_warn(mp, "%s: BAD after btree leaves for %d extents",
__func__, i);
- panic("%s: CORRUPTED BTREE OR SOMETHING", __func__);
+ xfs_err(mp, "%s: CORRUPTED BTREE OR SOMETHING", __func__);
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
return;
}
@@ -542,12 +544,13 @@ xfs_bmap_validate_ret(
* The list is maintained sorted (by block number).
*/
void
-xfs_bmap_add_free(
+__xfs_bmap_add_free(
struct xfs_mount *mp,
struct xfs_defer_ops *dfops,
xfs_fsblock_t bno,
xfs_filblks_t len,
- struct xfs_owner_info *oinfo)
+ struct xfs_owner_info *oinfo,
+ bool skip_discard)
{
struct xfs_extent_free_item *new; /* new element */
#ifdef DEBUG
@@ -574,6 +577,7 @@ xfs_bmap_add_free(
new->xefi_oinfo = *oinfo;
else
xfs_rmap_skip_owner_update(&new->xefi_oinfo);
+ new->xefi_skip_discard = skip_discard;
trace_xfs_bmap_free_defer(mp, XFS_FSB_TO_AGNO(mp, bno), 0,
XFS_FSB_TO_AGBNO(mp, bno), len);
xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list);
@@ -725,12 +729,16 @@ xfs_bmap_extents_to_btree(
*logflagsp = 0;
if ((error = xfs_alloc_vextent(&args))) {
xfs_iroot_realloc(ip, -1, whichfork);
+ ASSERT(ifp->if_broot == NULL);
+ XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
return error;
}
if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
xfs_iroot_realloc(ip, -1, whichfork);
+ ASSERT(ifp->if_broot == NULL);
+ XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
return -ENOSPC;
}
@@ -1997,10 +2005,13 @@ xfs_bmap_add_extent_delay_real(
ASSERT(0);
}
- /* add reverse mapping */
- error = xfs_rmap_map_extent(mp, bma->dfops, bma->ip, whichfork, new);
- if (error)
- goto done;
+ /* add reverse mapping unless caller opted out */
+ if (!(bma->flags & XFS_BMAPI_NORMAP)) {
+ error = xfs_rmap_map_extent(mp, bma->dfops, bma->ip,
+ whichfork, new);
+ if (error)
+ goto done;
+ }
/* convert to a btree if necessary */
if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
@@ -2664,7 +2675,8 @@ xfs_bmap_add_extent_hole_real(
struct xfs_bmbt_irec *new,
xfs_fsblock_t *first,
struct xfs_defer_ops *dfops,
- int *logflagsp)
+ int *logflagsp,
+ int flags)
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
struct xfs_mount *mp = ip->i_mount;
@@ -2841,10 +2853,12 @@ xfs_bmap_add_extent_hole_real(
break;
}
- /* add reverse mapping */
- error = xfs_rmap_map_extent(mp, dfops, ip, whichfork, new);
- if (error)
- goto done;
+ /* add reverse mapping unless caller opted out */
+ if (!(flags & XFS_BMAPI_NORMAP)) {
+ error = xfs_rmap_map_extent(mp, dfops, ip, whichfork, new);
+ if (error)
+ goto done;
+ }
/* convert to a btree if necessary */
if (xfs_bmap_needs_btree(ip, whichfork)) {
@@ -4119,7 +4133,8 @@ xfs_bmapi_allocate(
else
error = xfs_bmap_add_extent_hole_real(bma->tp, bma->ip,
whichfork, &bma->icur, &bma->cur, &bma->got,
- bma->firstblock, bma->dfops, &bma->logflags);
+ bma->firstblock, bma->dfops, &bma->logflags,
+ bma->flags);
bma->logflags |= tmp_logflags;
if (error)
@@ -4505,30 +4520,37 @@ xfs_bmapi_write(
return error;
}
-static int
+int
xfs_bmapi_remap(
struct xfs_trans *tp,
struct xfs_inode *ip,
xfs_fileoff_t bno,
xfs_filblks_t len,
xfs_fsblock_t startblock,
- struct xfs_defer_ops *dfops)
+ struct xfs_defer_ops *dfops,
+ int flags)
{
struct xfs_mount *mp = ip->i_mount;
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+ struct xfs_ifork *ifp;
struct xfs_btree_cur *cur = NULL;
xfs_fsblock_t firstblock = NULLFSBLOCK;
struct xfs_bmbt_irec got;
struct xfs_iext_cursor icur;
+ int whichfork = xfs_bmapi_whichfork(flags);
int logflags = 0, error;
+ ifp = XFS_IFORK_PTR(ip, whichfork);
ASSERT(len > 0);
ASSERT(len <= (xfs_filblks_t)MAXEXTLEN);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+ ASSERT(!(flags & ~(XFS_BMAPI_ATTRFORK | XFS_BMAPI_PREALLOC |
+ XFS_BMAPI_NORMAP)));
+ ASSERT((flags & (XFS_BMAPI_ATTRFORK | XFS_BMAPI_PREALLOC)) !=
+ (XFS_BMAPI_ATTRFORK | XFS_BMAPI_PREALLOC));
if (unlikely(XFS_TEST_ERROR(
- (XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_EXTENTS &&
- XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_BTREE),
+ (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
+ XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
mp, XFS_ERRTAG_BMAPIFORMAT))) {
XFS_ERROR_REPORT("xfs_bmapi_remap", XFS_ERRLEVEL_LOW, mp);
return -EFSCORRUPTED;
@@ -4538,7 +4560,7 @@ xfs_bmapi_remap(
return -EIO;
if (!(ifp->if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
+ error = xfs_iread_extents(tp, ip, whichfork);
if (error)
return error;
}
@@ -4553,7 +4575,7 @@ xfs_bmapi_remap(
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (ifp->if_flags & XFS_IFBROOT) {
- cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK);
+ cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
cur->bc_private.b.firstblock = firstblock;
cur->bc_private.b.dfops = dfops;
cur->bc_private.b.flags = 0;
@@ -4562,18 +4584,21 @@ xfs_bmapi_remap(
got.br_startoff = bno;
got.br_startblock = startblock;
got.br_blockcount = len;
- got.br_state = XFS_EXT_NORM;
+ if (flags & XFS_BMAPI_PREALLOC)
+ got.br_state = XFS_EXT_UNWRITTEN;
+ else
+ got.br_state = XFS_EXT_NORM;
- error = xfs_bmap_add_extent_hole_real(tp, ip, XFS_DATA_FORK, &icur,
- &cur, &got, &firstblock, dfops, &logflags);
+ error = xfs_bmap_add_extent_hole_real(tp, ip, whichfork, &icur,
+ &cur, &got, &firstblock, dfops, &logflags, flags);
if (error)
goto error0;
- if (xfs_bmap_wants_extents(ip, XFS_DATA_FORK)) {
+ if (xfs_bmap_wants_extents(ip, whichfork)) {
int tmp_logflags = 0;
error = xfs_bmap_btree_to_extents(tp, ip, cur,
- &tmp_logflags, XFS_DATA_FORK);
+ &tmp_logflags, whichfork);
logflags |= tmp_logflags;
}
@@ -5100,9 +5125,12 @@ xfs_bmap_del_extent_real(
error = xfs_refcount_decrease_extent(mp, dfops, del);
if (error)
goto done;
- } else
- xfs_bmap_add_free(mp, dfops, del->br_startblock,
- del->br_blockcount, NULL);
+ } else {
+ __xfs_bmap_add_free(mp, dfops, del->br_startblock,
+ del->br_blockcount, NULL,
+ (bflags & XFS_BMAPI_NODISCARD) ||
+ del->br_state == XFS_EXT_UNWRITTEN);
+ }
}
/*
@@ -6144,7 +6172,7 @@ xfs_bmap_finish_one(
switch (type) {
case XFS_BMAP_MAP:
error = xfs_bmapi_remap(tp, ip, startoff, *blockcount,
- startblock, dfops);
+ startblock, dfops, 0);
*blockcount = 0;
break;
case XFS_BMAP_UNMAP:
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 2b766b3..2c233f9 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -68,6 +68,7 @@ struct xfs_extent_free_item
xfs_extlen_t xefi_blockcount;/* number of blocks in extent */
struct list_head xefi_list;
struct xfs_owner_info xefi_oinfo; /* extent owner */
+ bool xefi_skip_discard;
};
#define XFS_BMAP_MAX_NMAP 4
@@ -116,6 +117,12 @@ struct xfs_extent_free_item
/* Only convert unwritten extents, don't allocate new blocks */
#define XFS_BMAPI_CONVERT_ONLY 0x800
+/* Skip online discard of freed extents */
+#define XFS_BMAPI_NODISCARD 0x1000
+
+/* Do not update the rmap btree. Used for reconstructing bmbt from rmapbt. */
+#define XFS_BMAPI_NORMAP 0x2000
+
#define XFS_BMAPI_FLAGS \
{ XFS_BMAPI_ENTIRE, "ENTIRE" }, \
{ XFS_BMAPI_METADATA, "METADATA" }, \
@@ -128,7 +135,9 @@ struct xfs_extent_free_item
{ XFS_BMAPI_REMAP, "REMAP" }, \
{ XFS_BMAPI_COWFORK, "COWFORK" }, \
{ XFS_BMAPI_DELALLOC, "DELALLOC" }, \
- { XFS_BMAPI_CONVERT_ONLY, "CONVERT_ONLY" }
+ { XFS_BMAPI_CONVERT_ONLY, "CONVERT_ONLY" }, \
+ { XFS_BMAPI_NODISCARD, "NODISCARD" }, \
+ { XFS_BMAPI_NORMAP, "NORMAP" }
static inline int xfs_bmapi_aflag(int w)
@@ -192,9 +201,9 @@ void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
void xfs_trim_extent_eof(struct xfs_bmbt_irec *, struct xfs_inode *);
int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
-void xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
+void __xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
xfs_fsblock_t bno, xfs_filblks_t len,
- struct xfs_owner_info *oinfo);
+ struct xfs_owner_info *oinfo, bool skip_discard);
void xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork);
int xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);
@@ -240,6 +249,17 @@ int xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork,
struct xfs_bmbt_irec *got, struct xfs_iext_cursor *cur,
int eof);
+static inline void
+xfs_bmap_add_free(
+ struct xfs_mount *mp,
+ struct xfs_defer_ops *dfops,
+ xfs_fsblock_t bno,
+ xfs_filblks_t len,
+ struct xfs_owner_info *oinfo)
+{
+ __xfs_bmap_add_free(mp, dfops, bno, len, oinfo, false);
+}
+
enum xfs_bmap_intent_type {
XFS_BMAP_MAP = 1,
XFS_BMAP_UNMAP,
@@ -277,4 +297,8 @@ static inline int xfs_bmap_fork_to_state(int whichfork)
xfs_failaddr_t xfs_bmap_validate_extent(struct xfs_inode *ip, int whichfork,
struct xfs_bmbt_irec *irec);
+int xfs_bmapi_remap(struct xfs_trans *tp, struct xfs_inode *ip,
+ xfs_fileoff_t bno, xfs_filblks_t len, xfs_fsblock_t startblock,
+ struct xfs_defer_ops *dfops, int flags);
+
#endif /* __XFS_BMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index d89d06b..ac9d4ae 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -660,3 +660,12 @@ xfs_bmbt_change_owner(
xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
return error;
}
+
+/* Calculate the bmap btree size for some records. */
+unsigned long long
+xfs_bmbt_calc_size(
+ struct xfs_mount *mp,
+ unsigned long long len)
+{
+ return xfs_btree_calc_size(mp->m_bmap_dmnr, len);
+}
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.h b/fs/xfs/libxfs/xfs_bmap_btree.h
index e450574..fb3cd2d 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.h
+++ b/fs/xfs/libxfs/xfs_bmap_btree.h
@@ -118,4 +118,7 @@ extern int xfs_bmbt_change_owner(struct xfs_trans *tp, struct xfs_inode *ip,
extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *,
struct xfs_trans *, struct xfs_inode *, int);
+extern unsigned long long xfs_bmbt_calc_size(struct xfs_mount *mp,
+ unsigned long long len);
+
#endif /* __XFS_BMAP_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index ac7d664..c825c81 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -4836,14 +4836,14 @@ xfs_btree_query_all(
* Calculate the number of blocks needed to store a given number of records
* in a short-format (per-AG metadata) btree.
*/
-xfs_extlen_t
+unsigned long long
xfs_btree_calc_size(
uint *limits,
unsigned long long len)
{
int level;
int maxrecs;
- xfs_extlen_t rval;
+ unsigned long long rval;
maxrecs = limits[0];
for (level = 0, rval = 0; len > 1; level++) {
@@ -4919,3 +4919,24 @@ xfs_btree_has_record(
*exists = false;
return error;
}
+
+/* Are there more records in this btree? */
+bool
+xfs_btree_has_more_records(
+ struct xfs_btree_cur *cur)
+{
+ struct xfs_btree_block *block;
+ struct xfs_buf *bp;
+
+ block = xfs_btree_get_block(cur, 0, &bp);
+
+ /* There are still records in this block. */
+ if (cur->bc_ptrs[0] < xfs_btree_get_numrecs(block))
+ return true;
+
+ /* There are more record blocks. */
+ if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+ return block->bb_u.l.bb_rightsib != cpu_to_be64(NULLFSBLOCK);
+ else
+ return block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK);
+}
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 9227159..d7911efe 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -482,7 +482,7 @@ xfs_failaddr_t xfs_btree_lblock_verify(struct xfs_buf *bp,
unsigned int max_recs);
uint xfs_btree_compute_maxlevels(uint *limits, unsigned long len);
-xfs_extlen_t xfs_btree_calc_size(uint *limits, unsigned long long len);
+unsigned long long xfs_btree_calc_size(uint *limits, unsigned long long len);
/* return codes */
#define XFS_BTREE_QUERY_RANGE_CONTINUE 0 /* keep iterating */
@@ -528,5 +528,6 @@ union xfs_btree_key *xfs_btree_high_key_from_key(struct xfs_btree_cur *cur,
union xfs_btree_key *key);
int xfs_btree_has_record(struct xfs_btree_cur *cur, union xfs_btree_irec *low,
union xfs_btree_irec *high, bool *exists);
+bool xfs_btree_has_more_records(struct xfs_btree_cur *cur);
#endif /* __XFS_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 087fea0..3daf175 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -220,7 +220,7 @@ xfs_defer_trans_abort(
{
struct xfs_defer_pending *dfp;
- trace_xfs_defer_trans_abort(tp->t_mountp, dop);
+ trace_xfs_defer_trans_abort(tp->t_mountp, dop, _RET_IP_);
/* Abort intent items that don't have a done item. */
list_for_each_entry(dfp, &dop->dop_pending, dfp_list) {
@@ -253,7 +253,7 @@ xfs_defer_trans_roll(
for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++)
xfs_trans_dirty_buf(*tp, dop->dop_bufs[i]);
- trace_xfs_defer_trans_roll((*tp)->t_mountp, dop);
+ trace_xfs_defer_trans_roll((*tp)->t_mountp, dop, _RET_IP_);
/* Roll the transaction. */
error = xfs_trans_roll(tp);
@@ -352,10 +352,21 @@ xfs_defer_finish(
void *state;
int error = 0;
void (*cleanup_fn)(struct xfs_trans *, void *, int);
+ struct xfs_defer_ops *orig_dop;
ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
- trace_xfs_defer_finish((*tp)->t_mountp, dop);
+ trace_xfs_defer_finish((*tp)->t_mountp, dop, _RET_IP_);
+
+ /*
+ * Attach dfops to the transaction during deferred ops processing. This
+ * explicitly causes calls into the allocator to defer AGFL block frees.
+ * Note that this code can go away once all dfops users attach to the
+ * associated tp.
+ */
+ ASSERT(!(*tp)->t_agfl_dfops || ((*tp)->t_agfl_dfops == dop));
+ orig_dop = (*tp)->t_agfl_dfops;
+ (*tp)->t_agfl_dfops = dop;
/* Until we run out of pending work to finish... */
while (xfs_defer_has_unfinished_work(dop)) {
@@ -428,10 +439,11 @@ xfs_defer_finish(
}
out:
+ (*tp)->t_agfl_dfops = orig_dop;
if (error)
trace_xfs_defer_finish_error((*tp)->t_mountp, dop, error);
else
- trace_xfs_defer_finish_done((*tp)->t_mountp, dop);
+ trace_xfs_defer_finish_done((*tp)->t_mountp, dop, _RET_IP_);
return error;
}
@@ -447,7 +459,7 @@ xfs_defer_cancel(
struct list_head *pwi;
struct list_head *n;
- trace_xfs_defer_cancel(NULL, dop);
+ trace_xfs_defer_cancel(NULL, dop, _RET_IP_);
/*
* Free the pending items. Caller should already have arranged
@@ -532,5 +544,5 @@ xfs_defer_init(
*fbp = NULLFSBLOCK;
INIT_LIST_HEAD(&dop->dop_intake);
INIT_LIST_HEAD(&dop->dop_pending);
- trace_xfs_defer_init(NULL, dop);
+ trace_xfs_defer_init(NULL, dop, _RET_IP_);
}
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 045beac..e70725b 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -55,6 +55,7 @@ enum xfs_defer_ops_type {
XFS_DEFER_OPS_TYPE_REFCOUNT,
XFS_DEFER_OPS_TYPE_RMAP,
XFS_DEFER_OPS_TYPE_FREE,
+ XFS_DEFER_OPS_TYPE_AGFL_FREE,
XFS_DEFER_OPS_TYPE_MAX,
};
diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c
index 8b7a6c3..cce520b 100644
--- a/fs/xfs/libxfs/xfs_dquot_buf.c
+++ b/fs/xfs/libxfs/xfs_dquot_buf.c
@@ -41,14 +41,18 @@ xfs_calc_dquots_per_chunk(
/*
* Do some primitive error checking on ondisk dquot data structures.
+ *
+ * The xfs_dqblk structure /contains/ the xfs_disk_dquot structure;
+ * we verify them separately because at some points we have only the
+ * smaller xfs_disk_dquot structure available.
*/
+
xfs_failaddr_t
xfs_dquot_verify(
struct xfs_mount *mp,
xfs_disk_dquot_t *ddq,
xfs_dqid_t id,
- uint type, /* used only when IO_dorepair is true */
- uint flags)
+ uint type) /* used only during quotacheck */
{
/*
* We can encounter an uninitialized dquot buffer for 2 reasons:
@@ -70,6 +74,8 @@ xfs_dquot_verify(
if (ddq->d_version != XFS_DQUOT_VERSION)
return __this_address;
+ if (type && ddq->d_flags != type)
+ return __this_address;
if (ddq->d_flags != XFS_DQ_USER &&
ddq->d_flags != XFS_DQ_PROJ &&
ddq->d_flags != XFS_DQ_GROUP)
@@ -99,33 +105,44 @@ xfs_dquot_verify(
return NULL;
}
+xfs_failaddr_t
+xfs_dqblk_verify(
+ struct xfs_mount *mp,
+ struct xfs_dqblk *dqb,
+ xfs_dqid_t id,
+ uint type) /* used only during quotacheck */
+{
+ if (xfs_sb_version_hascrc(&mp->m_sb) &&
+ !uuid_equal(&dqb->dd_uuid, &mp->m_sb.sb_meta_uuid))
+ return __this_address;
+
+ return xfs_dquot_verify(mp, &dqb->dd_diskdq, id, type);
+}
+
/*
* Do some primitive error checking on ondisk dquot data structures.
*/
int
-xfs_dquot_repair(
+xfs_dqblk_repair(
struct xfs_mount *mp,
- struct xfs_disk_dquot *ddq,
+ struct xfs_dqblk *dqb,
xfs_dqid_t id,
uint type)
{
- struct xfs_dqblk *d = (struct xfs_dqblk *)ddq;
-
-
/*
* Typically, a repair is only requested by quotacheck.
*/
ASSERT(id != -1);
- memset(d, 0, sizeof(xfs_dqblk_t));
+ memset(dqb, 0, sizeof(xfs_dqblk_t));
- d->dd_diskdq.d_magic = cpu_to_be16(XFS_DQUOT_MAGIC);
- d->dd_diskdq.d_version = XFS_DQUOT_VERSION;
- d->dd_diskdq.d_flags = type;
- d->dd_diskdq.d_id = cpu_to_be32(id);
+ dqb->dd_diskdq.d_magic = cpu_to_be16(XFS_DQUOT_MAGIC);
+ dqb->dd_diskdq.d_version = XFS_DQUOT_VERSION;
+ dqb->dd_diskdq.d_flags = type;
+ dqb->dd_diskdq.d_id = cpu_to_be32(id);
if (xfs_sb_version_hascrc(&mp->m_sb)) {
- uuid_copy(&d->dd_uuid, &mp->m_sb.sb_meta_uuid);
- xfs_update_cksum((char *)d, sizeof(struct xfs_dqblk),
+ uuid_copy(&dqb->dd_uuid, &mp->m_sb.sb_meta_uuid);
+ xfs_update_cksum((char *)dqb, sizeof(struct xfs_dqblk),
XFS_DQUOT_CRC_OFF);
}
@@ -135,7 +152,8 @@ xfs_dquot_repair(
STATIC bool
xfs_dquot_buf_verify_crc(
struct xfs_mount *mp,
- struct xfs_buf *bp)
+ struct xfs_buf *bp,
+ bool readahead)
{
struct xfs_dqblk *d = (struct xfs_dqblk *)bp->b_addr;
int ndquots;
@@ -156,10 +174,12 @@ xfs_dquot_buf_verify_crc(
for (i = 0; i < ndquots; i++, d++) {
if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk),
- XFS_DQUOT_CRC_OFF))
+ XFS_DQUOT_CRC_OFF)) {
+ if (!readahead)
+ xfs_buf_verifier_error(bp, -EFSBADCRC, __func__,
+ d, sizeof(*d), __this_address);
return false;
- if (!uuid_equal(&d->dd_uuid, &mp->m_sb.sb_meta_uuid))
- return false;
+ }
}
return true;
}
@@ -167,9 +187,10 @@ xfs_dquot_buf_verify_crc(
STATIC xfs_failaddr_t
xfs_dquot_buf_verify(
struct xfs_mount *mp,
- struct xfs_buf *bp)
+ struct xfs_buf *bp,
+ bool readahead)
{
- struct xfs_dqblk *d = (struct xfs_dqblk *)bp->b_addr;
+ struct xfs_dqblk *dqb = bp->b_addr;
xfs_failaddr_t fa;
xfs_dqid_t id = 0;
int ndquots;
@@ -195,14 +216,19 @@ xfs_dquot_buf_verify(
for (i = 0; i < ndquots; i++) {
struct xfs_disk_dquot *ddq;
- ddq = &d[i].dd_diskdq;
+ ddq = &dqb[i].dd_diskdq;
if (i == 0)
id = be32_to_cpu(ddq->d_id);
- fa = xfs_dquot_verify(mp, ddq, id + i, 0, 0);
- if (fa)
+ fa = xfs_dqblk_verify(mp, &dqb[i], id + i, 0);
+ if (fa) {
+ if (!readahead)
+ xfs_buf_verifier_error(bp, -EFSCORRUPTED,
+ __func__, &dqb[i],
+ sizeof(struct xfs_dqblk), fa);
return fa;
+ }
}
return NULL;
@@ -214,7 +240,7 @@ xfs_dquot_buf_verify_struct(
{
struct xfs_mount *mp = bp->b_target->bt_mount;
- return xfs_dquot_buf_verify(mp, bp);
+ return xfs_dquot_buf_verify(mp, bp, false);
}
static void
@@ -222,15 +248,10 @@ xfs_dquot_buf_read_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
- xfs_failaddr_t fa;
- if (!xfs_dquot_buf_verify_crc(mp, bp))
- xfs_verifier_error(bp, -EFSBADCRC, __this_address);
- else {
- fa = xfs_dquot_buf_verify(mp, bp);
- if (fa)
- xfs_verifier_error(bp, -EFSCORRUPTED, __this_address);
- }
+ if (!xfs_dquot_buf_verify_crc(mp, bp, false))
+ return;
+ xfs_dquot_buf_verify(mp, bp, false);
}
/*
@@ -245,8 +266,8 @@ xfs_dquot_buf_readahead_verify(
{
struct xfs_mount *mp = bp->b_target->bt_mount;
- if (!xfs_dquot_buf_verify_crc(mp, bp) ||
- xfs_dquot_buf_verify(mp, bp) != NULL) {
+ if (!xfs_dquot_buf_verify_crc(mp, bp, true) ||
+ xfs_dquot_buf_verify(mp, bp, true) != NULL) {
xfs_buf_ioerror(bp, -EIO);
bp->b_flags &= ~XBF_DONE;
}
@@ -262,11 +283,8 @@ xfs_dquot_buf_write_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
- xfs_failaddr_t fa;
- fa = xfs_dquot_buf_verify(mp, bp);
- if (fa)
- xfs_verifier_error(bp, -EFSCORRUPTED, __this_address);
+ xfs_dquot_buf_verify(mp, bp, false);
}
const struct xfs_buf_ops xfs_dquot_buf_ops = {
diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h
index bc1789d..d47b916 100644
--- a/fs/xfs/libxfs/xfs_errortag.h
+++ b/fs/xfs/libxfs/xfs_errortag.h
@@ -65,7 +65,8 @@
#define XFS_ERRTAG_LOG_BAD_CRC 29
#define XFS_ERRTAG_LOG_ITEM_PIN 30
#define XFS_ERRTAG_BUF_LRU_REF 31
-#define XFS_ERRTAG_MAX 32
+#define XFS_ERRTAG_FORCE_SCRUB_REPAIR 32
+#define XFS_ERRTAG_MAX 33
/*
* Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -102,5 +103,6 @@
#define XFS_RANDOM_LOG_BAD_CRC 1
#define XFS_RANDOM_LOG_ITEM_PIN 1
#define XFS_RANDOM_BUF_LRU_REF 2
+#define XFS_RANDOM_FORCE_SCRUB_REPAIR 1
#endif /* __XFS_ERRORTAG_H_ */
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 42956d8..c1cb29a 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -98,6 +98,9 @@ struct xfs_ifork;
XFS_SB_VERSION2_PROJID32BIT | \
XFS_SB_VERSION2_FTYPE)
+/* Maximum size of the xfs filesystem label, no terminating NULL */
+#define XFSLABEL_MAX 12
+
/*
* Superblock - in core version. Must match the ondisk version below.
* Must be padded to 64 bit alignment.
@@ -122,7 +125,7 @@ typedef struct xfs_sb {
uint16_t sb_sectsize; /* volume sector size, bytes */
uint16_t sb_inodesize; /* inode size, bytes */
uint16_t sb_inopblock; /* inodes per block */
- char sb_fname[12]; /* file system name */
+ char sb_fname[XFSLABEL_MAX]; /* file system name */
uint8_t sb_blocklog; /* log2 of sb_blocksize */
uint8_t sb_sectlog; /* log2 of sb_sectsize */
uint8_t sb_inodelog; /* log2 of sb_inodesize */
@@ -213,7 +216,7 @@ typedef struct xfs_dsb {
__be16 sb_sectsize; /* volume sector size, bytes */
__be16 sb_inodesize; /* inode size, bytes */
__be16 sb_inopblock; /* inodes per block */
- char sb_fname[12]; /* file system name */
+ char sb_fname[XFSLABEL_MAX]; /* file system name */
__u8 sb_blocklog; /* log2 of sb_blocksize */
__u8 sb_sectlog; /* log2 of sb_sectsize */
__u8 sb_inodelog; /* log2 of sb_inodesize */
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index faf1a4e..dddc75e 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -542,13 +542,20 @@ struct xfs_scrub_metadata {
/* o: Metadata object looked funny but isn't corrupt. */
#define XFS_SCRUB_OFLAG_WARNING (1 << 6)
+/*
+ * o: IFLAG_REPAIR was set but metadata object did not need fixing or
+ * optimization and has therefore not been altered.
+ */
+#define XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED (1 << 7)
+
#define XFS_SCRUB_FLAGS_IN (XFS_SCRUB_IFLAG_REPAIR)
#define XFS_SCRUB_FLAGS_OUT (XFS_SCRUB_OFLAG_CORRUPT | \
XFS_SCRUB_OFLAG_PREEN | \
XFS_SCRUB_OFLAG_XFAIL | \
XFS_SCRUB_OFLAG_XCORRUPT | \
XFS_SCRUB_OFLAG_INCOMPLETE | \
- XFS_SCRUB_OFLAG_WARNING)
+ XFS_SCRUB_OFLAG_WARNING | \
+ XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED)
#define XFS_SCRUB_FLAGS_ALL (XFS_SCRUB_FLAGS_IN | XFS_SCRUB_FLAGS_OUT)
/*
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index de627fa..4ca4ff7 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -148,7 +148,7 @@ xfs_inobt_get_rec(
/*
* Insert a single inobt record. Cursor must already point to desired location.
*/
-STATIC int
+int
xfs_inobt_insert_rec(
struct xfs_btree_cur *cur,
uint16_t holemask,
diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h
index c5402bb..77fffce 100644
--- a/fs/xfs/libxfs/xfs_ialloc.h
+++ b/fs/xfs/libxfs/xfs_ialloc.h
@@ -176,6 +176,9 @@ int xfs_ialloc_has_inode_record(struct xfs_btree_cur *cur, xfs_agino_t low,
xfs_agino_t high, bool *exists);
int xfs_ialloc_count_inodes(struct xfs_btree_cur *cur, xfs_agino_t *count,
xfs_agino_t *freecount);
+int xfs_inobt_insert_rec(struct xfs_btree_cur *cur, uint16_t holemask,
+ uint8_t count, int32_t freecount, xfs_inofree_t free,
+ int *stat);
int xfs_ialloc_cluster_alignment(struct xfs_mount *mp);
void xfs_ialloc_agino_range(struct xfs_mount *mp, xfs_agnumber_t agno,
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 367e9a0..b04c555 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -296,7 +296,7 @@ xfs_inobt_verify(
case cpu_to_be32(XFS_FIBT_MAGIC):
break;
default:
- return NULL;
+ return __this_address;
}
/* level verification */
@@ -608,3 +608,12 @@ xfs_finobt_calc_reserves(
*used += tree_len;
return 0;
}
+
+/* Calculate the inobt btree size for some records. */
+xfs_extlen_t
+xfs_iallocbt_calc_size(
+ struct xfs_mount *mp,
+ unsigned long long len)
+{
+ return xfs_btree_calc_size(mp->m_inobt_mnr, len);
+}
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.h b/fs/xfs/libxfs/xfs_ialloc_btree.h
index aa81e2e..4acdd54 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.h
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.h
@@ -74,5 +74,7 @@ int xfs_inobt_rec_check_count(struct xfs_mount *,
int xfs_finobt_calc_reserves(struct xfs_mount *mp, xfs_agnumber_t agno,
xfs_extlen_t *ask, xfs_extlen_t *used);
+extern xfs_extlen_t xfs_iallocbt_calc_size(struct xfs_mount *mp,
+ unsigned long long len);
#endif /* __XFS_IALLOC_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index ef68b1d..1201107 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -466,6 +466,8 @@ xfs_dinode_verify(
return __this_address;
if (di_size > XFS_DFORK_DSIZE(dip, mp))
return __this_address;
+ if (dip->di_nextents)
+ return __this_address;
/* fall through */
case XFS_DINODE_FMT_EXTENTS:
case XFS_DINODE_FMT_BTREE:
@@ -484,12 +486,31 @@ xfs_dinode_verify(
if (XFS_DFORK_Q(dip)) {
switch (dip->di_aformat) {
case XFS_DINODE_FMT_LOCAL:
+ if (dip->di_anextents)
+ return __this_address;
+ /* fall through */
case XFS_DINODE_FMT_EXTENTS:
case XFS_DINODE_FMT_BTREE:
break;
default:
return __this_address;
}
+ } else {
+ /*
+ * If there is no fork offset, this may be a freshly-made inode
+ * in a new disk cluster, in which case di_aformat is zeroed.
+ * Otherwise, such an inode must be in EXTENTS format; this goes
+ * for freed inodes as well.
+ */
+ switch (dip->di_aformat) {
+ case 0:
+ case XFS_DINODE_FMT_EXTENTS:
+ break;
+ default:
+ return __this_address;
+ }
+ if (dip->di_anextents)
+ return __this_address;
}
/* only version 3 or greater inodes are extensively verified here */
diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h
index bb1b13a..d4af280 100644
--- a/fs/xfs/libxfs/xfs_quota_defs.h
+++ b/fs/xfs/libxfs/xfs_quota_defs.h
@@ -107,14 +107,12 @@ typedef uint16_t xfs_qwarncnt_t;
* to a single function. None of these XFS_QMOPT_* flags are meant to have
* persistent values (ie. their values can and will change between versions)
*/
-#define XFS_QMOPT_DQALLOC 0x0000002 /* alloc dquot ondisk if needed */
#define XFS_QMOPT_UQUOTA 0x0000004 /* user dquot requested */
#define XFS_QMOPT_PQUOTA 0x0000008 /* project dquot requested */
#define XFS_QMOPT_FORCE_RES 0x0000010 /* ignore quota limits */
#define XFS_QMOPT_SBVERSION 0x0000040 /* change superblock version num */
#define XFS_QMOPT_GQUOTA 0x0002000 /* group dquot requested */
#define XFS_QMOPT_ENOSPC 0x0004000 /* enospc instead of edquot (prj) */
-#define XFS_QMOPT_DQNEXT 0x0008000 /* return next dquot >= this ID */
/*
* flags to xfs_trans_mod_dquot to indicate which field needs to be
@@ -152,10 +150,11 @@ typedef uint16_t xfs_qwarncnt_t;
#define XFS_QMOPT_RESBLK_MASK (XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_RES_RTBLKS)
extern xfs_failaddr_t xfs_dquot_verify(struct xfs_mount *mp,
- struct xfs_disk_dquot *ddq, xfs_dqid_t id, uint type,
- uint flags);
+ struct xfs_disk_dquot *ddq, xfs_dqid_t id, uint type);
+extern xfs_failaddr_t xfs_dqblk_verify(struct xfs_mount *mp,
+ struct xfs_dqblk *dqb, xfs_dqid_t id, uint type);
extern int xfs_calc_dquots_per_chunk(unsigned int nbblks);
-extern int xfs_dquot_repair(struct xfs_mount *mp, struct xfs_disk_dquot *ddq,
+extern int xfs_dqblk_repair(struct xfs_mount *mp, struct xfs_dqblk *dqb,
xfs_dqid_t id, uint type);
#endif /* __XFS_QUOTA_H__ */
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 560e284..418d532 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -88,8 +88,25 @@ xfs_refcount_lookup_ge(
return xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat);
}
+/*
+ * Look up the first record equal to [bno, len] in the btree
+ * given by cur.
+ */
+int
+xfs_refcount_lookup_eq(
+ struct xfs_btree_cur *cur,
+ xfs_agblock_t bno,
+ int *stat)
+{
+ trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_private.a.agno, bno,
+ XFS_LOOKUP_LE);
+ cur->bc_rec.rc.rc_startblock = bno;
+ cur->bc_rec.rc.rc_blockcount = 0;
+ return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat);
+}
+
/* Convert on-disk record to in-core format. */
-static inline void
+void
xfs_refcount_btrec_to_irec(
union xfs_btree_rec *rec,
struct xfs_refcount_irec *irec)
@@ -149,7 +166,7 @@ xfs_refcount_update(
* by [bno, len, refcount].
* This either works (return 0) or gets an EFSCORRUPTED error.
*/
-STATIC int
+int
xfs_refcount_insert(
struct xfs_btree_cur *cur,
struct xfs_refcount_irec *irec,
@@ -162,7 +179,10 @@ xfs_refcount_insert(
cur->bc_rec.rc.rc_blockcount = irec->rc_blockcount;
cur->bc_rec.rc.rc_refcount = irec->rc_refcount;
error = xfs_btree_insert(cur, i);
+ if (error)
+ goto out_error;
XFS_WANT_CORRUPTED_GOTO(cur->bc_mp, *i == 1, out_error);
+
out_error:
if (error)
trace_xfs_refcount_insert_error(cur->bc_mp,
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index 2a731ac..a92ad90 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -24,6 +24,8 @@ extern int xfs_refcount_lookup_le(struct xfs_btree_cur *cur,
xfs_agblock_t bno, int *stat);
extern int xfs_refcount_lookup_ge(struct xfs_btree_cur *cur,
xfs_agblock_t bno, int *stat);
+extern int xfs_refcount_lookup_eq(struct xfs_btree_cur *cur,
+ xfs_agblock_t bno, int *stat);
extern int xfs_refcount_get_rec(struct xfs_btree_cur *cur,
struct xfs_refcount_irec *irec, int *stat);
@@ -85,5 +87,10 @@ static inline xfs_fileoff_t xfs_refcount_max_unmap(int log_res)
extern int xfs_refcount_has_record(struct xfs_btree_cur *cur,
xfs_agblock_t bno, xfs_extlen_t len, bool *exists);
+union xfs_btree_rec;
+extern void xfs_refcount_btrec_to_irec(union xfs_btree_rec *rec,
+ struct xfs_refcount_irec *irec);
+extern int xfs_refcount_insert(struct xfs_btree_cur *cur,
+ struct xfs_refcount_irec *irec, int *stat);
#endif /* __XFS_REFCOUNT_H__ */
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index fba8d27..c0644f1 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -1374,6 +1374,8 @@ xfs_rmap_convert_shared(
*/
error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, flags,
&PREV, &i);
+ if (error)
+ goto done;
XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
ASSERT(PREV.rm_offset <= offset);
@@ -2030,6 +2032,34 @@ xfs_rmap_map_shared(
return error;
}
+/* Insert a raw rmap into the rmapbt. */
+int
+xfs_rmap_map_raw(
+ struct xfs_btree_cur *cur,
+ struct xfs_rmap_irec *rmap)
+{
+ struct xfs_owner_info oinfo;
+
+ oinfo.oi_owner = rmap->rm_owner;
+ oinfo.oi_offset = rmap->rm_offset;
+ oinfo.oi_flags = 0;
+ if (rmap->rm_flags & XFS_RMAP_ATTR_FORK)
+ oinfo.oi_flags |= XFS_OWNER_INFO_ATTR_FORK;
+ if (rmap->rm_flags & XFS_RMAP_BMBT_BLOCK)
+ oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK;
+
+ if (rmap->rm_flags || XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner))
+ return xfs_rmap_map(cur, rmap->rm_startblock,
+ rmap->rm_blockcount,
+ rmap->rm_flags & XFS_RMAP_UNWRITTEN,
+ &oinfo);
+
+ return xfs_rmap_map_shared(cur, rmap->rm_startblock,
+ rmap->rm_blockcount,
+ rmap->rm_flags & XFS_RMAP_UNWRITTEN,
+ &oinfo);
+}
+
struct xfs_rmap_query_range_info {
xfs_rmap_query_range_fn fn;
void *priv;
@@ -2453,3 +2483,56 @@ xfs_rmap_record_exists(
irec.rm_startblock + irec.rm_blockcount >= bno + len);
return 0;
}
+
+struct xfs_rmap_key_state {
+ uint64_t owner;
+ uint64_t offset;
+ unsigned int flags;
+ bool has_rmap;
+};
+
+/* For each rmap given, figure out if it doesn't match the key we want. */
+STATIC int
+xfs_rmap_has_other_keys_helper(
+ struct xfs_btree_cur *cur,
+ struct xfs_rmap_irec *rec,
+ void *priv)
+{
+ struct xfs_rmap_key_state *rks = priv;
+
+ if (rks->owner == rec->rm_owner && rks->offset == rec->rm_offset &&
+ ((rks->flags & rec->rm_flags) & XFS_RMAP_KEY_FLAGS) == rks->flags)
+ return 0;
+ rks->has_rmap = true;
+ return XFS_BTREE_QUERY_RANGE_ABORT;
+}
+
+/*
+ * Given an extent and some owner info, can we find records overlapping
+ * the extent whose owner info does not match the given owner?
+ */
+int
+xfs_rmap_has_other_keys(
+ struct xfs_btree_cur *cur,
+ xfs_agblock_t bno,
+ xfs_extlen_t len,
+ struct xfs_owner_info *oinfo,
+ bool *has_rmap)
+{
+ struct xfs_rmap_irec low = {0};
+ struct xfs_rmap_irec high;
+ struct xfs_rmap_key_state rks;
+ int error;
+
+ xfs_owner_info_unpack(oinfo, &rks.owner, &rks.offset, &rks.flags);
+ rks.has_rmap = false;
+
+ low.rm_startblock = bno;
+ memset(&high, 0xFF, sizeof(high));
+ high.rm_startblock = bno + len - 1;
+
+ error = xfs_rmap_query_range(cur, &low, &high,
+ xfs_rmap_has_other_keys_helper, &rks);
+ *has_rmap = rks.has_rmap;
+ return error;
+}
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 380e53b..43e506f 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -238,5 +238,9 @@ int xfs_rmap_has_record(struct xfs_btree_cur *cur, xfs_agblock_t bno,
int xfs_rmap_record_exists(struct xfs_btree_cur *cur, xfs_agblock_t bno,
xfs_extlen_t len, struct xfs_owner_info *oinfo,
bool *has_rmap);
+int xfs_rmap_has_other_keys(struct xfs_btree_cur *cur, xfs_agblock_t bno,
+ xfs_extlen_t len, struct xfs_owner_info *oinfo,
+ bool *has_rmap);
+int xfs_rmap_map_raw(struct xfs_btree_cur *cur, struct xfs_rmap_irec *rmap);
#endif /* __XFS_RMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 106be2d..369eeb7 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -90,6 +90,9 @@ xfs_rtbuf_get(
if (error)
return error;
+ if (nmap == 0 || !xfs_bmap_is_real_extent(&map))
+ return -EFSCORRUPTED;
+
ASSERT(map.br_startblock != NULLFSBLOCK);
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp, map.br_startblock),
@@ -1033,14 +1036,17 @@ xfs_rtalloc_query_range(
int is_free;
int error = 0;
- if (low_rec->ar_startblock > high_rec->ar_startblock)
+ if (low_rec->ar_startext > high_rec->ar_startext)
return -EINVAL;
- else if (low_rec->ar_startblock == high_rec->ar_startblock)
+ if (low_rec->ar_startext >= mp->m_sb.sb_rextents ||
+ low_rec->ar_startext == high_rec->ar_startext)
return 0;
+ if (high_rec->ar_startext >= mp->m_sb.sb_rextents)
+ high_rec->ar_startext = mp->m_sb.sb_rextents - 1;
/* Iterate the bitmap, looking for discrepancies. */
- rtstart = low_rec->ar_startblock;
- rem = high_rec->ar_startblock - rtstart;
+ rtstart = low_rec->ar_startext;
+ rem = high_rec->ar_startext - rtstart;
while (rem) {
/* Is the first block free? */
error = xfs_rtcheck_range(mp, tp, rtstart, 1, 1, &rtend,
@@ -1050,13 +1056,13 @@ xfs_rtalloc_query_range(
/* How long does the extent go for? */
error = xfs_rtfind_forw(mp, tp, rtstart,
- high_rec->ar_startblock - 1, &rtend);
+ high_rec->ar_startext - 1, &rtend);
if (error)
break;
if (is_free) {
- rec.ar_startblock = rtstart;
- rec.ar_blockcount = rtend - rtstart + 1;
+ rec.ar_startext = rtstart;
+ rec.ar_extcount = rtend - rtstart + 1;
error = fn(tp, &rec, priv);
if (error)
@@ -1079,9 +1085,9 @@ xfs_rtalloc_query_all(
{
struct xfs_rtalloc_rec keys[2];
- keys[0].ar_startblock = 0;
- keys[1].ar_startblock = tp->t_mountp->m_sb.sb_rblocks;
- keys[0].ar_blockcount = keys[1].ar_blockcount = 0;
+ keys[0].ar_startext = 0;
+ keys[1].ar_startext = tp->t_mountp->m_sb.sb_rextents - 1;
+ keys[0].ar_extcount = keys[1].ar_extcount = 0;
return xfs_rtalloc_query_range(tp, &keys[0], &keys[1], fn, priv);
}
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index d9b94bd..d485e14 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -888,6 +888,109 @@ xfs_sync_sb(
return xfs_trans_commit(tp);
}
+/*
+ * Update all the secondary superblocks to match the new state of the primary.
+ * Because we are completely overwriting all the existing fields in the
+ * secondary superblock buffers, there is no need to read them in from disk.
+ * Just get a new buffer, stamp it and write it.
+ *
+ * The sb buffers need to be cached here so that we serialise against other
+ * operations that access the secondary superblocks, but we don't want to keep
+ * them in memory once it is written so we mark it as a one-shot buffer.
+ */
+int
+xfs_update_secondary_sbs(
+ struct xfs_mount *mp)
+{
+ xfs_agnumber_t agno;
+ int saved_error = 0;
+ int error = 0;
+ LIST_HEAD (buffer_list);
+
+ /* update secondary superblocks. */
+ for (agno = 1; agno < mp->m_sb.sb_agcount; agno++) {
+ struct xfs_buf *bp;
+
+ bp = xfs_buf_get(mp->m_ddev_targp,
+ XFS_AG_DADDR(mp, agno, XFS_SB_DADDR),
+ XFS_FSS_TO_BB(mp, 1), 0);
+ /*
+ * If we get an error reading or writing alternate superblocks,
+ * continue. xfs_repair chooses the "best" superblock based
+ * on most matches; if we break early, we'll leave more
+ * superblocks un-updated than updated, and xfs_repair may
+ * pick them over the properly-updated primary.
+ */
+ if (!bp) {
+ xfs_warn(mp,
+ "error allocating secondary superblock for ag %d",
+ agno);
+ if (!saved_error)
+ saved_error = -ENOMEM;
+ continue;
+ }
+
+ bp->b_ops = &xfs_sb_buf_ops;
+ xfs_buf_oneshot(bp);
+ xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
+ xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb);
+ xfs_buf_delwri_queue(bp, &buffer_list);
+ xfs_buf_relse(bp);
+
+ /* don't hold too many buffers at once */
+ if (agno % 16)
+ continue;
+
+ error = xfs_buf_delwri_submit(&buffer_list);
+ if (error) {
+ xfs_warn(mp,
+ "write error %d updating a secondary superblock near ag %d",
+ error, agno);
+ if (!saved_error)
+ saved_error = error;
+ continue;
+ }
+ }
+ error = xfs_buf_delwri_submit(&buffer_list);
+ if (error) {
+ xfs_warn(mp,
+ "write error %d updating a secondary superblock near ag %d",
+ error, agno);
+ }
+
+ return saved_error ? saved_error : error;
+}
+
+/*
+ * Same behavior as xfs_sync_sb, except that it is always synchronous and it
+ * also writes the superblock buffer to disk sector 0 immediately.
+ */
+int
+xfs_sync_sb_buf(
+ struct xfs_mount *mp)
+{
+ struct xfs_trans *tp;
+ int error;
+
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0, 0, &tp);
+ if (error)
+ return error;
+
+ xfs_log_sb(tp);
+ xfs_trans_bhold(tp, mp->m_sb_bp);
+ xfs_trans_set_sync(tp);
+ error = xfs_trans_commit(tp);
+ if (error)
+ goto out;
+ /*
+ * write out the sb buffer to get the changes to disk
+ */
+ error = xfs_bwrite(mp->m_sb_bp);
+out:
+ xfs_buf_relse(mp->m_sb_bp);
+ return error;
+}
+
int
xfs_fs_geometry(
struct xfs_sb *sbp,
@@ -972,3 +1075,47 @@ xfs_fs_geometry(
return 0;
}
+
+/* Read a secondary superblock. */
+int
+xfs_sb_read_secondary(
+ struct xfs_mount *mp,
+ struct xfs_trans *tp,
+ xfs_agnumber_t agno,
+ struct xfs_buf **bpp)
+{
+ struct xfs_buf *bp;
+ int error;
+
+ ASSERT(agno != 0 && agno != NULLAGNUMBER);
+ error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
+ XFS_AG_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
+ XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_sb_buf_ops);
+ if (error)
+ return error;
+ xfs_buf_set_ref(bp, XFS_SSB_REF);
+ *bpp = bp;
+ return 0;
+}
+
+/* Get an uninitialised secondary superblock buffer. */
+int
+xfs_sb_get_secondary(
+ struct xfs_mount *mp,
+ struct xfs_trans *tp,
+ xfs_agnumber_t agno,
+ struct xfs_buf **bpp)
+{
+ struct xfs_buf *bp;
+
+ ASSERT(agno != 0 && agno != NULLAGNUMBER);
+ bp = xfs_trans_get_buf(tp, mp->m_ddev_targp,
+ XFS_AG_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
+ XFS_FSS_TO_BB(mp, 1), 0);
+ if (!bp)
+ return -ENOMEM;
+ bp->b_ops = &xfs_sb_buf_ops;
+ xfs_buf_oneshot(bp);
+ *bpp = bp;
+ return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h
index 63dcd2a..244e016 100644
--- a/fs/xfs/libxfs/xfs_sb.h
+++ b/fs/xfs/libxfs/xfs_sb.h
@@ -18,6 +18,13 @@
#ifndef __XFS_SB_H__
#define __XFS_SB_H__
+struct xfs_mount;
+struct xfs_sb;
+struct xfs_dsb;
+struct xfs_trans;
+struct xfs_fsop_geom;
+struct xfs_perag;
+
/*
* perag get/put wrappers for ref counting
*/
@@ -29,13 +36,22 @@ extern int xfs_initialize_perag_data(struct xfs_mount *, xfs_agnumber_t);
extern void xfs_log_sb(struct xfs_trans *tp);
extern int xfs_sync_sb(struct xfs_mount *mp, bool wait);
+extern int xfs_sync_sb_buf(struct xfs_mount *mp);
extern void xfs_sb_mount_common(struct xfs_mount *mp, struct xfs_sb *sbp);
extern void xfs_sb_from_disk(struct xfs_sb *to, struct xfs_dsb *from);
extern void xfs_sb_to_disk(struct xfs_dsb *to, struct xfs_sb *from);
extern void xfs_sb_quota_from_disk(struct xfs_sb *sbp);
+extern int xfs_update_secondary_sbs(struct xfs_mount *mp);
+
#define XFS_FS_GEOM_MAX_STRUCT_VER (4)
extern int xfs_fs_geometry(struct xfs_sb *sbp, struct xfs_fsop_geom *geo,
int struct_version);
+extern int xfs_sb_read_secondary(struct xfs_mount *mp,
+ struct xfs_trans *tp, xfs_agnumber_t agno,
+ struct xfs_buf **bpp);
+extern int xfs_sb_get_secondary(struct xfs_mount *mp,
+ struct xfs_trans *tp, xfs_agnumber_t agno,
+ struct xfs_buf **bpp);
#endif /* __XFS_SB_H__ */
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index d0b84da..ae99c26 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -57,21 +57,6 @@ extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops;
extern const struct xfs_buf_ops xfs_symlink_buf_ops;
extern const struct xfs_buf_ops xfs_rtbuf_ops;
-/*
- * This structure is used to track log items associated with
- * a transaction. It points to the log item and keeps some
- * flags to track the state of the log item. It also tracks
- * the amount of space needed to log the item it describes
- * once we get to commit processing (see xfs_trans_commit()).
- */
-struct xfs_log_item_desc {
- struct xfs_log_item *lid_item;
- struct list_head lid_trans;
- unsigned char lid_flags;
-};
-
-#define XFS_LID_DIRTY 0x1
-
/* log size calculation functions */
int xfs_log_calc_unit_res(struct xfs_mount *mp, int unit_bytes);
int xfs_log_calc_minimum_size(struct xfs_mount *);
@@ -127,6 +112,7 @@ void xfs_log_get_max_trans_res(struct xfs_mount *mp,
#define XFS_ATTR_BTREE_REF 1
#define XFS_DQUOT_REF 1
#define XFS_REFC_BTREE_REF 1
+#define XFS_SSB_REF 0
/*
* Flags for xfs_trans_ichgtime().
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 3c56069..ea18449 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -30,7 +30,7 @@ typedef int64_t xfs_fsize_t; /* bytes in a file */
typedef uint64_t xfs_ufsize_t; /* unsigned bytes in a file */
typedef int32_t xfs_suminfo_t; /* type of bitmap summary info */
-typedef int32_t xfs_rtword_t; /* word type for bitmap manipulations */
+typedef uint32_t xfs_rtword_t; /* word type for bitmap manipulations */
typedef int64_t xfs_lsn_t; /* log sequence number */
typedef int32_t xfs_tid_t; /* transaction identifier */
diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index 018aabbd..1f71793 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -38,68 +38,6 @@
#include "scrub/common.h"
#include "scrub/trace.h"
-/*
- * Walk all the blocks in the AGFL. The fn function can return any negative
- * error code or XFS_BTREE_QUERY_RANGE_ABORT.
- */
-int
-xfs_scrub_walk_agfl(
- struct xfs_scrub_context *sc,
- int (*fn)(struct xfs_scrub_context *,
- xfs_agblock_t bno, void *),
- void *priv)
-{
- struct xfs_agf *agf;
- __be32 *agfl_bno;
- struct xfs_mount *mp = sc->mp;
- unsigned int flfirst;
- unsigned int fllast;
- int i;
- int error;
-
- agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
- agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, sc->sa.agfl_bp);
- flfirst = be32_to_cpu(agf->agf_flfirst);
- fllast = be32_to_cpu(agf->agf_fllast);
-
- /* Nothing to walk in an empty AGFL. */
- if (agf->agf_flcount == cpu_to_be32(0))
- return 0;
-
- /* first to last is a consecutive list. */
- if (fllast >= flfirst) {
- for (i = flfirst; i <= fllast; i++) {
- error = fn(sc, be32_to_cpu(agfl_bno[i]), priv);
- if (error)
- return error;
- if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
- return error;
- }
-
- return 0;
- }
-
- /* first to the end */
- for (i = flfirst; i < xfs_agfl_size(mp); i++) {
- error = fn(sc, be32_to_cpu(agfl_bno[i]), priv);
- if (error)
- return error;
- if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
- return error;
- }
-
- /* the start to last. */
- for (i = 0; i <= fllast; i++) {
- error = fn(sc, be32_to_cpu(agfl_bno[i]), priv);
- if (error)
- return error;
- if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
- return error;
- }
-
- return 0;
-}
-
/* Superblock */
/* Cross-reference with the other btrees. */
@@ -157,9 +95,7 @@ xfs_scrub_superblock(
if (agno == 0)
return 0;
- error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
- XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
- XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_sb_buf_ops);
+ error = xfs_sb_read_secondary(mp, sc->tp, agno, &bp);
/*
* The superblock verifier can return several different error codes
* if it thinks the superblock doesn't look right. For a mount these
@@ -680,6 +616,7 @@ struct xfs_scrub_agfl_info {
unsigned int sz_entries;
unsigned int nr_entries;
xfs_agblock_t *entries;
+ struct xfs_scrub_context *sc;
};
/* Cross-reference with the other btrees. */
@@ -701,12 +638,12 @@ xfs_scrub_agfl_block_xref(
/* Scrub an AGFL block. */
STATIC int
xfs_scrub_agfl_block(
- struct xfs_scrub_context *sc,
+ struct xfs_mount *mp,
xfs_agblock_t agbno,
void *priv)
{
- struct xfs_mount *mp = sc->mp;
struct xfs_scrub_agfl_info *sai = priv;
+ struct xfs_scrub_context *sc = sai->sc;
xfs_agnumber_t agno = sc->sa.agno;
if (xfs_verify_agbno(mp, agno, agbno) &&
@@ -717,6 +654,9 @@ xfs_scrub_agfl_block(
xfs_scrub_agfl_block_xref(sc, agbno, priv);
+ if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+ return XFS_BTREE_QUERY_RANGE_ABORT;
+
return 0;
}
@@ -796,8 +736,10 @@ xfs_scrub_agfl(
goto out;
}
memset(&sai, 0, sizeof(sai));
+ sai.sc = sc;
sai.sz_entries = agflcount;
- sai.entries = kmem_zalloc(sizeof(xfs_agblock_t) * agflcount, KM_NOFS);
+ sai.entries = kmem_zalloc(sizeof(xfs_agblock_t) * agflcount,
+ KM_MAYFAIL);
if (!sai.entries) {
error = -ENOMEM;
goto out;
@@ -805,7 +747,12 @@ xfs_scrub_agfl(
/* Check the blocks in the AGFL. */
xfs_rmap_ag_owner(&sai.oinfo, XFS_RMAP_OWN_AG);
- error = xfs_scrub_walk_agfl(sc, xfs_scrub_agfl_block, &sai);
+ error = xfs_agfl_walk(sc->mp, XFS_BUF_TO_AGF(sc->sa.agf_bp),
+ sc->sa.agfl_bp, xfs_scrub_agfl_block, &sai);
+ if (error == XFS_BTREE_QUERY_RANGE_ABORT) {
+ error = 0;
+ goto out_free;
+ }
if (error)
goto out_free;
diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
new file mode 100644
index 0000000..8b91e9e
--- /dev/null
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -0,0 +1,70 @@
+/*
+ * Copyright (C) 2018 Oracle. All Rights Reserved.
+ *
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_alloc.h"
+#include "xfs_ialloc.h"
+#include "xfs_rmap.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+
+/* Superblock */
+
+/* Repair the superblock. */
+int
+xfs_repair_superblock(
+ struct xfs_scrub_context *sc)
+{
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_buf *bp;
+ xfs_agnumber_t agno;
+ int error;
+
+ /* Don't try to repair AG 0's sb; let xfs_repair deal with it. */
+ agno = sc->sm->sm_agno;
+ if (agno == 0)
+ return -EOPNOTSUPP;
+
+ error = xfs_sb_get_secondary(mp, sc->tp, agno, &bp);
+ if (error)
+ return error;
+
+ /* Copy AG 0's superblock to this one. */
+ xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
+ xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb);
+
+ /* Write this to disk. */
+ xfs_trans_buf_set_type(sc->tp, bp, XFS_BLFT_SB_BUF);
+ xfs_trans_log_buf(sc->tp, bp, 0, BBTOB(bp->b_length) - 1);
+ return error;
+}
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index 517c079..941a0a5 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -70,7 +70,7 @@ xfs_scrub_allocbt_xref_other(
pcur = &sc->sa.cnt_cur;
else
pcur = &sc->sa.bno_cur;
- if (!*pcur)
+ if (!*pcur || xfs_scrub_skip_xref(sc->sm))
return;
error = xfs_alloc_lookup_le(*pcur, agbno, len, &has_otherrec);
@@ -172,7 +172,7 @@ xfs_scrub_xref_is_used_space(
bool is_freesp;
int error;
- if (!sc->sa.bno_cur)
+ if (!sc->sa.bno_cur || xfs_scrub_skip_xref(sc->sm))
return;
error = xfs_alloc_has_record(sc->sa.bno_cur, agbno, len, &is_freesp);
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index 127575f..84b6d6b 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -126,8 +126,9 @@ xfs_scrub_xattr_listent(
if (args.valuelen != valuelen)
xfs_scrub_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK,
args.blkno);
-
fail_xref:
+ if (sx->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+ context->seen_enough = 1;
return;
}
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 639d14b..eeadb33 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -51,7 +51,6 @@ xfs_scrub_setup_inode_bmap(
struct xfs_scrub_context *sc,
struct xfs_inode *ip)
{
- struct xfs_mount *mp = sc->mp;
int error;
error = xfs_scrub_get_inode(sc, ip);
@@ -75,7 +74,7 @@ xfs_scrub_setup_inode_bmap(
}
/* Got the inode, lock it and we're ready to go. */
- error = xfs_scrub_trans_alloc(sc->sm, mp, &sc->tp);
+ error = xfs_scrub_trans_alloc(sc, 0);
if (error)
goto out;
sc->ilock_flags |= XFS_ILOCK_EXCL;
@@ -175,7 +174,7 @@ xfs_scrub_bmap_xref_rmap(
unsigned long long rmap_end;
uint64_t owner;
- if (!info->sc->sa.rmap_cur)
+ if (!info->sc->sa.rmap_cur || xfs_scrub_skip_xref(info->sc->sm))
return;
if (info->whichfork == XFS_COW_FORK)
@@ -684,7 +683,8 @@ xfs_scrub_bmap(
info.lastoff = 0;
ifp = XFS_IFORK_PTR(ip, whichfork);
for_each_xfs_iext(ifp, &icur, &irec) {
- if (xfs_scrub_should_terminate(sc, &error))
+ if (xfs_scrub_should_terminate(sc, &error) ||
+ (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
break;
if (isnullstartblock(irec.br_startblock))
continue;
diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
index 5421816..2d29dce 100644
--- a/fs/xfs/scrub/btree.c
+++ b/fs/xfs/scrub/btree.c
@@ -442,7 +442,7 @@ xfs_scrub_btree_check_owner(
*/
if (cur->bc_btnum == XFS_BTNUM_BNO || cur->bc_btnum == XFS_BTNUM_RMAP) {
co = kmem_alloc(sizeof(struct check_owner),
- KM_MAYFAIL | KM_NOFS);
+ KM_MAYFAIL);
if (!co)
return -ENOMEM;
co->level = level;
@@ -455,6 +455,44 @@ xfs_scrub_btree_check_owner(
}
/*
+ * Check that this btree block has at least minrecs records or is one of the
+ * special blocks that don't require that.
+ */
+STATIC void
+xfs_scrub_btree_check_minrecs(
+ struct xfs_scrub_btree *bs,
+ int level,
+ struct xfs_btree_block *block)
+{
+ unsigned int numrecs;
+ int ok_level;
+
+ numrecs = be16_to_cpu(block->bb_numrecs);
+
+ /* More records than minrecs means the block is ok. */
+ if (numrecs >= bs->cur->bc_ops->get_minrecs(bs->cur, level))
+ return;
+
+ /*
+ * Certain btree blocks /can/ have fewer than minrecs records. Any
+ * level greater than or equal to the level of the highest dedicated
+ * btree block are allowed to violate this constraint.
+ *
+ * For a btree rooted in a block, the btree root can have fewer than
+ * minrecs records. If the btree is rooted in an inode and does not
+ * store records in the root, the direct children of the root and the
+ * root itself can have fewer than minrecs records.
+ */
+ ok_level = bs->cur->bc_nlevels - 1;
+ if (bs->cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
+ ok_level--;
+ if (level >= ok_level)
+ return;
+
+ xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, level);
+}
+
+/*
* Grab and scrub a btree block given a btree pointer. Returns block
* and buffer pointers (if applicable) if they're ok to use.
*/
@@ -491,6 +529,8 @@ xfs_scrub_btree_get_block(
if (*pbp)
xfs_scrub_buffer_recheck(bs->sc, *pbp);
+ xfs_scrub_btree_check_minrecs(bs, level, *pblock);
+
/*
* Check the block's owner; this function absorbs error codes
* for us.
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 8ed91d5..41198a5 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -44,11 +44,14 @@
#include "xfs_rmap_btree.h"
#include "xfs_log.h"
#include "xfs_trans_priv.h"
+#include "xfs_attr.h"
+#include "xfs_reflink.h"
#include "scrub/xfs_scrub.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
#include "scrub/btree.h"
+#include "scrub/repair.h"
/* Common code for the metadata scrubbers. */
@@ -539,6 +542,10 @@ xfs_scrub_ag_free(
xfs_trans_brelse(sc->tp, sa->agi_bp);
sa->agi_bp = NULL;
}
+ if (sa->pag) {
+ xfs_perag_put(sa->pag);
+ sa->pag = NULL;
+ }
sa->agno = NULLAGNUMBER;
}
@@ -566,15 +573,53 @@ xfs_scrub_ag_init(
return xfs_scrub_ag_btcur_init(sc, sa);
}
+/*
+ * Grab the per-ag structure if we haven't already gotten it. Teardown of the
+ * xfs_scrub_ag will release it for us.
+ */
+void
+xfs_scrub_perag_get(
+ struct xfs_mount *mp,
+ struct xfs_scrub_ag *sa)
+{
+ if (!sa->pag)
+ sa->pag = xfs_perag_get(mp, sa->agno);
+}
+
/* Per-scrubber setup functions */
+/*
+ * Grab an empty transaction so that we can re-grab locked buffers if
+ * one of our btrees turns out to be cyclic.
+ *
+ * If we're going to repair something, we need to ask for the largest possible
+ * log reservation so that we can handle the worst case scenario for metadata
+ * updates while rebuilding a metadata item. We also need to reserve as many
+ * blocks in the head transaction as we think we're going to need to rebuild
+ * the metadata object.
+ */
+int
+xfs_scrub_trans_alloc(
+ struct xfs_scrub_context *sc,
+ uint resblks)
+{
+ if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)
+ return xfs_trans_alloc(sc->mp, &M_RES(sc->mp)->tr_itruncate,
+ resblks, 0, 0, &sc->tp);
+
+ return xfs_trans_alloc_empty(sc->mp, &sc->tp);
+}
+
/* Set us up with a transaction and an empty context. */
int
xfs_scrub_setup_fs(
struct xfs_scrub_context *sc,
struct xfs_inode *ip)
{
- return xfs_scrub_trans_alloc(sc->sm, sc->mp, &sc->tp);
+ uint resblks;
+
+ resblks = xfs_repair_calc_ag_resblks(sc);
+ return xfs_scrub_trans_alloc(sc, resblks);
}
/* Set us up with AG headers and btree cursors. */
@@ -695,7 +740,6 @@ xfs_scrub_setup_inode_contents(
struct xfs_inode *ip,
unsigned int resblks)
{
- struct xfs_mount *mp = sc->mp;
int error;
error = xfs_scrub_get_inode(sc, ip);
@@ -705,7 +749,7 @@ xfs_scrub_setup_inode_contents(
/* Got the inode, lock it and we're ready to go. */
sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
xfs_ilock(sc->ip, sc->ilock_flags);
- error = xfs_scrub_trans_alloc(sc->sm, mp, &sc->tp);
+ error = xfs_scrub_trans_alloc(sc, resblks);
if (error)
goto out;
sc->ilock_flags |= XFS_ILOCK_EXCL;
@@ -727,6 +771,10 @@ xfs_scrub_should_check_xref(
int *error,
struct xfs_btree_cur **curpp)
{
+ /* No point in xref if we already know we're corrupt. */
+ if (xfs_scrub_skip_xref(sc->sm))
+ return false;
+
if (*error == 0)
return true;
@@ -773,3 +821,80 @@ xfs_scrub_buffer_recheck(
sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
trace_xfs_scrub_block_error(sc, bp->b_bn, fa);
}
+
+/*
+ * Scrub the attr/data forks of a metadata inode. The metadata inode must be
+ * pointed to by sc->ip and the ILOCK must be held.
+ */
+int
+xfs_scrub_metadata_inode_forks(
+ struct xfs_scrub_context *sc)
+{
+ __u32 smtype;
+ bool shared;
+ int error;
+
+ if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+ return 0;
+
+ /* Metadata inodes don't live on the rt device. */
+ if (sc->ip->i_d.di_flags & XFS_DIFLAG_REALTIME) {
+ xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+ return 0;
+ }
+
+ /* They should never participate in reflink. */
+ if (xfs_is_reflink_inode(sc->ip)) {
+ xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+ return 0;
+ }
+
+ /* They also should never have extended attributes. */
+ if (xfs_inode_hasattr(sc->ip)) {
+ xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+ return 0;
+ }
+
+ /* Invoke the data fork scrubber. */
+ smtype = sc->sm->sm_type;
+ sc->sm->sm_type = XFS_SCRUB_TYPE_BMBTD;
+ error = xfs_scrub_bmap_data(sc);
+ sc->sm->sm_type = smtype;
+ if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
+ return error;
+
+ /* Look for incorrect shared blocks. */
+ if (xfs_sb_version_hasreflink(&sc->mp->m_sb)) {
+ error = xfs_reflink_inode_has_shared_extents(sc->tp, sc->ip,
+ &shared);
+ if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0,
+ &error))
+ return error;
+ if (shared)
+ xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+ }
+
+ return error;
+}
+
+/*
+ * Try to lock an inode in violation of the usual locking order rules. For
+ * example, trying to get the IOLOCK while in transaction context, or just
+ * plain breaking AG-order or inode-order inode locking rules. Either way,
+ * the only way to avoid an ABBA deadlock is to use trylock and back off if
+ * we can't.
+ */
+int
+xfs_scrub_ilock_inverted(
+ struct xfs_inode *ip,
+ uint lock_mode)
+{
+ int i;
+
+ for (i = 0; i < 20; i++) {
+ if (xfs_ilock_nowait(ip, lock_mode))
+ return 0;
+ delay(1);
+ }
+ return -EDEADLOCK;
+}
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index deaf604..76bb2d1 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -38,19 +38,7 @@ xfs_scrub_should_terminate(
return false;
}
-/*
- * Grab an empty transaction so that we can re-grab locked buffers if
- * one of our btrees turns out to be cyclic.
- */
-static inline int
-xfs_scrub_trans_alloc(
- struct xfs_scrub_metadata *sm,
- struct xfs_mount *mp,
- struct xfs_trans **tpp)
-{
- return xfs_trans_alloc_empty(mp, tpp);
-}
-
+int xfs_scrub_trans_alloc(struct xfs_scrub_context *sc, uint resblks);
bool xfs_scrub_process_error(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
xfs_agblock_t bno, int *error);
bool xfs_scrub_fblock_process_error(struct xfs_scrub_context *sc, int whichfork,
@@ -135,16 +123,13 @@ xfs_scrub_setup_quota(struct xfs_scrub_context *sc, struct xfs_inode *ip)
void xfs_scrub_ag_free(struct xfs_scrub_context *sc, struct xfs_scrub_ag *sa);
int xfs_scrub_ag_init(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
struct xfs_scrub_ag *sa);
+void xfs_scrub_perag_get(struct xfs_mount *mp, struct xfs_scrub_ag *sa);
int xfs_scrub_ag_read_headers(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
struct xfs_buf **agi, struct xfs_buf **agf,
struct xfs_buf **agfl);
void xfs_scrub_ag_btcur_free(struct xfs_scrub_ag *sa);
int xfs_scrub_ag_btcur_init(struct xfs_scrub_context *sc,
struct xfs_scrub_ag *sa);
-int xfs_scrub_walk_agfl(struct xfs_scrub_context *sc,
- int (*fn)(struct xfs_scrub_context *, xfs_agblock_t bno,
- void *),
- void *priv);
int xfs_scrub_count_rmap_ownedby_ag(struct xfs_scrub_context *sc,
struct xfs_btree_cur *cur,
struct xfs_owner_info *oinfo,
@@ -157,4 +142,17 @@ int xfs_scrub_setup_inode_contents(struct xfs_scrub_context *sc,
struct xfs_inode *ip, unsigned int resblks);
void xfs_scrub_buffer_recheck(struct xfs_scrub_context *sc, struct xfs_buf *bp);
+/*
+ * Don't bother cross-referencing if we already found corruption or cross
+ * referencing discrepancies.
+ */
+static inline bool xfs_scrub_skip_xref(struct xfs_scrub_metadata *sm)
+{
+ return sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
+ XFS_SCRUB_OFLAG_XCORRUPT);
+}
+
+int xfs_scrub_metadata_inode_forks(struct xfs_scrub_context *sc);
+int xfs_scrub_ilock_inverted(struct xfs_inode *ip, uint lock_mode);
+
#endif /* __XFS_SCRUB_COMMON_H__ */
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 38f2980..1a4309b 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -172,7 +172,7 @@ xfs_scrub_dir_actor(
error = xfs_dir_lookup(sdc->sc->tp, ip, &xname, &lookup_ino, NULL);
if (!xfs_scrub_fblock_process_error(sdc->sc, XFS_DATA_FORK, offset,
&error))
- goto fail_xref;
+ goto out;
if (lookup_ino != ino) {
xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
goto out;
@@ -183,8 +183,13 @@ xfs_scrub_dir_actor(
if (error)
goto out;
out:
- return error;
-fail_xref:
+ /*
+ * A negative error code returned here is supposed to cause the
+ * dir_emit caller (xfs_readdir) to abort the directory iteration
+ * and return zero to xfs_scrub_directory.
+ */
+ if (error == 0 && sdc->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+ return -EFSCORRUPTED;
return error;
}
@@ -240,6 +245,9 @@ xfs_scrub_dir_rec(
}
xfs_scrub_buffer_recheck(ds->sc, bp);
+ if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+ goto out_relse;
+
dent = (struct xfs_dir2_data_entry *)(((char *)bp->b_addr) + off);
/* Make sure we got a real directory entry. */
@@ -357,6 +365,9 @@ xfs_scrub_directory_data_bestfree(
/* XXX: Check xfs_dir3_data_hdr.pad is zero once we start setting it. */
+ if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+ goto out_buf;
+
/* Do the bestfrees correspond to actual free space? */
bf = d_ops->data_bestfree_p(bp->b_addr);
smallest_bestfree = UINT_MAX;
@@ -413,14 +424,18 @@ xfs_scrub_directory_data_bestfree(
/* Spot check this free entry */
tag = be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup));
- if (tag != ((char *)dup - (char *)bp->b_addr))
+ if (tag != ((char *)dup - (char *)bp->b_addr)) {
xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+ goto out_buf;
+ }
/*
* Either this entry is a bestfree or it's smaller than
* any of the bestfrees.
*/
xfs_scrub_directory_check_free_entry(sc, lblk, bf, dup);
+ if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+ goto out_buf;
/* Move on. */
newlen = be16_to_cpu(dup->length);
@@ -546,6 +561,8 @@ xfs_scrub_directory_leaf1_bestfree(
}
if (leafhdr.stale != stale)
xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+ if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+ goto out;
/* Check all the bestfree entries. */
for (i = 0; i < bestcount; i++, bestp++) {
@@ -556,9 +573,11 @@ xfs_scrub_directory_leaf1_bestfree(
i * args->geo->fsbcount, -1, &dbp);
if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk,
&error))
- continue;
+ break;
xfs_scrub_directory_check_freesp(sc, lblk, dbp, best);
xfs_trans_brelse(sc->tp, dbp);
+ if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+ goto out;
}
out:
return error;
@@ -607,7 +626,7 @@ xfs_scrub_directory_free_bestfree(
-1, &dbp);
if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk,
&error))
- continue;
+ break;
xfs_scrub_directory_check_freesp(sc, lblk, dbp, best);
xfs_trans_brelse(sc->tp, dbp);
}
@@ -656,7 +675,7 @@ xfs_scrub_directory_blocks(
/* Iterate all the data extents in the directory... */
found = xfs_iext_lookup_extent(sc->ip, ifp, lblk, &icur, &got);
- while (found) {
+ while (found && !(sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) {
/* Block directories only have a single block at offset 0. */
if (is_block &&
(got.br_startoff > 0 ||
@@ -719,7 +738,7 @@ xfs_scrub_directory_blocks(
/* Scan for free blocks */
lblk = free_lblk;
found = xfs_iext_lookup_extent(sc->ip, ifp, lblk, &icur, &got);
- while (found) {
+ while (found && !(sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) {
/*
* Dirs can't have blocks mapped above 2^32.
* Single-block dirs shouldn't even be here.
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index 106ca4b..00a834d 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -387,7 +387,8 @@ xfs_scrub_iallocbt_xref_rmap_btreeblks(
int error;
if (!sc->sa.ino_cur || !sc->sa.rmap_cur ||
- (xfs_sb_version_hasfinobt(&sc->mp->m_sb) && !sc->sa.fino_cur))
+ (xfs_sb_version_hasfinobt(&sc->mp->m_sb) && !sc->sa.fino_cur) ||
+ xfs_scrub_skip_xref(sc->sm))
return;
/* Check that we saw as many inobt blocks as the rmap says. */
@@ -424,7 +425,7 @@ xfs_scrub_iallocbt_xref_rmap_inodes(
xfs_filblks_t blocks;
int error;
- if (!sc->sa.rmap_cur)
+ if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
return;
/* Check that we saw as many inode blocks as the rmap knows about. */
@@ -496,7 +497,7 @@ xfs_scrub_xref_inode_check(
bool has_inodes;
int error;
- if (!(*icur))
+ if (!(*icur) || xfs_scrub_skip_xref(sc->sm))
return;
error = xfs_ialloc_has_inodes_at_extent(*icur, agbno, len, &has_inodes);
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index df14930..0c696f7 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -55,7 +55,6 @@ xfs_scrub_setup_inode(
struct xfs_scrub_context *sc,
struct xfs_inode *ip)
{
- struct xfs_mount *mp = sc->mp;
int error;
/*
@@ -68,7 +67,7 @@ xfs_scrub_setup_inode(
break;
case -EFSCORRUPTED:
case -EFSBADCRC:
- return xfs_scrub_trans_alloc(sc->sm, mp, &sc->tp);
+ return xfs_scrub_trans_alloc(sc, 0);
default:
return error;
}
@@ -76,7 +75,7 @@ xfs_scrub_setup_inode(
/* Got the inode, lock it and we're ready to go. */
sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
xfs_ilock(sc->ip, sc->ilock_flags);
- error = xfs_scrub_trans_alloc(sc->sm, mp, &sc->tp);
+ error = xfs_scrub_trans_alloc(sc, 0);
if (error)
goto out;
sc->ilock_flags |= XFS_ILOCK_EXCL;
@@ -449,7 +448,7 @@ xfs_scrub_inode_xref_finobt(
int has_record;
int error;
- if (!sc->sa.fino_cur)
+ if (!sc->sa.fino_cur || xfs_scrub_skip_xref(sc->sm))
return;
agino = XFS_INO_TO_AGINO(sc->mp, ino);
@@ -492,6 +491,9 @@ xfs_scrub_inode_xref_bmap(
xfs_filblks_t acount;
int error;
+ if (xfs_scrub_skip_xref(sc->sm))
+ return;
+
/* Walk all the extents to check nextents/naextents/nblocks. */
error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK,
&nextents, &count);
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index 1fb88c1..77c6b22 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -147,6 +147,9 @@ xfs_scrub_parent_validate(
*try_again = false;
+ if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
+ goto out;
+
/* '..' must not point to ourselves. */
if (sc->ip->i_ino == dnum) {
xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
@@ -211,7 +214,9 @@ xfs_scrub_parent_validate(
*/
xfs_iunlock(sc->ip, sc->ilock_flags);
sc->ilock_flags = 0;
- xfs_ilock(dp, XFS_IOLOCK_SHARED);
+ error = xfs_scrub_ilock_inverted(dp, XFS_IOLOCK_SHARED);
+ if (error)
+ goto out_rele;
/* Go looking for our dentry. */
error = xfs_scrub_parent_count_parent_dentries(sc, dp, &nlink);
@@ -220,8 +225,10 @@ xfs_scrub_parent_validate(
/* Drop the parent lock, relock this inode. */
xfs_iunlock(dp, XFS_IOLOCK_SHARED);
+ error = xfs_scrub_ilock_inverted(sc->ip, XFS_IOLOCK_EXCL);
+ if (error)
+ goto out_rele;
sc->ilock_flags = XFS_IOLOCK_EXCL;
- xfs_ilock(sc->ip, sc->ilock_flags);
/*
* If we're an unlinked directory, the parent /won't/ have a link
@@ -323,5 +330,13 @@ xfs_scrub_parent(
if (try_again && tries == 20)
xfs_scrub_set_incomplete(sc);
out:
+ /*
+ * If we failed to lock the parent inode even after a retry, just mark
+ * this scrub incomplete and return.
+ */
+ if (sc->try_harder && error == -EDEADLOCK) {
+ error = 0;
+ xfs_scrub_set_incomplete(sc);
+ }
return error;
}
diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c
index 6ba465e..15ae4d2 100644
--- a/fs/xfs/scrub/quota.c
+++ b/fs/xfs/scrub/quota.c
@@ -66,25 +66,43 @@ xfs_scrub_setup_quota(
struct xfs_inode *ip)
{
uint dqtype;
+ int error;
+
+ if (!XFS_IS_QUOTA_RUNNING(sc->mp) || !XFS_IS_QUOTA_ON(sc->mp))
+ return -ENOENT;
dqtype = xfs_scrub_quota_to_dqtype(sc);
if (dqtype == 0)
return -EINVAL;
+ sc->has_quotaofflock = true;
+ mutex_lock(&sc->mp->m_quotainfo->qi_quotaofflock);
if (!xfs_this_quota_on(sc->mp, dqtype))
return -ENOENT;
+ error = xfs_scrub_setup_fs(sc, ip);
+ if (error)
+ return error;
+ sc->ip = xfs_quota_inode(sc->mp, dqtype);
+ xfs_ilock(sc->ip, XFS_ILOCK_EXCL);
+ sc->ilock_flags = XFS_ILOCK_EXCL;
return 0;
}
/* Quotas. */
+struct xfs_scrub_quota_info {
+ struct xfs_scrub_context *sc;
+ xfs_dqid_t last_id;
+};
+
/* Scrub the fields in an individual quota item. */
-STATIC void
+STATIC int
xfs_scrub_quota_item(
- struct xfs_scrub_context *sc,
- uint dqtype,
struct xfs_dquot *dq,
- xfs_dqid_t id)
+ uint dqtype,
+ void *priv)
{
+ struct xfs_scrub_quota_info *sqi = priv;
+ struct xfs_scrub_context *sc = sqi->sc;
struct xfs_mount *mp = sc->mp;
struct xfs_disk_dquot *d = &dq->q_core;
struct xfs_quotainfo *qi = mp->m_quotainfo;
@@ -99,17 +117,18 @@ xfs_scrub_quota_item(
unsigned long long icount;
unsigned long long rcount;
xfs_ino_t fs_icount;
-
- offset = id / qi->qi_dqperchunk;
+ xfs_dqid_t id = be32_to_cpu(d->d_id);
/*
- * We fed $id and DQNEXT into the xfs_qm_dqget call, which means
- * that the actual dquot we got must either have the same id or
- * the next higher id.
+ * Except for the root dquot, the actual dquot we got must either have
+ * the same or higher id as we saw before.
*/
- if (id > be32_to_cpu(d->d_id))
+ offset = id / qi->qi_dqperchunk;
+ if (id && id <= sqi->last_id)
xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+ sqi->last_id = id;
+
/* Did we get the dquot type we wanted? */
if (dqtype != (d->d_flags & XFS_DQ_ALLTYPES))
xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
@@ -183,6 +202,47 @@ xfs_scrub_quota_item(
xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
if (id != 0 && rhard != 0 && rcount > rhard)
xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+
+ return 0;
+}
+
+/* Check the quota's data fork. */
+STATIC int
+xfs_scrub_quota_data_fork(
+ struct xfs_scrub_context *sc)
+{
+ struct xfs_bmbt_irec irec = { 0 };
+ struct xfs_iext_cursor icur;
+ struct xfs_quotainfo *qi = sc->mp->m_quotainfo;
+ struct xfs_ifork *ifp;
+ xfs_fileoff_t max_dqid_off;
+ int error = 0;
+
+ /* Invoke the fork scrubber. */
+ error = xfs_scrub_metadata_inode_forks(sc);
+ if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
+ return error;
+
+ /* Check for data fork problems that apply only to quota files. */
+ max_dqid_off = ((xfs_dqid_t)-1) / qi->qi_dqperchunk;
+ ifp = XFS_IFORK_PTR(sc->ip, XFS_DATA_FORK);
+ for_each_xfs_iext(ifp, &icur, &irec) {
+ if (xfs_scrub_should_terminate(sc, &error))
+ break;
+ /*
+ * delalloc extents or blocks mapped above the highest
+ * quota id shouldn't happen.
+ */
+ if (isnullstartblock(irec.br_startblock) ||
+ irec.br_startoff > max_dqid_off ||
+ irec.br_startoff + irec.br_blockcount - 1 > max_dqid_off) {
+ xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK,
+ irec.br_startoff);
+ break;
+ }
+ }
+
+ return error;
}
/* Scrub all of a quota type's items. */
@@ -190,108 +250,37 @@ int
xfs_scrub_quota(
struct xfs_scrub_context *sc)
{
- struct xfs_bmbt_irec irec = { 0 };
+ struct xfs_scrub_quota_info sqi;
struct xfs_mount *mp = sc->mp;
- struct xfs_inode *ip;
struct xfs_quotainfo *qi = mp->m_quotainfo;
- struct xfs_dquot *dq;
- xfs_fileoff_t max_dqid_off;
- xfs_fileoff_t off = 0;
- xfs_dqid_t id = 0;
uint dqtype;
- int nimaps;
int error = 0;
- if (!XFS_IS_QUOTA_RUNNING(mp) || !XFS_IS_QUOTA_ON(mp))
- return -ENOENT;
-
- mutex_lock(&qi->qi_quotaofflock);
dqtype = xfs_scrub_quota_to_dqtype(sc);
- if (!xfs_this_quota_on(sc->mp, dqtype)) {
- error = -ENOENT;
- goto out_unlock_quota;
- }
-
- /* Attach to the quota inode and set sc->ip so that reporting works. */
- ip = xfs_quota_inode(sc->mp, dqtype);
- sc->ip = ip;
/* Look for problem extents. */
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- if (ip->i_d.di_flags & XFS_DIFLAG_REALTIME) {
- xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
- goto out_unlock_inode;
- }
- max_dqid_off = ((xfs_dqid_t)-1) / qi->qi_dqperchunk;
- while (1) {
- if (xfs_scrub_should_terminate(sc, &error))
- break;
-
- off = irec.br_startoff + irec.br_blockcount;
- nimaps = 1;
- error = xfs_bmapi_read(ip, off, -1, &irec, &nimaps,
- XFS_BMAPI_ENTIRE);
- if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, off,
- &error))
- goto out_unlock_inode;
- if (!nimaps)
- break;
- if (irec.br_startblock == HOLESTARTBLOCK)
- continue;
-
- /* Check the extent record doesn't point to crap. */
- if (irec.br_startblock + irec.br_blockcount <=
- irec.br_startblock)
- xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK,
- irec.br_startoff);
- if (!xfs_verify_fsbno(mp, irec.br_startblock) ||
- !xfs_verify_fsbno(mp, irec.br_startblock +
- irec.br_blockcount - 1))
- xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK,
- irec.br_startoff);
-
- /*
- * Unwritten extents or blocks mapped above the highest
- * quota id shouldn't happen.
- */
- if (isnullstartblock(irec.br_startblock) ||
- irec.br_startoff > max_dqid_off ||
- irec.br_startoff + irec.br_blockcount > max_dqid_off + 1)
- xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, off);
- }
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ error = xfs_scrub_quota_data_fork(sc);
+ if (error)
+ goto out;
if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
goto out;
- /* Check all the quota items. */
- while (id < ((xfs_dqid_t)-1ULL)) {
- if (xfs_scrub_should_terminate(sc, &error))
- break;
-
- error = xfs_qm_dqget(mp, NULL, id, dqtype, XFS_QMOPT_DQNEXT,
- &dq);
- if (error == -ENOENT)
- break;
- if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK,
- id * qi->qi_dqperchunk, &error))
- break;
-
- xfs_scrub_quota_item(sc, dqtype, dq, id);
-
- id = be32_to_cpu(dq->q_core.d_id) + 1;
- xfs_qm_dqput(dq);
- if (!id)
- break;
- }
+ /*
+ * Check all the quota items. Now that we've checked the quota inode
+ * data fork we have to drop ILOCK_EXCL to use the regular dquot
+ * functions.
+ */
+ xfs_iunlock(sc->ip, sc->ilock_flags);
+ sc->ilock_flags = 0;
+ sqi.sc = sc;
+ sqi.last_id = 0;
+ error = xfs_qm_dqiterate(mp, dqtype, xfs_scrub_quota_item, &sqi);
+ sc->ilock_flags = XFS_ILOCK_EXCL;
+ xfs_ilock(sc->ip, sc->ilock_flags);
+ if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK,
+ sqi.last_id * qi->qi_dqperchunk, &error))
+ goto out;
out:
- /* We set sc->ip earlier, so make sure we clear it now. */
- sc->ip = NULL;
-out_unlock_quota:
- mutex_unlock(&qi->qi_quotaofflock);
return error;
-
-out_unlock_inode:
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- goto out;
}
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index 400f156..324a5f1 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -150,7 +150,7 @@ xfs_scrub_refcountbt_rmap_check(
* so we don't need insertion sort here.
*/
frag = kmem_alloc(sizeof(struct xfs_scrub_refcnt_frag),
- KM_MAYFAIL | KM_NOFS);
+ KM_MAYFAIL);
if (!frag)
return -ENOMEM;
memcpy(&frag->rm, rec, sizeof(frag->rm));
@@ -310,7 +310,7 @@ xfs_scrub_refcountbt_xref_rmap(
struct xfs_scrub_refcnt_frag *n;
int error;
- if (!sc->sa.rmap_cur)
+ if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
return;
/* Cross-reference with the rmapbt to confirm the refcount. */
@@ -404,7 +404,7 @@ xfs_scrub_refcount_xref_rmap(
xfs_filblks_t blocks;
int error;
- if (!sc->sa.rmap_cur)
+ if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
return;
/* Check that we saw as many refcbt blocks as the rmap knows about. */
@@ -460,7 +460,7 @@ xfs_scrub_xref_is_cow_staging(
int has_refcount;
int error;
- if (!sc->sa.refc_cur)
+ if (!sc->sa.refc_cur || xfs_scrub_skip_xref(sc->sm))
return;
/* Find the CoW staging extent. */
@@ -504,7 +504,7 @@ xfs_scrub_xref_is_not_shared(
bool shared;
int error;
- if (!sc->sa.refc_cur)
+ if (!sc->sa.refc_cur || xfs_scrub_skip_xref(sc->sm))
return;
error = xfs_refcount_has_record(sc->sa.refc_cur, agbno, len, &shared);
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
new file mode 100644
index 0000000..e3e8fba
--- /dev/null
+++ b/fs/xfs/scrub/repair.c
@@ -0,0 +1,1089 @@
+/*
+ * Copyright (C) 2018 Oracle. All Rights Reserved.
+ *
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_alloc.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_ialloc.h"
+#include "xfs_ialloc_btree.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_refcount.h"
+#include "xfs_refcount_btree.h"
+#include "xfs_extent_busy.h"
+#include "xfs_ag_resv.h"
+#include "xfs_trans_space.h"
+#include "xfs_quota.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+
+/*
+ * Attempt to repair some metadata, if the metadata is corrupt and userspace
+ * told us to fix it. This function returns -EAGAIN to mean "re-run scrub",
+ * and will set *fixed to true if it thinks it repaired anything.
+ */
+int
+xfs_repair_attempt(
+ struct xfs_inode *ip,
+ struct xfs_scrub_context *sc,
+ bool *fixed)
+{
+ int error = 0;
+
+ trace_xfs_repair_attempt(ip, sc->sm, error);
+
+ xfs_scrub_ag_btcur_free(&sc->sa);
+
+ /* Repair whatever's broken. */
+ ASSERT(sc->ops->repair);
+ error = sc->ops->repair(sc);
+ trace_xfs_repair_done(ip, sc->sm, error);
+ switch (error) {
+ case 0:
+ /*
+ * Repair succeeded. Commit the fixes and perform a second
+ * scrub so that we can tell userspace if we fixed the problem.
+ */
+ sc->sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT;
+ *fixed = true;
+ return -EAGAIN;
+ case -EDEADLOCK:
+ case -EAGAIN:
+ /* Tell the caller to try again having grabbed all the locks. */
+ if (!sc->try_harder) {
+ sc->try_harder = true;
+ return -EAGAIN;
+ }
+ /*
+ * We tried harder but still couldn't grab all the resources
+ * we needed to fix it. The corruption has not been fixed,
+ * so report back to userspace.
+ */
+ return -EFSCORRUPTED;
+ default:
+ return error;
+ }
+}
+
+/*
+ * Complain about unfixable problems in the filesystem. We don't log
+ * corruptions when IFLAG_REPAIR wasn't set on the assumption that the driver
+ * program is xfs_scrub, which will call back with IFLAG_REPAIR set if the
+ * administrator isn't running xfs_scrub in no-repairs mode.
+ *
+ * Use this helper function because _ratelimited silently declares a static
+ * structure to track rate limiting information.
+ */
+void
+xfs_repair_failure(
+ struct xfs_mount *mp)
+{
+ xfs_alert_ratelimited(mp,
+"Corruption not fixed during online repair. Unmount and run xfs_repair.");
+}
+
+/*
+ * Repair probe -- userspace uses this to probe if we're willing to repair a
+ * given mountpoint.
+ */
+int
+xfs_repair_probe(
+ struct xfs_scrub_context *sc)
+{
+ int error = 0;
+
+ if (xfs_scrub_should_terminate(sc, &error))
+ return error;
+
+ return 0;
+}
+
+/*
+ * Roll a transaction, keeping the AG headers locked and reinitializing
+ * the btree cursors.
+ */
+int
+xfs_repair_roll_ag_trans(
+ struct xfs_scrub_context *sc)
+{
+ int error;
+
+ /* Keep the AG header buffers locked so we can keep going. */
+ xfs_trans_bhold(sc->tp, sc->sa.agi_bp);
+ xfs_trans_bhold(sc->tp, sc->sa.agf_bp);
+ xfs_trans_bhold(sc->tp, sc->sa.agfl_bp);
+
+ /* Roll the transaction. */
+ error = xfs_trans_roll(&sc->tp);
+ if (error)
+ goto out_release;
+
+ /* Join AG headers to the new transaction. */
+ xfs_trans_bjoin(sc->tp, sc->sa.agi_bp);
+ xfs_trans_bjoin(sc->tp, sc->sa.agf_bp);
+ xfs_trans_bjoin(sc->tp, sc->sa.agfl_bp);
+
+ return 0;
+
+out_release:
+ /*
+ * Rolling failed, so release the hold on the buffers. The
+ * buffers will be released during teardown on our way out
+ * of the kernel.
+ */
+ xfs_trans_bhold_release(sc->tp, sc->sa.agi_bp);
+ xfs_trans_bhold_release(sc->tp, sc->sa.agf_bp);
+ xfs_trans_bhold_release(sc->tp, sc->sa.agfl_bp);
+
+ return error;
+}
+
+/*
+ * Does the given AG have enough space to rebuild a btree? Neither AG
+ * reservation can be critical, and we must have enough space (factoring
+ * in AG reservations) to construct a whole btree.
+ */
+bool
+xfs_repair_ag_has_space(
+ struct xfs_perag *pag,
+ xfs_extlen_t nr_blocks,
+ enum xfs_ag_resv_type type)
+{
+ return !xfs_ag_resv_critical(pag, XFS_AG_RESV_RMAPBT) &&
+ !xfs_ag_resv_critical(pag, XFS_AG_RESV_METADATA) &&
+ pag->pagf_freeblks > xfs_ag_resv_needed(pag, type) + nr_blocks;
+}
+
+/*
+ * Figure out how many blocks to reserve for an AG repair. We calculate the
+ * worst case estimate for the number of blocks we'd need to rebuild one of
+ * any type of per-AG btree.
+ */
+xfs_extlen_t
+xfs_repair_calc_ag_resblks(
+ struct xfs_scrub_context *sc)
+{
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_scrub_metadata *sm = sc->sm;
+ struct xfs_perag *pag;
+ struct xfs_buf *bp;
+ xfs_agino_t icount = 0;
+ xfs_extlen_t aglen = 0;
+ xfs_extlen_t usedlen;
+ xfs_extlen_t freelen;
+ xfs_extlen_t bnobt_sz;
+ xfs_extlen_t inobt_sz;
+ xfs_extlen_t rmapbt_sz;
+ xfs_extlen_t refcbt_sz;
+ int error;
+
+ if (!(sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR))
+ return 0;
+
+ /* Use in-core counters if possible. */
+ pag = xfs_perag_get(mp, sm->sm_agno);
+ if (pag->pagi_init)
+ icount = pag->pagi_count;
+
+ /*
+ * Otherwise try to get the actual counters from disk; if not, make
+ * some worst case assumptions.
+ */
+ if (icount == 0) {
+ error = xfs_ialloc_read_agi(mp, NULL, sm->sm_agno, &bp);
+ if (error) {
+ icount = mp->m_sb.sb_agblocks / mp->m_sb.sb_inopblock;
+ } else {
+ icount = pag->pagi_count;
+ xfs_buf_relse(bp);
+ }
+ }
+
+ /* Now grab the block counters from the AGF. */
+ error = xfs_alloc_read_agf(mp, NULL, sm->sm_agno, 0, &bp);
+ if (error) {
+ aglen = mp->m_sb.sb_agblocks;
+ freelen = aglen;
+ usedlen = aglen;
+ } else {
+ aglen = be32_to_cpu(XFS_BUF_TO_AGF(bp)->agf_length);
+ freelen = pag->pagf_freeblks;
+ usedlen = aglen - freelen;
+ xfs_buf_relse(bp);
+ }
+ xfs_perag_put(pag);
+
+ trace_xfs_repair_calc_ag_resblks(mp, sm->sm_agno, icount, aglen,
+ freelen, usedlen);
+
+ /*
+ * Figure out how many blocks we'd need worst case to rebuild
+ * each type of btree. Note that we can only rebuild the
+ * bnobt/cntbt or inobt/finobt as pairs.
+ */
+ bnobt_sz = 2 * xfs_allocbt_calc_size(mp, freelen);
+ if (xfs_sb_version_hassparseinodes(&mp->m_sb))
+ inobt_sz = xfs_iallocbt_calc_size(mp, icount /
+ XFS_INODES_PER_HOLEMASK_BIT);
+ else
+ inobt_sz = xfs_iallocbt_calc_size(mp, icount /
+ XFS_INODES_PER_CHUNK);
+ if (xfs_sb_version_hasfinobt(&mp->m_sb))
+ inobt_sz *= 2;
+ if (xfs_sb_version_hasreflink(&mp->m_sb))
+ refcbt_sz = xfs_refcountbt_calc_size(mp, usedlen);
+ else
+ refcbt_sz = 0;
+ if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
+ /*
+ * Guess how many blocks we need to rebuild the rmapbt.
+ * For non-reflink filesystems we can't have more records than
+ * used blocks. However, with reflink it's possible to have
+ * more than one rmap record per AG block. We don't know how
+ * many rmaps there could be in the AG, so we start off with
+ * what we hope is an generous over-estimation.
+ */
+ if (xfs_sb_version_hasreflink(&mp->m_sb))
+ rmapbt_sz = xfs_rmapbt_calc_size(mp,
+ (unsigned long long)aglen * 2);
+ else
+ rmapbt_sz = xfs_rmapbt_calc_size(mp, usedlen);
+ } else {
+ rmapbt_sz = 0;
+ }
+
+ trace_xfs_repair_calc_ag_resblks_btsize(mp, sm->sm_agno, bnobt_sz,
+ inobt_sz, rmapbt_sz, refcbt_sz);
+
+ return max(max(bnobt_sz, inobt_sz), max(rmapbt_sz, refcbt_sz));
+}
+
+/* Allocate a block in an AG. */
+int
+xfs_repair_alloc_ag_block(
+ struct xfs_scrub_context *sc,
+ struct xfs_owner_info *oinfo,
+ xfs_fsblock_t *fsbno,
+ enum xfs_ag_resv_type resv)
+{
+ struct xfs_alloc_arg args = {0};
+ xfs_agblock_t bno;
+ int error;
+
+ switch (resv) {
+ case XFS_AG_RESV_AGFL:
+ case XFS_AG_RESV_RMAPBT:
+ error = xfs_alloc_get_freelist(sc->tp, sc->sa.agf_bp, &bno, 1);
+ if (error)
+ return error;
+ if (bno == NULLAGBLOCK)
+ return -ENOSPC;
+ xfs_extent_busy_reuse(sc->mp, sc->sa.agno, bno,
+ 1, false);
+ *fsbno = XFS_AGB_TO_FSB(sc->mp, sc->sa.agno, bno);
+ if (resv == XFS_AG_RESV_RMAPBT)
+ xfs_ag_resv_rmapbt_alloc(sc->mp, sc->sa.agno);
+ return 0;
+ default:
+ break;
+ }
+
+ args.tp = sc->tp;
+ args.mp = sc->mp;
+ args.oinfo = *oinfo;
+ args.fsbno = XFS_AGB_TO_FSB(args.mp, sc->sa.agno, 0);
+ args.minlen = 1;
+ args.maxlen = 1;
+ args.prod = 1;
+ args.type = XFS_ALLOCTYPE_THIS_AG;
+ args.resv = resv;
+
+ error = xfs_alloc_vextent(&args);
+ if (error)
+ return error;
+ if (args.fsbno == NULLFSBLOCK)
+ return -ENOSPC;
+ ASSERT(args.len == 1);
+ *fsbno = args.fsbno;
+
+ return 0;
+}
+
+/* Initialize a new AG btree root block with zero entries. */
+int
+xfs_repair_init_btblock(
+ struct xfs_scrub_context *sc,
+ xfs_fsblock_t fsb,
+ struct xfs_buf **bpp,
+ xfs_btnum_t btnum,
+ const struct xfs_buf_ops *ops)
+{
+ struct xfs_trans *tp = sc->tp;
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_buf *bp;
+
+ trace_xfs_repair_init_btblock(mp, XFS_FSB_TO_AGNO(mp, fsb),
+ XFS_FSB_TO_AGBNO(mp, fsb), btnum);
+
+ ASSERT(XFS_FSB_TO_AGNO(mp, fsb) == sc->sa.agno);
+ bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, fsb),
+ XFS_FSB_TO_BB(mp, 1), 0);
+ xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
+ xfs_btree_init_block(mp, bp, btnum, 0, 0, sc->sa.agno, 0);
+ xfs_trans_buf_set_type(tp, bp, XFS_BLFT_BTREE_BUF);
+ xfs_trans_log_buf(tp, bp, 0, bp->b_length);
+ bp->b_ops = ops;
+ *bpp = bp;
+
+ return 0;
+}
+
+/*
+ * Reconstructing per-AG Btrees
+ *
+ * When a space btree is corrupt, we don't bother trying to fix it. Instead,
+ * we scan secondary space metadata to derive the records that should be in
+ * the damaged btree, initialize a fresh btree root, and insert the records.
+ * Note that for rebuilding the rmapbt we scan all the primary data to
+ * generate the new records.
+ *
+ * However, that leaves the matter of removing all the metadata describing the
+ * old broken structure. For primary metadata we use the rmap data to collect
+ * every extent with a matching rmap owner (exlist); we then iterate all other
+ * metadata structures with the same rmap owner to collect the extents that
+ * cannot be removed (sublist). We then subtract sublist from exlist to
+ * derive the blocks that were used by the old btree. These blocks can be
+ * reaped.
+ *
+ * For rmapbt reconstructions we must use different tactics for extent
+ * collection. First we iterate all primary metadata (this excludes the old
+ * rmapbt, obviously) to generate new rmap records. The gaps in the rmap
+ * records are collected as exlist. The bnobt records are collected as
+ * sublist. As with the other btrees we subtract sublist from exlist, and the
+ * result (since the rmapbt lives in the free space) are the blocks from the
+ * old rmapbt.
+ */
+
+/* Collect a dead btree extent for later disposal. */
+int
+xfs_repair_collect_btree_extent(
+ struct xfs_scrub_context *sc,
+ struct xfs_repair_extent_list *exlist,
+ xfs_fsblock_t fsbno,
+ xfs_extlen_t len)
+{
+ struct xfs_repair_extent *rex;
+
+ trace_xfs_repair_collect_btree_extent(sc->mp,
+ XFS_FSB_TO_AGNO(sc->mp, fsbno),
+ XFS_FSB_TO_AGBNO(sc->mp, fsbno), len);
+
+ rex = kmem_alloc(sizeof(struct xfs_repair_extent), KM_MAYFAIL);
+ if (!rex)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&rex->list);
+ rex->fsbno = fsbno;
+ rex->len = len;
+ list_add_tail(&rex->list, &exlist->list);
+
+ return 0;
+}
+
+/*
+ * An error happened during the rebuild so the transaction will be cancelled.
+ * The fs will shut down, and the administrator has to unmount and run repair.
+ * Therefore, free all the memory associated with the list so we can die.
+ */
+void
+xfs_repair_cancel_btree_extents(
+ struct xfs_scrub_context *sc,
+ struct xfs_repair_extent_list *exlist)
+{
+ struct xfs_repair_extent *rex;
+ struct xfs_repair_extent *n;
+
+ for_each_xfs_repair_extent_safe(rex, n, exlist) {
+ list_del(&rex->list);
+ kmem_free(rex);
+ }
+}
+
+/* Compare two btree extents. */
+static int
+xfs_repair_btree_extent_cmp(
+ void *priv,
+ struct list_head *a,
+ struct list_head *b)
+{
+ struct xfs_repair_extent *ap;
+ struct xfs_repair_extent *bp;
+
+ ap = container_of(a, struct xfs_repair_extent, list);
+ bp = container_of(b, struct xfs_repair_extent, list);
+
+ if (ap->fsbno > bp->fsbno)
+ return 1;
+ if (ap->fsbno < bp->fsbno)
+ return -1;
+ return 0;
+}
+
+/*
+ * Remove all the blocks mentioned in @sublist from the extents in @exlist.
+ *
+ * The intent is that callers will iterate the rmapbt for all of its records
+ * for a given owner to generate @exlist; and iterate all the blocks of the
+ * metadata structures that are not being rebuilt and have the same rmapbt
+ * owner to generate @sublist. This routine subtracts all the extents
+ * mentioned in sublist from all the extents linked in @exlist, which leaves
+ * @exlist as the list of blocks that are not accounted for, which we assume
+ * are the dead blocks of the old metadata structure. The blocks mentioned in
+ * @exlist can be reaped.
+ */
+#define LEFT_ALIGNED (1 << 0)
+#define RIGHT_ALIGNED (1 << 1)
+int
+xfs_repair_subtract_extents(
+ struct xfs_scrub_context *sc,
+ struct xfs_repair_extent_list *exlist,
+ struct xfs_repair_extent_list *sublist)
+{
+ struct list_head *lp;
+ struct xfs_repair_extent *ex;
+ struct xfs_repair_extent *newex;
+ struct xfs_repair_extent *subex;
+ xfs_fsblock_t sub_fsb;
+ xfs_extlen_t sub_len;
+ int state;
+ int error = 0;
+
+ if (list_empty(&exlist->list) || list_empty(&sublist->list))
+ return 0;
+ ASSERT(!list_empty(&sublist->list));
+
+ list_sort(NULL, &exlist->list, xfs_repair_btree_extent_cmp);
+ list_sort(NULL, &sublist->list, xfs_repair_btree_extent_cmp);
+
+ /*
+ * Now that we've sorted both lists, we iterate exlist once, rolling
+ * forward through sublist and/or exlist as necessary until we find an
+ * overlap or reach the end of either list. We do not reset lp to the
+ * head of exlist nor do we reset subex to the head of sublist. The
+ * list traversal is similar to merge sort, but we're deleting
+ * instead. In this manner we avoid O(n^2) operations.
+ */
+ subex = list_first_entry(&sublist->list, struct xfs_repair_extent,
+ list);
+ lp = exlist->list.next;
+ while (lp != &exlist->list) {
+ ex = list_entry(lp, struct xfs_repair_extent, list);
+
+ /*
+ * Advance subex and/or ex until we find a pair that
+ * intersect or we run out of extents.
+ */
+ while (subex->fsbno + subex->len <= ex->fsbno) {
+ if (list_is_last(&subex->list, &sublist->list))
+ goto out;
+ subex = list_next_entry(subex, list);
+ }
+ if (subex->fsbno >= ex->fsbno + ex->len) {
+ lp = lp->next;
+ continue;
+ }
+
+ /* trim subex to fit the extent we have */
+ sub_fsb = subex->fsbno;
+ sub_len = subex->len;
+ if (subex->fsbno < ex->fsbno) {
+ sub_len -= ex->fsbno - subex->fsbno;
+ sub_fsb = ex->fsbno;
+ }
+ if (sub_len > ex->len)
+ sub_len = ex->len;
+
+ state = 0;
+ if (sub_fsb == ex->fsbno)
+ state |= LEFT_ALIGNED;
+ if (sub_fsb + sub_len == ex->fsbno + ex->len)
+ state |= RIGHT_ALIGNED;
+ switch (state) {
+ case LEFT_ALIGNED:
+ /* Coincides with only the left. */
+ ex->fsbno += sub_len;
+ ex->len -= sub_len;
+ break;
+ case RIGHT_ALIGNED:
+ /* Coincides with only the right. */
+ ex->len -= sub_len;
+ lp = lp->next;
+ break;
+ case LEFT_ALIGNED | RIGHT_ALIGNED:
+ /* Total overlap, just delete ex. */
+ lp = lp->next;
+ list_del(&ex->list);
+ kmem_free(ex);
+ break;
+ case 0:
+ /*
+ * Deleting from the middle: add the new right extent
+ * and then shrink the left extent.
+ */
+ newex = kmem_alloc(sizeof(struct xfs_repair_extent),
+ KM_MAYFAIL);
+ if (!newex) {
+ error = -ENOMEM;
+ goto out;
+ }
+ INIT_LIST_HEAD(&newex->list);
+ newex->fsbno = sub_fsb + sub_len;
+ newex->len = ex->fsbno + ex->len - newex->fsbno;
+ list_add(&newex->list, &ex->list);
+ ex->len = sub_fsb - ex->fsbno;
+ lp = lp->next;
+ break;
+ default:
+ ASSERT(0);
+ break;
+ }
+ }
+
+out:
+ return error;
+}
+#undef LEFT_ALIGNED
+#undef RIGHT_ALIGNED
+
+/*
+ * Disposal of Blocks from Old per-AG Btrees
+ *
+ * Now that we've constructed a new btree to replace the damaged one, we want
+ * to dispose of the blocks that (we think) the old btree was using.
+ * Previously, we used the rmapbt to collect the extents (exlist) with the
+ * rmap owner corresponding to the tree we rebuilt, collected extents for any
+ * blocks with the same rmap owner that are owned by another data structure
+ * (sublist), and subtracted sublist from exlist. In theory the extents
+ * remaining in exlist are the old btree's blocks.
+ *
+ * Unfortunately, it's possible that the btree was crosslinked with other
+ * blocks on disk. The rmap data can tell us if there are multiple owners, so
+ * if the rmapbt says there is an owner of this block other than @oinfo, then
+ * the block is crosslinked. Remove the reverse mapping and continue.
+ *
+ * If there is one rmap record, we can free the block, which removes the
+ * reverse mapping but doesn't add the block to the free space. Our repair
+ * strategy is to hope the other metadata objects crosslinked on this block
+ * will be rebuilt (atop different blocks), thereby removing all the cross
+ * links.
+ *
+ * If there are no rmap records at all, we also free the block. If the btree
+ * being rebuilt lives in the free space (bnobt/cntbt/rmapbt) then there isn't
+ * supposed to be a rmap record and everything is ok. For other btrees there
+ * had to have been an rmap entry for the block to have ended up on @exlist,
+ * so if it's gone now there's something wrong and the fs will shut down.
+ *
+ * Note: If there are multiple rmap records with only the same rmap owner as
+ * the btree we're trying to rebuild and the block is indeed owned by another
+ * data structure with the same rmap owner, then the block will be in sublist
+ * and therefore doesn't need disposal. If there are multiple rmap records
+ * with only the same rmap owner but the block is not owned by something with
+ * the same rmap owner, the block will be freed.
+ *
+ * The caller is responsible for locking the AG headers for the entire rebuild
+ * operation so that nothing else can sneak in and change the AG state while
+ * we're not looking. We also assume that the caller already invalidated any
+ * buffers associated with @exlist.
+ */
+
+/*
+ * Invalidate buffers for per-AG btree blocks we're dumping. This function
+ * is not intended for use with file data repairs; we have bunmapi for that.
+ */
+int
+xfs_repair_invalidate_blocks(
+ struct xfs_scrub_context *sc,
+ struct xfs_repair_extent_list *exlist)
+{
+ struct xfs_repair_extent *rex;
+ struct xfs_repair_extent *n;
+ struct xfs_buf *bp;
+ xfs_fsblock_t fsbno;
+ xfs_agblock_t i;
+
+ /*
+ * For each block in each extent, see if there's an incore buffer for
+ * exactly that block; if so, invalidate it. The buffer cache only
+ * lets us look for one buffer at a time, so we have to look one block
+ * at a time. Avoid invalidating AG headers and post-EOFS blocks
+ * because we never own those; and if we can't TRYLOCK the buffer we
+ * assume it's owned by someone else.
+ */
+ for_each_xfs_repair_extent_safe(rex, n, exlist) {
+ for (fsbno = rex->fsbno, i = rex->len; i > 0; fsbno++, i--) {
+ /* Skip AG headers and post-EOFS blocks */
+ if (!xfs_verify_fsbno(sc->mp, fsbno))
+ continue;
+ bp = xfs_buf_incore(sc->mp->m_ddev_targp,
+ XFS_FSB_TO_DADDR(sc->mp, fsbno),
+ XFS_FSB_TO_BB(sc->mp, 1), XBF_TRYLOCK);
+ if (bp) {
+ xfs_trans_bjoin(sc->tp, bp);
+ xfs_trans_binval(sc->tp, bp);
+ }
+ }
+ }
+
+ return 0;
+}
+
+/* Ensure the freelist is the correct size. */
+int
+xfs_repair_fix_freelist(
+ struct xfs_scrub_context *sc,
+ bool can_shrink)
+{
+ struct xfs_alloc_arg args = {0};
+
+ args.mp = sc->mp;
+ args.tp = sc->tp;
+ args.agno = sc->sa.agno;
+ args.alignment = 1;
+ args.pag = sc->sa.pag;
+
+ return xfs_alloc_fix_freelist(&args,
+ can_shrink ? 0 : XFS_ALLOC_FLAG_NOSHRINK);
+}
+
+/*
+ * Put a block back on the AGFL.
+ */
+STATIC int
+xfs_repair_put_freelist(
+ struct xfs_scrub_context *sc,
+ xfs_agblock_t agbno)
+{
+ struct xfs_owner_info oinfo;
+ int error;
+
+ /* Make sure there's space on the freelist. */
+ error = xfs_repair_fix_freelist(sc, true);
+ if (error)
+ return error;
+
+ /*
+ * Since we're "freeing" a lost block onto the AGFL, we have to
+ * create an rmap for the block prior to merging it or else other
+ * parts will break.
+ */
+ xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG);
+ error = xfs_rmap_alloc(sc->tp, sc->sa.agf_bp, sc->sa.agno, agbno, 1,
+ &oinfo);
+ if (error)
+ return error;
+
+ /* Put the block on the AGFL. */
+ error = xfs_alloc_put_freelist(sc->tp, sc->sa.agf_bp, sc->sa.agfl_bp,
+ agbno, 0);
+ if (error)
+ return error;
+ xfs_extent_busy_insert(sc->tp, sc->sa.agno, agbno, 1,
+ XFS_EXTENT_BUSY_SKIP_DISCARD);
+
+ return 0;
+}
+
+/* Dispose of a single metadata block. */
+STATIC int
+xfs_repair_dispose_btree_block(
+ struct xfs_scrub_context *sc,
+ xfs_fsblock_t fsbno,
+ struct xfs_owner_info *oinfo,
+ enum xfs_ag_resv_type resv)
+{
+ struct xfs_btree_cur *cur;
+ struct xfs_buf *agf_bp = NULL;
+ xfs_agnumber_t agno;
+ xfs_agblock_t agbno;
+ bool has_other_rmap;
+ int error;
+
+ agno = XFS_FSB_TO_AGNO(sc->mp, fsbno);
+ agbno = XFS_FSB_TO_AGBNO(sc->mp, fsbno);
+
+ /*
+ * If we are repairing per-inode metadata, we need to read in the AGF
+ * buffer. Otherwise, we're repairing a per-AG structure, so reuse
+ * the AGF buffer that the setup functions already grabbed.
+ */
+ if (sc->ip) {
+ error = xfs_alloc_read_agf(sc->mp, sc->tp, agno, 0, &agf_bp);
+ if (error)
+ return error;
+ if (!agf_bp)
+ return -ENOMEM;
+ } else {
+ agf_bp = sc->sa.agf_bp;
+ }
+ cur = xfs_rmapbt_init_cursor(sc->mp, sc->tp, agf_bp, agno);
+
+ /* Can we find any other rmappings? */
+ error = xfs_rmap_has_other_keys(cur, agbno, 1, oinfo, &has_other_rmap);
+ if (error)
+ goto out_cur;
+ xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+
+ /*
+ * If there are other rmappings, this block is cross linked and must
+ * not be freed. Remove the reverse mapping and move on. Otherwise,
+ * we were the only owner of the block, so free the extent, which will
+ * also remove the rmap.
+ *
+ * XXX: XFS doesn't support detecting the case where a single block
+ * metadata structure is crosslinked with a multi-block structure
+ * because the buffer cache doesn't detect aliasing problems, so we
+ * can't fix 100% of crosslinking problems (yet). The verifiers will
+ * blow on writeout, the filesystem will shut down, and the admin gets
+ * to run xfs_repair.
+ */
+ if (has_other_rmap)
+ error = xfs_rmap_free(sc->tp, agf_bp, agno, agbno, 1, oinfo);
+ else if (resv == XFS_AG_RESV_AGFL)
+ error = xfs_repair_put_freelist(sc, agbno);
+ else
+ error = xfs_free_extent(sc->tp, fsbno, 1, oinfo, resv);
+ if (agf_bp != sc->sa.agf_bp)
+ xfs_trans_brelse(sc->tp, agf_bp);
+ if (error)
+ return error;
+
+ if (sc->ip)
+ return xfs_trans_roll_inode(&sc->tp, sc->ip);
+ return xfs_repair_roll_ag_trans(sc);
+
+out_cur:
+ xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+ if (agf_bp != sc->sa.agf_bp)
+ xfs_trans_brelse(sc->tp, agf_bp);
+ return error;
+}
+
+/* Dispose of btree blocks from an old per-AG btree. */
+int
+xfs_repair_reap_btree_extents(
+ struct xfs_scrub_context *sc,
+ struct xfs_repair_extent_list *exlist,
+ struct xfs_owner_info *oinfo,
+ enum xfs_ag_resv_type type)
+{
+ struct xfs_repair_extent *rex;
+ struct xfs_repair_extent *n;
+ int error = 0;
+
+ ASSERT(xfs_sb_version_hasrmapbt(&sc->mp->m_sb));
+
+ /* Dispose of every block from the old btree. */
+ for_each_xfs_repair_extent_safe(rex, n, exlist) {
+ ASSERT(sc->ip != NULL ||
+ XFS_FSB_TO_AGNO(sc->mp, rex->fsbno) == sc->sa.agno);
+
+ trace_xfs_repair_dispose_btree_extent(sc->mp,
+ XFS_FSB_TO_AGNO(sc->mp, rex->fsbno),
+ XFS_FSB_TO_AGBNO(sc->mp, rex->fsbno), rex->len);
+
+ for (; rex->len > 0; rex->len--, rex->fsbno++) {
+ error = xfs_repair_dispose_btree_block(sc, rex->fsbno,
+ oinfo, type);
+ if (error)
+ goto out;
+ }
+ list_del(&rex->list);
+ kmem_free(rex);
+ }
+
+out:
+ xfs_repair_cancel_btree_extents(sc, exlist);
+ return error;
+}
+
+/*
+ * Finding per-AG Btree Roots for AGF/AGI Reconstruction
+ *
+ * If the AGF or AGI become slightly corrupted, it may be necessary to rebuild
+ * the AG headers by using the rmap data to rummage through the AG looking for
+ * btree roots. This is not guaranteed to work if the AG is heavily damaged
+ * or the rmap data are corrupt.
+ *
+ * Callers of xfs_repair_find_ag_btree_roots must lock the AGF and AGFL
+ * buffers if the AGF is being rebuilt; or the AGF and AGI buffers if the
+ * AGI is being rebuilt. It must maintain these locks until it's safe for
+ * other threads to change the btrees' shapes. The caller provides
+ * information about the btrees to look for by passing in an array of
+ * xfs_repair_find_ag_btree with the (rmap owner, buf_ops, magic) fields set.
+ * The (root, height) fields will be set on return if anything is found. The
+ * last element of the array should have a NULL buf_ops to mark the end of the
+ * array.
+ *
+ * For every rmapbt record matching any of the rmap owners in btree_info,
+ * read each block referenced by the rmap record. If the block is a btree
+ * block from this filesystem matching any of the magic numbers and has a
+ * level higher than what we've already seen, remember the block and the
+ * height of the tree required to have such a block. When the call completes,
+ * we return the highest block we've found for each btree description; those
+ * should be the roots.
+ */
+
+struct xfs_repair_findroot {
+ struct xfs_scrub_context *sc;
+ struct xfs_buf *agfl_bp;
+ struct xfs_agf *agf;
+ struct xfs_repair_find_ag_btree *btree_info;
+};
+
+/* See if our block is in the AGFL. */
+STATIC int
+xfs_repair_findroot_agfl_walk(
+ struct xfs_mount *mp,
+ xfs_agblock_t bno,
+ void *priv)
+{
+ xfs_agblock_t *agbno = priv;
+
+ return (*agbno == bno) ? XFS_BTREE_QUERY_RANGE_ABORT : 0;
+}
+
+/* Does this block match the btree information passed in? */
+STATIC int
+xfs_repair_findroot_block(
+ struct xfs_repair_findroot *ri,
+ struct xfs_repair_find_ag_btree *fab,
+ uint64_t owner,
+ xfs_agblock_t agbno,
+ bool *found_it)
+{
+ struct xfs_mount *mp = ri->sc->mp;
+ struct xfs_buf *bp;
+ struct xfs_btree_block *btblock;
+ xfs_daddr_t daddr;
+ int error;
+
+ daddr = XFS_AGB_TO_DADDR(mp, ri->sc->sa.agno, agbno);
+
+ /*
+ * Blocks in the AGFL have stale contents that might just happen to
+ * have a matching magic and uuid. We don't want to pull these blocks
+ * in as part of a tree root, so we have to filter out the AGFL stuff
+ * here. If the AGFL looks insane we'll just refuse to repair.
+ */
+ if (owner == XFS_RMAP_OWN_AG) {
+ error = xfs_agfl_walk(mp, ri->agf, ri->agfl_bp,
+ xfs_repair_findroot_agfl_walk, &agbno);
+ if (error == XFS_BTREE_QUERY_RANGE_ABORT)
+ return 0;
+ if (error)
+ return error;
+ }
+
+ error = xfs_trans_read_buf(mp, ri->sc->tp, mp->m_ddev_targp, daddr,
+ mp->m_bsize, 0, &bp, NULL);
+ if (error)
+ return error;
+
+ /*
+ * Does this look like a block matching our fs and higher than any
+ * other block we've found so far? If so, reattach buffer verifiers
+ * so the AIL won't complain if the buffer is also dirty.
+ */
+ btblock = XFS_BUF_TO_BLOCK(bp);
+ if (be32_to_cpu(btblock->bb_magic) != fab->magic)
+ goto out;
+ if (xfs_sb_version_hascrc(&mp->m_sb) &&
+ !uuid_equal(&btblock->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid))
+ goto out;
+ bp->b_ops = fab->buf_ops;
+
+ /* Ignore this block if it's lower in the tree than we've seen. */
+ if (fab->root != NULLAGBLOCK &&
+ xfs_btree_get_level(btblock) < fab->height)
+ goto out;
+
+ /* Make sure we pass the verifiers. */
+ bp->b_ops->verify_read(bp);
+ if (bp->b_error)
+ goto out;
+ fab->root = agbno;
+ fab->height = xfs_btree_get_level(btblock) + 1;
+ *found_it = true;
+
+ trace_xfs_repair_findroot_block(mp, ri->sc->sa.agno, agbno,
+ be32_to_cpu(btblock->bb_magic), fab->height - 1);
+out:
+ xfs_trans_brelse(ri->sc->tp, bp);
+ return error;
+}
+
+/*
+ * Do any of the blocks in this rmap record match one of the btrees we're
+ * looking for?
+ */
+STATIC int
+xfs_repair_findroot_rmap(
+ struct xfs_btree_cur *cur,
+ struct xfs_rmap_irec *rec,
+ void *priv)
+{
+ struct xfs_repair_findroot *ri = priv;
+ struct xfs_repair_find_ag_btree *fab;
+ xfs_agblock_t b;
+ bool found_it;
+ int error = 0;
+
+ /* Ignore anything that isn't AG metadata. */
+ if (!XFS_RMAP_NON_INODE_OWNER(rec->rm_owner))
+ return 0;
+
+ /* Otherwise scan each block + btree type. */
+ for (b = 0; b < rec->rm_blockcount; b++) {
+ found_it = false;
+ for (fab = ri->btree_info; fab->buf_ops; fab++) {
+ if (rec->rm_owner != fab->rmap_owner)
+ continue;
+ error = xfs_repair_findroot_block(ri, fab,
+ rec->rm_owner, rec->rm_startblock + b,
+ &found_it);
+ if (error)
+ return error;
+ if (found_it)
+ break;
+ }
+ }
+
+ return 0;
+}
+
+/* Find the roots of the per-AG btrees described in btree_info. */
+int
+xfs_repair_find_ag_btree_roots(
+ struct xfs_scrub_context *sc,
+ struct xfs_buf *agf_bp,
+ struct xfs_repair_find_ag_btree *btree_info,
+ struct xfs_buf *agfl_bp)
+{
+ struct xfs_mount *mp = sc->mp;
+ struct xfs_repair_findroot ri;
+ struct xfs_repair_find_ag_btree *fab;
+ struct xfs_btree_cur *cur;
+ int error;
+
+ ASSERT(xfs_buf_islocked(agf_bp));
+ ASSERT(agfl_bp == NULL || xfs_buf_islocked(agfl_bp));
+
+ ri.sc = sc;
+ ri.btree_info = btree_info;
+ ri.agf = XFS_BUF_TO_AGF(agf_bp);
+ ri.agfl_bp = agfl_bp;
+ for (fab = btree_info; fab->buf_ops; fab++) {
+ ASSERT(agfl_bp || fab->rmap_owner != XFS_RMAP_OWN_AG);
+ ASSERT(XFS_RMAP_NON_INODE_OWNER(fab->rmap_owner));
+ fab->root = NULLAGBLOCK;
+ fab->height = 0;
+ }
+
+ cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno);
+ error = xfs_rmap_query_all(cur, xfs_repair_findroot_rmap, &ri);
+ xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+
+ return error;
+}
+
+/* Force a quotacheck the next time we mount. */
+void
+xfs_repair_force_quotacheck(
+ struct xfs_scrub_context *sc,
+ uint dqtype)
+{
+ uint flag;
+
+ flag = xfs_quota_chkd_flag(dqtype);
+ if (!(flag & sc->mp->m_qflags))
+ return;
+
+ sc->mp->m_qflags &= ~flag;
+ spin_lock(&sc->mp->m_sb_lock);
+ sc->mp->m_sb.sb_qflags &= ~flag;
+ spin_unlock(&sc->mp->m_sb_lock);
+ xfs_log_sb(sc->tp);
+}
+
+/*
+ * Attach dquots to this inode, or schedule quotacheck to fix them.
+ *
+ * This function ensures that the appropriate dquots are attached to an inode.
+ * We cannot allow the dquot code to allocate an on-disk dquot block here
+ * because we're already in transaction context with the inode locked. The
+ * on-disk dquot should already exist anyway. If the quota code signals
+ * corruption or missing quota information, schedule quotacheck, which will
+ * repair corruptions in the quota metadata.
+ */
+int
+xfs_repair_ino_dqattach(
+ struct xfs_scrub_context *sc)
+{
+ int error;
+
+ error = xfs_qm_dqattach_locked(sc->ip, false);
+ switch (error) {
+ case -EFSBADCRC:
+ case -EFSCORRUPTED:
+ case -ENOENT:
+ xfs_err_ratelimited(sc->mp,
+"inode %llu repair encountered quota error %d, quotacheck forced.",
+ (unsigned long long)sc->ip->i_ino, error);
+ if (XFS_IS_UQUOTA_ON(sc->mp) && !sc->ip->i_udquot)
+ xfs_repair_force_quotacheck(sc, XFS_DQ_USER);
+ if (XFS_IS_GQUOTA_ON(sc->mp) && !sc->ip->i_gdquot)
+ xfs_repair_force_quotacheck(sc, XFS_DQ_GROUP);
+ if (XFS_IS_PQUOTA_ON(sc->mp) && !sc->ip->i_pdquot)
+ xfs_repair_force_quotacheck(sc, XFS_DQ_PROJ);
+ /* fall through */
+ case -ESRCH:
+ error = 0;
+ break;
+ default:
+ break;
+ }
+
+ return error;
+}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
new file mode 100644
index 0000000..f2b0895
--- /dev/null
+++ b/fs/xfs/scrub/repair.h
@@ -0,0 +1,132 @@
+/*
+ * Copyright (C) 2018 Oracle. All Rights Reserved.
+ *
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
+ */
+#ifndef __XFS_SCRUB_REPAIR_H__
+#define __XFS_SCRUB_REPAIR_H__
+
+static inline int xfs_repair_notsupported(struct xfs_scrub_context *sc)
+{
+ return -EOPNOTSUPP;
+}
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+
+/* Repair helpers */
+
+int xfs_repair_attempt(struct xfs_inode *ip, struct xfs_scrub_context *sc,
+ bool *fixed);
+void xfs_repair_failure(struct xfs_mount *mp);
+int xfs_repair_roll_ag_trans(struct xfs_scrub_context *sc);
+bool xfs_repair_ag_has_space(struct xfs_perag *pag, xfs_extlen_t nr_blocks,
+ enum xfs_ag_resv_type type);
+xfs_extlen_t xfs_repair_calc_ag_resblks(struct xfs_scrub_context *sc);
+int xfs_repair_alloc_ag_block(struct xfs_scrub_context *sc,
+ struct xfs_owner_info *oinfo, xfs_fsblock_t *fsbno,
+ enum xfs_ag_resv_type resv);
+int xfs_repair_init_btblock(struct xfs_scrub_context *sc, xfs_fsblock_t fsb,
+ struct xfs_buf **bpp, xfs_btnum_t btnum,
+ const struct xfs_buf_ops *ops);
+
+struct xfs_repair_extent {
+ struct list_head list;
+ xfs_fsblock_t fsbno;
+ xfs_extlen_t len;
+};
+
+struct xfs_repair_extent_list {
+ struct list_head list;
+};
+
+static inline void
+xfs_repair_init_extent_list(
+ struct xfs_repair_extent_list *exlist)
+{
+ INIT_LIST_HEAD(&exlist->list);
+}
+
+#define for_each_xfs_repair_extent_safe(rbe, n, exlist) \
+ list_for_each_entry_safe((rbe), (n), &(exlist)->list, list)
+int xfs_repair_collect_btree_extent(struct xfs_scrub_context *sc,
+ struct xfs_repair_extent_list *btlist, xfs_fsblock_t fsbno,
+ xfs_extlen_t len);
+void xfs_repair_cancel_btree_extents(struct xfs_scrub_context *sc,
+ struct xfs_repair_extent_list *btlist);
+int xfs_repair_subtract_extents(struct xfs_scrub_context *sc,
+ struct xfs_repair_extent_list *exlist,
+ struct xfs_repair_extent_list *sublist);
+int xfs_repair_fix_freelist(struct xfs_scrub_context *sc, bool can_shrink);
+int xfs_repair_invalidate_blocks(struct xfs_scrub_context *sc,
+ struct xfs_repair_extent_list *btlist);
+int xfs_repair_reap_btree_extents(struct xfs_scrub_context *sc,
+ struct xfs_repair_extent_list *exlist,
+ struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type);
+
+struct xfs_repair_find_ag_btree {
+ /* in: rmap owner of the btree we're looking for */
+ uint64_t rmap_owner;
+
+ /* in: buffer ops */
+ const struct xfs_buf_ops *buf_ops;
+
+ /* in: magic number of the btree */
+ uint32_t magic;
+
+ /* out: the highest btree block found and the tree height */
+ xfs_agblock_t root;
+ unsigned int height;
+};
+
+int xfs_repair_find_ag_btree_roots(struct xfs_scrub_context *sc,
+ struct xfs_buf *agf_bp,
+ struct xfs_repair_find_ag_btree *btree_info,
+ struct xfs_buf *agfl_bp);
+void xfs_repair_force_quotacheck(struct xfs_scrub_context *sc, uint dqtype);
+int xfs_repair_ino_dqattach(struct xfs_scrub_context *sc);
+
+/* Metadata repairers */
+
+int xfs_repair_probe(struct xfs_scrub_context *sc);
+int xfs_repair_superblock(struct xfs_scrub_context *sc);
+
+#else
+
+static inline int xfs_repair_attempt(
+ struct xfs_inode *ip,
+ struct xfs_scrub_context *sc,
+ bool *fixed)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void xfs_repair_failure(struct xfs_mount *mp) {}
+
+static inline xfs_extlen_t
+xfs_repair_calc_ag_resblks(
+ struct xfs_scrub_context *sc)
+{
+ ASSERT(!(sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR));
+ return 0;
+}
+
+#define xfs_repair_probe xfs_repair_notsupported
+#define xfs_repair_superblock xfs_repair_notsupported
+
+#endif /* CONFIG_XFS_ONLINE_REPAIR */
+
+#endif /* __XFS_SCRUB_REPAIR_H__ */
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index 8f2a7c3..b376a9a 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -66,7 +66,7 @@ xfs_scrub_rmapbt_xref_refc(
bool is_unwritten;
int error;
- if (!sc->sa.refc_cur)
+ if (!sc->sa.refc_cur || xfs_scrub_skip_xref(sc->sm))
return;
non_inode = XFS_RMAP_NON_INODE_OWNER(irec->rm_owner);
@@ -207,7 +207,7 @@ xfs_scrub_xref_check_owner(
bool has_rmap;
int error;
- if (!sc->sa.rmap_cur)
+ if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
return;
error = xfs_rmap_record_exists(sc->sa.rmap_cur, bno, len, oinfo,
@@ -250,7 +250,7 @@ xfs_scrub_xref_has_no_owner(
bool has_rmap;
int error;
- if (!sc->sa.rmap_cur)
+ if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
return;
error = xfs_rmap_has_record(sc->sa.rmap_cur, bno, len, &has_rmap);
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index 39c41dfe..40f462a 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -66,11 +66,15 @@ xfs_scrub_rtbitmap_rec(
void *priv)
{
struct xfs_scrub_context *sc = priv;
+ xfs_rtblock_t startblock;
+ xfs_rtblock_t blockcount;
- if (rec->ar_startblock + rec->ar_blockcount <= rec->ar_startblock ||
- !xfs_verify_rtbno(sc->mp, rec->ar_startblock) ||
- !xfs_verify_rtbno(sc->mp, rec->ar_startblock +
- rec->ar_blockcount - 1))
+ startblock = rec->ar_startext * tp->t_mountp->m_sb.sb_rextsize;
+ blockcount = rec->ar_extcount * tp->t_mountp->m_sb.sb_rextsize;
+
+ if (startblock + blockcount <= startblock ||
+ !xfs_verify_rtbno(sc->mp, startblock) ||
+ !xfs_verify_rtbno(sc->mp, startblock + blockcount - 1))
xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
return 0;
}
@@ -82,6 +86,11 @@ xfs_scrub_rtbitmap(
{
int error;
+ /* Invoke the fork scrubber. */
+ error = xfs_scrub_metadata_inode_forks(sc);
+ if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
+ return error;
+
error = xfs_rtalloc_query_all(sc->tp, xfs_scrub_rtbitmap_rec, sc);
if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
goto out;
@@ -95,8 +104,35 @@ int
xfs_scrub_rtsummary(
struct xfs_scrub_context *sc)
{
+ struct xfs_inode *rsumip = sc->mp->m_rsumip;
+ struct xfs_inode *old_ip = sc->ip;
+ uint old_ilock_flags = sc->ilock_flags;
+ int error = 0;
+
+ /*
+ * We ILOCK'd the rt bitmap ip in the setup routine, now lock the
+ * rt summary ip in compliance with the rt inode locking rules.
+ *
+ * Since we switch sc->ip to rsumip we have to save the old ilock
+ * flags so that we don't mix up the inode state that @sc tracks.
+ */
+ sc->ip = rsumip;
+ sc->ilock_flags = XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM;
+ xfs_ilock(sc->ip, sc->ilock_flags);
+
+ /* Invoke the fork scrubber. */
+ error = xfs_scrub_metadata_inode_forks(sc);
+ if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
+ goto out;
+
/* XXX: implement this some day */
- return -ENOENT;
+ xfs_scrub_set_incomplete(sc);
+out:
+ /* Switch back to the rtbitmap inode and lock flags. */
+ xfs_iunlock(sc->ip, sc->ilock_flags);
+ sc->ilock_flags = old_ilock_flags;
+ sc->ip = old_ip;
+ return error;
}
@@ -107,11 +143,23 @@ xfs_scrub_xref_is_used_rt_space(
xfs_rtblock_t fsbno,
xfs_extlen_t len)
{
+ xfs_rtblock_t startext;
+ xfs_rtblock_t endext;
+ xfs_rtblock_t extcount;
bool is_free;
int error;
+ if (xfs_scrub_skip_xref(sc->sm))
+ return;
+
+ startext = fsbno;
+ endext = fsbno + len - 1;
+ do_div(startext, sc->mp->m_sb.sb_rextsize);
+ if (do_div(endext, sc->mp->m_sb.sb_rextsize))
+ endext++;
+ extcount = endext - startext;
xfs_ilock(sc->mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
- error = xfs_rtalloc_extent_is_free(sc->mp, sc->tp, fsbno, len,
+ error = xfs_rtalloc_extent_is_free(sc->mp, sc->tp, startext, extcount,
&is_free);
if (!xfs_scrub_should_check_xref(sc, &error, NULL))
goto out_unlock;
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 26c7596..36db098 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -42,11 +42,18 @@
#include "xfs_refcount_btree.h"
#include "xfs_rmap.h"
#include "xfs_rmap_btree.h"
+#include "xfs_quota.h"
+#include "xfs_qm.h"
+#include "xfs_errortag.h"
+#include "xfs_error.h"
+#include "xfs_log.h"
+#include "xfs_trans_priv.h"
#include "scrub/xfs_scrub.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
#include "scrub/trace.h"
#include "scrub/btree.h"
+#include "scrub/repair.h"
/*
* Online Scrub and Repair
@@ -120,6 +127,24 @@
* XCORRUPT flag; btree query function errors are noted by setting the
* XFAIL flag and deleting the cursor to prevent further attempts to
* cross-reference with a defective btree.
+ *
+ * If a piece of metadata proves corrupt or suboptimal, the userspace
+ * program can ask the kernel to apply some tender loving care (TLC) to
+ * the metadata object by setting the REPAIR flag and re-calling the
+ * scrub ioctl. "Corruption" is defined by metadata violating the
+ * on-disk specification; operations cannot continue if the violation is
+ * left untreated. It is possible for XFS to continue if an object is
+ * "suboptimal", however performance may be degraded. Repairs are
+ * usually performed by rebuilding the metadata entirely out of
+ * redundant metadata. Optimizing, on the other hand, can sometimes be
+ * done without rebuilding entire structures.
+ *
+ * Generally speaking, the repair code has the following code structure:
+ * Lock -> scrub -> repair -> commit -> re-lock -> re-scrub -> unlock.
+ * The first check helps us figure out if we need to rebuild or simply
+ * optimize the structure so that the rebuild knows what to do. The
+ * second check evaluates the completeness of the repair; that is what
+ * is reported to userspace.
*/
/*
@@ -155,7 +180,10 @@ xfs_scrub_teardown(
{
xfs_scrub_ag_free(sc, &sc->sa);
if (sc->tp) {
- xfs_trans_cancel(sc->tp);
+ if (error == 0 && (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR))
+ error = xfs_trans_commit(sc->tp);
+ else
+ xfs_trans_cancel(sc->tp);
sc->tp = NULL;
}
if (sc->ip) {
@@ -166,6 +194,8 @@ xfs_scrub_teardown(
iput(VFS_I(sc->ip));
sc->ip = NULL;
}
+ if (sc->has_quotaofflock)
+ mutex_unlock(&sc->mp->m_quotainfo->qi_quotaofflock);
if (sc->buf) {
kmem_free(sc->buf);
sc->buf = NULL;
@@ -180,126 +210,150 @@ static const struct xfs_scrub_meta_ops meta_scrub_ops[] = {
.type = ST_NONE,
.setup = xfs_scrub_setup_fs,
.scrub = xfs_scrub_probe,
+ .repair = xfs_repair_probe,
},
[XFS_SCRUB_TYPE_SB] = { /* superblock */
.type = ST_PERAG,
.setup = xfs_scrub_setup_fs,
.scrub = xfs_scrub_superblock,
+ .repair = xfs_repair_superblock,
},
[XFS_SCRUB_TYPE_AGF] = { /* agf */
.type = ST_PERAG,
.setup = xfs_scrub_setup_fs,
.scrub = xfs_scrub_agf,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_AGFL]= { /* agfl */
.type = ST_PERAG,
.setup = xfs_scrub_setup_fs,
.scrub = xfs_scrub_agfl,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_AGI] = { /* agi */
.type = ST_PERAG,
.setup = xfs_scrub_setup_fs,
.scrub = xfs_scrub_agi,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_BNOBT] = { /* bnobt */
.type = ST_PERAG,
.setup = xfs_scrub_setup_ag_allocbt,
.scrub = xfs_scrub_bnobt,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_CNTBT] = { /* cntbt */
.type = ST_PERAG,
.setup = xfs_scrub_setup_ag_allocbt,
.scrub = xfs_scrub_cntbt,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_INOBT] = { /* inobt */
.type = ST_PERAG,
.setup = xfs_scrub_setup_ag_iallocbt,
.scrub = xfs_scrub_inobt,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_FINOBT] = { /* finobt */
.type = ST_PERAG,
.setup = xfs_scrub_setup_ag_iallocbt,
.scrub = xfs_scrub_finobt,
.has = xfs_sb_version_hasfinobt,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_RMAPBT] = { /* rmapbt */
.type = ST_PERAG,
.setup = xfs_scrub_setup_ag_rmapbt,
.scrub = xfs_scrub_rmapbt,
.has = xfs_sb_version_hasrmapbt,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_REFCNTBT] = { /* refcountbt */
.type = ST_PERAG,
.setup = xfs_scrub_setup_ag_refcountbt,
.scrub = xfs_scrub_refcountbt,
.has = xfs_sb_version_hasreflink,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_INODE] = { /* inode record */
.type = ST_INODE,
.setup = xfs_scrub_setup_inode,
.scrub = xfs_scrub_inode,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_BMBTD] = { /* inode data fork */
.type = ST_INODE,
.setup = xfs_scrub_setup_inode_bmap,
.scrub = xfs_scrub_bmap_data,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_BMBTA] = { /* inode attr fork */
.type = ST_INODE,
.setup = xfs_scrub_setup_inode_bmap,
.scrub = xfs_scrub_bmap_attr,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_BMBTC] = { /* inode CoW fork */
.type = ST_INODE,
.setup = xfs_scrub_setup_inode_bmap,
.scrub = xfs_scrub_bmap_cow,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_DIR] = { /* directory */
.type = ST_INODE,
.setup = xfs_scrub_setup_directory,
.scrub = xfs_scrub_directory,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_XATTR] = { /* extended attributes */
.type = ST_INODE,
.setup = xfs_scrub_setup_xattr,
.scrub = xfs_scrub_xattr,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_SYMLINK] = { /* symbolic link */
.type = ST_INODE,
.setup = xfs_scrub_setup_symlink,
.scrub = xfs_scrub_symlink,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_PARENT] = { /* parent pointers */
.type = ST_INODE,
.setup = xfs_scrub_setup_parent,
.scrub = xfs_scrub_parent,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_RTBITMAP] = { /* realtime bitmap */
.type = ST_FS,
.setup = xfs_scrub_setup_rt,
.scrub = xfs_scrub_rtbitmap,
.has = xfs_sb_version_hasrealtime,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_RTSUM] = { /* realtime summary */
.type = ST_FS,
.setup = xfs_scrub_setup_rt,
.scrub = xfs_scrub_rtsummary,
.has = xfs_sb_version_hasrealtime,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_UQUOTA] = { /* user quota */
.type = ST_FS,
.setup = xfs_scrub_setup_quota,
.scrub = xfs_scrub_quota,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_GQUOTA] = { /* group quota */
.type = ST_FS,
.setup = xfs_scrub_setup_quota,
.scrub = xfs_scrub_quota,
+ .repair = xfs_repair_notsupported,
},
[XFS_SCRUB_TYPE_PQUOTA] = { /* project quota */
.type = ST_FS,
.setup = xfs_scrub_setup_quota,
.scrub = xfs_scrub_quota,
+ .repair = xfs_repair_notsupported,
},
};
@@ -379,15 +433,54 @@ xfs_scrub_validate_inputs(
if (!xfs_sb_version_hasextflgbit(&mp->m_sb))
goto out;
- /* We don't know how to repair anything yet. */
- if (sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)
- goto out;
+ /*
+ * We only want to repair read-write v5+ filesystems. Defer the check
+ * for ops->repair until after our scrub confirms that we need to
+ * perform repairs so that we avoid failing due to not supporting
+ * repairing an object that doesn't need repairs.
+ */
+ if (sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) {
+ error = -EOPNOTSUPP;
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ goto out;
+
+ error = -EROFS;
+ if (mp->m_flags & XFS_MOUNT_RDONLY)
+ goto out;
+ }
error = 0;
out:
return error;
}
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+static inline void xfs_scrub_postmortem(struct xfs_scrub_context *sc)
+{
+ /*
+ * Userspace asked us to repair something, we repaired it, rescanned
+ * it, and the rescan says it's still broken. Scream about this in
+ * the system logs.
+ */
+ if ((sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) &&
+ (sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
+ XFS_SCRUB_OFLAG_XCORRUPT)))
+ xfs_repair_failure(sc->mp);
+}
+#else
+static inline void xfs_scrub_postmortem(struct xfs_scrub_context *sc)
+{
+ /*
+ * Userspace asked us to scrub something, it's broken, and we have no
+ * way of fixing it. Scream in the logs.
+ */
+ if (sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
+ XFS_SCRUB_OFLAG_XCORRUPT))
+ xfs_alert_ratelimited(sc->mp,
+ "Corruption detected during scrub.");
+}
+#endif /* CONFIG_XFS_ONLINE_REPAIR */
+
/* Dispatch metadata scrubbing. */
int
xfs_scrub_metadata(
@@ -397,6 +490,7 @@ xfs_scrub_metadata(
struct xfs_scrub_context sc;
struct xfs_mount *mp = ip->i_mount;
bool try_harder = false;
+ bool already_fixed = false;
int error = 0;
BUILD_BUG_ON(sizeof(meta_scrub_ops) !=
@@ -446,10 +540,44 @@ xfs_scrub_metadata(
} else if (error)
goto out_teardown;
- if (sc.sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
- XFS_SCRUB_OFLAG_XCORRUPT))
- xfs_alert_ratelimited(mp, "Corruption detected during scrub.");
+ if ((sc.sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) && !already_fixed) {
+ bool needs_fix;
+ /* Let debug users force us into the repair routines. */
+ if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_FORCE_SCRUB_REPAIR))
+ sc.sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+
+ needs_fix = (sc.sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
+ XFS_SCRUB_OFLAG_XCORRUPT |
+ XFS_SCRUB_OFLAG_PREEN));
+ /*
+ * If userspace asked for a repair but it wasn't necessary,
+ * report that back to userspace.
+ */
+ if (!needs_fix) {
+ sc.sm->sm_flags |= XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED;
+ goto out_nofix;
+ }
+
+ /*
+ * If it's broken, userspace wants us to fix it, and we haven't
+ * already tried to fix it, then attempt a repair.
+ */
+ error = xfs_repair_attempt(ip, &sc, &already_fixed);
+ if (error == -EAGAIN) {
+ if (sc.try_harder)
+ try_harder = true;
+ error = xfs_scrub_teardown(&sc, ip, 0);
+ if (error) {
+ xfs_repair_failure(mp);
+ goto out;
+ }
+ goto retry_op;
+ }
+ }
+
+out_nofix:
+ xfs_scrub_postmortem(&sc);
out_teardown:
error = xfs_scrub_teardown(&sc, ip, error);
out:
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 0d92af8..636424d 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -38,6 +38,9 @@ struct xfs_scrub_meta_ops {
/* Examine metadata for errors. */
int (*scrub)(struct xfs_scrub_context *);
+ /* Repair or optimize the metadata. */
+ int (*repair)(struct xfs_scrub_context *);
+
/* Decide if we even have this piece of metadata. */
bool (*has)(struct xfs_sb *);
@@ -48,6 +51,7 @@ struct xfs_scrub_meta_ops {
/* Buffer pointers and btree cursors for an entire AG. */
struct xfs_scrub_ag {
xfs_agnumber_t agno;
+ struct xfs_perag *pag;
/* AG btree roots */
struct xfs_buf *agf_bp;
@@ -73,6 +77,7 @@ struct xfs_scrub_context {
void *buf;
uint ilock_flags;
bool try_harder;
+ bool has_quotaofflock;
/* State tracking for single-AG operations. */
struct xfs_scrub_ag sa;
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 5d2b1c2..794d56b 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -69,6 +69,8 @@ DEFINE_EVENT(xfs_scrub_class, name, \
DEFINE_SCRUB_EVENT(xfs_scrub_start);
DEFINE_SCRUB_EVENT(xfs_scrub_done);
DEFINE_SCRUB_EVENT(xfs_scrub_deadlock_retry);
+DEFINE_SCRUB_EVENT(xfs_repair_attempt);
+DEFINE_SCRUB_EVENT(xfs_repair_done);
TRACE_EVENT(xfs_scrub_op_error,
TP_PROTO(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
@@ -492,6 +494,262 @@ TRACE_EVENT(xfs_scrub_xref_error,
__entry->ret_ip)
);
+/* repair tracepoints */
+#if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)
+
+DECLARE_EVENT_CLASS(xfs_repair_extent_class,
+ TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+ xfs_agblock_t agbno, xfs_extlen_t len),
+ TP_ARGS(mp, agno, agbno, len),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agblock_t, agbno)
+ __field(xfs_extlen_t, len)
+ ),
+ TP_fast_assign(
+ __entry->dev = mp->m_super->s_dev;
+ __entry->agno = agno;
+ __entry->agbno = agbno;
+ __entry->len = len;
+ ),
+ TP_printk("dev %d:%d agno %u agbno %u len %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->agbno,
+ __entry->len)
+);
+#define DEFINE_REPAIR_EXTENT_EVENT(name) \
+DEFINE_EVENT(xfs_repair_extent_class, name, \
+ TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
+ xfs_agblock_t agbno, xfs_extlen_t len), \
+ TP_ARGS(mp, agno, agbno, len))
+DEFINE_REPAIR_EXTENT_EVENT(xfs_repair_dispose_btree_extent);
+DEFINE_REPAIR_EXTENT_EVENT(xfs_repair_collect_btree_extent);
+DEFINE_REPAIR_EXTENT_EVENT(xfs_repair_agfl_insert);
+
+DECLARE_EVENT_CLASS(xfs_repair_rmap_class,
+ TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+ xfs_agblock_t agbno, xfs_extlen_t len,
+ uint64_t owner, uint64_t offset, unsigned int flags),
+ TP_ARGS(mp, agno, agbno, len, owner, offset, flags),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agblock_t, agbno)
+ __field(xfs_extlen_t, len)
+ __field(uint64_t, owner)
+ __field(uint64_t, offset)
+ __field(unsigned int, flags)
+ ),
+ TP_fast_assign(
+ __entry->dev = mp->m_super->s_dev;
+ __entry->agno = agno;
+ __entry->agbno = agbno;
+ __entry->len = len;
+ __entry->owner = owner;
+ __entry->offset = offset;
+ __entry->flags = flags;
+ ),
+ TP_printk("dev %d:%d agno %u agbno %u len %u owner %lld offset %llu flags 0x%x",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->agbno,
+ __entry->len,
+ __entry->owner,
+ __entry->offset,
+ __entry->flags)
+);
+#define DEFINE_REPAIR_RMAP_EVENT(name) \
+DEFINE_EVENT(xfs_repair_rmap_class, name, \
+ TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
+ xfs_agblock_t agbno, xfs_extlen_t len, \
+ uint64_t owner, uint64_t offset, unsigned int flags), \
+ TP_ARGS(mp, agno, agbno, len, owner, offset, flags))
+DEFINE_REPAIR_RMAP_EVENT(xfs_repair_alloc_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xfs_repair_ialloc_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xfs_repair_rmap_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xfs_repair_bmap_extent_fn);
+
+TRACE_EVENT(xfs_repair_refcount_extent_fn,
+ TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+ struct xfs_refcount_irec *irec),
+ TP_ARGS(mp, agno, irec),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agblock_t, startblock)
+ __field(xfs_extlen_t, blockcount)
+ __field(xfs_nlink_t, refcount)
+ ),
+ TP_fast_assign(
+ __entry->dev = mp->m_super->s_dev;
+ __entry->agno = agno;
+ __entry->startblock = irec->rc_startblock;
+ __entry->blockcount = irec->rc_blockcount;
+ __entry->refcount = irec->rc_refcount;
+ ),
+ TP_printk("dev %d:%d agno %u agbno %u len %u refcount %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->startblock,
+ __entry->blockcount,
+ __entry->refcount)
+)
+
+TRACE_EVENT(xfs_repair_init_btblock,
+ TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
+ xfs_btnum_t btnum),
+ TP_ARGS(mp, agno, agbno, btnum),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agblock_t, agbno)
+ __field(uint32_t, btnum)
+ ),
+ TP_fast_assign(
+ __entry->dev = mp->m_super->s_dev;
+ __entry->agno = agno;
+ __entry->agbno = agbno;
+ __entry->btnum = btnum;
+ ),
+ TP_printk("dev %d:%d agno %u agbno %u btnum %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->agbno,
+ __entry->btnum)
+)
+TRACE_EVENT(xfs_repair_findroot_block,
+ TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
+ uint32_t magic, uint16_t level),
+ TP_ARGS(mp, agno, agbno, magic, level),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agblock_t, agbno)
+ __field(uint32_t, magic)
+ __field(uint16_t, level)
+ ),
+ TP_fast_assign(
+ __entry->dev = mp->m_super->s_dev;
+ __entry->agno = agno;
+ __entry->agbno = agbno;
+ __entry->magic = magic;
+ __entry->level = level;
+ ),
+ TP_printk("dev %d:%d agno %u agbno %u magic 0x%x level %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->agbno,
+ __entry->magic,
+ __entry->level)
+)
+TRACE_EVENT(xfs_repair_calc_ag_resblks,
+ TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+ xfs_agino_t icount, xfs_agblock_t aglen, xfs_agblock_t freelen,
+ xfs_agblock_t usedlen),
+ TP_ARGS(mp, agno, icount, aglen, freelen, usedlen),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agino_t, icount)
+ __field(xfs_agblock_t, aglen)
+ __field(xfs_agblock_t, freelen)
+ __field(xfs_agblock_t, usedlen)
+ ),
+ TP_fast_assign(
+ __entry->dev = mp->m_super->s_dev;
+ __entry->agno = agno;
+ __entry->icount = icount;
+ __entry->aglen = aglen;
+ __entry->freelen = freelen;
+ __entry->usedlen = usedlen;
+ ),
+ TP_printk("dev %d:%d agno %d icount %u aglen %u freelen %u usedlen %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->icount,
+ __entry->aglen,
+ __entry->freelen,
+ __entry->usedlen)
+)
+TRACE_EVENT(xfs_repair_calc_ag_resblks_btsize,
+ TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+ xfs_agblock_t bnobt_sz, xfs_agblock_t inobt_sz,
+ xfs_agblock_t rmapbt_sz, xfs_agblock_t refcbt_sz),
+ TP_ARGS(mp, agno, bnobt_sz, inobt_sz, rmapbt_sz, refcbt_sz),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agblock_t, bnobt_sz)
+ __field(xfs_agblock_t, inobt_sz)
+ __field(xfs_agblock_t, rmapbt_sz)
+ __field(xfs_agblock_t, refcbt_sz)
+ ),
+ TP_fast_assign(
+ __entry->dev = mp->m_super->s_dev;
+ __entry->agno = agno;
+ __entry->bnobt_sz = bnobt_sz;
+ __entry->inobt_sz = inobt_sz;
+ __entry->rmapbt_sz = rmapbt_sz;
+ __entry->refcbt_sz = refcbt_sz;
+ ),
+ TP_printk("dev %d:%d agno %d bno %u ino %u rmap %u refcount %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->bnobt_sz,
+ __entry->inobt_sz,
+ __entry->rmapbt_sz,
+ __entry->refcbt_sz)
+)
+TRACE_EVENT(xfs_repair_reset_counters,
+ TP_PROTO(struct xfs_mount *mp),
+ TP_ARGS(mp),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ ),
+ TP_fast_assign(
+ __entry->dev = mp->m_super->s_dev;
+ ),
+ TP_printk("dev %d:%d",
+ MAJOR(__entry->dev), MINOR(__entry->dev))
+)
+
+TRACE_EVENT(xfs_repair_ialloc_insert,
+ TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
+ xfs_agino_t startino, uint16_t holemask, uint8_t count,
+ uint8_t freecount, uint64_t freemask),
+ TP_ARGS(mp, agno, startino, holemask, count, freecount, freemask),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agino_t, startino)
+ __field(uint16_t, holemask)
+ __field(uint8_t, count)
+ __field(uint8_t, freecount)
+ __field(uint64_t, freemask)
+ ),
+ TP_fast_assign(
+ __entry->dev = mp->m_super->s_dev;
+ __entry->agno = agno;
+ __entry->startino = startino;
+ __entry->holemask = holemask;
+ __entry->count = count;
+ __entry->freecount = freecount;
+ __entry->freemask = freemask;
+ ),
+ TP_printk("dev %d:%d agno %d startino %u holemask 0x%x count %u freecount %u freemask 0x%llx",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->startino,
+ __entry->holemask,
+ __entry->count,
+ __entry->freecount,
+ __entry->freemask)
+)
+
+#endif /* IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) */
+
#endif /* _TRACE_XFS_SCRUB_TRACE_H */
#undef TRACE_INCLUDE_PATH
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 0ab824f..ca69037 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -594,7 +594,7 @@ xfs_alloc_ioend(
struct xfs_ioend *ioend;
struct bio *bio;
- bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, xfs_ioend_bioset);
+ bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &xfs_ioend_bioset);
xfs_init_bio_from_bh(bio, bh);
ioend = container_of(bio, struct xfs_ioend, io_inline_bio);
@@ -1378,10 +1378,9 @@ xfs_vm_bmap(
struct address_space *mapping,
sector_t block)
{
- struct inode *inode = (struct inode *)mapping->host;
- struct xfs_inode *ip = XFS_I(inode);
+ struct xfs_inode *ip = XFS_I(mapping->host);
- trace_xfs_vm_bmap(XFS_I(inode));
+ trace_xfs_vm_bmap(ip);
/*
* The swap code (ab-)uses ->bmap to get a block mapping and then
@@ -1394,9 +1393,7 @@ xfs_vm_bmap(
*/
if (xfs_is_reflink_inode(ip) || XFS_IS_REALTIME_INODE(ip))
return 0;
-
- filemap_write_and_wait(mapping);
- return generic_block_bmap(mapping, block, xfs_get_blocks);
+ return iomap_bmap(mapping, block, &xfs_iomap_ops);
}
STATIC int
@@ -1475,6 +1472,16 @@ xfs_vm_set_page_dirty(
return newly_dirty;
}
+static int
+xfs_iomap_swapfile_activate(
+ struct swap_info_struct *sis,
+ struct file *swap_file,
+ sector_t *span)
+{
+ sis->bdev = xfs_find_bdev_for_inode(file_inode(swap_file));
+ return iomap_swapfile_activate(sis, swap_file, span, &xfs_iomap_ops);
+}
+
const struct address_space_operations xfs_address_space_operations = {
.readpage = xfs_vm_readpage,
.readpages = xfs_vm_readpages,
@@ -1488,6 +1495,7 @@ const struct address_space_operations xfs_address_space_operations = {
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
+ .swap_activate = xfs_iomap_swapfile_activate,
};
const struct address_space_operations xfs_dax_aops = {
@@ -1495,4 +1503,5 @@ const struct address_space_operations xfs_dax_aops = {
.direct_IO = noop_direct_IO,
.set_page_dirty = noop_set_page_dirty,
.invalidatepage = noop_invalidatepage,
+ .swap_activate = xfs_iomap_swapfile_activate,
};
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index 69346d4..694c85b 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -18,7 +18,7 @@
#ifndef __XFS_AOPS_H__
#define __XFS_AOPS_H__
-extern struct bio_set *xfs_ioend_bioset;
+extern struct bio_set xfs_ioend_bioset;
/*
* Types of I/O for bmap clustering and I/O completion tracking.
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 2203465..618bb71 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -160,7 +160,7 @@ STATIC void
xfs_bui_item_unlock(
struct xfs_log_item *lip)
{
- if (lip->li_flags & XFS_LI_ABORTED)
+ if (test_bit(XFS_LI_ABORTED, &lip->li_flags))
xfs_bui_release(BUI_ITEM(lip));
}
@@ -305,7 +305,7 @@ xfs_bud_item_unlock(
{
struct xfs_bud_log_item *budp = BUD_ITEM(lip);
- if (lip->li_flags & XFS_LI_ABORTED) {
+ if (test_bit(XFS_LI_ABORTED, &lip->li_flags)) {
xfs_bui_release(budp->bud_buip);
kmem_zone_free(xfs_bud_zone, budp);
}
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 8cd8c41..06badcb 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -848,7 +848,7 @@ xfs_free_eofblocks(
/*
* Attach the dquots to the inode up front.
*/
- error = xfs_qm_dqattach(ip, 0);
+ error = xfs_qm_dqattach(ip);
if (error)
return error;
@@ -871,8 +871,8 @@ xfs_free_eofblocks(
* contents of the file are flushed to disk then the files
* may be full of holes (ie NULL files bug).
*/
- error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK,
- XFS_ISIZE(ip));
+ error = xfs_itruncate_extents_flags(&tp, ip, XFS_DATA_FORK,
+ XFS_ISIZE(ip), XFS_BMAPI_NODISCARD);
if (error) {
/*
* If we get an error at this point we simply don't
@@ -918,7 +918,7 @@ xfs_alloc_file_space(
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
- error = xfs_qm_dqattach(ip, 0);
+ error = xfs_qm_dqattach(ip);
if (error)
return error;
@@ -1169,7 +1169,7 @@ xfs_free_file_space(
trace_xfs_free_file_space(ip);
- error = xfs_qm_dqattach(ip, 0);
+ error = xfs_qm_dqattach(ip);
if (error)
return error;
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 55661cb..5179ab9 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -549,17 +549,31 @@ xfs_buf_hash_destroy(
}
/*
- * Look up, and creates if absent, a lockable buffer for
- * a given range of an inode. The buffer is returned
- * locked. No I/O is implied by this call.
+ * Look up a buffer in the buffer cache and return it referenced and locked
+ * in @found_bp.
+ *
+ * If @new_bp is supplied and we have a lookup miss, insert @new_bp into the
+ * cache.
+ *
+ * If XBF_TRYLOCK is set in @flags, only try to lock the buffer and return
+ * -EAGAIN if we fail to lock it.
+ *
+ * Return values are:
+ * -EFSCORRUPTED if have been supplied with an invalid address
+ * -EAGAIN on trylock failure
+ * -ENOENT if we fail to find a match and @new_bp was NULL
+ * 0, with @found_bp:
+ * - @new_bp if we inserted it into the cache
+ * - the buffer we found and locked.
*/
-xfs_buf_t *
-_xfs_buf_find(
+static int
+xfs_buf_find(
struct xfs_buftarg *btp,
struct xfs_buf_map *map,
int nmaps,
xfs_buf_flags_t flags,
- xfs_buf_t *new_bp)
+ struct xfs_buf *new_bp,
+ struct xfs_buf **found_bp)
{
struct xfs_perag *pag;
xfs_buf_t *bp;
@@ -567,6 +581,8 @@ _xfs_buf_find(
xfs_daddr_t eofs;
int i;
+ *found_bp = NULL;
+
for (i = 0; i < nmaps; i++)
cmap.bm_len += map[i].bm_len;
@@ -580,16 +596,11 @@ _xfs_buf_find(
*/
eofs = XFS_FSB_TO_BB(btp->bt_mount, btp->bt_mount->m_sb.sb_dblocks);
if (cmap.bm_bn < 0 || cmap.bm_bn >= eofs) {
- /*
- * XXX (dgc): we should really be returning -EFSCORRUPTED here,
- * but none of the higher level infrastructure supports
- * returning a specific error on buffer lookup failures.
- */
xfs_alert(btp->bt_mount,
"%s: daddr 0x%llx out of range, EOFS 0x%llx",
__func__, cmap.bm_bn, eofs);
WARN_ON(1);
- return NULL;
+ return -EFSCORRUPTED;
}
pag = xfs_perag_get(btp->bt_mount,
@@ -604,19 +615,20 @@ _xfs_buf_find(
}
/* No match found */
- if (new_bp) {
- /* the buffer keeps the perag reference until it is freed */
- new_bp->b_pag = pag;
- rhashtable_insert_fast(&pag->pag_buf_hash,
- &new_bp->b_rhash_head,
- xfs_buf_hash_params);
- spin_unlock(&pag->pag_buf_lock);
- } else {
+ if (!new_bp) {
XFS_STATS_INC(btp->bt_mount, xb_miss_locked);
spin_unlock(&pag->pag_buf_lock);
xfs_perag_put(pag);
+ return -ENOENT;
}
- return new_bp;
+
+ /* the buffer keeps the perag reference until it is freed */
+ new_bp->b_pag = pag;
+ rhashtable_insert_fast(&pag->pag_buf_hash, &new_bp->b_rhash_head,
+ xfs_buf_hash_params);
+ spin_unlock(&pag->pag_buf_lock);
+ *found_bp = new_bp;
+ return 0;
found:
spin_unlock(&pag->pag_buf_lock);
@@ -626,7 +638,7 @@ _xfs_buf_find(
if (flags & XBF_TRYLOCK) {
xfs_buf_rele(bp);
XFS_STATS_INC(btp->bt_mount, xb_busy_locked);
- return NULL;
+ return -EAGAIN;
}
xfs_buf_lock(bp);
XFS_STATS_INC(btp->bt_mount, xb_get_locked_waited);
@@ -646,6 +658,24 @@ _xfs_buf_find(
trace_xfs_buf_find(bp, flags, _RET_IP_);
XFS_STATS_INC(btp->bt_mount, xb_get_locked);
+ *found_bp = bp;
+ return 0;
+}
+
+struct xfs_buf *
+xfs_buf_incore(
+ struct xfs_buftarg *target,
+ xfs_daddr_t blkno,
+ size_t numblks,
+ xfs_buf_flags_t flags)
+{
+ struct xfs_buf *bp;
+ int error;
+ DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+
+ error = xfs_buf_find(target, &map, 1, flags, NULL, &bp);
+ if (error)
+ return NULL;
return bp;
}
@@ -665,9 +695,27 @@ xfs_buf_get_map(
struct xfs_buf *new_bp;
int error = 0;
- bp = _xfs_buf_find(target, map, nmaps, flags, NULL);
- if (likely(bp))
+ error = xfs_buf_find(target, map, nmaps, flags, NULL, &bp);
+
+ switch (error) {
+ case 0:
+ /* cache hit */
goto found;
+ case -EAGAIN:
+ /* cache hit, trylock failure, caller handles failure */
+ ASSERT(flags & XBF_TRYLOCK);
+ return NULL;
+ case -ENOENT:
+ /* cache miss, go for insert */
+ break;
+ case -EFSCORRUPTED:
+ default:
+ /*
+ * None of the higher layers understand failure types
+ * yet, so return NULL to signal a fatal lookup error.
+ */
+ return NULL;
+ }
new_bp = _xfs_buf_alloc(target, map, nmaps, flags);
if (unlikely(!new_bp))
@@ -679,8 +727,8 @@ xfs_buf_get_map(
return NULL;
}
- bp = _xfs_buf_find(target, map, nmaps, flags, new_bp);
- if (!bp) {
+ error = xfs_buf_find(target, map, nmaps, flags, new_bp, &bp);
+ if (error) {
xfs_buf_free(new_bp);
return NULL;
}
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index edced16..f5f2b71 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -218,20 +218,9 @@ typedef struct xfs_buf {
} xfs_buf_t;
/* Finding and Reading Buffers */
-struct xfs_buf *_xfs_buf_find(struct xfs_buftarg *target,
- struct xfs_buf_map *map, int nmaps,
- xfs_buf_flags_t flags, struct xfs_buf *new_bp);
-
-static inline struct xfs_buf *
-xfs_incore(
- struct xfs_buftarg *target,
- xfs_daddr_t blkno,
- size_t numblks,
- xfs_buf_flags_t flags)
-{
- DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
- return _xfs_buf_find(target, &map, 1, flags, NULL);
-}
+struct xfs_buf *xfs_buf_incore(struct xfs_buftarg *target,
+ xfs_daddr_t blkno, size_t numblks,
+ xfs_buf_flags_t flags);
struct xfs_buf *_xfs_buf_alloc(struct xfs_buftarg *target,
struct xfs_buf_map *map, int nmaps,
@@ -358,6 +347,18 @@ extern void xfs_buf_terminate(void);
void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref);
+/*
+ * If the buffer is already on the LRU, do nothing. Otherwise set the buffer
+ * up with a reference count of 0 so it will be tossed from the cache when
+ * released.
+ */
+static inline void xfs_buf_oneshot(struct xfs_buf *bp)
+{
+ if (!list_empty(&bp->b_lru) || atomic_read(&bp->b_lru_ref) > 1)
+ return;
+ atomic_set(&bp->b_lru_ref, 0);
+}
+
static inline int xfs_buf_ispinned(struct xfs_buf *bp)
{
return atomic_read(&bp->b_pin_count);
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 82ad270..c231137 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -438,7 +438,7 @@ xfs_buf_item_unpin(
* xfs_trans_uncommit() will try to reference the
* buffer which we no longer have a hold on.
*/
- if (lip->li_desc)
+ if (!list_empty(&lip->li_trans))
xfs_trans_del_item(lip);
/*
@@ -568,13 +568,15 @@ xfs_buf_item_unlock(
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
struct xfs_buf *bp = bip->bli_buf;
- bool aborted = !!(lip->li_flags & XFS_LI_ABORTED);
+ bool aborted;
bool hold = !!(bip->bli_flags & XFS_BLI_HOLD);
bool dirty = !!(bip->bli_flags & XFS_BLI_DIRTY);
#if defined(DEBUG) || defined(XFS_WARN)
bool ordered = !!(bip->bli_flags & XFS_BLI_ORDERED);
#endif
+ aborted = test_bit(XFS_LI_ABORTED, &lip->li_flags);
+
/* Clear the buffer's association with this transaction. */
bp->b_transp = NULL;
@@ -743,8 +745,10 @@ xfs_buf_item_init(
* nothing to do here so return.
*/
ASSERT(bp->b_target->bt_mount == mp);
- if (bip != NULL) {
+ if (bip) {
ASSERT(bip->bli_item.li_type == XFS_LI_BUF);
+ ASSERT(!bp->b_transp);
+ ASSERT(bip->bli_buf == bp);
return 0;
}
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index a7daef9..2567391 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -288,49 +288,43 @@ xfs_dquot_set_prealloc_limits(struct xfs_dquot *dqp)
}
/*
- * Allocate a block and fill it with dquots.
- * This is called when the bmapi finds a hole.
+ * Ensure that the given in-core dquot has a buffer on disk backing it, and
+ * return the buffer. This is called when the bmapi finds a hole.
*/
STATIC int
-xfs_qm_dqalloc(
- xfs_trans_t **tpp,
- xfs_mount_t *mp,
- xfs_dquot_t *dqp,
- xfs_inode_t *quotip,
- xfs_fileoff_t offset_fsb,
- xfs_buf_t **O_bpp)
+xfs_dquot_disk_alloc(
+ struct xfs_trans **tpp,
+ struct xfs_dquot *dqp,
+ struct xfs_buf **bpp)
{
- xfs_fsblock_t firstblock;
- struct xfs_defer_ops dfops;
- xfs_bmbt_irec_t map;
- int nmaps, error;
- xfs_buf_t *bp;
- xfs_trans_t *tp = *tpp;
-
- ASSERT(tp != NULL);
+ struct xfs_bmbt_irec map;
+ struct xfs_defer_ops dfops;
+ struct xfs_mount *mp = (*tpp)->t_mountp;
+ struct xfs_buf *bp;
+ struct xfs_inode *quotip = xfs_quota_inode(mp, dqp->dq_flags);
+ xfs_fsblock_t firstblock;
+ int nmaps = 1;
+ int error;
trace_xfs_dqalloc(dqp);
- /*
- * Initialize the bmap freelist prior to calling bmapi code.
- */
xfs_defer_init(&dfops, &firstblock);
xfs_ilock(quotip, XFS_ILOCK_EXCL);
- /*
- * Return if this type of quotas is turned off while we didn't
- * have an inode lock
- */
if (!xfs_this_quota_on(dqp->q_mount, dqp->dq_flags)) {
+ /*
+ * Return if this type of quotas is turned off while we didn't
+ * have an inode lock
+ */
xfs_iunlock(quotip, XFS_ILOCK_EXCL);
return -ESRCH;
}
- xfs_trans_ijoin(tp, quotip, XFS_ILOCK_EXCL);
- nmaps = 1;
- error = xfs_bmapi_write(tp, quotip, offset_fsb,
- XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA,
- &firstblock, XFS_QM_DQALLOC_SPACE_RES(mp),
- &map, &nmaps, &dfops);
+ /* Create the block mapping. */
+ xfs_trans_ijoin(*tpp, quotip, XFS_ILOCK_EXCL);
+ error = xfs_bmapi_write(*tpp, quotip, dqp->q_fileoffset,
+ XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA,
+ &firstblock, XFS_QM_DQALLOC_SPACE_RES(mp),
+ &map, &nmaps, &dfops);
if (error)
goto error0;
ASSERT(map.br_blockcount == XFS_DQUOT_CLUSTER_SIZE_FSB);
@@ -344,10 +338,8 @@ xfs_qm_dqalloc(
dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock);
/* now we can just get the buffer (there's nothing to read yet) */
- bp = xfs_trans_get_buf(tp, mp->m_ddev_targp,
- dqp->q_blkno,
- mp->m_quotainfo->qi_dqchunklen,
- 0);
+ bp = xfs_trans_get_buf(*tpp, mp->m_ddev_targp, dqp->q_blkno,
+ mp->m_quotainfo->qi_dqchunklen, 0);
if (!bp) {
error = -ENOMEM;
goto error1;
@@ -358,37 +350,45 @@ xfs_qm_dqalloc(
* Make a chunk of dquots out of this buffer and log
* the entire thing.
*/
- xfs_qm_init_dquot_blk(tp, mp, be32_to_cpu(dqp->q_core.d_id),
+ xfs_qm_init_dquot_blk(*tpp, mp, be32_to_cpu(dqp->q_core.d_id),
dqp->dq_flags & XFS_DQ_ALLTYPES, bp);
+ xfs_buf_set_ref(bp, XFS_DQUOT_REF);
/*
- * xfs_defer_finish() may commit the current transaction and
- * start a second transaction if the freelist is not empty.
+ * Hold the buffer and join it to the dfops so that we'll still own
+ * the buffer when we return to the caller. The buffer disposal on
+ * error must be paid attention to very carefully, as it has been
+ * broken since commit efa092f3d4c6 "[XFS] Fixes a bug in the quota
+ * code when allocating a new dquot record" in 2005, and the later
+ * conversion to xfs_defer_ops in commit 310a75a3c6c747 failed to keep
+ * the buffer locked across the _defer_finish call. We can now do
+ * this correctly with xfs_defer_bjoin.
*
- * Since we still want to modify this buffer, we need to
- * ensure that the buffer is not released on commit of
- * the first transaction and ensure the buffer is added to the
- * second transaction.
+ * Above, we allocated a disk block for the dquot information and
+ * used get_buf to initialize the dquot. If the _defer_bjoin fails,
+ * the buffer is still locked to *tpp, so we must _bhold_release and
+ * then _trans_brelse the buffer. If the _defer_finish fails, the old
+ * transaction is gone but the new buffer is not joined or held to any
+ * transaction, so we must _buf_relse it.
*
- * If there is only one transaction then don't stop the buffer
- * from being released when it commits later on.
+ * If everything succeeds, the caller of this function is returned a
+ * buffer that is locked and held to the transaction. The caller
+ * is responsible for unlocking any buffer passed back, either
+ * manually or by committing the transaction.
*/
-
- xfs_trans_bhold(tp, bp);
-
- error = xfs_defer_finish(tpp, &dfops);
- if (error)
+ xfs_trans_bhold(*tpp, bp);
+ error = xfs_defer_bjoin(&dfops, bp);
+ if (error) {
+ xfs_trans_bhold_release(*tpp, bp);
+ xfs_trans_brelse(*tpp, bp);
goto error1;
-
- /* Transaction was committed? */
- if (*tpp != tp) {
- tp = *tpp;
- xfs_trans_bjoin(tp, bp);
- } else {
- xfs_trans_bhold_release(tp, bp);
}
-
- *O_bpp = bp;
+ error = xfs_defer_finish(tpp, &dfops);
+ if (error) {
+ xfs_buf_relse(bp);
+ goto error1;
+ }
+ *bpp = bp;
return 0;
error1:
@@ -398,32 +398,24 @@ xfs_qm_dqalloc(
}
/*
- * Maps a dquot to the buffer containing its on-disk version.
- * This returns a ptr to the buffer containing the on-disk dquot
- * in the bpp param, and a ptr to the on-disk dquot within that buffer
+ * Read in the in-core dquot's on-disk metadata and return the buffer.
+ * Returns ENOENT to signal a hole.
*/
STATIC int
-xfs_qm_dqtobp(
- xfs_trans_t **tpp,
- xfs_dquot_t *dqp,
- xfs_disk_dquot_t **O_ddpp,
- xfs_buf_t **O_bpp,
- uint flags)
+xfs_dquot_disk_read(
+ struct xfs_mount *mp,
+ struct xfs_dquot *dqp,
+ struct xfs_buf **bpp)
{
struct xfs_bmbt_irec map;
- int nmaps = 1, error;
struct xfs_buf *bp;
- struct xfs_inode *quotip;
- struct xfs_mount *mp = dqp->q_mount;
- xfs_dqid_t id = be32_to_cpu(dqp->q_core.d_id);
- struct xfs_trans *tp = (tpp ? *tpp : NULL);
+ struct xfs_inode *quotip = xfs_quota_inode(mp, dqp->dq_flags);
uint lock_mode;
-
- quotip = xfs_quota_inode(dqp->q_mount, dqp->dq_flags);
- dqp->q_fileoffset = (xfs_fileoff_t)id / mp->m_quotainfo->qi_dqperchunk;
+ int nmaps = 1;
+ int error;
lock_mode = xfs_ilock_data_map_shared(quotip);
- if (!xfs_this_quota_on(dqp->q_mount, dqp->dq_flags)) {
+ if (!xfs_this_quota_on(mp, dqp->dq_flags)) {
/*
* Return if this type of quotas is turned off while we
* didn't have the quota inode lock.
@@ -436,81 +428,48 @@ xfs_qm_dqtobp(
* Find the block map; no allocations yet
*/
error = xfs_bmapi_read(quotip, dqp->q_fileoffset,
- XFS_DQUOT_CLUSTER_SIZE_FSB, &map, &nmaps, 0);
-
+ XFS_DQUOT_CLUSTER_SIZE_FSB, &map, &nmaps, 0);
xfs_iunlock(quotip, lock_mode);
if (error)
return error;
ASSERT(nmaps == 1);
- ASSERT(map.br_blockcount == 1);
+ ASSERT(map.br_blockcount >= 1);
+ ASSERT(map.br_startblock != DELAYSTARTBLOCK);
+ if (map.br_startblock == HOLESTARTBLOCK)
+ return -ENOENT;
+
+ trace_xfs_dqtobp_read(dqp);
/*
- * Offset of dquot in the (fixed sized) dquot chunk.
+ * store the blkno etc so that we don't have to do the
+ * mapping all the time
*/
- dqp->q_bufoffset = (id % mp->m_quotainfo->qi_dqperchunk) *
- sizeof(xfs_dqblk_t);
+ dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock);
- ASSERT(map.br_startblock != DELAYSTARTBLOCK);
- if (map.br_startblock == HOLESTARTBLOCK) {
- /*
- * We don't allocate unless we're asked to
- */
- if (!(flags & XFS_QMOPT_DQALLOC))
- return -ENOENT;
-
- ASSERT(tp);
- error = xfs_qm_dqalloc(tpp, mp, dqp, quotip,
- dqp->q_fileoffset, &bp);
- if (error)
- return error;
- tp = *tpp;
- } else {
- trace_xfs_dqtobp_read(dqp);
-
- /*
- * store the blkno etc so that we don't have to do the
- * mapping all the time
- */
- dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock);
-
- error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
- dqp->q_blkno,
- mp->m_quotainfo->qi_dqchunklen,
- 0, &bp, &xfs_dquot_buf_ops);
- if (error) {
- ASSERT(bp == NULL);
- return error;
- }
+ error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno,
+ mp->m_quotainfo->qi_dqchunklen, 0, &bp,
+ &xfs_dquot_buf_ops);
+ if (error) {
+ ASSERT(bp == NULL);
+ return error;
}
ASSERT(xfs_buf_islocked(bp));
- *O_bpp = bp;
- *O_ddpp = bp->b_addr + dqp->q_bufoffset;
+ xfs_buf_set_ref(bp, XFS_DQUOT_REF);
+ *bpp = bp;
return 0;
}
-
-/*
- * Read in the ondisk dquot using dqtobp() then copy it to an incore version,
- * and release the buffer immediately.
- *
- * If XFS_QMOPT_DQALLOC is set, allocate a dquot on disk if it needed.
- */
-int
-xfs_qm_dqread(
+/* Allocate and initialize everything we need for an incore dquot. */
+STATIC struct xfs_dquot *
+xfs_dquot_alloc(
struct xfs_mount *mp,
xfs_dqid_t id,
- uint type,
- uint flags,
- struct xfs_dquot **O_dqpp)
+ uint type)
{
struct xfs_dquot *dqp;
- struct xfs_disk_dquot *ddqp;
- struct xfs_buf *bp;
- struct xfs_trans *tp = NULL;
- int error;
dqp = kmem_zone_zalloc(xfs_qm_dqzone, KM_SLEEP);
@@ -520,6 +479,12 @@ xfs_qm_dqread(
INIT_LIST_HEAD(&dqp->q_lru);
mutex_init(&dqp->q_qlock);
init_waitqueue_head(&dqp->q_pinwait);
+ dqp->q_fileoffset = (xfs_fileoff_t)id / mp->m_quotainfo->qi_dqperchunk;
+ /*
+ * Offset of dquot in the (fixed sized) dquot chunk.
+ */
+ dqp->q_bufoffset = (id % mp->m_quotainfo->qi_dqperchunk) *
+ sizeof(xfs_dqblk_t);
/*
* Because we want to use a counting completion, complete
@@ -548,35 +513,22 @@ xfs_qm_dqread(
break;
}
+ xfs_qm_dquot_logitem_init(dqp);
+
XFS_STATS_INC(mp, xs_qm_dquot);
+ return dqp;
+}
- trace_xfs_dqread(dqp);
-
- if (flags & XFS_QMOPT_DQALLOC) {
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_qm_dqalloc,
- XFS_QM_DQALLOC_SPACE_RES(mp), 0, 0, &tp);
- if (error)
- goto error0;
- }
-
- /*
- * get a pointer to the on-disk dquot and the buffer containing it
- * dqp already knows its own type (GROUP/USER).
- */
- error = xfs_qm_dqtobp(&tp, dqp, &ddqp, &bp, flags);
- if (error) {
- /*
- * This can happen if quotas got turned off (ESRCH),
- * or if the dquot didn't exist on disk and we ask to
- * allocate (ENOENT).
- */
- trace_xfs_dqread_fail(dqp);
- goto error1;
- }
+/* Copy the in-core quota fields in from the on-disk buffer. */
+STATIC void
+xfs_dquot_from_disk(
+ struct xfs_dquot *dqp,
+ struct xfs_buf *bp)
+{
+ struct xfs_disk_dquot *ddqp = bp->b_addr + dqp->q_bufoffset;
/* copy everything from disk dquot to the incore dquot */
memcpy(&dqp->q_core, ddqp, sizeof(xfs_disk_dquot_t));
- xfs_qm_dquot_logitem_init(dqp);
/*
* Reservation counters are defined as reservation plus current usage
@@ -588,40 +540,90 @@ xfs_qm_dqread(
/* initialize the dquot speculative prealloc thresholds */
xfs_dquot_set_prealloc_limits(dqp);
+}
- /* Mark the buf so that this will stay incore a little longer */
- xfs_buf_set_ref(bp, XFS_DQUOT_REF);
+/* Allocate and initialize the dquot buffer for this in-core dquot. */
+static int
+xfs_qm_dqread_alloc(
+ struct xfs_mount *mp,
+ struct xfs_dquot *dqp,
+ struct xfs_buf **bpp)
+{
+ struct xfs_trans *tp;
+ struct xfs_buf *bp;
+ int error;
+
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_qm_dqalloc,
+ XFS_QM_DQALLOC_SPACE_RES(mp), 0, 0, &tp);
+ if (error)
+ goto err;
+
+ error = xfs_dquot_disk_alloc(&tp, dqp, &bp);
+ if (error)
+ goto err_cancel;
+
+ error = xfs_trans_commit(tp);
+ if (error) {
+ /*
+ * Buffer was held to the transaction, so we have to unlock it
+ * manually here because we're not passing it back.
+ */
+ xfs_buf_relse(bp);
+ goto err;
+ }
+ *bpp = bp;
+ return 0;
+
+err_cancel:
+ xfs_trans_cancel(tp);
+err:
+ return error;
+}
+
+/*
+ * Read in the ondisk dquot using dqtobp() then copy it to an incore version,
+ * and release the buffer immediately. If @can_alloc is true, fill any
+ * holes in the on-disk metadata.
+ */
+static int
+xfs_qm_dqread(
+ struct xfs_mount *mp,
+ xfs_dqid_t id,
+ uint type,
+ bool can_alloc,
+ struct xfs_dquot **dqpp)
+{
+ struct xfs_dquot *dqp;
+ struct xfs_buf *bp;
+ int error;
+
+ dqp = xfs_dquot_alloc(mp, id, type);
+ trace_xfs_dqread(dqp);
+
+ /* Try to read the buffer, allocating if necessary. */
+ error = xfs_dquot_disk_read(mp, dqp, &bp);
+ if (error == -ENOENT && can_alloc)
+ error = xfs_qm_dqread_alloc(mp, dqp, &bp);
+ if (error)
+ goto err;
/*
- * We got the buffer with a xfs_trans_read_buf() (in dqtobp())
- * So we need to release with xfs_trans_brelse().
- * The strategy here is identical to that of inodes; we lock
- * the dquot in xfs_qm_dqget() before making it accessible to
- * others. This is because dquots, like inodes, need a good level of
- * concurrency, and we don't want to take locks on the entire buffers
- * for dquot accesses.
- * Note also that the dquot buffer may even be dirty at this point, if
- * this particular dquot was repaired. We still aren't afraid to
- * brelse it because we have the changes incore.
+ * At this point we should have a clean locked buffer. Copy the data
+ * to the incore dquot and release the buffer since the incore dquot
+ * has its own locking protocol so we needn't tie up the buffer any
+ * further.
*/
ASSERT(xfs_buf_islocked(bp));
- xfs_trans_brelse(tp, bp);
+ xfs_dquot_from_disk(dqp, bp);
- if (tp) {
- error = xfs_trans_commit(tp);
- if (error)
- goto error0;
- }
-
- *O_dqpp = dqp;
+ xfs_buf_relse(bp);
+ *dqpp = dqp;
return error;
-error1:
- if (tp)
- xfs_trans_cancel(tp);
-error0:
+err:
+ trace_xfs_dqread_fail(dqp);
xfs_qm_dqdestroy(dqp);
- *O_dqpp = NULL;
+ *dqpp = NULL;
return error;
}
@@ -679,77 +681,230 @@ xfs_dq_get_next_id(
}
/*
- * Given the file system, inode OR id, and type (UDQUOT/GDQUOT), return a
- * a locked dquot, doing an allocation (if requested) as needed.
- * When both an inode and an id are given, the inode's id takes precedence.
- * That is, if the id changes while we don't hold the ilock inside this
- * function, the new dquot is returned, not necessarily the one requested
- * in the id argument.
+ * Look up the dquot in the in-core cache. If found, the dquot is returned
+ * locked and ready to go.
*/
-int
-xfs_qm_dqget(
- xfs_mount_t *mp,
- xfs_inode_t *ip, /* locked inode (optional) */
- xfs_dqid_t id, /* uid/projid/gid depending on type */
- uint type, /* XFS_DQ_USER/XFS_DQ_PROJ/XFS_DQ_GROUP */
- uint flags, /* DQALLOC, DQSUSER, DQREPAIR, DOWARN */
- xfs_dquot_t **O_dqpp) /* OUT : locked incore dquot */
+static struct xfs_dquot *
+xfs_qm_dqget_cache_lookup(
+ struct xfs_mount *mp,
+ struct xfs_quotainfo *qi,
+ struct radix_tree_root *tree,
+ xfs_dqid_t id)
{
- struct xfs_quotainfo *qi = mp->m_quotainfo;
- struct radix_tree_root *tree = xfs_dquot_tree(qi, type);
struct xfs_dquot *dqp;
- int error;
-
- ASSERT(XFS_IS_QUOTA_RUNNING(mp));
- if ((! XFS_IS_UQUOTA_ON(mp) && type == XFS_DQ_USER) ||
- (! XFS_IS_PQUOTA_ON(mp) && type == XFS_DQ_PROJ) ||
- (! XFS_IS_GQUOTA_ON(mp) && type == XFS_DQ_GROUP)) {
- return -ESRCH;
- }
-
- ASSERT(type == XFS_DQ_USER ||
- type == XFS_DQ_PROJ ||
- type == XFS_DQ_GROUP);
- if (ip) {
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
- ASSERT(xfs_inode_dquot(ip, type) == NULL);
- }
restart:
mutex_lock(&qi->qi_tree_lock);
dqp = radix_tree_lookup(tree, id);
- if (dqp) {
- xfs_dqlock(dqp);
- if (dqp->dq_flags & XFS_DQ_FREEING) {
- xfs_dqunlock(dqp);
- mutex_unlock(&qi->qi_tree_lock);
- trace_xfs_dqget_freeing(dqp);
- delay(1);
- goto restart;
- }
-
- /* uninit / unused quota found in radix tree, keep looking */
- if (flags & XFS_QMOPT_DQNEXT) {
- if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
- xfs_dqunlock(dqp);
- mutex_unlock(&qi->qi_tree_lock);
- error = xfs_dq_get_next_id(mp, type, &id);
- if (error)
- return error;
- goto restart;
- }
- }
-
- dqp->q_nrefs++;
+ if (!dqp) {
mutex_unlock(&qi->qi_tree_lock);
+ XFS_STATS_INC(mp, xs_qm_dqcachemisses);
+ return NULL;
+ }
- trace_xfs_dqget_hit(dqp);
- XFS_STATS_INC(mp, xs_qm_dqcachehits);
+ xfs_dqlock(dqp);
+ if (dqp->dq_flags & XFS_DQ_FREEING) {
+ xfs_dqunlock(dqp);
+ mutex_unlock(&qi->qi_tree_lock);
+ trace_xfs_dqget_freeing(dqp);
+ delay(1);
+ goto restart;
+ }
+
+ dqp->q_nrefs++;
+ mutex_unlock(&qi->qi_tree_lock);
+
+ trace_xfs_dqget_hit(dqp);
+ XFS_STATS_INC(mp, xs_qm_dqcachehits);
+ return dqp;
+}
+
+/*
+ * Try to insert a new dquot into the in-core cache. If an error occurs the
+ * caller should throw away the dquot and start over. Otherwise, the dquot
+ * is returned locked (and held by the cache) as if there had been a cache
+ * hit.
+ */
+static int
+xfs_qm_dqget_cache_insert(
+ struct xfs_mount *mp,
+ struct xfs_quotainfo *qi,
+ struct radix_tree_root *tree,
+ xfs_dqid_t id,
+ struct xfs_dquot *dqp)
+{
+ int error;
+
+ mutex_lock(&qi->qi_tree_lock);
+ error = radix_tree_insert(tree, id, dqp);
+ if (unlikely(error)) {
+ /* Duplicate found! Caller must try again. */
+ WARN_ON(error != -EEXIST);
+ mutex_unlock(&qi->qi_tree_lock);
+ trace_xfs_dqget_dup(dqp);
+ return error;
+ }
+
+ /* Return a locked dquot to the caller, with a reference taken. */
+ xfs_dqlock(dqp);
+ dqp->q_nrefs = 1;
+
+ qi->qi_dquots++;
+ mutex_unlock(&qi->qi_tree_lock);
+
+ return 0;
+}
+
+/* Check our input parameters. */
+static int
+xfs_qm_dqget_checks(
+ struct xfs_mount *mp,
+ uint type)
+{
+ if (WARN_ON_ONCE(!XFS_IS_QUOTA_RUNNING(mp)))
+ return -ESRCH;
+
+ switch (type) {
+ case XFS_DQ_USER:
+ if (!XFS_IS_UQUOTA_ON(mp))
+ return -ESRCH;
+ return 0;
+ case XFS_DQ_GROUP:
+ if (!XFS_IS_GQUOTA_ON(mp))
+ return -ESRCH;
+ return 0;
+ case XFS_DQ_PROJ:
+ if (!XFS_IS_PQUOTA_ON(mp))
+ return -ESRCH;
+ return 0;
+ default:
+ WARN_ON_ONCE(0);
+ return -EINVAL;
+ }
+}
+
+/*
+ * Given the file system, id, and type (UDQUOT/GDQUOT), return a a locked
+ * dquot, doing an allocation (if requested) as needed.
+ */
+int
+xfs_qm_dqget(
+ struct xfs_mount *mp,
+ xfs_dqid_t id,
+ uint type,
+ bool can_alloc,
+ struct xfs_dquot **O_dqpp)
+{
+ struct xfs_quotainfo *qi = mp->m_quotainfo;
+ struct radix_tree_root *tree = xfs_dquot_tree(qi, type);
+ struct xfs_dquot *dqp;
+ int error;
+
+ error = xfs_qm_dqget_checks(mp, type);
+ if (error)
+ return error;
+
+restart:
+ dqp = xfs_qm_dqget_cache_lookup(mp, qi, tree, id);
+ if (dqp) {
*O_dqpp = dqp;
return 0;
}
- mutex_unlock(&qi->qi_tree_lock);
- XFS_STATS_INC(mp, xs_qm_dqcachemisses);
+
+ error = xfs_qm_dqread(mp, id, type, can_alloc, &dqp);
+ if (error)
+ return error;
+
+ error = xfs_qm_dqget_cache_insert(mp, qi, tree, id, dqp);
+ if (error) {
+ /*
+ * Duplicate found. Just throw away the new dquot and start
+ * over.
+ */
+ xfs_qm_dqdestroy(dqp);
+ XFS_STATS_INC(mp, xs_qm_dquot_dups);
+ goto restart;
+ }
+
+ trace_xfs_dqget_miss(dqp);
+ *O_dqpp = dqp;
+ return 0;
+}
+
+/*
+ * Given a dquot id and type, read and initialize a dquot from the on-disk
+ * metadata. This function is only for use during quota initialization so
+ * it ignores the dquot cache assuming that the dquot shrinker isn't set up.
+ * The caller is responsible for _qm_dqdestroy'ing the returned dquot.
+ */
+int
+xfs_qm_dqget_uncached(
+ struct xfs_mount *mp,
+ xfs_dqid_t id,
+ uint type,
+ struct xfs_dquot **dqpp)
+{
+ int error;
+
+ error = xfs_qm_dqget_checks(mp, type);
+ if (error)
+ return error;
+
+ return xfs_qm_dqread(mp, id, type, 0, dqpp);
+}
+
+/* Return the quota id for a given inode and type. */
+xfs_dqid_t
+xfs_qm_id_for_quotatype(
+ struct xfs_inode *ip,
+ uint type)
+{
+ switch (type) {
+ case XFS_DQ_USER:
+ return ip->i_d.di_uid;
+ case XFS_DQ_GROUP:
+ return ip->i_d.di_gid;
+ case XFS_DQ_PROJ:
+ return xfs_get_projid(ip);
+ }
+ ASSERT(0);
+ return 0;
+}
+
+/*
+ * Return the dquot for a given inode and type. If @can_alloc is true, then
+ * allocate blocks if needed. The inode's ILOCK must be held and it must not
+ * have already had an inode attached.
+ */
+int
+xfs_qm_dqget_inode(
+ struct xfs_inode *ip,
+ uint type,
+ bool can_alloc,
+ struct xfs_dquot **O_dqpp)
+{
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_quotainfo *qi = mp->m_quotainfo;
+ struct radix_tree_root *tree = xfs_dquot_tree(qi, type);
+ struct xfs_dquot *dqp;
+ xfs_dqid_t id;
+ int error;
+
+ error = xfs_qm_dqget_checks(mp, type);
+ if (error)
+ return error;
+
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+ ASSERT(xfs_inode_dquot(ip, type) == NULL);
+
+ id = xfs_qm_id_for_quotatype(ip, type);
+
+restart:
+ dqp = xfs_qm_dqget_cache_lookup(mp, qi, tree, id);
+ if (dqp) {
+ *O_dqpp = dqp;
+ return 0;
+ }
/*
* Dquot cache miss. We don't want to keep the inode lock across
@@ -758,90 +913,84 @@ xfs_qm_dqget(
* lock here means dealing with a chown that can happen before
* we re-acquire the lock.
*/
- if (ip)
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
- error = xfs_qm_dqread(mp, id, type, flags, &dqp);
-
- if (ip)
- xfs_ilock(ip, XFS_ILOCK_EXCL);
-
- /* If we are asked to find next active id, keep looking */
- if (error == -ENOENT && (flags & XFS_QMOPT_DQNEXT)) {
- error = xfs_dq_get_next_id(mp, type, &id);
- if (!error)
- goto restart;
- }
-
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ error = xfs_qm_dqread(mp, id, type, can_alloc, &dqp);
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
if (error)
return error;
- if (ip) {
- /*
- * A dquot could be attached to this inode by now, since
- * we had dropped the ilock.
- */
- if (xfs_this_quota_on(mp, type)) {
- struct xfs_dquot *dqp1;
+ /*
+ * A dquot could be attached to this inode by now, since we had
+ * dropped the ilock.
+ */
+ if (xfs_this_quota_on(mp, type)) {
+ struct xfs_dquot *dqp1;
- dqp1 = xfs_inode_dquot(ip, type);
- if (dqp1) {
- xfs_qm_dqdestroy(dqp);
- dqp = dqp1;
- xfs_dqlock(dqp);
- goto dqret;
- }
- } else {
- /* inode stays locked on return */
+ dqp1 = xfs_inode_dquot(ip, type);
+ if (dqp1) {
xfs_qm_dqdestroy(dqp);
- return -ESRCH;
+ dqp = dqp1;
+ xfs_dqlock(dqp);
+ goto dqret;
}
+ } else {
+ /* inode stays locked on return */
+ xfs_qm_dqdestroy(dqp);
+ return -ESRCH;
}
- mutex_lock(&qi->qi_tree_lock);
- error = radix_tree_insert(tree, id, dqp);
- if (unlikely(error)) {
- WARN_ON(error != -EEXIST);
-
+ error = xfs_qm_dqget_cache_insert(mp, qi, tree, id, dqp);
+ if (error) {
/*
* Duplicate found. Just throw away the new dquot and start
* over.
*/
- mutex_unlock(&qi->qi_tree_lock);
- trace_xfs_dqget_dup(dqp);
xfs_qm_dqdestroy(dqp);
XFS_STATS_INC(mp, xs_qm_dquot_dups);
goto restart;
}
- /*
- * We return a locked dquot to the caller, with a reference taken
- */
- xfs_dqlock(dqp);
- dqp->q_nrefs = 1;
-
- qi->qi_dquots++;
- mutex_unlock(&qi->qi_tree_lock);
-
- /* If we are asked to find next active id, keep looking */
- if (flags & XFS_QMOPT_DQNEXT) {
- if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
- xfs_qm_dqput(dqp);
- error = xfs_dq_get_next_id(mp, type, &id);
- if (error)
- return error;
- goto restart;
- }
- }
-
- dqret:
- ASSERT((ip == NULL) || xfs_isilocked(ip, XFS_ILOCK_EXCL));
+dqret:
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
trace_xfs_dqget_miss(dqp);
*O_dqpp = dqp;
return 0;
}
/*
+ * Starting at @id and progressing upwards, look for an initialized incore
+ * dquot, lock it, and return it.
+ */
+int
+xfs_qm_dqget_next(
+ struct xfs_mount *mp,
+ xfs_dqid_t id,
+ uint type,
+ struct xfs_dquot **dqpp)
+{
+ struct xfs_dquot *dqp;
+ int error = 0;
+
+ *dqpp = NULL;
+ for (; !error; error = xfs_dq_get_next_id(mp, type, &id)) {
+ error = xfs_qm_dqget(mp, id, type, false, &dqp);
+ if (error == -ENOENT)
+ continue;
+ else if (error != 0)
+ break;
+
+ if (!XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
+ *dqpp = dqp;
+ return 0;
+ }
+
+ xfs_qm_dqput(dqp);
+ }
+
+ return error;
+}
+
+/*
* Release a reference to the dquot (decrement ref-count) and unlock it.
*
* If there is a group quota attached to this dquot, carefully release that
@@ -913,9 +1062,9 @@ xfs_qm_dqflush_done(
* since it's cheaper, and then we recheck while
* holding the lock before removing the dquot from the AIL.
*/
- if ((lip->li_flags & XFS_LI_IN_AIL) &&
+ if (test_bit(XFS_LI_IN_AIL, &lip->li_flags) &&
((lip->li_lsn == qip->qli_flush_lsn) ||
- (lip->li_flags & XFS_LI_FAILED))) {
+ test_bit(XFS_LI_FAILED, &lip->li_flags))) {
/* xfs_trans_ail_delete() drops the AIL lock. */
spin_lock(&ailp->ail_lock);
@@ -926,8 +1075,7 @@ xfs_qm_dqflush_done(
* Clear the failed state since we are about to drop the
* flush lock
*/
- if (lip->li_flags & XFS_LI_FAILED)
- xfs_clear_li_failed(lip);
+ xfs_clear_li_failed(lip);
spin_unlock(&ailp->ail_lock);
}
}
@@ -953,6 +1101,7 @@ xfs_qm_dqflush(
{
struct xfs_mount *mp = dqp->q_mount;
struct xfs_buf *bp;
+ struct xfs_dqblk *dqb;
struct xfs_disk_dquot *ddqp;
xfs_failaddr_t fa;
int error;
@@ -996,12 +1145,13 @@ xfs_qm_dqflush(
/*
* Calculate the location of the dquot inside the buffer.
*/
- ddqp = bp->b_addr + dqp->q_bufoffset;
+ dqb = bp->b_addr + dqp->q_bufoffset;
+ ddqp = &dqb->dd_diskdq;
/*
- * A simple sanity check in case we got a corrupted dquot..
+ * A simple sanity check in case we got a corrupted dquot.
*/
- fa = xfs_dquot_verify(mp, &dqp->q_core, be32_to_cpu(ddqp->d_id), 0, 0);
+ fa = xfs_dqblk_verify(mp, dqb, be32_to_cpu(ddqp->d_id), 0);
if (fa) {
xfs_alert(mp, "corrupt dquot ID 0x%x in memory at %pS",
be32_to_cpu(ddqp->d_id), fa);
@@ -1032,8 +1182,6 @@ xfs_qm_dqflush(
* of a dquot without an up-to-date CRC getting to disk.
*/
if (xfs_sb_version_hascrc(&mp->m_sb)) {
- struct xfs_dqblk *dqb = (struct xfs_dqblk *)ddqp;
-
dqb->dd_lsn = cpu_to_be64(dqp->q_logitem.qli_item.li_lsn);
xfs_update_cksum((char *)dqb, sizeof(struct xfs_dqblk),
XFS_DQUOT_CRC_OFF);
@@ -1119,3 +1267,35 @@ xfs_qm_exit(void)
kmem_zone_destroy(xfs_qm_dqtrxzone);
kmem_zone_destroy(xfs_qm_dqzone);
}
+
+/*
+ * Iterate every dquot of a particular type. The caller must ensure that the
+ * particular quota type is active. iter_fn can return negative error codes,
+ * or XFS_BTREE_QUERY_RANGE_ABORT to indicate that it wants to stop iterating.
+ */
+int
+xfs_qm_dqiterate(
+ struct xfs_mount *mp,
+ uint dqtype,
+ xfs_qm_dqiterate_fn iter_fn,
+ void *priv)
+{
+ struct xfs_dquot *dq;
+ xfs_dqid_t id = 0;
+ int error;
+
+ do {
+ error = xfs_qm_dqget_next(mp, id, dqtype, &dq);
+ if (error == -ENOENT)
+ return 0;
+ if (error)
+ return error;
+
+ error = iter_fn(dq, dqtype, priv);
+ id = be32_to_cpu(dq->q_core.d_id);
+ xfs_qm_dqput(dq);
+ id++;
+ } while (error == 0 && id != 0);
+
+ return error;
+}
diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h
index 2f536f3..bdd6bd9 100644
--- a/fs/xfs/xfs_dquot.h
+++ b/fs/xfs/xfs_dquot.h
@@ -160,8 +160,6 @@ static inline bool xfs_dquot_lowsp(struct xfs_dquot *dqp)
#define XFS_QM_ISPDQ(dqp) ((dqp)->dq_flags & XFS_DQ_PROJ)
#define XFS_QM_ISGDQ(dqp) ((dqp)->dq_flags & XFS_DQ_GROUP)
-extern int xfs_qm_dqread(struct xfs_mount *, xfs_dqid_t, uint,
- uint, struct xfs_dquot **);
extern void xfs_qm_dqdestroy(xfs_dquot_t *);
extern int xfs_qm_dqflush(struct xfs_dquot *, struct xfs_buf **);
extern void xfs_qm_dqunpin_wait(xfs_dquot_t *);
@@ -169,8 +167,19 @@ extern void xfs_qm_adjust_dqtimers(xfs_mount_t *,
xfs_disk_dquot_t *);
extern void xfs_qm_adjust_dqlimits(struct xfs_mount *,
struct xfs_dquot *);
-extern int xfs_qm_dqget(xfs_mount_t *, xfs_inode_t *,
- xfs_dqid_t, uint, uint, xfs_dquot_t **);
+extern xfs_dqid_t xfs_qm_id_for_quotatype(struct xfs_inode *ip,
+ uint type);
+extern int xfs_qm_dqget(struct xfs_mount *mp, xfs_dqid_t id,
+ uint type, bool can_alloc,
+ struct xfs_dquot **dqpp);
+extern int xfs_qm_dqget_inode(struct xfs_inode *ip, uint type,
+ bool can_alloc,
+ struct xfs_dquot **dqpp);
+extern int xfs_qm_dqget_next(struct xfs_mount *mp, xfs_dqid_t id,
+ uint type, struct xfs_dquot **dqpp);
+extern int xfs_qm_dqget_uncached(struct xfs_mount *mp,
+ xfs_dqid_t id, uint type,
+ struct xfs_dquot **dqpp);
extern void xfs_qm_dqput(xfs_dquot_t *);
extern void xfs_dqlock2(struct xfs_dquot *, struct xfs_dquot *);
@@ -185,4 +194,9 @@ static inline struct xfs_dquot *xfs_qm_dqhold(struct xfs_dquot *dqp)
return dqp;
}
+typedef int (*xfs_qm_dqiterate_fn)(struct xfs_dquot *dq, uint dqtype,
+ void *priv);
+int xfs_qm_dqiterate(struct xfs_mount *mp, uint dqtype,
+ xfs_qm_dqiterate_fn iter_fn, void *priv);
+
#endif /* __XFS_DQUOT_H__ */
diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c
index 4b331e3..8eb7415 100644
--- a/fs/xfs/xfs_dquot_item.c
+++ b/fs/xfs/xfs_dquot_item.c
@@ -173,7 +173,7 @@ xfs_qm_dquot_logitem_push(
* The buffer containing this item failed to be written back
* previously. Resubmit the buffer for IO
*/
- if (lip->li_flags & XFS_LI_FAILED) {
+ if (test_bit(XFS_LI_FAILED, &lip->li_flags)) {
if (!xfs_buf_trylock(bp))
return XFS_ITEM_LOCKED;
@@ -209,10 +209,7 @@ xfs_qm_dquot_logitem_push(
spin_unlock(&lip->li_ailp->ail_lock);
error = xfs_qm_dqflush(dqp, &bp);
- if (error) {
- xfs_warn(dqp->q_mount, "%s: push error %d on dqp "PTR_FMT,
- __func__, error, dqp);
- } else {
+ if (!error) {
if (!xfs_buf_delwri_queue(bp, buffer_list))
rval = XFS_ITEM_FLUSHING;
xfs_buf_relse(bp);
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index a63f508..7975634 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -61,6 +61,7 @@ static unsigned int xfs_errortag_random_default[] = {
XFS_RANDOM_LOG_BAD_CRC,
XFS_RANDOM_LOG_ITEM_PIN,
XFS_RANDOM_BUF_LRU_REF,
+ XFS_RANDOM_FORCE_SCRUB_REPAIR,
};
struct xfs_errortag_attr {
@@ -167,6 +168,7 @@ XFS_ERRORTAG_ATTR_RW(drop_writes, XFS_ERRTAG_DROP_WRITES);
XFS_ERRORTAG_ATTR_RW(log_bad_crc, XFS_ERRTAG_LOG_BAD_CRC);
XFS_ERRORTAG_ATTR_RW(log_item_pin, XFS_ERRTAG_LOG_ITEM_PIN);
XFS_ERRORTAG_ATTR_RW(buf_lru_ref, XFS_ERRTAG_BUF_LRU_REF);
+XFS_ERRORTAG_ATTR_RW(force_repair, XFS_ERRTAG_FORCE_SCRUB_REPAIR);
static struct attribute *xfs_errortag_attrs[] = {
XFS_ERRORTAG_ATTR_LIST(noerror),
@@ -201,6 +203,7 @@ static struct attribute *xfs_errortag_attrs[] = {
XFS_ERRORTAG_ATTR_LIST(log_bad_crc),
XFS_ERRORTAG_ATTR_LIST(log_item_pin),
XFS_ERRORTAG_ATTR_LIST(buf_lru_ref),
+ XFS_ERRORTAG_ATTR_LIST(force_repair),
NULL,
};
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index b5b1e56..a889b55 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -168,7 +168,7 @@ STATIC void
xfs_efi_item_unlock(
struct xfs_log_item *lip)
{
- if (lip->li_flags & XFS_LI_ABORTED)
+ if (test_bit(XFS_LI_ABORTED, &lip->li_flags))
xfs_efi_release(EFI_ITEM(lip));
}
@@ -402,7 +402,7 @@ xfs_efd_item_unlock(
{
struct xfs_efd_log_item *efdp = EFD_ITEM(lip);
- if (lip->li_flags & XFS_LI_ABORTED) {
+ if (test_bit(XFS_LI_ABORTED, &lip->li_flags)) {
xfs_efi_release(efdp->efd_efip);
xfs_efd_item_free(efdp);
}
@@ -542,7 +542,7 @@ xfs_efi_recover(
for (i = 0; i < efip->efi_format.efi_nextents; i++) {
extp = &efip->efi_format.efi_extents[i];
error = xfs_trans_free_extent(tp, efdp, extp->ext_start,
- extp->ext_len, &oinfo);
+ extp->ext_len, &oinfo, false);
if (error)
goto abort_error;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 299aee4..0e3fb89 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -414,6 +414,12 @@ xfs_dio_write_end_io(
if (size <= 0)
return size;
+ /*
+ * Capture amount written on completion as we can't reliably account
+ * for it on submission.
+ */
+ XFS_STATS_ADD(ip->i_mount, xs_write_bytes, size);
+
if (flags & IOMAP_DIO_COW) {
error = xfs_reflink_end_cow(ip, offset, size);
if (error)
@@ -599,7 +605,16 @@ xfs_file_dax_write(
}
out:
xfs_iunlock(ip, iolock);
- return error ? error : ret;
+ if (error)
+ return error;
+
+ if (ret > 0) {
+ XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret);
+
+ /* Handle various SYNC-type writes */
+ ret = generic_write_sync(iocb, ret);
+ }
+ return ret;
}
STATIC ssize_t
@@ -669,6 +684,12 @@ xfs_file_buffered_aio_write(
out:
if (iolock)
xfs_iunlock(ip, iolock);
+
+ if (ret > 0) {
+ XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret);
+ /* Handle various SYNC-type writes */
+ ret = generic_write_sync(iocb, ret);
+ }
return ret;
}
@@ -693,8 +714,9 @@ xfs_file_write_iter(
return -EIO;
if (IS_DAX(inode))
- ret = xfs_file_dax_write(iocb, from);
- else if (iocb->ki_flags & IOCB_DIRECT) {
+ return xfs_file_dax_write(iocb, from);
+
+ if (iocb->ki_flags & IOCB_DIRECT) {
/*
* Allow a directio write to fall back to a buffered
* write *only* in the case that we're doing a reflink
@@ -702,20 +724,11 @@ xfs_file_write_iter(
* allow an operation to fall back to buffered mode.
*/
ret = xfs_file_dio_aio_write(iocb, from);
- if (ret == -EREMCHG)
- goto buffered;
- } else {
-buffered:
- ret = xfs_file_buffered_aio_write(iocb, from);
+ if (ret != -EREMCHG)
+ return ret;
}
- if (ret > 0) {
- XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret);
-
- /* Handle various SYNC-type writes */
- ret = generic_write_sync(iocb, ret);
- }
- return ret;
+ return xfs_file_buffered_aio_write(iocb, from);
}
#define XFS_FALLOC_FL_SUPPORTED \
@@ -778,22 +791,26 @@ xfs_file_fallocate(
if (error)
goto out_unlock;
} else if (mode & FALLOC_FL_INSERT_RANGE) {
- unsigned int blksize_mask = i_blocksize(inode) - 1;
+ unsigned int blksize_mask = i_blocksize(inode) - 1;
+ loff_t isize = i_size_read(inode);
- new_size = i_size_read(inode) + len;
if (offset & blksize_mask || len & blksize_mask) {
error = -EINVAL;
goto out_unlock;
}
- /* check the new inode size does not wrap through zero */
- if (new_size > inode->i_sb->s_maxbytes) {
+ /*
+ * New inode size must not exceed ->s_maxbytes, accounting for
+ * possible signed overflow.
+ */
+ if (inode->i_sb->s_maxbytes - isize < len) {
error = -EFBIG;
goto out_unlock;
}
+ new_size = isize + len;
/* Offset should be less than i_size */
- if (offset >= i_size_read(inode)) {
+ if (offset >= isize) {
error = -EINVAL;
goto out_unlock;
}
@@ -876,8 +893,18 @@ xfs_file_dedupe_range(
struct file *dst_file,
u64 dst_loff)
{
+ struct inode *srci = file_inode(src_file);
+ u64 max_dedupe;
int error;
+ /*
+ * Since we have to read all these pages in to compare them, cut
+ * it off at MAX_RW_COUNT/2 rounded down to the nearest block.
+ * That means we won't do more than MAX_RW_COUNT IO per request.
+ */
+ max_dedupe = (MAX_RW_COUNT >> 1) & ~(i_blocksize(srci) - 1);
+ if (len > max_dedupe)
+ len = max_dedupe;
error = xfs_reflink_remap_range(src_file, loff, dst_file, dst_loff,
len, true);
if (error)
@@ -993,7 +1020,7 @@ xfs_file_llseek(
* page_lock (MM)
* i_lock (XFS - extent map serialisation)
*/
-static int
+static vm_fault_t
__xfs_filemap_fault(
struct vm_fault *vmf,
enum page_entry_size pe_size,
@@ -1001,7 +1028,7 @@ __xfs_filemap_fault(
{
struct inode *inode = file_inode(vmf->vma->vm_file);
struct xfs_inode *ip = XFS_I(inode);
- int ret;
+ vm_fault_t ret;
trace_xfs_filemap_fault(ip, pe_size, write_fault);
@@ -1030,7 +1057,7 @@ __xfs_filemap_fault(
return ret;
}
-static int
+static vm_fault_t
xfs_filemap_fault(
struct vm_fault *vmf)
{
@@ -1040,7 +1067,7 @@ xfs_filemap_fault(
(vmf->flags & FAULT_FLAG_WRITE));
}
-static int
+static vm_fault_t
xfs_filemap_huge_fault(
struct vm_fault *vmf,
enum page_entry_size pe_size)
@@ -1053,7 +1080,7 @@ xfs_filemap_huge_fault(
(vmf->flags & FAULT_FLAG_WRITE));
}
-static int
+static vm_fault_t
xfs_filemap_page_mkwrite(
struct vm_fault *vmf)
{
@@ -1065,7 +1092,7 @@ xfs_filemap_page_mkwrite(
* on write faults. In reality, it needs to serialise against truncate and
* prepare memory for writing so handle is as standard write fault.
*/
-static int
+static vm_fault_t
xfs_filemap_pfn_mkwrite(
struct vm_fault *vmf)
{
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 43cfc07..0299feb 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -465,10 +465,9 @@ xfs_getfsmap_rtdev_rtbitmap_helper(
struct xfs_rmap_irec irec;
xfs_daddr_t rec_daddr;
- rec_daddr = XFS_FSB_TO_BB(mp, rec->ar_startblock);
-
- irec.rm_startblock = rec->ar_startblock;
- irec.rm_blockcount = rec->ar_blockcount;
+ irec.rm_startblock = rec->ar_startext * mp->m_sb.sb_rextsize;
+ rec_daddr = XFS_FSB_TO_BB(mp, irec.rm_startblock);
+ irec.rm_blockcount = rec->ar_extcount * mp->m_sb.sb_rextsize;
irec.rm_owner = XFS_RMAP_OWN_NULL; /* "free" */
irec.rm_offset = 0;
irec.rm_flags = 0;
@@ -534,8 +533,11 @@ xfs_getfsmap_rtdev_rtbitmap_query(
xfs_ilock(tp->t_mountp->m_rbmip, XFS_ILOCK_SHARED);
- alow.ar_startblock = info->low.rm_startblock;
- ahigh.ar_startblock = info->high.rm_startblock;
+ alow.ar_startext = info->low.rm_startblock;
+ ahigh.ar_startext = info->high.rm_startblock;
+ do_div(alow.ar_startext, tp->t_mountp->m_sb.sb_rextsize);
+ if (do_div(ahigh.ar_startext, tp->t_mountp->m_sb.sb_rextsize))
+ ahigh.ar_startext++;
error = xfs_rtalloc_query_range(tp, &alow, &ahigh,
xfs_getfsmap_rtdev_rtbitmap_helper, info);
if (error)
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 5237927..bc7ef18 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -24,85 +24,42 @@
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
-#include "xfs_da_format.h"
-#include "xfs_da_btree.h"
-#include "xfs_inode.h"
#include "xfs_trans.h"
-#include "xfs_inode_item.h"
#include "xfs_error.h"
#include "xfs_btree.h"
-#include "xfs_alloc_btree.h"
#include "xfs_alloc.h"
-#include "xfs_rmap_btree.h"
-#include "xfs_ialloc.h"
#include "xfs_fsops.h"
-#include "xfs_itable.h"
#include "xfs_trans_space.h"
#include "xfs_rtalloc.h"
#include "xfs_trace.h"
#include "xfs_log.h"
-#include "xfs_filestream.h"
-#include "xfs_rmap.h"
+#include "xfs_ag.h"
#include "xfs_ag_resv.h"
/*
- * File system operations
+ * growfs operations
*/
-
-static struct xfs_buf *
-xfs_growfs_get_hdr_buf(
- struct xfs_mount *mp,
- xfs_daddr_t blkno,
- size_t numblks,
- int flags,
- const struct xfs_buf_ops *ops)
-{
- struct xfs_buf *bp;
-
- bp = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, flags);
- if (!bp)
- return NULL;
-
- xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
- bp->b_bn = blkno;
- bp->b_maps[0].bm_bn = blkno;
- bp->b_ops = ops;
-
- return bp;
-}
-
static int
xfs_growfs_data_private(
xfs_mount_t *mp, /* mount point for filesystem */
xfs_growfs_data_t *in) /* growfs data input struct */
{
- xfs_agf_t *agf;
- struct xfs_agfl *agfl;
- xfs_agi_t *agi;
- xfs_agnumber_t agno;
- xfs_extlen_t agsize;
- xfs_extlen_t tmpsize;
- xfs_alloc_rec_t *arec;
xfs_buf_t *bp;
- int bucket;
- int dpct;
- int error, saved_error = 0;
+ int error;
xfs_agnumber_t nagcount;
xfs_agnumber_t nagimax = 0;
xfs_rfsblock_t nb, nb_mod;
xfs_rfsblock_t new;
- xfs_rfsblock_t nfree;
xfs_agnumber_t oagcount;
- int pct;
xfs_trans_t *tp;
+ LIST_HEAD (buffer_list);
+ struct aghdr_init_data id = {};
nb = in->newblocks;
- pct = in->imaxpct;
- if (nb < mp->m_sb.sb_dblocks || pct < 0 || pct > 100)
+ if (nb < mp->m_sb.sb_dblocks)
return -EINVAL;
if ((error = xfs_sb_validate_fsb_count(&mp->m_sb, nb)))
return error;
- dpct = pct - mp->m_sb.sb_imax_pct;
error = xfs_buf_read_uncached(mp->m_ddev_targp,
XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1),
XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
@@ -135,376 +92,45 @@ xfs_growfs_data_private(
return error;
/*
- * Write new AG headers to disk. Non-transactional, but written
- * synchronously so they are completed prior to the growfs transaction
- * being logged.
+ * Write new AG headers to disk. Non-transactional, but need to be
+ * written and completed prior to the growfs transaction being logged.
+ * To do this, we use a delayed write buffer list and wait for
+ * submission and IO completion of the list as a whole. This allows the
+ * IO subsystem to merge all the AG headers in a single AG into a single
+ * IO and hide most of the latency of the IO from us.
+ *
+ * This also means that if we get an error whilst building the buffer
+ * list to write, we can cancel the entire list without having written
+ * anything.
*/
- nfree = 0;
- for (agno = nagcount - 1; agno >= oagcount; agno--, new -= agsize) {
- __be32 *agfl_bno;
+ INIT_LIST_HEAD(&id.buffer_list);
+ for (id.agno = nagcount - 1;
+ id.agno >= oagcount;
+ id.agno--, new -= id.agsize) {
- /*
- * AG freespace header block
- */
- bp = xfs_growfs_get_hdr_buf(mp,
- XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)),
- XFS_FSS_TO_BB(mp, 1), 0,
- &xfs_agf_buf_ops);
- if (!bp) {
- error = -ENOMEM;
- goto error0;
- }
-
- agf = XFS_BUF_TO_AGF(bp);
- agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC);
- agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION);
- agf->agf_seqno = cpu_to_be32(agno);
- if (agno == nagcount - 1)
- agsize =
- nb -
- (agno * (xfs_rfsblock_t)mp->m_sb.sb_agblocks);
+ if (id.agno == nagcount - 1)
+ id.agsize = nb -
+ (id.agno * (xfs_rfsblock_t)mp->m_sb.sb_agblocks);
else
- agsize = mp->m_sb.sb_agblocks;
- agf->agf_length = cpu_to_be32(agsize);
- agf->agf_roots[XFS_BTNUM_BNOi] = cpu_to_be32(XFS_BNO_BLOCK(mp));
- agf->agf_roots[XFS_BTNUM_CNTi] = cpu_to_be32(XFS_CNT_BLOCK(mp));
- agf->agf_levels[XFS_BTNUM_BNOi] = cpu_to_be32(1);
- agf->agf_levels[XFS_BTNUM_CNTi] = cpu_to_be32(1);
- if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
- agf->agf_roots[XFS_BTNUM_RMAPi] =
- cpu_to_be32(XFS_RMAP_BLOCK(mp));
- agf->agf_levels[XFS_BTNUM_RMAPi] = cpu_to_be32(1);
- agf->agf_rmap_blocks = cpu_to_be32(1);
- }
+ id.agsize = mp->m_sb.sb_agblocks;
- agf->agf_flfirst = cpu_to_be32(1);
- agf->agf_fllast = 0;
- agf->agf_flcount = 0;
- tmpsize = agsize - mp->m_ag_prealloc_blocks;
- agf->agf_freeblks = cpu_to_be32(tmpsize);
- agf->agf_longest = cpu_to_be32(tmpsize);
- if (xfs_sb_version_hascrc(&mp->m_sb))
- uuid_copy(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid);
- if (xfs_sb_version_hasreflink(&mp->m_sb)) {
- agf->agf_refcount_root = cpu_to_be32(
- xfs_refc_block(mp));
- agf->agf_refcount_level = cpu_to_be32(1);
- agf->agf_refcount_blocks = cpu_to_be32(1);
- }
-
- error = xfs_bwrite(bp);
- xfs_buf_relse(bp);
- if (error)
- goto error0;
-
- /*
- * AG freelist header block
- */
- bp = xfs_growfs_get_hdr_buf(mp,
- XFS_AG_DADDR(mp, agno, XFS_AGFL_DADDR(mp)),
- XFS_FSS_TO_BB(mp, 1), 0,
- &xfs_agfl_buf_ops);
- if (!bp) {
- error = -ENOMEM;
- goto error0;
- }
-
- agfl = XFS_BUF_TO_AGFL(bp);
- if (xfs_sb_version_hascrc(&mp->m_sb)) {
- agfl->agfl_magicnum = cpu_to_be32(XFS_AGFL_MAGIC);
- agfl->agfl_seqno = cpu_to_be32(agno);
- uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid);
- }
-
- agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, bp);
- for (bucket = 0; bucket < xfs_agfl_size(mp); bucket++)
- agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK);
-
- error = xfs_bwrite(bp);
- xfs_buf_relse(bp);
- if (error)
- goto error0;
-
- /*
- * AG inode header block
- */
- bp = xfs_growfs_get_hdr_buf(mp,
- XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
- XFS_FSS_TO_BB(mp, 1), 0,
- &xfs_agi_buf_ops);
- if (!bp) {
- error = -ENOMEM;
- goto error0;
- }
-
- agi = XFS_BUF_TO_AGI(bp);
- agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC);
- agi->agi_versionnum = cpu_to_be32(XFS_AGI_VERSION);
- agi->agi_seqno = cpu_to_be32(agno);
- agi->agi_length = cpu_to_be32(agsize);
- agi->agi_count = 0;
- agi->agi_root = cpu_to_be32(XFS_IBT_BLOCK(mp));
- agi->agi_level = cpu_to_be32(1);
- agi->agi_freecount = 0;
- agi->agi_newino = cpu_to_be32(NULLAGINO);
- agi->agi_dirino = cpu_to_be32(NULLAGINO);
- if (xfs_sb_version_hascrc(&mp->m_sb))
- uuid_copy(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid);
- if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
- agi->agi_free_root = cpu_to_be32(XFS_FIBT_BLOCK(mp));
- agi->agi_free_level = cpu_to_be32(1);
- }
- for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++)
- agi->agi_unlinked[bucket] = cpu_to_be32(NULLAGINO);
-
- error = xfs_bwrite(bp);
- xfs_buf_relse(bp);
- if (error)
- goto error0;
-
- /*
- * BNO btree root block
- */
- bp = xfs_growfs_get_hdr_buf(mp,
- XFS_AGB_TO_DADDR(mp, agno, XFS_BNO_BLOCK(mp)),
- BTOBB(mp->m_sb.sb_blocksize), 0,
- &xfs_allocbt_buf_ops);
-
- if (!bp) {
- error = -ENOMEM;
- goto error0;
- }
-
- xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 1, agno, 0);
-
- arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
- arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks);
- arec->ar_blockcount = cpu_to_be32(
- agsize - be32_to_cpu(arec->ar_startblock));
-
- error = xfs_bwrite(bp);
- xfs_buf_relse(bp);
- if (error)
- goto error0;
-
- /*
- * CNT btree root block
- */
- bp = xfs_growfs_get_hdr_buf(mp,
- XFS_AGB_TO_DADDR(mp, agno, XFS_CNT_BLOCK(mp)),
- BTOBB(mp->m_sb.sb_blocksize), 0,
- &xfs_allocbt_buf_ops);
- if (!bp) {
- error = -ENOMEM;
- goto error0;
- }
-
- xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 1, agno, 0);
-
- arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
- arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks);
- arec->ar_blockcount = cpu_to_be32(
- agsize - be32_to_cpu(arec->ar_startblock));
- nfree += be32_to_cpu(arec->ar_blockcount);
-
- error = xfs_bwrite(bp);
- xfs_buf_relse(bp);
- if (error)
- goto error0;
-
- /* RMAP btree root block */
- if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
- struct xfs_rmap_rec *rrec;
- struct xfs_btree_block *block;
-
- bp = xfs_growfs_get_hdr_buf(mp,
- XFS_AGB_TO_DADDR(mp, agno, XFS_RMAP_BLOCK(mp)),
- BTOBB(mp->m_sb.sb_blocksize), 0,
- &xfs_rmapbt_buf_ops);
- if (!bp) {
- error = -ENOMEM;
- goto error0;
- }
-
- xfs_btree_init_block(mp, bp, XFS_BTNUM_RMAP, 0, 0,
- agno, 0);
- block = XFS_BUF_TO_BLOCK(bp);
-
-
- /*
- * mark the AG header regions as static metadata The BNO
- * btree block is the first block after the headers, so
- * it's location defines the size of region the static
- * metadata consumes.
- *
- * Note: unlike mkfs, we never have to account for log
- * space when growing the data regions
- */
- rrec = XFS_RMAP_REC_ADDR(block, 1);
- rrec->rm_startblock = 0;
- rrec->rm_blockcount = cpu_to_be32(XFS_BNO_BLOCK(mp));
- rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_FS);
- rrec->rm_offset = 0;
- be16_add_cpu(&block->bb_numrecs, 1);
-
- /* account freespace btree root blocks */
- rrec = XFS_RMAP_REC_ADDR(block, 2);
- rrec->rm_startblock = cpu_to_be32(XFS_BNO_BLOCK(mp));
- rrec->rm_blockcount = cpu_to_be32(2);
- rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_AG);
- rrec->rm_offset = 0;
- be16_add_cpu(&block->bb_numrecs, 1);
-
- /* account inode btree root blocks */
- rrec = XFS_RMAP_REC_ADDR(block, 3);
- rrec->rm_startblock = cpu_to_be32(XFS_IBT_BLOCK(mp));
- rrec->rm_blockcount = cpu_to_be32(XFS_RMAP_BLOCK(mp) -
- XFS_IBT_BLOCK(mp));
- rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_INOBT);
- rrec->rm_offset = 0;
- be16_add_cpu(&block->bb_numrecs, 1);
-
- /* account for rmap btree root */
- rrec = XFS_RMAP_REC_ADDR(block, 4);
- rrec->rm_startblock = cpu_to_be32(XFS_RMAP_BLOCK(mp));
- rrec->rm_blockcount = cpu_to_be32(1);
- rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_AG);
- rrec->rm_offset = 0;
- be16_add_cpu(&block->bb_numrecs, 1);
-
- /* account for refc btree root */
- if (xfs_sb_version_hasreflink(&mp->m_sb)) {
- rrec = XFS_RMAP_REC_ADDR(block, 5);
- rrec->rm_startblock = cpu_to_be32(
- xfs_refc_block(mp));
- rrec->rm_blockcount = cpu_to_be32(1);
- rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_REFC);
- rrec->rm_offset = 0;
- be16_add_cpu(&block->bb_numrecs, 1);
- }
-
- error = xfs_bwrite(bp);
- xfs_buf_relse(bp);
- if (error)
- goto error0;
- }
-
- /*
- * INO btree root block
- */
- bp = xfs_growfs_get_hdr_buf(mp,
- XFS_AGB_TO_DADDR(mp, agno, XFS_IBT_BLOCK(mp)),
- BTOBB(mp->m_sb.sb_blocksize), 0,
- &xfs_inobt_buf_ops);
- if (!bp) {
- error = -ENOMEM;
- goto error0;
- }
-
- xfs_btree_init_block(mp, bp, XFS_BTNUM_INO , 0, 0, agno, 0);
-
- error = xfs_bwrite(bp);
- xfs_buf_relse(bp);
- if (error)
- goto error0;
-
- /*
- * FINO btree root block
- */
- if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
- bp = xfs_growfs_get_hdr_buf(mp,
- XFS_AGB_TO_DADDR(mp, agno, XFS_FIBT_BLOCK(mp)),
- BTOBB(mp->m_sb.sb_blocksize), 0,
- &xfs_inobt_buf_ops);
- if (!bp) {
- error = -ENOMEM;
- goto error0;
- }
-
- xfs_btree_init_block(mp, bp, XFS_BTNUM_FINO,
- 0, 0, agno, 0);
-
- error = xfs_bwrite(bp);
- xfs_buf_relse(bp);
- if (error)
- goto error0;
- }
-
- /*
- * refcount btree root block
- */
- if (xfs_sb_version_hasreflink(&mp->m_sb)) {
- bp = xfs_growfs_get_hdr_buf(mp,
- XFS_AGB_TO_DADDR(mp, agno, xfs_refc_block(mp)),
- BTOBB(mp->m_sb.sb_blocksize), 0,
- &xfs_refcountbt_buf_ops);
- if (!bp) {
- error = -ENOMEM;
- goto error0;
- }
-
- xfs_btree_init_block(mp, bp, XFS_BTNUM_REFC,
- 0, 0, agno, 0);
-
- error = xfs_bwrite(bp);
- xfs_buf_relse(bp);
- if (error)
- goto error0;
+ error = xfs_ag_init_headers(mp, &id);
+ if (error) {
+ xfs_buf_delwri_cancel(&id.buffer_list);
+ goto out_trans_cancel;
}
}
- xfs_trans_agblocks_delta(tp, nfree);
- /*
- * There are new blocks in the old last a.g.
- */
+ error = xfs_buf_delwri_submit(&id.buffer_list);
+ if (error)
+ goto out_trans_cancel;
+
+ xfs_trans_agblocks_delta(tp, id.nfree);
+
+ /* If there are new blocks in the old last AG, extend it. */
if (new) {
- struct xfs_owner_info oinfo;
-
- /*
- * Change the agi length.
- */
- error = xfs_ialloc_read_agi(mp, tp, agno, &bp);
- if (error) {
- goto error0;
- }
- ASSERT(bp);
- agi = XFS_BUF_TO_AGI(bp);
- be32_add_cpu(&agi->agi_length, new);
- ASSERT(nagcount == oagcount ||
- be32_to_cpu(agi->agi_length) == mp->m_sb.sb_agblocks);
- xfs_ialloc_log_agi(tp, bp, XFS_AGI_LENGTH);
- /*
- * Change agf length.
- */
- error = xfs_alloc_read_agf(mp, tp, agno, 0, &bp);
- if (error) {
- goto error0;
- }
- ASSERT(bp);
- agf = XFS_BUF_TO_AGF(bp);
- be32_add_cpu(&agf->agf_length, new);
- ASSERT(be32_to_cpu(agf->agf_length) ==
- be32_to_cpu(agi->agi_length));
-
- xfs_alloc_log_agf(tp, bp, XFS_AGF_LENGTH);
-
- /*
- * Free the new space.
- *
- * XFS_RMAP_OWN_NULL is used here to tell the rmap btree that
- * this doesn't actually exist in the rmap btree.
- */
- xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_NULL);
- error = xfs_rmap_free(tp, bp, agno,
- be32_to_cpu(agf->agf_length) - new,
- new, &oinfo);
+ error = xfs_ag_extend_space(mp, tp, &id, new);
if (error)
- goto error0;
- error = xfs_free_extent(tp,
- XFS_AGB_TO_FSB(mp, agno,
- be32_to_cpu(agf->agf_length) - new),
- new, &oinfo, XFS_AG_RESV_NONE);
- if (error)
- goto error0;
+ goto out_trans_cancel;
}
/*
@@ -517,10 +143,8 @@ xfs_growfs_data_private(
if (nb > mp->m_sb.sb_dblocks)
xfs_trans_mod_sb(tp, XFS_TRANS_SB_DBLOCKS,
nb - mp->m_sb.sb_dblocks);
- if (nfree)
- xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, nfree);
- if (dpct)
- xfs_trans_mod_sb(tp, XFS_TRANS_SB_IMAXPCT, dpct);
+ if (id.nfree)
+ xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, id.nfree);
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp);
if (error)
@@ -529,12 +153,6 @@ xfs_growfs_data_private(
/* New allocation groups fully initialized, so update mount struct */
if (nagimax)
mp->m_maxagi = nagimax;
- if (mp->m_sb.sb_imax_pct) {
- uint64_t icount = mp->m_sb.sb_dblocks * mp->m_sb.sb_imax_pct;
- do_div(icount, 100);
- mp->m_maxicount = icount << mp->m_sb.sb_inopblog;
- } else
- mp->m_maxicount = 0;
xfs_set_low_space_thresholds(mp);
mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);
@@ -545,73 +163,24 @@ xfs_growfs_data_private(
if (new) {
struct xfs_perag *pag;
- pag = xfs_perag_get(mp, agno);
+ pag = xfs_perag_get(mp, id.agno);
error = xfs_ag_resv_free(pag);
xfs_perag_put(pag);
if (error)
- goto out;
+ return error;
}
- /* Reserve AG metadata blocks. */
+ /*
+ * Reserve AG metadata blocks. ENOSPC here does not mean there was a
+ * growfs failure, just that there still isn't space for new user data
+ * after the grow has been run.
+ */
error = xfs_fs_reserve_ag_blocks(mp);
- if (error && error != -ENOSPC)
- goto out;
-
- /* update secondary superblocks. */
- for (agno = 1; agno < nagcount; agno++) {
+ if (error == -ENOSPC)
error = 0;
- /*
- * new secondary superblocks need to be zeroed, not read from
- * disk as the contents of the new area we are growing into is
- * completely unknown.
- */
- if (agno < oagcount) {
- error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp,
- XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
- XFS_FSS_TO_BB(mp, 1), 0, &bp,
- &xfs_sb_buf_ops);
- } else {
- bp = xfs_trans_get_buf(NULL, mp->m_ddev_targp,
- XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
- XFS_FSS_TO_BB(mp, 1), 0);
- if (bp) {
- bp->b_ops = &xfs_sb_buf_ops;
- xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
- } else
- error = -ENOMEM;
- }
+ return error;
- /*
- * If we get an error reading or writing alternate superblocks,
- * continue. xfs_repair chooses the "best" superblock based
- * on most matches; if we break early, we'll leave more
- * superblocks un-updated than updated, and xfs_repair may
- * pick them over the properly-updated primary.
- */
- if (error) {
- xfs_warn(mp,
- "error %d reading secondary superblock for ag %d",
- error, agno);
- saved_error = error;
- continue;
- }
- xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb);
-
- error = xfs_bwrite(bp);
- xfs_buf_relse(bp);
- if (error) {
- xfs_warn(mp,
- "write error %d updating secondary superblock for ag %d",
- error, agno);
- saved_error = error;
- continue;
- }
- }
-
- out:
- return saved_error ? saved_error : error;
-
- error0:
+out_trans_cancel:
xfs_trans_cancel(tp);
return error;
}
@@ -638,25 +207,71 @@ xfs_growfs_log_private(
return -ENOSYS;
}
+static int
+xfs_growfs_imaxpct(
+ struct xfs_mount *mp,
+ __u32 imaxpct)
+{
+ struct xfs_trans *tp;
+ int dpct;
+ int error;
+
+ if (imaxpct > 100)
+ return -EINVAL;
+
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata,
+ XFS_GROWFS_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp);
+ if (error)
+ return error;
+
+ dpct = imaxpct - mp->m_sb.sb_imax_pct;
+ xfs_trans_mod_sb(tp, XFS_TRANS_SB_IMAXPCT, dpct);
+ xfs_trans_set_sync(tp);
+ return xfs_trans_commit(tp);
+}
+
/*
* protected versions of growfs function acquire and release locks on the mount
* point - exported through ioctls: XFS_IOC_FSGROWFSDATA, XFS_IOC_FSGROWFSLOG,
* XFS_IOC_FSGROWFSRT
*/
-
-
int
xfs_growfs_data(
- xfs_mount_t *mp,
- xfs_growfs_data_t *in)
+ struct xfs_mount *mp,
+ struct xfs_growfs_data *in)
{
- int error;
+ int error = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!mutex_trylock(&mp->m_growlock))
return -EWOULDBLOCK;
- error = xfs_growfs_data_private(mp, in);
+
+ /* update imaxpct separately to the physical grow of the filesystem */
+ if (in->imaxpct != mp->m_sb.sb_imax_pct) {
+ error = xfs_growfs_imaxpct(mp, in->imaxpct);
+ if (error)
+ goto out_error;
+ }
+
+ if (in->newblocks != mp->m_sb.sb_dblocks) {
+ error = xfs_growfs_data_private(mp, in);
+ if (error)
+ goto out_error;
+ }
+
+ /* Post growfs calculations needed to reflect new state in operations */
+ if (mp->m_sb.sb_imax_pct) {
+ uint64_t icount = mp->m_sb.sb_dblocks * mp->m_sb.sb_imax_pct;
+ do_div(icount, 100);
+ mp->m_maxicount = icount << mp->m_sb.sb_inopblog;
+ } else
+ mp->m_maxicount = 0;
+
+ /* Update secondary superblocks now the physical grow has completed */
+ error = xfs_update_secondary_sbs(mp);
+
+out_error:
/*
* Increment the generation unconditionally, the error could be from
* updating the secondary superblocks, in which case the new size
diff --git a/fs/xfs/xfs_globals.c b/fs/xfs/xfs_globals.c
index 3e1cc30..fdde17a 100644
--- a/fs/xfs/xfs_globals.c
+++ b/fs/xfs/xfs_globals.c
@@ -47,6 +47,7 @@ xfs_param_t xfs_params = {
struct xfs_globals xfs_globals = {
.log_recovery_delay = 0, /* no delay by default */
+ .mount_delay = 0, /* no delay by default */
#ifdef XFS_ASSERT_FATAL
.bug_on_assert = true, /* assert failures BUG() */
#else
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 9a18f69..164350d 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -107,7 +107,8 @@ xfs_inode_free_callback(
xfs_idestroy_fork(ip, XFS_COW_FORK);
if (ip->i_itemp) {
- ASSERT(!(ip->i_itemp->ili_item.li_flags & XFS_LI_IN_AIL));
+ ASSERT(!test_bit(XFS_LI_IN_AIL,
+ &ip->i_itemp->ili_item.li_flags));
xfs_inode_item_destroy(ip);
ip->i_itemp = NULL;
}
@@ -309,6 +310,46 @@ xfs_reinit_inode(
}
/*
+ * If we are allocating a new inode, then check what was returned is
+ * actually a free, empty inode. If we are not allocating an inode,
+ * then check we didn't find a free inode.
+ *
+ * Returns:
+ * 0 if the inode free state matches the lookup context
+ * -ENOENT if the inode is free and we are not allocating
+ * -EFSCORRUPTED if there is any state mismatch at all
+ */
+static int
+xfs_iget_check_free_state(
+ struct xfs_inode *ip,
+ int flags)
+{
+ if (flags & XFS_IGET_CREATE) {
+ /* should be a free inode */
+ if (VFS_I(ip)->i_mode != 0) {
+ xfs_warn(ip->i_mount,
+"Corruption detected! Free inode 0x%llx not marked free! (mode 0x%x)",
+ ip->i_ino, VFS_I(ip)->i_mode);
+ return -EFSCORRUPTED;
+ }
+
+ if (ip->i_d.di_nblocks != 0) {
+ xfs_warn(ip->i_mount,
+"Corruption detected! Free inode 0x%llx has blocks allocated!",
+ ip->i_ino);
+ return -EFSCORRUPTED;
+ }
+ return 0;
+ }
+
+ /* should be an allocated inode */
+ if (VFS_I(ip)->i_mode == 0)
+ return -ENOENT;
+
+ return 0;
+}
+
+/*
* Check the validity of the inode we just found it the cache
*/
static int
@@ -357,12 +398,12 @@ xfs_iget_cache_hit(
}
/*
- * If lookup is racing with unlink return an error immediately.
+ * Check the inode free state is valid. This also detects lookup
+ * racing with unlinks.
*/
- if (VFS_I(ip)->i_mode == 0 && !(flags & XFS_IGET_CREATE)) {
- error = -ENOENT;
+ error = xfs_iget_check_free_state(ip, flags);
+ if (error)
goto out_error;
- }
/*
* If IRECLAIMABLE is set, we've torn down the VFS inode already.
@@ -485,29 +526,12 @@ xfs_iget_cache_miss(
/*
- * If we are allocating a new inode, then check what was returned is
- * actually a free, empty inode. If we are not allocating an inode,
- * the check we didn't find a free inode.
+ * Check the inode free state is valid. This also detects lookup
+ * racing with unlinks.
*/
- if (flags & XFS_IGET_CREATE) {
- if (VFS_I(ip)->i_mode != 0) {
- xfs_warn(mp,
-"Corruption detected! Free inode 0x%llx not marked free on disk",
- ino);
- error = -EFSCORRUPTED;
- goto out_destroy;
- }
- if (ip->i_d.di_nblocks != 0) {
- xfs_warn(mp,
-"Corruption detected! Free inode 0x%llx has blocks allocated!",
- ino);
- error = -EFSCORRUPTED;
- goto out_destroy;
- }
- } else if (VFS_I(ip)->i_mode == 0) {
- error = -ENOENT;
+ error = xfs_iget_check_free_state(ip, flags);
+ if (error)
goto out_destroy;
- }
/*
* Preload the radix tree so we can insert safely under the
@@ -1802,3 +1826,21 @@ xfs_inode_clear_cowblocks_tag(
return __xfs_inode_clear_blocks_tag(ip,
trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG);
}
+
+/* Disable post-EOF and CoW block auto-reclamation. */
+void
+xfs_icache_disable_reclaim(
+ struct xfs_mount *mp)
+{
+ cancel_delayed_work_sync(&mp->m_eofblocks_work);
+ cancel_delayed_work_sync(&mp->m_cowblocks_work);
+}
+
+/* Enable post-EOF and CoW block auto-reclamation. */
+void
+xfs_icache_enable_reclaim(
+ struct xfs_mount *mp)
+{
+ xfs_queue_eofblocks(mp);
+ xfs_queue_cowblocks(mp);
+}
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index d4a7758..d69a0f5 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -131,4 +131,7 @@ xfs_fs_eofblocks_from_user(
int xfs_icache_inode_is_allocated(struct xfs_mount *mp, struct xfs_trans *tp,
xfs_ino_t ino, bool *inuse);
+void xfs_icache_disable_reclaim(struct xfs_mount *mp);
+void xfs_icache_enable_reclaim(struct xfs_mount *mp);
+
#endif
diff --git a/fs/xfs/xfs_icreate_item.c b/fs/xfs/xfs_icreate_item.c
index 865ad13..5da9599 100644
--- a/fs/xfs/xfs_icreate_item.c
+++ b/fs/xfs/xfs_icreate_item.c
@@ -91,7 +91,7 @@ xfs_icreate_item_unlock(
{
struct xfs_icreate_item *icp = ICR_ITEM(lip);
- if (icp->ic_item.li_flags & XFS_LI_ABORTED)
+ if (test_bit(XFS_LI_ABORTED, &lip->li_flags))
kmem_zone_free(xfs_icreate_zone, icp);
return;
}
@@ -184,5 +184,5 @@ xfs_icreate_log(
xfs_trans_add_item(tp, &icp->ic_item);
tp->t_flags |= XFS_TRANS_DIRTY;
- icp->ic_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+ set_bit(XFS_LI_DIRTY, &icp->ic_item.li_flags);
}
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 2b70c8b..05207a64 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -498,7 +498,7 @@ xfs_lock_inodes(
if (!try_lock) {
for (j = (i - 1); j >= 0 && !try_lock; j--) {
lp = (xfs_log_item_t *)ips[j]->i_itemp;
- if (lp && (lp->li_flags & XFS_LI_IN_AIL))
+ if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags))
try_lock++;
}
}
@@ -598,7 +598,7 @@ xfs_lock_two_inodes(
* and try again.
*/
lp = (xfs_log_item_t *)ip0->i_itemp;
- if (lp && (lp->li_flags & XFS_LI_IN_AIL)) {
+ if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags)) {
if (!xfs_ilock_nowait(ip1, xfs_lock_inumorder(ip1_mode, 1))) {
xfs_iunlock(ip0, ip0_mode);
if ((++attempts % 5) == 0)
@@ -791,6 +791,18 @@ xfs_ialloc(
ASSERT(*ialloc_context == NULL);
/*
+ * Protect against obviously corrupt allocation btree records. Later
+ * xfs_iget checks will catch re-allocation of other active in-memory
+ * and on-disk inodes. If we don't catch reallocating the parent inode
+ * here we will deadlock in xfs_iget() so we have to do these checks
+ * first.
+ */
+ if ((pip && ino == pip->i_ino) || !xfs_verify_dir_ino(mp, ino)) {
+ xfs_alert(mp, "Allocated a known in-use inode 0x%llx!", ino);
+ return -EFSCORRUPTED;
+ }
+
+ /*
* Get the in-core inode with the lock held exclusively.
* This is because we're setting fields here we need
* to prevent others from looking at until we're done.
@@ -1196,6 +1208,7 @@ xfs_create(
unlock_dp_on_error = true;
xfs_defer_init(&dfops, &first_block);
+ tp->t_agfl_dfops = &dfops;
/*
* Reserve disk quota and the inode.
@@ -1411,11 +1424,11 @@ xfs_link(
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
- error = xfs_qm_dqattach(sip, 0);
+ error = xfs_qm_dqattach(sip);
if (error)
goto std_return;
- error = xfs_qm_dqattach(tdp, 0);
+ error = xfs_qm_dqattach(tdp);
if (error)
goto std_return;
@@ -1451,6 +1464,7 @@ xfs_link(
}
xfs_defer_init(&dfops, &first_block);
+ tp->t_agfl_dfops = &dfops;
/*
* Handle initial link state of O_TMPFILE inode
@@ -1534,11 +1548,12 @@ xfs_itruncate_clear_reflink_flags(
* dirty on error so that transactions can be easily aborted if possible.
*/
int
-xfs_itruncate_extents(
+xfs_itruncate_extents_flags(
struct xfs_trans **tpp,
struct xfs_inode *ip,
int whichfork,
- xfs_fsize_t new_size)
+ xfs_fsize_t new_size,
+ int flags)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp = *tpp;
@@ -1561,6 +1576,8 @@ xfs_itruncate_extents(
trace_xfs_itruncate_extents_start(ip, new_size);
+ flags |= xfs_bmapi_aflag(whichfork);
+
/*
* Since it is possible for space to become allocated beyond
* the end of the file (in a crash where the space is allocated
@@ -1579,12 +1596,9 @@ xfs_itruncate_extents(
unmap_len = last_block - first_unmap_block + 1;
while (!done) {
xfs_defer_init(&dfops, &first_block);
- error = xfs_bunmapi(tp, ip,
- first_unmap_block, unmap_len,
- xfs_bmapi_aflag(whichfork),
- XFS_ITRUNC_MAX_EXTENTS,
- &first_block, &dfops,
- &done);
+ error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
+ XFS_ITRUNC_MAX_EXTENTS, &first_block,
+ &dfops, &done);
if (error)
goto out_bmap_cancel;
@@ -1811,6 +1825,7 @@ xfs_inactive_ifree(
xfs_trans_ijoin(tp, ip, 0);
xfs_defer_init(&dfops, &first_block);
+ tp->t_agfl_dfops = &dfops;
error = xfs_ifree(tp, ip, &dfops);
if (error) {
/*
@@ -1911,7 +1926,7 @@ xfs_inactive(
ip->i_d.di_nextents > 0 || ip->i_delayed_blks > 0))
truncate = 1;
- error = xfs_qm_dqattach(ip, 0);
+ error = xfs_qm_dqattach(ip);
if (error)
return;
@@ -2574,11 +2589,11 @@ xfs_remove(
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
- error = xfs_qm_dqattach(dp, 0);
+ error = xfs_qm_dqattach(dp);
if (error)
goto std_return;
- error = xfs_qm_dqattach(ip, 0);
+ error = xfs_qm_dqattach(ip);
if (error)
goto std_return;
@@ -2647,6 +2662,7 @@ xfs_remove(
goto out_trans_cancel;
xfs_defer_init(&dfops, &first_block);
+ tp->t_agfl_dfops = &dfops;
error = xfs_dir_removename(tp, dp, name, ip->i_ino,
&first_block, &dfops, resblks);
if (error) {
@@ -3014,6 +3030,7 @@ xfs_rename(
}
xfs_defer_init(&dfops, &first_block);
+ tp->t_agfl_dfops = &dfops;
/* RENAME_EXCHANGE is unique from here on. */
if (flags & RENAME_EXCHANGE)
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 1eebc53..00fee68 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -415,8 +415,8 @@ uint xfs_ilock_attr_map_shared(struct xfs_inode *);
uint xfs_ip2xflags(struct xfs_inode *);
int xfs_ifree(struct xfs_trans *, xfs_inode_t *,
struct xfs_defer_ops *);
-int xfs_itruncate_extents(struct xfs_trans **, struct xfs_inode *,
- int, xfs_fsize_t);
+int xfs_itruncate_extents_flags(struct xfs_trans **,
+ struct xfs_inode *, int, xfs_fsize_t, int);
void xfs_iext_realloc(xfs_inode_t *, int, int);
void xfs_iunpin_wait(xfs_inode_t *);
@@ -433,6 +433,16 @@ int xfs_dir_ialloc(struct xfs_trans **, struct xfs_inode *, umode_t,
xfs_nlink_t, dev_t, prid_t,
struct xfs_inode **);
+static inline int
+xfs_itruncate_extents(
+ struct xfs_trans **tpp,
+ struct xfs_inode *ip,
+ int whichfork,
+ xfs_fsize_t new_size)
+{
+ return xfs_itruncate_extents_flags(tpp, ip, whichfork, new_size, 0);
+}
+
/* from xfs_file.c */
enum xfs_prealloc_flags {
XFS_PREALLOC_SET = (1 << 1),
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 34b91b7..3e5b857 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -518,7 +518,7 @@ xfs_inode_item_push(
* The buffer containing this item failed to be written back
* previously. Resubmit the buffer for IO.
*/
- if (lip->li_flags & XFS_LI_FAILED) {
+ if (test_bit(XFS_LI_FAILED, &lip->li_flags)) {
if (!xfs_buf_trylock(bp))
return XFS_ITEM_LOCKED;
@@ -729,14 +729,14 @@ xfs_iflush_done(
*/
iip = INODE_ITEM(blip);
if ((iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) ||
- (blip->li_flags & XFS_LI_FAILED))
+ test_bit(XFS_LI_FAILED, &blip->li_flags))
need_ail++;
}
/* make sure we capture the state of the initial inode. */
iip = INODE_ITEM(lip);
if ((iip->ili_logged && lip->li_lsn == iip->ili_flush_lsn) ||
- lip->li_flags & XFS_LI_FAILED)
+ test_bit(XFS_LI_FAILED, &lip->li_flags))
need_ail++;
/*
@@ -803,7 +803,7 @@ xfs_iflush_abort(
xfs_inode_log_item_t *iip = ip->i_itemp;
if (iip) {
- if (iip->ili_item.li_flags & XFS_LI_IN_AIL) {
+ if (test_bit(XFS_LI_IN_AIL, &iip->ili_item.li_flags)) {
xfs_trans_ail_remove(&iip->ili_item,
stale ? SHUTDOWN_LOG_IO_ERROR :
SHUTDOWN_CORRUPT_INCORE);
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 89fb1eb..5dd9e22 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1103,7 +1103,8 @@ xfs_ioctl_setattr_dax_invalidate(
if (fa->fsx_xflags & FS_XFLAG_DAX) {
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
return -EINVAL;
- if (bdev_dax_supported(sb, sb->s_blocksize) < 0)
+ if (!bdev_dax_supported(xfs_find_bdev_for_inode(VFS_I(ip)),
+ sb->s_blocksize))
return -EINVAL;
}
@@ -1811,6 +1812,88 @@ xfs_ioc_swapext(
return error;
}
+static int
+xfs_ioc_getlabel(
+ struct xfs_mount *mp,
+ char __user *user_label)
+{
+ struct xfs_sb *sbp = &mp->m_sb;
+ char label[XFSLABEL_MAX + 1];
+
+ /* Paranoia */
+ BUILD_BUG_ON(sizeof(sbp->sb_fname) > FSLABEL_MAX);
+
+ spin_lock(&mp->m_sb_lock);
+ strncpy(label, sbp->sb_fname, sizeof(sbp->sb_fname));
+ spin_unlock(&mp->m_sb_lock);
+
+ /* xfs on-disk label is 12 chars, be sure we send a null to user */
+ label[XFSLABEL_MAX] = '\0';
+ if (copy_to_user(user_label, label, sizeof(sbp->sb_fname)))
+ return -EFAULT;
+ return 0;
+}
+
+static int
+xfs_ioc_setlabel(
+ struct file *filp,
+ struct xfs_mount *mp,
+ char __user *newlabel)
+{
+ struct xfs_sb *sbp = &mp->m_sb;
+ char label[XFSLABEL_MAX + 1];
+ size_t len;
+ int error;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ /*
+ * The generic ioctl allows up to FSLABEL_MAX chars, but XFS is much
+ * smaller, at 12 bytes. We copy one more to be sure we find the
+ * (required) NULL character to test the incoming label length.
+ * NB: The on disk label doesn't need to be null terminated.
+ */
+ if (copy_from_user(label, newlabel, XFSLABEL_MAX + 1))
+ return -EFAULT;
+ len = strnlen(label, XFSLABEL_MAX + 1);
+ if (len > sizeof(sbp->sb_fname))
+ return -EINVAL;
+
+ error = mnt_want_write_file(filp);
+ if (error)
+ return error;
+
+ spin_lock(&mp->m_sb_lock);
+ memset(sbp->sb_fname, 0, sizeof(sbp->sb_fname));
+ strncpy(sbp->sb_fname, label, sizeof(sbp->sb_fname));
+ spin_unlock(&mp->m_sb_lock);
+
+ /*
+ * Now we do several things to satisfy userspace.
+ * In addition to normal logging of the primary superblock, we also
+ * immediately write these changes to sector zero for the primary, then
+ * update all backup supers (as xfs_db does for a label change), then
+ * invalidate the block device page cache. This is so that any prior
+ * buffered reads from userspace (i.e. from blkid) are invalidated,
+ * and userspace will see the newly-written label.
+ */
+ error = xfs_sync_sb_buf(mp);
+ if (error)
+ goto out;
+ /*
+ * growfs also updates backup supers so lock against that.
+ */
+ mutex_lock(&mp->m_growlock);
+ error = xfs_update_secondary_sbs(mp);
+ mutex_unlock(&mp->m_growlock);
+
+ invalidate_bdev(mp->m_ddev_targp->bt_bdev);
+
+out:
+ mnt_drop_write_file(filp);
+ return error;
+}
+
/*
* Note: some of the ioctl's return positive numbers as a
* byte count indicating success, such as readlink_by_handle.
@@ -1834,6 +1917,10 @@ xfs_file_ioctl(
switch (cmd) {
case FITRIM:
return xfs_ioc_trim(mp, arg);
+ case FS_IOC_GETFSLABEL:
+ return xfs_ioc_getlabel(mp, arg);
+ case FS_IOC_SETFSLABEL:
+ return xfs_ioc_setlabel(filp, mp, arg);
case XFS_IOC_ALLOCSP:
case XFS_IOC_FREESP:
case XFS_IOC_RESVSP:
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 046469f..c6ce6f9 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -224,7 +224,7 @@ xfs_iomap_write_direct(
* necessary and move on to transaction setup.
*/
xfs_iunlock(ip, lockmode);
- error = xfs_qm_dqattach(ip, 0);
+ error = xfs_qm_dqattach(ip);
if (error)
return error;
@@ -576,7 +576,7 @@ xfs_file_iomap_begin_delay(
goto done;
}
- error = xfs_qm_dqattach_locked(ip, 0);
+ error = xfs_qm_dqattach_locked(ip, false);
if (error)
goto out_unlock;
@@ -692,7 +692,7 @@ xfs_iomap_write_allocate(
/*
* Make sure that the dquots are there.
*/
- error = xfs_qm_dqattach(ip, 0);
+ error = xfs_qm_dqattach(ip);
if (error)
return error;
@@ -946,8 +946,11 @@ xfs_iomap_write_unwritten(
return error;
}
-static inline bool imap_needs_alloc(struct inode *inode,
- struct xfs_bmbt_irec *imap, int nimaps)
+static inline bool
+imap_needs_alloc(
+ struct inode *inode,
+ struct xfs_bmbt_irec *imap,
+ int nimaps)
{
return !nimaps ||
imap->br_startblock == HOLESTARTBLOCK ||
@@ -955,31 +958,58 @@ static inline bool imap_needs_alloc(struct inode *inode,
(IS_DAX(inode) && imap->br_state == XFS_EXT_UNWRITTEN);
}
-static inline bool needs_cow_for_zeroing(struct xfs_bmbt_irec *imap, int nimaps)
+static inline bool
+needs_cow_for_zeroing(
+ struct xfs_bmbt_irec *imap,
+ int nimaps)
{
return nimaps &&
imap->br_startblock != HOLESTARTBLOCK &&
imap->br_state != XFS_EXT_UNWRITTEN;
}
-static inline bool need_excl_ilock(struct xfs_inode *ip, unsigned flags)
+static int
+xfs_ilock_for_iomap(
+ struct xfs_inode *ip,
+ unsigned flags,
+ unsigned *lockmode)
{
+ unsigned mode = XFS_ILOCK_SHARED;
+
/*
* COW writes may allocate delalloc space or convert unwritten COW
* extents, so we need to make sure to take the lock exclusively here.
*/
- if (xfs_is_reflink_inode(ip) && (flags & (IOMAP_WRITE | IOMAP_ZERO)))
- return true;
+ if (xfs_is_reflink_inode(ip) && (flags & (IOMAP_WRITE | IOMAP_ZERO))) {
+ /*
+ * FIXME: It could still overwrite on unshared extents and not
+ * need allocation.
+ */
+ if (flags & IOMAP_NOWAIT)
+ return -EAGAIN;
+ mode = XFS_ILOCK_EXCL;
+ }
/*
- * Extents not yet cached requires exclusive access, don't block.
- * This is an opencoded xfs_ilock_data_map_shared() to cater for the
+ * Extents not yet cached requires exclusive access, don't block. This
+ * is an opencoded xfs_ilock_data_map_shared() call but with
* non-blocking behaviour.
*/
- if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE &&
- !(ip->i_df.if_flags & XFS_IFEXTENTS))
- return true;
- return false;
+ if (!(ip->i_df.if_flags & XFS_IFEXTENTS)) {
+ if (flags & IOMAP_NOWAIT)
+ return -EAGAIN;
+ mode = XFS_ILOCK_EXCL;
+ }
+
+ if (flags & IOMAP_NOWAIT) {
+ if (!xfs_ilock_nowait(ip, mode))
+ return -EAGAIN;
+ } else {
+ xfs_ilock(ip, mode);
+ }
+
+ *lockmode = mode;
+ return 0;
}
static int
@@ -1007,19 +1037,15 @@ xfs_file_iomap_begin(
return xfs_file_iomap_begin_delay(inode, offset, length, iomap);
}
- if (need_excl_ilock(ip, flags))
- lockmode = XFS_ILOCK_EXCL;
- else
- lockmode = XFS_ILOCK_SHARED;
-
- if (flags & IOMAP_NOWAIT) {
- if (!(ip->i_df.if_flags & XFS_IFEXTENTS))
- return -EAGAIN;
- if (!xfs_ilock_nowait(ip, lockmode))
- return -EAGAIN;
- } else {
- xfs_ilock(ip, lockmode);
- }
+ /*
+ * Lock the inode in the manner required for the specified operation and
+ * check for as many conditions that would result in blocking as
+ * possible. This removes most of the non-blocking checks from the
+ * mapping code below.
+ */
+ error = xfs_ilock_for_iomap(ip, flags, &lockmode);
+ if (error)
+ return error;
ASSERT(offset <= mp->m_super->s_maxbytes);
if (offset > mp->m_super->s_maxbytes - length)
@@ -1040,19 +1066,21 @@ xfs_file_iomap_begin(
goto out_unlock;
}
- if (xfs_is_reflink_inode(ip) &&
- ((flags & IOMAP_WRITE) ||
- ((flags & IOMAP_ZERO) && needs_cow_for_zeroing(&imap, nimaps)))) {
+ /* Non-modifying mapping requested, so we are done */
+ if (!(flags & (IOMAP_WRITE | IOMAP_ZERO)))
+ goto out_found;
+
+ /*
+ * Break shared extents if necessary. Checks for non-blocking IO have
+ * been done up front, so we don't need to do them here.
+ */
+ if (xfs_is_reflink_inode(ip)) {
+ /* if zeroing doesn't need COW allocation, then we are done. */
+ if ((flags & IOMAP_ZERO) &&
+ !needs_cow_for_zeroing(&imap, nimaps))
+ goto out_found;
+
if (flags & IOMAP_DIRECT) {
- /*
- * A reflinked inode will result in CoW alloc.
- * FIXME: It could still overwrite on unshared extents
- * and not need allocation.
- */
- if (flags & IOMAP_NOWAIT) {
- error = -EAGAIN;
- goto out_unlock;
- }
/* may drop and re-acquire the ilock */
error = xfs_reflink_allocate_cow(ip, &imap, &shared,
&lockmode);
@@ -1068,46 +1096,45 @@ xfs_file_iomap_begin(
length = XFS_FSB_TO_B(mp, end_fsb) - offset;
}
- if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) {
- /*
- * If nowait is set bail since we are going to make
- * allocations.
- */
- if (flags & IOMAP_NOWAIT) {
- error = -EAGAIN;
- goto out_unlock;
- }
- /*
- * We cap the maximum length we map here to MAX_WRITEBACK_PAGES
- * pages to keep the chunks of work done where somewhat symmetric
- * with the work writeback does. This is a completely arbitrary
- * number pulled out of thin air as a best guess for initial
- * testing.
- *
- * Note that the values needs to be less than 32-bits wide until
- * the lower level functions are updated.
- */
- length = min_t(loff_t, length, 1024 * PAGE_SIZE);
- /*
- * xfs_iomap_write_direct() expects the shared lock. It
- * is unlocked on return.
- */
- if (lockmode == XFS_ILOCK_EXCL)
- xfs_ilock_demote(ip, lockmode);
- error = xfs_iomap_write_direct(ip, offset, length, &imap,
- nimaps);
- if (error)
- return error;
+ /* Don't need to allocate over holes when doing zeroing operations. */
+ if (flags & IOMAP_ZERO)
+ goto out_found;
- iomap->flags = IOMAP_F_NEW;
- trace_xfs_iomap_alloc(ip, offset, length, 0, &imap);
- } else {
- ASSERT(nimaps);
+ if (!imap_needs_alloc(inode, &imap, nimaps))
+ goto out_found;
- xfs_iunlock(ip, lockmode);
- trace_xfs_iomap_found(ip, offset, length, 0, &imap);
+ /* If nowait is set bail since we are going to make allocations. */
+ if (flags & IOMAP_NOWAIT) {
+ error = -EAGAIN;
+ goto out_unlock;
}
+ /*
+ * We cap the maximum length we map to a sane size to keep the chunks
+ * of work done where somewhat symmetric with the work writeback does.
+ * This is a completely arbitrary number pulled out of thin air as a
+ * best guess for initial testing.
+ *
+ * Note that the values needs to be less than 32-bits wide until the
+ * lower level functions are updated.
+ */
+ length = min_t(loff_t, length, 1024 * PAGE_SIZE);
+
+ /*
+ * xfs_iomap_write_direct() expects the shared lock. It is unlocked on
+ * return.
+ */
+ if (lockmode == XFS_ILOCK_EXCL)
+ xfs_ilock_demote(ip, lockmode);
+ error = xfs_iomap_write_direct(ip, offset, length, &imap,
+ nimaps);
+ if (error)
+ return error;
+
+ iomap->flags = IOMAP_F_NEW;
+ trace_xfs_iomap_alloc(ip, offset, length, 0, &imap);
+
+out_finish:
if (xfs_ipincount(ip) && (ip->i_itemp->ili_fsync_fields
& ~XFS_ILOG_TIMESTAMP))
iomap->flags |= IOMAP_F_DIRTY;
@@ -1117,6 +1144,13 @@ xfs_file_iomap_begin(
if (shared)
iomap->flags |= IOMAP_F_SHARED;
return 0;
+
+out_found:
+ ASSERT(nimaps);
+ xfs_iunlock(ip, lockmode);
+ trace_xfs_iomap_found(ip, offset, length, 0, &imap);
+ goto out_finish;
+
out_unlock:
xfs_iunlock(ip, lockmode);
return error;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index a3ed3c8..b0eb49b 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -260,6 +260,7 @@ xfs_vn_lookup(
struct dentry *dentry,
unsigned int flags)
{
+ struct inode *inode;
struct xfs_inode *cip;
struct xfs_name name;
int error;
@@ -269,14 +270,13 @@ xfs_vn_lookup(
xfs_dentry_to_name(&name, dentry);
error = xfs_lookup(XFS_I(dir), &name, &cip, NULL);
- if (unlikely(error)) {
- if (unlikely(error != -ENOENT))
- return ERR_PTR(error);
- d_add(dentry, NULL);
- return NULL;
- }
-
- return d_splice_alias(VFS_I(cip), dentry);
+ if (likely(!error))
+ inode = VFS_I(cip);
+ else if (likely(error == -ENOENT))
+ inode = NULL;
+ else
+ inode = ERR_PTR(error);
+ return d_splice_alias(inode, dentry);
}
STATIC struct dentry *
@@ -855,7 +855,7 @@ xfs_setattr_size(
/*
* Make sure that the dquots are attached to the inode.
*/
- error = xfs_qm_dqattach(ip, 0);
+ error = xfs_qm_dqattach(ip);
if (error)
return error;
@@ -1195,6 +1195,30 @@ static const struct inode_operations xfs_inline_symlink_inode_operations = {
.update_time = xfs_vn_update_time,
};
+/* Figure out if this file actually supports DAX. */
+static bool
+xfs_inode_supports_dax(
+ struct xfs_inode *ip)
+{
+ struct xfs_mount *mp = ip->i_mount;
+
+ /* Only supported on non-reflinked files. */
+ if (!S_ISREG(VFS_I(ip)->i_mode) || xfs_is_reflink_inode(ip))
+ return false;
+
+ /* DAX mount option or DAX iflag must be set. */
+ if (!(mp->m_flags & XFS_MOUNT_DAX) &&
+ !(ip->i_d.di_flags2 & XFS_DIFLAG2_DAX))
+ return false;
+
+ /* Block size must match page size */
+ if (mp->m_sb.sb_blocksize != PAGE_SIZE)
+ return false;
+
+ /* Device has to support DAX too. */
+ return xfs_find_daxdev_for_inode(VFS_I(ip)) != NULL;
+}
+
STATIC void
xfs_diflags_to_iflags(
struct inode *inode,
@@ -1213,11 +1237,7 @@ xfs_diflags_to_iflags(
inode->i_flags |= S_SYNC;
if (flags & XFS_DIFLAG_NOATIME)
inode->i_flags |= S_NOATIME;
- if (S_ISREG(inode->i_mode) &&
- ip->i_mount->m_sb.sb_blocksize == PAGE_SIZE &&
- !xfs_is_reflink_inode(ip) &&
- (ip->i_mount->m_flags & XFS_MOUNT_DAX ||
- ip->i_d.di_flags2 & XFS_DIFLAG2_DAX))
+ if (xfs_inode_supports_dax(ip))
inode->i_flags |= S_DAX;
}
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 2fcd9ed..c21039f 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1047,6 +1047,7 @@ xfs_log_item_init(
INIT_LIST_HEAD(&item->li_ail);
INIT_LIST_HEAD(&item->li_cil);
INIT_LIST_HEAD(&item->li_bio_list);
+ INIT_LIST_HEAD(&item->li_trans);
}
/*
@@ -2110,10 +2111,10 @@ xlog_print_tic_res(
*/
void
xlog_print_trans(
- struct xfs_trans *tp)
+ struct xfs_trans *tp)
{
- struct xfs_mount *mp = tp->t_mountp;
- struct xfs_log_item_desc *lidp;
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_log_item *lip;
/* dump core transaction and ticket info */
xfs_warn(mp, "transaction summary:");
@@ -2124,15 +2125,14 @@ xlog_print_trans(
xlog_print_tic_res(mp, tp->t_ticket);
/* dump each log item */
- list_for_each_entry(lidp, &tp->t_items, lid_trans) {
- struct xfs_log_item *lip = lidp->lid_item;
+ list_for_each_entry(lip, &tp->t_items, li_trans) {
struct xfs_log_vec *lv = lip->li_lv;
struct xfs_log_iovec *vec;
int i;
xfs_warn(mp, "log item: ");
xfs_warn(mp, " type = 0x%x", lip->li_type);
- xfs_warn(mp, " flags = 0x%x", lip->li_flags);
+ xfs_warn(mp, " flags = 0x%lx", lip->li_flags);
if (!lv)
continue;
xfs_warn(mp, " niovecs = %d", lv->lv_niovecs);
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 4668403..c156877 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -141,10 +141,9 @@ xlog_cil_alloc_shadow_bufs(
struct xlog *log,
struct xfs_trans *tp)
{
- struct xfs_log_item_desc *lidp;
+ struct xfs_log_item *lip;
- list_for_each_entry(lidp, &tp->t_items, lid_trans) {
- struct xfs_log_item *lip = lidp->lid_item;
+ list_for_each_entry(lip, &tp->t_items, li_trans) {
struct xfs_log_vec *lv;
int niovecs = 0;
int nbytes = 0;
@@ -152,7 +151,7 @@ xlog_cil_alloc_shadow_bufs(
bool ordered = false;
/* Skip items which aren't dirty in this transaction. */
- if (!(lidp->lid_flags & XFS_LID_DIRTY))
+ if (!test_bit(XFS_LI_DIRTY, &lip->li_flags))
continue;
/* get number of vecs and size of data to be stored */
@@ -317,7 +316,7 @@ xlog_cil_insert_format_items(
int *diff_len,
int *diff_iovecs)
{
- struct xfs_log_item_desc *lidp;
+ struct xfs_log_item *lip;
/* Bail out if we didn't find a log item. */
@@ -326,15 +325,14 @@ xlog_cil_insert_format_items(
return;
}
- list_for_each_entry(lidp, &tp->t_items, lid_trans) {
- struct xfs_log_item *lip = lidp->lid_item;
+ list_for_each_entry(lip, &tp->t_items, li_trans) {
struct xfs_log_vec *lv;
struct xfs_log_vec *old_lv = NULL;
struct xfs_log_vec *shadow;
bool ordered = false;
/* Skip items which aren't dirty in this transaction. */
- if (!(lidp->lid_flags & XFS_LID_DIRTY))
+ if (!test_bit(XFS_LI_DIRTY, &lip->li_flags))
continue;
/*
@@ -406,7 +404,7 @@ xlog_cil_insert_items(
{
struct xfs_cil *cil = log->l_cilp;
struct xfs_cil_ctx *ctx = cil->xc_ctx;
- struct xfs_log_item_desc *lidp;
+ struct xfs_log_item *lip;
int len = 0;
int diff_iovecs = 0;
int iclog_space;
@@ -479,11 +477,10 @@ xlog_cil_insert_items(
* We do this here so we only need to take the CIL lock once during
* the transaction commit.
*/
- list_for_each_entry(lidp, &tp->t_items, lid_trans) {
- struct xfs_log_item *lip = lidp->lid_item;
+ list_for_each_entry(lip, &tp->t_items, li_trans) {
/* Skip items which aren't dirty in this transaction. */
- if (!(lidp->lid_flags & XFS_LID_DIRTY))
+ if (!test_bit(XFS_LI_DIRTY, &lip->li_flags))
continue;
/*
@@ -1013,6 +1010,7 @@ xfs_log_commit_cil(
*commit_lsn = xc_commit_lsn;
xfs_log_done(mp, tp->t_ticket, NULL, regrant);
+ tp->t_ticket = NULL;
xfs_trans_unreserve_and_mod_sb(tp);
/*
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 2b2383f..06a09cb 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2702,7 +2702,7 @@ xlog_recover_do_reg_buffer(
goto next;
}
fa = xfs_dquot_verify(mp, item->ri_buf[i].i_addr,
- -1, 0, 0);
+ -1, 0);
if (fa) {
xfs_alert(mp,
"dquot corrupt at %pS trying to replay into block 0x%llx",
@@ -3348,7 +3348,7 @@ xlog_recover_dquot_pass2(
*/
dq_f = item->ri_buf[0].i_addr;
ASSERT(dq_f);
- fa = xfs_dquot_verify(mp, recddq, dq_f->qlf_id, 0, 0);
+ fa = xfs_dquot_verify(mp, recddq, dq_f->qlf_id, 0);
if (fa) {
xfs_alert(mp, "corrupt dquot ID 0x%x in log at %pS",
dq_f->qlf_id, fa);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index a901b86..73ed8fe 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1072,9 +1072,7 @@ xfs_unmountfs(
uint64_t resblks;
int error;
- cancel_delayed_work_sync(&mp->m_eofblocks_work);
- cancel_delayed_work_sync(&mp->m_cowblocks_work);
-
+ xfs_icache_disable_reclaim(mp);
xfs_fs_unreserve_ag_blocks(mp);
xfs_qm_unmount_quotas(mp);
xfs_rtunmount_inodes(mp);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index ec39ae2..c3e014b 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -161,10 +161,7 @@ xfs_qm_dqpurge(
* to purge this dquot anyway, so we go ahead regardless.
*/
error = xfs_qm_dqflush(dqp, &bp);
- if (error) {
- xfs_warn(mp, "%s: dquot "PTR_FMT" flush failed",
- __func__, dqp);
- } else {
+ if (!error) {
error = xfs_bwrite(bp);
xfs_buf_relse(bp);
}
@@ -173,7 +170,7 @@ xfs_qm_dqpurge(
ASSERT(atomic_read(&dqp->q_pincount) == 0);
ASSERT(XFS_FORCED_SHUTDOWN(mp) ||
- !(dqp->q_logitem.qli_item.li_flags & XFS_LI_IN_AIL));
+ !test_bit(XFS_LI_IN_AIL, &dqp->q_logitem.qli_item.li_flags));
xfs_dqfunlock(dqp);
xfs_dqunlock(dqp);
@@ -265,7 +262,7 @@ xfs_qm_dqattach_one(
xfs_inode_t *ip,
xfs_dqid_t id,
uint type,
- uint doalloc,
+ bool doalloc,
xfs_dquot_t **IO_idqpp)
{
xfs_dquot_t *dqp;
@@ -291,7 +288,7 @@ xfs_qm_dqattach_one(
* exist on disk and we didn't ask it to allocate; ESRCH if quotas got
* turned off suddenly.
*/
- error = xfs_qm_dqget(ip->i_mount, ip, id, type, doalloc, &dqp);
+ error = xfs_qm_dqget_inode(ip, type, doalloc, &dqp);
if (error)
return error;
@@ -326,14 +323,14 @@ xfs_qm_need_dqattach(
/*
* Given a locked inode, attach dquot(s) to it, taking U/G/P-QUOTAON
* into account.
- * If XFS_QMOPT_DQALLOC, the dquot(s) will be allocated if needed.
+ * If @doalloc is true, the dquot(s) will be allocated if needed.
* Inode may get unlocked and relocked in here, and the caller must deal with
* the consequences.
*/
int
xfs_qm_dqattach_locked(
xfs_inode_t *ip,
- uint flags)
+ bool doalloc)
{
xfs_mount_t *mp = ip->i_mount;
int error = 0;
@@ -345,8 +342,7 @@ xfs_qm_dqattach_locked(
if (XFS_IS_UQUOTA_ON(mp) && !ip->i_udquot) {
error = xfs_qm_dqattach_one(ip, ip->i_d.di_uid, XFS_DQ_USER,
- flags & XFS_QMOPT_DQALLOC,
- &ip->i_udquot);
+ doalloc, &ip->i_udquot);
if (error)
goto done;
ASSERT(ip->i_udquot);
@@ -354,8 +350,7 @@ xfs_qm_dqattach_locked(
if (XFS_IS_GQUOTA_ON(mp) && !ip->i_gdquot) {
error = xfs_qm_dqattach_one(ip, ip->i_d.di_gid, XFS_DQ_GROUP,
- flags & XFS_QMOPT_DQALLOC,
- &ip->i_gdquot);
+ doalloc, &ip->i_gdquot);
if (error)
goto done;
ASSERT(ip->i_gdquot);
@@ -363,8 +358,7 @@ xfs_qm_dqattach_locked(
if (XFS_IS_PQUOTA_ON(mp) && !ip->i_pdquot) {
error = xfs_qm_dqattach_one(ip, xfs_get_projid(ip), XFS_DQ_PROJ,
- flags & XFS_QMOPT_DQALLOC,
- &ip->i_pdquot);
+ doalloc, &ip->i_pdquot);
if (error)
goto done;
ASSERT(ip->i_pdquot);
@@ -381,8 +375,7 @@ xfs_qm_dqattach_locked(
int
xfs_qm_dqattach(
- struct xfs_inode *ip,
- uint flags)
+ struct xfs_inode *ip)
{
int error;
@@ -390,7 +383,7 @@ xfs_qm_dqattach(
return 0;
xfs_ilock(ip, XFS_ILOCK_EXCL);
- error = xfs_qm_dqattach_locked(ip, flags);
+ error = xfs_qm_dqattach_locked(ip, false);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
@@ -479,11 +472,8 @@ xfs_qm_dquot_isolate(
spin_unlock(lru_lock);
error = xfs_qm_dqflush(dqp, &bp);
- if (error) {
- xfs_warn(dqp->q_mount, "%s: dquot "PTR_FMT" flush failed",
- __func__, dqp);
+ if (error)
goto out_unlock_dirty;
- }
xfs_buf_delwri_queue(bp, &isol->buffers);
xfs_buf_relse(bp);
@@ -571,27 +561,88 @@ xfs_qm_set_defquota(
{
xfs_dquot_t *dqp;
struct xfs_def_quota *defq;
+ struct xfs_disk_dquot *ddqp;
int error;
- error = xfs_qm_dqread(mp, 0, type, 0, &dqp);
+ error = xfs_qm_dqget_uncached(mp, 0, type, &dqp);
+ if (error)
+ return;
- if (!error) {
- xfs_disk_dquot_t *ddqp = &dqp->q_core;
+ ddqp = &dqp->q_core;
+ defq = xfs_get_defquota(dqp, qinf);
- defq = xfs_get_defquota(dqp, qinf);
+ /*
+ * Timers and warnings have been already set, let's just set the
+ * default limits for this quota type
+ */
+ defq->bhardlimit = be64_to_cpu(ddqp->d_blk_hardlimit);
+ defq->bsoftlimit = be64_to_cpu(ddqp->d_blk_softlimit);
+ defq->ihardlimit = be64_to_cpu(ddqp->d_ino_hardlimit);
+ defq->isoftlimit = be64_to_cpu(ddqp->d_ino_softlimit);
+ defq->rtbhardlimit = be64_to_cpu(ddqp->d_rtb_hardlimit);
+ defq->rtbsoftlimit = be64_to_cpu(ddqp->d_rtb_softlimit);
+ xfs_qm_dqdestroy(dqp);
+}
- /*
- * Timers and warnings have been already set, let's just set the
- * default limits for this quota type
- */
- defq->bhardlimit = be64_to_cpu(ddqp->d_blk_hardlimit);
- defq->bsoftlimit = be64_to_cpu(ddqp->d_blk_softlimit);
- defq->ihardlimit = be64_to_cpu(ddqp->d_ino_hardlimit);
- defq->isoftlimit = be64_to_cpu(ddqp->d_ino_softlimit);
- defq->rtbhardlimit = be64_to_cpu(ddqp->d_rtb_hardlimit);
- defq->rtbsoftlimit = be64_to_cpu(ddqp->d_rtb_softlimit);
- xfs_qm_dqdestroy(dqp);
- }
+/* Initialize quota time limits from the root dquot. */
+static void
+xfs_qm_init_timelimits(
+ struct xfs_mount *mp,
+ struct xfs_quotainfo *qinf)
+{
+ struct xfs_disk_dquot *ddqp;
+ struct xfs_dquot *dqp;
+ uint type;
+ int error;
+
+ qinf->qi_btimelimit = XFS_QM_BTIMELIMIT;
+ qinf->qi_itimelimit = XFS_QM_ITIMELIMIT;
+ qinf->qi_rtbtimelimit = XFS_QM_RTBTIMELIMIT;
+ qinf->qi_bwarnlimit = XFS_QM_BWARNLIMIT;
+ qinf->qi_iwarnlimit = XFS_QM_IWARNLIMIT;
+ qinf->qi_rtbwarnlimit = XFS_QM_RTBWARNLIMIT;
+
+ /*
+ * We try to get the limits from the superuser's limits fields.
+ * This is quite hacky, but it is standard quota practice.
+ *
+ * Since we may not have done a quotacheck by this point, just read
+ * the dquot without attaching it to any hashtables or lists.
+ *
+ * Timers and warnings are globally set by the first timer found in
+ * user/group/proj quota types, otherwise a default value is used.
+ * This should be split into different fields per quota type.
+ */
+ if (XFS_IS_UQUOTA_RUNNING(mp))
+ type = XFS_DQ_USER;
+ else if (XFS_IS_GQUOTA_RUNNING(mp))
+ type = XFS_DQ_GROUP;
+ else
+ type = XFS_DQ_PROJ;
+ error = xfs_qm_dqget_uncached(mp, 0, type, &dqp);
+ if (error)
+ return;
+
+ ddqp = &dqp->q_core;
+ /*
+ * The warnings and timers set the grace period given to
+ * a user or group before he or she can not perform any
+ * more writing. If it is zero, a default is used.
+ */
+ if (ddqp->d_btimer)
+ qinf->qi_btimelimit = be32_to_cpu(ddqp->d_btimer);
+ if (ddqp->d_itimer)
+ qinf->qi_itimelimit = be32_to_cpu(ddqp->d_itimer);
+ if (ddqp->d_rtbtimer)
+ qinf->qi_rtbtimelimit = be32_to_cpu(ddqp->d_rtbtimer);
+ if (ddqp->d_bwarns)
+ qinf->qi_bwarnlimit = be16_to_cpu(ddqp->d_bwarns);
+ if (ddqp->d_iwarns)
+ qinf->qi_iwarnlimit = be16_to_cpu(ddqp->d_iwarns);
+ if (ddqp->d_rtbwarns)
+ qinf->qi_rtbwarnlimit = be16_to_cpu(ddqp->d_rtbwarns);
+
+ xfs_qm_dqdestroy(dqp);
}
/*
@@ -600,11 +651,10 @@ xfs_qm_set_defquota(
*/
STATIC int
xfs_qm_init_quotainfo(
- xfs_mount_t *mp)
+ struct xfs_mount *mp)
{
- xfs_quotainfo_t *qinf;
- int error;
- xfs_dquot_t *dqp;
+ struct xfs_quotainfo *qinf;
+ int error;
ASSERT(XFS_IS_QUOTA_RUNNING(mp));
@@ -636,52 +686,7 @@ xfs_qm_init_quotainfo(
mp->m_qflags |= (mp->m_sb.sb_qflags & XFS_ALL_QUOTA_CHKD);
- /*
- * We try to get the limits from the superuser's limits fields.
- * This is quite hacky, but it is standard quota practice.
- *
- * Since we may not have done a quotacheck by this point, just read
- * the dquot without attaching it to any hashtables or lists.
- *
- * Timers and warnings are globally set by the first timer found in
- * user/group/proj quota types, otherwise a default value is used.
- * This should be split into different fields per quota type.
- */
- error = xfs_qm_dqread(mp, 0,
- XFS_IS_UQUOTA_RUNNING(mp) ? XFS_DQ_USER :
- (XFS_IS_GQUOTA_RUNNING(mp) ? XFS_DQ_GROUP :
- XFS_DQ_PROJ),
- 0, &dqp);
-
- if (!error) {
- xfs_disk_dquot_t *ddqp = &dqp->q_core;
-
- /*
- * The warnings and timers set the grace period given to
- * a user or group before he or she can not perform any
- * more writing. If it is zero, a default is used.
- */
- qinf->qi_btimelimit = ddqp->d_btimer ?
- be32_to_cpu(ddqp->d_btimer) : XFS_QM_BTIMELIMIT;
- qinf->qi_itimelimit = ddqp->d_itimer ?
- be32_to_cpu(ddqp->d_itimer) : XFS_QM_ITIMELIMIT;
- qinf->qi_rtbtimelimit = ddqp->d_rtbtimer ?
- be32_to_cpu(ddqp->d_rtbtimer) : XFS_QM_RTBTIMELIMIT;
- qinf->qi_bwarnlimit = ddqp->d_bwarns ?
- be16_to_cpu(ddqp->d_bwarns) : XFS_QM_BWARNLIMIT;
- qinf->qi_iwarnlimit = ddqp->d_iwarns ?
- be16_to_cpu(ddqp->d_iwarns) : XFS_QM_IWARNLIMIT;
- qinf->qi_rtbwarnlimit = ddqp->d_rtbwarns ?
- be16_to_cpu(ddqp->d_rtbwarns) : XFS_QM_RTBWARNLIMIT;
- xfs_qm_dqdestroy(dqp);
- } else {
- qinf->qi_btimelimit = XFS_QM_BTIMELIMIT;
- qinf->qi_itimelimit = XFS_QM_ITIMELIMIT;
- qinf->qi_rtbtimelimit = XFS_QM_RTBTIMELIMIT;
- qinf->qi_bwarnlimit = XFS_QM_BWARNLIMIT;
- qinf->qi_iwarnlimit = XFS_QM_IWARNLIMIT;
- qinf->qi_rtbwarnlimit = XFS_QM_RTBWARNLIMIT;
- }
+ xfs_qm_init_timelimits(mp, qinf);
if (XFS_IS_UQUOTA_RUNNING(mp))
xfs_qm_set_defquota(mp, XFS_DQ_USER, qinf);
@@ -865,9 +870,9 @@ xfs_qm_reset_dqcounts(
* find uninitialised dquot blks. See comment in
* xfs_dquot_verify.
*/
- fa = xfs_dquot_verify(mp, ddq, id + j, type, 0);
+ fa = xfs_dqblk_verify(mp, &dqb[j], id + j, type);
if (fa)
- xfs_dquot_repair(mp, ddq, id + j, type);
+ xfs_dqblk_repair(mp, &dqb[j], id + j, type);
/*
* Reset type in case we are reusing group quota file for
@@ -893,7 +898,7 @@ xfs_qm_reset_dqcounts(
}
STATIC int
-xfs_qm_dqiter_bufs(
+xfs_qm_reset_dqcounts_all(
struct xfs_mount *mp,
xfs_dqid_t firstid,
xfs_fsblock_t bno,
@@ -961,11 +966,11 @@ xfs_qm_dqiter_bufs(
}
/*
- * Iterate over all allocated USR/GRP/PRJ dquots in the system, calling a
- * caller supplied function for every chunk of dquots that we find.
+ * Iterate over all allocated dquot blocks in this quota inode, zeroing all
+ * counters for every chunk of dquots that we find.
*/
STATIC int
-xfs_qm_dqiterate(
+xfs_qm_reset_dqcounts_buf(
struct xfs_mount *mp,
struct xfs_inode *qip,
uint flags,
@@ -1041,7 +1046,7 @@ xfs_qm_dqiterate(
* Iterate thru all the blks in the extent and
* reset the counters of all the dquots inside them.
*/
- error = xfs_qm_dqiter_bufs(mp, firstid,
+ error = xfs_qm_reset_dqcounts_all(mp, firstid,
map[i].br_startblock,
map[i].br_blockcount,
flags, buffer_list);
@@ -1066,16 +1071,17 @@ xfs_qm_dqiterate(
STATIC int
xfs_qm_quotacheck_dqadjust(
struct xfs_inode *ip,
- xfs_dqid_t id,
uint type,
xfs_qcnt_t nblks,
xfs_qcnt_t rtblks)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_dquot *dqp;
+ xfs_dqid_t id;
int error;
- error = xfs_qm_dqget(mp, ip, id, type, XFS_QMOPT_DQALLOC, &dqp);
+ id = xfs_qm_id_for_quotatype(ip, type);
+ error = xfs_qm_dqget(mp, id, type, true, &dqp);
if (error) {
/*
* Shouldn't be able to turn off quotas here.
@@ -1148,13 +1154,10 @@ xfs_qm_dqusage_adjust(
}
/*
- * We don't _need_ to take the ilock EXCL. However, the xfs_qm_dqget
- * interface expects the inode to be exclusively locked because that's
- * the case in all other instances. It's OK that we do this because
- * quotacheck is done only at mount time.
+ * We don't _need_ to take the ilock EXCL here because quotacheck runs
+ * at mount time and therefore nobody will be racing chown/chproj.
*/
- error = xfs_iget(mp, NULL, ino, XFS_IGET_DONTCACHE, XFS_ILOCK_EXCL,
- &ip);
+ error = xfs_iget(mp, NULL, ino, XFS_IGET_DONTCACHE, 0, &ip);
if (error) {
*res = BULKSTAT_RV_NOTHING;
return error;
@@ -1189,33 +1192,31 @@ xfs_qm_dqusage_adjust(
* and quotaoffs don't race. (Quotachecks happen at mount time only).
*/
if (XFS_IS_UQUOTA_ON(mp)) {
- error = xfs_qm_quotacheck_dqadjust(ip, ip->i_d.di_uid,
- XFS_DQ_USER, nblks, rtblks);
+ error = xfs_qm_quotacheck_dqadjust(ip, XFS_DQ_USER, nblks,
+ rtblks);
if (error)
goto error0;
}
if (XFS_IS_GQUOTA_ON(mp)) {
- error = xfs_qm_quotacheck_dqadjust(ip, ip->i_d.di_gid,
- XFS_DQ_GROUP, nblks, rtblks);
+ error = xfs_qm_quotacheck_dqadjust(ip, XFS_DQ_GROUP, nblks,
+ rtblks);
if (error)
goto error0;
}
if (XFS_IS_PQUOTA_ON(mp)) {
- error = xfs_qm_quotacheck_dqadjust(ip, xfs_get_projid(ip),
- XFS_DQ_PROJ, nblks, rtblks);
+ error = xfs_qm_quotacheck_dqadjust(ip, XFS_DQ_PROJ, nblks,
+ rtblks);
if (error)
goto error0;
}
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
IRELE(ip);
*res = BULKSTAT_RV_DIDONE;
return 0;
error0:
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
IRELE(ip);
*res = BULKSTAT_RV_GIVEUP;
return error;
@@ -1247,9 +1248,8 @@ xfs_qm_flush_one(
*/
if (!xfs_dqflock_nowait(dqp)) {
/* buf is pinned in-core by delwri list */
- DEFINE_SINGLE_BUF_MAP(map, dqp->q_blkno,
- mp->m_quotainfo->qi_dqchunklen);
- bp = _xfs_buf_find(mp->m_ddev_targp, &map, 1, 0, NULL);
+ bp = xfs_buf_incore(mp->m_ddev_targp, dqp->q_blkno,
+ mp->m_quotainfo->qi_dqchunklen, 0);
if (!bp) {
error = -EINVAL;
goto out_unlock;
@@ -1307,7 +1307,7 @@ xfs_qm_quotacheck(
* We don't log our changes till later.
*/
if (uip) {
- error = xfs_qm_dqiterate(mp, uip, XFS_QMOPT_UQUOTA,
+ error = xfs_qm_reset_dqcounts_buf(mp, uip, XFS_QMOPT_UQUOTA,
&buffer_list);
if (error)
goto error_return;
@@ -1315,7 +1315,7 @@ xfs_qm_quotacheck(
}
if (gip) {
- error = xfs_qm_dqiterate(mp, gip, XFS_QMOPT_GQUOTA,
+ error = xfs_qm_reset_dqcounts_buf(mp, gip, XFS_QMOPT_GQUOTA,
&buffer_list);
if (error)
goto error_return;
@@ -1323,7 +1323,7 @@ xfs_qm_quotacheck(
}
if (pip) {
- error = xfs_qm_dqiterate(mp, pip, XFS_QMOPT_PQUOTA,
+ error = xfs_qm_reset_dqcounts_buf(mp, pip, XFS_QMOPT_PQUOTA,
&buffer_list);
if (error)
goto error_return;
@@ -1675,7 +1675,7 @@ xfs_qm_vop_dqalloc(
* if necessary. The dquot(s) will not be locked.
*/
if (XFS_NOT_DQATTACHED(mp, ip)) {
- error = xfs_qm_dqattach_locked(ip, XFS_QMOPT_DQALLOC);
+ error = xfs_qm_dqattach_locked(ip, true);
if (error) {
xfs_iunlock(ip, lockflags);
return error;
@@ -1694,10 +1694,7 @@ xfs_qm_vop_dqalloc(
* holding ilock.
*/
xfs_iunlock(ip, lockflags);
- error = xfs_qm_dqget(mp, NULL, uid,
- XFS_DQ_USER,
- XFS_QMOPT_DQALLOC,
- &uq);
+ error = xfs_qm_dqget(mp, uid, XFS_DQ_USER, true, &uq);
if (error) {
ASSERT(error != -ENOENT);
return error;
@@ -1720,10 +1717,7 @@ xfs_qm_vop_dqalloc(
if ((flags & XFS_QMOPT_GQUOTA) && XFS_IS_GQUOTA_ON(mp)) {
if (ip->i_d.di_gid != gid) {
xfs_iunlock(ip, lockflags);
- error = xfs_qm_dqget(mp, NULL, gid,
- XFS_DQ_GROUP,
- XFS_QMOPT_DQALLOC,
- &gq);
+ error = xfs_qm_dqget(mp, gid, XFS_DQ_GROUP, true, &gq);
if (error) {
ASSERT(error != -ENOENT);
goto error_rele;
@@ -1739,10 +1733,8 @@ xfs_qm_vop_dqalloc(
if ((flags & XFS_QMOPT_PQUOTA) && XFS_IS_PQUOTA_ON(mp)) {
if (xfs_get_projid(ip) != prid) {
xfs_iunlock(ip, lockflags);
- error = xfs_qm_dqget(mp, NULL, (xfs_dqid_t)prid,
- XFS_DQ_PROJ,
- XFS_QMOPT_DQALLOC,
- &pq);
+ error = xfs_qm_dqget(mp, (xfs_dqid_t)prid, XFS_DQ_PROJ,
+ true, &pq);
if (error) {
ASSERT(error != -ENOENT);
goto error_rele;
@@ -1933,7 +1925,7 @@ xfs_qm_vop_rename_dqattach(
*/
if (i == 0 || ip != i_tab[i-1]) {
if (XFS_NOT_DQATTACHED(mp, ip)) {
- error = xfs_qm_dqattach(ip, 0);
+ error = xfs_qm_dqattach(ip);
if (error)
return error;
}
diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h
index 2975a82..e3129b2 100644
--- a/fs/xfs/xfs_qm.h
+++ b/fs/xfs/xfs_qm.h
@@ -170,8 +170,10 @@ extern void xfs_qm_dqrele_all_inodes(struct xfs_mount *, uint);
/* quota ops */
extern int xfs_qm_scall_trunc_qfiles(struct xfs_mount *, uint);
-extern int xfs_qm_scall_getquota(struct xfs_mount *, xfs_dqid_t *,
- uint, struct qc_dqblk *, uint);
+extern int xfs_qm_scall_getquota(struct xfs_mount *, xfs_dqid_t,
+ uint, struct qc_dqblk *);
+extern int xfs_qm_scall_getquota_next(struct xfs_mount *,
+ xfs_dqid_t *, uint, struct qc_dqblk *);
extern int xfs_qm_scall_setqlim(struct xfs_mount *, xfs_dqid_t, uint,
struct qc_dqblk *);
extern int xfs_qm_scall_quotaon(struct xfs_mount *, uint);
diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c
index 2be6d27..36b89e2 100644
--- a/fs/xfs/xfs_qm_bhv.c
+++ b/fs/xfs/xfs_qm_bhv.c
@@ -72,7 +72,7 @@ xfs_qm_statvfs(
xfs_mount_t *mp = ip->i_mount;
xfs_dquot_t *dqp;
- if (!xfs_qm_dqget(mp, NULL, xfs_get_projid(ip), XFS_DQ_PROJ, 0, &dqp)) {
+ if (!xfs_qm_dqget(mp, xfs_get_projid(ip), XFS_DQ_PROJ, false, &dqp)) {
xfs_fill_statvfs_from_dquot(statp, dqp);
xfs_qm_dqput(dqp);
}
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index 9cb5c38..3e05d30 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -425,7 +425,7 @@ xfs_qm_scall_setqlim(
* a reference to the dquot, so it's safe to do this unlock/lock without
* it being reclaimed in the mean time.
*/
- error = xfs_qm_dqget(mp, NULL, id, type, XFS_QMOPT_DQALLOC, &dqp);
+ error = xfs_qm_dqget(mp, id, type, true, &dqp);
if (error) {
ASSERT(error != -ENOENT);
goto out_unlock;
@@ -622,39 +622,14 @@ xfs_qm_log_quotaoff(
return error;
}
-
-int
-xfs_qm_scall_getquota(
+/* Fill out the quota context. */
+static void
+xfs_qm_scall_getquota_fill_qc(
struct xfs_mount *mp,
- xfs_dqid_t *id,
uint type,
- struct qc_dqblk *dst,
- uint dqget_flags)
+ const struct xfs_dquot *dqp,
+ struct qc_dqblk *dst)
{
- struct xfs_dquot *dqp;
- int error;
-
- /*
- * Try to get the dquot. We don't want it allocated on disk, so
- * we aren't passing the XFS_QMOPT_DOALLOC flag. If it doesn't
- * exist, we'll get ENOENT back.
- */
- error = xfs_qm_dqget(mp, NULL, *id, type, dqget_flags, &dqp);
- if (error)
- return error;
-
- /*
- * If everything's NULL, this dquot doesn't quite exist as far as
- * our utility programs are concerned.
- */
- if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
- error = -ENOENT;
- goto out_put;
- }
-
- /* Fill in the ID we actually read from disk */
- *id = be32_to_cpu(dqp->q_core.d_id);
-
memset(dst, 0, sizeof(*dst));
dst->d_spc_hardlimit =
XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_hardlimit));
@@ -696,7 +671,7 @@ xfs_qm_scall_getquota(
if (((XFS_IS_UQUOTA_ENFORCED(mp) && type == XFS_DQ_USER) ||
(XFS_IS_GQUOTA_ENFORCED(mp) && type == XFS_DQ_GROUP) ||
(XFS_IS_PQUOTA_ENFORCED(mp) && type == XFS_DQ_PROJ)) &&
- *id != 0) {
+ dqp->q_core.d_id != 0) {
if ((dst->d_space > dst->d_spc_softlimit) &&
(dst->d_spc_softlimit > 0)) {
ASSERT(dst->d_spc_timer != 0);
@@ -707,11 +682,69 @@ xfs_qm_scall_getquota(
}
}
#endif
+}
+
+/* Return the quota information for the dquot matching id. */
+int
+xfs_qm_scall_getquota(
+ struct xfs_mount *mp,
+ xfs_dqid_t id,
+ uint type,
+ struct qc_dqblk *dst)
+{
+ struct xfs_dquot *dqp;
+ int error;
+
+ /*
+ * Try to get the dquot. We don't want it allocated on disk, so don't
+ * set doalloc. If it doesn't exist, we'll get ENOENT back.
+ */
+ error = xfs_qm_dqget(mp, id, type, false, &dqp);
+ if (error)
+ return error;
+
+ /*
+ * If everything's NULL, this dquot doesn't quite exist as far as
+ * our utility programs are concerned.
+ */
+ if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
+ error = -ENOENT;
+ goto out_put;
+ }
+
+ xfs_qm_scall_getquota_fill_qc(mp, type, dqp, dst);
+
out_put:
xfs_qm_dqput(dqp);
return error;
}
+/*
+ * Return the quota information for the first initialized dquot whose id
+ * is at least as high as id.
+ */
+int
+xfs_qm_scall_getquota_next(
+ struct xfs_mount *mp,
+ xfs_dqid_t *id,
+ uint type,
+ struct qc_dqblk *dst)
+{
+ struct xfs_dquot *dqp;
+ int error;
+
+ error = xfs_qm_dqget_next(mp, *id, type, &dqp);
+ if (error)
+ return error;
+
+ /* Fill in the ID we actually read from disk */
+ *id = be32_to_cpu(dqp->q_core.d_id);
+
+ xfs_qm_scall_getquota_fill_qc(mp, type, dqp, dst);
+
+ xfs_qm_dqput(dqp);
+ return error;
+}
STATIC int
xfs_dqrele_inode(
diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h
index ce6506a..3edf52b 100644
--- a/fs/xfs/xfs_quota.h
+++ b/fs/xfs/xfs_quota.h
@@ -48,6 +48,22 @@ struct xfs_trans;
(XFS_IS_PQUOTA_ON(mp) && \
(mp->m_sb.sb_qflags & XFS_PQUOTA_CHKD) == 0))
+static inline uint
+xfs_quota_chkd_flag(
+ uint dqtype)
+{
+ switch (dqtype) {
+ case XFS_DQ_USER:
+ return XFS_UQUOTA_CHKD;
+ case XFS_DQ_GROUP:
+ return XFS_GQUOTA_CHKD;
+ case XFS_DQ_PROJ:
+ return XFS_PQUOTA_CHKD;
+ default:
+ return 0;
+ }
+}
+
/*
* The structure kept inside the xfs_trans_t keep track of dquot changes
* within a transaction and apply them later.
@@ -90,8 +106,8 @@ extern struct xfs_dquot *xfs_qm_vop_chown(struct xfs_trans *,
extern int xfs_qm_vop_chown_reserve(struct xfs_trans *, struct xfs_inode *,
struct xfs_dquot *, struct xfs_dquot *,
struct xfs_dquot *, uint);
-extern int xfs_qm_dqattach(struct xfs_inode *, uint);
-extern int xfs_qm_dqattach_locked(struct xfs_inode *, uint);
+extern int xfs_qm_dqattach(struct xfs_inode *);
+extern int xfs_qm_dqattach_locked(struct xfs_inode *ip, bool doalloc);
extern void xfs_qm_dqdetach(struct xfs_inode *);
extern void xfs_qm_dqrele(struct xfs_dquot *);
extern void xfs_qm_statvfs(struct xfs_inode *, struct kstatfs *);
@@ -132,7 +148,7 @@ static inline int xfs_trans_reserve_quota_bydquots(struct xfs_trans *tp,
#define xfs_qm_vop_rename_dqattach(it) (0)
#define xfs_qm_vop_chown(tp, ip, old, new) (NULL)
#define xfs_qm_vop_chown_reserve(tp, ip, u, g, p, fl) (0)
-#define xfs_qm_dqattach(ip, fl) (0)
+#define xfs_qm_dqattach(ip) (0)
#define xfs_qm_dqattach_locked(ip, fl) (0)
#define xfs_qm_dqdetach(ip)
#define xfs_qm_dqrele(d)
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index a651085..c93fc91 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -239,8 +239,7 @@ xfs_fs_get_dqblk(
return -ESRCH;
id = from_kqid(&init_user_ns, qid);
- return xfs_qm_scall_getquota(mp, &id,
- xfs_quota_type(qid.type), qdq, 0);
+ return xfs_qm_scall_getquota(mp, id, xfs_quota_type(qid.type), qdq);
}
/* Return quota info for active quota >= this qid */
@@ -260,9 +259,8 @@ xfs_fs_get_nextdqblk(
return -ESRCH;
id = from_kqid(&init_user_ns, *qid);
- ret = xfs_qm_scall_getquota(mp, &id,
- xfs_quota_type(qid->type), qdq,
- XFS_QMOPT_DQNEXT);
+ ret = xfs_qm_scall_getquota_next(mp, &id, xfs_quota_type(qid->type),
+ qdq);
if (ret)
return ret;
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 15c9393..e5866b7 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -159,7 +159,7 @@ STATIC void
xfs_cui_item_unlock(
struct xfs_log_item *lip)
{
- if (lip->li_flags & XFS_LI_ABORTED)
+ if (test_bit(XFS_LI_ABORTED, &lip->li_flags))
xfs_cui_release(CUI_ITEM(lip));
}
@@ -310,7 +310,7 @@ xfs_cud_item_unlock(
{
struct xfs_cud_log_item *cudp = CUD_ITEM(lip);
- if (lip->li_flags & XFS_LI_ABORTED) {
+ if (test_bit(XFS_LI_ABORTED, &lip->li_flags)) {
xfs_cui_release(cudp->cud_cuip);
kmem_zone_free(xfs_cud_zone, cudp);
}
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index cdbd342..713e857 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -305,7 +305,7 @@ xfs_reflink_reserve_cow(
* Fork all the shared blocks from our write offset until the end of
* the extent.
*/
- error = xfs_qm_dqattach_locked(ip, 0);
+ error = xfs_qm_dqattach_locked(ip, false);
if (error)
return error;
@@ -431,7 +431,7 @@ xfs_reflink_allocate_cow(
if (error)
return error;
- error = xfs_qm_dqattach_locked(ip, 0);
+ error = xfs_qm_dqattach_locked(ip, false);
if (error)
goto out;
goto retry;
@@ -552,6 +552,9 @@ xfs_reflink_trim_irec_to_next_cow(
*
* If cancel_real is true this function cancels all COW fork extents for the
* inode; if cancel_real is false, real extents are not cleared.
+ *
+ * Caller must have already joined the inode to the current transaction. The
+ * inode will be joined to the transaction returned to the caller.
*/
int
xfs_reflink_cancel_cow_blocks(
@@ -592,7 +595,6 @@ xfs_reflink_cancel_cow_blocks(
if (error)
break;
} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
- xfs_trans_ijoin(*tpp, ip, 0);
xfs_defer_init(&dfops, &firstfsb);
/* Free the CoW orphan record. */
@@ -1359,7 +1361,7 @@ xfs_reflink_remap_range(
goto out_unlock;
/* Attach dquots to dest inode before changing block map */
- ret = xfs_qm_dqattach(dest, 0);
+ ret = xfs_qm_dqattach(dest);
if (ret)
goto out_unlock;
@@ -1551,7 +1553,12 @@ xfs_reflink_inode_has_shared_extents(
return 0;
}
-/* Clear the inode reflink flag if there are no shared extents. */
+/*
+ * Clear the inode reflink flag if there are no shared extents.
+ *
+ * The caller is responsible for joining the inode to the transaction passed in.
+ * The inode will be joined to the transaction that is returned to the caller.
+ */
int
xfs_reflink_clear_inode_flag(
struct xfs_inode *ip,
@@ -1578,7 +1585,6 @@ xfs_reflink_clear_inode_flag(
trace_xfs_reflink_unset_inode_flag(ip);
ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
xfs_inode_clear_cowblocks_tag(ip);
- xfs_trans_ijoin(*tpp, ip, 0);
xfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE);
return error;
diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c
index 06a0784..e5b5b3e 100644
--- a/fs/xfs/xfs_rmap_item.c
+++ b/fs/xfs/xfs_rmap_item.c
@@ -158,7 +158,7 @@ STATIC void
xfs_rui_item_unlock(
struct xfs_log_item *lip)
{
- if (lip->li_flags & XFS_LI_ABORTED)
+ if (test_bit(XFS_LI_ABORTED, &lip->li_flags))
xfs_rui_release(RUI_ITEM(lip));
}
@@ -331,7 +331,7 @@ xfs_rud_item_unlock(
{
struct xfs_rud_log_item *rudp = RUD_ITEM(lip);
- if (lip->li_flags & XFS_LI_ABORTED) {
+ if (test_bit(XFS_LI_ABORTED, &lip->li_flags)) {
xfs_rui_release(rudp->rud_ruip);
kmem_zone_free(xfs_rud_zone, rudp);
}
diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h
index dfee3c9..52632ab 100644
--- a/fs/xfs/xfs_rtalloc.h
+++ b/fs/xfs/xfs_rtalloc.h
@@ -23,9 +23,14 @@
struct xfs_mount;
struct xfs_trans;
+/*
+ * XXX: Most of the realtime allocation functions deal in units of realtime
+ * extents, not realtime blocks. This looks funny when paired with the type
+ * name and screams for a larger cleanup.
+ */
struct xfs_rtalloc_rec {
- xfs_rtblock_t ar_startblock;
- xfs_rtblock_t ar_blockcount;
+ xfs_rtblock_t ar_startext;
+ xfs_rtblock_t ar_extcount;
};
typedef int (*xfs_rtalloc_query_range_fn)(
diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c
index 056e12b..1cc7990 100644
--- a/fs/xfs/xfs_stats.c
+++ b/fs/xfs/xfs_stats.c
@@ -113,6 +113,7 @@ void xfs_stats_clearall(struct xfsstats __percpu *stats)
}
}
+#ifdef CONFIG_PROC_FS
/* legacy quota interfaces */
#ifdef CONFIG_XFS_QUOTA
static int xqm_proc_show(struct seq_file *m, void *v)
@@ -124,18 +125,6 @@ static int xqm_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int xqm_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, xqm_proc_show, NULL);
-}
-
-static const struct file_operations xqm_proc_fops = {
- .open = xqm_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/* legacy quota stats interface no 2 */
static int xqmstat_proc_show(struct seq_file *m, void *v)
{
@@ -147,22 +136,8 @@ static int xqmstat_proc_show(struct seq_file *m, void *v)
seq_putc(m, '\n');
return 0;
}
-
-static int xqmstat_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, xqmstat_proc_show, NULL);
-}
-
-static const struct file_operations xqmstat_proc_fops = {
- .owner = THIS_MODULE,
- .open = xqmstat_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif /* CONFIG_XFS_QUOTA */
-#ifdef CONFIG_PROC_FS
int
xfs_init_procfs(void)
{
@@ -174,11 +149,9 @@ xfs_init_procfs(void)
goto out;
#ifdef CONFIG_XFS_QUOTA
- if (!proc_create("fs/xfs/xqmstat", 0, NULL,
- &xqmstat_proc_fops))
+ if (!proc_create_single("fs/xfs/xqmstat", 0, NULL, xqmstat_proc_show))
goto out;
- if (!proc_create("fs/xfs/xqm", 0, NULL,
- &xqm_proc_fops))
+ if (!proc_create_single("fs/xfs/xqm", 0, NULL, xqm_proc_show))
goto out;
#endif
return 0;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index d714240..ed67389 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -63,7 +63,7 @@
#include <linux/parser.h>
static const struct super_operations xfs_super_operations;
-struct bio_set *xfs_ioend_bioset;
+struct bio_set xfs_ioend_bioset;
static struct kset *xfs_kset; /* top-level xfs sysfs dir */
#ifdef DEBUG
@@ -1372,7 +1372,6 @@ xfs_fs_remount(
*/
xfs_restore_resvblks(mp);
xfs_log_work_queue(mp);
- xfs_queue_eofblocks(mp);
/* Recover any CoW blocks that never got remapped. */
error = xfs_reflink_recover_cow(mp);
@@ -1382,7 +1381,7 @@ xfs_fs_remount(
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
return error;
}
- xfs_queue_cowblocks(mp);
+ xfs_icache_enable_reclaim(mp);
/* Create the per-AG metadata reservation pool .*/
error = xfs_fs_reserve_ag_blocks(mp);
@@ -1392,8 +1391,13 @@ xfs_fs_remount(
/* rw -> ro */
if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & SB_RDONLY)) {
+ /*
+ * Cancel background eofb scanning so it cannot race with the
+ * final log force+buftarg wait and deadlock the remount.
+ */
+ xfs_icache_disable_reclaim(mp);
+
/* Get rid of any leftover CoW reservations... */
- cancel_delayed_work_sync(&mp->m_cowblocks_work);
error = xfs_icache_free_cowblocks(mp, NULL);
if (error) {
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
@@ -1416,12 +1420,6 @@ xfs_fs_remount(
*/
xfs_save_resvblks(mp);
- /*
- * Cancel background eofb scanning so it cannot race with the
- * final log force+buftarg wait and deadlock the remount.
- */
- cancel_delayed_work_sync(&mp->m_eofblocks_work);
-
xfs_quiesce_attr(mp);
mp->m_flags |= XFS_MOUNT_RDONLY;
}
@@ -1441,6 +1439,7 @@ xfs_fs_freeze(
{
struct xfs_mount *mp = XFS_M(sb);
+ xfs_icache_disable_reclaim(mp);
xfs_save_resvblks(mp);
xfs_quiesce_attr(mp);
return xfs_sync_sb(mp, true);
@@ -1454,6 +1453,7 @@ xfs_fs_unfreeze(
xfs_restore_resvblks(mp);
xfs_log_work_queue(mp);
+ xfs_icache_enable_reclaim(mp);
return 0;
}
@@ -1635,6 +1635,17 @@ xfs_fs_fill_super(
#endif
sb->s_op = &xfs_super_operations;
+ /*
+ * Delay mount work if the debug hook is set. This is debug
+ * instrumention to coordinate simulation of xfs mount failures with
+ * VFS superblock operations
+ */
+ if (xfs_globals.mount_delay) {
+ xfs_notice(mp, "Delaying mount for %d seconds.",
+ xfs_globals.mount_delay);
+ msleep(xfs_globals.mount_delay * 1000);
+ }
+
if (silent)
flags |= XFS_MFSI_QUIET;
@@ -1690,11 +1701,17 @@ xfs_fs_fill_super(
sb->s_flags |= SB_I_VERSION;
if (mp->m_flags & XFS_MOUNT_DAX) {
+ bool rtdev_is_dax = false, datadev_is_dax;
+
xfs_warn(mp,
"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
- error = bdev_dax_supported(sb, sb->s_blocksize);
- if (error) {
+ datadev_is_dax = bdev_dax_supported(mp->m_ddev_targp->bt_bdev,
+ sb->s_blocksize);
+ if (mp->m_rtdev_targp)
+ rtdev_is_dax = bdev_dax_supported(
+ mp->m_rtdev_targp->bt_bdev, sb->s_blocksize);
+ if (!rtdev_is_dax && !datadev_is_dax) {
xfs_alert(mp,
"DAX unsupported by block device. Turning off DAX.");
mp->m_flags &= ~XFS_MOUNT_DAX;
@@ -1761,6 +1778,7 @@ xfs_fs_fill_super(
out_close_devices:
xfs_close_devices(mp);
out_free_fsname:
+ sb->s_fs_info = NULL;
xfs_free_fsname(mp);
kfree(mp);
out:
@@ -1778,6 +1796,10 @@ xfs_fs_put_super(
{
struct xfs_mount *mp = XFS_M(sb);
+ /* if ->fill_super failed, we have no mount to tear down */
+ if (!sb->s_fs_info)
+ return;
+
xfs_notice(mp, "Unmounting Filesystem");
xfs_filestream_unmount(mp);
xfs_unmountfs(mp);
@@ -1787,6 +1809,8 @@ xfs_fs_put_super(
xfs_destroy_percpu_counters(mp);
xfs_destroy_mount_workqueues(mp);
xfs_close_devices(mp);
+
+ sb->s_fs_info = NULL;
xfs_free_fsname(mp);
kfree(mp);
}
@@ -1806,6 +1830,9 @@ xfs_fs_nr_cached_objects(
struct super_block *sb,
struct shrink_control *sc)
{
+ /* Paranoia: catch incorrect calls during mount setup or teardown */
+ if (WARN_ON_ONCE(!sb->s_fs_info))
+ return 0;
return xfs_reclaim_inodes_count(XFS_M(sb));
}
@@ -1845,10 +1872,9 @@ MODULE_ALIAS_FS("xfs");
STATIC int __init
xfs_init_zones(void)
{
- xfs_ioend_bioset = bioset_create(4 * MAX_BUF_PER_PAGE,
+ if (bioset_init(&xfs_ioend_bioset, 4 * MAX_BUF_PER_PAGE,
offsetof(struct xfs_ioend, io_inline_bio),
- BIOSET_NEED_BVECS);
- if (!xfs_ioend_bioset)
+ BIOSET_NEED_BVECS))
goto out;
xfs_log_ticket_zone = kmem_zone_init(sizeof(xlog_ticket_t),
@@ -1880,11 +1906,6 @@ xfs_init_zones(void)
if (!xfs_trans_zone)
goto out_destroy_ifork_zone;
- xfs_log_item_desc_zone =
- kmem_zone_init(sizeof(struct xfs_log_item_desc),
- "xfs_log_item_desc");
- if (!xfs_log_item_desc_zone)
- goto out_destroy_trans_zone;
/*
* The size of the zone allocated buf log item is the maximum
@@ -1894,7 +1915,7 @@ xfs_init_zones(void)
xfs_buf_item_zone = kmem_zone_init(sizeof(struct xfs_buf_log_item),
"xfs_buf_item");
if (!xfs_buf_item_zone)
- goto out_destroy_log_item_desc_zone;
+ goto out_destroy_trans_zone;
xfs_efd_zone = kmem_zone_init((sizeof(xfs_efd_log_item_t) +
((XFS_EFD_MAX_FAST_EXTENTS - 1) *
@@ -1982,8 +2003,6 @@ xfs_init_zones(void)
kmem_zone_destroy(xfs_efd_zone);
out_destroy_buf_item_zone:
kmem_zone_destroy(xfs_buf_item_zone);
- out_destroy_log_item_desc_zone:
- kmem_zone_destroy(xfs_log_item_desc_zone);
out_destroy_trans_zone:
kmem_zone_destroy(xfs_trans_zone);
out_destroy_ifork_zone:
@@ -1997,7 +2016,7 @@ xfs_init_zones(void)
out_destroy_log_ticket_zone:
kmem_zone_destroy(xfs_log_ticket_zone);
out_free_ioend_bioset:
- bioset_free(xfs_ioend_bioset);
+ bioset_exit(&xfs_ioend_bioset);
out:
return -ENOMEM;
}
@@ -2022,14 +2041,13 @@ xfs_destroy_zones(void)
kmem_zone_destroy(xfs_efi_zone);
kmem_zone_destroy(xfs_efd_zone);
kmem_zone_destroy(xfs_buf_item_zone);
- kmem_zone_destroy(xfs_log_item_desc_zone);
kmem_zone_destroy(xfs_trans_zone);
kmem_zone_destroy(xfs_ifork_zone);
kmem_zone_destroy(xfs_da_state_zone);
kmem_zone_destroy(xfs_btree_cur_zone);
kmem_zone_destroy(xfs_bmap_free_item_zone);
kmem_zone_destroy(xfs_log_ticket_zone);
- bioset_free(xfs_ioend_bioset);
+ bioset_exit(&xfs_ioend_bioset);
}
STATIC int __init
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 5b66ac1..aed03da 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -259,6 +259,7 @@ xfs_symlink(
* bmapi or the directory create code.
*/
xfs_defer_init(&dfops, &first_block);
+ tp->t_agfl_dfops = &dfops;
/*
* Allocate an inode for the symlink.
@@ -488,16 +489,11 @@ xfs_inactive_symlink_rmt(
error = xfs_defer_finish(&tp, &dfops);
if (error)
goto error_bmap_cancel;
- /*
- * The first xact was committed, so add the inode to the new one.
- * Mark it dirty so it will be logged and moved forward in the log as
- * part of every commit.
- */
- xfs_trans_ijoin(tp, ip, 0);
- xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
/*
* Commit the transaction containing extent freeing and EFDs.
*/
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
error = xfs_trans_commit(tp);
if (error) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
diff --git a/fs/xfs/xfs_sysctl.h b/fs/xfs/xfs_sysctl.h
index 82afee0..b53a33e 100644
--- a/fs/xfs/xfs_sysctl.h
+++ b/fs/xfs/xfs_sysctl.h
@@ -95,6 +95,7 @@ extern xfs_param_t xfs_params;
struct xfs_globals {
int log_recovery_delay; /* log recovery delay (secs) */
+ int mount_delay; /* mount setup delay (secs) */
bool bug_on_assert; /* BUG() the kernel on assert failure */
};
extern struct xfs_globals xfs_globals;
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index 8b2ccc2..2d5cd25 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -165,9 +165,40 @@ log_recovery_delay_show(
}
XFS_SYSFS_ATTR_RW(log_recovery_delay);
+STATIC ssize_t
+mount_delay_store(
+ struct kobject *kobject,
+ const char *buf,
+ size_t count)
+{
+ int ret;
+ int val;
+
+ ret = kstrtoint(buf, 0, &val);
+ if (ret)
+ return ret;
+
+ if (val < 0 || val > 60)
+ return -EINVAL;
+
+ xfs_globals.mount_delay = val;
+
+ return count;
+}
+
+STATIC ssize_t
+mount_delay_show(
+ struct kobject *kobject,
+ char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.mount_delay);
+}
+XFS_SYSFS_ATTR_RW(mount_delay);
+
static struct attribute *xfs_dbg_attrs[] = {
ATTR_LIST(bug_on_assert),
ATTR_LIST(log_recovery_delay),
+ ATTR_LIST(mount_delay),
NULL,
};
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 8955254..9d4c4ca 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -441,8 +441,7 @@ DECLARE_EVENT_CLASS(xfs_buf_item_class,
__field(unsigned, bli_recur)
__field(int, bli_refcount)
__field(unsigned, bli_flags)
- __field(void *, li_desc)
- __field(unsigned, li_flags)
+ __field(unsigned long, li_flags)
),
TP_fast_assign(
__entry->dev = bip->bli_buf->b_target->bt_dev;
@@ -455,12 +454,11 @@ DECLARE_EVENT_CLASS(xfs_buf_item_class,
__entry->buf_hold = atomic_read(&bip->bli_buf->b_hold);
__entry->buf_pincount = atomic_read(&bip->bli_buf->b_pin_count);
__entry->buf_lockval = bip->bli_buf->b_sema.count;
- __entry->li_desc = bip->bli_item.li_desc;
__entry->li_flags = bip->bli_item.li_flags;
),
TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d "
"lock %d flags %s recur %d refcount %d bliflags %s "
- "lidesc %p liflags %s",
+ "liflags %s",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->buf_bno,
__entry->buf_len,
@@ -471,7 +469,6 @@ DECLARE_EVENT_CLASS(xfs_buf_item_class,
__entry->bli_recur,
__entry->bli_refcount,
__print_flags(__entry->bli_flags, "|", XFS_BLI_FLAGS),
- __entry->li_desc,
__print_flags(__entry->li_flags, "|", XFS_LI_FLAGS))
)
@@ -1018,7 +1015,7 @@ DECLARE_EVENT_CLASS(xfs_log_item_class,
__field(dev_t, dev)
__field(void *, lip)
__field(uint, type)
- __field(uint, flags)
+ __field(unsigned long, flags)
__field(xfs_lsn_t, lsn)
),
TP_fast_assign(
@@ -1070,7 +1067,7 @@ DECLARE_EVENT_CLASS(xfs_ail_class,
__field(dev_t, dev)
__field(void *, lip)
__field(uint, type)
- __field(uint, flags)
+ __field(unsigned long, flags)
__field(xfs_lsn_t, old_lsn)
__field(xfs_lsn_t, new_lsn)
),
@@ -1750,6 +1747,7 @@ DECLARE_EVENT_CLASS(xfs_attr_class,
__field(int, namelen)
__field(int, valuelen)
__field(xfs_dahash_t, hashval)
+ __field(int, flags)
__field(int, op_flags)
),
TP_fast_assign(
@@ -1760,10 +1758,11 @@ DECLARE_EVENT_CLASS(xfs_attr_class,
__entry->namelen = args->namelen;
__entry->valuelen = args->valuelen;
__entry->hashval = args->hashval;
+ __entry->flags = args->flags;
__entry->op_flags = args->op_flags;
),
TP_printk("dev %d:%d ino 0x%llx name %.*s namelen %d valuelen %d "
- "hashval 0x%x op_flags %s",
+ "hashval 0x%x flags %s op_flags %s",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->ino,
__entry->namelen,
@@ -1771,6 +1770,7 @@ DECLARE_EVENT_CLASS(xfs_attr_class,
__entry->namelen,
__entry->valuelen,
__entry->hashval,
+ __print_flags(__entry->flags, "|", XFS_ATTR_FLAGS),
__print_flags(__entry->op_flags, "|", XFS_DA_OP_FLAGS))
)
@@ -2243,30 +2243,35 @@ struct xfs_defer_pending;
struct xfs_defer_ops;
DECLARE_EVENT_CLASS(xfs_defer_class,
- TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop),
- TP_ARGS(mp, dop),
+ TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop,
+ unsigned long caller_ip),
+ TP_ARGS(mp, dop, caller_ip),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(void *, dop)
__field(char, committed)
__field(char, low)
+ __field(unsigned long, caller_ip)
),
TP_fast_assign(
__entry->dev = mp ? mp->m_super->s_dev : 0;
__entry->dop = dop;
__entry->committed = dop->dop_committed;
__entry->low = dop->dop_low;
+ __entry->caller_ip = caller_ip;
),
- TP_printk("dev %d:%d ops %p committed %d low %d",
+ TP_printk("dev %d:%d ops %p committed %d low %d, caller %pS",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->dop,
__entry->committed,
- __entry->low)
+ __entry->low,
+ (char *)__entry->caller_ip)
)
#define DEFINE_DEFER_EVENT(name) \
DEFINE_EVENT(xfs_defer_class, name, \
- TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop), \
- TP_ARGS(mp, dop))
+ TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop, \
+ unsigned long caller_ip), \
+ TP_ARGS(mp, dop, caller_ip))
DECLARE_EVENT_CLASS(xfs_defer_error_class,
TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop, int error),
@@ -2433,6 +2438,8 @@ DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_abort);
#define DEFINE_BMAP_FREE_DEFERRED_EVENT DEFINE_PHYS_EXTENT_DEFERRED_EVENT
DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_bmap_free_defer);
DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_bmap_free_deferred);
+DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_agfl_free_defer);
+DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_agfl_free_deferred);
/* rmap tracepoints */
DECLARE_EVENT_CLASS(xfs_rmap_class,
@@ -3346,6 +3353,43 @@ TRACE_EVENT(xfs_trans_resv_calc,
__entry->logflags)
);
+DECLARE_EVENT_CLASS(xfs_trans_class,
+ TP_PROTO(struct xfs_trans *tp, unsigned long caller_ip),
+ TP_ARGS(tp, caller_ip),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(uint32_t, tid)
+ __field(uint32_t, flags)
+ __field(unsigned long, caller_ip)
+ ),
+ TP_fast_assign(
+ __entry->dev = tp->t_mountp->m_super->s_dev;
+ __entry->tid = 0;
+ if (tp->t_ticket)
+ __entry->tid = tp->t_ticket->t_tid;
+ __entry->flags = tp->t_flags;
+ __entry->caller_ip = caller_ip;
+ ),
+ TP_printk("dev %d:%d trans %x flags 0x%x caller %pS",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->tid,
+ __entry->flags,
+ (char *)__entry->caller_ip)
+)
+
+#define DEFINE_TRANS_EVENT(name) \
+DEFINE_EVENT(xfs_trans_class, name, \
+ TP_PROTO(struct xfs_trans *tp, unsigned long caller_ip), \
+ TP_ARGS(tp, caller_ip))
+DEFINE_TRANS_EVENT(xfs_trans_alloc);
+DEFINE_TRANS_EVENT(xfs_trans_cancel);
+DEFINE_TRANS_EVENT(xfs_trans_commit);
+DEFINE_TRANS_EVENT(xfs_trans_dup);
+DEFINE_TRANS_EVENT(xfs_trans_free);
+DEFINE_TRANS_EVENT(xfs_trans_roll);
+DEFINE_TRANS_EVENT(xfs_trans_add_item);
+DEFINE_TRANS_EVENT(xfs_trans_free_items);
+
#endif /* _TRACE_XFS_H */
#undef TRACE_INCLUDE_PATH
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index d6d8f9d..fc7ba75 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -31,9 +31,9 @@
#include "xfs_log.h"
#include "xfs_trace.h"
#include "xfs_error.h"
+#include "xfs_defer.h"
kmem_zone_t *xfs_trans_zone;
-kmem_zone_t *xfs_log_item_desc_zone;
#if defined(CONFIG_TRACEPOINTS)
static void
@@ -79,6 +79,7 @@ xfs_trans_free(
xfs_extent_busy_sort(&tp->t_busy);
xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false);
+ trace_xfs_trans_free(tp, _RET_IP_);
atomic_dec(&tp->t_mountp->m_active_trans);
if (!(tp->t_flags & XFS_TRANS_NO_WRITECOUNT))
sb_end_intwrite(tp->t_mountp->m_super);
@@ -94,11 +95,13 @@ xfs_trans_free(
* blocks. Locks and log items, however, are no inherited. They must
* be added to the new transaction explicitly.
*/
-STATIC xfs_trans_t *
+STATIC struct xfs_trans *
xfs_trans_dup(
- xfs_trans_t *tp)
+ struct xfs_trans *tp)
{
- xfs_trans_t *ntp;
+ struct xfs_trans *ntp;
+
+ trace_xfs_trans_dup(tp, _RET_IP_);
ntp = kmem_zone_zalloc(xfs_trans_zone, KM_SLEEP);
@@ -127,6 +130,7 @@ xfs_trans_dup(
ntp->t_rtx_res = tp->t_rtx_res - tp->t_rtx_res_used;
tp->t_rtx_res = tp->t_rtx_res_used;
ntp->t_pflags = tp->t_pflags;
+ ntp->t_agfl_dfops = tp->t_agfl_dfops;
xfs_trans_dup_dqinfo(tp, ntp);
@@ -283,6 +287,8 @@ xfs_trans_alloc(
return error;
}
+ trace_xfs_trans_alloc(tp, _RET_IP_);
+
*tpp = tp;
return 0;
}
@@ -727,73 +733,52 @@ xfs_trans_unreserve_and_mod_sb(
return;
}
-/*
- * Add the given log item to the transaction's list of log items.
- *
- * The log item will now point to its new descriptor with its li_desc field.
- */
+/* Add the given log item to the transaction's list of log items. */
void
xfs_trans_add_item(
struct xfs_trans *tp,
struct xfs_log_item *lip)
{
- struct xfs_log_item_desc *lidp;
-
ASSERT(lip->li_mountp == tp->t_mountp);
ASSERT(lip->li_ailp == tp->t_mountp->m_ail);
+ ASSERT(list_empty(&lip->li_trans));
+ ASSERT(!test_bit(XFS_LI_DIRTY, &lip->li_flags));
- lidp = kmem_zone_zalloc(xfs_log_item_desc_zone, KM_SLEEP | KM_NOFS);
-
- lidp->lid_item = lip;
- lidp->lid_flags = 0;
- list_add_tail(&lidp->lid_trans, &tp->t_items);
-
- lip->li_desc = lidp;
-}
-
-STATIC void
-xfs_trans_free_item_desc(
- struct xfs_log_item_desc *lidp)
-{
- list_del_init(&lidp->lid_trans);
- kmem_zone_free(xfs_log_item_desc_zone, lidp);
+ list_add_tail(&lip->li_trans, &tp->t_items);
+ trace_xfs_trans_add_item(tp, _RET_IP_);
}
/*
- * Unlink and free the given descriptor.
+ * Unlink the log item from the transaction. the log item is no longer
+ * considered dirty in this transaction, as the linked transaction has
+ * finished, either by abort or commit completion.
*/
void
xfs_trans_del_item(
struct xfs_log_item *lip)
{
- xfs_trans_free_item_desc(lip->li_desc);
- lip->li_desc = NULL;
+ clear_bit(XFS_LI_DIRTY, &lip->li_flags);
+ list_del_init(&lip->li_trans);
}
-/*
- * Unlock all of the items of a transaction and free all the descriptors
- * of that transaction.
- */
+/* Detach and unlock all of the items in a transaction */
void
xfs_trans_free_items(
struct xfs_trans *tp,
xfs_lsn_t commit_lsn,
bool abort)
{
- struct xfs_log_item_desc *lidp, *next;
+ struct xfs_log_item *lip, *next;
- list_for_each_entry_safe(lidp, next, &tp->t_items, lid_trans) {
- struct xfs_log_item *lip = lidp->lid_item;
+ trace_xfs_trans_free_items(tp, _RET_IP_);
- lip->li_desc = NULL;
-
+ list_for_each_entry_safe(lip, next, &tp->t_items, li_trans) {
+ xfs_trans_del_item(lip);
if (commit_lsn != NULLCOMMITLSN)
lip->li_ops->iop_committing(lip, commit_lsn);
if (abort)
- lip->li_flags |= XFS_LI_ABORTED;
+ set_bit(XFS_LI_ABORTED, &lip->li_flags);
lip->li_ops->iop_unlock(lip);
-
- xfs_trans_free_item_desc(lidp);
}
}
@@ -861,7 +846,7 @@ xfs_trans_committed_bulk(
xfs_lsn_t item_lsn;
if (aborted)
- lip->li_flags |= XFS_LI_ABORTED;
+ set_bit(XFS_LI_ABORTED, &lip->li_flags);
item_lsn = lip->li_ops->iop_committed(lip, commit_lsn);
/* item_lsn of -1 means the item needs no further processing */
@@ -936,6 +921,11 @@ __xfs_trans_commit(
int error = 0;
int sync = tp->t_flags & XFS_TRANS_SYNC;
+ ASSERT(!tp->t_agfl_dfops ||
+ !xfs_defer_has_unfinished_work(tp->t_agfl_dfops) || regrant);
+
+ trace_xfs_trans_commit(tp, _RET_IP_);
+
/*
* If there is nothing to be logged by the transaction,
* then unlock all of the items associated with the
@@ -991,6 +981,7 @@ __xfs_trans_commit(
commit_lsn = xfs_log_done(mp, tp->t_ticket, NULL, regrant);
if (commit_lsn == -1 && !error)
error = -EIO;
+ tp->t_ticket = NULL;
}
current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
xfs_trans_free_items(tp, NULLCOMMITLSN, !!error);
@@ -1022,6 +1013,8 @@ xfs_trans_cancel(
struct xfs_mount *mp = tp->t_mountp;
bool dirty = (tp->t_flags & XFS_TRANS_DIRTY);
+ trace_xfs_trans_cancel(tp, _RET_IP_);
+
/*
* See if the caller is relying on us to shut down the
* filesystem. This happens in paths where we detect
@@ -1033,17 +1026,19 @@ xfs_trans_cancel(
}
#ifdef DEBUG
if (!dirty && !XFS_FORCED_SHUTDOWN(mp)) {
- struct xfs_log_item_desc *lidp;
+ struct xfs_log_item *lip;
- list_for_each_entry(lidp, &tp->t_items, lid_trans)
- ASSERT(!(lidp->lid_item->li_type == XFS_LI_EFD));
+ list_for_each_entry(lip, &tp->t_items, li_trans)
+ ASSERT(!(lip->li_type == XFS_LI_EFD));
}
#endif
xfs_trans_unreserve_and_mod_sb(tp);
xfs_trans_unreserve_and_mod_dquots(tp);
- if (tp->t_ticket)
+ if (tp->t_ticket) {
xfs_log_done(mp, tp->t_ticket, NULL, false);
+ tp->t_ticket = NULL;
+ }
/* mark this thread as no longer being in a transaction */
current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
@@ -1067,6 +1062,8 @@ xfs_trans_roll(
struct xfs_trans_res tres;
int error;
+ trace_xfs_trans_roll(trans, _RET_IP_);
+
/*
* Copy the critical parameters from one trans to the next.
*/
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 9d542df..29706b8 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -27,7 +27,6 @@ struct xfs_efi_log_item;
struct xfs_inode;
struct xfs_item_ops;
struct xfs_log_iovec;
-struct xfs_log_item_desc;
struct xfs_mount;
struct xfs_trans;
struct xfs_trans_res;
@@ -43,12 +42,12 @@ struct xfs_bud_log_item;
typedef struct xfs_log_item {
struct list_head li_ail; /* AIL pointers */
+ struct list_head li_trans; /* transaction list */
xfs_lsn_t li_lsn; /* last on-disk lsn */
- struct xfs_log_item_desc *li_desc; /* ptr to current desc*/
struct xfs_mount *li_mountp; /* ptr to fs mount */
struct xfs_ail *li_ailp; /* ptr to AIL */
uint li_type; /* item type */
- uint li_flags; /* misc flags */
+ unsigned long li_flags; /* misc flags */
struct xfs_buf *li_buf; /* real buffer pointer */
struct list_head li_bio_list; /* buffer item list */
void (*li_cb)(struct xfs_buf *,
@@ -64,14 +63,21 @@ typedef struct xfs_log_item {
xfs_lsn_t li_seq; /* CIL commit seq */
} xfs_log_item_t;
-#define XFS_LI_IN_AIL 0x1
-#define XFS_LI_ABORTED 0x2
-#define XFS_LI_FAILED 0x4
+/*
+ * li_flags use the (set/test/clear)_bit atomic interfaces because updates can
+ * race with each other and we don't want to have to use the AIL lock to
+ * serialise all updates.
+ */
+#define XFS_LI_IN_AIL 0
+#define XFS_LI_ABORTED 1
+#define XFS_LI_FAILED 2
+#define XFS_LI_DIRTY 3 /* log item dirty in transaction */
#define XFS_LI_FLAGS \
- { XFS_LI_IN_AIL, "IN_AIL" }, \
- { XFS_LI_ABORTED, "ABORTED" }, \
- { XFS_LI_FAILED, "FAILED" }
+ { (1 << XFS_LI_IN_AIL), "IN_AIL" }, \
+ { (1 << XFS_LI_ABORTED), "ABORTED" }, \
+ { (1 << XFS_LI_FAILED), "FAILED" }, \
+ { (1 << XFS_LI_DIRTY), "DIRTY" }
struct xfs_item_ops {
void (*iop_size)(xfs_log_item_t *, int *, int *);
@@ -111,6 +117,7 @@ typedef struct xfs_trans {
struct xlog_ticket *t_ticket; /* log mgr ticket */
struct xfs_mount *t_mountp; /* ptr to fs mount struct */
struct xfs_dquot_acct *t_dqinfo; /* acctg info for dquots */
+ struct xfs_defer_ops *t_agfl_dfops; /* optional agfl fixup dfops */
unsigned int t_flags; /* misc flags */
int64_t t_icount_delta; /* superblock icount change */
int64_t t_ifree_delta; /* superblock ifree change */
@@ -228,7 +235,8 @@ struct xfs_efd_log_item *xfs_trans_get_efd(struct xfs_trans *,
uint);
int xfs_trans_free_extent(struct xfs_trans *,
struct xfs_efd_log_item *, xfs_fsblock_t,
- xfs_extlen_t, struct xfs_owner_info *);
+ xfs_extlen_t, struct xfs_owner_info *,
+ bool);
int xfs_trans_commit(struct xfs_trans *);
int xfs_trans_roll(struct xfs_trans **);
int xfs_trans_roll_inode(struct xfs_trans **, struct xfs_inode *);
@@ -242,7 +250,6 @@ void xfs_trans_buf_copy_type(struct xfs_buf *dst_bp,
struct xfs_buf *src_bp);
extern kmem_zone_t *xfs_trans_zone;
-extern kmem_zone_t *xfs_log_item_desc_zone;
/* rmap updates */
enum xfs_rmap_intent_type;
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index d4a2445..41e280e 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -32,30 +32,51 @@
#ifdef DEBUG
/*
* Check that the list is sorted as it should be.
+ *
+ * Called with the ail lock held, but we don't want to assert fail with it
+ * held otherwise we'll lock everything up and won't be able to debug the
+ * cause. Hence we sample and check the state under the AIL lock and return if
+ * everything is fine, otherwise we drop the lock and run the ASSERT checks.
+ * Asserts may not be fatal, so pick the lock back up and continue onwards.
*/
STATIC void
xfs_ail_check(
- struct xfs_ail *ailp,
- xfs_log_item_t *lip)
+ struct xfs_ail *ailp,
+ struct xfs_log_item *lip)
{
- xfs_log_item_t *prev_lip;
+ struct xfs_log_item *prev_lip;
+ struct xfs_log_item *next_lip;
+ xfs_lsn_t prev_lsn = NULLCOMMITLSN;
+ xfs_lsn_t next_lsn = NULLCOMMITLSN;
+ xfs_lsn_t lsn;
+ bool in_ail;
+
if (list_empty(&ailp->ail_head))
return;
/*
- * Check the next and previous entries are valid.
+ * Sample then check the next and previous entries are valid.
*/
- ASSERT((lip->li_flags & XFS_LI_IN_AIL) != 0);
- prev_lip = list_entry(lip->li_ail.prev, xfs_log_item_t, li_ail);
+ in_ail = test_bit(XFS_LI_IN_AIL, &lip->li_flags);
+ prev_lip = list_entry(lip->li_ail.prev, struct xfs_log_item, li_ail);
if (&prev_lip->li_ail != &ailp->ail_head)
- ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) <= 0);
+ prev_lsn = prev_lip->li_lsn;
+ next_lip = list_entry(lip->li_ail.next, struct xfs_log_item, li_ail);
+ if (&next_lip->li_ail != &ailp->ail_head)
+ next_lsn = next_lip->li_lsn;
+ lsn = lip->li_lsn;
- prev_lip = list_entry(lip->li_ail.next, xfs_log_item_t, li_ail);
- if (&prev_lip->li_ail != &ailp->ail_head)
- ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) >= 0);
+ if (in_ail &&
+ (prev_lsn == NULLCOMMITLSN || XFS_LSN_CMP(prev_lsn, lsn) <= 0) &&
+ (next_lsn == NULLCOMMITLSN || XFS_LSN_CMP(next_lsn, lsn) >= 0))
+ return;
-
+ spin_unlock(&ailp->ail_lock);
+ ASSERT(in_ail);
+ ASSERT(prev_lsn == NULLCOMMITLSN || XFS_LSN_CMP(prev_lsn, lsn) <= 0);
+ ASSERT(next_lsn == NULLCOMMITLSN || XFS_LSN_CMP(next_lsn, lsn) >= 0);
+ spin_lock(&ailp->ail_lock);
}
#else /* !DEBUG */
#define xfs_ail_check(a,l)
@@ -684,7 +705,7 @@ xfs_trans_ail_update_bulk(
for (i = 0; i < nr_items; i++) {
struct xfs_log_item *lip = log_items[i];
- if (lip->li_flags & XFS_LI_IN_AIL) {
+ if (test_and_set_bit(XFS_LI_IN_AIL, &lip->li_flags)) {
/* check if we really need to move the item */
if (XFS_LSN_CMP(lsn, lip->li_lsn) <= 0)
continue;
@@ -694,7 +715,6 @@ xfs_trans_ail_update_bulk(
if (mlip == lip)
mlip_changed = 1;
} else {
- lip->li_flags |= XFS_LI_IN_AIL;
trace_xfs_ail_insert(lip, 0, lsn);
}
lip->li_lsn = lsn;
@@ -725,7 +745,7 @@ xfs_ail_delete_one(
trace_xfs_ail_delete(lip, mlip->li_lsn, lip->li_lsn);
xfs_ail_delete(ailp, lip);
xfs_clear_li_failed(lip);
- lip->li_flags &= ~XFS_LI_IN_AIL;
+ clear_bit(XFS_LI_IN_AIL, &lip->li_flags);
lip->li_lsn = 0;
return mlip == lip;
@@ -761,7 +781,7 @@ xfs_trans_ail_delete(
struct xfs_mount *mp = ailp->ail_mount;
bool mlip_changed;
- if (!(lip->li_flags & XFS_LI_IN_AIL)) {
+ if (!test_bit(XFS_LI_IN_AIL, &lip->li_flags)) {
spin_unlock(&ailp->ail_lock);
if (!XFS_FORCED_SHUTDOWN(mp)) {
xfs_alert_tag(mp, XFS_PTAG_AILDELETE,
diff --git a/fs/xfs/xfs_trans_bmap.c b/fs/xfs/xfs_trans_bmap.c
index 14543d9..230a21d 100644
--- a/fs/xfs/xfs_trans_bmap.c
+++ b/fs/xfs/xfs_trans_bmap.c
@@ -79,7 +79,7 @@ xfs_trans_log_finish_bmap_update(
* 2.) shuts down the filesystem
*/
tp->t_flags |= XFS_TRANS_DIRTY;
- budp->bud_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+ set_bit(XFS_LI_DIRTY, &budp->bud_item.li_flags);
return error;
}
@@ -158,7 +158,7 @@ xfs_bmap_update_log_item(
bmap = container_of(item, struct xfs_bmap_intent, bi_list);
tp->t_flags |= XFS_TRANS_DIRTY;
- buip->bui_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+ set_bit(XFS_LI_DIRTY, &buip->bui_item.li_flags);
/*
* atomic_inc_return gives us the value after the increment;
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index a5d9dfc..a8ddb4e 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -40,7 +40,7 @@ xfs_trans_buf_item_match(
struct xfs_buf_map *map,
int nmaps)
{
- struct xfs_log_item_desc *lidp;
+ struct xfs_log_item *lip;
struct xfs_buf_log_item *blip;
int len = 0;
int i;
@@ -48,8 +48,8 @@ xfs_trans_buf_item_match(
for (i = 0; i < nmaps; i++)
len += map[i].bm_len;
- list_for_each_entry(lidp, &tp->t_items, lid_trans) {
- blip = (struct xfs_buf_log_item *)lidp->lid_item;
+ list_for_each_entry(lip, &tp->t_items, li_trans) {
+ blip = (struct xfs_buf_log_item *)lip;
if (blip->bli_item.li_type == XFS_LI_BUF &&
blip->bli_buf->b_target == target &&
XFS_BUF_ADDR(blip->bli_buf) == map[0].bm_bn &&
@@ -100,14 +100,10 @@ _xfs_trans_bjoin(
atomic_inc(&bip->bli_refcount);
/*
- * Get a log_item_desc to point at the new item.
+ * Attach the item to the transaction so we can find it in
+ * xfs_trans_get_buf() and friends.
*/
xfs_trans_add_item(tp, &bip->bli_item);
-
- /*
- * Initialize b_fsprivate2 so we can find it with incore_match()
- * in xfs_trans_get_buf() and friends above.
- */
bp->b_transp = tp;
}
@@ -391,7 +387,7 @@ xfs_trans_brelse(
* If the buffer is dirty within this transaction, we can't
* release it until we commit.
*/
- if (bip->bli_item.li_desc->lid_flags & XFS_LID_DIRTY)
+ if (test_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags))
return;
/*
@@ -442,7 +438,7 @@ xfs_trans_brelse(
ASSERT(bp->b_pincount == 0);
***/
ASSERT(atomic_read(&bip->bli_refcount) == 0);
- ASSERT(!(bip->bli_item.li_flags & XFS_LI_IN_AIL));
+ ASSERT(!test_bit(XFS_LI_IN_AIL, &bip->bli_item.li_flags));
ASSERT(!(bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF));
xfs_buf_item_relse(bp);
}
@@ -542,7 +538,7 @@ xfs_trans_dirty_buf(
bip->bli_flags |= XFS_BLI_DIRTY | XFS_BLI_LOGGED;
tp->t_flags |= XFS_TRANS_DIRTY;
- bip->bli_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+ set_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags);
}
/*
@@ -626,7 +622,7 @@ xfs_trans_binval(
ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_INODE_BUF));
ASSERT(!(bip->__bli_format.blf_flags & XFS_BLFT_MASK));
ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
- ASSERT(bip->bli_item.li_desc->lid_flags & XFS_LID_DIRTY);
+ ASSERT(test_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags));
ASSERT(tp->t_flags & XFS_TRANS_DIRTY);
return;
}
@@ -642,7 +638,7 @@ xfs_trans_binval(
memset(bip->bli_formats[i].blf_data_map, 0,
(bip->bli_formats[i].blf_map_size * sizeof(uint)));
}
- bip->bli_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+ set_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags);
tp->t_flags |= XFS_TRANS_DIRTY;
}
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index c3d5472..c381c02 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -77,7 +77,7 @@ xfs_trans_log_dquot(
ASSERT(XFS_DQ_IS_LOCKED(dqp));
tp->t_flags |= XFS_TRANS_DIRTY;
- dqp->q_logitem.qli_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+ set_bit(XFS_LI_DIRTY, &dqp->q_logitem.qli_item.li_flags);
}
/*
@@ -879,7 +879,7 @@ xfs_trans_log_quotaoff_item(
xfs_qoff_logitem_t *qlp)
{
tp->t_flags |= XFS_TRANS_DIRTY;
- qlp->qql_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+ set_bit(XFS_LI_DIRTY, &qlp->qql_item.li_flags);
}
STATIC void
diff --git a/fs/xfs/xfs_trans_extfree.c b/fs/xfs/xfs_trans_extfree.c
index ab43864..2f44a08 100644
--- a/fs/xfs/xfs_trans_extfree.c
+++ b/fs/xfs/xfs_trans_extfree.c
@@ -68,7 +68,8 @@ xfs_trans_free_extent(
struct xfs_efd_log_item *efdp,
xfs_fsblock_t start_block,
xfs_extlen_t ext_len,
- struct xfs_owner_info *oinfo)
+ struct xfs_owner_info *oinfo,
+ bool skip_discard)
{
struct xfs_mount *mp = tp->t_mountp;
uint next_extent;
@@ -79,9 +80,8 @@ xfs_trans_free_extent(
trace_xfs_bmap_free_deferred(tp->t_mountp, agno, 0, agbno, ext_len);
- error = xfs_free_extent(tp, start_block, ext_len, oinfo,
- XFS_AG_RESV_NONE);
-
+ error = __xfs_free_extent(tp, start_block, ext_len,
+ oinfo, XFS_AG_RESV_NONE, skip_discard);
/*
* Mark the transaction dirty, even on error. This ensures the
* transaction is aborted, which:
@@ -90,7 +90,7 @@ xfs_trans_free_extent(
* 2.) shuts down the filesystem
*/
tp->t_flags |= XFS_TRANS_DIRTY;
- efdp->efd_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+ set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags);
next_extent = efdp->efd_next_extent;
ASSERT(next_extent < efdp->efd_format.efd_nextents);
@@ -155,7 +155,7 @@ xfs_extent_free_log_item(
free = container_of(item, struct xfs_extent_free_item, xefi_list);
tp->t_flags |= XFS_TRANS_DIRTY;
- efip->efi_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+ set_bit(XFS_LI_DIRTY, &efip->efi_item.li_flags);
/*
* atomic_inc_return gives us the value after the increment;
@@ -195,7 +195,7 @@ xfs_extent_free_finish_item(
error = xfs_trans_free_extent(tp, done_item,
free->xefi_startblock,
free->xefi_blockcount,
- &free->xefi_oinfo);
+ &free->xefi_oinfo, free->xefi_skip_discard);
kmem_free(free);
return error;
}
@@ -231,9 +231,79 @@ static const struct xfs_defer_op_type xfs_extent_free_defer_type = {
.cancel_item = xfs_extent_free_cancel_item,
};
+/*
+ * AGFL blocks are accounted differently in the reserve pools and are not
+ * inserted into the busy extent list.
+ */
+STATIC int
+xfs_agfl_free_finish_item(
+ struct xfs_trans *tp,
+ struct xfs_defer_ops *dop,
+ struct list_head *item,
+ void *done_item,
+ void **state)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_efd_log_item *efdp = done_item;
+ struct xfs_extent_free_item *free;
+ struct xfs_extent *extp;
+ struct xfs_buf *agbp;
+ int error;
+ xfs_agnumber_t agno;
+ xfs_agblock_t agbno;
+ uint next_extent;
+
+ free = container_of(item, struct xfs_extent_free_item, xefi_list);
+ ASSERT(free->xefi_blockcount == 1);
+ agno = XFS_FSB_TO_AGNO(mp, free->xefi_startblock);
+ agbno = XFS_FSB_TO_AGBNO(mp, free->xefi_startblock);
+
+ trace_xfs_agfl_free_deferred(mp, agno, 0, agbno, free->xefi_blockcount);
+
+ error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
+ if (!error)
+ error = xfs_free_agfl_block(tp, agno, agbno, agbp,
+ &free->xefi_oinfo);
+
+ /*
+ * Mark the transaction dirty, even on error. This ensures the
+ * transaction is aborted, which:
+ *
+ * 1.) releases the EFI and frees the EFD
+ * 2.) shuts down the filesystem
+ */
+ tp->t_flags |= XFS_TRANS_DIRTY;
+ set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags);
+
+ next_extent = efdp->efd_next_extent;
+ ASSERT(next_extent < efdp->efd_format.efd_nextents);
+ extp = &(efdp->efd_format.efd_extents[next_extent]);
+ extp->ext_start = free->xefi_startblock;
+ extp->ext_len = free->xefi_blockcount;
+ efdp->efd_next_extent++;
+
+ kmem_free(free);
+ return error;
+}
+
+
+/* sub-type with special handling for AGFL deferred frees */
+static const struct xfs_defer_op_type xfs_agfl_free_defer_type = {
+ .type = XFS_DEFER_OPS_TYPE_AGFL_FREE,
+ .max_items = XFS_EFI_MAX_FAST_EXTENTS,
+ .diff_items = xfs_extent_free_diff_items,
+ .create_intent = xfs_extent_free_create_intent,
+ .abort_intent = xfs_extent_free_abort_intent,
+ .log_item = xfs_extent_free_log_item,
+ .create_done = xfs_extent_free_create_done,
+ .finish_item = xfs_agfl_free_finish_item,
+ .cancel_item = xfs_extent_free_cancel_item,
+};
+
/* Register the deferred op type. */
void
xfs_extent_free_init_defer_op(void)
{
xfs_defer_init_op_type(&xfs_extent_free_defer_type);
+ xfs_defer_init_op_type(&xfs_agfl_free_defer_type);
}
diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c
index 07cea59..f7bd796 100644
--- a/fs/xfs/xfs_trans_inode.c
+++ b/fs/xfs/xfs_trans_inode.c
@@ -133,14 +133,13 @@ xfs_trans_log_inode(
* set however, then go ahead and bump the i_version counter
* unconditionally.
*/
- if (!(ip->i_itemp->ili_item.li_desc->lid_flags & XFS_LID_DIRTY) &&
+ if (!test_and_set_bit(XFS_LI_DIRTY, &ip->i_itemp->ili_item.li_flags) &&
IS_I_VERSION(VFS_I(ip))) {
if (inode_maybe_inc_iversion(VFS_I(ip), flags & XFS_ILOG_CORE))
flags |= XFS_ILOG_CORE;
}
tp->t_flags |= XFS_TRANS_DIRTY;
- ip->i_itemp->ili_item.li_desc->lid_flags |= XFS_LID_DIRTY;
/*
* Always OR in the bits from the ili_last_fields field.
diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h
index be24b0c8..9717ae7 100644
--- a/fs/xfs/xfs_trans_priv.h
+++ b/fs/xfs/xfs_trans_priv.h
@@ -19,7 +19,6 @@
#define __XFS_TRANS_PRIV_H__
struct xfs_log_item;
-struct xfs_log_item_desc;
struct xfs_mount;
struct xfs_trans;
struct xfs_ail;
@@ -119,7 +118,7 @@ xfs_trans_ail_remove(
spin_lock(&ailp->ail_lock);
/* xfs_trans_ail_delete() drops the AIL lock */
- if (lip->li_flags & XFS_LI_IN_AIL)
+ if (test_bit(XFS_LI_IN_AIL, &lip->li_flags))
xfs_trans_ail_delete(ailp, lip, shutdown_type);
else
spin_unlock(&ailp->ail_lock);
@@ -171,11 +170,10 @@ xfs_clear_li_failed(
{
struct xfs_buf *bp = lip->li_buf;
- ASSERT(lip->li_flags & XFS_LI_IN_AIL);
+ ASSERT(test_bit(XFS_LI_IN_AIL, &lip->li_flags));
lockdep_assert_held(&lip->li_ailp->ail_lock);
- if (lip->li_flags & XFS_LI_FAILED) {
- lip->li_flags &= ~XFS_LI_FAILED;
+ if (test_and_clear_bit(XFS_LI_FAILED, &lip->li_flags)) {
lip->li_buf = NULL;
xfs_buf_rele(bp);
}
@@ -188,9 +186,8 @@ xfs_set_li_failed(
{
lockdep_assert_held(&lip->li_ailp->ail_lock);
- if (!(lip->li_flags & XFS_LI_FAILED)) {
+ if (!test_and_set_bit(XFS_LI_FAILED, &lip->li_flags)) {
xfs_buf_hold(bp);
- lip->li_flags |= XFS_LI_FAILED;
lip->li_buf = bp;
}
}
diff --git a/fs/xfs/xfs_trans_refcount.c b/fs/xfs/xfs_trans_refcount.c
index 94c1877..c7f8e82 100644
--- a/fs/xfs/xfs_trans_refcount.c
+++ b/fs/xfs/xfs_trans_refcount.c
@@ -77,7 +77,7 @@ xfs_trans_log_finish_refcount_update(
* 2.) shuts down the filesystem
*/
tp->t_flags |= XFS_TRANS_DIRTY;
- cudp->cud_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+ set_bit(XFS_LI_DIRTY, &cudp->cud_item.li_flags);
return error;
}
@@ -154,7 +154,7 @@ xfs_refcount_update_log_item(
refc = container_of(item, struct xfs_refcount_intent, ri_list);
tp->t_flags |= XFS_TRANS_DIRTY;
- cuip->cui_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+ set_bit(XFS_LI_DIRTY, &cuip->cui_item.li_flags);
/*
* atomic_inc_return gives us the value after the increment;
diff --git a/fs/xfs/xfs_trans_rmap.c b/fs/xfs/xfs_trans_rmap.c
index 9b577be..5831ca0 100644
--- a/fs/xfs/xfs_trans_rmap.c
+++ b/fs/xfs/xfs_trans_rmap.c
@@ -117,7 +117,7 @@ xfs_trans_log_finish_rmap_update(
* 2.) shuts down the filesystem
*/
tp->t_flags |= XFS_TRANS_DIRTY;
- rudp->rud_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+ set_bit(XFS_LI_DIRTY, &rudp->rud_item.li_flags);
return error;
}
@@ -175,7 +175,7 @@ xfs_rmap_update_log_item(
rmap = container_of(item, struct xfs_rmap_intent, ri_list);
tp->t_flags |= XFS_TRANS_DIRTY;
- ruip->rui_item.li_desc->lid_flags |= XFS_LID_DIRTY;
+ set_bit(XFS_LI_DIRTY, &ruip->rui_item.li_flags);
/*
* atomic_inc_return gives us the value after the increment;
diff --git a/include/acpi/acnames.h b/include/acpi/acnames.h
index 7b289dd..6f69a4f 100644
--- a/include/acpi/acnames.h
+++ b/include/acpi/acnames.h
@@ -49,11 +49,14 @@
/* Definitions of the predefined namespace names */
#define ACPI_UNKNOWN_NAME (u32) 0x3F3F3F3F /* Unknown name is "????" */
-#define ACPI_ROOT_NAME (u32) 0x5F5F5F5C /* Root name is "\___" */
-
#define ACPI_PREFIX_MIXED (u32) 0x69706341 /* "Acpi" */
#define ACPI_PREFIX_LOWER (u32) 0x69706361 /* "acpi" */
+/* Root name stuff */
+
+#define ACPI_ROOT_NAME (u32) 0x5F5F5F5C /* Root name is "\___" */
+#define ACPI_ROOT_PATHNAME "\\___"
+#define ACPI_NAMESPACE_ROOT "Namespace Root"
#define ACPI_NS_ROOT_PATH "\\"
#endif /* __ACNAMES_H__ */
diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h
index 540d35f..eb1f21a 100644
--- a/include/acpi/acpiosxf.h
+++ b/include/acpi/acpiosxf.h
@@ -98,6 +98,27 @@ void acpi_os_release_lock(acpi_spinlock handle, acpi_cpu_flags flags);
#endif
/*
+ * RAW spinlock primitives. If the OS does not provide them, fallback to
+ * spinlock primitives
+ */
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_raw_lock
+# define acpi_os_create_raw_lock(out_handle) acpi_os_create_lock(out_handle)
+#endif
+
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_delete_raw_lock
+# define acpi_os_delete_raw_lock(handle) acpi_os_delete_lock(handle)
+#endif
+
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_acquire_raw_lock
+# define acpi_os_acquire_raw_lock(handle) acpi_os_acquire_lock(handle)
+#endif
+
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_release_raw_lock
+# define acpi_os_release_raw_lock(handle, flags) \
+ acpi_os_release_lock(handle, flags)
+#endif
+
+/*
* Semaphore primitives
*/
#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_semaphore
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index da0215e..77d71bd 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -12,7 +12,7 @@
/* Current ACPICA subsystem version in YYYYMMDD format */
-#define ACPI_CA_VERSION 0x20180313
+#define ACPI_CA_VERSION 0x20180508
#include <acpi/acconfig.h>
#include <acpi/actypes.h>
@@ -753,6 +753,7 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
u32 gpe_number,
acpi_event_status
*event_status))
+ACPI_HW_DEPENDENT_RETURN_VOID(void acpi_dispatch_gpe(acpi_handle gpe_device, u32 gpe_number))
ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_disable_all_gpes(void))
ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_runtime_gpes(void))
ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_wakeup_gpes(void))
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 1c530f9..2b1bafa 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -245,6 +245,10 @@ typedef u64 acpi_physical_address;
#define acpi_spinlock void *
#endif
+#ifndef acpi_raw_spinlock
+#define acpi_raw_spinlock acpi_spinlock
+#endif
+
#ifndef acpi_semaphore
#define acpi_semaphore void *
#endif
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index 2010c05..8e0b825 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -20,14 +20,16 @@
#include <acpi/pcc.h>
#include <acpi/processor.h>
-/* Only support CPPCv2 for now. */
-#define CPPC_NUM_ENT 21
-#define CPPC_REV 2
+/* Support CPPCv2 and CPPCv3 */
+#define CPPC_V2_REV 2
+#define CPPC_V3_REV 3
+#define CPPC_V2_NUM_ENT 21
+#define CPPC_V3_NUM_ENT 23
#define PCC_CMD_COMPLETE_MASK (1 << 0)
#define PCC_ERROR_MASK (1 << 2)
-#define MAX_CPC_REG_ENT 19
+#define MAX_CPC_REG_ENT 21
/* CPPC specific PCC commands. */
#define CMD_READ 0
@@ -91,6 +93,8 @@ enum cppc_regs {
AUTO_ACT_WINDOW,
ENERGY_PERF,
REFERENCE_PERF,
+ LOWEST_FREQ,
+ NOMINAL_FREQ,
};
/*
@@ -104,6 +108,8 @@ struct cppc_perf_caps {
u32 nominal_perf;
u32 lowest_perf;
u32 lowest_nonlinear_perf;
+ u32 lowest_freq;
+ u32 nominal_freq;
};
struct cppc_perf_ctrls {
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index a0b2327..7451b3b 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -102,6 +102,7 @@
#define acpi_cache_t struct kmem_cache
#define acpi_spinlock spinlock_t *
+#define acpi_raw_spinlock raw_spinlock_t *
#define acpi_cpu_flags unsigned long
/* Use native linux version of acpi_os_allocate_zeroed */
@@ -119,6 +120,10 @@
#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_acquire_object
#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_thread_id
#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_lock
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_raw_lock
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_delete_raw_lock
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_acquire_raw_lock
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_release_raw_lock
/*
* OSL interfaces used by debugger/disassembler
diff --git a/include/acpi/platform/aclinuxex.h b/include/acpi/platform/aclinuxex.h
index 7e81475..d754a1b 100644
--- a/include/acpi/platform/aclinuxex.h
+++ b/include/acpi/platform/aclinuxex.h
@@ -90,6 +90,36 @@ static inline acpi_thread_id acpi_os_get_thread_id(void)
lock ? AE_OK : AE_NO_MEMORY; \
})
+
+#define acpi_os_create_raw_lock(__handle) \
+ ({ \
+ raw_spinlock_t *lock = ACPI_ALLOCATE(sizeof(*lock)); \
+ if (lock) { \
+ *(__handle) = lock; \
+ raw_spin_lock_init(*(__handle)); \
+ } \
+ lock ? AE_OK : AE_NO_MEMORY; \
+ })
+
+static inline acpi_cpu_flags acpi_os_acquire_raw_lock(acpi_raw_spinlock lockp)
+{
+ acpi_cpu_flags flags;
+
+ raw_spin_lock_irqsave(lockp, flags);
+ return flags;
+}
+
+static inline void acpi_os_release_raw_lock(acpi_raw_spinlock lockp,
+ acpi_cpu_flags flags)
+{
+ raw_spin_unlock_irqrestore(lockp, flags);
+}
+
+static inline void acpi_os_delete_raw_lock(acpi_raw_spinlock handle)
+{
+ ACPI_FREE(handle);
+}
+
static inline u8 acpi_os_readable(void *pointer, acpi_size length)
{
return TRUE;
diff --git a/include/asm-generic/atomic-long.h b/include/asm-generic/atomic-long.h
index 34a028a..87d14476 100644
--- a/include/asm-generic/atomic-long.h
+++ b/include/asm-generic/atomic-long.h
@@ -25,6 +25,7 @@ typedef atomic64_t atomic_long_t;
#define ATOMIC_LONG_INIT(i) ATOMIC64_INIT(i)
#define ATOMIC_LONG_PFX(x) atomic64 ## x
+#define ATOMIC_LONG_TYPE s64
#else
@@ -32,6 +33,7 @@ typedef atomic_t atomic_long_t;
#define ATOMIC_LONG_INIT(i) ATOMIC_INIT(i)
#define ATOMIC_LONG_PFX(x) atomic ## x
+#define ATOMIC_LONG_TYPE int
#endif
@@ -90,6 +92,21 @@ ATOMIC_LONG_ADD_SUB_OP(sub, _release)
#define atomic_long_cmpxchg(l, old, new) \
(ATOMIC_LONG_PFX(_cmpxchg)((ATOMIC_LONG_PFX(_t) *)(l), (old), (new)))
+
+#define atomic_long_try_cmpxchg_relaxed(l, old, new) \
+ (ATOMIC_LONG_PFX(_try_cmpxchg_relaxed)((ATOMIC_LONG_PFX(_t) *)(l), \
+ (ATOMIC_LONG_TYPE *)(old), (ATOMIC_LONG_TYPE)(new)))
+#define atomic_long_try_cmpxchg_acquire(l, old, new) \
+ (ATOMIC_LONG_PFX(_try_cmpxchg_acquire)((ATOMIC_LONG_PFX(_t) *)(l), \
+ (ATOMIC_LONG_TYPE *)(old), (ATOMIC_LONG_TYPE)(new)))
+#define atomic_long_try_cmpxchg_release(l, old, new) \
+ (ATOMIC_LONG_PFX(_try_cmpxchg_release)((ATOMIC_LONG_PFX(_t) *)(l), \
+ (ATOMIC_LONG_TYPE *)(old), (ATOMIC_LONG_TYPE)(new)))
+#define atomic_long_try_cmpxchg(l, old, new) \
+ (ATOMIC_LONG_PFX(_try_cmpxchg)((ATOMIC_LONG_PFX(_t) *)(l), \
+ (ATOMIC_LONG_TYPE *)(old), (ATOMIC_LONG_TYPE)(new)))
+
+
#define atomic_long_xchg_relaxed(v, new) \
(ATOMIC_LONG_PFX(_xchg_relaxed)((ATOMIC_LONG_PFX(_t) *)(v), (new)))
#define atomic_long_xchg_acquire(v, new) \
@@ -244,6 +261,8 @@ static inline long atomic_long_add_unless(atomic_long_t *l, long a, long u)
#define atomic_long_inc_not_zero(l) \
ATOMIC_LONG_PFX(_inc_not_zero)((ATOMIC_LONG_PFX(_t) *)(l))
+#define atomic_long_cond_read_relaxed(v, c) \
+ ATOMIC_LONG_PFX(_cond_read_relaxed)((ATOMIC_LONG_PFX(_t) *)(v), (c))
#define atomic_long_cond_read_acquire(v, c) \
ATOMIC_LONG_PFX(_cond_read_acquire)((ATOMIC_LONG_PFX(_t) *)(v), (c))
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 29458bb..2cafdbb9 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -221,18 +221,17 @@ do { \
#endif
/**
- * smp_cond_load_acquire() - (Spin) wait for cond with ACQUIRE ordering
+ * smp_cond_load_relaxed() - (Spin) wait for cond with no ordering guarantees
* @ptr: pointer to the variable to wait on
* @cond: boolean expression to wait for
*
- * Equivalent to using smp_load_acquire() on the condition variable but employs
- * the control dependency of the wait to reduce the barrier on many platforms.
+ * Equivalent to using READ_ONCE() on the condition variable.
*
* Due to C lacking lambda expressions we load the value of *ptr into a
* pre-named variable @VAL to be used in @cond.
*/
-#ifndef smp_cond_load_acquire
-#define smp_cond_load_acquire(ptr, cond_expr) ({ \
+#ifndef smp_cond_load_relaxed
+#define smp_cond_load_relaxed(ptr, cond_expr) ({ \
typeof(ptr) __PTR = (ptr); \
typeof(*ptr) VAL; \
for (;;) { \
@@ -241,10 +240,26 @@ do { \
break; \
cpu_relax(); \
} \
- smp_acquire__after_ctrl_dep(); \
VAL; \
})
#endif
+/**
+ * smp_cond_load_acquire() - (Spin) wait for cond with ACQUIRE ordering
+ * @ptr: pointer to the variable to wait on
+ * @cond: boolean expression to wait for
+ *
+ * Equivalent to using smp_load_acquire() on the condition variable but employs
+ * the control dependency of the wait to reduce the barrier on many platforms.
+ */
+#ifndef smp_cond_load_acquire
+#define smp_cond_load_acquire(ptr, cond_expr) ({ \
+ typeof(*ptr) _val; \
+ _val = smp_cond_load_relaxed(ptr, cond_expr); \
+ smp_acquire__after_ctrl_dep(); \
+ _val; \
+})
+#endif
+
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_GENERIC_BARRIER_H */
diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h
new file mode 100644
index 0000000..2881945
--- /dev/null
+++ b/include/asm-generic/compat.h
@@ -0,0 +1,3 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* This is an empty stub for 32-bit-only architectures */
diff --git a/include/asm-generic/dma-mapping.h b/include/asm-generic/dma-mapping.h
index 880a292..ad28682 100644
--- a/include/asm-generic/dma-mapping.h
+++ b/include/asm-generic/dma-mapping.h
@@ -4,7 +4,16 @@
static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
{
+ /*
+ * Use the non-coherent ops if available. If an architecture wants a
+ * more fine-grained selection of operations it will have to implement
+ * get_arch_dma_ops itself or use the per-device dma_ops.
+ */
+#ifdef CONFIG_DMA_NONCOHERENT_OPS
+ return &dma_noncoherent_ops;
+#else
return &dma_direct_ops;
+#endif
}
#endif /* _ASM_GENERIC_DMA_MAPPING_H */
diff --git a/include/asm-generic/pci.h b/include/asm-generic/pci.h
index 830d765..6bb3cd3 100644
--- a/include/asm-generic/pci.h
+++ b/include/asm-generic/pci.h
@@ -14,12 +14,4 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
}
#endif /* HAVE_ARCH_PCI_GET_LEGACY_IDE_IRQ */
-/*
- * By default, assume that no iommu is in use and that the PCI
- * space is mapped to address physical 0.
- */
-#ifndef PCI_DMA_BUS_IS_PHYS
-#define PCI_DMA_BUS_IS_PHYS (1)
-#endif
-
#endif /* _ASM_GENERIC_PCI_H */
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index b37b4ad..9cc4575 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -26,7 +26,6 @@
* @lock: Pointer to queued spinlock structure
* Return: 1 if it is locked, 0 otherwise
*/
-#ifndef queued_spin_is_locked
static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
{
/*
@@ -35,7 +34,6 @@ static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
*/
return atomic_read(&lock->val);
}
-#endif
/**
* queued_spin_value_unlocked - is the spinlock structure unlocked?
@@ -100,7 +98,7 @@ static __always_inline void queued_spin_unlock(struct qspinlock *lock)
/*
* unlock() needs release semantics:
*/
- (void)atomic_sub_return_release(_Q_LOCKED_VAL, &lock->val);
+ smp_store_release(&lock->locked, 0);
}
#endif
diff --git a/include/asm-generic/qspinlock_types.h b/include/asm-generic/qspinlock_types.h
index 034acd0..0763f06 100644
--- a/include/asm-generic/qspinlock_types.h
+++ b/include/asm-generic/qspinlock_types.h
@@ -29,13 +29,41 @@
#endif
typedef struct qspinlock {
- atomic_t val;
+ union {
+ atomic_t val;
+
+ /*
+ * By using the whole 2nd least significant byte for the
+ * pending bit, we can allow better optimization of the lock
+ * acquisition for the pending bit holder.
+ */
+#ifdef __LITTLE_ENDIAN
+ struct {
+ u8 locked;
+ u8 pending;
+ };
+ struct {
+ u16 locked_pending;
+ u16 tail;
+ };
+#else
+ struct {
+ u16 tail;
+ u16 locked_pending;
+ };
+ struct {
+ u8 reserved[2];
+ u8 pending;
+ u8 locked;
+ };
+#endif
+ };
} arch_spinlock_t;
/*
* Initializier
*/
-#define __ARCH_SPIN_LOCK_UNLOCKED { ATOMIC_INIT(0) }
+#define __ARCH_SPIN_LOCK_UNLOCKED { .val = ATOMIC_INIT(0) }
/*
* Bitfields in the atomic value:
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 278841c..af24057 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -188,7 +188,7 @@
#endif
#ifdef CONFIG_SERIAL_EARLYCON
-#define EARLYCON_TABLE() STRUCT_ALIGN(); \
+#define EARLYCON_TABLE() . = ALIGN(8); \
VMLINUX_SYMBOL(__earlycon_table) = .; \
KEEP(*(__earlycon_table)) \
VMLINUX_SYMBOL(__earlycon_table_end) = .;
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
index 482461d..cc414db 100644
--- a/include/crypto/if_alg.h
+++ b/include/crypto/if_alg.h
@@ -245,8 +245,7 @@ ssize_t af_alg_sendpage(struct socket *sock, struct page *page,
int offset, size_t size, int flags);
void af_alg_free_resources(struct af_alg_async_req *areq);
void af_alg_async_cb(struct crypto_async_request *_req, int err);
-__poll_t af_alg_poll(struct file *file, struct socket *sock,
- poll_table *wait);
+__poll_t af_alg_poll_mask(struct socket *sock, __poll_t events);
struct af_alg_async_req *af_alg_alloc_areq(struct sock *sk,
unsigned int areqlen);
int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags,
diff --git a/include/drm/bridge/dw_hdmi.h b/include/drm/bridge/dw_hdmi.h
index dd2a8cf..ccb5aa8 100644
--- a/include/drm/bridge/dw_hdmi.h
+++ b/include/drm/bridge/dw_hdmi.h
@@ -151,7 +151,7 @@ struct dw_hdmi *dw_hdmi_bind(struct platform_device *pdev,
struct drm_encoder *encoder,
const struct dw_hdmi_plat_data *plat_data);
-void dw_hdmi_setup_rx_sense(struct device *dev, bool hpd, bool rx_sense);
+void dw_hdmi_setup_rx_sense(struct dw_hdmi *hdmi, bool hpd, bool rx_sense);
void dw_hdmi_set_sample_rate(struct dw_hdmi *hdmi, unsigned int rate);
void dw_hdmi_audio_enable(struct dw_hdmi *hdmi);
diff --git a/include/drm/drm_hdcp.h b/include/drm/drm_hdcp.h
index 562fa7d..98e63d8 100644
--- a/include/drm/drm_hdcp.h
+++ b/include/drm/drm_hdcp.h
@@ -19,7 +19,7 @@
#define DRM_HDCP_RI_LEN 2
#define DRM_HDCP_V_PRIME_PART_LEN 4
#define DRM_HDCP_V_PRIME_NUM_PARTS 5
-#define DRM_HDCP_NUM_DOWNSTREAM(x) (x & 0x3f)
+#define DRM_HDCP_NUM_DOWNSTREAM(x) (x & 0x7f)
#define DRM_HDCP_MAX_CASCADE_EXCEEDED(x) (x & BIT(3))
#define DRM_HDCP_MAX_DEVICE_EXCEEDED(x) (x & BIT(7))
diff --git a/include/dt-bindings/clock/stm32mp1-clks.h b/include/dt-bindings/clock/stm32mp1-clks.h
index 86e3ec6..90ec780 100644
--- a/include/dt-bindings/clock/stm32mp1-clks.h
+++ b/include/dt-bindings/clock/stm32mp1-clks.h
@@ -76,7 +76,7 @@
#define I2C6 63
#define USART1 64
#define RTCAPB 65
-#define TZC 66
+#define TZC1 66
#define TZPC 67
#define IWDG1 68
#define BSEC 69
@@ -123,6 +123,7 @@
#define CRC1 110
#define USBH 111
#define ETHSTP 112
+#define TZC2 113
/* Kernel clocks */
#define SDMMC1_K 118
@@ -228,7 +229,6 @@
#define CK_MCO2 212
/* TRACE & DEBUG clocks */
-#define DBG 213
#define CK_DBG 214
#define CK_TRACE 215
diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h
index e518e4e..4b15481 100644
--- a/include/kvm/arm_psci.h
+++ b/include/kvm/arm_psci.h
@@ -37,10 +37,15 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu, struct kvm *kvm)
* Our PSCI implementation stays the same across versions from
* v0.2 onward, only adding the few mandatory functions (such
* as FEATURES with 1.0) that are required by newer
- * revisions. It is thus safe to return the latest.
+ * revisions. It is thus safe to return the latest, unless
+ * userspace has instructed us otherwise.
*/
- if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
+ if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features)) {
+ if (vcpu->kvm->arch.psci_version)
+ return vcpu->kvm->arch.psci_version;
+
return KVM_ARM_PSCI_LATEST;
+ }
return KVM_ARM_PSCI_0_1;
}
@@ -48,4 +53,11 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu, struct kvm *kvm)
int kvm_hvc_call_handler(struct kvm_vcpu *vcpu);
+struct kvm_one_reg;
+
+int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu);
+int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
+int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
+int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
+
#endif /* __KVM_ARM_PSCI_H__ */
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 24f0394..e7efe12 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -131,6 +131,7 @@ struct vgic_irq {
u32 mpidr; /* GICv3 target VCPU */
};
u8 source; /* GICv2 SGIs only */
+ u8 active_source; /* GICv2 SGIs only */
u8 priority;
enum vgic_irq_config config; /* Level or edge */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 15bfb15..fd0ea6a 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -578,6 +578,7 @@ int acpi_match_platform_list(const struct acpi_platform_list *plat);
extern void acpi_early_init(void);
extern void acpi_subsystem_init(void);
+extern void arch_post_acpi_subsys_init(void);
extern int acpi_nvs_register(__u64 start, __u64 size);
@@ -899,7 +900,7 @@ static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; }
static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; }
static inline int acpi_dev_pm_attach(struct device *dev, bool power_on)
{
- return -ENODEV;
+ return 0;
}
#endif
diff --git a/include/linux/aio.h b/include/linux/aio.h
index 9d8aabe..b83e68d 100644
--- a/include/linux/aio.h
+++ b/include/linux/aio.h
@@ -8,8 +8,6 @@ struct kioctx;
struct kiocb;
struct mm_struct;
-#define KIOCB_KEY 0
-
typedef int (kiocb_cancel_fn)(struct kiocb *);
/* prototypes */
diff --git a/include/linux/atalk.h b/include/linux/atalk.h
index 4037392..23f8055 100644
--- a/include/linux/atalk.h
+++ b/include/linux/atalk.h
@@ -145,7 +145,12 @@ extern rwlock_t atalk_interfaces_lock;
extern struct atalk_route atrtr_default;
-extern const struct file_operations atalk_seq_arp_fops;
+struct aarp_iter_state {
+ int bucket;
+ struct aarp_entry **table;
+};
+
+extern const struct seq_operations aarp_seq_ops;
extern int sysctl_aarp_expiry_time;
extern int sysctl_aarp_tick_time;
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 8b276fd..01ce399 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -654,6 +654,7 @@ static inline int atomic_dec_if_positive(atomic_t *v)
}
#endif
+#define atomic_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c))
#define atomic_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c))
#ifdef CONFIG_GENERIC_ATOMIC64
@@ -1075,6 +1076,7 @@ static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v
}
#endif
+#define atomic64_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c))
#define atomic64_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c))
#include <asm-generic/atomic-long.h>
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index bfe86b5..0bd432a 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -223,6 +223,11 @@ static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync)
set_wb_congested(bdi->wb.congested, sync);
}
+struct wb_lock_cookie {
+ bool locked;
+ unsigned long flags;
+};
+
#ifdef CONFIG_CGROUP_WRITEBACK
/**
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index f6be4b0..72ca0f3 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -347,7 +347,7 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode)
/**
* unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction
* @inode: target inode
- * @lockedp: temp bool output param, to be passed to the end function
+ * @cookie: output param, to be passed to the end function
*
* The caller wants to access the wb associated with @inode but isn't
* holding inode->i_lock, the i_pages lock or wb->list_lock. This
@@ -355,12 +355,12 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode)
* association doesn't change until the transaction is finished with
* unlocked_inode_to_wb_end().
*
- * The caller must call unlocked_inode_to_wb_end() with *@lockdep
- * afterwards and can't sleep during transaction. IRQ may or may not be
- * disabled on return.
+ * The caller must call unlocked_inode_to_wb_end() with *@cookie afterwards and
+ * can't sleep during the transaction. IRQs may or may not be disabled on
+ * return.
*/
static inline struct bdi_writeback *
-unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
+unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie)
{
rcu_read_lock();
@@ -368,10 +368,10 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
* Paired with store_release in inode_switch_wb_work_fn() and
* ensures that we see the new wb if we see cleared I_WB_SWITCH.
*/
- *lockedp = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;
+ cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;
- if (unlikely(*lockedp))
- xa_lock_irq(&inode->i_mapping->i_pages);
+ if (unlikely(cookie->locked))
+ xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags);
/*
* Protected by either !I_WB_SWITCH + rcu_read_lock() or the i_pages
@@ -383,12 +383,13 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
/**
* unlocked_inode_to_wb_end - end inode wb access transaction
* @inode: target inode
- * @locked: *@lockedp from unlocked_inode_to_wb_begin()
+ * @cookie: @cookie from unlocked_inode_to_wb_begin()
*/
-static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
+static inline void unlocked_inode_to_wb_end(struct inode *inode,
+ struct wb_lock_cookie *cookie)
{
- if (unlikely(locked))
- xa_unlock_irq(&inode->i_mapping->i_pages);
+ if (unlikely(cookie->locked))
+ xa_unlock_irqrestore(&inode->i_mapping->i_pages, cookie->flags);
rcu_read_unlock();
}
@@ -435,12 +436,13 @@ static inline struct bdi_writeback *inode_to_wb(struct inode *inode)
}
static inline struct bdi_writeback *
-unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
+unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie)
{
return inode_to_wb(inode);
}
-static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
+static inline void unlocked_inode_to_wb_end(struct inode *inode,
+ struct wb_lock_cookie *cookie)
{
}
diff --git a/include/linux/bio.h b/include/linux/bio.h
index ce547a2..397a38a 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -67,8 +67,12 @@
#define bio_multiple_segments(bio) \
((bio)->bi_iter.bi_size != bio_iovec(bio).bv_len)
-#define bio_sectors(bio) ((bio)->bi_iter.bi_size >> 9)
-#define bio_end_sector(bio) ((bio)->bi_iter.bi_sector + bio_sectors((bio)))
+
+#define bvec_iter_sectors(iter) ((iter).bi_size >> 9)
+#define bvec_iter_end_sector(iter) ((iter).bi_sector + bvec_iter_sectors((iter)))
+
+#define bio_sectors(bio) bvec_iter_sectors((bio)->bi_iter)
+#define bio_end_sector(bio) bvec_iter_end_sector((bio)->bi_iter)
/*
* Return the data direction, READ or WRITE.
@@ -123,6 +127,11 @@ static inline void *bio_data(struct bio *bio)
return NULL;
}
+static inline bool bio_full(struct bio *bio)
+{
+ return bio->bi_vcnt >= bio->bi_max_vecs;
+}
+
/*
* will die
*/
@@ -406,13 +415,13 @@ static inline struct bio *bio_next_split(struct bio *bio, int sectors,
return bio_split(bio, sectors, gfp, bs);
}
-extern struct bio_set *bioset_create(unsigned int, unsigned int, int flags);
enum {
BIOSET_NEED_BVECS = BIT(0),
BIOSET_NEED_RESCUER = BIT(1),
};
-extern void bioset_free(struct bio_set *);
-extern mempool_t *biovec_create_pool(int pool_entries);
+extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags);
+extern void bioset_exit(struct bio_set *);
+extern int biovec_init_pool(mempool_t *pool, int pool_entries);
extern struct bio *bio_alloc_bioset(gfp_t, unsigned int, struct bio_set *);
extern void bio_put(struct bio *);
@@ -421,11 +430,11 @@ extern void __bio_clone_fast(struct bio *, struct bio *);
extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *);
extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs);
-extern struct bio_set *fs_bio_set;
+extern struct bio_set fs_bio_set;
static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
{
- return bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set);
+ return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set);
}
static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs)
@@ -470,6 +479,10 @@ void bio_chain(struct bio *, struct bio *);
extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int);
extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
unsigned int, unsigned int);
+bool __bio_try_merge_page(struct bio *bio, struct page *page,
+ unsigned int len, unsigned int off);
+void __bio_add_page(struct bio *bio, struct page *page,
+ unsigned int len, unsigned int off);
int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter);
struct rq_map_data;
extern struct bio *bio_map_user_iov(struct request_queue *,
@@ -499,7 +512,10 @@ static inline void bio_flush_dcache_pages(struct bio *bi)
}
#endif
+extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
+ struct bio *src, struct bvec_iter *src_iter);
extern void bio_copy_data(struct bio *dst, struct bio *src);
+extern void bio_list_copy_data(struct bio *dst, struct bio *src);
extern void bio_free_pages(struct bio *bio);
extern struct bio *bio_copy_user_iov(struct request_queue *,
@@ -507,7 +523,13 @@ extern struct bio *bio_copy_user_iov(struct request_queue *,
struct iov_iter *,
gfp_t);
extern int bio_uncopy_user(struct bio *);
-void zero_fill_bio(struct bio *bio);
+void zero_fill_bio_iter(struct bio *bio, struct bvec_iter iter);
+
+static inline void zero_fill_bio(struct bio *bio)
+{
+ zero_fill_bio_iter(bio, bio->bi_iter);
+}
+
extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *);
extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int);
extern unsigned int bvec_nr_vecs(unsigned short idx);
@@ -722,11 +744,11 @@ struct bio_set {
struct kmem_cache *bio_slab;
unsigned int front_pad;
- mempool_t *bio_pool;
- mempool_t *bvec_pool;
+ mempool_t bio_pool;
+ mempool_t bvec_pool;
#if defined(CONFIG_BLK_DEV_INTEGRITY)
- mempool_t *bio_integrity_pool;
- mempool_t *bvec_integrity_pool;
+ mempool_t bio_integrity_pool;
+ mempool_t bvec_integrity_pool;
#endif
/*
@@ -745,6 +767,11 @@ struct biovec_slab {
struct kmem_cache *slab;
};
+static inline bool bioset_initialized(struct bio_set *bs)
+{
+ return bs->bio_slab != NULL;
+}
+
/*
* a small number of entries is fine, not going to be performance critical.
* basically we just need to survive
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index e3986f4..fb35517 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -9,6 +9,9 @@
struct blk_mq_tags;
struct blk_flush_queue;
+/**
+ * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware block device
+ */
struct blk_mq_hw_ctx {
struct {
spinlock_t lock;
@@ -256,7 +259,8 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
void blk_mq_kick_requeue_list(struct request_queue *q);
void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
void blk_mq_complete_request(struct request *rq);
-
+bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
+ struct bio *bio);
bool blk_mq_queue_stopped(struct request_queue *q);
void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 17b18b9..3c4f390 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -8,6 +8,7 @@
#include <linux/types.h>
#include <linux/bvec.h>
+#include <linux/ktime.h>
struct bio_set;
struct bio;
@@ -90,10 +91,52 @@ static inline bool blk_path_error(blk_status_t error)
return true;
}
-struct blk_issue_stat {
- u64 stat;
+/*
+ * From most significant bit:
+ * 1 bit: reserved for other usage, see below
+ * 12 bits: original size of bio
+ * 51 bits: issue time of bio
+ */
+#define BIO_ISSUE_RES_BITS 1
+#define BIO_ISSUE_SIZE_BITS 12
+#define BIO_ISSUE_RES_SHIFT (64 - BIO_ISSUE_RES_BITS)
+#define BIO_ISSUE_SIZE_SHIFT (BIO_ISSUE_RES_SHIFT - BIO_ISSUE_SIZE_BITS)
+#define BIO_ISSUE_TIME_MASK ((1ULL << BIO_ISSUE_SIZE_SHIFT) - 1)
+#define BIO_ISSUE_SIZE_MASK \
+ (((1ULL << BIO_ISSUE_SIZE_BITS) - 1) << BIO_ISSUE_SIZE_SHIFT)
+#define BIO_ISSUE_RES_MASK (~((1ULL << BIO_ISSUE_RES_SHIFT) - 1))
+
+/* Reserved bit for blk-throtl */
+#define BIO_ISSUE_THROTL_SKIP_LATENCY (1ULL << 63)
+
+struct bio_issue {
+ u64 value;
};
+static inline u64 __bio_issue_time(u64 time)
+{
+ return time & BIO_ISSUE_TIME_MASK;
+}
+
+static inline u64 bio_issue_time(struct bio_issue *issue)
+{
+ return __bio_issue_time(issue->value);
+}
+
+static inline sector_t bio_issue_size(struct bio_issue *issue)
+{
+ return ((issue->value & BIO_ISSUE_SIZE_MASK) >> BIO_ISSUE_SIZE_SHIFT);
+}
+
+static inline void bio_issue_init(struct bio_issue *issue,
+ sector_t size)
+{
+ size &= (1ULL << BIO_ISSUE_SIZE_BITS) - 1;
+ issue->value = ((issue->value & BIO_ISSUE_RES_MASK) |
+ (ktime_get_ns() & BIO_ISSUE_TIME_MASK) |
+ ((u64)size << BIO_ISSUE_SIZE_SHIFT));
+}
+
/*
* main unit of I/O for the block layer and lower layers (ie drivers and
* stacking drivers)
@@ -138,7 +181,7 @@ struct bio {
struct cgroup_subsys_state *bi_css;
#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
void *bi_cg_private;
- struct blk_issue_stat bi_issue_stat;
+ struct bio_issue bi_issue;
#endif
#endif
union {
@@ -186,6 +229,8 @@ struct bio {
* throttling rules. Don't do it again. */
#define BIO_TRACE_COMPLETION 10 /* bio_endio() should trace the final completion
* of this bio. */
+#define BIO_QUEUE_ENTERED 11 /* can use blk_queue_enter_live() */
+
/* See BVEC_POOL_OFFSET below before adding new flags */
/*
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 9af3e0f..bca3a92 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -125,16 +125,23 @@ typedef __u32 __bitwise req_flags_t;
#define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18))
/* The per-zone write lock is held for this request */
#define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19))
-/* timeout is expired */
-#define RQF_MQ_TIMEOUT_EXPIRED ((__force req_flags_t)(1 << 20))
/* already slept for hybrid poll */
-#define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 21))
+#define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20))
/* flags that prevent us from merging requests: */
#define RQF_NOMERGE_FLAGS \
(RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD)
/*
+ * Request state for blk-mq.
+ */
+enum mq_rq_state {
+ MQ_RQ_IDLE = 0,
+ MQ_RQ_IN_FLIGHT = 1,
+ MQ_RQ_COMPLETE = 2,
+};
+
+/*
* Try to put the fields that are referenced together in the same cacheline.
*
* If you modify this structure, make sure to update blk_rq_init() and
@@ -205,9 +212,20 @@ struct request {
struct gendisk *rq_disk;
struct hd_struct *part;
- unsigned long start_time;
- struct blk_issue_stat issue_stat;
- /* Number of scatter-gather DMA addr+len pairs after
+ /* Time that I/O was submitted to the kernel. */
+ u64 start_time_ns;
+ /* Time that I/O was submitted to the device. */
+ u64 io_start_time_ns;
+
+#ifdef CONFIG_BLK_WBT
+ unsigned short wbt_flags;
+#endif
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+ unsigned short throtl_size;
+#endif
+
+ /*
+ * Number of scatter-gather DMA addr+len pairs after
* physical address coalescing is performed.
*/
unsigned short nr_phys_segments;
@@ -219,32 +237,14 @@ struct request {
unsigned short write_hint;
unsigned short ioprio;
- unsigned int timeout;
-
void *special; /* opaque pointer available for LLD use */
unsigned int extra_len; /* length of alignment and padding */
- /*
- * On blk-mq, the lower bits of ->gstate (generation number and
- * state) carry the MQ_RQ_* state value and the upper bits the
- * generation number which is monotonically incremented and used to
- * distinguish the reuse instances.
- *
- * ->gstate_seq allows updates to ->gstate and other fields
- * (currently ->deadline) during request start to be read
- * atomically from the timeout path, so that it can operate on a
- * coherent set of information.
- */
- seqcount_t gstate_seq;
- u64 gstate;
+ enum mq_rq_state state;
+ refcount_t ref;
- /*
- * ->aborted_gstate is used by the timeout to claim a specific
- * recycle instance of this request. See blk_mq_timeout_work().
- */
- struct u64_stats_sync aborted_gstate_sync;
- u64 aborted_gstate;
+ unsigned int timeout;
/* access through blk_rq_set_deadline, blk_rq_deadline */
unsigned long __deadline;
@@ -267,8 +267,6 @@ struct request {
#ifdef CONFIG_BLK_CGROUP
struct request_list *rl; /* rl this rq is alloced from */
- unsigned long long start_time_ns;
- unsigned long long io_start_time_ns; /* when passed to hardware */
#endif
};
@@ -328,9 +326,8 @@ typedef int (init_rq_fn)(struct request_queue *, struct request *, gfp_t);
typedef void (exit_rq_fn)(struct request_queue *, struct request *);
enum blk_eh_timer_return {
- BLK_EH_NOT_HANDLED,
- BLK_EH_HANDLED,
- BLK_EH_RESET_TIMER,
+ BLK_EH_DONE, /* drivers has completed the command */
+ BLK_EH_RESET_TIMER, /* reset timer and try again */
};
typedef enum blk_eh_timer_return (rq_timed_out_fn)(struct request *);
@@ -605,6 +602,11 @@ struct request_queue {
* initialized by the low level device driver (e.g. scsi/sd.c).
* Stacking drivers (device mappers) may or may not initialize
* these fields.
+ *
+ * Reads of this information must be protected with blk_queue_enter() /
+ * blk_queue_exit(). Modifying this information is only allowed while
+ * no requests are being processed. See also blk_mq_freeze_queue() and
+ * blk_mq_unfreeze_queue().
*/
unsigned int nr_zones;
unsigned long *seq_zones_bitmap;
@@ -650,7 +652,7 @@ struct request_queue {
struct blk_mq_tag_set *tag_set;
struct list_head tag_set_list;
- struct bio_set *bio_split;
+ struct bio_set bio_split;
#ifdef CONFIG_BLK_DEBUG_FS
struct dentry *debugfs_dir;
@@ -737,6 +739,7 @@ bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q);
#define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags)
#define blk_queue_preempt_only(q) \
test_bit(QUEUE_FLAG_PREEMPT_ONLY, &(q)->queue_flags)
+#define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags)
extern int blk_set_preempt_only(struct request_queue *q);
extern void blk_clear_preempt_only(struct request_queue *q);
@@ -961,11 +964,8 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq);
extern void blk_init_request_from_bio(struct request *req, struct bio *bio);
extern void blk_put_request(struct request *);
extern void __blk_put_request(struct request_queue *, struct request *);
-extern struct request *blk_get_request_flags(struct request_queue *,
- unsigned int op,
- blk_mq_req_flags_t flags);
extern struct request *blk_get_request(struct request_queue *, unsigned int op,
- gfp_t gfp_mask);
+ blk_mq_req_flags_t flags);
extern void blk_requeue_request(struct request_queue *, struct request *);
extern int blk_lld_busy(struct request_queue *q);
extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
@@ -1782,48 +1782,6 @@ int kblockd_schedule_work(struct work_struct *work);
int kblockd_schedule_work_on(int cpu, struct work_struct *work);
int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);
-#ifdef CONFIG_BLK_CGROUP
-/*
- * This should not be using sched_clock(). A real patch is in progress
- * to fix this up, until that is in place we need to disable preemption
- * around sched_clock() in this function and set_io_start_time_ns().
- */
-static inline void set_start_time_ns(struct request *req)
-{
- preempt_disable();
- req->start_time_ns = sched_clock();
- preempt_enable();
-}
-
-static inline void set_io_start_time_ns(struct request *req)
-{
- preempt_disable();
- req->io_start_time_ns = sched_clock();
- preempt_enable();
-}
-
-static inline uint64_t rq_start_time_ns(struct request *req)
-{
- return req->start_time_ns;
-}
-
-static inline uint64_t rq_io_start_time_ns(struct request *req)
-{
- return req->io_start_time_ns;
-}
-#else
-static inline void set_start_time_ns(struct request *req) {}
-static inline void set_io_start_time_ns(struct request *req) {}
-static inline uint64_t rq_start_time_ns(struct request *req)
-{
- return 0;
-}
-static inline uint64_t rq_io_start_time_ns(struct request *req)
-{
- return 0;
-}
-#endif
-
#define MODULE_ALIAS_BLOCKDEV(major,minor) \
MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor))
#define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 95a7abd..469b20e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -31,6 +31,7 @@ struct bpf_map_ops {
void (*map_release)(struct bpf_map *map, struct file *map_file);
void (*map_free)(struct bpf_map *map);
int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key);
+ void (*map_release_uref)(struct bpf_map *map);
/* funcs callable from userspace and from eBPF programs */
void *(*map_lookup_elem)(struct bpf_map *map, void *key);
@@ -339,8 +340,8 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
struct bpf_prog *old_prog);
int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
- __u32 __user *prog_ids, u32 request_cnt,
- __u32 __user *prog_cnt);
+ u32 *prog_ids, u32 request_cnt,
+ u32 *prog_cnt);
int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
struct bpf_prog *exclude_prog,
struct bpf_prog *include_prog,
@@ -351,6 +352,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
struct bpf_prog **_prog, *__prog; \
struct bpf_prog_array *_array; \
u32 _ret = 1; \
+ preempt_disable(); \
rcu_read_lock(); \
_array = rcu_dereference(array); \
if (unlikely(check_non_null && !_array))\
@@ -362,6 +364,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
} \
_out: \
rcu_read_unlock(); \
+ preempt_enable_no_resched(); \
_ret; \
})
@@ -434,7 +437,6 @@ int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value);
int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
void *key, void *value, u64 map_flags);
int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
-void bpf_fd_array_map_clear(struct bpf_map *map);
int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
void *key, void *value, u64 map_flags);
int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 7e61c39..df36b1b 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -142,10 +142,11 @@ struct bpf_verifier_state_list {
struct bpf_insn_aux_data {
union {
enum bpf_reg_type ptr_type; /* pointer type for load/store insns */
- struct bpf_map *map_ptr; /* pointer for call insn into lookup_elem */
+ unsigned long map_state; /* pointer/poison value for maps */
s32 call_imm; /* saved imm field of call insn */
};
int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
+ int sanitize_stack_off; /* stack slot to be cleared */
bool seen; /* this insn was processed by the verifier */
};
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index d3339dd..b324e01 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -25,6 +25,7 @@
#define PHY_ID_BCM54612E 0x03625e60
#define PHY_ID_BCM54616S 0x03625d10
#define PHY_ID_BCM57780 0x03625d90
+#define PHY_ID_BCM89610 0x03625cd0
#define PHY_ID_BCM7250 0xae025280
#define PHY_ID_BCM7260 0xae025190
diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h
index 28a7ccc..6aeaf64 100644
--- a/include/linux/bsg-lib.h
+++ b/include/linux/bsg-lib.h
@@ -72,8 +72,7 @@ struct bsg_job {
void bsg_job_done(struct bsg_job *job, int result,
unsigned int reply_payload_rcv_len);
struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
- bsg_job_fn *job_fn, int dd_job_size,
- void (*release)(struct device *));
+ bsg_job_fn *job_fn, int dd_job_size);
void bsg_job_put(struct bsg_job *job);
int __must_check bsg_job_get(struct bsg_job *job);
diff --git a/include/linux/bsg.h b/include/linux/bsg.h
index 0c7dd9c..dac37b6 100644
--- a/include/linux/bsg.h
+++ b/include/linux/bsg.h
@@ -17,17 +17,13 @@ struct bsg_ops {
struct bsg_class_device {
struct device *class_dev;
- struct device *parent;
int minor;
struct request_queue *queue;
- struct kref ref;
const struct bsg_ops *ops;
- void (*release)(struct device *);
};
int bsg_register_queue(struct request_queue *q, struct device *parent,
- const char *name, const struct bsg_ops *ops,
- void (*release)(struct device *));
+ const char *name, const struct bsg_ops *ops);
int bsg_scsi_register_queue(struct request_queue *q, struct device *parent);
void bsg_unregister_queue(struct request_queue *q);
#else
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 894e5d1..96225a7 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -205,8 +205,6 @@ void write_boundary_block(struct block_device *bdev,
sector_t bblock, unsigned blocksize);
int bh_uptodate_or_lock(struct buffer_head *bh);
int bh_submit_read(struct buffer_head *bh);
-loff_t page_cache_seek_hole_data(struct inode *inode, loff_t offset,
- loff_t length, int whence);
extern int buffer_heads_over_limit;
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 528ccc9..96bb322 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -77,7 +77,10 @@ struct ceph_osd_data {
u32 bio_length;
};
#endif /* CONFIG_BLOCK */
- struct ceph_bvec_iter bvec_pos;
+ struct {
+ struct ceph_bvec_iter bvec_pos;
+ u32 num_bvecs;
+ };
};
};
@@ -412,6 +415,10 @@ void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req,
struct ceph_bio_iter *bio_pos,
u32 bio_length);
#endif /* CONFIG_BLOCK */
+void osd_req_op_extent_osd_data_bvecs(struct ceph_osd_request *osd_req,
+ unsigned int which,
+ struct bio_vec *bvecs, u32 num_bvecs,
+ u32 bytes);
void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req,
unsigned int which,
struct ceph_bvec_iter *bvec_pos);
@@ -426,7 +433,8 @@ extern void osd_req_op_cls_request_data_pages(struct ceph_osd_request *,
bool own_pages);
void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req,
unsigned int which,
- struct bio_vec *bvecs, u32 bytes);
+ struct bio_vec *bvecs, u32 num_bvecs,
+ u32 bytes);
extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *,
unsigned int which,
struct page **pages, u64 length,
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 210a890..1d25e14 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -765,6 +765,9 @@ int __clk_mux_determine_rate(struct clk_hw *hw,
int __clk_determine_rate(struct clk_hw *core, struct clk_rate_request *req);
int __clk_mux_determine_rate_closest(struct clk_hw *hw,
struct clk_rate_request *req);
+int clk_mux_determine_rate_flags(struct clk_hw *hw,
+ struct clk_rate_request *req,
+ unsigned long flags);
void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent);
void clk_hw_set_rate_range(struct clk_hw *hw, unsigned long min_rate,
unsigned long max_rate);
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 081281a..b1a5562 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -7,8 +7,7 @@
*/
#include <linux/types.h>
-
-#ifdef CONFIG_COMPAT
+#include <linux/compat_time.h>
#include <linux/stat.h>
#include <linux/param.h> /* for HZ */
@@ -21,8 +20,11 @@
#include <linux/unistd.h>
#include <asm/compat.h>
+
+#ifdef CONFIG_COMPAT
#include <asm/siginfo.h>
#include <asm/signal.h>
+#endif
#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
/*
@@ -83,6 +85,8 @@
static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
#endif /* COMPAT_SYSCALL_DEFINEx */
+#ifdef CONFIG_COMPAT
+
#ifndef compat_user_stack_pointer
#define compat_user_stack_pointer() current_user_stack_pointer()
#endif
@@ -290,8 +294,6 @@ extern int compat_get_timespec(struct timespec *, const void __user *);
extern int compat_put_timespec(const struct timespec *, void __user *);
extern int compat_get_timeval(struct timeval *, const void __user *);
extern int compat_put_timeval(const struct timeval *, void __user *);
-extern int compat_get_timespec64(struct timespec64 *, const void __user *);
-extern int compat_put_timespec64(const struct timespec64 *, void __user *);
extern int get_compat_itimerspec64(struct itimerspec64 *its,
const struct compat_itimerspec __user *uits);
extern int put_compat_itimerspec64(const struct itimerspec64 *its,
@@ -330,6 +332,7 @@ extern int put_compat_rusage(const struct rusage *,
struct compat_rusage __user *);
struct compat_siginfo;
+struct __compat_aio_sigset;
struct compat_dirent {
u32 d_ino;
@@ -553,6 +556,12 @@ asmlinkage long compat_sys_io_getevents(compat_aio_context_t ctx_id,
compat_long_t nr,
struct io_event __user *events,
struct compat_timespec __user *timeout);
+asmlinkage long compat_sys_io_pgetevents(compat_aio_context_t ctx_id,
+ compat_long_t min_nr,
+ compat_long_t nr,
+ struct io_event __user *events,
+ struct compat_timespec __user *timeout,
+ const struct __compat_aio_sigset __user *usig);
/* fs/cookies.c */
asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, compat_size_t);
@@ -1016,7 +1025,9 @@ static inline struct compat_timeval ns_to_compat_timeval(s64 nsec)
#else /* !CONFIG_COMPAT */
#define is_compat_task() (0)
+#ifndef in_compat_syscall
static inline bool in_compat_syscall(void) { return false; }
+#endif
#endif /* CONFIG_COMPAT */
diff --git a/include/linux/compat_time.h b/include/linux/compat_time.h
new file mode 100644
index 0000000..31f2774
--- /dev/null
+++ b/include/linux/compat_time.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_COMPAT_TIME_H
+#define _LINUX_COMPAT_TIME_H
+
+#include <linux/types.h>
+#include <linux/time64.h>
+
+typedef s32 compat_time_t;
+
+struct compat_timespec {
+ compat_time_t tv_sec;
+ s32 tv_nsec;
+};
+
+struct compat_timeval {
+ compat_time_t tv_sec;
+ s32 tv_usec;
+};
+
+extern int compat_get_timespec64(struct timespec64 *, const void __user *);
+extern int compat_put_timespec64(const struct timespec64 *, void __user *);
+
+#endif /* _LINUX_COMPAT_TIME_H */
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index ceb96eca..7d98e26 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -25,6 +25,9 @@
#define __SANITIZE_ADDRESS__
#endif
+#undef __no_sanitize_address
+#define __no_sanitize_address __attribute__((no_sanitize("address")))
+
/* Clang doesn't have a way to turn it off per-function, yet. */
#ifdef __noretpoline
#undef __noretpoline
diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h
index edfeaba..a1a959b 100644
--- a/include/linux/coresight-pmu.h
+++ b/include/linux/coresight-pmu.h
@@ -1,18 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright(C) 2015 Linaro Limited. All rights reserved.
* Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program. If not, see <http://www.gnu.org/licenses/>.
*/
#ifndef _LINUX_CORESIGHT_PMU_H
diff --git a/include/linux/cper.h b/include/linux/cper.h
index d14ef4e..9c703a0 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -381,7 +381,7 @@ struct cper_sec_proc_generic {
/* IA32/X64 Processor Error Section */
struct cper_sec_proc_ia {
__u64 validation_bits;
- __u8 lapic_id;
+ __u64 lapic_id;
__u8 cpuid[48];
};
@@ -551,5 +551,7 @@ const char *cper_mem_err_unpack(struct trace_seq *,
struct cper_mem_err_compact *);
void cper_print_proc_arm(const char *pfx,
const struct cper_sec_proc_arm *proc);
+void cper_print_proc_ia(const char *pfx,
+ const struct cper_sec_proc_ia *proc);
#endif
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 7b01bc1..a97a63e 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -53,6 +53,8 @@ extern ssize_t cpu_show_spectre_v1(struct device *dev,
struct device_attribute *attr, char *buf);
extern ssize_t cpu_show_spectre_v2(struct device *dev,
struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_spec_store_bypass(struct device *dev,
+ struct device_attribute *attr, char *buf);
extern __printf(4, 5)
struct device *cpu_device_create(struct device *parent, void *drvdata,
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 87f48dd..882a9b9 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -571,7 +571,7 @@ struct governor_attr {
size_t count);
};
-static inline bool cpufreq_can_do_remote_dvfs(struct cpufreq_policy *policy)
+static inline bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy)
{
/*
* Allow remote callbacks if:
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 1eefabf..4325d6f 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -258,6 +258,7 @@ struct cpuidle_governor {
#ifdef CONFIG_CPU_IDLE
extern int cpuidle_register_governor(struct cpuidle_governor *gov);
+extern int cpuidle_governor_latency_req(unsigned int cpu);
#else
static inline int cpuidle_register_governor(struct cpuidle_governor *gov)
{return 0;}
diff --git a/include/linux/dax.h b/include/linux/dax.h
index f9eb22a..c99692d 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -64,10 +64,10 @@ static inline bool dax_write_cache_enabled(struct dax_device *dax_dev)
struct writeback_control;
int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
#if IS_ENABLED(CONFIG_FS_DAX)
-int __bdev_dax_supported(struct super_block *sb, int blocksize);
-static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
+bool __bdev_dax_supported(struct block_device *bdev, int blocksize);
+static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize)
{
- return __bdev_dax_supported(sb, blocksize);
+ return __bdev_dax_supported(bdev, blocksize);
}
static inline struct dax_device *fs_dax_get_by_host(const char *host)
@@ -84,9 +84,10 @@ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev);
int dax_writeback_mapping_range(struct address_space *mapping,
struct block_device *bdev, struct writeback_control *wbc);
#else
-static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
+static inline bool bdev_dax_supported(struct block_device *bdev,
+ int blocksize)
{
- return -EOPNOTSUPP;
+ return false;
}
static inline struct dax_device *fs_dax_get_by_host(const char *host)
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 94acbde..66c6e17 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -224,6 +224,7 @@ extern seqlock_t rename_lock;
* These are the low-level FS interfaces to the dcache..
*/
extern void d_instantiate(struct dentry *, struct inode *);
+extern void d_instantiate_new(struct dentry *, struct inode *);
extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *);
extern struct dentry * d_instantiate_anon(struct dentry *, struct inode *);
extern int d_instantiate_no_diralias(struct dentry *, struct inode *);
diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 5e335b6..e6c0448 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -29,7 +29,7 @@
#ifdef CONFIG_TASK_DELAY_ACCT
struct task_delay_info {
- spinlock_t lock;
+ raw_spinlock_t lock;
unsigned int flags; /* Private per-task flags */
/* For each stat XXX, add following, aligned appropriately
diff --git a/include/linux/device.h b/include/linux/device.h
index 0059b99..00b6c3b 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -88,6 +88,8 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *);
* @resume: Called to bring a device on this bus out of sleep mode.
* @num_vf: Called to find out how many virtual functions a device on this
* bus supports.
+ * @dma_configure: Called to setup DMA configuration on a device on
+ this bus.
* @pm: Power management operations of this bus, callback the specific
* device driver's pm-ops.
* @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU
@@ -96,8 +98,6 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *);
* @p: The private data of the driver core, only the driver core can
* touch this.
* @lock_key: Lock class key for use by the lock validator
- * @force_dma: Assume devices on this bus should be set up by dma_configure()
- * even if DMA capability is not explicitly described by firmware.
*
* A bus is a channel between the processor and one or more devices. For the
* purposes of the device model, all devices are connected via a bus, even if
@@ -130,14 +130,14 @@ struct bus_type {
int (*num_vf)(struct device *dev);
+ int (*dma_configure)(struct device *dev);
+
const struct dev_pm_ops *pm;
const struct iommu_ops *iommu_ops;
struct subsys_private *p;
struct lock_class_key lock_key;
-
- bool force_dma;
};
extern int __must_check bus_register(struct bus_type *bus);
@@ -256,7 +256,9 @@ enum probe_type {
* automatically.
* @pm: Power management operations of the device which matched
* this driver.
- * @coredump: Called through sysfs to initiate a device coredump.
+ * @coredump: Called when sysfs entry is written to. The device driver
+ * is expected to call the dev_coredump API resulting in a
+ * uevent.
* @p: Driver core's private data, no one other than the driver
* core can touch this.
*
@@ -288,7 +290,7 @@ struct device_driver {
const struct attribute_group **groups;
const struct dev_pm_ops *pm;
- int (*coredump) (struct device *dev);
+ void (*coredump) (struct device *dev);
struct driver_private *p;
};
@@ -902,6 +904,8 @@ struct dev_links_info {
* @offline: Set after successful invocation of bus type's .offline().
* @of_node_reused: Set if the device-tree node is shared with an ancestor
* device.
+ * @dma_32bit_limit: bridge limited to 32bit DMA even if the device itself
+ * indicates support for a higher limit in the dma_mask field.
*
* At the lowest level, every device in a Linux system is represented by an
* instance of struct device. The device structure contains the information
@@ -990,6 +994,7 @@ struct device {
bool offline_disabled:1;
bool offline:1;
bool of_node_reused:1;
+ bool dma_32bit_limit:1;
};
static inline struct device *kobj_to_dev(struct kobject *kobj)
diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h
index c7d844f..a785f25 100644
--- a/include/linux/dma-debug.h
+++ b/include/linux/dma-debug.h
@@ -30,8 +30,6 @@ struct bus_type;
extern void dma_debug_add_bus(struct bus_type *bus);
-extern void dma_debug_init(u32 num_entries);
-
extern int dma_debug_resize_entries(u32 num_entries);
extern void debug_dma_map_page(struct device *dev, struct page *page,
@@ -100,10 +98,6 @@ static inline void dma_debug_add_bus(struct bus_type *bus)
{
}
-static inline void dma_debug_init(u32 num_entries)
-{
-}
-
static inline int dma_debug_resize_entries(u32 num_entries)
{
return 0;
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 53ad6a4..8d9f33f 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -59,6 +59,11 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
gfp_t gfp, unsigned long attrs);
void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
dma_addr_t dma_addr, unsigned long attrs);
+dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size, enum dma_data_direction dir,
+ unsigned long attrs);
+int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+ enum dma_data_direction dir, unsigned long attrs);
int dma_direct_supported(struct device *dev, u64 mask);
-
+int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr);
#endif /* _LINUX_DMA_DIRECT_H */
diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h
index 92f2083..e8ca5e6 100644
--- a/include/linux/dma-iommu.h
+++ b/include/linux/dma-iommu.h
@@ -17,6 +17,7 @@
#define __DMA_IOMMU_H
#ifdef __KERNEL__
+#include <linux/types.h>
#include <asm/errno.h>
#ifdef CONFIG_IOMMU_DMA
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index f8ab1c0..f9cc309 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -133,10 +133,10 @@ struct dma_map_ops {
#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK
u64 (*get_required_mask)(struct device *dev);
#endif
- int is_phys;
};
extern const struct dma_map_ops dma_direct_ops;
+extern const struct dma_map_ops dma_noncoherent_ops;
extern const struct dma_map_ops dma_virt_ops;
#define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
@@ -502,7 +502,7 @@ dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr,
#define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0)
#ifndef arch_dma_alloc_attrs
-#define arch_dma_alloc_attrs(dev, flag) (true)
+#define arch_dma_alloc_attrs(dev) (true)
#endif
static inline void *dma_alloc_attrs(struct device *dev, size_t size,
@@ -521,7 +521,7 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size,
/* let the implementation decide on the zone to allocate from: */
flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
- if (!arch_dma_alloc_attrs(&dev, &flag))
+ if (!arch_dma_alloc_attrs(&dev))
return NULL;
if (!ops->alloc)
return NULL;
@@ -572,14 +572,6 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
return 0;
}
-/*
- * This is a hack for the legacy x86 forbid_dac and iommu_sac_force. Please
- * don't use this in new code.
- */
-#ifndef arch_dma_supported
-#define arch_dma_supported(dev, mask) (1)
-#endif
-
static inline void dma_check_mask(struct device *dev, u64 mask)
{
if (sme_active() && (mask < (((u64)sme_get_me_mask() << 1) - 1)))
@@ -592,9 +584,6 @@ static inline int dma_supported(struct device *dev, u64 mask)
if (!ops)
return 0;
- if (!arch_dma_supported(dev, mask))
- return 0;
-
if (!ops->dma_supported)
return 1;
return ops->dma_supported(dev, mask);
@@ -839,7 +828,7 @@ static inline int dma_mmap_wc(struct device *dev,
#define dma_mmap_writecombine dma_mmap_wc
#endif
-#if defined(CONFIG_NEED_DMA_MAP_STATE) || defined(CONFIG_DMA_API_DEBUG)
+#ifdef CONFIG_NEED_DMA_MAP_STATE
#define DEFINE_DMA_UNMAP_ADDR(ADDR_NAME) dma_addr_t ADDR_NAME
#define DEFINE_DMA_UNMAP_LEN(LEN_NAME) __u32 LEN_NAME
#define dma_unmap_addr(PTR, ADDR_NAME) ((PTR)->ADDR_NAME)
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
new file mode 100644
index 0000000..10b2654
--- /dev/null
+++ b/include/linux/dma-noncoherent.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_DMA_NONCOHERENT_H
+#define _LINUX_DMA_NONCOHERENT_H 1
+
+#include <linux/dma-mapping.h>
+
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t gfp, unsigned long attrs);
+void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
+ dma_addr_t dma_addr, unsigned long attrs);
+
+#ifdef CONFIG_DMA_NONCOHERENT_MMAP
+int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs);
+#else
+#define arch_dma_mmap NULL
+#endif /* CONFIG_DMA_NONCOHERENT_MMAP */
+
+#ifdef CONFIG_DMA_NONCOHERENT_CACHE_SYNC
+void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+ enum dma_data_direction direction);
+#else
+#define arch_dma_cache_sync NULL
+#endif /* CONFIG_DMA_NONCOHERENT_CACHE_SYNC */
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir);
+#else
+static inline void arch_sync_dma_for_device(struct device *dev,
+ phys_addr_t paddr, size_t size, enum dma_data_direction dir)
+{
+}
+#endif /* ARCH_HAS_SYNC_DMA_FOR_DEVICE */
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir);
+#else
+static inline void arch_sync_dma_for_cpu(struct device *dev,
+ phys_addr_t paddr, size_t size, enum dma_data_direction dir)
+{
+}
+#endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */
+
+#endif /* _LINUX_DMA_NONCOHERENT_H */
diff --git a/include/linux/efi.h b/include/linux/efi.h
index f1b7d68..56add82 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -395,9 +395,9 @@ typedef struct {
u32 attributes;
u32 get_bar_attributes;
u32 set_bar_attributes;
- uint64_t romsize;
- void *romimage;
-} efi_pci_io_protocol_32;
+ u64 romsize;
+ u32 romimage;
+} efi_pci_io_protocol_32_t;
typedef struct {
u64 poll_mem;
@@ -415,9 +415,9 @@ typedef struct {
u64 attributes;
u64 get_bar_attributes;
u64 set_bar_attributes;
- uint64_t romsize;
- void *romimage;
-} efi_pci_io_protocol_64;
+ u64 romsize;
+ u64 romimage;
+} efi_pci_io_protocol_64_t;
typedef struct {
void *poll_mem;
@@ -437,7 +437,7 @@ typedef struct {
void *set_bar_attributes;
uint64_t romsize;
void *romimage;
-} efi_pci_io_protocol;
+} efi_pci_io_protocol_t;
#define EFI_PCI_IO_ATTRIBUTE_ISA_MOTHERBOARD_IO 0x0001
#define EFI_PCI_IO_ATTRIBUTE_ISA_IO 0x0002
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 6d9e230..a02deea3 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -218,8 +218,6 @@ extern void elv_unregister(struct elevator_type *);
extern ssize_t elv_iosched_show(struct request_queue *, char *);
extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t);
-extern int elevator_init(struct request_queue *, char *);
-extern void elevator_exit(struct request_queue *, struct elevator_queue *);
extern bool elv_bio_merge_ok(struct request *, struct bio *);
extern struct elevator_queue *elevator_alloc(struct request_queue *,
struct elevator_type *);
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index ebe4181..b32cd20 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -310,6 +310,8 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32,
* fields should be ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS
* instead of the latter), any change to them will be overwritten
* by kernel. Returns a negative error code or zero.
+ * @get_fecparam: Get the network device Forward Error Correction parameters.
+ * @set_fecparam: Set the network device Forward Error Correction parameters.
*
* All operations are optional (i.e. the function pointer may be set
* to %NULL) and callers must take this into account. Callers must
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 760d8da..7ef7193 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -94,7 +94,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
/*
* flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond
- * to O_WRONLY and O_RDWR via the strange trick in __dentry_open()
+ * to O_WRONLY and O_RDWR via the strange trick in do_dentry_open()
*/
/* file is open for reading */
@@ -1250,7 +1250,7 @@ static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
}
struct fasync_struct {
- spinlock_t fa_lock;
+ rwlock_t fa_lock;
int magic;
int fa_fd;
struct fasync_struct *fa_next; /* singly linked list */
@@ -1364,9 +1364,9 @@ struct super_block {
void *s_security;
#endif
const struct xattr_handler **s_xattr;
-
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
const struct fscrypt_operations *s_cop;
-
+#endif
struct hlist_bl_head s_roots; /* alternate root dentries for NFS */
struct list_head s_mounts; /* list of mounts; _not_ for fs use */
struct block_device *s_bdev;
@@ -1597,6 +1597,11 @@ static inline void sb_start_intwrite(struct super_block *sb)
__sb_start_write(sb, SB_FREEZE_FS, true);
}
+static inline int sb_start_intwrite_trylock(struct super_block *sb)
+{
+ return __sb_start_write(sb, SB_FREEZE_FS, false);
+}
+
extern bool inode_owner_or_capable(const struct inode *inode);
@@ -1711,6 +1716,8 @@ struct file_operations {
int (*iterate) (struct file *, struct dir_context *);
int (*iterate_shared) (struct file *, struct dir_context *);
__poll_t (*poll) (struct file *, struct poll_table_struct *);
+ struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
+ __poll_t (*poll_mask) (struct file *, __poll_t);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
@@ -2570,7 +2577,7 @@ extern bool is_bad_inode(struct inode *);
#ifdef CONFIG_BLOCK
extern void check_disk_size_change(struct gendisk *disk,
- struct block_device *bdev);
+ struct block_device *bdev, bool verbose);
extern int revalidate_disk(struct gendisk *);
extern int check_disk_change(struct block_device *);
extern int __invalidate_device(struct block_device *, bool);
diff --git a/include/linux/fscrypt_notsupp.h b/include/linux/fscrypt_notsupp.h
index 44b50c0..25b6492 100644
--- a/include/linux/fscrypt_notsupp.h
+++ b/include/linux/fscrypt_notsupp.h
@@ -64,16 +64,6 @@ static inline void fscrypt_restore_control_page(struct page *page)
return;
}
-static inline void fscrypt_set_d_op(struct dentry *dentry)
-{
- return;
-}
-
-static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry)
-{
- return;
-}
-
/* policy.c */
static inline int fscrypt_ioctl_set_policy(struct file *filp,
const void __user *arg)
diff --git a/include/linux/fscrypt_supp.h b/include/linux/fscrypt_supp.h
index 477a7a6..5080cb1 100644
--- a/include/linux/fscrypt_supp.h
+++ b/include/linux/fscrypt_supp.h
@@ -29,7 +29,7 @@ struct fscrypt_operations {
int (*set_context)(struct inode *, const void *, size_t, void *);
bool (*dummy_context)(struct inode *);
bool (*empty_dir)(struct inode *);
- unsigned (*max_namelen)(struct inode *);
+ unsigned int max_namelen;
};
struct fscrypt_ctx {
@@ -74,20 +74,6 @@ static inline struct page *fscrypt_control_page(struct page *page)
extern void fscrypt_restore_control_page(struct page *);
-extern const struct dentry_operations fscrypt_d_ops;
-
-static inline void fscrypt_set_d_op(struct dentry *dentry)
-{
- d_set_d_op(dentry, &fscrypt_d_ops);
-}
-
-static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry)
-{
- spin_lock(&dentry->d_lock);
- dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY;
- spin_unlock(&dentry->d_lock);
-}
-
/* policy.c */
extern int fscrypt_ioctl_set_policy(struct file *, const void __user *);
extern int fscrypt_ioctl_get_policy(struct file *, void __user *);
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 9f1edb9..e64c029 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -217,12 +217,10 @@ struct fsnotify_mark_connector {
union { /* Object pointer [lock] */
struct inode *inode;
struct vfsmount *mnt;
- };
- union {
- struct hlist_head list;
/* Used listing heads to free after srcu period expires */
struct fsnotify_mark_connector *destroy_next;
};
+ struct hlist_head list;
};
/*
@@ -248,7 +246,7 @@ struct fsnotify_mark {
/* Group this mark is for. Set on mark creation, stable until last ref
* is dropped */
struct fsnotify_group *group;
- /* List of marks by group->i_fsnotify_marks. Also reused for queueing
+ /* List of marks by group->marks_list. Also reused for queueing
* mark into destroy_list when it's waiting for the end of SRCU period
* before it can be freed. [group->mark_mutex] */
struct list_head g_list;
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index c826b0b..6cb8a57 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -368,7 +368,9 @@ static inline void free_part_stats(struct hd_struct *part)
part_stat_add(cpu, gendiskp, field, -subnd)
void part_in_flight(struct request_queue *q, struct hd_struct *part,
- unsigned int inflight[2]);
+ unsigned int inflight[2]);
+void part_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+ unsigned int inflight[2]);
void part_dec_in_flight(struct request_queue *q, struct hd_struct *part,
int rw);
void part_inc_in_flight(struct request_queue *q, struct hd_struct *part,
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 1a4582b..fc5ab85 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -464,7 +464,7 @@ static inline struct page *
__alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
{
VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
- VM_WARN_ON(!node_online(nid));
+ VM_WARN_ON((gfp_mask & __GFP_THISNODE) && !node_online(nid));
return __alloc_pages(gfp_mask, order, nid);
}
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 8da3e1f..26240a2 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -516,6 +516,12 @@ enum hid_type {
HID_TYPE_USBNONE
};
+enum hid_battery_status {
+ HID_BATTERY_UNKNOWN = 0,
+ HID_BATTERY_QUERIED, /* Kernel explicitly queried battery strength */
+ HID_BATTERY_REPORTED, /* Device sent unsolicited battery strength report */
+};
+
struct hid_driver;
struct hid_ll_driver;
@@ -558,7 +564,8 @@ struct hid_device { /* device report descriptor */
__s32 battery_max;
__s32 battery_report_type;
__s32 battery_report_id;
- bool battery_reported;
+ enum hid_battery_status battery_status;
+ bool battery_avoid_query;
#endif
unsigned int status; /* see STAT flags above */
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index 3998892..2f1327c 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -16,7 +16,7 @@
/*
* Heterogeneous Memory Management (HMM)
*
- * See Documentation/vm/hmm.txt for reasons and overview of what HMM is and it
+ * See Documentation/vm/hmm.rst for reasons and overview of what HMM is and it
* is for. Here we focus on the HMM API description, with some explanation of
* the underlying implementation.
*
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index a2656c3..3892e9c 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -161,9 +161,11 @@ struct hrtimer_clock_base {
enum hrtimer_base_type {
HRTIMER_BASE_MONOTONIC,
HRTIMER_BASE_REALTIME,
+ HRTIMER_BASE_BOOTTIME,
HRTIMER_BASE_TAI,
HRTIMER_BASE_MONOTONIC_SOFT,
HRTIMER_BASE_REALTIME_SOFT,
+ HRTIMER_BASE_BOOTTIME_SOFT,
HRTIMER_BASE_TAI_SOFT,
HRTIMER_MAX_CLOCK_BASES,
};
diff --git a/include/linux/ide.h b/include/linux/ide.h
index ca9d34f..c74b032 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -961,7 +961,7 @@ __IDE_PROC_DEVSET(_name, _min, _max, NULL, NULL)
typedef struct {
const char *name;
umode_t mode;
- const struct file_operations *proc_fops;
+ int (*show)(struct seq_file *, void *);
} ide_proc_entry_t;
void proc_ide_create(void);
@@ -973,8 +973,8 @@ void ide_proc_unregister_port(ide_hwif_t *);
void ide_proc_register_driver(ide_drive_t *, struct ide_driver *);
void ide_proc_unregister_driver(ide_drive_t *, struct ide_driver *);
-extern const struct file_operations ide_capacity_proc_fops;
-extern const struct file_operations ide_geometry_proc_fops;
+int ide_capacity_proc_show(struct seq_file *m, void *v);
+int ide_geometry_proc_show(struct seq_file *m, void *v);
#else
static inline void proc_ide_create(void) { ; }
static inline void proc_ide_destroy(void) { ; }
@@ -1508,8 +1508,6 @@ static inline void ide_set_hwifdata (ide_hwif_t * hwif, void *data)
hwif->hwif_data = data;
}
-extern void ide_toggle_bounce(ide_drive_t *drive, int on);
-
u64 ide_get_lba_addr(struct ide_cmd *, int);
u8 ide_dump_status(ide_drive_t *, const char *, u8);
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index d11f41d..78a5a90 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -663,7 +663,7 @@ static inline bool skb_vlan_tagged(const struct sk_buff *skb)
* Returns true if the skb is tagged with multiple vlan headers, regardless
* of whether it is hardware accelerated or not.
*/
-static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
+static inline bool skb_vlan_tagged_multi(struct sk_buff *skb)
{
__be16 protocol = skb->protocol;
@@ -673,6 +673,9 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
if (likely(!eth_type_vlan(protocol)))
return false;
+ if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN)))
+ return false;
+
veh = (struct vlan_ethhdr *)skb->data;
protocol = veh->h_vlan_encapsulated_proto;
}
@@ -690,7 +693,7 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
*
* Returns features without unsafe ones if the skb has multiple tags.
*/
-static inline netdev_features_t vlan_features_check(const struct sk_buff *skb,
+static inline netdev_features_t vlan_features_check(struct sk_buff *skb,
netdev_features_t features)
{
if (skb_vlan_tagged_multi(skb)) {
diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h
index b9e22b7..d1171db2 100644
--- a/include/linux/iio/buffer_impl.h
+++ b/include/linux/iio/buffer_impl.h
@@ -53,7 +53,7 @@ struct iio_buffer_access_funcs {
int (*request_update)(struct iio_buffer *buffer);
int (*set_bytes_per_datum)(struct iio_buffer *buffer, size_t bpd);
- int (*set_length)(struct iio_buffer *buffer, int length);
+ int (*set_length)(struct iio_buffer *buffer, unsigned int length);
int (*enable)(struct iio_buffer *buffer, struct iio_dev *indio_dev);
int (*disable)(struct iio_buffer *buffer, struct iio_dev *indio_dev);
@@ -72,10 +72,10 @@ struct iio_buffer_access_funcs {
*/
struct iio_buffer {
/** @length: Number of datums in buffer. */
- int length;
+ unsigned int length;
/** @bytes_per_datum: Size of individual datum including timestamp. */
- int bytes_per_datum;
+ size_t bytes_per_datum;
/**
* @access: Buffer access functions associated with the
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 5426627..eeceac3 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -432,11 +432,18 @@ extern bool force_irqthreads;
#define force_irqthreads (0)
#endif
-#ifndef __ARCH_SET_SOFTIRQ_PENDING
-#define set_softirq_pending(x) (local_softirq_pending() = (x))
-#define or_softirq_pending(x) (local_softirq_pending() |= (x))
+#ifndef local_softirq_pending
+
+#ifndef local_softirq_pending_ref
+#define local_softirq_pending_ref irq_stat.__softirq_pending
#endif
+#define local_softirq_pending() (__this_cpu_read(local_softirq_pending_ref))
+#define set_softirq_pending(x) (__this_cpu_write(local_softirq_pending_ref, (x)))
+#define or_softirq_pending(x) (__this_cpu_or(local_softirq_pending_ref, (x)))
+
+#endif /* local_softirq_pending */
+
/* Some architectures might implement lazy enabling/disabling of
* interrupts. In some cases, such as stop_machine, we might want
* to ensure that after a local_irq_disable(), interrupts have
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 19a07de..a044a82 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -4,6 +4,7 @@
#include <linux/types.h>
+struct address_space;
struct fiemap_extent_info;
struct inode;
struct iov_iter;
@@ -18,6 +19,7 @@ struct vm_fault;
#define IOMAP_DELALLOC 0x02 /* delayed allocation blocks */
#define IOMAP_MAPPED 0x03 /* blocks allocated at @addr */
#define IOMAP_UNWRITTEN 0x04 /* blocks allocated at @addr in unwritten state */
+#define IOMAP_INLINE 0x05 /* data inline in the inode */
/*
* Flags for all iomap mappings:
@@ -26,15 +28,19 @@ struct vm_fault;
* written data and requires fdatasync to commit them to persistent storage.
*/
#define IOMAP_F_NEW 0x01 /* blocks have been newly allocated */
-#define IOMAP_F_BOUNDARY 0x02 /* mapping ends at metadata boundary */
-#define IOMAP_F_DIRTY 0x04 /* uncommitted metadata */
+#define IOMAP_F_DIRTY 0x02 /* uncommitted metadata */
/*
* Flags that only need to be reported for IOMAP_REPORT requests:
*/
#define IOMAP_F_MERGED 0x10 /* contains multiple blocks/extents */
#define IOMAP_F_SHARED 0x20 /* block shared with another file */
-#define IOMAP_F_DATA_INLINE 0x40 /* data inline in the inode */
+
+/*
+ * Flags from 0x1000 up are for file system specific usage:
+ */
+#define IOMAP_F_PRIVATE 0x1000
+
/*
* Magic value for addr:
@@ -59,7 +65,7 @@ struct iomap {
#define IOMAP_REPORT (1 << 2) /* report extent status, e.g. FIEMAP */
#define IOMAP_FAULT (1 << 3) /* mapping for page fault */
#define IOMAP_DIRECT (1 << 4) /* direct I/O */
-#define IOMAP_NOWAIT (1 << 5) /* Don't wait for writeback */
+#define IOMAP_NOWAIT (1 << 5) /* do not block */
struct iomap_ops {
/*
@@ -95,6 +101,8 @@ loff_t iomap_seek_hole(struct inode *inode, loff_t offset,
const struct iomap_ops *ops);
loff_t iomap_seek_data(struct inode *inode, loff_t offset,
const struct iomap_ops *ops);
+sector_t iomap_bmap(struct address_space *mapping, sector_t bno,
+ const struct iomap_ops *ops);
/*
* Flags for direct I/O ->end_io:
@@ -106,4 +114,15 @@ typedef int (iomap_dio_end_io_t)(struct kiocb *iocb, ssize_t ret,
ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
const struct iomap_ops *ops, iomap_dio_end_io_t end_io);
+#ifdef CONFIG_SWAP
+struct file;
+struct swap_info_struct;
+
+int iomap_swapfile_activate(struct swap_info_struct *sis,
+ struct file *swap_file, sector_t *pagespan,
+ const struct iomap_ops *ops);
+#else
+# define iomap_swapfile_activate(sis, swapfile, pagespan, ops) (-EIO)
+#endif /* CONFIG_SWAP */
+
#endif /* LINUX_IOMAP_H */
diff --git a/include/linux/iommu-helper.h b/include/linux/iommu-helper.h
index cb9a924..70d01ed 100644
--- a/include/linux/iommu-helper.h
+++ b/include/linux/iommu-helper.h
@@ -2,6 +2,7 @@
#ifndef _LINUX_IOMMU_HELPER_H
#define _LINUX_IOMMU_HELPER_H
+#include <linux/bug.h>
#include <linux/kernel.h>
static inline unsigned long iommu_device_max_index(unsigned long size,
@@ -14,9 +15,15 @@ static inline unsigned long iommu_device_max_index(unsigned long size,
return size;
}
-extern int iommu_is_span_boundary(unsigned int index, unsigned int nr,
- unsigned long shift,
- unsigned long boundary_size);
+static inline int iommu_is_span_boundary(unsigned int index, unsigned int nr,
+ unsigned long shift, unsigned long boundary_size)
+{
+ BUG_ON(!is_power_of_2(boundary_size));
+
+ shift = (shift + index) & (boundary_size - 1);
+ return shift + nr > boundary_size;
+}
+
extern unsigned long iommu_area_alloc(unsigned long *map, unsigned long size,
unsigned long start, unsigned int nr,
unsigned long shift,
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 65916a3..b206708 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -512,6 +512,7 @@ enum {
IRQCHIP_SKIP_SET_WAKE = (1 << 4),
IRQCHIP_ONESHOT_SAFE = (1 << 5),
IRQCHIP_EOI_THREADED = (1 << 6),
+ IRQCHIP_SUPPORTS_LEVEL_MSI = (1 << 7),
};
#include <linux/irqdesc.h>
diff --git a/include/linux/irq_cpustat.h b/include/linux/irq_cpustat.h
index 4954948..6e8895c 100644
--- a/include/linux/irq_cpustat.h
+++ b/include/linux/irq_cpustat.h
@@ -18,15 +18,11 @@
*/
#ifndef __ARCH_IRQ_STAT
-extern irq_cpustat_t irq_stat[]; /* defined in asm/hardirq.h */
-#define __IRQ_STAT(cpu, member) (irq_stat[cpu].member)
+DECLARE_PER_CPU_ALIGNED(irq_cpustat_t, irq_stat); /* defined in asm/hardirq.h */
+#define __IRQ_STAT(cpu, member) (per_cpu(irq_stat.member, cpu))
#endif
- /* arch independent irq_stat fields */
-#define local_softirq_pending() \
- __IRQ_STAT(smp_processor_id(), __softirq_pending)
-
- /* arch dependent irq_stat fields */
+/* arch dependent irq_stat fields */
#define nmi_count(cpu) __IRQ_STAT((cpu), __nmi_count) /* i386 */
#endif /* __irq_cpustat_h */
diff --git a/include/linux/irq_sim.h b/include/linux/irq_sim.h
index 0380d89..630a57e 100644
--- a/include/linux/irq_sim.h
+++ b/include/linux/irq_sim.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (C) 2017-2018 Bartosz Golaszewski <brgl@bgdev.pl>
+ */
+
#ifndef _LINUX_IRQ_SIM_H
#define _LINUX_IRQ_SIM_H
-/*
- * Copyright (C) 2017 Bartosz Golaszewski <brgl@bgdev.pl>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
- */
#include <linux/irq_work.h>
#include <linux/device.h>
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index f5af3b5..cbb872c 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -587,6 +587,7 @@ struct fwnode_handle;
int its_cpu_init(void);
int its_init(struct fwnode_handle *handle, struct rdists *rdists,
struct irq_domain *domain);
+int mbi_init(struct fwnode_handle *fwnode, struct irq_domain *parent);
static inline bool gic_enable_sre(void)
{
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 48c7e86..dccfa65 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -301,7 +301,13 @@ static inline struct irq_domain *irq_find_matching_host(struct device_node *node
static inline struct irq_domain *irq_find_host(struct device_node *node)
{
- return irq_find_matching_host(node, DOMAIN_BUS_ANY);
+ struct irq_domain *d;
+
+ d = irq_find_matching_host(node, DOMAIN_BUS_WIRED);
+ if (!d)
+ d = irq_find_matching_host(node, DOMAIN_BUS_ANY);
+
+ return d;
}
/**
diff --git a/include/linux/isdn/capilli.h b/include/linux/isdn/capilli.h
index 11b57c4..d75e1ad 100644
--- a/include/linux/isdn/capilli.h
+++ b/include/linux/isdn/capilli.h
@@ -50,7 +50,7 @@ struct capi_ctr {
u16 (*send_message)(struct capi_ctr *, struct sk_buff *skb);
char *(*procinfo)(struct capi_ctr *);
- const struct file_operations *proc_fops;
+ int (*proc_show)(struct seq_file *, void *);
/* filled in before calling ready callback */
u8 manu[CAPI_MANUFACTURER_LEN]; /* CAPI_GET_MANUFACTURER */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 6a1eb0b..7aed926 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -542,6 +542,7 @@ extern enum system_states {
SYSTEM_HALT,
SYSTEM_POWER_OFF,
SYSTEM_RESTART,
+ SYSTEM_SUSPEND,
} system_state;
/* This cannot be an enum because some may be used in assembly source. */
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index c196176..2803264 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -62,6 +62,7 @@ void *kthread_probe_data(struct task_struct *k);
int kthread_park(struct task_struct *k);
void kthread_unpark(struct task_struct *k);
void kthread_parkme(void);
+void kthread_park_complete(struct task_struct *k);
int kthreadd(void *unused);
extern struct task_struct *kthreadd_task;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 6930c63..6d6e79c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1045,13 +1045,7 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)
#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
-#ifdef CONFIG_S390
-#define KVM_MAX_IRQ_ROUTES 4096 //FIXME: we can have more than that...
-#elif defined(CONFIG_ARM64)
-#define KVM_MAX_IRQ_ROUTES 4096
-#else
-#define KVM_MAX_IRQ_ROUTES 1024
-#endif
+#define KVM_MAX_IRQ_ROUTES 4096 /* might need extension/rework in the future */
bool kvm_arch_can_set_irq_routing(struct kvm *kvm);
int kvm_set_irq_routing(struct kvm *kvm,
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 1795fec..1c11313 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1133,7 +1133,6 @@ extern int ata_sas_port_start(struct ata_port *ap);
extern void ata_sas_port_stop(struct ata_port *ap);
extern int ata_sas_slave_configure(struct scsi_device *, struct ata_port *);
extern int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap);
-extern enum blk_eh_timer_return ata_scsi_timed_out(struct scsi_cmnd *cmd);
extern int sata_scr_valid(struct ata_link *link);
extern int sata_scr_read(struct ata_link *link, int reg, u32 *val);
extern int sata_scr_write(struct ata_link *link, int reg, u32 val);
@@ -1359,7 +1358,6 @@ extern struct device_attribute *ata_common_sdev_attrs[];
.proc_name = drv_name, \
.slave_configure = ata_scsi_slave_config, \
.slave_destroy = ata_scsi_slave_destroy, \
- .eh_timed_out = ata_scsi_timed_out, \
.bios_param = ata_std_bios_param, \
.unlock_native_capacity = ata_scsi_unlock_native_capacity, \
.sdev_attrs = ata_common_sdev_attrs
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 6e0859b..e9e0d1c 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -489,7 +489,7 @@ typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *);
typedef sector_t (nvm_tgt_capacity_fn)(void *);
typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *,
int flags);
-typedef void (nvm_tgt_exit_fn)(void *);
+typedef void (nvm_tgt_exit_fn)(void *, bool);
typedef int (nvm_tgt_sysfs_init_fn)(struct gendisk *);
typedef void (nvm_tgt_sysfs_exit_fn)(struct gendisk *);
diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h
index 4754f01..aec44b1 100644
--- a/include/linux/livepatch.h
+++ b/include/linux/livepatch.h
@@ -186,13 +186,20 @@ static inline bool klp_have_reliable_stack(void)
IS_ENABLED(CONFIG_HAVE_RELIABLE_STACKTRACE);
}
+typedef int (*klp_shadow_ctor_t)(void *obj,
+ void *shadow_data,
+ void *ctor_data);
+typedef void (*klp_shadow_dtor_t)(void *obj, void *shadow_data);
+
void *klp_shadow_get(void *obj, unsigned long id);
-void *klp_shadow_alloc(void *obj, unsigned long id, void *data,
- size_t size, gfp_t gfp_flags);
-void *klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data,
- size_t size, gfp_t gfp_flags);
-void klp_shadow_free(void *obj, unsigned long id);
-void klp_shadow_free_all(unsigned long id);
+void *klp_shadow_alloc(void *obj, unsigned long id,
+ size_t size, gfp_t gfp_flags,
+ klp_shadow_ctor_t ctor, void *ctor_data);
+void *klp_shadow_get_or_alloc(void *obj, unsigned long id,
+ size_t size, gfp_t gfp_flags,
+ klp_shadow_ctor_t ctor, void *ctor_data);
+void klp_shadow_free(void *obj, unsigned long id, klp_shadow_dtor_t dtor);
+void klp_shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor);
#else /* !CONFIG_LIVEPATCH */
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index e0e49b5..2b02652 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -216,6 +216,9 @@ void put_online_mems(void);
void mem_hotplug_begin(void);
void mem_hotplug_done(void);
+extern void set_zone_contiguous(struct zone *zone);
+extern void clear_zone_contiguous(struct zone *zone);
+
#else /* ! CONFIG_MEMORY_HOTPLUG */
#define pfn_to_online_page(pfn) \
({ \
diff --git a/include/linux/mempool.h b/include/linux/mempool.h
index b51f5c4..0c964ac 100644
--- a/include/linux/mempool.h
+++ b/include/linux/mempool.h
@@ -25,6 +25,18 @@ typedef struct mempool_s {
wait_queue_head_t wait;
} mempool_t;
+static inline bool mempool_initialized(mempool_t *pool)
+{
+ return pool->elements != NULL;
+}
+
+void mempool_exit(mempool_t *pool);
+int mempool_init_node(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn,
+ mempool_free_t *free_fn, void *pool_data,
+ gfp_t gfp_mask, int node_id);
+int mempool_init(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn,
+ mempool_free_t *free_fn, void *pool_data);
+
extern mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn,
mempool_free_t *free_fn, void *pool_data);
extern mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn,
@@ -43,6 +55,14 @@ extern void mempool_free(void *element, mempool_t *pool);
*/
void *mempool_alloc_slab(gfp_t gfp_mask, void *pool_data);
void mempool_free_slab(void *element, void *pool_data);
+
+static inline int
+mempool_init_slab_pool(mempool_t *pool, int min_nr, struct kmem_cache *kc)
+{
+ return mempool_init(pool, min_nr, mempool_alloc_slab,
+ mempool_free_slab, (void *) kc);
+}
+
static inline mempool_t *
mempool_create_slab_pool(int min_nr, struct kmem_cache *kc)
{
@@ -56,6 +76,13 @@ mempool_create_slab_pool(int min_nr, struct kmem_cache *kc)
*/
void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data);
void mempool_kfree(void *element, void *pool_data);
+
+static inline int mempool_init_kmalloc_pool(mempool_t *pool, int min_nr, size_t size)
+{
+ return mempool_init(pool, min_nr, mempool_kmalloc,
+ mempool_kfree, (void *) size);
+}
+
static inline mempool_t *mempool_create_kmalloc_pool(int min_nr, size_t size)
{
return mempool_create(min_nr, mempool_kmalloc, mempool_kfree,
@@ -68,6 +95,13 @@ static inline mempool_t *mempool_create_kmalloc_pool(int min_nr, size_t size)
*/
void *mempool_alloc_pages(gfp_t gfp_mask, void *pool_data);
void mempool_free_pages(void *element, void *pool_data);
+
+static inline int mempool_init_page_pool(mempool_t *pool, int min_nr, int order)
+{
+ return mempool_init(pool, min_nr, mempool_alloc_pages,
+ mempool_free_pages, (void *)(long)order);
+}
+
static inline mempool_t *mempool_create_page_pool(int min_nr, int order)
{
return mempool_create(min_nr, mempool_alloc_pages, mempool_free_pages,
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 7b4899c0..74ea5e2 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -45,7 +45,7 @@ struct vmem_altmap {
* must be treated as an opaque object, rather than a "normal" struct page.
*
* A more complete discussion of unaddressable memory may be found in
- * include/linux/hmm.h and Documentation/vm/hmm.txt.
+ * include/linux/hmm.h and Documentation/vm/hmm.rst.
*
* MEMORY_DEVICE_PUBLIC:
* Device memory that is cache coherent from device and CPU point of view. This
@@ -67,7 +67,7 @@ enum memory_type {
* page_free()
*
* Additional notes about MEMORY_DEVICE_PRIVATE may be found in
- * include/linux/hmm.h and Documentation/vm/hmm.txt. There is also a brief
+ * include/linux/hmm.h and Documentation/vm/hmm.rst. There is also a brief
* explanation in include/linux/memory_hotplug.h.
*
* The page_fault() callback must migrate page back, from device memory to
diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h
index 2d4e23c..f09e9cf 100644
--- a/include/linux/mfd/cros_ec.h
+++ b/include/linux/mfd/cros_ec.h
@@ -197,6 +197,8 @@ struct cros_ec_dev {
u32 features[2];
};
+#define to_cros_ec_dev(dev) container_of(dev, struct cros_ec_dev, class_dev)
+
/**
* cros_ec_suspend - Handle a suspend operation for the ChromeOS EC device
*
diff --git a/include/linux/mfd/mc13xxx.h b/include/linux/mfd/mc13xxx.h
index 638222e..54a3cd8 100644
--- a/include/linux/mfd/mc13xxx.h
+++ b/include/linux/mfd/mc13xxx.h
@@ -243,6 +243,8 @@ struct mc13xxx_platform_data {
#define MC13XXX_ADC0_LICELLCON (1 << 0)
#define MC13XXX_ADC0_CHRGICON (1 << 1)
#define MC13XXX_ADC0_BATICON (1 << 2)
+#define MC13XXX_ADC0_ADIN7SEL_DIE (1 << 4)
+#define MC13XXX_ADC0_ADIN7SEL_UID (2 << 4)
#define MC13XXX_ADC0_ADREFEN (1 << 10)
#define MC13XXX_ADC0_TSMOD0 (1 << 12)
#define MC13XXX_ADC0_TSMOD1 (1 << 13)
diff --git a/include/linux/microchipphy.h b/include/linux/microchipphy.h
index eb492d4..8f9c903 100644
--- a/include/linux/microchipphy.h
+++ b/include/linux/microchipphy.h
@@ -70,4 +70,12 @@
#define LAN88XX_MMD3_CHIP_ID (32877)
#define LAN88XX_MMD3_CHIP_REV (32878)
+/* DSP registers */
+#define PHY_ARDENNES_MMD_DEV_3_PHY_CFG (0x806A)
+#define PHY_ARDENNES_MMD_DEV_3_PHY_CFG_ZD_DLY_EN_ (0x2000)
+#define LAN88XX_EXT_PAGE_ACCESS_TR (0x52B5)
+#define LAN88XX_EXT_PAGE_TR_CR 16
+#define LAN88XX_EXT_PAGE_TR_LOW_DATA 17
+#define LAN88XX_EXT_PAGE_TR_HIGH_DATA 18
+
#endif /* _MICROCHIPPHY_H */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 767d193..d703774 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1284,25 +1284,9 @@ enum {
};
static inline const struct cpumask *
-mlx5_get_vector_affinity(struct mlx5_core_dev *dev, int vector)
+mlx5_get_vector_affinity_hint(struct mlx5_core_dev *dev, int vector)
{
- const struct cpumask *mask;
- struct irq_desc *desc;
- unsigned int irq;
- int eqn;
- int err;
-
- err = mlx5_vector2eqn(dev, MLX5_EQ_VEC_COMP_BASE + vector, &eqn, &irq);
- if (err)
- return NULL;
-
- desc = irq_to_desc(irq);
-#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
- mask = irq_data_get_effective_affinity_mask(&desc->irq_data);
-#else
- mask = desc->irq_common_data.affinity;
-#endif
- return mask;
+ return dev->priv.irq_info[vector].mask;
}
#endif /* MLX5_DRIVER_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1ac1f06..02a616e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2109,7 +2109,6 @@ extern void setup_per_cpu_pageset(void);
extern void zone_pcp_update(struct zone *zone);
extern void zone_pcp_reset(struct zone *zone);
-extern void setup_zone_pageset(struct zone *zone);
/* page_alloc.c */
extern int min_free_kbytes;
@@ -2466,6 +2465,13 @@ static inline vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma,
return VM_FAULT_NOPAGE;
}
+static inline vm_fault_t vmf_error(int err)
+{
+ if (err == -ENOMEM)
+ return VM_FAULT_OOM;
+ return VM_FAULT_SIGBUS;
+}
+
struct page *follow_page_mask(struct vm_area_struct *vma,
unsigned long address, unsigned int foll_flags,
unsigned int *page_mask);
@@ -2493,6 +2499,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma,
#define FOLL_MLOCK 0x1000 /* lock present pages */
#define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */
#define FOLL_COW 0x4000 /* internal GUP flag */
+#define FOLL_ANON 0x8000 /* don't do file mappings */
static inline int vm_fault_to_errno(int vm_fault, int foll_flags)
{
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 2d07a1e..392e6af 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -174,7 +174,7 @@ struct mmu_notifier_ops {
* invalidate_range_start()/end() notifiers, as
* invalidate_range() alread catches the points in time when an
* external TLB range needs to be flushed. For more in depth
- * discussion on this see Documentation/vm/mmu_notifier.txt
+ * discussion on this see Documentation/vm/mmu_notifier.rst
*
* Note that this function might be called with just a sub-range
* of what was passed to invalidate_range_start()/end(), if
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 1f1bbb5..5839d80 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -289,6 +289,8 @@ enum {
* MSI_FLAG_ACTIVATE_EARLY has been set.
*/
MSI_FLAG_MUST_REACTIVATE = (1 << 5),
+ /* Is level-triggered capable, using two messages */
+ MSI_FLAG_LEVEL_CAPABLE = (1 << 6),
};
int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask,
diff --git a/include/linux/mtd/flashchip.h b/include/linux/mtd/flashchip.h
index b63fa45..3529683 100644
--- a/include/linux/mtd/flashchip.h
+++ b/include/linux/mtd/flashchip.h
@@ -85,6 +85,7 @@ struct flchip {
unsigned int write_suspended:1;
unsigned int erase_suspended:1;
unsigned long in_progress_block_addr;
+ unsigned long in_progress_block_mask;
struct mutex mutex;
wait_queue_head_t wq; /* Wait on here when we're waiting for the chip
diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h
index b5b43f9..01b990e 100644
--- a/include/linux/mtd/map.h
+++ b/include/linux/mtd/map.h
@@ -312,7 +312,7 @@ void map_destroy(struct mtd_info *mtd);
({ \
int i, ret = 1; \
for (i = 0; i < map_words(map); i++) { \
- if (((val1).x[i] & (val2).x[i]) != (val2).x[i]) { \
+ if (((val1).x[i] & (val2).x[i]) != (val3).x[i]) { \
ret = 0; \
break; \
} \
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 5dad59b..17c9194 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -867,12 +867,18 @@ struct nand_op_instr {
* tBERS (during an erase) which all of them are u64 values that cannot be
* divided by usual kernel macros and must be handled with the special
* DIV_ROUND_UP_ULL() macro.
+ *
+ * Cast to type of dividend is needed here to guarantee that the result won't
+ * be an unsigned long long when the dividend is an unsigned long (or smaller),
+ * which is what the compiler does when it sees ternary operator with 2
+ * different return types (picks the largest type to make sure there's no
+ * loss).
*/
-#define __DIVIDE(dividend, divisor) ({ \
- sizeof(dividend) == sizeof(u32) ? \
- DIV_ROUND_UP(dividend, divisor) : \
- DIV_ROUND_UP_ULL(dividend, divisor); \
- })
+#define __DIVIDE(dividend, divisor) ({ \
+ (__typeof__(dividend))(sizeof(dividend) <= sizeof(unsigned long) ? \
+ DIV_ROUND_UP(dividend, divisor) : \
+ DIV_ROUND_UP_ULL(dividend, divisor)); \
+ })
#define PSEC_TO_NSEC(x) __DIVIDE(x, 1000)
#define PSEC_TO_MSEC(x) __DIVIDE(x, 1000000000)
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 14bc0d5..3093dd1 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -146,9 +146,6 @@ extern void __mutex_init(struct mutex *lock, const char *name,
*/
static inline bool mutex_is_locked(struct mutex *lock)
{
- /*
- * XXX think about spin_is_locked
- */
return __mutex_owner(lock) != NULL;
}
diff --git a/include/linux/net.h b/include/linux/net.h
index 2248a05..3fd9d8c 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -147,6 +147,7 @@ struct proto_ops {
int (*getname) (struct socket *sock,
struct sockaddr *addr,
int peer);
+ __poll_t (*poll_mask) (struct socket *sock, __poll_t events);
__poll_t (*poll) (struct file *file, struct socket *sock,
struct poll_table_struct *wait);
int (*ioctl) (struct socket *sock, unsigned int cmd,
diff --git a/include/linux/node.h b/include/linux/node.h
index 41f17186..6d336e3 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -32,9 +32,11 @@ extern struct node *node_devices[];
typedef void (*node_registration_func_t)(struct node *);
#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA)
-extern int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages);
+extern int link_mem_sections(int nid, unsigned long start_pfn,
+ unsigned long nr_pages, bool check_nid);
#else
-static inline int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages)
+static inline int link_mem_sections(int nid, unsigned long start_pfn,
+ unsigned long nr_pages, bool check_nid)
{
return 0;
}
@@ -57,7 +59,7 @@ static inline int register_one_node(int nid)
if (error)
return error;
/* link memory sections under this node */
- error = link_mem_sections(nid, pgdat->node_start_pfn, pgdat->node_spanned_pages);
+ error = link_mem_sections(nid, pgdat->node_start_pfn, pgdat->node_spanned_pages, true);
}
return error;
diff --git a/include/linux/nospec.h b/include/linux/nospec.h
index e791ebc..0c5ef54 100644
--- a/include/linux/nospec.h
+++ b/include/linux/nospec.h
@@ -7,6 +7,8 @@
#define _LINUX_NOSPEC_H
#include <asm/barrier.h>
+struct task_struct;
+
/**
* array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise
* @index: array element index
@@ -55,4 +57,12 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
\
(typeof(_i)) (_i & _mask); \
})
+
+/* Speculation control prctl */
+int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which);
+int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
+ unsigned long ctrl);
+/* Speculation control for seccomp enforced mitigation */
+void arch_seccomp_spec_mitigate(struct task_struct *task);
+
#endif /* _LINUX_NOSPEC_H */
diff --git a/include/linux/notifier.h b/include/linux/notifier.h
index 6d73111..f35c7bf 100644
--- a/include/linux/notifier.h
+++ b/include/linux/notifier.h
@@ -43,9 +43,7 @@
* in srcu_notifier_call_chain(): no cache bounces and no memory barriers.
* As compensation, srcu_notifier_chain_unregister() is rather expensive.
* SRCU notifier chains should be used when the chain will be called very
- * often but notifier_blocks will seldom be removed. Also, SRCU notifier
- * chains are slightly more difficult to use because they require special
- * runtime initialization.
+ * often but notifier_blocks will seldom be removed.
*/
struct notifier_block;
@@ -91,7 +89,7 @@ struct srcu_notifier_head {
(name)->head = NULL; \
} while (0)
-/* srcu_notifier_heads must be initialized and cleaned up dynamically */
+/* srcu_notifier_heads must be cleaned up dynamically */
extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
#define srcu_cleanup_notifier_head(name) \
cleanup_srcu_struct(&(name)->srcu);
@@ -104,7 +102,13 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
.head = NULL }
#define RAW_NOTIFIER_INIT(name) { \
.head = NULL }
-/* srcu_notifier_heads cannot be initialized statically */
+
+#define SRCU_NOTIFIER_INIT(name, pcpu) \
+ { \
+ .mutex = __MUTEX_INITIALIZER(name.mutex), \
+ .head = NULL, \
+ .srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu), \
+ }
#define ATOMIC_NOTIFIER_HEAD(name) \
struct atomic_notifier_head name = \
@@ -116,6 +120,26 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
struct raw_notifier_head name = \
RAW_NOTIFIER_INIT(name)
+#ifdef CONFIG_TREE_SRCU
+#define _SRCU_NOTIFIER_HEAD(name, mod) \
+ static DEFINE_PER_CPU(struct srcu_data, \
+ name##_head_srcu_data); \
+ mod struct srcu_notifier_head name = \
+ SRCU_NOTIFIER_INIT(name, name##_head_srcu_data)
+
+#else
+#define _SRCU_NOTIFIER_HEAD(name, mod) \
+ mod struct srcu_notifier_head name = \
+ SRCU_NOTIFIER_INIT(name, name)
+
+#endif
+
+#define SRCU_NOTIFIER_HEAD(name) \
+ _SRCU_NOTIFIER_HEAD(name, /* not static */)
+
+#define SRCU_NOTIFIER_HEAD_STATIC(name) \
+ _SRCU_NOTIFIER_HEAD(name, static)
+
#ifdef __KERNEL__
extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh,
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 4112e2b..2950ce9 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -436,10 +436,19 @@ enum {
enum {
NVME_AER_ERROR = 0,
NVME_AER_SMART = 1,
+ NVME_AER_NOTICE = 2,
NVME_AER_CSS = 6,
NVME_AER_VS = 7,
- NVME_AER_NOTICE_NS_CHANGED = 0x0002,
- NVME_AER_NOTICE_FW_ACT_STARTING = 0x0102,
+};
+
+enum {
+ NVME_AER_NOTICE_NS_CHANGED = 0x00,
+ NVME_AER_NOTICE_FW_ACT_STARTING = 0x01,
+};
+
+enum {
+ NVME_AEN_CFG_NS_ATTR = 1 << 8,
+ NVME_AEN_CFG_FW_ACT = 1 << 9,
};
struct nvme_lba_range_type {
@@ -747,6 +756,7 @@ enum {
NVME_LOG_ERROR = 0x01,
NVME_LOG_SMART = 0x02,
NVME_LOG_FW_SLOT = 0x03,
+ NVME_LOG_CHANGED_NS = 0x04,
NVME_LOG_CMD_EFFECTS = 0x05,
NVME_LOG_DISC = 0x70,
NVME_LOG_RESERVATION = 0x80,
@@ -755,6 +765,8 @@ enum {
NVME_FWACT_ACTV = (2 << 3),
};
+#define NVME_MAX_CHANGED_NAMESPACES 1024
+
struct nvme_identify {
__u8 opcode;
__u8 flags;
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 8da5a1b3..165fd30 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -55,7 +55,9 @@ static inline struct device_node *of_cpu_device_node_get(int cpu)
return of_node_get(cpu_dev->of_node);
}
-int of_dma_configure(struct device *dev, struct device_node *np);
+int of_dma_configure(struct device *dev,
+ struct device_node *np,
+ bool force_dma);
void of_dma_deconfigure(struct device *dev);
#else /* CONFIG_OF */
@@ -105,7 +107,9 @@ static inline struct device_node *of_cpu_device_node_get(int cpu)
return NULL;
}
-static inline int of_dma_configure(struct device *dev, struct device_node *np)
+static inline int of_dma_configure(struct device *dev,
+ struct device_node *np,
+ bool force_dma)
{
return 0;
}
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 5bad038..6adac11 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -95,6 +95,8 @@ static inline int check_stable_address_space(struct mm_struct *mm)
return 0;
}
+void __oom_reap_task_mm(struct mm_struct *mm);
+
extern unsigned long oom_badness(struct task_struct *p,
struct mem_cgroup *memcg, const nodemask_t *nodemask,
unsigned long totalpages);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 73178a2..55371cb 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -670,7 +670,7 @@ int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn,
int raw_pci_write(unsigned int domain, unsigned int bus, unsigned int devfn,
int reg, int len, u32 val);
-#ifdef CONFIG_PCI_BUS_ADDR_T_64BIT
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
typedef u64 pci_bus_addr_t;
#else
typedef u32 pci_bus_addr_t;
diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index b1f37a8..79b99d6 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -133,7 +133,7 @@ static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem,
lock_release(&sem->rw_sem.dep_map, 1, ip);
#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
if (!read)
- sem->rw_sem.owner = NULL;
+ sem->rw_sem.owner = RWSEM_OWNER_UNKNOWN;
#endif
}
@@ -141,6 +141,10 @@ static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem,
bool read, unsigned long ip)
{
lock_acquire(&sem->rw_sem.dep_map, 0, 1, read, 1, NULL, ip);
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+ if (!read)
+ sem->rw_sem.owner = current;
+#endif
}
#endif
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e71e99e..bea0b0cd 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -467,7 +467,7 @@ enum perf_addr_filter_action_t {
*/
struct perf_addr_filter {
struct list_head entry;
- struct inode *inode;
+ struct path path;
unsigned long offset;
unsigned long size;
enum perf_addr_filter_action_t action;
@@ -1016,6 +1016,14 @@ static inline int is_software_event(struct perf_event *event)
return event->event_caps & PERF_EV_CAP_SOFTWARE;
}
+/*
+ * Return 1 for event in sw context, 0 for event in hw context
+ */
+static inline int in_software_context(struct perf_event *event)
+{
+ return event->ctx->pmu->task_ctx_nr == perf_sw_context;
+}
+
extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64);
diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h
index 93d142a..1746015 100644
--- a/include/linux/pktcdvd.h
+++ b/include/linux/pktcdvd.h
@@ -186,7 +186,7 @@ struct pktcdvd_device
sector_t current_sector; /* Keep track of where the elevator is */
atomic_t scan_queue; /* Set to non-zero when pkt_handle_queue */
/* needs to be run. */
- mempool_t *rb_pool; /* mempool for pkt_rb_node allocations */
+ mempool_t rb_pool; /* mempool for pkt_rb_node allocations */
struct packet_iosched iosched;
struct gendisk *disk;
diff --git a/include/linux/platform_data/clk-st.h b/include/linux/platform_data/clk-st.h
new file mode 100644
index 0000000..7cdb6a4
--- /dev/null
+++ b/include/linux/platform_data/clk-st.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * clock framework for AMD Stoney based clock
+ *
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ */
+
+#ifndef __CLK_ST_H
+#define __CLK_ST_H
+
+#include <linux/compiler.h>
+
+struct st_clk_data {
+ void __iomem *base;
+};
+
+#endif /* __CLK_ST_H */
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 49f634d..3097c94 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -356,6 +356,8 @@ extern int platform_pm_restore(struct device *dev);
#define platform_pm_restore NULL
#endif
+extern int platform_dma_configure(struct device *dev);
+
#ifdef CONFIG_PM_SLEEP
#define USE_PLATFORM_PM_SLEEP_OPS \
.suspend = platform_pm_suspend, \
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 04dbef9..42e0d64 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -47,8 +47,10 @@ struct genpd_power_state {
};
struct genpd_lock_ops;
+struct dev_pm_opp;
struct generic_pm_domain {
+ struct device dev;
struct dev_pm_domain domain; /* PM domain operations */
struct list_head gpd_list_node; /* Node in the global PM domains list */
struct list_head master_links; /* Links with PM domain as a master */
@@ -67,6 +69,8 @@ struct generic_pm_domain {
unsigned int performance_state; /* Aggregated max performance state */
int (*power_off)(struct generic_pm_domain *domain);
int (*power_on)(struct generic_pm_domain *domain);
+ unsigned int (*opp_to_performance_state)(struct generic_pm_domain *genpd,
+ struct dev_pm_opp *opp);
int (*set_performance_state)(struct generic_pm_domain *genpd,
unsigned int state);
struct gpd_dev_ops dev_ops;
@@ -139,21 +143,16 @@ static inline struct generic_pm_domain_data *dev_gpd_data(struct device *dev)
return to_gpd_data(dev->power.subsys_data->domain_data);
}
-extern int __pm_genpd_add_device(struct generic_pm_domain *genpd,
- struct device *dev,
- struct gpd_timing_data *td);
-
-extern int pm_genpd_remove_device(struct generic_pm_domain *genpd,
- struct device *dev);
-extern int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
- struct generic_pm_domain *new_subdomain);
-extern int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
- struct generic_pm_domain *target);
-extern int pm_genpd_init(struct generic_pm_domain *genpd,
- struct dev_power_governor *gov, bool is_off);
-extern int pm_genpd_remove(struct generic_pm_domain *genpd);
-extern int dev_pm_genpd_set_performance_state(struct device *dev,
- unsigned int state);
+int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev);
+int pm_genpd_remove_device(struct device *dev);
+int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
+ struct generic_pm_domain *new_subdomain);
+int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
+ struct generic_pm_domain *target);
+int pm_genpd_init(struct generic_pm_domain *genpd,
+ struct dev_power_governor *gov, bool is_off);
+int pm_genpd_remove(struct generic_pm_domain *genpd);
+int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state);
extern struct dev_power_governor simple_qos_governor;
extern struct dev_power_governor pm_domain_always_on_gov;
@@ -163,14 +162,12 @@ static inline struct generic_pm_domain_data *dev_gpd_data(struct device *dev)
{
return ERR_PTR(-ENOSYS);
}
-static inline int __pm_genpd_add_device(struct generic_pm_domain *genpd,
- struct device *dev,
- struct gpd_timing_data *td)
+static inline int pm_genpd_add_device(struct generic_pm_domain *genpd,
+ struct device *dev)
{
return -ENOSYS;
}
-static inline int pm_genpd_remove_device(struct generic_pm_domain *genpd,
- struct device *dev)
+static inline int pm_genpd_remove_device(struct device *dev)
{
return -ENOSYS;
}
@@ -204,15 +201,9 @@ static inline int dev_pm_genpd_set_performance_state(struct device *dev,
#define pm_domain_always_on_gov (*(struct dev_power_governor *)(NULL))
#endif
-static inline int pm_genpd_add_device(struct generic_pm_domain *genpd,
- struct device *dev)
-{
- return __pm_genpd_add_device(genpd, dev, NULL);
-}
-
#ifdef CONFIG_PM_GENERIC_DOMAINS_SLEEP
-extern void pm_genpd_syscore_poweroff(struct device *dev);
-extern void pm_genpd_syscore_poweron(struct device *dev);
+void pm_genpd_syscore_poweroff(struct device *dev);
+void pm_genpd_syscore_poweron(struct device *dev);
#else
static inline void pm_genpd_syscore_poweroff(struct device *dev) {}
static inline void pm_genpd_syscore_poweron(struct device *dev) {}
@@ -236,13 +227,14 @@ int of_genpd_add_provider_simple(struct device_node *np,
int of_genpd_add_provider_onecell(struct device_node *np,
struct genpd_onecell_data *data);
void of_genpd_del_provider(struct device_node *np);
-extern int of_genpd_add_device(struct of_phandle_args *args,
- struct device *dev);
-extern int of_genpd_add_subdomain(struct of_phandle_args *parent,
- struct of_phandle_args *new_subdomain);
-extern struct generic_pm_domain *of_genpd_remove_last(struct device_node *np);
-extern int of_genpd_parse_idle_states(struct device_node *dn,
- struct genpd_power_state **states, int *n);
+int of_genpd_add_device(struct of_phandle_args *args, struct device *dev);
+int of_genpd_add_subdomain(struct of_phandle_args *parent,
+ struct of_phandle_args *new_subdomain);
+struct generic_pm_domain *of_genpd_remove_last(struct device_node *np);
+int of_genpd_parse_idle_states(struct device_node *dn,
+ struct genpd_power_state **states, int *n);
+unsigned int of_genpd_opp_to_performance_state(struct device *dev,
+ struct device_node *opp_node);
int genpd_dev_pm_attach(struct device *dev);
#else /* !CONFIG_PM_GENERIC_DOMAINS_OF */
@@ -278,11 +270,18 @@ static inline int of_genpd_parse_idle_states(struct device_node *dn,
return -ENODEV;
}
-static inline int genpd_dev_pm_attach(struct device *dev)
+static inline unsigned int
+of_genpd_opp_to_performance_state(struct device *dev,
+ struct device_node *opp_node)
{
return -ENODEV;
}
+static inline int genpd_dev_pm_attach(struct device *dev)
+{
+ return 0;
+}
+
static inline
struct generic_pm_domain *of_genpd_remove_last(struct device_node *np)
{
@@ -291,13 +290,13 @@ struct generic_pm_domain *of_genpd_remove_last(struct device_node *np)
#endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
#ifdef CONFIG_PM
-extern int dev_pm_domain_attach(struct device *dev, bool power_on);
-extern void dev_pm_domain_detach(struct device *dev, bool power_off);
-extern void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd);
+int dev_pm_domain_attach(struct device *dev, bool power_on);
+void dev_pm_domain_detach(struct device *dev, bool power_off);
+void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd);
#else
static inline int dev_pm_domain_attach(struct device *dev, bool power_on)
{
- return -ENODEV;
+ return 0;
}
static inline void dev_pm_domain_detach(struct device *dev, bool power_off) {}
static inline void dev_pm_domain_set(struct device *dev,
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 6c2d2e8..099b319 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -125,8 +125,6 @@ struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name);
void dev_pm_opp_put_clkname(struct opp_table *opp_table);
struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data));
void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table);
-struct opp_table *dev_pm_opp_register_get_pstate_helper(struct device *dev, int (*get_pstate)(struct device *dev, unsigned long rate));
-void dev_pm_opp_unregister_get_pstate_helper(struct opp_table *opp_table);
int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq);
int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask);
int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask);
@@ -247,14 +245,6 @@ static inline struct opp_table *dev_pm_opp_register_set_opp_helper(struct device
static inline void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table) {}
-static inline struct opp_table *dev_pm_opp_register_get_pstate_helper(struct device *dev,
- int (*get_pstate)(struct device *dev, unsigned long rate))
-{
- return ERR_PTR(-ENOTSUPP);
-}
-
-static inline void dev_pm_opp_unregister_get_pstate_helper(struct opp_table *opp_table) {}
-
static inline struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name)
{
return ERR_PTR(-ENOTSUPP);
@@ -303,17 +293,25 @@ static inline void dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask
#if defined(CONFIG_PM_OPP) && defined(CONFIG_OF)
int dev_pm_opp_of_add_table(struct device *dev);
+int dev_pm_opp_of_add_table_indexed(struct device *dev, int index);
void dev_pm_opp_of_remove_table(struct device *dev);
int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask);
void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpumask);
int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask);
struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev);
+struct dev_pm_opp *of_dev_pm_opp_find_required_opp(struct device *dev, struct device_node *np);
+struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp);
#else
static inline int dev_pm_opp_of_add_table(struct device *dev)
{
return -ENOTSUPP;
}
+static inline int dev_pm_opp_of_add_table_indexed(struct device *dev, int index)
+{
+ return -ENOTSUPP;
+}
+
static inline void dev_pm_opp_of_remove_table(struct device *dev)
{
}
@@ -336,6 +334,15 @@ static inline struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device
{
return NULL;
}
+
+static inline struct dev_pm_opp *of_dev_pm_opp_find_required_opp(struct device *dev, struct device_node *np)
+{
+ return NULL;
+}
+static inline struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp)
+{
+ return NULL;
+}
#endif
#endif /* __LINUX_OPP_H__ */
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index f0fc470..db5dbbf 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -56,8 +56,7 @@ extern void pm_runtime_update_max_time_suspended(struct device *dev,
s64 delta_ns);
extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable);
extern void pm_runtime_clean_up_links(struct device *dev);
-extern void pm_runtime_get_suppliers(struct device *dev);
-extern void pm_runtime_put_suppliers(struct device *dev);
+extern void pm_runtime_resume_suppliers(struct device *dev);
extern void pm_runtime_new_link(struct device *dev);
extern void pm_runtime_drop_link(struct device *dev);
@@ -173,8 +172,7 @@ static inline unsigned long pm_runtime_autosuspend_expiration(
static inline void pm_runtime_set_memalloc_noio(struct device *dev,
bool enable){}
static inline void pm_runtime_clean_up_links(struct device *dev) {}
-static inline void pm_runtime_get_suppliers(struct device *dev) {}
-static inline void pm_runtime_put_suppliers(struct device *dev) {}
+static inline void pm_runtime_resume_suppliers(struct device *dev) {}
static inline void pm_runtime_new_link(struct device *dev) {}
static inline void pm_runtime_drop_link(struct device *dev) {}
diff --git a/include/linux/poll.h b/include/linux/poll.h
index f45ebd0..fdf86b4 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -74,6 +74,18 @@ static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc)
pt->_key = ~(__poll_t)0; /* all events enabled */
}
+static inline bool file_has_poll_mask(struct file *file)
+{
+ return file->f_op->get_poll_head && file->f_op->poll_mask;
+}
+
+static inline bool file_can_poll(struct file *file)
+{
+ return file->f_op->poll || file_has_poll_mask(file);
+}
+
+__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt);
+
struct poll_table_entry {
struct file *filp;
__poll_t key;
@@ -96,8 +108,6 @@ struct poll_wqueues {
extern void poll_initwait(struct poll_wqueues *pwq);
extern void poll_freewait(struct poll_wqueues *pwq);
-extern int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
- ktime_t *expires, unsigned long slack);
extern u64 select_estimate_accuracy(struct timespec64 *tv);
#define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1)
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 928ef9e..e518352 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -9,6 +9,8 @@
#include <linux/fs.h>
struct proc_dir_entry;
+struct seq_file;
+struct seq_operations;
#ifdef CONFIG_PROC_FS
@@ -23,6 +25,19 @@ extern struct proc_dir_entry *proc_mkdir_data(const char *, umode_t,
extern struct proc_dir_entry *proc_mkdir_mode(const char *, umode_t,
struct proc_dir_entry *);
struct proc_dir_entry *proc_create_mount_point(const char *name);
+
+struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
+ struct proc_dir_entry *parent, const struct seq_operations *ops,
+ unsigned int state_size, void *data);
+#define proc_create_seq_data(name, mode, parent, ops, data) \
+ proc_create_seq_private(name, mode, parent, ops, 0, data)
+#define proc_create_seq(name, mode, parent, ops) \
+ proc_create_seq_private(name, mode, parent, ops, 0, NULL)
+struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode,
+ struct proc_dir_entry *parent,
+ int (*show)(struct seq_file *, void *), void *data);
+#define proc_create_single(name, mode, parent, show) \
+ proc_create_single_data(name, mode, parent, show, NULL)
extern struct proc_dir_entry *proc_create_data(const char *, umode_t,
struct proc_dir_entry *,
@@ -38,6 +53,15 @@ extern void proc_remove(struct proc_dir_entry *);
extern void remove_proc_entry(const char *, struct proc_dir_entry *);
extern int remove_proc_subtree(const char *, struct proc_dir_entry *);
+struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode,
+ struct proc_dir_entry *parent, const struct seq_operations *ops,
+ unsigned int state_size, void *data);
+#define proc_create_net(name, mode, parent, state_size, ops) \
+ proc_create_net_data(name, mode, parent, state_size, ops, NULL)
+struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode,
+ struct proc_dir_entry *parent,
+ int (*show)(struct seq_file *, void *), void *data);
+
#else /* CONFIG_PROC_FS */
static inline void proc_root_init(void)
@@ -57,6 +81,11 @@ static inline struct proc_dir_entry *proc_mkdir_data(const char *name,
umode_t mode, struct proc_dir_entry *parent, void *data) { return NULL; }
static inline struct proc_dir_entry *proc_mkdir_mode(const char *name,
umode_t mode, struct proc_dir_entry *parent) { return NULL; }
+#define proc_create_seq_private(name, mode, parent, ops, size, data) ({NULL;})
+#define proc_create_seq_data(name, mode, parent, ops, data) ({NULL;})
+#define proc_create_seq(name, mode, parent, ops) ({NULL;})
+#define proc_create_single(name, mode, parent, show) ({NULL;})
+#define proc_create_single_data(name, mode, parent, show, data) ({NULL;})
#define proc_create(name, mode, parent, proc_fops) ({NULL;})
#define proc_create_data(name, mode, parent, proc_fops, data) ({NULL;})
@@ -69,6 +98,10 @@ static inline void proc_remove(struct proc_dir_entry *de) {}
#define remove_proc_entry(name, parent) do {} while (0)
static inline int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) { return 0; }
+#define proc_create_net_data(name, mode, parent, ops, state_size, data) ({NULL;})
+#define proc_create_net(name, mode, parent, state_size, ops) ({NULL;})
+#define proc_create_net_single(name, mode, parent, show, data) ({NULL;})
+
#endif /* CONFIG_PROC_FS */
struct net;
@@ -83,4 +116,10 @@ struct ns_common;
int open_related_ns(struct ns_common *ns,
struct ns_common *(*get_ns)(struct ns_common *ns));
+/* get the associated pid namespace for a file in procfs */
+static inline struct pid_namespace *proc_pid_ns(struct inode *inode)
+{
+ return inode->i_sb->s_fs_info;
+}
+
#endif /* _LINUX_PROC_FS_H */
diff --git a/include/linux/property.h b/include/linux/property.h
index 2eea4b3..ac8a1ebc 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -178,7 +178,7 @@ static inline int fwnode_property_read_u64(const struct fwnode_handle *fwnode,
* @name: Name of the property.
* @length: Length of data making up the value.
* @is_array: True when the property is an array.
- * @is_string: True when property is a string.
+ * @type: Type of the data in unions.
* @pointer: Pointer to the property (an array of items of the given type).
* @value: Value of the property (when it is a single item of the given type).
*/
@@ -186,10 +186,9 @@ struct property_entry {
const char *name;
size_t length;
bool is_array;
- bool is_string;
+ enum dev_prop_type type;
union {
union {
- const void *raw_data;
const u8 *u8_data;
const u16 *u16_data;
const u32 *u32_data;
@@ -197,7 +196,6 @@ struct property_entry {
const char * const *str;
} pointer;
union {
- unsigned long long raw_data;
u8 u8_data;
u16 u16_data;
u32 u32_data;
@@ -213,55 +211,55 @@ struct property_entry {
* and structs.
*/
-#define PROPERTY_ENTRY_INTEGER_ARRAY(_name_, _type_, _val_) \
-(struct property_entry) { \
- .name = _name_, \
- .length = ARRAY_SIZE(_val_) * sizeof(_type_), \
- .is_array = true, \
- .is_string = false, \
- { .pointer = { ._type_##_data = _val_ } }, \
+#define PROPERTY_ENTRY_INTEGER_ARRAY(_name_, _type_, _Type_, _val_) \
+(struct property_entry) { \
+ .name = _name_, \
+ .length = ARRAY_SIZE(_val_) * sizeof(_type_), \
+ .is_array = true, \
+ .type = DEV_PROP_##_Type_, \
+ { .pointer = { ._type_##_data = _val_ } }, \
}
#define PROPERTY_ENTRY_U8_ARRAY(_name_, _val_) \
- PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u8, _val_)
+ PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u8, U8, _val_)
#define PROPERTY_ENTRY_U16_ARRAY(_name_, _val_) \
- PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u16, _val_)
+ PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u16, U16, _val_)
#define PROPERTY_ENTRY_U32_ARRAY(_name_, _val_) \
- PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u32, _val_)
+ PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u32, U32, _val_)
#define PROPERTY_ENTRY_U64_ARRAY(_name_, _val_) \
- PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u64, _val_)
+ PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u64, U64, _val_)
#define PROPERTY_ENTRY_STRING_ARRAY(_name_, _val_) \
(struct property_entry) { \
.name = _name_, \
.length = ARRAY_SIZE(_val_) * sizeof(const char *), \
.is_array = true, \
- .is_string = true, \
+ .type = DEV_PROP_STRING, \
{ .pointer = { .str = _val_ } }, \
}
-#define PROPERTY_ENTRY_INTEGER(_name_, _type_, _val_) \
-(struct property_entry) { \
- .name = _name_, \
- .length = sizeof(_type_), \
- .is_string = false, \
- { .value = { ._type_##_data = _val_ } }, \
+#define PROPERTY_ENTRY_INTEGER(_name_, _type_, _Type_, _val_) \
+(struct property_entry) { \
+ .name = _name_, \
+ .length = sizeof(_type_), \
+ .type = DEV_PROP_##_Type_, \
+ { .value = { ._type_##_data = _val_ } }, \
}
#define PROPERTY_ENTRY_U8(_name_, _val_) \
- PROPERTY_ENTRY_INTEGER(_name_, u8, _val_)
+ PROPERTY_ENTRY_INTEGER(_name_, u8, U8, _val_)
#define PROPERTY_ENTRY_U16(_name_, _val_) \
- PROPERTY_ENTRY_INTEGER(_name_, u16, _val_)
+ PROPERTY_ENTRY_INTEGER(_name_, u16, U16, _val_)
#define PROPERTY_ENTRY_U32(_name_, _val_) \
- PROPERTY_ENTRY_INTEGER(_name_, u32, _val_)
+ PROPERTY_ENTRY_INTEGER(_name_, u32, U32, _val_)
#define PROPERTY_ENTRY_U64(_name_, _val_) \
- PROPERTY_ENTRY_INTEGER(_name_, u64, _val_)
+ PROPERTY_ENTRY_INTEGER(_name_, u64, U64, _val_)
#define PROPERTY_ENTRY_STRING(_name_, _val_) \
(struct property_entry) { \
.name = _name_, \
.length = sizeof(_val_), \
- .is_string = true, \
+ .type = DEV_PROP_STRING, \
{ .value = { .str = _val_ } }, \
}
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 919b2a0..037bf0e 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -345,7 +345,6 @@ extern void user_single_step_siginfo(struct task_struct *tsk,
static inline void user_single_step_siginfo(struct task_struct *tsk,
struct pt_regs *regs, siginfo_t *info)
{
- memset(info, 0, sizeof(*info));
info->si_signo = SIGTRAP;
}
#endif
diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h
index 6bfd2b5..af8a61b 100644
--- a/include/linux/rbtree_augmented.h
+++ b/include/linux/rbtree_augmented.h
@@ -26,6 +26,7 @@
#include <linux/compiler.h>
#include <linux/rbtree.h>
+#include <linux/rcupdate.h>
/*
* Please note - only struct rb_augment_callbacks and the prototypes for
diff --git a/include/linux/rbtree_latch.h b/include/linux/rbtree_latch.h
index ece43e8..7d012fa 100644
--- a/include/linux/rbtree_latch.h
+++ b/include/linux/rbtree_latch.h
@@ -35,6 +35,7 @@
#include <linux/rbtree.h>
#include <linux/seqlock.h>
+#include <linux/rcupdate.h>
struct latch_tree_node {
struct rb_node node[2];
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 36360d0..e679b17 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -108,7 +108,6 @@ void rcu_sched_qs(void);
void rcu_bh_qs(void);
void rcu_check_callbacks(int user);
void rcu_report_dead(unsigned int cpu);
-void rcu_cpu_starting(unsigned int cpu);
void rcutree_migrate_callbacks(int cpu);
#ifdef CONFIG_RCU_STALL_COMMON
@@ -188,13 +187,13 @@ static inline void exit_tasks_rcu_finish(void) { }
#endif /* #else #ifdef CONFIG_TASKS_RCU */
/**
- * cond_resched_rcu_qs - Report potential quiescent states to RCU
+ * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU
*
* This macro resembles cond_resched(), except that it is defined to
* report potential quiescent states to RCU-tasks even if the cond_resched()
* machinery were to be shut off, as some advocate for PREEMPT kernels.
*/
-#define cond_resched_rcu_qs() \
+#define cond_resched_tasks_rcu_qs() \
do { \
if (!cond_resched()) \
rcu_note_voluntary_context_switch_lite(current); \
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index ce9beec..7b3c82e 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -132,5 +132,6 @@ static inline void rcu_all_qs(void) { barrier(); }
#define rcutree_offline_cpu NULL
#define rcutree_dead_cpu NULL
#define rcutree_dying_cpu NULL
+static inline void rcu_cpu_starting(unsigned int cpu) { }
#endif /* __LINUX_RCUTINY_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index fd996cd..9146558 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -74,6 +74,7 @@ static inline void synchronize_rcu_bh_expedited(void)
void rcu_barrier(void);
void rcu_barrier_bh(void);
void rcu_barrier_sched(void);
+bool rcu_eqs_special_set(int cpu);
unsigned long get_state_synchronize_rcu(void);
void cond_synchronize_rcu(unsigned long oldstate);
unsigned long get_state_synchronize_sched(void);
@@ -100,5 +101,6 @@ int rcutree_online_cpu(unsigned int cpu);
int rcutree_offline_cpu(unsigned int cpu);
int rcutree_dead_cpu(unsigned int cpu);
int rcutree_dying_cpu(unsigned int cpu);
+void rcu_cpu_starting(unsigned int cpu);
#endif /* __LINUX_RCUTREE_H */
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 5f7ad05..4f38068 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -15,6 +15,7 @@
#include <linux/list.h>
#include <linux/rbtree.h>
+#include <linux/ktime.h>
#include <linux/delay.h>
#include <linux/err.h>
#include <linux/bug.h>
@@ -587,7 +588,10 @@ struct regmap *__devm_regmap_init_sdw(struct sdw_slave *sdw,
const struct regmap_config *config,
struct lock_class_key *lock_key,
const char *lock_name);
-
+struct regmap *__devm_regmap_init_slimbus(struct slim_device *slimbus,
+ const struct regmap_config *config,
+ struct lock_class_key *lock_key,
+ const char *lock_name);
/*
* Wrapper for regmap_init macros to include a unique lockdep key and name
* for each call. No-op if CONFIG_LOCKDEP is not set.
@@ -906,6 +910,19 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
__regmap_lockdep_wrapper(__devm_regmap_init_sdw, #config, \
sdw, config)
+/**
+ * devm_regmap_init_slimbus() - Initialise managed register map
+ *
+ * @slimbus: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer
+ * to a struct regmap. The regmap will be automatically freed by the
+ * device management code.
+ */
+#define devm_regmap_init_slimbus(slimbus, config) \
+ __regmap_lockdep_wrapper(__devm_regmap_init_slimbus, #config, \
+ slimbus, config)
int regmap_mmio_attach_clk(struct regmap *map, struct clk *clk);
void regmap_mmio_detach_clk(struct regmap *map);
void regmap_exit(struct regmap *map);
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index d09a9c7a..dfdaede9 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -569,7 +569,7 @@ static inline struct rproc *vdev_to_rproc(struct virtio_device *vdev)
void rproc_add_subdev(struct rproc *rproc,
struct rproc_subdev *subdev,
int (*probe)(struct rproc_subdev *subdev),
- void (*remove)(struct rproc_subdev *subdev, bool graceful));
+ void (*remove)(struct rproc_subdev *subdev, bool crashed));
void rproc_remove_subdev(struct rproc *rproc, struct rproc_subdev *subdev);
diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h
index bcfdb91..5d83d0c 100644
--- a/include/linux/restart_block.h
+++ b/include/linux/restart_block.h
@@ -7,6 +7,7 @@
#include <linux/compiler.h>
#include <linux/types.h>
+#include <linux/time64.h>
struct timespec;
struct compat_timespec;
@@ -15,9 +16,7 @@ struct pollfd;
enum timespec_type {
TT_NONE = 0,
TT_NATIVE = 1,
-#ifdef CONFIG_COMPAT
TT_COMPAT = 2,
-#endif
};
/*
@@ -40,10 +39,8 @@ struct restart_block {
clockid_t clockid;
enum timespec_type type;
union {
- struct timespec __user *rmtp;
-#ifdef CONFIG_COMPAT
+ struct __kernel_timespec __user *rmtp;
struct compat_timespec __user *compat_rmtp;
-#endif
};
u64 expires;
} nanosleep;
diff --git a/include/linux/rslib.h b/include/linux/rslib.h
index 746580c1..5974ced 100644
--- a/include/linux/rslib.h
+++ b/include/linux/rslib.h
@@ -1,28 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * include/linux/rslib.h
- *
- * Overview:
- * Generic Reed Solomon encoder / decoder library
+ * Generic Reed Solomon encoder / decoder library
*
* Copyright (C) 2004 Thomas Gleixner (tglx@linutronix.de)
*
* RS code lifted from reed solomon library written by Phil Karn
* Copyright 2002 Phil Karn, KA9Q
- *
- * $Id: rslib.h,v 1.4 2005/11/07 11:14:52 gleixner Exp $
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
-
#ifndef _RSLIB_H_
#define _RSLIB_H_
#include <linux/list.h>
+#include <linux/types.h> /* for gfp_t */
+#include <linux/gfp.h> /* for GFP_KERNEL */
/**
- * struct rs_control - rs control structure
+ * struct rs_codec - rs codec data
*
* @mm: Bits per symbol
* @nn: Symbols per block (= (1<<mm)-1)
@@ -36,24 +29,34 @@
* @gfpoly: The primitive generator polynominal
* @gffunc: Function to generate the field, if non-canonical representation
* @users: Users of this structure
- * @list: List entry for the rs control list
+ * @list: List entry for the rs codec list
*/
-struct rs_control {
- int mm;
- int nn;
+struct rs_codec {
+ int mm;
+ int nn;
uint16_t *alpha_to;
uint16_t *index_of;
uint16_t *genpoly;
- int nroots;
- int fcr;
- int prim;
- int iprim;
+ int nroots;
+ int fcr;
+ int prim;
+ int iprim;
int gfpoly;
int (*gffunc)(int);
int users;
struct list_head list;
};
+/**
+ * struct rs_control - rs control structure per instance
+ * @codec: The codec used for this instance
+ * @buffers: Internal scratch buffers used in calls to decode_rs()
+ */
+struct rs_control {
+ struct rs_codec *codec;
+ uint16_t buffers[0];
+};
+
/* General purpose RS codec, 8-bit data width, symbol width 1-15 bit */
#ifdef CONFIG_REED_SOLOMON_ENC8
int encode_rs8(struct rs_control *rs, uint8_t *data, int len, uint16_t *par,
@@ -76,18 +79,37 @@ int decode_rs16(struct rs_control *rs, uint16_t *data, uint16_t *par, int len,
uint16_t *corr);
#endif
-/* Create or get a matching rs control structure */
-struct rs_control *init_rs(int symsize, int gfpoly, int fcr, int prim,
- int nroots);
+struct rs_control *init_rs_gfp(int symsize, int gfpoly, int fcr, int prim,
+ int nroots, gfp_t gfp);
+
+/**
+ * init_rs - Create a RS control struct and initialize it
+ * @symsize: the symbol size (number of bits)
+ * @gfpoly: the extended Galois field generator polynomial coefficients,
+ * with the 0th coefficient in the low order bit. The polynomial
+ * must be primitive;
+ * @fcr: the first consecutive root of the rs code generator polynomial
+ * in index form
+ * @prim: primitive element to generate polynomial roots
+ * @nroots: RS code generator polynomial degree (number of roots)
+ *
+ * Allocations use GFP_KERNEL.
+ */
+static inline struct rs_control *init_rs(int symsize, int gfpoly, int fcr,
+ int prim, int nroots)
+{
+ return init_rs_gfp(symsize, gfpoly, fcr, prim, nroots, GFP_KERNEL);
+}
+
struct rs_control *init_rs_non_canonical(int symsize, int (*func)(int),
- int fcr, int prim, int nroots);
+ int fcr, int prim, int nroots);
/* Release a rs control structure */
void free_rs(struct rs_control *rs);
/** modulo replacement for galois field arithmetics
*
- * @rs: the rs control structure
+ * @rs: Pointer to the RS codec
* @x: the value to reduce
*
* where
@@ -97,7 +119,7 @@ void free_rs(struct rs_control *rs);
* Simple arithmetic modulo would return a wrong result for values
* >= 3 * rs->nn
*/
-static inline int rs_modnn(struct rs_control *rs, int x)
+static inline int rs_modnn(struct rs_codec *rs, int x)
{
while (x >= rs->nn) {
x -= rs->nn;
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 56707d5..ab93b6e 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -44,6 +44,12 @@ struct rw_semaphore {
#endif
};
+/*
+ * Setting bit 0 of the owner field with other non-zero bits will indicate
+ * that the rwsem is writer-owned with an unknown owner.
+ */
+#define RWSEM_OWNER_UNKNOWN ((struct task_struct *)-1L)
+
extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem);
extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index 841585f..e653953 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -127,6 +127,12 @@ struct sbitmap_queue {
* @round_robin: Allocate bits in strict round-robin order.
*/
bool round_robin;
+
+ /**
+ * @min_shallow_depth: The minimum shallow depth which may be passed to
+ * sbitmap_queue_get_shallow() or __sbitmap_queue_get_shallow().
+ */
+ unsigned int min_shallow_depth;
};
/**
@@ -390,6 +396,9 @@ int __sbitmap_queue_get(struct sbitmap_queue *sbq);
* @shallow_depth: The maximum number of bits to allocate from a single word.
* See sbitmap_get_shallow().
*
+ * If you call this, make sure to call sbitmap_queue_min_shallow_depth() after
+ * initializing @sbq.
+ *
* Return: Non-negative allocated bit number if successful, -1 otherwise.
*/
int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
@@ -424,6 +433,9 @@ static inline int sbitmap_queue_get(struct sbitmap_queue *sbq,
* @shallow_depth: The maximum number of bits to allocate from a single word.
* See sbitmap_get_shallow().
*
+ * If you call this, make sure to call sbitmap_queue_min_shallow_depth() after
+ * initializing @sbq.
+ *
* Return: Non-negative allocated bit number if successful, -1 otherwise.
*/
static inline int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
@@ -439,6 +451,23 @@ static inline int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
}
/**
+ * sbitmap_queue_min_shallow_depth() - Inform a &struct sbitmap_queue of the
+ * minimum shallow depth that will be used.
+ * @sbq: Bitmap queue in question.
+ * @min_shallow_depth: The minimum shallow depth that will be passed to
+ * sbitmap_queue_get_shallow() or __sbitmap_queue_get_shallow().
+ *
+ * sbitmap_queue_clear() batches wakeups as an optimization. The batch size
+ * depends on the depth of the bitmap. Since the shallow allocation functions
+ * effectively operate with a different depth, the shallow depth must be taken
+ * into account when calculating the batch size. This function must be called
+ * with the minimum shallow depth that will be used. Failure to do so can result
+ * in missed wakeups.
+ */
+void sbitmap_queue_min_shallow_depth(struct sbitmap_queue *sbq,
+ unsigned int min_shallow_depth);
+
+/**
* sbitmap_queue_clear() - Free an allocated bit and wake up waiters on a
* &struct sbitmap_queue.
* @sbq: Bitmap to free from.
@@ -484,6 +513,13 @@ static inline struct sbq_wait_state *sbq_wait_ptr(struct sbitmap_queue *sbq,
void sbitmap_queue_wake_all(struct sbitmap_queue *sbq);
/**
+ * sbitmap_queue_wake_up() - Wake up some of waiters in one waitqueue
+ * on a &struct sbitmap_queue.
+ * @sbq: Bitmap queue to wake up.
+ */
+void sbitmap_queue_wake_up(struct sbitmap_queue *sbq);
+
+/**
* sbitmap_queue_show() - Dump &struct sbitmap_queue information to a &struct
* seq_file.
* @sbq: Bitmap queue to show.
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b3d697f..14e4f9c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -112,17 +112,36 @@ struct task_group;
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+/*
+ * Special states are those that do not use the normal wait-loop pattern. See
+ * the comment with set_special_state().
+ */
+#define is_special_task_state(state) \
+ ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_DEAD))
+
#define __set_current_state(state_value) \
do { \
+ WARN_ON_ONCE(is_special_task_state(state_value));\
current->task_state_change = _THIS_IP_; \
current->state = (state_value); \
} while (0)
+
#define set_current_state(state_value) \
do { \
+ WARN_ON_ONCE(is_special_task_state(state_value));\
current->task_state_change = _THIS_IP_; \
smp_store_mb(current->state, (state_value)); \
} while (0)
+#define set_special_state(state_value) \
+ do { \
+ unsigned long flags; /* may shadow */ \
+ WARN_ON_ONCE(!is_special_task_state(state_value)); \
+ raw_spin_lock_irqsave(¤t->pi_lock, flags); \
+ current->task_state_change = _THIS_IP_; \
+ current->state = (state_value); \
+ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \
+ } while (0)
#else
/*
* set_current_state() includes a barrier so that the write of current->state
@@ -144,8 +163,8 @@ struct task_group;
*
* The above is typically ordered against the wakeup, which does:
*
- * need_sleep = false;
- * wake_up_state(p, TASK_UNINTERRUPTIBLE);
+ * need_sleep = false;
+ * wake_up_state(p, TASK_UNINTERRUPTIBLE);
*
* Where wake_up_state() (and all other wakeup primitives) imply enough
* barriers to order the store of the variable against wakeup.
@@ -154,12 +173,33 @@ struct task_group;
* once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
* TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING).
*
- * This is obviously fine, since they both store the exact same value.
+ * However, with slightly different timing the wakeup TASK_RUNNING store can
+ * also collide with the TASK_UNINTERRUPTIBLE store. Loosing that store is not
+ * a problem either because that will result in one extra go around the loop
+ * and our @cond test will save the day.
*
* Also see the comments of try_to_wake_up().
*/
-#define __set_current_state(state_value) do { current->state = (state_value); } while (0)
-#define set_current_state(state_value) smp_store_mb(current->state, (state_value))
+#define __set_current_state(state_value) \
+ current->state = (state_value)
+
+#define set_current_state(state_value) \
+ smp_store_mb(current->state, (state_value))
+
+/*
+ * set_special_state() should be used for those states when the blocking task
+ * can not use the regular condition based wait-loop. In that case we must
+ * serialize against wakeups such that any possible in-flight TASK_RUNNING stores
+ * will not collide with our state change.
+ */
+#define set_special_state(state_value) \
+ do { \
+ unsigned long flags; /* may shadow */ \
+ raw_spin_lock_irqsave(¤t->pi_lock, flags); \
+ current->state = (state_value); \
+ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \
+ } while (0)
+
#endif
/* Task command name length: */
@@ -1393,7 +1433,8 @@ static inline bool is_percpu_thread(void)
#define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */
#define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */
#define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */
-
+#define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */
+#define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/
#define TASK_PFA_TEST(name, func) \
static inline bool task_##func(struct task_struct *p) \
@@ -1418,6 +1459,13 @@ TASK_PFA_TEST(SPREAD_SLAB, spread_slab)
TASK_PFA_SET(SPREAD_SLAB, spread_slab)
TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab)
+TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable)
+TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable)
+TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable)
+
+TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)
+TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)
+
static inline void
current_restore_flags(unsigned long orig_flags, unsigned long flags)
{
@@ -1464,6 +1512,7 @@ static inline int task_nice(const struct task_struct *p)
extern int can_nice(const struct task_struct *p, const int nice);
extern int task_curr(const struct task_struct *p);
extern int idle_cpu(int cpu);
+extern int available_idle_cpu(int cpu);
extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *);
extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *);
extern int sched_setattr(struct task_struct *, const struct sched_attr *);
@@ -1613,7 +1662,6 @@ static inline int test_tsk_need_resched(struct task_struct *tsk)
* explicit rescheduling in places that are safe. The return
* value indicates whether a reschedule was done in fact.
* cond_resched_lock() will drop the spinlock before scheduling,
- * cond_resched_softirq() will enable bhs before scheduling.
*/
#ifndef CONFIG_PREEMPT
extern int _cond_resched(void);
@@ -1633,13 +1681,6 @@ extern int __cond_resched_lock(spinlock_t *lock);
__cond_resched_lock(lock); \
})
-extern int __cond_resched_softirq(void);
-
-#define cond_resched_softirq() ({ \
- ___might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \
- __cond_resched_softirq(); \
-})
-
static inline void cond_resched_rcu(void)
{
#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU)
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 2c570cd9..76a8cb4 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -28,7 +28,7 @@ extern struct mm_struct *mm_alloc(void);
*
* Use mmdrop() to release the reference acquired by mmgrab().
*
- * See also <Documentation/vm/active_mm.txt> for an in-depth explanation
+ * See also <Documentation/vm/active_mm.rst> for an in-depth explanation
* of &mm_struct.mm_count vs &mm_struct.mm_users.
*/
static inline void mmgrab(struct mm_struct *mm)
@@ -62,7 +62,7 @@ static inline void mmdrop(struct mm_struct *mm)
*
* Use mmput() to release the reference acquired by mmget().
*
- * See also <Documentation/vm/active_mm.txt> for an in-depth explanation
+ * See also <Documentation/vm/active_mm.rst> for an in-depth explanation
* of &mm_struct.mm_count vs &mm_struct.mm_users.
*/
static inline void mmget(struct mm_struct *mm)
@@ -170,6 +170,17 @@ static inline void fs_reclaim_acquire(gfp_t gfp_mask) { }
static inline void fs_reclaim_release(gfp_t gfp_mask) { }
#endif
+/**
+ * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope.
+ *
+ * This functions marks the beginning of the GFP_NOIO allocation scope.
+ * All further allocations will implicitly drop __GFP_IO flag and so
+ * they are safe for the IO critical section from the allocation recursion
+ * point of view. Use memalloc_noio_restore to end the scope with flags
+ * returned by this function.
+ *
+ * This function is safe to be used from any context.
+ */
static inline unsigned int memalloc_noio_save(void)
{
unsigned int flags = current->flags & PF_MEMALLOC_NOIO;
@@ -177,11 +188,30 @@ static inline unsigned int memalloc_noio_save(void)
return flags;
}
+/**
+ * memalloc_noio_restore - Ends the implicit GFP_NOIO scope.
+ * @flags: Flags to restore.
+ *
+ * Ends the implicit GFP_NOIO scope started by memalloc_noio_save function.
+ * Always make sure that that the given flags is the return value from the
+ * pairing memalloc_noio_save call.
+ */
static inline void memalloc_noio_restore(unsigned int flags)
{
current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
}
+/**
+ * memalloc_nofs_save - Marks implicit GFP_NOFS allocation scope.
+ *
+ * This functions marks the beginning of the GFP_NOFS allocation scope.
+ * All further allocations will implicitly drop __GFP_FS flag and so
+ * they are safe for the FS critical section from the allocation recursion
+ * point of view. Use memalloc_nofs_restore to end the scope with flags
+ * returned by this function.
+ *
+ * This function is safe to be used from any context.
+ */
static inline unsigned int memalloc_nofs_save(void)
{
unsigned int flags = current->flags & PF_MEMALLOC_NOFS;
@@ -189,6 +219,14 @@ static inline unsigned int memalloc_nofs_save(void)
return flags;
}
+/**
+ * memalloc_nofs_restore - Ends the implicit GFP_NOFS scope.
+ * @flags: Flags to restore.
+ *
+ * Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function.
+ * Always make sure that that the given flags is the return value from the
+ * pairing memalloc_nofs_save call.
+ */
static inline void memalloc_nofs_restore(unsigned int flags)
{
current->flags = (current->flags & ~PF_MEMALLOC_NOFS) | flags;
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index a7ce74c..113d1ad 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -280,7 +280,7 @@ static inline void kernel_signal_stop(void)
{
spin_lock_irq(¤t->sighand->siglock);
if (current->jobctl & JOBCTL_STOP_DEQUEUED)
- __set_current_state(TASK_STOPPED);
+ set_special_state(TASK_STOPPED);
spin_unlock_irq(¤t->sighand->siglock);
schedule();
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index c723a5c..e5320f6 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -4,8 +4,9 @@
#include <uapi/linux/seccomp.h>
-#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \
- SECCOMP_FILTER_FLAG_LOG)
+#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \
+ SECCOMP_FILTER_FLAG_LOG | \
+ SECCOMP_FILTER_FLAG_SPEC_ALLOW)
#ifdef CONFIG_SECCOMP
diff --git a/include/linux/seq_file_net.h b/include/linux/seq_file_net.h
index 43ccd84..0fdbe1d 100644
--- a/include/linux/seq_file_net.h
+++ b/include/linux/seq_file_net.h
@@ -13,12 +13,6 @@ struct seq_net_private {
#endif
};
-int seq_open_net(struct inode *, struct file *,
- const struct seq_operations *, int);
-int single_open_net(struct inode *, struct file *file,
- int (*show)(struct seq_file *, void *));
-int seq_release_net(struct inode *, struct file *);
-int single_release_net(struct inode *, struct file *);
static inline struct net *seq_file_net(struct seq_file *seq)
{
#ifdef CONFIG_NET_NS
@@ -28,4 +22,17 @@ static inline struct net *seq_file_net(struct seq_file *seq)
#endif
}
+/*
+ * This one is needed for proc_create_net_single since net is stored directly
+ * in private not as a struct i.e. seq_file_net can't be used.
+ */
+static inline struct net *seq_file_single_net(struct seq_file *seq)
+{
+#ifdef CONFIG_NET_NS
+ return (struct net *)seq->private;
+#else
+ return &init_net;
+#endif
+}
+
#endif
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 1d35610..b4c9fda 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -351,10 +351,10 @@ struct earlycon_id {
char name[16];
char compatible[128];
int (*setup)(struct earlycon_device *, const char *options);
-} __aligned(32);
+};
-extern const struct earlycon_id __earlycon_table[];
-extern const struct earlycon_id __earlycon_table_end[];
+extern const struct earlycon_id *__earlycon_table[];
+extern const struct earlycon_id *__earlycon_table_end[];
#if defined(CONFIG_SERIAL_EARLYCON) && !defined(MODULE)
#define EARLYCON_USED_OR_UNUSED __used
@@ -362,12 +362,19 @@ extern const struct earlycon_id __earlycon_table_end[];
#define EARLYCON_USED_OR_UNUSED __maybe_unused
#endif
-#define OF_EARLYCON_DECLARE(_name, compat, fn) \
- static const struct earlycon_id __UNIQUE_ID(__earlycon_##_name) \
- EARLYCON_USED_OR_UNUSED __section(__earlycon_table) \
+#define _OF_EARLYCON_DECLARE(_name, compat, fn, unique_id) \
+ static const struct earlycon_id unique_id \
+ EARLYCON_USED_OR_UNUSED __initconst \
= { .name = __stringify(_name), \
.compatible = compat, \
- .setup = fn }
+ .setup = fn }; \
+ static const struct earlycon_id EARLYCON_USED_OR_UNUSED \
+ __section(__earlycon_table) \
+ * const __PASTE(__p, unique_id) = &unique_id
+
+#define OF_EARLYCON_DECLARE(_name, compat, fn) \
+ _OF_EARLYCON_DECLARE(_name, compat, fn, \
+ __UNIQUE_ID(__earlycon_##_name))
#define EARLYCON_DECLARE(_name, fn) OF_EARLYCON_DECLARE(_name, "", fn)
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index 388ff29..6794490 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -75,6 +75,9 @@ struct shrinker {
#define SHRINKER_NUMA_AWARE (1 << 0)
#define SHRINKER_MEMCG_AWARE (1 << 1)
-extern int register_shrinker(struct shrinker *);
-extern void unregister_shrinker(struct shrinker *);
+extern int prealloc_shrinker(struct shrinker *shrinker);
+extern void register_shrinker_prepared(struct shrinker *shrinker);
+extern int register_shrinker(struct shrinker *shrinker);
+extern void unregister_shrinker(struct shrinker *shrinker);
+extern void free_prealloced_shrinker(struct shrinker *shrinker);
#endif
diff --git a/include/linux/signal.h b/include/linux/signal.h
index a9bc7e1..3c52001 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -28,6 +28,9 @@ enum siginfo_layout {
SIL_TIMER,
SIL_POLL,
SIL_FAULT,
+ SIL_FAULT_MCEERR,
+ SIL_FAULT_BNDERR,
+ SIL_FAULT_PKUERR,
SIL_CHLD,
SIL_RT,
SIL_SYS,
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9065477..8919837 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3250,8 +3250,7 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
int *peeked, int *off, int *err);
struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock,
int *err);
-__poll_t datagram_poll(struct file *file, struct socket *sock,
- struct poll_table_struct *wait);
+__poll_t datagram_poll_mask(struct socket *sock, __poll_t events);
int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
struct iov_iter *to, int size);
static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset,
diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h
new file mode 100644
index 0000000..bb4bd15
--- /dev/null
+++ b/include/linux/spi/spi-mem.h
@@ -0,0 +1,249 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (C) 2018 Exceet Electronics GmbH
+ * Copyright (C) 2018 Bootlin
+ *
+ * Author: Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#ifndef __LINUX_SPI_MEM_H
+#define __LINUX_SPI_MEM_H
+
+#include <linux/spi/spi.h>
+
+#define SPI_MEM_OP_CMD(__opcode, __buswidth) \
+ { \
+ .buswidth = __buswidth, \
+ .opcode = __opcode, \
+ }
+
+#define SPI_MEM_OP_ADDR(__nbytes, __val, __buswidth) \
+ { \
+ .nbytes = __nbytes, \
+ .val = __val, \
+ .buswidth = __buswidth, \
+ }
+
+#define SPI_MEM_OP_NO_ADDR { }
+
+#define SPI_MEM_OP_DUMMY(__nbytes, __buswidth) \
+ { \
+ .nbytes = __nbytes, \
+ .buswidth = __buswidth, \
+ }
+
+#define SPI_MEM_OP_NO_DUMMY { }
+
+#define SPI_MEM_OP_DATA_IN(__nbytes, __buf, __buswidth) \
+ { \
+ .dir = SPI_MEM_DATA_IN, \
+ .nbytes = __nbytes, \
+ .buf.in = __buf, \
+ .buswidth = __buswidth, \
+ }
+
+#define SPI_MEM_OP_DATA_OUT(__nbytes, __buf, __buswidth) \
+ { \
+ .dir = SPI_MEM_DATA_OUT, \
+ .nbytes = __nbytes, \
+ .buf.out = __buf, \
+ .buswidth = __buswidth, \
+ }
+
+#define SPI_MEM_OP_NO_DATA { }
+
+/**
+ * enum spi_mem_data_dir - describes the direction of a SPI memory data
+ * transfer from the controller perspective
+ * @SPI_MEM_DATA_IN: data coming from the SPI memory
+ * @SPI_MEM_DATA_OUT: data sent the SPI memory
+ */
+enum spi_mem_data_dir {
+ SPI_MEM_DATA_IN,
+ SPI_MEM_DATA_OUT,
+};
+
+/**
+ * struct spi_mem_op - describes a SPI memory operation
+ * @cmd.buswidth: number of IO lines used to transmit the command
+ * @cmd.opcode: operation opcode
+ * @addr.nbytes: number of address bytes to send. Can be zero if the operation
+ * does not need to send an address
+ * @addr.buswidth: number of IO lines used to transmit the address cycles
+ * @addr.val: address value. This value is always sent MSB first on the bus.
+ * Note that only @addr.nbytes are taken into account in this
+ * address value, so users should make sure the value fits in the
+ * assigned number of bytes.
+ * @dummy.nbytes: number of dummy bytes to send after an opcode or address. Can
+ * be zero if the operation does not require dummy bytes
+ * @dummy.buswidth: number of IO lanes used to transmit the dummy bytes
+ * @data.buswidth: number of IO lanes used to send/receive the data
+ * @data.dir: direction of the transfer
+ * @data.buf.in: input buffer
+ * @data.buf.out: output buffer
+ */
+struct spi_mem_op {
+ struct {
+ u8 buswidth;
+ u8 opcode;
+ } cmd;
+
+ struct {
+ u8 nbytes;
+ u8 buswidth;
+ u64 val;
+ } addr;
+
+ struct {
+ u8 nbytes;
+ u8 buswidth;
+ } dummy;
+
+ struct {
+ u8 buswidth;
+ enum spi_mem_data_dir dir;
+ unsigned int nbytes;
+ /* buf.{in,out} must be DMA-able. */
+ union {
+ void *in;
+ const void *out;
+ } buf;
+ } data;
+};
+
+#define SPI_MEM_OP(__cmd, __addr, __dummy, __data) \
+ { \
+ .cmd = __cmd, \
+ .addr = __addr, \
+ .dummy = __dummy, \
+ .data = __data, \
+ }
+
+/**
+ * struct spi_mem - describes a SPI memory device
+ * @spi: the underlying SPI device
+ * @drvpriv: spi_mem_drviver private data
+ *
+ * Extra information that describe the SPI memory device and may be needed by
+ * the controller to properly handle this device should be placed here.
+ *
+ * One example would be the device size since some controller expose their SPI
+ * mem devices through a io-mapped region.
+ */
+struct spi_mem {
+ struct spi_device *spi;
+ void *drvpriv;
+};
+
+/**
+ * struct spi_mem_set_drvdata() - attach driver private data to a SPI mem
+ * device
+ * @mem: memory device
+ * @data: data to attach to the memory device
+ */
+static inline void spi_mem_set_drvdata(struct spi_mem *mem, void *data)
+{
+ mem->drvpriv = data;
+}
+
+/**
+ * struct spi_mem_get_drvdata() - get driver private data attached to a SPI mem
+ * device
+ * @mem: memory device
+ *
+ * Return: the data attached to the mem device.
+ */
+static inline void *spi_mem_get_drvdata(struct spi_mem *mem)
+{
+ return mem->drvpriv;
+}
+
+/**
+ * struct spi_controller_mem_ops - SPI memory operations
+ * @adjust_op_size: shrink the data xfer of an operation to match controller's
+ * limitations (can be alignment of max RX/TX size
+ * limitations)
+ * @supports_op: check if an operation is supported by the controller
+ * @exec_op: execute a SPI memory operation
+ *
+ * This interface should be implemented by SPI controllers providing an
+ * high-level interface to execute SPI memory operation, which is usually the
+ * case for QSPI controllers.
+ */
+struct spi_controller_mem_ops {
+ int (*adjust_op_size)(struct spi_mem *mem, struct spi_mem_op *op);
+ bool (*supports_op)(struct spi_mem *mem,
+ const struct spi_mem_op *op);
+ int (*exec_op)(struct spi_mem *mem,
+ const struct spi_mem_op *op);
+};
+
+/**
+ * struct spi_mem_driver - SPI memory driver
+ * @spidrv: inherit from a SPI driver
+ * @probe: probe a SPI memory. Usually where detection/initialization takes
+ * place
+ * @remove: remove a SPI memory
+ * @shutdown: take appropriate action when the system is shutdown
+ *
+ * This is just a thin wrapper around a spi_driver. The core takes care of
+ * allocating the spi_mem object and forwarding the probe/remove/shutdown
+ * request to the spi_mem_driver. The reason we use this wrapper is because
+ * we might have to stuff more information into the spi_mem struct to let
+ * SPI controllers know more about the SPI memory they interact with, and
+ * having this intermediate layer allows us to do that without adding more
+ * useless fields to the spi_device object.
+ */
+struct spi_mem_driver {
+ struct spi_driver spidrv;
+ int (*probe)(struct spi_mem *mem);
+ int (*remove)(struct spi_mem *mem);
+ void (*shutdown)(struct spi_mem *mem);
+};
+
+#if IS_ENABLED(CONFIG_SPI_MEM)
+int spi_controller_dma_map_mem_op_data(struct spi_controller *ctlr,
+ const struct spi_mem_op *op,
+ struct sg_table *sg);
+
+void spi_controller_dma_unmap_mem_op_data(struct spi_controller *ctlr,
+ const struct spi_mem_op *op,
+ struct sg_table *sg);
+#else
+static inline int
+spi_controller_dma_map_mem_op_data(struct spi_controller *ctlr,
+ const struct spi_mem_op *op,
+ struct sg_table *sg)
+{
+ return -ENOTSUPP;
+}
+
+static inline void
+spi_controller_dma_unmap_mem_op_data(struct spi_controller *ctlr,
+ const struct spi_mem_op *op,
+ struct sg_table *sg)
+{
+}
+#endif /* CONFIG_SPI_MEM */
+
+int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op);
+
+bool spi_mem_supports_op(struct spi_mem *mem,
+ const struct spi_mem_op *op);
+
+int spi_mem_exec_op(struct spi_mem *mem,
+ const struct spi_mem_op *op);
+
+int spi_mem_driver_register_with_owner(struct spi_mem_driver *drv,
+ struct module *owner);
+
+void spi_mem_driver_unregister(struct spi_mem_driver *drv);
+
+#define spi_mem_driver_register(__drv) \
+ spi_mem_driver_register_with_owner(__drv, THIS_MODULE)
+
+#define module_spi_mem_driver(__drv) \
+ module_driver(__drv, spi_mem_driver_register, \
+ spi_mem_driver_unregister)
+
+#endif /* __LINUX_SPI_MEM_H */
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index bc6bb32..a64235e 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -26,7 +26,7 @@ struct dma_chan;
struct property_entry;
struct spi_controller;
struct spi_transfer;
-struct spi_flash_read_message;
+struct spi_controller_mem_ops;
/*
* INTERFACES between SPI master-side drivers and SPI slave protocol handlers,
@@ -376,13 +376,11 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
* transfer_one callback.
* @handle_err: the subsystem calls the driver to handle an error that occurs
* in the generic implementation of transfer_one_message().
+ * @mem_ops: optimized/dedicated operations for interactions with SPI memory.
+ * This field is optional and should only be implemented if the
+ * controller has native support for memory like operations.
* @unprepare_message: undo any work done by prepare_message().
* @slave_abort: abort the ongoing transfer request on an SPI slave controller
- * @spi_flash_read: to support spi-controller hardwares that provide
- * accelerated interface to read from flash devices.
- * @spi_flash_can_dma: analogous to can_dma() interface, but for
- * controllers implementing spi_flash_read.
- * @flash_read_supported: spi device supports flash read
* @cs_gpios: Array of GPIOs to use as chip select lines; one per CS
* number. Any individual value may be -ENOENT for CS lines that
* are not GPIOs (driven by the SPI controller itself).
@@ -548,11 +546,6 @@ struct spi_controller {
int (*unprepare_message)(struct spi_controller *ctlr,
struct spi_message *message);
int (*slave_abort)(struct spi_controller *ctlr);
- int (*spi_flash_read)(struct spi_device *spi,
- struct spi_flash_read_message *msg);
- bool (*spi_flash_can_dma)(struct spi_device *spi,
- struct spi_flash_read_message *msg);
- bool (*flash_read_supported)(struct spi_device *spi);
/*
* These hooks are for drivers that use a generic implementation
@@ -564,6 +557,9 @@ struct spi_controller {
void (*handle_err)(struct spi_controller *ctlr,
struct spi_message *message);
+ /* Optimized handlers for SPI memory-like operations. */
+ const struct spi_controller_mem_ops *mem_ops;
+
/* gpio chip select */
int *cs_gpios;
@@ -1183,48 +1179,6 @@ static inline ssize_t spi_w8r16be(struct spi_device *spi, u8 cmd)
return be16_to_cpu(result);
}
-/**
- * struct spi_flash_read_message - flash specific information for
- * spi-masters that provide accelerated flash read interfaces
- * @buf: buffer to read data
- * @from: offset within the flash from where data is to be read
- * @len: length of data to be read
- * @retlen: actual length of data read
- * @read_opcode: read_opcode to be used to communicate with flash
- * @addr_width: number of address bytes
- * @dummy_bytes: number of dummy bytes
- * @opcode_nbits: number of lines to send opcode
- * @addr_nbits: number of lines to send address
- * @data_nbits: number of lines for data
- * @rx_sg: Scatterlist for receive data read from flash
- * @cur_msg_mapped: message has been mapped for DMA
- */
-struct spi_flash_read_message {
- void *buf;
- loff_t from;
- size_t len;
- size_t retlen;
- u8 read_opcode;
- u8 addr_width;
- u8 dummy_bytes;
- u8 opcode_nbits;
- u8 addr_nbits;
- u8 data_nbits;
- struct sg_table rx_sg;
- bool cur_msg_mapped;
-};
-
-/* SPI core interface for flash read support */
-static inline bool spi_flash_read_supported(struct spi_device *spi)
-{
- return spi->controller->spi_flash_read &&
- (!spi->controller->flash_read_supported ||
- spi->controller->flash_read_supported(spi));
-}
-
-int spi_flash_read(struct spi_device *spi,
- struct spi_flash_read_message *msg);
-
/*---------------------------------------------------------------------------*/
/*
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 4894d32..1e8a464 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -380,6 +380,24 @@ static __always_inline int spin_trylock_irq(spinlock_t *lock)
raw_spin_trylock_irqsave(spinlock_check(lock), flags); \
})
+/**
+ * spin_is_locked() - Check whether a spinlock is locked.
+ * @lock: Pointer to the spinlock.
+ *
+ * This function is NOT required to provide any memory ordering
+ * guarantees; it could be used for debugging purposes or, when
+ * additional synchronization is needed, accompanied with other
+ * constructs (memory barriers) enforcing the synchronization.
+ *
+ * Returns: 1 if @lock is locked, 0 otherwise.
+ *
+ * Note that the function only tells you that the spinlock is
+ * seen to be locked, not that it is locked on your CPU.
+ *
+ * Further, on CONFIG_SMP=n builds with CONFIG_DEBUG_SPINLOCK=n,
+ * the return value is always 0 (see include/linux/spinlock_up.h).
+ * Therefore you should not rely heavily on the return value.
+ */
static __always_inline int spin_is_locked(spinlock_t *lock)
{
return raw_spin_is_locked(&lock->rlock);
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 33c1c69..91494d7 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -69,11 +69,45 @@ struct srcu_struct { };
void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
void (*func)(struct rcu_head *head));
-void cleanup_srcu_struct(struct srcu_struct *sp);
+void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced);
int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp);
void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp);
void synchronize_srcu(struct srcu_struct *sp);
+/**
+ * cleanup_srcu_struct - deconstruct a sleep-RCU structure
+ * @sp: structure to clean up.
+ *
+ * Must invoke this after you are finished using a given srcu_struct that
+ * was initialized via init_srcu_struct(), else you leak memory.
+ */
+static inline void cleanup_srcu_struct(struct srcu_struct *sp)
+{
+ _cleanup_srcu_struct(sp, false);
+}
+
+/**
+ * cleanup_srcu_struct_quiesced - deconstruct a quiesced sleep-RCU structure
+ * @sp: structure to clean up.
+ *
+ * Must invoke this after you are finished using a given srcu_struct that
+ * was initialized via init_srcu_struct(), else you leak memory. Also,
+ * all grace-period processing must have completed.
+ *
+ * "Completed" means that the last synchronize_srcu() and
+ * synchronize_srcu_expedited() calls must have returned before the call
+ * to cleanup_srcu_struct_quiesced(). It also means that the callback
+ * from the last call_srcu() must have been invoked before the call to
+ * cleanup_srcu_struct_quiesced(), but you can use srcu_barrier() to help
+ * with this last. Violating these rules will get you a WARN_ON() splat
+ * (with high probability, anyway), and will also cause the srcu_struct
+ * to be leaked.
+ */
+static inline void cleanup_srcu_struct_quiesced(struct srcu_struct *sp)
+{
+ _cleanup_srcu_struct(sp, true);
+}
+
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/**
diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h
index 261471f..f41d2fb 100644
--- a/include/linux/srcutiny.h
+++ b/include/linux/srcutiny.h
@@ -43,7 +43,7 @@ struct srcu_struct {
void srcu_drive_gp(struct work_struct *wp);
-#define __SRCU_STRUCT_INIT(name) \
+#define __SRCU_STRUCT_INIT(name, __ignored) \
{ \
.srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq), \
.srcu_cb_tail = &name.srcu_cb_head, \
@@ -56,9 +56,9 @@ void srcu_drive_gp(struct work_struct *wp);
* Tree SRCU, which needs some per-CPU data.
*/
#define DEFINE_SRCU(name) \
- struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+ struct srcu_struct name = __SRCU_STRUCT_INIT(name, name)
#define DEFINE_STATIC_SRCU(name) \
- static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+ static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name)
void synchronize_srcu(struct srcu_struct *sp);
diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index 4eda108..745d4ca 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -104,9 +104,9 @@ struct srcu_struct {
#define SRCU_STATE_SCAN1 1
#define SRCU_STATE_SCAN2 2
-#define __SRCU_STRUCT_INIT(name) \
+#define __SRCU_STRUCT_INIT(name, pcpu_name) \
{ \
- .sda = &name##_srcu_data, \
+ .sda = &pcpu_name, \
.lock = __SPIN_LOCK_UNLOCKED(name.lock), \
.srcu_gp_seq_needed = 0 - 1, \
__SRCU_DEP_MAP_INIT(name) \
@@ -133,7 +133,7 @@ struct srcu_struct {
*/
#define __DEFINE_SRCU(name, is_static) \
static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data);\
- is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+ is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name##_srcu_data)
#define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */)
#define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static)
diff --git a/include/linux/string.h b/include/linux/string.h
index dd39a69..4a5a0eb 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -147,8 +147,8 @@ extern int memcmp(const void *,const void *,__kernel_size_t);
extern void * memchr(const void *,int,__kernel_size_t);
#endif
#ifndef __HAVE_ARCH_MEMCPY_MCSAFE
-static inline __must_check int memcpy_mcsafe(void *dst, const void *src,
- size_t cnt)
+static inline __must_check unsigned long memcpy_mcsafe(void *dst,
+ const void *src, size_t cnt)
{
memcpy(dst, src, cnt);
return 0;
diff --git a/include/linux/stringhash.h b/include/linux/stringhash.h
index e8f0f85..c0c5c5b 100644
--- a/include/linux/stringhash.h
+++ b/include/linux/stringhash.h
@@ -50,9 +50,9 @@ partial_name_hash(unsigned long c, unsigned long prevhash)
* losing bits). This also has the property (wanted by the dcache)
* that the msbits make a good hash table index.
*/
-static inline unsigned long end_name_hash(unsigned long hash)
+static inline unsigned int end_name_hash(unsigned long hash)
{
- return __hash_32((unsigned int)hash);
+ return hash_long(hash, 32);
}
/*
diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h
index a5704da..e90b9bd 100644
--- a/include/linux/sunrpc/rpc_pipe_fs.h
+++ b/include/linux/sunrpc/rpc_pipe_fs.h
@@ -122,8 +122,6 @@ extern struct dentry *rpc_create_cache_dir(struct dentry *,
struct cache_detail *);
extern void rpc_remove_cache_dir(struct dentry *);
-extern int rpc_rmdir(struct dentry *dentry);
-
struct rpc_pipe *rpc_mkpipe_data(const struct rpc_pipe_ops *ops, int flags);
void rpc_destroy_pipe_data(struct rpc_pipe *pipe);
extern struct dentry *rpc_mkpipe_dentry(struct dentry *, const char *, void *,
diff --git a/include/linux/swait.h b/include/linux/swait.h
index c98aaf6..bf8cb0d 100644
--- a/include/linux/swait.h
+++ b/include/linux/swait.h
@@ -5,10 +5,23 @@
#include <linux/list.h>
#include <linux/stddef.h>
#include <linux/spinlock.h>
+#include <linux/wait.h>
#include <asm/current.h>
/*
- * Simple wait queues
+ * BROKEN wait-queues.
+ *
+ * These "simple" wait-queues are broken garbage, and should never be
+ * used. The comments below claim that they are "similar" to regular
+ * wait-queues, but the semantics are actually completely different, and
+ * every single user we have ever had has been buggy (or pointless).
+ *
+ * A "swake_up()" only wakes up _one_ waiter, which is not at all what
+ * "wake_up()" does, and has led to problems. In other cases, it has
+ * been fine, because there's only ever one waiter (kvm), but in that
+ * case gthe whole "simple" wait-queue is just pointless to begin with,
+ * since there is no "queue". Use "wake_up_process()" with a direct
+ * pointer instead.
*
* While these are very similar to regular wait queues (wait.h) the most
* important difference is that the simple waitqueue allows for deterministic
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 2417d28..c063443 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -53,7 +53,7 @@ static inline int current_is_kswapd(void)
/*
* Unaddressable device memory support. See include/linux/hmm.h and
- * Documentation/vm/hmm.txt. Short description is we need struct pages for
+ * Documentation/vm/hmm.rst. Short description is we need struct pages for
* device memory that is unaddressable (inaccessible) by CPU, so that we can
* migrate part of a process memory to device memory.
*
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 70fcda1..390e814 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -290,6 +290,12 @@ asmlinkage long sys_io_getevents(aio_context_t ctx_id,
long nr,
struct io_event __user *events,
struct timespec __user *timeout);
+asmlinkage long sys_io_pgetevents(aio_context_t ctx_id,
+ long min_nr,
+ long nr,
+ struct io_event __user *events,
+ struct timespec __user *timeout,
+ const struct __aio_sigset *sig);
/* fs/xattr.c */
asmlinkage long sys_setxattr(const char __user *path, const char __user *name,
@@ -536,7 +542,8 @@ asmlinkage long sys_set_robust_list(struct robust_list_head __user *head,
size_t len);
/* kernel/hrtimer.c */
-asmlinkage long sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp);
+asmlinkage long sys_nanosleep(struct __kernel_timespec __user *rqtp,
+ struct __kernel_timespec __user *rmtp);
/* kernel/itimer.c */
asmlinkage long sys_getitimer(int which, struct itimerval __user *value);
@@ -567,14 +574,14 @@ asmlinkage long sys_timer_settime(timer_t timer_id, int flags,
struct itimerspec __user *old_setting);
asmlinkage long sys_timer_delete(timer_t timer_id);
asmlinkage long sys_clock_settime(clockid_t which_clock,
- const struct timespec __user *tp);
+ const struct __kernel_timespec __user *tp);
asmlinkage long sys_clock_gettime(clockid_t which_clock,
- struct timespec __user *tp);
+ struct __kernel_timespec __user *tp);
asmlinkage long sys_clock_getres(clockid_t which_clock,
- struct timespec __user *tp);
+ struct __kernel_timespec __user *tp);
asmlinkage long sys_clock_nanosleep(clockid_t which_clock, int flags,
- const struct timespec __user *rqtp,
- struct timespec __user *rmtp);
+ const struct __kernel_timespec __user *rqtp,
+ struct __kernel_timespec __user *rmtp);
/* kernel/printk.c */
asmlinkage long sys_syslog(int type, char __user *buf, int len);
@@ -679,8 +686,8 @@ asmlinkage long sys_sysinfo(struct sysinfo __user *info);
/* ipc/mqueue.c */
asmlinkage long sys_mq_open(const char __user *name, int oflag, umode_t mode, struct mq_attr __user *attr);
asmlinkage long sys_mq_unlink(const char __user *name);
-asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *msg_ptr, size_t msg_len, unsigned int msg_prio, const struct timespec __user *abs_timeout);
-asmlinkage long sys_mq_timedreceive(mqd_t mqdes, char __user *msg_ptr, size_t msg_len, unsigned int __user *msg_prio, const struct timespec __user *abs_timeout);
+asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *msg_ptr, size_t msg_len, unsigned int msg_prio, const struct __kernel_timespec __user *abs_timeout);
+asmlinkage long sys_mq_timedreceive(mqd_t mqdes, char __user *msg_ptr, size_t msg_len, unsigned int __user *msg_prio, const struct __kernel_timespec __user *abs_timeout);
asmlinkage long sys_mq_notify(mqd_t mqdes, const struct sigevent __user *notification);
asmlinkage long sys_mq_getsetattr(mqd_t mqdes, const struct mq_attr __user *mqstat, struct mq_attr __user *omqstat);
@@ -697,7 +704,7 @@ asmlinkage long sys_semget(key_t key, int nsems, int semflg);
asmlinkage long sys_semctl(int semid, int semnum, int cmd, unsigned long arg);
asmlinkage long sys_semtimedop(int semid, struct sembuf __user *sops,
unsigned nsops,
- const struct timespec __user *timeout);
+ const struct __kernel_timespec __user *timeout);
asmlinkage long sys_semop(int semid, struct sembuf __user *sops,
unsigned nsops);
diff --git a/include/linux/textsearch.h b/include/linux/textsearch.h
index 0494db3..13770cf 100644
--- a/include/linux/textsearch.h
+++ b/include/linux/textsearch.h
@@ -62,7 +62,7 @@ struct ts_config
int flags;
/**
- * get_next_block - fetch next block of data
+ * @get_next_block: fetch next block of data
* @consumed: number of bytes consumed by the caller
* @dst: destination buffer
* @conf: search configuration
@@ -79,7 +79,7 @@ struct ts_config
struct ts_state *state);
/**
- * finish - finalize/clean a series of get_next_block() calls
+ * @finish: finalize/clean a series of get_next_block() calls
* @conf: search configuration
* @state: search state
*
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 34f053a..cf2862b 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -43,11 +43,7 @@ enum {
#define THREAD_ALIGN THREAD_SIZE
#endif
-#if IS_ENABLED(CONFIG_DEBUG_STACK_USAGE) || IS_ENABLED(CONFIG_DEBUG_KMEMLEAK)
-# define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO)
-#else
-# define THREADINFO_GFP (GFP_KERNEL_ACCOUNT)
-#endif
+#define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO)
/*
* flag set/clear/test wrappers
diff --git a/include/linux/ti-emif-sram.h b/include/linux/ti-emif-sram.h
index 45bc6b37..53604b0 100644
--- a/include/linux/ti-emif-sram.h
+++ b/include/linux/ti-emif-sram.h
@@ -60,6 +60,81 @@ struct ti_emif_pm_functions {
u32 abort_sr;
} __packed __aligned(8);
+static inline void ti_emif_asm_offsets(void)
+{
+ DEFINE(EMIF_SDCFG_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_sdcfg_val));
+ DEFINE(EMIF_TIMING1_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_timing1_val));
+ DEFINE(EMIF_TIMING2_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_timing2_val));
+ DEFINE(EMIF_TIMING3_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_timing3_val));
+ DEFINE(EMIF_REF_CTRL_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_ref_ctrl_val));
+ DEFINE(EMIF_ZQCFG_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_zqcfg_val));
+ DEFINE(EMIF_PMCR_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_pmcr_val));
+ DEFINE(EMIF_PMCR_SHDW_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_pmcr_shdw_val));
+ DEFINE(EMIF_RD_WR_LEVEL_RAMP_CTRL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_rd_wr_level_ramp_ctrl));
+ DEFINE(EMIF_RD_WR_EXEC_THRESH_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_rd_wr_exec_thresh));
+ DEFINE(EMIF_COS_CONFIG_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_cos_config));
+ DEFINE(EMIF_PRIORITY_TO_COS_MAPPING_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_priority_to_cos_mapping));
+ DEFINE(EMIF_CONNECT_ID_SERV_1_MAP_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_connect_id_serv_1_map));
+ DEFINE(EMIF_CONNECT_ID_SERV_2_MAP_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_connect_id_serv_2_map));
+ DEFINE(EMIF_OCP_CONFIG_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_ocp_config_val));
+ DEFINE(EMIF_LPDDR2_NVM_TIM_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_lpddr2_nvm_tim));
+ DEFINE(EMIF_LPDDR2_NVM_TIM_SHDW_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_lpddr2_nvm_tim_shdw));
+ DEFINE(EMIF_DLL_CALIB_CTRL_VAL_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_dll_calib_ctrl_val));
+ DEFINE(EMIF_DLL_CALIB_CTRL_VAL_SHDW_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_dll_calib_ctrl_val_shdw));
+ DEFINE(EMIF_DDR_PHY_CTLR_1_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_ddr_phy_ctlr_1));
+ DEFINE(EMIF_EXT_PHY_CTRL_VALS_OFFSET,
+ offsetof(struct emif_regs_amx3, emif_ext_phy_ctrl_vals));
+ DEFINE(EMIF_REGS_AMX3_SIZE, sizeof(struct emif_regs_amx3));
+
+ BLANK();
+
+ DEFINE(EMIF_PM_BASE_ADDR_VIRT_OFFSET,
+ offsetof(struct ti_emif_pm_data, ti_emif_base_addr_virt));
+ DEFINE(EMIF_PM_BASE_ADDR_PHYS_OFFSET,
+ offsetof(struct ti_emif_pm_data, ti_emif_base_addr_phys));
+ DEFINE(EMIF_PM_CONFIG_OFFSET,
+ offsetof(struct ti_emif_pm_data, ti_emif_sram_config));
+ DEFINE(EMIF_PM_REGS_VIRT_OFFSET,
+ offsetof(struct ti_emif_pm_data, regs_virt));
+ DEFINE(EMIF_PM_REGS_PHYS_OFFSET,
+ offsetof(struct ti_emif_pm_data, regs_phys));
+ DEFINE(EMIF_PM_DATA_SIZE, sizeof(struct ti_emif_pm_data));
+
+ BLANK();
+
+ DEFINE(EMIF_PM_SAVE_CONTEXT_OFFSET,
+ offsetof(struct ti_emif_pm_functions, save_context));
+ DEFINE(EMIF_PM_RESTORE_CONTEXT_OFFSET,
+ offsetof(struct ti_emif_pm_functions, restore_context));
+ DEFINE(EMIF_PM_ENTER_SR_OFFSET,
+ offsetof(struct ti_emif_pm_functions, enter_sr));
+ DEFINE(EMIF_PM_EXIT_SR_OFFSET,
+ offsetof(struct ti_emif_pm_functions, exit_sr));
+ DEFINE(EMIF_PM_ABORT_SR_OFFSET,
+ offsetof(struct ti_emif_pm_functions, abort_sr));
+ DEFINE(EMIF_PM_FUNCTIONS_SIZE, sizeof(struct ti_emif_pm_functions));
+}
+
struct gen_pool;
int ti_emif_copy_pm_function_table(struct gen_pool *sram_pool, void *dst);
diff --git a/include/linux/time.h b/include/linux/time.h
index 4b62a2c..aed7446 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -10,9 +10,9 @@
extern struct timezone sys_tz;
int get_timespec64(struct timespec64 *ts,
- const struct timespec __user *uts);
+ const struct __kernel_timespec __user *uts);
int put_timespec64(const struct timespec64 *ts,
- struct timespec __user *uts);
+ struct __kernel_timespec __user *uts);
int get_itimerspec64(struct itimerspec64 *it,
const struct itimerspec __user *uit);
int put_itimerspec64(const struct itimerspec64 *it,
diff --git a/include/linux/time32.h b/include/linux/time32.h
index d2bcd43..0b14f93 100644
--- a/include/linux/time32.h
+++ b/include/linux/time32.h
@@ -18,25 +18,14 @@
/* timespec64 is defined as timespec here */
static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64)
{
- return ts64;
+ return *(const struct timespec *)&ts64;
}
static inline struct timespec64 timespec_to_timespec64(const struct timespec ts)
{
- return ts;
+ return *(const struct timespec64 *)&ts;
}
-# define timespec_equal timespec64_equal
-# define timespec_compare timespec64_compare
-# define set_normalized_timespec set_normalized_timespec64
-# define timespec_add timespec64_add
-# define timespec_sub timespec64_sub
-# define timespec_valid timespec64_valid
-# define timespec_valid_strict timespec64_valid_strict
-# define timespec_to_ns timespec64_to_ns
-# define ns_to_timespec ns_to_timespec64
-# define timespec_add_ns timespec64_add_ns
-
#else
static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64)
{
@@ -55,6 +44,7 @@ static inline struct timespec64 timespec_to_timespec64(const struct timespec ts)
ret.tv_nsec = ts.tv_nsec;
return ret;
}
+#endif
static inline int timespec_equal(const struct timespec *a,
const struct timespec *b)
@@ -159,8 +149,6 @@ static __always_inline void timespec_add_ns(struct timespec *a, u64 ns)
a->tv_nsec = ns;
}
-#endif
-
/**
* time_to_tm - converts the calendar time to local broken-down time
*
diff --git a/include/linux/time64.h b/include/linux/time64.h
index 93d3949..0a7b2f7 100644
--- a/include/linux/time64.h
+++ b/include/linux/time64.h
@@ -2,17 +2,20 @@
#ifndef _LINUX_TIME64_H
#define _LINUX_TIME64_H
-#include <uapi/linux/time.h>
#include <linux/math64.h>
typedef __s64 time64_t;
typedef __u64 timeu64_t;
-#if __BITS_PER_LONG == 64
-/* this trick allows us to optimize out timespec64_to_timespec */
-# define timespec64 timespec
-#define itimerspec64 itimerspec
-#else
+/* CONFIG_64BIT_TIME enables new 64 bit time_t syscalls in the compat path
+ * and 32-bit emulation.
+ */
+#ifndef CONFIG_64BIT_TIME
+#define __kernel_timespec timespec
+#endif
+
+#include <uapi/linux/time.h>
+
struct timespec64 {
time64_t tv_sec; /* seconds */
long tv_nsec; /* nanoseconds */
@@ -23,8 +26,6 @@ struct itimerspec64 {
struct timespec64 it_value;
};
-#endif
-
/* Parameters used to convert the timespec values: */
#define MSEC_PER_SEC 1000L
#define USEC_PER_MSEC 1000L
diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index 4b3dca1..7acb953 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -52,7 +52,6 @@ struct tk_read_base {
* @offs_real: Offset clock monotonic -> clock realtime
* @offs_boot: Offset clock monotonic -> clock boottime
* @offs_tai: Offset clock monotonic -> clock tai
- * @time_suspended: Accumulated suspend time
* @tai_offset: The current UTC to TAI offset in seconds
* @clock_was_set_seq: The sequence number of clock was set events
* @cs_was_changed_seq: The sequence number of clocksource change events
@@ -95,7 +94,6 @@ struct timekeeper {
ktime_t offs_real;
ktime_t offs_boot;
ktime_t offs_tai;
- ktime_t time_suspended;
s32 tai_offset;
unsigned int clock_was_set_seq;
u8 cs_was_changed_seq;
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 9737fbe..86bc202 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -19,53 +19,43 @@ extern void xtime_update(unsigned long ticks);
extern int do_settimeofday64(const struct timespec64 *ts);
extern int do_sys_settimeofday64(const struct timespec64 *tv,
const struct timezone *tz);
-/*
- * Kernel time accessors
- */
-struct timespec64 current_kernel_time64(void);
/*
* timespec64 based interfaces
*/
-struct timespec64 get_monotonic_coarse64(void);
-extern void getrawmonotonic64(struct timespec64 *ts);
+extern void ktime_get_raw_ts64(struct timespec64 *ts);
extern void ktime_get_ts64(struct timespec64 *ts);
+extern void ktime_get_real_ts64(struct timespec64 *tv);
+extern void ktime_get_coarse_ts64(struct timespec64 *ts);
+extern void ktime_get_coarse_real_ts64(struct timespec64 *ts);
+
+void getboottime64(struct timespec64 *ts);
+
+/*
+ * time64_t base interfaces
+ */
extern time64_t ktime_get_seconds(void);
extern time64_t __ktime_get_real_seconds(void);
extern time64_t ktime_get_real_seconds(void);
-extern void ktime_get_active_ts64(struct timespec64 *ts);
-
-extern int __getnstimeofday64(struct timespec64 *tv);
-extern void getnstimeofday64(struct timespec64 *tv);
-extern void getboottime64(struct timespec64 *ts);
-
-#define ktime_get_real_ts64(ts) getnstimeofday64(ts)
-
-/* Clock BOOTTIME compatibility wrappers */
-static inline void get_monotonic_boottime64(struct timespec64 *ts)
-{
- ktime_get_ts64(ts);
-}
/*
* ktime_t based interfaces
*/
+
enum tk_offsets {
TK_OFFS_REAL,
+ TK_OFFS_BOOT,
TK_OFFS_TAI,
TK_OFFS_MAX,
};
extern ktime_t ktime_get(void);
extern ktime_t ktime_get_with_offset(enum tk_offsets offs);
+extern ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs);
extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs);
extern ktime_t ktime_get_raw(void);
extern u32 ktime_get_resolution_ns(void);
-/* Clock BOOTTIME compatibility wrappers */
-static inline ktime_t ktime_get_boottime(void) { return ktime_get(); }
-static inline u64 ktime_get_boot_ns(void) { return ktime_get(); }
-
/**
* ktime_get_real - get the real (wall-) time in ktime_t format
*/
@@ -74,6 +64,27 @@ static inline ktime_t ktime_get_real(void)
return ktime_get_with_offset(TK_OFFS_REAL);
}
+static inline ktime_t ktime_get_coarse_real(void)
+{
+ return ktime_get_coarse_with_offset(TK_OFFS_REAL);
+}
+
+/**
+ * ktime_get_boottime - Returns monotonic time since boot in ktime_t format
+ *
+ * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the
+ * time spent in suspend.
+ */
+static inline ktime_t ktime_get_boottime(void)
+{
+ return ktime_get_with_offset(TK_OFFS_BOOT);
+}
+
+static inline ktime_t ktime_get_coarse_boottime(void)
+{
+ return ktime_get_coarse_with_offset(TK_OFFS_BOOT);
+}
+
/**
* ktime_get_clocktai - Returns the TAI time of day in ktime_t format
*/
@@ -82,6 +93,11 @@ static inline ktime_t ktime_get_clocktai(void)
return ktime_get_with_offset(TK_OFFS_TAI);
}
+static inline ktime_t ktime_get_coarse_clocktai(void)
+{
+ return ktime_get_coarse_with_offset(TK_OFFS_TAI);
+}
+
/**
* ktime_mono_to_real - Convert monotonic time to clock realtime
*/
@@ -100,6 +116,11 @@ static inline u64 ktime_get_real_ns(void)
return ktime_to_ns(ktime_get_real());
}
+static inline u64 ktime_get_boot_ns(void)
+{
+ return ktime_to_ns(ktime_get_boottime());
+}
+
static inline u64 ktime_get_tai_ns(void)
{
return ktime_to_ns(ktime_get_clocktai());
@@ -112,16 +133,44 @@ static inline u64 ktime_get_raw_ns(void)
extern u64 ktime_get_mono_fast_ns(void);
extern u64 ktime_get_raw_fast_ns(void);
+extern u64 ktime_get_boot_fast_ns(void);
extern u64 ktime_get_real_fast_ns(void);
/*
- * timespec64 interfaces utilizing the ktime based ones
+ * timespec64/time64_t interfaces utilizing the ktime based ones
+ * for API completeness, these could be implemented more efficiently
+ * if needed.
*/
-static inline void timekeeping_clocktai64(struct timespec64 *ts)
+static inline void ktime_get_boottime_ts64(struct timespec64 *ts)
+{
+ *ts = ktime_to_timespec64(ktime_get_boottime());
+}
+
+static inline void ktime_get_coarse_boottime_ts64(struct timespec64 *ts)
+{
+ *ts = ktime_to_timespec64(ktime_get_coarse_boottime());
+}
+
+static inline time64_t ktime_get_boottime_seconds(void)
+{
+ return ktime_divns(ktime_get_coarse_boottime(), NSEC_PER_SEC);
+}
+
+static inline void ktime_get_clocktai_ts64(struct timespec64 *ts)
{
*ts = ktime_to_timespec64(ktime_get_clocktai());
}
+static inline void ktime_get_coarse_clocktai_ts64(struct timespec64 *ts)
+{
+ *ts = ktime_to_timespec64(ktime_get_coarse_clocktai());
+}
+
+static inline time64_t ktime_get_clocktai_seconds(void)
+{
+ return ktime_divns(ktime_get_coarse_clocktai(), NSEC_PER_SEC);
+}
+
/*
* RTC specific
*/
@@ -197,5 +246,30 @@ extern void read_persistent_clock64(struct timespec64 *ts);
extern void read_boot_clock64(struct timespec64 *ts);
extern int update_persistent_clock64(struct timespec64 now);
+/*
+ * deprecated aliases, don't use in new code
+ */
+#define getnstimeofday64(ts) ktime_get_real_ts64(ts)
+#define get_monotonic_boottime64(ts) ktime_get_boottime_ts64(ts)
+#define getrawmonotonic64(ts) ktime_get_raw_ts64(ts)
+#define timekeeping_clocktai64(ts) ktime_get_clocktai_ts64(ts)
+
+static inline struct timespec64 current_kernel_time64(void)
+{
+ struct timespec64 ts;
+
+ ktime_get_coarse_real_ts64(&ts);
+
+ return ts;
+}
+
+static inline struct timespec64 get_monotonic_coarse64(void)
+{
+ struct timespec64 ts;
+
+ ktime_get_coarse_ts64(&ts);
+
+ return ts;
+}
#endif
diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h
index af4114d..8762c2f 100644
--- a/include/linux/timekeeping32.h
+++ b/include/linux/timekeeping32.h
@@ -9,60 +9,15 @@
extern void do_gettimeofday(struct timeval *tv);
unsigned long get_seconds(void);
-/* does not take xtime_lock */
-struct timespec __current_kernel_time(void);
-
static inline struct timespec current_kernel_time(void)
{
- struct timespec64 now = current_kernel_time64();
+ struct timespec64 ts64;
- return timespec64_to_timespec(now);
+ ktime_get_coarse_real_ts64(&ts64);
+
+ return timespec64_to_timespec(ts64);
}
-#if BITS_PER_LONG == 64
-/**
- * Deprecated. Use do_settimeofday64().
- */
-static inline int do_settimeofday(const struct timespec *ts)
-{
- return do_settimeofday64(ts);
-}
-
-static inline int __getnstimeofday(struct timespec *ts)
-{
- return __getnstimeofday64(ts);
-}
-
-static inline void getnstimeofday(struct timespec *ts)
-{
- getnstimeofday64(ts);
-}
-
-static inline void ktime_get_ts(struct timespec *ts)
-{
- ktime_get_ts64(ts);
-}
-
-static inline void ktime_get_real_ts(struct timespec *ts)
-{
- getnstimeofday64(ts);
-}
-
-static inline void getrawmonotonic(struct timespec *ts)
-{
- getrawmonotonic64(ts);
-}
-
-static inline struct timespec get_monotonic_coarse(void)
-{
- return get_monotonic_coarse64();
-}
-
-static inline void getboottime(struct timespec *ts)
-{
- return getboottime64(ts);
-}
-#else
/**
* Deprecated. Use do_settimeofday64().
*/
@@ -74,20 +29,11 @@ static inline int do_settimeofday(const struct timespec *ts)
return do_settimeofday64(&ts64);
}
-static inline int __getnstimeofday(struct timespec *ts)
-{
- struct timespec64 ts64;
- int ret = __getnstimeofday64(&ts64);
-
- *ts = timespec64_to_timespec(ts64);
- return ret;
-}
-
static inline void getnstimeofday(struct timespec *ts)
{
struct timespec64 ts64;
- getnstimeofday64(&ts64);
+ ktime_get_real_ts64(&ts64);
*ts = timespec64_to_timespec(ts64);
}
@@ -103,7 +49,7 @@ static inline void ktime_get_real_ts(struct timespec *ts)
{
struct timespec64 ts64;
- getnstimeofday64(&ts64);
+ ktime_get_real_ts64(&ts64);
*ts = timespec64_to_timespec(ts64);
}
@@ -111,13 +57,17 @@ static inline void getrawmonotonic(struct timespec *ts)
{
struct timespec64 ts64;
- getrawmonotonic64(&ts64);
+ ktime_get_raw_ts64(&ts64);
*ts = timespec64_to_timespec(ts64);
}
static inline struct timespec get_monotonic_coarse(void)
{
- return timespec64_to_timespec(get_monotonic_coarse64());
+ struct timespec64 ts64;
+
+ ktime_get_coarse_ts64(&ts64);
+
+ return timespec64_to_timespec(ts64);
}
static inline void getboottime(struct timespec *ts)
@@ -127,7 +77,6 @@ static inline void getboottime(struct timespec *ts)
getboottime64(&ts64);
*ts = timespec64_to_timespec(ts64);
}
-#endif
/*
* Timespec interfaces utilizing the ktime based ones
diff --git a/include/linux/timer.h b/include/linux/timer.h
index 2448f9c..7b066fd 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -8,8 +8,6 @@
#include <linux/debugobjects.h>
#include <linux/stringify.h>
-struct tvec_base;
-
struct timer_list {
/*
* All fields that change during normal runtime grouped to the
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 26c1521..4a88419 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -124,6 +124,7 @@ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step)
{
if (step) {
siginfo_t info;
+ clear_siginfo(&info);
user_single_step_siginfo(current, regs, &info);
force_sig_info(SIGTRAP, &info, current);
return;
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 47f8af2..9bd7d37 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -10,6 +10,7 @@
#include <linux/tty_ldisc.h>
#include <linux/mutex.h>
#include <linux/tty_flags.h>
+#include <linux/seq_file.h>
#include <uapi/linux/tty.h>
#include <linux/rwsem.h>
#include <linux/llist.h>
@@ -535,7 +536,7 @@ extern void tty_ldisc_deref(struct tty_ldisc *);
extern struct tty_ldisc *tty_ldisc_ref_wait(struct tty_struct *);
extern void tty_ldisc_hangup(struct tty_struct *tty, bool reset);
extern int tty_ldisc_reinit(struct tty_struct *tty, int disc);
-extern const struct file_operations tty_ldiscs_proc_fops;
+extern const struct seq_operations tty_ldiscs_seq_ops;
extern void tty_wakeup(struct tty_struct *tty);
extern void tty_ldisc_flush(struct tty_struct *tty);
@@ -701,7 +702,7 @@ extern int tty_unregister_ldisc(int disc);
extern int tty_set_ldisc(struct tty_struct *tty, int disc);
extern int tty_ldisc_setup(struct tty_struct *tty, struct tty_struct *o_tty);
extern void tty_ldisc_release(struct tty_struct *tty);
-extern void tty_ldisc_init(struct tty_struct *tty);
+extern int __must_check tty_ldisc_init(struct tty_struct *tty);
extern void tty_ldisc_deinit(struct tty_struct *tty);
extern int tty_ldisc_receive_buf(struct tty_ldisc *ld, const unsigned char *p,
char *f, int count);
diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h
index 31c2b5b..71dbc89 100644
--- a/include/linux/tty_driver.h
+++ b/include/linux/tty_driver.h
@@ -293,7 +293,7 @@ struct tty_operations {
int (*poll_get_char)(struct tty_driver *driver, int line);
void (*poll_put_char)(struct tty_driver *driver, int line, char ch);
#endif
- const struct file_operations *proc_fops;
+ int (*proc_show)(struct seq_file *, void *);
} __randomize_layout;
struct tty_driver {
diff --git a/include/linux/uio.h b/include/linux/uio.h
index e67e12a..f5766e8 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -154,6 +154,12 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i);
#define _copy_from_iter_flushcache _copy_from_iter_nocache
#endif
+#ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE
+size_t _copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i);
+#else
+#define _copy_to_iter_mcsafe _copy_to_iter
+#endif
+
static __always_inline __must_check
size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
{
@@ -163,6 +169,15 @@ size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
return _copy_from_iter_flushcache(addr, bytes, i);
}
+static __always_inline __must_check
+size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i)
+{
+ if (unlikely(!check_copy_size(addr, bytes, false)))
+ return 0;
+ else
+ return _copy_to_iter_mcsafe(addr, bytes, i);
+}
+
size_t iov_iter_zero(size_t bytes, struct iov_iter *);
unsigned long iov_iter_alignment(const struct iov_iter *i);
unsigned long iov_iter_gap_alignment(const struct iov_iter *i);
diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h
index 4b6b928..8675e14 100644
--- a/include/linux/usb/composite.h
+++ b/include/linux/usb/composite.h
@@ -52,7 +52,7 @@
#define USB_GADGET_DELAYED_STATUS 0x7fff /* Impossibly large value */
/* big enough to hold our biggest descriptor */
-#define USB_COMP_EP0_BUFSIZ 1024
+#define USB_COMP_EP0_BUFSIZ 4096
/* OS feature descriptor length <= 4kB */
#define USB_COMP_EP0_OS_DESC_BUFSIZ 4096
diff --git a/include/linux/vbox_utils.h b/include/linux/vbox_utils.h
index c71def6..a240ed2 100644
--- a/include/linux/vbox_utils.h
+++ b/include/linux/vbox_utils.h
@@ -24,24 +24,6 @@ __printf(1, 2) void vbg_debug(const char *fmt, ...);
#define vbg_debug pr_debug
#endif
-/**
- * Allocate memory for generic request and initialize the request header.
- *
- * Return: the allocated memory
- * @len: Size of memory block required for the request.
- * @req_type: The generic request type.
- */
-void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type);
-
-/**
- * Perform a generic request.
- *
- * Return: VBox status code
- * @gdev: The Guest extension device.
- * @req: Pointer to the request structure.
- */
-int vbg_req_perform(struct vbg_dev *gdev, void *req);
-
int vbg_hgcm_connect(struct vbg_dev *gdev,
struct vmmdev_hgcm_service_location *loc,
u32 *client_id, int *vbox_status);
@@ -52,11 +34,6 @@ int vbg_hgcm_call(struct vbg_dev *gdev, u32 client_id, u32 function,
u32 timeout_ms, struct vmmdev_hgcm_function_parameter *parms,
u32 parm_count, int *vbox_status);
-int vbg_hgcm_call32(
- struct vbg_dev *gdev, u32 client_id, u32 function, u32 timeout_ms,
- struct vmmdev_hgcm_function_parameter32 *parm32, u32 parm_count,
- int *vbox_status);
-
/**
* Convert a VirtualBox status code to a standard Linux kernel return value.
* Return: 0 or negative errno value.
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 988c735..fa1b5da 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -157,6 +157,9 @@ int virtio_device_freeze(struct virtio_device *dev);
int virtio_device_restore(struct virtio_device *dev);
#endif
+#define virtio_device_for_each_vq(vdev, vq) \
+ list_for_each_entry(vq, &vdev->vqs, list)
+
/**
* virtio_driver - operations for a virtio I/O driver
* @driver: underlying device driver (populate name and owner).
diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h
index 9318b21..2b0072f 100644
--- a/include/linux/wait_bit.h
+++ b/include/linux/wait_bit.h
@@ -305,4 +305,21 @@ do { \
__ret; \
})
+/**
+ * clear_and_wake_up_bit - clear a bit and wake up anyone waiting on that bit
+ *
+ * @bit: the bit of the word being waited on
+ * @word: the word being waited on, a kernel virtual address
+ *
+ * You can use this helper if bitflags are manipulated atomically rather than
+ * non-atomically under a lock.
+ */
+static inline void clear_and_wake_up_bit(int bit, void *word)
+{
+ clear_bit_unlock(bit, word);
+ /* See wake_up_bit() for which memory barrier you need to use. */
+ smp_mb__after_atomic();
+ wake_up_bit(word, bit);
+}
+
#endif /* _LINUX_WAIT_BIT_H */
diff --git a/include/linux/xattr.h b/include/linux/xattr.h
index d70f77a4..6dad031 100644
--- a/include/linux/xattr.h
+++ b/include/linux/xattr.h
@@ -46,7 +46,6 @@ struct xattr {
size_t value_len;
};
-ssize_t xattr_getsecurity(struct inode *, const char *, void *, size_t);
ssize_t __vfs_getxattr(struct dentry *, struct inode *, const char *, void *, size_t);
ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t);
ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size);
diff --git a/include/media/i2c/tvp7002.h b/include/media/i2c/tvp7002.h
index 5ee007c..cb213c1 100644
--- a/include/media/i2c/tvp7002.h
+++ b/include/media/i2c/tvp7002.h
@@ -5,7 +5,7 @@
* Author: Santiago Nunez-Corrales <santiago.nunez@ridgerun.com>
*
* This code is partially based upon the TVP5150 driver
- * written by Mauro Carvalho Chehab (mchehab@infradead.org),
+ * written by Mauro Carvalho Chehab <mchehab@kernel.org>,
* the TVP514x driver written by Vaibhav Hiremath <hvaibhav@ti.com>
* and the TVP7002 driver in the TI LSP 2.10.00.14
*
diff --git a/include/media/videobuf-core.h b/include/media/videobuf-core.h
index 0bda0ad..60a664f 100644
--- a/include/media/videobuf-core.h
+++ b/include/media/videobuf-core.h
@@ -1,11 +1,11 @@
/*
* generic helper functions for handling video4linux capture buffers
*
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
*
* Highly based on video-buf written originally by:
* (c) 2001,02 Gerd Knorr <kraxel@bytesex.org>
- * (c) 2006 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2006 Mauro Carvalho Chehab, <mchehab@kernel.org>
* (c) 2006 Ted Walther and John Sokol
*
* This program is free software; you can redistribute it and/or modify
diff --git a/include/media/videobuf-dma-sg.h b/include/media/videobuf-dma-sg.h
index d8b27854..01bd142 100644
--- a/include/media/videobuf-dma-sg.h
+++ b/include/media/videobuf-dma-sg.h
@@ -6,11 +6,11 @@
* into PAGE_SIZE chunks). They also assume the driver does not need
* to touch the video data.
*
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
*
* Highly based on video-buf written originally by:
* (c) 2001,02 Gerd Knorr <kraxel@bytesex.org>
- * (c) 2006 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2006 Mauro Carvalho Chehab, <mchehab@kernel.org>
* (c) 2006 Ted Walther and John Sokol
*
* This program is free software; you can redistribute it and/or modify
diff --git a/include/media/videobuf-vmalloc.h b/include/media/videobuf-vmalloc.h
index 486a97e..36c6a4a 100644
--- a/include/media/videobuf-vmalloc.h
+++ b/include/media/videobuf-vmalloc.h
@@ -6,7 +6,7 @@
* into PAGE_SIZE chunks). They also assume the driver does not need
* to touch the video data.
*
- * (c) 2007 Mauro Carvalho Chehab, <mchehab@infradead.org>
+ * (c) 2007 Mauro Carvalho Chehab, <mchehab@kernel.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
diff --git a/include/net/ax25.h b/include/net/ax25.h
index c91bc87..3f9aea8 100644
--- a/include/net/ax25.h
+++ b/include/net/ax25.h
@@ -15,6 +15,7 @@
#include <linux/refcount.h>
#include <net/neighbour.h>
#include <net/sock.h>
+#include <linux/seq_file.h>
#define AX25_T1CLAMPLO 1
#define AX25_T1CLAMPHI (30 * HZ)
@@ -399,7 +400,7 @@ int ax25_check_iframes_acked(ax25_cb *, unsigned short);
/* ax25_route.c */
void ax25_rt_device_down(struct net_device *);
int ax25_rt_ioctl(unsigned int, void __user *);
-extern const struct file_operations ax25_route_fops;
+extern const struct seq_operations ax25_rt_seqops;
ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev);
int ax25_rt_autobind(ax25_cb *, ax25_address *);
struct sk_buff *ax25_rt_build_path(struct sk_buff *, ax25_address *,
@@ -455,7 +456,7 @@ unsigned long ax25_display_timer(struct timer_list *);
extern int ax25_uid_policy;
ax25_uid_assoc *ax25_findbyuid(kuid_t);
int __must_check ax25_uid_ioctl(int, struct sockaddr_ax25 *);
-extern const struct file_operations ax25_uid_fops;
+extern const struct seq_operations ax25_uid_seqops;
void ax25_uid_free(void);
/* sysctl_net_ax25.c */
diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index ec9d6bc..53ce817 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -271,7 +271,7 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
int flags);
int bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg,
size_t len, int flags);
-__poll_t bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait);
+__poll_t bt_sock_poll_mask(struct socket *sock, __poll_t events);
int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo);
int bt_sock_wait_ready(struct sock *sk, unsigned long flags);
diff --git a/include/net/bonding.h b/include/net/bonding.h
index f801fc9..b522351 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -198,6 +198,7 @@ struct bonding {
struct slave __rcu *primary_slave;
struct bond_up_slave __rcu *slave_arr; /* Array of usable slaves */
bool force_primary;
+ u32 nest_level;
s32 slave_cnt; /* never change this value outside the attach/detach wrappers */
int (*recv_probe)(const struct sk_buff *, struct bonding *,
struct slave *);
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 71c72a9..c518743 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -121,6 +121,21 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock)
#endif
}
+static inline void sock_poll_busy_loop(struct socket *sock, __poll_t events)
+{
+ if (sk_can_busy_loop(sock->sk) &&
+ events && (events & POLL_BUSY_LOOP)) {
+ /* once, only if requested by syscall */
+ sk_busy_loop(sock->sk, 1);
+ }
+}
+
+/* if this socket can poll_ll, tell the system call */
+static inline __poll_t sock_poll_busy_flag(struct socket *sock)
+{
+ return sk_can_busy_loop(sock->sk) ? POLL_BUSY_LOOP : 0;
+}
+
/* used in the NIC receive handler to mark the skb */
static inline void skb_mark_napi_id(struct sk_buff *skb,
struct napi_struct *napi)
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 9a07477..d1fcf24 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -251,7 +251,7 @@ extern struct flow_dissector flow_keys_buf_dissector;
* This structure is used to hold a digest of the full flow keys. This is a
* larger "hash" of a flow to allow definitively matching specific flows where
* the 32 bit skb->hash is not large enough. The size is limited to 16 bytes so
- * that it can by used in CB of skb (see sch_choke for an example).
+ * that it can be used in CB of skb (see sch_choke for an example).
*/
#define FLOW_KEYS_DIGEST_LEN 16
struct flow_keys_digest {
diff --git a/include/net/ife.h b/include/net/ife.h
index 44b9c00..e117617 100644
--- a/include/net/ife.h
+++ b/include/net/ife.h
@@ -12,7 +12,8 @@
void *ife_encode(struct sk_buff *skb, u16 metalen);
void *ife_decode(struct sk_buff *skb, u16 *metalen);
-void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen);
+void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype,
+ u16 *dlen, u16 *totlen);
int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen,
const void *dval);
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 5e86fd9..0e79c34 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -394,7 +394,15 @@ void fib6_gc_cleanup(void);
int fib6_init(void);
-int ipv6_route_open(struct inode *inode, struct file *file);
+struct ipv6_route_iter {
+ struct seq_net_private p;
+ struct fib6_walker w;
+ loff_t skip;
+ struct fib6_table *tbl;
+ int sernum;
+};
+
+extern const struct seq_operations ipv6_route_seq_ops;
int call_fib6_notifier(struct notifier_block *nb, struct net *net,
enum fib_event_type event_type,
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index eb0bec0..aea7a12 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -41,18 +41,6 @@ static inline struct netns_ipvs *net_ipvs(struct net* net)
return net->ipvs;
}
-/* This one needed for single_open_net since net is stored directly in
- * private not as a struct i.e. seq_file_net can't be used.
- */
-static inline struct net *seq_file_single_net(struct seq_file *seq)
-{
-#ifdef CONFIG_NET_NS
- return (struct net *)seq->private;
-#else
- return &init_net;
-#endif
-}
-
/* Connections' size value needed by ip_vs_ctl.c */
extern int ip_vs_conn_tab_size;
diff --git a/include/net/iucv/af_iucv.h b/include/net/iucv/af_iucv.h
index f4c21b5..b0eaeb0 100644
--- a/include/net/iucv/af_iucv.h
+++ b/include/net/iucv/af_iucv.h
@@ -153,8 +153,6 @@ struct iucv_sock_list {
atomic_t autobind_name;
};
-__poll_t iucv_sock_poll(struct file *file, struct socket *sock,
- poll_table *wait);
void iucv_sock_link(struct iucv_sock_list *l, struct sock *s);
void iucv_sock_unlink(struct iucv_sock_list *l, struct sock *s);
void iucv_accept_enqueue(struct sock *parent, struct sock *sk);
diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h
index 5c40f11..df528a6 100644
--- a/include/net/llc_conn.h
+++ b/include/net/llc_conn.h
@@ -97,6 +97,7 @@ static __inline__ char llc_backlog_type(struct sk_buff *skb)
struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority,
struct proto *prot, int kern);
+void llc_sk_stop_all_timers(struct sock *sk, bool sync);
void llc_sk_free(struct sock *sk);
void llc_sk_reset(struct sock *sk);
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index d2279b2..b2f3a0c 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2080,7 +2080,7 @@ struct ieee80211_txq {
* virtual interface might not be given air time for the transmission of
* the frame, as it is not synced with the AP/P2P GO yet, and thus the
* deauthentication frame might not be transmitted.
- >
+ *
* @IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP: The driver (or firmware) doesn't
* support QoS NDP for AP probing - that's most likely a driver bug.
*
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index cd368d1..a1e28dd 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -170,6 +170,7 @@ struct nft_data_desc {
int nft_data_init(const struct nft_ctx *ctx,
struct nft_data *data, unsigned int size,
struct nft_data_desc *desc, const struct nlattr *nla);
+void nft_data_hold(const struct nft_data *data, enum nft_data_types type);
void nft_data_release(const struct nft_data *data, enum nft_data_types type);
int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data,
enum nft_data_types type, unsigned int len);
@@ -736,6 +737,10 @@ struct nft_expr_ops {
int (*init)(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nlattr * const tb[]);
+ void (*activate)(const struct nft_ctx *ctx,
+ const struct nft_expr *expr);
+ void (*deactivate)(const struct nft_ctx *ctx,
+ const struct nft_expr *expr);
void (*destroy)(const struct nft_ctx *ctx,
const struct nft_expr *expr);
int (*dump)(struct sk_buff *skb,
diff --git a/include/net/netrom.h b/include/net/netrom.h
index 0dad2dd..5a0714f 100644
--- a/include/net/netrom.h
+++ b/include/net/netrom.h
@@ -13,6 +13,7 @@
#include <linux/slab.h>
#include <net/sock.h>
#include <linux/refcount.h>
+#include <linux/seq_file.h>
#define NR_NETWORK_LEN 15
#define NR_TRANSPORT_LEN 5
@@ -216,8 +217,8 @@ struct net_device *nr_dev_get(ax25_address *);
int nr_rt_ioctl(unsigned int, void __user *);
void nr_link_failed(ax25_cb *, int);
int nr_route_frame(struct sk_buff *, ax25_cb *);
-extern const struct file_operations nr_nodes_fops;
-extern const struct file_operations nr_neigh_fops;
+extern const struct seq_operations nr_node_seqops;
+extern const struct seq_operations nr_neigh_seqops;
void nr_rt_free(void);
/* nr_subr.c */
diff --git a/include/net/phonet/pn_dev.h b/include/net/phonet/pn_dev.h
index 8639de5..cbee32b 100644
--- a/include/net/phonet/pn_dev.h
+++ b/include/net/phonet/pn_dev.h
@@ -56,7 +56,7 @@ struct net_device *phonet_route_output(struct net *net, u8 daddr);
#define PN_NO_ADDR 0xff
-extern const struct file_operations pn_sock_seq_fops;
-extern const struct file_operations pn_res_seq_fops;
+extern const struct seq_operations pn_sock_seq_ops;
+extern const struct seq_operations pn_res_seq_ops;
#endif
diff --git a/include/net/ping.h b/include/net/ping.h
index 4cd90d6..fd080e0 100644
--- a/include/net/ping.h
+++ b/include/net/ping.h
@@ -83,20 +83,9 @@ int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
bool ping_rcv(struct sk_buff *skb);
#ifdef CONFIG_PROC_FS
-struct ping_seq_afinfo {
- char *name;
- sa_family_t family;
- const struct file_operations *seq_fops;
- const struct seq_operations seq_ops;
-};
-
-extern const struct file_operations ping_seq_fops;
-
void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family);
void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos);
void ping_seq_stop(struct seq_file *seq, void *v);
-int ping_proc_register(struct net *net, struct ping_seq_afinfo *afinfo);
-void ping_proc_unregister(struct net *net, struct ping_seq_afinfo *afinfo);
int __init ping_proc_init(void);
void ping_proc_exit(void);
diff --git a/include/net/raw.h b/include/net/raw.h
index 99d26d0..9c9fa98 100644
--- a/include/net/raw.h
+++ b/include/net/raw.h
@@ -48,7 +48,6 @@ void raw_proc_exit(void);
struct raw_iter_state {
struct seq_net_private p;
int bucket;
- struct raw_hashinfo *h;
};
static inline struct raw_iter_state *raw_seq_private(struct seq_file *seq)
@@ -58,9 +57,6 @@ static inline struct raw_iter_state *raw_seq_private(struct seq_file *seq)
void *raw_seq_start(struct seq_file *seq, loff_t *pos);
void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos);
void raw_seq_stop(struct seq_file *seq, void *v);
-int raw_seq_open(struct inode *ino, struct file *file,
- struct raw_hashinfo *h, const struct seq_operations *ops);
-
#endif
int raw_hash_sk(struct sock *sk);
diff --git a/include/net/rose.h b/include/net/rose.h
index 04b7268..cf517d3 100644
--- a/include/net/rose.h
+++ b/include/net/rose.h
@@ -200,9 +200,9 @@ void rose_enquiry_response(struct sock *);
/* rose_route.c */
extern struct rose_neigh *rose_loopback_neigh;
-extern const struct file_operations rose_neigh_fops;
-extern const struct file_operations rose_nodes_fops;
-extern const struct file_operations rose_routes_fops;
+extern const struct seq_operations rose_neigh_seqops;
+extern const struct seq_operations rose_node_seqops;
+extern struct seq_operations rose_route_seqops;
void rose_add_loopback_neigh(void);
int __must_check rose_add_loopback_node(rose_address *);
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 28b996d..e6d349b 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -103,12 +103,13 @@ void sctp_addr_wq_mgmt(struct net *, struct sctp_sockaddr_entry *, int);
/*
* sctp/socket.c
*/
+int sctp_inet_connect(struct socket *sock, struct sockaddr *uaddr,
+ int addr_len, int flags);
int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb);
int sctp_inet_listen(struct socket *sock, int backlog);
void sctp_write_space(struct sock *sk);
void sctp_data_ready(struct sock *sk);
-__poll_t sctp_poll(struct file *file, struct socket *sock,
- poll_table *wait);
+__poll_t sctp_poll_mask(struct socket *sock, __poll_t events);
void sctp_sock_rfree(struct sk_buff *skb);
void sctp_copy_sock(struct sock *newsk, struct sock *sk,
struct sctp_association *asoc);
diff --git a/include/net/sock.h b/include/net/sock.h
index 74d725f..4d2e8ad 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1591,8 +1591,6 @@ int sock_no_connect(struct socket *, struct sockaddr *, int, int);
int sock_no_socketpair(struct socket *, struct socket *);
int sock_no_accept(struct socket *, struct socket *, int, bool);
int sock_no_getname(struct socket *, struct sockaddr *, int);
-__poll_t sock_no_poll(struct file *, struct socket *,
- struct poll_table_struct *);
int sock_no_ioctl(struct socket *, unsigned int, unsigned long);
int sock_no_listen(struct socket *, int);
int sock_no_shutdown(struct socket *, int);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9c9b376..f88f8a2 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -388,8 +388,7 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
void tcp_close(struct sock *sk, long timeout);
void tcp_init_sock(struct sock *sk);
void tcp_init_transfer(struct sock *sk, int bpf_op);
-__poll_t tcp_poll(struct file *file, struct socket *sock,
- struct poll_table_struct *wait);
+__poll_t tcp_poll_mask(struct socket *sock, __poll_t events);
int tcp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
int tcp_setsockopt(struct sock *sk, int level, int optname,
@@ -1747,27 +1746,22 @@ enum tcp_seq_states {
TCP_SEQ_STATE_ESTABLISHED,
};
-int tcp_seq_open(struct inode *inode, struct file *file);
+void *tcp_seq_start(struct seq_file *seq, loff_t *pos);
+void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos);
+void tcp_seq_stop(struct seq_file *seq, void *v);
struct tcp_seq_afinfo {
- char *name;
sa_family_t family;
- const struct file_operations *seq_fops;
- struct seq_operations seq_ops;
};
struct tcp_iter_state {
struct seq_net_private p;
- sa_family_t family;
enum tcp_seq_states state;
struct sock *syn_wait_sk;
int bucket, offset, sbucket, num;
loff_t last_pos;
};
-int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo);
-void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo);
-
extern struct request_sock_ops tcp_request_sock_ops;
extern struct request_sock_ops tcp6_request_sock_ops;
diff --git a/include/net/tls.h b/include/net/tls.h
index 3da8e13..f5fb16d 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -97,6 +97,9 @@ struct tls_sw_context {
u8 control;
bool decrypted;
+ char rx_aad_ciphertext[TLS_AAD_SPACE_SIZE];
+ char rx_aad_plaintext[TLS_AAD_SPACE_SIZE];
+
/* Sending context */
char aad_space[TLS_AAD_SPACE_SIZE];
@@ -148,6 +151,7 @@ struct tls_context {
struct scatterlist *partially_sent_record;
u16 partially_sent_offset;
unsigned long flags;
+ bool in_tcp_sendpages;
u16 pending_open_record_frags;
int (*push_pending_record)(struct sock *sk, int flags);
diff --git a/include/net/udp.h b/include/net/udp.h
index 0676b27..d8ca3b2 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -276,7 +276,7 @@ int udp_init_sock(struct sock *sk);
int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
int __udp_disconnect(struct sock *sk, int flags);
int udp_disconnect(struct sock *sk, int flags);
-__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait);
+__poll_t udp_poll_mask(struct socket *sock, __poll_t events);
struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
netdev_features_t features,
bool is_ipv6);
@@ -408,31 +408,27 @@ do { \
#define __UDPX_INC_STATS(sk, field) __UDP_INC_STATS(sock_net(sk), field, 0)
#endif
-/* /proc */
-int udp_seq_open(struct inode *inode, struct file *file);
-
+#ifdef CONFIG_PROC_FS
struct udp_seq_afinfo {
- char *name;
sa_family_t family;
struct udp_table *udp_table;
- const struct file_operations *seq_fops;
- struct seq_operations seq_ops;
};
struct udp_iter_state {
struct seq_net_private p;
- sa_family_t family;
int bucket;
- struct udp_table *udp_table;
};
-#ifdef CONFIG_PROC_FS
-int udp_proc_register(struct net *net, struct udp_seq_afinfo *afinfo);
-void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo);
+void *udp_seq_start(struct seq_file *seq, loff_t *pos);
+void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos);
+void udp_seq_stop(struct seq_file *seq, void *v);
+
+extern const struct seq_operations udp_seq_ops;
+extern const struct seq_operations udp6_seq_ops;
int udp4_proc_init(void);
void udp4_proc_exit(void);
-#endif
+#endif /* CONFIG_PROC_FS */
int udpv4_offload_init(void);
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index a872379..45e75c3 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -375,6 +375,7 @@ struct xfrm_input_afinfo {
int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo);
int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo);
+void xfrm_flush_gc(void);
void xfrm_state_delete_tunnel(struct xfrm_state *x);
struct xfrm_type {
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 23159dd..a1fd638 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -48,7 +48,6 @@ struct ib_umem {
int writable;
int hugetlb;
struct work_struct work;
- struct pid *pid;
struct mm_struct *mm;
unsigned long diff;
struct ib_umem_odp *odp_data;
diff --git a/include/rdma/uverbs_ioctl.h b/include/rdma/uverbs_ioctl.h
index 4a4201d..095383a 100644
--- a/include/rdma/uverbs_ioctl.h
+++ b/include/rdma/uverbs_ioctl.h
@@ -411,13 +411,13 @@ static inline int uverbs_attr_get_enum_id(const struct uverbs_attr_bundle *attrs
static inline void *uverbs_attr_get_obj(const struct uverbs_attr_bundle *attrs_bundle,
u16 idx)
{
- struct ib_uobject *uobj =
- uverbs_attr_get(attrs_bundle, idx)->obj_attr.uobject;
+ const struct uverbs_attr *attr;
- if (IS_ERR(uobj))
- return uobj;
+ attr = uverbs_attr_get(attrs_bundle, idx);
+ if (IS_ERR(attr))
+ return ERR_CAST(attr);
- return uobj->object;
+ return attr->obj_attr.uobject->object;
}
static inline int uverbs_copy_to(const struct uverbs_attr_bundle *attrs_bundle,
diff --git a/include/scsi/osd_initiator.h b/include/scsi/osd_initiator.h
index a29d308..86a569d 100644
--- a/include/scsi/osd_initiator.h
+++ b/include/scsi/osd_initiator.h
@@ -148,7 +148,6 @@ struct osd_request {
u8 *pad_buff;
} out, in;
- gfp_t alloc_flags;
unsigned timeout;
unsigned retries;
unsigned sense_len;
@@ -202,14 +201,11 @@ static inline bool osd_req_is_ver1(struct osd_request *or)
*
* @osd_dev: OSD device that holds the scsi-device and default values
* that the request is associated with.
- * @gfp: The allocation flags to use for request allocation, and all
- * subsequent allocations. This will be stored at
- * osd_request->alloc_flags, can be changed by user later
*
* Allocate osd_request and initialize all members to the
* default/initial state.
*/
-struct osd_request *osd_start_request(struct osd_dev *od, gfp_t gfp);
+struct osd_request *osd_start_request(struct osd_dev *od);
enum osd_req_options {
OSD_REQ_FUA = 0x08, /* Force Unit Access */
diff --git a/include/scsi/scsi_dbg.h b/include/scsi/scsi_dbg.h
index 04e0679..e03bd9d 100644
--- a/include/scsi/scsi_dbg.h
+++ b/include/scsi/scsi_dbg.h
@@ -11,8 +11,6 @@ struct scsi_sense_hdr;
extern void scsi_print_command(struct scsi_cmnd *);
extern size_t __scsi_format_command(char *, size_t,
const unsigned char *, size_t);
-extern void scsi_show_extd_sense(const struct scsi_device *, const char *,
- unsigned char, unsigned char);
extern void scsi_print_sense_hdr(const struct scsi_device *, const char *,
const struct scsi_sense_hdr *);
extern void scsi_print_sense(const struct scsi_cmnd *);
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 12f454c..53b485f 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -307,7 +307,7 @@ struct scsi_host_template {
* EH_HANDLED: I fixed the error, please complete the command
* EH_RESET_TIMER: I need more time, reset the timer and
* begin counting again
- * EH_NOT_HANDLED Begin normal error recovery
+ * EH_DONE: Begin normal error recovery
*
* Status: OPTIONAL
*/
diff --git a/include/soc/bcm2835/raspberrypi-firmware.h b/include/soc/bcm2835/raspberrypi-firmware.h
index 50df5b2..8ee8991 100644
--- a/include/soc/bcm2835/raspberrypi-firmware.h
+++ b/include/soc/bcm2835/raspberrypi-firmware.h
@@ -143,13 +143,13 @@ struct rpi_firmware *rpi_firmware_get(struct device_node *firmware_node);
static inline int rpi_firmware_property(struct rpi_firmware *fw, u32 tag,
void *data, size_t len)
{
- return 0;
+ return -ENOSYS;
}
static inline int rpi_firmware_property_list(struct rpi_firmware *fw,
void *data, size_t tag_size)
{
- return 0;
+ return -ENOSYS;
}
static inline struct rpi_firmware *rpi_firmware_get(struct device_node *firmware_node)
diff --git a/include/sound/control.h b/include/sound/control.h
index ca13a44..6011a58 100644
--- a/include/sound/control.h
+++ b/include/sound/control.h
@@ -23,6 +23,7 @@
*/
#include <linux/wait.h>
+#include <linux/nospec.h>
#include <sound/asound.h>
#define snd_kcontrol_chip(kcontrol) ((kcontrol)->private_data)
@@ -148,12 +149,14 @@ int snd_ctl_get_preferred_subdevice(struct snd_card *card, int type);
static inline unsigned int snd_ctl_get_ioffnum(struct snd_kcontrol *kctl, struct snd_ctl_elem_id *id)
{
- return id->numid - kctl->id.numid;
+ unsigned int ioff = id->numid - kctl->id.numid;
+ return array_index_nospec(ioff, kctl->count);
}
static inline unsigned int snd_ctl_get_ioffidx(struct snd_kcontrol *kctl, struct snd_ctl_elem_id *id)
{
- return id->index - kctl->id.index;
+ unsigned int ioff = id->index - kctl->id.index;
+ return array_index_nospec(ioff, kctl->count);
}
static inline unsigned int snd_ctl_get_ioff(struct snd_kcontrol *kctl, struct snd_ctl_elem_id *id)
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index f0820554..d0a341b 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -575,6 +575,48 @@ TRACE_EVENT(afs_protocol_error,
__entry->call, __entry->error, __entry->where)
);
+TRACE_EVENT(afs_cm_no_server,
+ TP_PROTO(struct afs_call *call, struct sockaddr_rxrpc *srx),
+
+ TP_ARGS(call, srx),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, call )
+ __field(unsigned int, op_id )
+ __field_struct(struct sockaddr_rxrpc, srx )
+ ),
+
+ TP_fast_assign(
+ __entry->call = call->debug_id;
+ __entry->op_id = call->operation_ID;
+ memcpy(&__entry->srx, srx, sizeof(__entry->srx));
+ ),
+
+ TP_printk("c=%08x op=%u %pISpc",
+ __entry->call, __entry->op_id, &__entry->srx.transport)
+ );
+
+TRACE_EVENT(afs_cm_no_server_u,
+ TP_PROTO(struct afs_call *call, const uuid_t *uuid),
+
+ TP_ARGS(call, uuid),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, call )
+ __field(unsigned int, op_id )
+ __field_struct(uuid_t, uuid )
+ ),
+
+ TP_fast_assign(
+ __entry->call = call->debug_id;
+ __entry->op_id = call->operation_ID;
+ memcpy(&__entry->uuid, uuid, sizeof(__entry->uuid));
+ ),
+
+ TP_printk("c=%08x op=%u %pU",
+ __entry->call, __entry->op_id, &__entry->uuid)
+ );
+
#endif /* _TRACE_AFS_H */
/* This part must be outside protection */
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 965c650..39b94ec 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -121,9 +121,9 @@ TRACE_EVENT(btrfs_transaction_commit,
__entry->root_objectid = root->root_key.objectid;
),
- TP_printk_btrfs("root = %llu(%s), gen = %llu",
+ TP_printk_btrfs("root=%llu(%s) gen=%llu",
show_root_type(__entry->root_objectid),
- (unsigned long long)__entry->generation)
+ __entry->generation)
);
DECLARE_EVENT_CLASS(btrfs__inode,
@@ -133,7 +133,7 @@ DECLARE_EVENT_CLASS(btrfs__inode,
TP_ARGS(inode),
TP_STRUCT__entry_btrfs(
- __field( ino_t, ino )
+ __field( u64, ino )
__field( blkcnt_t, blocks )
__field( u64, disk_i_size )
__field( u64, generation )
@@ -143,7 +143,7 @@ DECLARE_EVENT_CLASS(btrfs__inode,
),
TP_fast_assign_btrfs(btrfs_sb(inode->i_sb),
- __entry->ino = inode->i_ino;
+ __entry->ino = btrfs_ino(BTRFS_I(inode));
__entry->blocks = inode->i_blocks;
__entry->disk_i_size = BTRFS_I(inode)->disk_i_size;
__entry->generation = BTRFS_I(inode)->generation;
@@ -153,15 +153,15 @@ DECLARE_EVENT_CLASS(btrfs__inode,
BTRFS_I(inode)->root->root_key.objectid;
),
- TP_printk_btrfs("root=%llu(%s) gen=%llu ino=%lu blocks=%llu "
+ TP_printk_btrfs("root=%llu(%s) gen=%llu ino=%llu blocks=%llu "
"disk_i_size=%llu last_trans=%llu logged_trans=%llu",
show_root_type(__entry->root_objectid),
- (unsigned long long)__entry->generation,
- (unsigned long)__entry->ino,
+ __entry->generation,
+ __entry->ino,
(unsigned long long)__entry->blocks,
- (unsigned long long)__entry->disk_i_size,
- (unsigned long long)__entry->last_trans,
- (unsigned long long)__entry->logged_trans)
+ __entry->disk_i_size,
+ __entry->last_trans,
+ __entry->logged_trans)
);
DEFINE_EVENT(btrfs__inode, btrfs_inode_new,
@@ -244,23 +244,25 @@ TRACE_EVENT_CONDITION(btrfs_get_extent,
"block_len=%llu flags=%s refs=%u "
"compress_type=%u",
show_root_type(__entry->root_objectid),
- (unsigned long long)__entry->ino,
- (unsigned long long)__entry->start,
- (unsigned long long)__entry->len,
- (unsigned long long)__entry->orig_start,
+ __entry->ino,
+ __entry->start,
+ __entry->len,
+ __entry->orig_start,
show_map_type(__entry->block_start),
- (unsigned long long)__entry->block_len,
+ __entry->block_len,
show_map_flags(__entry->flags),
__entry->refs, __entry->compress_type)
);
TRACE_EVENT(btrfs_handle_em_exist,
- TP_PROTO(const struct extent_map *existing, const struct extent_map *map, u64 start, u64 len),
+ TP_PROTO(struct btrfs_fs_info *fs_info,
+ const struct extent_map *existing, const struct extent_map *map,
+ u64 start, u64 len),
- TP_ARGS(existing, map, start, len),
+ TP_ARGS(fs_info, existing, map, start, len),
- TP_STRUCT__entry(
+ TP_STRUCT__entry_btrfs(
__field( u64, e_start )
__field( u64, e_len )
__field( u64, map_start )
@@ -269,7 +271,7 @@ TRACE_EVENT(btrfs_handle_em_exist,
__field( u64, len )
),
- TP_fast_assign(
+ TP_fast_assign_btrfs(fs_info,
__entry->e_start = existing->start;
__entry->e_len = existing->len;
__entry->map_start = map->start;
@@ -278,15 +280,15 @@ TRACE_EVENT(btrfs_handle_em_exist,
__entry->len = len;
),
- TP_printk("start=%llu len=%llu "
+ TP_printk_btrfs("start=%llu len=%llu "
"existing(start=%llu len=%llu) "
"em(start=%llu len=%llu)",
- (unsigned long long)__entry->start,
- (unsigned long long)__entry->len,
- (unsigned long long)__entry->e_start,
- (unsigned long long)__entry->e_len,
- (unsigned long long)__entry->map_start,
- (unsigned long long)__entry->map_len)
+ __entry->start,
+ __entry->len,
+ __entry->e_start,
+ __entry->e_len,
+ __entry->map_start,
+ __entry->map_len)
);
/* file extent item */
@@ -443,7 +445,7 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent,
TP_ARGS(inode, ordered),
TP_STRUCT__entry_btrfs(
- __field( ino_t, ino )
+ __field( u64, ino )
__field( u64, file_offset )
__field( u64, start )
__field( u64, len )
@@ -457,7 +459,7 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent,
),
TP_fast_assign_btrfs(btrfs_sb(inode->i_sb),
- __entry->ino = inode->i_ino;
+ __entry->ino = btrfs_ino(BTRFS_I(inode));
__entry->file_offset = ordered->file_offset;
__entry->start = ordered->start;
__entry->len = ordered->len;
@@ -477,13 +479,13 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent,
"bytes_left=%llu flags=%s compress_type=%d "
"refs=%d",
show_root_type(__entry->root_objectid),
- (unsigned long long)__entry->ino,
- (unsigned long long)__entry->file_offset,
- (unsigned long long)__entry->start,
- (unsigned long long)__entry->len,
- (unsigned long long)__entry->disk_len,
- (unsigned long long)__entry->truncated_len,
- (unsigned long long)__entry->bytes_left,
+ __entry->ino,
+ __entry->file_offset,
+ __entry->start,
+ __entry->len,
+ __entry->disk_len,
+ __entry->truncated_len,
+ __entry->bytes_left,
show_ordered_flags(__entry->flags),
__entry->compress_type, __entry->refs)
);
@@ -528,7 +530,7 @@ DECLARE_EVENT_CLASS(btrfs__writepage,
TP_ARGS(page, inode, wbc),
TP_STRUCT__entry_btrfs(
- __field( ino_t, ino )
+ __field( u64, ino )
__field( pgoff_t, index )
__field( long, nr_to_write )
__field( long, pages_skipped )
@@ -542,7 +544,7 @@ DECLARE_EVENT_CLASS(btrfs__writepage,
),
TP_fast_assign_btrfs(btrfs_sb(inode->i_sb),
- __entry->ino = inode->i_ino;
+ __entry->ino = btrfs_ino(BTRFS_I(inode));
__entry->index = page->index;
__entry->nr_to_write = wbc->nr_to_write;
__entry->pages_skipped = wbc->pages_skipped;
@@ -556,12 +558,12 @@ DECLARE_EVENT_CLASS(btrfs__writepage,
BTRFS_I(inode)->root->root_key.objectid;
),
- TP_printk_btrfs("root=%llu(%s) ino=%lu page_index=%lu "
+ TP_printk_btrfs("root=%llu(%s) ino=%llu page_index=%lu "
"nr_to_write=%ld pages_skipped=%ld range_start=%llu "
"range_end=%llu for_kupdate=%d "
"for_reclaim=%d range_cyclic=%d writeback_index=%lu",
show_root_type(__entry->root_objectid),
- (unsigned long)__entry->ino, __entry->index,
+ __entry->ino, __entry->index,
__entry->nr_to_write, __entry->pages_skipped,
__entry->range_start, __entry->range_end,
__entry->for_kupdate,
@@ -584,7 +586,7 @@ TRACE_EVENT(btrfs_writepage_end_io_hook,
TP_ARGS(page, start, end, uptodate),
TP_STRUCT__entry_btrfs(
- __field( ino_t, ino )
+ __field( u64, ino )
__field( pgoff_t, index )
__field( u64, start )
__field( u64, end )
@@ -593,7 +595,7 @@ TRACE_EVENT(btrfs_writepage_end_io_hook,
),
TP_fast_assign_btrfs(btrfs_sb(page->mapping->host->i_sb),
- __entry->ino = page->mapping->host->i_ino;
+ __entry->ino = btrfs_ino(BTRFS_I(page->mapping->host));
__entry->index = page->index;
__entry->start = start;
__entry->end = end;
@@ -602,12 +604,12 @@ TRACE_EVENT(btrfs_writepage_end_io_hook,
BTRFS_I(page->mapping->host)->root->root_key.objectid;
),
- TP_printk_btrfs("root=%llu(%s) ino=%lu page_index=%lu start=%llu "
+ TP_printk_btrfs("root=%llu(%s) ino=%llu page_index=%lu start=%llu "
"end=%llu uptodate=%d",
show_root_type(__entry->root_objectid),
- (unsigned long)__entry->ino, (unsigned long)__entry->index,
- (unsigned long long)__entry->start,
- (unsigned long long)__entry->end, __entry->uptodate)
+ __entry->ino, (unsigned long)__entry->index,
+ __entry->start,
+ __entry->end, __entry->uptodate)
);
TRACE_EVENT(btrfs_sync_file,
@@ -617,8 +619,8 @@ TRACE_EVENT(btrfs_sync_file,
TP_ARGS(file, datasync),
TP_STRUCT__entry_btrfs(
- __field( ino_t, ino )
- __field( ino_t, parent )
+ __field( u64, ino )
+ __field( u64, parent )
__field( int, datasync )
__field( u64, root_objectid )
),
@@ -628,16 +630,17 @@ TRACE_EVENT(btrfs_sync_file,
const struct inode *inode = d_inode(dentry);
TP_fast_assign_fsid(btrfs_sb(file->f_path.dentry->d_sb));
- __entry->ino = inode->i_ino;
- __entry->parent = d_inode(dentry->d_parent)->i_ino;
+ __entry->ino = btrfs_ino(BTRFS_I(inode));
+ __entry->parent = btrfs_ino(BTRFS_I(d_inode(dentry->d_parent)));
__entry->datasync = datasync;
__entry->root_objectid =
BTRFS_I(inode)->root->root_key.objectid;
),
- TP_printk_btrfs("root=%llu(%s) ino=%ld parent=%ld datasync=%d",
+ TP_printk_btrfs("root=%llu(%s) ino=%llu parent=%llu datasync=%d",
show_root_type(__entry->root_objectid),
- (unsigned long)__entry->ino, (unsigned long)__entry->parent,
+ __entry->ino,
+ __entry->parent,
__entry->datasync)
);
@@ -655,7 +658,7 @@ TRACE_EVENT(btrfs_sync_fs,
__entry->wait = wait;
),
- TP_printk_btrfs("wait = %d", __entry->wait)
+ TP_printk_btrfs("wait=%d", __entry->wait)
);
TRACE_EVENT(btrfs_add_block_group,
@@ -665,8 +668,7 @@ TRACE_EVENT(btrfs_add_block_group,
TP_ARGS(fs_info, block_group, create),
- TP_STRUCT__entry(
- __array( u8, fsid, BTRFS_FSID_SIZE )
+ TP_STRUCT__entry_btrfs(
__field( u64, offset )
__field( u64, size )
__field( u64, flags )
@@ -675,8 +677,7 @@ TRACE_EVENT(btrfs_add_block_group,
__field( int, create )
),
- TP_fast_assign(
- memcpy(__entry->fsid, fs_info->fsid, BTRFS_FSID_SIZE);
+ TP_fast_assign_btrfs(fs_info,
__entry->offset = block_group->key.objectid;
__entry->size = block_group->key.offset;
__entry->flags = block_group->flags;
@@ -686,16 +687,16 @@ TRACE_EVENT(btrfs_add_block_group,
__entry->create = create;
),
- TP_printk("%pU: block_group offset=%llu size=%llu "
+ TP_printk_btrfs("block_group offset=%llu size=%llu "
"flags=%llu(%s) bytes_used=%llu bytes_super=%llu "
- "create=%d", __entry->fsid,
- (unsigned long long)__entry->offset,
- (unsigned long long)__entry->size,
- (unsigned long long)__entry->flags,
+ "create=%d",
+ __entry->offset,
+ __entry->size,
+ __entry->flags,
__print_flags((unsigned long)__entry->flags, "|",
BTRFS_GROUP_FLAGS),
- (unsigned long long)__entry->bytes_used,
- (unsigned long long)__entry->bytes_super, __entry->create)
+ __entry->bytes_used,
+ __entry->bytes_super, __entry->create)
);
#define show_ref_action(action) \
@@ -740,13 +741,13 @@ DECLARE_EVENT_CLASS(btrfs_delayed_tree_ref,
TP_printk_btrfs("bytenr=%llu num_bytes=%llu action=%s "
"parent=%llu(%s) ref_root=%llu(%s) level=%d "
"type=%s seq=%llu",
- (unsigned long long)__entry->bytenr,
- (unsigned long long)__entry->num_bytes,
+ __entry->bytenr,
+ __entry->num_bytes,
show_ref_action(__entry->action),
show_root_type(__entry->parent),
show_root_type(__entry->ref_root),
__entry->level, show_ref_type(__entry->type),
- (unsigned long long)__entry->seq)
+ __entry->seq)
);
DEFINE_EVENT(btrfs_delayed_tree_ref, add_delayed_tree_ref,
@@ -805,15 +806,15 @@ DECLARE_EVENT_CLASS(btrfs_delayed_data_ref,
TP_printk_btrfs("bytenr=%llu num_bytes=%llu action=%s "
"parent=%llu(%s) ref_root=%llu(%s) owner=%llu "
"offset=%llu type=%s seq=%llu",
- (unsigned long long)__entry->bytenr,
- (unsigned long long)__entry->num_bytes,
+ __entry->bytenr,
+ __entry->num_bytes,
show_ref_action(__entry->action),
show_root_type(__entry->parent),
show_root_type(__entry->ref_root),
- (unsigned long long)__entry->owner,
- (unsigned long long)__entry->offset,
+ __entry->owner,
+ __entry->offset,
show_ref_type(__entry->type),
- (unsigned long long)__entry->seq)
+ __entry->seq)
);
DEFINE_EVENT(btrfs_delayed_data_ref, add_delayed_data_ref,
@@ -859,8 +860,8 @@ DECLARE_EVENT_CLASS(btrfs_delayed_ref_head,
),
TP_printk_btrfs("bytenr=%llu num_bytes=%llu action=%s is_data=%d",
- (unsigned long long)__entry->bytenr,
- (unsigned long long)__entry->num_bytes,
+ __entry->bytenr,
+ __entry->num_bytes,
show_ref_action(__entry->action),
__entry->is_data)
);
@@ -923,8 +924,8 @@ DECLARE_EVENT_CLASS(btrfs__chunk,
TP_printk_btrfs("root=%llu(%s) offset=%llu size=%llu "
"num_stripes=%d sub_stripes=%d type=%s",
show_root_type(__entry->root_objectid),
- (unsigned long long)__entry->offset,
- (unsigned long long)__entry->size,
+ __entry->offset,
+ __entry->size,
__entry->num_stripes, __entry->sub_stripes,
show_chunk_type(__entry->type))
);
@@ -974,9 +975,9 @@ TRACE_EVENT(btrfs_cow_block,
"(orig_level=%d) cow_buf=%llu (cow_level=%d)",
show_root_type(__entry->root_objectid),
__entry->refs,
- (unsigned long long)__entry->buf_start,
+ __entry->buf_start,
__entry->buf_level,
- (unsigned long long)__entry->cow_start,
+ __entry->cow_start,
__entry->cow_level)
);
@@ -1001,7 +1002,7 @@ TRACE_EVENT(btrfs_space_reservation,
__entry->reserve = reserve;
),
- TP_printk_btrfs("%s: %Lu %s %Lu", __get_str(type), __entry->val,
+ TP_printk_btrfs("%s: %llu %s %llu", __get_str(type), __entry->val,
__entry->reserve ? "reserve" : "release",
__entry->bytes)
);
@@ -1019,29 +1020,27 @@ TRACE_EVENT(btrfs_trigger_flush,
TP_ARGS(fs_info, flags, bytes, flush, reason),
- TP_STRUCT__entry(
- __array( u8, fsid, BTRFS_FSID_SIZE )
+ TP_STRUCT__entry_btrfs(
__field( u64, flags )
__field( u64, bytes )
__field( int, flush )
__string( reason, reason )
),
- TP_fast_assign(
- memcpy(__entry->fsid, fs_info->fsid, BTRFS_FSID_SIZE);
+ TP_fast_assign_btrfs(fs_info,
__entry->flags = flags;
__entry->bytes = bytes;
__entry->flush = flush;
__assign_str(reason, reason)
),
- TP_printk("%pU: %s: flush=%d(%s) flags=%llu(%s) bytes=%llu",
- __entry->fsid, __get_str(reason), __entry->flush,
+ TP_printk_btrfs("%s: flush=%d(%s) flags=%llu(%s) bytes=%llu",
+ __get_str(reason), __entry->flush,
show_flush_action(__entry->flush),
- (unsigned long long)__entry->flags,
+ __entry->flags,
__print_flags((unsigned long)__entry->flags, "|",
BTRFS_GROUP_FLAGS),
- (unsigned long long)__entry->bytes)
+ __entry->bytes)
);
#define show_flush_state(state) \
@@ -1060,29 +1059,27 @@ TRACE_EVENT(btrfs_flush_space,
TP_ARGS(fs_info, flags, num_bytes, state, ret),
- TP_STRUCT__entry(
- __array( u8, fsid, BTRFS_FSID_SIZE )
+ TP_STRUCT__entry_btrfs(
__field( u64, flags )
__field( u64, num_bytes )
__field( int, state )
__field( int, ret )
),
- TP_fast_assign(
- memcpy(__entry->fsid, fs_info->fsid, BTRFS_FSID_SIZE);
+ TP_fast_assign_btrfs(fs_info,
__entry->flags = flags;
__entry->num_bytes = num_bytes;
__entry->state = state;
__entry->ret = ret;
),
- TP_printk("%pU: state=%d(%s) flags=%llu(%s) num_bytes=%llu ret=%d",
- __entry->fsid, __entry->state,
+ TP_printk_btrfs("state=%d(%s) flags=%llu(%s) num_bytes=%llu ret=%d",
+ __entry->state,
show_flush_state(__entry->state),
- (unsigned long long)__entry->flags,
+ __entry->flags,
__print_flags((unsigned long)__entry->flags, "|",
BTRFS_GROUP_FLAGS),
- (unsigned long long)__entry->num_bytes, __entry->ret)
+ __entry->num_bytes, __entry->ret)
);
DECLARE_EVENT_CLASS(btrfs__reserved_extent,
@@ -1103,8 +1100,8 @@ DECLARE_EVENT_CLASS(btrfs__reserved_extent,
TP_printk_btrfs("root=%llu(%s) start=%llu len=%llu",
show_root_type(BTRFS_EXTENT_TREE_OBJECTID),
- (unsigned long long)__entry->start,
- (unsigned long long)__entry->len)
+ __entry->start,
+ __entry->len)
);
DEFINE_EVENT(btrfs__reserved_extent, btrfs_reserved_extent_alloc,
@@ -1140,7 +1137,7 @@ TRACE_EVENT(find_free_extent,
__entry->data = data;
),
- TP_printk_btrfs("root=%Lu(%s) len=%Lu empty_size=%Lu flags=%Lu(%s)",
+ TP_printk_btrfs("root=%llu(%s) len=%llu empty_size=%llu flags=%llu(%s)",
show_root_type(BTRFS_EXTENT_TREE_OBJECTID),
__entry->num_bytes, __entry->empty_size, __entry->data,
__print_flags((unsigned long)__entry->data, "|",
@@ -1149,11 +1146,10 @@ TRACE_EVENT(find_free_extent,
DECLARE_EVENT_CLASS(btrfs__reserve_extent,
- TP_PROTO(const struct btrfs_fs_info *fs_info,
- const struct btrfs_block_group_cache *block_group, u64 start,
+ TP_PROTO(const struct btrfs_block_group_cache *block_group, u64 start,
u64 len),
- TP_ARGS(fs_info, block_group, start, len),
+ TP_ARGS(block_group, start, len),
TP_STRUCT__entry_btrfs(
__field( u64, bg_objectid )
@@ -1162,15 +1158,15 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent,
__field( u64, len )
),
- TP_fast_assign_btrfs(fs_info,
+ TP_fast_assign_btrfs(block_group->fs_info,
__entry->bg_objectid = block_group->key.objectid;
__entry->flags = block_group->flags;
__entry->start = start;
__entry->len = len;
),
- TP_printk_btrfs("root=%Lu(%s) block_group=%Lu flags=%Lu(%s) "
- "start=%Lu len=%Lu",
+ TP_printk_btrfs("root=%llu(%s) block_group=%llu flags=%llu(%s) "
+ "start=%llu len=%llu",
show_root_type(BTRFS_EXTENT_TREE_OBJECTID),
__entry->bg_objectid,
__entry->flags, __print_flags((unsigned long)__entry->flags,
@@ -1180,20 +1176,18 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent,
DEFINE_EVENT(btrfs__reserve_extent, btrfs_reserve_extent,
- TP_PROTO(const struct btrfs_fs_info *fs_info,
- const struct btrfs_block_group_cache *block_group, u64 start,
+ TP_PROTO(const struct btrfs_block_group_cache *block_group, u64 start,
u64 len),
- TP_ARGS(fs_info, block_group, start, len)
+ TP_ARGS(block_group, start, len)
);
DEFINE_EVENT(btrfs__reserve_extent, btrfs_reserve_extent_cluster,
- TP_PROTO(const struct btrfs_fs_info *fs_info,
- const struct btrfs_block_group_cache *block_group, u64 start,
+ TP_PROTO(const struct btrfs_block_group_cache *block_group, u64 start,
u64 len),
- TP_ARGS(fs_info, block_group, start, len)
+ TP_ARGS(block_group, start, len)
);
TRACE_EVENT(btrfs_find_cluster,
@@ -1221,8 +1215,8 @@ TRACE_EVENT(btrfs_find_cluster,
__entry->min_bytes = min_bytes;
),
- TP_printk_btrfs("block_group=%Lu flags=%Lu(%s) start=%Lu len=%Lu "
- "empty_size=%Lu min_bytes=%Lu", __entry->bg_objectid,
+ TP_printk_btrfs("block_group=%llu flags=%llu(%s) start=%llu len=%llu "
+ "empty_size=%llu min_bytes=%llu", __entry->bg_objectid,
__entry->flags,
__print_flags((unsigned long)__entry->flags, "|",
BTRFS_GROUP_FLAGS), __entry->start,
@@ -1243,7 +1237,7 @@ TRACE_EVENT(btrfs_failed_cluster_setup,
__entry->bg_objectid = block_group->key.objectid;
),
- TP_printk_btrfs("block_group=%Lu", __entry->bg_objectid)
+ TP_printk_btrfs("block_group=%llu", __entry->bg_objectid)
);
TRACE_EVENT(btrfs_setup_cluster,
@@ -1272,8 +1266,8 @@ TRACE_EVENT(btrfs_setup_cluster,
__entry->bitmap = bitmap;
),
- TP_printk_btrfs("block_group=%Lu flags=%Lu(%s) window_start=%Lu "
- "size=%Lu max_size=%Lu bitmap=%d",
+ TP_printk_btrfs("block_group=%llu flags=%llu(%s) window_start=%llu "
+ "size=%llu max_size=%llu bitmap=%d",
__entry->bg_objectid,
__entry->flags,
__print_flags((unsigned long)__entry->flags, "|",
@@ -1476,7 +1470,7 @@ DECLARE_EVENT_CLASS(btrfs__qgroup_rsv_data,
TP_STRUCT__entry_btrfs(
__field( u64, rootid )
- __field( unsigned long, ino )
+ __field( u64, ino )
__field( u64, start )
__field( u64, len )
__field( u64, reserved )
@@ -1485,14 +1479,14 @@ DECLARE_EVENT_CLASS(btrfs__qgroup_rsv_data,
TP_fast_assign_btrfs(btrfs_sb(inode->i_sb),
__entry->rootid = BTRFS_I(inode)->root->objectid;
- __entry->ino = inode->i_ino;
+ __entry->ino = btrfs_ino(BTRFS_I(inode));
__entry->start = start;
__entry->len = len;
__entry->reserved = reserved;
__entry->op = op;
),
- TP_printk_btrfs("root=%llu ino=%lu start=%llu len=%llu reserved=%llu op=%s",
+ TP_printk_btrfs("root=%llu ino=%llu start=%llu len=%llu reserved=%llu op=%s",
__entry->rootid, __entry->ino, __entry->start, __entry->len,
__entry->reserved,
__print_flags((unsigned long)__entry->op, "",
@@ -1584,12 +1578,14 @@ DEFINE_EVENT(btrfs_qgroup_extent, btrfs_qgroup_trace_extent,
TRACE_EVENT(btrfs_qgroup_account_extent,
- TP_PROTO(const struct btrfs_fs_info *fs_info, u64 bytenr,
+ TP_PROTO(const struct btrfs_fs_info *fs_info, u64 transid, u64 bytenr,
u64 num_bytes, u64 nr_old_roots, u64 nr_new_roots),
- TP_ARGS(fs_info, bytenr, num_bytes, nr_old_roots, nr_new_roots),
+ TP_ARGS(fs_info, transid, bytenr, num_bytes, nr_old_roots,
+ nr_new_roots),
TP_STRUCT__entry_btrfs(
+ __field( u64, transid )
__field( u64, bytenr )
__field( u64, num_bytes )
__field( u64, nr_old_roots )
@@ -1597,43 +1593,49 @@ TRACE_EVENT(btrfs_qgroup_account_extent,
),
TP_fast_assign_btrfs(fs_info,
+ __entry->transid = transid;
__entry->bytenr = bytenr;
__entry->num_bytes = num_bytes;
__entry->nr_old_roots = nr_old_roots;
__entry->nr_new_roots = nr_new_roots;
),
- TP_printk_btrfs("bytenr=%llu num_bytes=%llu nr_old_roots=%llu "
- "nr_new_roots=%llu",
- __entry->bytenr,
- __entry->num_bytes,
- __entry->nr_old_roots,
- __entry->nr_new_roots)
+ TP_printk_btrfs(
+"transid=%llu bytenr=%llu num_bytes=%llu nr_old_roots=%llu nr_new_roots=%llu",
+ __entry->transid,
+ __entry->bytenr,
+ __entry->num_bytes,
+ __entry->nr_old_roots,
+ __entry->nr_new_roots)
);
TRACE_EVENT(qgroup_update_counters,
- TP_PROTO(const struct btrfs_fs_info *fs_info, u64 qgid,
+ TP_PROTO(const struct btrfs_fs_info *fs_info,
+ struct btrfs_qgroup *qgroup,
u64 cur_old_count, u64 cur_new_count),
- TP_ARGS(fs_info, qgid, cur_old_count, cur_new_count),
+ TP_ARGS(fs_info, qgroup, cur_old_count, cur_new_count),
TP_STRUCT__entry_btrfs(
__field( u64, qgid )
+ __field( u64, old_rfer )
+ __field( u64, old_excl )
__field( u64, cur_old_count )
__field( u64, cur_new_count )
),
TP_fast_assign_btrfs(fs_info,
- __entry->qgid = qgid;
+ __entry->qgid = qgroup->qgroupid;
+ __entry->old_rfer = qgroup->rfer;
+ __entry->old_excl = qgroup->excl;
__entry->cur_old_count = cur_old_count;
__entry->cur_new_count = cur_new_count;
),
- TP_printk_btrfs("qgid=%llu cur_old_count=%llu cur_new_count=%llu",
- __entry->qgid,
- __entry->cur_old_count,
- __entry->cur_new_count)
+ TP_printk_btrfs("qgid=%llu old_rfer=%llu old_excl=%llu cur_old_count=%llu cur_new_count=%llu",
+ __entry->qgid, __entry->old_rfer, __entry->old_excl,
+ __entry->cur_old_count, __entry->cur_new_count)
);
TRACE_EVENT(qgroup_update_reserve,
@@ -1765,14 +1767,14 @@ DECLARE_EVENT_CLASS(btrfs__prelim_ref,
),
TP_printk_btrfs("root_id=%llu key=[%llu,%u,%llu] level=%d count=[%d+%d=%d] parent=%llu wanted_disk_byte=%llu nodes=%llu",
- (unsigned long long)__entry->root_id,
- (unsigned long long)__entry->objectid, __entry->type,
- (unsigned long long)__entry->offset, __entry->level,
+ __entry->root_id,
+ __entry->objectid, __entry->type,
+ __entry->offset, __entry->level,
__entry->old_count, __entry->mod_count,
__entry->old_count + __entry->mod_count,
- (unsigned long long)__entry->parent,
- (unsigned long long)__entry->bytenr,
- (unsigned long long)__entry->tree_size)
+ __entry->parent,
+ __entry->bytenr,
+ __entry->tree_size)
);
DEFINE_EVENT(btrfs__prelim_ref, btrfs_prelim_ref_merge,
@@ -1808,8 +1810,51 @@ TRACE_EVENT(btrfs_inode_mod_outstanding_extents,
TP_printk_btrfs("root=%llu(%s) ino=%llu mod=%d",
show_root_type(__entry->root_objectid),
- (unsigned long long)__entry->ino, __entry->mod)
+ __entry->ino, __entry->mod)
);
+
+DECLARE_EVENT_CLASS(btrfs__block_group,
+ TP_PROTO(const struct btrfs_block_group_cache *bg_cache),
+
+ TP_ARGS(bg_cache),
+
+ TP_STRUCT__entry_btrfs(
+ __field( u64, bytenr )
+ __field( u64, len )
+ __field( u64, used )
+ __field( u64, flags )
+ ),
+
+ TP_fast_assign_btrfs(bg_cache->fs_info,
+ __entry->bytenr = bg_cache->key.objectid,
+ __entry->len = bg_cache->key.offset,
+ __entry->used = btrfs_block_group_used(&bg_cache->item);
+ __entry->flags = bg_cache->flags;
+ ),
+
+ TP_printk_btrfs("bg bytenr=%llu len=%llu used=%llu flags=%llu(%s)",
+ __entry->bytenr, __entry->len, __entry->used, __entry->flags,
+ __print_flags(__entry->flags, "|", BTRFS_GROUP_FLAGS))
+);
+
+DEFINE_EVENT(btrfs__block_group, btrfs_remove_block_group,
+ TP_PROTO(const struct btrfs_block_group_cache *bg_cache),
+
+ TP_ARGS(bg_cache)
+);
+
+DEFINE_EVENT(btrfs__block_group, btrfs_add_unused_block_group,
+ TP_PROTO(const struct btrfs_block_group_cache *bg_cache),
+
+ TP_ARGS(bg_cache)
+);
+
+DEFINE_EVENT(btrfs__block_group, btrfs_skip_unused_block_group,
+ TP_PROTO(const struct btrfs_block_group_cache *bg_cache),
+
+ TP_ARGS(bg_cache)
+);
+
#endif /* _TRACE_BTRFS_H */
/* This part must be outside protection */
diff --git a/include/trace/events/initcall.h b/include/trace/events/initcall.h
index 8d6cf10..eb903c3 100644
--- a/include/trace/events/initcall.h
+++ b/include/trace/events/initcall.h
@@ -31,7 +31,11 @@ TRACE_EVENT(initcall_start,
TP_ARGS(func),
TP_STRUCT__entry(
- __field(initcall_t, func)
+ /*
+ * Use field_struct to avoid is_signed_type()
+ * comparison of a function pointer
+ */
+ __field_struct(initcall_t, func)
),
TP_fast_assign(
@@ -48,8 +52,12 @@ TRACE_EVENT(initcall_finish,
TP_ARGS(func, ret),
TP_STRUCT__entry(
- __field(initcall_t, func)
- __field(int, ret)
+ /*
+ * Use field_struct to avoid is_signed_type()
+ * comparison of a function pointer
+ */
+ __field_struct(initcall_t, func)
+ __field(int, ret)
),
TP_fast_assign(
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index d8c3329..5936aac 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -84,20 +84,21 @@ TRACE_EVENT(rcu_grace_period,
);
/*
- * Tracepoint for future grace-period events, including those for no-callbacks
- * CPUs. The caller should pull the data from the rcu_node structure,
- * other than rcuname, which comes from the rcu_state structure, and event,
- * which is one of the following:
+ * Tracepoint for future grace-period events. The caller should pull
+ * the data from the rcu_node structure, other than rcuname, which comes
+ * from the rcu_state structure, and event, which is one of the following:
*
- * "Startleaf": Request a nocb grace period based on leaf-node data.
+ * "Startleaf": Request a grace period based on leaf-node data.
+ * "Prestarted": Someone beat us to the request
* "Startedleaf": Leaf-node start proved sufficient.
* "Startedleafroot": Leaf-node start proved sufficient after checking root.
* "Startedroot": Requested a nocb grace period based on root-node data.
+ * "NoGPkthread": The RCU grace-period kthread has not yet started.
* "StartWait": Start waiting for the requested grace period.
* "ResumeWait": Resume waiting after signal.
* "EndWait": Complete wait.
* "Cleanup": Clean up rcu_node structure after previous GP.
- * "CleanupMore": Clean up, and another no-CB GP is needed.
+ * "CleanupMore": Clean up, and another GP is needed.
*/
TRACE_EVENT(rcu_future_grace_period,
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 9e96c2f..077e664 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -15,6 +15,7 @@
#define _TRACE_RXRPC_H
#include <linux/tracepoint.h>
+#include <linux/errqueue.h>
/*
* Define enums for tracing information.
@@ -210,6 +211,20 @@ enum rxrpc_congest_change {
rxrpc_cong_saw_nack,
};
+enum rxrpc_tx_fail_trace {
+ rxrpc_tx_fail_call_abort,
+ rxrpc_tx_fail_call_ack,
+ rxrpc_tx_fail_call_data_frag,
+ rxrpc_tx_fail_call_data_nofrag,
+ rxrpc_tx_fail_call_final_resend,
+ rxrpc_tx_fail_conn_abort,
+ rxrpc_tx_fail_conn_challenge,
+ rxrpc_tx_fail_conn_response,
+ rxrpc_tx_fail_reject,
+ rxrpc_tx_fail_version_keepalive,
+ rxrpc_tx_fail_version_reply,
+};
+
#endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */
/*
@@ -437,6 +452,19 @@ enum rxrpc_congest_change {
EM(RXRPC_CALL_LOCAL_ERROR, "LocalError") \
E_(RXRPC_CALL_NETWORK_ERROR, "NetError")
+#define rxrpc_tx_fail_traces \
+ EM(rxrpc_tx_fail_call_abort, "CallAbort") \
+ EM(rxrpc_tx_fail_call_ack, "CallAck") \
+ EM(rxrpc_tx_fail_call_data_frag, "CallDataFrag") \
+ EM(rxrpc_tx_fail_call_data_nofrag, "CallDataNofrag") \
+ EM(rxrpc_tx_fail_call_final_resend, "CallFinalResend") \
+ EM(rxrpc_tx_fail_conn_abort, "ConnAbort") \
+ EM(rxrpc_tx_fail_conn_challenge, "ConnChall") \
+ EM(rxrpc_tx_fail_conn_response, "ConnResp") \
+ EM(rxrpc_tx_fail_reject, "Reject") \
+ EM(rxrpc_tx_fail_version_keepalive, "VerKeepalive") \
+ E_(rxrpc_tx_fail_version_reply, "VerReply")
+
/*
* Export enum symbols via userspace.
*/
@@ -460,6 +488,7 @@ rxrpc_propose_ack_traces;
rxrpc_propose_ack_outcomes;
rxrpc_congest_modes;
rxrpc_congest_changes;
+rxrpc_tx_fail_traces;
/*
* Now redefine the EM() and E_() macros to map the enums to the strings that
@@ -1374,6 +1403,62 @@ TRACE_EVENT(rxrpc_resend,
__entry->anno)
);
+TRACE_EVENT(rxrpc_rx_icmp,
+ TP_PROTO(struct rxrpc_peer *peer, struct sock_extended_err *ee,
+ struct sockaddr_rxrpc *srx),
+
+ TP_ARGS(peer, ee, srx),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, peer )
+ __field_struct(struct sock_extended_err, ee )
+ __field_struct(struct sockaddr_rxrpc, srx )
+ ),
+
+ TP_fast_assign(
+ __entry->peer = peer->debug_id;
+ memcpy(&__entry->ee, ee, sizeof(__entry->ee));
+ memcpy(&__entry->srx, srx, sizeof(__entry->srx));
+ ),
+
+ TP_printk("P=%08x o=%u t=%u c=%u i=%u d=%u e=%d %pISp",
+ __entry->peer,
+ __entry->ee.ee_origin,
+ __entry->ee.ee_type,
+ __entry->ee.ee_code,
+ __entry->ee.ee_info,
+ __entry->ee.ee_data,
+ __entry->ee.ee_errno,
+ &__entry->srx.transport)
+ );
+
+TRACE_EVENT(rxrpc_tx_fail,
+ TP_PROTO(unsigned int debug_id, rxrpc_serial_t serial, int ret,
+ enum rxrpc_tx_fail_trace what),
+
+ TP_ARGS(debug_id, serial, ret, what),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, debug_id )
+ __field(rxrpc_serial_t, serial )
+ __field(int, ret )
+ __field(enum rxrpc_tx_fail_trace, what )
+ ),
+
+ TP_fast_assign(
+ __entry->debug_id = debug_id;
+ __entry->serial = serial;
+ __entry->ret = ret;
+ __entry->what = what;
+ ),
+
+ TP_printk("c=%08x r=%x ret=%d %s",
+ __entry->debug_id,
+ __entry->serial,
+ __entry->ret,
+ __print_symbolic(__entry->what, rxrpc_tx_fail_traces))
+ );
+
#endif /* _TRACE_RXRPC_H */
/* This part must be outside protection */
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index bc01e06..0be866c 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -435,7 +435,9 @@ TRACE_EVENT(sched_pi_setprio,
memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
__entry->pid = tsk->pid;
__entry->oldprio = tsk->prio;
- __entry->newprio = pi_task ? pi_task->prio : tsk->prio;
+ __entry->newprio = pi_task ?
+ min(tsk->normal_prio, pi_task->prio) :
+ tsk->normal_prio;
/* XXX SCHED_DEADLINE bits missing */
),
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 335d872..bbb08a3 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -224,6 +224,8 @@ TRACE_EVENT(rpc_stats_latency,
TP_ARGS(task, backlog, rtt, execute),
TP_STRUCT__entry(
+ __field(unsigned int, task_id)
+ __field(unsigned int, client_id)
__field(u32, xid)
__field(int, version)
__string(progname, task->tk_client->cl_program->name)
@@ -231,13 +233,11 @@ TRACE_EVENT(rpc_stats_latency,
__field(unsigned long, backlog)
__field(unsigned long, rtt)
__field(unsigned long, execute)
- __string(addr,
- task->tk_xprt->address_strings[RPC_DISPLAY_ADDR])
- __string(port,
- task->tk_xprt->address_strings[RPC_DISPLAY_PORT])
),
TP_fast_assign(
+ __entry->client_id = task->tk_client->cl_clid;
+ __entry->task_id = task->tk_pid;
__entry->xid = be32_to_cpu(task->tk_rqstp->rq_xid);
__entry->version = task->tk_client->cl_vers;
__assign_str(progname, task->tk_client->cl_program->name)
@@ -245,14 +245,10 @@ TRACE_EVENT(rpc_stats_latency,
__entry->backlog = ktime_to_us(backlog);
__entry->rtt = ktime_to_us(rtt);
__entry->execute = ktime_to_us(execute);
- __assign_str(addr,
- task->tk_xprt->address_strings[RPC_DISPLAY_ADDR]);
- __assign_str(port,
- task->tk_xprt->address_strings[RPC_DISPLAY_PORT]);
),
- TP_printk("peer=[%s]:%s xid=0x%08x %sv%d %s backlog=%lu rtt=%lu execute=%lu",
- __get_str(addr), __get_str(port), __entry->xid,
+ TP_printk("task:%u@%d xid=0x%08x %sv%d %s backlog=%lu rtt=%lu execute=%lu",
+ __entry->task_id, __entry->client_id, __entry->xid,
__get_str(progname), __entry->version, __get_str(procname),
__entry->backlog, __entry->rtt, __entry->execute)
);
diff --git a/include/trace/events/ufs.h b/include/trace/events/ufs.h
index bf6f826..f8260e5 100644
--- a/include/trace/events/ufs.h
+++ b/include/trace/events/ufs.h
@@ -257,6 +257,33 @@ TRACE_EVENT(ufshcd_command,
)
);
+TRACE_EVENT(ufshcd_upiu,
+ TP_PROTO(const char *dev_name, const char *str, void *hdr, void *tsf),
+
+ TP_ARGS(dev_name, str, hdr, tsf),
+
+ TP_STRUCT__entry(
+ __string(dev_name, dev_name)
+ __string(str, str)
+ __array(unsigned char, hdr, 12)
+ __array(unsigned char, tsf, 16)
+ ),
+
+ TP_fast_assign(
+ __assign_str(dev_name, dev_name);
+ __assign_str(str, str);
+ memcpy(__entry->hdr, hdr, sizeof(__entry->hdr));
+ memcpy(__entry->tsf, tsf, sizeof(__entry->tsf));
+ ),
+
+ TP_printk(
+ "%s: %s: HDR:%s, CDB:%s",
+ __get_str(str), __get_str(dev_name),
+ __print_hex(__entry->hdr, sizeof(__entry->hdr)),
+ __print_hex(__entry->tsf, sizeof(__entry->tsf))
+ )
+);
+
#endif /* if !defined(_TRACE_UFS_H) || defined(TRACE_HEADER_MULTI_READ) */
/* This part must be outside protection */
diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h
index 2f057a4..9a761bc6a 100644
--- a/include/trace/events/workqueue.h
+++ b/include/trace/events/workqueue.h
@@ -25,6 +25,8 @@ DECLARE_EVENT_CLASS(workqueue_work,
TP_printk("work struct %p", __entry->work)
);
+struct pool_workqueue;
+
/**
* workqueue_queue_work - called when a work gets queued
* @req_cpu: the requested cpu
diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h
index 7dd8f34..fdcf88b 100644
--- a/include/trace/events/xen.h
+++ b/include/trace/events/xen.h
@@ -352,22 +352,6 @@ DECLARE_EVENT_CLASS(xen_mmu_pgd,
DEFINE_XEN_MMU_PGD_EVENT(xen_mmu_pgd_pin);
DEFINE_XEN_MMU_PGD_EVENT(xen_mmu_pgd_unpin);
-TRACE_EVENT(xen_mmu_flush_tlb_all,
- TP_PROTO(int x),
- TP_ARGS(x),
- TP_STRUCT__entry(__array(char, x, 0)),
- TP_fast_assign((void)x),
- TP_printk("%s", "")
- );
-
-TRACE_EVENT(xen_mmu_flush_tlb,
- TP_PROTO(int x),
- TP_ARGS(x),
- TP_STRUCT__entry(__array(char, x, 0)),
- TP_fast_assign((void)x),
- TP_printk("%s", "")
- );
-
TRACE_EVENT(xen_mmu_flush_tlb_one_user,
TP_PROTO(unsigned long addr),
TP_ARGS(addr),
diff --git a/include/uapi/asm-generic/msgbuf.h b/include/uapi/asm-generic/msgbuf.h
index fb306eb..9fe4881 100644
--- a/include/uapi/asm-generic/msgbuf.h
+++ b/include/uapi/asm-generic/msgbuf.h
@@ -18,31 +18,30 @@
* On big-endian systems, the padding is in the wrong place.
*
* Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
* - 2 miscellaneous 32-bit values
*/
struct msqid64_ds {
struct ipc64_perm msg_perm;
+#if __BITS_PER_LONG == 64
__kernel_time_t msg_stime; /* last msgsnd time */
-#if __BITS_PER_LONG != 64
- unsigned long __unused1;
-#endif
__kernel_time_t msg_rtime; /* last msgrcv time */
-#if __BITS_PER_LONG != 64
- unsigned long __unused2;
-#endif
__kernel_time_t msg_ctime; /* last change time */
-#if __BITS_PER_LONG != 64
- unsigned long __unused3;
+#else
+ unsigned long msg_stime; /* last msgsnd time */
+ unsigned long msg_stime_high;
+ unsigned long msg_rtime; /* last msgrcv time */
+ unsigned long msg_rtime_high;
+ unsigned long msg_ctime; /* last change time */
+ unsigned long msg_ctime_high;
#endif
- __kernel_ulong_t msg_cbytes; /* current number of bytes on queue */
- __kernel_ulong_t msg_qnum; /* number of messages in queue */
- __kernel_ulong_t msg_qbytes; /* max number of bytes on queue */
+ unsigned long msg_cbytes; /* current number of bytes on queue */
+ unsigned long msg_qnum; /* number of messages in queue */
+ unsigned long msg_qbytes; /* max number of bytes on queue */
__kernel_pid_t msg_lspid; /* pid of last msgsnd */
__kernel_pid_t msg_lrpid; /* last receive pid */
- __kernel_ulong_t __unused4;
- __kernel_ulong_t __unused5;
+ unsigned long __unused4;
+ unsigned long __unused5;
};
#endif /* __ASM_GENERIC_MSGBUF_H */
diff --git a/include/uapi/asm-generic/posix_types.h b/include/uapi/asm-generic/posix_types.h
index 5e6ea22..f0733a2 100644
--- a/include/uapi/asm-generic/posix_types.h
+++ b/include/uapi/asm-generic/posix_types.h
@@ -87,6 +87,7 @@ typedef struct {
typedef __kernel_long_t __kernel_off_t;
typedef long long __kernel_loff_t;
typedef __kernel_long_t __kernel_time_t;
+typedef long long __kernel_time64_t;
typedef __kernel_long_t __kernel_clock_t;
typedef int __kernel_timer_t;
typedef int __kernel_clockid_t;
diff --git a/include/uapi/asm-generic/sembuf.h b/include/uapi/asm-generic/sembuf.h
index cbf9cfe..0bae010 100644
--- a/include/uapi/asm-generic/sembuf.h
+++ b/include/uapi/asm-generic/sembuf.h
@@ -13,23 +13,29 @@
* everyone just ended up making identical copies without specific
* optimizations, so we may just as well all use the same one.
*
- * 64 bit architectures typically define a 64 bit __kernel_time_t,
+ * 64 bit architectures use a 64-bit __kernel_time_t here, while
+ * 32 bit architectures have a pair of unsigned long values.
* so they do not need the first two padding words.
- * On big-endian systems, the padding is in the wrong place.
*
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
+ * On big-endian systems, the padding is in the wrong place for
+ * historic reasons, so user space has to reconstruct a time_t
+ * value using
+ *
+ * user_semid_ds.sem_otime = kernel_semid64_ds.sem_otime +
+ * ((long long)kernel_semid64_ds.sem_otime_high << 32)
+ *
+ * Pad space is left for 2 miscellaneous 32-bit values
*/
struct semid64_ds {
struct ipc64_perm sem_perm; /* permissions .. see ipc.h */
+#if __BITS_PER_LONG == 64
__kernel_time_t sem_otime; /* last semop time */
-#if __BITS_PER_LONG != 64
- unsigned long __unused1;
-#endif
__kernel_time_t sem_ctime; /* last change time */
-#if __BITS_PER_LONG != 64
- unsigned long __unused2;
+#else
+ unsigned long sem_otime; /* last semop time */
+ unsigned long sem_otime_high;
+ unsigned long sem_ctime; /* last change time */
+ unsigned long sem_ctime_high;
#endif
unsigned long sem_nsems; /* no. of semaphores in array */
unsigned long __unused3;
diff --git a/include/uapi/asm-generic/shmbuf.h b/include/uapi/asm-generic/shmbuf.h
index 2b6c3bb9..e504422 100644
--- a/include/uapi/asm-generic/shmbuf.h
+++ b/include/uapi/asm-generic/shmbuf.h
@@ -19,42 +19,41 @@
*
*
* Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
* - 2 miscellaneous 32-bit values
*/
struct shmid64_ds {
struct ipc64_perm shm_perm; /* operation perms */
size_t shm_segsz; /* size of segment (bytes) */
+#if __BITS_PER_LONG == 64
__kernel_time_t shm_atime; /* last attach time */
-#if __BITS_PER_LONG != 64
- unsigned long __unused1;
-#endif
__kernel_time_t shm_dtime; /* last detach time */
-#if __BITS_PER_LONG != 64
- unsigned long __unused2;
-#endif
__kernel_time_t shm_ctime; /* last change time */
-#if __BITS_PER_LONG != 64
- unsigned long __unused3;
+#else
+ unsigned long shm_atime; /* last attach time */
+ unsigned long shm_atime_high;
+ unsigned long shm_dtime; /* last detach time */
+ unsigned long shm_dtime_high;
+ unsigned long shm_ctime; /* last change time */
+ unsigned long shm_ctime_high;
#endif
__kernel_pid_t shm_cpid; /* pid of creator */
__kernel_pid_t shm_lpid; /* pid of last operator */
- __kernel_ulong_t shm_nattch; /* no. of current attaches */
- __kernel_ulong_t __unused4;
- __kernel_ulong_t __unused5;
+ unsigned long shm_nattch; /* no. of current attaches */
+ unsigned long __unused4;
+ unsigned long __unused5;
};
struct shminfo64 {
- __kernel_ulong_t shmmax;
- __kernel_ulong_t shmmin;
- __kernel_ulong_t shmmni;
- __kernel_ulong_t shmseg;
- __kernel_ulong_t shmall;
- __kernel_ulong_t __unused1;
- __kernel_ulong_t __unused2;
- __kernel_ulong_t __unused3;
- __kernel_ulong_t __unused4;
+ unsigned long shmmax;
+ unsigned long shmmin;
+ unsigned long shmmni;
+ unsigned long shmseg;
+ unsigned long shmall;
+ unsigned long __unused1;
+ unsigned long __unused2;
+ unsigned long __unused3;
+ unsigned long __unused4;
};
#endif /* __ASM_GENERIC_SHMBUF_H */
diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h
index 558b902..80e2a72 100644
--- a/include/uapi/asm-generic/siginfo.h
+++ b/include/uapi/asm-generic/siginfo.h
@@ -249,7 +249,8 @@ typedef struct siginfo {
#define TRAP_TRACE 2 /* process trace trap */
#define TRAP_BRANCH 3 /* process taken branch trap */
#define TRAP_HWBKPT 4 /* hardware breakpoint/watchpoint */
-#define NSIGTRAP 4
+#define TRAP_UNK 5 /* undiagnosed trap */
+#define NSIGTRAP 5
/*
* There is an additional set of SIGTRAP si_codes used by ptrace
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 8bcb186..4299067 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -732,9 +732,11 @@ __SYSCALL(__NR_pkey_alloc, sys_pkey_alloc)
__SYSCALL(__NR_pkey_free, sys_pkey_free)
#define __NR_statx 291
__SYSCALL(__NR_statx, sys_statx)
+#define __NR_io_pgetevents 292
+__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
#undef __NR_syscalls
-#define __NR_syscalls 292
+#define __NR_syscalls 293
/*
* 32 bit systems traditionally used different
diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index a04adbc..ed01859 100644
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h
@@ -29,6 +29,7 @@
#include <linux/types.h>
#include <linux/fs.h>
+#include <linux/signal.h>
#include <asm/byteorder.h>
typedef __kernel_ulong_t aio_context_t;
@@ -38,10 +39,8 @@ enum {
IOCB_CMD_PWRITE = 1,
IOCB_CMD_FSYNC = 2,
IOCB_CMD_FDSYNC = 3,
- /* These two are experimental.
- * IOCB_CMD_PREADX = 4,
- * IOCB_CMD_POLL = 5,
- */
+ /* 4 was the experimental IOCB_CMD_PREADX */
+ IOCB_CMD_POLL = 5,
IOCB_CMD_NOOP = 6,
IOCB_CMD_PREADV = 7,
IOCB_CMD_PWRITEV = 8,
@@ -108,5 +107,10 @@ struct iocb {
#undef IFBIG
#undef IFLITTLE
+struct __aio_sigset {
+ sigset_t __user *sigmask;
+ size_t sigsetsize;
+};
+
#endif /* __LINUX__AIO_ABI_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c5ec897..8c31773 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1017,6 +1017,7 @@ struct bpf_prog_info {
__aligned_u64 map_ids;
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
+ __u32 :32;
__u64 netns_dev;
__u64 netns_ino;
} __attribute__((aligned(8)));
@@ -1030,6 +1031,7 @@ struct bpf_map_info {
__u32 map_flags;
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
+ __u32 :32;
__u64 netns_dev;
__u64 netns_ino;
} __attribute__((aligned(8)));
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index c8d99b9..5ca1d21 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -422,6 +422,21 @@ struct btrfs_ioctl_ino_lookup_args {
char name[BTRFS_INO_LOOKUP_PATH_MAX];
};
+#define BTRFS_INO_LOOKUP_USER_PATH_MAX (4080 - BTRFS_VOL_NAME_MAX - 1)
+struct btrfs_ioctl_ino_lookup_user_args {
+ /* in, inode number containing the subvolume of 'subvolid' */
+ __u64 dirid;
+ /* in */
+ __u64 treeid;
+ /* out, name of the subvolume of 'treeid' */
+ char name[BTRFS_VOL_NAME_MAX + 1];
+ /*
+ * out, constructed path from the directory with which the ioctl is
+ * called to dirid
+ */
+ char path[BTRFS_INO_LOOKUP_USER_PATH_MAX];
+};
+
/* Search criteria for the btrfs SEARCH ioctl family. */
struct btrfs_ioctl_search_key {
/*
@@ -725,6 +740,82 @@ struct btrfs_ioctl_send_args {
__u64 reserved[4]; /* in */
};
+/*
+ * Information about a fs tree root.
+ *
+ * All items are filled by the ioctl
+ */
+struct btrfs_ioctl_get_subvol_info_args {
+ /* Id of this subvolume */
+ __u64 treeid;
+
+ /* Name of this subvolume, used to get the real name at mount point */
+ char name[BTRFS_VOL_NAME_MAX + 1];
+
+ /*
+ * Id of the subvolume which contains this subvolume.
+ * Zero for top-level subvolume or a deleted subvolume.
+ */
+ __u64 parent_id;
+
+ /*
+ * Inode number of the directory which contains this subvolume.
+ * Zero for top-level subvolume or a deleted subvolume
+ */
+ __u64 dirid;
+
+ /* Latest transaction id of this subvolume */
+ __u64 generation;
+
+ /* Flags of this subvolume */
+ __u64 flags;
+
+ /* UUID of this subvolume */
+ __u8 uuid[BTRFS_UUID_SIZE];
+
+ /*
+ * UUID of the subvolume of which this subvolume is a snapshot.
+ * All zero for a non-snapshot subvolume.
+ */
+ __u8 parent_uuid[BTRFS_UUID_SIZE];
+
+ /*
+ * UUID of the subvolume from which this subvolume was received.
+ * All zero for non-received subvolume.
+ */
+ __u8 received_uuid[BTRFS_UUID_SIZE];
+
+ /* Transaction id indicating when change/create/send/receive happened */
+ __u64 ctransid;
+ __u64 otransid;
+ __u64 stransid;
+ __u64 rtransid;
+ /* Time corresponding to c/o/s/rtransid */
+ struct btrfs_ioctl_timespec ctime;
+ struct btrfs_ioctl_timespec otime;
+ struct btrfs_ioctl_timespec stime;
+ struct btrfs_ioctl_timespec rtime;
+
+ /* Must be zero */
+ __u64 reserved[8];
+};
+
+#define BTRFS_MAX_ROOTREF_BUFFER_NUM 255
+struct btrfs_ioctl_get_subvol_rootref_args {
+ /* in/out, minimum id of rootref's treeid to be searched */
+ __u64 min_treeid;
+
+ /* out */
+ struct {
+ __u64 treeid;
+ __u64 dirid;
+ } rootref[BTRFS_MAX_ROOTREF_BUFFER_NUM];
+
+ /* out, number of found items */
+ __u8 num_items;
+ __u8 align[7];
+};
+
/* Error codes as returned by the kernel */
enum btrfs_err_code {
BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET = 1,
@@ -843,5 +934,11 @@ enum btrfs_err_code {
struct btrfs_ioctl_vol_args_v2)
#define BTRFS_IOC_LOGICAL_INO_V2 _IOWR(BTRFS_IOCTL_MAGIC, 59, \
struct btrfs_ioctl_logical_ino_args)
+#define BTRFS_IOC_GET_SUBVOL_INFO _IOR(BTRFS_IOCTL_MAGIC, 60, \
+ struct btrfs_ioctl_get_subvol_info_args)
+#define BTRFS_IOC_GET_SUBVOL_ROOTREF _IOWR(BTRFS_IOCTL_MAGIC, 61, \
+ struct btrfs_ioctl_get_subvol_rootref_args)
+#define BTRFS_IOC_INO_LOOKUP_USER _IOWR(BTRFS_IOCTL_MAGIC, 62, \
+ struct btrfs_ioctl_ino_lookup_user_args)
#endif /* _UAPI_LINUX_BTRFS_H */
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index d2a8313..73e0191 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -242,6 +242,8 @@ struct fsxattr {
#define FICLONERANGE _IOW(0x94, 13, struct file_clone_range)
#define FIDEDUPERANGE _IOWR(0x94, 54, struct file_dedupe_range)
+#define FSLABEL_MAX 256 /* Max chars for the interface; each fs may differ */
+
#define FS_IOC_GETFLAGS _IOR('f', 1, long)
#define FS_IOC_SETFLAGS _IOW('f', 2, long)
#define FS_IOC_GETVERSION _IOR('v', 1, long)
@@ -251,8 +253,10 @@ struct fsxattr {
#define FS_IOC32_SETFLAGS _IOW('f', 2, int)
#define FS_IOC32_GETVERSION _IOR('v', 1, int)
#define FS_IOC32_SETVERSION _IOW('v', 2, int)
-#define FS_IOC_FSGETXATTR _IOR ('X', 31, struct fsxattr)
-#define FS_IOC_FSSETXATTR _IOW ('X', 32, struct fsxattr)
+#define FS_IOC_FSGETXATTR _IOR('X', 31, struct fsxattr)
+#define FS_IOC_FSSETXATTR _IOW('X', 32, struct fsxattr)
+#define FS_IOC_GETFSLABEL _IOR(0x94, 49, char[FSLABEL_MAX])
+#define FS_IOC_SETFSLABEL _IOW(0x94, 50, char[FSLABEL_MAX])
/*
* File system encryption support
@@ -275,6 +279,8 @@ struct fsxattr {
#define FS_ENCRYPTION_MODE_AES_256_CTS 4
#define FS_ENCRYPTION_MODE_AES_128_CBC 5
#define FS_ENCRYPTION_MODE_AES_128_CTS 6
+#define FS_ENCRYPTION_MODE_SPECK128_256_XTS 7
+#define FS_ENCRYPTION_MODE_SPECK128_256_CTS 8
struct fscrypt_policy {
__u8 version;
diff --git a/include/uapi/linux/if_infiniband.h b/include/uapi/linux/if_infiniband.h
index 050b92d..0fc33bf 100644
--- a/include/uapi/linux/if_infiniband.h
+++ b/include/uapi/linux/if_infiniband.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
/*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 1065006..b02c41e 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -676,6 +676,13 @@ struct kvm_ioeventfd {
__u8 pad[36];
};
+#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0)
+#define KVM_X86_DISABLE_EXITS_HTL (1 << 1)
+#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2)
+#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \
+ KVM_X86_DISABLE_EXITS_HTL | \
+ KVM_X86_DISABLE_EXITS_PAUSE)
+
/* for KVM_ENABLE_CAP */
struct kvm_enable_cap {
/* in */
diff --git a/include/uapi/linux/netfilter/nf_conntrack_tcp.h b/include/uapi/linux/netfilter/nf_conntrack_tcp.h
index 74b9115..bcba72d 100644
--- a/include/uapi/linux/netfilter/nf_conntrack_tcp.h
+++ b/include/uapi/linux/netfilter/nf_conntrack_tcp.h
@@ -46,6 +46,9 @@ enum tcp_conntrack {
/* Marks possibility for expected RFC5961 challenge ACK */
#define IP_CT_EXP_CHALLENGE_ACK 0x40
+/* Simultaneous open initialized */
+#define IP_CT_TCP_SIMULTANEOUS_OPEN 0x80
+
struct nf_ct_tcp_flags {
__u8 flags;
__u8 mask;
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 15daf5e..271b937 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2698,6 +2698,8 @@ enum nl80211_attrs {
#define NL80211_ATTR_KEYS NL80211_ATTR_KEYS
#define NL80211_ATTR_FEATURE_FLAGS NL80211_ATTR_FEATURE_FLAGS
+#define NL80211_WIPHY_NAME_MAXLEN 64
+
#define NL80211_MAX_SUPP_RATES 32
#define NL80211_MAX_SUPP_HT_RATES 77
#define NL80211_MAX_SUPP_REG_RULES 64
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 912b85b..b8e288a 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -650,11 +650,23 @@ struct perf_event_mmap_page {
#define PERF_RECORD_MISC_COMM_EXEC (1 << 13)
#define PERF_RECORD_MISC_SWITCH_OUT (1 << 13)
/*
- * Indicates that the content of PERF_SAMPLE_IP points to
- * the actual instruction that triggered the event. See also
- * perf_event_attr::precise_ip.
+ * These PERF_RECORD_MISC_* flags below are safely reused
+ * for the following events:
+ *
+ * PERF_RECORD_MISC_EXACT_IP - PERF_RECORD_SAMPLE of precise events
+ * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events
+ *
+ *
+ * PERF_RECORD_MISC_EXACT_IP:
+ * Indicates that the content of PERF_SAMPLE_IP points to
+ * the actual instruction that triggered the event. See also
+ * perf_event_attr::precise_ip.
+ *
+ * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT:
+ * Indicates that thread was preempted in TASK_RUNNING state.
*/
#define PERF_RECORD_MISC_EXACT_IP (1 << 14)
+#define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14)
/*
* Reserve the last bit to indicate some extended misc field
*/
diff --git a/include/uapi/linux/ppp-ioctl.h b/include/uapi/linux/ppp-ioctl.h
index b19a9c2..784c2e3 100644
--- a/include/uapi/linux/ppp-ioctl.h
+++ b/include/uapi/linux/ppp-ioctl.h
@@ -106,7 +106,7 @@ struct pppol2tp_ioc_stats {
#define PPPIOCGIDLE _IOR('t', 63, struct ppp_idle) /* get idle time */
#define PPPIOCNEWUNIT _IOWR('t', 62, int) /* create new ppp unit */
#define PPPIOCATTACH _IOW('t', 61, int) /* attach to ppp unit */
-#define PPPIOCDETACH _IOW('t', 60, int) /* detach from ppp unit/chan */
+#define PPPIOCDETACH _IOW('t', 60, int) /* obsolete, do not use */
#define PPPIOCSMRRU _IOW('t', 59, int) /* set multilink MRU */
#define PPPIOCCONNECT _IOW('t', 58, int) /* connect channel to unit */
#define PPPIOCDISCONN _IO('t', 57) /* disconnect channel */
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index af5f8c2..db9f15f5 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -207,4 +207,16 @@ struct prctl_mm_map {
# define PR_SVE_VL_LEN_MASK 0xffff
# define PR_SVE_VL_INHERIT (1 << 17) /* inherit across exec */
+/* Per task speculation control */
+#define PR_GET_SPECULATION_CTRL 52
+#define PR_SET_SPECULATION_CTRL 53
+/* Speculation control variants */
+# define PR_SPEC_STORE_BYPASS 0
+/* Return and control values for PR_SET/GET_SPECULATION_CTRL */
+# define PR_SPEC_NOT_AFFECTED 0
+# define PR_SPEC_PRCTL (1UL << 0)
+# define PR_SPEC_ENABLE (1UL << 1)
+# define PR_SPEC_DISABLE (1UL << 2)
+# define PR_SPEC_FORCE_DISABLE (1UL << 3)
+
#endif /* _LINUX_PRCTL_H */
diff --git a/include/uapi/linux/random.h b/include/uapi/linux/random.h
index c34f449..26ee913 100644
--- a/include/uapi/linux/random.h
+++ b/include/uapi/linux/random.h
@@ -35,6 +35,9 @@
/* Clear the entropy pool and associated counters. (Superuser only.) */
#define RNDCLEARPOOL _IO( 'R', 0x06 )
+/* Reseed CRNG. (Superuser only.) */
+#define RNDRESEEDCRNG _IO( 'R', 0x07 )
+
struct rand_pool_info {
int entropy_count;
int buf_size;
diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h
index a66b213..20c6bd0 100644
--- a/include/uapi/linux/rds.h
+++ b/include/uapi/linux/rds.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2008 Oracle. All rights reserved.
*
diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
index 2a0bd9d..9efc0e7 100644
--- a/include/uapi/linux/seccomp.h
+++ b/include/uapi/linux/seccomp.h
@@ -17,8 +17,9 @@
#define SECCOMP_GET_ACTION_AVAIL 2
/* Valid flags for SECCOMP_SET_MODE_FILTER */
-#define SECCOMP_FILTER_FLAG_TSYNC 1
-#define SECCOMP_FILTER_FLAG_LOG 2
+#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0)
+#define SECCOMP_FILTER_FLAG_LOG (1UL << 1)
+#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2)
/*
* All BPF programs must return a 32-bit value.
diff --git a/include/uapi/linux/signalfd.h b/include/uapi/linux/signalfd.h
index 6f0da42..83429a0 100644
--- a/include/uapi/linux/signalfd.h
+++ b/include/uapi/linux/signalfd.h
@@ -35,6 +35,10 @@ struct signalfd_siginfo {
__u64 ssi_stime;
__u64 ssi_addr;
__u16 ssi_addr_lsb;
+ __u16 __pad2;
+ __s32 ssi_syscall;
+ __u64 ssi_call_addr;
+ __u32 ssi_arch;
/*
* Pad strcture to 128 bytes. Remember to update the
@@ -45,7 +49,7 @@ struct signalfd_siginfo {
* comes out of a read(2) and we really don't want to have
* a compat on read(2).
*/
- __u8 __pad[46];
+ __u8 __pad[28];
};
diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h
index 0f27281..6b58371 100644
--- a/include/uapi/linux/sysctl.h
+++ b/include/uapi/linux/sysctl.h
@@ -780,24 +780,6 @@ enum {
NET_BRIDGE_NF_FILTER_PPPOE_TAGGED = 5,
};
-/* proc/sys/net/irda */
-enum {
- NET_IRDA_DISCOVERY=1,
- NET_IRDA_DEVNAME=2,
- NET_IRDA_DEBUG=3,
- NET_IRDA_FAST_POLL=4,
- NET_IRDA_DISCOVERY_SLOTS=5,
- NET_IRDA_DISCOVERY_TIMEOUT=6,
- NET_IRDA_SLOT_TIMEOUT=7,
- NET_IRDA_MAX_BAUD_RATE=8,
- NET_IRDA_MIN_TX_TURN_TIME=9,
- NET_IRDA_MAX_TX_DATA_SIZE=10,
- NET_IRDA_MAX_TX_WINDOW=11,
- NET_IRDA_MAX_NOREPLY_TIME=12,
- NET_IRDA_WARN_NOREPLY_TIME=13,
- NET_IRDA_LAP_KEEPALIVE_TIME=14,
-};
-
/* CTL_FS names: */
enum
diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h
index 16a2966..fcf9366 100644
--- a/include/uapi/linux/time.h
+++ b/include/uapi/linux/time.h
@@ -42,6 +42,13 @@ struct itimerval {
struct timeval it_value; /* current value */
};
+#ifndef __kernel_timespec
+struct __kernel_timespec {
+ __kernel_time64_t tv_sec; /* seconds */
+ long long tv_nsec; /* nanoseconds */
+};
+#endif
+
/*
* legacy timeval structure, only embedded in structures that
* traditionally used 'timeval' to pass time intervals (not absolute
@@ -73,7 +80,6 @@ struct __kernel_old_timeval {
*/
#define CLOCK_SGI_CYCLE 10
#define CLOCK_TAI 11
-#define CLOCK_MONOTONIC_ACTIVE 12
#define MAX_CLOCKS 16
#define CLOCKS_MASK (CLOCK_REALTIME | CLOCK_MONOTONIC)
diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h
index c6633e9..ff02287 100644
--- a/include/uapi/linux/tls.h
+++ b/include/uapi/linux/tls.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved.
*
diff --git a/include/uapi/linux/types.h b/include/uapi/linux/types.h
index cd4f0b8..2fce8b6 100644
--- a/include/uapi/linux/types.h
+++ b/include/uapi/linux/types.h
@@ -49,11 +49,7 @@ typedef __u32 __bitwise __wsum;
#define __aligned_be64 __be64 __attribute__((aligned(8)))
#define __aligned_le64 __le64 __attribute__((aligned(8)))
-#ifdef __CHECK_POLL
typedef unsigned __bitwise __poll_t;
-#else
-typedef unsigned __poll_t;
-#endif
#endif /* __ASSEMBLY__ */
#endif /* _UAPI_LINUX_TYPES_H */
diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h
index 40297a3..13b8cb5 100644
--- a/include/uapi/linux/virtio_balloon.h
+++ b/include/uapi/linux/virtio_balloon.h
@@ -57,6 +57,21 @@ struct virtio_balloon_config {
#define VIRTIO_BALLOON_S_HTLB_PGFAIL 9 /* Hugetlb page allocation failures */
#define VIRTIO_BALLOON_S_NR 10
+#define VIRTIO_BALLOON_S_NAMES_WITH_PREFIX(VIRTIO_BALLOON_S_NAMES_prefix) { \
+ VIRTIO_BALLOON_S_NAMES_prefix "swap-in", \
+ VIRTIO_BALLOON_S_NAMES_prefix "swap-out", \
+ VIRTIO_BALLOON_S_NAMES_prefix "major-faults", \
+ VIRTIO_BALLOON_S_NAMES_prefix "minor-faults", \
+ VIRTIO_BALLOON_S_NAMES_prefix "free-memory", \
+ VIRTIO_BALLOON_S_NAMES_prefix "total-memory", \
+ VIRTIO_BALLOON_S_NAMES_prefix "available-memory", \
+ VIRTIO_BALLOON_S_NAMES_prefix "disk-caches", \
+ VIRTIO_BALLOON_S_NAMES_prefix "hugetlb-allocations", \
+ VIRTIO_BALLOON_S_NAMES_prefix "hugetlb-failures" \
+}
+
+#define VIRTIO_BALLOON_S_NAMES VIRTIO_BALLOON_S_NAMES_WITH_PREFIX("")
+
/*
* Memory statistics structure.
* Driver fills an array of these structures and passes to device.
diff --git a/include/uapi/rdma/cxgb3-abi.h b/include/uapi/rdma/cxgb3-abi.h
index 9acb4b7..85aed67 100644
--- a/include/uapi/rdma/cxgb3-abi.h
+++ b/include/uapi/rdma/cxgb3-abi.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2006 Chelsio, Inc. All rights reserved.
*
diff --git a/include/uapi/rdma/cxgb4-abi.h b/include/uapi/rdma/cxgb4-abi.h
index 1fefd01..a159ba8 100644
--- a/include/uapi/rdma/cxgb4-abi.h
+++ b/include/uapi/rdma/cxgb4-abi.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2009-2010 Chelsio, Inc. All rights reserved.
*
diff --git a/include/uapi/rdma/hns-abi.h b/include/uapi/rdma/hns-abi.h
index 7092c8d..78613b6 100644
--- a/include/uapi/rdma/hns-abi.h
+++ b/include/uapi/rdma/hns-abi.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2016 Hisilicon Limited.
*
diff --git a/include/uapi/rdma/ib_user_cm.h b/include/uapi/rdma/ib_user_cm.h
index 4a8f956..e2709bb 100644
--- a/include/uapi/rdma/ib_user_cm.h
+++ b/include/uapi/rdma/ib_user_cm.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2005 Topspin Communications. All rights reserved.
* Copyright (c) 2005 Intel Corporation. All rights reserved.
diff --git a/include/uapi/rdma/ib_user_ioctl_verbs.h b/include/uapi/rdma/ib_user_ioctl_verbs.h
index 04e46ea..625545d 100644
--- a/include/uapi/rdma/ib_user_ioctl_verbs.h
+++ b/include/uapi/rdma/ib_user_ioctl_verbs.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2017-2018, Mellanox Technologies inc. All rights reserved.
*
diff --git a/include/uapi/rdma/ib_user_mad.h b/include/uapi/rdma/ib_user_mad.h
index ef92118..90c0cf2 100644
--- a/include/uapi/rdma/ib_user_mad.h
+++ b/include/uapi/rdma/ib_user_mad.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2004 Topspin Communications. All rights reserved.
* Copyright (c) 2005 Voltaire, Inc. All rights reserved.
diff --git a/include/uapi/rdma/ib_user_sa.h b/include/uapi/rdma/ib_user_sa.h
index 0d2607f..435155d 100644
--- a/include/uapi/rdma/ib_user_sa.h
+++ b/include/uapi/rdma/ib_user_sa.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2005 Intel Corporation. All rights reserved.
*
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 9be0739..6aeb033 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2005 Topspin Communications. All rights reserved.
* Copyright (c) 2005, 2006 Cisco Systems. All rights reserved.
diff --git a/include/uapi/rdma/mlx4-abi.h b/include/uapi/rdma/mlx4-abi.h
index 04f64bc..f745575 100644
--- a/include/uapi/rdma/mlx4-abi.h
+++ b/include/uapi/rdma/mlx4-abi.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2007 Cisco Systems, Inc. All rights reserved.
* Copyright (c) 2007, 2008 Mellanox Technologies. All rights reserved.
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index cb4a02c..fdaf00e 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved.
*
diff --git a/include/uapi/rdma/mthca-abi.h b/include/uapi/rdma/mthca-abi.h
index ac756cd..91b12e1 100644
--- a/include/uapi/rdma/mthca-abi.h
+++ b/include/uapi/rdma/mthca-abi.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2005 Topspin Communications. All rights reserved.
* Copyright (c) 2005, 2006 Cisco Systems. All rights reserved.
diff --git a/include/uapi/rdma/nes-abi.h b/include/uapi/rdma/nes-abi.h
index 35bfd40..f80495b 100644
--- a/include/uapi/rdma/nes-abi.h
+++ b/include/uapi/rdma/nes-abi.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2006 - 2011 Intel Corporation. All rights reserved.
* Copyright (c) 2005 Topspin Communications. All rights reserved.
diff --git a/include/uapi/rdma/qedr-abi.h b/include/uapi/rdma/qedr-abi.h
index 8ba0989..24c658b 100644
--- a/include/uapi/rdma/qedr-abi.h
+++ b/include/uapi/rdma/qedr-abi.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/* QLogic qedr NIC Driver
* Copyright (c) 2015-2016 QLogic Corporation
*
diff --git a/include/uapi/rdma/rdma_user_cm.h b/include/uapi/rdma/rdma_user_cm.h
index e126902..0d1e78e 100644
--- a/include/uapi/rdma/rdma_user_cm.h
+++ b/include/uapi/rdma/rdma_user_cm.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2005-2006 Intel Corporation. All rights reserved.
*
diff --git a/include/uapi/rdma/rdma_user_ioctl.h b/include/uapi/rdma/rdma_user_ioctl.h
index d223f41..d92d272 100644
--- a/include/uapi/rdma/rdma_user_ioctl.h
+++ b/include/uapi/rdma/rdma_user_ioctl.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2016 Mellanox Technologies, LTD. All rights reserved.
*
diff --git a/include/uapi/rdma/rdma_user_rxe.h b/include/uapi/rdma/rdma_user_rxe.h
index 1f8a9e7..44ef6a3 100644
--- a/include/uapi/rdma/rdma_user_rxe.h
+++ b/include/uapi/rdma/rdma_user_rxe.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
/*
* Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved.
*
diff --git a/include/xen/interface/io/sndif.h b/include/xen/interface/io/sndif.h
index 5c91827..78bb5d9 100644
--- a/include/xen/interface/io/sndif.h
+++ b/include/xen/interface/io/sndif.h
@@ -38,6 +38,13 @@
/*
******************************************************************************
+ * Protocol version
+ ******************************************************************************
+ */
+#define XENSND_PROTOCOL_VERSION 2
+
+/*
+ ******************************************************************************
* Feature and Parameter Negotiation
******************************************************************************
*
@@ -106,6 +113,8 @@
*
* /local/domain/1/device/vsnd/0/0/0/ring-ref = "386"
* /local/domain/1/device/vsnd/0/0/0/event-channel = "15"
+ * /local/domain/1/device/vsnd/0/0/0/evt-ring-ref = "1386"
+ * /local/domain/1/device/vsnd/0/0/0/evt-event-channel = "215"
*
*------------------------------ Stream 1, capture ----------------------------
*
@@ -115,6 +124,8 @@
*
* /local/domain/1/device/vsnd/0/0/1/ring-ref = "384"
* /local/domain/1/device/vsnd/0/0/1/event-channel = "13"
+ * /local/domain/1/device/vsnd/0/0/1/evt-ring-ref = "1384"
+ * /local/domain/1/device/vsnd/0/0/1/evt-event-channel = "213"
*
*------------------------------- PCM device 1 --------------------------------
*
@@ -128,6 +139,8 @@
*
* /local/domain/1/device/vsnd/0/1/0/ring-ref = "387"
* /local/domain/1/device/vsnd/0/1/0/event-channel = "151"
+ * /local/domain/1/device/vsnd/0/1/0/evt-ring-ref = "1387"
+ * /local/domain/1/device/vsnd/0/1/0/evt-event-channel = "351"
*
*------------------------------- PCM device 2 --------------------------------
*
@@ -140,6 +153,8 @@
*
* /local/domain/1/device/vsnd/0/2/0/ring-ref = "389"
* /local/domain/1/device/vsnd/0/2/0/event-channel = "152"
+ * /local/domain/1/device/vsnd/0/2/0/evt-ring-ref = "1389"
+ * /local/domain/1/device/vsnd/0/2/0/evt-event-channel = "452"
*
******************************************************************************
* Backend XenBus Nodes
@@ -285,6 +300,23 @@
* The Xen grant reference granting permission for the backend to map
* a sole page in a single page sized ring buffer.
*
+ *--------------------- Stream Event Transport Parameters ---------------------
+ *
+ * This communication path is used to deliver asynchronous events from backend
+ * to frontend, set up per stream.
+ *
+ * evt-event-channel
+ * Values: <uint32_t>
+ *
+ * The identifier of the Xen event channel used to signal activity
+ * in the ring buffer.
+ *
+ * evt-ring-ref
+ * Values: <uint32_t>
+ *
+ * The Xen grant reference granting permission for the backend to map
+ * a sole page in a single page sized ring buffer.
+ *
******************************************************************************
* STATE DIAGRAMS
******************************************************************************
@@ -432,6 +464,20 @@
#define XENSND_OP_GET_VOLUME 5
#define XENSND_OP_MUTE 6
#define XENSND_OP_UNMUTE 7
+#define XENSND_OP_TRIGGER 8
+#define XENSND_OP_HW_PARAM_QUERY 9
+
+#define XENSND_OP_TRIGGER_START 0
+#define XENSND_OP_TRIGGER_PAUSE 1
+#define XENSND_OP_TRIGGER_STOP 2
+#define XENSND_OP_TRIGGER_RESUME 3
+
+/*
+ ******************************************************************************
+ * EVENT CODES
+ ******************************************************************************
+ */
+#define XENSND_EVT_CUR_POS 0
/*
******************************************************************************
@@ -448,6 +494,8 @@
#define XENSND_FIELD_VCARD_LONG_NAME "long-name"
#define XENSND_FIELD_RING_REF "ring-ref"
#define XENSND_FIELD_EVT_CHNL "event-channel"
+#define XENSND_FIELD_EVT_RING_REF "evt-ring-ref"
+#define XENSND_FIELD_EVT_EVT_CHNL "evt-event-channel"
#define XENSND_FIELD_DEVICE_NAME "name"
#define XENSND_FIELD_TYPE "type"
#define XENSND_FIELD_STREAM_UNIQUE_ID "unique-id"
@@ -526,7 +574,7 @@
*
*---------------------------------- Requests ---------------------------------
*
- * All request packets have the same length (32 octets)
+ * All request packets have the same length (64 octets)
* All request packets have common header:
* 0 1 2 3 octet
* +----------------+----------------+----------------+----------------+
@@ -559,11 +607,13 @@
* +----------------+----------------+----------------+----------------+
* | gref_directory | 24
* +----------------+----------------+----------------+----------------+
- * | reserved | 28
+ * | period_sz | 28
+ * +----------------+----------------+----------------+----------------+
+ * | reserved | 32
* +----------------+----------------+----------------+----------------+
* |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
* +----------------+----------------+----------------+----------------+
- * | reserved | 32
+ * | reserved | 64
* +----------------+----------------+----------------+----------------+
*
* pcm_rate - uint32_t, stream data rate, Hz
@@ -571,6 +621,14 @@
* pcm_channels - uint8_t, number of channels of this stream,
* [channels-min; channels-max]
* buffer_sz - uint32_t, buffer size to be allocated, octets
+ * period_sz - uint32_t, event period size, octets
+ * This is the requested value of the period at which frontend would
+ * like to receive XENSND_EVT_CUR_POS notifications from the backend when
+ * stream position advances during playback/capture.
+ * It shows how many octets are expected to be played/captured before
+ * sending such an event.
+ * If set to 0 no XENSND_EVT_CUR_POS events are sent by the backend.
+ *
* gref_directory - grant_ref_t, a reference to the first shared page
* describing shared buffer references. At least one page exists. If shared
* buffer size (buffer_sz) exceeds what can be addressed by this single page,
@@ -585,6 +643,7 @@ struct xensnd_open_req {
uint16_t reserved;
uint32_t buffer_sz;
grant_ref_t gref_directory;
+ uint32_t period_sz;
};
/*
@@ -632,7 +691,7 @@ struct xensnd_page_directory {
* +----------------+----------------+----------------+----------------+
* |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
* +----------------+----------------+----------------+----------------+
- * | reserved | 32
+ * | reserved | 64
* +----------------+----------------+----------------+----------------+
*
* Request read/write - used for read (for capture) or write (for playback):
@@ -650,7 +709,7 @@ struct xensnd_page_directory {
* +----------------+----------------+----------------+----------------+
* |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
* +----------------+----------------+----------------+----------------+
- * | reserved | 32
+ * | reserved | 64
* +----------------+----------------+----------------+----------------+
*
* operation - XENSND_OP_READ for read or XENSND_OP_WRITE for write
@@ -673,9 +732,11 @@ struct xensnd_rw_req {
* +----------------+----------------+----------------+----------------+
* | length | 16
* +----------------+----------------+----------------+----------------+
+ * | reserved | 20
+ * +----------------+----------------+----------------+----------------+
* |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
* +----------------+----------------+----------------+----------------+
- * | reserved | 32
+ * | reserved | 64
* +----------------+----------------+----------------+----------------+
*
* operation - XENSND_OP_SET_VOLUME for volume set
@@ -713,9 +774,11 @@ struct xensnd_rw_req {
* +----------------+----------------+----------------+----------------+
* | length | 16
* +----------------+----------------+----------------+----------------+
+ * | reserved | 20
+ * +----------------+----------------+----------------+----------------+
* |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
* +----------------+----------------+----------------+----------------+
- * | reserved | 32
+ * | reserved | 64
* +----------------+----------------+----------------+----------------+
*
* operation - XENSND_OP_MUTE for mute or XENSND_OP_UNMUTE for unmute
@@ -743,32 +806,213 @@ struct xensnd_rw_req {
*
* The 'struct xensnd_rw_req' is also used for XENSND_OP_SET_VOLUME,
* XENSND_OP_GET_VOLUME, XENSND_OP_MUTE, XENSND_OP_UNMUTE.
+ *
+ * Request stream running state change - trigger PCM stream running state
+ * to start, stop, pause or resume:
+ *
+ * 0 1 2 3 octet
+ * +----------------+----------------+----------------+----------------+
+ * | id | _OP_TRIGGER | reserved | 4
+ * +----------------+----------------+----------------+----------------+
+ * | reserved | 8
+ * +----------------+----------------+----------------+----------------+
+ * | type | reserved | 12
+ * +----------------+----------------+----------------+----------------+
+ * | reserved | 16
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * | reserved | 64
+ * +----------------+----------------+----------------+----------------+
+ *
+ * type - uint8_t, XENSND_OP_TRIGGER_XXX value
*/
+struct xensnd_trigger_req {
+ uint8_t type;
+};
+
+/*
+ * Request stream parameter ranges: request intervals and
+ * masks of supported ranges for stream configuration values.
+ *
+ * Sound device configuration for a particular stream is a limited subset
+ * of the multidimensional configuration available on XenStore, e.g.
+ * once the frame rate has been selected there is a limited supported range
+ * for sample rates becomes available (which might be the same set configured
+ * on XenStore or less). For example, selecting 96kHz sample rate may limit
+ * number of channels available for such configuration from 4 to 2, etc.
+ * Thus, each call to XENSND_OP_HW_PARAM_QUERY may reduce configuration
+ * space making it possible to iteratively get the final stream configuration,
+ * used in XENSND_OP_OPEN request.
+ *
+ * See response format for this request.
+ *
+ * 0 1 2 3 octet
+ * +----------------+----------------+----------------+----------------+
+ * | id | _HW_PARAM_QUERY| reserved | 4
+ * +----------------+----------------+----------------+----------------+
+ * | reserved | 8
+ * +----------------+----------------+----------------+----------------+
+ * | formats mask low 32-bit | 12
+ * +----------------+----------------+----------------+----------------+
+ * | formats mask high 32-bit | 16
+ * +----------------+----------------+----------------+----------------+
+ * | min rate | 20
+ * +----------------+----------------+----------------+----------------+
+ * | max rate | 24
+ * +----------------+----------------+----------------+----------------+
+ * | min channels | 28
+ * +----------------+----------------+----------------+----------------+
+ * | max channels | 32
+ * +----------------+----------------+----------------+----------------+
+ * | min buffer frames | 36
+ * +----------------+----------------+----------------+----------------+
+ * | max buffer frames | 40
+ * +----------------+----------------+----------------+----------------+
+ * | min period frames | 44
+ * +----------------+----------------+----------------+----------------+
+ * | max period frames | 48
+ * +----------------+----------------+----------------+----------------+
+ * | reserved | 52
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * | reserved | 64
+ * +----------------+----------------+----------------+----------------+
+ *
+ * formats - uint64_t, bit mask representing values of the parameter
+ * made as bitwise OR of (1 << XENSND_PCM_FORMAT_XXX) values
+ *
+ * For interval parameters:
+ * min - uint32_t, minimum value of the parameter
+ * max - uint32_t, maximum value of the parameter
+ *
+ * Frame is defined as a product of the number of channels by the
+ * number of octets per one sample.
+ */
+
+struct xensnd_query_hw_param {
+ uint64_t formats;
+ struct {
+ uint32_t min;
+ uint32_t max;
+ } rates;
+ struct {
+ uint32_t min;
+ uint32_t max;
+ } channels;
+ struct {
+ uint32_t min;
+ uint32_t max;
+ } buffer;
+ struct {
+ uint32_t min;
+ uint32_t max;
+ } period;
+};
+
/*
*---------------------------------- Responses --------------------------------
*
- * All response packets have the same length (32 octets)
+ * All response packets have the same length (64 octets)
*
- * Response for all requests:
+ * All response packets have common header:
* 0 1 2 3 octet
* +----------------+----------------+----------------+----------------+
* | id | operation | reserved | 4
* +----------------+----------------+----------------+----------------+
* | status | 8
* +----------------+----------------+----------------+----------------+
- * | reserved | 12
- * +----------------+----------------+----------------+----------------+
- * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
- * +----------------+----------------+----------------+----------------+
- * | reserved | 32
- * +----------------+----------------+----------------+----------------+
*
* id - uint16_t, copied from the request
* operation - uint8_t, XENSND_OP_* - copied from request
* status - int32_t, response status, zero on success and -XEN_EXX on failure
+ *
+ *
+ * HW parameter query response - response for XENSND_OP_HW_PARAM_QUERY:
+ * 0 1 2 3 octet
+ * +----------------+----------------+----------------+----------------+
+ * | id | operation | reserved | 4
+ * +----------------+----------------+----------------+----------------+
+ * | status | 8
+ * +----------------+----------------+----------------+----------------+
+ * | formats mask low 32-bit | 12
+ * +----------------+----------------+----------------+----------------+
+ * | formats mask high 32-bit | 16
+ * +----------------+----------------+----------------+----------------+
+ * | min rate | 20
+ * +----------------+----------------+----------------+----------------+
+ * | max rate | 24
+ * +----------------+----------------+----------------+----------------+
+ * | min channels | 28
+ * +----------------+----------------+----------------+----------------+
+ * | max channels | 32
+ * +----------------+----------------+----------------+----------------+
+ * | min buffer frames | 36
+ * +----------------+----------------+----------------+----------------+
+ * | max buffer frames | 40
+ * +----------------+----------------+----------------+----------------+
+ * | min period frames | 44
+ * +----------------+----------------+----------------+----------------+
+ * | max period frames | 48
+ * +----------------+----------------+----------------+----------------+
+ * | reserved | 52
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * | reserved | 64
+ * +----------------+----------------+----------------+----------------+
+ *
+ * Meaning of the values in this response is the same as for
+ * XENSND_OP_HW_PARAM_QUERY request.
*/
+/*
+ *----------------------------------- Events ----------------------------------
+ *
+ * Events are sent via shared page allocated by the front and propagated by
+ * evt-event-channel/evt-ring-ref XenStore entries
+ * All event packets have the same length (64 octets)
+ * All event packets have common header:
+ * 0 1 2 3 octet
+ * +----------------+----------------+----------------+----------------+
+ * | id | type | reserved | 4
+ * +----------------+----------------+----------------+----------------+
+ * | reserved | 8
+ * +----------------+----------------+----------------+----------------+
+ *
+ * id - uint16_t, event id, may be used by front
+ * type - uint8_t, type of the event
+ *
+ *
+ * Current stream position - event from back to front when stream's
+ * playback/capture position has advanced:
+ * 0 1 2 3 octet
+ * +----------------+----------------+----------------+----------------+
+ * | id | _EVT_CUR_POS | reserved | 4
+ * +----------------+----------------+----------------+----------------+
+ * | reserved | 8
+ * +----------------+----------------+----------------+----------------+
+ * | position low 32-bit | 12
+ * +----------------+----------------+----------------+----------------+
+ * | position high 32-bit | 16
+ * +----------------+----------------+----------------+----------------+
+ * | reserved | 20
+ * +----------------+----------------+----------------+----------------+
+ * |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
+ * +----------------+----------------+----------------+----------------+
+ * | reserved | 64
+ * +----------------+----------------+----------------+----------------+
+ *
+ * position - current value of stream's playback/capture position, octets
+ *
+ */
+
+struct xensnd_cur_pos_evt {
+ uint64_t position;
+};
+
struct xensnd_req {
uint16_t id;
uint8_t operation;
@@ -776,7 +1020,9 @@ struct xensnd_req {
union {
struct xensnd_open_req open;
struct xensnd_rw_req rw;
- uint8_t reserved[24];
+ struct xensnd_trigger_req trigger;
+ struct xensnd_query_hw_param hw_param;
+ uint8_t reserved[56];
} op;
};
@@ -785,9 +1031,53 @@ struct xensnd_resp {
uint8_t operation;
uint8_t reserved;
int32_t status;
- uint8_t reserved1[24];
+ union {
+ struct xensnd_query_hw_param hw_param;
+ uint8_t reserved1[56];
+ } resp;
+};
+
+struct xensnd_evt {
+ uint16_t id;
+ uint8_t type;
+ uint8_t reserved[5];
+ union {
+ struct xensnd_cur_pos_evt cur_pos;
+ uint8_t reserved[56];
+ } op;
};
DEFINE_RING_TYPES(xen_sndif, struct xensnd_req, struct xensnd_resp);
+/*
+ ******************************************************************************
+ * Back to front events delivery
+ ******************************************************************************
+ * In order to deliver asynchronous events from back to front a shared page is
+ * allocated by front and its granted reference propagated to back via
+ * XenStore entries (evt-ring-ref/evt-event-channel).
+ * This page has a common header used by both front and back to synchronize
+ * access and control event's ring buffer, while back being a producer of the
+ * events and front being a consumer. The rest of the page after the header
+ * is used for event packets.
+ *
+ * Upon reception of an event(s) front may confirm its reception
+ * for either each event, group of events or none.
+ */
+
+struct xensnd_event_page {
+ uint32_t in_cons;
+ uint32_t in_prod;
+ uint8_t reserved[56];
+};
+
+#define XENSND_EVENT_PAGE_SIZE XEN_PAGE_SIZE
+#define XENSND_IN_RING_OFFS (sizeof(struct xensnd_event_page))
+#define XENSND_IN_RING_SIZE (XENSND_EVENT_PAGE_SIZE - XENSND_IN_RING_OFFS)
+#define XENSND_IN_RING_LEN (XENSND_IN_RING_SIZE / sizeof(struct xensnd_evt))
+#define XENSND_IN_RING(page) \
+ ((struct xensnd_evt *)((char *)(page) + XENSND_IN_RING_OFFS))
+#define XENSND_IN_RING_REF(page, idx) \
+ (XENSND_IN_RING((page))[(idx) % XENSND_IN_RING_LEN])
+
#endif /* __XEN_PUBLIC_IO_SNDIF_H__ */
diff --git a/init/Kconfig b/init/Kconfig
index f013afc..18b151f 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -738,7 +738,7 @@
tasks running within the fair group scheduler. Groups with no limit
set are considered to be unconstrained and will run with no
restriction.
- See tip/Documentation/scheduler/sched-bwc.txt for more information.
+ See Documentation/scheduler/sched-bwc.txt for more information.
config RT_GROUP_SCHED
bool "Group scheduling for SCHED_RR/FIFO"
diff --git a/init/main.c b/init/main.c
index b795aa3..3b4ada1 100644
--- a/init/main.c
+++ b/init/main.c
@@ -91,6 +91,7 @@
#include <linux/cache.h>
#include <linux/rodata_test.h>
#include <linux/jump_label.h>
+#include <linux/mem_encrypt.h>
#include <asm/io.h>
#include <asm/bugs.h>
@@ -423,7 +424,7 @@ static noinline void __ref rest_init(void)
/*
* Enable might_sleep() and smp_processor_id() checks.
- * They cannot be enabled earlier because with CONFIG_PRREMPT=y
+ * They cannot be enabled earlier because with CONFIG_PREEMPT=y
* kernel_thread() would trigger might_sleep() splats. With
* CONFIG_PREEMPT_VOLUNTARY=y the init task might have scheduled
* already, but it's stuck on the kthreadd_done completion.
@@ -1034,6 +1035,13 @@ __setup("rodata=", set_debug_rodata);
static void mark_readonly(void)
{
if (rodata_enabled) {
+ /*
+ * load_module() results in W+X mappings, which are cleaned up
+ * with call_rcu_sched(). Let's make sure that queued work is
+ * flushed so that we don't hit false positives looking for
+ * insecure pages which are W+X.
+ */
+ rcu_barrier_sched();
mark_rodata_ro();
rodata_test();
} else
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index a808f29..c0d58f3 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -691,7 +691,7 @@ static void __do_notify(struct mqueue_inode_info *info)
wake_up(&info->wait_q);
}
-static int prepare_timeout(const struct timespec __user *u_abs_timeout,
+static int prepare_timeout(const struct __kernel_timespec __user *u_abs_timeout,
struct timespec64 *ts)
{
if (get_timespec64(ts, u_abs_timeout))
@@ -1128,7 +1128,7 @@ static int do_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr,
SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
size_t, msg_len, unsigned int, msg_prio,
- const struct timespec __user *, u_abs_timeout)
+ const struct __kernel_timespec __user *, u_abs_timeout)
{
struct timespec64 ts, *p = NULL;
if (u_abs_timeout) {
@@ -1142,7 +1142,7 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr,
size_t, msg_len, unsigned int __user *, u_msg_prio,
- const struct timespec __user *, u_abs_timeout)
+ const struct __kernel_timespec __user *, u_abs_timeout)
{
struct timespec64 ts, *p = NULL;
if (u_abs_timeout) {
@@ -1420,6 +1420,47 @@ COMPAT_SYSCALL_DEFINE4(mq_open, const char __user *, u_name,
return do_mq_open(u_name, oflag, mode, p);
}
+COMPAT_SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes,
+ const struct compat_sigevent __user *, u_notification)
+{
+ struct sigevent n, *p = NULL;
+ if (u_notification) {
+ if (get_compat_sigevent(&n, u_notification))
+ return -EFAULT;
+ if (n.sigev_notify == SIGEV_THREAD)
+ n.sigev_value.sival_ptr = compat_ptr(n.sigev_value.sival_int);
+ p = &n;
+ }
+ return do_mq_notify(mqdes, p);
+}
+
+COMPAT_SYSCALL_DEFINE3(mq_getsetattr, mqd_t, mqdes,
+ const struct compat_mq_attr __user *, u_mqstat,
+ struct compat_mq_attr __user *, u_omqstat)
+{
+ int ret;
+ struct mq_attr mqstat, omqstat;
+ struct mq_attr *new = NULL, *old = NULL;
+
+ if (u_mqstat) {
+ new = &mqstat;
+ if (get_compat_mq_attr(new, u_mqstat))
+ return -EFAULT;
+ }
+ if (u_omqstat)
+ old = &omqstat;
+
+ ret = do_mq_getsetattr(mqdes, new, old);
+ if (ret || !old)
+ return ret;
+
+ if (put_compat_mq_attr(old, u_omqstat))
+ return -EFAULT;
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_COMPAT_32BIT_TIME
static int compat_prepare_timeout(const struct compat_timespec __user *p,
struct timespec64 *ts)
{
@@ -1459,45 +1500,6 @@ COMPAT_SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes,
}
return do_mq_timedreceive(mqdes, u_msg_ptr, msg_len, u_msg_prio, p);
}
-
-COMPAT_SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes,
- const struct compat_sigevent __user *, u_notification)
-{
- struct sigevent n, *p = NULL;
- if (u_notification) {
- if (get_compat_sigevent(&n, u_notification))
- return -EFAULT;
- if (n.sigev_notify == SIGEV_THREAD)
- n.sigev_value.sival_ptr = compat_ptr(n.sigev_value.sival_int);
- p = &n;
- }
- return do_mq_notify(mqdes, p);
-}
-
-COMPAT_SYSCALL_DEFINE3(mq_getsetattr, mqd_t, mqdes,
- const struct compat_mq_attr __user *, u_mqstat,
- struct compat_mq_attr __user *, u_omqstat)
-{
- int ret;
- struct mq_attr mqstat, omqstat;
- struct mq_attr *new = NULL, *old = NULL;
-
- if (u_mqstat) {
- new = &mqstat;
- if (get_compat_mq_attr(new, u_mqstat))
- return -EFAULT;
- }
- if (u_omqstat)
- old = &omqstat;
-
- ret = do_mq_getsetattr(mqdes, new, old);
- if (ret || !old)
- return ret;
-
- if (put_compat_mq_attr(old, u_omqstat))
- return -EFAULT;
- return 0;
-}
#endif
static const struct inode_operations mqueue_dir_inode_operations = {
diff --git a/ipc/msg.c b/ipc/msg.c
index 56fd1c7..3b65453 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -537,6 +537,11 @@ static int msgctl_stat(struct ipc_namespace *ns, int msqid,
p->msg_stime = msq->q_stime;
p->msg_rtime = msq->q_rtime;
p->msg_ctime = msq->q_ctime;
+#ifndef CONFIG_64BIT
+ p->msg_stime_high = msq->q_stime >> 32;
+ p->msg_rtime_high = msq->q_rtime >> 32;
+ p->msg_ctime_high = msq->q_ctime >> 32;
+#endif
p->msg_cbytes = msq->q_cbytes;
p->msg_qnum = msq->q_qnum;
p->msg_qbytes = msq->q_qbytes;
@@ -646,9 +651,12 @@ static int copy_compat_msqid_to_user(void __user *buf, struct msqid64_ds *in,
struct compat_msqid64_ds v;
memset(&v, 0, sizeof(v));
to_compat_ipc64_perm(&v.msg_perm, &in->msg_perm);
- v.msg_stime = in->msg_stime;
- v.msg_rtime = in->msg_rtime;
- v.msg_ctime = in->msg_ctime;
+ v.msg_stime = lower_32_bits(in->msg_stime);
+ v.msg_stime_high = upper_32_bits(in->msg_stime);
+ v.msg_rtime = lower_32_bits(in->msg_rtime);
+ v.msg_rtime_high = upper_32_bits(in->msg_rtime);
+ v.msg_ctime = lower_32_bits(in->msg_ctime);
+ v.msg_ctime_high = upper_32_bits(in->msg_ctime);
v.msg_cbytes = in->msg_cbytes;
v.msg_qnum = in->msg_qnum;
v.msg_qbytes = in->msg_qbytes;
@@ -758,7 +766,7 @@ static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg,
WRITE_ONCE(msr->r_msg, ERR_PTR(-E2BIG));
} else {
ipc_update_pid(&msq->q_lrpid, task_pid(msr->r_tsk));
- msq->q_rtime = get_seconds();
+ msq->q_rtime = ktime_get_real_seconds();
wake_q_add(wake_q, msr->r_tsk);
WRITE_ONCE(msr->r_msg, msg);
@@ -859,7 +867,7 @@ static long do_msgsnd(int msqid, long mtype, void __user *mtext,
}
ipc_update_pid(&msq->q_lspid, task_tgid(current));
- msq->q_stime = get_seconds();
+ msq->q_stime = ktime_get_real_seconds();
if (!pipelined_send(msq, msg, &wake_q)) {
/* no one is waiting for this message, enqueue it */
@@ -1087,7 +1095,7 @@ static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, in
list_del(&msg->m_list);
msq->q_qnum--;
- msq->q_rtime = get_seconds();
+ msq->q_rtime = ktime_get_real_seconds();
ipc_update_pid(&msq->q_lrpid, task_tgid(current));
msq->q_cbytes -= msg->m_ts;
atomic_sub(msg->m_ts, &ns->msg_bytes);
diff --git a/ipc/sem.c b/ipc/sem.c
index 06be75d..cfd94d4 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -70,6 +70,7 @@
* The worst-case behavior is nevertheless O(N^2) for N wakeups.
*/
+#include <linux/compat.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/init.h>
@@ -104,7 +105,7 @@ struct sem {
/* that alter the semaphore */
struct list_head pending_const; /* pending single-sop operations */
/* that do not alter the semaphore*/
- time_t sem_otime; /* candidate for sem_otime */
+ time64_t sem_otime; /* candidate for sem_otime */
} ____cacheline_aligned_in_smp;
/* One sem_array data structure for each set of semaphores in the system. */
@@ -984,10 +985,10 @@ static int update_queue(struct sem_array *sma, int semnum, struct wake_q_head *w
static void set_semotime(struct sem_array *sma, struct sembuf *sops)
{
if (sops == NULL) {
- sma->sems[0].sem_otime = get_seconds();
+ sma->sems[0].sem_otime = ktime_get_real_seconds();
} else {
sma->sems[sops[0].sem_num].sem_otime =
- get_seconds();
+ ktime_get_real_seconds();
}
}
@@ -1214,6 +1215,7 @@ static int semctl_stat(struct ipc_namespace *ns, int semid,
int cmd, struct semid64_ds *semid64)
{
struct sem_array *sma;
+ time64_t semotime;
int id = 0;
int err;
@@ -1257,8 +1259,13 @@ static int semctl_stat(struct ipc_namespace *ns, int semid,
}
kernel_to_ipc64_perm(&sma->sem_perm, &semid64->sem_perm);
- semid64->sem_otime = get_semotime(sma);
+ semotime = get_semotime(sma);
+ semid64->sem_otime = semotime;
semid64->sem_ctime = sma->sem_ctime;
+#ifndef CONFIG_64BIT
+ semid64->sem_otime_high = semotime >> 32;
+ semid64->sem_ctime_high = sma->sem_ctime >> 32;
+#endif
semid64->sem_nsems = sma->sem_nsems;
ipc_unlock_object(&sma->sem_perm);
@@ -1704,8 +1711,10 @@ static int copy_compat_semid_to_user(void __user *buf, struct semid64_ds *in,
struct compat_semid64_ds v;
memset(&v, 0, sizeof(v));
to_compat_ipc64_perm(&v.sem_perm, &in->sem_perm);
- v.sem_otime = in->sem_otime;
- v.sem_ctime = in->sem_ctime;
+ v.sem_otime = lower_32_bits(in->sem_otime);
+ v.sem_otime_high = upper_32_bits(in->sem_otime);
+ v.sem_ctime = lower_32_bits(in->sem_ctime);
+ v.sem_ctime_high = upper_32_bits(in->sem_ctime);
v.sem_nsems = in->sem_nsems;
return copy_to_user(buf, &v, sizeof(v));
} else {
@@ -2168,7 +2177,7 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops,
}
long ksys_semtimedop(int semid, struct sembuf __user *tsops,
- unsigned int nsops, const struct timespec __user *timeout)
+ unsigned int nsops, const struct __kernel_timespec __user *timeout)
{
if (timeout) {
struct timespec64 ts;
@@ -2180,12 +2189,12 @@ long ksys_semtimedop(int semid, struct sembuf __user *tsops,
}
SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
- unsigned int, nsops, const struct timespec __user *, timeout)
+ unsigned int, nsops, const struct __kernel_timespec __user *, timeout)
{
return ksys_semtimedop(semid, tsops, nsops, timeout);
}
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
long compat_ksys_semtimedop(int semid, struct sembuf __user *tsems,
unsigned int nsops,
const struct compat_timespec __user *timeout)
diff --git a/ipc/shm.c b/ipc/shm.c
index 3cf4898..29978ee 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -1002,6 +1002,11 @@ static int shmctl_stat(struct ipc_namespace *ns, int shmid,
tbuf->shm_atime = shp->shm_atim;
tbuf->shm_dtime = shp->shm_dtim;
tbuf->shm_ctime = shp->shm_ctim;
+#ifndef CONFIG_64BIT
+ tbuf->shm_atime_high = shp->shm_atim >> 32;
+ tbuf->shm_dtime_high = shp->shm_dtim >> 32;
+ tbuf->shm_ctime_high = shp->shm_ctim >> 32;
+#endif
tbuf->shm_cpid = pid_vnr(shp->shm_cprid);
tbuf->shm_lpid = pid_vnr(shp->shm_lprid);
tbuf->shm_nattch = shp->shm_nattch;
@@ -1233,9 +1238,12 @@ static int copy_compat_shmid_to_user(void __user *buf, struct shmid64_ds *in,
struct compat_shmid64_ds v;
memset(&v, 0, sizeof(v));
to_compat_ipc64_perm(&v.shm_perm, &in->shm_perm);
- v.shm_atime = in->shm_atime;
- v.shm_dtime = in->shm_dtime;
- v.shm_ctime = in->shm_ctime;
+ v.shm_atime = lower_32_bits(in->shm_atime);
+ v.shm_atime_high = upper_32_bits(in->shm_atime);
+ v.shm_dtime = lower_32_bits(in->shm_dtime);
+ v.shm_dtime_high = upper_32_bits(in->shm_dtime);
+ v.shm_ctime = lower_32_bits(in->shm_ctime);
+ v.shm_ctime_high = upper_32_bits(in->shm_ctime);
v.shm_segsz = in->shm_segsz;
v.shm_nattch = in->shm_nattch;
v.shm_cpid = in->shm_cpid;
@@ -1363,14 +1371,17 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
if (addr) {
if (addr & (shmlba - 1)) {
- /*
- * Round down to the nearest multiple of shmlba.
- * For sane do_mmap_pgoff() parameters, avoid
- * round downs that trigger nil-page and MAP_FIXED.
- */
- if ((shmflg & SHM_RND) && addr >= shmlba)
- addr &= ~(shmlba - 1);
- else
+ if (shmflg & SHM_RND) {
+ addr &= ~(shmlba - 1); /* round down */
+
+ /*
+ * Ensure that the round-down is non-nil
+ * when remapping. This can happen for
+ * cases when addr < shmlba.
+ */
+ if (!addr && (shmflg & SHM_REMAP))
+ goto out;
+ } else
#ifndef __ARCH_FORCE_SHMLBA
if (addr & ~PAGE_MASK)
#endif
diff --git a/ipc/syscall.c b/ipc/syscall.c
index 77a883e..65d405f 100644
--- a/ipc/syscall.c
+++ b/ipc/syscall.c
@@ -30,9 +30,14 @@ SYSCALL_DEFINE6(ipc, unsigned int, call, int, first, unsigned long, second,
return ksys_semtimedop(first, (struct sembuf __user *)ptr,
second, NULL);
case SEMTIMEDOP:
- return ksys_semtimedop(first, (struct sembuf __user *)ptr,
- second,
- (const struct timespec __user *)fifth);
+ if (IS_ENABLED(CONFIG_64BIT) || !IS_ENABLED(CONFIG_64BIT_TIME))
+ return ksys_semtimedop(first, ptr, second,
+ (const struct __kernel_timespec __user *)fifth);
+ else if (IS_ENABLED(CONFIG_COMPAT_32BIT_TIME))
+ return compat_ksys_semtimedop(first, ptr, second,
+ (const struct compat_timespec __user *)fifth);
+ else
+ return -ENOSYS;
case SEMGET:
return ksys_semget(first, second, third);
@@ -130,6 +135,8 @@ COMPAT_SYSCALL_DEFINE6(ipc, u32, call, int, first, int, second,
/* struct sembuf is the same on 32 and 64bit :)) */
return ksys_semtimedop(first, compat_ptr(ptr), second, NULL);
case SEMTIMEDOP:
+ if (!IS_ENABLED(CONFIG_COMPAT_32BIT_TIME))
+ return -ENOSYS;
return compat_ksys_semtimedop(first, compat_ptr(ptr), second,
compat_ptr(fifth));
case SEMGET:
diff --git a/ipc/util.h b/ipc/util.h
index acc5159..0aba323 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -251,7 +251,7 @@ static inline int compat_ipc_parse_version(int *cmd)
/* for __ARCH_WANT_SYS_IPC */
long ksys_semtimedop(int semid, struct sembuf __user *tsops,
unsigned int nsops,
- const struct timespec __user *timeout);
+ const struct __kernel_timespec __user *timeout);
long ksys_semget(key_t key, int nsems, int semflg);
long ksys_semctl(int semid, int semnum, int cmd, unsigned long arg);
long ksys_msgget(key_t key, int msgflg);
@@ -265,10 +265,10 @@ long ksys_shmdt(char __user *shmaddr);
long ksys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf);
/* for CONFIG_ARCH_WANT_OLD_COMPAT_IPC */
-#ifdef CONFIG_COMPAT
long compat_ksys_semtimedop(int semid, struct sembuf __user *tsems,
unsigned int nsops,
const struct compat_timespec __user *timeout);
+#ifdef CONFIG_COMPAT
long compat_ksys_semctl(int semid, int semnum, int cmd, int arg);
long compat_ksys_msgctl(int msqid, int cmd, void __user *uptr);
long compat_ksys_msgrcv(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz,
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 14750e7..027107f 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -476,7 +476,7 @@ static u32 prog_fd_array_sys_lookup_elem(void *ptr)
}
/* decrement refcnt of all bpf_progs that are stored in this map */
-void bpf_fd_array_map_clear(struct bpf_map *map)
+static void bpf_fd_array_map_clear(struct bpf_map *map)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
int i;
@@ -495,6 +495,7 @@ const struct bpf_map_ops prog_array_map_ops = {
.map_fd_get_ptr = prog_fd_array_get_ptr,
.map_fd_put_ptr = prog_fd_array_put_ptr,
.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
+ .map_release_uref = bpf_fd_array_map_clear,
};
static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index d315b39..6ef6746 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -218,47 +218,84 @@ int bpf_prog_calc_tag(struct bpf_prog *fp)
return 0;
}
-static void bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta)
+static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, u32 delta,
+ u32 curr, const bool probe_pass)
{
+ const s64 imm_min = S32_MIN, imm_max = S32_MAX;
+ s64 imm = insn->imm;
+
+ if (curr < pos && curr + imm + 1 > pos)
+ imm += delta;
+ else if (curr > pos + delta && curr + imm + 1 <= pos + delta)
+ imm -= delta;
+ if (imm < imm_min || imm > imm_max)
+ return -ERANGE;
+ if (!probe_pass)
+ insn->imm = imm;
+ return 0;
+}
+
+static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, u32 delta,
+ u32 curr, const bool probe_pass)
+{
+ const s32 off_min = S16_MIN, off_max = S16_MAX;
+ s32 off = insn->off;
+
+ if (curr < pos && curr + off + 1 > pos)
+ off += delta;
+ else if (curr > pos + delta && curr + off + 1 <= pos + delta)
+ off -= delta;
+ if (off < off_min || off > off_max)
+ return -ERANGE;
+ if (!probe_pass)
+ insn->off = off;
+ return 0;
+}
+
+static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta,
+ const bool probe_pass)
+{
+ u32 i, insn_cnt = prog->len + (probe_pass ? delta : 0);
struct bpf_insn *insn = prog->insnsi;
- u32 i, insn_cnt = prog->len;
- bool pseudo_call;
- u8 code;
- int off;
+ int ret = 0;
for (i = 0; i < insn_cnt; i++, insn++) {
- code = insn->code;
- if (BPF_CLASS(code) != BPF_JMP)
- continue;
- if (BPF_OP(code) == BPF_EXIT)
- continue;
- if (BPF_OP(code) == BPF_CALL) {
- if (insn->src_reg == BPF_PSEUDO_CALL)
- pseudo_call = true;
- else
- continue;
- } else {
- pseudo_call = false;
+ u8 code;
+
+ /* In the probing pass we still operate on the original,
+ * unpatched image in order to check overflows before we
+ * do any other adjustments. Therefore skip the patchlet.
+ */
+ if (probe_pass && i == pos) {
+ i += delta + 1;
+ insn++;
}
- off = pseudo_call ? insn->imm : insn->off;
-
- /* Adjust offset of jmps if we cross boundaries. */
- if (i < pos && i + off + 1 > pos)
- off += delta;
- else if (i > pos + delta && i + off + 1 <= pos + delta)
- off -= delta;
-
- if (pseudo_call)
- insn->imm = off;
- else
- insn->off = off;
+ code = insn->code;
+ if (BPF_CLASS(code) != BPF_JMP ||
+ BPF_OP(code) == BPF_EXIT)
+ continue;
+ /* Adjust offset of jmps if we cross patch boundaries. */
+ if (BPF_OP(code) == BPF_CALL) {
+ if (insn->src_reg != BPF_PSEUDO_CALL)
+ continue;
+ ret = bpf_adj_delta_to_imm(insn, pos, delta, i,
+ probe_pass);
+ } else {
+ ret = bpf_adj_delta_to_off(insn, pos, delta, i,
+ probe_pass);
+ }
+ if (ret)
+ break;
}
+
+ return ret;
}
struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
const struct bpf_insn *patch, u32 len)
{
u32 insn_adj_cnt, insn_rest, insn_delta = len - 1;
+ const u32 cnt_max = S16_MAX;
struct bpf_prog *prog_adj;
/* Since our patchlet doesn't expand the image, we're done. */
@@ -269,6 +306,15 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
insn_adj_cnt = prog->len + insn_delta;
+ /* Reject anything that would potentially let the insn->off
+ * target overflow when we have excessive program expansions.
+ * We need to probe here before we do any reallocation where
+ * we afterwards may not fail anymore.
+ */
+ if (insn_adj_cnt > cnt_max &&
+ bpf_adj_branches(prog, off, insn_delta, true))
+ return NULL;
+
/* Several new instructions need to be inserted. Make room
* for them. Likely, there's no need for a new allocation as
* last page could have large enough tailroom.
@@ -294,7 +340,11 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
sizeof(*patch) * insn_rest);
memcpy(prog_adj->insnsi + off, patch, sizeof(*patch) * len);
- bpf_adj_branches(prog_adj, off, insn_delta);
+ /* We are guaranteed to not fail at this point, otherwise
+ * the ship has sailed to reverse to the original state. An
+ * overflow cannot happen at this point.
+ */
+ BUG_ON(bpf_adj_branches(prog_adj, off, insn_delta, false));
return prog_adj;
}
@@ -1572,13 +1622,32 @@ int bpf_prog_array_length(struct bpf_prog_array __rcu *progs)
return cnt;
}
+static bool bpf_prog_array_copy_core(struct bpf_prog **prog,
+ u32 *prog_ids,
+ u32 request_cnt)
+{
+ int i = 0;
+
+ for (; *prog; prog++) {
+ if (*prog == &dummy_bpf_prog.prog)
+ continue;
+ prog_ids[i] = (*prog)->aux->id;
+ if (++i == request_cnt) {
+ prog++;
+ break;
+ }
+ }
+
+ return !!(*prog);
+}
+
int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
__u32 __user *prog_ids, u32 cnt)
{
struct bpf_prog **prog;
unsigned long err = 0;
- u32 i = 0, *ids;
bool nospc;
+ u32 *ids;
/* users of this function are doing:
* cnt = bpf_prog_array_length();
@@ -1595,16 +1664,7 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
return -ENOMEM;
rcu_read_lock();
prog = rcu_dereference(progs)->progs;
- for (; *prog; prog++) {
- if (*prog == &dummy_bpf_prog.prog)
- continue;
- ids[i] = (*prog)->aux->id;
- if (++i == cnt) {
- prog++;
- break;
- }
- }
- nospc = !!(*prog);
+ nospc = bpf_prog_array_copy_core(prog, ids, cnt);
rcu_read_unlock();
err = copy_to_user(prog_ids, ids, cnt * sizeof(u32));
kfree(ids);
@@ -1683,22 +1743,25 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
}
int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
- __u32 __user *prog_ids, u32 request_cnt,
- __u32 __user *prog_cnt)
+ u32 *prog_ids, u32 request_cnt,
+ u32 *prog_cnt)
{
+ struct bpf_prog **prog;
u32 cnt = 0;
if (array)
cnt = bpf_prog_array_length(array);
- if (copy_to_user(prog_cnt, &cnt, sizeof(cnt)))
- return -EFAULT;
+ *prog_cnt = cnt;
/* return early if user requested only program count or nothing to copy */
if (!request_cnt || !cnt)
return 0;
- return bpf_prog_array_copy_to_user(array, prog_ids, request_cnt);
+ /* this function is called under trace/bpf_trace.c: bpf_event_mutex */
+ prog = rcu_dereference_check(array, 1)->progs;
+ return bpf_prog_array_copy_core(prog, prog_ids, request_cnt) ? -ENOSPC
+ : 0;
}
static void bpf_prog_free_deferred(struct work_struct *work)
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 8dd9210..95a84b2 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -43,6 +43,7 @@
#include <net/tcp.h>
#include <linux/ptr_ring.h>
#include <net/inet_common.h>
+#include <linux/sched/signal.h>
#define SOCK_CREATE_FLAG_MASK \
(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
@@ -325,6 +326,9 @@ static int bpf_tcp_push(struct sock *sk, int apply_bytes,
if (ret > 0) {
if (apply)
apply_bytes -= ret;
+
+ sg->offset += ret;
+ sg->length -= ret;
size -= ret;
offset += ret;
if (uncharge)
@@ -332,8 +336,6 @@ static int bpf_tcp_push(struct sock *sk, int apply_bytes,
goto retry;
}
- sg->length = size;
- sg->offset = offset;
return ret;
}
@@ -391,7 +393,8 @@ static void return_mem_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
} while (i != md->sg_end);
}
-static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
+static void free_bytes_sg(struct sock *sk, int bytes,
+ struct sk_msg_buff *md, bool charge)
{
struct scatterlist *sg = md->sg_data;
int i = md->sg_start, free;
@@ -401,11 +404,13 @@ static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
if (bytes < free) {
sg[i].length -= bytes;
sg[i].offset += bytes;
- sk_mem_uncharge(sk, bytes);
+ if (charge)
+ sk_mem_uncharge(sk, bytes);
break;
}
- sk_mem_uncharge(sk, sg[i].length);
+ if (charge)
+ sk_mem_uncharge(sk, sg[i].length);
put_page(sg_page(&sg[i]));
bytes -= sg[i].length;
sg[i].length = 0;
@@ -416,6 +421,7 @@ static void free_bytes_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
if (i == MAX_SKB_FRAGS)
i = 0;
}
+ md->sg_start = i;
}
static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
@@ -523,8 +529,6 @@ static int bpf_tcp_ingress(struct sock *sk, int apply_bytes,
i = md->sg_start;
do {
- r->sg_data[i] = md->sg_data[i];
-
size = (apply && apply_bytes < md->sg_data[i].length) ?
apply_bytes : md->sg_data[i].length;
@@ -535,6 +539,7 @@ static int bpf_tcp_ingress(struct sock *sk, int apply_bytes,
}
sk_mem_charge(sk, size);
+ r->sg_data[i] = md->sg_data[i];
r->sg_data[i].length = size;
md->sg_data[i].length -= size;
md->sg_data[i].offset += size;
@@ -575,10 +580,10 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
struct sk_msg_buff *md,
int flags)
{
+ bool ingress = !!(md->flags & BPF_F_INGRESS);
struct smap_psock *psock;
struct scatterlist *sg;
- int i, err, free = 0;
- bool ingress = !!(md->flags & BPF_F_INGRESS);
+ int err = 0;
sg = md->sg_data;
@@ -606,16 +611,8 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
out_rcu:
rcu_read_unlock();
out:
- i = md->sg_start;
- while (sg[i].length) {
- free += sg[i].length;
- put_page(sg_page(&sg[i]));
- sg[i].length = 0;
- i++;
- if (i == MAX_SKB_FRAGS)
- i = 0;
- }
- return free;
+ free_bytes_sg(NULL, send, md, false);
+ return err;
}
static inline void bpf_md_init(struct smap_psock *psock)
@@ -700,19 +697,26 @@ static int bpf_exec_tx_verdict(struct smap_psock *psock,
err = bpf_tcp_sendmsg_do_redirect(redir, send, m, flags);
lock_sock(sk);
+ if (unlikely(err < 0)) {
+ free_start_sg(sk, m);
+ psock->sg_size = 0;
+ if (!cork)
+ *copied -= send;
+ } else {
+ psock->sg_size -= send;
+ }
+
if (cork) {
free_start_sg(sk, m);
+ psock->sg_size = 0;
kfree(m);
m = NULL;
+ err = 0;
}
- if (unlikely(err))
- *copied -= err;
- else
- psock->sg_size -= send;
break;
case __SK_DROP:
default:
- free_bytes_sg(sk, send, m);
+ free_bytes_sg(sk, send, m, true);
apply_bytes_dec(psock, send);
*copied -= send;
psock->sg_size -= send;
@@ -732,6 +736,26 @@ static int bpf_exec_tx_verdict(struct smap_psock *psock,
return err;
}
+static int bpf_wait_data(struct sock *sk,
+ struct smap_psock *psk, int flags,
+ long timeo, int *err)
+{
+ int rc;
+
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
+
+ add_wait_queue(sk_sleep(sk), &wait);
+ sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+ rc = sk_wait_event(sk, &timeo,
+ !list_empty(&psk->ingress) ||
+ !skb_queue_empty(&sk->sk_receive_queue),
+ &wait);
+ sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+ remove_wait_queue(sk_sleep(sk), &wait);
+
+ return rc;
+}
+
static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int nonblock, int flags, int *addr_len)
{
@@ -755,6 +779,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
lock_sock(sk);
+bytes_ready:
while (copied != len) {
struct scatterlist *sg;
struct sk_msg_buff *md;
@@ -809,6 +834,28 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
}
}
+ if (!copied) {
+ long timeo;
+ int data;
+ int err = 0;
+
+ timeo = sock_rcvtimeo(sk, nonblock);
+ data = bpf_wait_data(sk, psock, flags, timeo, &err);
+
+ if (data) {
+ if (!skb_queue_empty(&sk->sk_receive_queue)) {
+ release_sock(sk);
+ smap_release_sock(psock, sk);
+ copied = tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+ return copied;
+ }
+ goto bytes_ready;
+ }
+
+ if (err)
+ copied = err;
+ }
+
release_sock(sk);
smap_release_sock(psock, sk);
return copied;
@@ -1442,9 +1489,6 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
return ERR_PTR(-EINVAL);
- if (attr->value_size > KMALLOC_MAX_SIZE)
- return ERR_PTR(-E2BIG);
-
err = bpf_tcp_ulp_register();
if (err && err != -EEXIST)
return ERR_PTR(err);
@@ -1659,11 +1703,11 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
* we increment the refcnt. If this is the case abort with an
* error.
*/
- verdict = bpf_prog_inc_not_zero(stab->bpf_verdict);
+ verdict = bpf_prog_inc_not_zero(verdict);
if (IS_ERR(verdict))
return PTR_ERR(verdict);
- parse = bpf_prog_inc_not_zero(stab->bpf_parse);
+ parse = bpf_prog_inc_not_zero(parse);
if (IS_ERR(parse)) {
bpf_prog_put(verdict);
return PTR_ERR(parse);
@@ -1671,12 +1715,12 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
}
if (tx_msg) {
- tx_msg = bpf_prog_inc_not_zero(stab->bpf_tx_msg);
+ tx_msg = bpf_prog_inc_not_zero(tx_msg);
if (IS_ERR(tx_msg)) {
- if (verdict)
- bpf_prog_put(verdict);
- if (parse)
+ if (parse && verdict) {
bpf_prog_put(parse);
+ bpf_prog_put(verdict);
+ }
return PTR_ERR(tx_msg);
}
}
@@ -1761,10 +1805,10 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
out_free:
smap_release_sock(psock, sock);
out_progs:
- if (verdict)
- bpf_prog_put(verdict);
- if (parse)
+ if (parse && verdict) {
bpf_prog_put(parse);
+ bpf_prog_put(verdict);
+ }
if (tx_msg)
bpf_prog_put(tx_msg);
write_unlock_bh(&sock->sk_callback_lock);
@@ -1834,7 +1878,7 @@ static int sock_map_update_elem(struct bpf_map *map,
return err;
}
-static void sock_map_release(struct bpf_map *map, struct file *map_file)
+static void sock_map_release(struct bpf_map *map)
{
struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
struct bpf_prog *orig;
@@ -1858,7 +1902,7 @@ const struct bpf_map_ops sock_map_ops = {
.map_get_next_key = sock_map_get_next_key,
.map_update_elem = sock_map_update_elem,
.map_delete_elem = sock_map_delete_elem,
- .map_release = sock_map_release,
+ .map_release_uref = sock_map_release,
};
BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4ca46df..016ef90 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -26,6 +26,7 @@
#include <linux/cred.h>
#include <linux/timekeeping.h>
#include <linux/ctype.h>
+#include <linux/nospec.h>
#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \
(map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
@@ -102,12 +103,14 @@ const struct bpf_map_ops bpf_map_offload_ops = {
static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
{
const struct bpf_map_ops *ops;
+ u32 type = attr->map_type;
struct bpf_map *map;
int err;
- if (attr->map_type >= ARRAY_SIZE(bpf_map_types))
+ if (type >= ARRAY_SIZE(bpf_map_types))
return ERR_PTR(-EINVAL);
- ops = bpf_map_types[attr->map_type];
+ type = array_index_nospec(type, ARRAY_SIZE(bpf_map_types));
+ ops = bpf_map_types[type];
if (!ops)
return ERR_PTR(-EINVAL);
@@ -122,7 +125,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
if (IS_ERR(map))
return map;
map->ops = ops;
- map->map_type = attr->map_type;
+ map->map_type = type;
return map;
}
@@ -257,8 +260,8 @@ static void bpf_map_free_deferred(struct work_struct *work)
static void bpf_map_put_uref(struct bpf_map *map)
{
if (atomic_dec_and_test(&map->usercnt)) {
- if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
- bpf_fd_array_map_clear(map);
+ if (map->ops->map_release_uref)
+ map->ops->map_release_uref(map);
}
}
@@ -871,11 +874,17 @@ static const struct bpf_prog_ops * const bpf_prog_types[] = {
static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
{
- if (type >= ARRAY_SIZE(bpf_prog_types) || !bpf_prog_types[type])
+ const struct bpf_prog_ops *ops;
+
+ if (type >= ARRAY_SIZE(bpf_prog_types))
+ return -EINVAL;
+ type = array_index_nospec(type, ARRAY_SIZE(bpf_prog_types));
+ ops = bpf_prog_types[type];
+ if (!ops)
return -EINVAL;
if (!bpf_prog_is_dev_bound(prog->aux))
- prog->aux->ops = bpf_prog_types[type];
+ prog->aux->ops = ops;
else
prog->aux->ops = &bpf_offload_prog_ops;
prog->type = type;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5dd1dcb..1904e81 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -156,7 +156,29 @@ struct bpf_verifier_stack_elem {
#define BPF_COMPLEXITY_LIMIT_INSNS 131072
#define BPF_COMPLEXITY_LIMIT_STACK 1024
-#define BPF_MAP_PTR_POISON ((void *)0xeB9F + POISON_POINTER_DELTA)
+#define BPF_MAP_PTR_UNPRIV 1UL
+#define BPF_MAP_PTR_POISON ((void *)((0xeB9FUL << 1) + \
+ POISON_POINTER_DELTA))
+#define BPF_MAP_PTR(X) ((struct bpf_map *)((X) & ~BPF_MAP_PTR_UNPRIV))
+
+static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux)
+{
+ return BPF_MAP_PTR(aux->map_state) == BPF_MAP_PTR_POISON;
+}
+
+static bool bpf_map_ptr_unpriv(const struct bpf_insn_aux_data *aux)
+{
+ return aux->map_state & BPF_MAP_PTR_UNPRIV;
+}
+
+static void bpf_map_ptr_store(struct bpf_insn_aux_data *aux,
+ const struct bpf_map *map, bool unpriv)
+{
+ BUILD_BUG_ON((unsigned long)BPF_MAP_PTR_POISON & BPF_MAP_PTR_UNPRIV);
+ unpriv |= bpf_map_ptr_unpriv(aux);
+ aux->map_state = (unsigned long)map |
+ (unpriv ? BPF_MAP_PTR_UNPRIV : 0UL);
+}
struct bpf_call_arg_meta {
struct bpf_map *map_ptr;
@@ -978,7 +1000,7 @@ static bool register_is_null(struct bpf_reg_state *reg)
*/
static int check_stack_write(struct bpf_verifier_env *env,
struct bpf_func_state *state, /* func where register points to */
- int off, int size, int value_regno)
+ int off, int size, int value_regno, int insn_idx)
{
struct bpf_func_state *cur; /* state of the current function */
int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
@@ -1017,8 +1039,33 @@ static int check_stack_write(struct bpf_verifier_env *env,
state->stack[spi].spilled_ptr = cur->regs[value_regno];
state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
- for (i = 0; i < BPF_REG_SIZE; i++)
+ for (i = 0; i < BPF_REG_SIZE; i++) {
+ if (state->stack[spi].slot_type[i] == STACK_MISC &&
+ !env->allow_ptr_leaks) {
+ int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off;
+ int soff = (-spi - 1) * BPF_REG_SIZE;
+
+ /* detected reuse of integer stack slot with a pointer
+ * which means either llvm is reusing stack slot or
+ * an attacker is trying to exploit CVE-2018-3639
+ * (speculative store bypass)
+ * Have to sanitize that slot with preemptive
+ * store of zero.
+ */
+ if (*poff && *poff != soff) {
+ /* disallow programs where single insn stores
+ * into two different stack slots, since verifier
+ * cannot sanitize them
+ */
+ verbose(env,
+ "insn %d cannot access two stack slots fp%d and fp%d",
+ insn_idx, *poff, soff);
+ return -EINVAL;
+ }
+ *poff = soff;
+ }
state->stack[spi].slot_type[i] = STACK_SPILL;
+ }
} else {
u8 type = STACK_MISC;
@@ -1694,7 +1741,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
if (t == BPF_WRITE)
err = check_stack_write(env, state, off, size,
- value_regno);
+ value_regno, insn_idx);
else
err = check_stack_read(env, state, off, size,
value_regno);
@@ -2333,6 +2380,29 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
return 0;
}
+static int
+record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
+ int func_id, int insn_idx)
+{
+ struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
+
+ if (func_id != BPF_FUNC_tail_call &&
+ func_id != BPF_FUNC_map_lookup_elem)
+ return 0;
+ if (meta->map_ptr == NULL) {
+ verbose(env, "kernel subsystem misconfigured verifier\n");
+ return -EINVAL;
+ }
+
+ if (!BPF_MAP_PTR(aux->map_state))
+ bpf_map_ptr_store(aux, meta->map_ptr,
+ meta->map_ptr->unpriv_array);
+ else if (BPF_MAP_PTR(aux->map_state) != meta->map_ptr)
+ bpf_map_ptr_store(aux, BPF_MAP_PTR_POISON,
+ meta->map_ptr->unpriv_array);
+ return 0;
+}
+
static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
{
const struct bpf_func_proto *fn = NULL;
@@ -2387,13 +2457,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta);
if (err)
return err;
- if (func_id == BPF_FUNC_tail_call) {
- if (meta.map_ptr == NULL) {
- verbose(env, "verifier bug\n");
- return -EINVAL;
- }
- env->insn_aux_data[insn_idx].map_ptr = meta.map_ptr;
- }
err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta);
if (err)
return err;
@@ -2404,6 +2467,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
if (err)
return err;
+ err = record_func_map(env, &meta, func_id, insn_idx);
+ if (err)
+ return err;
+
/* Mark slots with STACK_MISC in case of raw mode, stack offset
* is inferred from register state.
*/
@@ -2428,8 +2495,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
} else if (fn->ret_type == RET_VOID) {
regs[BPF_REG_0].type = NOT_INIT;
} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) {
- struct bpf_insn_aux_data *insn_aux;
-
regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
/* There is no offset yet applied, variable or fixed */
mark_reg_known_zero(env, regs, BPF_REG_0);
@@ -2445,11 +2510,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
}
regs[BPF_REG_0].map_ptr = meta.map_ptr;
regs[BPF_REG_0].id = ++env->id_gen;
- insn_aux = &env->insn_aux_data[insn_idx];
- if (!insn_aux->map_ptr)
- insn_aux->map_ptr = meta.map_ptr;
- else if (insn_aux->map_ptr != meta.map_ptr)
- insn_aux->map_ptr = BPF_MAP_PTR_POISON;
} else {
verbose(env, "unknown return type %d of func %s#%d\n",
fn->ret_type, func_id_name(func_id), func_id);
@@ -5169,6 +5229,34 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
else
continue;
+ if (type == BPF_WRITE &&
+ env->insn_aux_data[i + delta].sanitize_stack_off) {
+ struct bpf_insn patch[] = {
+ /* Sanitize suspicious stack slot with zero.
+ * There are no memory dependencies for this store,
+ * since it's only using frame pointer and immediate
+ * constant of zero
+ */
+ BPF_ST_MEM(BPF_DW, BPF_REG_FP,
+ env->insn_aux_data[i + delta].sanitize_stack_off,
+ 0),
+ /* the original STX instruction will immediately
+ * overwrite the same stack slot with appropriate value
+ */
+ *insn,
+ };
+
+ cnt = ARRAY_SIZE(patch);
+ new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX)
continue;
@@ -5417,6 +5505,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
struct bpf_insn *insn = prog->insnsi;
const struct bpf_func_proto *fn;
const int insn_cnt = prog->len;
+ struct bpf_insn_aux_data *aux;
struct bpf_insn insn_buf[16];
struct bpf_prog *new_prog;
struct bpf_map *map_ptr;
@@ -5491,19 +5580,22 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
insn->imm = 0;
insn->code = BPF_JMP | BPF_TAIL_CALL;
+ aux = &env->insn_aux_data[i + delta];
+ if (!bpf_map_ptr_unpriv(aux))
+ continue;
+
/* instead of changing every JIT dealing with tail_call
* emit two extra insns:
* if (index >= max_entries) goto out;
* index &= array->index_mask;
* to avoid out-of-bounds cpu speculation
*/
- map_ptr = env->insn_aux_data[i + delta].map_ptr;
- if (map_ptr == BPF_MAP_PTR_POISON) {
+ if (bpf_map_ptr_poisoned(aux)) {
verbose(env, "tail_call abusing map_ptr\n");
return -EINVAL;
}
- if (!map_ptr->unpriv_array)
- continue;
+
+ map_ptr = BPF_MAP_PTR(aux->map_state);
insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3,
map_ptr->max_entries, 2);
insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3,
@@ -5527,9 +5619,12 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
*/
if (prog->jit_requested && BITS_PER_LONG == 64 &&
insn->imm == BPF_FUNC_map_lookup_elem) {
- map_ptr = env->insn_aux_data[i + delta].map_ptr;
- if (map_ptr == BPF_MAP_PTR_POISON ||
- !map_ptr->ops->map_gen_lookup)
+ aux = &env->insn_aux_data[i + delta];
+ if (bpf_map_ptr_poisoned(aux))
+ goto patch_call_imm;
+
+ map_ptr = BPF_MAP_PTR(aux->map_state);
+ if (!map_ptr->ops->map_gen_lookup)
goto patch_call_imm;
cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf);
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index b928b27..0808a33 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -218,9 +218,9 @@ extern const struct proc_ns_operations cgroupns_operations;
* cgroup-v1.c
*/
extern struct cftype cgroup1_base_files[];
-extern const struct file_operations proc_cgroupstats_operations;
extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops;
+int proc_cgroupstats_show(struct seq_file *m, void *v);
bool cgroup1_ssid_disabled(int ssid);
void cgroup1_pidlist_destroy_all(struct cgroup *cgrp);
void cgroup1_release_agent(struct work_struct *work);
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index a2c05d2..e06c97f 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -682,7 +682,7 @@ struct cftype cgroup1_base_files[] = {
};
/* Display information about each subsystem and each hierarchy */
-static int proc_cgroupstats_show(struct seq_file *m, void *v)
+int proc_cgroupstats_show(struct seq_file *m, void *v)
{
struct cgroup_subsys *ss;
int i;
@@ -705,18 +705,6 @@ static int proc_cgroupstats_show(struct seq_file *m, void *v)
return 0;
}
-static int cgroupstats_open(struct inode *inode, struct file *file)
-{
- return single_open(file, proc_cgroupstats_show, NULL);
-}
-
-const struct file_operations proc_cgroupstats_operations = {
- .open = cgroupstats_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/**
* cgroupstats_build - build and fill cgroupstats
* @stats: cgroupstats to fill information into
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index a662bfc..1288365 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -5335,7 +5335,7 @@ int __init cgroup_init(void)
WARN_ON(sysfs_create_mount_point(fs_kobj, "cgroup"));
WARN_ON(register_filesystem(&cgroup_fs_type));
WARN_ON(register_filesystem(&cgroup2_fs_type));
- WARN_ON(!proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations));
+ WARN_ON(!proc_create_single("cgroups", 0, NULL, proc_cgroupstats_show));
return 0;
}
diff --git a/kernel/compat.c b/kernel/compat.c
index 6d21894..702aa84 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -34,6 +34,7 @@ int compat_get_timex(struct timex *txc, const struct compat_timex __user *utp)
{
struct compat_timex tx32;
+ memset(txc, 0, sizeof(struct timex));
if (copy_from_user(&tx32, utp, sizeof(struct compat_timex)))
return -EFAULT;
@@ -120,50 +121,6 @@ static int __compat_put_timespec(const struct timespec *ts, struct compat_timesp
__put_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0;
}
-static int __compat_get_timespec64(struct timespec64 *ts64,
- const struct compat_timespec __user *cts)
-{
- struct compat_timespec ts;
- int ret;
-
- ret = copy_from_user(&ts, cts, sizeof(ts));
- if (ret)
- return -EFAULT;
-
- ts64->tv_sec = ts.tv_sec;
- ts64->tv_nsec = ts.tv_nsec;
-
- return 0;
-}
-
-static int __compat_put_timespec64(const struct timespec64 *ts64,
- struct compat_timespec __user *cts)
-{
- struct compat_timespec ts = {
- .tv_sec = ts64->tv_sec,
- .tv_nsec = ts64->tv_nsec
- };
- return copy_to_user(cts, &ts, sizeof(ts)) ? -EFAULT : 0;
-}
-
-int compat_get_timespec64(struct timespec64 *ts, const void __user *uts)
-{
- if (COMPAT_USE_64BIT_TIME)
- return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0;
- else
- return __compat_get_timespec64(ts, uts);
-}
-EXPORT_SYMBOL_GPL(compat_get_timespec64);
-
-int compat_put_timespec64(const struct timespec64 *ts, void __user *uts)
-{
- if (COMPAT_USE_64BIT_TIME)
- return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0;
- else
- return __compat_put_timespec64(ts, uts);
-}
-EXPORT_SYMBOL_GPL(compat_put_timespec64);
-
int compat_get_timeval(struct timeval *tv, const void __user *utv)
{
if (COMPAT_USE_64BIT_TIME)
@@ -367,6 +324,14 @@ COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t, pid, unsigned int, len,
return ret;
}
+/* Todo: Delete these extern declarations when get/put_compat_itimerspec64()
+ * are moved to kernel/time/time.c .
+ */
+extern int __compat_get_timespec64(struct timespec64 *ts64,
+ const struct compat_timespec __user *cts);
+extern int __compat_put_timespec64(const struct timespec64 *ts64,
+ struct compat_timespec __user *cts);
+
int get_compat_itimerspec64(struct itimerspec64 *its,
const struct compat_itimerspec __user *uits)
{
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index e2764d7..ca8ac28 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -44,23 +44,24 @@ void __delayacct_tsk_init(struct task_struct *tsk)
{
tsk->delays = kmem_cache_zalloc(delayacct_cache, GFP_KERNEL);
if (tsk->delays)
- spin_lock_init(&tsk->delays->lock);
+ raw_spin_lock_init(&tsk->delays->lock);
}
/*
* Finish delay accounting for a statistic using its timestamps (@start),
* accumalator (@total) and @count
*/
-static void delayacct_end(spinlock_t *lock, u64 *start, u64 *total, u32 *count)
+static void delayacct_end(raw_spinlock_t *lock, u64 *start, u64 *total,
+ u32 *count)
{
s64 ns = ktime_get_ns() - *start;
unsigned long flags;
if (ns > 0) {
- spin_lock_irqsave(lock, flags);
+ raw_spin_lock_irqsave(lock, flags);
*total += ns;
(*count)++;
- spin_unlock_irqrestore(lock, flags);
+ raw_spin_unlock_irqrestore(lock, flags);
}
}
@@ -127,7 +128,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
/* zero XXX_total, non-zero XXX_count implies XXX stat overflowed */
- spin_lock_irqsave(&tsk->delays->lock, flags);
+ raw_spin_lock_irqsave(&tsk->delays->lock, flags);
tmp = d->blkio_delay_total + tsk->delays->blkio_delay;
d->blkio_delay_total = (tmp < d->blkio_delay_total) ? 0 : tmp;
tmp = d->swapin_delay_total + tsk->delays->swapin_delay;
@@ -137,7 +138,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
d->blkio_count += tsk->delays->blkio_count;
d->swapin_count += tsk->delays->swapin_count;
d->freepages_count += tsk->delays->freepages_count;
- spin_unlock_irqrestore(&tsk->delays->lock, flags);
+ raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
return 0;
}
@@ -147,10 +148,10 @@ __u64 __delayacct_blkio_ticks(struct task_struct *tsk)
__u64 ret;
unsigned long flags;
- spin_lock_irqsave(&tsk->delays->lock, flags);
+ raw_spin_lock_irqsave(&tsk->delays->lock, flags);
ret = nsec_to_clock_t(tsk->delays->blkio_delay +
tsk->delays->swapin_delay);
- spin_unlock_irqrestore(&tsk->delays->lock, flags);
+ raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
return ret;
}
diff --git a/kernel/dma.c b/kernel/dma.c
index 3506fc3..40f1529 100644
--- a/kernel/dma.c
+++ b/kernel/dma.c
@@ -135,21 +135,9 @@ static int proc_dma_show(struct seq_file *m, void *v)
}
#endif /* MAX_DMA_CHANNELS */
-static int proc_dma_open(struct inode *inode, struct file *file)
-{
- return single_open(file, proc_dma_show, NULL);
-}
-
-static const struct file_operations proc_dma_operations = {
- .open = proc_dma_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __init proc_dma_init(void)
{
- proc_create("dma", 0, NULL, &proc_dma_operations);
+ proc_create_single("dma", 0, NULL, proc_dma_show);
return 0;
}
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 772a43f..c187aa3 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -119,23 +119,20 @@ int get_callchain_buffers(int event_max_stack)
goto exit;
}
- if (count > 1) {
- /* If the allocation failed, give up */
- if (!callchain_cpus_entries)
- err = -ENOMEM;
- /*
- * If requesting per event more than the global cap,
- * return a different error to help userspace figure
- * this out.
- *
- * And also do it here so that we have &callchain_mutex held.
- */
- if (event_max_stack > sysctl_perf_event_max_stack)
- err = -EOVERFLOW;
+ /*
+ * If requesting per event more than the global cap,
+ * return a different error to help userspace figure
+ * this out.
+ *
+ * And also do it here so that we have &callchain_mutex held.
+ */
+ if (event_max_stack > sysctl_perf_event_max_stack) {
+ err = -EOVERFLOW;
goto exit;
}
- err = alloc_callchain_buffers();
+ if (count == 1)
+ err = alloc_callchain_buffers();
exit:
if (err)
atomic_dec(&nr_callchain_events);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2d5fe26..08f5e1b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5120,6 +5120,8 @@ static long perf_compat_ioctl(struct file *file, unsigned int cmd,
switch (_IOC_NR(cmd)) {
case _IOC_NR(PERF_EVENT_IOC_SET_FILTER):
case _IOC_NR(PERF_EVENT_IOC_ID):
+ case _IOC_NR(PERF_EVENT_IOC_QUERY_BPF):
+ case _IOC_NR(PERF_EVENT_IOC_MODIFY_ATTRIBUTES):
/* Fix up pointer size (usually 4 -> 8 in 32-on-64-bit case */
if (_IOC_SIZE(cmd) == sizeof(compat_uptr_t)) {
cmd &= ~IOCSIZE_MASK;
@@ -6668,7 +6670,7 @@ static void perf_event_addr_filters_exec(struct perf_event *event, void *data)
raw_spin_lock_irqsave(&ifh->lock, flags);
list_for_each_entry(filter, &ifh->list, entry) {
- if (filter->inode) {
+ if (filter->path.dentry) {
event->addr_filters_offs[count] = 0;
restart++;
}
@@ -7333,7 +7335,7 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter,
struct file *file, unsigned long offset,
unsigned long size)
{
- if (filter->inode != file_inode(file))
+ if (d_inode(filter->path.dentry) != file_inode(file))
return false;
if (filter->offset > offset + size)
@@ -7587,6 +7589,10 @@ static void perf_event_switch(struct task_struct *task,
},
};
+ if (!sched_in && task->state == TASK_RUNNING)
+ switch_event.event_id.header.misc |=
+ PERF_RECORD_MISC_SWITCH_OUT_PREEMPT;
+
perf_iterate_sb(perf_event_switch_output,
&switch_event,
NULL);
@@ -8682,8 +8688,7 @@ static void free_filters_list(struct list_head *filters)
struct perf_addr_filter *filter, *iter;
list_for_each_entry_safe(filter, iter, filters, entry) {
- if (filter->inode)
- iput(filter->inode);
+ path_put(&filter->path);
list_del(&filter->entry);
kfree(filter);
}
@@ -8780,7 +8785,7 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
* Adjust base offset if the filter is associated to a binary
* that needs to be mapped:
*/
- if (filter->inode)
+ if (filter->path.dentry)
event->addr_filters_offs[count] =
perf_addr_filter_apply(filter, mm);
@@ -8854,7 +8859,6 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
{
struct perf_addr_filter *filter = NULL;
char *start, *orig, *filename = NULL;
- struct path path;
substring_t args[MAX_OPT_ARGS];
int state = IF_STATE_ACTION, token;
unsigned int kernel = 0;
@@ -8967,19 +8971,18 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
goto fail_free_name;
/* look up the path and grab its inode */
- ret = kern_path(filename, LOOKUP_FOLLOW, &path);
+ ret = kern_path(filename, LOOKUP_FOLLOW,
+ &filter->path);
if (ret)
goto fail_free_name;
- filter->inode = igrab(d_inode(path.dentry));
- path_put(&path);
kfree(filename);
filename = NULL;
ret = -EINVAL;
- if (!filter->inode ||
- !S_ISREG(filter->inode->i_mode))
- /* free_filters_list() will iput() */
+ if (!filter->path.dentry ||
+ !S_ISREG(d_inode(filter->path.dentry)
+ ->i_mode))
goto fail;
event->addr_filters.nr_file_filters++;
@@ -10205,9 +10208,9 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
* __u16 sample size limit.
*/
if (attr->sample_stack_user >= USHRT_MAX)
- ret = -EINVAL;
+ return -EINVAL;
else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64)))
- ret = -EINVAL;
+ return -EINVAL;
}
if (!attr->sample_max_stack)
@@ -10517,19 +10520,20 @@ SYSCALL_DEFINE5(perf_event_open,
if (pmu->task_ctx_nr == perf_sw_context)
event->event_caps |= PERF_EV_CAP_SOFTWARE;
- if (group_leader &&
- (is_software_event(event) != is_software_event(group_leader))) {
- if (is_software_event(event)) {
+ if (group_leader) {
+ if (is_software_event(event) &&
+ !in_software_context(group_leader)) {
/*
- * If event and group_leader are not both a software
- * event, and event is, then group leader is not.
+ * If the event is a sw event, but the group_leader
+ * is on hw context.
*
- * Allow the addition of software events to !software
- * groups, this is safe because software events never
- * fail to schedule.
+ * Allow the addition of software events to hw
+ * groups, this is safe because software events
+ * never fail to schedule.
*/
- pmu = group_leader->pmu;
- } else if (is_software_event(group_leader) &&
+ pmu = group_leader->ctx->pmu;
+ } else if (!is_software_event(event) &&
+ is_software_event(group_leader) &&
(group_leader->group_caps & PERF_EV_CAP_SOFTWARE)) {
/*
* In case the group is a pure software group, and we
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 6c6b3c4..1d8ca9e 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -14,6 +14,7 @@
#include <linux/slab.h>
#include <linux/circ_buf.h>
#include <linux/poll.h>
+#include <linux/nospec.h>
#include "internal.h"
@@ -867,8 +868,10 @@ perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff)
return NULL;
/* AUX space */
- if (pgoff >= rb->aux_pgoff)
- return virt_to_page(rb->aux_pages[pgoff - rb->aux_pgoff]);
+ if (pgoff >= rb->aux_pgoff) {
+ int aux_pgoff = array_index_nospec(pgoff - rb->aux_pgoff, rb->aux_nr_pages);
+ return virt_to_page(rb->aux_pages[aux_pgoff]);
+ }
}
return __perf_mmap_to_page(rb, pgoff);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index ce6848e..1725b90 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -491,7 +491,7 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
if (!uprobe)
return NULL;
- uprobe->inode = igrab(inode);
+ uprobe->inode = inode;
uprobe->offset = offset;
init_rwsem(&uprobe->register_rwsem);
init_rwsem(&uprobe->consumer_rwsem);
@@ -502,7 +502,6 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
if (cur_uprobe) {
kfree(uprobe);
uprobe = cur_uprobe;
- iput(inode);
}
return uprobe;
@@ -701,7 +700,6 @@ static void delete_uprobe(struct uprobe *uprobe)
rb_erase(&uprobe->rb_node, &uprobes_tree);
spin_unlock(&uprobes_treelock);
RB_CLEAR_NODE(&uprobe->rb_node); /* for uprobe_is_active() */
- iput(uprobe->inode);
put_uprobe(uprobe);
}
@@ -873,7 +871,8 @@ static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *u
* tuple). Creation refcount stops uprobe_unregister from freeing the
* @uprobe even before the register operation is complete. Creation
* refcount is released when the last @uc for the @uprobe
- * unregisters.
+ * unregisters. Caller of uprobe_register() is required to keep @inode
+ * (and the containing mount) referenced.
*
* Return errno if it cannot successully install probes
* else return 0 (success)
diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c
index a569711..33f07c5 100644
--- a/kernel/exec_domain.c
+++ b/kernel/exec_domain.c
@@ -27,21 +27,9 @@ static int execdomains_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int execdomains_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, execdomains_proc_show, NULL);
-}
-
-static const struct file_operations execdomains_proc_fops = {
- .open = execdomains_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __init proc_execdomains_init(void)
{
- proc_create("execdomains", 0, NULL, &execdomains_proc_fops);
+ proc_create_single("execdomains", 0, NULL, execdomains_proc_show);
return 0;
}
module_init(proc_execdomains_init);
diff --git a/kernel/fork.c b/kernel/fork.c
index 242c8c9..a5d21c4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -216,10 +216,9 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
if (!s)
continue;
-#ifdef CONFIG_DEBUG_KMEMLEAK
/* Clear stale pointers from reused stack. */
memset(s->addr, 0, THREAD_SIZE);
-#endif
+
tsk->stack_vm_area = s;
return s->addr;
}
diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c
index fc4f361..dd20d0d 100644
--- a/kernel/irq/irq_sim.c
+++ b/kernel/irq/irq_sim.c
@@ -1,11 +1,6 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * Copyright (C) 2017 Bartosz Golaszewski <brgl@bgdev.pl>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
+ * Copyright (C) 2017-2018 Bartosz Golaszewski <brgl@bgdev.pl>
*/
#include <linux/slab.h>
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 2a8571f..4ca2fd4 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -76,6 +76,19 @@ static inline void irq_chip_write_msi_msg(struct irq_data *data,
data->chip->irq_write_msi_msg(data, msg);
}
+static void msi_check_level(struct irq_domain *domain, struct msi_msg *msg)
+{
+ struct msi_domain_info *info = domain->host_data;
+
+ /*
+ * If the MSI provider has messed with the second message and
+ * not advertized that it is level-capable, signal the breakage.
+ */
+ WARN_ON(!((info->flags & MSI_FLAG_LEVEL_CAPABLE) &&
+ (info->chip->flags & IRQCHIP_SUPPORTS_LEVEL_MSI)) &&
+ (msg[1].address_lo || msg[1].address_hi || msg[1].data));
+}
+
/**
* msi_domain_set_affinity - Generic affinity setter function for MSI domains
* @irq_data: The irq data associated to the interrupt
@@ -89,13 +102,14 @@ int msi_domain_set_affinity(struct irq_data *irq_data,
const struct cpumask *mask, bool force)
{
struct irq_data *parent = irq_data->parent_data;
- struct msi_msg msg;
+ struct msi_msg msg[2] = { [1] = { }, };
int ret;
ret = parent->chip->irq_set_affinity(parent, mask, force);
if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) {
- BUG_ON(irq_chip_compose_msi_msg(irq_data, &msg));
- irq_chip_write_msi_msg(irq_data, &msg);
+ BUG_ON(irq_chip_compose_msi_msg(irq_data, msg));
+ msi_check_level(irq_data->domain, msg);
+ irq_chip_write_msi_msg(irq_data, msg);
}
return ret;
@@ -104,20 +118,21 @@ int msi_domain_set_affinity(struct irq_data *irq_data,
static int msi_domain_activate(struct irq_domain *domain,
struct irq_data *irq_data, bool early)
{
- struct msi_msg msg;
+ struct msi_msg msg[2] = { [1] = { }, };
- BUG_ON(irq_chip_compose_msi_msg(irq_data, &msg));
- irq_chip_write_msi_msg(irq_data, &msg);
+ BUG_ON(irq_chip_compose_msi_msg(irq_data, msg));
+ msi_check_level(irq_data->domain, msg);
+ irq_chip_write_msi_msg(irq_data, msg);
return 0;
}
static void msi_domain_deactivate(struct irq_domain *domain,
struct irq_data *irq_data)
{
- struct msi_msg msg;
+ struct msi_msg msg[2];
- memset(&msg, 0, sizeof(msg));
- irq_chip_write_msi_msg(irq_data, &msg);
+ memset(msg, 0, sizeof(msg));
+ irq_chip_write_msi_msg(irq_data, msg);
}
static int msi_domain_alloc(struct irq_domain *domain, unsigned int virq,
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 7cb091d..37eda10 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -185,11 +185,6 @@ static int irq_affinity_list_proc_open(struct inode *inode, struct file *file)
return single_open(file, irq_affinity_list_proc_show, PDE_DATA(inode));
}
-static int irq_affinity_hint_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, irq_affinity_hint_proc_show, PDE_DATA(inode));
-}
-
static const struct file_operations irq_affinity_proc_fops = {
.open = irq_affinity_proc_open,
.read = seq_read,
@@ -198,13 +193,6 @@ static const struct file_operations irq_affinity_proc_fops = {
.write = irq_affinity_proc_write,
};
-static const struct file_operations irq_affinity_hint_proc_fops = {
- .open = irq_affinity_hint_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static const struct file_operations irq_affinity_list_proc_fops = {
.open = irq_affinity_list_proc_open,
.read = seq_read,
@@ -223,32 +211,6 @@ static int irq_effective_aff_list_proc_show(struct seq_file *m, void *v)
{
return show_irq_affinity(EFFECTIVE_LIST, m);
}
-
-static int irq_effective_aff_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, irq_effective_aff_proc_show, PDE_DATA(inode));
-}
-
-static int irq_effective_aff_list_proc_open(struct inode *inode,
- struct file *file)
-{
- return single_open(file, irq_effective_aff_list_proc_show,
- PDE_DATA(inode));
-}
-
-static const struct file_operations irq_effective_aff_proc_fops = {
- .open = irq_effective_aff_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-static const struct file_operations irq_effective_aff_list_proc_fops = {
- .open = irq_effective_aff_list_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif
static int default_affinity_show(struct seq_file *m, void *v)
@@ -313,18 +275,6 @@ static int irq_node_proc_show(struct seq_file *m, void *v)
seq_printf(m, "%d\n", irq_desc_get_node(desc));
return 0;
}
-
-static int irq_node_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, irq_node_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations irq_node_proc_fops = {
- .open = irq_node_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif
static int irq_spurious_proc_show(struct seq_file *m, void *v)
@@ -337,18 +287,6 @@ static int irq_spurious_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int irq_spurious_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, irq_spurious_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations irq_spurious_proc_fops = {
- .open = irq_spurious_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
#define MAX_NAMELEN 128
static int name_unique(unsigned int irq, struct irqaction *new_action)
@@ -421,24 +359,24 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
&irq_affinity_proc_fops, irqp);
/* create /proc/irq/<irq>/affinity_hint */
- proc_create_data("affinity_hint", 0444, desc->dir,
- &irq_affinity_hint_proc_fops, irqp);
+ proc_create_single_data("affinity_hint", 0444, desc->dir,
+ irq_affinity_hint_proc_show, irqp);
/* create /proc/irq/<irq>/smp_affinity_list */
proc_create_data("smp_affinity_list", 0644, desc->dir,
&irq_affinity_list_proc_fops, irqp);
- proc_create_data("node", 0444, desc->dir,
- &irq_node_proc_fops, irqp);
+ proc_create_single_data("node", 0444, desc->dir, irq_node_proc_show,
+ irqp);
# ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
- proc_create_data("effective_affinity", 0444, desc->dir,
- &irq_effective_aff_proc_fops, irqp);
- proc_create_data("effective_affinity_list", 0444, desc->dir,
- &irq_effective_aff_list_proc_fops, irqp);
+ proc_create_single_data("effective_affinity", 0444, desc->dir,
+ irq_effective_aff_proc_show, irqp);
+ proc_create_single_data("effective_affinity_list", 0444, desc->dir,
+ irq_effective_aff_list_proc_show, irqp);
# endif
#endif
- proc_create_data("spurious", 0444, desc->dir,
- &irq_spurious_proc_fops, (void *)(long)irq);
+ proc_create_single_data("spurious", 0444, desc->dir,
+ irq_spurious_proc_show, (void *)(long)irq);
out_unlock:
mutex_unlock(®ister_lock);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 102160f..ea61902 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2428,7 +2428,7 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v)
struct kprobe_blacklist_entry *ent =
list_entry(v, struct kprobe_blacklist_entry, list);
- seq_printf(m, "0x%p-0x%p\t%ps\n", (void *)ent->start_addr,
+ seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr,
(void *)ent->end_addr, (void *)ent->start_addr);
return 0;
}
diff --git a/kernel/kthread.c b/kernel/kthread.c
index cd50e99..481951b 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -55,7 +55,6 @@ enum KTHREAD_BITS {
KTHREAD_IS_PER_CPU = 0,
KTHREAD_SHOULD_STOP,
KTHREAD_SHOULD_PARK,
- KTHREAD_IS_PARKED,
};
static inline void set_kthread_struct(void *kthread)
@@ -177,14 +176,12 @@ void *kthread_probe_data(struct task_struct *task)
static void __kthread_parkme(struct kthread *self)
{
- __set_current_state(TASK_PARKED);
- while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) {
- if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags))
- complete(&self->parked);
+ for (;;) {
+ set_current_state(TASK_PARKED);
+ if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
+ break;
schedule();
- __set_current_state(TASK_PARKED);
}
- clear_bit(KTHREAD_IS_PARKED, &self->flags);
__set_current_state(TASK_RUNNING);
}
@@ -194,6 +191,11 @@ void kthread_parkme(void)
}
EXPORT_SYMBOL_GPL(kthread_parkme);
+void kthread_park_complete(struct task_struct *k)
+{
+ complete_all(&to_kthread(k)->parked);
+}
+
static int kthread(void *_create)
{
/* Copy data: it's on kthread's stack */
@@ -450,22 +452,16 @@ void kthread_unpark(struct task_struct *k)
{
struct kthread *kthread = to_kthread(k);
- clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
/*
- * We clear the IS_PARKED bit here as we don't wait
- * until the task has left the park code. So if we'd
- * park before that happens we'd see the IS_PARKED bit
- * which might be about to be cleared.
+ * Newly created kthread was parked when the CPU was offline.
+ * The binding was lost and we need to set it again.
*/
- if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
- /*
- * Newly created kthread was parked when the CPU was offline.
- * The binding was lost and we need to set it again.
- */
- if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
- __kthread_bind(k, kthread->cpu, TASK_PARKED);
- wake_up_state(k, TASK_PARKED);
- }
+ if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
+ __kthread_bind(k, kthread->cpu, TASK_PARKED);
+
+ reinit_completion(&kthread->parked);
+ clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+ wake_up_state(k, TASK_PARKED);
}
EXPORT_SYMBOL_GPL(kthread_unpark);
@@ -488,12 +484,10 @@ int kthread_park(struct task_struct *k)
if (WARN_ON(k->flags & PF_EXITING))
return -ENOSYS;
- if (!test_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
- set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
- if (k != current) {
- wake_up_process(k);
- wait_for_completion(&kthread->parked);
- }
+ set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+ if (k != current) {
+ wake_up_process(k);
+ wait_for_completion(&kthread->parked);
}
return 0;
diff --git a/kernel/livepatch/shadow.c b/kernel/livepatch/shadow.c
index fdac275..83958c8 100644
--- a/kernel/livepatch/shadow.c
+++ b/kernel/livepatch/shadow.c
@@ -113,8 +113,10 @@ void *klp_shadow_get(void *obj, unsigned long id)
}
EXPORT_SYMBOL_GPL(klp_shadow_get);
-static void *__klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data,
- size_t size, gfp_t gfp_flags, bool warn_on_exist)
+static void *__klp_shadow_get_or_alloc(void *obj, unsigned long id,
+ size_t size, gfp_t gfp_flags,
+ klp_shadow_ctor_t ctor, void *ctor_data,
+ bool warn_on_exist)
{
struct klp_shadow *new_shadow;
void *shadow_data;
@@ -125,18 +127,15 @@ static void *__klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data,
if (shadow_data)
goto exists;
- /* Allocate a new shadow variable for use inside the lock below */
+ /*
+ * Allocate a new shadow variable. Fill it with zeroes by default.
+ * More complex setting can be done by @ctor function. But it is
+ * called only when the buffer is really used (under klp_shadow_lock).
+ */
new_shadow = kzalloc(size + sizeof(*new_shadow), gfp_flags);
if (!new_shadow)
return NULL;
- new_shadow->obj = obj;
- new_shadow->id = id;
-
- /* Initialize the shadow variable if data provided */
- if (data)
- memcpy(new_shadow->data, data, size);
-
/* Look for <obj, id> again under the lock */
spin_lock_irqsave(&klp_shadow_lock, flags);
shadow_data = klp_shadow_get(obj, id);
@@ -150,6 +149,22 @@ static void *__klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data,
goto exists;
}
+ new_shadow->obj = obj;
+ new_shadow->id = id;
+
+ if (ctor) {
+ int err;
+
+ err = ctor(obj, new_shadow->data, ctor_data);
+ if (err) {
+ spin_unlock_irqrestore(&klp_shadow_lock, flags);
+ kfree(new_shadow);
+ pr_err("Failed to construct shadow variable <%p, %lx> (%d)\n",
+ obj, id, err);
+ return NULL;
+ }
+ }
+
/* No <obj, id> found, so attach the newly allocated one */
hash_add_rcu(klp_shadow_hash, &new_shadow->node,
(unsigned long)new_shadow->obj);
@@ -170,26 +185,32 @@ static void *__klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data,
* klp_shadow_alloc() - allocate and add a new shadow variable
* @obj: pointer to parent object
* @id: data identifier
- * @data: pointer to data to attach to parent
* @size: size of attached data
* @gfp_flags: GFP mask for allocation
+ * @ctor: custom constructor to initialize the shadow data (optional)
+ * @ctor_data: pointer to any data needed by @ctor (optional)
*
- * Allocates @size bytes for new shadow variable data using @gfp_flags
- * and copies @size bytes from @data into the new shadow variable's own
- * data space. If @data is NULL, @size bytes are still allocated, but
- * no copy is performed. The new shadow variable is then added to the
- * global hashtable.
+ * Allocates @size bytes for new shadow variable data using @gfp_flags.
+ * The data are zeroed by default. They are further initialized by @ctor
+ * function if it is not NULL. The new shadow variable is then added
+ * to the global hashtable.
*
- * If an existing <obj, id> shadow variable can be found, this routine
- * will issue a WARN, exit early and return NULL.
+ * If an existing <obj, id> shadow variable can be found, this routine will
+ * issue a WARN, exit early and return NULL.
+ *
+ * This function guarantees that the constructor function is called only when
+ * the variable did not exist before. The cost is that @ctor is called
+ * in atomic context under a spin lock.
*
* Return: the shadow variable data element, NULL on duplicate or
* failure.
*/
-void *klp_shadow_alloc(void *obj, unsigned long id, void *data,
- size_t size, gfp_t gfp_flags)
+void *klp_shadow_alloc(void *obj, unsigned long id,
+ size_t size, gfp_t gfp_flags,
+ klp_shadow_ctor_t ctor, void *ctor_data)
{
- return __klp_shadow_get_or_alloc(obj, id, data, size, gfp_flags, true);
+ return __klp_shadow_get_or_alloc(obj, id, size, gfp_flags,
+ ctor, ctor_data, true);
}
EXPORT_SYMBOL_GPL(klp_shadow_alloc);
@@ -197,37 +218,51 @@ EXPORT_SYMBOL_GPL(klp_shadow_alloc);
* klp_shadow_get_or_alloc() - get existing or allocate a new shadow variable
* @obj: pointer to parent object
* @id: data identifier
- * @data: pointer to data to attach to parent
* @size: size of attached data
* @gfp_flags: GFP mask for allocation
+ * @ctor: custom constructor to initialize the shadow data (optional)
+ * @ctor_data: pointer to any data needed by @ctor (optional)
*
* Returns a pointer to existing shadow data if an <obj, id> shadow
* variable is already present. Otherwise, it creates a new shadow
* variable like klp_shadow_alloc().
*
- * This function guarantees that only one shadow variable exists with
- * the given @id for the given @obj. It also guarantees that the shadow
- * variable will be initialized by the given @data only when it did not
- * exist before.
+ * This function guarantees that only one shadow variable exists with the given
+ * @id for the given @obj. It also guarantees that the constructor function
+ * will be called only when the variable did not exist before. The cost is
+ * that @ctor is called in atomic context under a spin lock.
*
* Return: the shadow variable data element, NULL on failure.
*/
-void *klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data,
- size_t size, gfp_t gfp_flags)
+void *klp_shadow_get_or_alloc(void *obj, unsigned long id,
+ size_t size, gfp_t gfp_flags,
+ klp_shadow_ctor_t ctor, void *ctor_data)
{
- return __klp_shadow_get_or_alloc(obj, id, data, size, gfp_flags, false);
+ return __klp_shadow_get_or_alloc(obj, id, size, gfp_flags,
+ ctor, ctor_data, false);
}
EXPORT_SYMBOL_GPL(klp_shadow_get_or_alloc);
+static void klp_shadow_free_struct(struct klp_shadow *shadow,
+ klp_shadow_dtor_t dtor)
+{
+ hash_del_rcu(&shadow->node);
+ if (dtor)
+ dtor(shadow->obj, shadow->data);
+ kfree_rcu(shadow, rcu_head);
+}
+
/**
* klp_shadow_free() - detach and free a <obj, id> shadow variable
* @obj: pointer to parent object
* @id: data identifier
+ * @dtor: custom callback that can be used to unregister the variable
+ * and/or free data that the shadow variable points to (optional)
*
* This function releases the memory for this <obj, id> shadow variable
* instance, callers should stop referencing it accordingly.
*/
-void klp_shadow_free(void *obj, unsigned long id)
+void klp_shadow_free(void *obj, unsigned long id, klp_shadow_dtor_t dtor)
{
struct klp_shadow *shadow;
unsigned long flags;
@@ -239,8 +274,7 @@ void klp_shadow_free(void *obj, unsigned long id)
(unsigned long)obj) {
if (klp_shadow_match(shadow, obj, id)) {
- hash_del_rcu(&shadow->node);
- kfree_rcu(shadow, rcu_head);
+ klp_shadow_free_struct(shadow, dtor);
break;
}
}
@@ -252,11 +286,13 @@ EXPORT_SYMBOL_GPL(klp_shadow_free);
/**
* klp_shadow_free_all() - detach and free all <*, id> shadow variables
* @id: data identifier
+ * @dtor: custom callback that can be used to unregister the variable
+ * and/or free data that the shadow variable points to (optional)
*
* This function releases the memory for all <*, id> shadow variable
* instances, callers should stop referencing them accordingly.
*/
-void klp_shadow_free_all(unsigned long id)
+void klp_shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor)
{
struct klp_shadow *shadow;
unsigned long flags;
@@ -266,10 +302,8 @@ void klp_shadow_free_all(unsigned long id)
/* Delete all <*, id> from hash */
hash_for_each(klp_shadow_hash, i, shadow, node) {
- if (klp_shadow_match(shadow, shadow->obj, id)) {
- hash_del_rcu(&shadow->node);
- kfree_rcu(shadow, rcu_head);
- }
+ if (klp_shadow_match(shadow, shadow->obj, id))
+ klp_shadow_free_struct(shadow, dtor);
}
spin_unlock_irqrestore(&klp_shadow_lock, flags);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 0233863..edcac5d 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -561,20 +561,24 @@ static void print_lock(struct held_lock *hlock)
printk(KERN_CONT ", at: %pS\n", (void *)hlock->acquire_ip);
}
-static void lockdep_print_held_locks(struct task_struct *curr)
+static void lockdep_print_held_locks(struct task_struct *p)
{
- int i, depth = curr->lockdep_depth;
+ int i, depth = READ_ONCE(p->lockdep_depth);
- if (!depth) {
- printk("no locks held by %s/%d.\n", curr->comm, task_pid_nr(curr));
+ if (!depth)
+ printk("no locks held by %s/%d.\n", p->comm, task_pid_nr(p));
+ else
+ printk("%d lock%s held by %s/%d:\n", depth,
+ depth > 1 ? "s" : "", p->comm, task_pid_nr(p));
+ /*
+ * It's not reliable to print a task's held locks if it's not sleeping
+ * and it's not the current task.
+ */
+ if (p->state == TASK_RUNNING && p != current)
return;
- }
- printk("%d lock%s held by %s/%d:\n",
- depth, depth > 1 ? "s" : "", curr->comm, task_pid_nr(curr));
-
for (i = 0; i < depth; i++) {
printk(" #%d: ", i);
- print_lock(curr->held_locks + i);
+ print_lock(p->held_locks + i);
}
}
@@ -4451,8 +4455,6 @@ EXPORT_SYMBOL_GPL(debug_check_no_locks_held);
void debug_show_all_locks(void)
{
struct task_struct *g, *p;
- int count = 10;
- int unlock = 1;
if (unlikely(!debug_locks)) {
pr_warn("INFO: lockdep is turned off.\n");
@@ -4460,50 +4462,18 @@ void debug_show_all_locks(void)
}
pr_warn("\nShowing all locks held in the system:\n");
- /*
- * Here we try to get the tasklist_lock as hard as possible,
- * if not successful after 2 seconds we ignore it (but keep
- * trying). This is to enable a debug printout even if a
- * tasklist_lock-holding task deadlocks or crashes.
- */
-retry:
- if (!read_trylock(&tasklist_lock)) {
- if (count == 10)
- pr_warn("hm, tasklist_lock locked, retrying... ");
- if (count) {
- count--;
- pr_cont(" #%d", 10-count);
- mdelay(200);
- goto retry;
- }
- pr_cont(" ignoring it.\n");
- unlock = 0;
- } else {
- if (count != 10)
- pr_cont(" locked it.\n");
- }
-
- do_each_thread(g, p) {
- /*
- * It's not reliable to print a task's held locks
- * if it's not sleeping (or if it's not the current
- * task):
- */
- if (p->state == TASK_RUNNING && p != current)
+ rcu_read_lock();
+ for_each_process_thread(g, p) {
+ if (!p->lockdep_depth)
continue;
- if (p->lockdep_depth)
- lockdep_print_held_locks(p);
- if (!unlock)
- if (read_trylock(&tasklist_lock))
- unlock = 1;
+ lockdep_print_held_locks(p);
touch_nmi_watchdog();
- } while_each_thread(g, p);
+ touch_all_softlockup_watchdogs();
+ }
+ rcu_read_unlock();
pr_warn("\n");
pr_warn("=============================================\n\n");
-
- if (unlock)
- read_unlock(&tasklist_lock);
}
EXPORT_SYMBOL_GPL(debug_show_all_locks);
#endif
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index ad69bbc..3dd980d 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -101,18 +101,6 @@ static const struct seq_operations lockdep_ops = {
.show = l_show,
};
-static int lockdep_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &lockdep_ops);
-}
-
-static const struct file_operations proc_lockdep_operations = {
- .open = lockdep_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
#ifdef CONFIG_PROVE_LOCKING
static void *lc_start(struct seq_file *m, loff_t *pos)
{
@@ -170,18 +158,6 @@ static const struct seq_operations lockdep_chains_ops = {
.stop = lc_stop,
.show = lc_show,
};
-
-static int lockdep_chains_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &lockdep_chains_ops);
-}
-
-static const struct file_operations proc_lockdep_chains_operations = {
- .open = lockdep_chains_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
#endif /* CONFIG_PROVE_LOCKING */
static void lockdep_stats_debug_show(struct seq_file *m)
@@ -355,18 +331,6 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
return 0;
}
-static int lockdep_stats_open(struct inode *inode, struct file *file)
-{
- return single_open(file, lockdep_stats_show, NULL);
-}
-
-static const struct file_operations proc_lockdep_stats_operations = {
- .open = lockdep_stats_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
#ifdef CONFIG_LOCK_STAT
struct lock_stat_data {
@@ -682,14 +646,11 @@ static const struct file_operations proc_lock_stat_operations = {
static int __init lockdep_proc_init(void)
{
- proc_create("lockdep", S_IRUSR, NULL, &proc_lockdep_operations);
+ proc_create_seq("lockdep", S_IRUSR, NULL, &lockdep_ops);
#ifdef CONFIG_PROVE_LOCKING
- proc_create("lockdep_chains", S_IRUSR, NULL,
- &proc_lockdep_chains_operations);
+ proc_create_seq("lockdep_chains", S_IRUSR, NULL, &lockdep_chains_ops);
#endif
- proc_create("lockdep_stats", S_IRUSR, NULL,
- &proc_lockdep_stats_operations);
-
+ proc_create_single("lockdep_stats", S_IRUSR, NULL, lockdep_stats_show);
#ifdef CONFIG_LOCK_STAT
proc_create("lock_stat", S_IRUSR | S_IWUSR, NULL,
&proc_lock_stat_operations);
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index f046b7c..5e10153 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -23,13 +23,15 @@ struct mcs_spinlock {
#ifndef arch_mcs_spin_lock_contended
/*
- * Using smp_load_acquire() provides a memory barrier that ensures
- * subsequent operations happen after the lock is acquired.
+ * Using smp_cond_load_acquire() provides the acquire semantics
+ * required so that subsequent operations happen after the
+ * lock is acquired. Additionally, some architectures such as
+ * ARM64 would like to do spin-waiting instead of purely
+ * spinning, and smp_cond_load_acquire() provides that behavior.
*/
#define arch_mcs_spin_lock_contended(l) \
do { \
- while (!(smp_load_acquire(l))) \
- cpu_relax(); \
+ smp_cond_load_acquire(l, VAL); \
} while (0)
#endif
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 2048359..f44f658 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -139,8 +139,9 @@ static inline bool __mutex_trylock(struct mutex *lock)
static __always_inline bool __mutex_trylock_fast(struct mutex *lock)
{
unsigned long curr = (unsigned long)current;
+ unsigned long zero = 0UL;
- if (!atomic_long_cmpxchg_acquire(&lock->owner, 0UL, curr))
+ if (atomic_long_try_cmpxchg_acquire(&lock->owner, &zero, curr))
return true;
return false;
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index d880296..bfaeb05 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -12,11 +12,11 @@
* GNU General Public License for more details.
*
* (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
- * (C) Copyright 2013-2014 Red Hat, Inc.
+ * (C) Copyright 2013-2014,2018 Red Hat, Inc.
* (C) Copyright 2015 Intel Corp.
* (C) Copyright 2015 Hewlett-Packard Enterprise Development LP
*
- * Authors: Waiman Long <waiman.long@hpe.com>
+ * Authors: Waiman Long <longman@redhat.com>
* Peter Zijlstra <peterz@infradead.org>
*/
@@ -33,6 +33,11 @@
#include <asm/qspinlock.h>
/*
+ * Include queued spinlock statistics code
+ */
+#include "qspinlock_stat.h"
+
+/*
* The basic principle of a queue-based spinlock can best be understood
* by studying a classic queue-based spinlock implementation called the
* MCS lock. The paper below provides a good description for this kind
@@ -77,6 +82,18 @@
#endif
/*
+ * The pending bit spinning loop count.
+ * This heuristic is used to limit the number of lockword accesses
+ * made by atomic_cond_read_relaxed when waiting for the lock to
+ * transition out of the "== _Q_PENDING_VAL" state. We don't spin
+ * indefinitely because there's no guarantee that we'll make forward
+ * progress.
+ */
+#ifndef _Q_PENDING_LOOPS
+#define _Q_PENDING_LOOPS 1
+#endif
+
+/*
* Per-CPU queue node structures; we can never have more than 4 nested
* contexts: task, softirq, hardirq, nmi.
*
@@ -114,42 +131,19 @@ static inline __pure struct mcs_spinlock *decode_tail(u32 tail)
#define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK)
-/*
- * By using the whole 2nd least significant byte for the pending bit, we
- * can allow better optimization of the lock acquisition for the pending
- * bit holder.
- *
- * This internal structure is also used by the set_locked function which
- * is not restricted to _Q_PENDING_BITS == 8.
- */
-struct __qspinlock {
- union {
- atomic_t val;
-#ifdef __LITTLE_ENDIAN
- struct {
- u8 locked;
- u8 pending;
- };
- struct {
- u16 locked_pending;
- u16 tail;
- };
-#else
- struct {
- u16 tail;
- u16 locked_pending;
- };
- struct {
- u8 reserved[2];
- u8 pending;
- u8 locked;
- };
-#endif
- };
-};
-
#if _Q_PENDING_BITS == 8
/**
+ * clear_pending - clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,* -> *,0,*
+ */
+static __always_inline void clear_pending(struct qspinlock *lock)
+{
+ WRITE_ONCE(lock->pending, 0);
+}
+
+/**
* clear_pending_set_locked - take ownership and clear the pending bit.
* @lock: Pointer to queued spinlock structure
*
@@ -159,9 +153,7 @@ struct __qspinlock {
*/
static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
{
- struct __qspinlock *l = (void *)lock;
-
- WRITE_ONCE(l->locked_pending, _Q_LOCKED_VAL);
+ WRITE_ONCE(lock->locked_pending, _Q_LOCKED_VAL);
}
/*
@@ -176,19 +168,28 @@ static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
*/
static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
{
- struct __qspinlock *l = (void *)lock;
-
/*
- * Use release semantics to make sure that the MCS node is properly
- * initialized before changing the tail code.
+ * We can use relaxed semantics since the caller ensures that the
+ * MCS node is properly initialized before updating the tail.
*/
- return (u32)xchg_release(&l->tail,
+ return (u32)xchg_relaxed(&lock->tail,
tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET;
}
#else /* _Q_PENDING_BITS == 8 */
/**
+ * clear_pending - clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,* -> *,0,*
+ */
+static __always_inline void clear_pending(struct qspinlock *lock)
+{
+ atomic_andnot(_Q_PENDING_VAL, &lock->val);
+}
+
+/**
* clear_pending_set_locked - take ownership and clear the pending bit.
* @lock: Pointer to queued spinlock structure
*
@@ -216,10 +217,11 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
for (;;) {
new = (val & _Q_LOCKED_PENDING_MASK) | tail;
/*
- * Use release semantics to make sure that the MCS node is
- * properly initialized before changing the tail code.
+ * We can use relaxed semantics since the caller ensures that
+ * the MCS node is properly initialized before updating the
+ * tail.
*/
- old = atomic_cmpxchg_release(&lock->val, val, new);
+ old = atomic_cmpxchg_relaxed(&lock->val, val, new);
if (old == val)
break;
@@ -237,9 +239,7 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
*/
static __always_inline void set_locked(struct qspinlock *lock)
{
- struct __qspinlock *l = (void *)lock;
-
- WRITE_ONCE(l->locked, _Q_LOCKED_VAL);
+ WRITE_ONCE(lock->locked, _Q_LOCKED_VAL);
}
@@ -294,86 +294,83 @@ static __always_inline u32 __pv_wait_head_or_lock(struct qspinlock *lock,
void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
{
struct mcs_spinlock *prev, *next, *node;
- u32 new, old, tail;
+ u32 old, tail;
int idx;
BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS));
if (pv_enabled())
- goto queue;
+ goto pv_queue;
if (virt_spin_lock(lock))
return;
/*
- * wait for in-progress pending->locked hand-overs
+ * Wait for in-progress pending->locked hand-overs with a bounded
+ * number of spins so that we guarantee forward progress.
*
* 0,1,0 -> 0,0,1
*/
if (val == _Q_PENDING_VAL) {
- while ((val = atomic_read(&lock->val)) == _Q_PENDING_VAL)
- cpu_relax();
+ int cnt = _Q_PENDING_LOOPS;
+ val = atomic_cond_read_relaxed(&lock->val,
+ (VAL != _Q_PENDING_VAL) || !cnt--);
}
/*
+ * If we observe any contention; queue.
+ */
+ if (val & ~_Q_LOCKED_MASK)
+ goto queue;
+
+ /*
* trylock || pending
*
* 0,0,0 -> 0,0,1 ; trylock
* 0,0,1 -> 0,1,1 ; pending
*/
- for (;;) {
+ val = atomic_fetch_or_acquire(_Q_PENDING_VAL, &lock->val);
+ if (!(val & ~_Q_LOCKED_MASK)) {
/*
- * If we observe any contention; queue.
+ * We're pending, wait for the owner to go away.
+ *
+ * *,1,1 -> *,1,0
+ *
+ * this wait loop must be a load-acquire such that we match the
+ * store-release that clears the locked bit and create lock
+ * sequentiality; this is because not all
+ * clear_pending_set_locked() implementations imply full
+ * barriers.
*/
- if (val & ~_Q_LOCKED_MASK)
- goto queue;
-
- new = _Q_LOCKED_VAL;
- if (val == new)
- new |= _Q_PENDING_VAL;
+ if (val & _Q_LOCKED_MASK) {
+ atomic_cond_read_acquire(&lock->val,
+ !(VAL & _Q_LOCKED_MASK));
+ }
/*
- * Acquire semantic is required here as the function may
- * return immediately if the lock was free.
+ * take ownership and clear the pending bit.
+ *
+ * *,1,0 -> *,0,1
*/
- old = atomic_cmpxchg_acquire(&lock->val, val, new);
- if (old == val)
- break;
-
- val = old;
+ clear_pending_set_locked(lock);
+ qstat_inc(qstat_lock_pending, true);
+ return;
}
/*
- * we won the trylock
+ * If pending was clear but there are waiters in the queue, then
+ * we need to undo our setting of pending before we queue ourselves.
*/
- if (new == _Q_LOCKED_VAL)
- return;
-
- /*
- * we're pending, wait for the owner to go away.
- *
- * *,1,1 -> *,1,0
- *
- * this wait loop must be a load-acquire such that we match the
- * store-release that clears the locked bit and create lock
- * sequentiality; this is because not all clear_pending_set_locked()
- * implementations imply full barriers.
- */
- smp_cond_load_acquire(&lock->val.counter, !(VAL & _Q_LOCKED_MASK));
-
- /*
- * take ownership and clear the pending bit.
- *
- * *,1,0 -> *,0,1
- */
- clear_pending_set_locked(lock);
- return;
+ if (!(val & _Q_PENDING_MASK))
+ clear_pending(lock);
/*
* End of pending bit optimistic spinning and beginning of MCS
* queuing.
*/
queue:
+ qstat_inc(qstat_lock_slowpath, true);
+pv_queue:
node = this_cpu_ptr(&mcs_nodes[0]);
idx = node->count++;
tail = encode_tail(smp_processor_id(), idx);
@@ -400,12 +397,18 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
goto release;
/*
+ * Ensure that the initialisation of @node is complete before we
+ * publish the updated tail via xchg_tail() and potentially link
+ * @node into the waitqueue via WRITE_ONCE(prev->next, node) below.
+ */
+ smp_wmb();
+
+ /*
+ * Publish the updated tail.
* We have already touched the queueing cacheline; don't bother with
* pending stuff.
*
* p,*,* -> n,*,*
- *
- * RELEASE, such that the stores to @node must be complete.
*/
old = xchg_tail(lock, tail);
next = NULL;
@@ -417,14 +420,8 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
if (old & _Q_TAIL_MASK) {
prev = decode_tail(old);
- /*
- * We must ensure that the stores to @node are observed before
- * the write to prev->next. The address dependency from
- * xchg_tail is not sufficient to ensure this because the read
- * component of xchg_tail is unordered with respect to the
- * initialisation of @node.
- */
- smp_store_release(&prev->next, node);
+ /* Link @node into the waitqueue. */
+ WRITE_ONCE(prev->next, node);
pv_wait_node(node, prev);
arch_mcs_spin_lock_contended(&node->locked);
@@ -453,8 +450,8 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
*
* The PV pv_wait_head_or_lock function, if active, will acquire
* the lock and return a non-zero value. So we have to skip the
- * smp_cond_load_acquire() call. As the next PV queue head hasn't been
- * designated yet, there is no way for the locked value to become
+ * atomic_cond_read_acquire() call. As the next PV queue head hasn't
+ * been designated yet, there is no way for the locked value to become
* _Q_SLOW_VAL. So both the set_locked() and the
* atomic_cmpxchg_relaxed() calls will be safe.
*
@@ -464,44 +461,38 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
if ((val = pv_wait_head_or_lock(lock, node)))
goto locked;
- val = smp_cond_load_acquire(&lock->val.counter, !(VAL & _Q_LOCKED_PENDING_MASK));
+ val = atomic_cond_read_acquire(&lock->val, !(VAL & _Q_LOCKED_PENDING_MASK));
locked:
/*
* claim the lock:
*
* n,0,0 -> 0,0,1 : lock, uncontended
- * *,0,0 -> *,0,1 : lock, contended
+ * *,*,0 -> *,*,1 : lock, contended
*
- * If the queue head is the only one in the queue (lock value == tail),
- * clear the tail code and grab the lock. Otherwise, we only need
- * to grab the lock.
+ * If the queue head is the only one in the queue (lock value == tail)
+ * and nobody is pending, clear the tail code and grab the lock.
+ * Otherwise, we only need to grab the lock.
*/
- for (;;) {
- /* In the PV case we might already have _Q_LOCKED_VAL set */
- if ((val & _Q_TAIL_MASK) != tail) {
- set_locked(lock);
- break;
- }
- /*
- * The smp_cond_load_acquire() call above has provided the
- * necessary acquire semantics required for locking. At most
- * two iterations of this loop may be ran.
- */
- old = atomic_cmpxchg_relaxed(&lock->val, val, _Q_LOCKED_VAL);
- if (old == val)
- goto release; /* No contention */
- val = old;
- }
+ /*
+ * In the PV case we might already have _Q_LOCKED_VAL set.
+ *
+ * The atomic_cond_read_acquire() call above has provided the
+ * necessary acquire semantics required for locking.
+ */
+ if (((val & _Q_TAIL_MASK) == tail) &&
+ atomic_try_cmpxchg_relaxed(&lock->val, &val, _Q_LOCKED_VAL))
+ goto release; /* No contention */
+
+ /* Either somebody is queued behind us or _Q_PENDING_VAL is set */
+ set_locked(lock);
/*
* contended path; wait for next if not observed yet, release.
*/
- if (!next) {
- while (!(next = READ_ONCE(node->next)))
- cpu_relax();
- }
+ if (!next)
+ next = smp_cond_load_relaxed(&node->next, (VAL));
arch_mcs_spin_unlock_contended(&next->locked);
pv_kick_node(lock, next);
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 6ee4777..5a0cf5f 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -56,11 +56,6 @@ struct pv_node {
};
/*
- * Include queued spinlock statistics code
- */
-#include "qspinlock_stat.h"
-
-/*
* Hybrid PV queued/unfair lock
*
* By replacing the regular queued_spin_trylock() with the function below,
@@ -87,8 +82,6 @@ struct pv_node {
#define queued_spin_trylock(l) pv_hybrid_queued_unfair_trylock(l)
static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
{
- struct __qspinlock *l = (void *)lock;
-
/*
* Stay in unfair lock mode as long as queued mode waiters are
* present in the MCS wait queue but the pending bit isn't set.
@@ -97,7 +90,7 @@ static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
int val = atomic_read(&lock->val);
if (!(val & _Q_LOCKED_PENDING_MASK) &&
- (cmpxchg_acquire(&l->locked, 0, _Q_LOCKED_VAL) == 0)) {
+ (cmpxchg_acquire(&lock->locked, 0, _Q_LOCKED_VAL) == 0)) {
qstat_inc(qstat_pv_lock_stealing, true);
return true;
}
@@ -117,16 +110,7 @@ static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
#if _Q_PENDING_BITS == 8
static __always_inline void set_pending(struct qspinlock *lock)
{
- struct __qspinlock *l = (void *)lock;
-
- WRITE_ONCE(l->pending, 1);
-}
-
-static __always_inline void clear_pending(struct qspinlock *lock)
-{
- struct __qspinlock *l = (void *)lock;
-
- WRITE_ONCE(l->pending, 0);
+ WRITE_ONCE(lock->pending, 1);
}
/*
@@ -136,10 +120,8 @@ static __always_inline void clear_pending(struct qspinlock *lock)
*/
static __always_inline int trylock_clear_pending(struct qspinlock *lock)
{
- struct __qspinlock *l = (void *)lock;
-
- return !READ_ONCE(l->locked) &&
- (cmpxchg_acquire(&l->locked_pending, _Q_PENDING_VAL,
+ return !READ_ONCE(lock->locked) &&
+ (cmpxchg_acquire(&lock->locked_pending, _Q_PENDING_VAL,
_Q_LOCKED_VAL) == _Q_PENDING_VAL);
}
#else /* _Q_PENDING_BITS == 8 */
@@ -148,11 +130,6 @@ static __always_inline void set_pending(struct qspinlock *lock)
atomic_or(_Q_PENDING_VAL, &lock->val);
}
-static __always_inline void clear_pending(struct qspinlock *lock)
-{
- atomic_andnot(_Q_PENDING_VAL, &lock->val);
-}
-
static __always_inline int trylock_clear_pending(struct qspinlock *lock)
{
int val = atomic_read(&lock->val);
@@ -384,7 +361,6 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
{
struct pv_node *pn = (struct pv_node *)node;
- struct __qspinlock *l = (void *)lock;
/*
* If the vCPU is indeed halted, advance its state to match that of
@@ -413,7 +389,7 @@ static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
* the hash table later on at unlock time, no atomic instruction is
* needed.
*/
- WRITE_ONCE(l->locked, _Q_SLOW_VAL);
+ WRITE_ONCE(lock->locked, _Q_SLOW_VAL);
(void)pv_hash(lock, pn);
}
@@ -428,7 +404,6 @@ static u32
pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
{
struct pv_node *pn = (struct pv_node *)node;
- struct __qspinlock *l = (void *)lock;
struct qspinlock **lp = NULL;
int waitcnt = 0;
int loop;
@@ -443,7 +418,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
/*
* Tracking # of slowpath locking operations
*/
- qstat_inc(qstat_pv_lock_slowpath, true);
+ qstat_inc(qstat_lock_slowpath, true);
for (;; waitcnt++) {
/*
@@ -479,13 +454,13 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
*
* Matches the smp_rmb() in __pv_queued_spin_unlock().
*/
- if (xchg(&l->locked, _Q_SLOW_VAL) == 0) {
+ if (xchg(&lock->locked, _Q_SLOW_VAL) == 0) {
/*
* The lock was free and now we own the lock.
* Change the lock value back to _Q_LOCKED_VAL
* and unhash the table.
*/
- WRITE_ONCE(l->locked, _Q_LOCKED_VAL);
+ WRITE_ONCE(lock->locked, _Q_LOCKED_VAL);
WRITE_ONCE(*lp, NULL);
goto gotlock;
}
@@ -493,7 +468,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
WRITE_ONCE(pn->state, vcpu_hashed);
qstat_inc(qstat_pv_wait_head, true);
qstat_inc(qstat_pv_wait_again, waitcnt);
- pv_wait(&l->locked, _Q_SLOW_VAL);
+ pv_wait(&lock->locked, _Q_SLOW_VAL);
/*
* Because of lock stealing, the queue head vCPU may not be
@@ -518,7 +493,6 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
__visible void
__pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
{
- struct __qspinlock *l = (void *)lock;
struct pv_node *node;
if (unlikely(locked != _Q_SLOW_VAL)) {
@@ -547,7 +521,7 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
* Now that we have a reference to the (likely) blocked pv_node,
* release the lock.
*/
- smp_store_release(&l->locked, 0);
+ smp_store_release(&lock->locked, 0);
/*
* At this point the memory pointed at by lock can be freed/reused,
@@ -573,7 +547,6 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
#ifndef __pv_queued_spin_unlock
__visible void __pv_queued_spin_unlock(struct qspinlock *lock)
{
- struct __qspinlock *l = (void *)lock;
u8 locked;
/*
@@ -581,7 +554,7 @@ __visible void __pv_queued_spin_unlock(struct qspinlock *lock)
* unhash. Otherwise it would be possible to have multiple @lock
* entries, which would be BAD.
*/
- locked = cmpxchg_release(&l->locked, _Q_LOCKED_VAL, 0);
+ locked = cmpxchg_release(&lock->locked, _Q_LOCKED_VAL, 0);
if (likely(locked == _Q_LOCKED_VAL))
return;
diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h
index 4a30ef6..6bd78c0 100644
--- a/kernel/locking/qspinlock_stat.h
+++ b/kernel/locking/qspinlock_stat.h
@@ -22,13 +22,14 @@
* pv_kick_wake - # of vCPU kicks used for computing pv_latency_wake
* pv_latency_kick - average latency (ns) of vCPU kick operation
* pv_latency_wake - average latency (ns) from vCPU kick to wakeup
- * pv_lock_slowpath - # of locking operations via the slowpath
* pv_lock_stealing - # of lock stealing operations
* pv_spurious_wakeup - # of spurious wakeups in non-head vCPUs
* pv_wait_again - # of wait's after a queue head vCPU kick
* pv_wait_early - # of early vCPU wait's
* pv_wait_head - # of vCPU wait's at the queue head
* pv_wait_node - # of vCPU wait's at a non-head queue node
+ * lock_pending - # of locking operations via pending code
+ * lock_slowpath - # of locking operations via MCS lock queue
*
* Writing to the "reset_counters" file will reset all the above counter
* values.
@@ -46,13 +47,14 @@ enum qlock_stats {
qstat_pv_kick_wake,
qstat_pv_latency_kick,
qstat_pv_latency_wake,
- qstat_pv_lock_slowpath,
qstat_pv_lock_stealing,
qstat_pv_spurious_wakeup,
qstat_pv_wait_again,
qstat_pv_wait_early,
qstat_pv_wait_head,
qstat_pv_wait_node,
+ qstat_lock_pending,
+ qstat_lock_slowpath,
qstat_num, /* Total number of statistical counters */
qstat_reset_cnts = qstat_num,
};
@@ -73,12 +75,13 @@ static const char * const qstat_names[qstat_num + 1] = {
[qstat_pv_spurious_wakeup] = "pv_spurious_wakeup",
[qstat_pv_latency_kick] = "pv_latency_kick",
[qstat_pv_latency_wake] = "pv_latency_wake",
- [qstat_pv_lock_slowpath] = "pv_lock_slowpath",
[qstat_pv_lock_stealing] = "pv_lock_stealing",
[qstat_pv_wait_again] = "pv_wait_again",
[qstat_pv_wait_early] = "pv_wait_early",
[qstat_pv_wait_head] = "pv_wait_head",
[qstat_pv_wait_node] = "pv_wait_node",
+ [qstat_lock_pending] = "lock_pending",
+ [qstat_lock_slowpath] = "lock_slowpath",
[qstat_reset_cnts] = "reset_counters",
};
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index e795908..3064c50 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -347,30 +347,31 @@ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
}
}
+static inline bool owner_on_cpu(struct task_struct *owner)
+{
+ /*
+ * As lock holder preemption issue, we both skip spinning if
+ * task is not on cpu or its cpu is preempted
+ */
+ return owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
+}
+
static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
{
struct task_struct *owner;
bool ret = true;
+ BUILD_BUG_ON(!rwsem_has_anonymous_owner(RWSEM_OWNER_UNKNOWN));
+
if (need_resched())
return false;
rcu_read_lock();
owner = READ_ONCE(sem->owner);
- if (!rwsem_owner_is_writer(owner)) {
- /*
- * Don't spin if the rwsem is readers owned.
- */
- ret = !rwsem_owner_is_reader(owner);
- goto done;
+ if (owner) {
+ ret = is_rwsem_owner_spinnable(owner) &&
+ owner_on_cpu(owner);
}
-
- /*
- * As lock holder preemption issue, we both skip spinning if task is not
- * on cpu or its cpu is preempted
- */
- ret = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
-done:
rcu_read_unlock();
return ret;
}
@@ -382,11 +383,11 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
{
struct task_struct *owner = READ_ONCE(sem->owner);
- if (!rwsem_owner_is_writer(owner))
- goto out;
+ if (!is_rwsem_owner_spinnable(owner))
+ return false;
rcu_read_lock();
- while (sem->owner == owner) {
+ while (owner && (READ_ONCE(sem->owner) == owner)) {
/*
* Ensure we emit the owner->on_cpu, dereference _after_
* checking sem->owner still matches owner, if that fails,
@@ -399,8 +400,7 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
* abort spinning when need_resched or owner is not running or
* owner's cpu is preempted.
*/
- if (!owner->on_cpu || need_resched() ||
- vcpu_is_preempted(task_cpu(owner))) {
+ if (need_resched() || !owner_on_cpu(owner)) {
rcu_read_unlock();
return false;
}
@@ -408,12 +408,12 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
cpu_relax();
}
rcu_read_unlock();
-out:
+
/*
* If there is a new owner or the owner is not set, we continue
* spinning.
*/
- return !rwsem_owner_is_reader(READ_ONCE(sem->owner));
+ return is_rwsem_owner_spinnable(READ_ONCE(sem->owner));
}
static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 30465a2..bc1e507b 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -221,5 +221,3 @@ void up_read_non_owner(struct rw_semaphore *sem)
EXPORT_SYMBOL(up_read_non_owner);
#endif
-
-
diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
index a17cba8..b9d0e72 100644
--- a/kernel/locking/rwsem.h
+++ b/kernel/locking/rwsem.h
@@ -1,20 +1,24 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* The owner field of the rw_semaphore structure will be set to
- * RWSEM_READ_OWNED when a reader grabs the lock. A writer will clear
+ * RWSEM_READER_OWNED when a reader grabs the lock. A writer will clear
* the owner field when it unlocks. A reader, on the other hand, will
* not touch the owner field when it unlocks.
*
- * In essence, the owner field now has the following 3 states:
+ * In essence, the owner field now has the following 4 states:
* 1) 0
* - lock is free or the owner hasn't set the field yet
* 2) RWSEM_READER_OWNED
* - lock is currently or previously owned by readers (lock is free
* or not set by owner yet)
- * 3) Other non-zero value
- * - a writer owns the lock
+ * 3) RWSEM_ANONYMOUSLY_OWNED bit set with some other bits set as well
+ * - lock is owned by an anonymous writer, so spinning on the lock
+ * owner should be disabled.
+ * 4) Other non-zero value
+ * - a writer owns the lock and other writers can spin on the lock owner.
*/
-#define RWSEM_READER_OWNED ((struct task_struct *)1UL)
+#define RWSEM_ANONYMOUSLY_OWNED (1UL << 0)
+#define RWSEM_READER_OWNED ((struct task_struct *)RWSEM_ANONYMOUSLY_OWNED)
#ifdef CONFIG_DEBUG_RWSEMS
# define DEBUG_RWSEMS_WARN_ON(c) DEBUG_LOCKS_WARN_ON(c)
@@ -51,14 +55,22 @@ static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
WRITE_ONCE(sem->owner, RWSEM_READER_OWNED);
}
-static inline bool rwsem_owner_is_writer(struct task_struct *owner)
+/*
+ * Return true if the a rwsem waiter can spin on the rwsem's owner
+ * and steal the lock, i.e. the lock is not anonymously owned.
+ * N.B. !owner is considered spinnable.
+ */
+static inline bool is_rwsem_owner_spinnable(struct task_struct *owner)
{
- return owner && owner != RWSEM_READER_OWNED;
+ return !((unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED);
}
-static inline bool rwsem_owner_is_reader(struct task_struct *owner)
+/*
+ * Return true if rwsem is owned by an anonymous writer or readers.
+ */
+static inline bool rwsem_has_anonymous_owner(struct task_struct *owner)
{
- return owner == RWSEM_READER_OWNED;
+ return (unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED;
}
#else
static inline void rwsem_set_owner(struct rw_semaphore *sem)
diff --git a/kernel/module.c b/kernel/module.c
index a6e43a5..c9bea7f 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1472,7 +1472,8 @@ static ssize_t module_sect_show(struct module_attribute *mattr,
{
struct module_sect_attr *sattr =
container_of(mattr, struct module_sect_attr, mattr);
- return sprintf(buf, "0x%pK\n", (void *)sattr->address);
+ return sprintf(buf, "0x%px\n", kptr_restrict < 2 ?
+ (void *)sattr->address : NULL);
}
static void free_sect_attrs(struct module_sect_attrs *sect_attrs)
@@ -3516,6 +3517,11 @@ static noinline int do_init_module(struct module *mod)
* walking this with preempt disabled. In all the failure paths, we
* call synchronize_sched(), but we don't want to slow down the success
* path, so use actual RCU here.
+ * Note that module_alloc() on most architectures creates W+X page
+ * mappings which won't be cleaned up until do_free_init() runs. Any
+ * code such as mark_rodata_ro() which depends on those mappings to
+ * be cleaned up needs to sync with the queued work - ie
+ * rcu_barrier_sched()
*/
call_rcu_sched(&freeinit->rcu, do_free_init);
mutex_unlock(&module_mutex);
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 5454cc6..9c85c78 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -287,6 +287,8 @@ static int create_image(int platform_mode)
local_irq_disable();
+ system_state = SYSTEM_SUSPEND;
+
error = syscore_suspend();
if (error) {
pr_err("Some system devices failed to power down, aborting hibernation\n");
@@ -317,6 +319,7 @@ static int create_image(int platform_mode)
syscore_resume();
Enable_irqs:
+ system_state = SYSTEM_RUNNING;
local_irq_enable();
Enable_cpus:
@@ -445,6 +448,7 @@ static int resume_target_kernel(bool platform_mode)
goto Enable_cpus;
local_irq_disable();
+ system_state = SYSTEM_SUSPEND;
error = syscore_suspend();
if (error)
@@ -478,6 +482,7 @@ static int resume_target_kernel(bool platform_mode)
syscore_resume();
Enable_irqs:
+ system_state = SYSTEM_RUNNING;
local_irq_enable();
Enable_cpus:
@@ -563,6 +568,7 @@ int hibernation_platform_enter(void)
goto Enable_cpus;
local_irq_disable();
+ system_state = SYSTEM_SUSPEND;
syscore_suspend();
if (pm_wakeup_pending()) {
error = -EAGAIN;
@@ -575,6 +581,7 @@ int hibernation_platform_enter(void)
Power_up:
syscore_resume();
+ system_state = SYSTEM_RUNNING;
local_irq_enable();
Enable_cpus:
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index fa39092..86d72ffb 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -184,7 +184,6 @@ static inline void pm_qos_set_value(struct pm_qos_constraints *c, s32 value)
c->target_value = value;
}
-static inline int pm_qos_get_value(struct pm_qos_constraints *c);
static int pm_qos_dbg_show_requests(struct seq_file *s, void *unused)
{
struct pm_qos_object *qos = (struct pm_qos_object *)s->private;
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 4c10be0..8733156 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -27,6 +27,7 @@
#include <linux/export.h>
#include <linux/suspend.h>
#include <linux/syscore_ops.h>
+#include <linux/swait.h>
#include <linux/ftrace.h>
#include <trace/events/power.h>
#include <linux/compiler.h>
@@ -57,10 +58,10 @@ EXPORT_SYMBOL_GPL(pm_suspend_global_flags);
static const struct platform_suspend_ops *suspend_ops;
static const struct platform_s2idle_ops *s2idle_ops;
-static DECLARE_WAIT_QUEUE_HEAD(s2idle_wait_head);
+static DECLARE_SWAIT_QUEUE_HEAD(s2idle_wait_head);
enum s2idle_states __read_mostly s2idle_state;
-static DEFINE_SPINLOCK(s2idle_lock);
+static DEFINE_RAW_SPINLOCK(s2idle_lock);
void s2idle_set_ops(const struct platform_s2idle_ops *ops)
{
@@ -78,12 +79,12 @@ static void s2idle_enter(void)
{
trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_TO_IDLE, true);
- spin_lock_irq(&s2idle_lock);
+ raw_spin_lock_irq(&s2idle_lock);
if (pm_wakeup_pending())
goto out;
s2idle_state = S2IDLE_STATE_ENTER;
- spin_unlock_irq(&s2idle_lock);
+ raw_spin_unlock_irq(&s2idle_lock);
get_online_cpus();
cpuidle_resume();
@@ -91,17 +92,17 @@ static void s2idle_enter(void)
/* Push all the CPUs into the idle loop. */
wake_up_all_idle_cpus();
/* Make the current CPU wait so it can enter the idle loop too. */
- wait_event(s2idle_wait_head,
- s2idle_state == S2IDLE_STATE_WAKE);
+ swait_event(s2idle_wait_head,
+ s2idle_state == S2IDLE_STATE_WAKE);
cpuidle_pause();
put_online_cpus();
- spin_lock_irq(&s2idle_lock);
+ raw_spin_lock_irq(&s2idle_lock);
out:
s2idle_state = S2IDLE_STATE_NONE;
- spin_unlock_irq(&s2idle_lock);
+ raw_spin_unlock_irq(&s2idle_lock);
trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_TO_IDLE, false);
}
@@ -156,12 +157,12 @@ void s2idle_wake(void)
{
unsigned long flags;
- spin_lock_irqsave(&s2idle_lock, flags);
+ raw_spin_lock_irqsave(&s2idle_lock, flags);
if (s2idle_state > S2IDLE_STATE_NONE) {
s2idle_state = S2IDLE_STATE_WAKE;
- wake_up(&s2idle_wait_head);
+ swake_up(&s2idle_wait_head);
}
- spin_unlock_irqrestore(&s2idle_lock, flags);
+ raw_spin_unlock_irqrestore(&s2idle_lock, flags);
}
EXPORT_SYMBOL_GPL(s2idle_wake);
@@ -428,6 +429,8 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
arch_suspend_disable_irqs();
BUG_ON(!irqs_disabled());
+ system_state = SYSTEM_SUSPEND;
+
error = syscore_suspend();
if (!error) {
*wakeup = pm_wakeup_pending();
@@ -443,6 +446,8 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
syscore_resume();
}
+ system_state = SYSTEM_RUNNING;
+
arch_suspend_enable_irqs();
BUG_ON(irqs_disabled());
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 11b4282..1efcb5b 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -269,7 +269,7 @@ static int hib_submit_io(int op, int op_flags, pgoff_t page_off, void *addr,
struct bio *bio;
int error = 0;
- bio = bio_alloc(__GFP_RECLAIM | __GFP_HIGH, 1);
+ bio = bio_alloc(GFP_NOIO | __GFP_HIGH, 1);
bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9);
bio_set_dev(bio, hib_resume_bdev);
bio_set_op_attrs(bio, op, op_flags);
@@ -376,7 +376,7 @@ static int write_page(void *buf, sector_t offset, struct hib_bio_batch *hb)
return -ENOSPC;
if (hb) {
- src = (void *)__get_free_page(__GFP_RECLAIM | __GFP_NOWARN |
+ src = (void *)__get_free_page(GFP_NOIO | __GFP_NOWARN |
__GFP_NORETRY);
if (src) {
copy_page(src, buf);
@@ -384,7 +384,7 @@ static int write_page(void *buf, sector_t offset, struct hib_bio_batch *hb)
ret = hib_wait_io(hb); /* Free pages */
if (ret)
return ret;
- src = (void *)__get_free_page(__GFP_RECLAIM |
+ src = (void *)__get_free_page(GFP_NOIO |
__GFP_NOWARN |
__GFP_NORETRY);
if (src) {
@@ -691,7 +691,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
nr_threads = num_online_cpus() - 1;
nr_threads = clamp_val(nr_threads, 1, LZO_THREADS);
- page = (void *)__get_free_page(__GFP_RECLAIM | __GFP_HIGH);
+ page = (void *)__get_free_page(GFP_NOIO | __GFP_HIGH);
if (!page) {
pr_err("Failed to allocate LZO page\n");
ret = -ENOMEM;
@@ -989,7 +989,7 @@ static int get_swap_reader(struct swap_map_handle *handle,
last = tmp;
tmp->map = (struct swap_map_page *)
- __get_free_page(__GFP_RECLAIM | __GFP_HIGH);
+ __get_free_page(GFP_NOIO | __GFP_HIGH);
if (!tmp->map) {
release_swap_reader(handle);
return -ENOMEM;
@@ -1261,8 +1261,8 @@ static int load_image_lzo(struct swap_map_handle *handle,
for (i = 0; i < read_pages; i++) {
page[i] = (void *)__get_free_page(i < LZO_CMP_PAGES ?
- __GFP_RECLAIM | __GFP_HIGH :
- __GFP_RECLAIM | __GFP_NOWARN |
+ GFP_NOIO | __GFP_HIGH :
+ GFP_NOIO | __GFP_NOWARN |
__GFP_NORETRY);
if (!page[i]) {
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 75c959d..abd2255 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -186,6 +186,11 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf,
res = PAGE_SIZE - pg_offp;
}
+ if (!data_of(data->handle)) {
+ res = -EINVAL;
+ goto unlock;
+ }
+
res = simple_write_to_buffer(data_of(data->handle), res, &pg_offp,
buf, count);
if (res > 0)
diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c
index dfba59b..4210152 100644
--- a/kernel/power/wakelock.c
+++ b/kernel/power/wakelock.c
@@ -188,6 +188,7 @@ static struct wakelock *wakelock_lookup_add(const char *name, size_t len,
return ERR_PTR(-ENOMEM);
}
wl->ws.name = wl->name;
+ wl->ws.last_time = ktime_get();
wakeup_source_add(&wl->ws);
rb_link_node(&wl->node, parent, node);
rb_insert_color(&wl->node, &wakelocks_tree);
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 7a693e3..40cea67 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -270,6 +270,12 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
}
}
+/* Returns first leaf rcu_node of the specified RCU flavor. */
+#define rcu_first_leaf_node(rsp) ((rsp)->level[rcu_num_lvls - 1])
+
+/* Is this rcu_node a leaf? */
+#define rcu_is_leaf_node(rnp) ((rnp)->level == rcu_num_lvls - 1)
+
/*
* Do a full breadth-first scan of the rcu_node structures for the
* specified rcu_state structure.
@@ -284,8 +290,7 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
* rcu_node tree with but one rcu_node structure, this loop is a no-op.
*/
#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \
- for ((rnp) = &(rsp)->node[0]; \
- (rnp) < (rsp)->level[rcu_num_lvls - 1]; (rnp)++)
+ for ((rnp) = &(rsp)->node[0]; !rcu_is_leaf_node(rsp, rnp); (rnp)++)
/*
* Scan the leaves of the rcu_node hierarchy for the specified rcu_state
@@ -294,7 +299,7 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
* It is still a leaf node, even if it is also the root node.
*/
#define rcu_for_each_leaf_node(rsp, rnp) \
- for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \
+ for ((rnp) = rcu_first_leaf_node(rsp); \
(rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
/*
@@ -486,6 +491,7 @@ void rcu_force_quiescent_state(void);
void rcu_bh_force_quiescent_state(void);
void rcu_sched_force_quiescent_state(void);
extern struct workqueue_struct *rcu_gp_wq;
+extern struct workqueue_struct *rcu_par_gp_wq;
#endif /* #else #ifdef CONFIG_TINY_RCU */
#ifdef CONFIG_RCU_NOCB_CPU
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index 88cba7c..5aff271 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -404,24 +404,6 @@ bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq)
}
/*
- * Scan the specified rcu_segcblist structure for callbacks that need
- * a grace period later than the one specified by "seq". We don't look
- * at the RCU_DONE_TAIL or RCU_NEXT_TAIL segments because they don't
- * have a grace-period sequence number.
- */
-bool rcu_segcblist_future_gp_needed(struct rcu_segcblist *rsclp,
- unsigned long seq)
-{
- int i;
-
- for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++)
- if (rsclp->tails[i - 1] != rsclp->tails[i] &&
- ULONG_CMP_LT(seq, rsclp->gp_seq[i]))
- return true;
- return false;
-}
-
-/*
* Merge the source rcu_segcblist structure into the destination
* rcu_segcblist structure, then initialize the source. Any pending
* callbacks from the source get to start over. It is best to
diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h
index 581c12b..948470c 100644
--- a/kernel/rcu/rcu_segcblist.h
+++ b/kernel/rcu/rcu_segcblist.h
@@ -134,7 +134,5 @@ void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp);
void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq);
bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq);
-bool rcu_segcblist_future_gp_needed(struct rcu_segcblist *rsclp,
- unsigned long seq);
void rcu_segcblist_merge(struct rcu_segcblist *dst_rsclp,
struct rcu_segcblist *src_rsclp);
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index 777e7a6..e232846 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -369,7 +369,7 @@ static bool __maybe_unused torturing_tasks(void)
*/
static void rcu_perf_wait_shutdown(void)
{
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
if (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters)
return;
while (!torture_must_stop())
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 680c96d..e628fcf 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -593,7 +593,12 @@ static void srcu_torture_init(void)
static void srcu_torture_cleanup(void)
{
- cleanup_srcu_struct(&srcu_ctld);
+ static DEFINE_TORTURE_RANDOM(rand);
+
+ if (torture_random(&rand) & 0x800)
+ cleanup_srcu_struct(&srcu_ctld);
+ else
+ cleanup_srcu_struct_quiesced(&srcu_ctld);
srcu_ctlp = &srcu_ctl; /* In case of a later rcutorture run. */
}
@@ -1609,6 +1614,9 @@ static enum cpuhp_state rcutor_hp;
static void
rcu_torture_cleanup(void)
{
+ int flags = 0;
+ unsigned long gpnum = 0;
+ unsigned long completed = 0;
int i;
rcutorture_record_test_transition();
@@ -1639,6 +1647,11 @@ rcu_torture_cleanup(void)
fakewriter_tasks = NULL;
}
+ rcutorture_get_gp_data(cur_ops->ttype, &flags, &gpnum, &completed);
+ srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
+ &flags, &gpnum, &completed);
+ pr_alert("%s: End-test grace-period state: g%lu c%lu f%#x\n",
+ cur_ops->name, gpnum, completed, flags);
torture_stop_kthread(rcu_torture_stats, stats_task);
torture_stop_kthread(rcu_torture_fqs, fqs_task);
for (i = 0; i < ncbflooders; i++)
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 76ac5f5..622792a 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -86,16 +86,19 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
* Must invoke this after you are finished using a given srcu_struct that
* was initialized via init_srcu_struct(), else you leak memory.
*/
-void cleanup_srcu_struct(struct srcu_struct *sp)
+void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced)
{
WARN_ON(sp->srcu_lock_nesting[0] || sp->srcu_lock_nesting[1]);
- flush_work(&sp->srcu_work);
+ if (quiesced)
+ WARN_ON(work_pending(&sp->srcu_work));
+ else
+ flush_work(&sp->srcu_work);
WARN_ON(sp->srcu_gp_running);
WARN_ON(sp->srcu_gp_waiting);
WARN_ON(sp->srcu_cb_head);
WARN_ON(&sp->srcu_cb_head != sp->srcu_cb_tail);
}
-EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
+EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
/*
* Removes the count for the old reader from the appropriate element of
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index fb560fc..b4123d7 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -366,24 +366,28 @@ static unsigned long srcu_get_delay(struct srcu_struct *sp)
return SRCU_INTERVAL;
}
-/**
- * cleanup_srcu_struct - deconstruct a sleep-RCU structure
- * @sp: structure to clean up.
- *
- * Must invoke this after you are finished using a given srcu_struct that
- * was initialized via init_srcu_struct(), else you leak memory.
- */
-void cleanup_srcu_struct(struct srcu_struct *sp)
+/* Helper for cleanup_srcu_struct() and cleanup_srcu_struct_quiesced(). */
+void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced)
{
int cpu;
if (WARN_ON(!srcu_get_delay(sp)))
- return; /* Leakage unless caller handles error. */
+ return; /* Just leak it! */
if (WARN_ON(srcu_readers_active(sp)))
- return; /* Leakage unless caller handles error. */
- flush_delayed_work(&sp->work);
+ return; /* Just leak it! */
+ if (quiesced) {
+ if (WARN_ON(delayed_work_pending(&sp->work)))
+ return; /* Just leak it! */
+ } else {
+ flush_delayed_work(&sp->work);
+ }
for_each_possible_cpu(cpu)
- flush_delayed_work(&per_cpu_ptr(sp->sda, cpu)->work);
+ if (quiesced) {
+ if (WARN_ON(delayed_work_pending(&per_cpu_ptr(sp->sda, cpu)->work)))
+ return; /* Just leak it! */
+ } else {
+ flush_delayed_work(&per_cpu_ptr(sp->sda, cpu)->work);
+ }
if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
WARN_ON(srcu_readers_active(sp))) {
pr_info("%s: Active srcu_struct %p state: %d\n", __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
@@ -392,7 +396,7 @@ void cleanup_srcu_struct(struct srcu_struct *sp)
free_percpu(sp->sda);
sp->sda = NULL;
}
-EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
+EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
/*
* Counts the new reader in the appropriate per-CPU element of the
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 2a73469..aa7cade 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -524,8 +524,6 @@ module_param(rcu_kick_kthreads, bool, 0644);
static ulong jiffies_till_sched_qs = HZ / 10;
module_param(jiffies_till_sched_qs, ulong, 0444);
-static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
- struct rcu_data *rdp);
static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp));
static void force_quiescent_state(struct rcu_state *rsp);
static int rcu_pending(void);
@@ -711,44 +709,6 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
}
/*
- * Is there any need for future grace periods?
- * Interrupts must be disabled. If the caller does not hold the root
- * rnp_node structure's ->lock, the results are advisory only.
- */
-static int rcu_future_needs_gp(struct rcu_state *rsp)
-{
- struct rcu_node *rnp = rcu_get_root(rsp);
- int idx = (READ_ONCE(rnp->completed) + 1) & 0x1;
- int *fp = &rnp->need_future_gp[idx];
-
- lockdep_assert_irqs_disabled();
- return READ_ONCE(*fp);
-}
-
-/*
- * Does the current CPU require a not-yet-started grace period?
- * The caller must have disabled interrupts to prevent races with
- * normal callback registry.
- */
-static bool
-cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
-{
- lockdep_assert_irqs_disabled();
- if (rcu_gp_in_progress(rsp))
- return false; /* No, a grace period is already in progress. */
- if (rcu_future_needs_gp(rsp))
- return true; /* Yes, a no-CBs CPU needs one. */
- if (!rcu_segcblist_is_enabled(&rdp->cblist))
- return false; /* No, this is a no-CBs (or offline) CPU. */
- if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
- return true; /* Yes, CPU has newly registered callbacks. */
- if (rcu_segcblist_future_gp_needed(&rdp->cblist,
- READ_ONCE(rsp->completed)))
- return true; /* Yes, CBs for future grace period. */
- return false; /* No grace period needed. */
-}
-
-/*
* Enter an RCU extended quiescent state, which can be either the
* idle loop or adaptive-tickless usermode execution.
*
@@ -1234,10 +1194,10 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
}
/*
- * Has this CPU encountered a cond_resched_rcu_qs() since the
- * beginning of the grace period? For this to be the case,
- * the CPU has to have noticed the current grace period. This
- * might not be the case for nohz_full CPUs looping in the kernel.
+ * Has this CPU encountered a cond_resched() since the beginning
+ * of the grace period? For this to be the case, the CPU has to
+ * have noticed the current grace period. This might not be the
+ * case for nohz_full CPUs looping in the kernel.
*/
jtsq = jiffies_till_sched_qs;
ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu);
@@ -1642,18 +1602,30 @@ static unsigned long rcu_cbs_completed(struct rcu_state *rsp,
return rnp->completed + 1;
/*
+ * If the current rcu_node structure believes that RCU is
+ * idle, and if the rcu_state structure does not yet reflect
+ * the start of a new grace period, then the next grace period
+ * will suffice. The memory barrier is needed to accurately
+ * sample the rsp->gpnum, and pairs with the second lock
+ * acquisition in rcu_gp_init(), which is augmented with
+ * smp_mb__after_unlock_lock() for this purpose.
+ */
+ if (rnp->gpnum == rnp->completed) {
+ smp_mb(); /* See above block comment. */
+ if (READ_ONCE(rsp->gpnum) == rnp->completed)
+ return rnp->completed + 1;
+ }
+
+ /*
* Otherwise, wait for a possible partial grace period and
* then the subsequent full grace period.
*/
return rnp->completed + 2;
}
-/*
- * Trace-event helper function for rcu_start_future_gp() and
- * rcu_nocb_wait_gp().
- */
-static void trace_rcu_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
- unsigned long c, const char *s)
+/* Trace-event wrapper function for trace_rcu_future_grace_period. */
+static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
+ unsigned long c, const char *s)
{
trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum,
rnp->completed, c, rnp->level,
@@ -1661,96 +1633,67 @@ static void trace_rcu_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
}
/*
- * Start some future grace period, as needed to handle newly arrived
+ * Start the specified grace period, as needed to handle newly arrived
* callbacks. The required future grace periods are recorded in each
- * rcu_node structure's ->need_future_gp field. Returns true if there
+ * rcu_node structure's ->need_future_gp[] field. Returns true if there
* is reason to awaken the grace-period kthread.
*
- * The caller must hold the specified rcu_node structure's ->lock.
+ * The caller must hold the specified rcu_node structure's ->lock, which
+ * is why the caller is responsible for waking the grace-period kthread.
*/
-static bool __maybe_unused
-rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
- unsigned long *c_out)
+static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
+ unsigned long c)
{
- unsigned long c;
bool ret = false;
- struct rcu_node *rnp_root = rcu_get_root(rdp->rsp);
+ struct rcu_state *rsp = rdp->rsp;
+ struct rcu_node *rnp_root;
+ /*
+ * Use funnel locking to either acquire the root rcu_node
+ * structure's lock or bail out if the need for this grace period
+ * has already been recorded -- or has already started. If there
+ * is already a grace period in progress in a non-leaf node, no
+ * recording is needed because the end of the grace period will
+ * scan the leaf rcu_node structures. Note that rnp->lock must
+ * not be released.
+ */
raw_lockdep_assert_held_rcu_node(rnp);
-
- /*
- * Pick up grace-period number for new callbacks. If this
- * grace period is already marked as needed, return to the caller.
- */
- c = rcu_cbs_completed(rdp->rsp, rnp);
- trace_rcu_future_gp(rnp, rdp, c, TPS("Startleaf"));
- if (rnp->need_future_gp[c & 0x1]) {
- trace_rcu_future_gp(rnp, rdp, c, TPS("Prestartleaf"));
- goto out;
+ trace_rcu_this_gp(rnp, rdp, c, TPS("Startleaf"));
+ for (rnp_root = rnp; 1; rnp_root = rnp_root->parent) {
+ if (rnp_root != rnp)
+ raw_spin_lock_rcu_node(rnp_root);
+ WARN_ON_ONCE(ULONG_CMP_LT(rnp_root->gpnum +
+ need_future_gp_mask(), c));
+ if (need_future_gp_element(rnp_root, c) ||
+ ULONG_CMP_GE(rnp_root->gpnum, c) ||
+ (rnp != rnp_root &&
+ rnp_root->gpnum != rnp_root->completed)) {
+ trace_rcu_this_gp(rnp_root, rdp, c, TPS("Prestarted"));
+ goto unlock_out;
+ }
+ need_future_gp_element(rnp_root, c) = true;
+ if (rnp_root != rnp && rnp_root->parent != NULL)
+ raw_spin_unlock_rcu_node(rnp_root);
+ if (!rnp_root->parent)
+ break; /* At root, and perhaps also leaf. */
}
- /*
- * If either this rcu_node structure or the root rcu_node structure
- * believe that a grace period is in progress, then we must wait
- * for the one following, which is in "c". Because our request
- * will be noticed at the end of the current grace period, we don't
- * need to explicitly start one. We only do the lockless check
- * of rnp_root's fields if the current rcu_node structure thinks
- * there is no grace period in flight, and because we hold rnp->lock,
- * the only possible change is when rnp_root's two fields are
- * equal, in which case rnp_root->gpnum might be concurrently
- * incremented. But that is OK, as it will just result in our
- * doing some extra useless work.
- */
- if (rnp->gpnum != rnp->completed ||
- READ_ONCE(rnp_root->gpnum) != READ_ONCE(rnp_root->completed)) {
- rnp->need_future_gp[c & 0x1]++;
- trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf"));
- goto out;
- }
-
- /*
- * There might be no grace period in progress. If we don't already
- * hold it, acquire the root rcu_node structure's lock in order to
- * start one (if needed).
- */
- if (rnp != rnp_root)
- raw_spin_lock_rcu_node(rnp_root);
-
- /*
- * Get a new grace-period number. If there really is no grace
- * period in progress, it will be smaller than the one we obtained
- * earlier. Adjust callbacks as needed.
- */
- c = rcu_cbs_completed(rdp->rsp, rnp_root);
- if (!rcu_is_nocb_cpu(rdp->cpu))
- (void)rcu_segcblist_accelerate(&rdp->cblist, c);
-
- /*
- * If the needed for the required grace period is already
- * recorded, trace and leave.
- */
- if (rnp_root->need_future_gp[c & 0x1]) {
- trace_rcu_future_gp(rnp, rdp, c, TPS("Prestartedroot"));
+ /* If GP already in progress, just leave, otherwise start one. */
+ if (rnp_root->gpnum != rnp_root->completed) {
+ trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedleafroot"));
goto unlock_out;
}
-
- /* Record the need for the future grace period. */
- rnp_root->need_future_gp[c & 0x1]++;
-
- /* If a grace period is not already in progress, start one. */
- if (rnp_root->gpnum != rnp_root->completed) {
- trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleafroot"));
- } else {
- trace_rcu_future_gp(rnp, rdp, c, TPS("Startedroot"));
- ret = rcu_start_gp_advanced(rdp->rsp, rnp_root, rdp);
+ trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedroot"));
+ WRITE_ONCE(rsp->gp_flags, rsp->gp_flags | RCU_GP_FLAG_INIT);
+ if (!rsp->gp_kthread) {
+ trace_rcu_this_gp(rnp_root, rdp, c, TPS("NoGPkthread"));
+ goto unlock_out;
}
+ trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("newreq"));
+ ret = true; /* Caller must wake GP kthread. */
unlock_out:
if (rnp != rnp_root)
raw_spin_unlock_rcu_node(rnp_root);
-out:
- if (c_out != NULL)
- *c_out = c;
return ret;
}
@@ -1758,16 +1701,16 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
* Clean up any old requests for the just-ended grace period. Also return
* whether any additional grace periods have been requested.
*/
-static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
+static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
{
- int c = rnp->completed;
- int needmore;
+ unsigned long c = rnp->completed;
+ bool needmore;
struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
- rnp->need_future_gp[c & 0x1] = 0;
- needmore = rnp->need_future_gp[(c + 1) & 0x1];
- trace_rcu_future_gp(rnp, rdp, c,
- needmore ? TPS("CleanupMore") : TPS("Cleanup"));
+ need_future_gp_element(rnp, c) = false;
+ needmore = need_any_future_gp(rnp);
+ trace_rcu_this_gp(rnp, rdp, c,
+ needmore ? TPS("CleanupMore") : TPS("Cleanup"));
return needmore;
}
@@ -1802,6 +1745,7 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp)
static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
struct rcu_data *rdp)
{
+ unsigned long c;
bool ret = false;
raw_lockdep_assert_held_rcu_node(rnp);
@@ -1820,8 +1764,9 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
* accelerating callback invocation to an earlier grace-period
* number.
*/
- if (rcu_segcblist_accelerate(&rdp->cblist, rcu_cbs_completed(rsp, rnp)))
- ret = rcu_start_future_gp(rnp, rdp, NULL);
+ c = rcu_cbs_completed(rsp, rnp);
+ if (rcu_segcblist_accelerate(&rdp->cblist, c))
+ ret = rcu_start_this_gp(rnp, rdp, c);
/* Trace depending on how much we were able to accelerate. */
if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL))
@@ -2049,7 +1994,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
rnp->level, rnp->grplo,
rnp->grphi, rnp->qsmask);
raw_spin_unlock_irq_rcu_node(rnp);
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
}
@@ -2108,7 +2053,6 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
{
unsigned long gp_duration;
bool needgp = false;
- int nocb = 0;
struct rcu_data *rdp;
struct rcu_node *rnp = rcu_get_root(rsp);
struct swait_queue_head *sq;
@@ -2147,31 +2091,35 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
if (rnp == rdp->mynode)
needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
/* smp_mb() provided by prior unlock-lock pair. */
- nocb += rcu_future_gp_cleanup(rsp, rnp);
+ needgp = rcu_future_gp_cleanup(rsp, rnp) || needgp;
sq = rcu_nocb_gp_get(rnp);
raw_spin_unlock_irq_rcu_node(rnp);
rcu_nocb_gp_cleanup(sq);
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
rcu_gp_slow(rsp, gp_cleanup_delay);
}
rnp = rcu_get_root(rsp);
raw_spin_lock_irq_rcu_node(rnp); /* Order GP before ->completed update. */
- rcu_nocb_gp_set(rnp, nocb);
/* Declare grace period done. */
WRITE_ONCE(rsp->completed, rsp->gpnum);
trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
rsp->gp_state = RCU_GP_IDLE;
+ /* Check for GP requests since above loop. */
rdp = this_cpu_ptr(rsp->rda);
+ if (need_any_future_gp(rnp)) {
+ trace_rcu_this_gp(rnp, rdp, rsp->completed - 1,
+ TPS("CleanupMore"));
+ needgp = true;
+ }
/* Advance CBs to reduce false positives below. */
- needgp = rcu_advance_cbs(rsp, rnp, rdp) || needgp;
- if (needgp || cpu_needs_another_gp(rsp, rdp)) {
+ if (!rcu_accelerate_cbs(rsp, rnp, rdp) && needgp) {
WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
- trace_rcu_grace_period(rsp->name,
- READ_ONCE(rsp->gpnum),
+ trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
TPS("newreq"));
}
+ WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT);
raw_spin_unlock_irq_rcu_node(rnp);
}
@@ -2202,7 +2150,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
/* Locking provides needed memory barrier. */
if (rcu_gp_init(rsp))
break;
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rsp->name,
@@ -2247,7 +2195,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
trace_rcu_grace_period(rsp->name,
READ_ONCE(rsp->gpnum),
TPS("fqsend"));
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
ret = 0; /* Force full wait till next FQS. */
j = jiffies_till_next_fqs;
@@ -2260,7 +2208,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
}
} else {
/* Deal with stray signal. */
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
WRITE_ONCE(rsp->gp_activity, jiffies);
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rsp->name,
@@ -2283,71 +2231,6 @@ static int __noreturn rcu_gp_kthread(void *arg)
}
/*
- * Start a new RCU grace period if warranted, re-initializing the hierarchy
- * in preparation for detecting the next grace period. The caller must hold
- * the root node's ->lock and hard irqs must be disabled.
- *
- * Note that it is legal for a dying CPU (which is marked as offline) to
- * invoke this function. This can happen when the dying CPU reports its
- * quiescent state.
- *
- * Returns true if the grace-period kthread must be awakened.
- */
-static bool
-rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
- struct rcu_data *rdp)
-{
- raw_lockdep_assert_held_rcu_node(rnp);
- if (!rsp->gp_kthread || !cpu_needs_another_gp(rsp, rdp)) {
- /*
- * Either we have not yet spawned the grace-period
- * task, this CPU does not need another grace period,
- * or a grace period is already in progress.
- * Either way, don't start a new grace period.
- */
- return false;
- }
- WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
- trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
- TPS("newreq"));
-
- /*
- * We can't do wakeups while holding the rnp->lock, as that
- * could cause possible deadlocks with the rq->lock. Defer
- * the wakeup to our caller.
- */
- return true;
-}
-
-/*
- * Similar to rcu_start_gp_advanced(), but also advance the calling CPU's
- * callbacks. Note that rcu_start_gp_advanced() cannot do this because it
- * is invoked indirectly from rcu_advance_cbs(), which would result in
- * endless recursion -- or would do so if it wasn't for the self-deadlock
- * that is encountered beforehand.
- *
- * Returns true if the grace-period kthread needs to be awakened.
- */
-static bool rcu_start_gp(struct rcu_state *rsp)
-{
- struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
- struct rcu_node *rnp = rcu_get_root(rsp);
- bool ret = false;
-
- /*
- * If there is no grace period in progress right now, any
- * callbacks we have up to this point will be satisfied by the
- * next grace period. Also, advancing the callbacks reduces the
- * probability of false positives from cpu_needs_another_gp()
- * resulting in pointless grace periods. So, advance callbacks
- * then start the grace period!
- */
- ret = rcu_advance_cbs(rsp, rnp, rdp) || ret;
- ret = rcu_start_gp_advanced(rsp, rnp, rdp) || ret;
- return ret;
-}
-
-/*
* Report a full set of quiescent states to the specified rcu_state data
* structure. Invoke rcu_gp_kthread_wake() to awaken the grace-period
* kthread if another grace period is required. Whether we wake
@@ -2398,7 +2281,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
return;
}
WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */
- WARN_ON_ONCE(rnp->level != rcu_num_lvls - 1 &&
+ WARN_ON_ONCE(!rcu_is_leaf_node(rnp) &&
rcu_preempt_blocked_readers_cgp(rnp));
rnp->qsmask &= ~mask;
trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum,
@@ -2782,7 +2665,7 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp))
struct rcu_node *rnp;
rcu_for_each_leaf_node(rsp, rnp) {
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
mask = 0;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (rnp->qsmask == 0) {
@@ -2874,22 +2757,27 @@ __rcu_process_callbacks(struct rcu_state *rsp)
unsigned long flags;
bool needwake;
struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
+ struct rcu_node *rnp;
WARN_ON_ONCE(!rdp->beenonline);
/* Update RCU state based on any recent quiescent states. */
rcu_check_quiescent_state(rsp, rdp);
- /* Does this CPU require a not-yet-started grace period? */
- local_irq_save(flags);
- if (cpu_needs_another_gp(rsp, rdp)) {
- raw_spin_lock_rcu_node(rcu_get_root(rsp)); /* irqs disabled. */
- needwake = rcu_start_gp(rsp);
- raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags);
- if (needwake)
- rcu_gp_kthread_wake(rsp);
- } else {
- local_irq_restore(flags);
+ /* No grace period and unregistered callbacks? */
+ if (!rcu_gp_in_progress(rsp) &&
+ rcu_segcblist_is_enabled(&rdp->cblist)) {
+ local_irq_save(flags);
+ if (rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) {
+ local_irq_restore(flags);
+ } else {
+ rnp = rdp->mynode;
+ raw_spin_lock_rcu_node(rnp); /* irqs disabled. */
+ needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ if (needwake)
+ rcu_gp_kthread_wake(rsp);
+ }
}
/* If there are callbacks ready, invoke them. */
@@ -2973,11 +2861,11 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
/* Start a new grace period if one not already started. */
if (!rcu_gp_in_progress(rsp)) {
- struct rcu_node *rnp_root = rcu_get_root(rsp);
+ struct rcu_node *rnp = rdp->mynode;
- raw_spin_lock_rcu_node(rnp_root);
- needwake = rcu_start_gp(rsp);
- raw_spin_unlock_rcu_node(rnp_root);
+ raw_spin_lock_rcu_node(rnp);
+ needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
+ raw_spin_unlock_rcu_node(rnp);
if (needwake)
rcu_gp_kthread_wake(rsp);
} else {
@@ -3368,7 +3256,9 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
return 1;
/* Has RCU gone idle with this CPU needing another grace period? */
- if (cpu_needs_another_gp(rsp, rdp))
+ if (!rcu_gp_in_progress(rsp) &&
+ rcu_segcblist_is_enabled(&rdp->cblist) &&
+ !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
return 1;
/* Has another RCU grace period completed? */
@@ -3775,6 +3665,8 @@ int rcutree_dead_cpu(unsigned int cpu)
return 0;
}
+static DEFINE_PER_CPU(int, rcu_cpu_started);
+
/*
* Mark the specified CPU as being online so that subsequent grace periods
* (both expedited and normal) will wait on it. Note that this means that
@@ -3796,6 +3688,11 @@ void rcu_cpu_starting(unsigned int cpu)
struct rcu_node *rnp;
struct rcu_state *rsp;
+ if (per_cpu(rcu_cpu_started, cpu))
+ return;
+
+ per_cpu(rcu_cpu_started, cpu) = 1;
+
for_each_rcu_flavor(rsp) {
rdp = per_cpu_ptr(rsp->rda, cpu);
rnp = rdp->mynode;
@@ -3852,6 +3749,8 @@ void rcu_report_dead(unsigned int cpu)
preempt_enable();
for_each_rcu_flavor(rsp)
rcu_cleanup_dying_idle_cpu(cpu, rsp);
+
+ per_cpu(rcu_cpu_started, cpu) = 0;
}
/* Migrate the dead CPU's callbacks to the current CPU. */
@@ -3861,6 +3760,7 @@ static void rcu_migrate_callbacks(int cpu, struct rcu_state *rsp)
struct rcu_data *my_rdp;
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
struct rcu_node *rnp_root = rcu_get_root(rdp->rsp);
+ bool needwake;
if (rcu_is_nocb_cpu(cpu) || rcu_segcblist_empty(&rdp->cblist))
return; /* No callbacks to migrate. */
@@ -3872,12 +3772,15 @@ static void rcu_migrate_callbacks(int cpu, struct rcu_state *rsp)
return;
}
raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
- rcu_advance_cbs(rsp, rnp_root, rdp); /* Leverage recent GPs. */
- rcu_advance_cbs(rsp, rnp_root, my_rdp); /* Assign GP to pending CBs. */
+ /* Leverage recent GPs and set GP for new callbacks. */
+ needwake = rcu_advance_cbs(rsp, rnp_root, rdp) ||
+ rcu_advance_cbs(rsp, rnp_root, my_rdp);
rcu_segcblist_merge(&my_rdp->cblist, &rdp->cblist);
WARN_ON_ONCE(rcu_segcblist_empty(&my_rdp->cblist) !=
!rcu_segcblist_n_cbs(&my_rdp->cblist));
raw_spin_unlock_irqrestore_rcu_node(rnp_root, flags);
+ if (needwake)
+ rcu_gp_kthread_wake(rsp);
WARN_ONCE(rcu_segcblist_n_cbs(&rdp->cblist) != 0 ||
!rcu_segcblist_empty(&rdp->cblist),
"rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, 1stCB=%p\n",
@@ -4056,7 +3959,7 @@ static void __init rcu_init_one(struct rcu_state *rsp)
init_swait_queue_head(&rsp->gp_wq);
init_swait_queue_head(&rsp->expedited_wq);
- rnp = rsp->level[rcu_num_lvls - 1];
+ rnp = rcu_first_leaf_node(rsp);
for_each_possible_cpu(i) {
while (i > rnp->grphi)
rnp++;
@@ -4168,6 +4071,7 @@ static void __init rcu_dump_rcu_node_tree(struct rcu_state *rsp)
}
struct workqueue_struct *rcu_gp_wq;
+struct workqueue_struct *rcu_par_gp_wq;
void __init rcu_init(void)
{
@@ -4199,6 +4103,8 @@ void __init rcu_init(void)
/* Create workqueue for expedited GPs and for Tree SRCU. */
rcu_gp_wq = alloc_workqueue("rcu_gp", WQ_MEM_RECLAIM, 0);
WARN_ON(!rcu_gp_wq);
+ rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0);
+ WARN_ON(!rcu_par_gp_wq);
}
#include "tree_exp.h"
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index f491ab4..78e051d 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -58,6 +58,14 @@ struct rcu_dynticks {
#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
};
+/* Communicate arguments to a workqueue handler. */
+struct rcu_exp_work {
+ smp_call_func_t rew_func;
+ struct rcu_state *rew_rsp;
+ unsigned long rew_s;
+ struct work_struct rew_work;
+};
+
/* RCU's kthread states for tracing. */
#define RCU_KTHREAD_STOPPED 0
#define RCU_KTHREAD_RUNNING 1
@@ -150,15 +158,32 @@ struct rcu_node {
struct swait_queue_head nocb_gp_wq[2];
/* Place for rcu_nocb_kthread() to wait GP. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
- int need_future_gp[2];
- /* Counts of upcoming no-CB GP requests. */
+ u8 need_future_gp[4]; /* Counts of upcoming GP requests. */
raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp;
spinlock_t exp_lock ____cacheline_internodealigned_in_smp;
unsigned long exp_seq_rq;
wait_queue_head_t exp_wq[4];
+ struct rcu_exp_work rew;
+ bool exp_need_flush; /* Need to flush workitem? */
} ____cacheline_internodealigned_in_smp;
+/* Accessors for ->need_future_gp[] array. */
+#define need_future_gp_mask() \
+ (ARRAY_SIZE(((struct rcu_node *)NULL)->need_future_gp) - 1)
+#define need_future_gp_element(rnp, c) \
+ ((rnp)->need_future_gp[(c) & need_future_gp_mask()])
+#define need_any_future_gp(rnp) \
+({ \
+ int __i; \
+ bool __nonzero = false; \
+ \
+ for (__i = 0; __i < ARRAY_SIZE((rnp)->need_future_gp); __i++) \
+ __nonzero = __nonzero || \
+ READ_ONCE((rnp)->need_future_gp[__i]); \
+ __nonzero; \
+})
+
/*
* Bitmasks in an rcu_node cover the interval [grplo, grphi] of CPU IDs, and
* are indexed relative to this interval rather than the global CPU ID space.
@@ -224,10 +249,6 @@ struct rcu_data {
#ifdef CONFIG_RCU_FAST_NO_HZ
struct rcu_head oom_head;
#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
- atomic_long_t exp_workdone0; /* # done by workqueue. */
- atomic_long_t exp_workdone1; /* # done by others #1. */
- atomic_long_t exp_workdone2; /* # done by others #2. */
- atomic_long_t exp_workdone3; /* # done by others #3. */
int exp_dynticks_snap; /* Double-check need for IPI. */
/* 6) Callback offloading. */
@@ -408,7 +429,6 @@ extern struct rcu_state rcu_preempt_state;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
int rcu_dynticks_snap(struct rcu_dynticks *rdtp);
-bool rcu_eqs_special_set(int cpu);
#ifdef CONFIG_RCU_BOOST
DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
@@ -438,7 +458,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
static void invoke_rcu_callbacks_kthread(void);
static bool rcu_is_callbacks_kthread(void);
#ifdef CONFIG_RCU_BOOST
-static void rcu_preempt_do_callbacks(void);
static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
struct rcu_node *rnp);
#endif /* #ifdef CONFIG_RCU_BOOST */
@@ -454,7 +473,6 @@ static void print_cpu_stall_info_end(void);
static void zero_cpu_stall_ticks(struct rcu_data *rdp);
static void increment_cpu_stall_ticks(void);
static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu);
-static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp);
static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq);
static void rcu_init_one_nocb(struct rcu_node *rnp);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index f72eefa..d40708e 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -20,6 +20,8 @@
* Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
*/
+#include <linux/lockdep.h>
+
/*
* Record the start of an expedited grace period.
*/
@@ -154,15 +156,35 @@ static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp)
* for the current expedited grace period. Works only for preemptible
* RCU -- other RCU implementation use other means.
*
- * Caller must hold the rcu_state's exp_mutex.
+ * Caller must hold the specificed rcu_node structure's ->lock
*/
static bool sync_rcu_preempt_exp_done(struct rcu_node *rnp)
{
+ raw_lockdep_assert_held_rcu_node(rnp);
+
return rnp->exp_tasks == NULL &&
READ_ONCE(rnp->expmask) == 0;
}
/*
+ * Like sync_rcu_preempt_exp_done(), but this function assumes the caller
+ * doesn't hold the rcu_node's ->lock, and will acquire and release the lock
+ * itself
+ */
+static bool sync_rcu_preempt_exp_done_unlocked(struct rcu_node *rnp)
+{
+ unsigned long flags;
+ bool ret;
+
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ ret = sync_rcu_preempt_exp_done(rnp);
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+
+ return ret;
+}
+
+
+/*
* Report the exit from RCU read-side critical section for the last task
* that queued itself during or before the current expedited preemptible-RCU
* grace period. This event is reported either to the rcu_node structure on
@@ -170,8 +192,7 @@ static bool sync_rcu_preempt_exp_done(struct rcu_node *rnp)
* recursively up the tree. (Calm down, calm down, we do the recursion
* iteratively!)
*
- * Caller must hold the rcu_state's exp_mutex and the specified rcu_node
- * structure's ->lock.
+ * Caller must hold the specified rcu_node structure's ->lock.
*/
static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
bool wake, unsigned long flags)
@@ -207,8 +228,6 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
/*
* Report expedited quiescent state for specified node. This is a
* lock-acquisition wrapper function for __rcu_report_exp_rnp().
- *
- * Caller must hold the rcu_state's exp_mutex.
*/
static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp,
struct rcu_node *rnp, bool wake)
@@ -221,8 +240,7 @@ static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp,
/*
* Report expedited quiescent state for multiple CPUs, all covered by the
- * specified leaf rcu_node structure. Caller must hold the rcu_state's
- * exp_mutex.
+ * specified leaf rcu_node structure.
*/
static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp,
unsigned long mask, bool wake)
@@ -248,14 +266,12 @@ static void rcu_report_exp_rdp(struct rcu_state *rsp, struct rcu_data *rdp,
}
/* Common code for synchronize_{rcu,sched}_expedited() work-done checking. */
-static bool sync_exp_work_done(struct rcu_state *rsp, atomic_long_t *stat,
- unsigned long s)
+static bool sync_exp_work_done(struct rcu_state *rsp, unsigned long s)
{
if (rcu_exp_gp_seq_done(rsp, s)) {
trace_rcu_exp_grace_period(rsp->name, s, TPS("done"));
/* Ensure test happens before caller kfree(). */
smp_mb__before_atomic(); /* ^^^ */
- atomic_long_inc(stat);
return true;
}
return false;
@@ -289,7 +305,7 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
* promoting locality and is not strictly needed for correctness.
*/
for (; rnp != NULL; rnp = rnp->parent) {
- if (sync_exp_work_done(rsp, &rdp->exp_workdone1, s))
+ if (sync_exp_work_done(rsp, s))
return true;
/* Work not done, either wait here or go up. */
@@ -302,8 +318,7 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
rnp->grplo, rnp->grphi,
TPS("wait"));
wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
- sync_exp_work_done(rsp,
- &rdp->exp_workdone2, s));
+ sync_exp_work_done(rsp, s));
return true;
}
rnp->exp_seq_rq = s; /* Followers can wait on us. */
@@ -313,7 +328,7 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
}
mutex_lock(&rsp->exp_mutex);
fastpath:
- if (sync_exp_work_done(rsp, &rdp->exp_workdone3, s)) {
+ if (sync_exp_work_done(rsp, s)) {
mutex_unlock(&rsp->exp_mutex);
return true;
}
@@ -362,93 +377,129 @@ static void sync_sched_exp_online_cleanup(int cpu)
}
/*
+ * Select the CPUs within the specified rcu_node that the upcoming
+ * expedited grace period needs to wait for.
+ */
+static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
+{
+ int cpu;
+ unsigned long flags;
+ smp_call_func_t func;
+ unsigned long mask_ofl_test;
+ unsigned long mask_ofl_ipi;
+ int ret;
+ struct rcu_exp_work *rewp =
+ container_of(wp, struct rcu_exp_work, rew_work);
+ struct rcu_node *rnp = container_of(rewp, struct rcu_node, rew);
+ struct rcu_state *rsp = rewp->rew_rsp;
+
+ func = rewp->rew_func;
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+
+ /* Each pass checks a CPU for identity, offline, and idle. */
+ mask_ofl_test = 0;
+ for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
+ unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
+ struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+ struct rcu_dynticks *rdtp = per_cpu_ptr(&rcu_dynticks, cpu);
+ int snap;
+
+ if (raw_smp_processor_id() == cpu ||
+ !(rnp->qsmaskinitnext & mask)) {
+ mask_ofl_test |= mask;
+ } else {
+ snap = rcu_dynticks_snap(rdtp);
+ if (rcu_dynticks_in_eqs(snap))
+ mask_ofl_test |= mask;
+ else
+ rdp->exp_dynticks_snap = snap;
+ }
+ }
+ mask_ofl_ipi = rnp->expmask & ~mask_ofl_test;
+
+ /*
+ * Need to wait for any blocked tasks as well. Note that
+ * additional blocking tasks will also block the expedited GP
+ * until such time as the ->expmask bits are cleared.
+ */
+ if (rcu_preempt_has_tasks(rnp))
+ rnp->exp_tasks = rnp->blkd_tasks.next;
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+
+ /* IPI the remaining CPUs for expedited quiescent state. */
+ for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
+ unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
+ struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+
+ if (!(mask_ofl_ipi & mask))
+ continue;
+retry_ipi:
+ if (rcu_dynticks_in_eqs_since(rdp->dynticks,
+ rdp->exp_dynticks_snap)) {
+ mask_ofl_test |= mask;
+ continue;
+ }
+ ret = smp_call_function_single(cpu, func, rsp, 0);
+ if (!ret) {
+ mask_ofl_ipi &= ~mask;
+ continue;
+ }
+ /* Failed, raced with CPU hotplug operation. */
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ if ((rnp->qsmaskinitnext & mask) &&
+ (rnp->expmask & mask)) {
+ /* Online, so delay for a bit and try again. */
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("selectofl"));
+ schedule_timeout_uninterruptible(1);
+ goto retry_ipi;
+ }
+ /* CPU really is offline, so we can ignore it. */
+ if (!(rnp->expmask & mask))
+ mask_ofl_ipi &= ~mask;
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ }
+ /* Report quiescent states for those that went offline. */
+ mask_ofl_test |= mask_ofl_ipi;
+ if (mask_ofl_test)
+ rcu_report_exp_cpu_mult(rsp, rnp, mask_ofl_test, false);
+}
+
+/*
* Select the nodes that the upcoming expedited grace period needs
* to wait for.
*/
static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
smp_call_func_t func)
{
- int cpu;
- unsigned long flags;
- unsigned long mask_ofl_test;
- unsigned long mask_ofl_ipi;
- int ret;
struct rcu_node *rnp;
trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset"));
sync_exp_reset_tree(rsp);
trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("select"));
+
+ /* Schedule work for each leaf rcu_node structure. */
rcu_for_each_leaf_node(rsp, rnp) {
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
-
- /* Each pass checks a CPU for identity, offline, and idle. */
- mask_ofl_test = 0;
- for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
- unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
- struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
- struct rcu_dynticks *rdtp = per_cpu_ptr(&rcu_dynticks, cpu);
- int snap;
-
- if (raw_smp_processor_id() == cpu ||
- !(rnp->qsmaskinitnext & mask)) {
- mask_ofl_test |= mask;
- } else {
- snap = rcu_dynticks_snap(rdtp);
- if (rcu_dynticks_in_eqs(snap))
- mask_ofl_test |= mask;
- else
- rdp->exp_dynticks_snap = snap;
- }
+ rnp->exp_need_flush = false;
+ if (!READ_ONCE(rnp->expmask))
+ continue; /* Avoid early boot non-existent wq. */
+ rnp->rew.rew_func = func;
+ rnp->rew.rew_rsp = rsp;
+ if (!READ_ONCE(rcu_par_gp_wq) ||
+ rcu_scheduler_active != RCU_SCHEDULER_RUNNING) {
+ /* No workqueues yet. */
+ sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work);
+ continue;
}
- mask_ofl_ipi = rnp->expmask & ~mask_ofl_test;
-
- /*
- * Need to wait for any blocked tasks as well. Note that
- * additional blocking tasks will also block the expedited
- * GP until such time as the ->expmask bits are cleared.
- */
- if (rcu_preempt_has_tasks(rnp))
- rnp->exp_tasks = rnp->blkd_tasks.next;
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-
- /* IPI the remaining CPUs for expedited quiescent state. */
- for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
- unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
- struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
-
- if (!(mask_ofl_ipi & mask))
- continue;
-retry_ipi:
- if (rcu_dynticks_in_eqs_since(rdp->dynticks,
- rdp->exp_dynticks_snap)) {
- mask_ofl_test |= mask;
- continue;
- }
- ret = smp_call_function_single(cpu, func, rsp, 0);
- if (!ret) {
- mask_ofl_ipi &= ~mask;
- continue;
- }
- /* Failed, raced with CPU hotplug operation. */
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- if ((rnp->qsmaskinitnext & mask) &&
- (rnp->expmask & mask)) {
- /* Online, so delay for a bit and try again. */
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("selectofl"));
- schedule_timeout_uninterruptible(1);
- goto retry_ipi;
- }
- /* CPU really is offline, so we can ignore it. */
- if (!(rnp->expmask & mask))
- mask_ofl_ipi &= ~mask;
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
- }
- /* Report quiescent states for those that went offline. */
- mask_ofl_test |= mask_ofl_ipi;
- if (mask_ofl_test)
- rcu_report_exp_cpu_mult(rsp, rnp, mask_ofl_test, false);
+ INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
+ queue_work_on(rnp->grplo, rcu_par_gp_wq, &rnp->rew.rew_work);
+ rnp->exp_need_flush = true;
}
+
+ /* Wait for workqueue jobs (if any) to complete. */
+ rcu_for_each_leaf_node(rsp, rnp)
+ if (rnp->exp_need_flush)
+ flush_work(&rnp->rew.rew_work);
}
static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
@@ -469,9 +520,9 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
for (;;) {
ret = swait_event_timeout(
rsp->expedited_wq,
- sync_rcu_preempt_exp_done(rnp_root),
+ sync_rcu_preempt_exp_done_unlocked(rnp_root),
jiffies_stall);
- if (ret > 0 || sync_rcu_preempt_exp_done(rnp_root))
+ if (ret > 0 || sync_rcu_preempt_exp_done_unlocked(rnp_root))
return;
WARN_ON(ret < 0); /* workqueues should not be signaled. */
if (rcu_cpu_stall_suppress)
@@ -504,7 +555,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
rcu_for_each_node_breadth_first(rsp, rnp) {
if (rnp == rnp_root)
continue; /* printed unconditionally */
- if (sync_rcu_preempt_exp_done(rnp))
+ if (sync_rcu_preempt_exp_done_unlocked(rnp))
continue;
pr_cont(" l=%u:%d-%d:%#lx/%c",
rnp->level, rnp->grplo, rnp->grphi,
@@ -560,14 +611,6 @@ static void rcu_exp_wait_wake(struct rcu_state *rsp, unsigned long s)
mutex_unlock(&rsp->exp_wake_mutex);
}
-/* Let the workqueue handler know what it is supposed to do. */
-struct rcu_exp_work {
- smp_call_func_t rew_func;
- struct rcu_state *rew_rsp;
- unsigned long rew_s;
- struct work_struct rew_work;
-};
-
/*
* Common code to drive an expedited grace period forward, used by
* workqueues and mid-boot-time tasks.
@@ -633,7 +676,7 @@ static void _synchronize_rcu_expedited(struct rcu_state *rsp,
rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
rnp = rcu_get_root(rsp);
wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
- sync_exp_work_done(rsp, &rdp->exp_workdone0, s));
+ sync_exp_work_done(rsp, s));
smp_mb(); /* Workqueue actions happen before return. */
/* Let the next expedited grace period start. */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 84fbee4..7fd1203 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -182,7 +182,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
raw_lockdep_assert_held_rcu_node(rnp);
WARN_ON_ONCE(rdp->mynode != rnp);
- WARN_ON_ONCE(rnp->level != rcu_num_lvls - 1);
+ WARN_ON_ONCE(!rcu_is_leaf_node(rnp));
/*
* Decide where to queue the newly blocked task. In theory,
@@ -384,6 +384,50 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
}
/*
+ * Preemptible RCU implementation for rcu_read_lock().
+ * Just increment ->rcu_read_lock_nesting, shared state will be updated
+ * if we block.
+ */
+void __rcu_read_lock(void)
+{
+ current->rcu_read_lock_nesting++;
+ barrier(); /* critical section after entry code. */
+}
+EXPORT_SYMBOL_GPL(__rcu_read_lock);
+
+/*
+ * Preemptible RCU implementation for rcu_read_unlock().
+ * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost
+ * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then
+ * invoke rcu_read_unlock_special() to clean up after a context switch
+ * in an RCU read-side critical section and other special cases.
+ */
+void __rcu_read_unlock(void)
+{
+ struct task_struct *t = current;
+
+ if (t->rcu_read_lock_nesting != 1) {
+ --t->rcu_read_lock_nesting;
+ } else {
+ barrier(); /* critical section before exit code. */
+ t->rcu_read_lock_nesting = INT_MIN;
+ barrier(); /* assign before ->rcu_read_unlock_special load */
+ if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s)))
+ rcu_read_unlock_special(t);
+ barrier(); /* ->rcu_read_unlock_special load before assign */
+ t->rcu_read_lock_nesting = 0;
+ }
+#ifdef CONFIG_PROVE_LOCKING
+ {
+ int rrln = READ_ONCE(t->rcu_read_lock_nesting);
+
+ WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
+ }
+#endif /* #ifdef CONFIG_PROVE_LOCKING */
+}
+EXPORT_SYMBOL_GPL(__rcu_read_unlock);
+
+/*
* Advance a ->blkd_tasks-list pointer to the next entry, instead
* returning NULL if at the end of the list.
*/
@@ -489,7 +533,7 @@ void rcu_read_unlock_special(struct task_struct *t)
rnp = t->rcu_blocked_node;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
WARN_ON_ONCE(rnp != t->rcu_blocked_node);
- WARN_ON_ONCE(rnp->level != rcu_num_lvls - 1);
+ WARN_ON_ONCE(!rcu_is_leaf_node(rnp));
empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
empty_exp = sync_rcu_preempt_exp_done(rnp);
smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
@@ -685,15 +729,6 @@ static void rcu_preempt_check_callbacks(void)
t->rcu_read_unlock_special.b.need_qs = true;
}
-#ifdef CONFIG_RCU_BOOST
-
-static void rcu_preempt_do_callbacks(void)
-{
- rcu_do_batch(rcu_state_p, this_cpu_ptr(rcu_data_p));
-}
-
-#endif /* #ifdef CONFIG_RCU_BOOST */
-
/**
* call_rcu() - Queue an RCU callback for invocation after a grace period.
* @head: structure to be used for queueing the RCU updates.
@@ -1140,7 +1175,7 @@ static void rcu_kthread_do_work(void)
{
rcu_do_batch(&rcu_sched_state, this_cpu_ptr(&rcu_sched_data));
rcu_do_batch(&rcu_bh_state, this_cpu_ptr(&rcu_bh_data));
- rcu_preempt_do_callbacks();
+ rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data));
}
static void rcu_cpu_kthread_setup(unsigned int cpu)
@@ -1607,7 +1642,7 @@ static int rcu_oom_notify(struct notifier_block *self,
for_each_online_cpu(cpu) {
smp_call_function_single(cpu, rcu_oom_notify_cpu, NULL, 1);
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
}
/* Unconditionally decrement: no need to wake ourselves up. */
@@ -1780,19 +1815,6 @@ static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq)
swake_up_all(sq);
}
-/*
- * Set the root rcu_node structure's ->need_future_gp field
- * based on the sum of those of all rcu_node structures. This does
- * double-count the root rcu_node structure's requests, but this
- * is necessary to handle the possibility of a rcu_nocb_kthread()
- * having awakened during the time that the rcu_node structures
- * were being updated for the end of the previous grace period.
- */
-static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq)
-{
- rnp->need_future_gp[(rnp->completed + 1) & 0x1] += nrq;
-}
-
static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp)
{
return &rnp->nocb_gp_wq[rnp->completed & 0x1];
@@ -1966,7 +1988,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeOvf"));
} else {
- wake_nocb_leader_defer(rdp, RCU_NOCB_WAKE,
+ wake_nocb_leader_defer(rdp, RCU_NOCB_WAKE_FORCE,
TPS("WakeOvfIsDeferred"));
}
rdp->qlen_last_fqs_check = LONG_MAX / 2;
@@ -2048,7 +2070,8 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
struct rcu_node *rnp = rdp->mynode;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
- needwake = rcu_start_future_gp(rnp, rdp, &c);
+ c = rcu_cbs_completed(rdp->rsp, rnp);
+ needwake = rcu_start_this_gp(rnp, rdp, c);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
if (needwake)
rcu_gp_kthread_wake(rdp->rsp);
@@ -2057,7 +2080,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
* Wait for the grace period. Do so interruptibly to avoid messing
* up the load average.
*/
- trace_rcu_future_gp(rnp, rdp, c, TPS("StartWait"));
+ trace_rcu_this_gp(rnp, rdp, c, TPS("StartWait"));
for (;;) {
swait_event_interruptible(
rnp->nocb_gp_wq[c & 0x1],
@@ -2065,9 +2088,9 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
if (likely(d))
break;
WARN_ON(signal_pending(current));
- trace_rcu_future_gp(rnp, rdp, c, TPS("ResumeWait"));
+ trace_rcu_this_gp(rnp, rdp, c, TPS("ResumeWait"));
}
- trace_rcu_future_gp(rnp, rdp, c, TPS("EndWait"));
+ trace_rcu_this_gp(rnp, rdp, c, TPS("EndWait"));
smp_mb(); /* Ensure that CB invocation happens after GP end. */
}
@@ -2236,7 +2259,7 @@ static int rcu_nocb_kthread(void *arg)
cl++;
c++;
local_bh_enable();
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
list = next;
}
trace_rcu_batch_end(rdp->rsp->name, c, !!list, 0, 0, 1);
@@ -2292,7 +2315,7 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
void __init rcu_init_nohz(void)
{
int cpu;
- bool need_rcu_nocb_mask = true;
+ bool need_rcu_nocb_mask = false;
struct rcu_state *rsp;
#if defined(CONFIG_NO_HZ_FULL)
@@ -2315,7 +2338,7 @@ void __init rcu_init_nohz(void)
#endif /* #if defined(CONFIG_NO_HZ_FULL) */
if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
- pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n");
+ pr_info("\tNote: kernel parameter 'rcu_nocbs=', 'nohz_full', or 'isolcpus=' contains nonexistent CPUs.\n");
cpumask_and(rcu_nocb_mask, cpu_possible_mask,
rcu_nocb_mask);
}
@@ -2495,10 +2518,6 @@ static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq)
{
}
-static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq)
-{
-}
-
static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp)
{
return NULL;
@@ -2587,8 +2606,7 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
}
/*
- * Bind the grace-period kthread for the sysidle flavor of RCU to the
- * timekeeping CPU.
+ * Bind the RCU grace-period kthreads to the housekeeping CPU.
*/
static void rcu_bind_gp_kthread(void)
{
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 68fa19a..4c230a6 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -226,54 +226,6 @@ core_initcall(rcu_set_runtime_mode);
#endif /* #if !defined(CONFIG_TINY_RCU) || defined(CONFIG_SRCU) */
-#ifdef CONFIG_PREEMPT_RCU
-
-/*
- * Preemptible RCU implementation for rcu_read_lock().
- * Just increment ->rcu_read_lock_nesting, shared state will be updated
- * if we block.
- */
-void __rcu_read_lock(void)
-{
- current->rcu_read_lock_nesting++;
- barrier(); /* critical section after entry code. */
-}
-EXPORT_SYMBOL_GPL(__rcu_read_lock);
-
-/*
- * Preemptible RCU implementation for rcu_read_unlock().
- * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost
- * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then
- * invoke rcu_read_unlock_special() to clean up after a context switch
- * in an RCU read-side critical section and other special cases.
- */
-void __rcu_read_unlock(void)
-{
- struct task_struct *t = current;
-
- if (t->rcu_read_lock_nesting != 1) {
- --t->rcu_read_lock_nesting;
- } else {
- barrier(); /* critical section before exit code. */
- t->rcu_read_lock_nesting = INT_MIN;
- barrier(); /* assign before ->rcu_read_unlock_special load */
- if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s)))
- rcu_read_unlock_special(t);
- barrier(); /* ->rcu_read_unlock_special load before assign */
- t->rcu_read_lock_nesting = 0;
- }
-#ifdef CONFIG_PROVE_LOCKING
- {
- int rrln = READ_ONCE(t->rcu_read_lock_nesting);
-
- WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
- }
-#endif /* #ifdef CONFIG_PROVE_LOCKING */
-}
-EXPORT_SYMBOL_GPL(__rcu_read_unlock);
-
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
-
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key rcu_lock_key;
struct lockdep_map rcu_lock_map =
@@ -624,7 +576,7 @@ EXPORT_SYMBOL_GPL(call_rcu_tasks);
* grace period has elapsed, in other words after all currently
* executing rcu-tasks read-side critical sections have elapsed. These
* read-side critical sections are delimited by calls to schedule(),
- * cond_resched_rcu_qs(), idle execution, userspace execution, calls
+ * cond_resched_tasks_rcu_qs(), idle execution, userspace execution, calls
* to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched().
*
* This is a very specialized primitive, intended only for a few uses in
diff --git a/kernel/resource.c b/kernel/resource.c
index 2af6c03..b589dda 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -87,7 +87,7 @@ enum { MAX_IORES_LEVEL = 5 };
static void *r_start(struct seq_file *m, loff_t *pos)
__acquires(resource_lock)
{
- struct resource *p = m->private;
+ struct resource *p = PDE_DATA(file_inode(m->file));
loff_t l = 0;
read_lock(&resource_lock);
for (p = p->child; p && l < *pos; p = r_next(m, p, &l))
@@ -103,7 +103,7 @@ static void r_stop(struct seq_file *m, void *v)
static int r_show(struct seq_file *m, void *v)
{
- struct resource *root = m->private;
+ struct resource *root = PDE_DATA(file_inode(m->file));
struct resource *r = v, *p;
unsigned long long start, end;
int width = root->end < 0x10000 ? 4 : 8;
@@ -135,44 +135,11 @@ static const struct seq_operations resource_op = {
.show = r_show,
};
-static int ioports_open(struct inode *inode, struct file *file)
-{
- int res = seq_open(file, &resource_op);
- if (!res) {
- struct seq_file *m = file->private_data;
- m->private = &ioport_resource;
- }
- return res;
-}
-
-static int iomem_open(struct inode *inode, struct file *file)
-{
- int res = seq_open(file, &resource_op);
- if (!res) {
- struct seq_file *m = file->private_data;
- m->private = &iomem_resource;
- }
- return res;
-}
-
-static const struct file_operations proc_ioports_operations = {
- .open = ioports_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-static const struct file_operations proc_iomem_operations = {
- .open = iomem_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static int __init ioresources_init(void)
{
- proc_create("ioports", 0, NULL, &proc_ioports_operations);
- proc_create("iomem", 0, NULL, &proc_iomem_operations);
+ proc_create_seq_data("ioports", 0, NULL, &resource_op,
+ &ioport_resource);
+ proc_create_seq_data("iomem", 0, NULL, &resource_op, &iomem_resource);
return 0;
}
__initcall(ioresources_init);
diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c
index 6be6c57..2d4ff53 100644
--- a/kernel/sched/autogroup.c
+++ b/kernel/sched/autogroup.c
@@ -2,6 +2,7 @@
/*
* Auto-group scheduling implementation:
*/
+#include <linux/nospec.h>
#include "sched.h"
unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1;
@@ -209,7 +210,7 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
static unsigned long next = INITIAL_JIFFIES;
struct autogroup *ag;
unsigned long shares;
- int err;
+ int err, idx;
if (nice < MIN_NICE || nice > MAX_NICE)
return -EINVAL;
@@ -227,7 +228,9 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
next = HZ / 10 + jiffies;
ag = autogroup_task_get(p);
- shares = scale_load(sched_prio_to_weight[nice + 20]);
+
+ idx = array_index_nospec(nice + 20, 40);
+ shares = scale_load(sched_prio_to_weight[idx]);
down_write(&ag->lock);
err = sched_group_set_shares(ag->tg, shares);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5e10aae..e9866f8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7,6 +7,9 @@
*/
#include "sched.h"
+#include <linux/kthread.h>
+#include <linux/nospec.h>
+
#include <asm/switch_to.h>
#include <asm/tlb.h>
@@ -878,6 +881,33 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
}
#ifdef CONFIG_SMP
+
+static inline bool is_per_cpu_kthread(struct task_struct *p)
+{
+ if (!(p->flags & PF_KTHREAD))
+ return false;
+
+ if (p->nr_cpus_allowed != 1)
+ return false;
+
+ return true;
+}
+
+/*
+ * Per-CPU kthreads are allowed to run on !actie && online CPUs, see
+ * __set_cpus_allowed_ptr() and select_fallback_rq().
+ */
+static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
+{
+ if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+ return false;
+
+ if (is_per_cpu_kthread(p))
+ return cpu_online(cpu);
+
+ return cpu_active(cpu);
+}
+
/*
* This is how migration works:
*
@@ -935,16 +965,8 @@ struct migration_arg {
static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
struct task_struct *p, int dest_cpu)
{
- if (p->flags & PF_KTHREAD) {
- if (unlikely(!cpu_online(dest_cpu)))
- return rq;
- } else {
- if (unlikely(!cpu_active(dest_cpu)))
- return rq;
- }
-
/* Affinity changed (again). */
- if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
+ if (!is_cpu_allowed(p, dest_cpu))
return rq;
update_rq_clock(rq);
@@ -1473,10 +1495,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
for (;;) {
/* Any allowed, online CPU? */
for_each_cpu(dest_cpu, &p->cpus_allowed) {
- if (!(p->flags & PF_KTHREAD) && !cpu_active(dest_cpu))
+ if (!is_cpu_allowed(p, dest_cpu))
continue;
- if (!cpu_online(dest_cpu))
- continue;
+
goto out;
}
@@ -1539,8 +1560,7 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
* [ this allows ->select_task() to simply return task_cpu(p) and
* not worry about this generic constraint ]
*/
- if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed) ||
- !cpu_online(cpu)))
+ if (unlikely(!is_cpu_allowed(p, cpu)))
cpu = select_fallback_rq(task_cpu(p), p);
return cpu;
@@ -2174,27 +2194,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
INIT_HLIST_HEAD(&p->preempt_notifiers);
#endif
-#ifdef CONFIG_NUMA_BALANCING
- if (p->mm && atomic_read(&p->mm->mm_users) == 1) {
- p->mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
- p->mm->numa_scan_seq = 0;
- }
-
- if (clone_flags & CLONE_VM)
- p->numa_preferred_nid = current->numa_preferred_nid;
- else
- p->numa_preferred_nid = -1;
-
- p->node_stamp = 0ULL;
- p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
- p->numa_scan_period = sysctl_numa_balancing_scan_delay;
- p->numa_work.next = &p->numa_work;
- p->numa_faults = NULL;
- p->last_task_numa_placement = 0;
- p->last_sum_exec_runtime = 0;
-
- p->numa_group = NULL;
-#endif /* CONFIG_NUMA_BALANCING */
+ init_numa_balancing(clone_flags, p);
}
DEFINE_STATIC_KEY_FALSE(sched_numa_balancing);
@@ -2718,20 +2718,28 @@ static struct rq *finish_task_switch(struct task_struct *prev)
membarrier_mm_sync_core_before_usermode(mm);
mmdrop(mm);
}
- if (unlikely(prev_state == TASK_DEAD)) {
- if (prev->sched_class->task_dead)
- prev->sched_class->task_dead(prev);
+ if (unlikely(prev_state & (TASK_DEAD|TASK_PARKED))) {
+ switch (prev_state) {
+ case TASK_DEAD:
+ if (prev->sched_class->task_dead)
+ prev->sched_class->task_dead(prev);
- /*
- * Remove function-return probe instances associated with this
- * task and put them back on the free list.
- */
- kprobe_flush_task(prev);
+ /*
+ * Remove function-return probe instances associated with this
+ * task and put them back on the free list.
+ */
+ kprobe_flush_task(prev);
- /* Task is done with its stack. */
- put_task_stack(prev);
+ /* Task is done with its stack. */
+ put_task_stack(prev);
- put_task_struct(prev);
+ put_task_struct(prev);
+ break;
+
+ case TASK_PARKED:
+ kthread_park_complete(prev);
+ break;
+ }
}
tick_nohz_task_switch();
@@ -3498,23 +3506,8 @@ static void __sched notrace __schedule(bool preempt)
void __noreturn do_task_dead(void)
{
- /*
- * The setting of TASK_RUNNING by try_to_wake_up() may be delayed
- * when the following two conditions become true.
- * - There is race condition of mmap_sem (It is acquired by
- * exit_mm()), and
- * - SMI occurs before setting TASK_RUNINNG.
- * (or hypervisor of virtual machine switches to other guest)
- * As a result, we may become TASK_RUNNING after becoming TASK_DEAD
- *
- * To avoid it, we have to wait for releasing tsk->pi_lock which
- * is held by try_to_wake_up()
- */
- raw_spin_lock_irq(¤t->pi_lock);
- raw_spin_unlock_irq(¤t->pi_lock);
-
/* Causes final put_task_struct in finish_task_switch(): */
- __set_current_state(TASK_DEAD);
+ set_special_state(TASK_DEAD);
/* Tell freezer to ignore us: */
current->flags |= PF_NOFREEZE;
@@ -4037,6 +4030,23 @@ int idle_cpu(int cpu)
}
/**
+ * available_idle_cpu - is a given CPU idle for enqueuing work.
+ * @cpu: the CPU in question.
+ *
+ * Return: 1 if the CPU is currently idle. 0 otherwise.
+ */
+int available_idle_cpu(int cpu)
+{
+ if (!idle_cpu(cpu))
+ return 0;
+
+ if (vcpu_is_preempted(cpu))
+ return 0;
+
+ return 1;
+}
+
+/**
* idle_task - return the idle task for a given CPU.
* @cpu: the processor in question.
*
@@ -5012,20 +5022,6 @@ int __cond_resched_lock(spinlock_t *lock)
}
EXPORT_SYMBOL(__cond_resched_lock);
-int __sched __cond_resched_softirq(void)
-{
- BUG_ON(!in_softirq());
-
- if (should_resched(SOFTIRQ_DISABLE_OFFSET)) {
- local_bh_enable();
- preempt_schedule_common();
- local_bh_disable();
- return 1;
- }
- return 0;
-}
-EXPORT_SYMBOL(__cond_resched_softirq);
-
/**
* yield - yield the current processor to other threads.
*
@@ -6928,11 +6924,15 @@ static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css,
struct cftype *cft, s64 nice)
{
unsigned long weight;
+ int idx;
if (nice < MIN_NICE || nice > MAX_NICE)
return -ERANGE;
- weight = sched_prio_to_weight[NICE_TO_PRIO(nice) - MAX_RT_PRIO];
+ idx = NICE_TO_PRIO(nice) - MAX_RT_PRIO;
+ idx = array_index_nospec(idx, 40);
+ weight = sched_prio_to_weight[idx];
+
return sched_group_set_shares(css_tg(css), scale_load(weight));
}
#endif
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index d2c6083..3cde464 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -51,7 +51,7 @@ struct sugov_cpu {
bool iowait_boost_pending;
unsigned int iowait_boost;
unsigned int iowait_boost_max;
- u64 last_update;
+ u64 last_update;
/* The fields below are only needed when sharing a policy: */
unsigned long util_cfs;
@@ -89,46 +89,52 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
* schedule the kthread.
*/
if (sg_policy->policy->fast_switch_enabled &&
- !cpufreq_can_do_remote_dvfs(sg_policy->policy))
+ !cpufreq_this_cpu_can_update(sg_policy->policy))
return false;
- if (sg_policy->work_in_progress)
- return false;
-
- if (unlikely(sg_policy->need_freq_update)) {
- sg_policy->need_freq_update = false;
- /*
- * This happens when limits change, so forget the previous
- * next_freq value and force an update.
- */
- sg_policy->next_freq = UINT_MAX;
+ if (unlikely(sg_policy->need_freq_update))
return true;
- }
delta_ns = time - sg_policy->last_freq_update_time;
return delta_ns >= sg_policy->freq_update_delay_ns;
}
-static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
- unsigned int next_freq)
+static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
+ unsigned int next_freq)
{
- struct cpufreq_policy *policy = sg_policy->policy;
-
if (sg_policy->next_freq == next_freq)
- return;
+ return false;
sg_policy->next_freq = next_freq;
sg_policy->last_freq_update_time = time;
- if (policy->fast_switch_enabled) {
- next_freq = cpufreq_driver_fast_switch(policy, next_freq);
- if (!next_freq)
- return;
+ return true;
+}
- policy->cur = next_freq;
- trace_cpu_frequency(next_freq, smp_processor_id());
- } else {
+static void sugov_fast_switch(struct sugov_policy *sg_policy, u64 time,
+ unsigned int next_freq)
+{
+ struct cpufreq_policy *policy = sg_policy->policy;
+
+ if (!sugov_update_next_freq(sg_policy, time, next_freq))
+ return;
+
+ next_freq = cpufreq_driver_fast_switch(policy, next_freq);
+ if (!next_freq)
+ return;
+
+ policy->cur = next_freq;
+ trace_cpu_frequency(next_freq, smp_processor_id());
+}
+
+static void sugov_deferred_update(struct sugov_policy *sg_policy, u64 time,
+ unsigned int next_freq)
+{
+ if (!sugov_update_next_freq(sg_policy, time, next_freq))
+ return;
+
+ if (!sg_policy->work_in_progress) {
sg_policy->work_in_progress = true;
irq_work_queue(&sg_policy->irq_work);
}
@@ -165,8 +171,10 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
freq = (freq + (freq >> 2)) * util / max;
- if (freq == sg_policy->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
+ if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
return sg_policy->next_freq;
+
+ sg_policy->need_freq_update = false;
sg_policy->cached_raw_freq = freq;
return cpufreq_driver_resolve_freq(policy, freq);
}
@@ -183,61 +191,137 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu)
static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
{
struct rq *rq = cpu_rq(sg_cpu->cpu);
- unsigned long util;
- if (rq->rt.rt_nr_running) {
- util = sg_cpu->max;
- } else {
- util = sg_cpu->util_dl;
- if (rq->cfs.h_nr_running)
- util += sg_cpu->util_cfs;
- }
+ if (rq->rt.rt_nr_running)
+ return sg_cpu->max;
/*
+ * Utilization required by DEADLINE must always be granted while, for
+ * FAIR, we use blocked utilization of IDLE CPUs as a mechanism to
+ * gracefully reduce the frequency when no tasks show up for longer
+ * periods of time.
+ *
* Ideally we would like to set util_dl as min/guaranteed freq and
* util_cfs + util_dl as requested freq. However, cpufreq is not yet
* ready for such an interface. So, we only do the latter for now.
*/
- return min(util, sg_cpu->max);
+ return min(sg_cpu->max, (sg_cpu->util_dl + sg_cpu->util_cfs));
}
-static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time, unsigned int flags)
+/**
+ * sugov_iowait_reset() - Reset the IO boost status of a CPU.
+ * @sg_cpu: the sugov data for the CPU to boost
+ * @time: the update time from the caller
+ * @set_iowait_boost: true if an IO boost has been requested
+ *
+ * The IO wait boost of a task is disabled after a tick since the last update
+ * of a CPU. If a new IO wait boost is requested after more then a tick, then
+ * we enable the boost starting from the minimum frequency, which improves
+ * energy efficiency by ignoring sporadic wakeups from IO.
+ */
+static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time,
+ bool set_iowait_boost)
{
- if (flags & SCHED_CPUFREQ_IOWAIT) {
- if (sg_cpu->iowait_boost_pending)
- return;
+ s64 delta_ns = time - sg_cpu->last_update;
- sg_cpu->iowait_boost_pending = true;
+ /* Reset boost only if a tick has elapsed since last request */
+ if (delta_ns <= TICK_NSEC)
+ return false;
- if (sg_cpu->iowait_boost) {
- sg_cpu->iowait_boost <<= 1;
- if (sg_cpu->iowait_boost > sg_cpu->iowait_boost_max)
- sg_cpu->iowait_boost = sg_cpu->iowait_boost_max;
- } else {
- sg_cpu->iowait_boost = sg_cpu->sg_policy->policy->min;
- }
- } else if (sg_cpu->iowait_boost) {
- s64 delta_ns = time - sg_cpu->last_update;
+ sg_cpu->iowait_boost = set_iowait_boost
+ ? sg_cpu->sg_policy->policy->min : 0;
+ sg_cpu->iowait_boost_pending = set_iowait_boost;
- /* Clear iowait_boost if the CPU apprears to have been idle. */
- if (delta_ns > TICK_NSEC) {
- sg_cpu->iowait_boost = 0;
- sg_cpu->iowait_boost_pending = false;
- }
- }
+ return true;
}
-static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
- unsigned long *max)
+/**
+ * sugov_iowait_boost() - Updates the IO boost status of a CPU.
+ * @sg_cpu: the sugov data for the CPU to boost
+ * @time: the update time from the caller
+ * @flags: SCHED_CPUFREQ_IOWAIT if the task is waking up after an IO wait
+ *
+ * Each time a task wakes up after an IO operation, the CPU utilization can be
+ * boosted to a certain utilization which doubles at each "frequent and
+ * successive" wakeup from IO, ranging from the utilization of the minimum
+ * OPP to the utilization of the maximum OPP.
+ * To keep doubling, an IO boost has to be requested at least once per tick,
+ * otherwise we restart from the utilization of the minimum OPP.
+ */
+static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
+ unsigned int flags)
+{
+ bool set_iowait_boost = flags & SCHED_CPUFREQ_IOWAIT;
+
+ /* Reset boost if the CPU appears to have been idle enough */
+ if (sg_cpu->iowait_boost &&
+ sugov_iowait_reset(sg_cpu, time, set_iowait_boost))
+ return;
+
+ /* Boost only tasks waking up after IO */
+ if (!set_iowait_boost)
+ return;
+
+ /* Ensure boost doubles only one time at each request */
+ if (sg_cpu->iowait_boost_pending)
+ return;
+ sg_cpu->iowait_boost_pending = true;
+
+ /* Double the boost at each request */
+ if (sg_cpu->iowait_boost) {
+ sg_cpu->iowait_boost <<= 1;
+ if (sg_cpu->iowait_boost > sg_cpu->iowait_boost_max)
+ sg_cpu->iowait_boost = sg_cpu->iowait_boost_max;
+ return;
+ }
+
+ /* First wakeup after IO: start with minimum boost */
+ sg_cpu->iowait_boost = sg_cpu->sg_policy->policy->min;
+}
+
+/**
+ * sugov_iowait_apply() - Apply the IO boost to a CPU.
+ * @sg_cpu: the sugov data for the cpu to boost
+ * @time: the update time from the caller
+ * @util: the utilization to (eventually) boost
+ * @max: the maximum value the utilization can be boosted to
+ *
+ * A CPU running a task which woken up after an IO operation can have its
+ * utilization boosted to speed up the completion of those IO operations.
+ * The IO boost value is increased each time a task wakes up from IO, in
+ * sugov_iowait_apply(), and it's instead decreased by this function,
+ * each time an increase has not been requested (!iowait_boost_pending).
+ *
+ * A CPU which also appears to have been idle for at least one tick has also
+ * its IO boost utilization reset.
+ *
+ * This mechanism is designed to boost high frequently IO waiting tasks, while
+ * being more conservative on tasks which does sporadic IO operations.
+ */
+static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
+ unsigned long *util, unsigned long *max)
{
unsigned int boost_util, boost_max;
+ /* No boost currently required */
if (!sg_cpu->iowait_boost)
return;
+ /* Reset boost if the CPU appears to have been idle enough */
+ if (sugov_iowait_reset(sg_cpu, time, false))
+ return;
+
+ /*
+ * An IO waiting task has just woken up:
+ * allow to further double the boost value
+ */
if (sg_cpu->iowait_boost_pending) {
sg_cpu->iowait_boost_pending = false;
} else {
+ /*
+ * Otherwise: reduce the boost value and disable it when we
+ * reach the minimum.
+ */
sg_cpu->iowait_boost >>= 1;
if (sg_cpu->iowait_boost < sg_cpu->sg_policy->policy->min) {
sg_cpu->iowait_boost = 0;
@@ -245,9 +329,12 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
}
}
+ /*
+ * Apply the current boost value: a CPU is boosted only if its current
+ * utilization is smaller then the current IO boost level.
+ */
boost_util = sg_cpu->iowait_boost;
boost_max = sg_cpu->iowait_boost_max;
-
if (*util * boost_max < *max * boost_util) {
*util = boost_util;
*max = boost_max;
@@ -286,7 +373,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
unsigned int next_f;
bool busy;
- sugov_set_iowait_boost(sg_cpu, time, flags);
+ sugov_iowait_boost(sg_cpu, time, flags);
sg_cpu->last_update = time;
ignore_dl_rate_limit(sg_cpu, sg_policy);
@@ -299,7 +386,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
sugov_get_util(sg_cpu);
max = sg_cpu->max;
util = sugov_aggregate_util(sg_cpu);
- sugov_iowait_boost(sg_cpu, &util, &max);
+ sugov_iowait_apply(sg_cpu, time, &util, &max);
next_f = get_next_freq(sg_policy, util, max);
/*
* Do not reduce the frequency if the CPU has not been idle
@@ -312,7 +399,18 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
sg_policy->cached_raw_freq = 0;
}
- sugov_update_commit(sg_policy, time, next_f);
+ /*
+ * This code runs under rq->lock for the target CPU, so it won't run
+ * concurrently on two different CPUs for the same target and it is not
+ * necessary to acquire the lock in the fast switch case.
+ */
+ if (sg_policy->policy->fast_switch_enabled) {
+ sugov_fast_switch(sg_policy, time, next_f);
+ } else {
+ raw_spin_lock(&sg_policy->update_lock);
+ sugov_deferred_update(sg_policy, time, next_f);
+ raw_spin_unlock(&sg_policy->update_lock);
+ }
}
static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
@@ -325,28 +423,12 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
for_each_cpu(j, policy->cpus) {
struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
unsigned long j_util, j_max;
- s64 delta_ns;
sugov_get_util(j_sg_cpu);
-
- /*
- * If the CFS CPU utilization was last updated before the
- * previous frequency update and the time elapsed between the
- * last update of the CPU utilization and the last frequency
- * update is long enough, reset iowait_boost and util_cfs, as
- * they are now probably stale. However, still consider the
- * CPU contribution if it has some DEADLINE utilization
- * (util_dl).
- */
- delta_ns = time - j_sg_cpu->last_update;
- if (delta_ns > TICK_NSEC) {
- j_sg_cpu->iowait_boost = 0;
- j_sg_cpu->iowait_boost_pending = false;
- }
-
j_max = j_sg_cpu->max;
j_util = sugov_aggregate_util(j_sg_cpu);
- sugov_iowait_boost(j_sg_cpu, &j_util, &j_max);
+ sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max);
+
if (j_util * max > j_max * util) {
util = j_util;
max = j_max;
@@ -365,14 +447,18 @@ sugov_update_shared(struct update_util_data *hook, u64 time, unsigned int flags)
raw_spin_lock(&sg_policy->update_lock);
- sugov_set_iowait_boost(sg_cpu, time, flags);
+ sugov_iowait_boost(sg_cpu, time, flags);
sg_cpu->last_update = time;
ignore_dl_rate_limit(sg_cpu, sg_policy);
if (sugov_should_update_freq(sg_policy, time)) {
next_f = sugov_next_freq_shared(sg_cpu, time);
- sugov_update_commit(sg_policy, time, next_f);
+
+ if (sg_policy->policy->fast_switch_enabled)
+ sugov_fast_switch(sg_policy, time, next_f);
+ else
+ sugov_deferred_update(sg_policy, time, next_f);
}
raw_spin_unlock(&sg_policy->update_lock);
@@ -381,13 +467,27 @@ sugov_update_shared(struct update_util_data *hook, u64 time, unsigned int flags)
static void sugov_work(struct kthread_work *work)
{
struct sugov_policy *sg_policy = container_of(work, struct sugov_policy, work);
+ unsigned int freq;
+ unsigned long flags;
+
+ /*
+ * Hold sg_policy->update_lock shortly to handle the case where:
+ * incase sg_policy->next_freq is read here, and then updated by
+ * sugov_deferred_update() just before work_in_progress is set to false
+ * here, we may miss queueing the new update.
+ *
+ * Note: If a work was queued after the update_lock is released,
+ * sugov_work() will just be called again by kthread_work code; and the
+ * request will be proceed before the sugov thread sleeps.
+ */
+ raw_spin_lock_irqsave(&sg_policy->update_lock, flags);
+ freq = sg_policy->next_freq;
+ sg_policy->work_in_progress = false;
+ raw_spin_unlock_irqrestore(&sg_policy->update_lock, flags);
mutex_lock(&sg_policy->work_lock);
- __cpufreq_driver_target(sg_policy->policy, sg_policy->next_freq,
- CPUFREQ_RELATION_L);
+ __cpufreq_driver_target(sg_policy->policy, freq, CPUFREQ_RELATION_L);
mutex_unlock(&sg_policy->work_lock);
-
- sg_policy->work_in_progress = false;
}
static void sugov_irq_work(struct irq_work *irq_work)
@@ -396,19 +496,6 @@ static void sugov_irq_work(struct irq_work *irq_work)
sg_policy = container_of(irq_work, struct sugov_policy, irq_work);
- /*
- * For RT tasks, the schedutil governor shoots the frequency to maximum.
- * Special care must be taken to ensure that this kthread doesn't result
- * in the same behavior.
- *
- * This is (mostly) guaranteed by the work_in_progress flag. The flag is
- * updated only at the end of the sugov_work() function and before that
- * the schedutil governor rejects all other frequency scaling requests.
- *
- * There is a very rare case though, where the RT thread yields right
- * after the work_in_progress flag is cleared. The effects of that are
- * neglected for now.
- */
kthread_queue_work(&sg_policy->worker, &sg_policy->work);
}
@@ -523,11 +610,7 @@ static int sugov_kthread_create(struct sugov_policy *sg_policy)
}
sg_policy->thread = thread;
-
- /* Kthread is bound to all CPUs by default */
- if (!policy->dvfs_possible_from_any_cpu)
- kthread_bind_mask(thread, policy->related_cpus);
-
+ kthread_bind_mask(thread, policy->related_cpus);
init_irq_work(&sg_policy->irq_work, sugov_irq_work);
mutex_init(&sg_policy->work_lock);
@@ -670,7 +753,7 @@ static int sugov_start(struct cpufreq_policy *policy)
sg_policy->freq_update_delay_ns = sg_policy->tunables->rate_limit_us * NSEC_PER_USEC;
sg_policy->last_freq_update_time = 0;
- sg_policy->next_freq = UINT_MAX;
+ sg_policy->next_freq = 0;
sg_policy->work_in_progress = false;
sg_policy->need_freq_update = false;
sg_policy->cached_raw_freq = 0;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index e7b3008..fbfc3f1 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1117,7 +1117,7 @@ extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
* should be larger than 2^(64 - 20 - 8), which is more than 64 seconds.
* So, overflow is not an issue here.
*/
-u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
+static u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
{
u64 u_inact = rq->dl.this_bw - rq->dl.running_bw; /* Utot - Uact */
u64 u_act;
@@ -1259,6 +1259,9 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
rq = task_rq_lock(p, &rf);
+ sched_clock_tick();
+ update_rq_clock(rq);
+
if (!dl_task(p) || p->state == TASK_DEAD) {
struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
@@ -1278,9 +1281,6 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
if (dl_se->dl_non_contending == 0)
goto unlock;
- sched_clock_tick();
- update_rq_clock(rq);
-
sub_running_bw(dl_se, &rq->dl);
dl_se->dl_non_contending = 0;
unlock:
@@ -2731,8 +2731,6 @@ bool dl_cpu_busy(unsigned int cpu)
#endif
#ifdef CONFIG_SCHED_DEBUG
-extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
-
void print_dl_stats(struct seq_file *m, int cpu)
{
print_dl_rq(m, cpu, &cpu_rq(cpu)->dl);
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 15b10e2..e593b41 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -823,35 +823,9 @@ static const struct seq_operations sched_debug_sops = {
.show = sched_debug_show,
};
-static int sched_debug_release(struct inode *inode, struct file *file)
-{
- seq_release(inode, file);
-
- return 0;
-}
-
-static int sched_debug_open(struct inode *inode, struct file *filp)
-{
- int ret = 0;
-
- ret = seq_open(filp, &sched_debug_sops);
-
- return ret;
-}
-
-static const struct file_operations sched_debug_fops = {
- .open = sched_debug_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = sched_debug_release,
-};
-
static int __init init_sched_debug_procfs(void)
{
- struct proc_dir_entry *pe;
-
- pe = proc_create("sched_debug", 0444, NULL, &sched_debug_fops);
- if (!pe)
+ if (!proc_create_seq("sched_debug", 0444, NULL, &sched_debug_sops))
return -ENOMEM;
return 0;
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 54dc31e..e497c05 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1139,6 +1139,47 @@ static unsigned int task_scan_max(struct task_struct *p)
return max(smin, smax);
}
+void init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
+{
+ int mm_users = 0;
+ struct mm_struct *mm = p->mm;
+
+ if (mm) {
+ mm_users = atomic_read(&mm->mm_users);
+ if (mm_users == 1) {
+ mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
+ mm->numa_scan_seq = 0;
+ }
+ }
+ p->node_stamp = 0;
+ p->numa_scan_seq = mm ? mm->numa_scan_seq : 0;
+ p->numa_scan_period = sysctl_numa_balancing_scan_delay;
+ p->numa_work.next = &p->numa_work;
+ p->numa_faults = NULL;
+ p->numa_group = NULL;
+ p->last_task_numa_placement = 0;
+ p->last_sum_exec_runtime = 0;
+
+ /* New address space, reset the preferred nid */
+ if (!(clone_flags & CLONE_VM)) {
+ p->numa_preferred_nid = -1;
+ return;
+ }
+
+ /*
+ * New thread, keep existing numa_preferred_nid which should be copied
+ * already by arch_dup_task_struct but stagger when scans start.
+ */
+ if (mm) {
+ unsigned int delay;
+
+ delay = min_t(unsigned int, task_scan_max(current),
+ current->numa_scan_period * mm_users * NSEC_PER_MSEC);
+ delay += 2 * TICK_NSEC;
+ p->node_stamp = delay;
+ }
+}
+
static void account_numa_enqueue(struct rq *rq, struct task_struct *p)
{
rq->nr_numa_running += (p->numa_preferred_nid != -1);
@@ -1854,7 +1895,6 @@ static int task_numa_migrate(struct task_struct *p)
static void numa_migrate_preferred(struct task_struct *p)
{
unsigned long interval = HZ;
- unsigned long numa_migrate_retry;
/* This task has no NUMA fault statistics yet */
if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults))
@@ -1862,18 +1902,7 @@ static void numa_migrate_preferred(struct task_struct *p)
/* Periodically retry migrating the task to the preferred node */
interval = min(interval, msecs_to_jiffies(p->numa_scan_period) / 16);
- numa_migrate_retry = jiffies + interval;
-
- /*
- * Check that the new retry threshold is after the current one. If
- * the retry is in the future, it implies that wake_affine has
- * temporarily asked NUMA balancing to backoff from placement.
- */
- if (numa_migrate_retry > p->numa_migrate_retry)
- return;
-
- /* Safe to try placing the task on the preferred node */
- p->numa_migrate_retry = numa_migrate_retry;
+ p->numa_migrate_retry = jiffies + interval;
/* Success if task is already running on preferred CPU */
if (task_node(p) == p->numa_preferred_nid)
@@ -5357,6 +5386,14 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
struct sched_entity *se = &p->se;
/*
+ * The code below (indirectly) updates schedutil which looks at
+ * the cfs_rq utilization to select a frequency.
+ * Let's add the task's estimated utilization to the cfs_rq's
+ * estimated utilization, before we update schedutil.
+ */
+ util_est_enqueue(&rq->cfs, p);
+
+ /*
* If in_iowait is set, the code below may not trigger any cpufreq
* utilization updates, so do it here explicitly with the IOWAIT flag
* passed.
@@ -5397,7 +5434,6 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
if (!se)
add_nr_running(rq, 1);
- util_est_enqueue(&rq->cfs, p);
hrtick_update(rq);
}
@@ -5870,8 +5906,8 @@ wake_affine_idle(int this_cpu, int prev_cpu, int sync)
* a cpufreq perspective, it's better to have higher utilisation
* on one CPU.
*/
- if (idle_cpu(this_cpu) && cpus_share_cache(this_cpu, prev_cpu))
- return idle_cpu(prev_cpu) ? prev_cpu : this_cpu;
+ if (available_idle_cpu(this_cpu) && cpus_share_cache(this_cpu, prev_cpu))
+ return available_idle_cpu(prev_cpu) ? prev_cpu : this_cpu;
if (sync && cpu_rq(this_cpu)->nr_running == 1)
return this_cpu;
@@ -5922,48 +5958,6 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p,
return this_eff_load < prev_eff_load ? this_cpu : nr_cpumask_bits;
}
-#ifdef CONFIG_NUMA_BALANCING
-static void
-update_wa_numa_placement(struct task_struct *p, int prev_cpu, int target)
-{
- unsigned long interval;
-
- if (!static_branch_likely(&sched_numa_balancing))
- return;
-
- /* If balancing has no preference then continue gathering data */
- if (p->numa_preferred_nid == -1)
- return;
-
- /*
- * If the wakeup is not affecting locality then it is neutral from
- * the perspective of NUMA balacing so continue gathering data.
- */
- if (cpu_to_node(prev_cpu) == cpu_to_node(target))
- return;
-
- /*
- * Temporarily prevent NUMA balancing trying to place waker/wakee after
- * wakee has been moved by wake_affine. This will potentially allow
- * related tasks to converge and update their data placement. The
- * 4 * numa_scan_period is to allow the two-pass filter to migrate
- * hot data to the wakers node.
- */
- interval = max(sysctl_numa_balancing_scan_delay,
- p->numa_scan_period << 2);
- p->numa_migrate_retry = jiffies + msecs_to_jiffies(interval);
-
- interval = max(sysctl_numa_balancing_scan_delay,
- current->numa_scan_period << 2);
- current->numa_migrate_retry = jiffies + msecs_to_jiffies(interval);
-}
-#else
-static void
-update_wa_numa_placement(struct task_struct *p, int prev_cpu, int target)
-{
-}
-#endif
-
static int wake_affine(struct sched_domain *sd, struct task_struct *p,
int this_cpu, int prev_cpu, int sync)
{
@@ -5979,7 +5973,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
if (target == nr_cpumask_bits)
return prev_cpu;
- update_wa_numa_placement(p, prev_cpu, target);
schedstat_inc(sd->ttwu_move_affine);
schedstat_inc(p->se.statistics.nr_wakeups_affine);
return target;
@@ -6157,7 +6150,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
/* Traverse only the allowed CPUs */
for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) {
- if (idle_cpu(i)) {
+ if (available_idle_cpu(i)) {
struct rq *rq = cpu_rq(i);
struct cpuidle_state *idle = idle_get_state(rq);
if (idle && idle->exit_latency < min_exit_latency) {
@@ -6199,6 +6192,13 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
if (!cpumask_intersects(sched_domain_span(sd), &p->cpus_allowed))
return prev_cpu;
+ /*
+ * We need task's util for capacity_spare_wake, sync it up to prev_cpu's
+ * last_update_time.
+ */
+ if (!(sd_flag & SD_BALANCE_FORK))
+ sync_entity_load_avg(&p->se);
+
while (sd) {
struct sched_group *group;
struct sched_domain *tmp;
@@ -6279,7 +6279,7 @@ void __update_idle_core(struct rq *rq)
if (cpu == core)
continue;
- if (!idle_cpu(cpu))
+ if (!available_idle_cpu(cpu))
goto unlock;
}
@@ -6311,7 +6311,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
for_each_cpu(cpu, cpu_smt_mask(core)) {
cpumask_clear_cpu(cpu, cpus);
- if (!idle_cpu(cpu))
+ if (!available_idle_cpu(cpu))
idle = false;
}
@@ -6340,7 +6340,7 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t
for_each_cpu(cpu, cpu_smt_mask(target)) {
if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
continue;
- if (idle_cpu(cpu))
+ if (available_idle_cpu(cpu))
return cpu;
}
@@ -6403,7 +6403,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
return -1;
if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
continue;
- if (idle_cpu(cpu))
+ if (available_idle_cpu(cpu))
break;
}
@@ -6423,13 +6423,13 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
struct sched_domain *sd;
int i, recent_used_cpu;
- if (idle_cpu(target))
+ if (available_idle_cpu(target))
return target;
/*
* If the previous CPU is cache affine and idle, don't be stupid:
*/
- if (prev != target && cpus_share_cache(prev, target) && idle_cpu(prev))
+ if (prev != target && cpus_share_cache(prev, target) && available_idle_cpu(prev))
return prev;
/* Check a recently used CPU as a potential idle candidate: */
@@ -6437,7 +6437,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
if (recent_used_cpu != prev &&
recent_used_cpu != target &&
cpus_share_cache(recent_used_cpu, target) &&
- idle_cpu(recent_used_cpu) &&
+ available_idle_cpu(recent_used_cpu) &&
cpumask_test_cpu(p->recent_used_cpu, &p->cpus_allowed)) {
/*
* Replace recent_used_cpu with prev as it is a potential
@@ -6613,7 +6613,7 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
static int
select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags)
{
- struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
+ struct sched_domain *tmp, *sd = NULL;
int cpu = smp_processor_id();
int new_cpu = prev_cpu;
int want_affine = 0;
@@ -6636,7 +6636,10 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
*/
if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
- affine_sd = tmp;
+ if (cpu != prev_cpu)
+ new_cpu = wake_affine(tmp, p, cpu, prev_cpu, sync);
+
+ sd = NULL; /* Prefer wake_affine over balance flags */
break;
}
@@ -6646,33 +6649,16 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
break;
}
- if (affine_sd) {
- sd = NULL; /* Prefer wake_affine over balance flags */
- if (cpu == prev_cpu)
- goto pick_cpu;
-
- new_cpu = wake_affine(affine_sd, p, cpu, prev_cpu, sync);
- }
-
- if (sd && !(sd_flag & SD_BALANCE_FORK)) {
- /*
- * We're going to need the task's util for capacity_spare_wake
- * in find_idlest_group. Sync it up to prev_cpu's
- * last_update_time.
- */
- sync_entity_load_avg(&p->se);
- }
-
- if (!sd) {
-pick_cpu:
- if (sd_flag & SD_BALANCE_WAKE) { /* XXX always ? */
- new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
-
- if (want_affine)
- current->recent_used_cpu = cpu;
- }
- } else {
+ if (unlikely(sd)) {
+ /* Slow path */
new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag);
+ } else if (sd_flag & SD_BALANCE_WAKE) { /* XXX always ? */
+ /* Fast path */
+
+ new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
+
+ if (want_affine)
+ current->recent_used_cpu = cpu;
}
rcu_read_unlock();
@@ -9847,6 +9833,7 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf)
if (curr_cost > this_rq->max_idle_balance_cost)
this_rq->max_idle_balance_cost = curr_cost;
+out:
/*
* While browsing the domains, we released the rq lock, a task could
* have been enqueued in the meantime. Since we're not going idle,
@@ -9855,7 +9842,6 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf)
if (this_rq->cfs.h_nr_running && !pulled_task)
pulled_task = 1;
-out:
/* Move the next balance forward */
if (time_after(this_rq->next_balance, next_balance))
this_rq->next_balance = next_balance;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 7aef6b4..ef3c4e6 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2701,8 +2701,6 @@ int sched_rr_handler(struct ctl_table *table, int write,
}
#ifdef CONFIG_SCHED_DEBUG
-extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
-
void print_rt_stats(struct seq_file *m, int cpu)
{
rt_rq_iter_t iter;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 15750c2..6601baf 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -983,7 +983,7 @@ static inline void rq_clock_skip_update(struct rq *rq)
}
/*
- * See rt task throttoling, which is the only time a skip
+ * See rt task throttling, which is the only time a skip
* request is cancelled.
*/
static inline void rq_clock_cancel_skipupdate(struct rq *rq)
@@ -1069,6 +1069,12 @@ enum numa_faults_stats {
extern void sched_setnuma(struct task_struct *p, int node);
extern int migrate_task_to(struct task_struct *p, int cpu);
extern int migrate_swap(struct task_struct *, struct task_struct *);
+extern void init_numa_balancing(unsigned long clone_flags, struct task_struct *p);
+#else
+static inline void
+init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
+{
+}
#endif /* CONFIG_NUMA_BALANCING */
#ifdef CONFIG_SMP
@@ -2025,8 +2031,9 @@ extern bool sched_debug_enabled;
extern void print_cfs_stats(struct seq_file *m, int cpu);
extern void print_rt_stats(struct seq_file *m, int cpu);
extern void print_dl_stats(struct seq_file *m, int cpu);
-extern void
-print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
+extern void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
+extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
+extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
#ifdef CONFIG_NUMA_BALANCING
extern void
show_numa_stats(struct task_struct *p, struct seq_file *m);
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index ab112cb..750fb3c 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -120,22 +120,9 @@ static const struct seq_operations schedstat_sops = {
.show = show_schedstat,
};
-static int schedstat_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &schedstat_sops);
-}
-
-static const struct file_operations proc_schedstat_operations = {
- .open = schedstat_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static int __init proc_schedstat_init(void)
{
- proc_create("schedstat", 0, NULL, &proc_schedstat_operations);
-
+ proc_create_seq("schedstat", 0, NULL, &schedstat_sops);
return 0;
}
subsys_initcall(proc_schedstat_init);
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 64cc564..61a1125 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1708,7 +1708,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
rcu_read_unlock();
if (rq && sched_debug_enabled) {
- pr_info("span: %*pbl (max cpu_capacity = %lu)\n",
+ pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",
cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
}
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index dc77548..e691d9a 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -19,6 +19,8 @@
#include <linux/compat.h>
#include <linux/coredump.h>
#include <linux/kmemleak.h>
+#include <linux/nospec.h>
+#include <linux/prctl.h>
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
#include <linux/seccomp.h>
@@ -227,8 +229,11 @@ static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode)
return true;
}
+void __weak arch_seccomp_spec_mitigate(struct task_struct *task) { }
+
static inline void seccomp_assign_mode(struct task_struct *task,
- unsigned long seccomp_mode)
+ unsigned long seccomp_mode,
+ unsigned long flags)
{
assert_spin_locked(&task->sighand->siglock);
@@ -238,6 +243,9 @@ static inline void seccomp_assign_mode(struct task_struct *task,
* filter) is set.
*/
smp_mb__before_atomic();
+ /* Assume default seccomp processes want spec flaw mitigation. */
+ if ((flags & SECCOMP_FILTER_FLAG_SPEC_ALLOW) == 0)
+ arch_seccomp_spec_mitigate(task);
set_tsk_thread_flag(task, TIF_SECCOMP);
}
@@ -305,7 +313,7 @@ static inline pid_t seccomp_can_sync_threads(void)
* without dropping the locks.
*
*/
-static inline void seccomp_sync_threads(void)
+static inline void seccomp_sync_threads(unsigned long flags)
{
struct task_struct *thread, *caller;
@@ -346,7 +354,8 @@ static inline void seccomp_sync_threads(void)
* allow one thread to transition the other.
*/
if (thread->seccomp.mode == SECCOMP_MODE_DISABLED)
- seccomp_assign_mode(thread, SECCOMP_MODE_FILTER);
+ seccomp_assign_mode(thread, SECCOMP_MODE_FILTER,
+ flags);
}
}
@@ -469,7 +478,7 @@ static long seccomp_attach_filter(unsigned int flags,
/* Now that the new filter is in place, synchronize to all threads. */
if (flags & SECCOMP_FILTER_FLAG_TSYNC)
- seccomp_sync_threads();
+ seccomp_sync_threads(flags);
return 0;
}
@@ -818,7 +827,7 @@ static long seccomp_set_mode_strict(void)
#ifdef TIF_NOTSC
disable_TSC();
#endif
- seccomp_assign_mode(current, seccomp_mode);
+ seccomp_assign_mode(current, seccomp_mode, 0);
ret = 0;
out:
@@ -876,7 +885,7 @@ static long seccomp_set_mode_filter(unsigned int flags,
/* Do not free the successfully attached filter. */
prepared = NULL;
- seccomp_assign_mode(current, seccomp_mode);
+ seccomp_assign_mode(current, seccomp_mode, flags);
out:
spin_unlock_irq(¤t->sighand->siglock);
if (flags & SECCOMP_FILTER_FLAG_TSYNC)
diff --git a/kernel/signal.c b/kernel/signal.c
index d4ccea5..0f865d6 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1539,7 +1539,6 @@ int send_sig_fault(int sig, int code, void __user *addr
return send_sig_info(info.si_signo, &info, t);
}
-#if defined(BUS_MCEERR_AO) && defined(BUS_MCEERR_AR)
int force_sig_mceerr(int code, void __user *addr, short lsb, struct task_struct *t)
{
struct siginfo info;
@@ -1568,9 +1567,7 @@ int send_sig_mceerr(int code, void __user *addr, short lsb, struct task_struct *
return send_sig_info(info.si_signo, &info, t);
}
EXPORT_SYMBOL(send_sig_mceerr);
-#endif
-#ifdef SEGV_BNDERR
int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper)
{
struct siginfo info;
@@ -1584,7 +1581,6 @@ int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper)
info.si_upper = upper;
return force_sig_info(info.si_signo, &info, current);
}
-#endif
#ifdef SEGV_PKUERR
int force_sig_pkuerr(void __user *addr, u32 pkey)
@@ -1961,14 +1957,27 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
return;
}
+ set_special_state(TASK_TRACED);
+
/*
* We're committing to trapping. TRACED should be visible before
* TRAPPING is cleared; otherwise, the tracer might fail do_wait().
* Also, transition to TRACED and updates to ->jobctl should be
* atomic with respect to siglock and should be done after the arch
* hook as siglock is released and regrabbed across it.
+ *
+ * TRACER TRACEE
+ *
+ * ptrace_attach()
+ * [L] wait_on_bit(JOBCTL_TRAPPING) [S] set_special_state(TRACED)
+ * do_wait()
+ * set_current_state() smp_wmb();
+ * ptrace_do_wait()
+ * wait_task_stopped()
+ * task_stopped_code()
+ * [L] task_is_traced() [S] task_clear_jobctl_trapping();
*/
- set_current_state(TASK_TRACED);
+ smp_wmb();
current->last_siginfo = info;
current->exit_code = exit_code;
@@ -2176,7 +2185,7 @@ static bool do_signal_stop(int signr)
if (task_participate_group_stop(current))
notify = CLD_STOPPED;
- __set_current_state(TASK_STOPPED);
+ set_special_state(TASK_STOPPED);
spin_unlock_irq(¤t->sighand->siglock);
/*
@@ -2824,8 +2833,19 @@ enum siginfo_layout siginfo_layout(int sig, int si_code)
[SIGPOLL] = { NSIGPOLL, SIL_POLL },
[SIGSYS] = { NSIGSYS, SIL_SYS },
};
- if ((sig < ARRAY_SIZE(filter)) && (si_code <= filter[sig].limit))
+ if ((sig < ARRAY_SIZE(filter)) && (si_code <= filter[sig].limit)) {
layout = filter[sig].layout;
+ /* Handle the exceptions */
+ if ((sig == SIGBUS) &&
+ (si_code >= BUS_MCEERR_AR) && (si_code <= BUS_MCEERR_AO))
+ layout = SIL_FAULT_MCEERR;
+ else if ((sig == SIGSEGV) && (si_code == SEGV_BNDERR))
+ layout = SIL_FAULT_BNDERR;
+#ifdef SEGV_PKUERR
+ else if ((sig == SIGSEGV) && (si_code == SEGV_PKUERR))
+ layout = SIL_FAULT_PKUERR;
+#endif
+ }
else if (si_code <= NSIGPOLL)
layout = SIL_POLL;
} else {
@@ -2835,104 +2855,15 @@ enum siginfo_layout siginfo_layout(int sig, int si_code)
layout = SIL_POLL;
else if (si_code < 0)
layout = SIL_RT;
- /* Tests to support buggy kernel ABIs */
-#ifdef TRAP_FIXME
- if ((sig == SIGTRAP) && (si_code == TRAP_FIXME))
- layout = SIL_FAULT;
-#endif
-#ifdef FPE_FIXME
- if ((sig == SIGFPE) && (si_code == FPE_FIXME))
- layout = SIL_FAULT;
-#endif
}
return layout;
}
int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from)
{
- int err;
-
- if (!access_ok (VERIFY_WRITE, to, sizeof(siginfo_t)))
+ if (copy_to_user(to, from , sizeof(struct siginfo)))
return -EFAULT;
- if (from->si_code < 0)
- return __copy_to_user(to, from, sizeof(siginfo_t))
- ? -EFAULT : 0;
- /*
- * If you change siginfo_t structure, please be sure
- * this code is fixed accordingly.
- * Please remember to update the signalfd_copyinfo() function
- * inside fs/signalfd.c too, in case siginfo_t changes.
- * It should never copy any pad contained in the structure
- * to avoid security leaks, but must copy the generic
- * 3 ints plus the relevant union member.
- */
- err = __put_user(from->si_signo, &to->si_signo);
- err |= __put_user(from->si_errno, &to->si_errno);
- err |= __put_user(from->si_code, &to->si_code);
- switch (siginfo_layout(from->si_signo, from->si_code)) {
- case SIL_KILL:
- err |= __put_user(from->si_pid, &to->si_pid);
- err |= __put_user(from->si_uid, &to->si_uid);
- break;
- case SIL_TIMER:
- /* Unreached SI_TIMER is negative */
- break;
- case SIL_POLL:
- err |= __put_user(from->si_band, &to->si_band);
- err |= __put_user(from->si_fd, &to->si_fd);
- break;
- case SIL_FAULT:
- err |= __put_user(from->si_addr, &to->si_addr);
-#ifdef __ARCH_SI_TRAPNO
- err |= __put_user(from->si_trapno, &to->si_trapno);
-#endif
-#ifdef __ia64__
- err |= __put_user(from->si_imm, &to->si_imm);
- err |= __put_user(from->si_flags, &to->si_flags);
- err |= __put_user(from->si_isr, &to->si_isr);
-#endif
- /*
- * Other callers might not initialize the si_lsb field,
- * so check explicitly for the right codes here.
- */
-#ifdef BUS_MCEERR_AR
- if (from->si_signo == SIGBUS && from->si_code == BUS_MCEERR_AR)
- err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
-#endif
-#ifdef BUS_MCEERR_AO
- if (from->si_signo == SIGBUS && from->si_code == BUS_MCEERR_AO)
- err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
-#endif
-#ifdef SEGV_BNDERR
- if (from->si_signo == SIGSEGV && from->si_code == SEGV_BNDERR) {
- err |= __put_user(from->si_lower, &to->si_lower);
- err |= __put_user(from->si_upper, &to->si_upper);
- }
-#endif
-#ifdef SEGV_PKUERR
- if (from->si_signo == SIGSEGV && from->si_code == SEGV_PKUERR)
- err |= __put_user(from->si_pkey, &to->si_pkey);
-#endif
- break;
- case SIL_CHLD:
- err |= __put_user(from->si_pid, &to->si_pid);
- err |= __put_user(from->si_uid, &to->si_uid);
- err |= __put_user(from->si_status, &to->si_status);
- err |= __put_user(from->si_utime, &to->si_utime);
- err |= __put_user(from->si_stime, &to->si_stime);
- break;
- case SIL_RT:
- err |= __put_user(from->si_pid, &to->si_pid);
- err |= __put_user(from->si_uid, &to->si_uid);
- err |= __put_user(from->si_ptr, &to->si_ptr);
- break;
- case SIL_SYS:
- err |= __put_user(from->si_call_addr, &to->si_call_addr);
- err |= __put_user(from->si_syscall, &to->si_syscall);
- err |= __put_user(from->si_arch, &to->si_arch);
- break;
- }
- return err;
+ return 0;
}
#ifdef CONFIG_COMPAT
@@ -2971,27 +2902,28 @@ int __copy_siginfo_to_user32(struct compat_siginfo __user *to,
#ifdef __ARCH_SI_TRAPNO
new.si_trapno = from->si_trapno;
#endif
-#ifdef BUS_MCEERR_AR
- if ((from->si_signo == SIGBUS) && (from->si_code == BUS_MCEERR_AR))
- new.si_addr_lsb = from->si_addr_lsb;
+ break;
+ case SIL_FAULT_MCEERR:
+ new.si_addr = ptr_to_compat(from->si_addr);
+#ifdef __ARCH_SI_TRAPNO
+ new.si_trapno = from->si_trapno;
#endif
-#ifdef BUS_MCEERR_AO
- if ((from->si_signo == SIGBUS) && (from->si_code == BUS_MCEERR_AO))
- new.si_addr_lsb = from->si_addr_lsb;
+ new.si_addr_lsb = from->si_addr_lsb;
+ break;
+ case SIL_FAULT_BNDERR:
+ new.si_addr = ptr_to_compat(from->si_addr);
+#ifdef __ARCH_SI_TRAPNO
+ new.si_trapno = from->si_trapno;
#endif
-#ifdef SEGV_BNDERR
- if ((from->si_signo == SIGSEGV) &&
- (from->si_code == SEGV_BNDERR)) {
- new.si_lower = ptr_to_compat(from->si_lower);
- new.si_upper = ptr_to_compat(from->si_upper);
- }
+ new.si_lower = ptr_to_compat(from->si_lower);
+ new.si_upper = ptr_to_compat(from->si_upper);
+ break;
+ case SIL_FAULT_PKUERR:
+ new.si_addr = ptr_to_compat(from->si_addr);
+#ifdef __ARCH_SI_TRAPNO
+ new.si_trapno = from->si_trapno;
#endif
-#ifdef SEGV_PKUERR
- if ((from->si_signo == SIGSEGV) &&
- (from->si_code == SEGV_PKUERR))
- new.si_pkey = from->si_pkey;
-#endif
-
+ new.si_pkey = from->si_pkey;
break;
case SIL_CHLD:
new.si_pid = from->si_pid;
@@ -3057,24 +2989,28 @@ int copy_siginfo_from_user32(struct siginfo *to,
#ifdef __ARCH_SI_TRAPNO
to->si_trapno = from.si_trapno;
#endif
-#ifdef BUS_MCEERR_AR
- if ((from.si_signo == SIGBUS) && (from.si_code == BUS_MCEERR_AR))
- to->si_addr_lsb = from.si_addr_lsb;
+ break;
+ case SIL_FAULT_MCEERR:
+ to->si_addr = compat_ptr(from.si_addr);
+#ifdef __ARCH_SI_TRAPNO
+ to->si_trapno = from.si_trapno;
#endif
-#ifdef BUS_MCEER_AO
- if ((from.si_signo == SIGBUS) && (from.si_code == BUS_MCEERR_AO))
- to->si_addr_lsb = from.si_addr_lsb;
+ to->si_addr_lsb = from.si_addr_lsb;
+ break;
+ case SIL_FAULT_BNDERR:
+ to->si_addr = compat_ptr(from.si_addr);
+#ifdef __ARCH_SI_TRAPNO
+ to->si_trapno = from.si_trapno;
#endif
-#ifdef SEGV_BNDERR
- if ((from.si_signo == SIGSEGV) && (from.si_code == SEGV_BNDERR)) {
- to->si_lower = compat_ptr(from.si_lower);
- to->si_upper = compat_ptr(from.si_upper);
- }
+ to->si_lower = compat_ptr(from.si_lower);
+ to->si_upper = compat_ptr(from.si_upper);
+ break;
+ case SIL_FAULT_PKUERR:
+ to->si_addr = compat_ptr(from.si_addr);
+#ifdef __ARCH_SI_TRAPNO
+ to->si_trapno = from.si_trapno;
#endif
-#ifdef SEGV_PKUERR
- if ((from.si_signo == SIGSEGV) && (from.si_code == SEGV_PKUERR))
- to->si_pkey = from.si_pkey;
-#endif
+ to->si_pkey = from.si_pkey;
break;
case SIL_CHLD:
to->si_pid = from.si_pid;
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 177de36..de2f57f 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -49,8 +49,8 @@
*/
#ifndef __ARCH_IRQ_STAT
-irq_cpustat_t irq_stat[NR_CPUS] ____cacheline_aligned;
-EXPORT_SYMBOL(irq_stat);
+DEFINE_PER_CPU_ALIGNED(irq_cpustat_t, irq_stat);
+EXPORT_PER_CPU_SYMBOL(irq_stat);
#endif
static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;
@@ -145,8 +145,7 @@ static void __local_bh_enable(unsigned int cnt)
}
/*
- * Special-case - softirqs can safely be enabled in
- * cond_resched_softirq(), or by __do_softirq(),
+ * Special-case - softirqs can safely be enabled by __do_softirq(),
* without processing still-pending softirqs:
*/
void _local_bh_enable(void)
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index b759126..f89014a 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -21,6 +21,7 @@
#include <linux/smpboot.h>
#include <linux/atomic.h>
#include <linux/nmi.h>
+#include <linux/sched/wake_q.h>
/*
* Structure to determine completion condition and record errors. May
@@ -36,7 +37,7 @@ struct cpu_stop_done {
struct cpu_stopper {
struct task_struct *thread;
- spinlock_t lock;
+ raw_spinlock_t lock;
bool enabled; /* is this stopper enabled? */
struct list_head works; /* list of pending works */
@@ -65,26 +66,30 @@ static void cpu_stop_signal_done(struct cpu_stop_done *done)
}
static void __cpu_stop_queue_work(struct cpu_stopper *stopper,
- struct cpu_stop_work *work)
+ struct cpu_stop_work *work,
+ struct wake_q_head *wakeq)
{
list_add_tail(&work->list, &stopper->works);
- wake_up_process(stopper->thread);
+ wake_q_add(wakeq, stopper->thread);
}
/* queue @work to @stopper. if offline, @work is completed immediately */
static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
{
struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
+ DEFINE_WAKE_Q(wakeq);
unsigned long flags;
bool enabled;
- spin_lock_irqsave(&stopper->lock, flags);
+ raw_spin_lock_irqsave(&stopper->lock, flags);
enabled = stopper->enabled;
if (enabled)
- __cpu_stop_queue_work(stopper, work);
+ __cpu_stop_queue_work(stopper, work, &wakeq);
else if (work->done)
cpu_stop_signal_done(work->done);
- spin_unlock_irqrestore(&stopper->lock, flags);
+ raw_spin_unlock_irqrestore(&stopper->lock, flags);
+
+ wake_up_q(&wakeq);
return enabled;
}
@@ -229,10 +234,11 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
{
struct cpu_stopper *stopper1 = per_cpu_ptr(&cpu_stopper, cpu1);
struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);
+ DEFINE_WAKE_Q(wakeq);
int err;
retry:
- spin_lock_irq(&stopper1->lock);
- spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
+ raw_spin_lock_irq(&stopper1->lock);
+ raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
err = -ENOENT;
if (!stopper1->enabled || !stopper2->enabled)
@@ -252,17 +258,20 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
goto unlock;
err = 0;
- __cpu_stop_queue_work(stopper1, work1);
- __cpu_stop_queue_work(stopper2, work2);
+ __cpu_stop_queue_work(stopper1, work1, &wakeq);
+ __cpu_stop_queue_work(stopper2, work2, &wakeq);
unlock:
- spin_unlock(&stopper2->lock);
- spin_unlock_irq(&stopper1->lock);
+ raw_spin_unlock(&stopper2->lock);
+ raw_spin_unlock_irq(&stopper1->lock);
if (unlikely(err == -EDEADLK)) {
while (stop_cpus_in_progress)
cpu_relax();
goto retry;
}
+
+ wake_up_q(&wakeq);
+
return err;
}
/**
@@ -448,9 +457,9 @@ static int cpu_stop_should_run(unsigned int cpu)
unsigned long flags;
int run;
- spin_lock_irqsave(&stopper->lock, flags);
+ raw_spin_lock_irqsave(&stopper->lock, flags);
run = !list_empty(&stopper->works);
- spin_unlock_irqrestore(&stopper->lock, flags);
+ raw_spin_unlock_irqrestore(&stopper->lock, flags);
return run;
}
@@ -461,13 +470,13 @@ static void cpu_stopper_thread(unsigned int cpu)
repeat:
work = NULL;
- spin_lock_irq(&stopper->lock);
+ raw_spin_lock_irq(&stopper->lock);
if (!list_empty(&stopper->works)) {
work = list_first_entry(&stopper->works,
struct cpu_stop_work, list);
list_del_init(&work->list);
}
- spin_unlock_irq(&stopper->lock);
+ raw_spin_unlock_irq(&stopper->lock);
if (work) {
cpu_stop_fn_t fn = work->fn;
@@ -541,7 +550,7 @@ static int __init cpu_stop_init(void)
for_each_possible_cpu(cpu) {
struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
- spin_lock_init(&stopper->lock);
+ raw_spin_lock_init(&stopper->lock);
INIT_LIST_HEAD(&stopper->works);
}
diff --git a/kernel/sys.c b/kernel/sys.c
index ad69218..d1b2b8d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -61,6 +61,8 @@
#include <linux/uidgid.h>
#include <linux/cred.h>
+#include <linux/nospec.h>
+
#include <linux/kmsg_dump.h>
/* Move somewhere else to avoid recompiling? */
#include <generated/utsrelease.h>
@@ -69,6 +71,9 @@
#include <asm/io.h>
#include <asm/unistd.h>
+/* Hardening for Spectre-v1 */
+#include <linux/nospec.h>
+
#include "uid16.h"
#ifndef SET_UNALIGN_CTL
@@ -1451,6 +1456,7 @@ SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
if (resource >= RLIM_NLIMITS)
return -EINVAL;
+ resource = array_index_nospec(resource, RLIM_NLIMITS);
task_lock(current->group_leader);
x = current->signal->rlim[resource];
task_unlock(current->group_leader);
@@ -1470,6 +1476,7 @@ COMPAT_SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
if (resource >= RLIM_NLIMITS)
return -EINVAL;
+ resource = array_index_nospec(resource, RLIM_NLIMITS);
task_lock(current->group_leader);
r = current->signal->rlim[resource];
task_unlock(current->group_leader);
@@ -2242,6 +2249,17 @@ static int propagate_has_child_subreaper(struct task_struct *p, void *data)
return 1;
}
+int __weak arch_prctl_spec_ctrl_get(struct task_struct *t, unsigned long which)
+{
+ return -EINVAL;
+}
+
+int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which,
+ unsigned long ctrl)
+{
+ return -EINVAL;
+}
+
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
unsigned long, arg4, unsigned long, arg5)
{
@@ -2450,6 +2468,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
case PR_SVE_GET_VL:
error = SVE_GET_VL();
break;
+ case PR_GET_SPECULATION_CTRL:
+ if (arg3 || arg4 || arg5)
+ return -EINVAL;
+ error = arch_prctl_spec_ctrl_get(me, arg2);
+ break;
+ case PR_SET_SPECULATION_CTRL:
+ if (arg4 || arg5)
+ return -EINVAL;
+ error = arch_prctl_spec_ctrl_set(me, arg2, arg3);
+ break;
default:
error = -EINVAL;
break;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 9791364..183169c 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -43,7 +43,9 @@ COND_SYSCALL(io_submit);
COND_SYSCALL_COMPAT(io_submit);
COND_SYSCALL(io_cancel);
COND_SYSCALL(io_getevents);
+COND_SYSCALL(io_pgetevents);
COND_SYSCALL_COMPAT(io_getevents);
+COND_SYSCALL_COMPAT(io_pgetevents);
/* fs/xattr.c */
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index e8c0dab..07148b4 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -704,24 +704,6 @@ static const struct bin_table bin_net_netfilter_table[] = {
{}
};
-static const struct bin_table bin_net_irda_table[] = {
- { CTL_INT, NET_IRDA_DISCOVERY, "discovery" },
- { CTL_STR, NET_IRDA_DEVNAME, "devname" },
- { CTL_INT, NET_IRDA_DEBUG, "debug" },
- { CTL_INT, NET_IRDA_FAST_POLL, "fast_poll_increase" },
- { CTL_INT, NET_IRDA_DISCOVERY_SLOTS, "discovery_slots" },
- { CTL_INT, NET_IRDA_DISCOVERY_TIMEOUT, "discovery_timeout" },
- { CTL_INT, NET_IRDA_SLOT_TIMEOUT, "slot_timeout" },
- { CTL_INT, NET_IRDA_MAX_BAUD_RATE, "max_baud_rate" },
- { CTL_INT, NET_IRDA_MIN_TX_TURN_TIME, "min_tx_turn_time" },
- { CTL_INT, NET_IRDA_MAX_TX_DATA_SIZE, "max_tx_data_size" },
- { CTL_INT, NET_IRDA_MAX_TX_WINDOW, "max_tx_window" },
- { CTL_INT, NET_IRDA_MAX_NOREPLY_TIME, "max_noreply_time" },
- { CTL_INT, NET_IRDA_WARN_NOREPLY_TIME, "warn_noreply_time" },
- { CTL_INT, NET_IRDA_LAP_KEEPALIVE_TIME, "lap_keepalive_time" },
- {}
-};
-
static const struct bin_table bin_net_table[] = {
{ CTL_DIR, NET_CORE, "core", bin_net_core_table },
/* NET_ETHER not used */
@@ -743,7 +725,7 @@ static const struct bin_table bin_net_table[] = {
{ CTL_DIR, NET_LLC, "llc", bin_net_llc_table },
{ CTL_DIR, NET_NETFILTER, "netfilter", bin_net_netfilter_table },
/* NET_DCCP "dccp" no longer used */
- { CTL_DIR, NET_IRDA, "irda", bin_net_irda_table },
+ /* NET_IRDA "irda" no longer used */
{ CTL_INT, 2089, "nf_conntrack_max" },
{}
};
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 0e974cf..f89a78e 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -119,8 +119,15 @@ static DEFINE_SPINLOCK(watchdog_lock);
static int watchdog_running;
static atomic_t watchdog_reset_pending;
-static int clocksource_watchdog_kthread(void *data);
-static void __clocksource_change_rating(struct clocksource *cs, int rating);
+static void inline clocksource_watchdog_lock(unsigned long *flags)
+{
+ spin_lock_irqsave(&watchdog_lock, *flags);
+}
+
+static void inline clocksource_watchdog_unlock(unsigned long *flags)
+{
+ spin_unlock_irqrestore(&watchdog_lock, *flags);
+}
/*
* Interval: 0.5sec Threshold: 0.0625s
@@ -128,23 +135,24 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating);
#define WATCHDOG_INTERVAL (HZ >> 1)
#define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 4)
-static void clocksource_watchdog_work(struct work_struct *work)
-{
- /*
- * If kthread_run fails the next watchdog scan over the
- * watchdog_list will find the unstable clock again.
- */
- kthread_run(clocksource_watchdog_kthread, NULL, "kwatchdog");
-}
-
static void __clocksource_unstable(struct clocksource *cs)
{
cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
cs->flags |= CLOCK_SOURCE_UNSTABLE;
+ /*
+ * If the clocksource is registered clocksource_watchdog_work() will
+ * re-rate and re-select.
+ */
+ if (list_empty(&cs->list)) {
+ cs->rating = 0;
+ return;
+ }
+
if (cs->mark_unstable)
cs->mark_unstable(cs);
+ /* kick clocksource_watchdog_work() */
if (finished_booting)
schedule_work(&watchdog_work);
}
@@ -153,10 +161,8 @@ static void __clocksource_unstable(struct clocksource *cs)
* clocksource_mark_unstable - mark clocksource unstable via watchdog
* @cs: clocksource to be marked unstable
*
- * This function is called instead of clocksource_change_rating from
- * cpu hotplug code to avoid a deadlock between the clocksource mutex
- * and the cpu hotplug mutex. It defers the update of the clocksource
- * to the watchdog thread.
+ * This function is called by the x86 TSC code to mark clocksources as unstable;
+ * it defers demotion and re-selection to a work.
*/
void clocksource_mark_unstable(struct clocksource *cs)
{
@@ -164,7 +170,7 @@ void clocksource_mark_unstable(struct clocksource *cs)
spin_lock_irqsave(&watchdog_lock, flags);
if (!(cs->flags & CLOCK_SOURCE_UNSTABLE)) {
- if (list_empty(&cs->wd_list))
+ if (!list_empty(&cs->list) && list_empty(&cs->wd_list))
list_add(&cs->wd_list, &watchdog_list);
__clocksource_unstable(cs);
}
@@ -319,9 +325,8 @@ static void clocksource_resume_watchdog(void)
static void clocksource_enqueue_watchdog(struct clocksource *cs)
{
- unsigned long flags;
+ INIT_LIST_HEAD(&cs->wd_list);
- spin_lock_irqsave(&watchdog_lock, flags);
if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
/* cs is a clocksource to be watched. */
list_add(&cs->wd_list, &watchdog_list);
@@ -331,7 +336,6 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
}
- spin_unlock_irqrestore(&watchdog_lock, flags);
}
static void clocksource_select_watchdog(bool fallback)
@@ -373,9 +377,6 @@ static void clocksource_select_watchdog(bool fallback)
static void clocksource_dequeue_watchdog(struct clocksource *cs)
{
- unsigned long flags;
-
- spin_lock_irqsave(&watchdog_lock, flags);
if (cs != watchdog) {
if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
/* cs is a watched clocksource. */
@@ -384,21 +385,21 @@ static void clocksource_dequeue_watchdog(struct clocksource *cs)
clocksource_stop_watchdog();
}
}
- spin_unlock_irqrestore(&watchdog_lock, flags);
}
-static int __clocksource_watchdog_kthread(void)
+static void __clocksource_change_rating(struct clocksource *cs, int rating);
+
+static int __clocksource_watchdog_work(void)
{
struct clocksource *cs, *tmp;
unsigned long flags;
- LIST_HEAD(unstable);
int select = 0;
spin_lock_irqsave(&watchdog_lock, flags);
list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) {
if (cs->flags & CLOCK_SOURCE_UNSTABLE) {
list_del_init(&cs->wd_list);
- list_add(&cs->wd_list, &unstable);
+ __clocksource_change_rating(cs, 0);
select = 1;
}
if (cs->flags & CLOCK_SOURCE_RESELECT) {
@@ -410,21 +411,15 @@ static int __clocksource_watchdog_kthread(void)
clocksource_stop_watchdog();
spin_unlock_irqrestore(&watchdog_lock, flags);
- /* Needs to be done outside of watchdog lock */
- list_for_each_entry_safe(cs, tmp, &unstable, wd_list) {
- list_del_init(&cs->wd_list);
- __clocksource_change_rating(cs, 0);
- }
return select;
}
-static int clocksource_watchdog_kthread(void *data)
+static void clocksource_watchdog_work(struct work_struct *work)
{
mutex_lock(&clocksource_mutex);
- if (__clocksource_watchdog_kthread())
+ if (__clocksource_watchdog_work())
clocksource_select();
mutex_unlock(&clocksource_mutex);
- return 0;
}
static bool clocksource_is_watchdog(struct clocksource *cs)
@@ -443,10 +438,13 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
static void clocksource_select_watchdog(bool fallback) { }
static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { }
static inline void clocksource_resume_watchdog(void) { }
-static inline int __clocksource_watchdog_kthread(void) { return 0; }
+static inline int __clocksource_watchdog_work(void) { return 0; }
static bool clocksource_is_watchdog(struct clocksource *cs) { return false; }
void clocksource_mark_unstable(struct clocksource *cs) { }
+static inline void clocksource_watchdog_lock(unsigned long *flags) { }
+static inline void clocksource_watchdog_unlock(unsigned long *flags) { }
+
#endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
/**
@@ -674,7 +672,7 @@ static int __init clocksource_done_booting(void)
/*
* Run the watchdog first to eliminate unstable clock sources
*/
- __clocksource_watchdog_kthread();
+ __clocksource_watchdog_work();
clocksource_select();
mutex_unlock(&clocksource_mutex);
return 0;
@@ -779,14 +777,19 @@ EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale);
*/
int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
{
+ unsigned long flags;
/* Initialize mult/shift and max_idle_ns */
__clocksource_update_freq_scale(cs, scale, freq);
/* Add clocksource to the clocksource list */
mutex_lock(&clocksource_mutex);
+
+ clocksource_watchdog_lock(&flags);
clocksource_enqueue(cs);
clocksource_enqueue_watchdog(cs);
+ clocksource_watchdog_unlock(&flags);
+
clocksource_select();
clocksource_select_watchdog(false);
mutex_unlock(&clocksource_mutex);
@@ -808,8 +811,13 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating)
*/
void clocksource_change_rating(struct clocksource *cs, int rating)
{
+ unsigned long flags;
+
mutex_lock(&clocksource_mutex);
+ clocksource_watchdog_lock(&flags);
__clocksource_change_rating(cs, rating);
+ clocksource_watchdog_unlock(&flags);
+
clocksource_select();
clocksource_select_watchdog(false);
mutex_unlock(&clocksource_mutex);
@@ -821,6 +829,8 @@ EXPORT_SYMBOL(clocksource_change_rating);
*/
static int clocksource_unbind(struct clocksource *cs)
{
+ unsigned long flags;
+
if (clocksource_is_watchdog(cs)) {
/* Select and try to install a replacement watchdog. */
clocksource_select_watchdog(true);
@@ -834,8 +844,12 @@ static int clocksource_unbind(struct clocksource *cs)
if (curr_clocksource == cs)
return -EBUSY;
}
+
+ clocksource_watchdog_lock(&flags);
clocksource_dequeue_watchdog(cs);
list_del_init(&cs->list);
+ clocksource_watchdog_unlock(&flags);
+
return 0;
}
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index eda1210..055a4a7 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -91,6 +91,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
.get_time = &ktime_get_real,
},
{
+ .index = HRTIMER_BASE_BOOTTIME,
+ .clockid = CLOCK_BOOTTIME,
+ .get_time = &ktime_get_boottime,
+ },
+ {
.index = HRTIMER_BASE_TAI,
.clockid = CLOCK_TAI,
.get_time = &ktime_get_clocktai,
@@ -106,6 +111,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
.get_time = &ktime_get_real,
},
{
+ .index = HRTIMER_BASE_BOOTTIME_SOFT,
+ .clockid = CLOCK_BOOTTIME,
+ .get_time = &ktime_get_boottime,
+ },
+ {
.index = HRTIMER_BASE_TAI_SOFT,
.clockid = CLOCK_TAI,
.get_time = &ktime_get_clocktai,
@@ -119,7 +129,7 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
[CLOCK_REALTIME] = HRTIMER_BASE_REALTIME,
[CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC,
- [CLOCK_BOOTTIME] = HRTIMER_BASE_MONOTONIC,
+ [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME,
[CLOCK_TAI] = HRTIMER_BASE_TAI,
};
@@ -571,12 +581,14 @@ __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_
static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
{
ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
+ ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq,
- offs_real, offs_tai);
+ offs_real, offs_boot, offs_tai);
base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real;
+ base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot;
base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai;
return now;
@@ -1747,8 +1759,10 @@ long hrtimer_nanosleep(const struct timespec64 *rqtp,
return ret;
}
-SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
- struct timespec __user *, rmtp)
+#if !defined(CONFIG_64BIT_TIME) || defined(CONFIG_64BIT)
+
+SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp,
+ struct __kernel_timespec __user *, rmtp)
{
struct timespec64 tu;
@@ -1763,7 +1777,9 @@ SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
}
-#ifdef CONFIG_COMPAT
+#endif
+
+#ifdef CONFIG_COMPAT_32BIT_TIME
COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp,
struct compat_timespec __user *, rmtp)
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 2541bd8..5a6251ac 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1205,10 +1205,12 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
u64 *newval, u64 *oldval)
{
u64 now;
+ int ret;
WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED);
+ ret = cpu_timer_sample_group(clock_idx, tsk, &now);
- if (oldval && cpu_timer_sample_group(clock_idx, tsk, &now) != -EINVAL) {
+ if (oldval && ret != -EINVAL) {
/*
* We are setting itimer. The *oldval is absolute and we update
* it to be relative, *newval argument is relative and we update
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index e0dbae9..26aa956 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -59,7 +59,7 @@ SYS_NI(alarm);
*/
SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
- const struct timespec __user *, tp)
+ const struct __kernel_timespec __user *, tp)
{
struct timespec64 new_tp;
@@ -83,8 +83,6 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
case CLOCK_BOOTTIME:
get_monotonic_boottime64(tp);
break;
- case CLOCK_MONOTONIC_ACTIVE:
- ktime_get_active_ts64(tp);
default:
return -EINVAL;
}
@@ -92,7 +90,7 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
return 0;
}
SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
- struct timespec __user *, tp)
+ struct __kernel_timespec __user *, tp)
{
int ret;
struct timespec64 kernel_tp;
@@ -106,7 +104,7 @@ SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
return 0;
}
-SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock, struct timespec __user *, tp)
+SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock, struct __kernel_timespec __user *, tp)
{
struct timespec64 rtn_tp = {
.tv_sec = 0,
@@ -126,8 +124,8 @@ SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock, struct timespec __us
}
SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
- const struct timespec __user *, rqtp,
- struct timespec __user *, rmtp)
+ const struct __kernel_timespec __user *, rqtp,
+ struct __kernel_timespec __user *, rmtp)
{
struct timespec64 t;
@@ -160,7 +158,9 @@ COMPAT_SYS_NI(timer_settime);
COMPAT_SYS_NI(timer_gettime);
COMPAT_SYS_NI(getitimer);
COMPAT_SYS_NI(setitimer);
+#endif
+#ifdef CONFIG_COMPAT_32BIT_TIME
COMPAT_SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
struct compat_timespec __user *, tp)
{
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index b6899b5..e08ce3f 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -252,16 +252,15 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 *
return 0;
}
-static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
+static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp)
{
- timekeeping_clocktai64(tp);
+ get_monotonic_boottime64(tp);
return 0;
}
-static int posix_get_monotonic_active(clockid_t which_clock,
- struct timespec64 *tp)
+static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
{
- ktime_get_active_ts64(tp);
+ timekeeping_clocktai64(tp);
return 0;
}
@@ -1041,7 +1040,7 @@ void exit_itimers(struct signal_struct *sig)
}
SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
- const struct timespec __user *, tp)
+ const struct __kernel_timespec __user *, tp)
{
const struct k_clock *kc = clockid_to_kclock(which_clock);
struct timespec64 new_tp;
@@ -1056,7 +1055,7 @@ SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
}
SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
- struct timespec __user *,tp)
+ struct __kernel_timespec __user *, tp)
{
const struct k_clock *kc = clockid_to_kclock(which_clock);
struct timespec64 kernel_tp;
@@ -1097,7 +1096,7 @@ SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock,
}
SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
- struct timespec __user *, tp)
+ struct __kernel_timespec __user *, tp)
{
const struct k_clock *kc = clockid_to_kclock(which_clock);
struct timespec64 rtn_tp;
@@ -1114,7 +1113,7 @@ SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
return error;
}
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock,
struct compat_timespec __user *, tp)
@@ -1149,6 +1148,10 @@ COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock,
return err;
}
+#endif
+
+#ifdef CONFIG_COMPAT
+
COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock,
struct compat_timex __user *, utp)
{
@@ -1173,6 +1176,10 @@ COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock,
return err;
}
+#endif
+
+#ifdef CONFIG_COMPAT_32BIT_TIME
+
COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock,
struct compat_timespec __user *, tp)
{
@@ -1204,8 +1211,8 @@ static int common_nsleep(const clockid_t which_clock, int flags,
}
SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
- const struct timespec __user *, rqtp,
- struct timespec __user *, rmtp)
+ const struct __kernel_timespec __user *, rqtp,
+ struct __kernel_timespec __user *, rmtp)
{
const struct k_clock *kc = clockid_to_kclock(which_clock);
struct timespec64 t;
@@ -1228,7 +1235,8 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
return kc->nsleep(which_clock, flags, &t);
}
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
+
COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
struct compat_timespec __user *, rqtp,
struct compat_timespec __user *, rmtp)
@@ -1253,6 +1261,7 @@ COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
return kc->nsleep(which_clock, flags, &t);
}
+
#endif
static const struct k_clock clock_realtime = {
@@ -1317,9 +1326,19 @@ static const struct k_clock clock_tai = {
.timer_arm = common_hrtimer_arm,
};
-static const struct k_clock clock_monotonic_active = {
+static const struct k_clock clock_boottime = {
.clock_getres = posix_get_hrtimer_res,
- .clock_get = posix_get_monotonic_active,
+ .clock_get = posix_get_boottime,
+ .nsleep = common_nsleep,
+ .timer_create = common_timer_create,
+ .timer_set = common_timer_set,
+ .timer_get = common_timer_get,
+ .timer_del = common_timer_del,
+ .timer_rearm = common_hrtimer_rearm,
+ .timer_forward = common_hrtimer_forward,
+ .timer_remaining = common_hrtimer_remaining,
+ .timer_try_to_cancel = common_hrtimer_try_to_cancel,
+ .timer_arm = common_hrtimer_arm,
};
static const struct k_clock * const posix_clocks[] = {
@@ -1330,11 +1349,10 @@ static const struct k_clock * const posix_clocks[] = {
[CLOCK_MONOTONIC_RAW] = &clock_monotonic_raw,
[CLOCK_REALTIME_COARSE] = &clock_realtime_coarse,
[CLOCK_MONOTONIC_COARSE] = &clock_monotonic_coarse,
- [CLOCK_BOOTTIME] = &clock_monotonic,
+ [CLOCK_BOOTTIME] = &clock_boottime,
[CLOCK_REALTIME_ALARM] = &alarm_clock,
[CLOCK_BOOTTIME_ALARM] = &alarm_clock,
[CLOCK_TAI] = &clock_tai,
- [CLOCK_MONOTONIC_ACTIVE] = &clock_monotonic_active,
};
static const struct k_clock *clockid_to_kclock(const clockid_t id)
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index b398c2e..aa2094d 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -612,6 +612,14 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
now = ktime_get();
/* Find all expired events */
for_each_cpu(cpu, tick_broadcast_oneshot_mask) {
+ /*
+ * Required for !SMP because for_each_cpu() reports
+ * unconditionally CPU0 as set on UP kernels.
+ */
+ if (!IS_ENABLED(CONFIG_SMP) &&
+ cpumask_empty(tick_broadcast_oneshot_mask))
+ break;
+
td = &per_cpu(tick_cpu_device, cpu);
if (td->evtdev->next_event <= now) {
cpumask_set_cpu(cpu, tmpmask);
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 099572c..b7005dd 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -277,7 +277,8 @@ static bool tick_check_preferred(struct clock_event_device *curdev,
*/
return !curdev ||
newdev->rating > curdev->rating ||
- !cpumask_equal(curdev->cpumask, newdev->cpumask);
+ (!cpumask_equal(curdev->cpumask, newdev->cpumask) &&
+ !tick_check_percpu(curdev, newdev, smp_processor_id()));
}
/*
@@ -419,19 +420,6 @@ void tick_suspend_local(void)
clockevents_shutdown(td->evtdev);
}
-static void tick_forward_next_period(void)
-{
- ktime_t delta, now = ktime_get();
- u64 n;
-
- delta = ktime_sub(now, tick_next_period);
- n = ktime_divns(delta, tick_period);
- tick_next_period += n * tick_period;
- if (tick_next_period < now)
- tick_next_period += tick_period;
- tick_sched_forward_next_period();
-}
-
/**
* tick_resume_local - Resume the local tick device
*
@@ -444,8 +432,6 @@ void tick_resume_local(void)
struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
bool broadcast = tick_resume_check_broadcast();
- tick_forward_next_period();
-
clockevents_tick_resume(td->evtdev);
if (!broadcast) {
if (td->mode == TICKDEV_MODE_PERIODIC)
@@ -505,6 +491,7 @@ void tick_freeze(void)
if (tick_freeze_depth == num_online_cpus()) {
trace_suspend_resume(TPS("timekeeping_freeze"),
smp_processor_id(), true);
+ system_state = SYSTEM_SUSPEND;
timekeeping_suspend();
} else {
tick_suspend_local();
@@ -528,6 +515,7 @@ void tick_unfreeze(void)
if (tick_freeze_depth == num_online_cpus()) {
timekeeping_resume();
+ system_state = SYSTEM_RUNNING;
trace_suspend_resume(TPS("timekeeping_freeze"),
smp_processor_id(), false);
} else {
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 21efab7..e277284 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -141,12 +141,6 @@ static inline void tick_check_oneshot_broadcast_this_cpu(void) { }
static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); }
#endif /* !(BROADCAST && ONESHOT) */
-#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
-extern void tick_sched_forward_next_period(void);
-#else
-static inline void tick_sched_forward_next_period(void) { }
-#endif
-
/* NO_HZ_FULL internal */
#ifdef CONFIG_NO_HZ_FULL
extern void tick_nohz_init(void);
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index c1f518e..6fe615d 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -82,16 +82,15 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *))
if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT) ||
!tick_device_is_functional(dev)) {
- printk(KERN_INFO "Clockevents: "
- "could not switch to one-shot mode:");
+ pr_info("Clockevents: could not switch to one-shot mode:");
if (!dev) {
- printk(" no tick device\n");
+ pr_cont(" no tick device\n");
} else {
if (!tick_device_is_functional(dev))
- printk(" %s is not functional.\n", dev->name);
+ pr_cont(" %s is not functional.\n", dev->name);
else
- printk(" %s does not support one-shot mode.\n",
- dev->name);
+ pr_cont(" %s does not support one-shot mode.\n",
+ dev->name);
}
return -EINVAL;
}
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 646645e..da9455a 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -52,15 +52,6 @@ struct tick_sched *tick_get_tick_sched(int cpu)
static ktime_t last_jiffies_update;
/*
- * Called after resume. Make sure that jiffies are not fast forwarded due to
- * clock monotonic being forwarded by the suspended time.
- */
-void tick_sched_forward_next_period(void)
-{
- last_jiffies_update = tick_next_period;
-}
-
-/*
* Must be called with interrupts disabled !
*/
static void tick_do_update_jiffies64(ktime_t now)
@@ -804,12 +795,12 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
return;
}
- hrtimer_set_expires(&ts->sched_timer, tick);
-
- if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
- hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED);
- else
+ if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
+ hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED);
+ } else {
+ hrtimer_set_expires(&ts->sched_timer, tick);
tick_program_event(tick, 1);
+ }
}
static void tick_nohz_retain_tick(struct tick_sched *ts)
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 3044d48..6fa9921 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -407,7 +407,6 @@ time64_t mktime64(const unsigned int year0, const unsigned int mon0,
}
EXPORT_SYMBOL(mktime64);
-#if __BITS_PER_LONG == 32
/**
* set_normalized_timespec - set timespec sec and nsec parts and normalize
*
@@ -468,7 +467,6 @@ struct timespec ns_to_timespec(const s64 nsec)
return ts;
}
EXPORT_SYMBOL(ns_to_timespec);
-#endif
/**
* ns_to_timeval - Convert nanoseconds to timeval
@@ -853,9 +851,9 @@ struct timespec64 timespec64_add_safe(const struct timespec64 lhs,
}
int get_timespec64(struct timespec64 *ts,
- const struct timespec __user *uts)
+ const struct __kernel_timespec __user *uts)
{
- struct timespec kts;
+ struct __kernel_timespec kts;
int ret;
ret = copy_from_user(&kts, uts, sizeof(kts));
@@ -863,6 +861,11 @@ int get_timespec64(struct timespec64 *ts,
return -EFAULT;
ts->tv_sec = kts.tv_sec;
+
+ /* Zero out the padding for 32 bit systems or in compat mode */
+ if (IS_ENABLED(CONFIG_64BIT_TIME) && (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall()))
+ kts.tv_nsec &= 0xFFFFFFFFUL;
+
ts->tv_nsec = kts.tv_nsec;
return 0;
@@ -870,16 +873,61 @@ int get_timespec64(struct timespec64 *ts,
EXPORT_SYMBOL_GPL(get_timespec64);
int put_timespec64(const struct timespec64 *ts,
- struct timespec __user *uts)
+ struct __kernel_timespec __user *uts)
{
- struct timespec kts = {
+ struct __kernel_timespec kts = {
.tv_sec = ts->tv_sec,
.tv_nsec = ts->tv_nsec
};
+
return copy_to_user(uts, &kts, sizeof(kts)) ? -EFAULT : 0;
}
EXPORT_SYMBOL_GPL(put_timespec64);
+int __compat_get_timespec64(struct timespec64 *ts64,
+ const struct compat_timespec __user *cts)
+{
+ struct compat_timespec ts;
+ int ret;
+
+ ret = copy_from_user(&ts, cts, sizeof(ts));
+ if (ret)
+ return -EFAULT;
+
+ ts64->tv_sec = ts.tv_sec;
+ ts64->tv_nsec = ts.tv_nsec;
+
+ return 0;
+}
+
+int __compat_put_timespec64(const struct timespec64 *ts64,
+ struct compat_timespec __user *cts)
+{
+ struct compat_timespec ts = {
+ .tv_sec = ts64->tv_sec,
+ .tv_nsec = ts64->tv_nsec
+ };
+ return copy_to_user(cts, &ts, sizeof(ts)) ? -EFAULT : 0;
+}
+
+int compat_get_timespec64(struct timespec64 *ts, const void __user *uts)
+{
+ if (COMPAT_USE_64BIT_TIME)
+ return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0;
+ else
+ return __compat_get_timespec64(ts, uts);
+}
+EXPORT_SYMBOL_GPL(compat_get_timespec64);
+
+int compat_put_timespec64(const struct timespec64 *ts, void __user *uts)
+{
+ if (COMPAT_USE_64BIT_TIME)
+ return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0;
+ else
+ return __compat_put_timespec64(ts, uts);
+}
+EXPORT_SYMBOL_GPL(compat_put_timespec64);
+
int get_itimerspec64(struct itimerspec64 *it,
const struct itimerspec __user *uit)
{
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index ca90219..4786df9 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -138,12 +138,7 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm)
static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
{
- /* Update both bases so mono and raw stay coupled. */
- tk->tkr_mono.base += delta;
- tk->tkr_raw.base += delta;
-
- /* Accumulate time spent in suspend */
- tk->time_suspended += delta;
+ tk->offs_boot = ktime_add(tk->offs_boot, delta);
}
/*
@@ -473,6 +468,36 @@ u64 ktime_get_raw_fast_ns(void)
}
EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns);
+/**
+ * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock.
+ *
+ * To keep it NMI safe since we're accessing from tracing, we're not using a
+ * separate timekeeper with updates to monotonic clock and boot offset
+ * protected with seqlocks. This has the following minor side effects:
+ *
+ * (1) Its possible that a timestamp be taken after the boot offset is updated
+ * but before the timekeeper is updated. If this happens, the new boot offset
+ * is added to the old timekeeping making the clock appear to update slightly
+ * earlier:
+ * CPU 0 CPU 1
+ * timekeeping_inject_sleeptime64()
+ * __timekeeping_inject_sleeptime(tk, delta);
+ * timestamp();
+ * timekeeping_update(tk, TK_CLEAR_NTP...);
+ *
+ * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be
+ * partially updated. Since the tk->offs_boot update is a rare event, this
+ * should be a rare occurrence which postprocessing should be able to handle.
+ */
+u64 notrace ktime_get_boot_fast_ns(void)
+{
+ struct timekeeper *tk = &tk_core.timekeeper;
+
+ return (ktime_get_mono_fast_ns() + ktime_to_ns(tk->offs_boot));
+}
+EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns);
+
+
/*
* See comment for __ktime_get_fast_ns() vs. timestamp ordering
*/
@@ -680,18 +705,19 @@ static void timekeeping_forward_now(struct timekeeper *tk)
}
/**
- * __getnstimeofday64 - Returns the time of day in a timespec64.
+ * ktime_get_real_ts64 - Returns the time of day in a timespec64.
* @ts: pointer to the timespec to be set
*
- * Updates the time of day in the timespec.
- * Returns 0 on success, or -ve when suspended (timespec will be undefined).
+ * Returns the time of day in a timespec64 (WARN if suspended).
*/
-int __getnstimeofday64(struct timespec64 *ts)
+void ktime_get_real_ts64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned long seq;
u64 nsecs;
+ WARN_ON(timekeeping_suspended);
+
do {
seq = read_seqcount_begin(&tk_core.seq);
@@ -702,28 +728,8 @@ int __getnstimeofday64(struct timespec64 *ts)
ts->tv_nsec = 0;
timespec64_add_ns(ts, nsecs);
-
- /*
- * Do not bail out early, in case there were callers still using
- * the value, even in the face of the WARN_ON.
- */
- if (unlikely(timekeeping_suspended))
- return -EAGAIN;
- return 0;
}
-EXPORT_SYMBOL(__getnstimeofday64);
-
-/**
- * getnstimeofday64 - Returns the time of day in a timespec64.
- * @ts: pointer to the timespec64 to be set
- *
- * Returns the time of day in a timespec64 (WARN if suspended).
- */
-void getnstimeofday64(struct timespec64 *ts)
-{
- WARN_ON(__getnstimeofday64(ts));
-}
-EXPORT_SYMBOL(getnstimeofday64);
+EXPORT_SYMBOL(ktime_get_real_ts64);
ktime_t ktime_get(void)
{
@@ -764,6 +770,7 @@ EXPORT_SYMBOL_GPL(ktime_get_resolution_ns);
static ktime_t *offsets[TK_OFFS_MAX] = {
[TK_OFFS_REAL] = &tk_core.timekeeper.offs_real,
+ [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot,
[TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai,
};
@@ -788,6 +795,25 @@ ktime_t ktime_get_with_offset(enum tk_offsets offs)
}
EXPORT_SYMBOL_GPL(ktime_get_with_offset);
+ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs)
+{
+ struct timekeeper *tk = &tk_core.timekeeper;
+ unsigned int seq;
+ ktime_t base, *offset = offsets[offs];
+
+ WARN_ON(timekeeping_suspended);
+
+ do {
+ seq = read_seqcount_begin(&tk_core.seq);
+ base = ktime_add(tk->tkr_mono.base, *offset);
+
+ } while (read_seqcount_retry(&tk_core.seq, seq));
+
+ return base;
+
+}
+EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset);
+
/**
* ktime_mono_to_any() - convert mononotic time to any other time
* @tmono: time to convert.
@@ -861,39 +887,6 @@ void ktime_get_ts64(struct timespec64 *ts)
EXPORT_SYMBOL_GPL(ktime_get_ts64);
/**
- * ktime_get_active_ts64 - Get the active non-suspended monotonic clock
- * @ts: pointer to timespec variable
- *
- * The function calculates the monotonic clock from the realtime clock and
- * the wall_to_monotonic offset, subtracts the accumulated suspend time and
- * stores the result in normalized timespec64 format in the variable
- * pointed to by @ts.
- */
-void ktime_get_active_ts64(struct timespec64 *ts)
-{
- struct timekeeper *tk = &tk_core.timekeeper;
- struct timespec64 tomono, tsusp;
- u64 nsec, nssusp;
- unsigned int seq;
-
- WARN_ON(timekeeping_suspended);
-
- do {
- seq = read_seqcount_begin(&tk_core.seq);
- ts->tv_sec = tk->xtime_sec;
- nsec = timekeeping_get_ns(&tk->tkr_mono);
- tomono = tk->wall_to_monotonic;
- nssusp = tk->time_suspended;
- } while (read_seqcount_retry(&tk_core.seq, seq));
-
- ts->tv_sec += tomono.tv_sec;
- ts->tv_nsec = 0;
- timespec64_add_ns(ts, nsec + tomono.tv_nsec);
- tsusp = ns_to_timespec64(nssusp);
- *ts = timespec64_sub(*ts, tsusp);
-}
-
-/**
* ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC
*
* Returns the seconds portion of CLOCK_MONOTONIC with a single non
@@ -1417,12 +1410,12 @@ int timekeeping_notify(struct clocksource *clock)
}
/**
- * getrawmonotonic64 - Returns the raw monotonic time in a timespec
+ * ktime_get_raw_ts64 - Returns the raw monotonic time in a timespec
* @ts: pointer to the timespec64 to be set
*
* Returns the raw monotonic time (completely un-modified by ntp)
*/
-void getrawmonotonic64(struct timespec64 *ts)
+void ktime_get_raw_ts64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned long seq;
@@ -1438,7 +1431,7 @@ void getrawmonotonic64(struct timespec64 *ts)
ts->tv_nsec = 0;
timespec64_add_ns(ts, nsecs);
}
-EXPORT_SYMBOL(getrawmonotonic64);
+EXPORT_SYMBOL(ktime_get_raw_ts64);
/**
@@ -1593,6 +1586,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
return;
}
tk_xtime_add(tk, delta);
+ tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta));
tk_update_sleep_time(tk, timespec64_to_ktime(*delta));
tk_debug_account_sleep_time(delta);
}
@@ -2125,7 +2119,7 @@ void update_wall_time(void)
void getboottime64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
- ktime_t t = ktime_sub(tk->offs_real, tk->time_suspended);
+ ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot);
*ts = ktime_to_timespec64(t);
}
@@ -2139,30 +2133,20 @@ unsigned long get_seconds(void)
}
EXPORT_SYMBOL(get_seconds);
-struct timespec __current_kernel_time(void)
+void ktime_get_coarse_real_ts64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
-
- return timespec64_to_timespec(tk_xtime(tk));
-}
-
-struct timespec64 current_kernel_time64(void)
-{
- struct timekeeper *tk = &tk_core.timekeeper;
- struct timespec64 now;
unsigned long seq;
do {
seq = read_seqcount_begin(&tk_core.seq);
- now = tk_xtime(tk);
+ *ts = tk_xtime(tk);
} while (read_seqcount_retry(&tk_core.seq, seq));
-
- return now;
}
-EXPORT_SYMBOL(current_kernel_time64);
+EXPORT_SYMBOL(ktime_get_coarse_real_ts64);
-struct timespec64 get_monotonic_coarse64(void)
+void ktime_get_coarse_ts64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
struct timespec64 now, mono;
@@ -2175,12 +2159,10 @@ struct timespec64 get_monotonic_coarse64(void)
mono = tk->wall_to_monotonic;
} while (read_seqcount_retry(&tk_core.seq, seq));
- set_normalized_timespec64(&now, now.tv_sec + mono.tv_sec,
+ set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec,
now.tv_nsec + mono.tv_nsec);
-
- return now;
}
-EXPORT_SYMBOL(get_monotonic_coarse64);
+EXPORT_SYMBOL(ktime_get_coarse_ts64);
/*
* Must hold jiffies_lock
@@ -2195,6 +2177,7 @@ void do_timer(unsigned long ticks)
* ktime_get_update_offsets_now - hrtimer helper
* @cwsseq: pointer to check and store the clock was set sequence number
* @offs_real: pointer to storage for monotonic -> realtime offset
+ * @offs_boot: pointer to storage for monotonic -> boottime offset
* @offs_tai: pointer to storage for monotonic -> clock tai offset
*
* Returns current monotonic time and updates the offsets if the
@@ -2204,7 +2187,7 @@ void do_timer(unsigned long ticks)
* Called from hrtimer_interrupt() or retrigger_next_event()
*/
ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
- ktime_t *offs_tai)
+ ktime_t *offs_boot, ktime_t *offs_tai)
{
struct timekeeper *tk = &tk_core.timekeeper;
unsigned int seq;
@@ -2221,6 +2204,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
if (*cwsseq != tk->clock_was_set_seq) {
*cwsseq = tk->clock_was_set_seq;
*offs_real = tk->offs_real;
+ *offs_boot = tk->offs_boot;
*offs_tai = tk->offs_tai;
}
diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h
index 79b67f5e..7a9b4eb 100644
--- a/kernel/time/timekeeping.h
+++ b/kernel/time/timekeeping.h
@@ -6,6 +6,7 @@
*/
extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq,
ktime_t *offs_real,
+ ktime_t *offs_boot,
ktime_t *offs_tai);
extern int timekeeping_valid_for_hres(void);
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 4a4fd56..cc2d23e 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1251,18 +1251,18 @@ EXPORT_SYMBOL(try_to_del_timer_sync);
*
* Note: For !irqsafe timers, you must not hold locks that are held in
* interrupt context while calling this function. Even if the lock has
- * nothing to do with the timer in question. Here's why:
+ * nothing to do with the timer in question. Here's why::
*
* CPU0 CPU1
* ---- ----
- * <SOFTIRQ>
- * call_timer_fn();
- * base->running_timer = mytimer;
- * spin_lock_irq(somelock);
+ * <SOFTIRQ>
+ * call_timer_fn();
+ * base->running_timer = mytimer;
+ * spin_lock_irq(somelock);
* <IRQ>
* spin_lock(somelock);
- * del_timer_sync(mytimer);
- * while (base->running_timer == mytimer);
+ * del_timer_sync(mytimer);
+ * while (base->running_timer == mytimer);
*
* Now del_timer_sync() will never return and never release somelock.
* The interrupt on the other CPU is waiting to grab somelock but
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 0ed768b..d647dab 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -28,8 +28,6 @@ struct timer_list_iter {
u64 now;
};
-typedef void (*print_fn_t)(struct seq_file *m, unsigned int *classes);
-
/*
* This allows printing both to /proc/timer_list and
* to the console (on SysRq-Q):
@@ -372,24 +370,12 @@ static const struct seq_operations timer_list_sops = {
.show = timer_list_show,
};
-static int timer_list_open(struct inode *inode, struct file *filp)
-{
- return seq_open_private(filp, &timer_list_sops,
- sizeof(struct timer_list_iter));
-}
-
-static const struct file_operations timer_list_fops = {
- .open = timer_list_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_private,
-};
-
static int __init init_timer_list_procfs(void)
{
struct proc_dir_entry *pe;
- pe = proc_create("timer_list", 0400, NULL, &timer_list_fops);
+ pe = proc_create_seq_private("timer_list", 0400, NULL, &timer_list_sops,
+ sizeof(struct timer_list_iter), NULL);
if (!pe)
return -ENOMEM;
return 0;
diff --git a/kernel/torture.c b/kernel/torture.c
index 37b94012..3de1efb 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -574,7 +574,7 @@ void stutter_wait(const char *title)
{
int spt;
- cond_resched_rcu_qs();
+ cond_resched_tasks_rcu_qs();
spt = READ_ONCE(stutter_pause_test);
for (; spt; spt = READ_ONCE(stutter_pause_test)) {
if (spt == 1) {
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index d88e96d..56ba0f2 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -977,6 +977,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
{
struct perf_event_query_bpf __user *uquery = info;
struct perf_event_query_bpf query = {};
+ u32 *ids, prog_cnt, ids_len;
int ret;
if (!capable(CAP_SYS_ADMIN))
@@ -985,16 +986,32 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
return -EINVAL;
if (copy_from_user(&query, uquery, sizeof(query)))
return -EFAULT;
- if (query.ids_len > BPF_TRACE_MAX_PROGS)
+
+ ids_len = query.ids_len;
+ if (ids_len > BPF_TRACE_MAX_PROGS)
return -E2BIG;
+ ids = kcalloc(ids_len, sizeof(u32), GFP_USER | __GFP_NOWARN);
+ if (!ids)
+ return -ENOMEM;
+ /*
+ * The above kcalloc returns ZERO_SIZE_PTR when ids_len = 0, which
+ * is required when user only wants to check for uquery->prog_cnt.
+ * There is no need to check for it since the case is handled
+ * gracefully in bpf_prog_array_copy_info.
+ */
mutex_lock(&bpf_event_mutex);
ret = bpf_prog_array_copy_info(event->tp_event->prog_array,
- uquery->ids,
- query.ids_len,
- &uquery->prog_cnt);
+ ids,
+ ids_len,
+ &prog_cnt);
mutex_unlock(&bpf_event_mutex);
+ if (copy_to_user(&uquery->prog_cnt, &prog_cnt, sizeof(prog_cnt)) ||
+ copy_to_user(uquery->ids, ids, ids_len * sizeof(u32)))
+ ret = -EFAULT;
+
+ kfree(ids);
return ret;
}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 16bbf06..8d83bcf 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5514,10 +5514,10 @@ static __init int ftrace_init_dyn_tracefs(struct dentry *d_tracer)
ftrace_create_filter_files(&global_ops, d_tracer);
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- trace_create_file("set_graph_function", 0444, d_tracer,
+ trace_create_file("set_graph_function", 0644, d_tracer,
NULL,
&ftrace_graph_fops);
- trace_create_file("set_graph_notrace", 0444, d_tracer,
+ trace_create_file("set_graph_notrace", 0644, d_tracer,
NULL,
&ftrace_graph_notrace_fops);
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index dfbcf9e..bcd9303 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -893,7 +893,7 @@ int __trace_bputs(unsigned long ip, const char *str)
EXPORT_SYMBOL_GPL(__trace_bputs);
#ifdef CONFIG_TRACER_SNAPSHOT
-static void tracing_snapshot_instance(struct trace_array *tr)
+void tracing_snapshot_instance(struct trace_array *tr)
{
struct tracer *tracer = tr->current_trace;
unsigned long flags;
@@ -949,7 +949,7 @@ static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf,
struct trace_buffer *size_buf, int cpu_id);
static void set_buffer_entries(struct trace_buffer *buf, unsigned long val);
-static int alloc_snapshot(struct trace_array *tr)
+int tracing_alloc_snapshot_instance(struct trace_array *tr)
{
int ret;
@@ -995,7 +995,7 @@ int tracing_alloc_snapshot(void)
struct trace_array *tr = &global_trace;
int ret;
- ret = alloc_snapshot(tr);
+ ret = tracing_alloc_snapshot_instance(tr);
WARN_ON(ret < 0);
return ret;
@@ -1165,7 +1165,7 @@ static struct {
{ trace_clock, "perf", 1 },
{ ktime_get_mono_fast_ns, "mono", 1 },
{ ktime_get_raw_fast_ns, "mono_raw", 1 },
- { ktime_get_mono_fast_ns, "boot", 1 },
+ { ktime_get_boot_fast_ns, "boot", 1 },
ARCH_TRACE_CLOCKS
};
@@ -5408,7 +5408,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf)
#ifdef CONFIG_TRACER_MAX_TRACE
if (t->use_max_tr && !had_max_tr) {
- ret = alloc_snapshot(tr);
+ ret = tracing_alloc_snapshot_instance(tr);
if (ret < 0)
goto out;
}
@@ -6451,7 +6451,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
}
#endif
if (!tr->allocated_snapshot) {
- ret = alloc_snapshot(tr);
+ ret = tracing_alloc_snapshot_instance(tr);
if (ret < 0)
break;
}
@@ -7179,7 +7179,7 @@ ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash,
return ret;
out_reg:
- ret = alloc_snapshot(tr);
+ ret = tracing_alloc_snapshot_instance(tr);
if (ret < 0)
goto out;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6fb46a0..507954b 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1817,6 +1817,17 @@ static inline void __init trace_event_init(void) { }
static inline void trace_event_eval_update(struct trace_eval_map **map, int len) { }
#endif
+#ifdef CONFIG_TRACER_SNAPSHOT
+void tracing_snapshot_instance(struct trace_array *tr);
+int tracing_alloc_snapshot_instance(struct trace_array *tr);
+#else
+static inline void tracing_snapshot_instance(struct trace_array *tr) { }
+static inline int tracing_alloc_snapshot_instance(struct trace_array *tr)
+{
+ return 0;
+}
+#endif
+
extern struct trace_iterator *tracepoint_print_iter;
#endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c
index 22fee76..80e0b2a 100644
--- a/kernel/trace/trace_benchmark.c
+++ b/kernel/trace/trace_benchmark.c
@@ -159,13 +159,13 @@ static int benchmark_event_kthread(void *arg)
* wants to run, schedule in, but if the CPU is idle,
* we'll keep burning cycles.
*
- * Note the _rcu_qs() version of cond_resched() will
+ * Note the tasks_rcu_qs() version of cond_resched() will
* notify synchronize_rcu_tasks() that this thread has
* passed a quiescent state for rcu_tasks. Otherwise
* this thread will never voluntarily schedule which would
* block synchronize_rcu_tasks() indefinitely.
*/
- cond_resched();
+ cond_resched_tasks_rcu_qs();
}
return 0;
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index e954ae3..e3a658b 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -356,7 +356,7 @@ FTRACE_ENTRY(hwlat, hwlat_entry,
__field( unsigned int, seqnum )
),
- F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llunmi-ts:%llu\tnmi-count:%u\n",
+ F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llu\tnmi-ts:%llu\tnmi-count:%u\n",
__entry->seqnum,
__entry->tv_sec,
__entry->tv_nsec,
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 9b4716b..7d306b7 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -762,6 +762,9 @@ static int regex_match_full(char *str, struct regex *r, int len)
static int regex_match_front(char *str, struct regex *r, int len)
{
+ if (len < r->len)
+ return 0;
+
if (strncmp(str, r->pattern, r->len) == 0)
return 1;
return 0;
@@ -1499,14 +1502,14 @@ static int process_preds(struct trace_event_call *call,
return ret;
}
- if (!nr_preds) {
- prog = NULL;
- } else {
- prog = predicate_parse(filter_string, nr_parens, nr_preds,
+ if (!nr_preds)
+ return -EINVAL;
+
+ prog = predicate_parse(filter_string, nr_parens, nr_preds,
parse_pred, call, pe);
- if (IS_ERR(prog))
- return PTR_ERR(prog);
- }
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+
rcu_assign_pointer(filter->prog, prog);
return 0;
}
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 0d7b3ff..b9061ed 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -2466,6 +2466,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
else if (strcmp(modifier, "usecs") == 0)
*flags |= HIST_FIELD_FL_TIMESTAMP_USECS;
else {
+ hist_err("Invalid field modifier: ", modifier);
field = ERR_PTR(-EINVAL);
goto out;
}
@@ -2481,6 +2482,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
else {
field = trace_find_event_field(file->event_call, field_name);
if (!field || !field->size) {
+ hist_err("Couldn't find field: ", field_name);
field = ERR_PTR(-EINVAL);
goto out;
}
@@ -4913,6 +4915,16 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
seq_printf(m, "%s", field_name);
} else if (hist_field->flags & HIST_FIELD_FL_TIMESTAMP)
seq_puts(m, "common_timestamp");
+
+ if (hist_field->flags) {
+ if (!(hist_field->flags & HIST_FIELD_FL_VAR_REF) &&
+ !(hist_field->flags & HIST_FIELD_FL_EXPR)) {
+ const char *flags = get_hist_field_flags(hist_field);
+
+ if (flags)
+ seq_printf(m, ".%s", flags);
+ }
+ }
}
static int event_hist_trigger_print(struct seq_file *m,
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index d251cab..8b5bdcf 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -483,9 +483,10 @@ clear_event_triggers(struct trace_array *tr)
struct trace_event_file *file;
list_for_each_entry(file, &tr->events, list) {
- struct event_trigger_data *data;
- list_for_each_entry_rcu(data, &file->triggers, list) {
+ struct event_trigger_data *data, *n;
+ list_for_each_entry_safe(data, n, &file->triggers, list) {
trace_event_trigger_enable_disable(file, 0);
+ list_del_rcu(&data->list);
if (data->ops->free)
data->ops->free(data->ops, data);
}
@@ -642,6 +643,7 @@ event_trigger_callback(struct event_command *cmd_ops,
trigger_data->count = -1;
trigger_data->ops = trigger_ops;
trigger_data->cmd_ops = cmd_ops;
+ trigger_data->private_data = file;
INIT_LIST_HEAD(&trigger_data->list);
INIT_LIST_HEAD(&trigger_data->named_list);
@@ -1053,7 +1055,12 @@ static void
snapshot_trigger(struct event_trigger_data *data, void *rec,
struct ring_buffer_event *event)
{
- tracing_snapshot();
+ struct trace_event_file *file = data->private_data;
+
+ if (file)
+ tracing_snapshot_instance(file->tr);
+ else
+ tracing_snapshot();
}
static void
@@ -1076,7 +1083,7 @@ register_snapshot_trigger(char *glob, struct event_trigger_ops *ops,
{
int ret = register_trigger(glob, ops, data, file);
- if (ret > 0 && tracing_alloc_snapshot() != 0) {
+ if (ret > 0 && tracing_alloc_snapshot_instance(file->tr) != 0) {
unregister_trigger(glob, ops, data, file);
ret = 0;
}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 1cd3fb4..02aed76 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -512,8 +512,6 @@ static int __register_trace_kprobe(struct trace_kprobe *tk)
if (ret == 0)
tk->tp.flags |= TP_FLAG_REGISTERED;
else {
- pr_warn("Could not insert probe at %s+%lu: %d\n",
- trace_kprobe_symbol(tk), trace_kprobe_offset(tk), ret);
if (ret == -ENOENT && trace_kprobe_is_on_module(tk)) {
pr_warn("This probe might be able to register after target module is loaded. Continue.\n");
ret = 0;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 3c7bfc4..4237eba 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -472,7 +472,7 @@ static __init int stack_trace_init(void)
NULL, &stack_trace_fops);
#ifdef CONFIG_DYNAMIC_FTRACE
- trace_create_file("stack_trace_filter", 0444, d_tracer,
+ trace_create_file("stack_trace_filter", 0644, d_tracer,
&trace_ops, &stack_trace_filter_fops);
#endif
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 34fd0e0..ac89287 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -55,6 +55,7 @@ struct trace_uprobe {
struct list_head list;
struct trace_uprobe_filter filter;
struct uprobe_consumer consumer;
+ struct path path;
struct inode *inode;
char *filename;
unsigned long offset;
@@ -289,7 +290,7 @@ static void free_trace_uprobe(struct trace_uprobe *tu)
for (i = 0; i < tu->tp.nr_args; i++)
traceprobe_free_probe_arg(&tu->tp.args[i]);
- iput(tu->inode);
+ path_put(&tu->path);
kfree(tu->tp.call.class->system);
kfree(tu->tp.call.name);
kfree(tu->filename);
@@ -363,7 +364,6 @@ static int register_trace_uprobe(struct trace_uprobe *tu)
static int create_trace_uprobe(int argc, char **argv)
{
struct trace_uprobe *tu;
- struct inode *inode;
char *arg, *event, *group, *filename;
char buf[MAX_EVENT_NAME_LEN];
struct path path;
@@ -371,7 +371,6 @@ static int create_trace_uprobe(int argc, char **argv)
bool is_delete, is_return;
int i, ret;
- inode = NULL;
ret = 0;
is_delete = false;
is_return = false;
@@ -437,21 +436,16 @@ static int create_trace_uprobe(int argc, char **argv)
}
/* Find the last occurrence, in case the path contains ':' too. */
arg = strrchr(argv[1], ':');
- if (!arg) {
- ret = -EINVAL;
- goto fail_address_parse;
- }
+ if (!arg)
+ return -EINVAL;
*arg++ = '\0';
filename = argv[1];
ret = kern_path(filename, LOOKUP_FOLLOW, &path);
if (ret)
- goto fail_address_parse;
+ return ret;
- inode = igrab(d_real_inode(path.dentry));
- path_put(&path);
-
- if (!inode || !S_ISREG(inode->i_mode)) {
+ if (!d_is_reg(path.dentry)) {
ret = -EINVAL;
goto fail_address_parse;
}
@@ -490,7 +484,7 @@ static int create_trace_uprobe(int argc, char **argv)
goto fail_address_parse;
}
tu->offset = offset;
- tu->inode = inode;
+ tu->path = path;
tu->filename = kstrdup(filename, GFP_KERNEL);
if (!tu->filename) {
@@ -558,7 +552,7 @@ static int create_trace_uprobe(int argc, char **argv)
return ret;
fail_address_parse:
- iput(inode);
+ path_put(&path);
pr_info("Failed to parse address or file.\n");
@@ -922,6 +916,7 @@ probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file,
goto err_flags;
tu->consumer.filter = filter;
+ tu->inode = d_real_inode(tu->path.dentry);
ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
if (ret)
goto err_buffer;
@@ -967,6 +962,7 @@ probe_event_disable(struct trace_uprobe *tu, struct trace_event_file *file)
WARN_ON(!uprobe_filter_is_empty(&tu->filter));
uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
+ tu->inode = NULL;
tu->tp.flags &= file ? ~TP_FLAG_TRACE : ~TP_FLAG_PROFILE;
uprobe_buffer_disable();
@@ -1337,7 +1333,6 @@ struct trace_event_call *
create_local_trace_uprobe(char *name, unsigned long offs, bool is_return)
{
struct trace_uprobe *tu;
- struct inode *inode;
struct path path;
int ret;
@@ -1345,11 +1340,8 @@ create_local_trace_uprobe(char *name, unsigned long offs, bool is_return)
if (ret)
return ERR_PTR(ret);
- inode = igrab(d_inode(path.dentry));
- path_put(&path);
-
- if (!inode || !S_ISREG(inode->i_mode)) {
- iput(inode);
+ if (!d_is_reg(path.dentry)) {
+ path_put(&path);
return ERR_PTR(-EINVAL);
}
@@ -1364,11 +1356,12 @@ create_local_trace_uprobe(char *name, unsigned long offs, bool is_return)
if (IS_ERR(tu)) {
pr_info("Failed to allocate trace_uprobe.(%d)\n",
(int)PTR_ERR(tu));
+ path_put(&path);
return ERR_CAST(tu);
}
tu->offset = offs;
- tu->inode = inode;
+ tu->path = path;
tu->filename = kstrdup(name, GFP_KERNEL);
init_trace_event_call(tu, &tu->tp.call);
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 671b134..1e37da2 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -207,7 +207,7 @@ static int tracepoint_add_func(struct tracepoint *tp,
lockdep_is_held(&tracepoints_mutex));
old = func_add(&tp_funcs, func, prio);
if (IS_ERR(old)) {
- WARN_ON_ONCE(1);
+ WARN_ON_ONCE(PTR_ERR(old) != -ENOMEM);
return PTR_ERR(old);
}
@@ -239,7 +239,7 @@ static int tracepoint_remove_func(struct tracepoint *tp,
lockdep_is_held(&tracepoints_mutex));
old = func_remove(&tp_funcs, func);
if (IS_ERR(old)) {
- WARN_ON_ONCE(1);
+ WARN_ON_ONCE(PTR_ERR(old) != -ENOMEM);
return PTR_ERR(old);
}
diff --git a/lib/Kconfig b/lib/Kconfig
index 5fe5776..7a91393 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -429,15 +429,50 @@
bool
default n
+config NEED_SG_DMA_LENGTH
+ bool
+
+config NEED_DMA_MAP_STATE
+ bool
+
+config ARCH_DMA_ADDR_T_64BIT
+ def_bool 64BIT || PHYS_ADDR_T_64BIT
+
+config IOMMU_HELPER
+ bool
+
+config ARCH_HAS_SYNC_DMA_FOR_DEVICE
+ bool
+
+config ARCH_HAS_SYNC_DMA_FOR_CPU
+ bool
+ select NEED_DMA_MAP_STATE
+
config DMA_DIRECT_OPS
bool
- depends on HAS_DMA && (!64BIT || ARCH_DMA_ADDR_T_64BIT)
- default n
+ depends on HAS_DMA
+
+config DMA_NONCOHERENT_OPS
+ bool
+ depends on HAS_DMA
+ select DMA_DIRECT_OPS
+
+config DMA_NONCOHERENT_MMAP
+ bool
+ depends on DMA_NONCOHERENT_OPS
+
+config DMA_NONCOHERENT_CACHE_SYNC
+ bool
+ depends on DMA_NONCOHERENT_OPS
config DMA_VIRT_OPS
bool
- depends on HAS_DMA && (!64BIT || ARCH_DMA_ADDR_T_64BIT)
- default n
+ depends on HAS_DMA
+
+config SWIOTLB
+ bool
+ select DMA_DIRECT_OPS
+ select NEED_DMA_MAP_STATE
config CHECK_SIGNATURE
bool
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index c40c7b7..7655547 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1634,7 +1634,7 @@
config DMA_API_DEBUG
bool "Enable debugging of DMA-API usage"
- depends on HAVE_DMA_API_DEBUG
+ select NEED_DMA_MAP_STATE
help
Enable this option to debug the use of the DMA API by device drivers.
With this option you will be able to detect common bugs in device
@@ -1651,6 +1651,23 @@
If unsure, say N.
+config DMA_API_DEBUG_SG
+ bool "Debug DMA scatter-gather usage"
+ default y
+ depends on DMA_API_DEBUG
+ help
+ Perform extra checking that callers of dma_map_sg() have respected the
+ appropriate segment length/boundary limits for the given device when
+ preparing DMA scatterlists.
+
+ This is particularly likely to have been overlooked in cases where the
+ dma_map_sg() API is used for general bulk mapping of pages rather than
+ preparing literal scatter-gather descriptors, where there is a risk of
+ unexpected behaviour from DMA API implementations if the scatterlist
+ is technically out-of-spec.
+
+ If unsure, say N.
+
menuconfig RUNTIME_TESTING_MENU
bool "Runtime Testing"
def_bool y
diff --git a/lib/Makefile b/lib/Makefile
index ce20696..9f18c81 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -30,6 +30,7 @@
lib-$(CONFIG_MMU) += ioremap.o
lib-$(CONFIG_SMP) += cpumask.o
lib-$(CONFIG_DMA_DIRECT_OPS) += dma-direct.o
+lib-$(CONFIG_DMA_NONCOHERENT_OPS) += dma-noncoherent.o
lib-$(CONFIG_DMA_VIRT_OPS) += dma-virt.o
lib-y += kobject.o klist.o
@@ -147,7 +148,7 @@
obj-$(CONFIG_AUDIT_COMPAT_GENERIC) += compat_audit.o
obj-$(CONFIG_SWIOTLB) += swiotlb.o
-obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o iommu-common.o
+obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o
obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o
obj-$(CONFIG_PM_NOTIFIER_ERROR_INJECT) += pm-notifier-error-inject.o
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 7f5cdc1..c007d25 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -41,6 +41,11 @@
#define HASH_FN_SHIFT 13
#define HASH_FN_MASK (HASH_SIZE - 1)
+/* allow architectures to override this if absolutely required */
+#ifndef PREALLOC_DMA_DEBUG_ENTRIES
+#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
+#endif
+
enum {
dma_debug_single,
dma_debug_page,
@@ -127,7 +132,7 @@ static u32 min_free_entries;
static u32 nr_total_entries;
/* number of preallocated entries requested by kernel cmdline */
-static u32 req_entries;
+static u32 nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES;
/* debugfs dentry's for the stuff above */
static struct dentry *dma_debug_dent __read_mostly;
@@ -439,7 +444,6 @@ void debug_dma_dump_mappings(struct device *dev)
spin_unlock_irqrestore(&bucket->lock, flags);
}
}
-EXPORT_SYMBOL(debug_dma_dump_mappings);
/*
* For each mapping (initial cacheline in the case of
@@ -748,7 +752,6 @@ int dma_debug_resize_entries(u32 num_entries)
return ret;
}
-EXPORT_SYMBOL(dma_debug_resize_entries);
/*
* DMA-API debugging init code
@@ -1004,10 +1007,7 @@ void dma_debug_add_bus(struct bus_type *bus)
bus_register_notifier(bus, nb);
}
-/*
- * Let the architectures decide how many entries should be preallocated.
- */
-void dma_debug_init(u32 num_entries)
+static int dma_debug_init(void)
{
int i;
@@ -1015,7 +1015,7 @@ void dma_debug_init(u32 num_entries)
* called to set dma_debug_initialized
*/
if (global_disable)
- return;
+ return 0;
for (i = 0; i < HASH_SIZE; ++i) {
INIT_LIST_HEAD(&dma_entry_hash[i].list);
@@ -1026,17 +1026,14 @@ void dma_debug_init(u32 num_entries)
pr_err("DMA-API: error creating debugfs entries - disabling\n");
global_disable = true;
- return;
+ return 0;
}
- if (req_entries)
- num_entries = req_entries;
-
- if (prealloc_memory(num_entries) != 0) {
+ if (prealloc_memory(nr_prealloc_entries) != 0) {
pr_err("DMA-API: debugging out of memory error - disabled\n");
global_disable = true;
- return;
+ return 0;
}
nr_total_entries = num_free_entries;
@@ -1044,7 +1041,9 @@ void dma_debug_init(u32 num_entries)
dma_debug_initialized = true;
pr_info("DMA-API: debugging enabled by kernel config\n");
+ return 0;
}
+core_initcall(dma_debug_init);
static __init int dma_debug_cmdline(char *str)
{
@@ -1061,16 +1060,10 @@ static __init int dma_debug_cmdline(char *str)
static __init int dma_debug_entries_cmdline(char *str)
{
- int res;
-
if (!str)
return -EINVAL;
-
- res = get_option(&str, &req_entries);
-
- if (!res)
- req_entries = 0;
-
+ if (!get_option(&str, &nr_prealloc_entries))
+ nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES;
return 0;
}
@@ -1293,6 +1286,32 @@ static void check_sync(struct device *dev,
put_hash_bucket(bucket, &flags);
}
+static void check_sg_segment(struct device *dev, struct scatterlist *sg)
+{
+#ifdef CONFIG_DMA_API_DEBUG_SG
+ unsigned int max_seg = dma_get_max_seg_size(dev);
+ u64 start, end, boundary = dma_get_seg_boundary(dev);
+
+ /*
+ * Either the driver forgot to set dma_parms appropriately, or
+ * whoever generated the list forgot to check them.
+ */
+ if (sg->length > max_seg)
+ err_printk(dev, NULL, "DMA-API: mapping sg segment longer than device claims to support [len=%u] [max=%u]\n",
+ sg->length, max_seg);
+ /*
+ * In some cases this could potentially be the DMA API
+ * implementation's fault, but it would usually imply that
+ * the scatterlist was built inappropriately to begin with.
+ */
+ start = sg_dma_address(sg);
+ end = start + sg_dma_len(sg) - 1;
+ if ((start ^ end) & ~boundary)
+ err_printk(dev, NULL, "DMA-API: mapping sg segment across boundary [start=0x%016llx] [end=0x%016llx] [boundary=0x%016llx]\n",
+ start, end, boundary);
+#endif
+}
+
void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
size_t size, int direction, dma_addr_t dma_addr,
bool map_single)
@@ -1423,6 +1442,8 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
check_for_illegal_area(dev, sg_virt(s), sg_dma_len(s));
}
+ check_sg_segment(dev, s);
+
add_dma_entry(entry);
}
}
diff --git a/lib/dma-direct.c b/lib/dma-direct.c
index c0bba30..8be8106 100644
--- a/lib/dma-direct.c
+++ b/lib/dma-direct.c
@@ -34,6 +34,13 @@ check_addr(struct device *dev, dma_addr_t dma_addr, size_t size,
const char *caller)
{
if (unlikely(dev && !dma_capable(dev, dma_addr, size))) {
+ if (!dev->dma_mask) {
+ dev_err(dev,
+ "%s: call on device without dma_mask\n",
+ caller);
+ return false;
+ }
+
if (*dev->dma_mask >= DMA_BIT_MASK(32)) {
dev_err(dev,
"%s: overflow %pad+%zu of device mask %llx\n",
@@ -84,7 +91,15 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
__free_pages(page, page_order);
page = NULL;
- if (dev->coherent_dma_mask < DMA_BIT_MASK(32) &&
+ if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
+ dev->coherent_dma_mask < DMA_BIT_MASK(64) &&
+ !(gfp & (GFP_DMA32 | GFP_DMA))) {
+ gfp |= GFP_DMA32;
+ goto again;
+ }
+
+ if (IS_ENABLED(CONFIG_ZONE_DMA) &&
+ dev->coherent_dma_mask < DMA_BIT_MASK(32) &&
!(gfp & GFP_DMA)) {
gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
goto again;
@@ -120,7 +135,7 @@ void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
free_pages((unsigned long)cpu_addr, page_order);
}
-static dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
+dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
unsigned long offset, size_t size, enum dma_data_direction dir,
unsigned long attrs)
{
@@ -131,8 +146,8 @@ static dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
return dma_addr;
}
-static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
- int nents, enum dma_data_direction dir, unsigned long attrs)
+int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+ enum dma_data_direction dir, unsigned long attrs)
{
int i;
struct scatterlist *sg;
@@ -164,10 +179,16 @@ int dma_direct_supported(struct device *dev, u64 mask)
if (mask < DMA_BIT_MASK(32))
return 0;
#endif
+ /*
+ * Various PCI/PCIe bridges have broken support for > 32bit DMA even
+ * if the device itself might support it.
+ */
+ if (dev->dma_32bit_limit && mask > DMA_BIT_MASK(32))
+ return 0;
return 1;
}
-static int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr)
+int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
return dma_addr == DIRECT_MAPPING_ERROR;
}
@@ -179,6 +200,5 @@ const struct dma_map_ops dma_direct_ops = {
.map_sg = dma_direct_map_sg,
.dma_supported = dma_direct_supported,
.mapping_error = dma_direct_mapping_error,
- .is_phys = 1,
};
EXPORT_SYMBOL(dma_direct_ops);
diff --git a/lib/dma-noncoherent.c b/lib/dma-noncoherent.c
new file mode 100644
index 0000000..79e9a75
--- /dev/null
+++ b/lib/dma-noncoherent.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Christoph Hellwig.
+ *
+ * DMA operations that map physical memory directly without providing cache
+ * coherence.
+ */
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
+#include <linux/scatterlist.h>
+
+static void dma_noncoherent_sync_single_for_device(struct device *dev,
+ dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+ arch_sync_dma_for_device(dev, dma_to_phys(dev, addr), size, dir);
+}
+
+static void dma_noncoherent_sync_sg_for_device(struct device *dev,
+ struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sgl, sg, nents, i)
+ arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
+}
+
+static dma_addr_t dma_noncoherent_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ dma_addr_t addr;
+
+ addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
+ if (!dma_mapping_error(dev, addr) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ arch_sync_dma_for_device(dev, page_to_phys(page) + offset,
+ size, dir);
+ return addr;
+}
+
+static int dma_noncoherent_map_sg(struct device *dev, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+ nents = dma_direct_map_sg(dev, sgl, nents, dir, attrs);
+ if (nents > 0 && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ dma_noncoherent_sync_sg_for_device(dev, sgl, nents, dir);
+ return nents;
+}
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+static void dma_noncoherent_sync_single_for_cpu(struct device *dev,
+ dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+ arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir);
+}
+
+static void dma_noncoherent_sync_sg_for_cpu(struct device *dev,
+ struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sgl, sg, nents, i)
+ arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+}
+
+static void dma_noncoherent_unmap_page(struct device *dev, dma_addr_t addr,
+ size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+ if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ dma_noncoherent_sync_single_for_cpu(dev, addr, size, dir);
+}
+
+static void dma_noncoherent_unmap_sg(struct device *dev, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+ if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ dma_noncoherent_sync_sg_for_cpu(dev, sgl, nents, dir);
+}
+#endif
+
+const struct dma_map_ops dma_noncoherent_ops = {
+ .alloc = arch_dma_alloc,
+ .free = arch_dma_free,
+ .mmap = arch_dma_mmap,
+ .sync_single_for_device = dma_noncoherent_sync_single_for_device,
+ .sync_sg_for_device = dma_noncoherent_sync_sg_for_device,
+ .map_page = dma_noncoherent_map_page,
+ .map_sg = dma_noncoherent_map_sg,
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+ .sync_single_for_cpu = dma_noncoherent_sync_single_for_cpu,
+ .sync_sg_for_cpu = dma_noncoherent_sync_sg_for_cpu,
+ .unmap_page = dma_noncoherent_unmap_page,
+ .unmap_sg = dma_noncoherent_unmap_sg,
+#endif
+ .dma_supported = dma_direct_supported,
+ .mapping_error = dma_direct_mapping_error,
+ .cache_sync = arch_dma_cache_sync,
+};
+EXPORT_SYMBOL(dma_noncoherent_ops);
diff --git a/lib/errseq.c b/lib/errseq.c
index df78241..81f9e33 100644
--- a/lib/errseq.c
+++ b/lib/errseq.c
@@ -111,27 +111,22 @@ EXPORT_SYMBOL(errseq_set);
* errseq_sample() - Grab current errseq_t value.
* @eseq: Pointer to errseq_t to be sampled.
*
- * This function allows callers to sample an errseq_t value, marking it as
- * "seen" if required.
+ * This function allows callers to initialise their errseq_t variable.
+ * If the error has been "seen", new callers will not see an old error.
+ * If there is an unseen error in @eseq, the caller of this function will
+ * see it the next time it checks for an error.
*
+ * Context: Any context.
* Return: The current errseq value.
*/
errseq_t errseq_sample(errseq_t *eseq)
{
errseq_t old = READ_ONCE(*eseq);
- errseq_t new = old;
- /*
- * For the common case of no errors ever having been set, we can skip
- * marking the SEEN bit. Once an error has been set, the value will
- * never go back to zero.
- */
- if (old != 0) {
- new |= ERRSEQ_SEEN;
- if (old != new)
- cmpxchg(eseq, old, new);
- }
- return new;
+ /* If nobody has seen this error yet, then we can be the first. */
+ if (!(old & ERRSEQ_SEEN))
+ old = 0;
+ return old;
}
EXPORT_SYMBOL(errseq_sample);
diff --git a/lib/find_bit_benchmark.c b/lib/find_bit_benchmark.c
index 5985a25..5367ffa 100644
--- a/lib/find_bit_benchmark.c
+++ b/lib/find_bit_benchmark.c
@@ -132,7 +132,12 @@ static int __init find_bit_test(void)
test_find_next_bit(bitmap, BITMAP_LEN);
test_find_next_zero_bit(bitmap, BITMAP_LEN);
test_find_last_bit(bitmap, BITMAP_LEN);
- test_find_first_bit(bitmap, BITMAP_LEN);
+
+ /*
+ * test_find_first_bit() may take some time, so
+ * traverse only part of bitmap to avoid soft lockup.
+ */
+ test_find_first_bit(bitmap, BITMAP_LEN / 10);
test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN);
pr_err("\nStart testing find_bit() with sparse bitmap\n");
diff --git a/lib/iommu-helper.c b/lib/iommu-helper.c
index 23633c0..92a9f24 100644
--- a/lib/iommu-helper.c
+++ b/lib/iommu-helper.c
@@ -3,19 +3,8 @@
* IOMMU helper functions for the free area management
*/
-#include <linux/export.h>
#include <linux/bitmap.h>
-#include <linux/bug.h>
-
-int iommu_is_span_boundary(unsigned int index, unsigned int nr,
- unsigned long shift,
- unsigned long boundary_size)
-{
- BUG_ON(!is_power_of_2(boundary_size));
-
- shift = (shift + index) & (boundary_size - 1);
- return shift + nr > boundary_size;
-}
+#include <linux/iommu-helper.h>
unsigned long iommu_area_alloc(unsigned long *map, unsigned long size,
unsigned long start, unsigned int nr,
@@ -38,4 +27,3 @@ unsigned long iommu_area_alloc(unsigned long *map, unsigned long size,
}
return -1;
}
-EXPORT_SYMBOL(iommu_area_alloc);
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 9702126..7e43cd5 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -573,6 +573,67 @@ size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
}
EXPORT_SYMBOL(_copy_to_iter);
+#ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE
+static int copyout_mcsafe(void __user *to, const void *from, size_t n)
+{
+ if (access_ok(VERIFY_WRITE, to, n)) {
+ kasan_check_read(from, n);
+ n = copy_to_user_mcsafe((__force void *) to, from, n);
+ }
+ return n;
+}
+
+static unsigned long memcpy_mcsafe_to_page(struct page *page, size_t offset,
+ const char *from, size_t len)
+{
+ unsigned long ret;
+ char *to;
+
+ to = kmap_atomic(page);
+ ret = memcpy_mcsafe(to + offset, from, len);
+ kunmap_atomic(to);
+
+ return ret;
+}
+
+size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
+{
+ const char *from = addr;
+ unsigned long rem, curr_addr, s_addr = (unsigned long) addr;
+
+ if (unlikely(i->type & ITER_PIPE)) {
+ WARN_ON(1);
+ return 0;
+ }
+ if (iter_is_iovec(i))
+ might_fault();
+ iterate_and_advance(i, bytes, v,
+ copyout_mcsafe(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len),
+ ({
+ rem = memcpy_mcsafe_to_page(v.bv_page, v.bv_offset,
+ (from += v.bv_len) - v.bv_len, v.bv_len);
+ if (rem) {
+ curr_addr = (unsigned long) from;
+ bytes = curr_addr - s_addr - rem;
+ return bytes;
+ }
+ }),
+ ({
+ rem = memcpy_mcsafe(v.iov_base, (from += v.iov_len) - v.iov_len,
+ v.iov_len);
+ if (rem) {
+ curr_addr = (unsigned long) from;
+ bytes = curr_addr - s_addr - rem;
+ return bytes;
+ }
+ })
+ )
+
+ return bytes;
+}
+EXPORT_SYMBOL_GPL(_copy_to_iter_mcsafe);
+#endif /* CONFIG_ARCH_HAS_UACCESS_MCSAFE */
+
size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
{
char *to = addr;
@@ -1012,7 +1073,7 @@ unsigned long iov_iter_gap_alignment(const struct iov_iter *i)
}
EXPORT_SYMBOL(iov_iter_gap_alignment);
-static inline size_t __pipe_get_pages(struct iov_iter *i,
+static inline ssize_t __pipe_get_pages(struct iov_iter *i,
size_t maxsize,
struct page **pages,
int idx,
@@ -1102,7 +1163,7 @@ static ssize_t pipe_get_pages_alloc(struct iov_iter *i,
size_t *start)
{
struct page **p;
- size_t n;
+ ssize_t n;
int idx;
int npages;
diff --git a/lib/kobject.c b/lib/kobject.c
index e1d1f29..18989b5 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -233,13 +233,12 @@ static int kobject_add_internal(struct kobject *kobj)
/* be noisy on error issues */
if (error == -EEXIST)
- WARN(1,
- "%s failed for %s with -EEXIST, don't try to register things with the same name in the same directory.\n",
- __func__, kobject_name(kobj));
+ pr_err("%s failed for %s with -EEXIST, don't try to register things with the same name in the same directory.\n",
+ __func__, kobject_name(kobj));
else
- WARN(1, "%s failed for %s (error: %d parent: %s)\n",
- __func__, kobject_name(kobj), error,
- parent ? kobject_name(parent) : "'none'");
+ pr_err("%s failed for %s (error: %d parent: %s)\n",
+ __func__, kobject_name(kobj), error,
+ parent ? kobject_name(parent) : "'none'");
} else
kobj->state_in_sysfs = 1;
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index da9e10c..a9e41ae 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -1612,11 +1612,9 @@ static void set_iter_tags(struct radix_tree_iter *iter,
static void __rcu **skip_siblings(struct radix_tree_node **nodep,
void __rcu **slot, struct radix_tree_iter *iter)
{
- void *sib = node_to_entry(slot - 1);
-
while (iter->index < iter->next_index) {
*nodep = rcu_dereference_raw(*slot);
- if (*nodep && *nodep != sib)
+ if (*nodep && !is_sibling_entry(iter->node, *nodep))
return slot;
slot++;
iter->index = __radix_tree_iter_add(iter, 1);
@@ -1631,7 +1629,7 @@ void __rcu **__radix_tree_next_slot(void __rcu **slot,
struct radix_tree_iter *iter, unsigned flags)
{
unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK;
- struct radix_tree_node *node = rcu_dereference_raw(*slot);
+ struct radix_tree_node *node;
slot = skip_siblings(&node, slot, iter);
@@ -2036,10 +2034,12 @@ void *radix_tree_delete_item(struct radix_tree_root *root,
unsigned long index, void *item)
{
struct radix_tree_node *node = NULL;
- void __rcu **slot;
+ void __rcu **slot = NULL;
void *entry;
entry = __radix_tree_lookup(root, index, &node, &slot);
+ if (!slot)
+ return NULL;
if (!entry && (!is_idr(root) || node_tag_get(root, node, IDR_FREE,
get_slot_offset(node, slot))))
return NULL;
diff --git a/lib/reed_solomon/decode_rs.c b/lib/reed_solomon/decode_rs.c
index 0ec3f25..1db74eb 100644
--- a/lib/reed_solomon/decode_rs.c
+++ b/lib/reed_solomon/decode_rs.c
@@ -1,22 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * lib/reed_solomon/decode_rs.c
- *
- * Overview:
- * Generic Reed Solomon encoder / decoder library
+ * Generic Reed Solomon encoder / decoder library
*
* Copyright 2002, Phil Karn, KA9Q
* May be used under the terms of the GNU General Public License (GPL)
*
* Adaption to the kernel by Thomas Gleixner (tglx@linutronix.de)
*
- * $Id: decode_rs.c,v 1.7 2005/11/07 11:14:59 gleixner Exp $
- *
- */
-
-/* Generic data width independent code which is included by the
- * wrappers.
+ * Generic data width independent code which is included by the wrappers.
*/
{
+ struct rs_codec *rs = rsc->codec;
int deg_lambda, el, deg_omega;
int i, j, r, k, pad;
int nn = rs->nn;
@@ -27,16 +21,22 @@
uint16_t *alpha_to = rs->alpha_to;
uint16_t *index_of = rs->index_of;
uint16_t u, q, tmp, num1, num2, den, discr_r, syn_error;
- /* Err+Eras Locator poly and syndrome poly The maximum value
- * of nroots is 8. So the necessary stack size will be about
- * 220 bytes max.
- */
- uint16_t lambda[nroots + 1], syn[nroots];
- uint16_t b[nroots + 1], t[nroots + 1], omega[nroots + 1];
- uint16_t root[nroots], reg[nroots + 1], loc[nroots];
int count = 0;
uint16_t msk = (uint16_t) rs->nn;
+ /*
+ * The decoder buffers are in the rs control struct. They are
+ * arrays sized [nroots + 1]
+ */
+ uint16_t *lambda = rsc->buffers + RS_DECODE_LAMBDA * (nroots + 1);
+ uint16_t *syn = rsc->buffers + RS_DECODE_SYN * (nroots + 1);
+ uint16_t *b = rsc->buffers + RS_DECODE_B * (nroots + 1);
+ uint16_t *t = rsc->buffers + RS_DECODE_T * (nroots + 1);
+ uint16_t *omega = rsc->buffers + RS_DECODE_OMEGA * (nroots + 1);
+ uint16_t *root = rsc->buffers + RS_DECODE_ROOT * (nroots + 1);
+ uint16_t *reg = rsc->buffers + RS_DECODE_REG * (nroots + 1);
+ uint16_t *loc = rsc->buffers + RS_DECODE_LOC * (nroots + 1);
+
/* Check length parameter for validity */
pad = nn - nroots - len;
BUG_ON(pad < 0 || pad >= nn);
diff --git a/lib/reed_solomon/encode_rs.c b/lib/reed_solomon/encode_rs.c
index 0b5b1a6..9112d46 100644
--- a/lib/reed_solomon/encode_rs.c
+++ b/lib/reed_solomon/encode_rs.c
@@ -1,23 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * lib/reed_solomon/encode_rs.c
- *
- * Overview:
- * Generic Reed Solomon encoder / decoder library
+ * Generic Reed Solomon encoder / decoder library
*
* Copyright 2002, Phil Karn, KA9Q
* May be used under the terms of the GNU General Public License (GPL)
*
* Adaption to the kernel by Thomas Gleixner (tglx@linutronix.de)
*
- * $Id: encode_rs.c,v 1.5 2005/11/07 11:14:59 gleixner Exp $
- *
- */
-
-/* Generic data width independent code which is included by the
- * wrappers.
- * int encode_rsX (struct rs_control *rs, uintX_t *data, int len, uintY_t *par)
+ * Generic data width independent code which is included by the wrappers.
*/
{
+ struct rs_codec *rs = rsc->codec;
int i, j, pad;
int nn = rs->nn;
int nroots = rs->nroots;
diff --git a/lib/reed_solomon/reed_solomon.c b/lib/reed_solomon/reed_solomon.c
index 06d04cf..dfcf542 100644
--- a/lib/reed_solomon/reed_solomon.c
+++ b/lib/reed_solomon/reed_solomon.c
@@ -1,43 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * lib/reed_solomon/reed_solomon.c
- *
- * Overview:
- * Generic Reed Solomon encoder / decoder library
+ * Generic Reed Solomon encoder / decoder library
*
* Copyright (C) 2004 Thomas Gleixner (tglx@linutronix.de)
*
* Reed Solomon code lifted from reed solomon library written by Phil Karn
* Copyright 2002 Phil Karn, KA9Q
*
- * $Id: rslib.c,v 1.7 2005/11/07 11:14:59 gleixner Exp $
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
* Description:
*
* The generic Reed Solomon library provides runtime configurable
* encoding / decoding of RS codes.
- * Each user must call init_rs to get a pointer to a rs_control
- * structure for the given rs parameters. This structure is either
- * generated or a already available matching control structure is used.
- * If a structure is generated then the polynomial arrays for
- * fast encoding / decoding are built. This can take some time so
- * make sure not to call this function from a time critical path.
- * Usually a module / driver should initialize the necessary
- * rs_control structure on module / driver init and release it
- * on exit.
- * The encoding puts the calculated syndrome into a given syndrome
- * buffer.
- * The decoding is a two step process. The first step calculates
- * the syndrome over the received (data + syndrome) and calls the
- * second stage, which does the decoding / error correction itself.
- * Many hw encoders provide a syndrome calculation over the received
- * data + syndrome and can call the second stage directly.
*
+ * Each user must call init_rs to get a pointer to a rs_control structure
+ * for the given rs parameters. The control struct is unique per instance.
+ * It points to a codec which can be shared by multiple control structures.
+ * If a codec is newly allocated then the polynomial arrays for fast
+ * encoding / decoding are built. This can take some time so make sure not
+ * to call this function from a time critical path. Usually a module /
+ * driver should initialize the necessary rs_control structure on module /
+ * driver init and release it on exit.
+ *
+ * The encoding puts the calculated syndrome into a given syndrome buffer.
+ *
+ * The decoding is a two step process. The first step calculates the
+ * syndrome over the received (data + syndrome) and calls the second stage,
+ * which does the decoding / error correction itself. Many hw encoders
+ * provide a syndrome calculation over the received data + syndrome and can
+ * call the second stage directly.
*/
-
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/init.h>
@@ -46,32 +37,44 @@
#include <linux/slab.h>
#include <linux/mutex.h>
-/* This list holds all currently allocated rs control structures */
-static LIST_HEAD (rslist);
+enum {
+ RS_DECODE_LAMBDA,
+ RS_DECODE_SYN,
+ RS_DECODE_B,
+ RS_DECODE_T,
+ RS_DECODE_OMEGA,
+ RS_DECODE_ROOT,
+ RS_DECODE_REG,
+ RS_DECODE_LOC,
+ RS_DECODE_NUM_BUFFERS
+};
+
+/* This list holds all currently allocated rs codec structures */
+static LIST_HEAD(codec_list);
/* Protection for the list */
static DEFINE_MUTEX(rslistlock);
/**
- * rs_init - Initialize a Reed-Solomon codec
+ * codec_init - Initialize a Reed-Solomon codec
* @symsize: symbol size, bits (1-8)
* @gfpoly: Field generator polynomial coefficients
* @gffunc: Field generator function
* @fcr: first root of RS code generator polynomial, index form
* @prim: primitive element to generate polynomial roots
* @nroots: RS code generator polynomial degree (number of roots)
+ * @gfp: GFP_ flags for allocations
*
- * Allocate a control structure and the polynom arrays for faster
+ * Allocate a codec structure and the polynom arrays for faster
* en/decoding. Fill the arrays according to the given parameters.
*/
-static struct rs_control *rs_init(int symsize, int gfpoly, int (*gffunc)(int),
- int fcr, int prim, int nroots)
+static struct rs_codec *codec_init(int symsize, int gfpoly, int (*gffunc)(int),
+ int fcr, int prim, int nroots, gfp_t gfp)
{
- struct rs_control *rs;
int i, j, sr, root, iprim;
+ struct rs_codec *rs;
- /* Allocate the control structure */
- rs = kmalloc(sizeof (struct rs_control), GFP_KERNEL);
- if (rs == NULL)
+ rs = kzalloc(sizeof(*rs), gfp);
+ if (!rs)
return NULL;
INIT_LIST_HEAD(&rs->list);
@@ -85,17 +88,17 @@ static struct rs_control *rs_init(int symsize, int gfpoly, int (*gffunc)(int),
rs->gffunc = gffunc;
/* Allocate the arrays */
- rs->alpha_to = kmalloc(sizeof(uint16_t) * (rs->nn + 1), GFP_KERNEL);
+ rs->alpha_to = kmalloc(sizeof(uint16_t) * (rs->nn + 1), gfp);
if (rs->alpha_to == NULL)
- goto errrs;
+ goto err;
- rs->index_of = kmalloc(sizeof(uint16_t) * (rs->nn + 1), GFP_KERNEL);
+ rs->index_of = kmalloc(sizeof(uint16_t) * (rs->nn + 1), gfp);
if (rs->index_of == NULL)
- goto erralp;
+ goto err;
- rs->genpoly = kmalloc(sizeof(uint16_t) * (rs->nroots + 1), GFP_KERNEL);
+ rs->genpoly = kmalloc(sizeof(uint16_t) * (rs->nroots + 1), gfp);
if(rs->genpoly == NULL)
- goto erridx;
+ goto err;
/* Generate Galois field lookup tables */
rs->index_of[0] = rs->nn; /* log(zero) = -inf */
@@ -120,7 +123,7 @@ static struct rs_control *rs_init(int symsize, int gfpoly, int (*gffunc)(int),
}
/* If it's not primitive, exit */
if(sr != rs->alpha_to[0])
- goto errpol;
+ goto err;
/* Find prim-th root of 1, used in decoding */
for(iprim = 1; (iprim % prim) != 0; iprim += rs->nn);
@@ -148,42 +151,52 @@ static struct rs_control *rs_init(int symsize, int gfpoly, int (*gffunc)(int),
/* convert rs->genpoly[] to index form for quicker encoding */
for (i = 0; i <= nroots; i++)
rs->genpoly[i] = rs->index_of[rs->genpoly[i]];
+
+ rs->users = 1;
+ list_add(&rs->list, &codec_list);
return rs;
- /* Error exit */
-errpol:
+err:
kfree(rs->genpoly);
-erridx:
kfree(rs->index_of);
-erralp:
kfree(rs->alpha_to);
-errrs:
kfree(rs);
return NULL;
}
/**
- * free_rs - Free the rs control structure, if it is no longer used
- * @rs: the control structure which is not longer used by the
+ * free_rs - Free the rs control structure
+ * @rs: The control structure which is not longer used by the
* caller
+ *
+ * Free the control structure. If @rs is the last user of the associated
+ * codec, free the codec as well.
*/
void free_rs(struct rs_control *rs)
{
+ struct rs_codec *cd;
+
+ if (!rs)
+ return;
+
+ cd = rs->codec;
mutex_lock(&rslistlock);
- rs->users--;
- if(!rs->users) {
- list_del(&rs->list);
- kfree(rs->alpha_to);
- kfree(rs->index_of);
- kfree(rs->genpoly);
- kfree(rs);
+ cd->users--;
+ if(!cd->users) {
+ list_del(&cd->list);
+ kfree(cd->alpha_to);
+ kfree(cd->index_of);
+ kfree(cd->genpoly);
+ kfree(cd);
}
mutex_unlock(&rslistlock);
+ kfree(rs);
}
+EXPORT_SYMBOL_GPL(free_rs);
/**
- * init_rs_internal - Find a matching or allocate a new rs control structure
+ * init_rs_internal - Allocate rs control, find a matching codec or allocate a new one
* @symsize: the symbol size (number of bits)
* @gfpoly: the extended Galois field generator polynomial coefficients,
* with the 0th coefficient in the low order bit. The polynomial
@@ -191,55 +204,69 @@ void free_rs(struct rs_control *rs)
* @gffunc: pointer to function to generate the next field element,
* or the multiplicative identity element if given 0. Used
* instead of gfpoly if gfpoly is 0
- * @fcr: the first consecutive root of the rs code generator polynomial
+ * @fcr: the first consecutive root of the rs code generator polynomial
* in index form
* @prim: primitive element to generate polynomial roots
* @nroots: RS code generator polynomial degree (number of roots)
+ * @gfp: GFP_ flags for allocations
*/
static struct rs_control *init_rs_internal(int symsize, int gfpoly,
- int (*gffunc)(int), int fcr,
- int prim, int nroots)
+ int (*gffunc)(int), int fcr,
+ int prim, int nroots, gfp_t gfp)
{
- struct list_head *tmp;
- struct rs_control *rs;
+ struct list_head *tmp;
+ struct rs_control *rs;
+ unsigned int bsize;
/* Sanity checks */
if (symsize < 1)
return NULL;
if (fcr < 0 || fcr >= (1<<symsize))
- return NULL;
+ return NULL;
if (prim <= 0 || prim >= (1<<symsize))
- return NULL;
+ return NULL;
if (nroots < 0 || nroots >= (1<<symsize))
return NULL;
+ /*
+ * The decoder needs buffers in each control struct instance to
+ * avoid variable size or large fixed size allocations on
+ * stack. Size the buffers to arrays of [nroots + 1].
+ */
+ bsize = sizeof(uint16_t) * RS_DECODE_NUM_BUFFERS * (nroots + 1);
+ rs = kzalloc(sizeof(*rs) + bsize, gfp);
+ if (!rs)
+ return NULL;
+
mutex_lock(&rslistlock);
/* Walk through the list and look for a matching entry */
- list_for_each(tmp, &rslist) {
- rs = list_entry(tmp, struct rs_control, list);
- if (symsize != rs->mm)
+ list_for_each(tmp, &codec_list) {
+ struct rs_codec *cd = list_entry(tmp, struct rs_codec, list);
+
+ if (symsize != cd->mm)
continue;
- if (gfpoly != rs->gfpoly)
+ if (gfpoly != cd->gfpoly)
continue;
- if (gffunc != rs->gffunc)
+ if (gffunc != cd->gffunc)
continue;
- if (fcr != rs->fcr)
+ if (fcr != cd->fcr)
continue;
- if (prim != rs->prim)
+ if (prim != cd->prim)
continue;
- if (nroots != rs->nroots)
+ if (nroots != cd->nroots)
continue;
/* We have a matching one already */
- rs->users++;
+ cd->users++;
+ rs->codec = cd;
goto out;
}
/* Create a new one */
- rs = rs_init(symsize, gfpoly, gffunc, fcr, prim, nroots);
- if (rs) {
- rs->users = 1;
- list_add(&rs->list, &rslist);
+ rs->codec = codec_init(symsize, gfpoly, gffunc, fcr, prim, nroots, gfp);
+ if (!rs->codec) {
+ kfree(rs);
+ rs = NULL;
}
out:
mutex_unlock(&rslistlock);
@@ -247,45 +274,48 @@ static struct rs_control *init_rs_internal(int symsize, int gfpoly,
}
/**
- * init_rs - Find a matching or allocate a new rs control structure
+ * init_rs_gfp - Create a RS control struct and initialize it
* @symsize: the symbol size (number of bits)
* @gfpoly: the extended Galois field generator polynomial coefficients,
* with the 0th coefficient in the low order bit. The polynomial
* must be primitive;
- * @fcr: the first consecutive root of the rs code generator polynomial
+ * @fcr: the first consecutive root of the rs code generator polynomial
* in index form
* @prim: primitive element to generate polynomial roots
* @nroots: RS code generator polynomial degree (number of roots)
+ * @gfp: GFP_ flags for allocations
*/
-struct rs_control *init_rs(int symsize, int gfpoly, int fcr, int prim,
- int nroots)
+struct rs_control *init_rs_gfp(int symsize, int gfpoly, int fcr, int prim,
+ int nroots, gfp_t gfp)
{
- return init_rs_internal(symsize, gfpoly, NULL, fcr, prim, nroots);
+ return init_rs_internal(symsize, gfpoly, NULL, fcr, prim, nroots, gfp);
}
+EXPORT_SYMBOL_GPL(init_rs_gfp);
/**
- * init_rs_non_canonical - Find a matching or allocate a new rs control
- * structure, for fields with non-canonical
- * representation
+ * init_rs_non_canonical - Allocate rs control struct for fields with
+ * non-canonical representation
* @symsize: the symbol size (number of bits)
* @gffunc: pointer to function to generate the next field element,
* or the multiplicative identity element if given 0. Used
* instead of gfpoly if gfpoly is 0
- * @fcr: the first consecutive root of the rs code generator polynomial
+ * @fcr: the first consecutive root of the rs code generator polynomial
* in index form
* @prim: primitive element to generate polynomial roots
* @nroots: RS code generator polynomial degree (number of roots)
*/
struct rs_control *init_rs_non_canonical(int symsize, int (*gffunc)(int),
- int fcr, int prim, int nroots)
+ int fcr, int prim, int nroots)
{
- return init_rs_internal(symsize, 0, gffunc, fcr, prim, nroots);
+ return init_rs_internal(symsize, 0, gffunc, fcr, prim, nroots,
+ GFP_KERNEL);
}
+EXPORT_SYMBOL_GPL(init_rs_non_canonical);
#ifdef CONFIG_REED_SOLOMON_ENC8
/**
* encode_rs8 - Calculate the parity for data values (8bit data width)
- * @rs: the rs control structure
+ * @rsc: the rs control structure
* @data: data field of a given type
* @len: data length
* @par: parity data, must be initialized by caller (usually all 0)
@@ -295,7 +325,7 @@ struct rs_control *init_rs_non_canonical(int symsize, int (*gffunc)(int),
* symbol size > 8. The calling code must take care of encoding of the
* syndrome result for storage itself.
*/
-int encode_rs8(struct rs_control *rs, uint8_t *data, int len, uint16_t *par,
+int encode_rs8(struct rs_control *rsc, uint8_t *data, int len, uint16_t *par,
uint16_t invmsk)
{
#include "encode_rs.c"
@@ -306,7 +336,7 @@ EXPORT_SYMBOL_GPL(encode_rs8);
#ifdef CONFIG_REED_SOLOMON_DEC8
/**
* decode_rs8 - Decode codeword (8bit data width)
- * @rs: the rs control structure
+ * @rsc: the rs control structure
* @data: data field of a given type
* @par: received parity data field
* @len: data length
@@ -319,9 +349,14 @@ EXPORT_SYMBOL_GPL(encode_rs8);
* The syndrome and parity uses a uint16_t data type to enable
* symbol size > 8. The calling code must take care of decoding of the
* syndrome result and the received parity before calling this code.
+ *
+ * Note: The rs_control struct @rsc contains buffers which are used for
+ * decoding, so the caller has to ensure that decoder invocations are
+ * serialized.
+ *
* Returns the number of corrected bits or -EBADMSG for uncorrectable errors.
*/
-int decode_rs8(struct rs_control *rs, uint8_t *data, uint16_t *par, int len,
+int decode_rs8(struct rs_control *rsc, uint8_t *data, uint16_t *par, int len,
uint16_t *s, int no_eras, int *eras_pos, uint16_t invmsk,
uint16_t *corr)
{
@@ -333,7 +368,7 @@ EXPORT_SYMBOL_GPL(decode_rs8);
#ifdef CONFIG_REED_SOLOMON_ENC16
/**
* encode_rs16 - Calculate the parity for data values (16bit data width)
- * @rs: the rs control structure
+ * @rsc: the rs control structure
* @data: data field of a given type
* @len: data length
* @par: parity data, must be initialized by caller (usually all 0)
@@ -341,7 +376,7 @@ EXPORT_SYMBOL_GPL(decode_rs8);
*
* Each field in the data array contains up to symbol size bits of valid data.
*/
-int encode_rs16(struct rs_control *rs, uint16_t *data, int len, uint16_t *par,
+int encode_rs16(struct rs_control *rsc, uint16_t *data, int len, uint16_t *par,
uint16_t invmsk)
{
#include "encode_rs.c"
@@ -352,7 +387,7 @@ EXPORT_SYMBOL_GPL(encode_rs16);
#ifdef CONFIG_REED_SOLOMON_DEC16
/**
* decode_rs16 - Decode codeword (16bit data width)
- * @rs: the rs control structure
+ * @rsc: the rs control structure
* @data: data field of a given type
* @par: received parity data field
* @len: data length
@@ -363,9 +398,14 @@ EXPORT_SYMBOL_GPL(encode_rs16);
* @corr: buffer to store correction bitmask on eras_pos
*
* Each field in the data array contains up to symbol size bits of valid data.
+ *
+ * Note: The rc_control struct @rsc contains buffers which are used for
+ * decoding, so the caller has to ensure that decoder invocations are
+ * serialized.
+ *
* Returns the number of corrected bits or -EBADMSG for uncorrectable errors.
*/
-int decode_rs16(struct rs_control *rs, uint16_t *data, uint16_t *par, int len,
+int decode_rs16(struct rs_control *rsc, uint16_t *data, uint16_t *par, int len,
uint16_t *s, int no_eras, int *eras_pos, uint16_t invmsk,
uint16_t *corr)
{
@@ -374,10 +414,6 @@ int decode_rs16(struct rs_control *rs, uint16_t *data, uint16_t *par, int len,
EXPORT_SYMBOL_GPL(decode_rs16);
#endif
-EXPORT_SYMBOL_GPL(init_rs);
-EXPORT_SYMBOL_GPL(init_rs_non_canonical);
-EXPORT_SYMBOL_GPL(free_rs);
-
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Reed Solomon encoder/decoder");
MODULE_AUTHOR("Phil Karn, Thomas Gleixner");
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index e6a9c06e..6fdc626 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -270,18 +270,33 @@ void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m)
}
EXPORT_SYMBOL_GPL(sbitmap_bitmap_show);
-static unsigned int sbq_calc_wake_batch(unsigned int depth)
+static unsigned int sbq_calc_wake_batch(struct sbitmap_queue *sbq,
+ unsigned int depth)
{
unsigned int wake_batch;
+ unsigned int shallow_depth;
/*
* For each batch, we wake up one queue. We need to make sure that our
- * batch size is small enough that the full depth of the bitmap is
- * enough to wake up all of the queues.
+ * batch size is small enough that the full depth of the bitmap,
+ * potentially limited by a shallow depth, is enough to wake up all of
+ * the queues.
+ *
+ * Each full word of the bitmap has bits_per_word bits, and there might
+ * be a partial word. There are depth / bits_per_word full words and
+ * depth % bits_per_word bits left over. In bitwise arithmetic:
+ *
+ * bits_per_word = 1 << shift
+ * depth / bits_per_word = depth >> shift
+ * depth % bits_per_word = depth & ((1 << shift) - 1)
+ *
+ * Each word can be limited to sbq->min_shallow_depth bits.
*/
- wake_batch = SBQ_WAKE_BATCH;
- if (wake_batch > depth / SBQ_WAIT_QUEUES)
- wake_batch = max(1U, depth / SBQ_WAIT_QUEUES);
+ shallow_depth = min(1U << sbq->sb.shift, sbq->min_shallow_depth);
+ depth = ((depth >> sbq->sb.shift) * shallow_depth +
+ min(depth & ((1U << sbq->sb.shift) - 1), shallow_depth));
+ wake_batch = clamp_t(unsigned int, depth / SBQ_WAIT_QUEUES, 1,
+ SBQ_WAKE_BATCH);
return wake_batch;
}
@@ -307,7 +322,8 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
*per_cpu_ptr(sbq->alloc_hint, i) = prandom_u32() % depth;
}
- sbq->wake_batch = sbq_calc_wake_batch(depth);
+ sbq->min_shallow_depth = UINT_MAX;
+ sbq->wake_batch = sbq_calc_wake_batch(sbq, depth);
atomic_set(&sbq->wake_index, 0);
sbq->ws = kzalloc_node(SBQ_WAIT_QUEUES * sizeof(*sbq->ws), flags, node);
@@ -327,21 +343,28 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
}
EXPORT_SYMBOL_GPL(sbitmap_queue_init_node);
-void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth)
+static void sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq,
+ unsigned int depth)
{
- unsigned int wake_batch = sbq_calc_wake_batch(depth);
+ unsigned int wake_batch = sbq_calc_wake_batch(sbq, depth);
int i;
if (sbq->wake_batch != wake_batch) {
WRITE_ONCE(sbq->wake_batch, wake_batch);
/*
- * Pairs with the memory barrier in sbq_wake_up() to ensure that
- * the batch size is updated before the wait counts.
+ * Pairs with the memory barrier in sbitmap_queue_wake_up()
+ * to ensure that the batch size is updated before the wait
+ * counts.
*/
smp_mb__before_atomic();
for (i = 0; i < SBQ_WAIT_QUEUES; i++)
atomic_set(&sbq->ws[i].wait_cnt, 1);
}
+}
+
+void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth)
+{
+ sbitmap_queue_update_wake_batch(sbq, depth);
sbitmap_resize(&sbq->sb, depth);
}
EXPORT_SYMBOL_GPL(sbitmap_queue_resize);
@@ -380,6 +403,8 @@ int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
unsigned int hint, depth;
int nr;
+ WARN_ON_ONCE(shallow_depth < sbq->min_shallow_depth);
+
hint = this_cpu_read(*sbq->alloc_hint);
depth = READ_ONCE(sbq->sb.depth);
if (unlikely(hint >= depth)) {
@@ -403,6 +428,14 @@ int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
}
EXPORT_SYMBOL_GPL(__sbitmap_queue_get_shallow);
+void sbitmap_queue_min_shallow_depth(struct sbitmap_queue *sbq,
+ unsigned int min_shallow_depth)
+{
+ sbq->min_shallow_depth = min_shallow_depth;
+ sbitmap_queue_update_wake_batch(sbq, sbq->sb.depth);
+}
+EXPORT_SYMBOL_GPL(sbitmap_queue_min_shallow_depth);
+
static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq)
{
int i, wake_index;
@@ -425,52 +458,67 @@ static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq)
return NULL;
}
-static void sbq_wake_up(struct sbitmap_queue *sbq)
+static bool __sbq_wake_up(struct sbitmap_queue *sbq)
{
struct sbq_wait_state *ws;
unsigned int wake_batch;
int wait_cnt;
- /*
- * Pairs with the memory barrier in set_current_state() to ensure the
- * proper ordering of clear_bit()/waitqueue_active() in the waker and
- * test_and_set_bit_lock()/prepare_to_wait()/finish_wait() in the
- * waiter. See the comment on waitqueue_active(). This is __after_atomic
- * because we just did clear_bit_unlock() in the caller.
- */
- smp_mb__after_atomic();
-
ws = sbq_wake_ptr(sbq);
if (!ws)
- return;
+ return false;
wait_cnt = atomic_dec_return(&ws->wait_cnt);
if (wait_cnt <= 0) {
+ int ret;
+
wake_batch = READ_ONCE(sbq->wake_batch);
+
/*
* Pairs with the memory barrier in sbitmap_queue_resize() to
* ensure that we see the batch size update before the wait
* count is reset.
*/
smp_mb__before_atomic();
+
/*
- * If there are concurrent callers to sbq_wake_up(), the last
- * one to decrement the wait count below zero will bump it back
- * up. If there is a concurrent resize, the count reset will
- * either cause the cmpxchg to fail or overwrite after the
- * cmpxchg.
+ * For concurrent callers of this, the one that failed the
+ * atomic_cmpxhcg() race should call this function again
+ * to wakeup a new batch on a different 'ws'.
*/
- atomic_cmpxchg(&ws->wait_cnt, wait_cnt, wait_cnt + wake_batch);
- sbq_index_atomic_inc(&sbq->wake_index);
- wake_up_nr(&ws->wait, wake_batch);
+ ret = atomic_cmpxchg(&ws->wait_cnt, wait_cnt, wake_batch);
+ if (ret == wait_cnt) {
+ sbq_index_atomic_inc(&sbq->wake_index);
+ wake_up_nr(&ws->wait, wake_batch);
+ return false;
+ }
+
+ return true;
}
+
+ return false;
}
+void sbitmap_queue_wake_up(struct sbitmap_queue *sbq)
+{
+ while (__sbq_wake_up(sbq))
+ ;
+}
+EXPORT_SYMBOL_GPL(sbitmap_queue_wake_up);
+
void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,
unsigned int cpu)
{
sbitmap_clear_bit_unlock(&sbq->sb, nr);
- sbq_wake_up(sbq);
+ /*
+ * Pairs with the memory barrier in set_current_state() to ensure the
+ * proper ordering of clear_bit_unlock()/waitqueue_active() in the waker
+ * and test_and_set_bit_lock()/prepare_to_wait()/finish_wait() in the
+ * waiter. See the comment on waitqueue_active().
+ */
+ smp_mb__after_atomic();
+ sbitmap_queue_wake_up(sbq);
+
if (likely(!sbq->round_robin && nr < sbq->sb.depth))
*per_cpu_ptr(sbq->alloc_hint, cpu) = nr;
}
@@ -482,7 +530,7 @@ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq)
/*
* Pairs with the memory barrier in set_current_state() like in
- * sbq_wake_up().
+ * sbitmap_queue_wake_up().
*/
smp_mb();
wake_index = atomic_read(&sbq->wake_index);
@@ -528,5 +576,6 @@ void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m)
seq_puts(m, "}\n");
seq_printf(m, "round_robin=%d\n", sbq->round_robin);
+ seq_printf(m, "min_shallow_depth=%u\n", sbq->min_shallow_depth);
}
EXPORT_SYMBOL_GPL(sbitmap_queue_show);
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index fece575..04b68d9 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -593,9 +593,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
}
/*
- * Allocates bounce buffer and returns its kernel virtual address.
+ * Allocates bounce buffer and returns its physical address.
*/
-
static phys_addr_t
map_single(struct device *hwdev, phys_addr_t phys, size_t size,
enum dma_data_direction dir, unsigned long attrs)
@@ -614,7 +613,7 @@ map_single(struct device *hwdev, phys_addr_t phys, size_t size,
}
/*
- * dma_addr is the kernel virtual address of the bounce buffer to unmap.
+ * tlb_addr is the physical address of the bounce buffer to unmap.
*/
void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
size_t size, enum dma_data_direction dir,
@@ -692,7 +691,6 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
}
}
-#ifdef CONFIG_DMA_DIRECT_OPS
static inline bool dma_coherent_ok(struct device *dev, dma_addr_t addr,
size_t size)
{
@@ -714,7 +712,7 @@ swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle,
phys_addr = swiotlb_tbl_map_single(dev,
__phys_to_dma(dev, io_tlb_start),
- 0, size, DMA_FROM_DEVICE, 0);
+ 0, size, DMA_FROM_DEVICE, attrs);
if (phys_addr == SWIOTLB_MAP_ERROR)
goto out_warn;
@@ -727,7 +725,7 @@ swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle,
out_unmap:
dev_warn(dev, "hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
- (unsigned long long)(dev ? dev->coherent_dma_mask : 0),
+ (unsigned long long)dev->coherent_dma_mask,
(unsigned long long)*dma_handle);
/*
@@ -737,7 +735,7 @@ swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle,
swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE,
DMA_ATTR_SKIP_CPU_SYNC);
out_warn:
- if ((attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) {
+ if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) {
dev_warn(dev,
"swiotlb: coherent allocation failed, size=%zu\n",
size);
@@ -764,7 +762,6 @@ static bool swiotlb_free_buffer(struct device *dev, size_t size,
DMA_ATTR_SKIP_CPU_SYNC);
return true;
}
-#endif
static void
swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir,
@@ -1045,7 +1042,6 @@ swiotlb_dma_supported(struct device *hwdev, u64 mask)
return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
}
-#ifdef CONFIG_DMA_DIRECT_OPS
void *swiotlb_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
gfp_t gfp, unsigned long attrs)
{
@@ -1089,4 +1085,3 @@ const struct dma_map_ops swiotlb_dma_ops = {
.unmap_page = swiotlb_unmap_page,
.dma_supported = dma_direct_supported,
};
-#endif /* CONFIG_DMA_DIRECT_OPS */
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index de16f78..6cd7d07 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -331,23 +331,32 @@ static void noinline __init test_mem_optimisations(void)
unsigned int start, nbits;
for (start = 0; start < 1024; start += 8) {
- memset(bmap1, 0x5a, sizeof(bmap1));
- memset(bmap2, 0x5a, sizeof(bmap2));
for (nbits = 0; nbits < 1024 - start; nbits += 8) {
+ memset(bmap1, 0x5a, sizeof(bmap1));
+ memset(bmap2, 0x5a, sizeof(bmap2));
+
bitmap_set(bmap1, start, nbits);
__bitmap_set(bmap2, start, nbits);
- if (!bitmap_equal(bmap1, bmap2, 1024))
+ if (!bitmap_equal(bmap1, bmap2, 1024)) {
printk("set not equal %d %d\n", start, nbits);
- if (!__bitmap_equal(bmap1, bmap2, 1024))
+ failed_tests++;
+ }
+ if (!__bitmap_equal(bmap1, bmap2, 1024)) {
printk("set not __equal %d %d\n", start, nbits);
+ failed_tests++;
+ }
bitmap_clear(bmap1, start, nbits);
__bitmap_clear(bmap2, start, nbits);
- if (!bitmap_equal(bmap1, bmap2, 1024))
+ if (!bitmap_equal(bmap1, bmap2, 1024)) {
printk("clear not equal %d %d\n", start, nbits);
- if (!__bitmap_equal(bmap1, bmap2, 1024))
+ failed_tests++;
+ }
+ if (!__bitmap_equal(bmap1, bmap2, 1024)) {
printk("clear not __equal %d %d\n", start,
nbits);
+ failed_tests++;
+ }
}
}
}
diff --git a/lib/textsearch.c b/lib/textsearch.c
index 0b79908..5939549 100644
--- a/lib/textsearch.c
+++ b/lib/textsearch.c
@@ -10,7 +10,10 @@
* Pablo Neira Ayuso <pablo@netfilter.org>
*
* ==========================================================================
- *
+ */
+
+/**
+ * DOC: ts_intro
* INTRODUCTION
*
* The textsearch infrastructure provides text searching facilities for
@@ -19,7 +22,9 @@
*
* ARCHITECTURE
*
- * User
+ * .. code-block:: none
+ *
+ * User
* +----------------+
* | finish()|<--------------(6)-----------------+
* |get_next_block()|<--------------(5)---------------+ |
@@ -33,21 +38,21 @@
* | (3)|----->| find()/next() |-----------+ |
* | (7)|----->| destroy() |----------------------+
* +----------------+ +---------------+
- *
- * (1) User configures a search by calling _prepare() specifying the
- * search parameters such as the pattern and algorithm name.
+ *
+ * (1) User configures a search by calling textsearch_prepare() specifying
+ * the search parameters such as the pattern and algorithm name.
* (2) Core requests the algorithm to allocate and initialize a search
* configuration according to the specified parameters.
- * (3) User starts the search(es) by calling _find() or _next() to
- * fetch subsequent occurrences. A state variable is provided
- * to the algorithm to store persistent variables.
+ * (3) User starts the search(es) by calling textsearch_find() or
+ * textsearch_next() to fetch subsequent occurrences. A state variable
+ * is provided to the algorithm to store persistent variables.
* (4) Core eventually resets the search offset and forwards the find()
* request to the algorithm.
* (5) Algorithm calls get_next_block() provided by the user continuously
* to fetch the data to be searched in block by block.
* (6) Algorithm invokes finish() after the last call to get_next_block
* to clean up any leftovers from get_next_block. (Optional)
- * (7) User destroys the configuration by calling _destroy().
+ * (7) User destroys the configuration by calling textsearch_destroy().
* (8) Core notifies the algorithm to destroy algorithm specific
* allocations. (Optional)
*
@@ -62,9 +67,10 @@
* amount of times and even in parallel as long as a separate struct
* ts_state variable is provided to every instance.
*
- * The actual search is performed by either calling textsearch_find_-
- * continuous() for linear data or by providing an own get_next_block()
- * implementation and calling textsearch_find(). Both functions return
+ * The actual search is performed by either calling
+ * textsearch_find_continuous() for linear data or by providing
+ * an own get_next_block() implementation and
+ * calling textsearch_find(). Both functions return
* the position of the first occurrence of the pattern or UINT_MAX if
* no match was found. Subsequent occurrences can be found by calling
* textsearch_next() regardless of the linearity of the data.
@@ -72,7 +78,7 @@
* Once you're done using a configuration it must be given back via
* textsearch_destroy.
*
- * EXAMPLE
+ * EXAMPLE::
*
* int pos;
* struct ts_config *conf;
@@ -87,13 +93,13 @@
* goto errout;
* }
*
- * pos = textsearch_find_continuous(conf, &state, example, strlen(example));
+ * pos = textsearch_find_continuous(conf, \&state, example, strlen(example));
* if (pos != UINT_MAX)
- * panic("Oh my god, dancing chickens at %d\n", pos);
+ * panic("Oh my god, dancing chickens at \%d\n", pos);
*
* textsearch_destroy(conf);
- * ==========================================================================
*/
+/* ========================================================================== */
#include <linux/module.h>
#include <linux/types.h>
@@ -225,7 +231,7 @@ static unsigned int get_linear_data(unsigned int consumed, const u8 **dst,
*
* Returns the position of first occurrence of the pattern or
* %UINT_MAX if no occurrence was found.
- */
+ */
unsigned int textsearch_find_continuous(struct ts_config *conf,
struct ts_state *state,
const void *data, unsigned int len)
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 30c0cb8..23920c5 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -1669,19 +1669,22 @@ char *pointer_string(char *buf, char *end, const void *ptr,
return number(buf, end, (unsigned long int)ptr, spec);
}
-static bool have_filled_random_ptr_key __read_mostly;
+static DEFINE_STATIC_KEY_TRUE(not_filled_random_ptr_key);
static siphash_key_t ptr_key __read_mostly;
+static void enable_ptr_key_workfn(struct work_struct *work)
+{
+ get_random_bytes(&ptr_key, sizeof(ptr_key));
+ /* Needs to run from preemptible context */
+ static_branch_disable(¬_filled_random_ptr_key);
+}
+
+static DECLARE_WORK(enable_ptr_key_work, enable_ptr_key_workfn);
+
static void fill_random_ptr_key(struct random_ready_callback *unused)
{
- get_random_bytes(&ptr_key, sizeof(ptr_key));
- /*
- * have_filled_random_ptr_key==true is dependent on get_random_bytes().
- * ptr_to_id() needs to see have_filled_random_ptr_key==true
- * after get_random_bytes() returns.
- */
- smp_mb();
- WRITE_ONCE(have_filled_random_ptr_key, true);
+ /* This may be in an interrupt handler. */
+ queue_work(system_unbound_wq, &enable_ptr_key_work);
}
static struct random_ready_callback random_ready = {
@@ -1695,7 +1698,8 @@ static int __init initialize_ptr_random(void)
if (!ret) {
return 0;
} else if (ret == -EALREADY) {
- fill_random_ptr_key(&random_ready);
+ /* This is in preemptible context */
+ enable_ptr_key_workfn(&enable_ptr_key_work);
return 0;
}
@@ -1709,7 +1713,7 @@ static char *ptr_to_id(char *buf, char *end, void *ptr, struct printf_spec spec)
unsigned long hashval;
const int default_width = 2 * sizeof(ptr);
- if (unlikely(!have_filled_random_ptr_key)) {
+ if (static_branch_unlikely(¬_filled_random_ptr_key)) {
spec.field_width = default_width;
/* string length must be less than default_width */
return string(buf, end, "(ptrval)", spec);
diff --git a/mm/Kconfig b/mm/Kconfig
index d5004d8..3e0b6e8 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -266,7 +266,7 @@
bool
config PHYS_ADDR_T_64BIT
- def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT
+ def_bool 64BIT
config BOUNCE
bool "Enable bounce buffers"
@@ -305,7 +305,7 @@
the many instances by a single page with that content, so
saving memory until one or another app needs to modify the content.
Recommended for use with KVM, or with other duplicative applications.
- See Documentation/vm/ksm.txt for more information: KSM is inactive
+ See Documentation/vm/ksm.rst for more information: KSM is inactive
until a program has madvised that an area is MADV_MERGEABLE, and
root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
@@ -530,7 +530,7 @@
into a page just as regular dirty bit, but unlike the latter
it can be cleared by hands.
- See Documentation/vm/soft-dirty.txt for more details.
+ See Documentation/admin-guide/mm/soft-dirty.rst for more details.
config ZSWAP
bool "Compressed cache for swap pages (EXPERIMENTAL)"
@@ -636,6 +636,7 @@
default n
depends on NO_BOOTMEM
depends on !FLATMEM
+ depends on !NEED_PER_CPU_KM
help
Ordinarily all struct pages are initialised during early boot in a
single thread. On very large machines this can take a considerable
@@ -656,7 +657,8 @@
be useful to tune memory cgroup limits and/or for job placement
within a compute cluster.
- See Documentation/vm/idle_page_tracking.txt for more details.
+ See Documentation/admin-guide/mm/idle_page_tracking.rst for
+ more details.
# arch_add_memory() comprehends device memory
config ARCH_HAS_ZONE_DEVICE
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 023190c..8fe3ebd 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -115,6 +115,7 @@ static int bdi_debug_register(struct backing_dev_info *bdi, const char *name)
bdi, &bdi_debug_stats_fops);
if (!bdi->debug_stats) {
debugfs_remove(bdi->debug_dir);
+ bdi->debug_dir = NULL;
return -ENOMEM;
}
@@ -383,7 +384,7 @@ static void wb_shutdown(struct bdi_writeback *wb)
* the barrier provided by test_and_clear_bit() above.
*/
smp_wmb();
- clear_bit(WB_shutting_down, &wb->state);
+ clear_and_wake_up_bit(WB_shutting_down, &wb->state);
}
static void wb_exit(struct bdi_writeback *wb)
@@ -411,6 +412,7 @@ static void wb_exit(struct bdi_writeback *wb)
* protected.
*/
static DEFINE_SPINLOCK(cgwb_lock);
+static struct workqueue_struct *cgwb_release_wq;
/**
* wb_congested_get_create - get or create a wb_congested
@@ -521,7 +523,7 @@ static void cgwb_release(struct percpu_ref *refcnt)
{
struct bdi_writeback *wb = container_of(refcnt, struct bdi_writeback,
refcnt);
- schedule_work(&wb->release_work);
+ queue_work(cgwb_release_wq, &wb->release_work);
}
static void cgwb_kill(struct bdi_writeback *wb)
@@ -783,6 +785,21 @@ static void cgwb_bdi_register(struct backing_dev_info *bdi)
spin_unlock_irq(&cgwb_lock);
}
+static int __init cgwb_init(void)
+{
+ /*
+ * There can be many concurrent release work items overwhelming
+ * system_wq. Put them in a separate wq and limit concurrency.
+ * There's no point in executing many of these in parallel.
+ */
+ cgwb_release_wq = alloc_workqueue("cgwb_release", 0, 1);
+ if (!cgwb_release_wq)
+ return -ENOMEM;
+
+ return 0;
+}
+subsys_initcall(cgwb_init);
+
#else /* CONFIG_CGROUP_WRITEBACK */
static int cgwb_bdi_init(struct backing_dev_info *bdi)
diff --git a/mm/cleancache.c b/mm/cleancache.c
index f7b9fdc..126548b5 100644
--- a/mm/cleancache.c
+++ b/mm/cleancache.c
@@ -3,7 +3,7 @@
*
* This code provides the generic "frontend" layer to call a matching
* "backend" driver implementation of cleancache. See
- * Documentation/vm/cleancache.txt for more information.
+ * Documentation/vm/cleancache.rst for more information.
*
* Copyright (C) 2009-2010 Oracle Corp. All rights reserved.
* Author: Dan Magenheimer
diff --git a/mm/cma.c b/mm/cma.c
index aa40e6c..5809bbe 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -39,7 +39,6 @@
#include <trace/events/cma.h>
#include "cma.h"
-#include "internal.h"
struct cma cma_areas[MAX_CMA_AREAS];
unsigned cma_area_count;
@@ -110,25 +109,23 @@ static int __init cma_activate_area(struct cma *cma)
if (!cma->bitmap)
return -ENOMEM;
+ WARN_ON_ONCE(!pfn_valid(pfn));
+ zone = page_zone(pfn_to_page(pfn));
+
do {
unsigned j;
base_pfn = pfn;
- if (!pfn_valid(base_pfn))
- goto err;
-
- zone = page_zone(pfn_to_page(base_pfn));
for (j = pageblock_nr_pages; j; --j, pfn++) {
- if (!pfn_valid(pfn))
- goto err;
-
+ WARN_ON_ONCE(!pfn_valid(pfn));
/*
- * In init_cma_reserved_pageblock(), present_pages
- * is adjusted with assumption that all pages in
- * the pageblock come from a single zone.
+ * alloc_contig_range requires the pfn range
+ * specified to be in the same zone. Make this
+ * simple by forcing the entire CMA resv range
+ * to be in the same zone.
*/
if (page_zone(pfn_to_page(pfn)) != zone)
- goto err;
+ goto not_in_zone;
}
init_cma_reserved_pageblock(pfn_to_page(base_pfn));
} while (--i);
@@ -142,7 +139,7 @@ static int __init cma_activate_area(struct cma *cma)
return 0;
-err:
+not_in_zone:
pr_err("CMA area %s could not be activated\n", cma->name);
kfree(cma->bitmap);
cma->count = 0;
@@ -152,41 +149,6 @@ static int __init cma_activate_area(struct cma *cma)
static int __init cma_init_reserved_areas(void)
{
int i;
- struct zone *zone;
- pg_data_t *pgdat;
-
- if (!cma_area_count)
- return 0;
-
- for_each_online_pgdat(pgdat) {
- unsigned long start_pfn = UINT_MAX, end_pfn = 0;
-
- zone = &pgdat->node_zones[ZONE_MOVABLE];
-
- /*
- * In this case, we cannot adjust the zone range
- * since it is now maximum node span and we don't
- * know original zone range.
- */
- if (populated_zone(zone))
- continue;
-
- for (i = 0; i < cma_area_count; i++) {
- if (pfn_to_nid(cma_areas[i].base_pfn) !=
- pgdat->node_id)
- continue;
-
- start_pfn = min(start_pfn, cma_areas[i].base_pfn);
- end_pfn = max(end_pfn, cma_areas[i].base_pfn +
- cma_areas[i].count);
- }
-
- if (!end_pfn)
- continue;
-
- zone->zone_start_pfn = start_pfn;
- zone->spanned_pages = end_pfn - start_pfn;
- }
for (i = 0; i < cma_area_count; i++) {
int ret = cma_activate_area(&cma_areas[i]);
@@ -195,32 +157,9 @@ static int __init cma_init_reserved_areas(void)
return ret;
}
- /*
- * Reserved pages for ZONE_MOVABLE are now activated and
- * this would change ZONE_MOVABLE's managed page counter and
- * the other zones' present counter. We need to re-calculate
- * various zone information that depends on this initialization.
- */
- build_all_zonelists(NULL);
- for_each_populated_zone(zone) {
- if (zone_idx(zone) == ZONE_MOVABLE) {
- zone_pcp_reset(zone);
- setup_zone_pageset(zone);
- } else
- zone_pcp_update(zone);
-
- set_zone_contiguous(zone);
- }
-
- /*
- * We need to re-init per zone wmark by calling
- * init_per_zone_wmark_min() but doesn't call here because it is
- * registered on core_initcall and it will be called later than us.
- */
-
return 0;
}
-pure_initcall(cma_init_reserved_areas);
+core_initcall(cma_init_reserved_areas);
/**
* cma_init_reserved_mem() - create custom contiguous area from reserved memory
diff --git a/mm/compaction.c b/mm/compaction.c
index 028b721..29bd1df 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1450,12 +1450,14 @@ static enum compact_result __compaction_suitable(struct zone *zone, int order,
* if compaction succeeds.
* For costly orders, we require low watermark instead of min for
* compaction to proceed to increase its chances.
+ * ALLOC_CMA is used, as pages in CMA pageblocks are considered
+ * suitable migration targets
*/
watermark = (order > PAGE_ALLOC_COSTLY_ORDER) ?
low_wmark_pages(zone) : min_wmark_pages(zone);
watermark += compact_gap(order);
if (!__zone_watermark_ok(zone, 0, watermark, classzone_idx,
- 0, wmark_target))
+ ALLOC_CMA, wmark_target))
return COMPACT_SKIPPED;
return COMPACT_CONTINUE;
diff --git a/mm/filemap.c b/mm/filemap.c
index 9276bdb2..0604cb0 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -786,7 +786,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
VM_BUG_ON_PAGE(!PageLocked(new), new);
VM_BUG_ON_PAGE(new->mapping, new);
- error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
+ error = radix_tree_preload(gfp_mask & GFP_RECLAIM_MASK);
if (!error) {
struct address_space *mapping = old->mapping;
void (*freepage)(struct page *);
@@ -842,7 +842,7 @@ static int __add_to_page_cache_locked(struct page *page,
return error;
}
- error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM);
+ error = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK);
if (error) {
if (!huge)
mem_cgroup_cancel_charge(page, memcg, false);
@@ -1585,8 +1585,7 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
if (fgp_flags & FGP_ACCESSED)
__SetPageReferenced(page);
- err = add_to_page_cache_lru(page, mapping, offset,
- gfp_mask & GFP_RECLAIM_MASK);
+ err = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
if (unlikely(err)) {
put_page(page);
page = NULL;
@@ -2387,7 +2386,7 @@ static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask)
if (!page)
return -ENOMEM;
- ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask & GFP_KERNEL);
+ ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
if (ret == 0)
ret = mapping->a_ops->readpage(file, page);
else if (ret == -EEXIST)
diff --git a/mm/frontswap.c b/mm/frontswap.c
index fec8b50..4f5476a 100644
--- a/mm/frontswap.c
+++ b/mm/frontswap.c
@@ -3,7 +3,7 @@
*
* This code provides the generic "frontend" layer to call a matching
* "backend" driver implementation of frontswap. See
- * Documentation/vm/frontswap.txt for more information.
+ * Documentation/vm/frontswap.rst for more information.
*
* Copyright (C) 2009-2012 Oracle Corp. All rights reserved.
* Author: Dan Magenheimer
diff --git a/mm/gup.c b/mm/gup.c
index 76af4cf..541904a 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -544,6 +544,9 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
if (vm_flags & (VM_IO | VM_PFNMAP))
return -EFAULT;
+ if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma))
+ return -EFAULT;
+
if (write) {
if (!(vm_flags & VM_WRITE)) {
if (!(gup_flags & FOLL_FORCE))
diff --git a/mm/hmm.c b/mm/hmm.c
index 486dc394..e63e353 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -37,7 +37,7 @@
#if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC)
/*
- * Device private memory see HMM (Documentation/vm/hmm.txt) or hmm.h
+ * Device private memory see HMM (Documentation/vm/hmm.rst) or hmm.h
*/
DEFINE_STATIC_KEY_FALSE(device_private_key);
EXPORT_SYMBOL(device_private_key);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 14ed6ee..ac5591d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1185,7 +1185,7 @@ static int do_huge_pmd_wp_page_fallback(struct vm_fault *vmf, pmd_t orig_pmd,
* mmu_notifier_invalidate_range_end() happens which can lead to a
* device seeing memory write in different order than CPU.
*
- * See Documentation/vm/mmu_notifier.txt
+ * See Documentation/vm/mmu_notifier.rst
*/
pmdp_huge_clear_flush_notify(vma, haddr, vmf->pmd);
@@ -2037,7 +2037,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
* replacing a zero pmd write protected page with a zero pte write
* protected page.
*
- * See Documentation/vm/mmu_notifier.txt
+ * See Documentation/vm/mmu_notifier.rst
*/
pmdp_huge_clear_flush(vma, haddr, pmd);
@@ -2431,7 +2431,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
__split_huge_page_tail(head, i, lruvec, list);
/* Some pages can be beyond i_size: drop them from page cache */
if (head[i].index >= end) {
- __ClearPageDirty(head + i);
+ ClearPageDirty(head + i);
__delete_from_page_cache(head + i, NULL);
if (IS_ENABLED(CONFIG_SHMEM) && PageSwapBacked(head))
shmem_uncharge(head->mapping->host, 1);
@@ -2925,7 +2925,10 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
pmde = maybe_pmd_mkwrite(pmde, vma);
flush_cache_range(vma, mmun_start, mmun_start + HPAGE_PMD_SIZE);
- page_add_anon_rmap(new, vma, mmun_start, true);
+ if (PageAnon(new))
+ page_add_anon_rmap(new, vma, mmun_start, true);
+ else
+ page_add_file_rmap(new, true);
set_pmd_at(mm, mmun_start, pvmw->pmd, pmde);
if (vma->vm_flags & VM_LOCKED)
mlock_vma_page(new);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 2186791..1290887 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3291,7 +3291,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
* table protection not changing it to point
* to a new page.
*
- * See Documentation/vm/mmu_notifier.txt
+ * See Documentation/vm/mmu_notifier.rst
*/
huge_ptep_set_wrprotect(src, addr, src_pte);
}
@@ -4357,7 +4357,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
* No need to call mmu_notifier_invalidate_range() we are downgrading
* page table protection not changing it to point to a new page.
*
- * See Documentation/vm/mmu_notifier.txt
+ * See Documentation/vm/mmu_notifier.rst
*/
i_mmap_unlock_write(vma->vm_file->f_mapping);
mmu_notifier_invalidate_range_end(mm, start, end);
diff --git a/mm/internal.h b/mm/internal.h
index 62d8c34..9e3654d 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -53,7 +53,7 @@ void unmap_page_range(struct mmu_gather *tlb,
unsigned long addr, unsigned long end,
struct zap_details *details);
-extern int __do_page_cache_readahead(struct address_space *mapping,
+extern unsigned int __do_page_cache_readahead(struct address_space *mapping,
struct file *filp, pgoff_t offset, unsigned long nr_to_read,
unsigned long lookahead_size);
@@ -168,9 +168,6 @@ extern void post_alloc_hook(struct page *page, unsigned int order,
gfp_t gfp_flags);
extern int user_min_free_kbytes;
-extern void set_zone_contiguous(struct zone *zone);
-extern void clear_zone_contiguous(struct zone *zone);
-
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/*
@@ -498,6 +495,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
#define ALLOC_HARDER 0x10 /* try to alloc harder */
#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */
#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
+#define ALLOC_CMA 0x80 /* allow allocations from CMA areas */
enum ttu_flags;
struct tlbflush_unmap_batch;
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index bc0e68f..f185455 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -792,6 +792,40 @@ DEFINE_ASAN_SET_SHADOW(f5);
DEFINE_ASAN_SET_SHADOW(f8);
#ifdef CONFIG_MEMORY_HOTPLUG
+static bool shadow_mapped(unsigned long addr)
+{
+ pgd_t *pgd = pgd_offset_k(addr);
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ if (pgd_none(*pgd))
+ return false;
+ p4d = p4d_offset(pgd, addr);
+ if (p4d_none(*p4d))
+ return false;
+ pud = pud_offset(p4d, addr);
+ if (pud_none(*pud))
+ return false;
+
+ /*
+ * We can't use pud_large() or pud_huge(), the first one is
+ * arch-specific, the last one depends on HUGETLB_PAGE. So let's abuse
+ * pud_bad(), if pud is bad then it's bad because it's huge.
+ */
+ if (pud_bad(*pud))
+ return true;
+ pmd = pmd_offset(pud, addr);
+ if (pmd_none(*pmd))
+ return false;
+
+ if (pmd_bad(*pmd))
+ return true;
+ pte = pte_offset_kernel(pmd, addr);
+ return !pte_none(*pte);
+}
+
static int __meminit kasan_mem_notifier(struct notifier_block *nb,
unsigned long action, void *data)
{
@@ -813,6 +847,14 @@ static int __meminit kasan_mem_notifier(struct notifier_block *nb,
case MEM_GOING_ONLINE: {
void *ret;
+ /*
+ * If shadow is mapped already than it must have been mapped
+ * during the boot. This could happen if we onlining previously
+ * offlined memory.
+ */
+ if (shadow_mapped(shadow_start))
+ return NOTIFY_OK;
+
ret = __vmalloc_node_range(shadow_size, PAGE_SIZE, shadow_start,
shadow_end, GFP_KERNEL,
PAGE_KERNEL, VM_NO_GUARD,
@@ -824,8 +866,26 @@ static int __meminit kasan_mem_notifier(struct notifier_block *nb,
kmemleak_ignore(ret);
return NOTIFY_OK;
}
- case MEM_OFFLINE:
- vfree((void *)shadow_start);
+ case MEM_CANCEL_ONLINE:
+ case MEM_OFFLINE: {
+ struct vm_struct *vm;
+
+ /*
+ * shadow_start was either mapped during boot by kasan_init()
+ * or during memory online by __vmalloc_node_range().
+ * In the latter case we can use vfree() to free shadow.
+ * Non-NULL result of the find_vm_area() will tell us if
+ * that was the second case.
+ *
+ * Currently it's not possible to free shadow mapped
+ * during boot by kasan_init(). It's because the code
+ * to do that hasn't been written yet. So we'll just
+ * leak the memory.
+ */
+ vm = find_vm_area((void *)shadow_start);
+ if (vm)
+ vfree((void *)shadow_start);
+ }
}
return NOTIFY_OK;
@@ -838,5 +898,5 @@ static int __init kasan_memhotplug_init(void)
return 0;
}
-module_init(kasan_memhotplug_init);
+core_initcall(kasan_memhotplug_init);
#endif
diff --git a/mm/ksm.c b/mm/ksm.c
index e3cbf9a..7d6558f 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -51,7 +51,9 @@
#define DO_NUMA(x) do { } while (0)
#endif
-/*
+/**
+ * DOC: Overview
+ *
* A few notes about the KSM scanning process,
* to make it easier to understand the data structures below:
*
@@ -67,6 +69,21 @@
* this tree is fully assured to be working (except when pages are unmapped),
* and therefore this tree is called the stable tree.
*
+ * The stable tree node includes information required for reverse
+ * mapping from a KSM page to virtual addresses that map this page.
+ *
+ * In order to avoid large latencies of the rmap walks on KSM pages,
+ * KSM maintains two types of nodes in the stable tree:
+ *
+ * * the regular nodes that keep the reverse mapping structures in a
+ * linked list
+ * * the "chains" that link nodes ("dups") that represent the same
+ * write protected memory content, but each "dup" corresponds to a
+ * different KSM page copy of that content
+ *
+ * Internally, the regular nodes, "dups" and "chains" are represented
+ * using the same :c:type:`struct stable_node` structure.
+ *
* In addition to the stable tree, KSM uses a second data structure called the
* unstable tree: this tree holds pointers to pages which have been found to
* be "unchanged for a period of time". The unstable tree sorts these pages
@@ -1049,7 +1066,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
* No need to notify as we are downgrading page table to read
* only not changing it to point to a new page.
*
- * See Documentation/vm/mmu_notifier.txt
+ * See Documentation/vm/mmu_notifier.rst
*/
entry = ptep_clear_flush(vma, pvmw.address, pvmw.pte);
/*
@@ -1145,7 +1162,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
* No need to notify as we are replacing a read only page with another
* read only page with the same content.
*
- * See Documentation/vm/mmu_notifier.txt
+ * See Documentation/vm/mmu_notifier.rst
*/
ptep_clear_flush(vma, addr, ptep);
set_pte_at_notify(mm, addr, ptep, newpte);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e074f7c..1695f38 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2192,7 +2192,7 @@ static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
{
struct memcg_kmem_cache_create_work *cw;
- cw = kmalloc(sizeof(*cw), GFP_NOWAIT);
+ cw = kmalloc(sizeof(*cw), GFP_NOWAIT | __GFP_NOWARN);
if (!cw)
return;
@@ -3849,7 +3849,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
if (ret)
goto out_put_css;
- efile.file->f_op->poll(efile.file, &event->pt);
+ vfs_poll(efile.file, &event->pt);
spin_lock(&memcg->event_list_lock);
list_add(&event->list, &memcg->event_list);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index f74826c..2598246 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1158,7 +1158,7 @@ int __ref add_memory_resource(int nid, struct resource *res, bool online)
* nodes have to go through register_node.
* TODO clean up this mess.
*/
- ret = link_mem_sections(nid, start_pfn, nr_pages);
+ ret = link_mem_sections(nid, start_pfn, nr_pages, false);
register_fail:
/*
* If sysfs file of new node can't create, cpu on the node
diff --git a/mm/mempool.c b/mm/mempool.c
index 5c9dce3..b54f2c2 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -138,6 +138,28 @@ static void *remove_element(mempool_t *pool, gfp_t flags)
}
/**
+ * mempool_exit - exit a mempool initialized with mempool_init()
+ * @pool: pointer to the memory pool which was initialized with
+ * mempool_init().
+ *
+ * Free all reserved elements in @pool and @pool itself. This function
+ * only sleeps if the free_fn() function sleeps.
+ *
+ * May be called on a zeroed but uninitialized mempool (i.e. allocated with
+ * kzalloc()).
+ */
+void mempool_exit(mempool_t *pool)
+{
+ while (pool->curr_nr) {
+ void *element = remove_element(pool, GFP_KERNEL);
+ pool->free(element, pool->pool_data);
+ }
+ kfree(pool->elements);
+ pool->elements = NULL;
+}
+EXPORT_SYMBOL(mempool_exit);
+
+/**
* mempool_destroy - deallocate a memory pool
* @pool: pointer to the memory pool which was allocated via
* mempool_create().
@@ -150,15 +172,65 @@ void mempool_destroy(mempool_t *pool)
if (unlikely(!pool))
return;
- while (pool->curr_nr) {
- void *element = remove_element(pool, GFP_KERNEL);
- pool->free(element, pool->pool_data);
- }
- kfree(pool->elements);
+ mempool_exit(pool);
kfree(pool);
}
EXPORT_SYMBOL(mempool_destroy);
+int mempool_init_node(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn,
+ mempool_free_t *free_fn, void *pool_data,
+ gfp_t gfp_mask, int node_id)
+{
+ spin_lock_init(&pool->lock);
+ pool->min_nr = min_nr;
+ pool->pool_data = pool_data;
+ pool->alloc = alloc_fn;
+ pool->free = free_fn;
+ init_waitqueue_head(&pool->wait);
+
+ pool->elements = kmalloc_array_node(min_nr, sizeof(void *),
+ gfp_mask, node_id);
+ if (!pool->elements)
+ return -ENOMEM;
+
+ /*
+ * First pre-allocate the guaranteed number of buffers.
+ */
+ while (pool->curr_nr < pool->min_nr) {
+ void *element;
+
+ element = pool->alloc(gfp_mask, pool->pool_data);
+ if (unlikely(!element)) {
+ mempool_exit(pool);
+ return -ENOMEM;
+ }
+ add_element(pool, element);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(mempool_init_node);
+
+/**
+ * mempool_init - initialize a memory pool
+ * @min_nr: the minimum number of elements guaranteed to be
+ * allocated for this pool.
+ * @alloc_fn: user-defined element-allocation function.
+ * @free_fn: user-defined element-freeing function.
+ * @pool_data: optional private data available to the user-defined functions.
+ *
+ * Like mempool_create(), but initializes the pool in (i.e. embedded in another
+ * structure).
+ */
+int mempool_init(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn,
+ mempool_free_t *free_fn, void *pool_data)
+{
+ return mempool_init_node(pool, min_nr, alloc_fn, free_fn,
+ pool_data, GFP_KERNEL, NUMA_NO_NODE);
+
+}
+EXPORT_SYMBOL(mempool_init);
+
/**
* mempool_create - create a memory pool
* @min_nr: the minimum number of elements guaranteed to be
@@ -186,35 +258,17 @@ mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn,
gfp_t gfp_mask, int node_id)
{
mempool_t *pool;
+
pool = kzalloc_node(sizeof(*pool), gfp_mask, node_id);
if (!pool)
return NULL;
- pool->elements = kmalloc_array_node(min_nr, sizeof(void *),
- gfp_mask, node_id);
- if (!pool->elements) {
+
+ if (mempool_init_node(pool, min_nr, alloc_fn, free_fn, pool_data,
+ gfp_mask, node_id)) {
kfree(pool);
return NULL;
}
- spin_lock_init(&pool->lock);
- pool->min_nr = min_nr;
- pool->pool_data = pool_data;
- init_waitqueue_head(&pool->wait);
- pool->alloc = alloc_fn;
- pool->free = free_fn;
- /*
- * First pre-allocate the guaranteed number of buffers.
- */
- while (pool->curr_nr < pool->min_nr) {
- void *element;
-
- element = pool->alloc(gfp_mask, pool->pool_data);
- if (unlikely(!element)) {
- mempool_destroy(pool);
- return NULL;
- }
- add_element(pool, element);
- }
return pool;
}
EXPORT_SYMBOL(mempool_create_node);
diff --git a/mm/migrate.c b/mm/migrate.c
index f65dd69..8c0af0f 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -472,7 +472,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
pslot = radix_tree_lookup_slot(&mapping->i_pages,
page_index(page));
- expected_count += 1 + page_has_private(page);
+ expected_count += hpage_nr_pages(page) + page_has_private(page);
if (page_count(page) != expected_count ||
radix_tree_deref_slot_protected(pslot,
&mapping->i_pages.xa_lock) != page) {
@@ -505,7 +505,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
*/
newpage->index = page->index;
newpage->mapping = page->mapping;
- get_page(newpage); /* add cache reference */
+ page_ref_add(newpage, hpage_nr_pages(page)); /* add cache reference */
if (PageSwapBacked(page)) {
__SetPageSwapBacked(newpage);
if (PageSwapCache(page)) {
@@ -524,13 +524,24 @@ int migrate_page_move_mapping(struct address_space *mapping,
}
radix_tree_replace_slot(&mapping->i_pages, pslot, newpage);
+ if (PageTransHuge(page)) {
+ int i;
+ int index = page_index(page);
+
+ for (i = 1; i < HPAGE_PMD_NR; i++) {
+ pslot = radix_tree_lookup_slot(&mapping->i_pages,
+ index + i);
+ radix_tree_replace_slot(&mapping->i_pages, pslot,
+ newpage + i);
+ }
+ }
/*
* Drop cache reference from old page by unfreezing
* to one less reference.
* We know this isn't the last reference.
*/
- page_ref_unfreeze(page, expected_count - 1);
+ page_ref_unfreeze(page, expected_count - hpage_nr_pages(page));
xa_unlock(&mapping->i_pages);
/* Leave irq disabled to prevent preemption while updating stats */
@@ -1622,6 +1633,9 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
current_node = NUMA_NO_NODE;
}
out_flush:
+ if (list_empty(&pagelist))
+ return err;
+
/* Make sure we do not overwrite the existing error */
err1 = do_move_pages_to_node(mm, &pagelist, current_node);
if (!err1)
diff --git a/mm/mmap.c b/mm/mmap.c
index 188f195..d817764 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -100,11 +100,20 @@ pgprot_t protection_map[16] __ro_after_init = {
__S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111
};
+#ifndef CONFIG_ARCH_HAS_FILTER_PGPROT
+static inline pgprot_t arch_filter_pgprot(pgprot_t prot)
+{
+ return prot;
+}
+#endif
+
pgprot_t vm_get_page_prot(unsigned long vm_flags)
{
- return __pgprot(pgprot_val(protection_map[vm_flags &
+ pgprot_t ret = __pgprot(pgprot_val(protection_map[vm_flags &
(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]) |
pgprot_val(arch_vm_get_page_prot(vm_flags)));
+
+ return arch_filter_pgprot(ret);
}
EXPORT_SYMBOL(vm_get_page_prot);
@@ -1315,6 +1324,35 @@ static inline int mlock_future_check(struct mm_struct *mm,
return 0;
}
+static inline u64 file_mmap_size_max(struct file *file, struct inode *inode)
+{
+ if (S_ISREG(inode->i_mode))
+ return MAX_LFS_FILESIZE;
+
+ if (S_ISBLK(inode->i_mode))
+ return MAX_LFS_FILESIZE;
+
+ /* Special "we do even unsigned file positions" case */
+ if (file->f_mode & FMODE_UNSIGNED_OFFSET)
+ return 0;
+
+ /* Yes, random drivers might want more. But I'm tired of buggy drivers */
+ return ULONG_MAX;
+}
+
+static inline bool file_mmap_ok(struct file *file, struct inode *inode,
+ unsigned long pgoff, unsigned long len)
+{
+ u64 maxsize = file_mmap_size_max(file, inode);
+
+ if (maxsize && len > maxsize)
+ return false;
+ maxsize -= len;
+ if (pgoff > maxsize >> PAGE_SHIFT)
+ return false;
+ return true;
+}
+
/*
* The caller must hold down_write(¤t->mm->mmap_sem).
*/
@@ -1400,6 +1438,9 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
struct inode *inode = file_inode(file);
unsigned long flags_mask;
+ if (!file_mmap_ok(file, inode, pgoff, len))
+ return -EOVERFLOW;
+
flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags;
switch (flags & MAP_TYPE) {
@@ -2787,7 +2828,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
unsigned long ret = -EINVAL;
struct file *file;
- pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/vm/remap_file_pages.txt.\n",
+ pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/vm/remap_file_pages.rst.\n",
current->comm, current->pid);
if (prot)
@@ -3015,6 +3056,32 @@ void exit_mmap(struct mm_struct *mm)
/* mm's last user has gone, and its about to be pulled down */
mmu_notifier_release(mm);
+ if (unlikely(mm_is_oom_victim(mm))) {
+ /*
+ * Manually reap the mm to free as much memory as possible.
+ * Then, as the oom reaper does, set MMF_OOM_SKIP to disregard
+ * this mm from further consideration. Taking mm->mmap_sem for
+ * write after setting MMF_OOM_SKIP will guarantee that the oom
+ * reaper will not run on this mm again after mmap_sem is
+ * dropped.
+ *
+ * Nothing can be holding mm->mmap_sem here and the above call
+ * to mmu_notifier_release(mm) ensures mmu notifier callbacks in
+ * __oom_reap_task_mm() will not block.
+ *
+ * This needs to be done before calling munlock_vma_pages_all(),
+ * which clears VM_LOCKED, otherwise the oom reaper cannot
+ * reliably test it.
+ */
+ mutex_lock(&oom_lock);
+ __oom_reap_task_mm(mm);
+ mutex_unlock(&oom_lock);
+
+ set_bit(MMF_OOM_SKIP, &mm->flags);
+ down_write(&mm->mmap_sem);
+ up_write(&mm->mmap_sem);
+ }
+
if (mm->locked_vm) {
vma = mm->mmap;
while (vma) {
@@ -3036,24 +3103,6 @@ void exit_mmap(struct mm_struct *mm)
/* update_hiwater_rss(mm) here? but nobody should be looking */
/* Use -1 here to ensure all VMAs in the mm are unmapped */
unmap_vmas(&tlb, vma, 0, -1);
-
- if (unlikely(mm_is_oom_victim(mm))) {
- /*
- * Wait for oom_reap_task() to stop working on this
- * mm. Because MMF_OOM_SKIP is already set before
- * calling down_read(), oom_reap_task() will not run
- * on this "mm" post up_write().
- *
- * mm_is_oom_victim() cannot be set from under us
- * either because victim->mm is already set to NULL
- * under task_lock before calling mmput and oom_mm is
- * set not NULL by the OOM killer only if victim->mm
- * is found not NULL while holding the task_lock.
- */
- set_bit(MMF_OOM_SKIP, &mm->flags);
- down_write(&mm->mmap_sem);
- up_write(&mm->mmap_sem);
- }
free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING);
tlb_finish_mmu(&tlb, 0, -1);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index ff992fa..8ba6cb8 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -469,7 +469,6 @@ bool process_shares_mm(struct task_struct *p, struct mm_struct *mm)
return false;
}
-
#ifdef CONFIG_MMU
/*
* OOM Reaper kernel thread which tries to reap the memory used by the OOM
@@ -480,16 +479,54 @@ static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait);
static struct task_struct *oom_reaper_list;
static DEFINE_SPINLOCK(oom_reaper_lock);
-static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
+void __oom_reap_task_mm(struct mm_struct *mm)
{
- struct mmu_gather tlb;
struct vm_area_struct *vma;
+
+ /*
+ * Tell all users of get_user/copy_from_user etc... that the content
+ * is no longer stable. No barriers really needed because unmapping
+ * should imply barriers already and the reader would hit a page fault
+ * if it stumbled over a reaped memory.
+ */
+ set_bit(MMF_UNSTABLE, &mm->flags);
+
+ for (vma = mm->mmap ; vma; vma = vma->vm_next) {
+ if (!can_madv_dontneed_vma(vma))
+ continue;
+
+ /*
+ * Only anonymous pages have a good chance to be dropped
+ * without additional steps which we cannot afford as we
+ * are OOM already.
+ *
+ * We do not even care about fs backed pages because all
+ * which are reclaimable have already been reclaimed and
+ * we do not want to block exit_mmap by keeping mm ref
+ * count elevated without a good reason.
+ */
+ if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
+ const unsigned long start = vma->vm_start;
+ const unsigned long end = vma->vm_end;
+ struct mmu_gather tlb;
+
+ tlb_gather_mmu(&tlb, mm, start, end);
+ mmu_notifier_invalidate_range_start(mm, start, end);
+ unmap_page_range(&tlb, vma, start, end, NULL);
+ mmu_notifier_invalidate_range_end(mm, start, end);
+ tlb_finish_mmu(&tlb, start, end);
+ }
+ }
+}
+
+static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
+{
bool ret = true;
/*
* We have to make sure to not race with the victim exit path
* and cause premature new oom victim selection:
- * __oom_reap_task_mm exit_mm
+ * oom_reap_task_mm exit_mm
* mmget_not_zero
* mmput
* atomic_dec_and_test
@@ -534,39 +571,8 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
trace_start_task_reaping(tsk->pid);
- /*
- * Tell all users of get_user/copy_from_user etc... that the content
- * is no longer stable. No barriers really needed because unmapping
- * should imply barriers already and the reader would hit a page fault
- * if it stumbled over a reaped memory.
- */
- set_bit(MMF_UNSTABLE, &mm->flags);
+ __oom_reap_task_mm(mm);
- for (vma = mm->mmap ; vma; vma = vma->vm_next) {
- if (!can_madv_dontneed_vma(vma))
- continue;
-
- /*
- * Only anonymous pages have a good chance to be dropped
- * without additional steps which we cannot afford as we
- * are OOM already.
- *
- * We do not even care about fs backed pages because all
- * which are reclaimable have already been reclaimed and
- * we do not want to block exit_mmap by keeping mm ref
- * count elevated without a good reason.
- */
- if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) {
- const unsigned long start = vma->vm_start;
- const unsigned long end = vma->vm_end;
-
- tlb_gather_mmu(&tlb, mm, start, end);
- mmu_notifier_invalidate_range_start(mm, start, end);
- unmap_page_range(&tlb, vma, start, end, NULL);
- mmu_notifier_invalidate_range_end(mm, start, end);
- tlb_finish_mmu(&tlb, start, end);
- }
- }
pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n",
task_pid_nr(tsk), tsk->comm,
K(get_mm_counter(mm, MM_ANONPAGES)),
@@ -587,14 +593,13 @@ static void oom_reap_task(struct task_struct *tsk)
struct mm_struct *mm = tsk->signal->oom_mm;
/* Retry the down_read_trylock(mmap_sem) a few times */
- while (attempts++ < MAX_OOM_REAP_RETRIES && !__oom_reap_task_mm(tsk, mm))
+ while (attempts++ < MAX_OOM_REAP_RETRIES && !oom_reap_task_mm(tsk, mm))
schedule_timeout_idle(HZ/10);
if (attempts <= MAX_OOM_REAP_RETRIES ||
test_bit(MMF_OOM_SKIP, &mm->flags))
goto done;
-
pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
task_pid_nr(tsk), tsk->comm);
debug_show_all_locks();
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 5c1a327..337c6af 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2502,13 +2502,13 @@ void account_page_redirty(struct page *page)
if (mapping && mapping_cap_account_dirty(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
- bool locked;
+ struct wb_lock_cookie cookie = {};
- wb = unlocked_inode_to_wb_begin(inode, &locked);
+ wb = unlocked_inode_to_wb_begin(inode, &cookie);
current->nr_dirtied--;
dec_node_page_state(page, NR_DIRTIED);
dec_wb_stat(wb, WB_DIRTIED);
- unlocked_inode_to_wb_end(inode, locked);
+ unlocked_inode_to_wb_end(inode, &cookie);
}
}
EXPORT_SYMBOL(account_page_redirty);
@@ -2614,15 +2614,15 @@ void __cancel_dirty_page(struct page *page)
if (mapping_cap_account_dirty(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
- bool locked;
+ struct wb_lock_cookie cookie = {};
lock_page_memcg(page);
- wb = unlocked_inode_to_wb_begin(inode, &locked);
+ wb = unlocked_inode_to_wb_begin(inode, &cookie);
if (TestClearPageDirty(page))
account_page_cleaned(page, mapping, wb);
- unlocked_inode_to_wb_end(inode, locked);
+ unlocked_inode_to_wb_end(inode, &cookie);
unlock_page_memcg(page);
} else {
ClearPageDirty(page);
@@ -2654,7 +2654,7 @@ int clear_page_dirty_for_io(struct page *page)
if (mapping && mapping_cap_account_dirty(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
- bool locked;
+ struct wb_lock_cookie cookie = {};
/*
* Yes, Virginia, this is indeed insane.
@@ -2691,14 +2691,14 @@ int clear_page_dirty_for_io(struct page *page)
* always locked coming in here, so we get the desired
* exclusion.
*/
- wb = unlocked_inode_to_wb_begin(inode, &locked);
+ wb = unlocked_inode_to_wb_begin(inode, &cookie);
if (TestClearPageDirty(page)) {
dec_lruvec_page_state(page, NR_FILE_DIRTY);
dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
dec_wb_stat(wb, WB_RECLAIMABLE);
ret = 1;
}
- unlocked_inode_to_wb_end(inode, locked);
+ unlocked_inode_to_wb_end(inode, &cookie);
return ret;
}
return TestClearPageDirty(page);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 905db9d..22320ea27 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1743,38 +1743,16 @@ void __init page_alloc_init_late(void)
}
#ifdef CONFIG_CMA
-static void __init adjust_present_page_count(struct page *page, long count)
-{
- struct zone *zone = page_zone(page);
-
- /* We don't need to hold a lock since it is boot-up process */
- zone->present_pages += count;
-}
-
/* Free whole pageblock and set its migration type to MIGRATE_CMA. */
void __init init_cma_reserved_pageblock(struct page *page)
{
unsigned i = pageblock_nr_pages;
- unsigned long pfn = page_to_pfn(page);
struct page *p = page;
- int nid = page_to_nid(page);
-
- /*
- * ZONE_MOVABLE will steal present pages from other zones by
- * changing page links so page_zone() is changed. Before that,
- * we need to adjust previous zone's page count first.
- */
- adjust_present_page_count(page, -pageblock_nr_pages);
do {
__ClearPageReserved(p);
set_page_count(p, 0);
-
- /* Steal pages from other zones */
- set_page_links(p, ZONE_MOVABLE, nid, pfn);
- } while (++p, ++pfn, --i);
-
- adjust_present_page_count(page, pageblock_nr_pages);
+ } while (++p, --i);
set_pageblock_migratetype(page, MIGRATE_CMA);
@@ -2889,7 +2867,7 @@ int __isolate_free_page(struct page *page, unsigned int order)
* exists.
*/
watermark = min_wmark_pages(zone) + (1UL << order);
- if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
+ if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA))
return 0;
__mod_zone_freepage_state(zone, -(1UL << order), mt);
@@ -3165,6 +3143,12 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
}
+#ifdef CONFIG_CMA
+ /* If allocation can't use CMA areas don't use free CMA pages */
+ if (!(alloc_flags & ALLOC_CMA))
+ free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
+#endif
+
/*
* Check watermarks for an order-0 allocation request. If these
* are not met, then a high-order request also cannot go ahead
@@ -3191,8 +3175,10 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
}
#ifdef CONFIG_CMA
- if (!list_empty(&area->free_list[MIGRATE_CMA]))
+ if ((alloc_flags & ALLOC_CMA) &&
+ !list_empty(&area->free_list[MIGRATE_CMA])) {
return true;
+ }
#endif
if (alloc_harder &&
!list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
@@ -3212,6 +3198,13 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
unsigned long mark, int classzone_idx, unsigned int alloc_flags)
{
long free_pages = zone_page_state(z, NR_FREE_PAGES);
+ long cma_pages = 0;
+
+#ifdef CONFIG_CMA
+ /* If allocation can't use CMA areas don't use free CMA pages */
+ if (!(alloc_flags & ALLOC_CMA))
+ cma_pages = zone_page_state(z, NR_FREE_CMA_PAGES);
+#endif
/*
* Fast check for order-0 only. If this fails then the reserves
@@ -3220,7 +3213,7 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
* the caller is !atomic then it'll uselessly search the free
* list. That corner case is then slower but it is harmless.
*/
- if (!order && free_pages > mark + z->lowmem_reserve[classzone_idx])
+ if (!order && (free_pages - cma_pages) > mark + z->lowmem_reserve[classzone_idx])
return true;
return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
@@ -3856,6 +3849,10 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
} else if (unlikely(rt_task(current)) && !in_interrupt())
alloc_flags |= ALLOC_HARDER;
+#ifdef CONFIG_CMA
+ if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
+ alloc_flags |= ALLOC_CMA;
+#endif
return alloc_flags;
}
@@ -4322,6 +4319,9 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
if (should_fail_alloc_page(gfp_mask, order))
return false;
+ if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE)
+ *alloc_flags |= ALLOC_CMA;
+
return true;
}
@@ -6204,7 +6204,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
{
enum zone_type j;
int nid = pgdat->node_id;
- unsigned long node_end_pfn = 0;
pgdat_resize_init(pgdat);
#ifdef CONFIG_NUMA_BALANCING
@@ -6232,13 +6231,9 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
struct zone *zone = pgdat->node_zones + j;
unsigned long size, realsize, freesize, memmap_pages;
unsigned long zone_start_pfn = zone->zone_start_pfn;
- unsigned long movable_size = 0;
size = zone->spanned_pages;
realsize = freesize = zone->present_pages;
- if (zone_end_pfn(zone) > node_end_pfn)
- node_end_pfn = zone_end_pfn(zone);
-
/*
* Adjust freesize so that it accounts for how much memory
@@ -6287,30 +6282,12 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
zone_seqlock_init(zone);
zone_pcp_init(zone);
- /*
- * The size of the CMA area is unknown now so we need to
- * prepare the memory for the usemap at maximum.
- */
- if (IS_ENABLED(CONFIG_CMA) && j == ZONE_MOVABLE &&
- pgdat->node_spanned_pages) {
- movable_size = node_end_pfn - pgdat->node_start_pfn;
- }
-
- if (!size && !movable_size)
+ if (!size)
continue;
set_pageblock_order();
- if (movable_size) {
- zone->zone_start_pfn = pgdat->node_start_pfn;
- zone->spanned_pages = movable_size;
- setup_usemap(pgdat, zone,
- pgdat->node_start_pfn, movable_size);
- init_currently_empty_zone(zone,
- pgdat->node_start_pfn, movable_size);
- } else {
- setup_usemap(pgdat, zone, zone_start_pfn, size);
- init_currently_empty_zone(zone, zone_start_pfn, size);
- }
+ setup_usemap(pgdat, zone, zone_start_pfn, size);
+ init_currently_empty_zone(zone, zone_start_pfn, size);
memmap_init(size, nid, j, zone_start_pfn);
}
}
@@ -7621,11 +7598,12 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
unsigned long pfn, iter, found;
/*
- * For avoiding noise data, lru_add_drain_all() should be called
- * If ZONE_MOVABLE, the zone never contains unmovable pages
+ * TODO we could make this much more efficient by not checking every
+ * page in the range if we know all of them are in MOVABLE_ZONE and
+ * that the movable zone guarantees that pages are migratable but
+ * the later is not the case right now unfortunatelly. E.g. movablecore
+ * can still lead to having bootmem allocations in zone_movable.
*/
- if (zone_idx(zone) == ZONE_MOVABLE)
- return false;
/*
* CMA allocations (alloc_contig_range) really need to mark isolate
@@ -7646,7 +7624,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
page = pfn_to_page(check);
if (PageReserved(page))
- return true;
+ goto unmovable;
/*
* Hugepages are not in LRU lists, but they're movable.
@@ -7696,9 +7674,12 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
* page at boot.
*/
if (found > count)
- return true;
+ goto unmovable;
}
return false;
+unmovable:
+ WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE);
+ return true;
}
bool is_pageblock_removable_nolock(struct page *page)
@@ -7951,7 +7932,7 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages)
}
#endif
-#if defined CONFIG_MEMORY_HOTPLUG || defined CONFIG_CMA
+#ifdef CONFIG_MEMORY_HOTPLUG
/*
* The zone indicated has a new number of managed_pages; batch sizes and percpu
* page high values need to be recalulated.
diff --git a/mm/readahead.c b/mm/readahead.c
index 539bbb6..e273f0d 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -140,23 +140,23 @@ static int read_pages(struct address_space *mapping, struct file *filp,
}
/*
- * __do_page_cache_readahead() actually reads a chunk of disk. It allocates all
- * the pages first, then submits them all for I/O. This avoids the very bad
+ * __do_page_cache_readahead() actually reads a chunk of disk. It allocates
+ * the pages first, then submits them for I/O. This avoids the very bad
* behaviour which would occur if page allocations are causing VM writeback.
* We really don't want to intermingle reads and writes like that.
*
* Returns the number of pages requested, or the maximum amount of I/O allowed.
*/
-int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
- pgoff_t offset, unsigned long nr_to_read,
- unsigned long lookahead_size)
+unsigned int __do_page_cache_readahead(struct address_space *mapping,
+ struct file *filp, pgoff_t offset, unsigned long nr_to_read,
+ unsigned long lookahead_size)
{
struct inode *inode = mapping->host;
struct page *page;
unsigned long end_index; /* The last page we want to read */
LIST_HEAD(page_pool);
int page_idx;
- int ret = 0;
+ unsigned int nr_pages = 0;
loff_t isize = i_size_read(inode);
gfp_t gfp_mask = readahead_gfp_mask(mapping);
@@ -177,8 +177,18 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
rcu_read_lock();
page = radix_tree_lookup(&mapping->i_pages, page_offset);
rcu_read_unlock();
- if (page && !radix_tree_exceptional_entry(page))
+ if (page && !radix_tree_exceptional_entry(page)) {
+ /*
+ * Page already present? Kick off the current batch of
+ * contiguous pages before continuing with the next
+ * batch.
+ */
+ if (nr_pages)
+ read_pages(mapping, filp, &page_pool, nr_pages,
+ gfp_mask);
+ nr_pages = 0;
continue;
+ }
page = __page_cache_alloc(gfp_mask);
if (!page)
@@ -187,7 +197,7 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
list_add(&page->lru, &page_pool);
if (page_idx == nr_to_read - lookahead_size)
SetPageReadahead(page);
- ret++;
+ nr_pages++;
}
/*
@@ -195,11 +205,11 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
* uptodate then the caller will launch readpage again, and
* will then handle the error.
*/
- if (ret)
- read_pages(mapping, filp, &page_pool, ret, gfp_mask);
+ if (nr_pages)
+ read_pages(mapping, filp, &page_pool, nr_pages, gfp_mask);
BUG_ON(!list_empty(&page_pool));
out:
- return ret;
+ return nr_pages;
}
/*
@@ -223,16 +233,11 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages);
nr_to_read = min(nr_to_read, max_pages);
while (nr_to_read) {
- int err;
-
unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE;
if (this_chunk > nr_to_read)
this_chunk = nr_to_read;
- err = __do_page_cache_readahead(mapping, filp,
- offset, this_chunk, 0);
- if (err < 0)
- return err;
+ __do_page_cache_readahead(mapping, filp, offset, this_chunk, 0);
offset += this_chunk;
nr_to_read -= this_chunk;
diff --git a/mm/rmap.c b/mm/rmap.c
index f0dd4e4..6db729d 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -942,7 +942,7 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
* downgrading page table protection not changing it to point
* to a new page.
*
- * See Documentation/vm/mmu_notifier.txt
+ * See Documentation/vm/mmu_notifier.rst
*/
if (ret)
(*cleaned)++;
@@ -1374,9 +1374,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
if (!pvmw.pte && (flags & TTU_MIGRATION)) {
VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page);
- if (!PageAnon(page))
- continue;
-
set_pmd_migration_entry(&pvmw, page);
continue;
}
@@ -1602,7 +1599,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
* point at new page while a device still is using this
* page.
*
- * See Documentation/vm/mmu_notifier.txt
+ * See Documentation/vm/mmu_notifier.rst
*/
dec_mm_counter(mm, mm_counter_file(page));
}
@@ -1612,7 +1609,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
* done above for all cases requiring it to happen under page
* table lock before mmu_notifier_invalidate_range_end()
*
- * See Documentation/vm/mmu_notifier.txt
+ * See Documentation/vm/mmu_notifier.rst
*/
page_remove_rmap(subpage, PageHuge(page));
put_page(page);
diff --git a/mm/sparse.c b/mm/sparse.c
index 62eef26..73dc2fc 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -629,7 +629,7 @@ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
unsigned long pfn;
for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
- unsigned long section_nr = pfn_to_section_nr(start_pfn);
+ unsigned long section_nr = pfn_to_section_nr(pfn);
struct mem_section *ms;
/*
diff --git a/mm/swapfile.c b/mm/swapfile.c
index cc2cf04..78a015f 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3112,6 +3112,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
unsigned long *frontswap_map = NULL;
struct page *page = NULL;
struct inode *inode = NULL;
+ bool inced_nr_rotate_swap = false;
if (swap_flags & ~SWAP_FLAGS_VALID)
return -EINVAL;
@@ -3215,8 +3216,10 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
cluster = per_cpu_ptr(p->percpu_cluster, cpu);
cluster_set_null(&cluster->index);
}
- } else
+ } else {
atomic_inc(&nr_rotate_swap);
+ inced_nr_rotate_swap = true;
+ }
error = swap_cgroup_swapon(p->type, maxpages);
if (error)
@@ -3307,6 +3310,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
vfree(swap_map);
kvfree(cluster_info);
kvfree(frontswap_map);
+ if (inced_nr_rotate_swap)
+ atomic_dec(&nr_rotate_swap);
if (swap_file) {
if (inode && S_ISREG(inode->i_mode)) {
inode_unlock(inode);
diff --git a/mm/util.c b/mm/util.c
index 45fc316..c2d0a7c 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -621,7 +621,7 @@ EXPORT_SYMBOL_GPL(vm_memory_committed);
* succeed and -ENOMEM implies there is not.
*
* We currently support three overcommit policies, which are set via the
- * vm.overcommit_memory sysctl. See Documentation/vm/overcommit-accounting
+ * vm.overcommit_memory sysctl. See Documentation/vm/overcommit-accounting.rst
*
* Strict overcommit modes added 2002 Feb 26 by Alan Cox.
* Additional code 2002 Jul 20 by Robert Love.
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index ebff729..63a5f50 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2751,25 +2751,14 @@ static const struct seq_operations vmalloc_op = {
.show = s_show,
};
-static int vmalloc_open(struct inode *inode, struct file *file)
-{
- if (IS_ENABLED(CONFIG_NUMA))
- return seq_open_private(file, &vmalloc_op,
- nr_node_ids * sizeof(unsigned int));
- else
- return seq_open(file, &vmalloc_op);
-}
-
-static const struct file_operations proc_vmalloc_operations = {
- .open = vmalloc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_private,
-};
-
static int __init proc_vmalloc_init(void)
{
- proc_create("vmallocinfo", S_IRUSR, NULL, &proc_vmalloc_operations);
+ if (IS_ENABLED(CONFIG_NUMA))
+ proc_create_seq_private("vmallocinfo", S_IRUSR, NULL,
+ &vmalloc_op,
+ nr_node_ids * sizeof(unsigned int), NULL);
+ else
+ proc_create_seq("vmallocinfo", S_IRUSR, NULL, &vmalloc_op);
return 0;
}
module_init(proc_vmalloc_init);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8b920ce..9270a43 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -303,7 +303,7 @@ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone
/*
* Add a shrinker callback to be called from the vm.
*/
-int register_shrinker(struct shrinker *shrinker)
+int prealloc_shrinker(struct shrinker *shrinker)
{
size_t size = sizeof(*shrinker->nr_deferred);
@@ -313,10 +313,29 @@ int register_shrinker(struct shrinker *shrinker)
shrinker->nr_deferred = kzalloc(size, GFP_KERNEL);
if (!shrinker->nr_deferred)
return -ENOMEM;
+ return 0;
+}
+void free_prealloced_shrinker(struct shrinker *shrinker)
+{
+ kfree(shrinker->nr_deferred);
+ shrinker->nr_deferred = NULL;
+}
+
+void register_shrinker_prepared(struct shrinker *shrinker)
+{
down_write(&shrinker_rwsem);
list_add_tail(&shrinker->list, &shrinker_list);
up_write(&shrinker_rwsem);
+}
+
+int register_shrinker(struct shrinker *shrinker)
+{
+ int err = prealloc_shrinker(shrinker);
+
+ if (err)
+ return err;
+ register_shrinker_prepared(shrinker);
return 0;
}
EXPORT_SYMBOL(register_shrinker);
@@ -1399,7 +1418,7 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
return ret;
mapping = page_mapping(page);
- migrate_dirty = mapping && mapping->a_ops->migratepage;
+ migrate_dirty = !mapping || mapping->a_ops->migratepage;
unlock_page(page);
if (!migrate_dirty)
return ret;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 536332e..75eda9c2 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1161,7 +1161,7 @@ const char * const vmstat_text[] = {
"nr_vmscan_immediate_reclaim",
"nr_dirtied",
"nr_written",
- "nr_indirectly_reclaimable",
+ "", /* nr_indirectly_reclaimable */
/* enum writeback_stat_item counters */
"nr_dirty_threshold",
@@ -1516,18 +1516,6 @@ static const struct seq_operations fragmentation_op = {
.show = frag_show,
};
-static int fragmentation_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &fragmentation_op);
-}
-
-static const struct file_operations buddyinfo_file_operations = {
- .open = fragmentation_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static const struct seq_operations pagetypeinfo_op = {
.start = frag_start,
.next = frag_next,
@@ -1535,18 +1523,6 @@ static const struct seq_operations pagetypeinfo_op = {
.show = pagetypeinfo_show,
};
-static int pagetypeinfo_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &pagetypeinfo_op);
-}
-
-static const struct file_operations pagetypeinfo_file_operations = {
- .open = pagetypeinfo_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static bool is_zone_first_populated(pg_data_t *pgdat, struct zone *zone)
{
int zid;
@@ -1663,18 +1639,6 @@ static const struct seq_operations zoneinfo_op = {
.show = zoneinfo_show,
};
-static int zoneinfo_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &zoneinfo_op);
-}
-
-static const struct file_operations zoneinfo_file_operations = {
- .open = zoneinfo_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
enum writeback_stat_item {
NR_DIRTY_THRESHOLD,
NR_DIRTY_BG_THRESHOLD,
@@ -1740,6 +1704,10 @@ static int vmstat_show(struct seq_file *m, void *arg)
unsigned long *l = arg;
unsigned long off = l - (unsigned long *)m->private;
+ /* Skip hidden vmstat items. */
+ if (*vmstat_text[off] == '\0')
+ return 0;
+
seq_puts(m, vmstat_text[off]);
seq_put_decimal_ull(m, " ", *l);
seq_putc(m, '\n');
@@ -1758,18 +1726,6 @@ static const struct seq_operations vmstat_op = {
.stop = vmstat_stop,
.show = vmstat_show,
};
-
-static int vmstat_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &vmstat_op);
-}
-
-static const struct file_operations vmstat_file_operations = {
- .open = vmstat_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
#endif /* CONFIG_PROC_FS */
#ifdef CONFIG_SMP
@@ -2016,10 +1972,10 @@ void __init init_mm_internals(void)
start_shepherd_timer();
#endif
#ifdef CONFIG_PROC_FS
- proc_create("buddyinfo", 0444, NULL, &buddyinfo_file_operations);
- proc_create("pagetypeinfo", 0444, NULL, &pagetypeinfo_file_operations);
- proc_create("vmstat", 0444, NULL, &vmstat_file_operations);
- proc_create("zoneinfo", 0444, NULL, &zoneinfo_file_operations);
+ proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op);
+ proc_create_seq("pagetypeinfo", 0444, NULL, &pagetypeinfo_op);
+ proc_create_seq("vmstat", 0444, NULL, &vmstat_op);
+ proc_create_seq("zoneinfo", 0444, NULL, &zoneinfo_op);
#endif
}
diff --git a/mm/z3fold.c b/mm/z3fold.c
index c0bca61..4b366d1 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -144,7 +144,8 @@ enum z3fold_page_flags {
PAGE_HEADLESS = 0,
MIDDLE_CHUNK_MAPPED,
NEEDS_COMPACTING,
- PAGE_STALE
+ PAGE_STALE,
+ UNDER_RECLAIM
};
/*****************
@@ -173,6 +174,7 @@ static struct z3fold_header *init_z3fold_page(struct page *page,
clear_bit(MIDDLE_CHUNK_MAPPED, &page->private);
clear_bit(NEEDS_COMPACTING, &page->private);
clear_bit(PAGE_STALE, &page->private);
+ clear_bit(UNDER_RECLAIM, &page->private);
spin_lock_init(&zhdr->page_lock);
kref_init(&zhdr->refcount);
@@ -756,6 +758,10 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
atomic64_dec(&pool->pages_nr);
return;
}
+ if (test_bit(UNDER_RECLAIM, &page->private)) {
+ z3fold_page_unlock(zhdr);
+ return;
+ }
if (test_and_set_bit(NEEDS_COMPACTING, &page->private)) {
z3fold_page_unlock(zhdr);
return;
@@ -840,6 +846,8 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
kref_get(&zhdr->refcount);
list_del_init(&zhdr->buddy);
zhdr->cpu = -1;
+ set_bit(UNDER_RECLAIM, &page->private);
+ break;
}
list_del_init(&page->lru);
@@ -887,25 +895,35 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
goto next;
}
next:
- spin_lock(&pool->lock);
if (test_bit(PAGE_HEADLESS, &page->private)) {
if (ret == 0) {
- spin_unlock(&pool->lock);
free_z3fold_page(page);
return 0;
}
- } else if (kref_put(&zhdr->refcount, release_z3fold_page)) {
- atomic64_dec(&pool->pages_nr);
+ spin_lock(&pool->lock);
+ list_add(&page->lru, &pool->lru);
spin_unlock(&pool->lock);
- return 0;
+ } else {
+ z3fold_page_lock(zhdr);
+ clear_bit(UNDER_RECLAIM, &page->private);
+ if (kref_put(&zhdr->refcount,
+ release_z3fold_page_locked)) {
+ atomic64_dec(&pool->pages_nr);
+ return 0;
+ }
+ /*
+ * if we are here, the page is still not completely
+ * free. Take the global pool lock then to be able
+ * to add it back to the lru list
+ */
+ spin_lock(&pool->lock);
+ list_add(&page->lru, &pool->lru);
+ spin_unlock(&pool->lock);
+ z3fold_page_unlock(zhdr);
}
- /*
- * Add to the beginning of LRU.
- * Pool lock has to be kept here to ensure the page has
- * not already been released
- */
- list_add(&page->lru, &pool->lru);
+ /* We started off locked to we need to lock the pool back */
+ spin_lock(&pool->lock);
}
spin_unlock(&pool->lock);
return -EAGAIN;
diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c
index a627a5d..d36e8c4 100644
--- a/net/8021q/vlanproc.c
+++ b/net/8021q/vlanproc.c
@@ -73,35 +73,6 @@ static const struct seq_operations vlan_seq_ops = {
.show = vlan_seq_show,
};
-static int vlan_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &vlan_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-static const struct file_operations vlan_fops = {
- .open = vlan_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
-/*
- * /proc/net/vlan/<device> file and inode operations
- */
-
-static int vlandev_seq_open(struct inode *inode, struct file *file)
-{
- return single_open(file, vlandev_seq_show, PDE_DATA(inode));
-}
-
-static const struct file_operations vlandev_fops = {
- .open = vlandev_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/*
* Proc filesystem directory entries.
*/
@@ -148,8 +119,9 @@ int __net_init vlan_proc_init(struct net *net)
if (!vn->proc_vlan_dir)
goto err;
- vn->proc_vlan_conf = proc_create(name_conf, S_IFREG | 0600,
- vn->proc_vlan_dir, &vlan_fops);
+ vn->proc_vlan_conf = proc_create_net(name_conf, S_IFREG | 0600,
+ vn->proc_vlan_dir, &vlan_seq_ops,
+ sizeof(struct seq_net_private));
if (!vn->proc_vlan_conf)
goto err;
return 0;
@@ -171,9 +143,8 @@ int vlan_proc_add_dev(struct net_device *vlandev)
if (!strcmp(vlandev->name, name_conf))
return -EINVAL;
- vlan->dent =
- proc_create_data(vlandev->name, S_IFREG | 0600,
- vn->proc_vlan_dir, &vlandev_fops, vlandev);
+ vlan->dent = proc_create_single_data(vlandev->name, S_IFREG | 0600,
+ vn->proc_vlan_dir, vlandev_seq_show, vlandev);
if (!vlan->dent)
return -ENOBUFS;
return 0;
diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c
index 38aa634..b718db2 100644
--- a/net/9p/trans_common.c
+++ b/net/9p/trans_common.c
@@ -16,7 +16,7 @@
#include <linux/module.h>
/**
- * p9_release_req_pages - Release pages after the transaction.
+ * p9_release_pages - Release pages after the transaction.
*/
void p9_release_pages(struct page **pages, int nr_pages)
{
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 0cfba91..588bf88 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -231,7 +231,7 @@ static void p9_conn_cancel(struct p9_conn *m, int err)
static __poll_t
p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt, int *err)
{
- __poll_t ret, n;
+ __poll_t ret;
struct p9_trans_fd *ts = NULL;
if (client && client->status == Connected)
@@ -243,19 +243,9 @@ p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt, int *err)
return EPOLLERR;
}
- if (!ts->rd->f_op->poll)
- ret = DEFAULT_POLLMASK;
- else
- ret = ts->rd->f_op->poll(ts->rd, pt);
-
- if (ts->rd != ts->wr) {
- if (!ts->wr->f_op->poll)
- n = DEFAULT_POLLMASK;
- else
- n = ts->wr->f_op->poll(ts->wr, pt);
- ret = (ret & ~EPOLLOUT) | (n & ~EPOLLIN);
- }
-
+ ret = vfs_poll(ts->rd, pt);
+ if (ts->rd != ts->wr)
+ ret = (ret & ~EPOLLOUT) | (vfs_poll(ts->wr, pt) & ~EPOLLIN);
return ret;
}
@@ -1092,8 +1082,8 @@ static struct p9_trans_module p9_fd_trans = {
};
/**
- * p9_poll_proc - poll worker thread
- * @a: thread state and arguments
+ * p9_poll_workfn - poll worker thread
+ * @work: work queue
*
* polls all v9fs transports for new events and queues the appropriate
* work to the work queue
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index 6d8e303..3d414ac 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -68,8 +68,6 @@
* @pd: Protection Domain pointer
* @qp: Queue Pair pointer
* @cq: Completion Queue pointer
- * @dm_mr: DMA Memory Region pointer
- * @lkey: The local access only memory region key
* @timeout: Number of uSecs to wait for connection management events
* @privport: Whether a privileged port may be used
* @port: The port to use
@@ -632,7 +630,7 @@ static int p9_rdma_bind_privport(struct p9_trans_rdma *rdma)
}
/**
- * trans_create_rdma - Transport method for creating atransport instance
+ * rdma_create_trans - Transport method for creating a transport instance
* @client: client instance
* @addr: IP address string
* @args: Mount options string
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 3aa5a93..4d03722 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -60,7 +60,6 @@ static atomic_t vp_pinned = ATOMIC_INIT(0);
/**
* struct virtio_chan - per-instance transport information
- * @initialized: whether the channel is initialized
* @inuse: whether the channel is in use
* @lock: protects multiple elements within this structure
* @client: client instance
@@ -385,8 +384,8 @@ static int p9_get_mapped_pages(struct virtio_chan *chan,
* @uidata: user bffer that should be ued for zero copy read
* @uodata: user buffer that shoud be user for zero copy write
* @inlen: read buffer size
- * @olen: write buffer size
- * @hdrlen: reader header size, This is the size of response protocol data
+ * @outlen: write buffer size
+ * @in_hdr_len: reader header size, This is the size of response protocol data
*
*/
static int
diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c
index 086a4ab..0f19960 100644
--- a/net/9p/trans_xen.c
+++ b/net/9p/trans_xen.c
@@ -485,7 +485,7 @@ static int xen_9pfs_front_probe(struct xenbus_device *dev,
static int xen_9pfs_front_resume(struct xenbus_device *dev)
{
- dev_warn(&dev->dev, "suspsend/resume unsupported\n");
+ dev_warn(&dev->dev, "suspend/resume unsupported\n");
return 0;
}
diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c
index d4c1021..49a16ce 100644
--- a/net/appletalk/aarp.c
+++ b/net/appletalk/aarp.c
@@ -907,11 +907,6 @@ void aarp_device_down(struct net_device *dev)
}
#ifdef CONFIG_PROC_FS
-struct aarp_iter_state {
- int bucket;
- struct aarp_entry **table;
-};
-
/*
* Get the aarp entry that is in the chain described
* by the iterator.
@@ -1033,25 +1028,12 @@ static int aarp_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static const struct seq_operations aarp_seq_ops = {
+const struct seq_operations aarp_seq_ops = {
.start = aarp_seq_start,
.next = aarp_seq_next,
.stop = aarp_seq_stop,
.show = aarp_seq_show,
};
-
-static int aarp_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_private(file, &aarp_seq_ops,
- sizeof(struct aarp_iter_state));
-}
-
-const struct file_operations atalk_seq_arp_fops = {
- .open = aarp_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_private,
-};
#endif
/* General module cleanup. Called from cleanup_module() in ddp.c. */
diff --git a/net/appletalk/atalk_proc.c b/net/appletalk/atalk_proc.c
index 7214aea..8006295 100644
--- a/net/appletalk/atalk_proc.c
+++ b/net/appletalk/atalk_proc.c
@@ -210,42 +210,6 @@ static const struct seq_operations atalk_seq_socket_ops = {
.show = atalk_seq_socket_show,
};
-static int atalk_seq_interface_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &atalk_seq_interface_ops);
-}
-
-static int atalk_seq_route_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &atalk_seq_route_ops);
-}
-
-static int atalk_seq_socket_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &atalk_seq_socket_ops);
-}
-
-static const struct file_operations atalk_seq_interface_fops = {
- .open = atalk_seq_interface_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-static const struct file_operations atalk_seq_route_fops = {
- .open = atalk_seq_route_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-static const struct file_operations atalk_seq_socket_fops = {
- .open = atalk_seq_socket_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static struct proc_dir_entry *atalk_proc_dir;
int __init atalk_proc_init(void)
@@ -257,22 +221,23 @@ int __init atalk_proc_init(void)
if (!atalk_proc_dir)
goto out;
- p = proc_create("interface", 0444, atalk_proc_dir,
- &atalk_seq_interface_fops);
+ p = proc_create_seq("interface", 0444, atalk_proc_dir,
+ &atalk_seq_interface_ops);
if (!p)
goto out_interface;
- p = proc_create("route", 0444, atalk_proc_dir,
- &atalk_seq_route_fops);
+ p = proc_create_seq("route", 0444, atalk_proc_dir,
+ &atalk_seq_route_ops);
if (!p)
goto out_route;
- p = proc_create("socket", 0444, atalk_proc_dir,
- &atalk_seq_socket_fops);
+ p = proc_create_seq("socket", 0444, atalk_proc_dir,
+ &atalk_seq_socket_ops);
if (!p)
goto out_socket;
- p = proc_create("arp", 0444, atalk_proc_dir, &atalk_seq_arp_fops);
+ p = proc_create_seq_private("arp", 0444, atalk_proc_dir, &aarp_seq_ops,
+ sizeof(struct aarp_iter_state), NULL);
if (!p)
goto out_arp;
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 9b6bc5a..55fdba0 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1869,7 +1869,7 @@ static const struct proto_ops atalk_dgram_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = atalk_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = atalk_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = atalk_compat_ioctl,
diff --git a/net/atm/br2684.c b/net/atm/br2684.c
index fd94bea..36b3ada 100644
--- a/net/atm/br2684.c
+++ b/net/atm/br2684.c
@@ -818,18 +818,6 @@ static const struct seq_operations br2684_seq_ops = {
.show = br2684_seq_show,
};
-static int br2684_proc_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &br2684_seq_ops);
-}
-
-static const struct file_operations br2684_proc_ops = {
- .open = br2684_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
extern struct proc_dir_entry *atm_proc_root; /* from proc.c */
#endif /* CONFIG_PROC_FS */
@@ -837,7 +825,7 @@ static int __init br2684_init(void)
{
#ifdef CONFIG_PROC_FS
struct proc_dir_entry *p;
- p = proc_create("br2684", 0, atm_proc_root, &br2684_proc_ops);
+ p = proc_create_seq("br2684", 0, atm_proc_root, &br2684_seq_ops);
if (p == NULL)
return -ENOMEM;
#endif
diff --git a/net/atm/clip.c b/net/atm/clip.c
index f07dbc6..66caa48 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -863,20 +863,6 @@ static const struct seq_operations arp_seq_ops = {
.stop = neigh_seq_stop,
.show = clip_seq_show,
};
-
-static int arp_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &arp_seq_ops,
- sizeof(struct clip_seq_state));
-}
-
-static const struct file_operations arp_seq_fops = {
- .open = arp_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
- .owner = THIS_MODULE
-};
#endif
static void atm_clip_exit_noproc(void);
@@ -893,7 +879,8 @@ static int __init atm_clip_init(void)
{
struct proc_dir_entry *p;
- p = proc_create("arp", 0444, atm_proc_root, &arp_seq_fops);
+ p = proc_create_net("arp", 0444, atm_proc_root, &arp_seq_ops,
+ sizeof(struct clip_seq_state));
if (!p) {
pr_err("Unable to initialize /proc/net/atm/arp\n");
atm_clip_exit_noproc();
diff --git a/net/atm/common.c b/net/atm/common.c
index fc78a05..1f2af59 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -648,16 +648,11 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size)
return error;
}
-__poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait)
+__poll_t vcc_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
- struct atm_vcc *vcc;
- __poll_t mask;
-
- sock_poll_wait(file, sk_sleep(sk), wait);
- mask = 0;
-
- vcc = ATM_SD(sock);
+ struct atm_vcc *vcc = ATM_SD(sock);
+ __poll_t mask = 0;
/* exceptional events */
if (sk->sk_err)
diff --git a/net/atm/common.h b/net/atm/common.h
index 58506490..526796a 100644
--- a/net/atm/common.h
+++ b/net/atm/common.h
@@ -17,7 +17,7 @@ int vcc_connect(struct socket *sock, int itf, short vpi, int vci);
int vcc_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int flags);
int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len);
-__poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait);
+__poll_t vcc_poll_mask(struct socket *sock, __poll_t events);
int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
int vcc_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
int vcc_setsockopt(struct socket *sock, int level, int optname,
diff --git a/net/atm/lec.c b/net/atm/lec.c
index 01d5d20..5a95fcf 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -41,6 +41,9 @@ static unsigned char bridge_ula_lec[] = { 0x01, 0x80, 0xc2, 0x00, 0x00 };
#include <linux/module.h>
#include <linux/init.h>
+/* Hardening for Spectre-v1 */
+#include <linux/nospec.h>
+
#include "lec.h"
#include "lec_arpc.h"
#include "resources.h"
@@ -687,8 +690,10 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg)
bytes_left = copy_from_user(&ioc_data, arg, sizeof(struct atmlec_ioc));
if (bytes_left != 0)
pr_info("copy from user failed for %d bytes\n", bytes_left);
- if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF ||
- !dev_lec[ioc_data.dev_num])
+ if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF)
+ return -EINVAL;
+ ioc_data.dev_num = array_index_nospec(ioc_data.dev_num, MAX_LEC_ITF);
+ if (!dev_lec[ioc_data.dev_num])
return -EINVAL;
vpriv = kmalloc(sizeof(struct lec_vcc_priv), GFP_KERNEL);
if (!vpriv)
@@ -985,18 +990,6 @@ static const struct seq_operations lec_seq_ops = {
.stop = lec_seq_stop,
.show = lec_seq_show,
};
-
-static int lec_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_private(file, &lec_seq_ops, sizeof(struct lec_state));
-}
-
-static const struct file_operations lec_seq_fops = {
- .open = lec_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_private,
-};
#endif
static int lane_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
@@ -1042,7 +1035,8 @@ static int __init lane_module_init(void)
#ifdef CONFIG_PROC_FS
struct proc_dir_entry *p;
- p = proc_create("lec", 0444, atm_proc_root, &lec_seq_fops);
+ p = proc_create_seq_private("lec", 0444, atm_proc_root, &lec_seq_ops,
+ sizeof(struct lec_state), NULL);
if (!p) {
pr_err("Unable to initialize /proc/net/atm/lec\n");
return -ENOMEM;
diff --git a/net/atm/proc.c b/net/atm/proc.c
index 55410c0..0b0495a 100644
--- a/net/atm/proc.c
+++ b/net/atm/proc.c
@@ -68,7 +68,6 @@ static void atm_dev_info(struct seq_file *seq, const struct atm_dev *dev)
struct vcc_state {
int bucket;
struct sock *sk;
- int family;
};
static inline int compare_family(struct sock *sk, int family)
@@ -106,25 +105,15 @@ static int __vcc_walk(struct sock **sock, int family, int *bucket, loff_t l)
return (l < 0);
}
-static inline void *vcc_walk(struct vcc_state *state, loff_t l)
+static inline void *vcc_walk(struct seq_file *seq, loff_t l)
{
- return __vcc_walk(&state->sk, state->family, &state->bucket, l) ?
+ struct vcc_state *state = seq->private;
+ int family = (uintptr_t)(PDE_DATA(file_inode(seq->file)));
+
+ return __vcc_walk(&state->sk, family, &state->bucket, l) ?
state : NULL;
}
-static int __vcc_seq_open(struct inode *inode, struct file *file,
- int family, const struct seq_operations *ops)
-{
- struct vcc_state *state;
-
- state = __seq_open_private(file, ops, sizeof(*state));
- if (state == NULL)
- return -ENOMEM;
-
- state->family = family;
- return 0;
-}
-
static void *vcc_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(vcc_sklist_lock)
{
@@ -133,7 +122,7 @@ static void *vcc_seq_start(struct seq_file *seq, loff_t *pos)
read_lock(&vcc_sklist_lock);
state->sk = SEQ_START_TOKEN;
- return left ? vcc_walk(state, left) : SEQ_START_TOKEN;
+ return left ? vcc_walk(seq, left) : SEQ_START_TOKEN;
}
static void vcc_seq_stop(struct seq_file *seq, void *v)
@@ -144,9 +133,7 @@ static void vcc_seq_stop(struct seq_file *seq, void *v)
static void *vcc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct vcc_state *state = seq->private;
-
- v = vcc_walk(state, 1);
+ v = vcc_walk(seq, 1);
*pos += !!PTR_ERR(v);
return v;
}
@@ -257,18 +244,6 @@ static const struct seq_operations atm_dev_seq_ops = {
.show = atm_dev_seq_show,
};
-static int atm_dev_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &atm_dev_seq_ops);
-}
-
-static const struct file_operations devices_seq_fops = {
- .open = atm_dev_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static int pvc_seq_show(struct seq_file *seq, void *v)
{
static char atm_pvc_banner[] =
@@ -292,18 +267,6 @@ static const struct seq_operations pvc_seq_ops = {
.show = pvc_seq_show,
};
-static int pvc_seq_open(struct inode *inode, struct file *file)
-{
- return __vcc_seq_open(inode, file, PF_ATMPVC, &pvc_seq_ops);
-}
-
-static const struct file_operations pvc_seq_fops = {
- .open = pvc_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_private,
-};
-
static int vcc_seq_show(struct seq_file *seq, void *v)
{
if (v == SEQ_START_TOKEN) {
@@ -326,18 +289,6 @@ static const struct seq_operations vcc_seq_ops = {
.show = vcc_seq_show,
};
-static int vcc_seq_open(struct inode *inode, struct file *file)
-{
- return __vcc_seq_open(inode, file, 0, &vcc_seq_ops);
-}
-
-static const struct file_operations vcc_seq_fops = {
- .open = vcc_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_private,
-};
-
static int svc_seq_show(struct seq_file *seq, void *v)
{
static const char atm_svc_banner[] =
@@ -361,18 +312,6 @@ static const struct seq_operations svc_seq_ops = {
.show = svc_seq_show,
};
-static int svc_seq_open(struct inode *inode, struct file *file)
-{
- return __vcc_seq_open(inode, file, PF_ATMSVC, &svc_seq_ops);
-}
-
-static const struct file_operations svc_seq_fops = {
- .open = svc_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_private,
-};
-
static ssize_t proc_dev_atm_read(struct file *file, char __user *buf,
size_t count, loff_t *pos)
{
@@ -440,58 +379,22 @@ void atm_proc_dev_deregister(struct atm_dev *dev)
kfree(dev->proc_name);
}
-static struct atm_proc_entry {
- char *name;
- const struct file_operations *proc_fops;
- struct proc_dir_entry *dirent;
-} atm_proc_ents[] = {
- { .name = "devices", .proc_fops = &devices_seq_fops },
- { .name = "pvc", .proc_fops = &pvc_seq_fops },
- { .name = "svc", .proc_fops = &svc_seq_fops },
- { .name = "vc", .proc_fops = &vcc_seq_fops },
- { .name = NULL, .proc_fops = NULL }
-};
-
-static void atm_proc_dirs_remove(void)
-{
- static struct atm_proc_entry *e;
-
- for (e = atm_proc_ents; e->name; e++) {
- if (e->dirent)
- remove_proc_entry(e->name, atm_proc_root);
- }
- remove_proc_entry("atm", init_net.proc_net);
-}
-
int __init atm_proc_init(void)
{
- static struct atm_proc_entry *e;
- int ret;
-
atm_proc_root = proc_net_mkdir(&init_net, "atm", init_net.proc_net);
if (!atm_proc_root)
- goto err_out;
- for (e = atm_proc_ents; e->name; e++) {
- struct proc_dir_entry *dirent;
-
- dirent = proc_create(e->name, 0444,
- atm_proc_root, e->proc_fops);
- if (!dirent)
- goto err_out_remove;
- e->dirent = dirent;
- }
- ret = 0;
-out:
- return ret;
-
-err_out_remove:
- atm_proc_dirs_remove();
-err_out:
- ret = -ENOMEM;
- goto out;
+ return -ENOMEM;
+ proc_create_seq("devices", 0444, atm_proc_root, &atm_dev_seq_ops);
+ proc_create_seq_private("pvc", 0444, atm_proc_root, &pvc_seq_ops,
+ sizeof(struct vcc_state), (void *)(uintptr_t)PF_ATMPVC);
+ proc_create_seq_private("svc", 0444, atm_proc_root, &svc_seq_ops,
+ sizeof(struct vcc_state), (void *)(uintptr_t)PF_ATMSVC);
+ proc_create_seq_private("vc", 0444, atm_proc_root, &vcc_seq_ops,
+ sizeof(struct vcc_state), NULL);
+ return 0;
}
void atm_proc_exit(void)
{
- atm_proc_dirs_remove();
+ remove_proc_subtree("atm", init_net.proc_net);
}
diff --git a/net/atm/pvc.c b/net/atm/pvc.c
index 2cb10af..9f75092 100644
--- a/net/atm/pvc.c
+++ b/net/atm/pvc.c
@@ -113,7 +113,7 @@ static const struct proto_ops pvc_proto_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = pvc_getname,
- .poll = vcc_poll,
+ .poll_mask = vcc_poll_mask,
.ioctl = vcc_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = vcc_compat_ioctl,
diff --git a/net/atm/svc.c b/net/atm/svc.c
index 2f91b76..53f4ad7 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -636,7 +636,7 @@ static const struct proto_ops svc_proto_ops = {
.socketpair = sock_no_socketpair,
.accept = svc_accept,
.getname = svc_getname,
- .poll = vcc_poll,
+ .poll_mask = vcc_poll_mask,
.ioctl = svc_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = svc_compat_ioctl,
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 2b41366..d1d2442 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1924,19 +1924,6 @@ static const struct seq_operations ax25_info_seqops = {
.stop = ax25_info_stop,
.show = ax25_info_show,
};
-
-static int ax25_info_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &ax25_info_seqops);
-}
-
-static const struct file_operations ax25_info_fops = {
- .open = ax25_info_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
#endif
static const struct net_proto_family ax25_family_ops = {
@@ -1954,7 +1941,7 @@ static const struct proto_ops ax25_proto_ops = {
.socketpair = sock_no_socketpair,
.accept = ax25_accept,
.getname = ax25_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = ax25_ioctl,
.listen = ax25_listen,
.shutdown = ax25_shutdown,
@@ -1989,10 +1976,10 @@ static int __init ax25_init(void)
dev_add_pack(&ax25_packet_type);
register_netdevice_notifier(&ax25_dev_notifier);
- proc_create("ax25_route", 0444, init_net.proc_net,
- &ax25_route_fops);
- proc_create("ax25", 0444, init_net.proc_net, &ax25_info_fops);
- proc_create("ax25_calls", 0444, init_net.proc_net, &ax25_uid_fops);
+ proc_create_seq("ax25_route", 0444, init_net.proc_net, &ax25_rt_seqops);
+ proc_create_seq("ax25", 0444, init_net.proc_net, &ax25_info_seqops);
+ proc_create_seq("ax25_calls", 0444, init_net.proc_net,
+ &ax25_uid_seqops);
out:
return rc;
}
diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c
index 5255589..a0eff32 100644
--- a/net/ax25/ax25_route.c
+++ b/net/ax25/ax25_route.c
@@ -323,25 +323,12 @@ static int ax25_rt_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static const struct seq_operations ax25_rt_seqops = {
+const struct seq_operations ax25_rt_seqops = {
.start = ax25_rt_seq_start,
.next = ax25_rt_seq_next,
.stop = ax25_rt_seq_stop,
.show = ax25_rt_seq_show,
};
-
-static int ax25_rt_info_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &ax25_rt_seqops);
-}
-
-const struct file_operations ax25_route_fops = {
- .open = ax25_rt_info_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
#endif
/*
diff --git a/net/ax25/ax25_uid.c b/net/ax25/ax25_uid.c
index 4ebe91b..99d02e3 100644
--- a/net/ax25/ax25_uid.c
+++ b/net/ax25/ax25_uid.c
@@ -181,25 +181,12 @@ static int ax25_uid_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static const struct seq_operations ax25_uid_seqops = {
+const struct seq_operations ax25_uid_seqops = {
.start = ax25_uid_seq_start,
.next = ax25_uid_seq_next,
.stop = ax25_uid_seq_stop,
.show = ax25_uid_seq_show,
};
-
-static int ax25_uid_info_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &ax25_uid_seqops);
-}
-
-const struct file_operations ax25_uid_fops = {
- .open = ax25_uid_info_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
#endif
/*
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index a11d3d8..a35f597 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -1536,7 +1536,7 @@ batadv_mcast_netlink_get_primary(struct netlink_callback *cb,
if (!ret && primary_if)
*primary_if = hard_iface;
- else
+ else if (hard_iface)
batadv_hardif_put(hard_iface);
return ret;
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 0225616..3986551 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -862,7 +862,7 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node,
struct batadv_orig_node_vlan *vlan;
u8 *tt_change_ptr;
- rcu_read_lock();
+ spin_lock_bh(&orig_node->vlan_list_lock);
hlist_for_each_entry_rcu(vlan, &orig_node->vlan_list, list) {
num_vlan++;
num_entries += atomic_read(&vlan->tt.num_entries);
@@ -900,7 +900,7 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node,
*tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr;
out:
- rcu_read_unlock();
+ spin_unlock_bh(&orig_node->vlan_list_lock);
return tvlv_len;
}
@@ -931,15 +931,20 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv,
struct batadv_tvlv_tt_vlan_data *tt_vlan;
struct batadv_softif_vlan *vlan;
u16 num_vlan = 0;
- u16 num_entries = 0;
+ u16 vlan_entries = 0;
+ u16 total_entries = 0;
u16 tvlv_len;
u8 *tt_change_ptr;
int change_offset;
- rcu_read_lock();
+ spin_lock_bh(&bat_priv->softif_vlan_list_lock);
hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) {
+ vlan_entries = atomic_read(&vlan->tt.num_entries);
+ if (vlan_entries < 1)
+ continue;
+
num_vlan++;
- num_entries += atomic_read(&vlan->tt.num_entries);
+ total_entries += vlan_entries;
}
change_offset = sizeof(**tt_data);
@@ -947,7 +952,7 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv,
/* if tt_len is negative, allocate the space needed by the full table */
if (*tt_len < 0)
- *tt_len = batadv_tt_len(num_entries);
+ *tt_len = batadv_tt_len(total_entries);
tvlv_len = *tt_len;
tvlv_len += change_offset;
@@ -964,6 +969,10 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv,
tt_vlan = (struct batadv_tvlv_tt_vlan_data *)(*tt_data + 1);
hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) {
+ vlan_entries = atomic_read(&vlan->tt.num_entries);
+ if (vlan_entries < 1)
+ continue;
+
tt_vlan->vid = htons(vlan->vid);
tt_vlan->crc = htonl(vlan->tt.crc);
@@ -974,7 +983,7 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv,
*tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr;
out:
- rcu_read_unlock();
+ spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
return tvlv_len;
}
@@ -1538,6 +1547,8 @@ batadv_tt_global_orig_entry_find(const struct batadv_tt_global_entry *entry,
* handled by a given originator
* @entry: the TT global entry to check
* @orig_node: the originator to search in the list
+ * @flags: a pointer to store TT flags for the given @entry received
+ * from @orig_node
*
* find out if an orig_node is already in the list of a tt_global_entry.
*
@@ -1545,7 +1556,8 @@ batadv_tt_global_orig_entry_find(const struct batadv_tt_global_entry *entry,
*/
static bool
batadv_tt_global_entry_has_orig(const struct batadv_tt_global_entry *entry,
- const struct batadv_orig_node *orig_node)
+ const struct batadv_orig_node *orig_node,
+ u8 *flags)
{
struct batadv_tt_orig_list_entry *orig_entry;
bool found = false;
@@ -1553,6 +1565,10 @@ batadv_tt_global_entry_has_orig(const struct batadv_tt_global_entry *entry,
orig_entry = batadv_tt_global_orig_entry_find(entry, orig_node);
if (orig_entry) {
found = true;
+
+ if (flags)
+ *flags = orig_entry->flags;
+
batadv_tt_orig_list_entry_put(orig_entry);
}
@@ -1731,7 +1747,7 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv,
if (!(common->flags & BATADV_TT_CLIENT_TEMP))
goto out;
if (batadv_tt_global_entry_has_orig(tt_global_entry,
- orig_node))
+ orig_node, NULL))
goto out_remove;
batadv_tt_global_del_orig_list(tt_global_entry);
goto add_orig_entry;
@@ -2880,23 +2896,46 @@ batadv_tt_req_node_new(struct batadv_priv *bat_priv,
}
/**
- * batadv_tt_local_valid() - verify that given tt entry is a valid one
+ * batadv_tt_local_valid() - verify local tt entry and get flags
* @entry_ptr: to be checked local tt entry
* @data_ptr: not used but definition required to satisfy the callback prototype
+ * @flags: a pointer to store TT flags for this client to
+ *
+ * Checks the validity of the given local TT entry. If it is, then the provided
+ * flags pointer is updated.
*
* Return: true if the entry is a valid, false otherwise.
*/
-static bool batadv_tt_local_valid(const void *entry_ptr, const void *data_ptr)
+static bool batadv_tt_local_valid(const void *entry_ptr,
+ const void *data_ptr,
+ u8 *flags)
{
const struct batadv_tt_common_entry *tt_common_entry = entry_ptr;
if (tt_common_entry->flags & BATADV_TT_CLIENT_NEW)
return false;
+
+ if (flags)
+ *flags = tt_common_entry->flags;
+
return true;
}
+/**
+ * batadv_tt_global_valid() - verify global tt entry and get flags
+ * @entry_ptr: to be checked global tt entry
+ * @data_ptr: an orig_node object (may be NULL)
+ * @flags: a pointer to store TT flags for this client to
+ *
+ * Checks the validity of the given global TT entry. If it is, then the provided
+ * flags pointer is updated either with the common (summed) TT flags if data_ptr
+ * is NULL or the specific, per originator TT flags otherwise.
+ *
+ * Return: true if the entry is a valid, false otherwise.
+ */
static bool batadv_tt_global_valid(const void *entry_ptr,
- const void *data_ptr)
+ const void *data_ptr,
+ u8 *flags)
{
const struct batadv_tt_common_entry *tt_common_entry = entry_ptr;
const struct batadv_tt_global_entry *tt_global_entry;
@@ -2910,7 +2949,8 @@ static bool batadv_tt_global_valid(const void *entry_ptr,
struct batadv_tt_global_entry,
common);
- return batadv_tt_global_entry_has_orig(tt_global_entry, orig_node);
+ return batadv_tt_global_entry_has_orig(tt_global_entry, orig_node,
+ flags);
}
/**
@@ -2920,25 +2960,34 @@ static bool batadv_tt_global_valid(const void *entry_ptr,
* @hash: hash table containing the tt entries
* @tt_len: expected tvlv tt data buffer length in number of bytes
* @tvlv_buff: pointer to the buffer to fill with the TT data
- * @valid_cb: function to filter tt change entries
+ * @valid_cb: function to filter tt change entries and to return TT flags
* @cb_data: data passed to the filter function as argument
+ *
+ * Fills the tvlv buff with the tt entries from the specified hash. If valid_cb
+ * is not provided then this becomes a no-op.
*/
static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv,
struct batadv_hashtable *hash,
void *tvlv_buff, u16 tt_len,
bool (*valid_cb)(const void *,
- const void *),
+ const void *,
+ u8 *flags),
void *cb_data)
{
struct batadv_tt_common_entry *tt_common_entry;
struct batadv_tvlv_tt_change *tt_change;
struct hlist_head *head;
u16 tt_tot, tt_num_entries = 0;
+ u8 flags;
+ bool ret;
u32 i;
tt_tot = batadv_tt_entries(tt_len);
tt_change = (struct batadv_tvlv_tt_change *)tvlv_buff;
+ if (!valid_cb)
+ return;
+
rcu_read_lock();
for (i = 0; i < hash->size; i++) {
head = &hash->table[i];
@@ -2948,11 +2997,12 @@ static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv,
if (tt_tot == tt_num_entries)
break;
- if ((valid_cb) && (!valid_cb(tt_common_entry, cb_data)))
+ ret = valid_cb(tt_common_entry, cb_data, &flags);
+ if (!ret)
continue;
ether_addr_copy(tt_change->addr, tt_common_entry->addr);
- tt_change->flags = tt_common_entry->flags;
+ tt_change->flags = flags;
tt_change->vid = htons(tt_common_entry->vid);
memset(tt_change->reserved, 0,
sizeof(tt_change->reserved));
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 84d92a0..510ab4f 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -437,16 +437,13 @@ static inline __poll_t bt_accept_poll(struct sock *parent)
return 0;
}
-__poll_t bt_sock_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+__poll_t bt_sock_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
__poll_t mask = 0;
BT_DBG("sock %p, sk %p", sock, sk);
- poll_wait(file, sk_sleep(sk), wait);
-
if (sk->sk_state == BT_LISTEN)
return bt_accept_poll(sk);
@@ -478,7 +475,7 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock,
return mask;
}
-EXPORT_SYMBOL(bt_sock_poll);
+EXPORT_SYMBOL(bt_sock_poll_mask);
int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
@@ -605,15 +602,10 @@ int bt_sock_wait_ready(struct sock *sk, unsigned long flags)
EXPORT_SYMBOL(bt_sock_wait_ready);
#ifdef CONFIG_PROC_FS
-struct bt_seq_state {
- struct bt_sock_list *l;
-};
-
static void *bt_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(seq->private->l->lock)
{
- struct bt_seq_state *s = seq->private;
- struct bt_sock_list *l = s->l;
+ struct bt_sock_list *l = PDE_DATA(file_inode(seq->file));
read_lock(&l->lock);
return seq_hlist_start_head(&l->head, *pos);
@@ -621,8 +613,7 @@ static void *bt_seq_start(struct seq_file *seq, loff_t *pos)
static void *bt_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct bt_seq_state *s = seq->private;
- struct bt_sock_list *l = s->l;
+ struct bt_sock_list *l = PDE_DATA(file_inode(seq->file));
return seq_hlist_next(v, &l->head, pos);
}
@@ -630,16 +621,14 @@ static void *bt_seq_next(struct seq_file *seq, void *v, loff_t *pos)
static void bt_seq_stop(struct seq_file *seq, void *v)
__releases(seq->private->l->lock)
{
- struct bt_seq_state *s = seq->private;
- struct bt_sock_list *l = s->l;
+ struct bt_sock_list *l = PDE_DATA(file_inode(seq->file));
read_unlock(&l->lock);
}
static int bt_seq_show(struct seq_file *seq, void *v)
{
- struct bt_seq_state *s = seq->private;
- struct bt_sock_list *l = s->l;
+ struct bt_sock_list *l = PDE_DATA(file_inode(seq->file));
if (v == SEQ_START_TOKEN) {
seq_puts(seq ,"sk RefCnt Rmem Wmem User Inode Parent");
@@ -681,35 +670,13 @@ static const struct seq_operations bt_seq_ops = {
.show = bt_seq_show,
};
-static int bt_seq_open(struct inode *inode, struct file *file)
-{
- struct bt_sock_list *sk_list;
- struct bt_seq_state *s;
-
- sk_list = PDE_DATA(inode);
- s = __seq_open_private(file, &bt_seq_ops,
- sizeof(struct bt_seq_state));
- if (!s)
- return -ENOMEM;
-
- s->l = sk_list;
- return 0;
-}
-
-static const struct file_operations bt_fops = {
- .open = bt_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_private
-};
-
int bt_procfs_init(struct net *net, const char *name,
struct bt_sock_list *sk_list,
int (* seq_show)(struct seq_file *, void *))
{
sk_list->custom_seq_show = seq_show;
- if (!proc_create_data(name, 0, net->proc_net, &bt_fops, sk_list))
+ if (!proc_create_seq_data(name, 0, net->proc_net, &bt_seq_ops, sk_list))
return -ENOMEM;
return 0;
}
diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c
index b5116fa..00deacd 100644
--- a/net/bluetooth/bnep/sock.c
+++ b/net/bluetooth/bnep/sock.c
@@ -175,7 +175,6 @@ static const struct proto_ops bnep_sock_ops = {
.getname = sock_no_getname,
.sendmsg = sock_no_sendmsg,
.recvmsg = sock_no_recvmsg,
- .poll = sock_no_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c
index 426a92f..eb415560 100644
--- a/net/bluetooth/cmtp/capi.c
+++ b/net/bluetooth/cmtp/capi.c
@@ -521,18 +521,6 @@ static int cmtp_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int cmtp_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, cmtp_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations cmtp_proc_fops = {
- .open = cmtp_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
int cmtp_attach_device(struct cmtp_session *session)
{
unsigned char buf[4];
@@ -571,7 +559,7 @@ int cmtp_attach_device(struct cmtp_session *session)
session->ctrl.send_message = cmtp_send_message;
session->ctrl.procinfo = cmtp_procinfo;
- session->ctrl.proc_fops = &cmtp_proc_fops;
+ session->ctrl.proc_show = cmtp_proc_show;
if (attach_capi_ctr(&session->ctrl) < 0) {
BT_ERR("Can't attach new controller");
diff --git a/net/bluetooth/cmtp/sock.c b/net/bluetooth/cmtp/sock.c
index ce86a7b..e08f28fa 100644
--- a/net/bluetooth/cmtp/sock.c
+++ b/net/bluetooth/cmtp/sock.c
@@ -178,7 +178,6 @@ static const struct proto_ops cmtp_sock_ops = {
.getname = sock_no_getname,
.sendmsg = sock_no_sendmsg,
.recvmsg = sock_no_recvmsg,
- .poll = sock_no_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 1506e16..d6c0998 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -1975,7 +1975,7 @@ static const struct proto_ops hci_sock_ops = {
.sendmsg = hci_sock_sendmsg,
.recvmsg = hci_sock_recvmsg,
.ioctl = hci_sock_ioctl,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = hci_sock_setsockopt,
diff --git a/net/bluetooth/hidp/sock.c b/net/bluetooth/hidp/sock.c
index 008ba43..1eaac01 100644
--- a/net/bluetooth/hidp/sock.c
+++ b/net/bluetooth/hidp/sock.c
@@ -208,7 +208,6 @@ static const struct proto_ops hidp_sock_ops = {
.getname = sock_no_getname,
.sendmsg = sock_no_sendmsg,
.recvmsg = sock_no_recvmsg,
- .poll = sock_no_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 686bdc6..742a190 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1653,7 +1653,7 @@ static const struct proto_ops l2cap_sock_ops = {
.getname = l2cap_sock_getname,
.sendmsg = l2cap_sock_sendmsg,
.recvmsg = l2cap_sock_recvmsg,
- .poll = bt_sock_poll,
+ .poll_mask = bt_sock_poll_mask,
.ioctl = bt_sock_ioctl,
.mmap = sock_no_mmap,
.socketpair = sock_no_socketpair,
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index d606e92..1cf5762 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -1049,7 +1049,7 @@ static const struct proto_ops rfcomm_sock_ops = {
.setsockopt = rfcomm_sock_setsockopt,
.getsockopt = rfcomm_sock_getsockopt,
.ioctl = rfcomm_sock_ioctl,
- .poll = bt_sock_poll,
+ .poll_mask = bt_sock_poll_mask,
.socketpair = sock_no_socketpair,
.mmap = sock_no_mmap
};
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 413b8ee..d60dbc6 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -1197,7 +1197,7 @@ static const struct proto_ops sco_sock_ops = {
.getname = sco_sock_getname,
.sendmsg = sco_sock_sendmsg,
.recvmsg = sco_sock_recvmsg,
- .poll = bt_sock_poll,
+ .poll_mask = bt_sock_poll_mask,
.ioctl = bt_sock_ioctl,
.mmap = sock_no_mmap,
.socketpair = sock_no_socketpair,
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 82c1a6f..5bb6681 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -518,8 +518,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
return -ELOOP;
}
- /* Device is already being bridged */
- if (br_port_exists(dev))
+ /* Device has master upper dev */
+ if (netdev_master_upper_dev_get(dev))
return -EBUSY;
/* No bridging devices that dislike that (e.g. wireless) */
diff --git a/net/bridge/netfilter/ebt_stp.c b/net/bridge/netfilter/ebt_stp.c
index 47ba98d..46c1fe7 100644
--- a/net/bridge/netfilter/ebt_stp.c
+++ b/net/bridge/netfilter/ebt_stp.c
@@ -161,8 +161,8 @@ static int ebt_stp_mt_check(const struct xt_mtchk_param *par)
/* Make sure the match only receives stp frames */
if (!par->nft_compat &&
(!ether_addr_equal(e->destmac, eth_stp_addr) ||
- !is_broadcast_ether_addr(e->destmsk) ||
- !(e->bitmask & EBT_DESTMAC)))
+ !(e->bitmask & EBT_DESTMAC) ||
+ !is_broadcast_ether_addr(e->destmsk)))
return -EINVAL;
return 0;
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 032e0fe4..6ba639f 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1825,13 +1825,14 @@ static int compat_table_info(const struct ebt_table_info *info,
{
unsigned int size = info->entries_size;
const void *entries = info->entries;
- int ret;
newinfo->entries_size = size;
-
- ret = xt_compat_init_offsets(NFPROTO_BRIDGE, info->nentries);
- if (ret)
- return ret;
+ if (info->nentries) {
+ int ret = xt_compat_init_offsets(NFPROTO_BRIDGE,
+ info->nentries);
+ if (ret)
+ return ret;
+ }
return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info,
entries, newinfo);
@@ -1953,7 +1954,8 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt,
int off, pad = 0;
unsigned int size_kern, match_size = mwt->match_size;
- strlcpy(name, mwt->u.name, sizeof(name));
+ if (strscpy(name, mwt->u.name, sizeof(name)) < 0)
+ return -EINVAL;
if (state->buf_kern_start)
dst = state->buf_kern_start + state->buf_kern_offset;
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index a6fb1b3..c799186 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -934,15 +934,11 @@ static int caif_release(struct socket *sock)
}
/* Copied from af_unix.c:unix_poll(), added CAIF tx_flow handling */
-static __poll_t caif_poll(struct file *file,
- struct socket *sock, poll_table *wait)
+static __poll_t caif_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
- __poll_t mask;
struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
-
- sock_poll_wait(file, sk_sleep(sk), wait);
- mask = 0;
+ __poll_t mask = 0;
/* exceptional events? */
if (sk->sk_err)
@@ -976,7 +972,7 @@ static const struct proto_ops caif_seqpacket_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll = caif_poll,
+ .poll_mask = caif_poll_mask,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
@@ -997,7 +993,7 @@ static const struct proto_ops caif_stream_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll = caif_poll,
+ .poll_mask = caif_poll_mask,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 53ecda1..13e2ae6 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -174,7 +174,7 @@ static void chnl_flowctrl_cb(struct cflayer *layr, enum caif_ctrlcmd flow,
flow == CAIF_CTRLCMD_DEINIT_RSP ? "CLOSE/DEINIT" :
flow == CAIF_CTRLCMD_INIT_FAIL_RSP ? "OPEN_FAIL" :
flow == CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND ?
- "REMOTE_SHUTDOWN" : "UKNOWN CTRL COMMAND");
+ "REMOTE_SHUTDOWN" : "UNKNOWN CTRL COMMAND");
diff --git a/net/can/bcm.c b/net/can/bcm.c
index ac5e5e3..97fedff 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -239,18 +239,6 @@ static int bcm_proc_show(struct seq_file *m, void *v)
seq_putc(m, '\n');
return 0;
}
-
-static int bcm_proc_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, bcm_proc_show);
-}
-
-static const struct file_operations bcm_proc_fops = {
- .open = bcm_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif /* CONFIG_PROC_FS */
/*
@@ -1606,9 +1594,9 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len,
if (net->can.bcmproc_dir) {
/* unique socket address as filename */
sprintf(bo->procname, "%lu", sock_i_ino(sk));
- bo->bcm_proc_read = proc_create_data(bo->procname, 0644,
+ bo->bcm_proc_read = proc_create_net_single(bo->procname, 0644,
net->can.bcmproc_dir,
- &bcm_proc_fops, sk);
+ bcm_proc_show, sk);
if (!bo->bcm_proc_read) {
ret = -ENOMEM;
goto fail;
@@ -1669,7 +1657,7 @@ static const struct proto_ops bcm_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = can_ioctl, /* use can_ioctl() from af_can.c */
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
diff --git a/net/can/proc.c b/net/can/proc.c
index fdf704e..70fea17 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -270,18 +270,6 @@ static int can_stats_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int can_stats_proc_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, can_stats_proc_show);
-}
-
-static const struct file_operations can_stats_proc_fops = {
- .open = can_stats_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int can_reset_stats_proc_show(struct seq_file *m, void *v)
{
struct net *net = m->private;
@@ -303,36 +291,12 @@ static int can_reset_stats_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int can_reset_stats_proc_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, can_reset_stats_proc_show);
-}
-
-static const struct file_operations can_reset_stats_proc_fops = {
- .open = can_reset_stats_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int can_version_proc_show(struct seq_file *m, void *v)
{
seq_printf(m, "%s\n", CAN_VERSION_STRING);
return 0;
}
-static int can_version_proc_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, can_version_proc_show);
-}
-
-static const struct file_operations can_version_proc_fops = {
- .open = can_version_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static inline void can_rcvlist_proc_show_one(struct seq_file *m, int idx,
struct net_device *dev,
struct can_dev_rcv_lists *d)
@@ -373,18 +337,6 @@ static int can_rcvlist_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int can_rcvlist_proc_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, can_rcvlist_proc_show);
-}
-
-static const struct file_operations can_rcvlist_proc_fops = {
- .open = can_rcvlist_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static inline void can_rcvlist_proc_show_array(struct seq_file *m,
struct net_device *dev,
struct hlist_head *rcv_array,
@@ -440,19 +392,6 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int can_rcvlist_sff_proc_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, can_rcvlist_sff_proc_show);
-}
-
-static const struct file_operations can_rcvlist_sff_proc_fops = {
- .open = can_rcvlist_sff_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-
static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v)
{
struct net_device *dev;
@@ -483,18 +422,6 @@ static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v)
return 0;
}
-static int can_rcvlist_eff_proc_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, can_rcvlist_eff_proc_show);
-}
-
-static const struct file_operations can_rcvlist_eff_proc_fops = {
- .open = can_rcvlist_eff_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
/*
* can_init_proc - create main CAN proc directory and procfs entries
*/
@@ -510,37 +437,29 @@ void can_init_proc(struct net *net)
}
/* own procfs entries from the AF_CAN core */
- net->can.pde_version = proc_create(CAN_PROC_VERSION, 0644,
- net->can.proc_dir,
- &can_version_proc_fops);
- net->can.pde_stats = proc_create(CAN_PROC_STATS, 0644,
- net->can.proc_dir,
- &can_stats_proc_fops);
- net->can.pde_reset_stats = proc_create(CAN_PROC_RESET_STATS, 0644,
- net->can.proc_dir,
- &can_reset_stats_proc_fops);
- net->can.pde_rcvlist_err = proc_create_data(CAN_PROC_RCVLIST_ERR, 0644,
- net->can.proc_dir,
- &can_rcvlist_proc_fops,
- (void *)RX_ERR);
- net->can.pde_rcvlist_all = proc_create_data(CAN_PROC_RCVLIST_ALL, 0644,
- net->can.proc_dir,
- &can_rcvlist_proc_fops,
- (void *)RX_ALL);
- net->can.pde_rcvlist_fil = proc_create_data(CAN_PROC_RCVLIST_FIL, 0644,
- net->can.proc_dir,
- &can_rcvlist_proc_fops,
- (void *)RX_FIL);
- net->can.pde_rcvlist_inv = proc_create_data(CAN_PROC_RCVLIST_INV, 0644,
- net->can.proc_dir,
- &can_rcvlist_proc_fops,
- (void *)RX_INV);
- net->can.pde_rcvlist_eff = proc_create(CAN_PROC_RCVLIST_EFF, 0644,
- net->can.proc_dir,
- &can_rcvlist_eff_proc_fops);
- net->can.pde_rcvlist_sff = proc_create(CAN_PROC_RCVLIST_SFF, 0644,
- net->can.proc_dir,
- &can_rcvlist_sff_proc_fops);
+ net->can.pde_version = proc_create_net_single(CAN_PROC_VERSION, 0644,
+ net->can.proc_dir, can_version_proc_show, NULL);
+ net->can.pde_stats = proc_create_net_single(CAN_PROC_STATS, 0644,
+ net->can.proc_dir, can_stats_proc_show, NULL);
+ net->can.pde_reset_stats = proc_create_net_single(CAN_PROC_RESET_STATS,
+ 0644, net->can.proc_dir, can_reset_stats_proc_show,
+ NULL);
+ net->can.pde_rcvlist_err = proc_create_net_single(CAN_PROC_RCVLIST_ERR,
+ 0644, net->can.proc_dir, can_rcvlist_proc_show,
+ (void *)RX_ERR);
+ net->can.pde_rcvlist_all = proc_create_net_single(CAN_PROC_RCVLIST_ALL,
+ 0644, net->can.proc_dir, can_rcvlist_proc_show,
+ (void *)RX_ALL);
+ net->can.pde_rcvlist_fil = proc_create_net_single(CAN_PROC_RCVLIST_FIL,
+ 0644, net->can.proc_dir, can_rcvlist_proc_show,
+ (void *)RX_FIL);
+ net->can.pde_rcvlist_inv = proc_create_net_single(CAN_PROC_RCVLIST_INV,
+ 0644, net->can.proc_dir, can_rcvlist_proc_show,
+ (void *)RX_INV);
+ net->can.pde_rcvlist_eff = proc_create_net_single(CAN_PROC_RCVLIST_EFF,
+ 0644, net->can.proc_dir, can_rcvlist_eff_proc_show, NULL);
+ net->can.pde_rcvlist_sff = proc_create_net_single(CAN_PROC_RCVLIST_SFF,
+ 0644, net->can.proc_dir, can_rcvlist_sff_proc_show, NULL);
}
/*
diff --git a/net/can/raw.c b/net/can/raw.c
index 1051eee..fd7e2f4 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -843,7 +843,7 @@ static const struct proto_ops raw_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = raw_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = can_ioctl, /* use can_ioctl() from af_can.c */
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index fcb40c1..3b3d33e 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -2569,6 +2569,11 @@ static int try_write(struct ceph_connection *con)
int ret = 1;
dout("try_write start %p state %lu\n", con, con->state);
+ if (con->state != CON_STATE_PREOPEN &&
+ con->state != CON_STATE_CONNECTING &&
+ con->state != CON_STATE_NEGOTIATING &&
+ con->state != CON_STATE_OPEN)
+ return 0;
more:
dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes);
@@ -2594,6 +2599,8 @@ static int try_write(struct ceph_connection *con)
}
more_kvec:
+ BUG_ON(!con->sock);
+
/* kvec data queued? */
if (con->out_kvec_left) {
ret = write_partial_kvec(con);
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index b3dac24..21ac6e3 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -209,6 +209,14 @@ static void reopen_session(struct ceph_mon_client *monc)
__open_session(monc);
}
+static void un_backoff(struct ceph_mon_client *monc)
+{
+ monc->hunt_mult /= 2; /* reduce by 50% */
+ if (monc->hunt_mult < 1)
+ monc->hunt_mult = 1;
+ dout("%s hunt_mult now %d\n", __func__, monc->hunt_mult);
+}
+
/*
* Reschedule delayed work timer.
*/
@@ -963,6 +971,7 @@ static void delayed_work(struct work_struct *work)
if (!monc->hunting) {
ceph_con_keepalive(&monc->con);
__validate_auth(monc);
+ un_backoff(monc);
}
if (is_auth &&
@@ -1123,9 +1132,8 @@ static void finish_hunting(struct ceph_mon_client *monc)
dout("%s found mon%d\n", __func__, monc->cur_mon);
monc->hunting = false;
monc->had_a_connection = true;
- monc->hunt_mult /= 2; /* reduce by 50% */
- if (monc->hunt_mult < 1)
- monc->hunt_mult = 1;
+ un_backoff(monc);
+ __schedule_delayed(monc);
}
}
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index ea2a6c9f..d2667e5 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -157,10 +157,12 @@ static void ceph_osd_data_bio_init(struct ceph_osd_data *osd_data,
#endif /* CONFIG_BLOCK */
static void ceph_osd_data_bvecs_init(struct ceph_osd_data *osd_data,
- struct ceph_bvec_iter *bvec_pos)
+ struct ceph_bvec_iter *bvec_pos,
+ u32 num_bvecs)
{
osd_data->type = CEPH_OSD_DATA_TYPE_BVECS;
osd_data->bvec_pos = *bvec_pos;
+ osd_data->num_bvecs = num_bvecs;
}
#define osd_req_op_data(oreq, whch, typ, fld) \
@@ -237,6 +239,22 @@ void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req,
EXPORT_SYMBOL(osd_req_op_extent_osd_data_bio);
#endif /* CONFIG_BLOCK */
+void osd_req_op_extent_osd_data_bvecs(struct ceph_osd_request *osd_req,
+ unsigned int which,
+ struct bio_vec *bvecs, u32 num_bvecs,
+ u32 bytes)
+{
+ struct ceph_osd_data *osd_data;
+ struct ceph_bvec_iter it = {
+ .bvecs = bvecs,
+ .iter = { .bi_size = bytes },
+ };
+
+ osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
+ ceph_osd_data_bvecs_init(osd_data, &it, num_bvecs);
+}
+EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvecs);
+
void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req,
unsigned int which,
struct ceph_bvec_iter *bvec_pos)
@@ -244,7 +262,7 @@ void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req,
struct ceph_osd_data *osd_data;
osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
- ceph_osd_data_bvecs_init(osd_data, bvec_pos);
+ ceph_osd_data_bvecs_init(osd_data, bvec_pos, 0);
}
EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvec_pos);
@@ -287,7 +305,8 @@ EXPORT_SYMBOL(osd_req_op_cls_request_data_pages);
void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req,
unsigned int which,
- struct bio_vec *bvecs, u32 bytes)
+ struct bio_vec *bvecs, u32 num_bvecs,
+ u32 bytes)
{
struct ceph_osd_data *osd_data;
struct ceph_bvec_iter it = {
@@ -296,7 +315,7 @@ void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req,
};
osd_data = osd_req_op_data(osd_req, which, cls, request_data);
- ceph_osd_data_bvecs_init(osd_data, &it);
+ ceph_osd_data_bvecs_init(osd_data, &it, num_bvecs);
osd_req->r_ops[which].cls.indata_len += bytes;
osd_req->r_ops[which].indata_len += bytes;
}
diff --git a/net/compat.c b/net/compat.c
index 5ae7437d..7242cce 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -377,7 +377,8 @@ static int compat_sock_setsockopt(struct socket *sock, int level, int optname,
optname == SO_ATTACH_REUSEPORT_CBPF)
return do_set_attach_filter(sock, level, optname,
optval, optlen);
- if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)
+ if (!COMPAT_USE_64BIT_TIME &&
+ (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO))
return do_set_sock_timeout(sock, level, optname, optval, optlen);
return sock_setsockopt(sock, level, optname, optval, optlen);
@@ -448,7 +449,8 @@ static int do_get_sock_timeout(struct socket *sock, int level, int optname,
static int compat_sock_getsockopt(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen)
{
- if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)
+ if (!COMPAT_USE_64BIT_TIME &&
+ (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO))
return do_get_sock_timeout(sock, level, optname, optval, optlen);
return sock_getsockopt(sock, level, optname, optval, optlen);
}
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 9938952..f19bf3d 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -819,9 +819,8 @@ EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg);
/**
* datagram_poll - generic datagram poll
- * @file: file struct
* @sock: socket
- * @wait: poll table
+ * @events to wait for
*
* Datagram poll: Again totally generic. This also handles
* sequenced packet sockets providing the socket receive queue
@@ -831,14 +830,10 @@ EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg);
* and you use a different write policy from sock_writeable()
* then please supply your own write_space callback.
*/
-__poll_t datagram_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+__poll_t datagram_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
- __poll_t mask;
-
- sock_poll_wait(file, sk_sleep(sk), wait);
- mask = 0;
+ __poll_t mask = 0;
/* exceptional events? */
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
@@ -871,4 +866,4 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
return mask;
}
-EXPORT_SYMBOL(datagram_poll);
+EXPORT_SYMBOL(datagram_poll_mask);
diff --git a/net/core/dev.c b/net/core/dev.c
index 969462e..983b277 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2124,7 +2124,7 @@ static bool remove_xps_queue_cpu(struct net_device *dev,
int i, j;
for (i = count, j = offset; i--; j++) {
- if (!remove_xps_queue(dev_maps, cpu, j))
+ if (!remove_xps_queue(dev_maps, tci, j))
break;
}
@@ -2884,11 +2884,7 @@ void netdev_rx_csum_fault(struct net_device *dev)
EXPORT_SYMBOL(netdev_rx_csum_fault);
#endif
-/* Actually, we should eliminate this check as soon as we know, that:
- * 1. IOMMU is present and allows to map all the memory.
- * 2. No high memory really exists on this machine.
- */
-
+/* XXX: check that highmem exists at all on the given machine. */
static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
{
#ifdef CONFIG_HIGHMEM
@@ -2902,20 +2898,6 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
return 1;
}
}
-
- if (PCI_DMA_BUS_IS_PHYS) {
- struct device *pdev = dev->dev.parent;
-
- if (!pdev)
- return 0;
- for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
- skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
- dma_addr_t addr = page_to_phys(skb_frag_page(frag));
-
- if (!pdev->dma_mask || addr + PAGE_SIZE - 1 > *pdev->dma_mask)
- return 1;
- }
- }
#endif
return 0;
}
@@ -2969,7 +2951,7 @@ netdev_features_t passthru_features_check(struct sk_buff *skb,
}
EXPORT_SYMBOL(passthru_features_check);
-static netdev_features_t dflt_features_check(const struct sk_buff *skb,
+static netdev_features_t dflt_features_check(struct sk_buff *skb,
struct net_device *dev,
netdev_features_t features)
{
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index e3e6a3e..d884d8f 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -839,7 +839,7 @@ void dev_mc_flush(struct net_device *dev)
EXPORT_SYMBOL(dev_mc_flush);
/**
- * dev_mc_flush - Init multicast address list
+ * dev_mc_init - Init multicast address list
* @dev: device
*
* Init multicast address list.
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 03416e6..ba02f0d 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1032,6 +1032,11 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev,
info_size = sizeof(info);
if (copy_from_user(&info, useraddr, info_size))
return -EFAULT;
+ /* Since malicious users may modify the original data,
+ * we need to check whether FLOW_RSS is still requested.
+ */
+ if (!(info.flow_type & FLOW_RSS))
+ return -EINVAL;
}
if (info.cmd == ETHTOOL_GRXCLSRLALL) {
diff --git a/net/core/filter.c b/net/core/filter.c
index d31aff9..201ff36b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -481,11 +481,18 @@ static int bpf_convert_filter(struct sock_filter *prog, int len,
#define BPF_EMIT_JMP \
do { \
+ const s32 off_min = S16_MIN, off_max = S16_MAX; \
+ s32 off; \
+ \
if (target >= len || target < 0) \
goto err; \
- insn->off = addrs ? addrs[target] - addrs[i] - 1 : 0; \
+ off = addrs ? addrs[target] - addrs[i] - 1 : 0; \
/* Adjust pc relative offset for 2nd or 3rd insn. */ \
- insn->off -= insn - tmp_insns; \
+ off -= insn - tmp_insns; \
+ /* Reject anything not fitting into insn->off. */ \
+ if (off < off_min || off > off_max) \
+ goto err; \
+ insn->off = off; \
} while (0)
case BPF_JMP | BPF_JA:
@@ -3240,6 +3247,7 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb,
skb_dst_set(skb, (struct dst_entry *) md);
info = &md->u.tun_info;
+ memset(info, 0, sizeof(*info));
info->mode = IP_TUNNEL_INFO_TX;
info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 7b7a14a..1fb43bf 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -55,10 +55,11 @@ static void neigh_timer_handler(struct timer_list *t);
static void __neigh_notify(struct neighbour *n, int type, int flags,
u32 pid);
static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid);
-static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
+static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
+ struct net_device *dev);
#ifdef CONFIG_PROC_FS
-static const struct file_operations neigh_stat_seq_fops;
+static const struct seq_operations neigh_stat_seq_ops;
#endif
/*
@@ -291,8 +292,7 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
{
write_lock_bh(&tbl->lock);
neigh_flush_dev(tbl, dev);
- pneigh_ifdown(tbl, dev);
- write_unlock_bh(&tbl->lock);
+ pneigh_ifdown_and_unlock(tbl, dev);
del_timer_sync(&tbl->proxy_timer);
pneigh_queue_purge(&tbl->proxy_queue);
@@ -681,9 +681,10 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey,
return -ENOENT;
}
-static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
+static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
+ struct net_device *dev)
{
- struct pneigh_entry *n, **np;
+ struct pneigh_entry *n, **np, *freelist = NULL;
u32 h;
for (h = 0; h <= PNEIGH_HASHMASK; h++) {
@@ -691,16 +692,23 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
while ((n = *np) != NULL) {
if (!dev || n->dev == dev) {
*np = n->next;
- if (tbl->pdestructor)
- tbl->pdestructor(n);
- if (n->dev)
- dev_put(n->dev);
- kfree(n);
+ n->next = freelist;
+ freelist = n;
continue;
}
np = &n->next;
}
}
+ write_unlock_bh(&tbl->lock);
+ while ((n = freelist)) {
+ freelist = n->next;
+ n->next = NULL;
+ if (tbl->pdestructor)
+ tbl->pdestructor(n);
+ if (n->dev)
+ dev_put(n->dev);
+ kfree(n);
+ }
return -ENOENT;
}
@@ -1550,8 +1558,8 @@ void neigh_table_init(int index, struct neigh_table *tbl)
panic("cannot create neighbour cache statistics");
#ifdef CONFIG_PROC_FS
- if (!proc_create_data(tbl->id, 0, init_net.proc_net_stat,
- &neigh_stat_seq_fops, tbl))
+ if (!proc_create_seq_data(tbl->id, 0, init_net.proc_net_stat,
+ &neigh_stat_seq_ops, tbl))
panic("cannot create neighbour proc dir entry");
#endif
@@ -2323,12 +2331,16 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL, NULL);
if (!err) {
- if (tb[NDA_IFINDEX])
+ if (tb[NDA_IFINDEX]) {
+ if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32))
+ return -EINVAL;
filter_idx = nla_get_u32(tb[NDA_IFINDEX]);
-
- if (tb[NDA_MASTER])
+ }
+ if (tb[NDA_MASTER]) {
+ if (nla_len(tb[NDA_MASTER]) != sizeof(u32))
+ return -EINVAL;
filter_master_idx = nla_get_u32(tb[NDA_MASTER]);
-
+ }
if (filter_idx || filter_master_idx)
flags |= NLM_F_DUMP_FILTERED;
}
@@ -2774,7 +2786,7 @@ EXPORT_SYMBOL(neigh_seq_stop);
static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos)
{
- struct neigh_table *tbl = seq->private;
+ struct neigh_table *tbl = PDE_DATA(file_inode(seq->file));
int cpu;
if (*pos == 0)
@@ -2791,7 +2803,7 @@ static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos)
static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct neigh_table *tbl = seq->private;
+ struct neigh_table *tbl = PDE_DATA(file_inode(seq->file));
int cpu;
for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) {
@@ -2810,7 +2822,7 @@ static void neigh_stat_seq_stop(struct seq_file *seq, void *v)
static int neigh_stat_seq_show(struct seq_file *seq, void *v)
{
- struct neigh_table *tbl = seq->private;
+ struct neigh_table *tbl = PDE_DATA(file_inode(seq->file));
struct neigh_statistics *st = v;
if (v == SEQ_START_TOKEN) {
@@ -2849,25 +2861,6 @@ static const struct seq_operations neigh_stat_seq_ops = {
.stop = neigh_stat_seq_stop,
.show = neigh_stat_seq_show,
};
-
-static int neigh_stat_seq_open(struct inode *inode, struct file *file)
-{
- int ret = seq_open(file, &neigh_stat_seq_ops);
-
- if (!ret) {
- struct seq_file *sf = file->private_data;
- sf->private = PDE_DATA(inode);
- }
- return ret;
-};
-
-static const struct file_operations neigh_stat_seq_fops = {
- .open = neigh_stat_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
#endif /* CONFIG_PROC_FS */
static inline size_t neigh_nlmsg_size(void)
diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c
index 9737302..63881f7 100644
--- a/net/core/net-procfs.c
+++ b/net/core/net-procfs.c
@@ -175,19 +175,6 @@ static const struct seq_operations dev_seq_ops = {
.show = dev_seq_show,
};
-static int dev_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &dev_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-static const struct file_operations dev_seq_fops = {
- .open = dev_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static const struct seq_operations softnet_seq_ops = {
.start = softnet_seq_start,
.next = softnet_seq_next,
@@ -195,18 +182,6 @@ static const struct seq_operations softnet_seq_ops = {
.show = softnet_seq_show,
};
-static int softnet_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &softnet_seq_ops);
-}
-
-static const struct file_operations softnet_seq_fops = {
- .open = softnet_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static void *ptype_get_idx(loff_t pos)
{
struct packet_type *pt = NULL;
@@ -297,30 +272,18 @@ static const struct seq_operations ptype_seq_ops = {
.show = ptype_seq_show,
};
-static int ptype_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &ptype_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-static const struct file_operations ptype_seq_fops = {
- .open = ptype_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
-
static int __net_init dev_proc_net_init(struct net *net)
{
int rc = -ENOMEM;
- if (!proc_create("dev", 0444, net->proc_net, &dev_seq_fops))
+ if (!proc_create_net("dev", 0444, net->proc_net, &dev_seq_ops,
+ sizeof(struct seq_net_private)))
goto out;
- if (!proc_create("softnet_stat", 0444, net->proc_net,
- &softnet_seq_fops))
+ if (!proc_create_seq("softnet_stat", 0444, net->proc_net,
+ &softnet_seq_ops))
goto out_dev;
- if (!proc_create("ptype", 0444, net->proc_net, &ptype_seq_fops))
+ if (!proc_create_net("ptype", 0444, net->proc_net, &ptype_seq_ops,
+ sizeof(struct seq_net_private)))
goto out_softnet;
if (wext_proc_init(net))
@@ -377,22 +340,10 @@ static const struct seq_operations dev_mc_seq_ops = {
.show = dev_mc_seq_show,
};
-static int dev_mc_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &dev_mc_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-static const struct file_operations dev_mc_seq_fops = {
- .open = dev_mc_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static int __net_init dev_mc_net_init(struct net *net)
{
- if (!proc_create("dev_mcast", 0, net->proc_net, &dev_mc_seq_fops))
+ if (!proc_create_net("dev_mcast", 0, net->proc_net, &dev_mc_seq_ops,
+ sizeof(struct seq_net_private)))
return -ENOMEM;
return 0;
}
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index c476f07..bb7e80f 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1214,9 +1214,6 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue,
cpumask_var_t mask;
unsigned long index;
- if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
- return -ENOMEM;
-
index = get_netdev_queue_index(queue);
if (dev->num_tc) {
@@ -1226,6 +1223,9 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue,
return -EINVAL;
}
+ if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
+ return -ENOMEM;
+
rcu_read_lock();
dev_maps = rcu_dereference(dev->xps_maps);
if (dev_maps) {
diff --git a/net/core/sock.c b/net/core/sock.c
index 6444525..2aed99a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1606,7 +1606,7 @@ static void __sk_free(struct sock *sk)
if (likely(sk->sk_net_refcnt))
sock_inuse_add(sock_net(sk), -1);
- if (unlikely(sock_diag_has_destroy_listeners(sk) && sk->sk_net_refcnt))
+ if (unlikely(sk->sk_net_refcnt && sock_diag_has_destroy_listeners(sk)))
sock_diag_broadcast_destroy(sk);
else
sk_destruct(sk);
@@ -2567,12 +2567,6 @@ int sock_no_getname(struct socket *sock, struct sockaddr *saddr,
}
EXPORT_SYMBOL(sock_no_getname);
-__poll_t sock_no_poll(struct file *file, struct socket *sock, poll_table *pt)
-{
- return 0;
-}
-EXPORT_SYMBOL(sock_no_poll);
-
int sock_no_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
return -EOPNOTSUPP;
@@ -3439,22 +3433,10 @@ static const struct seq_operations proto_seq_ops = {
.show = proto_seq_show,
};
-static int proto_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &proto_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-static const struct file_operations proto_seq_fops = {
- .open = proto_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static __net_init int proto_init_net(struct net *net)
{
- if (!proc_create("protocols", 0444, net->proc_net, &proto_seq_fops))
+ if (!proc_create_net("protocols", 0444, net->proc_net, &proto_seq_ops,
+ sizeof(struct seq_net_private)))
return -ENOMEM;
return 0;
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index 92d016e..385f153 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -126,6 +126,16 @@ static void ccid2_change_l_seq_window(struct sock *sk, u64 val)
DCCPF_SEQ_WMAX));
}
+static void dccp_tasklet_schedule(struct sock *sk)
+{
+ struct tasklet_struct *t = &dccp_sk(sk)->dccps_xmitlet;
+
+ if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
+ sock_hold(sk);
+ __tasklet_schedule(t);
+ }
+}
+
static void ccid2_hc_tx_rto_expire(struct timer_list *t)
{
struct ccid2_hc_tx_sock *hc = from_timer(hc, t, tx_rtotimer);
@@ -166,7 +176,7 @@ static void ccid2_hc_tx_rto_expire(struct timer_list *t)
/* if we were blocked before, we may now send cwnd=1 packet */
if (sender_was_blocked)
- tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet);
+ dccp_tasklet_schedule(sk);
/* restart backed-off timer */
sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
out:
@@ -706,7 +716,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
done:
/* check if incoming Acks allow pending packets to be sent */
if (sender_was_blocked && !ccid2_cwnd_network_limited(hc))
- tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet);
+ dccp_tasklet_schedule(sk);
dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks);
}
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index f91e381..0ea2ee5 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -316,8 +316,7 @@ int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
int flags, int *addr_len);
void dccp_shutdown(struct sock *sk, int how);
int inet_dccp_listen(struct socket *sock, int backlog);
-__poll_t dccp_poll(struct file *file, struct socket *sock,
- poll_table *wait);
+__poll_t dccp_poll_mask(struct socket *sock, __poll_t events);
int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
void dccp_req_err(struct sock *sk, u64 seq);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index b08feb2..a9e478c 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -984,7 +984,7 @@ static const struct proto_ops inet_dccp_ops = {
.accept = inet_accept,
.getname = inet_getname,
/* FIXME: work on tcp_poll to rename it to inet_csk_poll */
- .poll = dccp_poll,
+ .poll_mask = dccp_poll_mask,
.ioctl = inet_ioctl,
/* FIXME: work on inet_listen to rename it to sock_common_listen */
.listen = inet_dccp_listen,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 6344f1b..17fc4e0 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -1070,7 +1070,7 @@ static const struct proto_ops inet6_dccp_ops = {
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = inet6_getname,
- .poll = dccp_poll,
+ .poll_mask = dccp_poll_mask,
.ioctl = inet6_ioctl,
.listen = inet_dccp_listen,
.shutdown = inet_shutdown,
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 84cd4e3..ca21c1c 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -283,9 +283,7 @@ int dccp_disconnect(struct sock *sk, int flags)
dccp_clear_xmit_timers(sk);
ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
- ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
dp->dccps_hc_rx_ccid = NULL;
- dp->dccps_hc_tx_ccid = NULL;
__skb_queue_purge(&sk->sk_receive_queue);
__skb_queue_purge(&sk->sk_write_queue);
@@ -314,20 +312,11 @@ int dccp_disconnect(struct sock *sk, int flags)
EXPORT_SYMBOL_GPL(dccp_disconnect);
-/*
- * Wait for a DCCP event.
- *
- * Note that we don't need to lock the socket, as the upper poll layers
- * take care of normal races (between the test and the event) and we don't
- * go look at any of the socket buffers directly.
- */
-__poll_t dccp_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+__poll_t dccp_poll_mask(struct socket *sock, __poll_t events)
{
__poll_t mask;
struct sock *sk = sock->sk;
- sock_poll_wait(file, sk_sleep(sk), wait);
if (sk->sk_state == DCCP_LISTEN)
return inet_csk_listen_poll(sk);
@@ -369,7 +358,7 @@ __poll_t dccp_poll(struct file *file, struct socket *sock,
return mask;
}
-EXPORT_SYMBOL_GPL(dccp_poll);
+EXPORT_SYMBOL_GPL(dccp_poll_mask);
int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
index b50a873..1501a20 100644
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -232,6 +232,7 @@ static void dccp_write_xmitlet(unsigned long data)
else
dccp_write_xmit(sk);
bh_unlock_sock(sk);
+ sock_put(sk);
}
static void dccp_write_xmit_timer(struct timer_list *t)
@@ -240,7 +241,6 @@ static void dccp_write_xmit_timer(struct timer_list *t)
struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk;
dccp_write_xmitlet((unsigned long)sk);
- sock_put(sk);
}
void dccp_init_xmit_timers(struct sock *sk)
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 3275160..9a686d8 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1207,11 +1207,11 @@ static int dn_getname(struct socket *sock, struct sockaddr *uaddr,int peer)
}
-static __poll_t dn_poll(struct file *file, struct socket *sock, poll_table *wait)
+static __poll_t dn_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
struct dn_scp *scp = DN_SK(sk);
- __poll_t mask = datagram_poll(file, sock, wait);
+ __poll_t mask = datagram_poll_mask(sock, events);
if (!skb_queue_empty(&scp->other_receive_queue))
mask |= EPOLLRDBAND;
@@ -2314,19 +2314,6 @@ static const struct seq_operations dn_socket_seq_ops = {
.stop = dn_socket_seq_stop,
.show = dn_socket_seq_show,
};
-
-static int dn_socket_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_private(file, &dn_socket_seq_ops,
- sizeof(struct dn_iter_state));
-}
-
-static const struct file_operations dn_socket_seq_fops = {
- .open = dn_socket_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_private,
-};
#endif
static const struct net_proto_family dn_family_ops = {
@@ -2344,7 +2331,7 @@ static const struct proto_ops dn_proto_ops = {
.socketpair = sock_no_socketpair,
.accept = dn_accept,
.getname = dn_getname,
- .poll = dn_poll,
+ .poll_mask = dn_poll_mask,
.ioctl = dn_ioctl,
.listen = dn_listen,
.shutdown = dn_shutdown,
@@ -2383,7 +2370,9 @@ static int __init decnet_init(void)
dev_add_pack(&dn_dix_packet_type);
register_netdevice_notifier(&dn_dev_notifier);
- proc_create("decnet", 0444, init_net.proc_net, &dn_socket_seq_fops);
+ proc_create_seq_private("decnet", 0444, init_net.proc_net,
+ &dn_socket_seq_ops, sizeof(struct dn_iter_state),
+ NULL);
dn_register_sysctl();
out:
return rc;
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index c03b046..bfd43e8 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -1382,19 +1382,6 @@ static const struct seq_operations dn_dev_seq_ops = {
.stop = dn_dev_seq_stop,
.show = dn_dev_seq_show,
};
-
-static int dn_dev_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &dn_dev_seq_ops);
-}
-
-static const struct file_operations dn_dev_seq_fops = {
- .open = dn_dev_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
#endif /* CONFIG_PROC_FS */
static int addr[2];
@@ -1424,7 +1411,7 @@ void __init dn_dev_init(void)
rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_GETADDR,
NULL, dn_nl_dump_ifaddr, 0);
- proc_create("decnet_dev", 0444, init_net.proc_net, &dn_dev_seq_fops);
+ proc_create_seq("decnet_dev", 0444, init_net.proc_net, &dn_dev_seq_ops);
#ifdef CONFIG_SYSCTL
{
diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c
index 1315616..94b306f 100644
--- a/net/decnet/dn_neigh.c
+++ b/net/decnet/dn_neigh.c
@@ -589,27 +589,13 @@ static const struct seq_operations dn_neigh_seq_ops = {
.stop = neigh_seq_stop,
.show = dn_neigh_seq_show,
};
-
-static int dn_neigh_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &dn_neigh_seq_ops,
- sizeof(struct neigh_seq_state));
-}
-
-static const struct file_operations dn_neigh_seq_fops = {
- .open = dn_neigh_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
#endif
void __init dn_neigh_init(void)
{
neigh_table_init(NEIGH_DN_TABLE, &dn_neigh_table);
- proc_create("decnet_neigh", 0444, init_net.proc_net,
- &dn_neigh_seq_fops);
+ proc_create_net("decnet_neigh", 0444, init_net.proc_net,
+ &dn_neigh_seq_ops, sizeof(struct neigh_seq_state));
}
void __exit dn_neigh_cleanup(void)
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index eca0cc6..e747650 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1852,20 +1852,6 @@ static const struct seq_operations dn_rt_cache_seq_ops = {
.stop = dn_rt_cache_seq_stop,
.show = dn_rt_cache_seq_show,
};
-
-static int dn_rt_cache_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_private(file, &dn_rt_cache_seq_ops,
- sizeof(struct dn_rt_cache_iter_state));
-}
-
-static const struct file_operations dn_rt_cache_seq_fops = {
- .open = dn_rt_cache_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_private,
-};
-
#endif /* CONFIG_PROC_FS */
void __init dn_route_init(void)
@@ -1918,8 +1904,9 @@ void __init dn_route_init(void)
dn_dst_ops.gc_thresh = (dn_rt_hash_mask + 1);
- proc_create("decnet_cache", 0444, init_net.proc_net,
- &dn_rt_cache_seq_fops);
+ proc_create_seq_private("decnet_cache", 0444, init_net.proc_net,
+ &dn_rt_cache_seq_ops,
+ sizeof(struct dn_rt_cache_iter_state), NULL);
#ifdef CONFIG_DECNET_ROUTER
rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_GETROUTE,
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index 8396705..40c8516 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -91,9 +91,9 @@ dns_resolver_preparse(struct key_preparsed_payload *prep)
next_opt = memchr(opt, '#', end - opt) ?: end;
opt_len = next_opt - opt;
- if (!opt_len) {
- printk(KERN_WARNING
- "Empty option to dns_resolver key\n");
+ if (opt_len <= 0 || opt_len > 128) {
+ pr_warn_ratelimited("Invalid option length (%d) for dns_resolver key\n",
+ opt_len);
return -EINVAL;
}
@@ -127,10 +127,8 @@ dns_resolver_preparse(struct key_preparsed_payload *prep)
}
bad_option_value:
- printk(KERN_WARNING
- "Option '%*.*s' to dns_resolver key:"
- " bad/missing value\n",
- opt_nlen, opt_nlen, opt);
+ pr_warn_ratelimited("Option '%*.*s' to dns_resolver key: bad/missing value\n",
+ opt_nlen, opt_nlen, opt);
return -EINVAL;
} while (opt = next_opt + 1, opt < end);
}
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index adf50fb..4772525 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -258,11 +258,13 @@ static void dsa_tree_teardown_default_cpu(struct dsa_switch_tree *dst)
static int dsa_port_setup(struct dsa_port *dp)
{
struct dsa_switch *ds = dp->ds;
- int err;
+ int err = 0;
memset(&dp->devlink_port, 0, sizeof(dp->devlink_port));
- err = devlink_port_register(ds->devlink, &dp->devlink_port, dp->index);
+ if (dp->type != DSA_PORT_TYPE_UNUSED)
+ err = devlink_port_register(ds->devlink, &dp->devlink_port,
+ dp->index);
if (err)
return err;
@@ -293,7 +295,8 @@ static int dsa_port_setup(struct dsa_port *dp)
static void dsa_port_teardown(struct dsa_port *dp)
{
- devlink_port_unregister(&dp->devlink_port);
+ if (dp->type != DSA_PORT_TYPE_UNUSED)
+ devlink_port_unregister(&dp->devlink_port);
switch (dp->type) {
case DSA_PORT_TYPE_UNUSED:
diff --git a/net/ieee802154/6lowpan/6lowpan_i.h b/net/ieee802154/6lowpan/6lowpan_i.h
index b8d95cb..44a7e16 100644
--- a/net/ieee802154/6lowpan/6lowpan_i.h
+++ b/net/ieee802154/6lowpan/6lowpan_i.h
@@ -20,8 +20,8 @@ typedef unsigned __bitwise lowpan_rx_result;
struct frag_lowpan_compare_key {
u16 tag;
u16 d_size;
- const struct ieee802154_addr src;
- const struct ieee802154_addr dst;
+ struct ieee802154_addr src;
+ struct ieee802154_addr dst;
};
/* Equivalent of ipv4 struct ipq
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 1790b65..2cc2241 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -75,14 +75,14 @@ fq_find(struct net *net, const struct lowpan_802154_cb *cb,
{
struct netns_ieee802154_lowpan *ieee802154_lowpan =
net_ieee802154_lowpan(net);
- struct frag_lowpan_compare_key key = {
- .tag = cb->d_tag,
- .d_size = cb->d_size,
- .src = *src,
- .dst = *dst,
- };
+ struct frag_lowpan_compare_key key = {};
struct inet_frag_queue *q;
+ key.tag = cb->d_tag;
+ key.d_size = cb->d_size;
+ key.src = *src;
+ key.dst = *dst;
+
q = inet_frag_find(&ieee802154_lowpan->frags, &key);
if (!q)
return NULL;
@@ -372,7 +372,7 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type)
struct lowpan_frag_queue *fq;
struct net *net = dev_net(skb->dev);
struct lowpan_802154_cb *cb = lowpan_802154_cb(skb);
- struct ieee802154_hdr hdr;
+ struct ieee802154_hdr hdr = {};
int err;
if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0)
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index a60658c..a0768d2 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -423,7 +423,7 @@ static const struct proto_ops ieee802154_raw_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = ieee802154_sock_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
@@ -969,7 +969,7 @@ static const struct proto_ops ieee802154_dgram_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = ieee802154_sock_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
diff --git a/net/ife/ife.c b/net/ife/ife.c
index 7d1ec76..13bbf8c 100644
--- a/net/ife/ife.c
+++ b/net/ife/ife.c
@@ -69,6 +69,9 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen)
int total_pull;
u16 ifehdrln;
+ if (!pskb_may_pull(skb, skb->dev->hard_header_len + IFE_METAHDRLEN))
+ return NULL;
+
ifehdr = (struct ifeheadr *) (skb->data + skb->dev->hard_header_len);
ifehdrln = ntohs(ifehdr->metalen);
total_pull = skb->dev->hard_header_len + ifehdrln;
@@ -92,12 +95,43 @@ struct meta_tlvhdr {
__be16 len;
};
+static bool __ife_tlv_meta_valid(const unsigned char *skbdata,
+ const unsigned char *ifehdr_end)
+{
+ const struct meta_tlvhdr *tlv;
+ u16 tlvlen;
+
+ if (unlikely(skbdata + sizeof(*tlv) > ifehdr_end))
+ return false;
+
+ tlv = (const struct meta_tlvhdr *)skbdata;
+ tlvlen = ntohs(tlv->len);
+
+ /* tlv length field is inc header, check on minimum */
+ if (tlvlen < NLA_HDRLEN)
+ return false;
+
+ /* overflow by NLA_ALIGN check */
+ if (NLA_ALIGN(tlvlen) < tlvlen)
+ return false;
+
+ if (unlikely(skbdata + NLA_ALIGN(tlvlen) > ifehdr_end))
+ return false;
+
+ return true;
+}
+
/* Caller takes care of presenting data in network order
*/
-void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen)
+void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype,
+ u16 *dlen, u16 *totlen)
{
- struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata;
+ struct meta_tlvhdr *tlv;
+ if (!__ife_tlv_meta_valid(skbdata, ifehdr_end))
+ return NULL;
+
+ tlv = (struct meta_tlvhdr *)skbdata;
*dlen = ntohs(tlv->len) - NLA_HDRLEN;
*attrtype = ntohs(tlv->type);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index eaed036..8a59428 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -986,7 +986,7 @@ const struct proto_ops inet_stream_ops = {
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = inet_getname,
- .poll = tcp_poll,
+ .poll_mask = tcp_poll_mask,
.ioctl = inet_ioctl,
.listen = inet_listen,
.shutdown = inet_shutdown,
@@ -1018,7 +1018,7 @@ const struct proto_ops inet_dgram_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = inet_getname,
- .poll = udp_poll,
+ .poll_mask = udp_poll_mask,
.ioctl = inet_ioctl,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
@@ -1039,7 +1039,7 @@ EXPORT_SYMBOL(inet_dgram_ops);
/*
* For SOCK_RAW sockets; should be the same as inet_dgram_ops but without
- * udp_poll
+ * udp_poll_mask
*/
static const struct proto_ops inet_sockraw_ops = {
.family = PF_INET,
@@ -1050,7 +1050,7 @@ static const struct proto_ops inet_sockraw_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = inet_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = inet_ioctl,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index bf6c2d4..e90c89e 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1418,23 +1418,12 @@ static const struct seq_operations arp_seq_ops = {
.show = arp_seq_show,
};
-static int arp_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &arp_seq_ops,
- sizeof(struct neigh_seq_state));
-}
-
-static const struct file_operations arp_seq_fops = {
- .open = arp_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
+/* ------------------------------------------------------------------------ */
static int __net_init arp_net_init(struct net *net)
{
- if (!proc_create("arp", 0444, net->proc_net, &arp_seq_fops))
+ if (!proc_create_net("arp", 0444, net->proc_net, &arp_seq_ops,
+ sizeof(struct neigh_seq_state)))
return -ENOMEM;
return 0;
}
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index f05afaf..e66172a 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -326,10 +326,11 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
u8 tos, int oif, struct net_device *dev,
int rpf, struct in_device *idev, u32 *itag)
{
+ struct net *net = dev_net(dev);
+ struct flow_keys flkeys;
int ret, no_addr;
struct fib_result res;
struct flowi4 fl4;
- struct net *net = dev_net(dev);
bool dev_match;
fl4.flowi4_oif = 0;
@@ -347,6 +348,11 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
no_addr = idev->ifa_list == NULL;
fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0;
+ if (!fib4_rules_early_flow_dissect(net, skb, &fl4, &flkeys)) {
+ fl4.flowi4_proto = 0;
+ fl4.fl4_sport = 0;
+ fl4.fl4_dport = 0;
+ }
trace_fib_validate_source(dev, &fl4);
@@ -643,6 +649,7 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
[RTA_ENCAP] = { .type = NLA_NESTED },
[RTA_UID] = { .type = NLA_U32 },
[RTA_MARK] = { .type = NLA_U32 },
+ [RTA_TABLE] = { .type = NLA_U32 },
};
static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 3dcffd3..99c23a0 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2348,18 +2348,6 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static int fib_triestat_seq_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, fib_triestat_seq_show);
-}
-
-static const struct file_operations fib_triestat_fops = {
- .open = fib_triestat_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release_net,
-};
-
static struct key_vector *fib_trie_get_idx(struct seq_file *seq, loff_t pos)
{
struct fib_trie_iter *iter = seq->private;
@@ -2533,19 +2521,6 @@ static const struct seq_operations fib_trie_seq_ops = {
.show = fib_trie_seq_show,
};
-static int fib_trie_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &fib_trie_seq_ops,
- sizeof(struct fib_trie_iter));
-}
-
-static const struct file_operations fib_trie_fops = {
- .open = fib_trie_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
struct fib_route_iter {
struct seq_net_private p;
struct fib_table *main_tb;
@@ -2726,29 +2701,18 @@ static const struct seq_operations fib_route_seq_ops = {
.show = fib_route_seq_show,
};
-static int fib_route_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &fib_route_seq_ops,
- sizeof(struct fib_route_iter));
-}
-
-static const struct file_operations fib_route_fops = {
- .open = fib_route_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
int __net_init fib_proc_init(struct net *net)
{
- if (!proc_create("fib_trie", 0444, net->proc_net, &fib_trie_fops))
+ if (!proc_create_net("fib_trie", 0444, net->proc_net, &fib_trie_seq_ops,
+ sizeof(struct fib_trie_iter)))
goto out1;
- if (!proc_create("fib_triestat", 0444, net->proc_net,
- &fib_triestat_fops))
+ if (!proc_create_net_single("fib_triestat", 0444, net->proc_net,
+ fib_triestat_seq_show, NULL))
goto out2;
- if (!proc_create("route", 0444, net->proc_net, &fib_route_fops))
+ if (!proc_create_net("route", 0444, net->proc_net, &fib_route_seq_ops,
+ sizeof(struct fib_route_iter)))
goto out3;
return 0;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index b26a81a..85b617b 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2829,19 +2829,6 @@ static const struct seq_operations igmp_mc_seq_ops = {
.show = igmp_mc_seq_show,
};
-static int igmp_mc_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &igmp_mc_seq_ops,
- sizeof(struct igmp_mc_iter_state));
-}
-
-static const struct file_operations igmp_mc_seq_fops = {
- .open = igmp_mc_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
struct igmp_mcf_iter_state {
struct seq_net_private p;
struct net_device *dev;
@@ -2975,29 +2962,17 @@ static const struct seq_operations igmp_mcf_seq_ops = {
.show = igmp_mcf_seq_show,
};
-static int igmp_mcf_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &igmp_mcf_seq_ops,
- sizeof(struct igmp_mcf_iter_state));
-}
-
-static const struct file_operations igmp_mcf_seq_fops = {
- .open = igmp_mcf_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static int __net_init igmp_net_init(struct net *net)
{
struct proc_dir_entry *pde;
int err;
- pde = proc_create("igmp", 0444, net->proc_net, &igmp_mc_seq_fops);
+ pde = proc_create_net("igmp", 0444, net->proc_net, &igmp_mc_seq_ops,
+ sizeof(struct igmp_mc_iter_state));
if (!pde)
goto out_igmp;
- pde = proc_create("mcfilter", 0444, net->proc_net,
- &igmp_mcf_seq_fops);
+ pde = proc_create_net("mcfilter", 0444, net->proc_net,
+ &igmp_mcf_seq_ops, sizeof(struct igmp_mcf_iter_state));
if (!pde)
goto out_mcfilter;
err = inet_ctl_sock_create(&net->ipv4.mc_autojoin_sk, AF_INET,
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 9c169bb..f200b30 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -722,10 +722,12 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb,
erspan_build_header(skb, ntohl(tunnel->parms.o_key),
tunnel->index,
truncate, true);
- else
+ else if (tunnel->erspan_ver == 2)
erspan_build_header_v2(skb, ntohl(tunnel->parms.o_key),
tunnel->dir, tunnel->hwid,
truncate, true);
+ else
+ goto free_skb;
tunnel->parms.o_flags &= ~TUNNEL_KEY;
__gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_ERSPAN));
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 4c11b81..d54abc0 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1045,7 +1045,8 @@ static int __ip_append_data(struct sock *sk,
if (copy > length)
copy = length;
- if (!(rt->dst.dev->features&NETIF_F_SG)) {
+ if (!(rt->dst.dev->features&NETIF_F_SG) &&
+ skb_tailroom(skb) >= copy) {
unsigned int off;
off = skb->len;
@@ -1109,6 +1110,10 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
struct ip_options_rcu *opt;
struct rtable *rt;
+ rt = *rtp;
+ if (unlikely(!rt))
+ return -EFAULT;
+
/*
* setup for corking.
*/
@@ -1124,9 +1129,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
cork->flags |= IPCORK_OPT;
cork->addr = ipc->addr;
}
- rt = *rtp;
- if (unlikely(!rt))
- return -EFAULT;
+
/*
* We steal reference to this route, caller should not release it
*/
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 5ad2d8e..57bbb06 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -505,8 +505,6 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
int err;
int copied;
- WARN_ON_ONCE(sk->sk_family == AF_INET6);
-
err = -EAGAIN;
skb = sock_dequeue_err_skb(sk);
if (!skb)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 6b0e362..38d906b 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -328,7 +328,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
if (tdev) {
hlen = tdev->hard_header_len + tdev->needed_headroom;
- mtu = tdev->mtu;
+ mtu = min(tdev->mtu, IP_MAX_MTU);
}
dev->needed_headroom = t_hlen + hlen;
@@ -362,7 +362,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
nt = netdev_priv(dev);
t_hlen = nt->hlen + sizeof(struct iphdr);
dev->min_mtu = ETH_MIN_MTU;
- dev->max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
+ dev->max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen;
ip_tunnel_add(itn, nt);
return nt;
@@ -930,7 +930,7 @@ int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
int t_hlen = tunnel->hlen + sizeof(struct iphdr);
- int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
+ int max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen;
if (new_mtu < ETH_MIN_MTU)
return -EINVAL;
@@ -1107,7 +1107,7 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
mtu = ip_tunnel_bind_dev(dev);
if (tb[IFLA_MTU]) {
- unsigned int max = 0xfff8 - dev->hard_header_len - nt->hlen;
+ unsigned int max = IP_MAX_MTU - dev->hard_header_len - nt->hlen;
mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU,
(unsigned int)(max - sizeof(struct iphdr)));
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 43f620f..bbcbcc1 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1282,18 +1282,6 @@ static int pnp_seq_show(struct seq_file *seq, void *v)
&ic_servaddr);
return 0;
}
-
-static int pnp_seq_open(struct inode *indoe, struct file *file)
-{
- return single_open(file, pnp_seq_show, NULL);
-}
-
-static const struct file_operations pnp_seq_fops = {
- .open = pnp_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif /* CONFIG_PROC_FS */
/*
@@ -1369,7 +1357,7 @@ static int __init ip_auto_config(void)
unsigned int i;
#ifdef CONFIG_PROC_FS
- proc_create("pnp", 0444, init_net.proc_net, &pnp_seq_fops);
+ proc_create_single("pnp", 0444, init_net.proc_net, pnp_seq_show);
#endif /* CONFIG_PROC_FS */
if (!ic_enable)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 2fb4de3..37c4f88 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2828,19 +2828,6 @@ static const struct seq_operations ipmr_vif_seq_ops = {
.show = ipmr_vif_seq_show,
};
-static int ipmr_vif_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &ipmr_vif_seq_ops,
- sizeof(struct mr_vif_iter));
-}
-
-static const struct file_operations ipmr_vif_fops = {
- .open = ipmr_vif_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
{
struct net *net = seq_file_net(seq);
@@ -2900,19 +2887,6 @@ static const struct seq_operations ipmr_mfc_seq_ops = {
.stop = mr_mfc_seq_stop,
.show = ipmr_mfc_seq_show,
};
-
-static int ipmr_mfc_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &ipmr_mfc_seq_ops,
- sizeof(struct mr_mfc_iter));
-}
-
-static const struct file_operations ipmr_mfc_fops = {
- .open = ipmr_mfc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
#endif
#ifdef CONFIG_IP_PIMSM_V2
@@ -2977,9 +2951,11 @@ static int __net_init ipmr_net_init(struct net *net)
#ifdef CONFIG_PROC_FS
err = -ENOMEM;
- if (!proc_create("ip_mr_vif", 0, net->proc_net, &ipmr_vif_fops))
+ if (!proc_create_net("ip_mr_vif", 0, net->proc_net, &ipmr_vif_seq_ops,
+ sizeof(struct mr_vif_iter)))
goto proc_vif_fail;
- if (!proc_create("ip_mr_cache", 0, net->proc_net, &ipmr_mfc_fops))
+ if (!proc_create_net("ip_mr_cache", 0, net->proc_net, &ipmr_mfc_seq_ops,
+ sizeof(struct mr_mfc_iter)))
goto proc_cache_fail;
#endif
return 0;
diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c
index 4fe9772..3022170 100644
--- a/net/ipv4/ipmr_base.c
+++ b/net/ipv4/ipmr_base.c
@@ -43,7 +43,10 @@ mr_table_alloc(struct net *net, u32 id,
write_pnet(&mrt->net, net);
mrt->ops = *ops;
- rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params);
+ if (rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params)) {
+ kfree(mrt);
+ return NULL;
+ }
INIT_LIST_HEAD(&mrt->mfc_cache_list);
INIT_LIST_HEAD(&mrt->mfc_unres_queue);
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 44b308d..e85f35b 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -34,6 +34,7 @@
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
MODULE_DESCRIPTION("IPv4 packet filter");
+MODULE_ALIAS("ipt_icmp");
void *ipt_alloc_initial_table(const struct xt_table *info)
{
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index fd01f13..12843c9 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -89,10 +89,10 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
return true ^ invert;
}
+ memset(&flow, 0, sizeof(flow));
flow.flowi4_iif = LOOPBACK_IFINDEX;
flow.daddr = iph->saddr;
flow.saddr = rpfilter_get_saddr(iph->daddr);
- flow.flowi4_oif = 0;
flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
flow.flowi4_tos = RT_TOS(iph->tos);
flow.flowi4_scope = RT_SCOPE_UNIVERSE;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 05e47d7..2ed64bc 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -775,8 +775,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
ipc.addr = faddr = daddr;
if (ipc.opt && ipc.opt->opt.srr) {
- if (!daddr)
- return -EINVAL;
+ if (!daddr) {
+ err = -EINVAL;
+ goto out_free;
+ }
faddr = ipc.opt->opt.faddr;
}
tos = get_rttos(&ipc, inet);
@@ -842,6 +844,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
out:
ip_rt_put(rt);
+out_free:
if (free)
kfree(ipc.opt);
if (!err) {
@@ -1147,58 +1150,24 @@ static int ping_v4_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static int ping_seq_open(struct inode *inode, struct file *file)
-{
- struct ping_seq_afinfo *afinfo = PDE_DATA(inode);
- return seq_open_net(inode, file, &afinfo->seq_ops,
- sizeof(struct ping_iter_state));
-}
-
-const struct file_operations ping_seq_fops = {
- .open = ping_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
+static const struct seq_operations ping_v4_seq_ops = {
+ .start = ping_v4_seq_start,
+ .show = ping_v4_seq_show,
+ .next = ping_seq_next,
+ .stop = ping_seq_stop,
};
-EXPORT_SYMBOL_GPL(ping_seq_fops);
-
-static struct ping_seq_afinfo ping_v4_seq_afinfo = {
- .name = "icmp",
- .family = AF_INET,
- .seq_fops = &ping_seq_fops,
- .seq_ops = {
- .start = ping_v4_seq_start,
- .show = ping_v4_seq_show,
- .next = ping_seq_next,
- .stop = ping_seq_stop,
- },
-};
-
-int ping_proc_register(struct net *net, struct ping_seq_afinfo *afinfo)
-{
- struct proc_dir_entry *p;
- p = proc_create_data(afinfo->name, 0444, net->proc_net,
- afinfo->seq_fops, afinfo);
- if (!p)
- return -ENOMEM;
- return 0;
-}
-EXPORT_SYMBOL_GPL(ping_proc_register);
-
-void ping_proc_unregister(struct net *net, struct ping_seq_afinfo *afinfo)
-{
- remove_proc_entry(afinfo->name, net->proc_net);
-}
-EXPORT_SYMBOL_GPL(ping_proc_unregister);
static int __net_init ping_v4_proc_init_net(struct net *net)
{
- return ping_proc_register(net, &ping_v4_seq_afinfo);
+ if (!proc_create_net("icmp", 0444, net->proc_net, &ping_v4_seq_ops,
+ sizeof(struct ping_iter_state)))
+ return -ENOMEM;
+ return 0;
}
static void __net_exit ping_v4_proc_exit_net(struct net *net)
{
- ping_proc_unregister(net, &ping_v4_seq_afinfo);
+ remove_proc_entry("icmp", net->proc_net);
}
static struct pernet_operations ping_v4_net_ops = {
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index a058de6..573e43c 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -77,18 +77,6 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static int sockstat_seq_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, sockstat_seq_show);
-}
-
-static const struct file_operations sockstat_seq_fops = {
- .open = sockstat_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release_net,
-};
-
/* snmp items */
static const struct snmp_mib snmp4_ipstats_list[] = {
SNMP_MIB_ITEM("InReceives", IPSTATS_MIB_INPKTS),
@@ -460,20 +448,6 @@ static int snmp_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static int snmp_seq_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, snmp_seq_show);
-}
-
-static const struct file_operations snmp_seq_fops = {
- .open = snmp_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release_net,
-};
-
-
-
/*
* Output /proc/net/netstat
*/
@@ -507,26 +481,16 @@ static int netstat_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static int netstat_seq_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, netstat_seq_show);
-}
-
-static const struct file_operations netstat_seq_fops = {
- .open = netstat_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release_net,
-};
-
static __net_init int ip_proc_init_net(struct net *net)
{
- if (!proc_create("sockstat", 0444, net->proc_net,
- &sockstat_seq_fops))
+ if (!proc_create_net_single("sockstat", 0444, net->proc_net,
+ sockstat_seq_show, NULL))
goto out_sockstat;
- if (!proc_create("netstat", 0444, net->proc_net, &netstat_seq_fops))
+ if (!proc_create_net_single("netstat", 0444, net->proc_net,
+ netstat_seq_show, NULL))
goto out_netstat;
- if (!proc_create("snmp", 0444, net->proc_net, &snmp_seq_fops))
+ if (!proc_create_net_single("snmp", 0444, net->proc_net, snmp_seq_show,
+ NULL))
goto out_snmp;
return 0;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 1b4d335..abb3c94 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -1003,11 +1003,12 @@ struct proto raw_prot = {
static struct sock *raw_get_first(struct seq_file *seq)
{
struct sock *sk;
+ struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file));
struct raw_iter_state *state = raw_seq_private(seq);
for (state->bucket = 0; state->bucket < RAW_HTABLE_SIZE;
++state->bucket) {
- sk_for_each(sk, &state->h->ht[state->bucket])
+ sk_for_each(sk, &h->ht[state->bucket])
if (sock_net(sk) == seq_file_net(seq))
goto found;
}
@@ -1018,6 +1019,7 @@ static struct sock *raw_get_first(struct seq_file *seq)
static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk)
{
+ struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file));
struct raw_iter_state *state = raw_seq_private(seq);
do {
@@ -1027,7 +1029,7 @@ static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk)
} while (sk && sock_net(sk) != seq_file_net(seq));
if (!sk && ++state->bucket < RAW_HTABLE_SIZE) {
- sk = sk_head(&state->h->ht[state->bucket]);
+ sk = sk_head(&h->ht[state->bucket]);
goto try_again;
}
return sk;
@@ -1045,9 +1047,9 @@ static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos)
void *raw_seq_start(struct seq_file *seq, loff_t *pos)
{
- struct raw_iter_state *state = raw_seq_private(seq);
+ struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file));
- read_lock(&state->h->lock);
+ read_lock(&h->lock);
return *pos ? raw_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
}
EXPORT_SYMBOL_GPL(raw_seq_start);
@@ -1067,9 +1069,9 @@ EXPORT_SYMBOL_GPL(raw_seq_next);
void raw_seq_stop(struct seq_file *seq, void *v)
{
- struct raw_iter_state *state = raw_seq_private(seq);
+ struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file));
- read_unlock(&state->h->lock);
+ read_unlock(&h->lock);
}
EXPORT_SYMBOL_GPL(raw_seq_stop);
@@ -1110,37 +1112,10 @@ static const struct seq_operations raw_seq_ops = {
.show = raw_seq_show,
};
-int raw_seq_open(struct inode *ino, struct file *file,
- struct raw_hashinfo *h, const struct seq_operations *ops)
-{
- int err;
- struct raw_iter_state *i;
-
- err = seq_open_net(ino, file, ops, sizeof(struct raw_iter_state));
- if (err < 0)
- return err;
-
- i = raw_seq_private((struct seq_file *)file->private_data);
- i->h = h;
- return 0;
-}
-EXPORT_SYMBOL_GPL(raw_seq_open);
-
-static int raw_v4_seq_open(struct inode *inode, struct file *file)
-{
- return raw_seq_open(inode, file, &raw_v4_hashinfo, &raw_seq_ops);
-}
-
-static const struct file_operations raw_seq_fops = {
- .open = raw_v4_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static __net_init int raw_init_net(struct net *net)
{
- if (!proc_create("raw", 0444, net->proc_net, &raw_seq_fops))
+ if (!proc_create_net_data("raw", 0444, net->proc_net, &raw_seq_ops,
+ sizeof(struct raw_iter_state), &raw_v4_hashinfo))
return -ENOMEM;
return 0;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ccb25d80..75fb886 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -360,18 +360,6 @@ static int rt_acct_proc_show(struct seq_file *m, void *v)
kfree(dst);
return 0;
}
-
-static int rt_acct_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, rt_acct_proc_show, NULL);
-}
-
-static const struct file_operations rt_acct_proc_fops = {
- .open = rt_acct_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
#endif
static int __net_init ip_rt_do_proc_init(struct net *net)
@@ -389,7 +377,8 @@ static int __net_init ip_rt_do_proc_init(struct net *net)
goto err2;
#ifdef CONFIG_IP_ROUTE_CLASSID
- pde = proc_create("rt_acct", 0, net->proc_net, &rt_acct_proc_fops);
+ pde = proc_create_single("rt_acct", 0, net->proc_net,
+ rt_acct_proc_show);
if (!pde)
goto err3;
#endif
@@ -709,7 +698,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
fnhe->fnhe_gw = gw;
fnhe->fnhe_pmtu = pmtu;
fnhe->fnhe_mtu_locked = lock;
- fnhe->fnhe_expires = expires;
+ fnhe->fnhe_expires = max(1UL, expires);
/* Exception created; mark the cached routes for the nexthop
* stale, so anyone caching it rechecks if this exception
@@ -1297,6 +1286,36 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
}
+static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
+{
+ struct fnhe_hash_bucket *hash;
+ struct fib_nh_exception *fnhe, __rcu **fnhe_p;
+ u32 hval = fnhe_hashfun(daddr);
+
+ spin_lock_bh(&fnhe_lock);
+
+ hash = rcu_dereference_protected(nh->nh_exceptions,
+ lockdep_is_held(&fnhe_lock));
+ hash += hval;
+
+ fnhe_p = &hash->chain;
+ fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
+ while (fnhe) {
+ if (fnhe->fnhe_daddr == daddr) {
+ rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
+ fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+ fnhe_flush_routes(fnhe);
+ kfree_rcu(fnhe, rcu);
+ break;
+ }
+ fnhe_p = &fnhe->fnhe_next;
+ fnhe = rcu_dereference_protected(fnhe->fnhe_next,
+ lockdep_is_held(&fnhe_lock));
+ }
+
+ spin_unlock_bh(&fnhe_lock);
+}
+
static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
{
struct fnhe_hash_bucket *hash = rcu_dereference(nh->nh_exceptions);
@@ -1310,8 +1329,14 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
for (fnhe = rcu_dereference(hash[hval].chain); fnhe;
fnhe = rcu_dereference(fnhe->fnhe_next)) {
- if (fnhe->fnhe_daddr == daddr)
+ if (fnhe->fnhe_daddr == daddr) {
+ if (fnhe->fnhe_expires &&
+ time_after(jiffies, fnhe->fnhe_expires)) {
+ ip_del_fnhe(nh, daddr);
+ break;
+ }
return fnhe;
+ }
}
return NULL;
}
@@ -1339,6 +1364,7 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
fnhe->fnhe_gw = 0;
fnhe->fnhe_pmtu = 0;
fnhe->fnhe_expires = 0;
+ fnhe->fnhe_mtu_locked = false;
fnhe_flush_routes(fnhe);
orig = NULL;
}
@@ -1636,36 +1662,6 @@ static void ip_handle_martian_source(struct net_device *dev,
#endif
}
-static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
-{
- struct fnhe_hash_bucket *hash;
- struct fib_nh_exception *fnhe, __rcu **fnhe_p;
- u32 hval = fnhe_hashfun(daddr);
-
- spin_lock_bh(&fnhe_lock);
-
- hash = rcu_dereference_protected(nh->nh_exceptions,
- lockdep_is_held(&fnhe_lock));
- hash += hval;
-
- fnhe_p = &hash->chain;
- fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
- while (fnhe) {
- if (fnhe->fnhe_daddr == daddr) {
- rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
- fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
- fnhe_flush_routes(fnhe);
- kfree_rcu(fnhe, rcu);
- break;
- }
- fnhe_p = &fnhe->fnhe_next;
- fnhe = rcu_dereference_protected(fnhe->fnhe_next,
- lockdep_is_held(&fnhe_lock));
- }
-
- spin_unlock_bh(&fnhe_lock);
-}
-
/* called in rcu_read_lock() section */
static int __mkroute_input(struct sk_buff *skb,
const struct fib_result *res,
@@ -1719,20 +1715,10 @@ static int __mkroute_input(struct sk_buff *skb,
fnhe = find_exception(&FIB_RES_NH(*res), daddr);
if (do_cache) {
- if (fnhe) {
+ if (fnhe)
rth = rcu_dereference(fnhe->fnhe_rth_input);
- if (rth && rth->dst.expires &&
- time_after(jiffies, rth->dst.expires)) {
- ip_del_fnhe(&FIB_RES_NH(*res), daddr);
- fnhe = NULL;
- } else {
- goto rt_cache;
- }
- }
-
- rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
-
-rt_cache:
+ else
+ rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
if (rt_cache_valid(rth)) {
skb_dst_set_noref(skb, &rth->dst);
goto out;
@@ -1964,8 +1950,13 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
fl4.saddr = saddr;
fl4.flowi4_uid = sock_net_uid(net, NULL);
- if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys))
+ if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) {
flkeys = &_flkeys;
+ } else {
+ fl4.flowi4_proto = 0;
+ fl4.fl4_sport = 0;
+ fl4.fl4_dport = 0;
+ }
err = fib_lookup(net, &fl4, res, 0);
if (err != 0) {
@@ -2216,39 +2207,31 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
* the loopback interface and the IP_PKTINFO ipi_ifindex will
* be set to the loopback interface as well.
*/
- fi = NULL;
+ do_cache = false;
}
fnhe = NULL;
do_cache &= fi != NULL;
- if (do_cache) {
+ if (fi) {
struct rtable __rcu **prth;
struct fib_nh *nh = &FIB_RES_NH(*res);
fnhe = find_exception(nh, fl4->daddr);
+ if (!do_cache)
+ goto add;
if (fnhe) {
prth = &fnhe->fnhe_rth_output;
- rth = rcu_dereference(*prth);
- if (rth && rth->dst.expires &&
- time_after(jiffies, rth->dst.expires)) {
- ip_del_fnhe(nh, fl4->daddr);
- fnhe = NULL;
- } else {
- goto rt_cache;
+ } else {
+ if (unlikely(fl4->flowi4_flags &
+ FLOWI_FLAG_KNOWN_NH &&
+ !(nh->nh_gw &&
+ nh->nh_scope == RT_SCOPE_LINK))) {
+ do_cache = false;
+ goto add;
}
+ prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
}
-
- if (unlikely(fl4->flowi4_flags &
- FLOWI_FLAG_KNOWN_NH &&
- !(nh->nh_gw &&
- nh->nh_scope == RT_SCOPE_LINK))) {
- do_cache = false;
- goto add;
- }
- prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
rth = rcu_dereference(*prth);
-
-rt_cache:
if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst))
return rth;
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bccc4c2..dec47e6 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -494,32 +494,21 @@ static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
}
/*
- * Wait for a TCP event.
- *
- * Note that we don't need to lock the socket, as the upper poll layers
- * take care of normal races (between the test and the event) and we don't
- * go look at any of the socket buffers directly.
+ * Socket is not locked. We are protected from async events by poll logic and
+ * correct handling of state changes made by other threads is impossible in
+ * any case.
*/
-__poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
+__poll_t tcp_poll_mask(struct socket *sock, __poll_t events)
{
- __poll_t mask;
struct sock *sk = sock->sk;
const struct tcp_sock *tp = tcp_sk(sk);
+ __poll_t mask = 0;
int state;
- sock_poll_wait(file, sk_sleep(sk), wait);
-
state = inet_sk_state_load(sk);
if (state == TCP_LISTEN)
return inet_csk_listen_poll(sk);
- /* Socket is not locked. We are protected from async events
- * by poll logic and correct handling of state changes
- * made by other threads is impossible in any case.
- */
-
- mask = 0;
-
/*
* EPOLLHUP is certainly not done right. But poll() doesn't
* have a notion of HUP in just one direction, and for a
@@ -600,7 +589,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
return mask;
}
-EXPORT_SYMBOL(tcp_poll);
+EXPORT_SYMBOL(tcp_poll_mask);
int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
@@ -697,7 +686,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
{
return skb->len < size_goal &&
sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
- skb != tcp_write_queue_head(sk) &&
+ !tcp_rtx_queue_empty(sk) &&
refcount_read(&sk->sk_wmem_alloc) > skb->truesize;
}
@@ -1204,7 +1193,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
uarg->zerocopy = 0;
}
- if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect)) {
+ if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) &&
+ !tp->repair) {
err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
if (err == -EINPROGRESS && copied_syn > 0)
goto out;
@@ -2368,6 +2358,7 @@ void tcp_write_queue_purge(struct sock *sk)
INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue);
sk_mem_reclaim(sk);
tcp_clear_all_retrans_hints(tcp_sk(sk));
+ tcp_sk(sk)->packets_out = 0;
}
int tcp_disconnect(struct sock *sk, int flags)
@@ -2417,7 +2408,6 @@ int tcp_disconnect(struct sock *sk, int flags)
icsk->icsk_backoff = 0;
tp->snd_cwnd = 2;
icsk->icsk_probes_out = 0;
- tp->packets_out = 0;
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd_cnt = 0;
tp->window_clamp = 0;
@@ -2673,7 +2663,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
case TCP_REPAIR_QUEUE:
if (!tp->repair)
err = -EPERM;
- else if (val < TCP_QUEUES_NR)
+ else if ((unsigned int)val < TCP_QUEUES_NR)
tp->repair_queue = val;
else
err = -EINVAL;
@@ -2813,8 +2803,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
#ifdef CONFIG_TCP_MD5SIG
case TCP_MD5SIG:
case TCP_MD5SIG_EXT:
- /* Read the IP->Key mappings from userspace */
- err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
+ if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
+ err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
+ else
+ err = -EINVAL;
break;
#endif
case TCP_USER_TIMEOUT:
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 158d105..58e2f47 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -806,7 +806,9 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs)
}
}
}
- bbr->idle_restart = 0;
+ /* Restart after idle ends only once we process a new S/ACK for data */
+ if (rs->delivered > 0)
+ bbr->idle_restart = 0;
}
static void bbr_update_model(struct sock *sk, const struct rate_sample *rs)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 367def6..e51c644 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3868,11 +3868,8 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th)
int length = (th->doff << 2) - sizeof(*th);
const u8 *ptr = (const u8 *)(th + 1);
- /* If the TCP option is too short, we can short cut */
- if (length < TCPOLEN_MD5SIG)
- return NULL;
-
- while (length > 0) {
+ /* If not enough data remaining, we can short cut */
+ while (length >= TCPOLEN_MD5SIG) {
int opcode = *ptr++;
int opsize;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f70586b..2c97062 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1961,6 +1961,7 @@ EXPORT_SYMBOL(tcp_v4_destroy_sock);
*/
static void *listening_get_next(struct seq_file *seq, void *cur)
{
+ struct tcp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file));
struct tcp_iter_state *st = seq->private;
struct net *net = seq_file_net(seq);
struct inet_listen_hashbucket *ilb;
@@ -1983,7 +1984,7 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
sk_for_each_from(sk) {
if (!net_eq(sock_net(sk), net))
continue;
- if (sk->sk_family == st->family)
+ if (sk->sk_family == afinfo->family)
return sk;
}
spin_unlock(&ilb->lock);
@@ -2020,6 +2021,7 @@ static inline bool empty_bucket(const struct tcp_iter_state *st)
*/
static void *established_get_first(struct seq_file *seq)
{
+ struct tcp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file));
struct tcp_iter_state *st = seq->private;
struct net *net = seq_file_net(seq);
void *rc = NULL;
@@ -2036,7 +2038,7 @@ static void *established_get_first(struct seq_file *seq)
spin_lock_bh(lock);
sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) {
- if (sk->sk_family != st->family ||
+ if (sk->sk_family != afinfo->family ||
!net_eq(sock_net(sk), net)) {
continue;
}
@@ -2051,6 +2053,7 @@ static void *established_get_first(struct seq_file *seq)
static void *established_get_next(struct seq_file *seq, void *cur)
{
+ struct tcp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file));
struct sock *sk = cur;
struct hlist_nulls_node *node;
struct tcp_iter_state *st = seq->private;
@@ -2062,7 +2065,8 @@ static void *established_get_next(struct seq_file *seq, void *cur)
sk = sk_nulls_next(sk);
sk_nulls_for_each_from(sk, node) {
- if (sk->sk_family == st->family && net_eq(sock_net(sk), net))
+ if (sk->sk_family == afinfo->family &&
+ net_eq(sock_net(sk), net))
return sk;
}
@@ -2135,7 +2139,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq)
return rc;
}
-static void *tcp_seq_start(struct seq_file *seq, loff_t *pos)
+void *tcp_seq_start(struct seq_file *seq, loff_t *pos)
{
struct tcp_iter_state *st = seq->private;
void *rc;
@@ -2156,8 +2160,9 @@ static void *tcp_seq_start(struct seq_file *seq, loff_t *pos)
st->last_pos = *pos;
return rc;
}
+EXPORT_SYMBOL(tcp_seq_start);
-static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct tcp_iter_state *st = seq->private;
void *rc = NULL;
@@ -2186,8 +2191,9 @@ static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
st->last_pos = *pos;
return rc;
}
+EXPORT_SYMBOL(tcp_seq_next);
-static void tcp_seq_stop(struct seq_file *seq, void *v)
+void tcp_seq_stop(struct seq_file *seq, void *v)
{
struct tcp_iter_state *st = seq->private;
@@ -2202,47 +2208,7 @@ static void tcp_seq_stop(struct seq_file *seq, void *v)
break;
}
}
-
-int tcp_seq_open(struct inode *inode, struct file *file)
-{
- struct tcp_seq_afinfo *afinfo = PDE_DATA(inode);
- struct tcp_iter_state *s;
- int err;
-
- err = seq_open_net(inode, file, &afinfo->seq_ops,
- sizeof(struct tcp_iter_state));
- if (err < 0)
- return err;
-
- s = ((struct seq_file *)file->private_data)->private;
- s->family = afinfo->family;
- s->last_pos = 0;
- return 0;
-}
-EXPORT_SYMBOL(tcp_seq_open);
-
-int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo)
-{
- int rc = 0;
- struct proc_dir_entry *p;
-
- afinfo->seq_ops.start = tcp_seq_start;
- afinfo->seq_ops.next = tcp_seq_next;
- afinfo->seq_ops.stop = tcp_seq_stop;
-
- p = proc_create_data(afinfo->name, 0444, net->proc_net,
- afinfo->seq_fops, afinfo);
- if (!p)
- rc = -ENOMEM;
- return rc;
-}
-EXPORT_SYMBOL(tcp_proc_register);
-
-void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo)
-{
- remove_proc_entry(afinfo->name, net->proc_net);
-}
-EXPORT_SYMBOL(tcp_proc_unregister);
+EXPORT_SYMBOL(tcp_seq_stop);
static void get_openreq4(const struct request_sock *req,
struct seq_file *f, int i)
@@ -2377,30 +2343,28 @@ static int tcp4_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static const struct file_operations tcp_afinfo_seq_fops = {
- .open = tcp_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net
+static const struct seq_operations tcp4_seq_ops = {
+ .show = tcp4_seq_show,
+ .start = tcp_seq_start,
+ .next = tcp_seq_next,
+ .stop = tcp_seq_stop,
};
static struct tcp_seq_afinfo tcp4_seq_afinfo = {
- .name = "tcp",
.family = AF_INET,
- .seq_fops = &tcp_afinfo_seq_fops,
- .seq_ops = {
- .show = tcp4_seq_show,
- },
};
static int __net_init tcp4_proc_init_net(struct net *net)
{
- return tcp_proc_register(net, &tcp4_seq_afinfo);
+ if (!proc_create_net_data("tcp", 0444, net->proc_net, &tcp4_seq_ops,
+ sizeof(struct tcp_iter_state), &tcp4_seq_afinfo))
+ return -ENOMEM;
+ return 0;
}
static void __net_exit tcp4_proc_exit_net(struct net *net)
{
- tcp_proc_unregister(net, &tcp4_seq_afinfo);
+ remove_proc_entry("tcp", net->proc_net);
}
static struct pernet_operations tcp4_net_ops = {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 383cac0..d07e34f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2833,8 +2833,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
return -EBUSY;
if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
- if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
- BUG();
+ if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) {
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+ }
if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq))
return -ENOMEM;
}
@@ -3342,6 +3344,7 @@ static void tcp_connect_init(struct sock *sk)
sock_reset_flag(sk, SOCK_DONE);
tp->snd_wnd = 0;
tcp_init_wl(tp, 0);
+ tcp_write_queue_purge(sk);
tp->snd_una = tp->write_seq;
tp->snd_sml = tp->write_seq;
tp->snd_up = tp->write_seq;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 24b5c59..675433e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -401,9 +401,9 @@ static int compute_score(struct sock *sk, struct net *net,
bool dev_match = (sk->sk_bound_dev_if == dif ||
sk->sk_bound_dev_if == sdif);
- if (exact_dif && !dev_match)
+ if (!dev_match)
return -1;
- if (sk->sk_bound_dev_if && dev_match)
+ if (sk->sk_bound_dev_if)
score += 4;
}
@@ -952,8 +952,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags);
if (ipc.opt && ipc.opt->opt.srr) {
- if (!daddr)
- return -EINVAL;
+ if (!daddr) {
+ err = -EINVAL;
+ goto out_free;
+ }
faddr = ipc.opt->opt.faddr;
connected = 0;
}
@@ -1074,6 +1076,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
out:
ip_rt_put(rt);
+out_free:
if (free)
kfree(ipc.opt);
if (!err)
@@ -2498,7 +2501,7 @@ int compat_udp_getsockopt(struct sock *sk, int level, int optname,
* udp_poll - wait for a UDP event.
* @file - file struct
* @sock - socket
- * @wait - poll table
+ * @events - events to wait for
*
* This is same as datagram poll, except for the special case of
* blocking sockets. If application is using a blocking fd
@@ -2507,23 +2510,23 @@ int compat_udp_getsockopt(struct sock *sk, int level, int optname,
* but then block when reading it. Add special case code
* to work around these arguably broken applications.
*/
-__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait)
+__poll_t udp_poll_mask(struct socket *sock, __poll_t events)
{
- __poll_t mask = datagram_poll(file, sock, wait);
+ __poll_t mask = datagram_poll_mask(sock, events);
struct sock *sk = sock->sk;
if (!skb_queue_empty(&udp_sk(sk)->reader_queue))
mask |= EPOLLIN | EPOLLRDNORM;
/* Check for false positives due to checksum errors */
- if ((mask & EPOLLRDNORM) && !(file->f_flags & O_NONBLOCK) &&
+ if ((mask & EPOLLRDNORM) && !(sock->file->f_flags & O_NONBLOCK) &&
!(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
mask &= ~(EPOLLIN | EPOLLRDNORM);
return mask;
}
-EXPORT_SYMBOL(udp_poll);
+EXPORT_SYMBOL(udp_poll_mask);
int udp_abort(struct sock *sk, int err)
{
@@ -2579,12 +2582,13 @@ EXPORT_SYMBOL(udp_prot);
static struct sock *udp_get_first(struct seq_file *seq, int start)
{
struct sock *sk;
+ struct udp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file));
struct udp_iter_state *state = seq->private;
struct net *net = seq_file_net(seq);
- for (state->bucket = start; state->bucket <= state->udp_table->mask;
+ for (state->bucket = start; state->bucket <= afinfo->udp_table->mask;
++state->bucket) {
- struct udp_hslot *hslot = &state->udp_table->hash[state->bucket];
+ struct udp_hslot *hslot = &afinfo->udp_table->hash[state->bucket];
if (hlist_empty(&hslot->head))
continue;
@@ -2593,7 +2597,7 @@ static struct sock *udp_get_first(struct seq_file *seq, int start)
sk_for_each(sk, &hslot->head) {
if (!net_eq(sock_net(sk), net))
continue;
- if (sk->sk_family == state->family)
+ if (sk->sk_family == afinfo->family)
goto found;
}
spin_unlock_bh(&hslot->lock);
@@ -2605,16 +2609,17 @@ static struct sock *udp_get_first(struct seq_file *seq, int start)
static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk)
{
+ struct udp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file));
struct udp_iter_state *state = seq->private;
struct net *net = seq_file_net(seq);
do {
sk = sk_next(sk);
- } while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != state->family));
+ } while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != afinfo->family));
if (!sk) {
- if (state->bucket <= state->udp_table->mask)
- spin_unlock_bh(&state->udp_table->hash[state->bucket].lock);
+ if (state->bucket <= afinfo->udp_table->mask)
+ spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock);
return udp_get_first(seq, state->bucket + 1);
}
return sk;
@@ -2630,15 +2635,16 @@ static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos)
return pos ? NULL : sk;
}
-static void *udp_seq_start(struct seq_file *seq, loff_t *pos)
+void *udp_seq_start(struct seq_file *seq, loff_t *pos)
{
struct udp_iter_state *state = seq->private;
state->bucket = MAX_UDP_PORTS;
return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN;
}
+EXPORT_SYMBOL(udp_seq_start);
-static void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct sock *sk;
@@ -2650,56 +2656,17 @@ static void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
++*pos;
return sk;
}
+EXPORT_SYMBOL(udp_seq_next);
-static void udp_seq_stop(struct seq_file *seq, void *v)
+void udp_seq_stop(struct seq_file *seq, void *v)
{
+ struct udp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file));
struct udp_iter_state *state = seq->private;
- if (state->bucket <= state->udp_table->mask)
- spin_unlock_bh(&state->udp_table->hash[state->bucket].lock);
+ if (state->bucket <= afinfo->udp_table->mask)
+ spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock);
}
-
-int udp_seq_open(struct inode *inode, struct file *file)
-{
- struct udp_seq_afinfo *afinfo = PDE_DATA(inode);
- struct udp_iter_state *s;
- int err;
-
- err = seq_open_net(inode, file, &afinfo->seq_ops,
- sizeof(struct udp_iter_state));
- if (err < 0)
- return err;
-
- s = ((struct seq_file *)file->private_data)->private;
- s->family = afinfo->family;
- s->udp_table = afinfo->udp_table;
- return err;
-}
-EXPORT_SYMBOL(udp_seq_open);
-
-/* ------------------------------------------------------------------------ */
-int udp_proc_register(struct net *net, struct udp_seq_afinfo *afinfo)
-{
- struct proc_dir_entry *p;
- int rc = 0;
-
- afinfo->seq_ops.start = udp_seq_start;
- afinfo->seq_ops.next = udp_seq_next;
- afinfo->seq_ops.stop = udp_seq_stop;
-
- p = proc_create_data(afinfo->name, 0444, net->proc_net,
- afinfo->seq_fops, afinfo);
- if (!p)
- rc = -ENOMEM;
- return rc;
-}
-EXPORT_SYMBOL(udp_proc_register);
-
-void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo)
-{
- remove_proc_entry(afinfo->name, net->proc_net);
-}
-EXPORT_SYMBOL(udp_proc_unregister);
+EXPORT_SYMBOL(udp_seq_stop);
/* ------------------------------------------------------------------------ */
static void udp4_format_sock(struct sock *sp, struct seq_file *f,
@@ -2739,32 +2706,30 @@ int udp4_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static const struct file_operations udp_afinfo_seq_fops = {
- .open = udp_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net
+const struct seq_operations udp_seq_ops = {
+ .start = udp_seq_start,
+ .next = udp_seq_next,
+ .stop = udp_seq_stop,
+ .show = udp4_seq_show,
};
+EXPORT_SYMBOL(udp_seq_ops);
-/* ------------------------------------------------------------------------ */
static struct udp_seq_afinfo udp4_seq_afinfo = {
- .name = "udp",
.family = AF_INET,
.udp_table = &udp_table,
- .seq_fops = &udp_afinfo_seq_fops,
- .seq_ops = {
- .show = udp4_seq_show,
- },
};
static int __net_init udp4_proc_init_net(struct net *net)
{
- return udp_proc_register(net, &udp4_seq_afinfo);
+ if (!proc_create_net_data("udp", 0444, net->proc_net, &udp_seq_ops,
+ sizeof(struct udp_iter_state), &udp4_seq_afinfo))
+ return -ENOMEM;
+ return 0;
}
static void __net_exit udp4_proc_exit_net(struct net *net)
{
- udp_proc_unregister(net, &udp4_seq_afinfo);
+ remove_proc_entry("udp", net->proc_net);
}
static struct pernet_operations udp4_net_ops = {
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index f96614e..85454577 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -14,6 +14,7 @@
#define pr_fmt(fmt) "UDPLite: " fmt
#include <linux/export.h>
+#include <linux/proc_fs.h>
#include "udp_impl.h"
struct udp_table udplite_table __read_mostly;
@@ -73,32 +74,22 @@ static struct inet_protosw udplite4_protosw = {
};
#ifdef CONFIG_PROC_FS
-
-static const struct file_operations udplite_afinfo_seq_fops = {
- .open = udp_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net
-};
-
static struct udp_seq_afinfo udplite4_seq_afinfo = {
- .name = "udplite",
.family = AF_INET,
.udp_table = &udplite_table,
- .seq_fops = &udplite_afinfo_seq_fops,
- .seq_ops = {
- .show = udp4_seq_show,
- },
};
static int __net_init udplite4_proc_init_net(struct net *net)
{
- return udp_proc_register(net, &udplite4_seq_afinfo);
+ if (!proc_create_net_data("udplite", 0444, net->proc_net, &udp_seq_ops,
+ sizeof(struct udp_iter_state), &udplite4_seq_afinfo))
+ return -ENOMEM;
+ return 0;
}
static void __net_exit udplite4_proc_exit_net(struct net *net)
{
- udp_proc_unregister(net, &udplite4_seq_afinfo);
+ remove_proc_entry("udplite", net->proc_net);
}
static struct pernet_operations udplite4_net_ops = {
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 6794ddf..11e4e80 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -34,16 +34,15 @@
bool "IPv6: Route Information (RFC 4191) support"
depends on IPV6_ROUTER_PREF
---help---
- This is experimental support of Route Information.
+ Support of Route Information.
If unsure, say N.
config IPV6_OPTIMISTIC_DAD
bool "IPv6: Enable RFC 4429 Optimistic DAD"
---help---
- This is experimental support for optimistic Duplicate
- Address Detection. It allows for autoconfigured addresses
- to be used more quickly.
+ Support for optimistic Duplicate Address Detection. It allows for
+ autoconfigured addresses to be used more quickly.
If unsure, say N.
@@ -280,7 +279,7 @@
depends on IPV6
select IP_MROUTE_COMMON
---help---
- Experimental support for IPv6 multicast forwarding.
+ Support for IPv6 multicast forwarding.
If unsure, say N.
config IPV6_MROUTE_MULTIPLE_TABLES
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 78cef00..1b5ea33 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4254,22 +4254,10 @@ static const struct seq_operations if6_seq_ops = {
.stop = if6_seq_stop,
};
-static int if6_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &if6_seq_ops,
- sizeof(struct if6_iter_state));
-}
-
-static const struct file_operations if6_fops = {
- .open = if6_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static int __net_init if6_proc_net_init(struct net *net)
{
- if (!proc_create("if_inet6", 0444, net->proc_net, &if6_fops))
+ if (!proc_create_net("if_inet6", 0444, net->proc_net, &if6_seq_ops,
+ sizeof(struct if6_iter_state)))
return -ENOMEM;
return 0;
}
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 8da0b51..d443c18 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -571,7 +571,7 @@ const struct proto_ops inet6_stream_ops = {
.socketpair = sock_no_socketpair, /* a do nothing */
.accept = inet_accept, /* ok */
.getname = inet6_getname,
- .poll = tcp_poll, /* ok */
+ .poll_mask = tcp_poll_mask, /* ok */
.ioctl = inet6_ioctl, /* must change */
.listen = inet_listen, /* ok */
.shutdown = inet_shutdown, /* ok */
@@ -601,7 +601,7 @@ const struct proto_ops inet6_dgram_ops = {
.socketpair = sock_no_socketpair, /* a do nothing */
.accept = sock_no_accept, /* a do nothing */
.getname = inet6_getname,
- .poll = udp_poll, /* ok */
+ .poll_mask = udp_poll_mask, /* ok */
.ioctl = inet6_ioctl, /* must change */
.listen = sock_no_listen, /* ok */
.shutdown = inet_shutdown, /* ok */
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index bbcabbb..ebeaf47 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -529,22 +529,10 @@ static const struct seq_operations ac6_seq_ops = {
.show = ac6_seq_show,
};
-static int ac6_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &ac6_seq_ops,
- sizeof(struct ac6_iter_state));
-}
-
-static const struct file_operations ac6_seq_fops = {
- .open = ac6_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
int __net_init ac6_proc_init(struct net *net)
{
- if (!proc_create("anycast6", 0444, net->proc_net, &ac6_seq_fops))
+ if (!proc_create_net("anycast6", 0444, net->proc_net, &ac6_seq_ops,
+ sizeof(struct ac6_iter_state)))
return -ENOMEM;
return 0;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index deab2db..01372dd 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -2209,15 +2209,6 @@ void fib6_gc_cleanup(void)
}
#ifdef CONFIG_PROC_FS
-
-struct ipv6_route_iter {
- struct seq_net_private p;
- struct fib6_walker w;
- loff_t skip;
- struct fib6_table *tbl;
- int sernum;
-};
-
static int ipv6_route_seq_show(struct seq_file *seq, void *v)
{
struct rt6_info *rt = v;
@@ -2383,17 +2374,10 @@ static void ipv6_route_seq_stop(struct seq_file *seq, void *v)
rcu_read_unlock_bh();
}
-static const struct seq_operations ipv6_route_seq_ops = {
+const struct seq_operations ipv6_route_seq_ops = {
.start = ipv6_route_seq_start,
.next = ipv6_route_seq_next,
.stop = ipv6_route_seq_stop,
.show = ipv6_route_seq_show
};
-
-int ipv6_route_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &ipv6_route_seq_ops,
- sizeof(struct ipv6_route_iter));
-}
-
#endif /* CONFIG_PROC_FS */
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index c05c4e8..3eee763 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -754,6 +754,10 @@ static struct ip6_flowlabel *ip6fl_get_idx(struct seq_file *seq, loff_t pos)
static void *ip6fl_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(RCU)
{
+ struct ip6fl_iter_state *state = ip6fl_seq_private(seq);
+
+ state->pid_ns = proc_pid_ns(file_inode(seq->file));
+
rcu_read_lock_bh();
return *pos ? ip6fl_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
}
@@ -808,44 +812,10 @@ static const struct seq_operations ip6fl_seq_ops = {
.show = ip6fl_seq_show,
};
-static int ip6fl_seq_open(struct inode *inode, struct file *file)
-{
- struct seq_file *seq;
- struct ip6fl_iter_state *state;
- int err;
-
- err = seq_open_net(inode, file, &ip6fl_seq_ops,
- sizeof(struct ip6fl_iter_state));
-
- if (!err) {
- seq = file->private_data;
- state = ip6fl_seq_private(seq);
- rcu_read_lock();
- state->pid_ns = get_pid_ns(task_active_pid_ns(current));
- rcu_read_unlock();
- }
- return err;
-}
-
-static int ip6fl_seq_release(struct inode *inode, struct file *file)
-{
- struct seq_file *seq = file->private_data;
- struct ip6fl_iter_state *state = ip6fl_seq_private(seq);
- put_pid_ns(state->pid_ns);
- return seq_release_net(inode, file);
-}
-
-static const struct file_operations ip6fl_seq_fops = {
- .open = ip6fl_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = ip6fl_seq_release,
-};
-
static int __net_init ip6_flowlabel_proc_init(struct net *net)
{
- if (!proc_create("ip6_flowlabel", 0444, net->proc_net,
- &ip6fl_seq_fops))
+ if (!proc_create_net("ip6_flowlabel", 0444, net->proc_net,
+ &ip6fl_seq_ops, sizeof(struct ip6fl_iter_state)))
return -ENOMEM;
return 0;
}
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 69727bc..458de35 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -71,6 +71,7 @@ struct ip6gre_net {
struct ip6_tnl __rcu *tunnels[4][IP6_GRE_HASH_SIZE];
struct ip6_tnl __rcu *collect_md_tun;
+ struct ip6_tnl __rcu *collect_md_tun_erspan;
struct net_device *fb_tunnel_dev;
};
@@ -81,6 +82,7 @@ static int ip6gre_tunnel_init(struct net_device *dev);
static void ip6gre_tunnel_setup(struct net_device *dev);
static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t);
static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu);
+static void ip6erspan_tnl_link_config(struct ip6_tnl *t, int set_mtu);
/* Tunnel hash table */
@@ -232,7 +234,12 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
if (cand)
return cand;
- t = rcu_dereference(ign->collect_md_tun);
+ if (gre_proto == htons(ETH_P_ERSPAN) ||
+ gre_proto == htons(ETH_P_ERSPAN2))
+ t = rcu_dereference(ign->collect_md_tun_erspan);
+ else
+ t = rcu_dereference(ign->collect_md_tun);
+
if (t && t->dev->flags & IFF_UP)
return t;
@@ -261,6 +268,31 @@ static struct ip6_tnl __rcu **__ip6gre_bucket(struct ip6gre_net *ign,
return &ign->tunnels[prio][h];
}
+static void ip6gre_tunnel_link_md(struct ip6gre_net *ign, struct ip6_tnl *t)
+{
+ if (t->parms.collect_md)
+ rcu_assign_pointer(ign->collect_md_tun, t);
+}
+
+static void ip6erspan_tunnel_link_md(struct ip6gre_net *ign, struct ip6_tnl *t)
+{
+ if (t->parms.collect_md)
+ rcu_assign_pointer(ign->collect_md_tun_erspan, t);
+}
+
+static void ip6gre_tunnel_unlink_md(struct ip6gre_net *ign, struct ip6_tnl *t)
+{
+ if (t->parms.collect_md)
+ rcu_assign_pointer(ign->collect_md_tun, NULL);
+}
+
+static void ip6erspan_tunnel_unlink_md(struct ip6gre_net *ign,
+ struct ip6_tnl *t)
+{
+ if (t->parms.collect_md)
+ rcu_assign_pointer(ign->collect_md_tun_erspan, NULL);
+}
+
static inline struct ip6_tnl __rcu **ip6gre_bucket(struct ip6gre_net *ign,
const struct ip6_tnl *t)
{
@@ -271,9 +303,6 @@ static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t)
{
struct ip6_tnl __rcu **tp = ip6gre_bucket(ign, t);
- if (t->parms.collect_md)
- rcu_assign_pointer(ign->collect_md_tun, t);
-
rcu_assign_pointer(t->next, rtnl_dereference(*tp));
rcu_assign_pointer(*tp, t);
}
@@ -283,9 +312,6 @@ static void ip6gre_tunnel_unlink(struct ip6gre_net *ign, struct ip6_tnl *t)
struct ip6_tnl __rcu **tp;
struct ip6_tnl *iter;
- if (t->parms.collect_md)
- rcu_assign_pointer(ign->collect_md_tun, NULL);
-
for (tp = ip6gre_bucket(ign, t);
(iter = rtnl_dereference(*tp)) != NULL;
tp = &iter->next) {
@@ -374,11 +400,23 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net,
return NULL;
}
+static void ip6erspan_tunnel_uninit(struct net_device *dev)
+{
+ struct ip6_tnl *t = netdev_priv(dev);
+ struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
+
+ ip6erspan_tunnel_unlink_md(ign, t);
+ ip6gre_tunnel_unlink(ign, t);
+ dst_cache_reset(&t->dst_cache);
+ dev_put(dev);
+}
+
static void ip6gre_tunnel_uninit(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
+ ip6gre_tunnel_unlink_md(ign, t);
ip6gre_tunnel_unlink(ign, t);
dst_cache_reset(&t->dst_cache);
dev_put(dev);
@@ -698,6 +736,9 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
else
fl6->daddr = tunnel->parms.raddr;
+ if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen))
+ return -ENOMEM;
+
/* Push GRE header. */
protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto;
@@ -908,7 +949,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
truncate = true;
}
- if (skb_cow_head(skb, dev->needed_headroom))
+ if (skb_cow_head(skb, dev->needed_headroom ?: t->hlen))
goto tx_err;
t->parms.o_flags &= ~TUNNEL_KEY;
@@ -979,11 +1020,14 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
erspan_build_header(skb, ntohl(t->parms.o_key),
t->parms.index,
truncate, false);
- else
+ else if (t->parms.erspan_ver == 2)
erspan_build_header_v2(skb, ntohl(t->parms.o_key),
t->parms.dir,
t->parms.hwid,
truncate, false);
+ else
+ goto tx_err;
+
fl6.daddr = t->parms.raddr;
}
@@ -1019,12 +1063,11 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
return NETDEV_TX_OK;
}
-static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
+static void ip6gre_tnl_link_config_common(struct ip6_tnl *t)
{
struct net_device *dev = t->dev;
struct __ip6_tnl_parm *p = &t->parms;
struct flowi6 *fl6 = &t->fl.u.ip6;
- int t_hlen;
if (dev->type != ARPHRD_ETHER) {
memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
@@ -1051,12 +1094,13 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
dev->flags |= IFF_POINTOPOINT;
else
dev->flags &= ~IFF_POINTOPOINT;
+}
- t->tun_hlen = gre_calc_hlen(t->parms.o_flags);
-
- t->hlen = t->encap_hlen + t->tun_hlen;
-
- t_hlen = t->hlen + sizeof(struct ipv6hdr);
+static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu,
+ int t_hlen)
+{
+ const struct __ip6_tnl_parm *p = &t->parms;
+ struct net_device *dev = t->dev;
if (p->flags & IP6_TNL_F_CAP_XMIT) {
int strict = (ipv6_addr_type(&p->raddr) &
@@ -1088,8 +1132,26 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
}
}
-static int ip6gre_tnl_change(struct ip6_tnl *t,
- const struct __ip6_tnl_parm *p, int set_mtu)
+static int ip6gre_calc_hlen(struct ip6_tnl *tunnel)
+{
+ int t_hlen;
+
+ tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags);
+ tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;
+
+ t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
+ tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+ return t_hlen;
+}
+
+static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
+{
+ ip6gre_tnl_link_config_common(t);
+ ip6gre_tnl_link_config_route(t, set_mtu, ip6gre_calc_hlen(t));
+}
+
+static void ip6gre_tnl_copy_tnl_parm(struct ip6_tnl *t,
+ const struct __ip6_tnl_parm *p)
{
t->parms.laddr = p->laddr;
t->parms.raddr = p->raddr;
@@ -1105,6 +1167,12 @@ static int ip6gre_tnl_change(struct ip6_tnl *t,
t->parms.o_flags = p->o_flags;
t->parms.fwmark = p->fwmark;
dst_cache_reset(&t->dst_cache);
+}
+
+static int ip6gre_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p,
+ int set_mtu)
+{
+ ip6gre_tnl_copy_tnl_parm(t, p);
ip6gre_tnl_link_config(t, set_mtu);
return 0;
}
@@ -1381,11 +1449,7 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
return ret;
}
- tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags);
- tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;
- t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
-
- dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+ t_hlen = ip6gre_calc_hlen(tunnel);
dev->mtu = ETH_DATA_LEN - t_hlen;
if (dev->type == ARPHRD_ETHER)
dev->mtu -= ETH_HLEN;
@@ -1728,6 +1792,19 @@ static const struct net_device_ops ip6gre_tap_netdev_ops = {
.ndo_get_iflink = ip6_tnl_get_iflink,
};
+static int ip6erspan_calc_hlen(struct ip6_tnl *tunnel)
+{
+ int t_hlen;
+
+ tunnel->tun_hlen = 8;
+ tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen +
+ erspan_hdr_len(tunnel->parms.erspan_ver);
+
+ t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
+ tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+ return t_hlen;
+}
+
static int ip6erspan_tap_init(struct net_device *dev)
{
struct ip6_tnl *tunnel;
@@ -1751,12 +1828,7 @@ static int ip6erspan_tap_init(struct net_device *dev)
return ret;
}
- tunnel->tun_hlen = 8;
- tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen +
- erspan_hdr_len(tunnel->parms.erspan_ver);
- t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
-
- dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+ t_hlen = ip6erspan_calc_hlen(tunnel);
dev->mtu = ETH_DATA_LEN - t_hlen;
if (dev->type == ARPHRD_ETHER)
dev->mtu -= ETH_HLEN;
@@ -1764,14 +1836,14 @@ static int ip6erspan_tap_init(struct net_device *dev)
dev->mtu -= 8;
dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
- ip6gre_tnl_link_config(tunnel, 1);
+ ip6erspan_tnl_link_config(tunnel, 1);
return 0;
}
static const struct net_device_ops ip6erspan_netdev_ops = {
.ndo_init = ip6erspan_tap_init,
- .ndo_uninit = ip6gre_tunnel_uninit,
+ .ndo_uninit = ip6erspan_tunnel_uninit,
.ndo_start_xmit = ip6erspan_tunnel_xmit,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
@@ -1835,13 +1907,11 @@ static bool ip6gre_netlink_encap_parms(struct nlattr *data[],
return ret;
}
-static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
- struct nlattr *tb[], struct nlattr *data[],
- struct netlink_ext_ack *extack)
+static int ip6gre_newlink_common(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[],
+ struct netlink_ext_ack *extack)
{
struct ip6_tnl *nt;
- struct net *net = dev_net(dev);
- struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
struct ip_tunnel_encap ipencap;
int err;
@@ -1854,16 +1924,6 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
return err;
}
- ip6gre_netlink_parms(data, &nt->parms);
-
- if (nt->parms.collect_md) {
- if (rtnl_dereference(ign->collect_md_tun))
- return -EEXIST;
- } else {
- if (ip6gre_tunnel_find(net, &nt->parms, dev->type))
- return -EEXIST;
- }
-
if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
eth_hw_addr_random(dev);
@@ -1874,51 +1934,94 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
if (err)
goto out;
- ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
-
if (tb[IFLA_MTU])
ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU]));
dev_hold(dev);
- ip6gre_tunnel_link(ign, nt);
out:
return err;
}
+static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[],
+ struct netlink_ext_ack *extack)
+{
+ struct ip6_tnl *nt = netdev_priv(dev);
+ struct net *net = dev_net(dev);
+ struct ip6gre_net *ign;
+ int err;
+
+ ip6gre_netlink_parms(data, &nt->parms);
+ ign = net_generic(net, ip6gre_net_id);
+
+ if (nt->parms.collect_md) {
+ if (rtnl_dereference(ign->collect_md_tun))
+ return -EEXIST;
+ } else {
+ if (ip6gre_tunnel_find(net, &nt->parms, dev->type))
+ return -EEXIST;
+ }
+
+ err = ip6gre_newlink_common(src_net, dev, tb, data, extack);
+ if (!err) {
+ ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
+ ip6gre_tunnel_link_md(ign, nt);
+ ip6gre_tunnel_link(net_generic(net, ip6gre_net_id), nt);
+ }
+ return err;
+}
+
+static struct ip6_tnl *
+ip6gre_changelink_common(struct net_device *dev, struct nlattr *tb[],
+ struct nlattr *data[], struct __ip6_tnl_parm *p_p,
+ struct netlink_ext_ack *extack)
+{
+ struct ip6_tnl *t, *nt = netdev_priv(dev);
+ struct net *net = nt->net;
+ struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+ struct ip_tunnel_encap ipencap;
+
+ if (dev == ign->fb_tunnel_dev)
+ return ERR_PTR(-EINVAL);
+
+ if (ip6gre_netlink_encap_parms(data, &ipencap)) {
+ int err = ip6_tnl_encap_setup(nt, &ipencap);
+
+ if (err < 0)
+ return ERR_PTR(err);
+ }
+
+ ip6gre_netlink_parms(data, p_p);
+
+ t = ip6gre_tunnel_locate(net, p_p, 0);
+
+ if (t) {
+ if (t->dev != dev)
+ return ERR_PTR(-EEXIST);
+ } else {
+ t = nt;
+ }
+
+ return t;
+}
+
static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[],
struct netlink_ext_ack *extack)
{
- struct ip6_tnl *t, *nt = netdev_priv(dev);
- struct net *net = nt->net;
- struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+ struct ip6gre_net *ign = net_generic(dev_net(dev), ip6gre_net_id);
struct __ip6_tnl_parm p;
- struct ip_tunnel_encap ipencap;
+ struct ip6_tnl *t;
- if (dev == ign->fb_tunnel_dev)
- return -EINVAL;
+ t = ip6gre_changelink_common(dev, tb, data, &p, extack);
+ if (IS_ERR(t))
+ return PTR_ERR(t);
- if (ip6gre_netlink_encap_parms(data, &ipencap)) {
- int err = ip6_tnl_encap_setup(nt, &ipencap);
-
- if (err < 0)
- return err;
- }
-
- ip6gre_netlink_parms(data, &p);
-
- t = ip6gre_tunnel_locate(net, &p, 0);
-
- if (t) {
- if (t->dev != dev)
- return -EEXIST;
- } else {
- t = nt;
- }
-
+ ip6gre_tunnel_unlink_md(ign, t);
ip6gre_tunnel_unlink(ign, t);
ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]);
+ ip6gre_tunnel_link_md(ign, t);
ip6gre_tunnel_link(ign, t);
return 0;
}
@@ -2068,6 +2171,69 @@ static void ip6erspan_tap_setup(struct net_device *dev)
netif_keep_dst(dev);
}
+static int ip6erspan_newlink(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[],
+ struct netlink_ext_ack *extack)
+{
+ struct ip6_tnl *nt = netdev_priv(dev);
+ struct net *net = dev_net(dev);
+ struct ip6gre_net *ign;
+ int err;
+
+ ip6gre_netlink_parms(data, &nt->parms);
+ ign = net_generic(net, ip6gre_net_id);
+
+ if (nt->parms.collect_md) {
+ if (rtnl_dereference(ign->collect_md_tun_erspan))
+ return -EEXIST;
+ } else {
+ if (ip6gre_tunnel_find(net, &nt->parms, dev->type))
+ return -EEXIST;
+ }
+
+ err = ip6gre_newlink_common(src_net, dev, tb, data, extack);
+ if (!err) {
+ ip6erspan_tnl_link_config(nt, !tb[IFLA_MTU]);
+ ip6erspan_tunnel_link_md(ign, nt);
+ ip6gre_tunnel_link(net_generic(net, ip6gre_net_id), nt);
+ }
+ return err;
+}
+
+static void ip6erspan_tnl_link_config(struct ip6_tnl *t, int set_mtu)
+{
+ ip6gre_tnl_link_config_common(t);
+ ip6gre_tnl_link_config_route(t, set_mtu, ip6erspan_calc_hlen(t));
+}
+
+static int ip6erspan_tnl_change(struct ip6_tnl *t,
+ const struct __ip6_tnl_parm *p, int set_mtu)
+{
+ ip6gre_tnl_copy_tnl_parm(t, p);
+ ip6erspan_tnl_link_config(t, set_mtu);
+ return 0;
+}
+
+static int ip6erspan_changelink(struct net_device *dev, struct nlattr *tb[],
+ struct nlattr *data[],
+ struct netlink_ext_ack *extack)
+{
+ struct ip6gre_net *ign = net_generic(dev_net(dev), ip6gre_net_id);
+ struct __ip6_tnl_parm p;
+ struct ip6_tnl *t;
+
+ t = ip6gre_changelink_common(dev, tb, data, &p, extack);
+ if (IS_ERR(t))
+ return PTR_ERR(t);
+
+ ip6gre_tunnel_unlink_md(ign, t);
+ ip6gre_tunnel_unlink(ign, t);
+ ip6erspan_tnl_change(t, &p, !tb[IFLA_MTU]);
+ ip6erspan_tunnel_link_md(ign, t);
+ ip6gre_tunnel_link(ign, t);
+ return 0;
+}
+
static struct rtnl_link_ops ip6gre_link_ops __read_mostly = {
.kind = "ip6gre",
.maxtype = IFLA_GRE_MAX,
@@ -2104,8 +2270,8 @@ static struct rtnl_link_ops ip6erspan_tap_ops __read_mostly = {
.priv_size = sizeof(struct ip6_tnl),
.setup = ip6erspan_tap_setup,
.validate = ip6erspan_tap_validate,
- .newlink = ip6gre_newlink,
- .changelink = ip6gre_changelink,
+ .newlink = ip6erspan_newlink,
+ .changelink = ip6erspan_changelink,
.get_size = ip6gre_get_size,
.fill_info = ip6gre_fill_info,
.get_link_net = ip6_tnl_get_link_net,
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 2e891d2..7b6d168 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1503,7 +1503,8 @@ static int __ip6_append_data(struct sock *sk,
if (copy > length)
copy = length;
- if (!(rt->dst.dev->features&NETIF_F_SG)) {
+ if (!(rt->dst.dev->features&NETIF_F_SG) &&
+ skb_tailroom(skb) >= copy) {
unsigned int off;
off = skb->len;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index da66aaa..00e138a 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1692,8 +1692,13 @@ int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)
if (new_mtu < ETH_MIN_MTU)
return -EINVAL;
}
- if (new_mtu > 0xFFF8 - dev->hard_header_len)
- return -EINVAL;
+ if (tnl->parms.proto == IPPROTO_IPV6 || tnl->parms.proto == 0) {
+ if (new_mtu > IP6_MAX_MTU - dev->hard_header_len)
+ return -EINVAL;
+ } else {
+ if (new_mtu > IP_MAX_MTU - dev->hard_header_len)
+ return -EINVAL;
+ }
dev->mtu = new_mtu;
return 0;
}
@@ -1841,7 +1846,7 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
dev->mtu -= 8;
dev->min_mtu = ETH_MIN_MTU;
- dev->max_mtu = 0xFFF8 - dev->hard_header_len;
+ dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len;
return 0;
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index c214ffe..ca957dd 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -669,7 +669,7 @@ static void vti6_link_config(struct ip6_tnl *t, bool keep_mtu)
else
mtu = ETH_DATA_LEN - LL_MAX_HEADER - sizeof(struct ipv6hdr);
- dev->mtu = max_t(int, mtu, IPV6_MIN_MTU);
+ dev->mtu = max_t(int, mtu, IPV4_MIN_MTU);
}
/**
@@ -881,7 +881,7 @@ static void vti6_dev_setup(struct net_device *dev)
dev->priv_destructor = vti6_dev_free;
dev->type = ARPHRD_TUNNEL6;
- dev->min_mtu = IPV6_MIN_MTU;
+ dev->min_mtu = IPV4_MIN_MTU;
dev->max_mtu = IP_MAX_MTU - sizeof(struct ipv6hdr);
dev->flags |= IFF_NOARP;
dev->addr_len = sizeof(struct in6_addr);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 298fd8b..4a15529 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -439,19 +439,6 @@ static const struct seq_operations ip6mr_vif_seq_ops = {
.show = ip6mr_vif_seq_show,
};
-static int ip6mr_vif_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &ip6mr_vif_seq_ops,
- sizeof(struct mr_vif_iter));
-}
-
-static const struct file_operations ip6mr_vif_fops = {
- .open = ip6mr_vif_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
{
struct net *net = seq_file_net(seq);
@@ -512,19 +499,6 @@ static const struct seq_operations ipmr_mfc_seq_ops = {
.stop = mr_mfc_seq_stop,
.show = ipmr_mfc_seq_show,
};
-
-static int ipmr_mfc_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &ipmr_mfc_seq_ops,
- sizeof(struct mr_mfc_iter));
-}
-
-static const struct file_operations ip6mr_mfc_fops = {
- .open = ipmr_mfc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
#endif
#ifdef CONFIG_IPV6_PIMSM_V2
@@ -1316,9 +1290,11 @@ static int __net_init ip6mr_net_init(struct net *net)
#ifdef CONFIG_PROC_FS
err = -ENOMEM;
- if (!proc_create("ip6_mr_vif", 0, net->proc_net, &ip6mr_vif_fops))
+ if (!proc_create_net("ip6_mr_vif", 0, net->proc_net, &ip6mr_vif_seq_ops,
+ sizeof(struct mr_vif_iter)))
goto proc_vif_fail;
- if (!proc_create("ip6_mr_cache", 0, net->proc_net, &ip6mr_mfc_fops))
+ if (!proc_create_net("ip6_mr_cache", 0, net->proc_net, &ipmr_mfc_seq_ops,
+ sizeof(struct mr_mfc_iter)))
goto proc_cache_fail;
#endif
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 793159d..975021d 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2749,19 +2749,6 @@ static const struct seq_operations igmp6_mc_seq_ops = {
.show = igmp6_mc_seq_show,
};
-static int igmp6_mc_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &igmp6_mc_seq_ops,
- sizeof(struct igmp6_mc_iter_state));
-}
-
-static const struct file_operations igmp6_mc_seq_fops = {
- .open = igmp6_mc_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
struct igmp6_mcf_iter_state {
struct seq_net_private p;
struct net_device *dev;
@@ -2903,28 +2890,17 @@ static const struct seq_operations igmp6_mcf_seq_ops = {
.show = igmp6_mcf_seq_show,
};
-static int igmp6_mcf_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &igmp6_mcf_seq_ops,
- sizeof(struct igmp6_mcf_iter_state));
-}
-
-static const struct file_operations igmp6_mcf_seq_fops = {
- .open = igmp6_mcf_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static int __net_init igmp6_proc_init(struct net *net)
{
int err;
err = -ENOMEM;
- if (!proc_create("igmp6", 0444, net->proc_net, &igmp6_mc_seq_fops))
+ if (!proc_create_net("igmp6", 0444, net->proc_net, &igmp6_mc_seq_ops,
+ sizeof(struct igmp6_mc_iter_state)))
goto out;
- if (!proc_create("mcfilter6", 0444, net->proc_net,
- &igmp6_mcf_seq_fops))
+ if (!proc_create_net("mcfilter6", 0444, net->proc_net,
+ &igmp6_mcf_seq_ops,
+ sizeof(struct igmp6_mcf_iter_state)))
goto out_proc_net_igmp6;
err = 0;
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index ccbfa83..ce77bcc 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -48,6 +48,34 @@
fields such as the source, destination, flowlabel, hop-limit and
the packet mark.
+if NF_NAT_IPV6
+
+config NFT_CHAIN_NAT_IPV6
+ tristate "IPv6 nf_tables nat chain support"
+ help
+ This option enables the "nat" chain for IPv6 in nf_tables. This
+ chain type is used to perform Network Address Translation (NAT)
+ packet transformations such as the source, destination address and
+ source and destination ports.
+
+config NFT_MASQ_IPV6
+ tristate "IPv6 masquerade support for nf_tables"
+ depends on NFT_MASQ
+ select NF_NAT_MASQUERADE_IPV6
+ help
+ This is the expression that provides IPv4 masquerading support for
+ nf_tables.
+
+config NFT_REDIR_IPV6
+ tristate "IPv6 redirect support for nf_tables"
+ depends on NFT_REDIR
+ select NF_NAT_REDIRECT
+ help
+ This is the expression that provides IPv4 redirect support for
+ nf_tables.
+
+endif # NF_NAT_IPV6
+
config NFT_REJECT_IPV6
select NF_REJECT_IPV6
default NFT_REJECT
@@ -107,39 +135,12 @@
if NF_NAT_IPV6
-config NFT_CHAIN_NAT_IPV6
- depends on NF_TABLES_IPV6
- tristate "IPv6 nf_tables nat chain support"
- help
- This option enables the "nat" chain for IPv6 in nf_tables. This
- chain type is used to perform Network Address Translation (NAT)
- packet transformations such as the source, destination address and
- source and destination ports.
-
config NF_NAT_MASQUERADE_IPV6
tristate "IPv6 masquerade support"
help
This is the kernel functionality to provide NAT in the masquerade
flavour (automatic source address selection) for IPv6.
-config NFT_MASQ_IPV6
- tristate "IPv6 masquerade support for nf_tables"
- depends on NF_TABLES_IPV6
- depends on NFT_MASQ
- select NF_NAT_MASQUERADE_IPV6
- help
- This is the expression that provides IPv4 masquerading support for
- nf_tables.
-
-config NFT_REDIR_IPV6
- tristate "IPv6 redirect support for nf_tables"
- depends on NF_TABLES_IPV6
- depends on NFT_REDIR
- select NF_NAT_REDIRECT
- help
- This is the expression that provides IPv4 redirect support for
- nf_tables.
-
endif # NF_NAT_IPV6
config IP6_NF_IPTABLES
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 65c9e1a..97f79dc 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -38,6 +38,7 @@
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
MODULE_DESCRIPTION("IPv6 packet filter");
+MODULE_ALIAS("ip6t_icmp6");
void *ip6t_alloc_initial_table(const struct xt_table *info)
{
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 746eeae..96f56bf 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -24,6 +24,7 @@
#include <net/protocol.h>
#include <net/udp.h>
#include <net/transp_v6.h>
+#include <linux/proc_fs.h>
#include <net/ping.h>
/* Compatibility glue so we can support IPv6 when it's compiled as a module */
@@ -215,26 +216,24 @@ static int ping_v6_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static struct ping_seq_afinfo ping_v6_seq_afinfo = {
- .name = "icmp6",
- .family = AF_INET6,
- .seq_fops = &ping_seq_fops,
- .seq_ops = {
- .start = ping_v6_seq_start,
- .show = ping_v6_seq_show,
- .next = ping_seq_next,
- .stop = ping_seq_stop,
- },
+static const struct seq_operations ping_v6_seq_ops = {
+ .start = ping_v6_seq_start,
+ .show = ping_v6_seq_show,
+ .next = ping_seq_next,
+ .stop = ping_seq_stop,
};
static int __net_init ping_v6_proc_init_net(struct net *net)
{
- return ping_proc_register(net, &ping_v6_seq_afinfo);
+ if (!proc_create_net("icmp6", 0444, net->proc_net, &ping_v6_seq_ops,
+ sizeof(struct ping_iter_state)))
+ return -ENOMEM;
+ return 0;
}
static void __net_init ping_v6_proc_exit_net(struct net *net)
{
- return ping_proc_unregister(net, &ping_v6_seq_afinfo);
+ remove_proc_entry("icmp6", net->proc_net);
}
static struct pernet_operations ping_v6_net_ops = {
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index a85f7e0..2356b4a 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -53,18 +53,6 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static int sockstat6_seq_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, sockstat6_seq_show);
-}
-
-static const struct file_operations sockstat6_seq_fops = {
- .open = sockstat6_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release_net,
-};
-
static const struct snmp_mib snmp6_ipstats_list[] = {
/* ipv6 mib according to RFC 2465 */
SNMP_MIB_ITEM("Ip6InReceives", IPSTATS_MIB_INPKTS),
@@ -242,18 +230,6 @@ static int snmp6_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static int snmp6_seq_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, snmp6_seq_show);
-}
-
-static const struct file_operations snmp6_seq_fops = {
- .open = snmp6_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release_net,
-};
-
static int snmp6_dev_seq_show(struct seq_file *seq, void *v)
{
struct inet6_dev *idev = (struct inet6_dev *)seq->private;
@@ -267,18 +243,6 @@ static int snmp6_dev_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static int snmp6_dev_seq_open(struct inode *inode, struct file *file)
-{
- return single_open(file, snmp6_dev_seq_show, PDE_DATA(inode));
-}
-
-static const struct file_operations snmp6_dev_seq_fops = {
- .open = snmp6_dev_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
int snmp6_register_dev(struct inet6_dev *idev)
{
struct proc_dir_entry *p;
@@ -291,9 +255,8 @@ int snmp6_register_dev(struct inet6_dev *idev)
if (!net->mib.proc_net_devsnmp6)
return -ENOENT;
- p = proc_create_data(idev->dev->name, 0444,
- net->mib.proc_net_devsnmp6,
- &snmp6_dev_seq_fops, idev);
+ p = proc_create_single_data(idev->dev->name, 0444,
+ net->mib.proc_net_devsnmp6, snmp6_dev_seq_show, idev);
if (!p)
return -ENOMEM;
@@ -315,11 +278,12 @@ int snmp6_unregister_dev(struct inet6_dev *idev)
static int __net_init ipv6_proc_init_net(struct net *net)
{
- if (!proc_create("sockstat6", 0444, net->proc_net,
- &sockstat6_seq_fops))
+ if (!proc_create_net_single("sockstat6", 0444, net->proc_net,
+ sockstat6_seq_show, NULL))
return -ENOMEM;
- if (!proc_create("snmp6", 0444, net->proc_net, &snmp6_seq_fops))
+ if (!proc_create_net_single("snmp6", 0444, net->proc_net,
+ snmp6_seq_show, NULL))
goto proc_snmp6_fail;
net->mib.proc_net_devsnmp6 = proc_mkdir("dev_snmp6", net->proc_net);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 5eb9b08..ce6f0d1 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1304,21 +1304,10 @@ static const struct seq_operations raw6_seq_ops = {
.show = raw6_seq_show,
};
-static int raw6_seq_open(struct inode *inode, struct file *file)
-{
- return raw_seq_open(inode, file, &raw_v6_hashinfo, &raw6_seq_ops);
-}
-
-static const struct file_operations raw6_seq_fops = {
- .open = raw6_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static int __net_init raw6_init_net(struct net *net)
{
- if (!proc_create("raw6", 0444, net->proc_net, &raw6_seq_fops))
+ if (!proc_create_net_data("raw6", 0444, net->proc_net, &raw6_seq_ops,
+ sizeof(struct raw_iter_state), &raw_v6_hashinfo))
return -ENOMEM;
return 0;
@@ -1345,7 +1334,7 @@ void raw6_proc_exit(void)
}
#endif /* CONFIG_PROC_FS */
-/* Same as inet6_dgram_ops, sans udp_poll. */
+/* Same as inet6_dgram_ops, sans udp_poll_mask. */
const struct proto_ops inet6_sockraw_ops = {
.family = PF_INET6,
.owner = THIS_MODULE,
@@ -1355,7 +1344,7 @@ const struct proto_ops inet6_sockraw_ops = {
.socketpair = sock_no_socketpair, /* a do nothing */
.accept = sock_no_accept, /* a do nothing */
.getname = inet6_getname,
- .poll = datagram_poll, /* ok */
+ .poll_mask = datagram_poll_mask, /* ok */
.ioctl = inet6_ioctl, /* must change */
.listen = sock_no_listen, /* ok */
.shutdown = inet_shutdown, /* ok */
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 49b954d..a659876 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1835,11 +1835,16 @@ static void ip6_multipath_l3_keys(const struct sk_buff *skb,
const struct ipv6hdr *inner_iph;
const struct icmp6hdr *icmph;
struct ipv6hdr _inner_iph;
+ struct icmp6hdr _icmph;
if (likely(outer_iph->nexthdr != IPPROTO_ICMPV6))
goto out;
- icmph = icmp6_hdr(skb);
+ icmph = skb_header_pointer(skb, skb_transport_offset(skb),
+ sizeof(_icmph), &_icmph);
+ if (!icmph)
+ goto out;
+
if (icmph->icmp6_type != ICMPV6_DEST_UNREACH &&
icmph->icmp6_type != ICMPV6_PKT_TOOBIG &&
icmph->icmp6_type != ICMPV6_TIME_EXCEED &&
@@ -3975,6 +3980,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu)
static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_GATEWAY] = { .len = sizeof(struct in6_addr) },
+ [RTA_PREFSRC] = { .len = sizeof(struct in6_addr) },
[RTA_OIF] = { .type = NLA_U32 },
[RTA_IIF] = { .type = NLA_U32 },
[RTA_PRIORITY] = { .type = NLA_U32 },
@@ -3986,6 +3992,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_EXPIRES] = { .type = NLA_U32 },
[RTA_UID] = { .type = NLA_U32 },
[RTA_MARK] = { .type = NLA_U32 },
+ [RTA_TABLE] = { .type = NLA_U32 },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -4855,14 +4862,6 @@ static int ip6_route_dev_notify(struct notifier_block *this,
*/
#ifdef CONFIG_PROC_FS
-
-static const struct file_operations ipv6_route_proc_fops = {
- .open = ipv6_route_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static int rt6_stats_seq_show(struct seq_file *seq, void *v)
{
struct net *net = (struct net *)seq->private;
@@ -4877,18 +4876,6 @@ static int rt6_stats_seq_show(struct seq_file *seq, void *v)
return 0;
}
-
-static int rt6_stats_seq_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, rt6_stats_seq_show);
-}
-
-static const struct file_operations rt6_stats_seq_fops = {
- .open = rt6_stats_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release_net,
-};
#endif /* CONFIG_PROC_FS */
#ifdef CONFIG_SYSCTL
@@ -5093,8 +5080,10 @@ static void __net_exit ip6_route_net_exit(struct net *net)
static int __net_init ip6_route_net_init_late(struct net *net)
{
#ifdef CONFIG_PROC_FS
- proc_create("ipv6_route", 0, net->proc_net, &ipv6_route_proc_fops);
- proc_create("rt6_stats", 0444, net->proc_net, &rt6_stats_seq_fops);
+ proc_create_net("ipv6_route", 0, net->proc_net, &ipv6_route_seq_ops,
+ sizeof(struct ipv6_route_iter));
+ proc_create_net_single("rt6_stats", 0444, net->proc_net,
+ rt6_stats_seq_show, NULL);
#endif
return 0;
}
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index f343e6f..bf4763fd 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -103,7 +103,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
hdrlen = (osrh->hdrlen + 1) << 3;
tot_len = hdrlen + sizeof(*hdr);
- err = skb_cow_head(skb, tot_len);
+ err = skb_cow_head(skb, tot_len + skb->mac_len);
if (unlikely(err))
return err;
@@ -136,7 +136,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
isrh->nexthdr = proto;
hdr->daddr = isrh->segments[isrh->first_segment];
- set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr);
+ set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr);
#ifdef CONFIG_IPV6_SEG6_HMAC
if (sr_has_hmac(isrh)) {
@@ -161,7 +161,7 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
hdrlen = (osrh->hdrlen + 1) << 3;
- err = skb_cow_head(skb, hdrlen);
+ err = skb_cow_head(skb, hdrlen + skb->mac_len);
if (unlikely(err))
return err;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 2afce37..e9400ff 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1371,7 +1371,7 @@ static void ipip6_tunnel_setup(struct net_device *dev)
dev->hard_header_len = LL_MAX_HEADER + t_hlen;
dev->mtu = ETH_DATA_LEN - t_hlen;
dev->min_mtu = IPV6_MIN_MTU;
- dev->max_mtu = 0xFFF8 - t_hlen;
+ dev->max_mtu = IP6_MAX_MTU - t_hlen;
dev->flags = IFF_NOARP;
netif_keep_dst(dev);
dev->addr_len = 4;
@@ -1583,7 +1583,8 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev,
if (tb[IFLA_MTU]) {
u32 mtu = nla_get_u32(tb[IFLA_MTU]);
- if (mtu >= IPV6_MIN_MTU && mtu <= 0xFFF8 - dev->hard_header_len)
+ if (mtu >= IPV6_MIN_MTU &&
+ mtu <= IP6_MAX_MTU - dev->hard_header_len)
dev->mtu = mtu;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 6d664d8..d2ce66b 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1909,30 +1909,28 @@ static int tcp6_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static const struct file_operations tcp6_afinfo_seq_fops = {
- .open = tcp_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net
+static const struct seq_operations tcp6_seq_ops = {
+ .show = tcp6_seq_show,
+ .start = tcp_seq_start,
+ .next = tcp_seq_next,
+ .stop = tcp_seq_stop,
};
static struct tcp_seq_afinfo tcp6_seq_afinfo = {
- .name = "tcp6",
.family = AF_INET6,
- .seq_fops = &tcp6_afinfo_seq_fops,
- .seq_ops = {
- .show = tcp6_seq_show,
- },
};
int __net_init tcp6_proc_init(struct net *net)
{
- return tcp_proc_register(net, &tcp6_seq_afinfo);
+ if (!proc_create_net_data("tcp6", 0444, net->proc_net, &tcp6_seq_ops,
+ sizeof(struct tcp_iter_state), &tcp6_seq_afinfo))
+ return -ENOMEM;
+ return 0;
}
void tcp6_proc_exit(struct net *net)
{
- tcp_proc_unregister(net, &tcp6_seq_afinfo);
+ remove_proc_entry("tcp6", net->proc_net);
}
#endif
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4ec76a8..00e2112 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -148,9 +148,9 @@ static int compute_score(struct sock *sk, struct net *net,
bool dev_match = (sk->sk_bound_dev_if == dif ||
sk->sk_bound_dev_if == sdif);
- if (exact_dif && !dev_match)
+ if (!dev_match)
return -1;
- if (sk->sk_bound_dev_if && dev_match)
+ if (sk->sk_bound_dev_if)
score++;
}
@@ -1480,31 +1480,30 @@ int udp6_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static const struct file_operations udp6_afinfo_seq_fops = {
- .open = udp_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net
+const struct seq_operations udp6_seq_ops = {
+ .start = udp_seq_start,
+ .next = udp_seq_next,
+ .stop = udp_seq_stop,
+ .show = udp6_seq_show,
};
+EXPORT_SYMBOL(udp6_seq_ops);
static struct udp_seq_afinfo udp6_seq_afinfo = {
- .name = "udp6",
.family = AF_INET6,
.udp_table = &udp_table,
- .seq_fops = &udp6_afinfo_seq_fops,
- .seq_ops = {
- .show = udp6_seq_show,
- },
};
int __net_init udp6_proc_init(struct net *net)
{
- return udp_proc_register(net, &udp6_seq_afinfo);
+ if (!proc_create_net_data("udp6", 0444, net->proc_net, &udp6_seq_ops,
+ sizeof(struct udp_iter_state), &udp6_seq_afinfo))
+ return -ENOMEM;
+ return 0;
}
void udp6_proc_exit(struct net *net)
{
- udp_proc_unregister(net, &udp6_seq_afinfo);
+ remove_proc_entry("udp6", net->proc_net);
}
#endif /* CONFIG_PROC_FS */
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 14ae32b..5000ad6 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -12,6 +12,7 @@
* 2 of the License, or (at your option) any later version.
*/
#include <linux/export.h>
+#include <linux/proc_fs.h>
#include "udp_impl.h"
static int udplitev6_rcv(struct sk_buff *skb)
@@ -92,32 +93,23 @@ void udplitev6_exit(void)
}
#ifdef CONFIG_PROC_FS
-
-static const struct file_operations udplite6_afinfo_seq_fops = {
- .open = udp_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net
-};
-
static struct udp_seq_afinfo udplite6_seq_afinfo = {
- .name = "udplite6",
.family = AF_INET6,
.udp_table = &udplite_table,
- .seq_fops = &udplite6_afinfo_seq_fops,
- .seq_ops = {
- .show = udp6_seq_show,
- },
};
static int __net_init udplite6_proc_init_net(struct net *net)
{
- return udp_proc_register(net, &udplite6_seq_afinfo);
+ if (!proc_create_net_data("udplite6", 0444, net->proc_net,
+ &udp6_seq_ops, sizeof(struct udp_iter_state),
+ &udplite6_seq_afinfo))
+ return -ENOMEM;
+ return 0;
}
static void __net_exit udplite6_proc_exit_net(struct net *net)
{
- udp_proc_unregister(net, &udplite6_seq_afinfo);
+ remove_proc_entry("udplite6", net->proc_net);
}
static struct pernet_operations udplite6_net_ops = {
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 416fe67..86dba28 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -126,7 +126,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
struct flowi6 *fl6 = &fl->u.ip6;
int onlyproto = 0;
const struct ipv6hdr *hdr = ipv6_hdr(skb);
- u16 offset = sizeof(*hdr);
+ u32 offset = sizeof(*hdr);
struct ipv6_opt_hdr *exthdr;
const unsigned char *nh = skb_network_header(skb);
u16 nhoff = IP6CB(skb)->nhoff;
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index f85f0d7..4a46df8 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -341,6 +341,9 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net)
struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net);
unsigned int i;
+ xfrm_state_flush(net, IPSEC_PROTO_ANY, false);
+ xfrm_flush_gc();
+
for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++)
WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i]));
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 893a022..68e8625 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1488,14 +1488,11 @@ static inline __poll_t iucv_accept_poll(struct sock *parent)
return 0;
}
-__poll_t iucv_sock_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+static __poll_t iucv_sock_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
__poll_t mask = 0;
- sock_poll_wait(file, sk_sleep(sk), wait);
-
if (sk->sk_state == IUCV_LISTEN)
return iucv_accept_poll(sk);
@@ -2388,7 +2385,7 @@ static const struct proto_ops iucv_sock_ops = {
.getname = iucv_sock_getname,
.sendmsg = iucv_sock_sendmsg,
.recvmsg = iucv_sock_recvmsg,
- .poll = iucv_sock_poll,
+ .poll_mask = iucv_sock_poll_mask,
.ioctl = sock_no_ioctl,
.mmap = sock_no_mmap,
.socketpair = sock_no_socketpair,
diff --git a/net/kcm/kcmproc.c b/net/kcm/kcmproc.c
index 1fac925..370da2f 100644
--- a/net/kcm/kcmproc.c
+++ b/net/kcm/kcmproc.c
@@ -15,12 +15,6 @@
#include <net/tcp.h>
#ifdef CONFIG_PROC_FS
-struct kcm_seq_muxinfo {
- char *name;
- const struct file_operations *seq_fops;
- const struct seq_operations seq_ops;
-};
-
static struct kcm_mux *kcm_get_first(struct seq_file *seq)
{
struct net *net = seq_file_net(seq);
@@ -86,14 +80,6 @@ struct kcm_proc_mux_state {
int idx;
};
-static int kcm_seq_open(struct inode *inode, struct file *file)
-{
- struct kcm_seq_muxinfo *muxinfo = PDE_DATA(inode);
-
- return seq_open_net(inode, file, &muxinfo->seq_ops,
- sizeof(struct kcm_proc_mux_state));
-}
-
static void kcm_format_mux_header(struct seq_file *seq)
{
struct net *net = seq_file_net(seq);
@@ -246,44 +232,13 @@ static int kcm_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static const struct file_operations kcm_seq_fops = {
- .open = kcm_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
+static const struct seq_operations kcm_seq_ops = {
+ .show = kcm_seq_show,
+ .start = kcm_seq_start,
+ .next = kcm_seq_next,
+ .stop = kcm_seq_stop,
};
-static struct kcm_seq_muxinfo kcm_seq_muxinfo = {
- .name = "kcm",
- .seq_fops = &kcm_seq_fops,
- .seq_ops = {
- .show = kcm_seq_show,
- .start = kcm_seq_start,
- .next = kcm_seq_next,
- .stop = kcm_seq_stop,
- }
-};
-
-static int kcm_proc_register(struct net *net, struct kcm_seq_muxinfo *muxinfo)
-{
- struct proc_dir_entry *p;
- int rc = 0;
-
- p = proc_create_data(muxinfo->name, 0444, net->proc_net,
- muxinfo->seq_fops, muxinfo);
- if (!p)
- rc = -ENOMEM;
- return rc;
-}
-EXPORT_SYMBOL(kcm_proc_register);
-
-static void kcm_proc_unregister(struct net *net,
- struct kcm_seq_muxinfo *muxinfo)
-{
- remove_proc_entry(muxinfo->name, net->proc_net);
-}
-EXPORT_SYMBOL(kcm_proc_unregister);
-
static int kcm_stats_seq_show(struct seq_file *seq, void *v)
{
struct kcm_psock_stats psock_stats;
@@ -390,30 +345,14 @@ static int kcm_stats_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static int kcm_stats_seq_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, kcm_stats_seq_show);
-}
-
-static const struct file_operations kcm_stats_seq_fops = {
- .open = kcm_stats_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release_net,
-};
-
static int kcm_proc_init_net(struct net *net)
{
- int err;
-
- if (!proc_create("kcm_stats", 0444, net->proc_net,
- &kcm_stats_seq_fops)) {
- err = -ENOMEM;
+ if (!proc_create_net_single("kcm_stats", 0444, net->proc_net,
+ kcm_stats_seq_show, NULL))
goto out_kcm_stats;
- }
- err = kcm_proc_register(net, &kcm_seq_muxinfo);
- if (err)
+ if (!proc_create_net("kcm", 0444, net->proc_net, &kcm_seq_ops,
+ sizeof(struct kcm_proc_mux_state)))
goto out_kcm;
return 0;
@@ -421,12 +360,12 @@ static int kcm_proc_init_net(struct net *net)
out_kcm:
remove_proc_entry("kcm_stats", net->proc_net);
out_kcm_stats:
- return err;
+ return -ENOMEM;
}
static void kcm_proc_exit_net(struct net *net)
{
- kcm_proc_unregister(net, &kcm_seq_muxinfo);
+ remove_proc_entry("kcm", net->proc_net);
remove_proc_entry("kcm_stats", net->proc_net);
}
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index dc76bc3..84b7d5c 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1336,9 +1336,9 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux)
struct list_head *head;
int index = 0;
- /* For SOCK_SEQPACKET sock type, datagram_poll checks the sk_state, so
- * we set sk_state, otherwise epoll_wait always returns right away with
- * EPOLLHUP
+ /* For SOCK_SEQPACKET sock type, datagram_poll_mask checks the sk_state,
+ * so we set sk_state, otherwise epoll_wait always returns right away
+ * with EPOLLHUP
*/
kcm->sk.sk_state = TCP_ESTABLISHED;
@@ -1671,7 +1671,7 @@ static struct file *kcm_clone(struct socket *osock)
__module_get(newsock->ops->owner);
newsk = sk_alloc(sock_net(osock->sk), PF_KCM, GFP_KERNEL,
- &kcm_proto, true);
+ &kcm_proto, false);
if (!newsk) {
sock_release(newsock);
return ERR_PTR(-ENOMEM);
@@ -1903,7 +1903,7 @@ static const struct proto_ops kcm_dgram_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = kcm_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
@@ -1924,7 +1924,7 @@ static const struct proto_ops kcm_seqpacket_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = kcm_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 7e2e718..8bdc1cb 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -437,6 +437,24 @@ static int verify_address_len(const void *p)
return 0;
}
+static inline int sadb_key_len(const struct sadb_key *key)
+{
+ int key_bytes = DIV_ROUND_UP(key->sadb_key_bits, 8);
+
+ return DIV_ROUND_UP(sizeof(struct sadb_key) + key_bytes,
+ sizeof(uint64_t));
+}
+
+static int verify_key_len(const void *p)
+{
+ const struct sadb_key *key = p;
+
+ if (sadb_key_len(key) > key->sadb_key_len)
+ return -EINVAL;
+
+ return 0;
+}
+
static inline int pfkey_sec_ctx_len(const struct sadb_x_sec_ctx *sec_ctx)
{
return DIV_ROUND_UP(sizeof(struct sadb_x_sec_ctx) +
@@ -533,16 +551,25 @@ static int parse_exthdrs(struct sk_buff *skb, const struct sadb_msg *hdr, void *
return -EINVAL;
if (ext_hdrs[ext_type-1] != NULL)
return -EINVAL;
- if (ext_type == SADB_EXT_ADDRESS_SRC ||
- ext_type == SADB_EXT_ADDRESS_DST ||
- ext_type == SADB_EXT_ADDRESS_PROXY ||
- ext_type == SADB_X_EXT_NAT_T_OA) {
+ switch (ext_type) {
+ case SADB_EXT_ADDRESS_SRC:
+ case SADB_EXT_ADDRESS_DST:
+ case SADB_EXT_ADDRESS_PROXY:
+ case SADB_X_EXT_NAT_T_OA:
if (verify_address_len(p))
return -EINVAL;
- }
- if (ext_type == SADB_X_EXT_SEC_CTX) {
+ break;
+ case SADB_X_EXT_SEC_CTX:
if (verify_sec_ctx_len(p))
return -EINVAL;
+ break;
+ case SADB_EXT_KEY_AUTH:
+ case SADB_EXT_KEY_ENCRYPT:
+ if (verify_key_len(p))
+ return -EINVAL;
+ break;
+ default:
+ break;
}
ext_hdrs[ext_type-1] = (void *) p;
}
@@ -1104,14 +1131,12 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net,
key = ext_hdrs[SADB_EXT_KEY_AUTH - 1];
if (key != NULL &&
sa->sadb_sa_auth != SADB_X_AALG_NULL &&
- ((key->sadb_key_bits+7) / 8 == 0 ||
- (key->sadb_key_bits+7) / 8 > key->sadb_key_len * sizeof(uint64_t)))
+ key->sadb_key_bits == 0)
return ERR_PTR(-EINVAL);
key = ext_hdrs[SADB_EXT_KEY_ENCRYPT-1];
if (key != NULL &&
sa->sadb_sa_encrypt != SADB_EALG_NULL &&
- ((key->sadb_key_bits+7) / 8 == 0 ||
- (key->sadb_key_bits+7) / 8 > key->sadb_key_len * sizeof(uint64_t)))
+ key->sadb_key_bits == 0)
return ERR_PTR(-EINVAL);
x = xfrm_state_alloc(net);
@@ -3726,7 +3751,7 @@ static const struct proto_ops pfkey_ops = {
/* Now the operations that really occur. */
.release = pfkey_release,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.sendmsg = pfkey_sendmsg,
.recvmsg = pfkey_recvmsg,
};
@@ -3787,24 +3812,12 @@ static const struct seq_operations pfkey_seq_ops = {
.show = pfkey_seq_show,
};
-static int pfkey_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &pfkey_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-static const struct file_operations pfkey_proc_ops = {
- .open = pfkey_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static int __net_init pfkey_init_proc(struct net *net)
{
struct proc_dir_entry *e;
- e = proc_create("pfkey", 0, net->proc_net, &pfkey_proc_ops);
+ e = proc_create_net("pfkey", 0, net->proc_net, &pfkey_seq_ops,
+ sizeof(struct seq_net_private));
if (e == NULL)
return -ENOMEM;
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 0fbd3ee..40261cb 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -183,6 +183,26 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id)
}
EXPORT_SYMBOL_GPL(l2tp_tunnel_get);
+struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth)
+{
+ const struct l2tp_net *pn = l2tp_pernet(net);
+ struct l2tp_tunnel *tunnel;
+ int count = 0;
+
+ rcu_read_lock_bh();
+ list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
+ if (++count > nth) {
+ l2tp_tunnel_inc_refcount(tunnel);
+ rcu_read_unlock_bh();
+ return tunnel;
+ }
+ }
+ rcu_read_unlock_bh();
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_get_nth);
+
/* Lookup a session. A new reference is held on the returned session. */
struct l2tp_session *l2tp_session_get(const struct net *net,
struct l2tp_tunnel *tunnel,
@@ -335,26 +355,6 @@ int l2tp_session_register(struct l2tp_session *session,
}
EXPORT_SYMBOL_GPL(l2tp_session_register);
-struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth)
-{
- struct l2tp_net *pn = l2tp_pernet(net);
- struct l2tp_tunnel *tunnel;
- int count = 0;
-
- rcu_read_lock_bh();
- list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- if (++count > nth) {
- rcu_read_unlock_bh();
- return tunnel;
- }
- }
-
- rcu_read_unlock_bh();
-
- return NULL;
-}
-EXPORT_SYMBOL_GPL(l2tp_tunnel_find_nth);
-
/*****************************************************************************
* Receive data handling
*****************************************************************************/
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index ba33cbe..c199020 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -212,6 +212,8 @@ static inline void *l2tp_session_priv(struct l2tp_session *session)
}
struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id);
+struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth);
+
void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
struct l2tp_session *l2tp_session_get(const struct net *net,
@@ -220,7 +222,6 @@ struct l2tp_session *l2tp_session_get(const struct net *net,
struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth);
struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
const char *ifname);
-struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth);
int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id,
u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg,
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index 72e713d..7f1e842 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -47,7 +47,11 @@ struct l2tp_dfs_seq_data {
static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd)
{
- pd->tunnel = l2tp_tunnel_find_nth(pd->net, pd->tunnel_idx);
+ /* Drop reference taken during previous invocation */
+ if (pd->tunnel)
+ l2tp_tunnel_dec_refcount(pd->tunnel);
+
+ pd->tunnel = l2tp_tunnel_get_nth(pd->net, pd->tunnel_idx);
pd->tunnel_idx++;
}
@@ -96,7 +100,17 @@ static void *l2tp_dfs_seq_next(struct seq_file *m, void *v, loff_t *pos)
static void l2tp_dfs_seq_stop(struct seq_file *p, void *v)
{
- /* nothing to do */
+ struct l2tp_dfs_seq_data *pd = v;
+
+ if (!pd || pd == SEQ_START_TOKEN)
+ return;
+
+ /* Drop reference taken by last invocation of l2tp_dfs_next_tunnel() */
+ if (pd->tunnel) {
+ l2tp_tunnel_dec_refcount(pd->tunnel);
+ pd->tunnel = NULL;
+ pd->session = NULL;
+ }
}
static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v)
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index a9c05b2..181073b 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -613,7 +613,7 @@ static const struct proto_ops l2tp_ip_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = l2tp_ip_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = inet_ioctl,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 9573691..336e4c0 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -754,7 +754,7 @@ static const struct proto_ops l2tp_ip6_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = l2tp_ip6_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = inet6_ioctl,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index b05dbd9..6616c9f 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -487,14 +487,17 @@ static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback
struct net *net = sock_net(skb->sk);
for (;;) {
- tunnel = l2tp_tunnel_find_nth(net, ti);
+ tunnel = l2tp_tunnel_get_nth(net, ti);
if (tunnel == NULL)
goto out;
if (l2tp_nl_tunnel_send(skb, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
- tunnel, L2TP_CMD_TUNNEL_GET) < 0)
+ tunnel, L2TP_CMD_TUNNEL_GET) < 0) {
+ l2tp_tunnel_dec_refcount(tunnel);
goto out;
+ }
+ l2tp_tunnel_dec_refcount(tunnel);
ti++;
}
@@ -848,7 +851,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
for (;;) {
if (tunnel == NULL) {
- tunnel = l2tp_tunnel_find_nth(net, ti);
+ tunnel = l2tp_tunnel_get_nth(net, ti);
if (tunnel == NULL)
goto out;
}
@@ -856,6 +859,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
session = l2tp_session_get_nth(tunnel, si);
if (session == NULL) {
ti++;
+ l2tp_tunnel_dec_refcount(tunnel);
tunnel = NULL;
si = 0;
continue;
@@ -865,6 +869,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
cb->nlh->nlmsg_seq, NLM_F_MULTI,
session, L2TP_CMD_SESSION_GET) < 0) {
l2tp_session_dec_refcount(session);
+ l2tp_tunnel_dec_refcount(tunnel);
break;
}
l2tp_session_dec_refcount(session);
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 896bbca..3d8ca12 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -619,6 +619,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
lock_sock(sk);
error = -EINVAL;
+
+ if (sockaddr_len != sizeof(struct sockaddr_pppol2tp) &&
+ sockaddr_len != sizeof(struct sockaddr_pppol2tpv3) &&
+ sockaddr_len != sizeof(struct sockaddr_pppol2tpin6) &&
+ sockaddr_len != sizeof(struct sockaddr_pppol2tpv3in6))
+ goto end;
+
if (sp->sa_protocol != PX_PROTO_OL2TP)
goto end;
@@ -1551,16 +1558,19 @@ struct pppol2tp_seq_data {
static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd)
{
+ /* Drop reference taken during previous invocation */
+ if (pd->tunnel)
+ l2tp_tunnel_dec_refcount(pd->tunnel);
+
for (;;) {
- pd->tunnel = l2tp_tunnel_find_nth(net, pd->tunnel_idx);
+ pd->tunnel = l2tp_tunnel_get_nth(net, pd->tunnel_idx);
pd->tunnel_idx++;
- if (pd->tunnel == NULL)
- break;
+ /* Only accept L2TPv2 tunnels */
+ if (!pd->tunnel || pd->tunnel->version == 2)
+ return;
- /* Ignore L2TPv3 tunnels */
- if (pd->tunnel->version < 3)
- break;
+ l2tp_tunnel_dec_refcount(pd->tunnel);
}
}
@@ -1609,7 +1619,17 @@ static void *pppol2tp_seq_next(struct seq_file *m, void *v, loff_t *pos)
static void pppol2tp_seq_stop(struct seq_file *p, void *v)
{
- /* nothing to do */
+ struct pppol2tp_seq_data *pd = v;
+
+ if (!pd || pd == SEQ_START_TOKEN)
+ return;
+
+ /* Drop reference taken by last invocation of pppol2tp_next_tunnel() */
+ if (pd->tunnel) {
+ l2tp_tunnel_dec_refcount(pd->tunnel);
+ pd->tunnel = NULL;
+ pd->session = NULL;
+ }
}
static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v)
@@ -1722,24 +1742,6 @@ static const struct seq_operations pppol2tp_seq_ops = {
.stop = pppol2tp_seq_stop,
.show = pppol2tp_seq_show,
};
-
-/* Called when our /proc file is opened. We allocate data for use when
- * iterating our tunnel / session contexts and store it in the private
- * data of the seq_file.
- */
-static int pppol2tp_proc_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &pppol2tp_seq_ops,
- sizeof(struct pppol2tp_seq_data));
-}
-
-static const struct file_operations pppol2tp_proc_fops = {
- .open = pppol2tp_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
#endif /* CONFIG_PROC_FS */
/*****************************************************************************
@@ -1751,8 +1753,8 @@ static __net_init int pppol2tp_init_net(struct net *net)
struct proc_dir_entry *pde;
int err = 0;
- pde = proc_create("pppol2tp", 0444, net->proc_net,
- &pppol2tp_proc_fops);
+ pde = proc_create_net("pppol2tp", 0444, net->proc_net,
+ &pppol2tp_seq_ops, sizeof(struct pppol2tp_seq_data));
if (!pde) {
err = -ENOMEM;
goto out;
@@ -1786,7 +1788,7 @@ static const struct proto_ops pppol2tp_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = pppol2tp_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = pppol2tp_setsockopt,
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 01dcc08..804de84 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -199,9 +199,19 @@ static int llc_ui_release(struct socket *sock)
llc->laddr.lsap, llc->daddr.lsap);
if (!llc_send_disc(sk))
llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo);
- if (!sock_flag(sk, SOCK_ZAPPED))
+ if (!sock_flag(sk, SOCK_ZAPPED)) {
+ struct llc_sap *sap = llc->sap;
+
+ /* Hold this for release_sock(), so that llc_backlog_rcv()
+ * could still use it.
+ */
+ llc_sap_hold(sap);
llc_sap_remove_socket(llc->sap, sk);
- release_sock(sk);
+ release_sock(sk);
+ llc_sap_put(sap);
+ } else {
+ release_sock(sk);
+ }
if (llc->dev)
dev_put(llc->dev);
sock_put(sk);
@@ -920,6 +930,9 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
if (size > llc->dev->mtu)
size = llc->dev->mtu;
copied = size - hdrlen;
+ rc = -EINVAL;
+ if (copied < 0)
+ goto release;
release_sock(sk);
skb = sock_alloc_send_skb(sk, size, noblock, &rc);
lock_sock(sk);
@@ -1179,7 +1192,7 @@ static const struct proto_ops llc_ui_ops = {
.socketpair = sock_no_socketpair,
.accept = llc_ui_accept,
.getname = llc_ui_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = llc_ui_ioctl,
.listen = llc_ui_listen,
.shutdown = llc_ui_shutdown,
diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c
index 1631211..4d78375 100644
--- a/net/llc/llc_c_ac.c
+++ b/net/llc/llc_c_ac.c
@@ -1099,14 +1099,7 @@ int llc_conn_ac_inc_tx_win_size(struct sock *sk, struct sk_buff *skb)
int llc_conn_ac_stop_all_timers(struct sock *sk, struct sk_buff *skb)
{
- struct llc_sock *llc = llc_sk(sk);
-
- del_timer(&llc->pf_cycle_timer.timer);
- del_timer(&llc->ack_timer.timer);
- del_timer(&llc->rej_sent_timer.timer);
- del_timer(&llc->busy_state_timer.timer);
- llc->ack_must_be_send = 0;
- llc->ack_pf = 0;
+ llc_sk_stop_all_timers(sk, false);
return 0;
}
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 110e32b..c0ac522 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -961,6 +961,26 @@ struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority, struct pr
return sk;
}
+void llc_sk_stop_all_timers(struct sock *sk, bool sync)
+{
+ struct llc_sock *llc = llc_sk(sk);
+
+ if (sync) {
+ del_timer_sync(&llc->pf_cycle_timer.timer);
+ del_timer_sync(&llc->ack_timer.timer);
+ del_timer_sync(&llc->rej_sent_timer.timer);
+ del_timer_sync(&llc->busy_state_timer.timer);
+ } else {
+ del_timer(&llc->pf_cycle_timer.timer);
+ del_timer(&llc->ack_timer.timer);
+ del_timer(&llc->rej_sent_timer.timer);
+ del_timer(&llc->busy_state_timer.timer);
+ }
+
+ llc->ack_must_be_send = 0;
+ llc->ack_pf = 0;
+}
+
/**
* llc_sk_free - Frees a LLC socket
* @sk - socket to free
@@ -973,7 +993,7 @@ void llc_sk_free(struct sock *sk)
llc->state = LLC_CONN_OUT_OF_SVC;
/* Stop all (possibly) running timers */
- llc_conn_ac_stop_all_timers(sk, NULL);
+ llc_sk_stop_all_timers(sk, true);
#ifdef DEBUG_LLC_CONN_ALLOC
printk(KERN_INFO "%s: unackq=%d, txq=%d\n", __func__,
skb_queue_len(&llc->pdu_unack_q),
diff --git a/net/llc/llc_proc.c b/net/llc/llc_proc.c
index 62ea0ae..f3a36c1 100644
--- a/net/llc/llc_proc.c
+++ b/net/llc/llc_proc.c
@@ -214,30 +214,6 @@ static const struct seq_operations llc_seq_core_ops = {
.show = llc_seq_core_show,
};
-static int llc_seq_socket_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &llc_seq_socket_ops);
-}
-
-static int llc_seq_core_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &llc_seq_core_ops);
-}
-
-static const struct file_operations llc_seq_socket_fops = {
- .open = llc_seq_socket_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-static const struct file_operations llc_seq_core_fops = {
- .open = llc_seq_core_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static struct proc_dir_entry *llc_proc_dir;
int __init llc_proc_init(void)
@@ -249,11 +225,11 @@ int __init llc_proc_init(void)
if (!llc_proc_dir)
goto out;
- p = proc_create("socket", 0444, llc_proc_dir, &llc_seq_socket_fops);
+ p = proc_create_seq("socket", 0444, llc_proc_dir, &llc_seq_socket_ops);
if (!p)
goto out_socket;
- p = proc_create("core", 0444, llc_proc_dir, &llc_seq_core_fops);
+ p = proc_create_seq("core", 0444, llc_proc_dir, &llc_seq_core_ops);
if (!p)
goto out_core;
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 595c662..ac42952 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -8,6 +8,7 @@
* Copyright 2007, Michael Wu <flamingice@sourmilk.net>
* Copyright 2007-2010, Intel Corporation
* Copyright(c) 2015-2017 Intel Deutschland GmbH
+ * Copyright (C) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -970,6 +971,9 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local,
sta->ampdu_mlme.addba_req_num[tid] = 0;
+ tid_tx->timeout =
+ le16_to_cpu(mgmt->u.action.u.addba_resp.timeout);
+
if (tid_tx->timeout) {
mod_timer(&tid_tx->session_timer,
TU_TO_EXP_TIME(tid_tx->timeout));
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index 0f6c9ca..5b5b0f9 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -401,7 +401,7 @@ u32 mesh_plink_deactivate(struct sta_info *sta)
static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata,
struct sta_info *sta,
- struct ieee802_11_elems *elems, bool insert)
+ struct ieee802_11_elems *elems)
{
struct ieee80211_local *local = sdata->local;
struct ieee80211_supported_band *sband;
@@ -447,7 +447,7 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata,
sta->sta.bandwidth = IEEE80211_STA_RX_BW_20;
}
- if (insert)
+ if (!test_sta_flag(sta, WLAN_STA_RATE_CONTROL))
rate_control_rate_init(sta);
else
rate_control_rate_update(local, sband, sta, changed);
@@ -551,7 +551,7 @@ mesh_sta_info_get(struct ieee80211_sub_if_data *sdata,
rcu_read_lock();
sta = sta_info_get(sdata, addr);
if (sta) {
- mesh_sta_info_init(sdata, sta, elems, false);
+ mesh_sta_info_init(sdata, sta, elems);
} else {
rcu_read_unlock();
/* can't run atomic */
@@ -561,7 +561,7 @@ mesh_sta_info_get(struct ieee80211_sub_if_data *sdata,
return NULL;
}
- mesh_sta_info_init(sdata, sta, elems, true);
+ mesh_sta_info_init(sdata, sta, elems);
if (sta_info_insert_rcu(sta))
return NULL;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 69449db..2330687 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -36,6 +36,7 @@
#define IEEE80211_AUTH_TIMEOUT (HZ / 5)
#define IEEE80211_AUTH_TIMEOUT_LONG (HZ / 2)
#define IEEE80211_AUTH_TIMEOUT_SHORT (HZ / 10)
+#define IEEE80211_AUTH_TIMEOUT_SAE (HZ * 2)
#define IEEE80211_AUTH_MAX_TRIES 3
#define IEEE80211_AUTH_WAIT_ASSOC (HZ * 5)
#define IEEE80211_ASSOC_TIMEOUT (HZ / 5)
@@ -1787,7 +1788,7 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local,
params[ac].acm = acm;
params[ac].uapsd = uapsd;
- if (params->cw_min == 0 ||
+ if (params[ac].cw_min == 0 ||
params[ac].cw_min > params[ac].cw_max) {
sdata_info(sdata,
"AP has invalid WMM params (CWmin/max=%d/%d for ACI %d), using defaults\n",
@@ -3814,16 +3815,19 @@ static int ieee80211_auth(struct ieee80211_sub_if_data *sdata)
tx_flags);
if (tx_flags == 0) {
- auth_data->timeout = jiffies + IEEE80211_AUTH_TIMEOUT;
- auth_data->timeout_started = true;
- run_again(sdata, auth_data->timeout);
+ if (auth_data->algorithm == WLAN_AUTH_SAE)
+ auth_data->timeout = jiffies +
+ IEEE80211_AUTH_TIMEOUT_SAE;
+ else
+ auth_data->timeout = jiffies + IEEE80211_AUTH_TIMEOUT;
} else {
auth_data->timeout =
round_jiffies_up(jiffies + IEEE80211_AUTH_TIMEOUT_LONG);
- auth_data->timeout_started = true;
- run_again(sdata, auth_data->timeout);
}
+ auth_data->timeout_started = true;
+ run_again(sdata, auth_data->timeout);
+
return 0;
}
@@ -3894,8 +3898,15 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata)
ifmgd->status_received = false;
if (ifmgd->auth_data && ieee80211_is_auth(fc)) {
if (status_acked) {
- ifmgd->auth_data->timeout =
- jiffies + IEEE80211_AUTH_TIMEOUT_SHORT;
+ if (ifmgd->auth_data->algorithm ==
+ WLAN_AUTH_SAE)
+ ifmgd->auth_data->timeout =
+ jiffies +
+ IEEE80211_AUTH_TIMEOUT_SAE;
+ else
+ ifmgd->auth_data->timeout =
+ jiffies +
+ IEEE80211_AUTH_TIMEOUT_SHORT;
run_again(sdata, ifmgd->auth_data->timeout);
} else {
ifmgd->auth_data->timeout = jiffies - 1;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 535de31..05a265c 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -4,6 +4,7 @@
* Copyright 2006-2007 Jiri Benc <jbenc@suse.cz>
* Copyright 2007 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
+ * Copyright (C) 2018 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -1135,7 +1136,7 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx,
}
/* reset session timer */
- if (reset_agg_timer && tid_tx->timeout)
+ if (reset_agg_timer)
tid_tx->last_tx = jiffies;
return queued;
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index 8d7e849..41cede4 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -215,7 +215,7 @@ static int ncsi_pkg_info_nl(struct sk_buff *msg, struct genl_info *info)
static int ncsi_pkg_info_all_nl(struct sk_buff *skb,
struct netlink_callback *cb)
{
- struct nlattr *attrs[NCSI_ATTR_MAX];
+ struct nlattr *attrs[NCSI_ATTR_MAX + 1];
struct ncsi_package *np, *package;
struct ncsi_dev_priv *ndp;
unsigned int package_id;
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 704b383..44d8a55 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -594,6 +594,7 @@
config NFT_REJECT
default m if NETFILTER_ADVANCED=n
tristate "Netfilter nf_tables reject support"
+ depends on !NF_TABLES_INET || (IPV6!=m || m)
help
This option adds the "reject" expression that you can use to
explicitly deny and notify via TCP reset/ICMP informational errors
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 0f6b817..206fb2c 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -585,7 +585,8 @@ void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *);
EXPORT_SYMBOL(nf_nat_decode_session_hook);
#endif
-static void __net_init __netfilter_net_init(struct nf_hook_entries **e, int max)
+static void __net_init
+__netfilter_net_init(struct nf_hook_entries __rcu **e, int max)
{
int h;
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 1c98c90..c3db074 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -587,25 +587,13 @@ static const struct seq_operations ip_vs_app_seq_ops = {
.stop = ip_vs_app_seq_stop,
.show = ip_vs_app_seq_show,
};
-
-static int ip_vs_app_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &ip_vs_app_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-static const struct file_operations ip_vs_app_fops = {
- .open = ip_vs_app_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
#endif
int __net_init ip_vs_app_net_init(struct netns_ipvs *ipvs)
{
INIT_LIST_HEAD(&ipvs->app_list);
- proc_create("ip_vs_app", 0, ipvs->net->proc_net, &ip_vs_app_fops);
+ proc_create_net("ip_vs_app", 0, ipvs->net->proc_net, &ip_vs_app_seq_ops,
+ sizeof(struct seq_net_private));
return 0;
}
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 370abbf..61c3a38 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -232,7 +232,10 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp)
static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp)
{
unsigned int hash;
- bool ret;
+ bool ret = false;
+
+ if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
+ return refcount_dec_if_one(&cp->refcnt);
hash = ip_vs_conn_hashkey_conn(cp);
@@ -240,15 +243,13 @@ static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp)
spin_lock(&cp->lock);
if (cp->flags & IP_VS_CONN_F_HASHED) {
- ret = false;
/* Decrease refcnt and unlink conn only if we are last user */
if (refcount_dec_if_one(&cp->refcnt)) {
hlist_del_rcu(&cp->c_list);
cp->flags &= ~IP_VS_CONN_F_HASHED;
ret = true;
}
- } else
- ret = refcount_read(&cp->refcnt) ? false : true;
+ }
spin_unlock(&cp->lock);
ct_write_unlock_bh(hash);
@@ -454,12 +455,6 @@ ip_vs_conn_out_get_proto(struct netns_ipvs *ipvs, int af,
}
EXPORT_SYMBOL_GPL(ip_vs_conn_out_get_proto);
-static void __ip_vs_conn_put_notimer(struct ip_vs_conn *cp)
-{
- __ip_vs_conn_put(cp);
- ip_vs_conn_expire(&cp->timer);
-}
-
/*
* Put back the conn and restart its timer with its timeout
*/
@@ -478,7 +473,7 @@ void ip_vs_conn_put(struct ip_vs_conn *cp)
(refcount_read(&cp->refcnt) == 1) &&
!timer_pending(&cp->timer))
/* expire connection immediately */
- __ip_vs_conn_put_notimer(cp);
+ ip_vs_conn_expire(&cp->timer);
else
__ip_vs_conn_put_timer(cp);
}
@@ -1136,19 +1131,6 @@ static const struct seq_operations ip_vs_conn_seq_ops = {
.show = ip_vs_conn_seq_show,
};
-static int ip_vs_conn_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &ip_vs_conn_seq_ops,
- sizeof(struct ip_vs_iter_state));
-}
-
-static const struct file_operations ip_vs_conn_fops = {
- .open = ip_vs_conn_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static const char *ip_vs_origin_name(unsigned int flags)
{
if (flags & IP_VS_CONN_F_SYNC)
@@ -1212,20 +1194,6 @@ static const struct seq_operations ip_vs_conn_sync_seq_ops = {
.stop = ip_vs_conn_seq_stop,
.show = ip_vs_conn_sync_seq_show,
};
-
-static int ip_vs_conn_sync_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &ip_vs_conn_sync_seq_ops,
- sizeof(struct ip_vs_iter_state));
-}
-
-static const struct file_operations ip_vs_conn_sync_fops = {
- .open = ip_vs_conn_sync_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
#endif
@@ -1385,9 +1353,11 @@ int __net_init ip_vs_conn_net_init(struct netns_ipvs *ipvs)
{
atomic_set(&ipvs->conn_count, 0);
- proc_create("ip_vs_conn", 0, ipvs->net->proc_net, &ip_vs_conn_fops);
- proc_create("ip_vs_conn_sync", 0, ipvs->net->proc_net,
- &ip_vs_conn_sync_fops);
+ proc_create_net("ip_vs_conn", 0, ipvs->net->proc_net,
+ &ip_vs_conn_seq_ops, sizeof(struct ip_vs_iter_state));
+ proc_create_net("ip_vs_conn_sync", 0, ipvs->net->proc_net,
+ &ip_vs_conn_sync_seq_ops,
+ sizeof(struct ip_vs_iter_state));
return 0;
}
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 5f6f73c..0679dd1 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -119,6 +119,8 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
struct ip_vs_cpu_stats *s;
struct ip_vs_service *svc;
+ local_bh_disable();
+
s = this_cpu_ptr(dest->stats.cpustats);
u64_stats_update_begin(&s->syncp);
s->cnt.inpkts++;
@@ -137,6 +139,8 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
s->cnt.inpkts++;
s->cnt.inbytes += skb->len;
u64_stats_update_end(&s->syncp);
+
+ local_bh_enable();
}
}
@@ -151,6 +155,8 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
struct ip_vs_cpu_stats *s;
struct ip_vs_service *svc;
+ local_bh_disable();
+
s = this_cpu_ptr(dest->stats.cpustats);
u64_stats_update_begin(&s->syncp);
s->cnt.outpkts++;
@@ -169,6 +175,8 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
s->cnt.outpkts++;
s->cnt.outbytes += skb->len;
u64_stats_update_end(&s->syncp);
+
+ local_bh_enable();
}
}
@@ -179,6 +187,8 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
struct netns_ipvs *ipvs = svc->ipvs;
struct ip_vs_cpu_stats *s;
+ local_bh_disable();
+
s = this_cpu_ptr(cp->dest->stats.cpustats);
u64_stats_update_begin(&s->syncp);
s->cnt.conns++;
@@ -193,6 +203,8 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
u64_stats_update_begin(&s->syncp);
s->cnt.conns++;
u64_stats_update_end(&s->syncp);
+
+ local_bh_enable();
}
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 5ebde4b..141b150 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2109,19 +2109,6 @@ static const struct seq_operations ip_vs_info_seq_ops = {
.show = ip_vs_info_seq_show,
};
-static int ip_vs_info_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &ip_vs_info_seq_ops,
- sizeof(struct ip_vs_iter));
-}
-
-static const struct file_operations ip_vs_info_fops = {
- .open = ip_vs_info_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static int ip_vs_stats_show(struct seq_file *seq, void *v)
{
struct net *net = seq_file_single_net(seq);
@@ -2154,18 +2141,6 @@ static int ip_vs_stats_show(struct seq_file *seq, void *v)
return 0;
}
-static int ip_vs_stats_seq_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, ip_vs_stats_show);
-}
-
-static const struct file_operations ip_vs_stats_fops = {
- .open = ip_vs_stats_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release_net,
-};
-
static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
{
struct net *net = seq_file_single_net(seq);
@@ -2221,18 +2196,6 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
return 0;
}
-
-static int ip_vs_stats_percpu_seq_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, ip_vs_stats_percpu_show);
-}
-
-static const struct file_operations ip_vs_stats_percpu_fops = {
- .open = ip_vs_stats_percpu_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release_net,
-};
#endif
/*
@@ -2381,14 +2344,12 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
struct ipvs_sync_daemon_cfg cfg;
memset(&cfg, 0, sizeof(cfg));
- strlcpy(cfg.mcast_ifn, dm->mcast_ifn,
- sizeof(cfg.mcast_ifn));
+ ret = -EINVAL;
+ if (strscpy(cfg.mcast_ifn, dm->mcast_ifn,
+ sizeof(cfg.mcast_ifn)) <= 0)
+ goto out_dec;
cfg.syncid = dm->syncid;
- rtnl_lock();
- mutex_lock(&ipvs->sync_mutex);
ret = start_sync_thread(ipvs, &cfg, dm->state);
- mutex_unlock(&ipvs->sync_mutex);
- rtnl_unlock();
} else {
mutex_lock(&ipvs->sync_mutex);
ret = stop_sync_thread(ipvs, dm->state);
@@ -2424,12 +2385,19 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
}
}
+ if ((cmd == IP_VS_SO_SET_ADD || cmd == IP_VS_SO_SET_EDIT) &&
+ strnlen(usvc.sched_name, IP_VS_SCHEDNAME_MAXLEN) ==
+ IP_VS_SCHEDNAME_MAXLEN) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
/* Check for valid protocol: TCP or UDP or SCTP, even for fwmark!=0 */
if (usvc.protocol != IPPROTO_TCP && usvc.protocol != IPPROTO_UDP &&
usvc.protocol != IPPROTO_SCTP) {
- pr_err("set_ctl: invalid protocol: %d %pI4:%d %s\n",
+ pr_err("set_ctl: invalid protocol: %d %pI4:%d\n",
usvc.protocol, &usvc.addr.ip,
- ntohs(usvc.port), usvc.sched_name);
+ ntohs(usvc.port));
ret = -EFAULT;
goto out_unlock;
}
@@ -2851,7 +2819,7 @@ static const struct nla_policy ip_vs_cmd_policy[IPVS_CMD_ATTR_MAX + 1] = {
static const struct nla_policy ip_vs_daemon_policy[IPVS_DAEMON_ATTR_MAX + 1] = {
[IPVS_DAEMON_ATTR_STATE] = { .type = NLA_U32 },
[IPVS_DAEMON_ATTR_MCAST_IFN] = { .type = NLA_NUL_STRING,
- .len = IP_VS_IFNAME_MAXLEN },
+ .len = IP_VS_IFNAME_MAXLEN - 1 },
[IPVS_DAEMON_ATTR_SYNC_ID] = { .type = NLA_U32 },
[IPVS_DAEMON_ATTR_SYNC_MAXLEN] = { .type = NLA_U16 },
[IPVS_DAEMON_ATTR_MCAST_GROUP] = { .type = NLA_U32 },
@@ -2869,7 +2837,7 @@ static const struct nla_policy ip_vs_svc_policy[IPVS_SVC_ATTR_MAX + 1] = {
[IPVS_SVC_ATTR_PORT] = { .type = NLA_U16 },
[IPVS_SVC_ATTR_FWMARK] = { .type = NLA_U32 },
[IPVS_SVC_ATTR_SCHED_NAME] = { .type = NLA_NUL_STRING,
- .len = IP_VS_SCHEDNAME_MAXLEN },
+ .len = IP_VS_SCHEDNAME_MAXLEN - 1 },
[IPVS_SVC_ATTR_PE_NAME] = { .type = NLA_NUL_STRING,
.len = IP_VS_PENAME_MAXLEN },
[IPVS_SVC_ATTR_FLAGS] = { .type = NLA_BINARY,
@@ -3481,12 +3449,8 @@ static int ip_vs_genl_new_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs)
if (ipvs->mixed_address_family_dests > 0)
return -EINVAL;
- rtnl_lock();
- mutex_lock(&ipvs->sync_mutex);
ret = start_sync_thread(ipvs, &c,
nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
- mutex_unlock(&ipvs->sync_mutex);
- rtnl_unlock();
return ret;
}
@@ -4038,10 +4002,12 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs)
spin_lock_init(&ipvs->tot_stats.lock);
- proc_create("ip_vs", 0, ipvs->net->proc_net, &ip_vs_info_fops);
- proc_create("ip_vs_stats", 0, ipvs->net->proc_net, &ip_vs_stats_fops);
- proc_create("ip_vs_stats_percpu", 0, ipvs->net->proc_net,
- &ip_vs_stats_percpu_fops);
+ proc_create_net("ip_vs", 0, ipvs->net->proc_net, &ip_vs_info_seq_ops,
+ sizeof(struct ip_vs_iter));
+ proc_create_net_single("ip_vs_stats", 0, ipvs->net->proc_net,
+ ip_vs_stats_show, NULL);
+ proc_create_net_single("ip_vs_stats_percpu", 0, ipvs->net->proc_net,
+ ip_vs_stats_percpu_show, NULL);
if (ip_vs_control_net_init_sysctl(ipvs))
goto err;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index fbaf3bd..001501e 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -49,6 +49,7 @@
#include <linux/kthread.h>
#include <linux/wait.h>
#include <linux/kernel.h>
+#include <linux/sched/signal.h>
#include <asm/unaligned.h> /* Used for ntoh_seq and hton_seq */
@@ -1360,15 +1361,9 @@ static void set_mcast_pmtudisc(struct sock *sk, int val)
/*
* Specifiy default interface for outgoing multicasts
*/
-static int set_mcast_if(struct sock *sk, char *ifname)
+static int set_mcast_if(struct sock *sk, struct net_device *dev)
{
- struct net_device *dev;
struct inet_sock *inet = inet_sk(sk);
- struct net *net = sock_net(sk);
-
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
@@ -1396,19 +1391,14 @@ static int set_mcast_if(struct sock *sk, char *ifname)
* in the in_addr structure passed in as a parameter.
*/
static int
-join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
+join_mcast_group(struct sock *sk, struct in_addr *addr, struct net_device *dev)
{
- struct net *net = sock_net(sk);
struct ip_mreqn mreq;
- struct net_device *dev;
int ret;
memset(&mreq, 0, sizeof(mreq));
memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr));
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
@@ -1423,15 +1413,10 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
#ifdef CONFIG_IP_VS_IPV6
static int join_mcast_group6(struct sock *sk, struct in6_addr *addr,
- char *ifname)
+ struct net_device *dev)
{
- struct net *net = sock_net(sk);
- struct net_device *dev;
int ret;
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
@@ -1443,24 +1428,18 @@ static int join_mcast_group6(struct sock *sk, struct in6_addr *addr,
}
#endif
-static int bind_mcastif_addr(struct socket *sock, char *ifname)
+static int bind_mcastif_addr(struct socket *sock, struct net_device *dev)
{
- struct net *net = sock_net(sock->sk);
- struct net_device *dev;
__be32 addr;
struct sockaddr_in sin;
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
-
addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
if (!addr)
pr_err("You probably need to specify IP address on "
"multicast interface.\n");
IP_VS_DBG(7, "binding socket with (%s) %pI4\n",
- ifname, &addr);
+ dev->name, &addr);
/* Now bind the socket with the address of multicast interface */
sin.sin_family = AF_INET;
@@ -1493,7 +1472,8 @@ static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen,
/*
* Set up sending multicast socket over UDP
*/
-static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
+static int make_send_sock(struct netns_ipvs *ipvs, int id,
+ struct net_device *dev, struct socket **sock_ret)
{
/* multicast addr */
union ipvs_sockaddr mcast_addr;
@@ -1505,9 +1485,10 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
- return ERR_PTR(result);
+ goto error;
}
- result = set_mcast_if(sock->sk, ipvs->mcfg.mcast_ifn);
+ *sock_ret = sock;
+ result = set_mcast_if(sock->sk, dev);
if (result < 0) {
pr_err("Error setting outbound mcast interface\n");
goto error;
@@ -1522,7 +1503,7 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
set_sock_size(sock->sk, 1, result);
if (AF_INET == ipvs->mcfg.mcast_af)
- result = bind_mcastif_addr(sock, ipvs->mcfg.mcast_ifn);
+ result = bind_mcastif_addr(sock, dev);
else
result = 0;
if (result < 0) {
@@ -1538,19 +1519,18 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
goto error;
}
- return sock;
+ return 0;
error:
- sock_release(sock);
- return ERR_PTR(result);
+ return result;
}
/*
* Set up receiving multicast socket over UDP
*/
-static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
- int ifindex)
+static int make_receive_sock(struct netns_ipvs *ipvs, int id,
+ struct net_device *dev, struct socket **sock_ret)
{
/* multicast addr */
union ipvs_sockaddr mcast_addr;
@@ -1562,8 +1542,9 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
- return ERR_PTR(result);
+ goto error;
}
+ *sock_ret = sock;
/* it is equivalent to the REUSEADDR option in user-space */
sock->sk->sk_reuse = SK_CAN_REUSE;
result = sysctl_sync_sock_size(ipvs);
@@ -1571,7 +1552,7 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
set_sock_size(sock->sk, 0, result);
get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id);
- sock->sk->sk_bound_dev_if = ifindex;
+ sock->sk->sk_bound_dev_if = dev->ifindex;
result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen);
if (result < 0) {
pr_err("Error binding to the multicast addr\n");
@@ -1582,21 +1563,20 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
#ifdef CONFIG_IP_VS_IPV6
if (ipvs->bcfg.mcast_af == AF_INET6)
result = join_mcast_group6(sock->sk, &mcast_addr.in6.sin6_addr,
- ipvs->bcfg.mcast_ifn);
+ dev);
else
#endif
result = join_mcast_group(sock->sk, &mcast_addr.in.sin_addr,
- ipvs->bcfg.mcast_ifn);
+ dev);
if (result < 0) {
pr_err("Error joining to the multicast group\n");
goto error;
}
- return sock;
+ return 0;
error:
- sock_release(sock);
- return ERR_PTR(result);
+ return result;
}
@@ -1778,13 +1758,12 @@ static int sync_thread_backup(void *data)
int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
int state)
{
- struct ip_vs_sync_thread_data *tinfo;
+ struct ip_vs_sync_thread_data *tinfo = NULL;
struct task_struct **array = NULL, *task;
- struct socket *sock;
struct net_device *dev;
char *name;
int (*threadfn)(void *data);
- int id, count, hlen;
+ int id = 0, count, hlen;
int result = -ENOMEM;
u16 mtu, min_mtu;
@@ -1792,6 +1771,18 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %zd bytes\n",
sizeof(struct ip_vs_sync_conn_v0));
+ /* Do not hold one mutex and then to block on another */
+ for (;;) {
+ rtnl_lock();
+ if (mutex_trylock(&ipvs->sync_mutex))
+ break;
+ rtnl_unlock();
+ mutex_lock(&ipvs->sync_mutex);
+ if (rtnl_trylock())
+ break;
+ mutex_unlock(&ipvs->sync_mutex);
+ }
+
if (!ipvs->sync_state) {
count = clamp(sysctl_sync_ports(ipvs), 1, IPVS_SYNC_PORTS_MAX);
ipvs->threads_mask = count - 1;
@@ -1810,7 +1801,8 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
dev = __dev_get_by_name(ipvs->net, c->mcast_ifn);
if (!dev) {
pr_err("Unknown mcast interface: %s\n", c->mcast_ifn);
- return -ENODEV;
+ result = -ENODEV;
+ goto out_early;
}
hlen = (AF_INET6 == c->mcast_af) ?
sizeof(struct ipv6hdr) + sizeof(struct udphdr) :
@@ -1827,26 +1819,30 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
c->sync_maxlen = mtu - hlen;
if (state == IP_VS_STATE_MASTER) {
+ result = -EEXIST;
if (ipvs->ms)
- return -EEXIST;
+ goto out_early;
ipvs->mcfg = *c;
name = "ipvs-m:%d:%d";
threadfn = sync_thread_master;
} else if (state == IP_VS_STATE_BACKUP) {
+ result = -EEXIST;
if (ipvs->backup_threads)
- return -EEXIST;
+ goto out_early;
ipvs->bcfg = *c;
name = "ipvs-b:%d:%d";
threadfn = sync_thread_backup;
} else {
- return -EINVAL;
+ result = -EINVAL;
+ goto out_early;
}
if (state == IP_VS_STATE_MASTER) {
struct ipvs_master_sync_state *ms;
+ result = -ENOMEM;
ipvs->ms = kcalloc(count, sizeof(ipvs->ms[0]), GFP_KERNEL);
if (!ipvs->ms)
goto out;
@@ -1862,39 +1858,38 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
} else {
array = kcalloc(count, sizeof(struct task_struct *),
GFP_KERNEL);
+ result = -ENOMEM;
if (!array)
goto out;
}
- tinfo = NULL;
for (id = 0; id < count; id++) {
- if (state == IP_VS_STATE_MASTER)
- sock = make_send_sock(ipvs, id);
- else
- sock = make_receive_sock(ipvs, id, dev->ifindex);
- if (IS_ERR(sock)) {
- result = PTR_ERR(sock);
- goto outtinfo;
- }
+ result = -ENOMEM;
tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
if (!tinfo)
- goto outsocket;
+ goto out;
tinfo->ipvs = ipvs;
- tinfo->sock = sock;
+ tinfo->sock = NULL;
if (state == IP_VS_STATE_BACKUP) {
tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen,
GFP_KERNEL);
if (!tinfo->buf)
- goto outtinfo;
+ goto out;
} else {
tinfo->buf = NULL;
}
tinfo->id = id;
+ if (state == IP_VS_STATE_MASTER)
+ result = make_send_sock(ipvs, id, dev, &tinfo->sock);
+ else
+ result = make_receive_sock(ipvs, id, dev, &tinfo->sock);
+ if (result < 0)
+ goto out;
task = kthread_run(threadfn, tinfo, name, ipvs->gen, id);
if (IS_ERR(task)) {
result = PTR_ERR(task);
- goto outtinfo;
+ goto out;
}
tinfo = NULL;
if (state == IP_VS_STATE_MASTER)
@@ -1911,20 +1906,20 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
ipvs->sync_state |= state;
spin_unlock_bh(&ipvs->sync_buff_lock);
+ mutex_unlock(&ipvs->sync_mutex);
+ rtnl_unlock();
+
/* increase the module use count */
ip_vs_use_count_inc();
return 0;
-outsocket:
- sock_release(sock);
-
-outtinfo:
- if (tinfo) {
- sock_release(tinfo->sock);
- kfree(tinfo->buf);
- kfree(tinfo);
- }
+out:
+ /* We do not need RTNL lock anymore, release it here so that
+ * sock_release below and in the kthreads can use rtnl_lock
+ * to leave the mcast group.
+ */
+ rtnl_unlock();
count = id;
while (count-- > 0) {
if (state == IP_VS_STATE_MASTER)
@@ -1932,13 +1927,23 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
else
kthread_stop(array[count]);
}
- kfree(array);
-
-out:
if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
kfree(ipvs->ms);
ipvs->ms = NULL;
}
+ mutex_unlock(&ipvs->sync_mutex);
+ if (tinfo) {
+ if (tinfo->sock)
+ sock_release(tinfo->sock);
+ kfree(tinfo->buf);
+ kfree(tinfo);
+ }
+ kfree(array);
+ return result;
+
+out_early:
+ mutex_unlock(&ipvs->sync_mutex);
+ rtnl_unlock();
return result;
}
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 8ef21d9..853b232 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -252,7 +252,7 @@ static inline int expect_clash(const struct nf_conntrack_expect *a,
static inline int expect_matches(const struct nf_conntrack_expect *a,
const struct nf_conntrack_expect *b)
{
- return a->master == b->master && a->class == b->class &&
+ return a->master == b->master &&
nf_ct_tuple_equal(&a->tuple, &b->tuple) &&
nf_ct_tuple_mask_equal(&a->mask, &b->mask) &&
net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) &&
@@ -421,6 +421,9 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
h = nf_ct_expect_dst_hash(net, &expect->tuple);
hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) {
if (expect_matches(i, expect)) {
+ if (i->class != expect->class)
+ return -EALREADY;
+
if (nf_ct_remove_expect(i))
break;
} else if (expect_clash(i, expect)) {
@@ -641,19 +644,6 @@ static const struct seq_operations exp_seq_ops = {
.stop = exp_seq_stop,
.show = exp_seq_show
};
-
-static int exp_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &exp_seq_ops,
- sizeof(struct ct_expect_iter_state));
-}
-
-static const struct file_operations exp_file_ops = {
- .open = exp_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
#endif /* CONFIG_NF_CONNTRACK_PROCFS */
static int exp_proc_init(struct net *net)
@@ -663,8 +653,8 @@ static int exp_proc_init(struct net *net)
kuid_t root_uid;
kgid_t root_gid;
- proc = proc_create("nf_conntrack_expect", 0440, net->proc_net,
- &exp_file_ops);
+ proc = proc_create_net("nf_conntrack_expect", 0440, net->proc_net,
+ &exp_seq_ops, sizeof(struct ct_expect_iter_state));
if (!proc)
return -ENOMEM;
diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index 9fe0ddc..277bbfe 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -9,6 +9,7 @@
* 2 of the License, or (at your option) any later version.
*/
#include <linux/kernel.h>
+#include <linux/kmemleak.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/rcupdate.h>
@@ -71,6 +72,7 @@ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
rcu_read_unlock();
alloc = max(newlen, NF_CT_EXT_PREALLOC);
+ kmemleak_not_leak(old);
new = __krealloc(old, alloc, gfp);
if (!new)
return NULL;
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index e97cdc1..8e67910 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -981,6 +981,17 @@ static int tcp_packet(struct nf_conn *ct,
return NF_ACCEPT; /* Don't change state */
}
break;
+ case TCP_CONNTRACK_SYN_SENT2:
+ /* tcp_conntracks table is not smart enough to handle
+ * simultaneous open.
+ */
+ ct->proto.tcp.last_flags |= IP_CT_TCP_SIMULTANEOUS_OPEN;
+ break;
+ case TCP_CONNTRACK_SYN_RECV:
+ if (dir == IP_CT_DIR_REPLY && index == TCP_ACK_SET &&
+ ct->proto.tcp.last_flags & IP_CT_TCP_SIMULTANEOUS_OPEN)
+ new_state = TCP_CONNTRACK_ESTABLISHED;
+ break;
case TCP_CONNTRACK_CLOSE:
if (index == TCP_RST_SET
&& (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET)
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 4dbb5ba..908e51e 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -938,11 +938,19 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
datalen, rtp_exp, rtcp_exp,
mediaoff, medialen, daddr);
else {
- if (nf_ct_expect_related(rtp_exp) == 0) {
- if (nf_ct_expect_related(rtcp_exp) != 0)
- nf_ct_unexpect_related(rtp_exp);
- else
+ /* -EALREADY handling works around end-points that send
+ * SDP messages with identical port but different media type,
+ * we pretend expectation was set up.
+ */
+ int errp = nf_ct_expect_related(rtp_exp);
+
+ if (errp == 0 || errp == -EALREADY) {
+ int errcp = nf_ct_expect_related(rtcp_exp);
+
+ if (errcp == 0 || errcp == -EALREADY)
ret = NF_ACCEPT;
+ else if (errp == 0)
+ nf_ct_unexpect_related(rtp_exp);
}
}
nf_ct_expect_put(rtcp_exp);
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 037fec5..b642c0b 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -375,19 +375,6 @@ static const struct seq_operations ct_seq_ops = {
.show = ct_seq_show
};
-static int ct_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &ct_seq_ops,
- sizeof(struct ct_iter_state));
-}
-
-static const struct file_operations ct_file_ops = {
- .open = ct_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static void *ct_cpu_seq_start(struct seq_file *seq, loff_t *pos)
{
struct net *net = seq_file_net(seq);
@@ -467,26 +454,14 @@ static const struct seq_operations ct_cpu_seq_ops = {
.show = ct_cpu_seq_show,
};
-static int ct_cpu_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &ct_cpu_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-static const struct file_operations ct_cpu_seq_fops = {
- .open = ct_cpu_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static int nf_conntrack_standalone_init_proc(struct net *net)
{
struct proc_dir_entry *pde;
kuid_t root_uid;
kgid_t root_gid;
- pde = proc_create("nf_conntrack", 0440, net->proc_net, &ct_file_ops);
+ pde = proc_create_net("nf_conntrack", 0440, net->proc_net, &ct_seq_ops,
+ sizeof(struct ct_iter_state));
if (!pde)
goto out_nf_conntrack;
@@ -495,8 +470,8 @@ static int nf_conntrack_standalone_init_proc(struct net *net)
if (uid_valid(root_uid) && gid_valid(root_gid))
proc_set_user(pde, root_uid, root_gid);
- pde = proc_create("nf_conntrack", 0444, net->proc_net_stat,
- &ct_cpu_seq_fops);
+ pde = proc_create_net("nf_conntrack", 0444, net->proc_net_stat,
+ &ct_cpu_seq_ops, sizeof(struct seq_net_private));
if (!pde)
goto out_stat_nf_conntrack;
return 0;
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 6d03578..4264570 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -394,21 +394,6 @@ static const struct seq_operations nflog_seq_ops = {
.stop = seq_stop,
.show = seq_show,
};
-
-static int nflog_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &nflog_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-static const struct file_operations nflog_file_ops = {
- .open = nflog_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
-
#endif /* PROC_FS */
#ifdef CONFIG_SYSCTL
@@ -549,8 +534,8 @@ static int __net_init nf_log_net_init(struct net *net)
int ret = -ENOMEM;
#ifdef CONFIG_PROC_FS
- if (!proc_create("nf_log", 0444,
- net->nf.proc_netfilter, &nflog_file_ops))
+ if (!proc_create_net("nf_log", 0444, net->nf.proc_netfilter,
+ &nflog_seq_ops, sizeof(struct seq_net_private)))
return ret;
#endif
ret = netfilter_log_sysctl_init(net);
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 6039b35..8ff4d22 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -310,23 +310,10 @@ static const struct seq_operations synproxy_cpu_seq_ops = {
.show = synproxy_cpu_seq_show,
};
-static int synproxy_cpu_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &synproxy_cpu_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-static const struct file_operations synproxy_cpu_seq_fops = {
- .open = synproxy_cpu_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static int __net_init synproxy_proc_init(struct net *net)
{
- if (!proc_create("synproxy", 0444, net->proc_net_stat,
- &synproxy_cpu_seq_fops))
+ if (!proc_create_net("synproxy", 0444, net->proc_net_stat,
+ &synproxy_cpu_seq_ops, sizeof(struct seq_net_private)))
return -ENOMEM;
return 0;
}
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 9134cc4..501e48a 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -214,6 +214,34 @@ static int nft_delchain(struct nft_ctx *ctx)
return err;
}
+static void nft_rule_expr_activate(const struct nft_ctx *ctx,
+ struct nft_rule *rule)
+{
+ struct nft_expr *expr;
+
+ expr = nft_expr_first(rule);
+ while (expr != nft_expr_last(rule) && expr->ops) {
+ if (expr->ops->activate)
+ expr->ops->activate(ctx, expr);
+
+ expr = nft_expr_next(expr);
+ }
+}
+
+static void nft_rule_expr_deactivate(const struct nft_ctx *ctx,
+ struct nft_rule *rule)
+{
+ struct nft_expr *expr;
+
+ expr = nft_expr_first(rule);
+ while (expr != nft_expr_last(rule) && expr->ops) {
+ if (expr->ops->deactivate)
+ expr->ops->deactivate(ctx, expr);
+
+ expr = nft_expr_next(expr);
+ }
+}
+
static int
nf_tables_delrule_deactivate(struct nft_ctx *ctx, struct nft_rule *rule)
{
@@ -259,6 +287,7 @@ static int nft_delrule(struct nft_ctx *ctx, struct nft_rule *rule)
nft_trans_destroy(trans);
return err;
}
+ nft_rule_expr_deactivate(ctx, rule);
return 0;
}
@@ -1269,8 +1298,10 @@ static void nft_chain_stats_replace(struct nft_base_chain *chain,
rcu_assign_pointer(chain->stats, newstats);
synchronize_rcu();
free_percpu(oldstats);
- } else
+ } else {
rcu_assign_pointer(chain->stats, newstats);
+ static_branch_inc(&nft_counters_enabled);
+ }
}
static void nf_tables_chain_destroy(struct nft_ctx *ctx)
@@ -2238,6 +2269,13 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
kfree(rule);
}
+static void nf_tables_rule_release(const struct nft_ctx *ctx,
+ struct nft_rule *rule)
+{
+ nft_rule_expr_deactivate(ctx, rule);
+ nf_tables_rule_destroy(ctx, rule);
+}
+
#define NFT_RULE_MAXEXPRS 128
static struct nft_expr_info *info;
@@ -2361,43 +2399,48 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
}
if (nlh->nlmsg_flags & NLM_F_REPLACE) {
- if (nft_is_active_next(net, old_rule)) {
- trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
- old_rule);
- if (trans == NULL) {
- err = -ENOMEM;
- goto err2;
- }
- nft_deactivate_next(net, old_rule);
- chain->use--;
- list_add_tail_rcu(&rule->list, &old_rule->list);
- } else {
+ if (!nft_is_active_next(net, old_rule)) {
err = -ENOENT;
goto err2;
}
- } else if (nlh->nlmsg_flags & NLM_F_APPEND)
- if (old_rule)
- list_add_rcu(&rule->list, &old_rule->list);
- else
- list_add_tail_rcu(&rule->list, &chain->rules);
- else {
- if (old_rule)
- list_add_tail_rcu(&rule->list, &old_rule->list);
- else
- list_add_rcu(&rule->list, &chain->rules);
- }
+ trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
+ old_rule);
+ if (trans == NULL) {
+ err = -ENOMEM;
+ goto err2;
+ }
+ nft_deactivate_next(net, old_rule);
+ chain->use--;
- if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
- err = -ENOMEM;
- goto err3;
+ if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
+ err = -ENOMEM;
+ goto err2;
+ }
+
+ list_add_tail_rcu(&rule->list, &old_rule->list);
+ } else {
+ if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
+ err = -ENOMEM;
+ goto err2;
+ }
+
+ if (nlh->nlmsg_flags & NLM_F_APPEND) {
+ if (old_rule)
+ list_add_rcu(&rule->list, &old_rule->list);
+ else
+ list_add_tail_rcu(&rule->list, &chain->rules);
+ } else {
+ if (old_rule)
+ list_add_tail_rcu(&rule->list, &old_rule->list);
+ else
+ list_add_rcu(&rule->list, &chain->rules);
+ }
}
chain->use++;
return 0;
-err3:
- list_del_rcu(&rule->list);
err2:
- nf_tables_rule_destroy(&ctx, rule);
+ nf_tables_rule_release(&ctx, rule);
err1:
for (i = 0; i < n; i++) {
if (info[i].ops != NULL)
@@ -3207,18 +3250,20 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
err = ops->init(set, &desc, nla);
if (err < 0)
- goto err2;
+ goto err3;
err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set);
if (err < 0)
- goto err3;
+ goto err4;
list_add_tail_rcu(&set->list, &table->sets);
table->use++;
return 0;
-err3:
+err4:
ops->destroy(set);
+err3:
+ kfree(set->name);
err2:
kvfree(set);
err1:
@@ -4037,8 +4082,10 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) ^
nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) ||
nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) ^
- nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF))
- return -EBUSY;
+ nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF)) {
+ err = -EBUSY;
+ goto err5;
+ }
if ((nft_set_ext_exists(ext, NFT_SET_EXT_DATA) &&
nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) &&
memcmp(nft_set_ext_data(ext),
@@ -4123,7 +4170,7 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk,
* NFT_GOTO verdicts. This function must be called on active data objects
* from the second phase of the commit protocol.
*/
-static void nft_data_hold(const struct nft_data *data, enum nft_data_types type)
+void nft_data_hold(const struct nft_data *data, enum nft_data_types type)
{
if (type == NFT_DATA_VERDICT) {
switch (data->verdict.code) {
@@ -4661,7 +4708,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
if (idx > s_idx)
memset(&cb->args[1], 0,
sizeof(cb->args) - sizeof(cb->args[0]));
- if (filter && filter->table[0] &&
+ if (filter && filter->table &&
strcmp(filter->table, table->name))
goto cont;
if (filter &&
@@ -5335,7 +5382,7 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb,
if (idx > s_idx)
memset(&cb->args[1], 0,
sizeof(cb->args) - sizeof(cb->args[0]));
- if (filter && filter->table[0] &&
+ if (filter && filter->table &&
strcmp(filter->table, table->name))
goto cont;
@@ -5738,7 +5785,7 @@ static void nft_chain_commit_update(struct nft_trans *trans)
struct nft_base_chain *basechain;
if (nft_trans_chain_name(trans))
- strcpy(trans->ctx.chain->name, nft_trans_chain_name(trans));
+ swap(trans->ctx.chain->name, nft_trans_chain_name(trans));
if (!nft_is_base_chain(trans->ctx.chain))
return;
@@ -5754,7 +5801,7 @@ static void nft_chain_commit_update(struct nft_trans *trans)
}
}
-static void nf_tables_commit_release(struct nft_trans *trans)
+static void nft_commit_release(struct nft_trans *trans)
{
switch (trans->msg_type) {
case NFT_MSG_DELTABLE:
@@ -5783,6 +5830,21 @@ static void nf_tables_commit_release(struct nft_trans *trans)
kfree(trans);
}
+static void nf_tables_commit_release(struct net *net)
+{
+ struct nft_trans *trans, *next;
+
+ if (list_empty(&net->nft.commit_list))
+ return;
+
+ synchronize_rcu();
+
+ list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
+ list_del(&trans->list);
+ nft_commit_release(trans);
+ }
+}
+
static int nf_tables_commit(struct net *net, struct sk_buff *skb)
{
struct nft_trans *trans, *next;
@@ -5913,13 +5975,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
}
}
- synchronize_rcu();
-
- list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
- list_del(&trans->list);
- nf_tables_commit_release(trans);
- }
-
+ nf_tables_commit_release(net);
nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN);
return 0;
@@ -5999,10 +6055,12 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb)
case NFT_MSG_NEWRULE:
trans->ctx.chain->use--;
list_del_rcu(&nft_trans_rule(trans)->list);
+ nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans));
break;
case NFT_MSG_DELRULE:
trans->ctx.chain->use++;
nft_clear(trans->ctx.net, nft_trans_rule(trans));
+ nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans));
nft_trans_destroy(trans);
break;
case NFT_MSG_NEWSET:
@@ -6578,7 +6636,7 @@ int __nft_release_basechain(struct nft_ctx *ctx)
list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) {
list_del(&rule->list);
ctx->chain->use--;
- nf_tables_rule_destroy(ctx, rule);
+ nf_tables_rule_release(ctx, rule);
}
list_del(&ctx->chain->list);
ctx->table->use--;
@@ -6616,7 +6674,7 @@ static void __nft_release_tables(struct net *net)
list_for_each_entry_safe(rule, nr, &chain->rules, list) {
list_del(&rule->list);
chain->use--;
- nf_tables_rule_destroy(&ctx, rule);
+ nf_tables_rule_release(&ctx, rule);
}
}
list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) {
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index dfd0bf3..40e74457 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -119,14 +119,21 @@ DEFINE_STATIC_KEY_FALSE(nft_counters_enabled);
static noinline void nft_update_chain_stats(const struct nft_chain *chain,
const struct nft_pktinfo *pkt)
{
+ struct nft_base_chain *base_chain;
struct nft_stats *stats;
+ base_chain = nft_base_chain(chain);
+ if (!base_chain->stats)
+ return;
+
local_bh_disable();
- stats = this_cpu_ptr(rcu_dereference(nft_base_chain(chain)->stats));
- u64_stats_update_begin(&stats->syncp);
- stats->pkts++;
- stats->bytes += pkt->skb->len;
- u64_stats_update_end(&stats->syncp);
+ stats = this_cpu_ptr(rcu_dereference(base_chain->stats));
+ if (stats) {
+ u64_stats_update_begin(&stats->syncp);
+ stats->pkts++;
+ stats->bytes += pkt->skb->len;
+ u64_stats_update_end(&stats->syncp);
+ }
local_bh_enable();
}
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index b9505bc..a0e5adf 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -115,7 +115,7 @@ static int nfnl_acct_new(struct net *net, struct sock *nfnl,
nfacct->flags = flags;
}
- strncpy(nfacct->name, nla_data(tb[NFACCT_NAME]), NFACCT_NAME_MAX);
+ nla_strlcpy(nfacct->name, tb[NFACCT_NAME], NFACCT_NAME_MAX);
if (tb[NFACCT_BYTES]) {
atomic64_set(&nfacct->bytes,
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index 4a4b293..cb5b5f2 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -149,8 +149,8 @@ nfnl_cthelper_expect_policy(struct nf_conntrack_expect_policy *expect_policy,
!tb[NFCTH_POLICY_EXPECT_TIMEOUT])
return -EINVAL;
- strncpy(expect_policy->name,
- nla_data(tb[NFCTH_POLICY_NAME]), NF_CT_HELPER_NAME_LEN);
+ nla_strlcpy(expect_policy->name,
+ tb[NFCTH_POLICY_NAME], NF_CT_HELPER_NAME_LEN);
expect_policy->max_expected =
ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX]));
if (expect_policy->max_expected > NF_CT_EXPECT_MAX_CNT)
@@ -234,7 +234,8 @@ nfnl_cthelper_create(const struct nlattr * const tb[],
if (ret < 0)
goto err1;
- strncpy(helper->name, nla_data(tb[NFCTH_NAME]), NF_CT_HELPER_NAME_LEN);
+ nla_strlcpy(helper->name,
+ tb[NFCTH_NAME], NF_CT_HELPER_NAME_LEN);
size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN]));
if (size > FIELD_SIZEOF(struct nf_conn_help, data)) {
ret = -ENOMEM;
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 7b46aa4..c14822b 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -1046,20 +1046,6 @@ static const struct seq_operations nful_seq_ops = {
.stop = seq_stop,
.show = seq_show,
};
-
-static int nful_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &nful_seq_ops,
- sizeof(struct iter_state));
-}
-
-static const struct file_operations nful_file_ops = {
- .open = nful_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
#endif /* PROC_FS */
static int __net_init nfnl_log_net_init(struct net *net)
@@ -1077,8 +1063,8 @@ static int __net_init nfnl_log_net_init(struct net *net)
spin_lock_init(&log->instances_lock);
#ifdef CONFIG_PROC_FS
- proc = proc_create("nfnetlink_log", 0440,
- net->nf.proc_netfilter, &nful_file_ops);
+ proc = proc_create_net("nfnetlink_log", 0440, net->nf.proc_netfilter,
+ &nful_seq_ops, sizeof(struct iter_state));
if (!proc)
return -ENOMEM;
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 74a0463..494a9ab 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -1469,20 +1469,6 @@ static const struct seq_operations nfqnl_seq_ops = {
.stop = seq_stop,
.show = seq_show,
};
-
-static int nfqnl_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &nfqnl_seq_ops,
- sizeof(struct iter_state));
-}
-
-static const struct file_operations nfqnl_file_ops = {
- .open = nfqnl_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
#endif /* PROC_FS */
static int __net_init nfnl_queue_net_init(struct net *net)
@@ -1496,8 +1482,8 @@ static int __net_init nfnl_queue_net_init(struct net *net)
spin_lock_init(&q->instances_lock);
#ifdef CONFIG_PROC_FS
- if (!proc_create("nfnetlink_queue", 0440,
- net->nf.proc_netfilter, &nfqnl_file_ops))
+ if (!proc_create_net("nfnetlink_queue", 0440, net->nf.proc_netfilter,
+ &nfqnl_seq_ops, sizeof(struct iter_state)))
return -ENOMEM;
#endif
nf_register_queue_handler(net, &nfqh);
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 8e23726..1d99a1ef 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -27,14 +27,31 @@ struct nft_xt {
struct list_head head;
struct nft_expr_ops ops;
unsigned int refcnt;
+
+ /* Unlike other expressions, ops doesn't have static storage duration.
+ * nft core assumes they do. We use kfree_rcu so that nft core can
+ * can check expr->ops->size even after nft_compat->destroy() frees
+ * the nft_xt struct that holds the ops structure.
+ */
+ struct rcu_head rcu_head;
};
-static void nft_xt_put(struct nft_xt *xt)
+/* Used for matches where *info is larger than X byte */
+#define NFT_MATCH_LARGE_THRESH 192
+
+struct nft_xt_match_priv {
+ void *info;
+};
+
+static bool nft_xt_put(struct nft_xt *xt)
{
if (--xt->refcnt == 0) {
list_del(&xt->head);
- kfree(xt);
+ kfree_rcu(xt, rcu_head);
+ return true;
}
+
+ return false;
}
static int nft_compat_chain_validate_dependency(const char *tablename,
@@ -226,6 +243,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
struct xt_target *target = expr->ops->data;
struct xt_tgchk_param par;
size_t size = XT_ALIGN(nla_len(tb[NFTA_TARGET_INFO]));
+ struct nft_xt *nft_xt;
u16 proto = 0;
bool inv = false;
union nft_entry e = {};
@@ -236,25 +254,22 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
if (ctx->nla[NFTA_RULE_COMPAT]) {
ret = nft_parse_compat(ctx->nla[NFTA_RULE_COMPAT], &proto, &inv);
if (ret < 0)
- goto err;
+ return ret;
}
nft_target_set_tgchk_param(&par, ctx, target, info, &e, proto, inv);
ret = xt_check_target(&par, size, proto, inv);
if (ret < 0)
- goto err;
+ return ret;
/* The standard target cannot be used */
- if (target->target == NULL) {
- ret = -EINVAL;
- goto err;
- }
+ if (!target->target)
+ return -EINVAL;
+ nft_xt = container_of(expr->ops, struct nft_xt, ops);
+ nft_xt->refcnt++;
return 0;
-err:
- module_put(target->me);
- return ret;
}
static void
@@ -271,8 +286,8 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
if (par.target->destroy != NULL)
par.target->destroy(&par);
- nft_xt_put(container_of(expr->ops, struct nft_xt, ops));
- module_put(target->me);
+ if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops)))
+ module_put(target->me);
}
static int nft_target_dump(struct sk_buff *skb, const struct nft_expr *expr)
@@ -316,11 +331,11 @@ static int nft_target_validate(const struct nft_ctx *ctx,
return 0;
}
-static void nft_match_eval(const struct nft_expr *expr,
- struct nft_regs *regs,
- const struct nft_pktinfo *pkt)
+static void __nft_match_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt,
+ void *info)
{
- void *info = nft_expr_priv(expr);
struct xt_match *match = expr->ops->data;
struct sk_buff *skb = pkt->skb;
bool ret;
@@ -344,6 +359,22 @@ static void nft_match_eval(const struct nft_expr *expr,
}
}
+static void nft_match_large_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ struct nft_xt_match_priv *priv = nft_expr_priv(expr);
+
+ __nft_match_eval(expr, regs, pkt, priv->info);
+}
+
+static void nft_match_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ __nft_match_eval(expr, regs, pkt, nft_expr_priv(expr));
+}
+
static const struct nla_policy nft_match_policy[NFTA_MATCH_MAX + 1] = {
[NFTA_MATCH_NAME] = { .type = NLA_NUL_STRING },
[NFTA_MATCH_REV] = { .type = NLA_U32 },
@@ -404,13 +435,14 @@ static void match_compat_from_user(struct xt_match *m, void *in, void *out)
}
static int
-nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
- const struct nlattr * const tb[])
+__nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+ const struct nlattr * const tb[],
+ void *info)
{
- void *info = nft_expr_priv(expr);
struct xt_match *match = expr->ops->data;
struct xt_mtchk_param par;
size_t size = XT_ALIGN(nla_len(tb[NFTA_MATCH_INFO]));
+ struct nft_xt *nft_xt;
u16 proto = 0;
bool inv = false;
union nft_entry e = {};
@@ -421,26 +453,50 @@ nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
if (ctx->nla[NFTA_RULE_COMPAT]) {
ret = nft_parse_compat(ctx->nla[NFTA_RULE_COMPAT], &proto, &inv);
if (ret < 0)
- goto err;
+ return ret;
}
nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv);
ret = xt_check_match(&par, size, proto, inv);
if (ret < 0)
- goto err;
+ return ret;
+ nft_xt = container_of(expr->ops, struct nft_xt, ops);
+ nft_xt->refcnt++;
return 0;
-err:
- module_put(match->me);
+}
+
+static int
+nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ return __nft_match_init(ctx, expr, tb, nft_expr_priv(expr));
+}
+
+static int
+nft_match_large_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_xt_match_priv *priv = nft_expr_priv(expr);
+ struct xt_match *m = expr->ops->data;
+ int ret;
+
+ priv->info = kmalloc(XT_ALIGN(m->matchsize), GFP_KERNEL);
+ if (!priv->info)
+ return -ENOMEM;
+
+ ret = __nft_match_init(ctx, expr, tb, priv->info);
+ if (ret)
+ kfree(priv->info);
return ret;
}
static void
-nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+__nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr,
+ void *info)
{
struct xt_match *match = expr->ops->data;
- void *info = nft_expr_priv(expr);
struct xt_mtdtor_param par;
par.net = ctx->net;
@@ -450,13 +506,28 @@ nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
if (par.match->destroy != NULL)
par.match->destroy(&par);
- nft_xt_put(container_of(expr->ops, struct nft_xt, ops));
- module_put(match->me);
+ if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops)))
+ module_put(match->me);
}
-static int nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr)
+static void
+nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
{
- void *info = nft_expr_priv(expr);
+ __nft_match_destroy(ctx, expr, nft_expr_priv(expr));
+}
+
+static void
+nft_match_large_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+ struct nft_xt_match_priv *priv = nft_expr_priv(expr);
+
+ __nft_match_destroy(ctx, expr, priv->info);
+ kfree(priv->info);
+}
+
+static int __nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr,
+ void *info)
+{
struct xt_match *match = expr->ops->data;
if (nla_put_string(skb, NFTA_MATCH_NAME, match->name) ||
@@ -470,6 +541,18 @@ static int nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr)
return -1;
}
+static int nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ return __nft_match_dump(skb, expr, nft_expr_priv(expr));
+}
+
+static int nft_match_large_dump(struct sk_buff *skb, const struct nft_expr *e)
+{
+ struct nft_xt_match_priv *priv = nft_expr_priv(e);
+
+ return __nft_match_dump(skb, e, priv->info);
+}
+
static int nft_match_validate(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nft_data **data)
@@ -637,6 +720,7 @@ nft_match_select_ops(const struct nft_ctx *ctx,
{
struct nft_xt *nft_match;
struct xt_match *match;
+ unsigned int matchsize;
char *mt_name;
u32 rev, family;
int err;
@@ -654,13 +738,8 @@ nft_match_select_ops(const struct nft_ctx *ctx,
list_for_each_entry(nft_match, &nft_match_list, head) {
struct xt_match *match = nft_match->ops.data;
- if (nft_match_cmp(match, mt_name, rev, family)) {
- if (!try_module_get(match->me))
- return ERR_PTR(-ENOENT);
-
- nft_match->refcnt++;
+ if (nft_match_cmp(match, mt_name, rev, family))
return &nft_match->ops;
- }
}
match = xt_request_find_match(family, mt_name, rev);
@@ -679,9 +758,8 @@ nft_match_select_ops(const struct nft_ctx *ctx,
goto err;
}
- nft_match->refcnt = 1;
+ nft_match->refcnt = 0;
nft_match->ops.type = &nft_match_type;
- nft_match->ops.size = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize));
nft_match->ops.eval = nft_match_eval;
nft_match->ops.init = nft_match_init;
nft_match->ops.destroy = nft_match_destroy;
@@ -689,6 +767,18 @@ nft_match_select_ops(const struct nft_ctx *ctx,
nft_match->ops.validate = nft_match_validate;
nft_match->ops.data = match;
+ matchsize = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize));
+ if (matchsize > NFT_MATCH_LARGE_THRESH) {
+ matchsize = NFT_EXPR_SIZE(sizeof(struct nft_xt_match_priv));
+
+ nft_match->ops.eval = nft_match_large_eval;
+ nft_match->ops.init = nft_match_large_init;
+ nft_match->ops.destroy = nft_match_large_destroy;
+ nft_match->ops.dump = nft_match_large_dump;
+ }
+
+ nft_match->ops.size = matchsize;
+
list_add(&nft_match->head, &nft_match_list);
return &nft_match->ops;
@@ -739,13 +829,8 @@ nft_target_select_ops(const struct nft_ctx *ctx,
list_for_each_entry(nft_target, &nft_target_list, head) {
struct xt_target *target = nft_target->ops.data;
- if (nft_target_cmp(target, tg_name, rev, family)) {
- if (!try_module_get(target->me))
- return ERR_PTR(-ENOENT);
-
- nft_target->refcnt++;
+ if (nft_target_cmp(target, tg_name, rev, family))
return &nft_target->ops;
- }
}
target = xt_request_find_target(family, tg_name, rev);
@@ -764,7 +849,7 @@ nft_target_select_ops(const struct nft_ctx *ctx,
goto err;
}
- nft_target->refcnt = 1;
+ nft_target->refcnt = 0;
nft_target->ops.type = &nft_target_type;
nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize));
nft_target->ops.init = nft_target_init;
@@ -823,6 +908,32 @@ static int __init nft_compat_module_init(void)
static void __exit nft_compat_module_exit(void)
{
+ struct nft_xt *xt, *next;
+
+ /* list should be empty here, it can be non-empty only in case there
+ * was an error that caused nft_xt expr to not be initialized fully
+ * and noone else requested the same expression later.
+ *
+ * In this case, the lists contain 0-refcount entries that still
+ * hold module reference.
+ */
+ list_for_each_entry_safe(xt, next, &nft_target_list, head) {
+ struct xt_target *target = xt->ops.data;
+
+ if (WARN_ON_ONCE(xt->refcnt))
+ continue;
+ module_put(target->me);
+ kfree(xt);
+ }
+
+ list_for_each_entry_safe(xt, next, &nft_match_list, head) {
+ struct xt_match *match = xt->ops.data;
+
+ if (WARN_ON_ONCE(xt->refcnt))
+ continue;
+ module_put(match->me);
+ kfree(xt);
+ }
nfnetlink_subsys_unregister(&nfnl_compat_subsys);
nft_unregister_expr(&nft_target_type);
nft_unregister_expr(&nft_match_type);
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index ea737fd..5c0de70 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -880,22 +880,26 @@ static int nft_ct_helper_obj_dump(struct sk_buff *skb,
struct nft_object *obj, bool reset)
{
const struct nft_ct_helper_obj *priv = nft_obj_data(obj);
- const struct nf_conntrack_helper *helper = priv->helper4;
+ const struct nf_conntrack_helper *helper;
u16 family;
+ if (priv->helper4 && priv->helper6) {
+ family = NFPROTO_INET;
+ helper = priv->helper4;
+ } else if (priv->helper6) {
+ family = NFPROTO_IPV6;
+ helper = priv->helper6;
+ } else {
+ family = NFPROTO_IPV4;
+ helper = priv->helper4;
+ }
+
if (nla_put_string(skb, NFTA_CT_HELPER_NAME, helper->name))
return -1;
if (nla_put_u8(skb, NFTA_CT_HELPER_L4PROTO, priv->l4proto))
return -1;
- if (priv->helper4 && priv->helper6)
- family = NFPROTO_INET;
- else if (priv->helper6)
- family = NFPROTO_IPV6;
- else
- family = NFPROTO_IPV4;
-
if (nla_put_be16(skb, NFTA_CT_HELPER_L3PROTO, htons(family)))
return -1;
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index 4717d77..aa87ff8 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -69,8 +69,16 @@ static int nft_immediate_init(const struct nft_ctx *ctx,
return err;
}
-static void nft_immediate_destroy(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+static void nft_immediate_activate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
+{
+ const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+
+ return nft_data_hold(&priv->data, nft_dreg_to_type(priv->dreg));
+}
+
+static void nft_immediate_deactivate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
{
const struct nft_immediate_expr *priv = nft_expr_priv(expr);
@@ -108,7 +116,8 @@ static const struct nft_expr_ops nft_imm_ops = {
.size = NFT_EXPR_SIZE(sizeof(struct nft_immediate_expr)),
.eval = nft_immediate_eval,
.init = nft_immediate_init,
- .destroy = nft_immediate_destroy,
+ .activate = nft_immediate_activate,
+ .deactivate = nft_immediate_deactivate,
.dump = nft_immediate_dump,
.validate = nft_immediate_validate,
};
diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c
index a9fc298..72f13a1 100644
--- a/net/netfilter/nft_limit.c
+++ b/net/netfilter/nft_limit.c
@@ -51,10 +51,13 @@ static inline bool nft_limit_eval(struct nft_limit *limit, u64 cost)
return !limit->invert;
}
+/* Use same default as in iptables. */
+#define NFT_LIMIT_PKT_BURST_DEFAULT 5
+
static int nft_limit_init(struct nft_limit *limit,
- const struct nlattr * const tb[])
+ const struct nlattr * const tb[], bool pkts)
{
- u64 unit;
+ u64 unit, tokens;
if (tb[NFTA_LIMIT_RATE] == NULL ||
tb[NFTA_LIMIT_UNIT] == NULL)
@@ -68,18 +71,25 @@ static int nft_limit_init(struct nft_limit *limit,
if (tb[NFTA_LIMIT_BURST])
limit->burst = ntohl(nla_get_be32(tb[NFTA_LIMIT_BURST]));
- else
- limit->burst = 0;
+
+ if (pkts && limit->burst == 0)
+ limit->burst = NFT_LIMIT_PKT_BURST_DEFAULT;
if (limit->rate + limit->burst < limit->rate)
return -EOVERFLOW;
- /* The token bucket size limits the number of tokens can be
- * accumulated. tokens_max specifies the bucket size.
- * tokens_max = unit * (rate + burst) / rate.
- */
- limit->tokens = div_u64(limit->nsecs * (limit->rate + limit->burst),
- limit->rate);
+ if (pkts) {
+ tokens = div_u64(limit->nsecs, limit->rate) * limit->burst;
+ } else {
+ /* The token bucket size limits the number of tokens can be
+ * accumulated. tokens_max specifies the bucket size.
+ * tokens_max = unit * (rate + burst) / rate.
+ */
+ tokens = div_u64(limit->nsecs * (limit->rate + limit->burst),
+ limit->rate);
+ }
+
+ limit->tokens = tokens;
limit->tokens_max = limit->tokens;
if (tb[NFTA_LIMIT_FLAGS]) {
@@ -144,7 +154,7 @@ static int nft_limit_pkts_init(const struct nft_ctx *ctx,
struct nft_limit_pkts *priv = nft_expr_priv(expr);
int err;
- err = nft_limit_init(&priv->limit, tb);
+ err = nft_limit_init(&priv->limit, tb, true);
if (err < 0)
return err;
@@ -185,7 +195,7 @@ static int nft_limit_bytes_init(const struct nft_ctx *ctx,
{
struct nft_limit *priv = nft_expr_priv(expr);
- return nft_limit_init(priv, tb);
+ return nft_limit_init(priv, tb, false);
}
static int nft_limit_bytes_dump(struct sk_buff *skb,
@@ -246,7 +256,7 @@ static int nft_limit_obj_pkts_init(const struct nft_ctx *ctx,
struct nft_limit_pkts *priv = nft_obj_data(obj);
int err;
- err = nft_limit_init(&priv->limit, tb);
+ err = nft_limit_init(&priv->limit, tb, true);
if (err < 0)
return err;
@@ -289,7 +299,7 @@ static int nft_limit_obj_bytes_init(const struct nft_ctx *ctx,
{
struct nft_limit *priv = nft_obj_data(obj);
- return nft_limit_init(priv, tb);
+ return nft_limit_init(priv, tb, false);
}
static int nft_limit_obj_bytes_dump(struct sk_buff *skb,
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 8fb91940..204af98 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -234,7 +234,7 @@ void nft_meta_set_eval(const struct nft_expr *expr,
struct sk_buff *skb = pkt->skb;
u32 *sreg = ®s->data[meta->sreg];
u32 value = *sreg;
- u8 pkt_type;
+ u8 value8;
switch (meta->key) {
case NFT_META_MARK:
@@ -244,15 +244,17 @@ void nft_meta_set_eval(const struct nft_expr *expr,
skb->priority = value;
break;
case NFT_META_PKTTYPE:
- pkt_type = nft_reg_load8(sreg);
+ value8 = nft_reg_load8(sreg);
- if (skb->pkt_type != pkt_type &&
- skb_pkt_type_ok(pkt_type) &&
+ if (skb->pkt_type != value8 &&
+ skb_pkt_type_ok(value8) &&
skb_pkt_type_ok(skb->pkt_type))
- skb->pkt_type = pkt_type;
+ skb->pkt_type = value8;
break;
case NFT_META_NFTRACE:
- skb->nf_trace = !!value;
+ value8 = nft_reg_load8(sreg);
+
+ skb->nf_trace = !!value8;
break;
default:
WARN_ON(1);
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 71325fe..55cb4d1 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -183,6 +183,9 @@ struct xt_match *xt_find_match(u8 af, const char *name, u8 revision)
struct xt_match *m;
int err = -ENOENT;
+ if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN)
+ return ERR_PTR(-EINVAL);
+
mutex_lock(&xt[af].mutex);
list_for_each_entry(m, &xt[af].match, list) {
if (strcmp(m->name, name) == 0) {
@@ -229,6 +232,9 @@ struct xt_target *xt_find_target(u8 af, const char *name, u8 revision)
struct xt_target *t;
int err = -ENOENT;
+ if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN)
+ return ERR_PTR(-EINVAL);
+
mutex_lock(&xt[af].mutex);
list_for_each_entry(t, &xt[af].target, list) {
if (strcmp(t->name, name) == 0) {
@@ -1489,15 +1495,10 @@ void *xt_unregister_table(struct xt_table *table)
EXPORT_SYMBOL_GPL(xt_unregister_table);
#ifdef CONFIG_PROC_FS
-struct xt_names_priv {
- struct seq_net_private p;
- u_int8_t af;
-};
static void *xt_table_seq_start(struct seq_file *seq, loff_t *pos)
{
- struct xt_names_priv *priv = seq->private;
struct net *net = seq_file_net(seq);
- u_int8_t af = priv->af;
+ u_int8_t af = (unsigned long)PDE_DATA(file_inode(seq->file));
mutex_lock(&xt[af].mutex);
return seq_list_start(&net->xt.tables[af], *pos);
@@ -1505,17 +1506,15 @@ static void *xt_table_seq_start(struct seq_file *seq, loff_t *pos)
static void *xt_table_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct xt_names_priv *priv = seq->private;
struct net *net = seq_file_net(seq);
- u_int8_t af = priv->af;
+ u_int8_t af = (unsigned long)PDE_DATA(file_inode(seq->file));
return seq_list_next(v, &net->xt.tables[af], pos);
}
static void xt_table_seq_stop(struct seq_file *seq, void *v)
{
- struct xt_names_priv *priv = seq->private;
- u_int8_t af = priv->af;
+ u_int8_t af = (unsigned long)PDE_DATA(file_inode(seq->file));
mutex_unlock(&xt[af].mutex);
}
@@ -1536,34 +1535,13 @@ static const struct seq_operations xt_table_seq_ops = {
.show = xt_table_seq_show,
};
-static int xt_table_open(struct inode *inode, struct file *file)
-{
- int ret;
- struct xt_names_priv *priv;
-
- ret = seq_open_net(inode, file, &xt_table_seq_ops,
- sizeof(struct xt_names_priv));
- if (!ret) {
- priv = ((struct seq_file *)file->private_data)->private;
- priv->af = (unsigned long)PDE_DATA(inode);
- }
- return ret;
-}
-
-static const struct file_operations xt_table_ops = {
- .open = xt_table_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
/*
* Traverse state for ip{,6}_{tables,matches} for helping crossing
* the multi-AF mutexes.
*/
struct nf_mttg_trav {
struct list_head *head, *curr;
- uint8_t class, nfproto;
+ uint8_t class;
};
enum {
@@ -1580,6 +1558,7 @@ static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos,
[MTTG_TRAV_NFP_UNSPEC] = MTTG_TRAV_NFP_SPEC,
[MTTG_TRAV_NFP_SPEC] = MTTG_TRAV_DONE,
};
+ uint8_t nfproto = (unsigned long)PDE_DATA(file_inode(seq->file));
struct nf_mttg_trav *trav = seq->private;
switch (trav->class) {
@@ -1594,9 +1573,9 @@ static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos,
if (trav->curr != trav->head)
break;
mutex_unlock(&xt[NFPROTO_UNSPEC].mutex);
- mutex_lock(&xt[trav->nfproto].mutex);
+ mutex_lock(&xt[nfproto].mutex);
trav->head = trav->curr = is_target ?
- &xt[trav->nfproto].target : &xt[trav->nfproto].match;
+ &xt[nfproto].target : &xt[nfproto].match;
trav->class = next_class[trav->class];
break;
case MTTG_TRAV_NFP_SPEC:
@@ -1628,6 +1607,7 @@ static void *xt_mttg_seq_start(struct seq_file *seq, loff_t *pos,
static void xt_mttg_seq_stop(struct seq_file *seq, void *v)
{
+ uint8_t nfproto = (unsigned long)PDE_DATA(file_inode(seq->file));
struct nf_mttg_trav *trav = seq->private;
switch (trav->class) {
@@ -1635,7 +1615,7 @@ static void xt_mttg_seq_stop(struct seq_file *seq, void *v)
mutex_unlock(&xt[NFPROTO_UNSPEC].mutex);
break;
case MTTG_TRAV_NFP_SPEC:
- mutex_unlock(&xt[trav->nfproto].mutex);
+ mutex_unlock(&xt[nfproto].mutex);
break;
}
}
@@ -1674,24 +1654,6 @@ static const struct seq_operations xt_match_seq_ops = {
.show = xt_match_seq_show,
};
-static int xt_match_open(struct inode *inode, struct file *file)
-{
- struct nf_mttg_trav *trav;
- trav = __seq_open_private(file, &xt_match_seq_ops, sizeof(*trav));
- if (!trav)
- return -ENOMEM;
-
- trav->nfproto = (unsigned long)PDE_DATA(inode);
- return 0;
-}
-
-static const struct file_operations xt_match_ops = {
- .open = xt_match_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_private,
-};
-
static void *xt_target_seq_start(struct seq_file *seq, loff_t *pos)
{
return xt_mttg_seq_start(seq, pos, true);
@@ -1726,24 +1688,6 @@ static const struct seq_operations xt_target_seq_ops = {
.show = xt_target_seq_show,
};
-static int xt_target_open(struct inode *inode, struct file *file)
-{
- struct nf_mttg_trav *trav;
- trav = __seq_open_private(file, &xt_target_seq_ops, sizeof(*trav));
- if (!trav)
- return -ENOMEM;
-
- trav->nfproto = (unsigned long)PDE_DATA(inode);
- return 0;
-}
-
-static const struct file_operations xt_target_ops = {
- .open = xt_target_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_private,
-};
-
#define FORMAT_TABLES "_tables_names"
#define FORMAT_MATCHES "_tables_matches"
#define FORMAT_TARGETS "_tables_targets"
@@ -1807,8 +1751,9 @@ int xt_proto_init(struct net *net, u_int8_t af)
strlcpy(buf, xt_prefix[af], sizeof(buf));
strlcat(buf, FORMAT_TABLES, sizeof(buf));
- proc = proc_create_data(buf, 0440, net->proc_net, &xt_table_ops,
- (void *)(unsigned long)af);
+ proc = proc_create_net_data(buf, 0440, net->proc_net, &xt_table_seq_ops,
+ sizeof(struct seq_net_private),
+ (void *)(unsigned long)af);
if (!proc)
goto out;
if (uid_valid(root_uid) && gid_valid(root_gid))
@@ -1816,8 +1761,9 @@ int xt_proto_init(struct net *net, u_int8_t af)
strlcpy(buf, xt_prefix[af], sizeof(buf));
strlcat(buf, FORMAT_MATCHES, sizeof(buf));
- proc = proc_create_data(buf, 0440, net->proc_net, &xt_match_ops,
- (void *)(unsigned long)af);
+ proc = proc_create_seq_private(buf, 0440, net->proc_net,
+ &xt_match_seq_ops, sizeof(struct nf_mttg_trav),
+ (void *)(unsigned long)af);
if (!proc)
goto out_remove_tables;
if (uid_valid(root_uid) && gid_valid(root_gid))
@@ -1825,8 +1771,9 @@ int xt_proto_init(struct net *net, u_int8_t af)
strlcpy(buf, xt_prefix[af], sizeof(buf));
strlcat(buf, FORMAT_TARGETS, sizeof(buf));
- proc = proc_create_data(buf, 0440, net->proc_net, &xt_target_ops,
- (void *)(unsigned long)af);
+ proc = proc_create_seq_private(buf, 0440, net->proc_net,
+ &xt_target_seq_ops, sizeof(struct nf_mttg_trav),
+ (void *)(unsigned long)af);
if (!proc)
goto out_remove_matches;
if (uid_valid(root_uid) && gid_valid(root_gid))
diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c
index 773da82..94df000 100644
--- a/net/netfilter/xt_connmark.c
+++ b/net/netfilter/xt_connmark.c
@@ -36,11 +36,10 @@ MODULE_ALIAS("ipt_connmark");
MODULE_ALIAS("ip6t_connmark");
static unsigned int
-connmark_tg_shift(struct sk_buff *skb,
- const struct xt_connmark_tginfo1 *info,
- u8 shift_bits, u8 shift_dir)
+connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info)
{
enum ip_conntrack_info ctinfo;
+ u_int32_t new_targetmark;
struct nf_conn *ct;
u_int32_t newmark;
@@ -51,34 +50,39 @@ connmark_tg_shift(struct sk_buff *skb,
switch (info->mode) {
case XT_CONNMARK_SET:
newmark = (ct->mark & ~info->ctmask) ^ info->ctmark;
- if (shift_dir == D_SHIFT_RIGHT)
- newmark >>= shift_bits;
+ if (info->shift_dir == D_SHIFT_RIGHT)
+ newmark >>= info->shift_bits;
else
- newmark <<= shift_bits;
+ newmark <<= info->shift_bits;
+
if (ct->mark != newmark) {
ct->mark = newmark;
nf_conntrack_event_cache(IPCT_MARK, ct);
}
break;
case XT_CONNMARK_SAVE:
- newmark = (ct->mark & ~info->ctmask) ^
- (skb->mark & info->nfmask);
- if (shift_dir == D_SHIFT_RIGHT)
- newmark >>= shift_bits;
+ new_targetmark = (skb->mark & info->nfmask);
+ if (info->shift_dir == D_SHIFT_RIGHT)
+ new_targetmark >>= info->shift_bits;
else
- newmark <<= shift_bits;
+ new_targetmark <<= info->shift_bits;
+
+ newmark = (ct->mark & ~info->ctmask) ^
+ new_targetmark;
if (ct->mark != newmark) {
ct->mark = newmark;
nf_conntrack_event_cache(IPCT_MARK, ct);
}
break;
case XT_CONNMARK_RESTORE:
- newmark = (skb->mark & ~info->nfmask) ^
- (ct->mark & info->ctmask);
- if (shift_dir == D_SHIFT_RIGHT)
- newmark >>= shift_bits;
+ new_targetmark = (ct->mark & info->ctmask);
+ if (info->shift_dir == D_SHIFT_RIGHT)
+ new_targetmark >>= info->shift_bits;
else
- newmark <<= shift_bits;
+ new_targetmark <<= info->shift_bits;
+
+ newmark = (skb->mark & ~info->nfmask) ^
+ new_targetmark;
skb->mark = newmark;
break;
}
@@ -89,8 +93,14 @@ static unsigned int
connmark_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_connmark_tginfo1 *info = par->targinfo;
+ const struct xt_connmark_tginfo2 info2 = {
+ .ctmark = info->ctmark,
+ .ctmask = info->ctmask,
+ .nfmask = info->nfmask,
+ .mode = info->mode,
+ };
- return connmark_tg_shift(skb, info, 0, 0);
+ return connmark_tg_shift(skb, &info2);
}
static unsigned int
@@ -98,8 +108,7 @@ connmark_tg_v2(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_connmark_tginfo2 *info = par->targinfo;
- return connmark_tg_shift(skb, (const struct xt_connmark_tginfo1 *)info,
- info->shift_bits, info->shift_dir);
+ return connmark_tg_shift(skb, info);
}
static int connmark_tg_check(const struct xt_tgchk_param *par)
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 0cd7356..9b16402 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -57,9 +57,9 @@ static inline struct hashlimit_net *hashlimit_pernet(struct net *net)
}
/* need to declare this at the top */
-static const struct file_operations dl_file_ops_v2;
-static const struct file_operations dl_file_ops_v1;
-static const struct file_operations dl_file_ops;
+static const struct seq_operations dl_seq_ops_v2;
+static const struct seq_operations dl_seq_ops_v1;
+static const struct seq_operations dl_seq_ops;
/* hash table crap */
struct dsthash_dst {
@@ -272,7 +272,7 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg,
{
struct hashlimit_net *hashlimit_net = hashlimit_pernet(net);
struct xt_hashlimit_htable *hinfo;
- const struct file_operations *fops;
+ const struct seq_operations *ops;
unsigned int size, i;
int ret;
@@ -321,19 +321,19 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg,
switch (revision) {
case 1:
- fops = &dl_file_ops_v1;
+ ops = &dl_seq_ops_v1;
break;
case 2:
- fops = &dl_file_ops_v2;
+ ops = &dl_seq_ops_v2;
break;
default:
- fops = &dl_file_ops;
+ ops = &dl_seq_ops;
}
- hinfo->pde = proc_create_data(name, 0,
+ hinfo->pde = proc_create_seq_data(name, 0,
(family == NFPROTO_IPV4) ?
hashlimit_net->ipt_hashlimit : hashlimit_net->ip6t_hashlimit,
- fops, hinfo);
+ ops, hinfo);
if (hinfo->pde == NULL) {
kfree(hinfo->name);
vfree(hinfo);
@@ -1057,7 +1057,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = {
static void *dl_seq_start(struct seq_file *s, loff_t *pos)
__acquires(htable->lock)
{
- struct xt_hashlimit_htable *htable = s->private;
+ struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private));
unsigned int *bucket;
spin_lock_bh(&htable->lock);
@@ -1074,7 +1074,7 @@ static void *dl_seq_start(struct seq_file *s, loff_t *pos)
static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos)
{
- struct xt_hashlimit_htable *htable = s->private;
+ struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private));
unsigned int *bucket = v;
*pos = ++(*bucket);
@@ -1088,7 +1088,7 @@ static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos)
static void dl_seq_stop(struct seq_file *s, void *v)
__releases(htable->lock)
{
- struct xt_hashlimit_htable *htable = s->private;
+ struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private));
unsigned int *bucket = v;
if (!IS_ERR(bucket))
@@ -1130,7 +1130,7 @@ static void dl_seq_print(struct dsthash_ent *ent, u_int8_t family,
static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family,
struct seq_file *s)
{
- const struct xt_hashlimit_htable *ht = s->private;
+ struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->private));
spin_lock(&ent->lock);
/* recalculate to show accurate numbers */
@@ -1145,7 +1145,7 @@ static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family,
static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family,
struct seq_file *s)
{
- const struct xt_hashlimit_htable *ht = s->private;
+ struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->private));
spin_lock(&ent->lock);
/* recalculate to show accurate numbers */
@@ -1160,7 +1160,7 @@ static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family,
static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family,
struct seq_file *s)
{
- const struct xt_hashlimit_htable *ht = s->private;
+ struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->private));
spin_lock(&ent->lock);
/* recalculate to show accurate numbers */
@@ -1174,7 +1174,7 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family,
static int dl_seq_show_v2(struct seq_file *s, void *v)
{
- struct xt_hashlimit_htable *htable = s->private;
+ struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private));
unsigned int *bucket = (unsigned int *)v;
struct dsthash_ent *ent;
@@ -1188,7 +1188,7 @@ static int dl_seq_show_v2(struct seq_file *s, void *v)
static int dl_seq_show_v1(struct seq_file *s, void *v)
{
- struct xt_hashlimit_htable *htable = s->private;
+ struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private));
unsigned int *bucket = v;
struct dsthash_ent *ent;
@@ -1202,7 +1202,7 @@ static int dl_seq_show_v1(struct seq_file *s, void *v)
static int dl_seq_show(struct seq_file *s, void *v)
{
- struct xt_hashlimit_htable *htable = s->private;
+ struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private));
unsigned int *bucket = v;
struct dsthash_ent *ent;
@@ -1235,62 +1235,6 @@ static const struct seq_operations dl_seq_ops = {
.show = dl_seq_show
};
-static int dl_proc_open_v2(struct inode *inode, struct file *file)
-{
- int ret = seq_open(file, &dl_seq_ops_v2);
-
- if (!ret) {
- struct seq_file *sf = file->private_data;
-
- sf->private = PDE_DATA(inode);
- }
- return ret;
-}
-
-static int dl_proc_open_v1(struct inode *inode, struct file *file)
-{
- int ret = seq_open(file, &dl_seq_ops_v1);
-
- if (!ret) {
- struct seq_file *sf = file->private_data;
- sf->private = PDE_DATA(inode);
- }
- return ret;
-}
-
-static int dl_proc_open(struct inode *inode, struct file *file)
-{
- int ret = seq_open(file, &dl_seq_ops);
-
- if (!ret) {
- struct seq_file *sf = file->private_data;
-
- sf->private = PDE_DATA(inode);
- }
- return ret;
-}
-
-static const struct file_operations dl_file_ops_v2 = {
- .open = dl_proc_open_v2,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release
-};
-
-static const struct file_operations dl_file_ops_v1 = {
- .open = dl_proc_open_v1,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release
-};
-
-static const struct file_operations dl_file_ops = {
- .open = dl_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release
-};
-
static int __net_init hashlimit_proc_net_init(struct net *net)
{
struct hashlimit_net *hashlimit_net = hashlimit_pernet(net);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 55342c4..1189b84 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2606,13 +2606,13 @@ static int netlink_seq_show(struct seq_file *seq, void *v)
{
if (v == SEQ_START_TOKEN) {
seq_puts(seq,
- "sk Eth Pid Groups "
- "Rmem Wmem Dump Locks Drops Inode\n");
+ "sk Eth Pid Groups "
+ "Rmem Wmem Dump Locks Drops Inode\n");
} else {
struct sock *s = v;
struct netlink_sock *nlk = nlk_sk(s);
- seq_printf(seq, "%pK %-3d %-6u %08x %-8d %-8d %d %-8d %-8d %-8lu\n",
+ seq_printf(seq, "%pK %-3d %-10u %08x %-8d %-8d %-5d %-8d %-8d %-8lu\n",
s,
s->sk_protocol,
nlk->portid,
@@ -2635,21 +2635,6 @@ static const struct seq_operations netlink_seq_ops = {
.stop = netlink_seq_stop,
.show = netlink_seq_show,
};
-
-
-static int netlink_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &netlink_seq_ops,
- sizeof(struct nl_seq_iter));
-}
-
-static const struct file_operations netlink_seq_fops = {
- .open = netlink_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
#endif
int netlink_register_notifier(struct notifier_block *nb)
@@ -2673,7 +2658,7 @@ static const struct proto_ops netlink_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = netlink_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = netlink_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
@@ -2694,7 +2679,8 @@ static const struct net_proto_family netlink_family_ops = {
static int __net_init netlink_net_init(struct net *net)
{
#ifdef CONFIG_PROC_FS
- if (!proc_create("netlink", 0, net->proc_net, &netlink_seq_fops))
+ if (!proc_create_net("netlink", 0, net->proc_net, &netlink_seq_ops,
+ sizeof(struct nl_seq_iter)))
return -ENOMEM;
#endif
return 0;
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 4221d98..b97eb76 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1338,18 +1338,6 @@ static const struct seq_operations nr_info_seqops = {
.stop = nr_info_stop,
.show = nr_info_show,
};
-
-static int nr_info_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &nr_info_seqops);
-}
-
-static const struct file_operations nr_info_fops = {
- .open = nr_info_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
#endif /* CONFIG_PROC_FS */
static const struct net_proto_family nr_family_ops = {
@@ -1367,7 +1355,7 @@ static const struct proto_ops nr_proto_ops = {
.socketpair = sock_no_socketpair,
.accept = nr_accept,
.getname = nr_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = nr_ioctl,
.listen = nr_listen,
.shutdown = sock_no_shutdown,
@@ -1450,9 +1438,9 @@ static int __init nr_proto_init(void)
nr_loopback_init();
- proc_create("nr", 0444, init_net.proc_net, &nr_info_fops);
- proc_create("nr_neigh", 0444, init_net.proc_net, &nr_neigh_fops);
- proc_create("nr_nodes", 0444, init_net.proc_net, &nr_nodes_fops);
+ proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops);
+ proc_create_seq("nr_neigh", 0444, init_net.proc_net, &nr_neigh_seqops);
+ proc_create_seq("nr_nodes", 0444, init_net.proc_net, &nr_node_seqops);
out:
return rc;
fail:
diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c
index b5a7dcb..6485f59 100644
--- a/net/netrom/nr_route.c
+++ b/net/netrom/nr_route.c
@@ -888,25 +888,13 @@ static int nr_node_show(struct seq_file *seq, void *v)
return 0;
}
-static const struct seq_operations nr_node_seqops = {
+const struct seq_operations nr_node_seqops = {
.start = nr_node_start,
.next = nr_node_next,
.stop = nr_node_stop,
.show = nr_node_show,
};
-static int nr_node_info_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &nr_node_seqops);
-}
-
-const struct file_operations nr_nodes_fops = {
- .open = nr_node_info_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static void *nr_neigh_start(struct seq_file *seq, loff_t *pos)
{
spin_lock_bh(&nr_neigh_list_lock);
@@ -954,25 +942,12 @@ static int nr_neigh_show(struct seq_file *seq, void *v)
return 0;
}
-static const struct seq_operations nr_neigh_seqops = {
+const struct seq_operations nr_neigh_seqops = {
.start = nr_neigh_start,
.next = nr_neigh_next,
.stop = nr_neigh_stop,
.show = nr_neigh_show,
};
-
-static int nr_neigh_info_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &nr_neigh_seqops);
-}
-
-const struct file_operations nr_neigh_fops = {
- .open = nr_neigh_info_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
#endif
/*
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index ea0c0c6..ab5bb14 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -548,16 +548,13 @@ static inline __poll_t llcp_accept_poll(struct sock *parent)
return 0;
}
-static __poll_t llcp_sock_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+static __poll_t llcp_sock_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
__poll_t mask = 0;
pr_debug("%p\n", sk);
- sock_poll_wait(file, sk_sleep(sk), wait);
-
if (sk->sk_state == LLCP_LISTEN)
return llcp_accept_poll(sk);
@@ -899,7 +896,7 @@ static const struct proto_ops llcp_sock_ops = {
.socketpair = sock_no_socketpair,
.accept = llcp_sock_accept,
.getname = llcp_sock_getname,
- .poll = llcp_sock_poll,
+ .poll_mask = llcp_sock_poll_mask,
.ioctl = sock_no_ioctl,
.listen = llcp_sock_listen,
.shutdown = sock_no_shutdown,
@@ -919,7 +916,7 @@ static const struct proto_ops llcp_rawsock_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = llcp_sock_getname,
- .poll = llcp_sock_poll,
+ .poll_mask = llcp_sock_poll_mask,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index e2188de..60c3225 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -284,7 +284,7 @@ static const struct proto_ops rawsock_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
@@ -304,7 +304,7 @@ static const struct proto_ops rawsock_raw_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c
index d7da99a..9696ef9 100644
--- a/net/nsh/nsh.c
+++ b/net/nsh/nsh.c
@@ -57,6 +57,8 @@ int nsh_pop(struct sk_buff *skb)
return -ENOMEM;
nh = (struct nshhdr *)(skb->data);
length = nsh_hdr_len(nh);
+ if (length < NSH_BASE_HDR_LEN)
+ return -EINVAL;
inner_proto = tun_p_to_eth_p(nh->np);
if (!pskb_may_pull(skb, length))
return -ENOMEM;
@@ -90,6 +92,8 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb,
if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN)))
goto out;
nsh_len = nsh_hdr_len(nsh_hdr(skb));
+ if (nsh_len < NSH_BASE_HDR_LEN)
+ goto out;
if (unlikely(!pskb_may_pull(skb, nsh_len)))
goto out;
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 7322aa1..492ab0c 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -1712,13 +1712,10 @@ static void nlattr_set(struct nlattr *attr, u8 val,
/* The nlattr stream should already have been validated */
nla_for_each_nested(nla, attr, rem) {
- if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) {
- if (tbl[nla_type(nla)].next)
- tbl = tbl[nla_type(nla)].next;
- nlattr_set(nla, val, tbl);
- } else {
+ if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED)
+ nlattr_set(nla, val, tbl[nla_type(nla)].next ? : tbl);
+ else
memset(nla_data(nla), val, nla_len(nla));
- }
if (nla_type(nla) == OVS_KEY_ATTR_CT_STATE)
*(u32 *)nla_data(nla) &= CT_SUPPORTED_MASK;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 616cb9c..674390b 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -329,11 +329,11 @@ static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
skb_set_queue_mapping(skb, queue_index);
}
-/* register_prot_hook must be invoked with the po->bind_lock held,
+/* __register_prot_hook must be invoked through register_prot_hook
* or from a context in which asynchronous accesses to the packet
* socket is not possible (packet_create()).
*/
-static void register_prot_hook(struct sock *sk)
+static void __register_prot_hook(struct sock *sk)
{
struct packet_sock *po = pkt_sk(sk);
@@ -348,8 +348,13 @@ static void register_prot_hook(struct sock *sk)
}
}
-/* {,__}unregister_prot_hook() must be invoked with the po->bind_lock
- * held. If the sync parameter is true, we will temporarily drop
+static void register_prot_hook(struct sock *sk)
+{
+ lockdep_assert_held_once(&pkt_sk(sk)->bind_lock);
+ __register_prot_hook(sk);
+}
+
+/* If the sync parameter is true, we will temporarily drop
* the po->bind_lock and do a synchronize_net to make sure no
* asynchronous packet processing paths still refer to the elements
* of po->prot_hook. If the sync parameter is false, it is the
@@ -359,6 +364,8 @@ static void __unregister_prot_hook(struct sock *sk, bool sync)
{
struct packet_sock *po = pkt_sk(sk);
+ lockdep_assert_held_once(&po->bind_lock);
+
po->running = 0;
if (po->fanout)
@@ -2896,13 +2903,15 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
if (skb == NULL)
goto out_unlock;
- skb_set_network_header(skb, reserve);
+ skb_reset_network_header(skb);
err = -EINVAL;
if (sock->type == SOCK_DGRAM) {
offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len);
if (unlikely(offset < 0))
goto out_free;
+ } else if (reserve) {
+ skb_reserve(skb, -reserve);
}
/* Returns -EFAULT on error */
@@ -3008,6 +3017,7 @@ static int packet_release(struct socket *sock)
packet_flush_mclist(sk);
+ lock_sock(sk);
if (po->rx_ring.pg_vec) {
memset(&req_u, 0, sizeof(req_u));
packet_set_ring(sk, &req_u, 1, 0);
@@ -3017,6 +3027,7 @@ static int packet_release(struct socket *sock)
memset(&req_u, 0, sizeof(req_u));
packet_set_ring(sk, &req_u, 1, 1);
}
+ release_sock(sk);
f = fanout_release(sk);
@@ -3250,7 +3261,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
if (proto) {
po->prot_hook.type = proto;
- register_prot_hook(sk);
+ __register_prot_hook(sk);
}
mutex_lock(&net->packet.sklist_lock);
@@ -3643,6 +3654,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
union tpacket_req_u req_u;
int len;
+ lock_sock(sk);
switch (po->tp_version) {
case TPACKET_V1:
case TPACKET_V2:
@@ -3653,12 +3665,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
len = sizeof(req_u.req3);
break;
}
- if (optlen < len)
- return -EINVAL;
- if (copy_from_user(&req_u.req, optval, len))
- return -EFAULT;
- return packet_set_ring(sk, &req_u, 0,
- optname == PACKET_TX_RING);
+ if (optlen < len) {
+ ret = -EINVAL;
+ } else {
+ if (copy_from_user(&req_u.req, optval, len))
+ ret = -EFAULT;
+ else
+ ret = packet_set_ring(sk, &req_u, 0,
+ optname == PACKET_TX_RING);
+ }
+ release_sock(sk);
+ return ret;
}
case PACKET_COPY_THRESH:
{
@@ -3724,12 +3741,18 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (optlen != sizeof(val))
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
- po->tp_loss = !!val;
- return 0;
+
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->tp_loss = !!val;
+ ret = 0;
+ }
+ release_sock(sk);
+ return ret;
}
case PACKET_AUXDATA:
{
@@ -3740,7 +3763,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
+ lock_sock(sk);
po->auxdata = !!val;
+ release_sock(sk);
return 0;
}
case PACKET_ORIGDEV:
@@ -3752,7 +3777,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
+ lock_sock(sk);
po->origdev = !!val;
+ release_sock(sk);
return 0;
}
case PACKET_VNET_HDR:
@@ -3761,15 +3788,20 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (sock->type != SOCK_RAW)
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (optlen < sizeof(val))
return -EINVAL;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
- po->has_vnet_hdr = !!val;
- return 0;
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->has_vnet_hdr = !!val;
+ ret = 0;
+ }
+ release_sock(sk);
+ return ret;
}
case PACKET_TIMESTAMP:
{
@@ -3807,11 +3839,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
if (optlen != sizeof(val))
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
- po->tp_tx_has_off = !!val;
+
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->tp_tx_has_off = !!val;
+ ret = 0;
+ }
+ release_sock(sk);
return 0;
}
case PACKET_QDISC_BYPASS:
@@ -4072,12 +4110,11 @@ static int packet_ioctl(struct socket *sock, unsigned int cmd,
return 0;
}
-static __poll_t packet_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+static __poll_t packet_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
struct packet_sock *po = pkt_sk(sk);
- __poll_t mask = datagram_poll(file, sock, wait);
+ __poll_t mask = datagram_poll_mask(sock, events);
spin_lock_bh(&sk->sk_receive_queue.lock);
if (po->rx_ring.pg_vec) {
@@ -4208,8 +4245,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
/* Added to avoid minimal code churn */
struct tpacket_req *req = &req_u->req;
- lock_sock(sk);
-
rb = tx_ring ? &po->tx_ring : &po->rx_ring;
rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
@@ -4347,7 +4382,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
if (pg_vec)
free_pg_vec(pg_vec, order, req->tp_block_nr);
out:
- release_sock(sk);
return err;
}
@@ -4422,7 +4456,7 @@ static const struct proto_ops packet_ops_spkt = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = packet_getname_spkt,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = packet_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
@@ -4443,7 +4477,7 @@ static const struct proto_ops packet_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = packet_getname,
- .poll = packet_poll,
+ .poll_mask = packet_poll_mask,
.ioctl = packet_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
@@ -4521,20 +4555,6 @@ static const struct seq_operations packet_seq_ops = {
.stop = packet_seq_stop,
.show = packet_seq_show,
};
-
-static int packet_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &packet_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-static const struct file_operations packet_seq_fops = {
- .open = packet_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
#endif
static int __net_init packet_net_init(struct net *net)
@@ -4542,7 +4562,8 @@ static int __net_init packet_net_init(struct net *net)
mutex_init(&net->packet.sklist_lock);
INIT_HLIST_HEAD(&net->packet.sklist);
- if (!proc_create("packet", 0, net->proc_net, &packet_seq_fops))
+ if (!proc_create_net("packet", 0, net->proc_net, &packet_seq_ops,
+ sizeof(struct seq_net_private)))
return -ENOMEM;
return 0;
diff --git a/net/packet/internal.h b/net/packet/internal.h
index a1d2b23..3bb7c5f 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -112,10 +112,12 @@ struct packet_sock {
int copy_thresh;
spinlock_t bind_lock;
struct mutex pg_vec_lock;
- unsigned int running:1, /* prot_hook is attached*/
- auxdata:1,
+ unsigned int running; /* bind_lock must be held */
+ unsigned int auxdata:1, /* writer must hold sock lock */
origdev:1,
- has_vnet_hdr:1;
+ has_vnet_hdr:1,
+ tp_loss:1,
+ tp_tx_has_off:1;
int pressure;
int ifindex; /* bound device */
__be16 num;
@@ -125,8 +127,6 @@ struct packet_sock {
enum tpacket_versions tp_version;
unsigned int tp_hdrlen;
unsigned int tp_reserve;
- unsigned int tp_loss:1;
- unsigned int tp_tx_has_off:1;
unsigned int tp_tstamp;
struct net_device __rcu *cached_dev;
int (*xmit)(struct sk_buff *skb);
diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c
index 7778751..6cb4f60 100644
--- a/net/phonet/pn_dev.c
+++ b/net/phonet/pn_dev.c
@@ -320,7 +320,8 @@ static int __net_init phonet_init_net(struct net *net)
{
struct phonet_net *pnn = phonet_pernet(net);
- if (!proc_create("phonet", 0, net->proc_net, &pn_sock_seq_fops))
+ if (!proc_create_net("phonet", 0, net->proc_net, &pn_sock_seq_ops,
+ sizeof(struct seq_net_private)))
return -ENOMEM;
INIT_LIST_HEAD(&pnn->pndevs.list);
@@ -351,7 +352,8 @@ int __init phonet_device_init(void)
if (err)
return err;
- proc_create("pnresource", 0, init_net.proc_net, &pn_res_seq_fops);
+ proc_create_net("pnresource", 0, init_net.proc_net, &pn_res_seq_ops,
+ sizeof(struct seq_net_private));
register_netdevice_notifier(&phonet_device_notifier);
err = phonet_netlink_register();
if (err)
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index f9b40e6..c295c4e 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -340,15 +340,12 @@ static int pn_socket_getname(struct socket *sock, struct sockaddr *addr,
return sizeof(struct sockaddr_pn);
}
-static __poll_t pn_socket_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+static __poll_t pn_socket_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
struct pep_sock *pn = pep_sk(sk);
__poll_t mask = 0;
- poll_wait(file, sk_sleep(sk), wait);
-
if (sk->sk_state == TCP_CLOSE)
return EPOLLERR;
if (!skb_queue_empty(&sk->sk_receive_queue))
@@ -448,7 +445,7 @@ const struct proto_ops phonet_dgram_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = pn_socket_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = pn_socket_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
@@ -473,7 +470,7 @@ const struct proto_ops phonet_stream_ops = {
.socketpair = sock_no_socketpair,
.accept = pn_socket_accept,
.getname = pn_socket_getname,
- .poll = pn_socket_poll,
+ .poll_mask = pn_socket_poll_mask,
.ioctl = pn_socket_ioctl,
.listen = pn_socket_listen,
.shutdown = sock_no_shutdown,
@@ -620,25 +617,12 @@ static int pn_sock_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static const struct seq_operations pn_sock_seq_ops = {
+const struct seq_operations pn_sock_seq_ops = {
.start = pn_sock_seq_start,
.next = pn_sock_seq_next,
.stop = pn_sock_seq_stop,
.show = pn_sock_seq_show,
};
-
-static int pn_sock_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &pn_sock_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-const struct file_operations pn_sock_seq_fops = {
- .open = pn_sock_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
#endif
static struct {
@@ -802,23 +786,10 @@ static int pn_res_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static const struct seq_operations pn_res_seq_ops = {
+const struct seq_operations pn_res_seq_ops = {
.start = pn_res_seq_start,
.next = pn_res_seq_next,
.stop = pn_res_seq_stop,
.show = pn_res_seq_show,
};
-
-static int pn_res_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &pn_res_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-const struct file_operations pn_res_seq_fops = {
- .open = pn_res_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
#endif
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index b33e5ae..1b5025e 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -1023,7 +1023,7 @@ static const struct proto_ops qrtr_proto_ops = {
.recvmsg = qrtr_recvmsg,
.getname = qrtr_getname,
.ioctl = qrtr_ioctl,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
.getsockopt = sock_no_getsockopt,
@@ -1135,3 +1135,4 @@ module_exit(qrtr_proto_fini);
MODULE_DESCRIPTION("Qualcomm IPC-router driver");
MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_NETPROTO(PF_QIPCRTR);
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index eea1d86..13b38ad 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -547,7 +547,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
rdsdebug("conn %p pd %p cq %p %p\n", conn, ic->i_pd,
ic->i_send_cq, ic->i_recv_cq);
- return ret;
+ goto out;
sends_out:
vfree(ic->i_sends);
@@ -572,6 +572,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
ic->i_send_cq = NULL;
rds_ibdev_out:
rds_ib_remove_conn(rds_ibdev, conn);
+out:
rds_ib_dev_put(rds_ibdev);
return ret;
diff --git a/net/rds/recv.c b/net/rds/recv.c
index de50e21..dc67458 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -558,6 +558,7 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg,
struct rds_cmsg_rx_trace t;
int i, j;
+ memset(&t, 0, sizeof(t));
inc->i_rx_lat_trace[RDS_MSG_RX_CMSG] = local_clock();
t.rx_traces = rs->rs_rx_traces;
for (i = 0; i < rs->rs_rx_traces; i++) {
diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c
index 41bd496..00192a9 100644
--- a/net/rfkill/rfkill-gpio.c
+++ b/net/rfkill/rfkill-gpio.c
@@ -137,13 +137,18 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
ret = rfkill_register(rfkill->rfkill_dev);
if (ret < 0)
- return ret;
+ goto err_destroy;
platform_set_drvdata(pdev, rfkill);
dev_info(&pdev->dev, "%s device registered.\n", rfkill->name);
return 0;
+
+err_destroy:
+ rfkill_destroy(rfkill->rfkill_dev);
+
+ return ret;
}
static int rfkill_gpio_remove(struct platform_device *pdev)
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 9ff5e0a..5b73fea 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1453,18 +1453,6 @@ static const struct seq_operations rose_info_seqops = {
.stop = rose_info_stop,
.show = rose_info_show,
};
-
-static int rose_info_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &rose_info_seqops);
-}
-
-static const struct file_operations rose_info_fops = {
- .open = rose_info_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
#endif /* CONFIG_PROC_FS */
static const struct net_proto_family rose_family_ops = {
@@ -1482,7 +1470,7 @@ static const struct proto_ops rose_proto_ops = {
.socketpair = sock_no_socketpair,
.accept = rose_accept,
.getname = rose_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = rose_ioctl,
.listen = rose_listen,
.shutdown = sock_no_shutdown,
@@ -1567,13 +1555,13 @@ static int __init rose_proto_init(void)
rose_add_loopback_neigh();
- proc_create("rose", 0444, init_net.proc_net, &rose_info_fops);
- proc_create("rose_neigh", 0444, init_net.proc_net,
- &rose_neigh_fops);
- proc_create("rose_nodes", 0444, init_net.proc_net,
- &rose_nodes_fops);
- proc_create("rose_routes", 0444, init_net.proc_net,
- &rose_routes_fops);
+ proc_create_seq("rose", 0444, init_net.proc_net, &rose_info_seqops);
+ proc_create_seq("rose_neigh", 0444, init_net.proc_net,
+ &rose_neigh_seqops);
+ proc_create_seq("rose_nodes", 0444, init_net.proc_net,
+ &rose_node_seqops);
+ proc_create_seq("rose_routes", 0444, init_net.proc_net,
+ &rose_route_seqops);
out:
return rc;
fail:
diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
index 178619d..77e9f85 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -1143,25 +1143,13 @@ static int rose_node_show(struct seq_file *seq, void *v)
return 0;
}
-static const struct seq_operations rose_node_seqops = {
+const struct seq_operations rose_node_seqops = {
.start = rose_node_start,
.next = rose_node_next,
.stop = rose_node_stop,
.show = rose_node_show,
};
-static int rose_nodes_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &rose_node_seqops);
-}
-
-const struct file_operations rose_nodes_fops = {
- .open = rose_nodes_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
static void *rose_neigh_start(struct seq_file *seq, loff_t *pos)
__acquires(rose_neigh_list_lock)
{
@@ -1226,26 +1214,13 @@ static int rose_neigh_show(struct seq_file *seq, void *v)
}
-static const struct seq_operations rose_neigh_seqops = {
+const struct seq_operations rose_neigh_seqops = {
.start = rose_neigh_start,
.next = rose_neigh_next,
.stop = rose_neigh_stop,
.show = rose_neigh_show,
};
-static int rose_neigh_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &rose_neigh_seqops);
-}
-
-const struct file_operations rose_neigh_fops = {
- .open = rose_neigh_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-
static void *rose_route_start(struct seq_file *seq, loff_t *pos)
__acquires(rose_route_list_lock)
{
@@ -1311,25 +1286,12 @@ static int rose_route_show(struct seq_file *seq, void *v)
return 0;
}
-static const struct seq_operations rose_route_seqops = {
+struct seq_operations rose_route_seqops = {
.start = rose_route_start,
.next = rose_route_next,
.stop = rose_route_stop,
.show = rose_route_show,
};
-
-static int rose_route_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &rose_route_seqops);
-}
-
-const struct file_operations rose_routes_fops = {
- .open = rose_route_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
#endif /* CONFIG_PROC_FS */
/*
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 9a2c8e7..3b1ac93 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -313,7 +313,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
memset(&cp, 0, sizeof(cp));
cp.local = rx->local;
cp.key = key;
- cp.security_level = 0;
+ cp.security_level = rx->min_sec_level;
cp.exclusive = false;
cp.upgrade = upgrade;
cp.service_id = srx->srx_service;
@@ -734,15 +734,11 @@ static int rxrpc_getsockopt(struct socket *sock, int level, int optname,
/*
* permit an RxRPC socket to be polled
*/
-static __poll_t rxrpc_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+static __poll_t rxrpc_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
struct rxrpc_sock *rx = rxrpc_sk(sk);
- __poll_t mask;
-
- sock_poll_wait(file, sk_sleep(sk), wait);
- mask = 0;
+ __poll_t mask = 0;
/* the socket is readable if there are any messages waiting on the Rx
* queue */
@@ -949,7 +945,7 @@ static const struct proto_ops rxrpc_rpc_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll = rxrpc_poll,
+ .poll_mask = rxrpc_poll_mask,
.ioctl = sock_no_ioctl,
.listen = rxrpc_listen,
.shutdown = rxrpc_shutdown,
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 90d7079..29923ec 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -476,6 +476,7 @@ enum rxrpc_call_flag {
RXRPC_CALL_SEND_PING, /* A ping will need to be sent */
RXRPC_CALL_PINGING, /* Ping in process */
RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */
+ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */
};
/*
@@ -1050,8 +1051,8 @@ void __rxrpc_queue_peer_error(struct rxrpc_peer *);
/*
* proc.c
*/
-extern const struct file_operations rxrpc_call_seq_fops;
-extern const struct file_operations rxrpc_connection_seq_fops;
+extern const struct seq_operations rxrpc_call_seq_ops;
+extern const struct seq_operations rxrpc_connection_seq_ops;
/*
* recvmsg.c
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index c717152..1350f1b 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -40,7 +40,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
} __attribute__((packed)) pkt;
struct rxrpc_ackinfo ack_info;
size_t len;
- int ioc;
+ int ret, ioc;
u32 serial, mtu, call_id, padding;
_enter("%d", conn->debug_id);
@@ -135,10 +135,13 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
break;
}
- kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len);
+ ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len);
conn->params.peer->last_tx_at = ktime_get_real();
+ if (ret < 0)
+ trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
+ rxrpc_tx_fail_call_final_resend);
+
_leave("");
- return;
}
/*
@@ -236,6 +239,8 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
if (ret < 0) {
+ trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
+ rxrpc_tx_fail_conn_abort);
_debug("sendmsg failed: %d", ret);
return -EAGAIN;
}
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 0410d22..b5fd638 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -971,7 +971,7 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call,
if (timo) {
unsigned long now = jiffies, expect_rx_by;
- expect_rx_by = jiffies + timo;
+ expect_rx_by = now + timo;
WRITE_ONCE(call->expect_rx_by, expect_rx_by);
rxrpc_reduce_call_timer(call, expect_rx_by, now,
rxrpc_timer_set_for_normal);
diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c
index 93b5d91..8325f1b 100644
--- a/net/rxrpc/local_event.c
+++ b/net/rxrpc/local_event.c
@@ -71,7 +71,8 @@ static void rxrpc_send_version_request(struct rxrpc_local *local,
ret = kernel_sendmsg(local->socket, &msg, iov, 2, len);
if (ret < 0)
- _debug("sendmsg failed: %d", ret);
+ trace_rxrpc_tx_fail(local->debug_id, 0, ret,
+ rxrpc_tx_fail_version_reply);
_leave("");
}
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 8b54e95..b493e6b 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -134,22 +134,49 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
}
}
- /* we want to receive ICMP errors */
- opt = 1;
- ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
- (char *) &opt, sizeof(opt));
- if (ret < 0) {
- _debug("setsockopt failed");
- goto error;
- }
+ switch (local->srx.transport.family) {
+ case AF_INET:
+ /* we want to receive ICMP errors */
+ opt = 1;
+ ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
+ (char *) &opt, sizeof(opt));
+ if (ret < 0) {
+ _debug("setsockopt failed");
+ goto error;
+ }
- /* we want to set the don't fragment bit */
- opt = IP_PMTUDISC_DO;
- ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
- (char *) &opt, sizeof(opt));
- if (ret < 0) {
- _debug("setsockopt failed");
- goto error;
+ /* we want to set the don't fragment bit */
+ opt = IP_PMTUDISC_DO;
+ ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
+ (char *) &opt, sizeof(opt));
+ if (ret < 0) {
+ _debug("setsockopt failed");
+ goto error;
+ }
+ break;
+
+ case AF_INET6:
+ /* we want to receive ICMP errors */
+ opt = 1;
+ ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR,
+ (char *) &opt, sizeof(opt));
+ if (ret < 0) {
+ _debug("setsockopt failed");
+ goto error;
+ }
+
+ /* we want to set the don't fragment bit */
+ opt = IPV6_PMTUDISC_DO;
+ ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER,
+ (char *) &opt, sizeof(opt));
+ if (ret < 0) {
+ _debug("setsockopt failed");
+ goto error;
+ }
+ break;
+
+ default:
+ BUG();
}
/* set the socket up */
diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
index c7a023f..5d6a773d 100644
--- a/net/rxrpc/net_ns.c
+++ b/net/rxrpc/net_ns.c
@@ -97,8 +97,11 @@ static __net_init int rxrpc_init_net(struct net *net)
if (!rxnet->proc_net)
goto err_proc;
- proc_create("calls", 0444, rxnet->proc_net, &rxrpc_call_seq_fops);
- proc_create("conns", 0444, rxnet->proc_net, &rxrpc_connection_seq_fops);
+ proc_create_net("calls", 0444, rxnet->proc_net, &rxrpc_call_seq_ops,
+ sizeof(struct seq_net_private));
+ proc_create_net("conns", 0444, rxnet->proc_net,
+ &rxrpc_connection_seq_ops,
+ sizeof(struct seq_net_private));
return 0;
err_proc:
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 7f1fc04..f03de1c 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -210,6 +210,9 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
if (ping)
call->ping_time = now;
conn->params.peer->last_tx_at = ktime_get_real();
+ if (ret < 0)
+ trace_rxrpc_tx_fail(call->debug_id, serial, ret,
+ rxrpc_tx_fail_call_ack);
if (call->state < RXRPC_CALL_COMPLETE) {
if (ret < 0) {
@@ -294,6 +297,10 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
ret = kernel_sendmsg(conn->params.local->socket,
&msg, iov, 1, sizeof(pkt));
conn->params.peer->last_tx_at = ktime_get_real();
+ if (ret < 0)
+ trace_rxrpc_tx_fail(call->debug_id, serial, ret,
+ rxrpc_tx_fail_call_abort);
+
rxrpc_put_connection(conn);
return ret;
@@ -387,6 +394,9 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
conn->params.peer->last_tx_at = ktime_get_real();
up_read(&conn->params.local->defrag_sem);
+ if (ret < 0)
+ trace_rxrpc_tx_fail(call->debug_id, serial, ret,
+ rxrpc_tx_fail_call_data_nofrag);
if (ret == -EMSGSIZE)
goto send_fragmentable;
@@ -414,6 +424,17 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
rxrpc_timer_set_for_lost_ack);
}
}
+
+ if (sp->hdr.seq == 1 &&
+ !test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER,
+ &call->flags)) {
+ unsigned long nowj = jiffies, expect_rx_by;
+
+ expect_rx_by = nowj + call->next_rx_timo;
+ WRITE_ONCE(call->expect_rx_by, expect_rx_by);
+ rxrpc_reduce_call_timer(call, expect_rx_by, nowj,
+ rxrpc_timer_set_for_normal);
+ }
}
rxrpc_set_keepalive(call);
@@ -465,6 +486,10 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
#endif
}
+ if (ret < 0)
+ trace_rxrpc_tx_fail(call->debug_id, serial, ret,
+ rxrpc_tx_fail_call_data_frag);
+
up_write(&conn->params.local->defrag_sem);
goto done;
}
@@ -482,6 +507,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local)
struct kvec iov[2];
size_t size;
__be32 code;
+ int ret;
_enter("%d", local->debug_id);
@@ -516,7 +542,10 @@ void rxrpc_reject_packets(struct rxrpc_local *local)
whdr.flags ^= RXRPC_CLIENT_INITIATED;
whdr.flags &= RXRPC_CLIENT_INITIATED;
- kernel_sendmsg(local->socket, &msg, iov, 2, size);
+ ret = kernel_sendmsg(local->socket, &msg, iov, 2, size);
+ if (ret < 0)
+ trace_rxrpc_tx_fail(local->debug_id, 0, ret,
+ rxrpc_tx_fail_reject);
}
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
@@ -567,7 +596,8 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer)
ret = kernel_sendmsg(peer->local->socket, &msg, iov, 2, len);
if (ret < 0)
- _debug("sendmsg failed: %d", ret);
+ trace_rxrpc_tx_fail(peer->debug_id, 0, ret,
+ rxrpc_tx_fail_version_keepalive);
peer->last_tx_at = ktime_get_real();
_leave("");
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index 78c2f95..0ed8b65 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -28,39 +28,39 @@ static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *);
* Find the peer associated with an ICMP packet.
*/
static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
- const struct sk_buff *skb)
+ const struct sk_buff *skb,
+ struct sockaddr_rxrpc *srx)
{
struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
- struct sockaddr_rxrpc srx;
_enter("");
- memset(&srx, 0, sizeof(srx));
- srx.transport_type = local->srx.transport_type;
- srx.transport_len = local->srx.transport_len;
- srx.transport.family = local->srx.transport.family;
+ memset(srx, 0, sizeof(*srx));
+ srx->transport_type = local->srx.transport_type;
+ srx->transport_len = local->srx.transport_len;
+ srx->transport.family = local->srx.transport.family;
/* Can we see an ICMP4 packet on an ICMP6 listening socket? and vice
* versa?
*/
- switch (srx.transport.family) {
+ switch (srx->transport.family) {
case AF_INET:
- srx.transport.sin.sin_port = serr->port;
+ srx->transport.sin.sin_port = serr->port;
switch (serr->ee.ee_origin) {
case SO_EE_ORIGIN_ICMP:
_net("Rx ICMP");
- memcpy(&srx.transport.sin.sin_addr,
+ memcpy(&srx->transport.sin.sin_addr,
skb_network_header(skb) + serr->addr_offset,
sizeof(struct in_addr));
break;
case SO_EE_ORIGIN_ICMP6:
_net("Rx ICMP6 on v4 sock");
- memcpy(&srx.transport.sin.sin_addr,
+ memcpy(&srx->transport.sin.sin_addr,
skb_network_header(skb) + serr->addr_offset + 12,
sizeof(struct in_addr));
break;
default:
- memcpy(&srx.transport.sin.sin_addr, &ip_hdr(skb)->saddr,
+ memcpy(&srx->transport.sin.sin_addr, &ip_hdr(skb)->saddr,
sizeof(struct in_addr));
break;
}
@@ -68,25 +68,25 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
#ifdef CONFIG_AF_RXRPC_IPV6
case AF_INET6:
- srx.transport.sin6.sin6_port = serr->port;
+ srx->transport.sin6.sin6_port = serr->port;
switch (serr->ee.ee_origin) {
case SO_EE_ORIGIN_ICMP6:
_net("Rx ICMP6");
- memcpy(&srx.transport.sin6.sin6_addr,
+ memcpy(&srx->transport.sin6.sin6_addr,
skb_network_header(skb) + serr->addr_offset,
sizeof(struct in6_addr));
break;
case SO_EE_ORIGIN_ICMP:
_net("Rx ICMP on v6 sock");
- srx.transport.sin6.sin6_addr.s6_addr32[0] = 0;
- srx.transport.sin6.sin6_addr.s6_addr32[1] = 0;
- srx.transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
- memcpy(srx.transport.sin6.sin6_addr.s6_addr + 12,
+ srx->transport.sin6.sin6_addr.s6_addr32[0] = 0;
+ srx->transport.sin6.sin6_addr.s6_addr32[1] = 0;
+ srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
+ memcpy(srx->transport.sin6.sin6_addr.s6_addr + 12,
skb_network_header(skb) + serr->addr_offset,
sizeof(struct in_addr));
break;
default:
- memcpy(&srx.transport.sin6.sin6_addr,
+ memcpy(&srx->transport.sin6.sin6_addr,
&ipv6_hdr(skb)->saddr,
sizeof(struct in6_addr));
break;
@@ -98,7 +98,7 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
BUG();
}
- return rxrpc_lookup_peer_rcu(local, &srx);
+ return rxrpc_lookup_peer_rcu(local, srx);
}
/*
@@ -146,6 +146,7 @@ static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, struct sock_exterr_skb *se
void rxrpc_error_report(struct sock *sk)
{
struct sock_exterr_skb *serr;
+ struct sockaddr_rxrpc srx;
struct rxrpc_local *local = sk->sk_user_data;
struct rxrpc_peer *peer;
struct sk_buff *skb;
@@ -166,7 +167,7 @@ void rxrpc_error_report(struct sock *sk)
}
rcu_read_lock();
- peer = rxrpc_lookup_peer_icmp_rcu(local, skb);
+ peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx);
if (peer && !rxrpc_get_peer_maybe(peer))
peer = NULL;
if (!peer) {
@@ -176,6 +177,8 @@ void rxrpc_error_report(struct sock *sk)
return;
}
+ trace_rxrpc_rx_icmp(peer, &serr->ee, &srx);
+
if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP &&
serr->ee.ee_type == ICMP_DEST_UNREACH &&
serr->ee.ee_code == ICMP_FRAG_NEEDED)) {
@@ -209,9 +212,6 @@ static void rxrpc_store_error(struct rxrpc_peer *peer,
ee = &serr->ee;
- _net("Rx Error o=%d t=%d c=%d e=%d",
- ee->ee_origin, ee->ee_type, ee->ee_code, ee->ee_errno);
-
err = ee->ee_errno;
switch (ee->ee_origin) {
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index 7e45db0..d9fca8c 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -115,26 +115,13 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static const struct seq_operations rxrpc_call_seq_ops = {
+const struct seq_operations rxrpc_call_seq_ops = {
.start = rxrpc_call_seq_start,
.next = rxrpc_call_seq_next,
.stop = rxrpc_call_seq_stop,
.show = rxrpc_call_seq_show,
};
-static int rxrpc_call_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &rxrpc_call_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-const struct file_operations rxrpc_call_seq_fops = {
- .open = rxrpc_call_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
/*
* generate a list of extant virtual connections in /proc/net/rxrpc_conns
*/
@@ -207,23 +194,9 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static const struct seq_operations rxrpc_connection_seq_ops = {
+const struct seq_operations rxrpc_connection_seq_ops = {
.start = rxrpc_connection_seq_start,
.next = rxrpc_connection_seq_next,
.stop = rxrpc_connection_seq_stop,
.show = rxrpc_connection_seq_show,
};
-
-
-static int rxrpc_connection_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &rxrpc_connection_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-const struct file_operations rxrpc_connection_seq_fops = {
- .open = rxrpc_connection_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 588fea0..6c0ae27 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -664,7 +664,8 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
if (ret < 0) {
- _debug("sendmsg failed: %d", ret);
+ trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
+ rxrpc_tx_fail_conn_challenge);
return -EAGAIN;
}
@@ -719,7 +720,8 @@ static int rxkad_send_response(struct rxrpc_connection *conn,
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 3, len);
if (ret < 0) {
- _debug("sendmsg failed: %d", ret);
+ trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
+ rxrpc_tx_fail_conn_response);
return -EAGAIN;
}
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 206e802..be01f9c 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -223,6 +223,15 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
ret = rxrpc_send_data_packet(call, skb, false);
if (ret < 0) {
+ switch (ret) {
+ case -ENETUNREACH:
+ case -EHOSTUNREACH:
+ case -ECONNREFUSED:
+ rxrpc_set_call_completion(call,
+ RXRPC_CALL_LOCAL_ERROR,
+ 0, ret);
+ goto out;
+ }
_debug("need instant resend %d", ret);
rxrpc_instant_resend(call, ix);
} else {
@@ -241,6 +250,7 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
rxrpc_timer_set_for_send);
}
+out:
rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
_leave("");
}
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index a5994cf..8527cfd 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -652,7 +652,7 @@ static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife,
}
}
- return 0;
+ return -ENOENT;
}
static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
@@ -682,7 +682,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
u16 mtype;
u16 dlen;
- curr_data = ife_tlv_meta_decode(tlv_data, &mtype, &dlen, NULL);
+ curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype,
+ &dlen, NULL);
+ if (!curr_data) {
+ qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
+ return TC_ACT_SHOT;
+ }
if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) {
/* abuse overlimits to count when we receive metadata
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index ddf69fc..6138d1d7 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -121,7 +121,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
return 0;
if (!flags) {
- tcf_idr_release(*a, bind);
+ if (exists)
+ tcf_idr_release(*a, bind);
return -EINVAL;
}
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index bbcbdce..ad050d7 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -131,8 +131,11 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
if (exists && bind)
return 0;
- if (!lflags)
+ if (!lflags) {
+ if (exists)
+ tcf_idr_release(*a, bind);
return -EINVAL;
+ }
if (!exists) {
ret = tcf_idr_create(tn, parm->index, est, a,
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 8536046..1fb39e1 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -161,6 +161,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
case htons(ETH_P_8021AD):
break;
default:
+ if (exists)
+ tcf_idr_release(*a, bind);
return -EPROTONOSUPPORT;
}
} else {
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index b66754f..a57e112 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -152,8 +152,8 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol,
NL_SET_ERR_MSG(extack, "TC classifier not found");
err = -ENOENT;
}
- goto errout;
#endif
+ goto errout;
}
tp->classify = tp->ops->classify;
tp->protocol = protocol;
@@ -1588,7 +1588,7 @@ int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts,
return ret;
ok_count = ret;
- if (!exts)
+ if (!exts || ok_count)
return ok_count;
ret = tc_exts_setup_cb_egdev_call(exts, type, type_data, err_stop);
if (ret < 0)
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index d964e60..c79f6e7 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -977,7 +977,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
return 0;
errout_idr:
- if (fnew->handle)
+ if (!fold)
idr_remove(&head->handle_idr, fnew->handle);
errout:
tcf_exts_destroy(&fnew->exts);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 106dae7e..54eca68 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -2092,23 +2092,11 @@ static int psched_show(struct seq_file *seq, void *v)
return 0;
}
-static int psched_open(struct inode *inode, struct file *file)
-{
- return single_open(file, psched_show, NULL);
-}
-
-static const struct file_operations psched_fops = {
- .open = psched_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int __net_init psched_net_init(struct net *net)
{
struct proc_dir_entry *e;
- e = proc_create("psched", 0, net->proc_net, &psched_fops);
+ e = proc_create_single("psched", 0, net->proc_net, psched_show);
if (e == NULL)
return -ENOMEM;
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index a366e4c..4808713 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -128,6 +128,28 @@ static bool fq_flow_is_detached(const struct fq_flow *f)
return f->next == &detached;
}
+static bool fq_flow_is_throttled(const struct fq_flow *f)
+{
+ return f->next == &throttled;
+}
+
+static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow)
+{
+ if (head->first)
+ head->last->next = flow;
+ else
+ head->first = flow;
+ head->last = flow;
+ flow->next = NULL;
+}
+
+static void fq_flow_unset_throttled(struct fq_sched_data *q, struct fq_flow *f)
+{
+ rb_erase(&f->rate_node, &q->delayed);
+ q->throttled_flows--;
+ fq_flow_add_tail(&q->old_flows, f);
+}
+
static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f)
{
struct rb_node **p = &q->delayed.rb_node, *parent = NULL;
@@ -155,15 +177,6 @@ static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f)
static struct kmem_cache *fq_flow_cachep __read_mostly;
-static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow)
-{
- if (head->first)
- head->last->next = flow;
- else
- head->first = flow;
- head->last = flow;
- flow->next = NULL;
-}
/* limit number of collected flows per round */
#define FQ_GC_MAX 8
@@ -267,6 +280,8 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
f->socket_hash != sk->sk_hash)) {
f->credit = q->initial_quantum;
f->socket_hash = sk->sk_hash;
+ if (fq_flow_is_throttled(f))
+ fq_flow_unset_throttled(q, f);
f->time_next_packet = 0ULL;
}
return f;
@@ -438,9 +453,7 @@ static void fq_check_throttled(struct fq_sched_data *q, u64 now)
q->time_next_delayed_flow = f->time_next_packet;
break;
}
- rb_erase(p, &q->delayed);
- q->throttled_flows--;
- fq_flow_add_tail(&q->old_flows, f);
+ fq_flow_unset_throttled(q, f);
}
}
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 16644b3..56c181c 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -222,10 +222,11 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt,
extack);
if (IS_ERR(child))
return PTR_ERR(child);
+
+ /* child is fifo, no need to check for noop_qdisc */
+ qdisc_hash_add(child, true);
}
- if (child != &noop_qdisc)
- qdisc_hash_add(child, true);
sch_tree_lock(sch);
q->flags = ctl->flags;
q->limit = ctl->limit;
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 03225a8..6f74a42 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -383,6 +383,9 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
err = PTR_ERR(child);
goto done;
}
+
+ /* child is fifo, no need to check for noop_qdisc */
+ qdisc_hash_add(child, true);
}
sch_tree_lock(sch);
@@ -391,8 +394,6 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
q->qdisc->qstats.backlog);
qdisc_destroy(q->qdisc);
q->qdisc = child;
- if (child != &noop_qdisc)
- qdisc_hash_add(child, true);
}
q->limit = qopt->limit;
if (tb[TCA_TBF_PBURST])
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 837806d..a47179d 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1024,8 +1024,9 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
struct sctp_endpoint *ep;
struct sctp_chunk *chunk;
struct sctp_inq *inqueue;
- int state;
+ int first_time = 1; /* is this the first time through the loop */
int error = 0;
+ int state;
/* The association should be held so we should be safe. */
ep = asoc->ep;
@@ -1036,6 +1037,30 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
state = asoc->state;
subtype = SCTP_ST_CHUNK(chunk->chunk_hdr->type);
+ /* If the first chunk in the packet is AUTH, do special
+ * processing specified in Section 6.3 of SCTP-AUTH spec
+ */
+ if (first_time && subtype.chunk == SCTP_CID_AUTH) {
+ struct sctp_chunkhdr *next_hdr;
+
+ next_hdr = sctp_inq_peek(inqueue);
+ if (!next_hdr)
+ goto normal;
+
+ /* If the next chunk is COOKIE-ECHO, skip the AUTH
+ * chunk while saving a pointer to it so we can do
+ * Authentication later (during cookie-echo
+ * processing).
+ */
+ if (next_hdr->type == SCTP_CID_COOKIE_ECHO) {
+ chunk->auth_chunk = skb_clone(chunk->skb,
+ GFP_ATOMIC);
+ chunk->auth = 1;
+ continue;
+ }
+ }
+
+normal:
/* SCTP-AUTH, Section 6.3:
* The receiver has a list of chunk types which it expects
* to be received only after an AUTH-chunk. This list has
@@ -1074,6 +1099,9 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
/* If there is an error on chunk, discard this packet. */
if (error && chunk)
chunk->pdiscard = 1;
+
+ if (first_time)
+ first_time = 0;
}
sctp_association_put(asoc);
}
diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index 23ebc53..eb93ffe 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -217,7 +217,7 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
skb_pull(chunk->skb, sizeof(*ch));
chunk->subh.v = NULL; /* Subheader is no longer valid. */
- if (chunk->chunk_end + sizeof(*ch) < skb_tail_pointer(chunk->skb)) {
+ if (chunk->chunk_end + sizeof(*ch) <= skb_tail_pointer(chunk->skb)) {
/* This is not a singleton */
chunk->singleton = 0;
} else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) {
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 31083b5..7339918 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -556,44 +556,47 @@ static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr,
addr->v6.sin6_scope_id = 0;
}
+static int __sctp_v6_cmp_addr(const union sctp_addr *addr1,
+ const union sctp_addr *addr2)
+{
+ if (addr1->sa.sa_family != addr2->sa.sa_family) {
+ if (addr1->sa.sa_family == AF_INET &&
+ addr2->sa.sa_family == AF_INET6 &&
+ ipv6_addr_v4mapped(&addr2->v6.sin6_addr) &&
+ addr2->v6.sin6_addr.s6_addr32[3] ==
+ addr1->v4.sin_addr.s_addr)
+ return 1;
+
+ if (addr2->sa.sa_family == AF_INET &&
+ addr1->sa.sa_family == AF_INET6 &&
+ ipv6_addr_v4mapped(&addr1->v6.sin6_addr) &&
+ addr1->v6.sin6_addr.s6_addr32[3] ==
+ addr2->v4.sin_addr.s_addr)
+ return 1;
+
+ return 0;
+ }
+
+ if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr))
+ return 0;
+
+ /* If this is a linklocal address, compare the scope_id. */
+ if ((ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) &&
+ addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id &&
+ addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id)
+ return 0;
+
+ return 1;
+}
+
/* Compare addresses exactly.
* v4-mapped-v6 is also in consideration.
*/
static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
const union sctp_addr *addr2)
{
- if (addr1->sa.sa_family != addr2->sa.sa_family) {
- if (addr1->sa.sa_family == AF_INET &&
- addr2->sa.sa_family == AF_INET6 &&
- ipv6_addr_v4mapped(&addr2->v6.sin6_addr)) {
- if (addr2->v6.sin6_port == addr1->v4.sin_port &&
- addr2->v6.sin6_addr.s6_addr32[3] ==
- addr1->v4.sin_addr.s_addr)
- return 1;
- }
- if (addr2->sa.sa_family == AF_INET &&
- addr1->sa.sa_family == AF_INET6 &&
- ipv6_addr_v4mapped(&addr1->v6.sin6_addr)) {
- if (addr1->v6.sin6_port == addr2->v4.sin_port &&
- addr1->v6.sin6_addr.s6_addr32[3] ==
- addr2->v4.sin_addr.s_addr)
- return 1;
- }
- return 0;
- }
- if (addr1->v6.sin6_port != addr2->v6.sin6_port)
- return 0;
- if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr))
- return 0;
- /* If this is a linklocal address, compare the scope_id. */
- if (ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) {
- if (addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id &&
- (addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id)) {
- return 0;
- }
- }
-
- return 1;
+ return __sctp_v6_cmp_addr(addr1, addr2) &&
+ addr1->v6.sin6_port == addr2->v6.sin6_port;
}
/* Initialize addr struct to INADDR_ANY. */
@@ -875,8 +878,8 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1,
const union sctp_addr *addr2,
struct sctp_sock *opt)
{
- struct sctp_af *af1, *af2;
struct sock *sk = sctp_opt2sk(opt);
+ struct sctp_af *af1, *af2;
af1 = sctp_get_af_specific(addr1->sa.sa_family);
af2 = sctp_get_af_specific(addr2->sa.sa_family);
@@ -892,10 +895,10 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1,
if (sctp_is_any(sk, addr1) || sctp_is_any(sk, addr2))
return 1;
- if (addr1->sa.sa_family != addr2->sa.sa_family)
- return 0;
+ if (addr1->sa.sa_family == AF_INET && addr2->sa.sa_family == AF_INET)
+ return addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr;
- return af1->cmp_addr(addr1, addr2);
+ return __sctp_v6_cmp_addr(addr1, addr2);
}
/* Verify that the provided sockaddr looks bindable. Common verification,
@@ -1003,11 +1006,11 @@ static const struct proto_ops inet6_seqpacket_ops = {
.owner = THIS_MODULE,
.release = inet6_release,
.bind = inet6_bind,
- .connect = inet_dgram_connect,
+ .connect = sctp_inet_connect,
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = sctp_getname,
- .poll = sctp_poll,
+ .poll_mask = sctp_poll_mask,
.ioctl = inet6_ioctl,
.listen = sctp_inet_listen,
.shutdown = inet_shutdown,
diff --git a/net/sctp/objcnt.c b/net/sctp/objcnt.c
index fd2684a..a6179b2 100644
--- a/net/sctp/objcnt.c
+++ b/net/sctp/objcnt.c
@@ -108,25 +108,13 @@ static const struct seq_operations sctp_objcnt_seq_ops = {
.show = sctp_objcnt_seq_show,
};
-static int sctp_objcnt_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &sctp_objcnt_seq_ops);
-}
-
-static const struct file_operations sctp_objcnt_ops = {
- .open = sctp_objcnt_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
/* Initialize the objcount in the proc filesystem. */
void sctp_dbg_objcnt_init(struct net *net)
{
struct proc_dir_entry *ent;
- ent = proc_create("sctp_dbg_objcnt", 0,
- net->sctp.proc_net_sctp, &sctp_objcnt_ops);
+ ent = proc_create_seq("sctp_dbg_objcnt", 0,
+ net->sctp.proc_net_sctp, &sctp_objcnt_seq_ops);
if (!ent)
pr_warn("sctp_dbg_objcnt: Unable to create /proc entry.\n");
}
diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index 1d9ccc6..ef5c9a8 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -88,19 +88,6 @@ static int sctp_snmp_seq_show(struct seq_file *seq, void *v)
return 0;
}
-/* Initialize the seq file operations for 'snmp' object. */
-static int sctp_snmp_seq_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, sctp_snmp_seq_show);
-}
-
-static const struct file_operations sctp_snmp_seq_fops = {
- .open = sctp_snmp_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release_net,
-};
-
/* Dump local addresses of an association/endpoint. */
static void sctp_seq_dump_local_addrs(struct seq_file *seq, struct sctp_ep_common *epb)
{
@@ -225,21 +212,6 @@ static const struct seq_operations sctp_eps_ops = {
.show = sctp_eps_seq_show,
};
-
-/* Initialize the seq file operations for 'eps' object. */
-static int sctp_eps_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &sctp_eps_ops,
- sizeof(struct seq_net_private));
-}
-
-static const struct file_operations sctp_eps_seq_fops = {
- .open = sctp_eps_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
struct sctp_ht_iter {
struct seq_net_private p;
struct rhashtable_iter hti;
@@ -338,20 +310,6 @@ static const struct seq_operations sctp_assoc_ops = {
.show = sctp_assocs_seq_show,
};
-/* Initialize the seq file operations for 'assocs' object. */
-static int sctp_assocs_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &sctp_assoc_ops,
- sizeof(struct sctp_ht_iter));
-}
-
-static const struct file_operations sctp_assocs_seq_fops = {
- .open = sctp_assocs_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static int sctp_remaddr_seq_show(struct seq_file *seq, void *v)
{
struct sctp_association *assoc;
@@ -431,36 +389,23 @@ static const struct seq_operations sctp_remaddr_ops = {
.show = sctp_remaddr_seq_show,
};
-static int sctp_remaddr_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &sctp_remaddr_ops,
- sizeof(struct sctp_ht_iter));
-}
-
-static const struct file_operations sctp_remaddr_seq_fops = {
- .open = sctp_remaddr_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
/* Set up the proc fs entry for the SCTP protocol. */
int __net_init sctp_proc_init(struct net *net)
{
net->sctp.proc_net_sctp = proc_net_mkdir(net, "sctp", net->proc_net);
if (!net->sctp.proc_net_sctp)
return -ENOMEM;
- if (!proc_create("snmp", 0444, net->sctp.proc_net_sctp,
- &sctp_snmp_seq_fops))
+ if (!proc_create_net_single("snmp", 0444, net->sctp.proc_net_sctp,
+ sctp_snmp_seq_show, NULL))
goto cleanup;
- if (!proc_create("eps", 0444, net->sctp.proc_net_sctp,
- &sctp_eps_seq_fops))
+ if (!proc_create_net("eps", 0444, net->sctp.proc_net_sctp,
+ &sctp_eps_ops, sizeof(struct seq_net_private)))
goto cleanup;
- if (!proc_create("assocs", 0444, net->sctp.proc_net_sctp,
- &sctp_assocs_seq_fops))
+ if (!proc_create_net("assocs", 0444, net->sctp.proc_net_sctp,
+ &sctp_assoc_ops, sizeof(struct sctp_ht_iter)))
goto cleanup;
- if (!proc_create("remaddr", 0444, net->sctp.proc_net_sctp,
- &sctp_remaddr_seq_fops))
+ if (!proc_create_net("remaddr", 0444, net->sctp.proc_net_sctp,
+ &sctp_remaddr_ops, sizeof(struct sctp_ht_iter)))
goto cleanup;
return 0;
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index d685f84..11d9337 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1012,11 +1012,11 @@ static const struct proto_ops inet_seqpacket_ops = {
.owner = THIS_MODULE,
.release = inet_release, /* Needs to be wrapped... */
.bind = inet_bind,
- .connect = inet_dgram_connect,
+ .connect = sctp_inet_connect,
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = inet_getname, /* Semantics are different. */
- .poll = sctp_poll,
+ .poll_mask = sctp_poll_mask,
.ioctl = inet_ioctl,
.listen = sctp_inet_listen,
.shutdown = inet_shutdown, /* Looks harmless. */
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 5a4fb1d..e62addb 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1152,7 +1152,7 @@ struct sctp_chunk *sctp_make_violation_max_retrans(
const struct sctp_association *asoc,
const struct sctp_chunk *chunk)
{
- static const char error[] = "Association exceeded its max_retans count";
+ static const char error[] = "Association exceeded its max_retrans count";
size_t payload_len = sizeof(error) + sizeof(struct sctp_errhdr);
struct sctp_chunk *retval;
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index dd0594a..c9ae340 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -153,10 +153,7 @@ static enum sctp_disposition sctp_sf_violation_chunk(
struct sctp_cmd_seq *commands);
static enum sctp_ierror sctp_sf_authenticate(
- struct net *net,
- const struct sctp_endpoint *ep,
const struct sctp_association *asoc,
- const union sctp_subtype type,
struct sctp_chunk *chunk);
static enum sctp_disposition __sctp_sf_do_9_1_abort(
@@ -626,6 +623,38 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net,
return SCTP_DISPOSITION_CONSUME;
}
+static bool sctp_auth_chunk_verify(struct net *net, struct sctp_chunk *chunk,
+ const struct sctp_association *asoc)
+{
+ struct sctp_chunk auth;
+
+ if (!chunk->auth_chunk)
+ return true;
+
+ /* SCTP-AUTH: auth_chunk pointer is only set when the cookie-echo
+ * is supposed to be authenticated and we have to do delayed
+ * authentication. We've just recreated the association using
+ * the information in the cookie and now it's much easier to
+ * do the authentication.
+ */
+
+ /* Make sure that we and the peer are AUTH capable */
+ if (!net->sctp.auth_enable || !asoc->peer.auth_capable)
+ return false;
+
+ /* set-up our fake chunk so that we can process it */
+ auth.skb = chunk->auth_chunk;
+ auth.asoc = chunk->asoc;
+ auth.sctp_hdr = chunk->sctp_hdr;
+ auth.chunk_hdr = (struct sctp_chunkhdr *)
+ skb_push(chunk->auth_chunk,
+ sizeof(struct sctp_chunkhdr));
+ skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr));
+ auth.transport = chunk->transport;
+
+ return sctp_sf_authenticate(asoc, &auth) == SCTP_IERROR_NO_ERROR;
+}
+
/*
* Respond to a normal COOKIE ECHO chunk.
* We are the side that is being asked for an association.
@@ -763,37 +792,9 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
if (error)
goto nomem_init;
- /* SCTP-AUTH: auth_chunk pointer is only set when the cookie-echo
- * is supposed to be authenticated and we have to do delayed
- * authentication. We've just recreated the association using
- * the information in the cookie and now it's much easier to
- * do the authentication.
- */
- if (chunk->auth_chunk) {
- struct sctp_chunk auth;
- enum sctp_ierror ret;
-
- /* Make sure that we and the peer are AUTH capable */
- if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) {
- sctp_association_free(new_asoc);
- return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
- }
-
- /* set-up our fake chunk so that we can process it */
- auth.skb = chunk->auth_chunk;
- auth.asoc = chunk->asoc;
- auth.sctp_hdr = chunk->sctp_hdr;
- auth.chunk_hdr = (struct sctp_chunkhdr *)
- skb_push(chunk->auth_chunk,
- sizeof(struct sctp_chunkhdr));
- skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr));
- auth.transport = chunk->transport;
-
- ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth);
- if (ret != SCTP_IERROR_NO_ERROR) {
- sctp_association_free(new_asoc);
- return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
- }
+ if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) {
+ sctp_association_free(new_asoc);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
}
repl = sctp_make_cookie_ack(new_asoc, chunk);
@@ -1794,13 +1795,18 @@ static enum sctp_disposition sctp_sf_do_dupcook_a(
GFP_ATOMIC))
goto nomem;
+ if (sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC))
+ goto nomem;
+
+ if (!sctp_auth_chunk_verify(net, chunk, new_asoc))
+ return SCTP_DISPOSITION_DISCARD;
+
/* Make sure no new addresses are being added during the
* restart. Though this is a pretty complicated attack
* since you'd have to get inside the cookie.
*/
- if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) {
+ if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands))
return SCTP_DISPOSITION_CONSUME;
- }
/* If the endpoint is in the SHUTDOWN-ACK-SENT state and recognizes
* the peer has restarted (Action A), it MUST NOT setup a new
@@ -1906,6 +1912,12 @@ static enum sctp_disposition sctp_sf_do_dupcook_b(
GFP_ATOMIC))
goto nomem;
+ if (sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC))
+ goto nomem;
+
+ if (!sctp_auth_chunk_verify(net, chunk, new_asoc))
+ return SCTP_DISPOSITION_DISCARD;
+
/* Update the content of current association. */
sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc));
sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
@@ -2003,6 +2015,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_d(
* a COOKIE ACK.
*/
+ if (!sctp_auth_chunk_verify(net, chunk, asoc))
+ return SCTP_DISPOSITION_DISCARD;
+
/* Don't accidentally move back into established state. */
if (asoc->state < SCTP_STATE_ESTABLISHED) {
sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
@@ -2050,7 +2065,7 @@ static enum sctp_disposition sctp_sf_do_dupcook_d(
}
}
- repl = sctp_make_cookie_ack(new_asoc, chunk);
+ repl = sctp_make_cookie_ack(asoc, chunk);
if (!repl)
goto nomem;
@@ -4165,10 +4180,7 @@ enum sctp_disposition sctp_sf_eat_fwd_tsn_fast(
* The return value is the disposition of the chunk.
*/
static enum sctp_ierror sctp_sf_authenticate(
- struct net *net,
- const struct sctp_endpoint *ep,
const struct sctp_association *asoc,
- const union sctp_subtype type,
struct sctp_chunk *chunk)
{
struct sctp_shared_key *sh_key = NULL;
@@ -4269,7 +4281,7 @@ enum sctp_disposition sctp_sf_eat_auth(struct net *net,
commands);
auth_hdr = (struct sctp_authhdr *)chunk->skb->data;
- error = sctp_sf_authenticate(net, ep, asoc, type, chunk);
+ error = sctp_sf_authenticate(asoc, chunk);
switch (error) {
case SCTP_IERROR_AUTH_BAD_HMAC:
/* Generate the ERROR chunk and discard the rest
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 80835ac..bf74709 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1086,7 +1086,7 @@ static int sctp_setsockopt_bindx(struct sock *sk,
*/
static int __sctp_connect(struct sock *sk,
struct sockaddr *kaddrs,
- int addrs_size,
+ int addrs_size, int flags,
sctp_assoc_t *assoc_id)
{
struct net *net = sock_net(sk);
@@ -1104,7 +1104,6 @@ static int __sctp_connect(struct sock *sk,
union sctp_addr *sa_addr = NULL;
void *addr_buf;
unsigned short port;
- unsigned int f_flags = 0;
sp = sctp_sk(sk);
ep = sp->ep;
@@ -1254,13 +1253,7 @@ static int __sctp_connect(struct sock *sk,
sp->pf->to_sk_daddr(sa_addr, sk);
sk->sk_err = 0;
- /* in-kernel sockets don't generally have a file allocated to them
- * if all they do is call sock_create_kern().
- */
- if (sk->sk_socket->file)
- f_flags = sk->sk_socket->file->f_flags;
-
- timeo = sock_sndtimeo(sk, f_flags & O_NONBLOCK);
+ timeo = sock_sndtimeo(sk, flags & O_NONBLOCK);
if (assoc_id)
*assoc_id = asoc->assoc_id;
@@ -1348,7 +1341,7 @@ static int __sctp_setsockopt_connectx(struct sock *sk,
sctp_assoc_t *assoc_id)
{
struct sockaddr *kaddrs;
- int err = 0;
+ int err = 0, flags = 0;
pr_debug("%s: sk:%p addrs:%p addrs_size:%d\n",
__func__, sk, addrs, addrs_size);
@@ -1367,7 +1360,13 @@ static int __sctp_setsockopt_connectx(struct sock *sk,
if (err)
goto out_free;
- err = __sctp_connect(sk, kaddrs, addrs_size, assoc_id);
+ /* in-kernel sockets don't generally have a file allocated to them
+ * if all they do is call sock_create_kern().
+ */
+ if (sk->sk_socket->file)
+ flags = sk->sk_socket->file->f_flags;
+
+ err = __sctp_connect(sk, kaddrs, addrs_size, flags, assoc_id);
out_free:
kvfree(kaddrs);
@@ -4397,16 +4396,26 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
* len: the size of the address.
*/
static int sctp_connect(struct sock *sk, struct sockaddr *addr,
- int addr_len)
+ int addr_len, int flags)
{
- int err = 0;
+ struct inet_sock *inet = inet_sk(sk);
struct sctp_af *af;
+ int err = 0;
lock_sock(sk);
pr_debug("%s: sk:%p, sockaddr:%p, addr_len:%d\n", __func__, sk,
addr, addr_len);
+ /* We may need to bind the socket. */
+ if (!inet->inet_num) {
+ if (sk->sk_prot->get_port(sk, 0)) {
+ release_sock(sk);
+ return -EAGAIN;
+ }
+ inet->inet_sport = htons(inet->inet_num);
+ }
+
/* Validate addr_len before calling common connect/connectx routine. */
af = sctp_get_af_specific(addr->sa_family);
if (!af || addr_len < af->sockaddr_len) {
@@ -4415,13 +4424,25 @@ static int sctp_connect(struct sock *sk, struct sockaddr *addr,
/* Pass correct addr len to common routine (so it knows there
* is only one address being passed.
*/
- err = __sctp_connect(sk, addr, af->sockaddr_len, NULL);
+ err = __sctp_connect(sk, addr, af->sockaddr_len, flags, NULL);
}
release_sock(sk);
return err;
}
+int sctp_inet_connect(struct socket *sock, struct sockaddr *uaddr,
+ int addr_len, int flags)
+{
+ if (addr_len < sizeof(uaddr->sa_family))
+ return -EINVAL;
+
+ if (uaddr->sa_family == AF_UNSPEC)
+ return -EOPNOTSUPP;
+
+ return sctp_connect(sock->sk, uaddr, addr_len, flags);
+}
+
/* FIXME: Write comments. */
static int sctp_disconnect(struct sock *sk, int flags)
{
@@ -7701,14 +7722,12 @@ int sctp_inet_listen(struct socket *sock, int backlog)
* here, again, by modeling the current TCP/UDP code. We don't have
* a good way to test with it yet.
*/
-__poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait)
+__poll_t sctp_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
struct sctp_sock *sp = sctp_sk(sk);
__poll_t mask;
- poll_wait(file, sk_sleep(sk), wait);
-
sock_rps_record_flow(sk);
/* A TCP-style listening socket becomes readable when the accept queue
@@ -8724,7 +8743,6 @@ struct proto sctp_prot = {
.name = "SCTP",
.owner = THIS_MODULE,
.close = sctp_close,
- .connect = sctp_connect,
.disconnect = sctp_disconnect,
.accept = sctp_accept,
.ioctl = sctp_ioctl,
@@ -8767,7 +8785,6 @@ struct proto sctpv6_prot = {
.name = "SCTPv6",
.owner = THIS_MODULE,
.close = sctp_close,
- .connect = sctp_connect,
.disconnect = sctp_disconnect,
.accept = sctp_accept,
.ioctl = sctp_ioctl,
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index f799043..f1f1d1b 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -240,6 +240,8 @@ void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new)
new->out = NULL;
new->in = NULL;
+ new->outcnt = 0;
+ new->incnt = 0;
}
static int sctp_send_reconf(struct sctp_association *asoc,
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 84207ad..8cb7d98 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -715,7 +715,6 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
return event;
fail_mark:
- sctp_chunk_put(chunk);
kfree_skb(skb);
fail:
return NULL;
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 5f8046c..544bab4 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -292,6 +292,17 @@ static void smc_copy_sock_settings_to_smc(struct smc_sock *smc)
smc_copy_sock_settings(&smc->sk, smc->clcsock->sk, SK_FLAGS_CLC_TO_SMC);
}
+/* register a new rmb */
+static int smc_reg_rmb(struct smc_link *link, struct smc_buf_desc *rmb_desc)
+{
+ /* register memory region for new rmb */
+ if (smc_wr_reg_send(link, rmb_desc->mr_rx[SMC_SINGLE_LINK])) {
+ rmb_desc->regerr = 1;
+ return -EFAULT;
+ }
+ return 0;
+}
+
static int smc_clnt_conf_first_link(struct smc_sock *smc)
{
struct smc_link_group *lgr = smc->conn.lgr;
@@ -321,9 +332,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
smc_wr_remember_qp_attr(link);
- rc = smc_wr_reg_send(link,
- smc->conn.rmb_desc->mr_rx[SMC_SINGLE_LINK]);
- if (rc)
+ if (smc_reg_rmb(link, smc->conn.rmb_desc))
return SMC_CLC_DECL_INTERR;
/* send CONFIRM LINK response over RoCE fabric */
@@ -473,13 +482,8 @@ static int smc_connect_rdma(struct smc_sock *smc)
goto decline_rdma_unlock;
}
} else {
- struct smc_buf_desc *buf_desc = smc->conn.rmb_desc;
-
- if (!buf_desc->reused) {
- /* register memory region for new rmb */
- rc = smc_wr_reg_send(link,
- buf_desc->mr_rx[SMC_SINGLE_LINK]);
- if (rc) {
+ if (!smc->conn.rmb_desc->reused) {
+ if (smc_reg_rmb(link, smc->conn.rmb_desc)) {
reason_code = SMC_CLC_DECL_INTERR;
goto decline_rdma_unlock;
}
@@ -719,9 +723,7 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
link = &lgr->lnk[SMC_SINGLE_LINK];
- rc = smc_wr_reg_send(link,
- smc->conn.rmb_desc->mr_rx[SMC_SINGLE_LINK]);
- if (rc)
+ if (smc_reg_rmb(link, smc->conn.rmb_desc))
return SMC_CLC_DECL_INTERR;
/* send CONFIRM LINK request to client over the RoCE fabric */
@@ -854,13 +856,8 @@ static void smc_listen_work(struct work_struct *work)
smc_rx_init(new_smc);
if (local_contact != SMC_FIRST_CONTACT) {
- struct smc_buf_desc *buf_desc = new_smc->conn.rmb_desc;
-
- if (!buf_desc->reused) {
- /* register memory region for new rmb */
- rc = smc_wr_reg_send(link,
- buf_desc->mr_rx[SMC_SINGLE_LINK]);
- if (rc) {
+ if (!new_smc->conn.rmb_desc->reused) {
+ if (smc_reg_rmb(link, new_smc->conn.rmb_desc)) {
reason_code = SMC_CLC_DECL_INTERR;
goto decline_rdma_unlock;
}
@@ -978,10 +975,6 @@ static void smc_tcp_listen_work(struct work_struct *work)
}
out:
- if (lsmc->clcsock) {
- sock_release(lsmc->clcsock);
- lsmc->clcsock = NULL;
- }
release_sock(lsk);
sock_put(&lsmc->sk); /* sock_hold in smc_listen */
}
@@ -1170,13 +1163,15 @@ static __poll_t smc_poll(struct file *file, struct socket *sock,
/* delegate to CLC child sock */
release_sock(sk);
mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
- /* if non-blocking connect finished ... */
lock_sock(sk);
- if ((sk->sk_state == SMC_INIT) && (mask & EPOLLOUT)) {
- sk->sk_err = smc->clcsock->sk->sk_err;
- if (sk->sk_err) {
- mask |= EPOLLERR;
- } else {
+ sk->sk_err = smc->clcsock->sk->sk_err;
+ if (sk->sk_err) {
+ mask |= EPOLLERR;
+ } else {
+ /* if non-blocking connect finished ... */
+ if (sk->sk_state == SMC_INIT &&
+ mask & EPOLLOUT &&
+ smc->clcsock->sk->sk_state != TCP_CLOSE) {
rc = smc_connect_rdma(smc);
if (rc < 0)
mask |= EPOLLERR;
@@ -1259,14 +1254,12 @@ static int smc_shutdown(struct socket *sock, int how)
rc = smc_close_shutdown_write(smc);
break;
case SHUT_RD:
- if (sk->sk_state == SMC_LISTEN)
- rc = smc_close_active(smc);
- else
- rc = 0;
- /* nothing more to do because peer is not involved */
+ rc = 0;
+ /* nothing more to do because peer is not involved */
break;
}
- rc1 = kernel_sock_shutdown(smc->clcsock, how);
+ if (smc->clcsock)
+ rc1 = kernel_sock_shutdown(smc->clcsock, how);
/* map sock_shutdown_cmd constants to sk_shutdown value range */
sk->sk_shutdown |= how + 1;
@@ -1322,8 +1315,11 @@ static ssize_t smc_sendpage(struct socket *sock, struct page *page,
smc = smc_sk(sk);
lock_sock(sk);
- if (sk->sk_state != SMC_ACTIVE)
+ if (sk->sk_state != SMC_ACTIVE) {
+ release_sock(sk);
goto out;
+ }
+ release_sock(sk);
if (smc->use_fallback)
rc = kernel_sendpage(smc->clcsock, page, offset,
size, flags);
@@ -1331,7 +1327,6 @@ static ssize_t smc_sendpage(struct socket *sock, struct page *page,
rc = sock_no_sendpage(sock, page, offset, size, flags);
out:
- release_sock(sk);
return rc;
}
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index f44f680..d4bd01b 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -32,6 +32,9 @@
static u32 smc_lgr_num; /* unique link group number */
+static void smc_buf_free(struct smc_buf_desc *buf_desc, struct smc_link *lnk,
+ bool is_rmb);
+
static void smc_lgr_schedule_free_work(struct smc_link_group *lgr)
{
/* client link group creation always follows the server link group
@@ -234,9 +237,22 @@ static void smc_buf_unuse(struct smc_connection *conn)
conn->sndbuf_size = 0;
}
if (conn->rmb_desc) {
- conn->rmb_desc->reused = true;
- conn->rmb_desc->used = 0;
- conn->rmbe_size = 0;
+ if (!conn->rmb_desc->regerr) {
+ conn->rmb_desc->reused = 1;
+ conn->rmb_desc->used = 0;
+ conn->rmbe_size = 0;
+ } else {
+ /* buf registration failed, reuse not possible */
+ struct smc_link_group *lgr = conn->lgr;
+ struct smc_link *lnk;
+
+ write_lock_bh(&lgr->rmbs_lock);
+ list_del(&conn->rmb_desc->list);
+ write_unlock_bh(&lgr->rmbs_lock);
+
+ lnk = &lgr->lnk[SMC_SINGLE_LINK];
+ smc_buf_free(conn->rmb_desc, lnk, true);
+ }
}
}
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 07e2a39..5dfcb15 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -123,7 +123,8 @@ struct smc_buf_desc {
*/
u32 order; /* allocation order */
u32 used; /* currently used / unused */
- bool reused; /* new created / reused */
+ u8 reused : 1; /* new created / reused */
+ u8 regerr : 1; /* err during registration */
};
struct smc_rtoken { /* address/key of remote RMB */
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 74568cd..d7b88b2 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -245,40 +245,45 @@ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name)
static int smc_pnet_fill_entry(struct net *net, struct smc_pnetentry *pnetelem,
struct nlattr *tb[])
{
- char *string, *ibname = NULL;
- int rc = 0;
+ char *string, *ibname;
+ int rc;
memset(pnetelem, 0, sizeof(*pnetelem));
INIT_LIST_HEAD(&pnetelem->list);
- if (tb[SMC_PNETID_NAME]) {
- string = (char *)nla_data(tb[SMC_PNETID_NAME]);
- if (!smc_pnetid_valid(string, pnetelem->pnet_name)) {
- rc = -EINVAL;
- goto error;
- }
- }
- if (tb[SMC_PNETID_ETHNAME]) {
- string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]);
- pnetelem->ndev = dev_get_by_name(net, string);
- if (!pnetelem->ndev)
- return -ENOENT;
- }
- if (tb[SMC_PNETID_IBNAME]) {
- ibname = (char *)nla_data(tb[SMC_PNETID_IBNAME]);
- ibname = strim(ibname);
- pnetelem->smcibdev = smc_pnet_find_ib(ibname);
- if (!pnetelem->smcibdev) {
- rc = -ENOENT;
- goto error;
- }
- }
- if (tb[SMC_PNETID_IBPORT]) {
- pnetelem->ib_port = nla_get_u8(tb[SMC_PNETID_IBPORT]);
- if (pnetelem->ib_port > SMC_MAX_PORTS) {
- rc = -EINVAL;
- goto error;
- }
- }
+
+ rc = -EINVAL;
+ if (!tb[SMC_PNETID_NAME])
+ goto error;
+ string = (char *)nla_data(tb[SMC_PNETID_NAME]);
+ if (!smc_pnetid_valid(string, pnetelem->pnet_name))
+ goto error;
+
+ rc = -EINVAL;
+ if (!tb[SMC_PNETID_ETHNAME])
+ goto error;
+ rc = -ENOENT;
+ string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]);
+ pnetelem->ndev = dev_get_by_name(net, string);
+ if (!pnetelem->ndev)
+ goto error;
+
+ rc = -EINVAL;
+ if (!tb[SMC_PNETID_IBNAME])
+ goto error;
+ rc = -ENOENT;
+ ibname = (char *)nla_data(tb[SMC_PNETID_IBNAME]);
+ ibname = strim(ibname);
+ pnetelem->smcibdev = smc_pnet_find_ib(ibname);
+ if (!pnetelem->smcibdev)
+ goto error;
+
+ rc = -EINVAL;
+ if (!tb[SMC_PNETID_IBPORT])
+ goto error;
+ pnetelem->ib_port = nla_get_u8(tb[SMC_PNETID_IBPORT]);
+ if (pnetelem->ib_port < 1 || pnetelem->ib_port > SMC_MAX_PORTS)
+ goto error;
+
return 0;
error:
@@ -307,6 +312,8 @@ static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info)
void *hdr;
int rc;
+ if (!info->attrs[SMC_PNETID_NAME])
+ return -EINVAL;
pnetelem = smc_pnet_find_pnetid(
(char *)nla_data(info->attrs[SMC_PNETID_NAME]));
if (!pnetelem)
@@ -359,6 +366,8 @@ static int smc_pnet_add(struct sk_buff *skb, struct genl_info *info)
static int smc_pnet_del(struct sk_buff *skb, struct genl_info *info)
{
+ if (!info->attrs[SMC_PNETID_NAME])
+ return -EINVAL;
return smc_pnet_remove_by_pnetid(
(char *)nla_data(info->attrs[SMC_PNETID_NAME]));
}
diff --git a/net/socket.c b/net/socket.c
index f10f1d9..2d752e9 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -117,8 +117,10 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from);
static int sock_mmap(struct file *file, struct vm_area_struct *vma);
static int sock_close(struct inode *inode, struct file *file);
-static __poll_t sock_poll(struct file *file,
- struct poll_table_struct *wait);
+static struct wait_queue_head *sock_get_poll_head(struct file *file,
+ __poll_t events);
+static __poll_t sock_poll_mask(struct file *file, __poll_t);
+static __poll_t sock_poll(struct file *file, struct poll_table_struct *wait);
static long sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
#ifdef CONFIG_COMPAT
static long compat_sock_ioctl(struct file *file,
@@ -141,6 +143,8 @@ static const struct file_operations socket_file_ops = {
.llseek = no_llseek,
.read_iter = sock_read_iter,
.write_iter = sock_write_iter,
+ .get_poll_head = sock_get_poll_head,
+ .poll_mask = sock_poll_mask,
.poll = sock_poll,
.unlocked_ioctl = sock_ioctl,
#ifdef CONFIG_COMPAT
@@ -1114,27 +1118,48 @@ int sock_create_lite(int family, int type, int protocol, struct socket **res)
}
EXPORT_SYMBOL(sock_create_lite);
+static struct wait_queue_head *sock_get_poll_head(struct file *file,
+ __poll_t events)
+{
+ struct socket *sock = file->private_data;
+
+ if (!sock->ops->poll_mask)
+ return NULL;
+ sock_poll_busy_loop(sock, events);
+ return sk_sleep(sock->sk);
+}
+
+static __poll_t sock_poll_mask(struct file *file, __poll_t events)
+{
+ struct socket *sock = file->private_data;
+
+ /*
+ * We need to be sure we are in sync with the socket flags modification.
+ *
+ * This memory barrier is paired in the wq_has_sleeper.
+ */
+ smp_mb();
+
+ /* this socket can poll_ll so tell the system call */
+ return sock->ops->poll_mask(sock, events) |
+ (sk_can_busy_loop(sock->sk) ? POLL_BUSY_LOOP : 0);
+}
+
/* No kernel lock held - perfect */
static __poll_t sock_poll(struct file *file, poll_table *wait)
{
- __poll_t busy_flag = 0;
- struct socket *sock;
+ struct socket *sock = file->private_data;
+ __poll_t events = poll_requested_events(wait), mask = 0;
- /*
- * We can't return errors to poll, so it's either yes or no.
- */
- sock = file->private_data;
-
- if (sk_can_busy_loop(sock->sk)) {
- /* this socket can poll_ll so tell the system call */
- busy_flag = POLL_BUSY_LOOP;
-
- /* once, only if requested by syscall */
- if (wait && (wait->_key & POLL_BUSY_LOOP))
- sk_busy_loop(sock->sk, 1);
+ if (sock->ops->poll) {
+ sock_poll_busy_loop(sock, events);
+ mask = sock->ops->poll(file, sock, wait);
+ } else if (sock->ops->poll_mask) {
+ sock_poll_wait(file, sock_get_poll_head(file, events), wait);
+ mask = sock->ops->poll_mask(sock, events);
}
- return busy_flag | sock->ops->poll(file, sock, wait);
+ return mask | sock_poll_busy_flag(sock);
}
static int sock_mmap(struct file *file, struct vm_area_struct *vma)
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index b9283ce5..092bebc 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -67,7 +67,7 @@ static void strp_abort_strp(struct strparser *strp, int err)
static void strp_start_timer(struct strparser *strp, long timeo)
{
- if (timeo)
+ if (timeo && timeo != LONG_MAX)
mod_delayed_work(strp_wq, &strp->msg_timer_work, timeo);
}
@@ -296,9 +296,9 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
strp_start_timer(strp, timeo);
}
+ stm->accum_len += cand_len;
strp->need_bytes = stm->strp.full_len -
stm->accum_len;
- stm->accum_len += cand_len;
stm->early_eaten = cand_len;
STRP_STATS_ADD(strp->stats.bytes, cand_len);
desc->count = 0; /* Stop reading socket */
@@ -321,6 +321,7 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
/* Hurray, we have a new message! */
cancel_delayed_work(&strp->msg_timer_work);
strp->skb_head = NULL;
+ strp->need_bytes = 0;
STRP_STATS_INCR(strp->stats.msgs);
/* Give skb to upper layer */
@@ -410,9 +411,7 @@ void strp_data_ready(struct strparser *strp)
return;
if (strp->need_bytes) {
- if (strp_peek_len(strp) >= strp->need_bytes)
- strp->need_bytes = 0;
- else
+ if (strp_peek_len(strp) < strp->need_bytes)
return;
}
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 0f08934..4fda18d 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -609,22 +609,6 @@ static int __rpc_rmdir(struct inode *dir, struct dentry *dentry)
return ret;
}
-int rpc_rmdir(struct dentry *dentry)
-{
- struct dentry *parent;
- struct inode *dir;
- int error;
-
- parent = dget_parent(dentry);
- dir = d_inode(parent);
- inode_lock_nested(dir, I_MUTEX_PARENT);
- error = __rpc_rmdir(dir, dentry);
- inode_unlock(dir);
- dput(parent);
- return error;
-}
-EXPORT_SYMBOL_GPL(rpc_rmdir);
-
static int __rpc_unlink(struct inode *dir, struct dentry *dentry)
{
int ret;
@@ -1375,6 +1359,7 @@ rpc_gssd_dummy_depopulate(struct dentry *pipe_dentry)
struct dentry *clnt_dir = pipe_dentry->d_parent;
struct dentry *gssd_dir = clnt_dir->d_parent;
+ dget(pipe_dentry);
__rpc_rmpipe(d_inode(clnt_dir), pipe_dentry);
__rpc_depopulate(clnt_dir, gssd_dummy_info_file, 0, 1);
__rpc_depopulate(gssd_dir, gssd_dummy_clnt_dir, 0, 1);
diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c
index 5cc68a8..f2f6395 100644
--- a/net/sunrpc/xprtrdma/fmr_ops.c
+++ b/net/sunrpc/xprtrdma/fmr_ops.c
@@ -72,6 +72,7 @@ fmr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr)
if (IS_ERR(mr->fmr.fm_mr))
goto out_fmr_err;
+ INIT_LIST_HEAD(&mr->mr_list);
return 0;
out_fmr_err:
@@ -102,10 +103,6 @@ fmr_op_release_mr(struct rpcrdma_mr *mr)
LIST_HEAD(unmap_list);
int rc;
- /* Ensure MW is not on any rl_registered list */
- if (!list_empty(&mr->mr_list))
- list_del(&mr->mr_list);
-
kfree(mr->fmr.fm_physaddrs);
kfree(mr->mr_sg);
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index c5743a0..c59c5c7 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -110,6 +110,7 @@ frwr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr)
if (!mr->mr_sg)
goto out_list_err;
+ INIT_LIST_HEAD(&mr->mr_list);
sg_init_table(mr->mr_sg, depth);
init_completion(&frwr->fr_linv_done);
return 0;
@@ -133,10 +134,6 @@ frwr_op_release_mr(struct rpcrdma_mr *mr)
{
int rc;
- /* Ensure MR is not on any rl_registered list */
- if (!list_empty(&mr->mr_list))
- list_del(&mr->mr_list);
-
rc = ib_dereg_mr(mr->frwr.fr_mr);
if (rc)
pr_err("rpcrdma: final ib_dereg_mr for %p returned %i\n",
@@ -195,7 +192,7 @@ frwr_op_recover_mr(struct rpcrdma_mr *mr)
return;
out_release:
- pr_err("rpcrdma: FRWR reset failed %d, %p release\n", rc, mr);
+ pr_err("rpcrdma: FRWR reset failed %d, %p released\n", rc, mr);
r_xprt->rx_stats.mrs_orphaned++;
spin_lock(&r_xprt->rx_buf.rb_mrlock);
@@ -476,7 +473,7 @@ frwr_op_reminv(struct rpcrdma_rep *rep, struct list_head *mrs)
list_for_each_entry(mr, mrs, mr_list)
if (mr->mr_handle == rep->rr_inv_rkey) {
- list_del(&mr->mr_list);
+ list_del_init(&mr->mr_list);
trace_xprtrdma_remoteinv(mr);
mr->frwr.fr_state = FRWR_IS_INVALID;
rpcrdma_mr_unmap_and_put(mr);
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index fe5eaca..c345d36 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1254,6 +1254,11 @@ rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf)
list_del(&mr->mr_all);
spin_unlock(&buf->rb_mrlock);
+
+ /* Ensure MW is not on any rl_registered list */
+ if (!list_empty(&mr->mr_list))
+ list_del(&mr->mr_list);
+
ia->ri_ops->ro_release_mr(mr);
count++;
spin_lock(&buf->rb_mrlock);
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 3d3b423..cb41b12 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -380,7 +380,7 @@ rpcrdma_mr_pop(struct list_head *list)
struct rpcrdma_mr *mr;
mr = list_first_entry(list, struct rpcrdma_mr, mr_list);
- list_del(&mr->mr_list);
+ list_del_init(&mr->mr_list);
return mr;
}
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
index 32dc33a..5453e56 100644
--- a/net/tipc/monitor.c
+++ b/net/tipc/monitor.c
@@ -777,7 +777,7 @@ int __tipc_nl_add_monitor(struct net *net, struct tipc_nl_msg *msg,
ret = tipc_bearer_get_name(net, bearer_name, bearer_id);
if (ret || !mon)
- return -EINVAL;
+ return 0;
hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
NLM_F_MULTI, TIPC_NL_MON_GET);
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index b1fe209..dd1c4fa 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -241,7 +241,8 @@ static struct publication *tipc_service_insert_publ(struct net *net,
static struct publication *tipc_service_remove_publ(struct net *net,
struct tipc_service *sc,
u32 lower, u32 upper,
- u32 node, u32 key)
+ u32 node, u32 key,
+ struct service_range **rng)
{
struct tipc_subscription *sub, *tmp;
struct service_range *sr;
@@ -275,19 +276,15 @@ static struct publication *tipc_service_remove_publ(struct net *net,
list_del(&p->all_publ);
list_del(&p->local_publ);
-
- /* Remove service range item if this was its last publication */
- if (list_empty(&sr->all_publ)) {
+ if (list_empty(&sr->all_publ))
last = true;
- rb_erase(&sr->tree_node, &sc->ranges);
- kfree(sr);
- }
/* Notify any waiting subscriptions */
list_for_each_entry_safe(sub, tmp, &sc->subscriptions, service_list) {
tipc_sub_report_overlap(sub, p->lower, p->upper, TIPC_WITHDRAWN,
p->port, p->node, p->scope, last);
}
+ *rng = sr;
return p;
}
@@ -379,13 +376,20 @@ struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type,
u32 node, u32 key)
{
struct tipc_service *sc = tipc_service_find(net, type);
+ struct service_range *sr = NULL;
struct publication *p = NULL;
if (!sc)
return NULL;
spin_lock_bh(&sc->lock);
- p = tipc_service_remove_publ(net, sc, lower, upper, node, key);
+ p = tipc_service_remove_publ(net, sc, lower, upper, node, key, &sr);
+
+ /* Remove service range item if this was its last publication */
+ if (sr && list_empty(&sr->all_publ)) {
+ rb_erase(&sr->tree_node, &sc->ranges);
+ kfree(sr);
+ }
/* Delete service item if this no more publications and subscriptions */
if (RB_EMPTY_ROOT(&sc->ranges) && list_empty(&sc->subscriptions)) {
@@ -665,13 +669,14 @@ int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower,
/**
* tipc_nametbl_subscribe - add a subscription object to the name table
*/
-void tipc_nametbl_subscribe(struct tipc_subscription *sub)
+bool tipc_nametbl_subscribe(struct tipc_subscription *sub)
{
struct name_table *nt = tipc_name_table(sub->net);
struct tipc_net *tn = tipc_net(sub->net);
struct tipc_subscr *s = &sub->evt.s;
u32 type = tipc_sub_read(s, seq.type);
struct tipc_service *sc;
+ bool res = true;
spin_lock_bh(&tn->nametbl_lock);
sc = tipc_service_find(sub->net, type);
@@ -685,8 +690,10 @@ void tipc_nametbl_subscribe(struct tipc_subscription *sub)
pr_warn("Failed to subscribe for {%u,%u,%u}\n", type,
tipc_sub_read(s, seq.lower),
tipc_sub_read(s, seq.upper));
+ res = false;
}
spin_unlock_bh(&tn->nametbl_lock);
+ return res;
}
/**
@@ -744,16 +751,17 @@ int tipc_nametbl_init(struct net *net)
static void tipc_service_delete(struct net *net, struct tipc_service *sc)
{
struct service_range *sr, *tmpr;
- struct publication *p, *tmpb;
+ struct publication *p, *tmp;
spin_lock_bh(&sc->lock);
rbtree_postorder_for_each_entry_safe(sr, tmpr, &sc->ranges, tree_node) {
- list_for_each_entry_safe(p, tmpb,
- &sr->all_publ, all_publ) {
+ list_for_each_entry_safe(p, tmp, &sr->all_publ, all_publ) {
tipc_service_remove_publ(net, sc, p->lower, p->upper,
- p->node, p->key);
+ p->node, p->key, &sr);
kfree_rcu(p, rcu);
}
+ rb_erase(&sr->tree_node, &sc->ranges);
+ kfree(sr);
}
hlist_del_init_rcu(&sc->service_list);
spin_unlock_bh(&sc->lock);
diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h
index 4b14fc2..0febba4 100644
--- a/net/tipc/name_table.h
+++ b/net/tipc/name_table.h
@@ -126,7 +126,7 @@ struct publication *tipc_nametbl_insert_publ(struct net *net, u32 type,
struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type,
u32 lower, u32 upper,
u32 node, u32 key);
-void tipc_nametbl_subscribe(struct tipc_subscription *s);
+bool tipc_nametbl_subscribe(struct tipc_subscription *s);
void tipc_nametbl_unsubscribe(struct tipc_subscription *s);
int tipc_nametbl_init(struct net *net);
void tipc_nametbl_stop(struct net *net);
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 856f9e9..4fbaa04 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -252,6 +252,8 @@ int __tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info)
u64 *w0 = (u64 *)&node_id[0];
u64 *w1 = (u64 *)&node_id[8];
+ if (!attrs[TIPC_NLA_NET_NODEID_W1])
+ return -EINVAL;
*w0 = nla_get_u64(attrs[TIPC_NLA_NET_NODEID]);
*w1 = nla_get_u64(attrs[TIPC_NLA_NET_NODEID_W1]);
tipc_net_init(net, node_id, 0);
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index b76f13f..6ff2254 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -79,7 +79,10 @@ const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = {
const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = {
[TIPC_NLA_NET_UNSPEC] = { .type = NLA_UNSPEC },
- [TIPC_NLA_NET_ID] = { .type = NLA_U32 }
+ [TIPC_NLA_NET_ID] = { .type = NLA_U32 },
+ [TIPC_NLA_NET_ADDR] = { .type = NLA_U32 },
+ [TIPC_NLA_NET_NODEID] = { .type = NLA_U64 },
+ [TIPC_NLA_NET_NODEID_W1] = { .type = NLA_U64 },
};
const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = {
diff --git a/net/tipc/node.c b/net/tipc/node.c
index c77dd2f..f29549d 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1950,6 +1950,7 @@ int tipc_nl_node_set_link(struct sk_buff *skb, struct genl_info *info)
int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info)
{
struct net *net = genl_info_net(info);
+ struct nlattr *attrs[TIPC_NLA_LINK_MAX + 1];
struct tipc_nl_msg msg;
char *name;
int err;
@@ -1957,9 +1958,19 @@ int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info)
msg.portid = info->snd_portid;
msg.seq = info->snd_seq;
- if (!info->attrs[TIPC_NLA_LINK_NAME])
+ if (!info->attrs[TIPC_NLA_LINK])
return -EINVAL;
- name = nla_data(info->attrs[TIPC_NLA_LINK_NAME]);
+
+ err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX,
+ info->attrs[TIPC_NLA_LINK],
+ tipc_nl_link_policy, info->extack);
+ if (err)
+ return err;
+
+ if (!attrs[TIPC_NLA_LINK_NAME])
+ return -EINVAL;
+
+ name = nla_data(attrs[TIPC_NLA_LINK_NAME]);
msg.skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
if (!msg.skb)
@@ -2232,8 +2243,8 @@ int tipc_nl_node_dump_monitor(struct sk_buff *skb, struct netlink_callback *cb)
struct net *net = sock_net(skb->sk);
u32 prev_bearer = cb->args[0];
struct tipc_nl_msg msg;
+ int bearer_id;
int err;
- int i;
if (prev_bearer == MAX_BEARERS)
return 0;
@@ -2243,16 +2254,13 @@ int tipc_nl_node_dump_monitor(struct sk_buff *skb, struct netlink_callback *cb)
msg.seq = cb->nlh->nlmsg_seq;
rtnl_lock();
- for (i = prev_bearer; i < MAX_BEARERS; i++) {
- prev_bearer = i;
- err = __tipc_nl_add_monitor(net, &msg, prev_bearer);
+ for (bearer_id = prev_bearer; bearer_id < MAX_BEARERS; bearer_id++) {
+ err = __tipc_nl_add_monitor(net, &msg, bearer_id);
if (err)
- goto out;
+ break;
}
-
-out:
rtnl_unlock();
- cb->args[0] = prev_bearer;
+ cb->args[0] = bearer_id;
return skb->len;
}
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 1fd1c8b..3bb4504 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -692,10 +692,9 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
}
/**
- * tipc_poll - read and possibly block on pollmask
+ * tipc_poll - read pollmask
* @file: file structure associated with the socket
* @sock: socket for which to calculate the poll bits
- * @wait: ???
*
* Returns pollmask value
*
@@ -709,15 +708,12 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
* imply that the operation will succeed, merely that it should be performed
* and will not block.
*/
-static __poll_t tipc_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+static __poll_t tipc_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
__poll_t revents = 0;
- sock_poll_wait(file, sk_sleep(sk), wait);
-
if (sk->sk_shutdown & RCV_SHUTDOWN)
revents |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
if (sk->sk_shutdown == SHUTDOWN_MASK)
@@ -1278,7 +1274,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
struct tipc_msg *hdr = &tsk->phdr;
struct tipc_name_seq *seq;
struct sk_buff_head pkts;
- u32 dnode, dport;
+ u32 dport, dnode = 0;
u32 type, inst;
int mtu, rc;
@@ -1348,6 +1344,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
msg_set_destnode(hdr, dnode);
msg_set_destport(hdr, dest->addr.id.ref);
msg_set_hdr_sz(hdr, BASIC_H_SIZE);
+ } else {
+ return -EINVAL;
}
/* Block or return if destination link is congested */
@@ -1514,10 +1512,10 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb)
srcaddr->sock.family = AF_TIPC;
srcaddr->sock.addrtype = TIPC_ADDR_ID;
+ srcaddr->sock.scope = 0;
srcaddr->sock.addr.id.ref = msg_origport(hdr);
srcaddr->sock.addr.id.node = msg_orignode(hdr);
srcaddr->sock.addr.name.domain = 0;
- srcaddr->sock.scope = 0;
m->msg_namelen = sizeof(struct sockaddr_tipc);
if (!msg_in_group(hdr))
@@ -1526,6 +1524,7 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb)
/* Group message users may also want to know sending member's id */
srcaddr->member.family = AF_TIPC;
srcaddr->member.addrtype = TIPC_ADDR_NAME;
+ srcaddr->member.scope = 0;
srcaddr->member.addr.name.name.type = msg_nametype(hdr);
srcaddr->member.addr.name.name.instance = TIPC_SKB_CB(skb)->orig_member;
srcaddr->member.addr.name.domain = 0;
@@ -3025,7 +3024,7 @@ static const struct proto_ops msg_ops = {
.socketpair = tipc_socketpair,
.accept = sock_no_accept,
.getname = tipc_getname,
- .poll = tipc_poll,
+ .poll_mask = tipc_poll_mask,
.ioctl = tipc_ioctl,
.listen = sock_no_listen,
.shutdown = tipc_shutdown,
@@ -3046,7 +3045,7 @@ static const struct proto_ops packet_ops = {
.socketpair = tipc_socketpair,
.accept = tipc_accept,
.getname = tipc_getname,
- .poll = tipc_poll,
+ .poll_mask = tipc_poll_mask,
.ioctl = tipc_ioctl,
.listen = tipc_listen,
.shutdown = tipc_shutdown,
@@ -3067,7 +3066,7 @@ static const struct proto_ops stream_ops = {
.socketpair = tipc_socketpair,
.accept = tipc_accept,
.getname = tipc_getname,
- .poll = tipc_poll,
+ .poll_mask = tipc_poll_mask,
.ioctl = tipc_ioctl,
.listen = tipc_listen,
.shutdown = tipc_shutdown,
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index b7d80bc..f340e53 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -153,7 +153,10 @@ struct tipc_subscription *tipc_sub_subscribe(struct net *net,
memcpy(&sub->evt.s, s, sizeof(*s));
spin_lock_init(&sub->lock);
kref_init(&sub->kref);
- tipc_nametbl_subscribe(sub);
+ if (!tipc_nametbl_subscribe(sub)) {
+ kfree(sub);
+ return NULL;
+ }
timer_setup(&sub->timer, tipc_sub_timeout, 0);
timeout = tipc_sub_read(&sub->evt.s, timeout);
if (timeout != TIPC_WAIT_FOREVER)
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 0d37997..20cd93be62 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -114,6 +114,7 @@ int tls_push_sg(struct sock *sk,
size = sg->length - offset;
offset += sg->offset;
+ ctx->in_tcp_sendpages = true;
while (1) {
if (sg_is_last(sg))
sendpage_flags = flags;
@@ -134,6 +135,7 @@ int tls_push_sg(struct sock *sk,
offset -= sg->offset;
ctx->partially_sent_offset = offset;
ctx->partially_sent_record = (void *)sg;
+ ctx->in_tcp_sendpages = false;
return ret;
}
@@ -148,6 +150,8 @@ int tls_push_sg(struct sock *sk,
}
clear_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags);
+ ctx->in_tcp_sendpages = false;
+ ctx->sk_write_space(sk);
return 0;
}
@@ -217,6 +221,10 @@ static void tls_write_space(struct sock *sk)
{
struct tls_context *ctx = tls_get_ctx(sk);
+ /* We are already sending pages, ignore notification */
+ if (ctx->in_tcp_sendpages)
+ return;
+
if (!sk->sk_write_pending && tls_is_pending_closed_record(ctx)) {
gfp_t sk_allocation = sk->sk_allocation;
int rc;
@@ -241,16 +249,13 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
struct tls_context *ctx = tls_get_ctx(sk);
long timeo = sock_sndtimeo(sk, 0);
void (*sk_proto_close)(struct sock *sk, long timeout);
+ bool free_ctx = false;
lock_sock(sk);
sk_proto_close = ctx->sk_proto_close;
- if (ctx->conf == TLS_HW_RECORD)
- goto skip_tx_cleanup;
-
- if (ctx->conf == TLS_BASE) {
- kfree(ctx);
- ctx = NULL;
+ if (ctx->conf == TLS_BASE || ctx->conf == TLS_HW_RECORD) {
+ free_ctx = true;
goto skip_tx_cleanup;
}
@@ -287,7 +292,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
/* free ctx for TLS_HW_RECORD, used by tcp_set_state
* for sk->sk_prot->unhash [tls_hw_unhash]
*/
- if (ctx && ctx->conf == TLS_HW_RECORD)
+ if (free_ctx)
kfree(ctx);
}
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 4dc766b..e1c93ce 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -41,6 +41,8 @@
#include <net/strparser.h>
#include <net/tls.h>
+#define MAX_IV_SIZE TLS_CIPHER_AES_GCM_128_IV_SIZE
+
static int tls_do_decryption(struct sock *sk,
struct scatterlist *sgin,
struct scatterlist *sgout,
@@ -673,12 +675,11 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb,
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
- char iv[TLS_CIPHER_AES_GCM_128_SALT_SIZE + tls_ctx->rx.iv_size];
+ char iv[TLS_CIPHER_AES_GCM_128_SALT_SIZE + MAX_IV_SIZE];
struct scatterlist sgin_arr[MAX_SKB_FRAGS + 2];
struct scatterlist *sgin = &sgin_arr[0];
struct strp_msg *rxm = strp_msg(skb);
int ret, nsg = ARRAY_SIZE(sgin_arr);
- char aad_recv[TLS_AAD_SPACE_SIZE];
struct sk_buff *unused;
ret = skb_copy_bits(skb, rxm->offset + TLS_HEADER_SIZE,
@@ -696,13 +697,13 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb,
}
sg_init_table(sgin, nsg);
- sg_set_buf(&sgin[0], aad_recv, sizeof(aad_recv));
+ sg_set_buf(&sgin[0], ctx->rx_aad_ciphertext, TLS_AAD_SPACE_SIZE);
nsg = skb_to_sgvec(skb, &sgin[1],
rxm->offset + tls_ctx->rx.prepend_size,
rxm->full_len - tls_ctx->rx.prepend_size);
- tls_make_aad(aad_recv,
+ tls_make_aad(ctx->rx_aad_ciphertext,
rxm->full_len - tls_ctx->rx.overhead_size,
tls_ctx->rx.rec_seq,
tls_ctx->rx.rec_seq_size,
@@ -801,12 +802,12 @@ int tls_sw_recvmsg(struct sock *sk,
if (to_copy <= len && page_count < MAX_SKB_FRAGS &&
likely(!(flags & MSG_PEEK))) {
struct scatterlist sgin[MAX_SKB_FRAGS + 1];
- char unused[21];
int pages = 0;
zc = true;
sg_init_table(sgin, MAX_SKB_FRAGS + 1);
- sg_set_buf(&sgin[0], unused, 13);
+ sg_set_buf(&sgin[0], ctx->rx_aad_plaintext,
+ TLS_AAD_SPACE_SIZE);
err = zerocopy_from_iter(sk, &msg->msg_iter,
to_copy, &pages,
@@ -1094,6 +1095,12 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
goto free_priv;
}
+ /* Sanity-check the IV size for stack allocations. */
+ if (iv_size > MAX_IV_SIZE) {
+ rc = -EINVAL;
+ goto free_priv;
+ }
+
cctx->prepend_size = TLS_HEADER_SIZE + nonce_size;
cctx->tag_size = tag_size;
cctx->overhead_size = cctx->prepend_size + cctx->tag_size;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 68bb70a..95b02a7 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -638,9 +638,8 @@ static int unix_stream_connect(struct socket *, struct sockaddr *,
static int unix_socketpair(struct socket *, struct socket *);
static int unix_accept(struct socket *, struct socket *, int, bool);
static int unix_getname(struct socket *, struct sockaddr *, int);
-static __poll_t unix_poll(struct file *, struct socket *, poll_table *);
-static __poll_t unix_dgram_poll(struct file *, struct socket *,
- poll_table *);
+static __poll_t unix_poll_mask(struct socket *, __poll_t);
+static __poll_t unix_dgram_poll_mask(struct socket *, __poll_t);
static int unix_ioctl(struct socket *, unsigned int, unsigned long);
static int unix_shutdown(struct socket *, int);
static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t);
@@ -681,7 +680,7 @@ static const struct proto_ops unix_stream_ops = {
.socketpair = unix_socketpair,
.accept = unix_accept,
.getname = unix_getname,
- .poll = unix_poll,
+ .poll_mask = unix_poll_mask,
.ioctl = unix_ioctl,
.listen = unix_listen,
.shutdown = unix_shutdown,
@@ -704,7 +703,7 @@ static const struct proto_ops unix_dgram_ops = {
.socketpair = unix_socketpair,
.accept = sock_no_accept,
.getname = unix_getname,
- .poll = unix_dgram_poll,
+ .poll_mask = unix_dgram_poll_mask,
.ioctl = unix_ioctl,
.listen = sock_no_listen,
.shutdown = unix_shutdown,
@@ -726,7 +725,7 @@ static const struct proto_ops unix_seqpacket_ops = {
.socketpair = unix_socketpair,
.accept = unix_accept,
.getname = unix_getname,
- .poll = unix_dgram_poll,
+ .poll_mask = unix_dgram_poll_mask,
.ioctl = unix_ioctl,
.listen = unix_listen,
.shutdown = unix_shutdown,
@@ -2630,13 +2629,10 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
return err;
}
-static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wait)
+static __poll_t unix_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
- __poll_t mask;
-
- sock_poll_wait(file, sk_sleep(sk), wait);
- mask = 0;
+ __poll_t mask = 0;
/* exceptional events? */
if (sk->sk_err)
@@ -2665,15 +2661,11 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa
return mask;
}
-static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+static __poll_t unix_dgram_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk, *other;
- unsigned int writable;
- __poll_t mask;
-
- sock_poll_wait(file, sk_sleep(sk), wait);
- mask = 0;
+ int writable;
+ __poll_t mask = 0;
/* exceptional events? */
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
@@ -2699,7 +2691,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
}
/* No write status requested, avoid expensive OUT tests. */
- if (!(poll_requested_events(wait) & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT)))
+ if (!(events & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT)))
return mask;
writable = unix_writable(sk);
@@ -2852,20 +2844,6 @@ static const struct seq_operations unix_seq_ops = {
.stop = unix_seq_stop,
.show = unix_seq_show,
};
-
-static int unix_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &unix_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-static const struct file_operations unix_seq_fops = {
- .open = unix_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
#endif
static const struct net_proto_family unix_family_ops = {
@@ -2884,7 +2862,8 @@ static int __net_init unix_net_init(struct net *net)
goto out;
#ifdef CONFIG_PROC_FS
- if (!proc_create("unix", 0, net->proc_net, &unix_seq_fops)) {
+ if (!proc_create_net("unix", 0, net->proc_net, &unix_seq_ops,
+ sizeof(struct seq_net_private))) {
unix_sysctl_unregister(net);
goto out;
}
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index aac9b8f..bb5d5fa 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -850,18 +850,11 @@ static int vsock_shutdown(struct socket *sock, int mode)
return err;
}
-static __poll_t vsock_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+static __poll_t vsock_poll_mask(struct socket *sock, __poll_t events)
{
- struct sock *sk;
- __poll_t mask;
- struct vsock_sock *vsk;
-
- sk = sock->sk;
- vsk = vsock_sk(sk);
-
- poll_wait(file, sk_sleep(sk), wait);
- mask = 0;
+ struct sock *sk = sock->sk;
+ struct vsock_sock *vsk = vsock_sk(sk);
+ __poll_t mask = 0;
if (sk->sk_err)
/* Signify that there has been an error on this socket. */
@@ -1091,7 +1084,7 @@ static const struct proto_ops vsock_dgram_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = vsock_getname,
- .poll = vsock_poll,
+ .poll_mask = vsock_poll_mask,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = vsock_shutdown,
@@ -1849,7 +1842,7 @@ static const struct proto_ops vsock_stream_ops = {
.socketpair = sock_no_socketpair,
.accept = vsock_accept,
.getname = vsock_getname,
- .poll = vsock_poll,
+ .poll_mask = vsock_poll_mask,
.ioctl = sock_no_ioctl,
.listen = vsock_listen,
.shutdown = vsock_shutdown,
@@ -2018,7 +2011,13 @@ const struct vsock_transport *vsock_core_get_transport(void)
}
EXPORT_SYMBOL_GPL(vsock_core_get_transport);
+static void __exit vsock_exit(void)
+{
+ /* Do nothing. This function makes this module removable. */
+}
+
module_init(vsock_init_tables);
+module_exit(vsock_exit);
MODULE_AUTHOR("VMware, Inc.");
MODULE_DESCRIPTION("VMware Virtual Socket Family");
diff --git a/net/wireless/core.c b/net/wireless/core.c
index a6f3cac..c0fd8a8 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -95,6 +95,9 @@ static int cfg80211_dev_check_name(struct cfg80211_registered_device *rdev,
ASSERT_RTNL();
+ if (strlen(newname) > NL80211_WIPHY_NAME_MAXLEN)
+ return -EINVAL;
+
/* prohibit calling the thing phy%d when %d is not its number */
sscanf(newname, PHY_NAME "%d%n", &wiphy_idx, &taken);
if (taken == strlen(newname) && wiphy_idx != rdev->wiphy_idx) {
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index ff28f8f..7c5135a 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -9214,6 +9214,7 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
if (nla_get_flag(info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT])) {
if (!info->attrs[NL80211_ATTR_SOCKET_OWNER]) {
+ kzfree(connkeys);
GENL_SET_ERR_MSG(info,
"external auth requires connection ownership");
return -EINVAL;
@@ -15554,7 +15555,8 @@ void cfg80211_ft_event(struct net_device *netdev,
if (!ft_event->target_ap)
return;
- msg = nlmsg_new(100 + ft_event->ric_ies_len, GFP_KERNEL);
+ msg = nlmsg_new(100 + ft_event->ies_len + ft_event->ric_ies_len,
+ GFP_KERNEL);
if (!msg)
return;
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 16c7e4e..5fcec5c 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -916,6 +916,9 @@ int reg_query_regdb_wmm(char *alpha2, int freq, u32 *dbptr,
const struct fwdb_header *hdr = regdb;
const struct fwdb_country *country;
+ if (!regdb)
+ return -ENODATA;
+
if (IS_ERR(regdb))
return PTR_ERR(regdb);
@@ -1026,6 +1029,7 @@ static int regdb_query_country(const struct fwdb_header *db,
if (!tmp_rd) {
kfree(regdom);
+ kfree(wmm_ptrs);
return -ENOMEM;
}
regdom = tmp_rd;
diff --git a/net/wireless/wext-proc.c b/net/wireless/wext-proc.c
index b4c4645..cadcf86 100644
--- a/net/wireless/wext-proc.c
+++ b/net/wireless/wext-proc.c
@@ -126,24 +126,11 @@ static const struct seq_operations wireless_seq_ops = {
.show = wireless_dev_seq_show,
};
-static int seq_open_wireless(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &wireless_seq_ops,
- sizeof(struct seq_net_private));
-}
-
-static const struct file_operations wireless_seq_fops = {
- .open = seq_open_wireless,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
int __net_init wext_proc_init(struct net *net)
{
/* Create /proc/net/wireless entry */
- if (!proc_create("wireless", 0444, net->proc_net,
- &wireless_seq_fops))
+ if (!proc_create_net("wireless", 0444, net->proc_net,
+ &wireless_seq_ops, sizeof(struct seq_net_private)))
return -ENOMEM;
return 0;
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index d49aa79..f93365a 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1750,7 +1750,7 @@ static const struct proto_ops x25_proto_ops = {
.socketpair = sock_no_socketpair,
.accept = x25_accept,
.getname = x25_getname,
- .poll = datagram_poll,
+ .poll_mask = datagram_poll_mask,
.ioctl = x25_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = compat_x25_ioctl,
diff --git a/net/x25/x25_proc.c b/net/x25/x25_proc.c
index 64b415e..da52c9d 100644
--- a/net/x25/x25_proc.c
+++ b/net/x25/x25_proc.c
@@ -171,57 +171,21 @@ static const struct seq_operations x25_seq_forward_ops = {
.show = x25_seq_forward_show,
};
-static int x25_seq_socket_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &x25_seq_socket_ops);
-}
-
-static int x25_seq_route_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &x25_seq_route_ops);
-}
-
-static int x25_seq_forward_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &x25_seq_forward_ops);
-}
-
-static const struct file_operations x25_seq_socket_fops = {
- .open = x25_seq_socket_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-static const struct file_operations x25_seq_route_fops = {
- .open = x25_seq_route_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-static const struct file_operations x25_seq_forward_fops = {
- .open = x25_seq_forward_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
int __init x25_proc_init(void)
{
if (!proc_mkdir("x25", init_net.proc_net))
return -ENOMEM;
- if (!proc_create("x25/route", 0444, init_net.proc_net,
- &x25_seq_route_fops))
+ if (!proc_create_seq("x25/route", 0444, init_net.proc_net,
+ &x25_seq_route_ops))
goto out;
- if (!proc_create("x25/socket", 0444, init_net.proc_net,
- &x25_seq_socket_fops))
+ if (!proc_create_seq("x25/socket", 0444, init_net.proc_net,
+ &x25_seq_socket_ops))
goto out;
- if (!proc_create("x25/forward", 0444, init_net.proc_net,
- &x25_seq_forward_fops))
+ if (!proc_create_seq("x25/forward", 0444, init_net.proc_net,
+ &x25_seq_forward_ops))
goto out;
return 0;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 40b54cc..5f48251 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1658,7 +1658,6 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
trailer_len -= xdst_prev->u.dst.xfrm->props.trailer_len;
}
-out:
return &xdst0->u.dst;
put_states:
@@ -1667,8 +1666,8 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
free_dst:
if (xdst0)
dst_release_immediate(&xdst0->u.dst);
- xdst0 = ERR_PTR(err);
- goto out;
+
+ return ERR_PTR(err);
}
static int xfrm_expand_policies(const struct flowi *fl, u16 family,
diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c
index ed06903..178318d 100644
--- a/net/xfrm/xfrm_proc.c
+++ b/net/xfrm/xfrm_proc.c
@@ -65,22 +65,10 @@ static int xfrm_statistics_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static int xfrm_statistics_seq_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, xfrm_statistics_seq_show);
-}
-
-static const struct file_operations xfrm_statistics_seq_fops = {
- .open = xfrm_statistics_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release_net,
-};
-
int __net_init xfrm_proc_init(struct net *net)
{
- if (!proc_create("xfrm_stat", 0444, net->proc_net,
- &xfrm_statistics_seq_fops))
+ if (!proc_create_net_single("xfrm_stat", 0444, net->proc_net,
+ xfrm_statistics_seq_show, NULL))
return -ENOMEM;
return 0;
}
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index f9d2f22..6c177ae 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2175,6 +2175,12 @@ struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family)
return afinfo;
}
+void xfrm_flush_gc(void)
+{
+ flush_work(&xfrm_state_gc_work);
+}
+EXPORT_SYMBOL(xfrm_flush_gc);
+
/* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */
void xfrm_state_delete_tunnel(struct xfrm_state *x)
{
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 4d6a6ed..0929476 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -255,7 +255,7 @@
$(obj)/%.o: $(src)/%.c
$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
-I$(srctree)/tools/testing/selftests/bpf/ \
- -D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \
+ -D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \
-D__TARGET_ARCH_$(ARCH) -Wno-compare-distinct-pointer-types \
-Wno-gnu-variable-sized-type-not-at-end \
-Wno-address-of-packed-member -Wno-tautological-compare \
diff --git a/samples/livepatch/livepatch-shadow-fix1.c b/samples/livepatch/livepatch-shadow-fix1.c
index 830c555..49b1355 100644
--- a/samples/livepatch/livepatch-shadow-fix1.c
+++ b/samples/livepatch/livepatch-shadow-fix1.c
@@ -56,6 +56,21 @@ struct dummy {
unsigned long jiffies_expire;
};
+/*
+ * The constructor makes more sense together with klp_shadow_get_or_alloc().
+ * In this example, it would be safe to assign the pointer also to the shadow
+ * variable returned by klp_shadow_alloc(). But we wanted to show the more
+ * complicated use of the API.
+ */
+static int shadow_leak_ctor(void *obj, void *shadow_data, void *ctor_data)
+{
+ void **shadow_leak = shadow_data;
+ void *leak = ctor_data;
+
+ *shadow_leak = leak;
+ return 0;
+}
+
struct dummy *livepatch_fix1_dummy_alloc(void)
{
struct dummy *d;
@@ -74,7 +89,8 @@ struct dummy *livepatch_fix1_dummy_alloc(void)
* pointer to handle resource release.
*/
leak = kzalloc(sizeof(int), GFP_KERNEL);
- klp_shadow_alloc(d, SV_LEAK, &leak, sizeof(leak), GFP_KERNEL);
+ klp_shadow_alloc(d, SV_LEAK, sizeof(leak), GFP_KERNEL,
+ shadow_leak_ctor, leak);
pr_info("%s: dummy @ %p, expires @ %lx\n",
__func__, d, d->jiffies_expire);
@@ -82,9 +98,19 @@ struct dummy *livepatch_fix1_dummy_alloc(void)
return d;
}
+static void livepatch_fix1_dummy_leak_dtor(void *obj, void *shadow_data)
+{
+ void *d = obj;
+ void **shadow_leak = shadow_data;
+
+ kfree(*shadow_leak);
+ pr_info("%s: dummy @ %p, prevented leak @ %p\n",
+ __func__, d, *shadow_leak);
+}
+
void livepatch_fix1_dummy_free(struct dummy *d)
{
- void **shadow_leak, *leak;
+ void **shadow_leak;
/*
* Patch: fetch the saved SV_LEAK shadow variable, detach and
@@ -93,15 +119,10 @@ void livepatch_fix1_dummy_free(struct dummy *d)
* was loaded.)
*/
shadow_leak = klp_shadow_get(d, SV_LEAK);
- if (shadow_leak) {
- leak = *shadow_leak;
- klp_shadow_free(d, SV_LEAK);
- kfree(leak);
- pr_info("%s: dummy @ %p, prevented leak @ %p\n",
- __func__, d, leak);
- } else {
+ if (shadow_leak)
+ klp_shadow_free(d, SV_LEAK, livepatch_fix1_dummy_leak_dtor);
+ else
pr_info("%s: dummy @ %p leaked!\n", __func__, d);
- }
kfree(d);
}
@@ -147,7 +168,7 @@ static int livepatch_shadow_fix1_init(void)
static void livepatch_shadow_fix1_exit(void)
{
/* Cleanup any existing SV_LEAK shadow variables */
- klp_shadow_free_all(SV_LEAK);
+ klp_shadow_free_all(SV_LEAK, livepatch_fix1_dummy_leak_dtor);
WARN_ON(klp_unregister_patch(&patch));
}
diff --git a/samples/livepatch/livepatch-shadow-fix2.c b/samples/livepatch/livepatch-shadow-fix2.c
index ff9948f..b34c7bf 100644
--- a/samples/livepatch/livepatch-shadow-fix2.c
+++ b/samples/livepatch/livepatch-shadow-fix2.c
@@ -53,39 +53,42 @@ struct dummy {
bool livepatch_fix2_dummy_check(struct dummy *d, unsigned long jiffies)
{
int *shadow_count;
- int count;
/*
* Patch: handle in-flight dummy structures, if they do not
* already have a SV_COUNTER shadow variable, then attach a
* new one.
*/
- count = 0;
shadow_count = klp_shadow_get_or_alloc(d, SV_COUNTER,
- &count, sizeof(count),
- GFP_NOWAIT);
+ sizeof(*shadow_count), GFP_NOWAIT,
+ NULL, NULL);
if (shadow_count)
*shadow_count += 1;
return time_after(jiffies, d->jiffies_expire);
}
+static void livepatch_fix2_dummy_leak_dtor(void *obj, void *shadow_data)
+{
+ void *d = obj;
+ void **shadow_leak = shadow_data;
+
+ kfree(*shadow_leak);
+ pr_info("%s: dummy @ %p, prevented leak @ %p\n",
+ __func__, d, *shadow_leak);
+}
+
void livepatch_fix2_dummy_free(struct dummy *d)
{
- void **shadow_leak, *leak;
+ void **shadow_leak;
int *shadow_count;
/* Patch: copy the memory leak patch from the fix1 module. */
shadow_leak = klp_shadow_get(d, SV_LEAK);
- if (shadow_leak) {
- leak = *shadow_leak;
- klp_shadow_free(d, SV_LEAK);
- kfree(leak);
- pr_info("%s: dummy @ %p, prevented leak @ %p\n",
- __func__, d, leak);
- } else {
+ if (shadow_leak)
+ klp_shadow_free(d, SV_LEAK, livepatch_fix2_dummy_leak_dtor);
+ else
pr_info("%s: dummy @ %p leaked!\n", __func__, d);
- }
/*
* Patch: fetch the SV_COUNTER shadow variable and display
@@ -95,7 +98,7 @@ void livepatch_fix2_dummy_free(struct dummy *d)
if (shadow_count) {
pr_info("%s: dummy @ %p, check counter = %d\n",
__func__, d, *shadow_count);
- klp_shadow_free(d, SV_COUNTER);
+ klp_shadow_free(d, SV_COUNTER, NULL);
}
kfree(d);
@@ -142,7 +145,7 @@ static int livepatch_shadow_fix2_init(void)
static void livepatch_shadow_fix2_exit(void)
{
/* Cleanup any existing SV_COUNTER shadow variables */
- klp_shadow_free_all(SV_COUNTER);
+ klp_shadow_free_all(SV_COUNTER, NULL);
WARN_ON(klp_unregister_patch(&patch));
}
diff --git a/samples/sockmap/Makefile b/samples/sockmap/Makefile
index 9bf2881..fa53f4d 100644
--- a/samples/sockmap/Makefile
+++ b/samples/sockmap/Makefile
@@ -65,11 +65,14 @@
# asm/sysreg.h - inline assembly used by it is incompatible with llvm.
# But, there is no easy way to fix it, so just exclude it since it is
# useless for BPF samples.
+#
+# -target bpf option required with SK_MSG programs, this is to ensure
+# reading 'void *' data types for data and data_end are __u64 reads.
$(obj)/%.o: $(src)/%.c
$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
-D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \
-Wno-compare-distinct-pointer-types \
-Wno-gnu-variable-sized-type-not-at-end \
-Wno-address-of-packed-member -Wno-tautological-compare \
- -Wno-unknown-warning-option \
- -O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@
+ -Wno-unknown-warning-option -O2 -target bpf \
+ -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@
diff --git a/scripts/Makefile.gcc-plugins b/scripts/Makefile.gcc-plugins
index b2a95af..7f5c8624 100644
--- a/scripts/Makefile.gcc-plugins
+++ b/scripts/Makefile.gcc-plugins
@@ -14,7 +14,7 @@
endif
ifdef CONFIG_GCC_PLUGIN_SANCOV
- ifeq ($(CFLAGS_KCOV),)
+ ifeq ($(strip $(CFLAGS_KCOV)),)
# It is needed because of the gcc-plugin.sh and gcc version checks.
gcc-plugin-$(CONFIG_GCC_PLUGIN_SANCOV) += sancov_plugin.so
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 07d0740..5af34a2b 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -196,7 +196,7 @@
$(call if_changed,bison)
quiet_cmd_bison_h = YACC $@
- cmd_bison_h = bison -o/dev/null --defines=$@ -t -l $<
+ cmd_bison_h = $(YACC) -o/dev/null --defines=$@ -t -l $<
$(obj)/%.tab.h: $(src)/%.y FORCE
$(call if_changed,bison_h)
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index e16d671..2d42eb9 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -5041,7 +5041,7 @@
$tmp_stmt =~ s/\b(typeof|__typeof__|__builtin\w+|typecheck\s*\(\s*$Type\s*,|\#+)\s*\(*\s*$arg\s*\)*\b//g;
$tmp_stmt =~ s/\#+\s*$arg\b//g;
$tmp_stmt =~ s/\b$arg\s*\#\#//g;
- my $use_cnt = $tmp_stmt =~ s/\b$arg\b//g;
+ my $use_cnt = () = $tmp_stmt =~ /\b$arg\b/g;
if ($use_cnt > 1) {
CHK("MACRO_ARG_REUSE",
"Macro argument reuse '$arg' - possible side-effects?\n" . "$herectx");
diff --git a/scripts/documentation-file-ref-check b/scripts/documentation-file-ref-check
index bc16599..2520bc1 100755
--- a/scripts/documentation-file-ref-check
+++ b/scripts/documentation-file-ref-check
@@ -1,15 +1,116 @@
-#!/bin/sh
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+#
# Treewide grep for references to files under Documentation, and report
# non-existing files in stderr.
-for f in $(git ls-files); do
- for ref in $(grep -ho "Documentation/[A-Za-z0-9_.,~/*+-]*" "$f"); do
- # presume trailing . and , are not part of the name
- ref=${ref%%[.,]}
+use warnings;
+use strict;
+use Getopt::Long qw(:config no_auto_abbrev);
- # use ls to handle wildcards
- if ! ls $ref >/dev/null 2>&1; then
- echo "$f: $ref" >&2
- fi
- done
-done
+my $scriptname = $0;
+$scriptname =~ s,.*/([^/]+/),$1,;
+
+# Parse arguments
+my $help = 0;
+my $fix = 0;
+
+GetOptions(
+ 'fix' => \$fix,
+ 'h|help|usage' => \$help,
+);
+
+if ($help != 0) {
+ print "$scriptname [--help] [--fix-rst]\n";
+ exit -1;
+}
+
+# Step 1: find broken references
+print "Finding broken references. This may take a while... " if ($fix);
+
+my %broken_ref;
+
+open IN, "git grep 'Documentation/'|"
+ or die "Failed to run git grep";
+while (<IN>) {
+ next if (!m/^([^:]+):(.*)/);
+
+ my $f = $1;
+ my $ln = $2;
+
+ # Makefiles contain nasty expressions to parse docs
+ next if ($f =~ m/Makefile/);
+ # Skip this script
+ next if ($f eq $scriptname);
+
+ if ($ln =~ m,\b(\S*)(Documentation/[A-Za-z0-9\_\.\,\~/\*+-]*),) {
+ my $prefix = $1;
+ my $ref = $2;
+ my $base = $2;
+
+ $ref =~ s/[\,\.]+$//;
+
+ my $fulref = "$prefix$ref";
+
+ $fulref =~ s/^(\<file|ref)://;
+ $fulref =~ s/^[\'\`]+//;
+ $fulref =~ s,^\$\(.*\)/,,;
+ $base =~ s,.*/,,;
+
+ # Remove URL false-positives
+ next if ($fulref =~ m/^http/);
+
+ # Check if exists, evaluating wildcards
+ next if (grep -e, glob("$ref $fulref"));
+
+ if ($fix) {
+ if (!($ref =~ m/(devicetree|scripts|Kconfig|Kbuild)/)) {
+ $broken_ref{$ref}++;
+ }
+ } else {
+ print STDERR "$f: $fulref\n";
+ }
+ }
+}
+
+exit 0 if (!$fix);
+
+# Step 2: Seek for file name alternatives
+print "Auto-fixing broken references. Please double-check the results\n";
+
+foreach my $ref (keys %broken_ref) {
+ my $new =$ref;
+
+ # get just the basename
+ $new =~ s,.*/,,;
+
+ # Seek for the same name on another place, as it may have been moved
+ my $f="";
+
+ $f = qx(find . -iname $new) if ($new);
+
+ # usual reason for breakage: file renamed to .rst
+ if (!$f) {
+ $new =~ s/\.txt$/.rst/;
+ $f=qx(find . -iname $new) if ($new);
+ }
+
+ my @find = split /\s+/, $f;
+
+ if (!$f) {
+ print STDERR "ERROR: Didn't find a replacement for $ref\n";
+ } elsif (scalar(@find) > 1) {
+ print STDERR "WARNING: Won't auto-replace, as found multiple files close to $ref:\n";
+ foreach my $j (@find) {
+ $j =~ s,^./,,;
+ print STDERR " $j\n";
+ }
+ } else {
+ $f = $find[0];
+ $f =~ s,^./,,;
+ print "INFO: Replacing $ref to $f\n";
+ foreach my $j (qx(git grep -l $ref)) {
+ qx(sed "s\@$ref\@$f\@g" -i $j);
+ }
+ }
+}
diff --git a/scripts/dtc/checks.c b/scripts/dtc/checks.c
index c07ba4d..815eaf1 100644
--- a/scripts/dtc/checks.c
+++ b/scripts/dtc/checks.c
@@ -787,10 +787,9 @@ static void check_pci_bridge(struct check *c, struct dt_info *dti, struct node *
FAIL(c, dti, node, "incorrect #size-cells for PCI bridge");
prop = get_property(node, "bus-range");
- if (!prop) {
- FAIL(c, dti, node, "missing bus-range for PCI bridge");
+ if (!prop)
return;
- }
+
if (prop->val.len != (sizeof(cell_t) * 2)) {
FAIL_PROP(c, dti, node, prop, "value must be 2 cells");
return;
diff --git a/scripts/extract_xc3028.pl b/scripts/extract_xc3028.pl
index 61d9b25..a1c51b7 100755
--- a/scripts/extract_xc3028.pl
+++ b/scripts/extract_xc3028.pl
@@ -1,6 +1,6 @@
#!/usr/bin/env perl
-# Copyright (c) Mauro Carvalho Chehab <mchehab@infradead.org>
+# Copyright (c) Mauro Carvalho Chehab <mchehab@kernel.org>
# Released under GPLv2
#
# In order to use, you need to:
diff --git a/scripts/faddr2line b/scripts/faddr2line
index 9e5735a..a0149db 100755
--- a/scripts/faddr2line
+++ b/scripts/faddr2line
@@ -56,7 +56,7 @@
command -v ${NM} >/dev/null 2>&1 || die "nm isn't installed"
usage() {
- echo "usage: faddr2line <object file> <func+offset> <func+offset>..." >&2
+ echo "usage: faddr2line [--list] <object file> <func+offset> <func+offset>..." >&2
exit 1
}
@@ -166,12 +166,25 @@
local file_lines=$(${ADDR2LINE} -fpie $objfile $addr | sed "s; $dir_prefix\(\./\)*; ;")
[[ -z $file_lines ]] && return
+ if [[ $LIST = 0 ]]; then
+ echo "$file_lines" | while read -r line
+ do
+ echo $line
+ done
+ DONE=1;
+ return
+ fi
+
# show each line with context
echo "$file_lines" | while read -r line
do
+ echo
echo $line
- eval $(echo $line | awk -F "[ :]" '{printf("n1=%d;n2=%d;f=%s",$NF-5, $NF+5, $(NF-1))}')
- awk 'NR>=strtonum("'$n1'") && NR<=strtonum("'$n2'") {printf("%d\t%s\n", NR, $0)}' $f
+ n=$(echo $line | sed 's/.*:\([0-9]\+\).*/\1/g')
+ n1=$[$n-5]
+ n2=$[$n+5]
+ f=$(echo $line | sed 's/.*at \(.\+\):.*/\1/g')
+ awk 'NR>=strtonum("'$n1'") && NR<=strtonum("'$n2'") { if (NR=='$n') printf(">%d<", NR); else printf(" %d ", NR); printf("\t%s\n", $0)}' $f
done
DONE=1
@@ -182,6 +195,10 @@
[[ $# -lt 2 ]] && usage
objfile=$1
+
+LIST=0
+[[ "$objfile" == "--list" ]] && LIST=1 && shift && objfile=$1
+
[[ ! -f $objfile ]] && die "can't find objfile $objfile"
shift
diff --git a/scripts/genksyms/Makefile b/scripts/genksyms/Makefile
index ef0287e..03b7ce9 100644
--- a/scripts/genksyms/Makefile
+++ b/scripts/genksyms/Makefile
@@ -14,14 +14,14 @@
# so that 'bison: not found' will be displayed if it is missing.
ifeq ($(findstring 1,$(KBUILD_ENABLE_EXTRA_GCC_CHECKS)),)
-quiet_cmd_bison_no_warn = $(quet_cmd_bison)
+quiet_cmd_bison_no_warn = $(quiet_cmd_bison)
cmd_bison_no_warn = $(YACC) --version >/dev/null; \
$(cmd_bison) 2>/dev/null
$(obj)/parse.tab.c: $(src)/parse.y FORCE
$(call if_changed,bison_no_warn)
-quiet_cmd_bison_h_no_warn = $(quet_cmd_bison_h)
+quiet_cmd_bison_h_no_warn = $(quiet_cmd_bison_h)
cmd_bison_h_no_warn = $(YACC) --version >/dev/null; \
$(cmd_bison_h) 2>/dev/null
diff --git a/scripts/mod/sumversion.c b/scripts/mod/sumversion.c
index 944418d..0f6dcb40 100644
--- a/scripts/mod/sumversion.c
+++ b/scripts/mod/sumversion.c
@@ -330,14 +330,7 @@ static int parse_source_files(const char *objfile, struct md4_ctx *md)
goto out;
}
- /* There will be a line like so:
- deps_drivers/net/dummy.o := \
- drivers/net/dummy.c \
- $(wildcard include/config/net/fastroute.h) \
- include/linux/module.h \
-
- Sum all files in the same dir or subdirs.
- */
+ /* Sum all files in the same dir or subdirs. */
while ((line = get_next_line(&pos, file, flen)) != NULL) {
char* p = line;
diff --git a/scripts/spdxcheck.py b/scripts/spdxcheck.py
new file mode 100755
index 0000000..7deaef2
--- /dev/null
+++ b/scripts/spdxcheck.py
@@ -0,0 +1,284 @@
+#!/usr/bin/env python
+# SPDX-License-Identifier: GPL-2.0
+# Copyright Thomas Gleixner <tglx@linutronix.de>
+
+from argparse import ArgumentParser
+from ply import lex, yacc
+import traceback
+import sys
+import git
+import re
+import os
+
+class ParserException(Exception):
+ def __init__(self, tok, txt):
+ self.tok = tok
+ self.txt = txt
+
+class SPDXException(Exception):
+ def __init__(self, el, txt):
+ self.el = el
+ self.txt = txt
+
+class SPDXdata(object):
+ def __init__(self):
+ self.license_files = 0
+ self.exception_files = 0
+ self.licenses = [ ]
+ self.exceptions = { }
+
+# Read the spdx data from the LICENSES directory
+def read_spdxdata(repo):
+
+ # The subdirectories of LICENSES in the kernel source
+ license_dirs = [ "preferred", "other", "exceptions" ]
+ lictree = repo.heads.master.commit.tree['LICENSES']
+
+ spdx = SPDXdata()
+
+ for d in license_dirs:
+ for el in lictree[d].traverse():
+ if not os.path.isfile(el.path):
+ continue
+
+ exception = None
+ for l in open(el.path).readlines():
+ if l.startswith('Valid-License-Identifier:'):
+ lid = l.split(':')[1].strip().upper()
+ if lid in spdx.licenses:
+ raise SPDXException(el, 'Duplicate License Identifier: %s' %lid)
+ else:
+ spdx.licenses.append(lid)
+
+ elif l.startswith('SPDX-Exception-Identifier:'):
+ exception = l.split(':')[1].strip().upper()
+ spdx.exceptions[exception] = []
+
+ elif l.startswith('SPDX-Licenses:'):
+ for lic in l.split(':')[1].upper().strip().replace(' ', '').replace('\t', '').split(','):
+ if not lic in spdx.licenses:
+ raise SPDXException(None, 'Exception %s missing license %s' %(ex, lic))
+ spdx.exceptions[exception].append(lic)
+
+ elif l.startswith("License-Text:"):
+ if exception:
+ if not len(spdx.exceptions[exception]):
+ raise SPDXException(el, 'Exception %s is missing SPDX-Licenses' %excid)
+ spdx.exception_files += 1
+ else:
+ spdx.license_files += 1
+ break
+ return spdx
+
+class id_parser(object):
+
+ reserved = [ 'AND', 'OR', 'WITH' ]
+ tokens = [ 'LPAR', 'RPAR', 'ID', 'EXC' ] + reserved
+
+ precedence = ( ('nonassoc', 'AND', 'OR'), )
+
+ t_ignore = ' \t'
+
+ def __init__(self, spdx):
+ self.spdx = spdx
+ self.lasttok = None
+ self.lastid = None
+ self.lexer = lex.lex(module = self, reflags = re.UNICODE)
+ # Initialize the parser. No debug file and no parser rules stored on disk
+ # The rules are small enough to be generated on the fly
+ self.parser = yacc.yacc(module = self, write_tables = False, debug = False)
+ self.lines_checked = 0
+ self.checked = 0
+ self.spdx_valid = 0
+ self.spdx_errors = 0
+ self.curline = 0
+ self.deepest = 0
+
+ # Validate License and Exception IDs
+ def validate(self, tok):
+ id = tok.value.upper()
+ if tok.type == 'ID':
+ if not id in self.spdx.licenses:
+ raise ParserException(tok, 'Invalid License ID')
+ self.lastid = id
+ elif tok.type == 'EXC':
+ if not self.spdx.exceptions.has_key(id):
+ raise ParserException(tok, 'Invalid Exception ID')
+ if self.lastid not in self.spdx.exceptions[id]:
+ raise ParserException(tok, 'Exception not valid for license %s' %self.lastid)
+ self.lastid = None
+ elif tok.type != 'WITH':
+ self.lastid = None
+
+ # Lexer functions
+ def t_RPAR(self, tok):
+ r'\)'
+ self.lasttok = tok.type
+ return tok
+
+ def t_LPAR(self, tok):
+ r'\('
+ self.lasttok = tok.type
+ return tok
+
+ def t_ID(self, tok):
+ r'[A-Za-z.0-9\-+]+'
+
+ if self.lasttok == 'EXC':
+ print(tok)
+ raise ParserException(tok, 'Missing parentheses')
+
+ tok.value = tok.value.strip()
+ val = tok.value.upper()
+
+ if val in self.reserved:
+ tok.type = val
+ elif self.lasttok == 'WITH':
+ tok.type = 'EXC'
+
+ self.lasttok = tok.type
+ self.validate(tok)
+ return tok
+
+ def t_error(self, tok):
+ raise ParserException(tok, 'Invalid token')
+
+ def p_expr(self, p):
+ '''expr : ID
+ | ID WITH EXC
+ | expr AND expr
+ | expr OR expr
+ | LPAR expr RPAR'''
+ pass
+
+ def p_error(self, p):
+ if not p:
+ raise ParserException(None, 'Unfinished license expression')
+ else:
+ raise ParserException(p, 'Syntax error')
+
+ def parse(self, expr):
+ self.lasttok = None
+ self.lastid = None
+ self.parser.parse(expr, lexer = self.lexer)
+
+ def parse_lines(self, fd, maxlines, fname):
+ self.checked += 1
+ self.curline = 0
+ try:
+ for line in fd:
+ self.curline += 1
+ if self.curline > maxlines:
+ break
+ self.lines_checked += 1
+ if line.find("SPDX-License-Identifier:") < 0:
+ continue
+ expr = line.split(':')[1].replace('*/', '').strip()
+ self.parse(expr)
+ self.spdx_valid += 1
+ #
+ # Should we check for more SPDX ids in the same file and
+ # complain if there are any?
+ #
+ break
+
+ except ParserException as pe:
+ if pe.tok:
+ col = line.find(expr) + pe.tok.lexpos
+ tok = pe.tok.value
+ sys.stdout.write('%s: %d:%d %s: %s\n' %(fname, self.curline, col, pe.txt, tok))
+ else:
+ sys.stdout.write('%s: %d:0 %s\n' %(fname, self.curline, col, pe.txt))
+ self.spdx_errors += 1
+
+def scan_git_tree(tree):
+ for el in tree.traverse():
+ # Exclude stuff which would make pointless noise
+ # FIXME: Put this somewhere more sensible
+ if el.path.startswith("LICENSES"):
+ continue
+ if el.path.find("license-rules.rst") >= 0:
+ continue
+ if el.path == 'scripts/checkpatch.pl':
+ continue
+ if not os.path.isfile(el.path):
+ continue
+ parser.parse_lines(open(el.path), args.maxlines, el.path)
+
+def scan_git_subtree(tree, path):
+ for p in path.strip('/').split('/'):
+ tree = tree[p]
+ scan_git_tree(tree)
+
+if __name__ == '__main__':
+
+ ap = ArgumentParser(description='SPDX expression checker')
+ ap.add_argument('path', nargs='*', help='Check path or file. If not given full git tree scan. For stdin use "-"')
+ ap.add_argument('-m', '--maxlines', type=int, default=15,
+ help='Maximum number of lines to scan in a file. Default 15')
+ ap.add_argument('-v', '--verbose', action='store_true', help='Verbose statistics output')
+ args = ap.parse_args()
+
+ # Sanity check path arguments
+ if '-' in args.path and len(args.path) > 1:
+ sys.stderr.write('stdin input "-" must be the only path argument\n')
+ sys.exit(1)
+
+ try:
+ # Use git to get the valid license expressions
+ repo = git.Repo(os.getcwd())
+ assert not repo.bare
+
+ # Initialize SPDX data
+ spdx = read_spdxdata(repo)
+
+ # Initilize the parser
+ parser = id_parser(spdx)
+
+ except SPDXException as se:
+ if se.el:
+ sys.stderr.write('%s: %s\n' %(se.el.path, se.txt))
+ else:
+ sys.stderr.write('%s\n' %se.txt)
+ sys.exit(1)
+
+ except Exception as ex:
+ sys.stderr.write('FAIL: %s\n' %ex)
+ sys.stderr.write('%s\n' %traceback.format_exc())
+ sys.exit(1)
+
+ try:
+ if len(args.path) and args.path[0] == '-':
+ parser.parse_lines(sys.stdin, args.maxlines, '-')
+ else:
+ if args.path:
+ for p in args.path:
+ if os.path.isfile(p):
+ parser.parse_lines(open(p), args.maxlines, p)
+ elif os.path.isdir(p):
+ scan_git_subtree(repo.head.reference.commit.tree, p)
+ else:
+ sys.stderr.write('path %s does not exist\n' %p)
+ sys.exit(1)
+ else:
+ # Full git tree scan
+ scan_git_tree(repo.head.commit.tree)
+
+ if args.verbose:
+ sys.stderr.write('\n')
+ sys.stderr.write('License files: %12d\n' %spdx.license_files)
+ sys.stderr.write('Exception files: %12d\n' %spdx.exception_files)
+ sys.stderr.write('License IDs %12d\n' %len(spdx.licenses))
+ sys.stderr.write('Exception IDs %12d\n' %len(spdx.exceptions))
+ sys.stderr.write('\n')
+ sys.stderr.write('Files checked: %12d\n' %parser.checked)
+ sys.stderr.write('Lines checked: %12d\n' %parser.lines_checked)
+ sys.stderr.write('Files with SPDX: %12d\n' %parser.spdx_valid)
+ sys.stderr.write('Files with errors: %12d\n' %parser.spdx_errors)
+
+ sys.exit(0)
+
+ except Exception as ex:
+ sys.stderr.write('FAIL: %s\n' %ex)
+ sys.stderr.write('%s\n' %traceback.format_exc())
+ sys.exit(1)
diff --git a/scripts/split-man.pl b/scripts/split-man.pl
index bfe16cb..c3db607 100755
--- a/scripts/split-man.pl
+++ b/scripts/split-man.pl
@@ -1,7 +1,7 @@
#!/usr/bin/perl
# SPDX-License-Identifier: GPL-2.0
#
-# Author: Mauro Carvalho Chehab <mchehab@s-opensource.com>
+# Author: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
#
# Produce manpages from kernel-doc.
# See Documentation/doc-guide/kernel-doc.rst for instructions
diff --git a/security/commoncap.c b/security/commoncap.c
index 48620c9..f4c33ab 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -449,6 +449,8 @@ int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer,
magic |= VFS_CAP_FLAGS_EFFECTIVE;
memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
cap->magic_etc = cpu_to_le32(magic);
+ } else {
+ size = -ENOMEM;
}
}
kfree(tmpbuf);
@@ -917,6 +919,8 @@ int cap_bprm_set_creds(struct linux_binprm *bprm)
int cap_inode_setxattr(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
+ struct user_namespace *user_ns = dentry->d_sb->s_user_ns;
+
/* Ignore non-security xattrs */
if (strncmp(name, XATTR_SECURITY_PREFIX,
sizeof(XATTR_SECURITY_PREFIX) - 1) != 0)
@@ -929,7 +933,7 @@ int cap_inode_setxattr(struct dentry *dentry, const char *name,
if (strcmp(name, XATTR_NAME_CAPS) == 0)
return 0;
- if (!capable(CAP_SYS_ADMIN))
+ if (!ns_capable(user_ns, CAP_SYS_ADMIN))
return -EPERM;
return 0;
}
@@ -947,6 +951,8 @@ int cap_inode_setxattr(struct dentry *dentry, const char *name,
*/
int cap_inode_removexattr(struct dentry *dentry, const char *name)
{
+ struct user_namespace *user_ns = dentry->d_sb->s_user_ns;
+
/* Ignore non-security xattrs */
if (strncmp(name, XATTR_SECURITY_PREFIX,
sizeof(XATTR_SECURITY_PREFIX) - 1) != 0)
@@ -962,7 +968,7 @@ int cap_inode_removexattr(struct dentry *dentry, const char *name)
return 0;
}
- if (!capable(CAP_SYS_ADMIN))
+ if (!ns_capable(user_ns, CAP_SYS_ADMIN))
return -EPERM;
return 0;
}
diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c
index a46fba3..facf9cd 100644
--- a/security/integrity/evm/evm_crypto.c
+++ b/security/integrity/evm/evm_crypto.c
@@ -200,7 +200,8 @@ static int evm_calc_hmac_or_hash(struct dentry *dentry,
int size;
bool ima_present = false;
- if (!(inode->i_opflags & IOP_XATTR))
+ if (!(inode->i_opflags & IOP_XATTR) ||
+ inode->i_sb->s_user_ns != &init_user_ns)
return -EOPNOTSUPP;
desc = init_desc(type);
diff --git a/security/keys/proc.c b/security/keys/proc.c
index fbc4af5..5af2934 100644
--- a/security/keys/proc.c
+++ b/security/keys/proc.c
@@ -18,7 +18,6 @@
#include <asm/errno.h>
#include "internal.h"
-static int proc_keys_open(struct inode *inode, struct file *file);
static void *proc_keys_start(struct seq_file *p, loff_t *_pos);
static void *proc_keys_next(struct seq_file *p, void *v, loff_t *_pos);
static void proc_keys_stop(struct seq_file *p, void *v);
@@ -31,14 +30,6 @@ static const struct seq_operations proc_keys_ops = {
.show = proc_keys_show,
};
-static const struct file_operations proc_keys_fops = {
- .open = proc_keys_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-static int proc_key_users_open(struct inode *inode, struct file *file);
static void *proc_key_users_start(struct seq_file *p, loff_t *_pos);
static void *proc_key_users_next(struct seq_file *p, void *v, loff_t *_pos);
static void proc_key_users_stop(struct seq_file *p, void *v);
@@ -51,13 +42,6 @@ static const struct seq_operations proc_key_users_ops = {
.show = proc_key_users_show,
};
-static const struct file_operations proc_key_users_fops = {
- .open = proc_key_users_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
/*
* Declare the /proc files.
*/
@@ -65,11 +49,11 @@ static int __init key_proc_init(void)
{
struct proc_dir_entry *p;
- p = proc_create("keys", 0, NULL, &proc_keys_fops);
+ p = proc_create_seq("keys", 0, NULL, &proc_keys_ops);
if (!p)
panic("Cannot create /proc/keys\n");
- p = proc_create("key-users", 0, NULL, &proc_key_users_fops);
+ p = proc_create_seq("key-users", 0, NULL, &proc_key_users_ops);
if (!p)
panic("Cannot create /proc/key-users\n");
@@ -96,11 +80,6 @@ static struct rb_node *key_serial_next(struct seq_file *p, struct rb_node *n)
return n;
}
-static int proc_keys_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &proc_keys_ops);
-}
-
static struct key *find_ge_key(struct seq_file *p, key_serial_t id)
{
struct user_namespace *user_ns = seq_user_ns(p);
@@ -293,15 +272,6 @@ static struct rb_node *key_user_first(struct user_namespace *user_ns, struct rb_
return __key_user_next(user_ns, n);
}
-/*
- * Implement "/proc/key-users" to provides a list of the key users and their
- * quotas.
- */
-static int proc_key_users_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &proc_key_users_ops);
-}
-
static void *proc_key_users_start(struct seq_file *p, loff_t *_pos)
__acquires(key_user_lock)
{
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 4cafe6a..99c4675 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -274,11 +274,10 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent
* Try reloading inode security labels that have been marked as invalid. The
* @may_sleep parameter indicates when sleeping and thus reloading labels is
* allowed; when set to false, returns -ECHILD when the label is
- * invalid. The @opt_dentry parameter should be set to a dentry of the inode;
- * when no dentry is available, set it to NULL instead.
+ * invalid. The @dentry parameter should be set to a dentry of the inode.
*/
static int __inode_security_revalidate(struct inode *inode,
- struct dentry *opt_dentry,
+ struct dentry *dentry,
bool may_sleep)
{
struct inode_security_struct *isec = inode->i_security;
@@ -295,7 +294,7 @@ static int __inode_security_revalidate(struct inode *inode,
* @opt_dentry is NULL and no dentry for this inode can be
* found; in that case, continue using the old label.
*/
- inode_doinit_with_dentry(inode, opt_dentry);
+ inode_doinit_with_dentry(inode, dentry);
}
return 0;
}
@@ -1568,8 +1567,15 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent
/* Called from d_instantiate or d_splice_alias. */
dentry = dget(opt_dentry);
} else {
- /* Called from selinux_complete_init, try to find a dentry. */
+ /*
+ * Called from selinux_complete_init, try to find a dentry.
+ * Some filesystems really want a connected one, so try
+ * that first. We could split SECURITY_FS_USE_XATTR in
+ * two, depending upon that...
+ */
dentry = d_find_alias(inode);
+ if (!dentry)
+ dentry = d_find_any_alias(inode);
}
if (!dentry) {
/*
@@ -1674,14 +1680,19 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent
if ((sbsec->flags & SE_SBGENFS) && !S_ISLNK(inode->i_mode)) {
/* We must have a dentry to determine the label on
* procfs inodes */
- if (opt_dentry)
+ if (opt_dentry) {
/* Called from d_instantiate or
* d_splice_alias. */
dentry = dget(opt_dentry);
- else
+ } else {
/* Called from selinux_complete_init, try to
- * find a dentry. */
+ * find a dentry. Some filesystems really want
+ * a connected one, so try that first.
+ */
dentry = d_find_alias(inode);
+ if (!dentry)
+ dentry = d_find_any_alias(inode);
+ }
/*
* This can be hit on boot when a file is accessed
* before the policy is loaded. When we load policy we
@@ -4576,6 +4587,7 @@ static int selinux_socket_post_create(struct socket *sock, int family,
static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen)
{
struct sock *sk = sock->sk;
+ struct sk_security_struct *sksec = sk->sk_security;
u16 family;
int err;
@@ -4587,11 +4599,11 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
family = sk->sk_family;
if (family == PF_INET || family == PF_INET6) {
char *addrp;
- struct sk_security_struct *sksec = sk->sk_security;
struct common_audit_data ad;
struct lsm_network_audit net = {0,};
struct sockaddr_in *addr4 = NULL;
struct sockaddr_in6 *addr6 = NULL;
+ u16 family_sa = address->sa_family;
unsigned short snum;
u32 sid, node_perm;
@@ -4601,11 +4613,20 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
* need to check address->sa_family as it is possible to have
* sk->sk_family = PF_INET6 with addr->sa_family = AF_INET.
*/
- switch (address->sa_family) {
+ switch (family_sa) {
+ case AF_UNSPEC:
case AF_INET:
if (addrlen < sizeof(struct sockaddr_in))
return -EINVAL;
addr4 = (struct sockaddr_in *)address;
+ if (family_sa == AF_UNSPEC) {
+ /* see __inet_bind(), we only want to allow
+ * AF_UNSPEC if the address is INADDR_ANY
+ */
+ if (addr4->sin_addr.s_addr != htonl(INADDR_ANY))
+ goto err_af;
+ family_sa = AF_INET;
+ }
snum = ntohs(addr4->sin_port);
addrp = (char *)&addr4->sin_addr.s_addr;
break;
@@ -4617,15 +4638,14 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
addrp = (char *)&addr6->sin6_addr.s6_addr;
break;
default:
- /* Note that SCTP services expect -EINVAL, whereas
- * others expect -EAFNOSUPPORT.
- */
- if (sksec->sclass == SECCLASS_SCTP_SOCKET)
- return -EINVAL;
- else
- return -EAFNOSUPPORT;
+ goto err_af;
}
+ ad.type = LSM_AUDIT_DATA_NET;
+ ad.u.net = &net;
+ ad.u.net->sport = htons(snum);
+ ad.u.net->family = family_sa;
+
if (snum) {
int low, high;
@@ -4637,10 +4657,6 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
snum, &sid);
if (err)
goto out;
- ad.type = LSM_AUDIT_DATA_NET;
- ad.u.net = &net;
- ad.u.net->sport = htons(snum);
- ad.u.net->family = family;
err = avc_has_perm(&selinux_state,
sksec->sid, sid,
sksec->sclass,
@@ -4672,16 +4688,11 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
break;
}
- err = sel_netnode_sid(addrp, family, &sid);
+ err = sel_netnode_sid(addrp, family_sa, &sid);
if (err)
goto out;
- ad.type = LSM_AUDIT_DATA_NET;
- ad.u.net = &net;
- ad.u.net->sport = htons(snum);
- ad.u.net->family = family;
-
- if (address->sa_family == AF_INET)
+ if (family_sa == AF_INET)
ad.u.net->v4info.saddr = addr4->sin_addr.s_addr;
else
ad.u.net->v6info.saddr = addr6->sin6_addr;
@@ -4694,6 +4705,11 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
}
out:
return err;
+err_af:
+ /* Note that SCTP services expect -EINVAL, others -EAFNOSUPPORT. */
+ if (sksec->sclass == SECCLASS_SCTP_SOCKET)
+ return -EINVAL;
+ return -EAFNOSUPPORT;
}
/* This supports connect(2) and SCTP connect services such as sctp_connectx(3)
@@ -4771,7 +4787,7 @@ static int selinux_socket_connect_helper(struct socket *sock,
ad.type = LSM_AUDIT_DATA_NET;
ad.u.net = &net;
ad.u.net->dport = htons(snum);
- ad.u.net->family = sk->sk_family;
+ ad.u.net->family = address->sa_family;
err = avc_has_perm(&selinux_state,
sksec->sid, sid, sksec->sclass, perm, &ad);
if (err)
@@ -5272,6 +5288,7 @@ static int selinux_sctp_bind_connect(struct sock *sk, int optname,
while (walk_size < addrlen) {
addr = addr_buf;
switch (addr->sa_family) {
+ case AF_UNSPEC:
case AF_INET:
len = sizeof(struct sockaddr_in);
break;
@@ -5279,7 +5296,7 @@ static int selinux_sctp_bind_connect(struct sock *sk, int optname,
len = sizeof(struct sockaddr_in6);
break;
default:
- return -EAFNOSUPPORT;
+ return -EINVAL;
}
err = -EINVAL;
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 8057e19..3ce225e 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -1494,7 +1494,7 @@ static int security_context_to_sid_core(struct selinux_state *state,
scontext_len, &context, def_sid);
if (rc == -EINVAL && force) {
context.str = str;
- context.len = scontext_len;
+ context.len = strlen(str) + 1;
str = NULL;
} else if (rc)
goto out_unlock;
diff --git a/sound/core/control.c b/sound/core/control.c
index 69734b0..9aa15bf 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -1492,7 +1492,7 @@ static int snd_ctl_tlv_ioctl(struct snd_ctl_file *file,
int op_flag)
{
struct snd_ctl_tlv header;
- unsigned int *container;
+ unsigned int __user *container;
unsigned int container_size;
struct snd_kcontrol *kctl;
struct snd_ctl_elem_id id;
diff --git a/sound/core/control_compat.c b/sound/core/control_compat.c
index a848836..507fd52 100644
--- a/sound/core/control_compat.c
+++ b/sound/core/control_compat.c
@@ -396,8 +396,7 @@ static int snd_ctl_elem_add_compat(struct snd_ctl_file *file,
if (copy_from_user(&data->id, &data32->id, sizeof(data->id)) ||
copy_from_user(&data->type, &data32->type, 3 * sizeof(u32)))
goto error;
- if (get_user(data->owner, &data32->owner) ||
- get_user(data->type, &data32->type))
+ if (get_user(data->owner, &data32->owner))
goto error;
switch (data->type) {
case SNDRV_CTL_ELEM_TYPE_BOOLEAN:
diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c
index b719d0b..6491afb 100644
--- a/sound/core/pcm_compat.c
+++ b/sound/core/pcm_compat.c
@@ -27,10 +27,11 @@ static int snd_pcm_ioctl_delay_compat(struct snd_pcm_substream *substream,
s32 __user *src)
{
snd_pcm_sframes_t delay;
+ int err;
- delay = snd_pcm_delay(substream);
- if (delay < 0)
- return delay;
+ err = snd_pcm_delay(substream, &delay);
+ if (err)
+ return err;
if (put_user(delay, src))
return -EFAULT;
return 0;
@@ -422,6 +423,8 @@ static int snd_pcm_ioctl_xfern_compat(struct snd_pcm_substream *substream,
return -ENOTTY;
if (substream->stream != dir)
return -EINVAL;
+ if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN)
+ return -EBADFD;
if ((ch = substream->runtime->channels) > 128)
return -EINVAL;
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 35ffcce..0e875d5 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -2692,7 +2692,8 @@ static int snd_pcm_hwsync(struct snd_pcm_substream *substream)
return err;
}
-static snd_pcm_sframes_t snd_pcm_delay(struct snd_pcm_substream *substream)
+static int snd_pcm_delay(struct snd_pcm_substream *substream,
+ snd_pcm_sframes_t *delay)
{
struct snd_pcm_runtime *runtime = substream->runtime;
int err;
@@ -2708,7 +2709,9 @@ static snd_pcm_sframes_t snd_pcm_delay(struct snd_pcm_substream *substream)
n += runtime->delay;
}
snd_pcm_stream_unlock_irq(substream);
- return err < 0 ? err : n;
+ if (!err)
+ *delay = n;
+ return err;
}
static int snd_pcm_sync_ptr(struct snd_pcm_substream *substream,
@@ -2751,6 +2754,7 @@ static int snd_pcm_sync_ptr(struct snd_pcm_substream *substream,
sync_ptr.s.status.hw_ptr = status->hw_ptr;
sync_ptr.s.status.tstamp = status->tstamp;
sync_ptr.s.status.suspended_state = status->suspended_state;
+ sync_ptr.s.status.audio_tstamp = status->audio_tstamp;
snd_pcm_stream_unlock_irq(substream);
if (copy_to_user(_sync_ptr, &sync_ptr, sizeof(sync_ptr)))
return -EFAULT;
@@ -2916,11 +2920,13 @@ static int snd_pcm_common_ioctl(struct file *file,
return snd_pcm_hwsync(substream);
case SNDRV_PCM_IOCTL_DELAY:
{
- snd_pcm_sframes_t delay = snd_pcm_delay(substream);
+ snd_pcm_sframes_t delay;
snd_pcm_sframes_t __user *res = arg;
+ int err;
- if (delay < 0)
- return delay;
+ err = snd_pcm_delay(substream, &delay);
+ if (err)
+ return err;
if (put_user(delay, res))
return -EFAULT;
return 0;
@@ -3008,13 +3014,7 @@ int snd_pcm_kernel_ioctl(struct snd_pcm_substream *substream,
case SNDRV_PCM_IOCTL_DROP:
return snd_pcm_drop(substream);
case SNDRV_PCM_IOCTL_DELAY:
- {
- result = snd_pcm_delay(substream);
- if (result < 0)
- return result;
- *frames = result;
- return 0;
- }
+ return snd_pcm_delay(substream, frames);
default:
return -EINVAL;
}
@@ -3234,7 +3234,7 @@ static __poll_t snd_pcm_capture_poll(struct file *file, poll_table * wait)
/*
* mmap status record
*/
-static int snd_pcm_mmap_status_fault(struct vm_fault *vmf)
+static vm_fault_t snd_pcm_mmap_status_fault(struct vm_fault *vmf)
{
struct snd_pcm_substream *substream = vmf->vma->vm_private_data;
struct snd_pcm_runtime *runtime;
@@ -3270,7 +3270,7 @@ static int snd_pcm_mmap_status(struct snd_pcm_substream *substream, struct file
/*
* mmap control record
*/
-static int snd_pcm_mmap_control_fault(struct vm_fault *vmf)
+static vm_fault_t snd_pcm_mmap_control_fault(struct vm_fault *vmf)
{
struct snd_pcm_substream *substream = vmf->vma->vm_private_data;
struct snd_pcm_runtime *runtime;
@@ -3359,7 +3359,7 @@ snd_pcm_default_page_ops(struct snd_pcm_substream *substream, unsigned long ofs)
/*
* fault callback for mmapping a RAM page
*/
-static int snd_pcm_mmap_data_fault(struct vm_fault *vmf)
+static vm_fault_t snd_pcm_mmap_data_fault(struct vm_fault *vmf)
{
struct snd_pcm_substream *substream = vmf->vma->vm_private_data;
struct snd_pcm_runtime *runtime;
diff --git a/sound/core/rawmidi_compat.c b/sound/core/rawmidi_compat.c
index f69764d..e30e30b 100644
--- a/sound/core/rawmidi_compat.c
+++ b/sound/core/rawmidi_compat.c
@@ -36,8 +36,6 @@ static int snd_rawmidi_ioctl_params_compat(struct snd_rawmidi_file *rfile,
struct snd_rawmidi_params params;
unsigned int val;
- if (rfile->output == NULL)
- return -EINVAL;
if (get_user(params.stream, &src->stream) ||
get_user(params.buffer_size, &src->buffer_size) ||
get_user(params.avail_min, &src->avail_min) ||
@@ -46,8 +44,12 @@ static int snd_rawmidi_ioctl_params_compat(struct snd_rawmidi_file *rfile,
params.no_active_sensing = val;
switch (params.stream) {
case SNDRV_RAWMIDI_STREAM_OUTPUT:
+ if (!rfile->output)
+ return -EINVAL;
return snd_rawmidi_output_params(rfile->output, ¶ms);
case SNDRV_RAWMIDI_STREAM_INPUT:
+ if (!rfile->input)
+ return -EINVAL;
return snd_rawmidi_input_params(rfile->input, ¶ms);
}
return -EINVAL;
@@ -67,16 +69,18 @@ static int snd_rawmidi_ioctl_status_compat(struct snd_rawmidi_file *rfile,
int err;
struct snd_rawmidi_status status;
- if (rfile->output == NULL)
- return -EINVAL;
if (get_user(status.stream, &src->stream))
return -EFAULT;
switch (status.stream) {
case SNDRV_RAWMIDI_STREAM_OUTPUT:
+ if (!rfile->output)
+ return -EINVAL;
err = snd_rawmidi_output_status(rfile->output, &status);
break;
case SNDRV_RAWMIDI_STREAM_INPUT:
+ if (!rfile->input)
+ return -EINVAL;
err = snd_rawmidi_input_status(rfile->input, &status);
break;
default:
@@ -112,16 +116,18 @@ static int snd_rawmidi_ioctl_status_x32(struct snd_rawmidi_file *rfile,
int err;
struct snd_rawmidi_status status;
- if (rfile->output == NULL)
- return -EINVAL;
if (get_user(status.stream, &src->stream))
return -EFAULT;
switch (status.stream) {
case SNDRV_RAWMIDI_STREAM_OUTPUT:
+ if (!rfile->output)
+ return -EINVAL;
err = snd_rawmidi_output_status(rfile->output, &status);
break;
case SNDRV_RAWMIDI_STREAM_INPUT:
+ if (!rfile->input)
+ return -EINVAL;
err = snd_rawmidi_input_status(rfile->input, &status);
break;
default:
diff --git a/sound/core/seq/oss/seq_oss_event.c b/sound/core/seq/oss/seq_oss_event.c
index c390886..86ca584 100644
--- a/sound/core/seq/oss/seq_oss_event.c
+++ b/sound/core/seq/oss/seq_oss_event.c
@@ -26,6 +26,7 @@
#include <sound/seq_oss_legacy.h>
#include "seq_oss_readq.h"
#include "seq_oss_writeq.h"
+#include <linux/nospec.h>
/*
@@ -287,10 +288,10 @@ note_on_event(struct seq_oss_devinfo *dp, int dev, int ch, int note, int vel, st
{
struct seq_oss_synthinfo *info;
- if (!snd_seq_oss_synth_is_valid(dp, dev))
+ info = snd_seq_oss_synth_info(dp, dev);
+ if (!info)
return -ENXIO;
- info = &dp->synths[dev];
switch (info->arg.event_passing) {
case SNDRV_SEQ_OSS_PROCESS_EVENTS:
if (! info->ch || ch < 0 || ch >= info->nr_voices) {
@@ -298,6 +299,7 @@ note_on_event(struct seq_oss_devinfo *dp, int dev, int ch, int note, int vel, st
return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEON, ch, note, vel, ev);
}
+ ch = array_index_nospec(ch, info->nr_voices);
if (note == 255 && info->ch[ch].note >= 0) {
/* volume control */
int type;
@@ -347,10 +349,10 @@ note_off_event(struct seq_oss_devinfo *dp, int dev, int ch, int note, int vel, s
{
struct seq_oss_synthinfo *info;
- if (!snd_seq_oss_synth_is_valid(dp, dev))
+ info = snd_seq_oss_synth_info(dp, dev);
+ if (!info)
return -ENXIO;
- info = &dp->synths[dev];
switch (info->arg.event_passing) {
case SNDRV_SEQ_OSS_PROCESS_EVENTS:
if (! info->ch || ch < 0 || ch >= info->nr_voices) {
@@ -358,6 +360,7 @@ note_off_event(struct seq_oss_devinfo *dp, int dev, int ch, int note, int vel, s
return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEON, ch, note, vel, ev);
}
+ ch = array_index_nospec(ch, info->nr_voices);
if (info->ch[ch].note >= 0) {
note = info->ch[ch].note;
info->ch[ch].vel = 0;
@@ -381,7 +384,7 @@ note_off_event(struct seq_oss_devinfo *dp, int dev, int ch, int note, int vel, s
static int
set_note_event(struct seq_oss_devinfo *dp, int dev, int type, int ch, int note, int vel, struct snd_seq_event *ev)
{
- if (! snd_seq_oss_synth_is_valid(dp, dev))
+ if (!snd_seq_oss_synth_info(dp, dev))
return -ENXIO;
ev->type = type;
@@ -399,7 +402,7 @@ set_note_event(struct seq_oss_devinfo *dp, int dev, int type, int ch, int note,
static int
set_control_event(struct seq_oss_devinfo *dp, int dev, int type, int ch, int param, int val, struct snd_seq_event *ev)
{
- if (! snd_seq_oss_synth_is_valid(dp, dev))
+ if (!snd_seq_oss_synth_info(dp, dev))
return -ENXIO;
ev->type = type;
diff --git a/sound/core/seq/oss/seq_oss_midi.c b/sound/core/seq/oss/seq_oss_midi.c
index b30b213..9debd1b 100644
--- a/sound/core/seq/oss/seq_oss_midi.c
+++ b/sound/core/seq/oss/seq_oss_midi.c
@@ -29,6 +29,7 @@
#include "../seq_lock.h"
#include <linux/init.h>
#include <linux/slab.h>
+#include <linux/nospec.h>
/*
@@ -315,6 +316,7 @@ get_mididev(struct seq_oss_devinfo *dp, int dev)
{
if (dev < 0 || dev >= dp->max_mididev)
return NULL;
+ dev = array_index_nospec(dev, dp->max_mididev);
return get_mdev(dev);
}
diff --git a/sound/core/seq/oss/seq_oss_synth.c b/sound/core/seq/oss/seq_oss_synth.c
index cd0e0eb..278ebb9 100644
--- a/sound/core/seq/oss/seq_oss_synth.c
+++ b/sound/core/seq/oss/seq_oss_synth.c
@@ -26,6 +26,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/nospec.h>
/*
* constants
@@ -339,17 +340,13 @@ snd_seq_oss_synth_cleanup(struct seq_oss_devinfo *dp)
dp->max_synthdev = 0;
}
-/*
- * check if the specified device is MIDI mapped device
- */
-static int
-is_midi_dev(struct seq_oss_devinfo *dp, int dev)
+static struct seq_oss_synthinfo *
+get_synthinfo_nospec(struct seq_oss_devinfo *dp, int dev)
{
if (dev < 0 || dev >= dp->max_synthdev)
- return 0;
- if (dp->synths[dev].is_midi)
- return 1;
- return 0;
+ return NULL;
+ dev = array_index_nospec(dev, SNDRV_SEQ_OSS_MAX_SYNTH_DEVS);
+ return &dp->synths[dev];
}
/*
@@ -359,14 +356,20 @@ static struct seq_oss_synth *
get_synthdev(struct seq_oss_devinfo *dp, int dev)
{
struct seq_oss_synth *rec;
- if (dev < 0 || dev >= dp->max_synthdev)
+ struct seq_oss_synthinfo *info = get_synthinfo_nospec(dp, dev);
+
+ if (!info)
return NULL;
- if (! dp->synths[dev].opened)
+ if (!info->opened)
return NULL;
- if (dp->synths[dev].is_midi)
- return &midi_synth_dev;
- if ((rec = get_sdev(dev)) == NULL)
- return NULL;
+ if (info->is_midi) {
+ rec = &midi_synth_dev;
+ snd_use_lock_use(&rec->use_lock);
+ } else {
+ rec = get_sdev(dev);
+ if (!rec)
+ return NULL;
+ }
if (! rec->opened) {
snd_use_lock_free(&rec->use_lock);
return NULL;
@@ -402,10 +405,8 @@ snd_seq_oss_synth_reset(struct seq_oss_devinfo *dp, int dev)
struct seq_oss_synth *rec;
struct seq_oss_synthinfo *info;
- if (snd_BUG_ON(dev < 0 || dev >= dp->max_synthdev))
- return;
- info = &dp->synths[dev];
- if (! info->opened)
+ info = get_synthinfo_nospec(dp, dev);
+ if (!info || !info->opened)
return;
if (info->sysex)
info->sysex->len = 0; /* reset sysex */
@@ -454,12 +455,14 @@ snd_seq_oss_synth_load_patch(struct seq_oss_devinfo *dp, int dev, int fmt,
const char __user *buf, int p, int c)
{
struct seq_oss_synth *rec;
+ struct seq_oss_synthinfo *info;
int rc;
- if (dev < 0 || dev >= dp->max_synthdev)
+ info = get_synthinfo_nospec(dp, dev);
+ if (!info)
return -ENXIO;
- if (is_midi_dev(dp, dev))
+ if (info->is_midi)
return 0;
if ((rec = get_synthdev(dp, dev)) == NULL)
return -ENXIO;
@@ -467,24 +470,25 @@ snd_seq_oss_synth_load_patch(struct seq_oss_devinfo *dp, int dev, int fmt,
if (rec->oper.load_patch == NULL)
rc = -ENXIO;
else
- rc = rec->oper.load_patch(&dp->synths[dev].arg, fmt, buf, p, c);
+ rc = rec->oper.load_patch(&info->arg, fmt, buf, p, c);
snd_use_lock_free(&rec->use_lock);
return rc;
}
/*
- * check if the device is valid synth device
+ * check if the device is valid synth device and return the synth info
*/
-int
-snd_seq_oss_synth_is_valid(struct seq_oss_devinfo *dp, int dev)
+struct seq_oss_synthinfo *
+snd_seq_oss_synth_info(struct seq_oss_devinfo *dp, int dev)
{
struct seq_oss_synth *rec;
+
rec = get_synthdev(dp, dev);
if (rec) {
snd_use_lock_free(&rec->use_lock);
- return 1;
+ return get_synthinfo_nospec(dp, dev);
}
- return 0;
+ return NULL;
}
@@ -499,16 +503,18 @@ snd_seq_oss_synth_sysex(struct seq_oss_devinfo *dp, int dev, unsigned char *buf,
int i, send;
unsigned char *dest;
struct seq_oss_synth_sysex *sysex;
+ struct seq_oss_synthinfo *info;
- if (! snd_seq_oss_synth_is_valid(dp, dev))
+ info = snd_seq_oss_synth_info(dp, dev);
+ if (!info)
return -ENXIO;
- sysex = dp->synths[dev].sysex;
+ sysex = info->sysex;
if (sysex == NULL) {
sysex = kzalloc(sizeof(*sysex), GFP_KERNEL);
if (sysex == NULL)
return -ENOMEM;
- dp->synths[dev].sysex = sysex;
+ info->sysex = sysex;
}
send = 0;
@@ -553,10 +559,12 @@ snd_seq_oss_synth_sysex(struct seq_oss_devinfo *dp, int dev, unsigned char *buf,
int
snd_seq_oss_synth_addr(struct seq_oss_devinfo *dp, int dev, struct snd_seq_event *ev)
{
- if (! snd_seq_oss_synth_is_valid(dp, dev))
+ struct seq_oss_synthinfo *info = snd_seq_oss_synth_info(dp, dev);
+
+ if (!info)
return -EINVAL;
- snd_seq_oss_fill_addr(dp, ev, dp->synths[dev].arg.addr.client,
- dp->synths[dev].arg.addr.port);
+ snd_seq_oss_fill_addr(dp, ev, info->arg.addr.client,
+ info->arg.addr.port);
return 0;
}
@@ -568,16 +576,18 @@ int
snd_seq_oss_synth_ioctl(struct seq_oss_devinfo *dp, int dev, unsigned int cmd, unsigned long addr)
{
struct seq_oss_synth *rec;
+ struct seq_oss_synthinfo *info;
int rc;
- if (is_midi_dev(dp, dev))
+ info = get_synthinfo_nospec(dp, dev);
+ if (!info || info->is_midi)
return -ENXIO;
if ((rec = get_synthdev(dp, dev)) == NULL)
return -ENXIO;
if (rec->oper.ioctl == NULL)
rc = -ENXIO;
else
- rc = rec->oper.ioctl(&dp->synths[dev].arg, cmd, addr);
+ rc = rec->oper.ioctl(&info->arg, cmd, addr);
snd_use_lock_free(&rec->use_lock);
return rc;
}
@@ -589,7 +599,10 @@ snd_seq_oss_synth_ioctl(struct seq_oss_devinfo *dp, int dev, unsigned int cmd, u
int
snd_seq_oss_synth_raw_event(struct seq_oss_devinfo *dp, int dev, unsigned char *data, struct snd_seq_event *ev)
{
- if (! snd_seq_oss_synth_is_valid(dp, dev) || is_midi_dev(dp, dev))
+ struct seq_oss_synthinfo *info;
+
+ info = snd_seq_oss_synth_info(dp, dev);
+ if (!info || info->is_midi)
return -ENXIO;
ev->type = SNDRV_SEQ_EVENT_OSS;
memcpy(ev->data.raw8.d, data, 8);
diff --git a/sound/core/seq/oss/seq_oss_synth.h b/sound/core/seq/oss/seq_oss_synth.h
index 74ac55f..a63f9e2 100644
--- a/sound/core/seq/oss/seq_oss_synth.h
+++ b/sound/core/seq/oss/seq_oss_synth.h
@@ -37,7 +37,8 @@ void snd_seq_oss_synth_cleanup(struct seq_oss_devinfo *dp);
void snd_seq_oss_synth_reset(struct seq_oss_devinfo *dp, int dev);
int snd_seq_oss_synth_load_patch(struct seq_oss_devinfo *dp, int dev, int fmt,
const char __user *buf, int p, int c);
-int snd_seq_oss_synth_is_valid(struct seq_oss_devinfo *dp, int dev);
+struct seq_oss_synthinfo *snd_seq_oss_synth_info(struct seq_oss_devinfo *dp,
+ int dev);
int snd_seq_oss_synth_sysex(struct seq_oss_devinfo *dp, int dev, unsigned char *buf,
struct snd_seq_event *ev);
int snd_seq_oss_synth_addr(struct seq_oss_devinfo *dp, int dev, struct snd_seq_event *ev);
diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c
index f48a4cd..289ae6b 100644
--- a/sound/core/seq/seq_virmidi.c
+++ b/sound/core/seq/seq_virmidi.c
@@ -174,12 +174,12 @@ static void snd_virmidi_output_trigger(struct snd_rawmidi_substream *substream,
}
return;
}
+ spin_lock_irqsave(&substream->runtime->lock, flags);
if (vmidi->event.type != SNDRV_SEQ_EVENT_NONE) {
if (snd_seq_kernel_client_dispatch(vmidi->client, &vmidi->event, in_atomic(), 0) < 0)
- return;
+ goto out;
vmidi->event.type = SNDRV_SEQ_EVENT_NONE;
}
- spin_lock_irqsave(&substream->runtime->lock, flags);
while (1) {
count = __snd_rawmidi_transmit_peek(substream, buf, sizeof(buf));
if (count <= 0)
diff --git a/sound/core/timer.c b/sound/core/timer.c
index dc87728..0ddcae4 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -592,7 +592,7 @@ static int snd_timer_stop1(struct snd_timer_instance *timeri, bool stop)
else
timeri->flags |= SNDRV_TIMER_IFLG_PAUSED;
snd_timer_notify1(timeri, stop ? SNDRV_TIMER_EVENT_STOP :
- SNDRV_TIMER_EVENT_CONTINUE);
+ SNDRV_TIMER_EVENT_PAUSE);
unlock:
spin_unlock_irqrestore(&timer->lock, flags);
return result;
@@ -614,7 +614,7 @@ static int snd_timer_stop_slave(struct snd_timer_instance *timeri, bool stop)
list_del_init(&timeri->ack_list);
list_del_init(&timeri->active_list);
snd_timer_notify1(timeri, stop ? SNDRV_TIMER_EVENT_STOP :
- SNDRV_TIMER_EVENT_CONTINUE);
+ SNDRV_TIMER_EVENT_PAUSE);
spin_unlock(&timeri->timer->lock);
}
spin_unlock_irqrestore(&slave_active_lock, flags);
diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c
index 58e349f..eab7f59 100644
--- a/sound/drivers/aloop.c
+++ b/sound/drivers/aloop.c
@@ -831,9 +831,11 @@ static int loopback_rate_shift_get(struct snd_kcontrol *kcontrol,
{
struct loopback *loopback = snd_kcontrol_chip(kcontrol);
+ mutex_lock(&loopback->cable_lock);
ucontrol->value.integer.value[0] =
loopback->setup[kcontrol->id.subdevice]
[kcontrol->id.device].rate_shift;
+ mutex_unlock(&loopback->cable_lock);
return 0;
}
@@ -865,9 +867,11 @@ static int loopback_notify_get(struct snd_kcontrol *kcontrol,
{
struct loopback *loopback = snd_kcontrol_chip(kcontrol);
+ mutex_lock(&loopback->cable_lock);
ucontrol->value.integer.value[0] =
loopback->setup[kcontrol->id.subdevice]
[kcontrol->id.device].notify;
+ mutex_unlock(&loopback->cable_lock);
return 0;
}
@@ -879,12 +883,14 @@ static int loopback_notify_put(struct snd_kcontrol *kcontrol,
int change = 0;
val = ucontrol->value.integer.value[0] ? 1 : 0;
+ mutex_lock(&loopback->cable_lock);
if (val != loopback->setup[kcontrol->id.subdevice]
[kcontrol->id.device].notify) {
loopback->setup[kcontrol->id.subdevice]
[kcontrol->id.device].notify = val;
change = 1;
}
+ mutex_unlock(&loopback->cable_lock);
return change;
}
@@ -892,15 +898,18 @@ static int loopback_active_get(struct snd_kcontrol *kcontrol,
struct snd_ctl_elem_value *ucontrol)
{
struct loopback *loopback = snd_kcontrol_chip(kcontrol);
- struct loopback_cable *cable = loopback->cables
- [kcontrol->id.subdevice][kcontrol->id.device ^ 1];
+ struct loopback_cable *cable;
+
unsigned int val = 0;
+ mutex_lock(&loopback->cable_lock);
+ cable = loopback->cables[kcontrol->id.subdevice][kcontrol->id.device ^ 1];
if (cable != NULL) {
unsigned int running = cable->running ^ cable->pause;
val = (running & (1 << SNDRV_PCM_STREAM_PLAYBACK)) ? 1 : 0;
}
+ mutex_unlock(&loopback->cable_lock);
ucontrol->value.integer.value[0] = val;
return 0;
}
@@ -943,9 +952,11 @@ static int loopback_rate_get(struct snd_kcontrol *kcontrol,
{
struct loopback *loopback = snd_kcontrol_chip(kcontrol);
+ mutex_lock(&loopback->cable_lock);
ucontrol->value.integer.value[0] =
loopback->setup[kcontrol->id.subdevice]
[kcontrol->id.device].rate;
+ mutex_unlock(&loopback->cable_lock);
return 0;
}
@@ -965,9 +976,11 @@ static int loopback_channels_get(struct snd_kcontrol *kcontrol,
{
struct loopback *loopback = snd_kcontrol_chip(kcontrol);
+ mutex_lock(&loopback->cable_lock);
ucontrol->value.integer.value[0] =
loopback->setup[kcontrol->id.subdevice]
[kcontrol->id.device].channels;
+ mutex_unlock(&loopback->cable_lock);
return 0;
}
diff --git a/sound/drivers/opl3/opl3_synth.c b/sound/drivers/opl3/opl3_synth.c
index ddcc1a3..42920a2 100644
--- a/sound/drivers/opl3/opl3_synth.c
+++ b/sound/drivers/opl3/opl3_synth.c
@@ -21,6 +21,7 @@
#include <linux/slab.h>
#include <linux/export.h>
+#include <linux/nospec.h>
#include <sound/opl3.h>
#include <sound/asound_fm.h>
@@ -448,7 +449,7 @@ static int snd_opl3_set_voice(struct snd_opl3 * opl3, struct snd_dm_fm_voice * v
{
unsigned short reg_side;
unsigned char op_offset;
- unsigned char voice_offset;
+ unsigned char voice_offset, voice_op;
unsigned short opl3_reg;
unsigned char reg_val;
@@ -473,7 +474,9 @@ static int snd_opl3_set_voice(struct snd_opl3 * opl3, struct snd_dm_fm_voice * v
voice_offset = voice->voice - MAX_OPL2_VOICES;
}
/* Get register offset of operator */
- op_offset = snd_opl3_regmap[voice_offset][voice->op];
+ voice_offset = array_index_nospec(voice_offset, MAX_OPL2_VOICES);
+ voice_op = array_index_nospec(voice->op, 4);
+ op_offset = snd_opl3_regmap[voice_offset][voice_op];
reg_val = 0x00;
/* Set amplitude modulation (tremolo) effect */
diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c
index 4a1dc14..cb9acfe 100644
--- a/sound/firewire/amdtp-stream.c
+++ b/sound/firewire/amdtp-stream.c
@@ -773,8 +773,6 @@ static void amdtp_stream_first_callback(struct fw_iso_context *context,
u32 cycle;
unsigned int packets;
- s->max_payload_length = amdtp_stream_get_max_payload(s);
-
/*
* For in-stream, first packet has come.
* For out-stream, prepared to transmit first packet
@@ -879,6 +877,9 @@ int amdtp_stream_start(struct amdtp_stream *s, int channel, int speed)
amdtp_stream_update(s);
+ if (s->direction == AMDTP_IN_STREAM)
+ s->max_payload_length = amdtp_stream_get_max_payload(s);
+
if (s->flags & CIP_NO_HEADER)
s->tag = TAG_NO_CIP_HEADER;
else
diff --git a/sound/firewire/dice/dice-stream.c b/sound/firewire/dice/dice-stream.c
index 8573289..928a255 100644
--- a/sound/firewire/dice/dice-stream.c
+++ b/sound/firewire/dice/dice-stream.c
@@ -435,7 +435,7 @@ int snd_dice_stream_init_duplex(struct snd_dice *dice)
err = init_stream(dice, AMDTP_IN_STREAM, i);
if (err < 0) {
for (; i >= 0; i--)
- destroy_stream(dice, AMDTP_OUT_STREAM, i);
+ destroy_stream(dice, AMDTP_IN_STREAM, i);
goto end;
}
}
diff --git a/sound/firewire/dice/dice.c b/sound/firewire/dice/dice.c
index 4ddb4cd..96bb01b 100644
--- a/sound/firewire/dice/dice.c
+++ b/sound/firewire/dice/dice.c
@@ -14,7 +14,7 @@ MODULE_LICENSE("GPL v2");
#define OUI_WEISS 0x001c6a
#define OUI_LOUD 0x000ff2
#define OUI_FOCUSRITE 0x00130e
-#define OUI_TCELECTRONIC 0x001486
+#define OUI_TCELECTRONIC 0x000166
#define DICE_CATEGORY_ID 0x04
#define WEISS_CATEGORY_ID 0x00
diff --git a/sound/pci/asihpi/hpimsginit.c b/sound/pci/asihpi/hpimsginit.c
index 7eb6171..a31a70d 100644
--- a/sound/pci/asihpi/hpimsginit.c
+++ b/sound/pci/asihpi/hpimsginit.c
@@ -23,6 +23,7 @@
#include "hpi_internal.h"
#include "hpimsginit.h"
+#include <linux/nospec.h>
/* The actual message size for each object type */
static u16 msg_size[HPI_OBJ_MAXINDEX + 1] = HPI_MESSAGE_SIZE_BY_OBJECT;
@@ -39,10 +40,12 @@ static void hpi_init_message(struct hpi_message *phm, u16 object,
{
u16 size;
- if ((object > 0) && (object <= HPI_OBJ_MAXINDEX))
+ if ((object > 0) && (object <= HPI_OBJ_MAXINDEX)) {
+ object = array_index_nospec(object, HPI_OBJ_MAXINDEX + 1);
size = msg_size[object];
- else
+ } else {
size = sizeof(*phm);
+ }
memset(phm, 0, size);
phm->size = size;
@@ -66,10 +69,12 @@ void hpi_init_response(struct hpi_response *phr, u16 object, u16 function,
{
u16 size;
- if ((object > 0) && (object <= HPI_OBJ_MAXINDEX))
+ if ((object > 0) && (object <= HPI_OBJ_MAXINDEX)) {
+ object = array_index_nospec(object, HPI_OBJ_MAXINDEX + 1);
size = res_size[object];
- else
+ } else {
size = sizeof(*phr);
+ }
memset(phr, 0, sizeof(*phr));
phr->size = size;
diff --git a/sound/pci/asihpi/hpioctl.c b/sound/pci/asihpi/hpioctl.c
index 5badd08..b1a2a7e 100644
--- a/sound/pci/asihpi/hpioctl.c
+++ b/sound/pci/asihpi/hpioctl.c
@@ -33,6 +33,7 @@
#include <linux/stringify.h>
#include <linux/module.h>
#include <linux/vmalloc.h>
+#include <linux/nospec.h>
#ifdef MODULE_FIRMWARE
MODULE_FIRMWARE("asihpi/dsp5000.bin");
@@ -186,7 +187,8 @@ long asihpi_hpi_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
struct hpi_adapter *pa = NULL;
if (hm->h.adapter_index < ARRAY_SIZE(adapters))
- pa = &adapters[hm->h.adapter_index];
+ pa = &adapters[array_index_nospec(hm->h.adapter_index,
+ ARRAY_SIZE(adapters))];
if (!pa || !pa->adapter || !pa->adapter->type) {
hpi_init_response(&hr->r0, hm->h.object,
diff --git a/sound/pci/hda/hda_hwdep.c b/sound/pci/hda/hda_hwdep.c
index 57df06e..cc009a4 100644
--- a/sound/pci/hda/hda_hwdep.c
+++ b/sound/pci/hda/hda_hwdep.c
@@ -21,6 +21,7 @@
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/compat.h>
+#include <linux/nospec.h>
#include <sound/core.h>
#include "hda_codec.h"
#include "hda_local.h"
@@ -51,7 +52,16 @@ static int get_wcap_ioctl(struct hda_codec *codec,
if (get_user(verb, &arg->verb))
return -EFAULT;
- res = get_wcaps(codec, verb >> 24);
+ /* open-code get_wcaps(verb>>24) with nospec */
+ verb >>= 24;
+ if (verb < codec->core.start_nid ||
+ verb >= codec->core.start_nid + codec->core.num_nodes) {
+ res = 0;
+ } else {
+ verb -= codec->core.start_nid;
+ verb = array_index_nospec(verb, codec->core.num_nodes);
+ res = codec->wcaps[verb];
+ }
if (put_user(res, &arg->res))
return -EFAULT;
return 0;
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 7a111a1..a0c93b9 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1647,7 +1647,8 @@ static void azx_check_snoop_available(struct azx *chip)
*/
u8 val;
pci_read_config_byte(chip->pci, 0x42, &val);
- if (!(val & 0x80) && chip->pci->revision == 0x30)
+ if (!(val & 0x80) && (chip->pci->revision == 0x30 ||
+ chip->pci->revision == 0x20))
snoop = false;
}
@@ -2209,6 +2210,8 @@ static struct snd_pci_quirk power_save_blacklist[] = {
SND_PCI_QUIRK(0x1849, 0x0c0c, "Asrock B85M-ITX", 0),
/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
SND_PCI_QUIRK(0x1043, 0x8733, "Asus Prime X370-Pro", 0),
+ /* https://bugzilla.redhat.com/show_bug.cgi?id=1572975 */
+ SND_PCI_QUIRK(0x17aa, 0x36a7, "Lenovo C50 All in one", 0),
/* https://bugzilla.kernel.org/show_bug.cgi?id=198611 */
SND_PCI_QUIRK(0x17aa, 0x2227, "Lenovo X1 Carbon 3rd Gen", 0),
{}
diff --git a/sound/pci/hda/hda_local.h b/sound/pci/hda/hda_local.h
index 321e78b..9bd9352 100644
--- a/sound/pci/hda/hda_local.h
+++ b/sound/pci/hda/hda_local.h
@@ -622,8 +622,10 @@ snd_hda_check_power_state(struct hda_codec *codec, hda_nid_t nid,
{
return snd_hdac_check_power_state(&codec->core, nid, target_state);
}
-static inline bool snd_hda_sync_power_state(struct hda_codec *codec,
- hda_nid_t nid, unsigned int target_state)
+
+static inline unsigned int snd_hda_sync_power_state(struct hda_codec *codec,
+ hda_nid_t nid,
+ unsigned int target_state)
{
return snd_hdac_sync_power_state(&codec->core, nid, target_state);
}
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index b4f1b6e..7d7eb13 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -1383,6 +1383,8 @@ static void hdmi_pcm_setup_pin(struct hdmi_spec *spec,
pcm = get_pcm_rec(spec, per_pin->pcm_idx);
else
return;
+ if (!pcm->pcm)
+ return;
if (!test_bit(per_pin->pcm_idx, &spec->pcm_in_use))
return;
@@ -2151,8 +2153,13 @@ static int generic_hdmi_build_controls(struct hda_codec *codec)
int dev, err;
int pin_idx, pcm_idx;
-
for (pcm_idx = 0; pcm_idx < spec->pcm_used; pcm_idx++) {
+ if (!get_pcm_rec(spec, pcm_idx)->pcm) {
+ /* no PCM: mark this for skipping permanently */
+ set_bit(pcm_idx, &spec->pcm_bitmap);
+ continue;
+ }
+
err = generic_hdmi_build_jack(codec, pcm_idx);
if (err < 0)
return err;
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index aef1f52..01a6643 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -331,6 +331,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
/* fallthrough */
case 0x10ec0215:
case 0x10ec0233:
+ case 0x10ec0235:
case 0x10ec0236:
case 0x10ec0255:
case 0x10ec0256:
@@ -2362,6 +2363,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX),
SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950),
+ SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD),
SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD),
SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Y530", ALC882_FIXUP_LENOVO_Y530),
@@ -3831,7 +3833,7 @@ static void alc280_fixup_hp_gpio4(struct hda_codec *codec,
}
}
-#if IS_REACHABLE(INPUT)
+#if IS_REACHABLE(CONFIG_INPUT)
static void gpio2_mic_hotkey_event(struct hda_codec *codec,
struct hda_jack_callback *event)
{
@@ -6370,6 +6372,8 @@ static const struct hda_fixup alc269_fixups[] = {
{ 0x19, 0x01a1913c }, /* use as headset mic, without its own jack detect */
{ }
},
+ .chained = true,
+ .chain_id = ALC269_FIXUP_HEADSET_MIC
},
};
@@ -6573,6 +6577,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
+ SND_PCI_QUIRK(0x17aa, 0x312f, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
+ SND_PCI_QUIRK(0x17aa, 0x3138, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
SND_PCI_QUIRK(0x17aa, 0x313c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
SND_PCI_QUIRK(0x17aa, 0x3112, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
@@ -7157,8 +7163,11 @@ static int patch_alc269(struct hda_codec *codec)
case 0x10ec0298:
spec->codec_variant = ALC269_TYPE_ALC298;
break;
+ case 0x10ec0235:
case 0x10ec0255:
spec->codec_variant = ALC269_TYPE_ALC255;
+ spec->shutup = alc256_shutup;
+ spec->init_hook = alc256_init;
break;
case 0x10ec0236:
case 0x10ec0256:
diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c
index 4c59983..11b5b5e0 100644
--- a/sound/pci/rme9652/hdspm.c
+++ b/sound/pci/rme9652/hdspm.c
@@ -137,6 +137,7 @@
#include <linux/pci.h>
#include <linux/math64.h>
#include <linux/io.h>
+#include <linux/nospec.h>
#include <sound/core.h>
#include <sound/control.h>
@@ -5698,40 +5699,43 @@ static int snd_hdspm_channel_info(struct snd_pcm_substream *substream,
struct snd_pcm_channel_info *info)
{
struct hdspm *hdspm = snd_pcm_substream_chip(substream);
+ unsigned int channel = info->channel;
if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
- if (snd_BUG_ON(info->channel >= hdspm->max_channels_out)) {
+ if (snd_BUG_ON(channel >= hdspm->max_channels_out)) {
dev_info(hdspm->card->dev,
"snd_hdspm_channel_info: output channel out of range (%d)\n",
- info->channel);
+ channel);
return -EINVAL;
}
- if (hdspm->channel_map_out[info->channel] < 0) {
+ channel = array_index_nospec(channel, hdspm->max_channels_out);
+ if (hdspm->channel_map_out[channel] < 0) {
dev_info(hdspm->card->dev,
"snd_hdspm_channel_info: output channel %d mapped out\n",
- info->channel);
+ channel);
return -EINVAL;
}
- info->offset = hdspm->channel_map_out[info->channel] *
+ info->offset = hdspm->channel_map_out[channel] *
HDSPM_CHANNEL_BUFFER_BYTES;
} else {
- if (snd_BUG_ON(info->channel >= hdspm->max_channels_in)) {
+ if (snd_BUG_ON(channel >= hdspm->max_channels_in)) {
dev_info(hdspm->card->dev,
"snd_hdspm_channel_info: input channel out of range (%d)\n",
- info->channel);
+ channel);
return -EINVAL;
}
- if (hdspm->channel_map_in[info->channel] < 0) {
+ channel = array_index_nospec(channel, hdspm->max_channels_in);
+ if (hdspm->channel_map_in[channel] < 0) {
dev_info(hdspm->card->dev,
"snd_hdspm_channel_info: input channel %d mapped out\n",
- info->channel);
+ channel);
return -EINVAL;
}
- info->offset = hdspm->channel_map_in[info->channel] *
+ info->offset = hdspm->channel_map_in[channel] *
HDSPM_CHANNEL_BUFFER_BYTES;
}
diff --git a/sound/pci/rme9652/rme9652.c b/sound/pci/rme9652/rme9652.c
index df648b1..edd765e 100644
--- a/sound/pci/rme9652/rme9652.c
+++ b/sound/pci/rme9652/rme9652.c
@@ -26,6 +26,7 @@
#include <linux/pci.h>
#include <linux/module.h>
#include <linux/io.h>
+#include <linux/nospec.h>
#include <sound/core.h>
#include <sound/control.h>
@@ -2071,9 +2072,10 @@ static int snd_rme9652_channel_info(struct snd_pcm_substream *substream,
if (snd_BUG_ON(info->channel >= RME9652_NCHANNELS))
return -EINVAL;
- if ((chn = rme9652->channel_map[info->channel]) < 0) {
+ chn = rme9652->channel_map[array_index_nospec(info->channel,
+ RME9652_NCHANNELS)];
+ if (chn < 0)
return -EINVAL;
- }
info->offset = chn * RME9652_CHANNEL_BUFFER_BYTES;
info->first = 0;
diff --git a/sound/soc/amd/acp-da7219-max98357a.c b/sound/soc/amd/acp-da7219-max98357a.c
index b205c78..f41560e 100644
--- a/sound/soc/amd/acp-da7219-max98357a.c
+++ b/sound/soc/amd/acp-da7219-max98357a.c
@@ -43,7 +43,7 @@
#define DUAL_CHANNEL 2
static struct snd_soc_jack cz_jack;
-struct clk *da7219_dai_clk;
+static struct clk *da7219_dai_clk;
static int cz_da7219_init(struct snd_soc_pcm_runtime *rtd)
{
diff --git a/sound/soc/codecs/adau17x1.c b/sound/soc/codecs/adau17x1.c
index 80c2a06..12bf24c 100644
--- a/sound/soc/codecs/adau17x1.c
+++ b/sound/soc/codecs/adau17x1.c
@@ -502,7 +502,7 @@ static int adau17x1_hw_params(struct snd_pcm_substream *substream,
}
if (adau->sigmadsp) {
- ret = adau17x1_setup_firmware(adau, params_rate(params));
+ ret = adau17x1_setup_firmware(component, params_rate(params));
if (ret < 0)
return ret;
}
@@ -835,26 +835,40 @@ bool adau17x1_volatile_register(struct device *dev, unsigned int reg)
}
EXPORT_SYMBOL_GPL(adau17x1_volatile_register);
-int adau17x1_setup_firmware(struct adau *adau, unsigned int rate)
+int adau17x1_setup_firmware(struct snd_soc_component *component,
+ unsigned int rate)
{
int ret;
- int dspsr;
+ int dspsr, dsp_run;
+ struct adau *adau = snd_soc_component_get_drvdata(component);
+ struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(component);
+
+ snd_soc_dapm_mutex_lock(dapm);
ret = regmap_read(adau->regmap, ADAU17X1_DSP_SAMPLING_RATE, &dspsr);
if (ret)
- return ret;
+ goto err;
+
+ ret = regmap_read(adau->regmap, ADAU17X1_DSP_RUN, &dsp_run);
+ if (ret)
+ goto err;
regmap_write(adau->regmap, ADAU17X1_DSP_ENABLE, 1);
regmap_write(adau->regmap, ADAU17X1_DSP_SAMPLING_RATE, 0xf);
+ regmap_write(adau->regmap, ADAU17X1_DSP_RUN, 0);
ret = sigmadsp_setup(adau->sigmadsp, rate);
if (ret) {
regmap_write(adau->regmap, ADAU17X1_DSP_ENABLE, 0);
- return ret;
+ goto err;
}
regmap_write(adau->regmap, ADAU17X1_DSP_SAMPLING_RATE, dspsr);
+ regmap_write(adau->regmap, ADAU17X1_DSP_RUN, dsp_run);
- return 0;
+err:
+ snd_soc_dapm_mutex_unlock(dapm);
+
+ return ret;
}
EXPORT_SYMBOL_GPL(adau17x1_setup_firmware);
diff --git a/sound/soc/codecs/adau17x1.h b/sound/soc/codecs/adau17x1.h
index a7b1cb7..e6fe87b 100644
--- a/sound/soc/codecs/adau17x1.h
+++ b/sound/soc/codecs/adau17x1.h
@@ -68,7 +68,8 @@ int adau17x1_resume(struct snd_soc_component *component);
extern const struct snd_soc_dai_ops adau17x1_dai_ops;
-int adau17x1_setup_firmware(struct adau *adau, unsigned int rate);
+int adau17x1_setup_firmware(struct snd_soc_component *component,
+ unsigned int rate);
bool adau17x1_has_dsp(struct adau *adau);
#define ADAU17X1_CLOCK_CONTROL 0x4000
diff --git a/sound/soc/codecs/msm8916-wcd-analog.c b/sound/soc/codecs/msm8916-wcd-analog.c
index 12ee83d..b7cf7cc 100644
--- a/sound/soc/codecs/msm8916-wcd-analog.c
+++ b/sound/soc/codecs/msm8916-wcd-analog.c
@@ -1187,7 +1187,8 @@ static int pm8916_wcd_analog_spmi_probe(struct platform_device *pdev)
return irq;
}
- ret = devm_request_irq(dev, irq, pm8916_mbhc_switch_irq_handler,
+ ret = devm_request_threaded_irq(dev, irq, NULL,
+ pm8916_mbhc_switch_irq_handler,
IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING |
IRQF_ONESHOT,
"mbhc switch irq", priv);
@@ -1201,7 +1202,8 @@ static int pm8916_wcd_analog_spmi_probe(struct platform_device *pdev)
return irq;
}
- ret = devm_request_irq(dev, irq, mbhc_btn_press_irq_handler,
+ ret = devm_request_threaded_irq(dev, irq, NULL,
+ mbhc_btn_press_irq_handler,
IRQF_TRIGGER_RISING |
IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
"mbhc btn press irq", priv);
@@ -1214,7 +1216,8 @@ static int pm8916_wcd_analog_spmi_probe(struct platform_device *pdev)
return irq;
}
- ret = devm_request_irq(dev, irq, mbhc_btn_release_irq_handler,
+ ret = devm_request_threaded_irq(dev, irq, NULL,
+ mbhc_btn_release_irq_handler,
IRQF_TRIGGER_RISING |
IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
"mbhc btn release irq", priv);
diff --git a/sound/soc/codecs/rt5514.c b/sound/soc/codecs/rt5514.c
index e8a66b0..1570b91 100644
--- a/sound/soc/codecs/rt5514.c
+++ b/sound/soc/codecs/rt5514.c
@@ -89,6 +89,7 @@ static const struct reg_default rt5514_reg[] = {
{RT5514_PLL3_CALIB_CTRL5, 0x40220012},
{RT5514_DELAY_BUF_CTRL1, 0x7fff006a},
{RT5514_DELAY_BUF_CTRL3, 0x00000000},
+ {RT5514_ASRC_IN_CTRL1, 0x00000003},
{RT5514_DOWNFILTER0_CTRL1, 0x00020c2f},
{RT5514_DOWNFILTER0_CTRL2, 0x00020c2f},
{RT5514_DOWNFILTER0_CTRL3, 0x10000362},
@@ -181,6 +182,7 @@ static bool rt5514_readable_register(struct device *dev, unsigned int reg)
case RT5514_PLL3_CALIB_CTRL5:
case RT5514_DELAY_BUF_CTRL1:
case RT5514_DELAY_BUF_CTRL3:
+ case RT5514_ASRC_IN_CTRL1:
case RT5514_DOWNFILTER0_CTRL1:
case RT5514_DOWNFILTER0_CTRL2:
case RT5514_DOWNFILTER0_CTRL3:
@@ -238,6 +240,7 @@ static bool rt5514_i2c_readable_register(struct device *dev,
case RT5514_DSP_MAPPING | RT5514_PLL3_CALIB_CTRL5:
case RT5514_DSP_MAPPING | RT5514_DELAY_BUF_CTRL1:
case RT5514_DSP_MAPPING | RT5514_DELAY_BUF_CTRL3:
+ case RT5514_DSP_MAPPING | RT5514_ASRC_IN_CTRL1:
case RT5514_DSP_MAPPING | RT5514_DOWNFILTER0_CTRL1:
case RT5514_DSP_MAPPING | RT5514_DOWNFILTER0_CTRL2:
case RT5514_DSP_MAPPING | RT5514_DOWNFILTER0_CTRL3:
diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c
index 40a7004..da8fd98 100644
--- a/sound/soc/fsl/fsl_esai.c
+++ b/sound/soc/fsl/fsl_esai.c
@@ -144,6 +144,13 @@ static int fsl_esai_divisor_cal(struct snd_soc_dai *dai, bool tx, u32 ratio,
psr = ratio <= 256 * maxfp ? ESAI_xCCR_xPSR_BYPASS : ESAI_xCCR_xPSR_DIV8;
+ /* Do not loop-search if PM (1 ~ 256) alone can serve the ratio */
+ if (ratio <= 256) {
+ pm = ratio;
+ fp = 1;
+ goto out;
+ }
+
/* Set the max fluctuation -- 0.1% of the max devisor */
savesub = (psr ? 1 : 8) * 256 * maxfp / 1000;
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index 0823b08..89df2d9 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -217,6 +217,7 @@ struct fsl_ssi_soc_data {
* @dai_fmt: DAI configuration this device is currently used with
* @streams: Mask of current active streams: BIT(TX) and BIT(RX)
* @i2s_net: I2S and Network mode configurations of SCR register
+ * (this is the initial settings based on the DAI format)
* @synchronous: Use synchronous mode - both of TX and RX use STCK and SFCK
* @use_dma: DMA is used or FIQ with stream filter
* @use_dual_fifo: DMA with support for dual FIFO mode
@@ -829,16 +830,23 @@ static int fsl_ssi_hw_params(struct snd_pcm_substream *substream,
}
if (!fsl_ssi_is_ac97(ssi)) {
+ /*
+ * Keep the ssi->i2s_net intact while having a local variable
+ * to override settings for special use cases. Otherwise, the
+ * ssi->i2s_net will lose the settings for regular use cases.
+ */
+ u8 i2s_net = ssi->i2s_net;
+
/* Normal + Network mode to send 16-bit data in 32-bit frames */
if (fsl_ssi_is_i2s_cbm_cfs(ssi) && sample_size == 16)
- ssi->i2s_net = SSI_SCR_I2S_MODE_NORMAL | SSI_SCR_NET;
+ i2s_net = SSI_SCR_I2S_MODE_NORMAL | SSI_SCR_NET;
/* Use Normal mode to send mono data at 1st slot of 2 slots */
if (channels == 1)
- ssi->i2s_net = SSI_SCR_I2S_MODE_NORMAL;
+ i2s_net = SSI_SCR_I2S_MODE_NORMAL;
regmap_update_bits(regs, REG_SSI_SCR,
- SSI_SCR_I2S_NET_MASK, ssi->i2s_net);
+ SSI_SCR_I2S_NET_MASK, i2s_net);
}
/* In synchronous mode, the SSI uses STCCR for capture */
diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig
index ceb105c..addac2a 100644
--- a/sound/soc/intel/Kconfig
+++ b/sound/soc/intel/Kconfig
@@ -72,24 +72,28 @@
for Baytrail Chromebooks but this option is now deprecated and is
not recommended, use SND_SST_ATOM_HIFI2_PLATFORM instead.
+config SND_SST_ATOM_HIFI2_PLATFORM
+ tristate
+ select SND_SOC_COMPRESS
+
config SND_SST_ATOM_HIFI2_PLATFORM_PCI
- tristate "PCI HiFi2 (Medfield, Merrifield) Platforms"
+ tristate "PCI HiFi2 (Merrifield) Platforms"
depends on X86 && PCI
select SND_SST_IPC_PCI
- select SND_SOC_COMPRESS
+ select SND_SST_ATOM_HIFI2_PLATFORM
help
- If you have a Intel Medfield or Merrifield/Edison platform, then
+ If you have a Intel Merrifield/Edison platform, then
enable this option by saying Y or m. Distros will typically not
- enable this option: Medfield devices are not available to
- developers and while Merrifield/Edison can run a mainline kernel with
- limited functionality it will require a firmware file which
- is not in the standard firmware tree
+ enable this option: while Merrifield/Edison can run a mainline
+ kernel with limited functionality it will require a firmware file
+ which is not in the standard firmware tree
-config SND_SST_ATOM_HIFI2_PLATFORM
+config SND_SST_ATOM_HIFI2_PLATFORM_ACPI
tristate "ACPI HiFi2 (Baytrail, Cherrytrail) Platforms"
+ default ACPI
depends on X86 && ACPI
select SND_SST_IPC_ACPI
- select SND_SOC_COMPRESS
+ select SND_SST_ATOM_HIFI2_PLATFORM
select SND_SOC_ACPI_INTEL_MATCH
select IOSF_MBI
help
diff --git a/sound/soc/omap/omap-dmic.c b/sound/soc/omap/omap-dmic.c
index 09db2ae..b2f5d2f 100644
--- a/sound/soc/omap/omap-dmic.c
+++ b/sound/soc/omap/omap-dmic.c
@@ -281,7 +281,7 @@ static int omap_dmic_dai_trigger(struct snd_pcm_substream *substream,
static int omap_dmic_select_fclk(struct omap_dmic *dmic, int clk_id,
unsigned int freq)
{
- struct clk *parent_clk;
+ struct clk *parent_clk, *mux;
char *parent_clk_name;
int ret = 0;
@@ -329,14 +329,21 @@ static int omap_dmic_select_fclk(struct omap_dmic *dmic, int clk_id,
return -ENODEV;
}
+ mux = clk_get_parent(dmic->fclk);
+ if (IS_ERR(mux)) {
+ dev_err(dmic->dev, "can't get fck mux parent\n");
+ clk_put(parent_clk);
+ return -ENODEV;
+ }
+
mutex_lock(&dmic->mutex);
if (dmic->active) {
/* disable clock while reparenting */
pm_runtime_put_sync(dmic->dev);
- ret = clk_set_parent(dmic->fclk, parent_clk);
+ ret = clk_set_parent(mux, parent_clk);
pm_runtime_get_sync(dmic->dev);
} else {
- ret = clk_set_parent(dmic->fclk, parent_clk);
+ ret = clk_set_parent(mux, parent_clk);
}
mutex_unlock(&dmic->mutex);
@@ -349,6 +356,7 @@ static int omap_dmic_select_fclk(struct omap_dmic *dmic, int clk_id,
dmic->fclk_freq = freq;
err_busy:
+ clk_put(mux);
clk_put(parent_clk);
return ret;
diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index 6a76688..94f081b 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -1536,7 +1536,7 @@ static int rsnd_remove(struct platform_device *pdev)
return ret;
}
-static int rsnd_suspend(struct device *dev)
+static int __maybe_unused rsnd_suspend(struct device *dev)
{
struct rsnd_priv *priv = dev_get_drvdata(dev);
@@ -1545,7 +1545,7 @@ static int rsnd_suspend(struct device *dev)
return 0;
}
-static int rsnd_resume(struct device *dev)
+static int __maybe_unused rsnd_resume(struct device *dev)
{
struct rsnd_priv *priv = dev_get_drvdata(dev);
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index fa27d0f..986b8b2 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -513,7 +513,7 @@ static void remove_widget(struct snd_soc_component *comp,
*/
if (dobj->widget.kcontrol_type == SND_SOC_TPLG_TYPE_ENUM) {
/* enumerated widget mixer */
- for (i = 0; i < w->num_kcontrols; i++) {
+ for (i = 0; w->kcontrols != NULL && i < w->num_kcontrols; i++) {
struct snd_kcontrol *kcontrol = w->kcontrols[i];
struct soc_enum *se =
(struct soc_enum *)kcontrol->private_value;
@@ -530,7 +530,7 @@ static void remove_widget(struct snd_soc_component *comp,
}
} else {
/* volume mixer or bytes controls */
- for (i = 0; i < w->num_kcontrols; i++) {
+ for (i = 0; w->kcontrols != NULL && i < w->num_kcontrols; i++) {
struct snd_kcontrol *kcontrol = w->kcontrols[i];
if (dobj->widget.kcontrol_type
@@ -1325,8 +1325,10 @@ static struct snd_kcontrol_new *soc_tplg_dapm_widget_denum_create(
ec->hdr.name);
kc[i].name = kstrdup(ec->hdr.name, GFP_KERNEL);
- if (kc[i].name == NULL)
+ if (kc[i].name == NULL) {
+ kfree(se);
goto err_se;
+ }
kc[i].private_value = (long)se;
kc[i].iface = SNDRV_CTL_ELEM_IFACE_MIXER;
kc[i].access = ec->hdr.access;
@@ -1442,8 +1444,10 @@ static struct snd_kcontrol_new *soc_tplg_dapm_widget_dbytes_create(
be->hdr.name, be->hdr.access);
kc[i].name = kstrdup(be->hdr.name, GFP_KERNEL);
- if (kc[i].name == NULL)
+ if (kc[i].name == NULL) {
+ kfree(sbe);
goto err;
+ }
kc[i].private_value = (long)sbe;
kc[i].iface = SNDRV_CTL_ELEM_IFACE_MIXER;
kc[i].access = be->hdr.access;
@@ -2576,7 +2580,7 @@ int snd_soc_tplg_component_remove(struct snd_soc_component *comp, u32 index)
/* match index */
if (dobj->index != index &&
- dobj->index != SND_SOC_TPLG_INDEX_ALL)
+ index != SND_SOC_TPLG_INDEX_ALL)
continue;
switch (dobj->type) {
diff --git a/sound/usb/line6/midi.c b/sound/usb/line6/midi.c
index 6d7cde5..e2cf55c 100644
--- a/sound/usb/line6/midi.c
+++ b/sound/usb/line6/midi.c
@@ -125,7 +125,7 @@ static int send_midi_async(struct usb_line6 *line6, unsigned char *data,
}
usb_fill_int_urb(urb, line6->usbdev,
- usb_sndbulkpipe(line6->usbdev,
+ usb_sndintpipe(line6->usbdev,
line6->properties->ep_ctrl_w),
transfer_buffer, length, midi_sent, line6,
line6->interval);
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 301ad61..bb5ab7a 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -967,6 +967,14 @@ static void volume_control_quirks(struct usb_mixer_elem_info *cval,
}
break;
+ case USB_ID(0x0d8c, 0x0103):
+ if (!strcmp(kctl->id.name, "PCM Playback Volume")) {
+ usb_audio_info(chip,
+ "set volume quirk for CM102-A+/102S+\n");
+ cval->min = -256;
+ }
+ break;
+
case USB_ID(0x0471, 0x0101):
case USB_ID(0x0471, 0x0104):
case USB_ID(0x0471, 0x0105):
@@ -1776,7 +1784,8 @@ static int parse_audio_feature_unit(struct mixer_build *state, int unitid,
build_feature_ctl(state, _ftr, ch_bits, control,
&iterm, unitid, ch_read_only);
if (uac_v2v3_control_is_readable(master_bits, control))
- build_feature_ctl(state, _ftr, 0, i, &iterm, unitid,
+ build_feature_ctl(state, _ftr, 0, control,
+ &iterm, unitid,
!uac_v2v3_control_is_writeable(master_bits,
control));
}
@@ -1859,7 +1868,7 @@ static int parse_audio_input_terminal(struct mixer_build *state, int unitid,
check_input_term(state, d->bTerminalID, &iterm);
if (state->mixer->protocol == UAC_VERSION_2) {
/* Check for jack detection. */
- if (uac_v2v3_control_is_readable(d->bmControls,
+ if (uac_v2v3_control_is_readable(le16_to_cpu(d->bmControls),
UAC2_TE_CONNECTOR)) {
build_connector_control(state, &iterm, true);
}
@@ -2561,7 +2570,7 @@ static int snd_usb_mixer_controls(struct usb_mixer_interface *mixer)
if (err < 0 && err != -EINVAL)
return err;
- if (uac_v2v3_control_is_readable(desc->bmControls,
+ if (uac_v2v3_control_is_readable(le16_to_cpu(desc->bmControls),
UAC2_TE_CONNECTOR)) {
build_connector_control(&state, &state.oterm,
false);
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index 9038b2e..eaa03ac 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -353,8 +353,11 @@ static struct usbmix_name_map bose_companion5_map[] = {
/*
* Dell usb dock with ALC4020 codec had a firmware problem where it got
* screwed up when zero volume is passed; just skip it as a workaround
+ *
+ * Also the extension unit gives an access error, so skip it as well.
*/
static const struct usbmix_name_map dell_alc4020_map[] = {
+ { 4, NULL }, /* extension unit */
{ 16, NULL },
{ 19, NULL },
{ 0 }
diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index 6a8f584..5ed3345 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -349,7 +349,7 @@ snd_pcm_chmap_elem *convert_chmap_v3(struct uac3_cluster_header_descriptor
* TODO: this conversion is not complete, update it
* after adding UAC3 values to asound.h
*/
- switch (is->bChPurpose) {
+ switch (is->bChRelationship) {
case UAC3_CH_MONO:
map = SNDRV_CHMAP_MONO;
break;
@@ -576,7 +576,7 @@ static int parse_uac_endpoint_attributes(struct snd_usb_audio *chip,
if (protocol == UAC_VERSION_1) {
attributes = csep->bmAttributes;
- } else {
+ } else if (protocol == UAC_VERSION_2) {
struct uac2_iso_endpoint_descriptor *csep2 =
(struct uac2_iso_endpoint_descriptor *) csep;
@@ -585,6 +585,13 @@ static int parse_uac_endpoint_attributes(struct snd_usb_audio *chip,
/* emulate the endpoint attributes of a v1 device */
if (csep2->bmControls & UAC2_CONTROL_PITCH)
attributes |= UAC_EP_CS_ATTR_PITCH_CONTROL;
+ } else { /* UAC_VERSION_3 */
+ struct uac3_iso_endpoint_descriptor *csep3 =
+ (struct uac3_iso_endpoint_descriptor *) csep;
+
+ /* emulate the endpoint attributes of a v1 device */
+ if (le32_to_cpu(csep3->bmControls) & UAC2_CONTROL_PITCH)
+ attributes |= UAC_EP_CS_ATTR_PITCH_CONTROL;
}
return attributes;
diff --git a/sound/usb/usx2y/us122l.c b/sound/usb/usx2y/us122l.c
index ebcab5c..8082f7b 100644
--- a/sound/usb/usx2y/us122l.c
+++ b/sound/usb/usx2y/us122l.c
@@ -139,7 +139,7 @@ static void usb_stream_hwdep_vm_open(struct vm_area_struct *area)
snd_printdd(KERN_DEBUG "%i\n", atomic_read(&us122l->mmap_count));
}
-static int usb_stream_hwdep_vm_fault(struct vm_fault *vmf)
+static vm_fault_t usb_stream_hwdep_vm_fault(struct vm_fault *vmf)
{
unsigned long offset;
struct page *page;
diff --git a/sound/usb/usx2y/usX2Yhwdep.c b/sound/usb/usx2y/usX2Yhwdep.c
index d8bd7c9..c1dd9a7 100644
--- a/sound/usb/usx2y/usX2Yhwdep.c
+++ b/sound/usb/usx2y/usX2Yhwdep.c
@@ -31,7 +31,7 @@
#include "usbusx2y.h"
#include "usX2Yhwdep.h"
-static int snd_us428ctls_vm_fault(struct vm_fault *vmf)
+static vm_fault_t snd_us428ctls_vm_fault(struct vm_fault *vmf)
{
unsigned long offset;
struct page * page;
diff --git a/sound/usb/usx2y/usx2yhwdeppcm.c b/sound/usb/usx2y/usx2yhwdeppcm.c
index 0d05052..4fd9276 100644
--- a/sound/usb/usx2y/usx2yhwdeppcm.c
+++ b/sound/usb/usx2y/usx2yhwdeppcm.c
@@ -652,7 +652,7 @@ static void snd_usX2Y_hwdep_pcm_vm_close(struct vm_area_struct *area)
}
-static int snd_usX2Y_hwdep_pcm_vm_fault(struct vm_fault *vmf)
+static vm_fault_t snd_usX2Y_hwdep_pcm_vm_fault(struct vm_fault *vmf)
{
unsigned long offset;
void *vaddr;
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index 6edd177..caae484 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -135,6 +135,15 @@ struct kvm_arch_memory_slot {
#define KVM_REG_ARM_CRM_SHIFT 7
#define KVM_REG_ARM_32_CRN_MASK 0x0000000000007800
#define KVM_REG_ARM_32_CRN_SHIFT 11
+/*
+ * For KVM currently all guest registers are nonsecure, but we reserve a bit
+ * in the encoding to distinguish secure from nonsecure for AArch32 system
+ * registers that are banked by security. This is 1 for the secure banked
+ * register, and 0 for the nonsecure banked register or if the register is
+ * not banked by security.
+ */
+#define KVM_REG_ARM_SECURE_MASK 0x0000000010000000
+#define KVM_REG_ARM_SECURE_SHIFT 28
#define ARM_CP15_REG_SHIFT_MASK(x,n) \
(((x) << KVM_REG_ARM_ ## n ## _SHIFT) & KVM_REG_ARM_ ## n ## _MASK)
@@ -186,6 +195,12 @@ struct kvm_arch_memory_slot {
#define KVM_REG_ARM_VFP_FPINST 0x1009
#define KVM_REG_ARM_VFP_FPINST2 0x100A
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM | KVM_REG_SIZE_U64 | \
+ KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0)
+
/* Device Control API: ARM VGIC */
#define KVM_DEV_ARM_VGIC_GRP_ADDR 0
#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 9abbf30..04b3256 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -206,6 +206,12 @@ struct kvm_arch_memory_slot {
#define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2)
#define KVM_REG_ARM_TIMER_CVAL ARM64_SYS_REG(3, 3, 14, 0, 2)
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
+ KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0)
+
/* Device Control API: ARM VGIC */
#define KVM_DEV_ARM_VGIC_GRP_ADDR 0
#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index d554c11..fb00a2f 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -198,7 +198,6 @@
#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */
#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */
#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
-
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */
@@ -207,13 +206,19 @@
#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
#define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */
-
+#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
+#define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */
#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */
#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */
#define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */
-
#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */
+#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */
+#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* "" AMD SSBD implementation via LS_CFG MSR */
+#define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
@@ -274,9 +279,10 @@
#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
#define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */
#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */
-#define X86_FEATURE_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */
-#define X86_FEATURE_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */
-#define X86_FEATURE_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */
+#define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */
+#define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */
/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */
@@ -320,6 +326,7 @@
#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */
#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */
+#define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */
/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */
@@ -333,6 +340,7 @@
#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */
#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
+#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */
/*
* BUG word(s)
@@ -362,5 +370,6 @@
#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
+#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
index fb3a6de..6847d85 100644
--- a/tools/arch/x86/include/asm/required-features.h
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -53,12 +53,6 @@
# define NEED_MOVBE 0
#endif
-#ifdef CONFIG_X86_5LEVEL
-# define NEED_LA57 (1<<(X86_FEATURE_LA57 & 31))
-#else
-# define NEED_LA57 0
-#endif
-
#ifdef CONFIG_X86_64
#ifdef CONFIG_PARAVIRT
/* Paravirtualized systems may not have PSE or PGE available */
@@ -104,7 +98,7 @@
#define REQUIRED_MASK13 0
#define REQUIRED_MASK14 0
#define REQUIRED_MASK15 0
-#define REQUIRED_MASK16 (NEED_LA57)
+#define REQUIRED_MASK16 0
#define REQUIRED_MASK17 0
#define REQUIRED_MASK18 0
#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index f3a9604..c535c2f 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -354,8 +354,25 @@ struct kvm_xcrs {
__u64 padding[16];
};
-/* definition of registers in kvm_run */
+#define KVM_SYNC_X86_REGS (1UL << 0)
+#define KVM_SYNC_X86_SREGS (1UL << 1)
+#define KVM_SYNC_X86_EVENTS (1UL << 2)
+
+#define KVM_SYNC_X86_VALID_FIELDS \
+ (KVM_SYNC_X86_REGS| \
+ KVM_SYNC_X86_SREGS| \
+ KVM_SYNC_X86_EVENTS)
+
+/* kvm_sync_regs struct included by kvm_run struct */
struct kvm_sync_regs {
+ /* Members of this structure are potentially malicious.
+ * Care must be taken by code reading, esp. interpreting,
+ * data fields from them inside KVM to prevent TOCTOU and
+ * double-fetch types of vulnerabilities.
+ */
+ struct kvm_regs regs;
+ struct kvm_sregs sregs;
+ struct kvm_vcpu_events events;
};
#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0)
diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile
index 1ea5459..53b60ad 100644
--- a/tools/bpf/Makefile
+++ b/tools/bpf/Makefile
@@ -76,6 +76,8 @@
$(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $^
$(OUTPUT)bpf_exp.lex.c: $(OUTPUT)bpf_exp.yacc.c
+$(OUTPUT)bpf_exp.yacc.o: $(OUTPUT)bpf_exp.yacc.c
+$(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c
clean: bpftool_clean
$(call QUIET_CLEAN, bpf-progs)
diff --git a/tools/bpf/bpf_dbg.c b/tools/bpf/bpf_dbg.c
index 4f254bc..61b9aa5 100644
--- a/tools/bpf/bpf_dbg.c
+++ b/tools/bpf/bpf_dbg.c
@@ -1063,7 +1063,7 @@ static int cmd_load_pcap(char *file)
static int cmd_load(char *arg)
{
- char *subcmd, *cont, *tmp = strdup(arg);
+ char *subcmd, *cont = NULL, *tmp = strdup(arg);
int ret = CMD_OK;
subcmd = strtok_r(tmp, " ", &cont);
@@ -1073,7 +1073,10 @@ static int cmd_load(char *arg)
bpf_reset();
bpf_reset_breakpoints();
- ret = cmd_load_bpf(cont);
+ if (!cont)
+ ret = CMD_ERR;
+ else
+ ret = cmd_load_bpf(cont);
} else if (matches(subcmd, "pcap") == 0) {
ret = cmd_load_pcap(cont);
} else {
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
index a3a4427..70fe612 100644
--- a/tools/include/linux/compiler-gcc.h
+++ b/tools/include/linux/compiler-gcc.h
@@ -21,6 +21,9 @@
/* &a[0] degrades to a pointer: a different type from an array */
#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
+#ifndef __pure
+#define __pure __attribute__((pure))
+#endif
#define noinline __attribute__((noinline))
#ifndef __packed
#define __packed __attribute__((packed))
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 04e32f9..1827c2f 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -151,11 +151,21 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
* required ordering.
*/
-#define READ_ONCE(x) \
- ({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+#define READ_ONCE(x) \
+({ \
+ union { typeof(x) __val; char __c[1]; } __u = \
+ { .__c = { 0 } }; \
+ __read_once_size(&(x), __u.__c, sizeof(x)); \
+ __u.__val; \
+})
-#define WRITE_ONCE(x, val) \
- ({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+#define WRITE_ONCE(x, val) \
+({ \
+ union { typeof(x) __val; char __c[1]; } __u = \
+ { .__val = (val) }; \
+ __write_once_size(&(x), __u.__c, sizeof(x)); \
+ __u.__val; \
+})
#ifndef __fallthrough
diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h
index edfeaba..a1a959b 100644
--- a/tools/include/linux/coresight-pmu.h
+++ b/tools/include/linux/coresight-pmu.h
@@ -1,18 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright(C) 2015 Linaro Limited. All rights reserved.
* Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program. If not, see <http://www.gnu.org/licenses/>.
*/
#ifndef _LINUX_CORESIGHT_PMU_H
diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h
index b21b586..1738c03 100644
--- a/tools/include/linux/spinlock.h
+++ b/tools/include/linux/spinlock.h
@@ -6,8 +6,9 @@
#include <stdbool.h>
#define spinlock_t pthread_mutex_t
-#define DEFINE_SPINLOCK(x) pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER;
+#define DEFINE_SPINLOCK(x) pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER
#define __SPIN_LOCK_UNLOCKED(x) (pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER
+#define spin_lock_init(x) pthread_mutex_init(x, NULL)
#define spin_lock_irqsave(x, f) (void)f, pthread_mutex_lock(x)
#define spin_unlock_irqrestore(x, f) (void)f, pthread_mutex_unlock(x)
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index f8b134f..e7ee328 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -27,6 +27,9 @@
# define MAP_UNINITIALIZED 0x0 /* Don't support this flag */
#endif
+/* 0x0100 - 0x80000 flags are defined in asm-generic/mman.h */
+#define MAP_FIXED_NOREPLACE 0x100000 /* MAP_FIXED which doesn't unmap underlying mapping */
+
/*
* Flags for mlock
*/
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 9d07465..8c31773 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -864,6 +864,7 @@ enum bpf_func_id {
/* BPF_FUNC_skb_set_tunnel_key flags. */
#define BPF_F_ZERO_CSUM_TX (1ULL << 1)
#define BPF_F_DONT_FRAGMENT (1ULL << 2)
+#define BPF_F_SEQ_NUMBER (1ULL << 3)
/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
* BPF_FUNC_perf_event_read_value flags.
@@ -1016,6 +1017,7 @@ struct bpf_prog_info {
__aligned_u64 map_ids;
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
+ __u32 :32;
__u64 netns_dev;
__u64 netns_ino;
} __attribute__((aligned(8)));
@@ -1029,6 +1031,7 @@ struct bpf_map_info {
__u32 map_flags;
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
+ __u32 :32;
__u64 netns_dev;
__u64 netns_ino;
} __attribute__((aligned(8)));
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 6d94477..68699f6 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -941,4 +941,43 @@ enum {
IFLA_EVENT_BONDING_OPTIONS, /* change in bonding options */
};
+/* tun section */
+
+enum {
+ IFLA_TUN_UNSPEC,
+ IFLA_TUN_OWNER,
+ IFLA_TUN_GROUP,
+ IFLA_TUN_TYPE,
+ IFLA_TUN_PI,
+ IFLA_TUN_VNET_HDR,
+ IFLA_TUN_PERSIST,
+ IFLA_TUN_MULTI_QUEUE,
+ IFLA_TUN_NUM_QUEUES,
+ IFLA_TUN_NUM_DISABLED_QUEUES,
+ __IFLA_TUN_MAX,
+};
+
+#define IFLA_TUN_MAX (__IFLA_TUN_MAX - 1)
+
+/* rmnet section */
+
+#define RMNET_FLAGS_INGRESS_DEAGGREGATION (1U << 0)
+#define RMNET_FLAGS_INGRESS_MAP_COMMANDS (1U << 1)
+#define RMNET_FLAGS_INGRESS_MAP_CKSUMV4 (1U << 2)
+#define RMNET_FLAGS_EGRESS_MAP_CKSUMV4 (1U << 3)
+
+enum {
+ IFLA_RMNET_UNSPEC,
+ IFLA_RMNET_MUX_ID,
+ IFLA_RMNET_FLAGS,
+ __IFLA_RMNET_MAX,
+};
+
+#define IFLA_RMNET_MAX (__IFLA_RMNET_MAX - 1)
+
+struct ifla_rmnet_flags {
+ __u32 flags;
+ __u32 mask;
+};
+
#endif /* _UAPI_LINUX_IF_LINK_H */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 6b89f87..b02c41e 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -396,6 +396,10 @@ struct kvm_run {
char padding[256];
};
+ /* 2048 is the size of the char array used to bound/pad the size
+ * of the union that holds sync regs.
+ */
+ #define SYNC_REGS_SIZE_BYTES 2048
/*
* shared registers between kvm and userspace.
* kvm_valid_regs specifies the register classes set by the host
@@ -407,7 +411,7 @@ struct kvm_run {
__u64 kvm_dirty_regs;
union {
struct kvm_sync_regs regs;
- char padding[2048];
+ char padding[SYNC_REGS_SIZE_BYTES];
} s;
};
@@ -672,6 +676,13 @@ struct kvm_ioeventfd {
__u8 pad[36];
};
+#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0)
+#define KVM_X86_DISABLE_EXITS_HTL (1 << 1)
+#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2)
+#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \
+ KVM_X86_DISABLE_EXITS_HTL | \
+ KVM_X86_DISABLE_EXITS_PAUSE)
+
/* for KVM_ENABLE_CAP */
struct kvm_enable_cap {
/* in */
@@ -936,6 +947,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_PPC_GET_CPU_CHAR 151
#define KVM_CAP_S390_BPB 152
#define KVM_CAP_GET_MSR_FEATURES 153
+#define KVM_CAP_HYPERV_EVENTFD 154
#ifdef KVM_CAP_IRQ_ROUTING
@@ -1375,6 +1387,10 @@ struct kvm_enc_region {
#define KVM_MEMORY_ENCRYPT_REG_REGION _IOR(KVMIO, 0xbb, struct kvm_enc_region)
#define KVM_MEMORY_ENCRYPT_UNREG_REGION _IOR(KVMIO, 0xbc, struct kvm_enc_region)
+/* Available with KVM_CAP_HYPERV_EVENTFD */
+#define KVM_HYPERV_EVENTFD _IOW(KVMIO, 0xbd, struct kvm_hyperv_eventfd)
+
+
/* Secure Encrypted Virtualization command */
enum sev_cmd_id {
/* Guest initialization commands */
@@ -1515,4 +1531,14 @@ struct kvm_assigned_msix_entry {
#define KVM_ARM_DEV_EL1_PTIMER (1 << 1)
#define KVM_ARM_DEV_PMU (1 << 2)
+struct kvm_hyperv_eventfd {
+ __u32 conn_id;
+ __s32 fd;
+ __u32 flags;
+ __u32 padding[3];
+};
+
+#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff
+#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0)
+
#endif /* __LINUX_KVM_H */
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 912b85b..b8e288a 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -650,11 +650,23 @@ struct perf_event_mmap_page {
#define PERF_RECORD_MISC_COMM_EXEC (1 << 13)
#define PERF_RECORD_MISC_SWITCH_OUT (1 << 13)
/*
- * Indicates that the content of PERF_SAMPLE_IP points to
- * the actual instruction that triggered the event. See also
- * perf_event_attr::precise_ip.
+ * These PERF_RECORD_MISC_* flags below are safely reused
+ * for the following events:
+ *
+ * PERF_RECORD_MISC_EXACT_IP - PERF_RECORD_SAMPLE of precise events
+ * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events
+ *
+ *
+ * PERF_RECORD_MISC_EXACT_IP:
+ * Indicates that the content of PERF_SAMPLE_IP points to
+ * the actual instruction that triggered the event. See also
+ * perf_event_attr::precise_ip.
+ *
+ * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT:
+ * Indicates that thread was preempted in TASK_RUNNING state.
*/
#define PERF_RECORD_MISC_EXACT_IP (1 << 14)
+#define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14)
/*
* Reserve the last bit to indicate some extended misc field
*/
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index af5f8c2..db9f15f5 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -207,4 +207,16 @@ struct prctl_mm_map {
# define PR_SVE_VL_LEN_MASK 0xffff
# define PR_SVE_VL_INHERIT (1 << 17) /* inherit across exec */
+/* Per task speculation control */
+#define PR_GET_SPECULATION_CTRL 52
+#define PR_SET_SPECULATION_CTRL 53
+/* Speculation control variants */
+# define PR_SPEC_STORE_BYPASS 0
+/* Return and control values for PR_SET/GET_SPECULATION_CTRL */
+# define PR_SPEC_NOT_AFFECTED 0
+# define PR_SPEC_PRCTL (1UL << 0)
+# define PR_SPEC_ENABLE (1UL << 1)
+# define PR_SPEC_DISABLE (1UL << 2)
+# define PR_SPEC_FORCE_DISABLE (1UL << 3)
+
#endif /* _LINUX_PRCTL_H */
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index 07d6158..ed0a120 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -242,6 +242,7 @@ typedef int __bitwise snd_pcm_format_t;
#define SNDRV_PCM_FORMAT_DSD_U16_BE ((__force snd_pcm_format_t) 51) /* DSD, 2-byte samples DSD (x16), big endian */
#define SNDRV_PCM_FORMAT_DSD_U32_BE ((__force snd_pcm_format_t) 52) /* DSD, 4-byte samples DSD (x32), big endian */
#define SNDRV_PCM_FORMAT_LAST SNDRV_PCM_FORMAT_DSD_U32_BE
+#define SNDRV_PCM_FORMAT_FIRST SNDRV_PCM_FORMAT_S8
#ifdef SNDRV_LITTLE_ENDIAN
#define SNDRV_PCM_FORMAT_S16 SNDRV_PCM_FORMAT_S16_LE
diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c
index 7b7fd0b..1200374 100644
--- a/tools/lib/api/fs/tracing_path.c
+++ b/tools/lib/api/fs/tracing_path.c
@@ -13,11 +13,9 @@
#include "tracing_path.h"
-
-char tracing_mnt[PATH_MAX] = "/sys/kernel/debug";
-char tracing_path[PATH_MAX] = "/sys/kernel/debug/tracing";
-char tracing_events_path[PATH_MAX] = "/sys/kernel/debug/tracing/events";
-
+static char tracing_mnt[PATH_MAX] = "/sys/kernel/debug";
+static char tracing_path[PATH_MAX] = "/sys/kernel/debug/tracing";
+static char tracing_events_path[PATH_MAX] = "/sys/kernel/debug/tracing/events";
static void __tracing_path_set(const char *tracing, const char *mountpoint)
{
@@ -76,7 +74,7 @@ char *get_tracing_file(const char *name)
{
char *file;
- if (asprintf(&file, "%s/%s", tracing_path, name) < 0)
+ if (asprintf(&file, "%s/%s", tracing_path_mount(), name) < 0)
return NULL;
return file;
@@ -87,6 +85,34 @@ void put_tracing_file(char *file)
free(file);
}
+char *get_events_file(const char *name)
+{
+ char *file;
+
+ if (asprintf(&file, "%s/events/%s", tracing_path_mount(), name) < 0)
+ return NULL;
+
+ return file;
+}
+
+void put_events_file(char *file)
+{
+ free(file);
+}
+
+DIR *tracing_events__opendir(void)
+{
+ DIR *dir = NULL;
+ char *path = get_tracing_file("events");
+
+ if (path) {
+ dir = opendir(path);
+ put_events_file(path);
+ }
+
+ return dir;
+}
+
int tracing_path__strerror_open_tp(int err, char *buf, size_t size,
const char *sys, const char *name)
{
@@ -129,7 +155,7 @@ int tracing_path__strerror_open_tp(int err, char *buf, size_t size,
snprintf(buf, size,
"Error:\tNo permissions to read %s/%s\n"
"Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n",
- tracing_events_path, filename, tracing_mnt);
+ tracing_events_path, filename, tracing_path_mount());
}
break;
default:
diff --git a/tools/lib/api/fs/tracing_path.h b/tools/lib/api/fs/tracing_path.h
index 0066f06..a19136b 100644
--- a/tools/lib/api/fs/tracing_path.h
+++ b/tools/lib/api/fs/tracing_path.h
@@ -3,9 +3,9 @@
#define __API_FS_TRACING_PATH_H
#include <linux/types.h>
+#include <dirent.h>
-extern char tracing_path[];
-extern char tracing_events_path[];
+DIR *tracing_events__opendir(void);
void tracing_path_set(const char *mountpoint);
const char *tracing_path_mount(void);
@@ -13,5 +13,10 @@ const char *tracing_path_mount(void);
char *get_tracing_file(const char *name);
void put_tracing_file(char *file);
+char *get_events_file(const char *name);
+void put_events_file(char *file);
+
+#define zput_events_file(ptr) ({ free(*ptr); *ptr = NULL; })
+
int tracing_path__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name);
#endif /* __API_FS_TRACING_PATH_H */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 5922443..0f9f06d 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2035,7 +2035,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
return -EINVAL;
obj = bpf_object__open(attr->file);
- if (IS_ERR(obj))
+ if (IS_ERR_OR_NULL(obj))
return -ENOENT;
bpf_object__for_each_program(prog, obj) {
diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c
index f6a1bab..cb7154e 100644
--- a/tools/lib/subcmd/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -433,7 +433,7 @@ static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg,
if (ambiguous_option) {
fprintf(stderr,
- " Error: Ambiguous option: %s (could be --%s%s or --%s%s)",
+ " Error: Ambiguous option: %s (could be --%s%s or --%s%s)\n",
arg,
(ambiguous_flags & OPT_UNSET) ? "no-" : "",
ambiguous_option->long_name,
@@ -458,7 +458,7 @@ static void check_typos(const char *arg, const struct option *options)
return;
if (strstarts(arg, "no-")) {
- fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)", arg);
+ fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)\n", arg);
exit(129);
}
@@ -466,7 +466,7 @@ static void check_typos(const char *arg, const struct option *options)
if (!options->long_name)
continue;
if (strstarts(options->long_name, arg)) {
- fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)", arg);
+ fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)\n", arg);
exit(129);
}
}
diff --git a/tools/lib/symbol/kallsyms.c b/tools/lib/symbol/kallsyms.c
index 689b6a1..96d8305 100644
--- a/tools/lib/symbol/kallsyms.c
+++ b/tools/lib/symbol/kallsyms.c
@@ -10,6 +10,12 @@ u8 kallsyms2elf_type(char type)
return (type == 't' || type == 'w') ? STT_FUNC : STT_OBJECT;
}
+bool kallsyms__is_function(char symbol_type)
+{
+ symbol_type = toupper(symbol_type);
+ return symbol_type == 'T' || symbol_type == 'W';
+}
+
int kallsyms__parse(const char *filename, void *arg,
int (*process_symbol)(void *arg, const char *name,
char type, u64 start))
diff --git a/tools/lib/symbol/kallsyms.h b/tools/lib/symbol/kallsyms.h
index bc40101..72ab987 100644
--- a/tools/lib/symbol/kallsyms.h
+++ b/tools/lib/symbol/kallsyms.h
@@ -20,6 +20,8 @@ static inline u8 kallsyms2elf_binding(char type)
u8 kallsyms2elf_type(char type);
+bool kallsyms__is_function(char symbol_type);
+
int kallsyms__parse(const char *filename, void *arg,
int (*process_symbol)(void *arg, const char *name,
char type, u64 start));
diff --git a/tools/memory-model/Documentation/cheatsheet.txt b/tools/memory-model/Documentation/cheatsheet.txt
index 956b1ae4..33ba98d 100644
--- a/tools/memory-model/Documentation/cheatsheet.txt
+++ b/tools/memory-model/Documentation/cheatsheet.txt
@@ -1,6 +1,6 @@
Prior Operation Subsequent Operation
--------------- ---------------------------
- C Self R W RWM Self R W DR DW RMW SV
+ C Self R W RMW Self R W DR DW RMW SV
-- ---- - - --- ---- - - -- -- --- --
Store, e.g., WRITE_ONCE() Y Y
@@ -14,7 +14,7 @@
smp_mb() & synchronize_rcu() CP Y Y Y Y Y Y Y Y
Successful full non-void RMW CP Y Y Y Y Y Y Y Y Y Y Y
smp_mb__before_atomic() CP Y Y Y a a a a Y
-smp_mb__after_atomic() CP a a Y Y Y Y Y
+smp_mb__after_atomic() CP a a Y Y Y Y Y Y
Key: C: Ordering is cumulative
@@ -26,4 +26,5 @@
DR: Dependent read (address dependency)
DW: Dependent write (address, data, or control dependency)
RMW: Atomic read-modify-write operation
- SV Same-variable access
+ SELF: Orders self, as opposed to accesses before and/or after
+ SV: Orders later accesses to the same variable
diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt
index a727c82..1b09f31 100644
--- a/tools/memory-model/Documentation/explanation.txt
+++ b/tools/memory-model/Documentation/explanation.txt
@@ -27,7 +27,7 @@
19. AND THEN THERE WAS ALPHA
20. THE HAPPENS-BEFORE RELATION: hb
21. THE PROPAGATES-BEFORE RELATION: pb
- 22. RCU RELATIONS: link, gp-link, rscs-link, and rcu-path
+ 22. RCU RELATIONS: rcu-link, gp, rscs, rcu-fence, and rb
23. ODDS AND ENDS
@@ -1451,8 +1451,8 @@
the content of the LKMM's "propagation" axiom.
-RCU RELATIONS: link, gp-link, rscs-link, and rcu-path
------------------------------------------------------
+RCU RELATIONS: rcu-link, gp, rscs, rcu-fence, and rb
+----------------------------------------------------
RCU (Read-Copy-Update) is a powerful synchronization mechanism. It
rests on two concepts: grace periods and read-side critical sections.
@@ -1509,8 +1509,8 @@
propagate to P1 before the end of the grace period, violating the
Guarantee.
-In the kernel's implementations of RCU, the business about stores
-propagating to every CPU is realized by placing strong fences at
+In the kernel's implementations of RCU, the requirements for stores
+to propagate to every CPU are fulfilled by placing strong fences at
suitable places in the RCU-related code. Thus, if a critical section
starts before a grace period does then the critical section's CPU will
execute an smp_mb() fence after the end of the critical section and
@@ -1523,72 +1523,124 @@
What exactly do we mean by saying that a critical section "starts
before" or "ends after" a grace period? Some aspects of the meaning
are pretty obvious, as in the example above, but the details aren't
-entirely clear. The LKMM formalizes this notion by means of a
-relation with the unfortunately generic name "link". It is a very
-general relation; among other things, X ->link Z includes cases where
-X happens-before or is equal to some event Y which is equal to or
-comes before Z in the coherence order. Taking Y = Z, this says that
-X ->rfe Z implies X ->link Z, and taking Y = X, it says that X ->fr Z
-and X ->co Z each imply X ->link Z.
+entirely clear. The LKMM formalizes this notion by means of the
+rcu-link relation. rcu-link encompasses a very general notion of
+"before": Among other things, X ->rcu-link Z includes cases where X
+happens-before or is equal to some event Y which is equal to or comes
+before Z in the coherence order. When Y = Z this says that X ->rfe Z
+implies X ->rcu-link Z. In addition, when Y = X it says that X ->fr Z
+and X ->co Z each imply X ->rcu-link Z.
-The formal definition of the link relation is more than a little
+The formal definition of the rcu-link relation is more than a little
obscure, and we won't give it here. It is closely related to the pb
relation, and the details don't matter unless you want to comb through
a somewhat lengthy formal proof. Pretty much all you need to know
-about link is the information in the preceding paragraph.
+about rcu-link is the information in the preceding paragraph.
-The LKMM goes on to define the gp-link and rscs-link relations. They
-bring grace periods and read-side critical sections into the picture,
-in the following way:
+The LKMM also defines the gp and rscs relations. They bring grace
+periods and read-side critical sections into the picture, in the
+following way:
- E ->gp-link F means there is a synchronize_rcu() fence event S
- and an event X such that E ->po S, either S ->po X or S = X,
- and X ->link F. In other words, E and F are connected by a
- grace period followed by an instance of link.
+ E ->gp F means there is a synchronize_rcu() fence event S such
+ that E ->po S and either S ->po F or S = F. In simple terms,
+ there is a grace period po-between E and F.
- E ->rscs-link F means there is a critical section delimited by
- an rcu_read_lock() fence L and an rcu_read_unlock() fence U,
- and an event X such that E ->po U, either L ->po X or L = X,
- and X ->link F. Roughly speaking, this says that some event
- in the same critical section as E is connected by link to F.
+ E ->rscs F means there is a critical section delimited by an
+ rcu_read_lock() fence L and an rcu_read_unlock() fence U, such
+ that E ->po U and either L ->po F or L = F. You can think of
+ this as saying that E and F are in the same critical section
+ (in fact, it also allows E to be po-before the start of the
+ critical section and F to be po-after the end).
-If we think of the link relation as standing for an extended "before",
-then E ->gp-link F says that E executes before a grace period which
-ends before F executes. (In fact it says more than this, because it
-includes cases where E executes before a grace period and some store
-propagates to F's CPU before F executes and doesn't propagate to some
-other CPU until after the grace period ends.) Similarly,
-E ->rscs-link F says that E is part of (or before the start of) a
-critical section which starts before F executes.
+If we think of the rcu-link relation as standing for an extended
+"before", then X ->gp Y ->rcu-link Z says that X executes before a
+grace period which ends before Z executes. (In fact it covers more
+than this, because it also includes cases where X executes before a
+grace period and some store propagates to Z's CPU before Z executes
+but doesn't propagate to some other CPU until after the grace period
+ends.) Similarly, X ->rscs Y ->rcu-link Z says that X is part of (or
+before the start of) a critical section which starts before Z
+executes.
+
+The LKMM goes on to define the rcu-fence relation as a sequence of gp
+and rscs links separated by rcu-link links, in which the number of gp
+links is >= the number of rscs links. For example:
+
+ X ->gp Y ->rcu-link Z ->rscs T ->rcu-link U ->gp V
+
+would imply that X ->rcu-fence V, because this sequence contains two
+gp links and only one rscs link. (It also implies that X ->rcu-fence T
+and Z ->rcu-fence V.) On the other hand:
+
+ X ->rscs Y ->rcu-link Z ->rscs T ->rcu-link U ->gp V
+
+does not imply X ->rcu-fence V, because the sequence contains only
+one gp link but two rscs links.
+
+The rcu-fence relation is important because the Grace Period Guarantee
+means that rcu-fence acts kind of like a strong fence. In particular,
+if W is a write and we have W ->rcu-fence Z, the Guarantee says that W
+will propagate to every CPU before Z executes.
+
+To prove this in full generality requires some intellectual effort.
+We'll consider just a very simple case:
+
+ W ->gp X ->rcu-link Y ->rscs Z.
+
+This formula means that there is a grace period G and a critical
+section C such that:
+
+ 1. W is po-before G;
+
+ 2. X is equal to or po-after G;
+
+ 3. X comes "before" Y in some sense;
+
+ 4. Y is po-before the end of C;
+
+ 5. Z is equal to or po-after the start of C.
+
+From 2 - 4 we deduce that the grace period G ends before the critical
+section C. Then the second part of the Grace Period Guarantee says
+not only that G starts before C does, but also that W (which executes
+on G's CPU before G starts) must propagate to every CPU before C
+starts. In particular, W propagates to every CPU before Z executes
+(or finishes executing, in the case where Z is equal to the
+rcu_read_lock() fence event which starts C.) This sort of reasoning
+can be expanded to handle all the situations covered by rcu-fence.
+
+Finally, the LKMM defines the RCU-before (rb) relation in terms of
+rcu-fence. This is done in essentially the same way as the pb
+relation was defined in terms of strong-fence. We will omit the
+details; the end result is that E ->rb F implies E must execute before
+F, just as E ->pb F does (and for much the same reasons).
Putting this all together, the LKMM expresses the Grace Period
-Guarantee by requiring that there are no cycles consisting of gp-link
-and rscs-link connections in which the number of gp-link instances is
->= the number of rscs-link instances. It does this by defining the
-rcu-path relation to link events E and F whenever it is possible to
-pass from E to F by a sequence of gp-link and rscs-link connections
-with at least as many of the former as the latter. The LKMM's "rcu"
-axiom then says that there are no events E such that E ->rcu-path E.
+Guarantee by requiring that the rb relation does not contain a cycle.
+Equivalently, this "rcu" axiom requires that there are no events E and
+F with E ->rcu-link F ->rcu-fence E. Or to put it a third way, the
+axiom requires that there are no cycles consisting of gp and rscs
+alternating with rcu-link, where the number of gp links is >= the
+number of rscs links.
-Justifying this axiom takes some intellectual effort, but it is in
-fact a valid formalization of the Grace Period Guarantee. We won't
-attempt to go through the detailed argument, but the following
-analysis gives a taste of what is involved. Suppose we have a
-violation of the first part of the Guarantee: A critical section
-starts before a grace period, and some store propagates to the
-critical section's CPU before the end of the critical section but
-doesn't propagate to some other CPU until after the end of the grace
-period.
+Justifying the axiom isn't easy, but it is in fact a valid
+formalization of the Grace Period Guarantee. We won't attempt to go
+through the detailed argument, but the following analysis gives a
+taste of what is involved. Suppose we have a violation of the first
+part of the Guarantee: A critical section starts before a grace
+period, and some store propagates to the critical section's CPU before
+the end of the critical section but doesn't propagate to some other
+CPU until after the end of the grace period.
Putting symbols to these ideas, let L and U be the rcu_read_lock() and
rcu_read_unlock() fence events delimiting the critical section in
question, and let S be the synchronize_rcu() fence event for the grace
period. Saying that the critical section starts before S means there
are events E and F where E is po-after L (which marks the start of the
-critical section), E is "before" F in the sense of the link relation,
-and F is po-before the grace period S:
+critical section), E is "before" F in the sense of the rcu-link
+relation, and F is po-before the grace period S:
- L ->po E ->link F ->po S.
+ L ->po E ->rcu-link F ->po S.
Let W be the store mentioned above, let Z come before the end of the
critical section and witness that W propagates to the critical
@@ -1600,16 +1652,19 @@
The fr link from Y to W indicates that W has not propagated to Y's CPU
at the time that Y executes. From this, it can be shown (see the
-discussion of the link relation earlier) that X and Z are connected by
-link, yielding:
+discussion of the rcu-link relation earlier) that X and Z are related
+by rcu-link, yielding:
- S ->po X ->link Z ->po U.
+ S ->po X ->rcu-link Z ->po U.
-These formulas say that S is po-between F and X, hence F ->gp-link Z
-via X. They also say that Z comes before the end of the critical
-section and E comes after its start, hence Z ->rscs-link F via E. But
-now we have a forbidden cycle: F ->gp-link Z ->rscs-link F. Thus the
-"rcu" axiom rules out this violation of the Grace Period Guarantee.
+The formulas say that S is po-between F and X, hence F ->gp X. They
+also say that Z comes before the end of the critical section and E
+comes after its start, hence Z ->rscs E. From all this we obtain:
+
+ F ->gp X ->rcu-link Z ->rscs E ->rcu-link F,
+
+a forbidden cycle. Thus the "rcu" axiom rules out this violation of
+the Grace Period Guarantee.
For something a little more down-to-earth, let's see how the axiom
works out in practice. Consider the RCU code example from above, this
@@ -1635,18 +1690,18 @@
}
-If r2 = 0 at the end then P0's store at X overwrites the value
-that P1's load at Z reads from, so we have Z ->fre X and thus
-Z ->link X. In addition, there is a synchronize_rcu() between Y and
-Z, so therefore we have Y ->gp-link X.
+If r2 = 0 at the end then P0's store at X overwrites the value that
+P1's load at Z reads from, so we have Z ->fre X and thus Z ->rcu-link X.
+In addition, there is a synchronize_rcu() between Y and Z, so therefore
+we have Y ->gp Z.
If r1 = 1 at the end then P1's load at Y reads from P0's store at W,
-so we have W ->link Y. In addition, W and X are in the same critical
-section, so therefore we have X ->rscs-link Y.
+so we have W ->rcu-link Y. In addition, W and X are in the same critical
+section, so therefore we have X ->rscs W.
-This gives us a cycle, Y ->gp-link X ->rscs-link Y, with one gp-link
-and one rscs-link, violating the "rcu" axiom. Hence the outcome is
-not allowed by the LKMM, as we would expect.
+Then X ->rscs W ->rcu-link Y ->gp Z ->rcu-link X is a forbidden cycle,
+violating the "rcu" axiom. Hence the outcome is not allowed by the
+LKMM, as we would expect.
For contrast, let's see what can happen in a more complicated example:
@@ -1682,15 +1737,11 @@
}
If r0 = r1 = r2 = 1 at the end, then similar reasoning to before shows
-that W ->rscs-link Y via X, Y ->gp-link U via Z, and U ->rscs-link W
-via V. And just as before, this gives a cycle:
-
- W ->rscs-link Y ->gp-link U ->rscs-link W.
-
-However, this cycle has fewer gp-link instances than rscs-link
-instances, and consequently the outcome is not forbidden by the LKMM.
-The following instruction timing diagram shows how it might actually
-occur:
+that W ->rscs X ->rcu-link Y ->gp Z ->rcu-link U ->rscs V ->rcu-link W.
+However this cycle is not forbidden, because the sequence of relations
+contains fewer instances of gp (one) than of rscs (two). Consequently
+the outcome is allowed by the LKMM. The following instruction timing
+diagram shows how it might actually occur:
P0 P1 P2
-------------------- -------------------- --------------------
diff --git a/tools/memory-model/Documentation/references.txt b/tools/memory-model/Documentation/references.txt
index ba2e34c..b177f3e 100644
--- a/tools/memory-model/Documentation/references.txt
+++ b/tools/memory-model/Documentation/references.txt
@@ -63,15 +63,22 @@
Principles of Programming Languages (POPL 2017). ACM, New York,
NY, USA, 429–442.
+o Christopher Pulte, Shaked Flur, Will Deacon, Jon French,
+ Susmit Sarkar, and Peter Sewell. 2018. "Simplifying ARM concurrency:
+ multicopy-atomic axiomatic and operational models for ARMv8". In
+ Proceedings of the ACM on Programming Languages, Volume 2, Issue
+ POPL, Article No. 19. ACM, New York, NY, USA.
+
Linux-kernel memory model
=========================
-o Andrea Parri, Alan Stern, Luc Maranget, Paul E. McKenney,
- and Jade Alglave. 2017. "A formal model of
- Linux-kernel memory ordering - companion webpage".
- http://moscova.inria.fr/∼maranget/cats7/linux/. (2017). [Online;
- accessed 30-January-2017].
+o Jade Alglave, Luc Maranget, Paul E. McKenney, Andrea Parri, and
+ Alan Stern. 2018. "Frightening small children and disconcerting
+ grown-ups: Concurrency in the Linux kernel". In Proceedings of
+ the 23rd International Conference on Architectural Support for
+ Programming Languages and Operating Systems (ASPLOS 2018). ACM,
+ New York, NY, USA, 405-418. Webpage: http://diy.inria.fr/linux/.
o Jade Alglave, Luc Maranget, Paul E. McKenney, Andrea Parri, and
Alan Stern. 2017. "A formal kernel memory-ordering model (part 1)"
diff --git a/tools/memory-model/README b/tools/memory-model/README
index 0b3a5f3..734f7fe 100644
--- a/tools/memory-model/README
+++ b/tools/memory-model/README
@@ -20,7 +20,7 @@
REQUIREMENTS
============
-Version 7.48 of the "herd7" and "klitmus7" tools must be downloaded
+Version 7.49 of the "herd7" and "klitmus7" tools must be downloaded
separately:
https://github.com/herd/herdtools7
diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell
index 432c7cf..64f5740 100644
--- a/tools/memory-model/linux-kernel.bell
+++ b/tools/memory-model/linux-kernel.bell
@@ -5,10 +5,10 @@
* Copyright (C) 2017 Alan Stern <stern@rowland.harvard.edu>,
* Andrea Parri <parri.andrea@gmail.com>
*
- * An earlier version of this file appears in the companion webpage for
+ * An earlier version of this file appeared in the companion webpage for
* "Frightening small children and disconcerting grown-ups: Concurrency
* in the Linux kernel" by Alglave, Maranget, McKenney, Parri, and Stern,
- * which is to appear in ASPLOS 2018.
+ * which appeared in ASPLOS 2018.
*)
"Linux-kernel memory consistency model"
diff --git a/tools/memory-model/linux-kernel.cat b/tools/memory-model/linux-kernel.cat
index df97db0..59b5cbe 100644
--- a/tools/memory-model/linux-kernel.cat
+++ b/tools/memory-model/linux-kernel.cat
@@ -5,10 +5,10 @@
* Copyright (C) 2017 Alan Stern <stern@rowland.harvard.edu>,
* Andrea Parri <parri.andrea@gmail.com>
*
- * An earlier version of this file appears in the companion webpage for
+ * An earlier version of this file appeared in the companion webpage for
* "Frightening small children and disconcerting grown-ups: Concurrency
* in the Linux kernel" by Alglave, Maranget, McKenney, Parri, and Stern,
- * which is to appear in ASPLOS 2018.
+ * which appeared in ASPLOS 2018.
*)
"Linux-kernel memory consistency model"
@@ -100,22 +100,29 @@
* one but two non-rf relations, but only in conjunction with an RCU
* read-side critical section.
*)
-let link = hb* ; pb* ; prop
-
-(* Chains that affect the RCU grace-period guarantee *)
-let gp-link = gp ; link
-let rscs-link = rscs ; link
+let rcu-link = hb* ; pb* ; prop
(*
- * A cycle containing at least as many grace periods as RCU read-side
- * critical sections is forbidden.
+ * Any sequence containing at least as many grace periods as RCU read-side
+ * critical sections (joined by rcu-link) acts as a generalized strong fence.
*)
-let rec rcu-path =
- gp-link |
- (gp-link ; rscs-link) |
- (rscs-link ; gp-link) |
- (rcu-path ; rcu-path) |
- (gp-link ; rcu-path ; rscs-link) |
- (rscs-link ; rcu-path ; gp-link)
+let rec rcu-fence = gp |
+ (gp ; rcu-link ; rscs) |
+ (rscs ; rcu-link ; gp) |
+ (gp ; rcu-link ; rcu-fence ; rcu-link ; rscs) |
+ (rscs ; rcu-link ; rcu-fence ; rcu-link ; gp) |
+ (rcu-fence ; rcu-link ; rcu-fence)
-irreflexive rcu-path as rcu
+(* rb orders instructions just as pb does *)
+let rb = prop ; rcu-fence ; hb* ; pb*
+
+irreflexive rb as rcu
+
+(*
+ * The happens-before, propagation, and rcu constraints are all
+ * expressions of temporal ordering. They could be replaced by
+ * a single constraint on an "executes-before" relation, xb:
+ *
+ * let xb = hb | pb | rb
+ * acyclic xb as executes-before
+ *)
diff --git a/tools/memory-model/linux-kernel.def b/tools/memory-model/linux-kernel.def
index 397e4e6..6fa3eb2 100644
--- a/tools/memory-model/linux-kernel.def
+++ b/tools/memory-model/linux-kernel.def
@@ -1,9 +1,9 @@
// SPDX-License-Identifier: GPL-2.0+
//
-// An earlier version of this file appears in the companion webpage for
+// An earlier version of this file appeared in the companion webpage for
// "Frightening small children and disconcerting grown-ups: Concurrency
// in the Linux kernel" by Alglave, Maranget, McKenney, Parri, and Stern,
-// which is to appear in ASPLOS 2018.
+// which appeared in ASPLOS 2018.
// ONCE
READ_ONCE(X) __load{once}(X)
@@ -14,14 +14,15 @@
smp_load_acquire(X) __load{acquire}(*X)
rcu_assign_pointer(X,V) { __store{release}(X,V); }
rcu_dereference(X) __load{once}(X)
+smp_store_mb(X,V) { __store{once}(X,V); __fence{mb}; }
// Fences
-smp_mb() { __fence{mb} ; }
-smp_rmb() { __fence{rmb} ; }
-smp_wmb() { __fence{wmb} ; }
-smp_mb__before_atomic() { __fence{before-atomic} ; }
-smp_mb__after_atomic() { __fence{after-atomic} ; }
-smp_mb__after_spinlock() { __fence{after-spinlock} ; }
+smp_mb() { __fence{mb}; }
+smp_rmb() { __fence{rmb}; }
+smp_wmb() { __fence{wmb}; }
+smp_mb__before_atomic() { __fence{before-atomic}; }
+smp_mb__after_atomic() { __fence{after-atomic}; }
+smp_mb__after_spinlock() { __fence{after-spinlock}; }
// Exchange
xchg(X,V) __xchg{mb}(X,V)
@@ -34,26 +35,27 @@
cmpxchg_release(X,V,W) __cmpxchg{release}(X,V,W)
// Spinlocks
-spin_lock(X) { __lock(X) ; }
-spin_unlock(X) { __unlock(X) ; }
+spin_lock(X) { __lock(X); }
+spin_unlock(X) { __unlock(X); }
spin_trylock(X) __trylock(X)
+spin_is_locked(X) __islocked(X)
// RCU
rcu_read_lock() { __fence{rcu-lock}; }
-rcu_read_unlock() { __fence{rcu-unlock};}
+rcu_read_unlock() { __fence{rcu-unlock}; }
synchronize_rcu() { __fence{sync-rcu}; }
synchronize_rcu_expedited() { __fence{sync-rcu}; }
// Atomic
atomic_read(X) READ_ONCE(*X)
-atomic_set(X,V) { WRITE_ONCE(*X,V) ; }
+atomic_set(X,V) { WRITE_ONCE(*X,V); }
atomic_read_acquire(X) smp_load_acquire(X)
atomic_set_release(X,V) { smp_store_release(X,V); }
-atomic_add(V,X) { __atomic_op(X,+,V) ; }
-atomic_sub(V,X) { __atomic_op(X,-,V) ; }
-atomic_inc(X) { __atomic_op(X,+,1) ; }
-atomic_dec(X) { __atomic_op(X,-,1) ; }
+atomic_add(V,X) { __atomic_op(X,+,V); }
+atomic_sub(V,X) { __atomic_op(X,-,V); }
+atomic_inc(X) { __atomic_op(X,+,1); }
+atomic_dec(X) { __atomic_op(X,-,1); }
atomic_add_return(V,X) __atomic_op_return{mb}(X,+,V)
atomic_add_return_relaxed(V,X) __atomic_op_return{once}(X,+,V)
diff --git a/tools/memory-model/litmus-tests/.gitignore b/tools/memory-model/litmus-tests/.gitignore
new file mode 100644
index 0000000..6e2ddc54
--- /dev/null
+++ b/tools/memory-model/litmus-tests/.gitignore
@@ -0,0 +1 @@
+*.litmus.out
diff --git a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus b/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus
index 50d5db9..98a3716 100644
--- a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus
+++ b/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus
@@ -7,7 +7,7 @@
* between each pairs of reads. In other words, is smp_mb() sufficient to
* cause two different reading processes to agree on the order of a pair
* of writes, where each write is to a different variable by a different
- * process?
+ * process? This litmus test exercises LKMM's "propagation" rule.
*)
{}
diff --git a/tools/memory-model/litmus-tests/MP+polockmbonce+poacquiresilsil.litmus b/tools/memory-model/litmus-tests/MP+polockmbonce+poacquiresilsil.litmus
new file mode 100644
index 0000000..50f4d62
--- /dev/null
+++ b/tools/memory-model/litmus-tests/MP+polockmbonce+poacquiresilsil.litmus
@@ -0,0 +1,35 @@
+C MP+polockmbonce+poacquiresilsil
+
+(*
+ * Result: Never
+ *
+ * Do spinlocks combined with smp_mb__after_spinlock() provide order
+ * to outside observers using spin_is_locked() to sense the lock-held
+ * state, ordered by acquire? Note that when the first spin_is_locked()
+ * returns false and the second true, we know that the smp_load_acquire()
+ * executed before the lock was acquired (loosely speaking).
+ *)
+
+{
+}
+
+P0(spinlock_t *lo, int *x)
+{
+ spin_lock(lo);
+ smp_mb__after_spinlock();
+ WRITE_ONCE(*x, 1);
+ spin_unlock(lo);
+}
+
+P1(spinlock_t *lo, int *x)
+{
+ int r1;
+ int r2;
+ int r3;
+
+ r1 = smp_load_acquire(x);
+ r2 = spin_is_locked(lo);
+ r3 = spin_is_locked(lo);
+}
+
+exists (1:r1=1 /\ 1:r2=0 /\ 1:r3=1)
diff --git a/tools/memory-model/litmus-tests/MP+polockonce+poacquiresilsil.litmus b/tools/memory-model/litmus-tests/MP+polockonce+poacquiresilsil.litmus
new file mode 100644
index 0000000..abf81e7
--- /dev/null
+++ b/tools/memory-model/litmus-tests/MP+polockonce+poacquiresilsil.litmus
@@ -0,0 +1,34 @@
+C MP+polockonce+poacquiresilsil
+
+(*
+ * Result: Sometimes
+ *
+ * Do spinlocks provide order to outside observers using spin_is_locked()
+ * to sense the lock-held state, ordered by acquire? Note that when the
+ * first spin_is_locked() returns false and the second true, we know that
+ * the smp_load_acquire() executed before the lock was acquired (loosely
+ * speaking).
+ *)
+
+{
+}
+
+P0(spinlock_t *lo, int *x)
+{
+ spin_lock(lo);
+ WRITE_ONCE(*x, 1);
+ spin_unlock(lo);
+}
+
+P1(spinlock_t *lo, int *x)
+{
+ int r1;
+ int r2;
+ int r3;
+
+ r1 = smp_load_acquire(x);
+ r2 = spin_is_locked(lo);
+ r3 = spin_is_locked(lo);
+}
+
+exists (1:r1=1 /\ 1:r2=0 /\ 1:r3=1)
diff --git a/tools/memory-model/litmus-tests/README b/tools/memory-model/litmus-tests/README
index 04096fb..17eb9a8 100644
--- a/tools/memory-model/litmus-tests/README
+++ b/tools/memory-model/litmus-tests/README
@@ -23,7 +23,8 @@
between each pairs of reads. In other words, is smp_mb()
sufficient to cause two different reading processes to agree on
the order of a pair of writes, where each write is to a different
- variable by a different process?
+ variable by a different process? This litmus test is forbidden
+ by LKMM's propagation rule.
IRIW+poonceonces+OnceOnce.litmus
Test of independent reads from independent writes with nothing
@@ -63,6 +64,16 @@
MP+onceassign+derefonce.litmus
As below, but with rcu_assign_pointer() and an rcu_dereference().
+MP+polockmbonce+poacquiresilsil.litmus
+ Protect the access with a lock and an smp_mb__after_spinlock()
+ in one process, and use an acquire load followed by a pair of
+ spin_is_locked() calls in the other process.
+
+MP+polockonce+poacquiresilsil.litmus
+ Protect the access with a lock in one process, and use an
+ acquire load followed by a pair of spin_is_locked() calls
+ in the other process.
+
MP+polocks.litmus
As below, but with the second access of the writer process
and the first access of reader process protected by a lock.
@@ -109,8 +120,10 @@
WRC+poonceonces+Once.litmus
WRC+pooncerelease+rmbonceonce+Once.litmus
- These two are members of an extension of the MP litmus-test class
- in which the first write is moved to a separate process.
+ These two are members of an extension of the MP litmus-test
+ class in which the first write is moved to a separate process.
+ The second is forbidden because smp_store_release() is
+ A-cumulative in LKMM.
Z6.0+pooncelock+pooncelock+pombonce.litmus
Is the ordering provided by a spin_unlock() and a subsequent
diff --git a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus b/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus
index 97fcbff..ad3448b 100644
--- a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus
+++ b/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus
@@ -5,7 +5,9 @@
*
* This litmus test is an extension of the message-passing pattern, where
* the first write is moved to a separate process. Because it features
- * a release and a read memory barrier, it should be forbidden.
+ * a release and a read memory barrier, it should be forbidden. More
+ * specifically, this litmus test is forbidden because smp_store_release()
+ * is A-cumulative in LKMM.
*)
{}
diff --git a/tools/memory-model/lock.cat b/tools/memory-model/lock.cat
index ba4a4ec..305ded1 100644
--- a/tools/memory-model/lock.cat
+++ b/tools/memory-model/lock.cat
@@ -4,46 +4,72 @@
* Copyright (C) 2017 Alan Stern <stern@rowland.harvard.edu>
*)
-(* Generate coherence orders and handle lock operations *)
+(*
+ * Generate coherence orders and handle lock operations
+ *
+ * Warning: spin_is_locked() crashes herd7 versions strictly before 7.48.
+ * spin_is_locked() is functional from herd7 version 7.49.
+ *)
include "cross.cat"
-(* From lock reads to their partner lock writes *)
+(*
+ * The lock-related events generated by herd are as follows:
+ *
+ * LKR Lock-Read: the read part of a spin_lock() or successful
+ * spin_trylock() read-modify-write event pair
+ * LKW Lock-Write: the write part of a spin_lock() or successful
+ * spin_trylock() RMW event pair
+ * UL Unlock: a spin_unlock() event
+ * LF Lock-Fail: a failed spin_trylock() event
+ * RL Read-Locked: a spin_is_locked() event which returns True
+ * RU Read-Unlocked: a spin_is_locked() event which returns False
+ *
+ * LKR and LKW events always come paired, like all RMW event sequences.
+ *
+ * LKR, LF, RL, and RU are read events; LKR has Acquire ordering.
+ * LKW and UL are write events; UL has Release ordering.
+ * LKW, LF, RL, and RU have no ordering properties.
+ *)
+
+(* Backward compatibility *)
+let RL = try RL with emptyset
+let RU = try RU with emptyset
+
+(* Treat RL as a kind of LF: a read with no ordering properties *)
+let LF = LF | RL
+
+(* There should be no ordinary R or W accesses to spinlocks *)
+let ALL-LOCKS = LKR | LKW | UL | LF | RU
+flag ~empty [M \ IW] ; loc ; [ALL-LOCKS] as mixed-lock-accesses
+
+(* Link Lock-Reads to their RMW-partner Lock-Writes *)
let lk-rmw = ([LKR] ; po-loc ; [LKW]) \ (po ; po)
let rmw = rmw | lk-rmw
-(*
- * A paired LKR must always see an unlocked value; spin_lock() calls nested
- * inside a critical section (for the same lock) always deadlock.
- *)
-empty ([LKW] ; po-loc ; [domain(lk-rmw)]) \ (po-loc ; [UL] ; po-loc)
- as lock-nest
-
-(* The litmus test is invalid if an LKW event is not part of an RMW pair *)
+(* The litmus test is invalid if an LKR/LKW event is not part of an RMW pair *)
flag ~empty LKW \ range(lk-rmw) as unpaired-LKW
-
-(* This will be allowed if we implement spin_is_locked() *)
flag ~empty LKR \ domain(lk-rmw) as unpaired-LKR
-(* There should be no R or W accesses to spinlocks *)
-let ALL-LOCKS = LKR | LKW | UL | LF
-flag ~empty [M \ IW] ; loc ; [ALL-LOCKS] as mixed-lock-accesses
+(*
+ * An LKR must always see an unlocked value; spin_lock() calls nested
+ * inside a critical section (for the same lock) always deadlock.
+ *)
+empty ([LKW] ; po-loc ; [LKR]) \ (po-loc ; [UL] ; po-loc) as lock-nest
(* The final value of a spinlock should not be tested *)
flag ~empty [FW] ; loc ; [ALL-LOCKS] as lock-final
-
(*
* Put lock operations in their appropriate classes, but leave UL out of W
* until after the co relation has been generated.
*)
-let R = R | LKR | LF
+let R = R | LKR | LF | RU
let W = W | LKW
let Release = Release | UL
let Acquire = Acquire | LKR
-
(* Match LKW events to their corresponding UL events *)
let critical = ([LKW] ; po-loc ; [UL]) \ (po-loc ; [LKW | UL] ; po-loc)
@@ -53,27 +79,48 @@
let UNMATCHED-LKW = LKW \ domain(critical)
empty ([UNMATCHED-LKW] ; loc ; [UNMATCHED-LKW]) \ id as unmatched-locks
-
(* rfi for LF events: link each LKW to the LF events in its critical section *)
let rfi-lf = ([LKW] ; po-loc ; [LF]) \ ([LKW] ; po-loc ; [UL] ; po-loc)
(* rfe for LF events *)
let all-possible-rfe-lf =
- (*
- * Given an LF event r, compute the possible rfe edges for that event
- * (all those starting from LKW events in other threads),
- * and then convert that relation to a set of single-edge relations.
- *)
- let possible-rfe-lf r =
- let pair-to-relation p = p ++ 0
- in map pair-to-relation ((LKW * {r}) & loc & ext)
- (* Do this for each LF event r that isn't in rfi-lf *)
- in map possible-rfe-lf (LF \ range(rfi-lf))
+ (*
+ * Given an LF event r, compute the possible rfe edges for that event
+ * (all those starting from LKW events in other threads),
+ * and then convert that relation to a set of single-edge relations.
+ *)
+ let possible-rfe-lf r =
+ let pair-to-relation p = p ++ 0
+ in map pair-to-relation ((LKW * {r}) & loc & ext)
+ (* Do this for each LF event r that isn't in rfi-lf *)
+ in map possible-rfe-lf (LF \ range(rfi-lf))
(* Generate all rf relations for LF events *)
with rfe-lf from cross(all-possible-rfe-lf)
-let rf = rf | rfi-lf | rfe-lf
+let rf-lf = rfe-lf | rfi-lf
+(*
+ * RU, i.e., spin_is_locked() returning False, is slightly different.
+ * We rely on the memory model to rule out cases where spin_is_locked()
+ * within one of the lock's critical sections returns False.
+ *)
+
+(* rfi for RU events: an RU may read from the last po-previous UL *)
+let rfi-ru = ([UL] ; po-loc ; [RU]) \ ([UL] ; po-loc ; [LKW] ; po-loc)
+
+(* rfe for RU events: an RU may read from an external UL or the initial write *)
+let all-possible-rfe-ru =
+ let possible-rfe-ru r =
+ let pair-to-relation p = p ++ 0
+ in map pair-to-relation (((UL | IW) * {r}) & loc & ext)
+ in map possible-rfe-ru RU
+
+(* Generate all rf relations for RU events *)
+with rfe-ru from cross(all-possible-rfe-ru)
+let rf-ru = rfe-ru | rfi-ru
+
+(* Final rf relation *)
+let rf = rf | rf-lf | rf-ru
(* Generate all co relations, including LKW events but not UL *)
let co0 = co0 | ([IW] ; loc ; [LKW]) |
diff --git a/tools/memory-model/scripts/checkalllitmus.sh b/tools/memory-model/scripts/checkalllitmus.sh
new file mode 100644
index 0000000..af0aa15
--- /dev/null
+++ b/tools/memory-model/scripts/checkalllitmus.sh
@@ -0,0 +1,73 @@
+#!/bin/sh
+#
+# Run herd tests on all .litmus files in the specified directory (which
+# defaults to litmus-tests) and check each file's result against a "Result:"
+# comment within that litmus test. If the verification result does not
+# match that specified in the litmus test, this script prints an error
+# message prefixed with "^^^". It also outputs verification results to
+# a file whose name is that of the specified litmus test, but with ".out"
+# appended.
+#
+# Usage:
+# sh checkalllitmus.sh [ directory ]
+#
+# The LINUX_HERD_OPTIONS environment variable may be used to specify
+# arguments to herd, whose default is defined by the checklitmus.sh script.
+# Thus, one would normally run this in the directory containing the memory
+# model, specifying the pathname of the litmus test to check.
+#
+# This script makes no attempt to run the litmus tests concurrently.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
+#
+# Copyright IBM Corporation, 2018
+#
+# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+litmusdir=${1-litmus-tests}
+if test -d "$litmusdir" -a -r "$litmusdir" -a -x "$litmusdir"
+then
+ :
+else
+ echo ' --- ' error: $litmusdir is not an accessible directory
+ exit 255
+fi
+
+# Find the checklitmus script. If it is not where we expect it, then
+# assume that the caller has the PATH environment variable set
+# appropriately.
+if test -x scripts/checklitmus.sh
+then
+ clscript=scripts/checklitmus.sh
+else
+ clscript=checklitmus.sh
+fi
+
+# Run the script on all the litmus tests in the specified directory
+ret=0
+for i in litmus-tests/*.litmus
+do
+ if ! $clscript $i
+ then
+ ret=1
+ fi
+done
+if test "$ret" -ne 0
+then
+ echo " ^^^ VERIFICATION MISMATCHES"
+else
+ echo All litmus tests verified as was expected.
+fi
+exit $ret
diff --git a/tools/memory-model/scripts/checklitmus.sh b/tools/memory-model/scripts/checklitmus.sh
new file mode 100644
index 0000000..e2e4774
--- /dev/null
+++ b/tools/memory-model/scripts/checklitmus.sh
@@ -0,0 +1,86 @@
+#!/bin/sh
+#
+# Run a herd test and check the result against a "Result:" comment within
+# the litmus test. If the verification result does not match that specified
+# in the litmus test, this script prints an error message prefixed with
+# "^^^" and exits with a non-zero status. It also outputs verification
+# results to a file whose name is that of the specified litmus test, but
+# with ".out" appended.
+#
+# Usage:
+# sh checklitmus.sh file.litmus
+#
+# The LINUX_HERD_OPTIONS environment variable may be used to specify
+# arguments to herd, which default to "-conf linux-kernel.cfg". Thus,
+# one would normally run this in the directory containing the memory model,
+# specifying the pathname of the litmus test to check.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
+#
+# Copyright IBM Corporation, 2018
+#
+# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+litmus=$1
+herdoptions=${LINUX_HERD_OPTIONS--conf linux-kernel.cfg}
+
+if test -f "$litmus" -a -r "$litmus"
+then
+ :
+else
+ echo ' --- ' error: \"$litmus\" is not a readable file
+ exit 255
+fi
+if grep -q '^ \* Result: ' $litmus
+then
+ outcome=`grep -m 1 '^ \* Result: ' $litmus | awk '{ print $3 }'`
+else
+ outcome=specified
+fi
+
+echo Herd options: $herdoptions > $litmus.out
+/usr/bin/time herd7 -o ~/tmp $herdoptions $litmus >> $litmus.out 2>&1
+grep "Herd options:" $litmus.out
+grep '^Observation' $litmus.out
+if grep -q '^Observation' $litmus.out
+then
+ :
+else
+ cat $litmus.out
+ echo ' ^^^ Verification error'
+ echo ' ^^^ Verification error' >> $litmus.out 2>&1
+ exit 255
+fi
+if test "$outcome" = DEADLOCK
+then
+ echo grep 3 and 4
+ if grep '^Observation' $litmus.out | grep -q 'Never 0 0$'
+ then
+ ret=0
+ else
+ echo " ^^^ Unexpected non-$outcome verification"
+ echo " ^^^ Unexpected non-$outcome verification" >> $litmus.out 2>&1
+ ret=1
+ fi
+elif grep '^Observation' $litmus.out | grep -q $outcome || test "$outcome" = Maybe
+then
+ ret=0
+else
+ echo " ^^^ Unexpected non-$outcome verification"
+ echo " ^^^ Unexpected non-$outcome verification" >> $litmus.out 2>&1
+ ret=1
+fi
+tail -2 $litmus.out | head -1
+exit $ret
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 8ae824d..f76d991 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -31,8 +31,8 @@
-I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
-I$(srctree)/tools/objtool/arch/$(ARCH)/include
WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
-CFLAGS += -Wall -Werror $(WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES)
-LDFLAGS += -lelf $(LIBSUBCMD)
+CFLAGS += -Werror $(WARNINGS) $(HOSTCFLAGS) -g $(INCLUDES)
+LDFLAGS += -lelf $(LIBSUBCMD) $(HOSTLDFLAGS)
# Allow old libelf to be used:
elfshdr := $(shell echo '$(pound)include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | grep elf_getshdr)
diff --git a/tools/objtool/arch/x86/include/asm/insn.h b/tools/objtool/arch/x86/include/asm/insn.h
index b3e32b0..c2c01f8 100644
--- a/tools/objtool/arch/x86/include/asm/insn.h
+++ b/tools/objtool/arch/x86/include/asm/insn.h
@@ -208,4 +208,22 @@ static inline int insn_offset_immediate(struct insn *insn)
return insn_offset_displacement(insn) + insn->displacement.nbytes;
}
+#define POP_SS_OPCODE 0x1f
+#define MOV_SREG_OPCODE 0x8e
+
+/*
+ * Intel SDM Vol.3A 6.8.3 states;
+ * "Any single-step trap that would be delivered following the MOV to SS
+ * instruction or POP to SS instruction (because EFLAGS.TF is 1) is
+ * suppressed."
+ * This function returns true if @insn is MOV SS or POP SS. On these
+ * instructions, single stepping is suppressed.
+ */
+static inline int insn_masking_exception(struct insn *insn)
+{
+ return insn->opcode.bytes[0] == POP_SS_OPCODE ||
+ (insn->opcode.bytes[0] == MOV_SREG_OPCODE &&
+ X86_MODRM_REG(insn->modrm.bytes[0]) == 2);
+}
+
#endif /* _ASM_X86_INSN_H */
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 5409f6f..3a31b23 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -59,6 +59,31 @@ static struct instruction *next_insn_same_sec(struct objtool_file *file,
return next;
}
+static struct instruction *next_insn_same_func(struct objtool_file *file,
+ struct instruction *insn)
+{
+ struct instruction *next = list_next_entry(insn, list);
+ struct symbol *func = insn->func;
+
+ if (!func)
+ return NULL;
+
+ if (&next->list != &file->insn_list && next->func == func)
+ return next;
+
+ /* Check if we're already in the subfunction: */
+ if (func == func->cfunc)
+ return NULL;
+
+ /* Move to the subfunction: */
+ return find_insn(file, func->cfunc->sec, func->cfunc->offset);
+}
+
+#define func_for_each_insn_all(file, func, insn) \
+ for (insn = find_insn(file, func->sec, func->offset); \
+ insn; \
+ insn = next_insn_same_func(file, insn))
+
#define func_for_each_insn(file, func, insn) \
for (insn = find_insn(file, func->sec, func->offset); \
insn && &insn->list != &file->insn_list && \
@@ -149,10 +174,14 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func,
if (!strcmp(func->name, global_noreturns[i]))
return 1;
- if (!func->sec)
+ if (!func->len)
return 0;
- func_for_each_insn(file, func, insn) {
+ insn = find_insn(file, func->sec, func->offset);
+ if (!insn->func)
+ return 0;
+
+ func_for_each_insn_all(file, func, insn) {
empty = false;
if (insn->type == INSN_RETURN)
@@ -167,35 +196,28 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func,
* case, the function's dead-end status depends on whether the target
* of the sibling call returns.
*/
- func_for_each_insn(file, func, insn) {
- if (insn->sec != func->sec ||
- insn->offset >= func->offset + func->len)
- break;
-
+ func_for_each_insn_all(file, func, insn) {
if (insn->type == INSN_JUMP_UNCONDITIONAL) {
struct instruction *dest = insn->jump_dest;
- struct symbol *dest_func;
if (!dest)
/* sibling call to another file */
return 0;
- if (dest->sec != func->sec ||
- dest->offset < func->offset ||
- dest->offset >= func->offset + func->len) {
- /* local sibling call */
- dest_func = find_symbol_by_offset(dest->sec,
- dest->offset);
- if (!dest_func)
- continue;
+ if (dest->func && dest->func->pfunc != insn->func->pfunc) {
+ /* local sibling call */
if (recursion == 5) {
- WARN_FUNC("infinite recursion (objtool bug!)",
- dest->sec, dest->offset);
- return -1;
+ /*
+ * Infinite recursion: two functions
+ * have sibling calls to each other.
+ * This is a very rare case. It means
+ * they aren't dead ends.
+ */
+ return 0;
}
- return __dead_end_function(file, dest_func,
+ return __dead_end_function(file, dest->func,
recursion + 1);
}
}
@@ -422,7 +444,7 @@ static void add_ignores(struct objtool_file *file)
if (!ignore_func(file, func))
continue;
- func_for_each_insn(file, func, insn)
+ func_for_each_insn_all(file, func, insn)
insn->ignore = true;
}
}
@@ -782,30 +804,35 @@ static int add_special_section_alts(struct objtool_file *file)
return ret;
}
-static int add_switch_table(struct objtool_file *file, struct symbol *func,
- struct instruction *insn, struct rela *table,
- struct rela *next_table)
+static int add_switch_table(struct objtool_file *file, struct instruction *insn,
+ struct rela *table, struct rela *next_table)
{
struct rela *rela = table;
struct instruction *alt_insn;
struct alternative *alt;
+ struct symbol *pfunc = insn->func->pfunc;
+ unsigned int prev_offset = 0;
list_for_each_entry_from(rela, &file->rodata->rela->rela_list, list) {
if (rela == next_table)
break;
- if (rela->sym->sec != insn->sec ||
- rela->addend <= func->offset ||
- rela->addend >= func->offset + func->len)
+ /* Make sure the switch table entries are consecutive: */
+ if (prev_offset && rela->offset != prev_offset + 8)
break;
- alt_insn = find_insn(file, insn->sec, rela->addend);
- if (!alt_insn) {
- WARN("%s: can't find instruction at %s+0x%x",
- file->rodata->rela->name, insn->sec->name,
- rela->addend);
- return -1;
- }
+ /* Detect function pointers from contiguous objects: */
+ if (rela->sym->sec == pfunc->sec &&
+ rela->addend == pfunc->offset)
+ break;
+
+ alt_insn = find_insn(file, rela->sym->sec, rela->addend);
+ if (!alt_insn)
+ break;
+
+ /* Make sure the jmp dest is in the function or subfunction: */
+ if (alt_insn->func->pfunc != pfunc)
+ break;
alt = malloc(sizeof(*alt));
if (!alt) {
@@ -815,6 +842,13 @@ static int add_switch_table(struct objtool_file *file, struct symbol *func,
alt->insn = alt_insn;
list_add_tail(&alt->list, &insn->alts);
+ prev_offset = rela->offset;
+ }
+
+ if (!prev_offset) {
+ WARN_FUNC("can't find switch jump table",
+ insn->sec, insn->offset);
+ return -1;
}
return 0;
@@ -869,40 +903,21 @@ static struct rela *find_switch_table(struct objtool_file *file,
{
struct rela *text_rela, *rodata_rela;
struct instruction *orig_insn = insn;
+ unsigned long table_offset;
- text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len);
- if (text_rela && text_rela->sym == file->rodata->sym) {
- /* case 1 */
- rodata_rela = find_rela_by_dest(file->rodata,
- text_rela->addend);
- if (rodata_rela)
- return rodata_rela;
-
- /* case 2 */
- rodata_rela = find_rela_by_dest(file->rodata,
- text_rela->addend + 4);
- if (!rodata_rela)
- return NULL;
-
- file->ignore_unreachables = true;
- return rodata_rela;
- }
-
- /* case 3 */
/*
* Backward search using the @first_jump_src links, these help avoid
* much of the 'in between' code. Which avoids us getting confused by
* it.
*/
- for (insn = list_prev_entry(insn, list);
-
+ for (;
&insn->list != &file->insn_list &&
insn->sec == func->sec &&
insn->offset >= func->offset;
insn = insn->first_jump_src ?: list_prev_entry(insn, list)) {
- if (insn->type == INSN_JUMP_DYNAMIC)
+ if (insn != orig_insn && insn->type == INSN_JUMP_DYNAMIC)
break;
/* allow small jumps within the range */
@@ -918,18 +933,29 @@ static struct rela *find_switch_table(struct objtool_file *file,
if (!text_rela || text_rela->sym != file->rodata->sym)
continue;
+ table_offset = text_rela->addend;
+ if (text_rela->type == R_X86_64_PC32)
+ table_offset += 4;
+
/*
* Make sure the .rodata address isn't associated with a
* symbol. gcc jump tables are anonymous data.
*/
- if (find_symbol_containing(file->rodata, text_rela->addend))
+ if (find_symbol_containing(file->rodata, table_offset))
continue;
- rodata_rela = find_rela_by_dest(file->rodata, text_rela->addend);
- if (!rodata_rela)
- continue;
+ rodata_rela = find_rela_by_dest(file->rodata, table_offset);
+ if (rodata_rela) {
+ /*
+ * Use of RIP-relative switch jumps is quite rare, and
+ * indicates a rare GCC quirk/bug which can leave dead
+ * code behind.
+ */
+ if (text_rela->type == R_X86_64_PC32)
+ file->ignore_unreachables = true;
- return rodata_rela;
+ return rodata_rela;
+ }
}
return NULL;
@@ -943,7 +969,7 @@ static int add_func_switch_tables(struct objtool_file *file,
struct rela *rela, *prev_rela = NULL;
int ret;
- func_for_each_insn(file, func, insn) {
+ func_for_each_insn_all(file, func, insn) {
if (!last)
last = insn;
@@ -974,8 +1000,7 @@ static int add_func_switch_tables(struct objtool_file *file,
* the beginning of another switch table in the same function.
*/
if (prev_jump) {
- ret = add_switch_table(file, func, prev_jump, prev_rela,
- rela);
+ ret = add_switch_table(file, prev_jump, prev_rela, rela);
if (ret)
return ret;
}
@@ -985,7 +1010,7 @@ static int add_func_switch_tables(struct objtool_file *file,
}
if (prev_jump) {
- ret = add_switch_table(file, func, prev_jump, prev_rela, NULL);
+ ret = add_switch_table(file, prev_jump, prev_rela, NULL);
if (ret)
return ret;
}
@@ -1749,15 +1774,13 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
while (1) {
next_insn = next_insn_same_sec(file, insn);
-
- if (file->c_file && func && insn->func && func != insn->func) {
+ if (file->c_file && func && insn->func && func != insn->func->pfunc) {
WARN("%s() falls through to next function %s()",
func->name, insn->func->name);
return 1;
}
- if (insn->func)
- func = insn->func;
+ func = insn->func ? insn->func->pfunc : NULL;
if (func && insn->ignore) {
WARN_FUNC("BUG: why am I validating an ignored function?",
@@ -1778,7 +1801,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
i = insn;
save_insn = NULL;
- func_for_each_insn_continue_reverse(file, func, i) {
+ func_for_each_insn_continue_reverse(file, insn->func, i) {
if (i->save) {
save_insn = i;
break;
@@ -1865,7 +1888,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
case INSN_JUMP_UNCONDITIONAL:
if (insn->jump_dest &&
(!func || !insn->jump_dest->func ||
- func == insn->jump_dest->func)) {
+ insn->jump_dest->func->pfunc == func)) {
ret = validate_branch(file, insn->jump_dest,
state);
if (ret)
@@ -2060,7 +2083,7 @@ static int validate_functions(struct objtool_file *file)
for_each_sec(file, sec) {
list_for_each_entry(func, &sec->symbol_list, list) {
- if (func->type != STT_FUNC)
+ if (func->type != STT_FUNC || func->pfunc != func)
continue;
insn = find_insn(file, sec, func->offset);
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index c1c3386..4e60e10 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -79,6 +79,19 @@ struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset)
return NULL;
}
+struct symbol *find_symbol_by_name(struct elf *elf, const char *name)
+{
+ struct section *sec;
+ struct symbol *sym;
+
+ list_for_each_entry(sec, &elf->sections, list)
+ list_for_each_entry(sym, &sec->symbol_list, list)
+ if (!strcmp(sym->name, name))
+ return sym;
+
+ return NULL;
+}
+
struct symbol *find_symbol_containing(struct section *sec, unsigned long offset)
{
struct symbol *sym;
@@ -203,10 +216,11 @@ static int read_sections(struct elf *elf)
static int read_symbols(struct elf *elf)
{
- struct section *symtab;
- struct symbol *sym;
+ struct section *symtab, *sec;
+ struct symbol *sym, *pfunc;
struct list_head *entry, *tmp;
int symbols_nr, i;
+ char *coldstr;
symtab = find_section_by_name(elf, ".symtab");
if (!symtab) {
@@ -281,6 +295,30 @@ static int read_symbols(struct elf *elf)
hash_add(sym->sec->symbol_hash, &sym->hash, sym->idx);
}
+ /* Create parent/child links for any cold subfunctions */
+ list_for_each_entry(sec, &elf->sections, list) {
+ list_for_each_entry(sym, &sec->symbol_list, list) {
+ if (sym->type != STT_FUNC)
+ continue;
+ sym->pfunc = sym->cfunc = sym;
+ coldstr = strstr(sym->name, ".cold.");
+ if (coldstr) {
+ coldstr[0] = '\0';
+ pfunc = find_symbol_by_name(elf, sym->name);
+ coldstr[0] = '.';
+
+ if (!pfunc) {
+ WARN("%s(): can't find parent function",
+ sym->name);
+ goto err;
+ }
+
+ sym->pfunc = pfunc;
+ pfunc->cfunc = sym;
+ }
+ }
+ }
+
return 0;
err:
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index d86e2ff1..de5cd2d 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -61,6 +61,7 @@ struct symbol {
unsigned char bind, type;
unsigned long offset;
unsigned int len;
+ struct symbol *pfunc, *cfunc;
};
struct rela {
@@ -86,6 +87,7 @@ struct elf {
struct elf *elf_open(const char *name, int flags);
struct section *find_section_by_name(struct elf *elf, const char *name);
struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset);
+struct symbol *find_symbol_by_name(struct elf *elf, const char *name);
struct symbol *find_symbol_containing(struct section *sec, unsigned long offset);
struct rela *find_rela_by_dest(struct section *sec, unsigned long offset);
struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index db11478..42261a9 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -47,7 +47,8 @@
man7dir=$(mandir)/man7
ASCIIDOC=asciidoc
-ASCIIDOC_EXTRA = --unsafe
+ASCIIDOC_EXTRA = --unsafe -f asciidoc.conf
+ASCIIDOC_HTML = xhtml11
MANPAGE_XSL = manpage-normal.xsl
XMLTO_EXTRA =
INSTALL?=install
@@ -55,6 +56,14 @@
DOC_REF = origin/man
HTML_REF = origin/html
+ifdef USE_ASCIIDOCTOR
+ASCIIDOC = asciidoctor
+ASCIIDOC_EXTRA = -a compat-mode
+ASCIIDOC_EXTRA += -I. -rasciidoctor-extensions
+ASCIIDOC_EXTRA += -a mansource="perf" -a manmanual="perf Manual"
+ASCIIDOC_HTML = xhtml5
+endif
+
infodir?=$(prefix)/share/info
MAKEINFO=makeinfo
INSTALL_INFO=install-info
@@ -73,10 +82,12 @@
missing_tools = $(ASCIIDOC)
endif
+ifndef USE_ASCIIDOCTOR
_tmp_tool_path := $(call get-executable,$(XMLTO))
ifeq ($(_tmp_tool_path),)
missing_tools += $(XMLTO)
endif
+endif
#
# For asciidoc ...
@@ -264,17 +275,25 @@
$(MAN_HTML): $(OUTPUT)%.html : %.txt
$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
- $(ASCIIDOC) -b xhtml11 -d manpage -f asciidoc.conf \
+ $(ASCIIDOC) -b $(ASCIIDOC_HTML) -d manpage \
$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
mv $@+ $@
+ifdef USE_ASCIIDOCTOR
+$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.txt
+ $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
+ $(ASCIIDOC) -b manpage -d manpage \
+ $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
+ mv $@+ $@
+endif
+
$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml
$(QUIET_XMLTO)$(RM) $@ && \
$(XMLTO) -o $(OUTPUT). -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $<
$(OUTPUT)%.xml : %.txt
$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
- $(ASCIIDOC) -b docbook -d manpage -f asciidoc.conf \
+ $(ASCIIDOC) -b docbook -d manpage \
$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
mv $@+ $@
@@ -321,13 +340,13 @@
mv $@+ $@
$(patsubst %,%.html,$(ARTICLES)) : %.html : %.txt
- $(QUIET_ASCIIDOC)$(ASCIIDOC) -b xhtml11 $*.txt
+ $(QUIET_ASCIIDOC)$(ASCIIDOC) -b $(ASCIIDOC_HTML) $*.txt
WEBDOC_DEST = /pub/software/tools/perf/docs
$(patsubst %.txt,%.html,$(wildcard howto/*.txt)): %.html : %.txt
$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
- sed -e '1,/^$$/d' $< | $(ASCIIDOC) -b xhtml11 - >$@+ && \
+ sed -e '1,/^$$/d' $< | $(ASCIIDOC) -b $(ASCIIDOC_HTML) - >$@+ && \
mv $@+ $@
# UNIMPLEMENTED
diff --git a/tools/perf/Documentation/asciidoctor-extensions.rb b/tools/perf/Documentation/asciidoctor-extensions.rb
new file mode 100644
index 0000000..d148fe9
--- /dev/null
+++ b/tools/perf/Documentation/asciidoctor-extensions.rb
@@ -0,0 +1,29 @@
+require 'asciidoctor'
+require 'asciidoctor/extensions'
+
+module Perf
+ module Documentation
+ class LinkPerfProcessor < Asciidoctor::Extensions::InlineMacroProcessor
+ use_dsl
+
+ named :chrome
+
+ def process(parent, target, attrs)
+ if parent.document.basebackend? 'html'
+ %(<a href="#{target}.html">#{target}(#{attrs[1]})</a>\n)
+ elsif parent.document.basebackend? 'manpage'
+ "#{target}(#{attrs[1]})"
+ elsif parent.document.basebackend? 'docbook'
+ "<citerefentry>\n" \
+ "<refentrytitle>#{target}</refentrytitle>" \
+ "<manvolnum>#{attrs[1]}</manvolnum>\n" \
+ "</citerefentry>\n"
+ end
+ end
+ end
+ end
+end
+
+Asciidoctor::Extensions.register do
+ inline_macro Perf::Documentation::LinkPerfProcessor, :linkperf
+end
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index 73c2650..f6de095 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -48,6 +48,9 @@
--purge=::
Purge all cached binaries including older caches which have specified
path from the cache.
+-P::
+--purge-all::
+ Purge all cached binaries. This will flush out entire cache.
-M::
--missing=::
List missing build ids in the cache for the specified file.
@@ -59,7 +62,9 @@
exactly same build-id, that is replaced by new one. It can be used
to update kallsyms and kernel dso to vmlinux in order to support
annotation.
-
+-l::
+--list::
+ List all valid binaries from cache.
-v::
--verbose::
Be more verbose.
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 5b4fff3..32f4a89 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -334,6 +334,11 @@
99.93 │ mov %eax,%eax
+ annotate.offset_level::
+ Default is '1', meaning just jump targets will have offsets show right beside
+ the instruction. When set to '2' 'call' instructions will also have its offsets
+ shown, 3 or higher will show offsets for all instructions.
+
hist.*::
hist.percentage::
This option control the way to calculate overhead of filtered entries -
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index b021141..f8d2167 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -28,29 +28,46 @@
<command>...::
Any command you can specify in a shell.
+-i::
+--input=<file>::
+ Input file name.
+
-f::
--force::
Don't do ownership validation
-t::
---type=::
+--type=<type>::
Select the memory operation type: load or store (default: load,store)
-D::
---dump-raw-samples=::
+--dump-raw-samples::
Dump the raw decoded samples on the screen in a format that is easy to parse with
one sample per line.
-x::
---field-separator::
+--field-separator=<separator>::
Specify the field separator used when dump raw samples (-D option). By default,
The separator is the space character.
-C::
---cpu-list::
- Restrict dump of raw samples to those provided via this option. Note that the same
- option can be passed in record mode. It will be interpreted the same way as perf
- record.
+--cpu=<cpu>::
+ Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a
+ comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2. Default
+ is to monitor all CPUS.
+-U::
+--hide-unresolved::
+ Only display entries resolved to a symbol.
+
+-p::
+--phys-data::
+ Record/Report sample physical addresses
+
+RECORD OPTIONS
+--------------
+-e::
+--event <event>::
+ Event selector. Use 'perf mem record -e list' to list available events.
-K::
--all-kernel::
@@ -60,12 +77,15 @@
--all-user::
Configure all used events to run in user space.
---ldload::
+-v::
+--verbose::
+ Be more verbose (show counter open errors, etc)
+
+--ldlat <n>::
Specify desired latency for loads event.
--p::
---phys-data::
- Record/Report sample physical addresses
+In addition, for report all perf report options are valid, and for record
+all perf record options.
SEE ALSO
--------
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index bb33601a..63f938b 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -104,8 +104,8 @@
kallsyms pathname
-g::
---no-call-graph::
- Do not display call chains if present.
+--call-graph::
+ Display call chains if present (default on).
--max-stack::
Maximum number of functions to display in backtrace, default 5.
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 36ec025..afdafe2 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -228,14 +228,15 @@
For sample events it's possible to display misc field with -F +misc option,
following letters are displayed for each bit:
- PERF_RECORD_MISC_KERNEL K
- PERF_RECORD_MISC_USER U
- PERF_RECORD_MISC_HYPERVISOR H
- PERF_RECORD_MISC_GUEST_KERNEL G
- PERF_RECORD_MISC_GUEST_USER g
- PERF_RECORD_MISC_MMAP_DATA* M
- PERF_RECORD_MISC_COMM_EXEC E
- PERF_RECORD_MISC_SWITCH_OUT S
+ PERF_RECORD_MISC_KERNEL K
+ PERF_RECORD_MISC_USER U
+ PERF_RECORD_MISC_HYPERVISOR H
+ PERF_RECORD_MISC_GUEST_KERNEL G
+ PERF_RECORD_MISC_GUEST_USER g
+ PERF_RECORD_MISC_MMAP_DATA* M
+ PERF_RECORD_MISC_COMM_EXEC E
+ PERF_RECORD_MISC_SWITCH_OUT S
+ PERF_RECORD_MISC_SWITCH_OUT_PREEMPT Sp
$ perf script -F +misc ...
sched-messaging 1414 K 28690.636582: 4590 cycles ...
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index f15b306..3a822f3 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -116,6 +116,22 @@
print counts using a CSV-style output to make it easy to import directly into
spreadsheets. Columns are separated by the string specified in SEP.
+--table:: Display time for each run (-r option), in a table format, e.g.:
+
+ $ perf stat --null -r 5 --table perf bench sched pipe
+
+ Performance counter stats for 'perf bench sched pipe' (5 runs):
+
+ # Table of individual measurements:
+ 5.189 (-0.293) #
+ 5.189 (-0.294) #
+ 5.186 (-0.296) #
+ 5.663 (+0.181) ##
+ 6.186 (+0.703) ####
+
+ # Final result:
+ 5.483 +- 0.198 seconds time elapsed ( +- 3.62% )
+
-G name::
--cgroup name::
monitor only in the container (cgroup) called "name". This option is available only
@@ -153,7 +169,7 @@
-I msecs::
--interval-print msecs::
-Print count deltas every N milliseconds (minimum: 10ms)
+Print count deltas every N milliseconds (minimum: 1ms)
The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals. Use with caution.
example: 'perf stat -I 1000 -e cycles -a sleep 5'
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index d00f0d5..dfb218f 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -111,8 +111,8 @@
A structure defining the number of CPUs.
struct nr_cpus {
- uint32_t nr_cpus_online;
uint32_t nr_cpus_available; /* CPUs not yet onlined */
+ uint32_t nr_cpus_online;
};
HEADER_CPUDESC = 8,
@@ -153,10 +153,18 @@
HEADER_CPU_TOPOLOGY = 13,
String lists defining the core and CPU threads topology.
+The string lists are followed by a variable length array
+which contains core_id and socket_id of each cpu.
+The number of entries can be determined by the size of the
+section minus the sizes of both string lists.
struct {
struct perf_header_string_list cores; /* Variable length */
struct perf_header_string_list threads; /* Variable length */
+ struct {
+ uint32_t core_id;
+ uint32_t socket_id;
+ } cpus[nr]; /* Variable length records */
};
Example:
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index c7abd83..b5ac356b 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -68,7 +68,7 @@
endif
ifneq ($(NO_SYSCALL_TABLE),1)
- CFLAGS += -DHAVE_SYSCALL_TABLE
+ CFLAGS += -DHAVE_SYSCALL_TABLE_SUPPORT
endif
# So far there's only x86 and arm libdw unwind support merged in perf.
@@ -847,7 +847,7 @@
ifeq ($(feature-jvmti), 1)
$(call detected_var,JDIR)
else
- $(warning No openjdk development package found, please install JDK package)
+ $(warning No openjdk development package found, please install JDK package, e.g. openjdk-8-jdk, java-1.8.0-openjdk-devel)
NO_JVMTI := 1
endif
endif
@@ -885,6 +885,8 @@
# Among the variables below, these:
# perfexecdir
+# perf_include_dir
+# perf_examples_dir
# template_dir
# mandir
# infodir
@@ -904,6 +906,8 @@
mandir = share/man
infodir = share/info
perfexecdir = libexec/perf-core
+perf_include_dir = lib/include/perf
+perf_examples_dir = lib/examples/perf
sharedir = $(prefix)/share
template_dir = share/perf-core/templates
STRACE_GROUPS_DIR = share/perf-core/strace/groups
@@ -934,6 +938,8 @@
mandir_SQ = $(subst ','\'',$(mandir))
infodir_SQ = $(subst ','\'',$(infodir))
perfexecdir_SQ = $(subst ','\'',$(perfexecdir))
+perf_include_dir_SQ = $(subst ','\'',$(perf_include_dir))
+perf_examples_dir_SQ = $(subst ','\'',$(perf_examples_dir))
template_dir_SQ = $(subst ','\'',$(template_dir))
htmldir_SQ = $(subst ','\'',$(htmldir))
tipdir_SQ = $(subst ','\'',$(tipdir))
@@ -944,14 +950,20 @@
ifneq ($(filter /%,$(firstword $(perfexecdir))),)
perfexec_instdir = $(perfexecdir)
+perf_include_instdir = $(perf_include_dir)
+perf_examples_instdir = $(perf_examples_dir)
STRACE_GROUPS_INSTDIR = $(STRACE_GROUPS_DIR)
tip_instdir = $(tipdir)
else
perfexec_instdir = $(prefix)/$(perfexecdir)
+perf_include_instdir = $(prefix)/$(perf_include_dir)
+perf_examples_instdir = $(prefix)/$(perf_examples_dir)
STRACE_GROUPS_INSTDIR = $(prefix)/$(STRACE_GROUPS_DIR)
tip_instdir = $(prefix)/$(tipdir)
endif
perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
+perf_include_instdir_SQ = $(subst ','\'',$(perf_include_instdir))
+perf_examples_instdir_SQ = $(subst ','\'',$(perf_examples_instdir))
STRACE_GROUPS_INSTDIR_SQ = $(subst ','\'',$(STRACE_GROUPS_INSTDIR))
tip_instdir_SQ = $(subst ','\'',$(tip_instdir))
@@ -999,6 +1011,8 @@
$(call detected_var,STRACE_GROUPS_DIR_SQ)
$(call detected_var,prefix_SQ)
$(call detected_var,perfexecdir_SQ)
+$(call detected_var,perf_include_dir_SQ)
+$(call detected_var,perf_examples_dir_SQ)
$(call detected_var,tipdir_SQ)
$(call detected_var,srcdir_SQ)
$(call detected_var,LIBDIR)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 83e453d..ecc9fc9 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -767,6 +767,16 @@
endif
$(call QUIET_INSTALL, libexec) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+ifndef NO_LIBBPF
+ $(call QUIET_INSTALL, lib) \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
+ $(call QUIET_INSTALL, include/bpf) \
+ $(INSTALL) include/bpf/*.h '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
+ $(call QUIET_INSTALL, lib) \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
+ $(call QUIET_INSTALL, examples/bpf) \
+ $(INSTALL) examples/bpf/*.c '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
+endif
$(call QUIET_INSTALL, perf-archive) \
$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
$(call QUIET_INSTALL, perf-with-kcore) \
diff --git a/tools/perf/arch/arm/include/arch-tests.h b/tools/perf/arch/arm/include/arch-tests.h
new file mode 100644
index 0000000..90ec4c8
--- /dev/null
+++ b/tools/perf/arch/arm/include/arch-tests.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ARCH_TESTS_H
+#define ARCH_TESTS_H
+
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+struct thread;
+struct perf_sample;
+#endif
+
+extern struct test arch_tests[];
+
+#endif
diff --git a/tools/perf/arch/arm/tests/Build b/tools/perf/arch/arm/tests/Build
index b30eff9..883c57f 100644
--- a/tools/perf/arch/arm/tests/Build
+++ b/tools/perf/arch/arm/tests/Build
@@ -1,2 +1,4 @@
libperf-y += regs_load.o
libperf-y += dwarf-unwind.o
+
+libperf-y += arch-tests.o
diff --git a/tools/perf/arch/arm/tests/arch-tests.c b/tools/perf/arch/arm/tests/arch-tests.c
new file mode 100644
index 0000000..5b1543c
--- /dev/null
+++ b/tools/perf/arch/arm/tests/arch-tests.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+struct test arch_tests[] = {
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+ {
+ .desc = "DWARF unwind",
+ .func = test__dwarf_unwind,
+ },
+#endif
+ {
+ .func = NULL,
+ },
+};
diff --git a/tools/perf/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c
index 8cb3477..9a0242e 100644
--- a/tools/perf/arch/arm/tests/dwarf-unwind.c
+++ b/tools/perf/arch/arm/tests/dwarf-unwind.c
@@ -25,7 +25,7 @@ static int sample_ustack(struct perf_sample *sample,
sp = (unsigned long) regs[PERF_REG_ARM_SP];
- map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+ map = map_groups__find(thread->mg, (u64)sp);
if (!map) {
pr_debug("failed to get stack map\n");
free(buf);
diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c
index fa639e3..1ce6bdb 100644
--- a/tools/perf/arch/arm/util/auxtrace.c
+++ b/tools/perf/arch/arm/util/auxtrace.c
@@ -1,18 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright(C) 2015 Linaro Limited. All rights reserved.
* Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <stdbool.h>
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 5c655ad4..2f595cd 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -1,18 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright(C) 2015 Linaro Limited. All rights reserved.
* Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <api/fs/fs.h>
diff --git a/tools/perf/arch/arm/util/cs-etm.h b/tools/perf/arch/arm/util/cs-etm.h
index 5256741..1a12e64 100644
--- a/tools/perf/arch/arm/util/cs-etm.h
+++ b/tools/perf/arch/arm/util/cs-etm.h
@@ -1,18 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright(C) 2015 Linaro Limited. All rights reserved.
* Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program. If not, see <http://www.gnu.org/licenses/>.
*/
#ifndef INCLUDE__PERF_CS_ETM_H__
diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c
index ac4dffc..e047571 100644
--- a/tools/perf/arch/arm/util/pmu.c
+++ b/tools/perf/arch/arm/util/pmu.c
@@ -1,18 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright(C) 2015 Linaro Limited. All rights reserved.
* Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <string.h>
diff --git a/tools/perf/arch/arm64/tests/dwarf-unwind.c b/tools/perf/arch/arm64/tests/dwarf-unwind.c
index e907f0f..5522ce3 100644
--- a/tools/perf/arch/arm64/tests/dwarf-unwind.c
+++ b/tools/perf/arch/arm64/tests/dwarf-unwind.c
@@ -25,7 +25,7 @@ static int sample_ustack(struct perf_sample *sample,
sp = (unsigned long) regs[PERF_REG_ARM64_SP];
- map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+ map = map_groups__find(thread->mg, (u64)sp);
if (!map) {
pr_debug("failed to get stack map\n");
free(buf);
diff --git a/tools/perf/arch/powerpc/tests/dwarf-unwind.c b/tools/perf/arch/powerpc/tests/dwarf-unwind.c
index 30cbbd6..5f39efe 100644
--- a/tools/perf/arch/powerpc/tests/dwarf-unwind.c
+++ b/tools/perf/arch/powerpc/tests/dwarf-unwind.c
@@ -26,7 +26,7 @@ static int sample_ustack(struct perf_sample *sample,
sp = (unsigned long) regs[PERF_REG_POWERPC_R1];
- map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+ map = map_groups__find(thread->mg, (u64)sp);
if (!map) {
pr_debug("failed to get stack map\n");
free(buf);
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index 0c370f8..3598b8b 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -248,8 +248,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
ip = chain->ips[2];
- thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
- MAP__FUNCTION, ip, &al);
+ thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
if (al.map)
dso = al.map->dso;
diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c
index 6cb48e4..3afe825 100644
--- a/tools/perf/arch/s390/util/auxtrace.c
+++ b/tools/perf/arch/s390/util/auxtrace.c
@@ -87,6 +87,7 @@ struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
struct perf_evsel *pos;
int diagnose = 0;
+ *err = 0;
if (evlist->nr_entries == 0)
return NULL;
diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c
index a4c30f1..163b92f 100644
--- a/tools/perf/arch/s390/util/header.c
+++ b/tools/perf/arch/s390/util/header.c
@@ -146,21 +146,3 @@ char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
zfree(&buf);
return buf;
}
-
-/*
- * Compare the cpuid string returned by get_cpuid() function
- * with the name generated by the jevents file read from
- * pmu-events/arch/s390/mapfile.csv.
- *
- * Parameter mapcpuid is the cpuid as stored in the
- * pmu-events/arch/s390/mapfile.csv. This is just the type number.
- * Parameter cpuid is the cpuid returned by function get_cpuid().
- */
-int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
-{
- char *cp = strchr(cpuid, ',');
-
- if (cp == NULL)
- return -1;
- return strncmp(cp + 1, mapcpuid, strlen(mapcpuid));
-}
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index d74eaa7..1a38e78 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -21,7 +21,7 @@
$(header): $(sys)/syscall_64.tbl $(systbl)
@(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
(diff -B arch/x86/entry/syscalls/syscall_64.tbl ../../arch/x86/entry/syscalls/syscall_64.tbl >/dev/null) \
- || echo "Warning: Kernel ABI header at 'tools/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl'" >&2 )) || true
+ || echo "Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl'" >&2 )) || true
$(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@
clean::
diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index 5bd1ba8..44f5aba 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -1,21 +1,43 @@
// SPDX-License-Identifier: GPL-2.0
static struct ins x86__instructions[] = {
+ { .name = "adc", .ops = &mov_ops, },
+ { .name = "adcb", .ops = &mov_ops, },
+ { .name = "adcl", .ops = &mov_ops, },
{ .name = "add", .ops = &mov_ops, },
{ .name = "addl", .ops = &mov_ops, },
{ .name = "addq", .ops = &mov_ops, },
+ { .name = "addsd", .ops = &mov_ops, },
{ .name = "addw", .ops = &mov_ops, },
{ .name = "and", .ops = &mov_ops, },
+ { .name = "andb", .ops = &mov_ops, },
+ { .name = "andl", .ops = &mov_ops, },
+ { .name = "andpd", .ops = &mov_ops, },
+ { .name = "andps", .ops = &mov_ops, },
+ { .name = "andq", .ops = &mov_ops, },
+ { .name = "andw", .ops = &mov_ops, },
+ { .name = "bsr", .ops = &mov_ops, },
+ { .name = "bt", .ops = &mov_ops, },
+ { .name = "btr", .ops = &mov_ops, },
{ .name = "bts", .ops = &mov_ops, },
+ { .name = "btsq", .ops = &mov_ops, },
{ .name = "call", .ops = &call_ops, },
{ .name = "callq", .ops = &call_ops, },
+ { .name = "cmovbe", .ops = &mov_ops, },
+ { .name = "cmove", .ops = &mov_ops, },
+ { .name = "cmovae", .ops = &mov_ops, },
{ .name = "cmp", .ops = &mov_ops, },
{ .name = "cmpb", .ops = &mov_ops, },
{ .name = "cmpl", .ops = &mov_ops, },
{ .name = "cmpq", .ops = &mov_ops, },
{ .name = "cmpw", .ops = &mov_ops, },
{ .name = "cmpxch", .ops = &mov_ops, },
+ { .name = "cmpxchg", .ops = &mov_ops, },
+ { .name = "cs", .ops = &mov_ops, },
{ .name = "dec", .ops = &dec_ops, },
{ .name = "decl", .ops = &dec_ops, },
+ { .name = "divsd", .ops = &mov_ops, },
+ { .name = "divss", .ops = &mov_ops, },
+ { .name = "gs", .ops = &mov_ops, },
{ .name = "imul", .ops = &mov_ops, },
{ .name = "inc", .ops = &dec_ops, },
{ .name = "incl", .ops = &dec_ops, },
@@ -57,25 +79,68 @@ static struct ins x86__instructions[] = {
{ .name = "lea", .ops = &mov_ops, },
{ .name = "lock", .ops = &lock_ops, },
{ .name = "mov", .ops = &mov_ops, },
+ { .name = "movapd", .ops = &mov_ops, },
+ { .name = "movaps", .ops = &mov_ops, },
{ .name = "movb", .ops = &mov_ops, },
{ .name = "movdqa", .ops = &mov_ops, },
+ { .name = "movdqu", .ops = &mov_ops, },
{ .name = "movl", .ops = &mov_ops, },
{ .name = "movq", .ops = &mov_ops, },
+ { .name = "movsd", .ops = &mov_ops, },
{ .name = "movslq", .ops = &mov_ops, },
+ { .name = "movss", .ops = &mov_ops, },
+ { .name = "movupd", .ops = &mov_ops, },
+ { .name = "movups", .ops = &mov_ops, },
+ { .name = "movw", .ops = &mov_ops, },
{ .name = "movzbl", .ops = &mov_ops, },
{ .name = "movzwl", .ops = &mov_ops, },
+ { .name = "mulsd", .ops = &mov_ops, },
+ { .name = "mulss", .ops = &mov_ops, },
{ .name = "nop", .ops = &nop_ops, },
{ .name = "nopl", .ops = &nop_ops, },
{ .name = "nopw", .ops = &nop_ops, },
{ .name = "or", .ops = &mov_ops, },
+ { .name = "orb", .ops = &mov_ops, },
{ .name = "orl", .ops = &mov_ops, },
+ { .name = "orps", .ops = &mov_ops, },
+ { .name = "orq", .ops = &mov_ops, },
+ { .name = "pand", .ops = &mov_ops, },
+ { .name = "paddq", .ops = &mov_ops, },
+ { .name = "pcmpeqb", .ops = &mov_ops, },
+ { .name = "por", .ops = &mov_ops, },
+ { .name = "rclb", .ops = &mov_ops, },
+ { .name = "rcll", .ops = &mov_ops, },
+ { .name = "retq", .ops = &ret_ops, },
+ { .name = "sbb", .ops = &mov_ops, },
+ { .name = "sbbl", .ops = &mov_ops, },
+ { .name = "sete", .ops = &mov_ops, },
+ { .name = "sub", .ops = &mov_ops, },
+ { .name = "subl", .ops = &mov_ops, },
+ { .name = "subq", .ops = &mov_ops, },
+ { .name = "subsd", .ops = &mov_ops, },
+ { .name = "subw", .ops = &mov_ops, },
{ .name = "test", .ops = &mov_ops, },
{ .name = "testb", .ops = &mov_ops, },
{ .name = "testl", .ops = &mov_ops, },
+ { .name = "ucomisd", .ops = &mov_ops, },
+ { .name = "ucomiss", .ops = &mov_ops, },
+ { .name = "vaddsd", .ops = &mov_ops, },
+ { .name = "vandpd", .ops = &mov_ops, },
+ { .name = "vmovdqa", .ops = &mov_ops, },
+ { .name = "vmovq", .ops = &mov_ops, },
+ { .name = "vmovsd", .ops = &mov_ops, },
+ { .name = "vmulsd", .ops = &mov_ops, },
+ { .name = "vorpd", .ops = &mov_ops, },
+ { .name = "vsubsd", .ops = &mov_ops, },
+ { .name = "vucomisd", .ops = &mov_ops, },
{ .name = "xadd", .ops = &mov_ops, },
{ .name = "xbeginl", .ops = &jump_ops, },
{ .name = "xbeginq", .ops = &jump_ops, },
- { .name = "retq", .ops = &ret_ops, },
+ { .name = "xchg", .ops = &mov_ops, },
+ { .name = "xor", .ops = &mov_ops, },
+ { .name = "xorb", .ops = &mov_ops, },
+ { .name = "xorpd", .ops = &mov_ops, },
+ { .name = "xorps", .ops = &mov_ops, },
};
static bool x86__ins_is_fused(struct arch *arch, const char *ins1,
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 5aef183..4dfe426 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -4,379 +4,383 @@
# The format is:
# <number> <abi> <name> <entry point>
#
+# The __x64_sys_*() stubs are created on-the-fly for sys_*() system calls
+#
# The abi is "common", "64" or "x32" for this file.
#
-0 common read sys_read
-1 common write sys_write
-2 common open sys_open
-3 common close sys_close
-4 common stat sys_newstat
-5 common fstat sys_newfstat
-6 common lstat sys_newlstat
-7 common poll sys_poll
-8 common lseek sys_lseek
-9 common mmap sys_mmap
-10 common mprotect sys_mprotect
-11 common munmap sys_munmap
-12 common brk sys_brk
-13 64 rt_sigaction sys_rt_sigaction
-14 common rt_sigprocmask sys_rt_sigprocmask
-15 64 rt_sigreturn sys_rt_sigreturn/ptregs
-16 64 ioctl sys_ioctl
-17 common pread64 sys_pread64
-18 common pwrite64 sys_pwrite64
-19 64 readv sys_readv
-20 64 writev sys_writev
-21 common access sys_access
-22 common pipe sys_pipe
-23 common select sys_select
-24 common sched_yield sys_sched_yield
-25 common mremap sys_mremap
-26 common msync sys_msync
-27 common mincore sys_mincore
-28 common madvise sys_madvise
-29 common shmget sys_shmget
-30 common shmat sys_shmat
-31 common shmctl sys_shmctl
-32 common dup sys_dup
-33 common dup2 sys_dup2
-34 common pause sys_pause
-35 common nanosleep sys_nanosleep
-36 common getitimer sys_getitimer
-37 common alarm sys_alarm
-38 common setitimer sys_setitimer
-39 common getpid sys_getpid
-40 common sendfile sys_sendfile64
-41 common socket sys_socket
-42 common connect sys_connect
-43 common accept sys_accept
-44 common sendto sys_sendto
-45 64 recvfrom sys_recvfrom
-46 64 sendmsg sys_sendmsg
-47 64 recvmsg sys_recvmsg
-48 common shutdown sys_shutdown
-49 common bind sys_bind
-50 common listen sys_listen
-51 common getsockname sys_getsockname
-52 common getpeername sys_getpeername
-53 common socketpair sys_socketpair
-54 64 setsockopt sys_setsockopt
-55 64 getsockopt sys_getsockopt
-56 common clone sys_clone/ptregs
-57 common fork sys_fork/ptregs
-58 common vfork sys_vfork/ptregs
-59 64 execve sys_execve/ptregs
-60 common exit sys_exit
-61 common wait4 sys_wait4
-62 common kill sys_kill
-63 common uname sys_newuname
-64 common semget sys_semget
-65 common semop sys_semop
-66 common semctl sys_semctl
-67 common shmdt sys_shmdt
-68 common msgget sys_msgget
-69 common msgsnd sys_msgsnd
-70 common msgrcv sys_msgrcv
-71 common msgctl sys_msgctl
-72 common fcntl sys_fcntl
-73 common flock sys_flock
-74 common fsync sys_fsync
-75 common fdatasync sys_fdatasync
-76 common truncate sys_truncate
-77 common ftruncate sys_ftruncate
-78 common getdents sys_getdents
-79 common getcwd sys_getcwd
-80 common chdir sys_chdir
-81 common fchdir sys_fchdir
-82 common rename sys_rename
-83 common mkdir sys_mkdir
-84 common rmdir sys_rmdir
-85 common creat sys_creat
-86 common link sys_link
-87 common unlink sys_unlink
-88 common symlink sys_symlink
-89 common readlink sys_readlink
-90 common chmod sys_chmod
-91 common fchmod sys_fchmod
-92 common chown sys_chown
-93 common fchown sys_fchown
-94 common lchown sys_lchown
-95 common umask sys_umask
-96 common gettimeofday sys_gettimeofday
-97 common getrlimit sys_getrlimit
-98 common getrusage sys_getrusage
-99 common sysinfo sys_sysinfo
-100 common times sys_times
-101 64 ptrace sys_ptrace
-102 common getuid sys_getuid
-103 common syslog sys_syslog
-104 common getgid sys_getgid
-105 common setuid sys_setuid
-106 common setgid sys_setgid
-107 common geteuid sys_geteuid
-108 common getegid sys_getegid
-109 common setpgid sys_setpgid
-110 common getppid sys_getppid
-111 common getpgrp sys_getpgrp
-112 common setsid sys_setsid
-113 common setreuid sys_setreuid
-114 common setregid sys_setregid
-115 common getgroups sys_getgroups
-116 common setgroups sys_setgroups
-117 common setresuid sys_setresuid
-118 common getresuid sys_getresuid
-119 common setresgid sys_setresgid
-120 common getresgid sys_getresgid
-121 common getpgid sys_getpgid
-122 common setfsuid sys_setfsuid
-123 common setfsgid sys_setfsgid
-124 common getsid sys_getsid
-125 common capget sys_capget
-126 common capset sys_capset
-127 64 rt_sigpending sys_rt_sigpending
-128 64 rt_sigtimedwait sys_rt_sigtimedwait
-129 64 rt_sigqueueinfo sys_rt_sigqueueinfo
-130 common rt_sigsuspend sys_rt_sigsuspend
-131 64 sigaltstack sys_sigaltstack
-132 common utime sys_utime
-133 common mknod sys_mknod
+0 common read __x64_sys_read
+1 common write __x64_sys_write
+2 common open __x64_sys_open
+3 common close __x64_sys_close
+4 common stat __x64_sys_newstat
+5 common fstat __x64_sys_newfstat
+6 common lstat __x64_sys_newlstat
+7 common poll __x64_sys_poll
+8 common lseek __x64_sys_lseek
+9 common mmap __x64_sys_mmap
+10 common mprotect __x64_sys_mprotect
+11 common munmap __x64_sys_munmap
+12 common brk __x64_sys_brk
+13 64 rt_sigaction __x64_sys_rt_sigaction
+14 common rt_sigprocmask __x64_sys_rt_sigprocmask
+15 64 rt_sigreturn __x64_sys_rt_sigreturn/ptregs
+16 64 ioctl __x64_sys_ioctl
+17 common pread64 __x64_sys_pread64
+18 common pwrite64 __x64_sys_pwrite64
+19 64 readv __x64_sys_readv
+20 64 writev __x64_sys_writev
+21 common access __x64_sys_access
+22 common pipe __x64_sys_pipe
+23 common select __x64_sys_select
+24 common sched_yield __x64_sys_sched_yield
+25 common mremap __x64_sys_mremap
+26 common msync __x64_sys_msync
+27 common mincore __x64_sys_mincore
+28 common madvise __x64_sys_madvise
+29 common shmget __x64_sys_shmget
+30 common shmat __x64_sys_shmat
+31 common shmctl __x64_sys_shmctl
+32 common dup __x64_sys_dup
+33 common dup2 __x64_sys_dup2
+34 common pause __x64_sys_pause
+35 common nanosleep __x64_sys_nanosleep
+36 common getitimer __x64_sys_getitimer
+37 common alarm __x64_sys_alarm
+38 common setitimer __x64_sys_setitimer
+39 common getpid __x64_sys_getpid
+40 common sendfile __x64_sys_sendfile64
+41 common socket __x64_sys_socket
+42 common connect __x64_sys_connect
+43 common accept __x64_sys_accept
+44 common sendto __x64_sys_sendto
+45 64 recvfrom __x64_sys_recvfrom
+46 64 sendmsg __x64_sys_sendmsg
+47 64 recvmsg __x64_sys_recvmsg
+48 common shutdown __x64_sys_shutdown
+49 common bind __x64_sys_bind
+50 common listen __x64_sys_listen
+51 common getsockname __x64_sys_getsockname
+52 common getpeername __x64_sys_getpeername
+53 common socketpair __x64_sys_socketpair
+54 64 setsockopt __x64_sys_setsockopt
+55 64 getsockopt __x64_sys_getsockopt
+56 common clone __x64_sys_clone/ptregs
+57 common fork __x64_sys_fork/ptregs
+58 common vfork __x64_sys_vfork/ptregs
+59 64 execve __x64_sys_execve/ptregs
+60 common exit __x64_sys_exit
+61 common wait4 __x64_sys_wait4
+62 common kill __x64_sys_kill
+63 common uname __x64_sys_newuname
+64 common semget __x64_sys_semget
+65 common semop __x64_sys_semop
+66 common semctl __x64_sys_semctl
+67 common shmdt __x64_sys_shmdt
+68 common msgget __x64_sys_msgget
+69 common msgsnd __x64_sys_msgsnd
+70 common msgrcv __x64_sys_msgrcv
+71 common msgctl __x64_sys_msgctl
+72 common fcntl __x64_sys_fcntl
+73 common flock __x64_sys_flock
+74 common fsync __x64_sys_fsync
+75 common fdatasync __x64_sys_fdatasync
+76 common truncate __x64_sys_truncate
+77 common ftruncate __x64_sys_ftruncate
+78 common getdents __x64_sys_getdents
+79 common getcwd __x64_sys_getcwd
+80 common chdir __x64_sys_chdir
+81 common fchdir __x64_sys_fchdir
+82 common rename __x64_sys_rename
+83 common mkdir __x64_sys_mkdir
+84 common rmdir __x64_sys_rmdir
+85 common creat __x64_sys_creat
+86 common link __x64_sys_link
+87 common unlink __x64_sys_unlink
+88 common symlink __x64_sys_symlink
+89 common readlink __x64_sys_readlink
+90 common chmod __x64_sys_chmod
+91 common fchmod __x64_sys_fchmod
+92 common chown __x64_sys_chown
+93 common fchown __x64_sys_fchown
+94 common lchown __x64_sys_lchown
+95 common umask __x64_sys_umask
+96 common gettimeofday __x64_sys_gettimeofday
+97 common getrlimit __x64_sys_getrlimit
+98 common getrusage __x64_sys_getrusage
+99 common sysinfo __x64_sys_sysinfo
+100 common times __x64_sys_times
+101 64 ptrace __x64_sys_ptrace
+102 common getuid __x64_sys_getuid
+103 common syslog __x64_sys_syslog
+104 common getgid __x64_sys_getgid
+105 common setuid __x64_sys_setuid
+106 common setgid __x64_sys_setgid
+107 common geteuid __x64_sys_geteuid
+108 common getegid __x64_sys_getegid
+109 common setpgid __x64_sys_setpgid
+110 common getppid __x64_sys_getppid
+111 common getpgrp __x64_sys_getpgrp
+112 common setsid __x64_sys_setsid
+113 common setreuid __x64_sys_setreuid
+114 common setregid __x64_sys_setregid
+115 common getgroups __x64_sys_getgroups
+116 common setgroups __x64_sys_setgroups
+117 common setresuid __x64_sys_setresuid
+118 common getresuid __x64_sys_getresuid
+119 common setresgid __x64_sys_setresgid
+120 common getresgid __x64_sys_getresgid
+121 common getpgid __x64_sys_getpgid
+122 common setfsuid __x64_sys_setfsuid
+123 common setfsgid __x64_sys_setfsgid
+124 common getsid __x64_sys_getsid
+125 common capget __x64_sys_capget
+126 common capset __x64_sys_capset
+127 64 rt_sigpending __x64_sys_rt_sigpending
+128 64 rt_sigtimedwait __x64_sys_rt_sigtimedwait
+129 64 rt_sigqueueinfo __x64_sys_rt_sigqueueinfo
+130 common rt_sigsuspend __x64_sys_rt_sigsuspend
+131 64 sigaltstack __x64_sys_sigaltstack
+132 common utime __x64_sys_utime
+133 common mknod __x64_sys_mknod
134 64 uselib
-135 common personality sys_personality
-136 common ustat sys_ustat
-137 common statfs sys_statfs
-138 common fstatfs sys_fstatfs
-139 common sysfs sys_sysfs
-140 common getpriority sys_getpriority
-141 common setpriority sys_setpriority
-142 common sched_setparam sys_sched_setparam
-143 common sched_getparam sys_sched_getparam
-144 common sched_setscheduler sys_sched_setscheduler
-145 common sched_getscheduler sys_sched_getscheduler
-146 common sched_get_priority_max sys_sched_get_priority_max
-147 common sched_get_priority_min sys_sched_get_priority_min
-148 common sched_rr_get_interval sys_sched_rr_get_interval
-149 common mlock sys_mlock
-150 common munlock sys_munlock
-151 common mlockall sys_mlockall
-152 common munlockall sys_munlockall
-153 common vhangup sys_vhangup
-154 common modify_ldt sys_modify_ldt
-155 common pivot_root sys_pivot_root
-156 64 _sysctl sys_sysctl
-157 common prctl sys_prctl
-158 common arch_prctl sys_arch_prctl
-159 common adjtimex sys_adjtimex
-160 common setrlimit sys_setrlimit
-161 common chroot sys_chroot
-162 common sync sys_sync
-163 common acct sys_acct
-164 common settimeofday sys_settimeofday
-165 common mount sys_mount
-166 common umount2 sys_umount
-167 common swapon sys_swapon
-168 common swapoff sys_swapoff
-169 common reboot sys_reboot
-170 common sethostname sys_sethostname
-171 common setdomainname sys_setdomainname
-172 common iopl sys_iopl/ptregs
-173 common ioperm sys_ioperm
+135 common personality __x64_sys_personality
+136 common ustat __x64_sys_ustat
+137 common statfs __x64_sys_statfs
+138 common fstatfs __x64_sys_fstatfs
+139 common sysfs __x64_sys_sysfs
+140 common getpriority __x64_sys_getpriority
+141 common setpriority __x64_sys_setpriority
+142 common sched_setparam __x64_sys_sched_setparam
+143 common sched_getparam __x64_sys_sched_getparam
+144 common sched_setscheduler __x64_sys_sched_setscheduler
+145 common sched_getscheduler __x64_sys_sched_getscheduler
+146 common sched_get_priority_max __x64_sys_sched_get_priority_max
+147 common sched_get_priority_min __x64_sys_sched_get_priority_min
+148 common sched_rr_get_interval __x64_sys_sched_rr_get_interval
+149 common mlock __x64_sys_mlock
+150 common munlock __x64_sys_munlock
+151 common mlockall __x64_sys_mlockall
+152 common munlockall __x64_sys_munlockall
+153 common vhangup __x64_sys_vhangup
+154 common modify_ldt __x64_sys_modify_ldt
+155 common pivot_root __x64_sys_pivot_root
+156 64 _sysctl __x64_sys_sysctl
+157 common prctl __x64_sys_prctl
+158 common arch_prctl __x64_sys_arch_prctl
+159 common adjtimex __x64_sys_adjtimex
+160 common setrlimit __x64_sys_setrlimit
+161 common chroot __x64_sys_chroot
+162 common sync __x64_sys_sync
+163 common acct __x64_sys_acct
+164 common settimeofday __x64_sys_settimeofday
+165 common mount __x64_sys_mount
+166 common umount2 __x64_sys_umount
+167 common swapon __x64_sys_swapon
+168 common swapoff __x64_sys_swapoff
+169 common reboot __x64_sys_reboot
+170 common sethostname __x64_sys_sethostname
+171 common setdomainname __x64_sys_setdomainname
+172 common iopl __x64_sys_iopl/ptregs
+173 common ioperm __x64_sys_ioperm
174 64 create_module
-175 common init_module sys_init_module
-176 common delete_module sys_delete_module
+175 common init_module __x64_sys_init_module
+176 common delete_module __x64_sys_delete_module
177 64 get_kernel_syms
178 64 query_module
-179 common quotactl sys_quotactl
+179 common quotactl __x64_sys_quotactl
180 64 nfsservctl
181 common getpmsg
182 common putpmsg
183 common afs_syscall
184 common tuxcall
185 common security
-186 common gettid sys_gettid
-187 common readahead sys_readahead
-188 common setxattr sys_setxattr
-189 common lsetxattr sys_lsetxattr
-190 common fsetxattr sys_fsetxattr
-191 common getxattr sys_getxattr
-192 common lgetxattr sys_lgetxattr
-193 common fgetxattr sys_fgetxattr
-194 common listxattr sys_listxattr
-195 common llistxattr sys_llistxattr
-196 common flistxattr sys_flistxattr
-197 common removexattr sys_removexattr
-198 common lremovexattr sys_lremovexattr
-199 common fremovexattr sys_fremovexattr
-200 common tkill sys_tkill
-201 common time sys_time
-202 common futex sys_futex
-203 common sched_setaffinity sys_sched_setaffinity
-204 common sched_getaffinity sys_sched_getaffinity
+186 common gettid __x64_sys_gettid
+187 common readahead __x64_sys_readahead
+188 common setxattr __x64_sys_setxattr
+189 common lsetxattr __x64_sys_lsetxattr
+190 common fsetxattr __x64_sys_fsetxattr
+191 common getxattr __x64_sys_getxattr
+192 common lgetxattr __x64_sys_lgetxattr
+193 common fgetxattr __x64_sys_fgetxattr
+194 common listxattr __x64_sys_listxattr
+195 common llistxattr __x64_sys_llistxattr
+196 common flistxattr __x64_sys_flistxattr
+197 common removexattr __x64_sys_removexattr
+198 common lremovexattr __x64_sys_lremovexattr
+199 common fremovexattr __x64_sys_fremovexattr
+200 common tkill __x64_sys_tkill
+201 common time __x64_sys_time
+202 common futex __x64_sys_futex
+203 common sched_setaffinity __x64_sys_sched_setaffinity
+204 common sched_getaffinity __x64_sys_sched_getaffinity
205 64 set_thread_area
-206 64 io_setup sys_io_setup
-207 common io_destroy sys_io_destroy
-208 common io_getevents sys_io_getevents
-209 64 io_submit sys_io_submit
-210 common io_cancel sys_io_cancel
+206 64 io_setup __x64_sys_io_setup
+207 common io_destroy __x64_sys_io_destroy
+208 common io_getevents __x64_sys_io_getevents
+209 64 io_submit __x64_sys_io_submit
+210 common io_cancel __x64_sys_io_cancel
211 64 get_thread_area
-212 common lookup_dcookie sys_lookup_dcookie
-213 common epoll_create sys_epoll_create
+212 common lookup_dcookie __x64_sys_lookup_dcookie
+213 common epoll_create __x64_sys_epoll_create
214 64 epoll_ctl_old
215 64 epoll_wait_old
-216 common remap_file_pages sys_remap_file_pages
-217 common getdents64 sys_getdents64
-218 common set_tid_address sys_set_tid_address
-219 common restart_syscall sys_restart_syscall
-220 common semtimedop sys_semtimedop
-221 common fadvise64 sys_fadvise64
-222 64 timer_create sys_timer_create
-223 common timer_settime sys_timer_settime
-224 common timer_gettime sys_timer_gettime
-225 common timer_getoverrun sys_timer_getoverrun
-226 common timer_delete sys_timer_delete
-227 common clock_settime sys_clock_settime
-228 common clock_gettime sys_clock_gettime
-229 common clock_getres sys_clock_getres
-230 common clock_nanosleep sys_clock_nanosleep
-231 common exit_group sys_exit_group
-232 common epoll_wait sys_epoll_wait
-233 common epoll_ctl sys_epoll_ctl
-234 common tgkill sys_tgkill
-235 common utimes sys_utimes
+216 common remap_file_pages __x64_sys_remap_file_pages
+217 common getdents64 __x64_sys_getdents64
+218 common set_tid_address __x64_sys_set_tid_address
+219 common restart_syscall __x64_sys_restart_syscall
+220 common semtimedop __x64_sys_semtimedop
+221 common fadvise64 __x64_sys_fadvise64
+222 64 timer_create __x64_sys_timer_create
+223 common timer_settime __x64_sys_timer_settime
+224 common timer_gettime __x64_sys_timer_gettime
+225 common timer_getoverrun __x64_sys_timer_getoverrun
+226 common timer_delete __x64_sys_timer_delete
+227 common clock_settime __x64_sys_clock_settime
+228 common clock_gettime __x64_sys_clock_gettime
+229 common clock_getres __x64_sys_clock_getres
+230 common clock_nanosleep __x64_sys_clock_nanosleep
+231 common exit_group __x64_sys_exit_group
+232 common epoll_wait __x64_sys_epoll_wait
+233 common epoll_ctl __x64_sys_epoll_ctl
+234 common tgkill __x64_sys_tgkill
+235 common utimes __x64_sys_utimes
236 64 vserver
-237 common mbind sys_mbind
-238 common set_mempolicy sys_set_mempolicy
-239 common get_mempolicy sys_get_mempolicy
-240 common mq_open sys_mq_open
-241 common mq_unlink sys_mq_unlink
-242 common mq_timedsend sys_mq_timedsend
-243 common mq_timedreceive sys_mq_timedreceive
-244 64 mq_notify sys_mq_notify
-245 common mq_getsetattr sys_mq_getsetattr
-246 64 kexec_load sys_kexec_load
-247 64 waitid sys_waitid
-248 common add_key sys_add_key
-249 common request_key sys_request_key
-250 common keyctl sys_keyctl
-251 common ioprio_set sys_ioprio_set
-252 common ioprio_get sys_ioprio_get
-253 common inotify_init sys_inotify_init
-254 common inotify_add_watch sys_inotify_add_watch
-255 common inotify_rm_watch sys_inotify_rm_watch
-256 common migrate_pages sys_migrate_pages
-257 common openat sys_openat
-258 common mkdirat sys_mkdirat
-259 common mknodat sys_mknodat
-260 common fchownat sys_fchownat
-261 common futimesat sys_futimesat
-262 common newfstatat sys_newfstatat
-263 common unlinkat sys_unlinkat
-264 common renameat sys_renameat
-265 common linkat sys_linkat
-266 common symlinkat sys_symlinkat
-267 common readlinkat sys_readlinkat
-268 common fchmodat sys_fchmodat
-269 common faccessat sys_faccessat
-270 common pselect6 sys_pselect6
-271 common ppoll sys_ppoll
-272 common unshare sys_unshare
-273 64 set_robust_list sys_set_robust_list
-274 64 get_robust_list sys_get_robust_list
-275 common splice sys_splice
-276 common tee sys_tee
-277 common sync_file_range sys_sync_file_range
-278 64 vmsplice sys_vmsplice
-279 64 move_pages sys_move_pages
-280 common utimensat sys_utimensat
-281 common epoll_pwait sys_epoll_pwait
-282 common signalfd sys_signalfd
-283 common timerfd_create sys_timerfd_create
-284 common eventfd sys_eventfd
-285 common fallocate sys_fallocate
-286 common timerfd_settime sys_timerfd_settime
-287 common timerfd_gettime sys_timerfd_gettime
-288 common accept4 sys_accept4
-289 common signalfd4 sys_signalfd4
-290 common eventfd2 sys_eventfd2
-291 common epoll_create1 sys_epoll_create1
-292 common dup3 sys_dup3
-293 common pipe2 sys_pipe2
-294 common inotify_init1 sys_inotify_init1
-295 64 preadv sys_preadv
-296 64 pwritev sys_pwritev
-297 64 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo
-298 common perf_event_open sys_perf_event_open
-299 64 recvmmsg sys_recvmmsg
-300 common fanotify_init sys_fanotify_init
-301 common fanotify_mark sys_fanotify_mark
-302 common prlimit64 sys_prlimit64
-303 common name_to_handle_at sys_name_to_handle_at
-304 common open_by_handle_at sys_open_by_handle_at
-305 common clock_adjtime sys_clock_adjtime
-306 common syncfs sys_syncfs
-307 64 sendmmsg sys_sendmmsg
-308 common setns sys_setns
-309 common getcpu sys_getcpu
-310 64 process_vm_readv sys_process_vm_readv
-311 64 process_vm_writev sys_process_vm_writev
-312 common kcmp sys_kcmp
-313 common finit_module sys_finit_module
-314 common sched_setattr sys_sched_setattr
-315 common sched_getattr sys_sched_getattr
-316 common renameat2 sys_renameat2
-317 common seccomp sys_seccomp
-318 common getrandom sys_getrandom
-319 common memfd_create sys_memfd_create
-320 common kexec_file_load sys_kexec_file_load
-321 common bpf sys_bpf
-322 64 execveat sys_execveat/ptregs
-323 common userfaultfd sys_userfaultfd
-324 common membarrier sys_membarrier
-325 common mlock2 sys_mlock2
-326 common copy_file_range sys_copy_file_range
-327 64 preadv2 sys_preadv2
-328 64 pwritev2 sys_pwritev2
-329 common pkey_mprotect sys_pkey_mprotect
-330 common pkey_alloc sys_pkey_alloc
-331 common pkey_free sys_pkey_free
-332 common statx sys_statx
+237 common mbind __x64_sys_mbind
+238 common set_mempolicy __x64_sys_set_mempolicy
+239 common get_mempolicy __x64_sys_get_mempolicy
+240 common mq_open __x64_sys_mq_open
+241 common mq_unlink __x64_sys_mq_unlink
+242 common mq_timedsend __x64_sys_mq_timedsend
+243 common mq_timedreceive __x64_sys_mq_timedreceive
+244 64 mq_notify __x64_sys_mq_notify
+245 common mq_getsetattr __x64_sys_mq_getsetattr
+246 64 kexec_load __x64_sys_kexec_load
+247 64 waitid __x64_sys_waitid
+248 common add_key __x64_sys_add_key
+249 common request_key __x64_sys_request_key
+250 common keyctl __x64_sys_keyctl
+251 common ioprio_set __x64_sys_ioprio_set
+252 common ioprio_get __x64_sys_ioprio_get
+253 common inotify_init __x64_sys_inotify_init
+254 common inotify_add_watch __x64_sys_inotify_add_watch
+255 common inotify_rm_watch __x64_sys_inotify_rm_watch
+256 common migrate_pages __x64_sys_migrate_pages
+257 common openat __x64_sys_openat
+258 common mkdirat __x64_sys_mkdirat
+259 common mknodat __x64_sys_mknodat
+260 common fchownat __x64_sys_fchownat
+261 common futimesat __x64_sys_futimesat
+262 common newfstatat __x64_sys_newfstatat
+263 common unlinkat __x64_sys_unlinkat
+264 common renameat __x64_sys_renameat
+265 common linkat __x64_sys_linkat
+266 common symlinkat __x64_sys_symlinkat
+267 common readlinkat __x64_sys_readlinkat
+268 common fchmodat __x64_sys_fchmodat
+269 common faccessat __x64_sys_faccessat
+270 common pselect6 __x64_sys_pselect6
+271 common ppoll __x64_sys_ppoll
+272 common unshare __x64_sys_unshare
+273 64 set_robust_list __x64_sys_set_robust_list
+274 64 get_robust_list __x64_sys_get_robust_list
+275 common splice __x64_sys_splice
+276 common tee __x64_sys_tee
+277 common sync_file_range __x64_sys_sync_file_range
+278 64 vmsplice __x64_sys_vmsplice
+279 64 move_pages __x64_sys_move_pages
+280 common utimensat __x64_sys_utimensat
+281 common epoll_pwait __x64_sys_epoll_pwait
+282 common signalfd __x64_sys_signalfd
+283 common timerfd_create __x64_sys_timerfd_create
+284 common eventfd __x64_sys_eventfd
+285 common fallocate __x64_sys_fallocate
+286 common timerfd_settime __x64_sys_timerfd_settime
+287 common timerfd_gettime __x64_sys_timerfd_gettime
+288 common accept4 __x64_sys_accept4
+289 common signalfd4 __x64_sys_signalfd4
+290 common eventfd2 __x64_sys_eventfd2
+291 common epoll_create1 __x64_sys_epoll_create1
+292 common dup3 __x64_sys_dup3
+293 common pipe2 __x64_sys_pipe2
+294 common inotify_init1 __x64_sys_inotify_init1
+295 64 preadv __x64_sys_preadv
+296 64 pwritev __x64_sys_pwritev
+297 64 rt_tgsigqueueinfo __x64_sys_rt_tgsigqueueinfo
+298 common perf_event_open __x64_sys_perf_event_open
+299 64 recvmmsg __x64_sys_recvmmsg
+300 common fanotify_init __x64_sys_fanotify_init
+301 common fanotify_mark __x64_sys_fanotify_mark
+302 common prlimit64 __x64_sys_prlimit64
+303 common name_to_handle_at __x64_sys_name_to_handle_at
+304 common open_by_handle_at __x64_sys_open_by_handle_at
+305 common clock_adjtime __x64_sys_clock_adjtime
+306 common syncfs __x64_sys_syncfs
+307 64 sendmmsg __x64_sys_sendmmsg
+308 common setns __x64_sys_setns
+309 common getcpu __x64_sys_getcpu
+310 64 process_vm_readv __x64_sys_process_vm_readv
+311 64 process_vm_writev __x64_sys_process_vm_writev
+312 common kcmp __x64_sys_kcmp
+313 common finit_module __x64_sys_finit_module
+314 common sched_setattr __x64_sys_sched_setattr
+315 common sched_getattr __x64_sys_sched_getattr
+316 common renameat2 __x64_sys_renameat2
+317 common seccomp __x64_sys_seccomp
+318 common getrandom __x64_sys_getrandom
+319 common memfd_create __x64_sys_memfd_create
+320 common kexec_file_load __x64_sys_kexec_file_load
+321 common bpf __x64_sys_bpf
+322 64 execveat __x64_sys_execveat/ptregs
+323 common userfaultfd __x64_sys_userfaultfd
+324 common membarrier __x64_sys_membarrier
+325 common mlock2 __x64_sys_mlock2
+326 common copy_file_range __x64_sys_copy_file_range
+327 64 preadv2 __x64_sys_preadv2
+328 64 pwritev2 __x64_sys_pwritev2
+329 common pkey_mprotect __x64_sys_pkey_mprotect
+330 common pkey_alloc __x64_sys_pkey_alloc
+331 common pkey_free __x64_sys_pkey_free
+332 common statx __x64_sys_statx
#
# x32-specific system call numbers start at 512 to avoid cache impact
-# for native 64-bit operation.
+# for native 64-bit operation. The __x32_compat_sys stubs are created
+# on-the-fly for compat_sys_*() compatibility system calls if X86_X32
+# is defined.
#
-512 x32 rt_sigaction compat_sys_rt_sigaction
+512 x32 rt_sigaction __x32_compat_sys_rt_sigaction
513 x32 rt_sigreturn sys32_x32_rt_sigreturn
-514 x32 ioctl compat_sys_ioctl
-515 x32 readv compat_sys_readv
-516 x32 writev compat_sys_writev
-517 x32 recvfrom compat_sys_recvfrom
-518 x32 sendmsg compat_sys_sendmsg
-519 x32 recvmsg compat_sys_recvmsg
-520 x32 execve compat_sys_execve/ptregs
-521 x32 ptrace compat_sys_ptrace
-522 x32 rt_sigpending compat_sys_rt_sigpending
-523 x32 rt_sigtimedwait compat_sys_rt_sigtimedwait
-524 x32 rt_sigqueueinfo compat_sys_rt_sigqueueinfo
-525 x32 sigaltstack compat_sys_sigaltstack
-526 x32 timer_create compat_sys_timer_create
-527 x32 mq_notify compat_sys_mq_notify
-528 x32 kexec_load compat_sys_kexec_load
-529 x32 waitid compat_sys_waitid
-530 x32 set_robust_list compat_sys_set_robust_list
-531 x32 get_robust_list compat_sys_get_robust_list
-532 x32 vmsplice compat_sys_vmsplice
-533 x32 move_pages compat_sys_move_pages
-534 x32 preadv compat_sys_preadv64
-535 x32 pwritev compat_sys_pwritev64
-536 x32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo
-537 x32 recvmmsg compat_sys_recvmmsg
-538 x32 sendmmsg compat_sys_sendmmsg
-539 x32 process_vm_readv compat_sys_process_vm_readv
-540 x32 process_vm_writev compat_sys_process_vm_writev
-541 x32 setsockopt compat_sys_setsockopt
-542 x32 getsockopt compat_sys_getsockopt
-543 x32 io_setup compat_sys_io_setup
-544 x32 io_submit compat_sys_io_submit
-545 x32 execveat compat_sys_execveat/ptregs
-546 x32 preadv2 compat_sys_preadv64v2
-547 x32 pwritev2 compat_sys_pwritev64v2
+514 x32 ioctl __x32_compat_sys_ioctl
+515 x32 readv __x32_compat_sys_readv
+516 x32 writev __x32_compat_sys_writev
+517 x32 recvfrom __x32_compat_sys_recvfrom
+518 x32 sendmsg __x32_compat_sys_sendmsg
+519 x32 recvmsg __x32_compat_sys_recvmsg
+520 x32 execve __x32_compat_sys_execve/ptregs
+521 x32 ptrace __x32_compat_sys_ptrace
+522 x32 rt_sigpending __x32_compat_sys_rt_sigpending
+523 x32 rt_sigtimedwait __x32_compat_sys_rt_sigtimedwait
+524 x32 rt_sigqueueinfo __x32_compat_sys_rt_sigqueueinfo
+525 x32 sigaltstack __x32_compat_sys_sigaltstack
+526 x32 timer_create __x32_compat_sys_timer_create
+527 x32 mq_notify __x32_compat_sys_mq_notify
+528 x32 kexec_load __x32_compat_sys_kexec_load
+529 x32 waitid __x32_compat_sys_waitid
+530 x32 set_robust_list __x32_compat_sys_set_robust_list
+531 x32 get_robust_list __x32_compat_sys_get_robust_list
+532 x32 vmsplice __x32_compat_sys_vmsplice
+533 x32 move_pages __x32_compat_sys_move_pages
+534 x32 preadv __x32_compat_sys_preadv64
+535 x32 pwritev __x32_compat_sys_pwritev64
+536 x32 rt_tgsigqueueinfo __x32_compat_sys_rt_tgsigqueueinfo
+537 x32 recvmmsg __x32_compat_sys_recvmmsg
+538 x32 sendmmsg __x32_compat_sys_sendmmsg
+539 x32 process_vm_readv __x32_compat_sys_process_vm_readv
+540 x32 process_vm_writev __x32_compat_sys_process_vm_writev
+541 x32 setsockopt __x32_compat_sys_setsockopt
+542 x32 getsockopt __x32_compat_sys_getsockopt
+543 x32 io_setup __x32_compat_sys_io_setup
+544 x32 io_submit __x32_compat_sys_io_submit
+545 x32 execveat __x32_compat_sys_execveat/ptregs
+546 x32 preadv2 __x32_compat_sys_preadv64v2
+547 x32 pwritev2 __x32_compat_sys_pwritev64v2
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
index 95036c7..7879df3 100644
--- a/tools/perf/arch/x86/tests/dwarf-unwind.c
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -26,7 +26,7 @@ static int sample_ustack(struct perf_sample *sample,
sp = (unsigned long) regs[PERF_REG_X86_SP];
- map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+ map = map_groups__find(thread->mg, (u64)sp);
if (!map) {
pr_debug("failed to get stack map\n");
free(buf);
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index f95e6f4..844b8f3 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -4,6 +4,8 @@
libperf-y += kvm-stat.o
libperf-y += perf_regs.o
libperf-y += group.o
+libperf-y += machine.o
+libperf-y += event.o
libperf-$(CONFIG_DWARF) += dwarf-regs.o
libperf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c
new file mode 100644
index 0000000..675a021
--- /dev/null
+++ b/tools/perf/arch/x86/util/event.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <linux/string.h>
+
+#include "../../util/machine.h"
+#include "../../util/tool.h"
+#include "../../util/map.h"
+#include "../../util/util.h"
+#include "../../util/debug.h"
+
+#if defined(__x86_64__)
+
+int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
+ perf_event__handler_t process,
+ struct machine *machine)
+{
+ int rc = 0;
+ struct map *pos;
+ struct map_groups *kmaps = &machine->kmaps;
+ struct maps *maps = &kmaps->maps;
+ union perf_event *event = zalloc(sizeof(event->mmap) +
+ machine->id_hdr_size);
+
+ if (!event) {
+ pr_debug("Not enough memory synthesizing mmap event "
+ "for extra kernel maps\n");
+ return -1;
+ }
+
+ for (pos = maps__first(maps); pos; pos = map__next(pos)) {
+ struct kmap *kmap;
+ size_t size;
+
+ if (!__map__is_extra_kernel_map(pos))
+ continue;
+
+ kmap = map__kmap(pos);
+
+ size = sizeof(event->mmap) - sizeof(event->mmap.filename) +
+ PERF_ALIGN(strlen(kmap->name) + 1, sizeof(u64)) +
+ machine->id_hdr_size;
+
+ memset(event, 0, size);
+
+ event->mmap.header.type = PERF_RECORD_MMAP;
+
+ /*
+ * kernel uses 0 for user space maps, see kernel/perf_event.c
+ * __perf_event_mmap
+ */
+ if (machine__is_host(machine))
+ event->header.misc = PERF_RECORD_MISC_KERNEL;
+ else
+ event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
+
+ event->mmap.header.size = size;
+
+ event->mmap.start = pos->start;
+ event->mmap.len = pos->end - pos->start;
+ event->mmap.pgoff = pos->pgoff;
+ event->mmap.pid = machine->pid;
+
+ strlcpy(event->mmap.filename, kmap->name, PATH_MAX);
+
+ if (perf_tool__process_synth_event(tool, event, machine,
+ process) != 0) {
+ rc = -1;
+ break;
+ }
+ }
+
+ free(event);
+ return rc;
+}
+
+#endif
diff --git a/tools/perf/arch/x86/util/machine.c b/tools/perf/arch/x86/util/machine.c
new file mode 100644
index 0000000..4520ac5
--- /dev/null
+++ b/tools/perf/arch/x86/util/machine.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <linux/string.h>
+#include <stdlib.h>
+
+#include "../../util/machine.h"
+#include "../../util/map.h"
+#include "../../util/symbol.h"
+#include "../../util/sane_ctype.h"
+
+#include <symbol/kallsyms.h>
+
+#if defined(__x86_64__)
+
+struct extra_kernel_map_info {
+ int cnt;
+ int max_cnt;
+ struct extra_kernel_map *maps;
+ bool get_entry_trampolines;
+ u64 entry_trampoline;
+};
+
+static int add_extra_kernel_map(struct extra_kernel_map_info *mi, u64 start,
+ u64 end, u64 pgoff, const char *name)
+{
+ if (mi->cnt >= mi->max_cnt) {
+ void *buf;
+ size_t sz;
+
+ mi->max_cnt = mi->max_cnt ? mi->max_cnt * 2 : 32;
+ sz = sizeof(struct extra_kernel_map) * mi->max_cnt;
+ buf = realloc(mi->maps, sz);
+ if (!buf)
+ return -1;
+ mi->maps = buf;
+ }
+
+ mi->maps[mi->cnt].start = start;
+ mi->maps[mi->cnt].end = end;
+ mi->maps[mi->cnt].pgoff = pgoff;
+ strlcpy(mi->maps[mi->cnt].name, name, KMAP_NAME_LEN);
+
+ mi->cnt += 1;
+
+ return 0;
+}
+
+static int find_extra_kernel_maps(void *arg, const char *name, char type,
+ u64 start)
+{
+ struct extra_kernel_map_info *mi = arg;
+
+ if (!mi->entry_trampoline && kallsyms2elf_binding(type) == STB_GLOBAL &&
+ !strcmp(name, "_entry_trampoline")) {
+ mi->entry_trampoline = start;
+ return 0;
+ }
+
+ if (is_entry_trampoline(name)) {
+ u64 end = start + page_size;
+
+ return add_extra_kernel_map(mi, start, end, 0, name);
+ }
+
+ return 0;
+}
+
+int machine__create_extra_kernel_maps(struct machine *machine,
+ struct dso *kernel)
+{
+ struct extra_kernel_map_info mi = { .cnt = 0, };
+ char filename[PATH_MAX];
+ int ret;
+ int i;
+
+ machine__get_kallsyms_filename(machine, filename, PATH_MAX);
+
+ if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+ return 0;
+
+ ret = kallsyms__parse(filename, &mi, find_extra_kernel_maps);
+ if (ret)
+ goto out_free;
+
+ if (!mi.entry_trampoline)
+ goto out_free;
+
+ for (i = 0; i < mi.cnt; i++) {
+ struct extra_kernel_map *xm = &mi.maps[i];
+
+ xm->pgoff = mi.entry_trampoline;
+ ret = machine__create_extra_kernel_map(machine, kernel, xm);
+ if (ret)
+ goto out_free;
+ }
+
+ machine->trampolines_mapped = mi.cnt;
+out_free:
+ free(mi.maps);
+ return ret;
+}
+
+#endif
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 944070e..63eb4908 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -175,7 +175,7 @@ static const struct option options[] = {
OPT_UINTEGER('s', "nr_secs" , &p0.nr_secs, "max number of seconds to run (default: 5 secs)"),
OPT_UINTEGER('u', "usleep" , &p0.sleep_usecs, "usecs to sleep per loop iteration"),
- OPT_BOOLEAN('R', "data_reads" , &p0.data_reads, "access the data via writes (can be mixed with -W)"),
+ OPT_BOOLEAN('R', "data_reads" , &p0.data_reads, "access the data via reads (can be mixed with -W)"),
OPT_BOOLEAN('W', "data_writes" , &p0.data_writes, "access the data via writes (can be mixed with -R)"),
OPT_BOOLEAN('B', "data_backwards", &p0.data_backwards, "access the data backwards as well"),
OPT_BOOLEAN('Z', "data_zero_memset", &p0.data_zero_memset,"access the data via glibc bzero only"),
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 51709a9..da57042 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -45,6 +45,7 @@ struct perf_annotate {
bool print_line;
bool skip_missing;
bool has_br_stack;
+ bool group_set;
const char *sym_hist_filter;
const char *cpu_list;
DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -228,7 +229,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
*/
if (al->sym != NULL) {
rb_erase(&al->sym->rb_node,
- &al->map->dso->symbols[al->map->type]);
+ &al->map->dso->symbols);
symbol__delete(al->sym);
dso__reset_find_symbol_cache(al->map->dso);
}
@@ -508,6 +509,9 @@ int cmd_annotate(int argc, const char **argv)
"Don't shorten the displayed pathnames"),
OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing,
"Skip symbols that cannot be annotated"),
+ OPT_BOOLEAN_SET(0, "group", &symbol_conf.event_group,
+ &annotate.group_set,
+ "Show event group information together"),
OPT_STRING('C', "cpu", &annotate.cpu_list, "cpu", "list of cpus to profile"),
OPT_CALLBACK(0, "symfs", NULL, "directory",
"Look for files with symbols relative to this directory",
@@ -570,6 +574,9 @@ int cmd_annotate(int argc, const char **argv)
annotate.has_br_stack = perf_header__has_feat(&annotate.session->header,
HEADER_BRANCH_STACK);
+ if (annotate.group_set)
+ perf_evlist__force_leader(annotate.session->evlist);
+
ret = symbol__annotation_init();
if (ret < 0)
goto out_delete;
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 41db2cb..115110a 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -25,6 +25,7 @@
#include "util/session.h"
#include "util/symbol.h"
#include "util/time-utils.h"
+#include "util/probe-file.h"
static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid)
{
@@ -239,6 +240,34 @@ static int build_id_cache__purge_path(const char *pathname, struct nsinfo *nsi)
return err;
}
+static int build_id_cache__purge_all(void)
+{
+ struct strlist *list;
+ struct str_node *pos;
+ int err = 0;
+ char *buf;
+
+ list = build_id_cache__list_all(false);
+ if (!list) {
+ pr_debug("Failed to get buildids: -%d\n", errno);
+ return -EINVAL;
+ }
+
+ strlist__for_each_entry(pos, list) {
+ buf = build_id_cache__origname(pos->s);
+ err = build_id_cache__remove_s(pos->s);
+ pr_debug("Removing %s (%s): %s\n", buf, pos->s,
+ err ? "FAIL" : "Ok");
+ free(buf);
+ if (err)
+ break;
+ }
+ strlist__delete(list);
+
+ pr_debug("Purged all: %s\n", err ? "FAIL" : "Ok");
+ return err;
+}
+
static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused)
{
char filename[PATH_MAX];
@@ -297,6 +326,26 @@ static int build_id_cache__update_file(const char *filename, struct nsinfo *nsi)
return err;
}
+static int build_id_cache__show_all(void)
+{
+ struct strlist *bidlist;
+ struct str_node *nd;
+ char *buf;
+
+ bidlist = build_id_cache__list_all(true);
+ if (!bidlist) {
+ pr_debug("Failed to get buildids: -%d\n", errno);
+ return -1;
+ }
+ strlist__for_each_entry(nd, bidlist) {
+ buf = build_id_cache__origname(nd->s);
+ fprintf(stdout, "%s %s\n", nd->s, buf);
+ free(buf);
+ }
+ strlist__delete(bidlist);
+ return 0;
+}
+
int cmd_buildid_cache(int argc, const char **argv)
{
struct strlist *list;
@@ -304,6 +353,9 @@ int cmd_buildid_cache(int argc, const char **argv)
int ret = 0;
int ns_id = -1;
bool force = false;
+ bool list_files = false;
+ bool opts_flag = false;
+ bool purge_all = false;
char const *add_name_list_str = NULL,
*remove_name_list_str = NULL,
*purge_name_list_str = NULL,
@@ -327,6 +379,8 @@ int cmd_buildid_cache(int argc, const char **argv)
"file(s) to remove"),
OPT_STRING('p', "purge", &purge_name_list_str, "file list",
"file(s) to remove (remove old caches too)"),
+ OPT_BOOLEAN('P', "purge-all", &purge_all, "purge all cached files"),
+ OPT_BOOLEAN('l', "list", &list_files, "list all cached files"),
OPT_STRING('M', "missing", &missing_filename, "file",
"to find missing build ids in the cache"),
OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
@@ -344,11 +398,20 @@ int cmd_buildid_cache(int argc, const char **argv)
argc = parse_options(argc, argv, buildid_cache_options,
buildid_cache_usage, 0);
- if (argc || (!add_name_list_str && !kcore_filename &&
- !remove_name_list_str && !purge_name_list_str &&
- !missing_filename && !update_name_list_str))
+ opts_flag = add_name_list_str || kcore_filename ||
+ remove_name_list_str || purge_name_list_str ||
+ missing_filename || update_name_list_str ||
+ purge_all;
+
+ if (argc || !(list_files || opts_flag))
usage_with_options(buildid_cache_usage, buildid_cache_options);
+ /* -l is exclusive. It can not be used with other options. */
+ if (list_files && opts_flag) {
+ usage_with_options_msg(buildid_cache_usage,
+ buildid_cache_options, "-l is exclusive.\n");
+ }
+
if (ns_id > 0)
nsi = nsinfo__new(ns_id);
@@ -366,6 +429,11 @@ int cmd_buildid_cache(int argc, const char **argv)
setup_pager();
+ if (list_files) {
+ ret = build_id_cache__show_all();
+ goto out;
+ }
+
if (add_name_list_str) {
list = strlist__new(add_name_list_str, NULL);
if (list) {
@@ -420,6 +488,13 @@ int cmd_buildid_cache(int argc, const char **argv)
}
}
+ if (purge_all) {
+ if (build_id_cache__purge_all()) {
+ pr_warning("Couldn't remove some caches. Error: %s.\n",
+ str_error_r(errno, sbuf, sizeof(sbuf)));
+ }
+ }
+
if (missing_filename)
ret = build_id_cache__fprintf_missing(session, stdout);
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 4aca13f..1c41b4e 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -439,7 +439,7 @@ int cmd_help(int argc, const char **argv)
#ifdef HAVE_LIBELF_SUPPORT
"probe",
#endif
-#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)
+#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)
"trace",
#endif
NULL };
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 40fe919..a3b3463 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -440,9 +440,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
goto repipe;
}
- thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, &al);
-
- if (al.map != NULL) {
+ if (thread__find_map(thread, sample->cpumode, sample->ip, &al)) {
if (!al.map->dso->hit) {
al.map->dso->hit = 1;
if (map__load(al.map) >= 0) {
diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c
index bcfb363..90d1a23 100644
--- a/tools/perf/builtin-kallsyms.c
+++ b/tools/perf/builtin-kallsyms.c
@@ -27,7 +27,7 @@ static int __cmd_kallsyms(int argc, const char **argv)
for (i = 0; i < argc; ++i) {
struct map *map;
- struct symbol *symbol = machine__find_kernel_function_by_name(machine, argv[i], &map);
+ struct symbol *symbol = machine__find_kernel_symbol_by_name(machine, argv[i], &map);
if (symbol == NULL) {
printf("%s: not found\n", argv[i]);
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index ae11e4c..54d3f21 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1004,7 +1004,7 @@ static void __print_slab_result(struct rb_root *root,
if (is_caller) {
addr = data->call_site;
if (!raw_ip)
- sym = machine__find_kernel_function(machine, addr, &map);
+ sym = machine__find_kernel_symbol(machine, addr, &map);
} else
addr = data->ptr;
@@ -1068,7 +1068,7 @@ static void __print_page_alloc_result(struct perf_session *session, int n_lines)
char *caller = buf;
data = rb_entry(next, struct page_stat, node);
- sym = machine__find_kernel_function(machine, data->callsite, &map);
+ sym = machine__find_kernel_symbol(machine, data->callsite, &map);
if (sym)
caller = sym->name;
else
@@ -1110,7 +1110,7 @@ static void __print_page_caller_result(struct perf_session *session, int n_lines
char *caller = buf;
data = rb_entry(next, struct page_stat, node);
- sym = machine__find_kernel_function(machine, data->callsite, &map);
+ sym = machine__find_kernel_symbol(machine, data->callsite, &map);
if (sym)
caller = sym->name;
else
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 5065646..57393e9 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -83,7 +83,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
};
argc = parse_options(argc, argv, options, record_mem_usage,
- PARSE_OPT_STOP_AT_NON_OPTION);
+ PARSE_OPT_KEEP_UNKNOWN);
rec_argc = argc + 9; /* max number of arguments */
rec_argv = calloc(rec_argc + 1, sizeof(char *));
@@ -436,7 +436,7 @@ int cmd_mem(int argc, const char **argv)
}
argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
- mem_usage, PARSE_OPT_STOP_AT_NON_OPTION);
+ mem_usage, PARSE_OPT_KEEP_UNKNOWN);
if (!argc || !(strncmp(argv[0], "rec", 3) || mem.operation))
usage_with_options(mem_usage, mem_options);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 0f198f6..ad978e3 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -194,20 +194,11 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter,
return err;
}
-/*
- * Events in data file are not collect in groups, but we still want
- * the group display. Set the artificial group and set the leader's
- * forced_leader flag to notify the display code.
- */
static void setup_forced_leader(struct report *report,
struct perf_evlist *evlist)
{
- if (report->group_set && !evlist->nr_groups) {
- struct perf_evsel *leader = perf_evlist__first(evlist);
-
- perf_evlist__set_leader(evlist);
- leader->forced_leader = true;
- }
+ if (report->group_set)
+ perf_evlist__force_leader(evlist);
}
static int process_feature_event(struct perf_tool *tool,
@@ -523,12 +514,9 @@ static void report__warn_kptr_restrict(const struct report *rep)
"As no suitable kallsyms nor vmlinux was found, kernel samples\n"
"can't be resolved.";
- if (kernel_map) {
- const struct dso *kdso = kernel_map->dso;
- if (!RB_EMPTY_ROOT(&kdso->symbols[MAP__FUNCTION])) {
- desc = "If some relocation was applied (e.g. "
- "kexec) symbols may be misresolved.";
- }
+ if (kernel_map && map__has_symbols(kernel_map)) {
+ desc = "If some relocation was applied (e.g. "
+ "kexec) symbols may be misresolved.";
}
ui__warning(
@@ -718,10 +706,7 @@ static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp)
static int map_groups__fprintf_task(struct map_groups *mg, int indent, FILE *fp)
{
- int printed = 0, i;
- for (i = 0; i < MAP__NR_TYPES; ++i)
- printed += maps__fprintf_task(&mg->maps[i], indent, fp);
- return printed;
+ return maps__fprintf_task(&mg->maps, indent, fp);
}
static void task__print_level(struct task *task, FILE *fp, int level)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 313c424..cefc881 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -153,8 +153,8 @@ static struct {
.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
- PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
- PERF_OUTPUT_PERIOD,
+ PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+ PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD,
.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
},
@@ -165,8 +165,9 @@ static struct {
.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
- PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
- PERF_OUTPUT_PERIOD | PERF_OUTPUT_BPF_OUTPUT,
+ PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+ PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD |
+ PERF_OUTPUT_BPF_OUTPUT,
.invalid_fields = PERF_OUTPUT_TRACE,
},
@@ -185,10 +186,10 @@ static struct {
.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
- PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
- PERF_OUTPUT_PERIOD | PERF_OUTPUT_ADDR |
- PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT |
- PERF_OUTPUT_PHYS_ADDR,
+ PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+ PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD |
+ PERF_OUTPUT_ADDR | PERF_OUTPUT_DATA_SRC |
+ PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR,
.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
},
@@ -199,8 +200,8 @@ static struct {
.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
- PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
- PERF_OUTPUT_PERIOD,
+ PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+ PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD,
.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
},
@@ -211,8 +212,8 @@ static struct {
.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
- PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
- PERF_OUTPUT_SYNTH,
+ PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+ PERF_OUTPUT_DSO | PERF_OUTPUT_SYNTH,
.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
},
@@ -544,6 +545,7 @@ static int perf_session__check_output_opt(struct perf_session *session)
if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) {
output[j].fields |= PERF_OUTPUT_IP;
output[j].fields |= PERF_OUTPUT_SYM;
+ output[j].fields |= PERF_OUTPUT_SYMOFFSET;
output[j].fields |= PERF_OUTPUT_DSO;
set_print_ip_opts(attr);
goto out;
@@ -657,8 +659,11 @@ static int perf_sample__fprintf_start(struct perf_sample *sample,
break;
case PERF_RECORD_SWITCH:
case PERF_RECORD_SWITCH_CPU_WIDE:
- if (has(SWITCH_OUT))
+ if (has(SWITCH_OUT)) {
ret += fprintf(fp, "S");
+ if (sample->misc & PERF_RECORD_MISC_SWITCH_OUT_PREEMPT)
+ ret += fprintf(fp, "p");
+ }
default:
break;
}
@@ -714,8 +719,8 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample,
if (PRINT_FIELD(DSO)) {
memset(&alf, 0, sizeof(alf));
memset(&alt, 0, sizeof(alt));
- thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf);
- thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
+ thread__find_map(thread, sample->cpumode, from, &alf);
+ thread__find_map(thread, sample->cpumode, to, &alt);
}
printed += fprintf(fp, " 0x%"PRIx64, from);
@@ -761,13 +766,8 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample,
from = br->entries[i].from;
to = br->entries[i].to;
- thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf);
- if (alf.map)
- alf.sym = map__find_symbol(alf.map, alf.addr);
-
- thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
- if (alt.map)
- alt.sym = map__find_symbol(alt.map, alt.addr);
+ thread__find_symbol(thread, sample->cpumode, from, &alf);
+ thread__find_symbol(thread, sample->cpumode, to, &alt);
printed += symbol__fprintf_symname_offs(alf.sym, &alf, fp);
if (PRINT_FIELD(DSO)) {
@@ -811,12 +811,12 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample,
from = br->entries[i].from;
to = br->entries[i].to;
- thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf);
- if (alf.map && !alf.map->dso->adjust_symbols)
+ if (thread__find_map(thread, sample->cpumode, from, &alf) &&
+ !alf.map->dso->adjust_symbols)
from = map__map_ip(alf.map, from);
- thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
- if (alt.map && !alt.map->dso->adjust_symbols)
+ if (thread__find_map(thread, sample->cpumode, to, &alt) &&
+ !alt.map->dso->adjust_symbols)
to = map__map_ip(alt.map, to);
printed += fprintf(fp, " 0x%"PRIx64, from);
@@ -879,8 +879,7 @@ static int grab_bb(u8 *buffer, u64 start, u64 end,
return 0;
}
- thread__find_addr_map(thread, *cpumode, MAP__FUNCTION, start, &al);
- if (!al.map || !al.map->dso) {
+ if (!thread__find_map(thread, *cpumode, start, &al) || !al.map->dso) {
pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
return 0;
}
@@ -930,10 +929,8 @@ static int ip__fprintf_sym(uint64_t addr, struct thread *thread,
memset(&al, 0, sizeof(al));
- thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al);
- if (!al.map)
- thread__find_addr_map(thread, cpumode, MAP__VARIABLE,
- addr, &al);
+ thread__find_map(thread, cpumode, addr, &al);
+
if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end)
return 0;
@@ -2801,11 +2798,11 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
for_each_lang(scripts_path, scripts_dir, lang_dirent) {
scnprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path,
lang_dirent->d_name);
-#ifdef NO_LIBPERL
+#ifndef HAVE_LIBPERL_SUPPORT
if (strstr(lang_path, "perl"))
continue;
#endif
-#ifdef NO_LIBPYTHON
+#ifndef HAVE_LIBPYTHON_SUPPORT
if (strstr(lang_path, "python"))
continue;
#endif
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f5c4548..a4f662a 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -164,6 +164,7 @@ static bool forever = false;
static bool metric_only = false;
static bool force_metric_only = false;
static bool no_merge = false;
+static bool walltime_run_table = false;
static struct timespec ref_time;
static struct cpu_map *aggr_map;
static aggr_get_id_t aggr_get_id;
@@ -172,6 +173,8 @@ static bool interval_count;
static const char *output_name;
static int output_fd;
static int print_free_counters_hint;
+static int print_mixed_hw_group_error;
+static u64 *walltime_run;
struct perf_stat {
bool record;
@@ -568,7 +571,7 @@ static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
return leader;
}
-static int __run_perf_stat(int argc, const char **argv)
+static int __run_perf_stat(int argc, const char **argv, int run_idx)
{
int interval = stat_config.interval;
int times = stat_config.times;
@@ -751,6 +754,9 @@ static int __run_perf_stat(int argc, const char **argv)
t1 = rdclock();
+ if (walltime_run_table)
+ walltime_run[run_idx] = t1 - t0;
+
update_stats(&walltime_nsecs_stats, t1 - t0);
/*
@@ -765,7 +771,7 @@ static int __run_perf_stat(int argc, const char **argv)
return WEXITSTATUS(status);
}
-static int run_perf_stat(int argc, const char **argv)
+static int run_perf_stat(int argc, const char **argv, int run_idx)
{
int ret;
@@ -778,7 +784,7 @@ static int run_perf_stat(int argc, const char **argv)
if (sync_run)
sync();
- ret = __run_perf_stat(argc, argv);
+ ret = __run_perf_stat(argc, argv, run_idx);
if (ret)
return ret;
@@ -1126,6 +1132,30 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
}
+static bool is_mixed_hw_group(struct perf_evsel *counter)
+{
+ struct perf_evlist *evlist = counter->evlist;
+ u32 pmu_type = counter->attr.type;
+ struct perf_evsel *pos;
+
+ if (counter->nr_members < 2)
+ return false;
+
+ evlist__for_each_entry(evlist, pos) {
+ /* software events can be part of any hardware group */
+ if (pos->attr.type == PERF_TYPE_SOFTWARE)
+ continue;
+ if (pmu_type == PERF_TYPE_SOFTWARE) {
+ pmu_type = pos->attr.type;
+ continue;
+ }
+ if (pmu_type != pos->attr.type)
+ return true;
+ }
+
+ return false;
+}
+
static void printout(int id, int nr, struct perf_evsel *counter, double uval,
char *prefix, u64 run, u64 ena, double noise,
struct runtime_stat *st)
@@ -1178,8 +1208,11 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
csv_sep);
- if (counter->supported)
+ if (counter->supported) {
print_free_counters_hint = 1;
+ if (is_mixed_hw_group(counter))
+ print_mixed_hw_group_error = 1;
+ }
fprintf(stat_config.output, "%-*s%s",
csv_output ? 0 : unit_width,
@@ -1256,7 +1289,8 @@ static void uniquify_event_name(struct perf_evsel *counter)
char *new_name;
char *config;
- if (!counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
+ if (counter->uniquified_name ||
+ !counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
strlen(counter->pmu_name)))
return;
@@ -1274,6 +1308,8 @@ static void uniquify_event_name(struct perf_evsel *counter)
counter->name = new_name;
}
}
+
+ counter->uniquified_name = true;
}
static void collect_all_aliases(struct perf_evsel *counter,
@@ -1733,19 +1769,67 @@ static void print_header(int argc, const char **argv)
}
}
+static int get_precision(double num)
+{
+ if (num > 1)
+ return 0;
+
+ return lround(ceil(-log10(num)));
+}
+
+static void print_table(FILE *output, int precision, double avg)
+{
+ char tmp[64];
+ int idx, indent = 0;
+
+ scnprintf(tmp, 64, " %17.*f", precision, avg);
+ while (tmp[indent] == ' ')
+ indent++;
+
+ fprintf(output, "%*s# Table of individual measurements:\n", indent, "");
+
+ for (idx = 0; idx < run_count; idx++) {
+ double run = (double) walltime_run[idx] / NSEC_PER_SEC;
+ int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5);
+
+ fprintf(output, " %17.*f (%+.*f) ",
+ precision, run, precision, run - avg);
+
+ for (h = 0; h < n; h++)
+ fprintf(output, "#");
+
+ fprintf(output, "\n");
+ }
+
+ fprintf(output, "\n%*s# Final result:\n", indent, "");
+}
+
static void print_footer(void)
{
+ double avg = avg_stats(&walltime_nsecs_stats) / NSEC_PER_SEC;
FILE *output = stat_config.output;
int n;
if (!null_run)
fprintf(output, "\n");
- fprintf(output, " %17.9f seconds time elapsed",
- avg_stats(&walltime_nsecs_stats) / NSEC_PER_SEC);
- if (run_count > 1) {
- fprintf(output, " ");
- print_noise_pct(stddev_stats(&walltime_nsecs_stats),
- avg_stats(&walltime_nsecs_stats));
+
+ if (run_count == 1) {
+ fprintf(output, " %17.9f seconds time elapsed", avg);
+ } else {
+ double sd = stddev_stats(&walltime_nsecs_stats) / NSEC_PER_SEC;
+ /*
+ * Display at most 2 more significant
+ * digits than the stddev inaccuracy.
+ */
+ int precision = get_precision(sd) + 2;
+
+ if (walltime_run_table)
+ print_table(output, precision, avg);
+
+ fprintf(output, " %17.*f +- %.*f seconds time elapsed",
+ precision, avg, precision, sd);
+
+ print_noise_pct(sd, avg);
}
fprintf(output, "\n\n");
@@ -1757,6 +1841,11 @@ static void print_footer(void)
" echo 0 > /proc/sys/kernel/nmi_watchdog\n"
" perf stat ...\n"
" echo 1 > /proc/sys/kernel/nmi_watchdog\n");
+
+ if (print_mixed_hw_group_error)
+ fprintf(output,
+ "The events in group usually have to be from "
+ "the same PMU. Try reorganizing the group.\n");
}
static void print_counters(struct timespec *ts, int argc, const char **argv)
@@ -1916,6 +2005,8 @@ static const struct option stat_options[] = {
"be more verbose (show counter open errors, etc)"),
OPT_INTEGER('r', "repeat", &run_count,
"repeat command and print average + stddev (max: 100, forever: 0)"),
+ OPT_BOOLEAN(0, "table", &walltime_run_table,
+ "display details about each run (only with -r option)"),
OPT_BOOLEAN('n', "null", &null_run,
"null run - dont start any counters"),
OPT_INCR('d', "detailed", &detailed_run,
@@ -1943,7 +2034,8 @@ static const struct option stat_options[] = {
OPT_STRING(0, "post", &post_cmd, "command",
"command to run after to the measured command"),
OPT_UINTEGER('I', "interval-print", &stat_config.interval,
- "print counts at regular interval in ms (>= 10)"),
+ "print counts at regular interval in ms "
+ "(overhead is possible for values <= 100ms)"),
OPT_INTEGER(0, "interval-count", &stat_config.times,
"print counts for fixed number of times"),
OPT_UINTEGER(0, "timeout", &stat_config.timeout,
@@ -2806,6 +2898,13 @@ int cmd_stat(int argc, const char **argv)
goto out;
}
+ if (walltime_run_table && run_count <= 1) {
+ fprintf(stderr, "--table is only supported with -r\n");
+ parse_options_usage(stat_usage, stat_options, "r", 1);
+ parse_options_usage(NULL, stat_options, "table", 0);
+ goto out;
+ }
+
if (output_fd < 0) {
fprintf(stderr, "argument to --log-fd must be a > 0\n");
parse_options_usage(stat_usage, stat_options, "log-fd", 0);
@@ -2860,6 +2959,14 @@ int cmd_stat(int argc, const char **argv)
run_count = 1;
}
+ if (walltime_run_table) {
+ walltime_run = zalloc(run_count * sizeof(walltime_run[0]));
+ if (!walltime_run) {
+ pr_err("failed to setup -r option");
+ goto out;
+ }
+ }
+
if ((stat_config.aggr_mode == AGGR_THREAD) &&
!target__has_task(&target)) {
if (!target.system_wide || target.cpu_list) {
@@ -2923,17 +3030,6 @@ int cmd_stat(int argc, const char **argv)
}
}
- if (interval && interval < 100) {
- if (interval < 10) {
- pr_err("print interval must be >= 10ms\n");
- parse_options_usage(stat_usage, stat_options, "I", 1);
- goto out;
- } else
- pr_warning("print interval < 100ms. "
- "The overhead percentage could be high in some cases. "
- "Please proceed with caution.\n");
- }
-
if (stat_config.times && interval)
interval_count = true;
else if (stat_config.times && !interval) {
@@ -2986,7 +3082,7 @@ int cmd_stat(int argc, const char **argv)
fprintf(output, "[ perf stat: executing run #%d ... ]\n",
run_idx + 1);
- status = run_perf_stat(argc, argv);
+ status = run_perf_stat(argc, argv, run_idx);
if (forever && status != -1) {
print_counters(NULL, argc, argv);
perf_stat__reset_stats();
@@ -3034,6 +3130,8 @@ int cmd_stat(int argc, const char **argv)
perf_stat__exit_aggr_mode();
perf_evlist__free_stats(evsel_list);
out:
+ free(walltime_run);
+
if (smi_cost && smi_reset)
sysfs__write_int(FREEZE_ON_SMI_PATH, 0);
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 813698a..a827919 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -533,12 +533,8 @@ static const char *cat_backtrace(union perf_event *event,
}
tal.filtered = 0;
- thread__find_addr_location(al.thread, cpumode,
- MAP__FUNCTION, ip, &tal);
-
- if (tal.sym)
- fprintf(f, "..... %016" PRIx64 " %s\n", ip,
- tal.sym->name);
+ if (thread__find_symbol(al.thread, cpumode, ip, &tal))
+ fprintf(f, "..... %016" PRIx64 " %s\n", ip, tal.sym->name);
else
fprintf(f, "..... %016" PRIx64 "\n", ip);
}
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index f39bd60..7a349fc 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -742,7 +742,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
"Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
"Check /proc/sys/kernel/kptr_restrict.\n\n"
"Kernel%s samples will not be resolved.\n",
- al.map && !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
+ al.map && map__has_symbols(al.map) ?
" modules" : "");
if (use_browser <= 0)
sleep(5);
@@ -750,7 +750,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
machine->kptr_restrict_warned = true;
}
- if (al.sym == NULL) {
+ if (al.sym == NULL && al.map != NULL) {
const char *msg = "Kernel samples will not be resolved.\n";
/*
* As we do lazy loading of symtabs we only will know if the
@@ -764,8 +764,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
* invalid --vmlinux ;-)
*/
if (!machine->kptr_restrict_warned && !top->vmlinux_warned &&
- al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
- RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
+ __map__is_kernel(al.map) && map__has_symbols(al.map)) {
if (symbol_conf.vmlinux_name) {
char serr[256];
dso__strerror_load(al.map->dso, serr, sizeof(serr));
@@ -1265,7 +1264,7 @@ int cmd_top(int argc, const char **argv)
.proc_map_timeout = 500,
.overwrite = 1,
},
- .max_stack = sysctl_perf_event_max_stack,
+ .max_stack = sysctl__max_stack(),
.sym_pcnt_filter = 5,
.nr_threads_synthesize = UINT_MAX,
};
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 3ad17ee..560aed7 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2024,8 +2024,7 @@ static int trace__pgfault(struct trace *trace,
if (trace->summary_only)
goto out;
- thread__find_addr_location(thread, sample->cpumode, MAP__FUNCTION,
- sample->ip, &al);
+ thread__find_symbol(thread, sample->cpumode, sample->ip, &al);
trace__fprintf_entry_head(trace, thread, 0, true, sample->time, trace->output);
@@ -2037,12 +2036,10 @@ static int trace__pgfault(struct trace *trace,
fprintf(trace->output, "] => ");
- thread__find_addr_location(thread, sample->cpumode, MAP__VARIABLE,
- sample->addr, &al);
+ thread__find_symbol(thread, sample->cpumode, sample->addr, &al);
if (!al.map) {
- thread__find_addr_location(thread, sample->cpumode,
- MAP__FUNCTION, sample->addr, &al);
+ thread__find_symbol(thread, sample->cpumode, sample->addr, &al);
if (al.map)
map_type = 'x';
@@ -3165,7 +3162,7 @@ int cmd_trace(int argc, const char **argv)
mmap_pages_user_set = false;
if (trace.max_stack == UINT_MAX) {
- trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl_perf_event_max_stack;
+ trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl__max_stack();
max_stack_user_set = false;
}
diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c
index 2abe391..50df168 100644
--- a/tools/perf/builtin-version.c
+++ b/tools/perf/builtin-version.c
@@ -60,7 +60,10 @@ static void library_status(void)
STATUS(HAVE_DWARF_GETLOCATIONS_SUPPORT, dwarf_getlocations);
STATUS(HAVE_GLIBC_SUPPORT, glibc);
STATUS(HAVE_GTK2_SUPPORT, gtk2);
+#ifndef HAVE_SYSCALL_TABLE_SUPPORT
STATUS(HAVE_LIBAUDIT_SUPPORT, libaudit);
+#endif
+ STATUS(HAVE_SYSCALL_TABLE_SUPPORT, syscall_table);
STATUS(HAVE_LIBBFD_SUPPORT, libbfd);
STATUS(HAVE_LIBELF_SUPPORT, libelf);
STATUS(HAVE_LIBNUMA_SUPPORT, libnuma);
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 9aff89b..10f333e 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -55,23 +55,27 @@
include/uapi/asm-generic/mman-common.h
'
+check_2 () {
+ file1=$1
+ file2=$2
+
+ shift
+ shift
+
+ cmd="diff $* $file1 $file2 > /dev/null"
+
+ test -f $file2 &&
+ eval $cmd || echo "Warning: Kernel ABI header at 'tools/$file' differs from latest version at '$file'" >&2
+}
+
check () {
file=$1
shift
- opts=
- while [ -n "$*" ]; do
- opts="$opts \"$1\""
- shift
- done
- cmd="diff $opts ../$file ../../$file > /dev/null"
-
- test -f ../../$file &&
- eval $cmd || echo "Warning: Kernel ABI header at 'tools/$file' differs from latest version at '$file'" >&2
+ check_2 ../$file ../../$file $*
}
-
# Check if we have the kernel headers (tools/perf/../../include), else
# we're probably on a detached tarball, so no point in trying to check
# differences.
@@ -83,7 +87,7 @@
done
# diff with extra ignore lines
-check arch/x86/lib/memcpy_64.S -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"
-check arch/x86/lib/memset_64.S -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"
-check include/uapi/asm-generic/mman.h -I "^#include <\(uapi/\)*asm-generic/mman-common.h>"
-check include/uapi/linux/mman.h -I "^#include <\(uapi/\)*asm/mman.h>"
+check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
+check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
+check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common.h>"'
+check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"'
diff --git a/tools/perf/examples/bpf/5sec.c b/tools/perf/examples/bpf/5sec.c
new file mode 100644
index 0000000..b9c20321
--- /dev/null
+++ b/tools/perf/examples/bpf/5sec.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ Description:
+
+ . Disable strace like syscall tracing (--no-syscalls), or try tracing
+ just some (-e *sleep).
+
+ . Attach a filter function to a kernel function, returning when it should
+ be considered, i.e. appear on the output.
+
+ . Run it system wide, so that any sleep of >= 5 seconds and < than 6
+ seconds gets caught.
+
+ . Ask for callgraphs using DWARF info, so that userspace can be unwound
+
+ . While this is running, run something like "sleep 5s".
+
+ . If we decide to add tv_nsec as well, then it becomes:
+
+ int probe(hrtimer_nanosleep, rqtp->tv_sec rqtp->tv_nsec)(void *ctx, int err, long sec, long nsec)
+
+ I.e. add where it comes from (rqtp->tv_nsec) and where it will be
+ accessible in the function body (nsec)
+
+ # perf trace --no-syscalls -e tools/perf/examples/bpf/5sec.c/call-graph=dwarf/
+ 0.000 perf_bpf_probe:func:(ffffffff9811b5f0) tv_sec=5
+ hrtimer_nanosleep ([kernel.kallsyms])
+ __x64_sys_nanosleep ([kernel.kallsyms])
+ do_syscall_64 ([kernel.kallsyms])
+ entry_SYSCALL_64 ([kernel.kallsyms])
+ __GI___nanosleep (/usr/lib64/libc-2.26.so)
+ rpl_nanosleep (/usr/bin/sleep)
+ xnanosleep (/usr/bin/sleep)
+ main (/usr/bin/sleep)
+ __libc_start_main (/usr/lib64/libc-2.26.so)
+ _start (/usr/bin/sleep)
+ ^C#
+
+ Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com>
+*/
+
+#include <bpf.h>
+
+int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec)
+{
+ return sec == 5;
+}
+
+license(GPL);
diff --git a/tools/perf/examples/bpf/empty.c b/tools/perf/examples/bpf/empty.c
new file mode 100644
index 0000000..3776d26
--- /dev/null
+++ b/tools/perf/examples/bpf/empty.c
@@ -0,0 +1,3 @@
+#include <bpf.h>
+
+license(GPL);
diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h
new file mode 100644
index 0000000..dd764ad
--- /dev/null
+++ b/tools/perf/include/bpf/bpf.h
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _PERF_BPF_H
+#define _PERF_BPF_H
+#define SEC(NAME) __attribute__((section(NAME), used))
+
+#define probe(function, vars) \
+ SEC(#function "=" #function " " #vars) function
+
+#define license(name) \
+char _license[] SEC("license") = #name; \
+int _version SEC("version") = LINUX_VERSION_CODE;
+
+#endif /* _PERF_BPF_H */
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 1659029..51c8150 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -73,7 +73,7 @@ static struct cmd_struct commands[] = {
{ "lock", cmd_lock, 0 },
{ "kvm", cmd_kvm, 0 },
{ "test", cmd_test, 0 },
-#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)
+#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)
{ "trace", cmd_trace, 0 },
#endif
{ "inject", cmd_inject, 0 },
@@ -238,7 +238,7 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
(*argc)--;
} else if (strstarts(cmd, CMD_DEBUGFS_DIR)) {
tracing_path_set(cmd + strlen(CMD_DEBUGFS_DIR));
- fprintf(stderr, "dir: %s\n", tracing_path);
+ fprintf(stderr, "dir: %s\n", tracing_path_mount());
if (envchanged)
*envchanged = 1;
} else if (!strcmp(cmd, "--list-cmds")) {
@@ -421,22 +421,11 @@ void pthread__unblock_sigwinch(void)
pthread_sigmask(SIG_UNBLOCK, &set, NULL);
}
-#ifdef _SC_LEVEL1_DCACHE_LINESIZE
-#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE)
-#else
-static void cache_line_size(int *cacheline_sizep)
-{
- if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep))
- pr_debug("cannot determine cache line size");
-}
-#endif
-
int main(int argc, const char **argv)
{
int err;
const char *cmd;
char sbuf[STRERR_BUFSIZE];
- int value;
/* libsubcmd init */
exec_cmd_init("perf", PREFIX, PERF_EXEC_PATH, EXEC_PATH_ENVIRONMENT);
@@ -444,13 +433,6 @@ int main(int argc, const char **argv)
/* The page_size is placed in util object. */
page_size = sysconf(_SC_PAGE_SIZE);
- cache_line_size(&cacheline_size);
-
- if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
- sysctl_perf_event_max_stack = value;
-
- if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0)
- sysctl_perf_event_max_contexts_per_stack = value;
cmd = extract_argv0_path(argv[0]);
if (!cmd)
@@ -458,15 +440,11 @@ int main(int argc, const char **argv)
srandom(time(NULL));
- perf_config__init();
err = perf_config(perf_default_config, NULL);
if (err)
return err;
set_buildid_dir(NULL);
- /* get debugfs/tracefs mount point from /proc/mounts */
- tracing_path_mount();
-
/*
* "perf-xxxx" is the same as "perf xxxx", but we obviously:
*
@@ -491,7 +469,7 @@ int main(int argc, const char **argv)
argv[0] = cmd;
}
if (strstarts(cmd, "trace")) {
-#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)
+#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)
setup_path();
argv[0] = "trace";
return cmd_trace(argc, argv);
diff --git a/tools/perf/pmu-events/arch/s390/mapfile.csv b/tools/perf/pmu-events/arch/s390/mapfile.csv
index ca76827..78bcf7f 100644
--- a/tools/perf/pmu-events/arch/s390/mapfile.csv
+++ b/tools/perf/pmu-events/arch/s390/mapfile.csv
@@ -1,6 +1,6 @@
Family-model,Version,Filename,EventType
-209[78],1,cf_z10,core
-281[78],1,cf_z196,core
-282[78],1,cf_zec12,core
-296[45],1,cf_z13,core
-3906,3,cf_z14,core
+^IBM.209[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z10,core
+^IBM.281[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z196,core
+^IBM.282[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_zec12,core
+^IBM.296[45].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z13,core
+^IBM.390[67].*[13]\.[1-5].[[:xdigit:]]+$,3,cf_z14,core
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 93656f2..7e3cce3 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -29,7 +29,6 @@
GenuineIntel-6-4C,v13,silvermont,core
GenuineIntel-6-2A,v15,sandybridge,core
GenuineIntel-6-2C,v2,westmereep-dp,core
-GenuineIntel-6-2C,v2,westmereep-dp,core
GenuineIntel-6-25,v2,westmereep-sp,core
GenuineIntel-6-2F,v2,westmereex,core
GenuineIntel-6-55,v1,skylakex,core
diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling
index f906b79..8a33ca4 100644
--- a/tools/perf/tests/attr/test-record-group-sampling
+++ b/tools/perf/tests/attr/test-record-group-sampling
@@ -35,3 +35,6 @@
# sampling disabled
sample_freq=0
sample_period=0
+freq=0
+write_backward=0
+sample_id_all=0
diff --git a/tools/perf/tests/bpf-script-example.c b/tools/perf/tests/bpf-script-example.c
index e4123c1..1ca5106d 100644
--- a/tools/perf/tests/bpf-script-example.c
+++ b/tools/perf/tests/bpf-script-example.c
@@ -31,7 +31,7 @@ struct bpf_map_def SEC("maps") flip_table = {
.max_entries = 1,
};
-SEC("func=SyS_epoll_pwait")
+SEC("func=do_epoll_wait")
int bpf_func__SyS_epoll_pwait(void *ctx)
{
int ind =0;
diff --git a/tools/perf/tests/bpf-script-test-kbuild.c b/tools/perf/tests/bpf-script-test-kbuild.c
index 3626924..ff3ec833 100644
--- a/tools/perf/tests/bpf-script-test-kbuild.c
+++ b/tools/perf/tests/bpf-script-test-kbuild.c
@@ -9,7 +9,6 @@
#define SEC(NAME) __attribute__((section(NAME), used))
#include <uapi/linux/fs.h>
-#include <uapi/asm/ptrace.h>
SEC("func=vfs_llseek")
int bpf_func__vfs_llseek(void *ctx)
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 625f5a6..2bde505 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -118,6 +118,7 @@ static struct test generic_tests[] = {
{
.desc = "Breakpoint accounting",
.func = test__bp_accounting,
+ .is_supported = test__bp_signal_is_supported,
},
{
.desc = "Number of exit events of a simple workload",
@@ -653,6 +654,15 @@ static int perf_test__list(int argc, const char **argv)
continue;
pr_info("%2d: %s\n", i, t->desc);
+
+ if (t->subtest.get_nr) {
+ int subn = t->subtest.get_nr();
+ int subi;
+
+ for (subi = 0; subi < subn; subi++)
+ pr_info("%2d:%1d: %s\n", i, subi + 1,
+ t->subtest.get_desc(subi));
+ }
}
perf_test__list_shell(argc, argv, i);
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 9993635..afa4ce2 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -236,14 +236,13 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
- thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al);
- if (!al.map || !al.map->dso) {
+ if (!thread__find_map(thread, cpumode, addr, &al) || !al.map->dso) {
if (cpumode == PERF_RECORD_MISC_HYPERVISOR) {
pr_debug("Hypervisor address can not be resolved - skipping\n");
return 0;
}
- pr_debug("thread__find_addr_map failed\n");
+ pr_debug("thread__find_map failed\n");
return -1;
}
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index f7c5b61..b889a28f 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -131,20 +131,20 @@ struct machine *setup_fake_machine(struct machines *machines)
goto out;
/* emulate dso__load() */
- dso__set_loaded(dso, MAP__FUNCTION);
+ dso__set_loaded(dso);
for (k = 0; k < fake_symbols[i].nr_syms; k++) {
struct symbol *sym;
struct fake_sym *fsym = &fake_symbols[i].syms[k];
sym = symbol__new(fsym->start, fsym->length,
- STB_GLOBAL, fsym->name);
+ STB_GLOBAL, STT_FUNC, fsym->name);
if (sym == NULL) {
dso__put(dso);
goto out;
}
- symbols__insert(&dso->symbols[MAP__FUNCTION], sym);
+ symbols__insert(&dso->symbols, sym);
}
dso__put(dso);
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index bb8e6bc..0919b07 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -75,7 +75,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]);
evsels[i] = perf_evsel__newtp("syscalls", name);
if (IS_ERR(evsels[i])) {
- pr_debug("perf_evsel__new\n");
+ pr_debug("perf_evsel__new(%s)\n", name);
goto out_delete_evlist;
}
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 868d82b5..b1af249 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -188,9 +188,8 @@ static int mmap_events(synth_cb synth)
pr_debug("looking for map %p\n", td->map);
- thread__find_addr_map(thread,
- PERF_RECORD_MISC_USER, MAP__FUNCTION,
- (unsigned long) (td->map + 1), &al);
+ thread__find_map(thread, PERF_RECORD_MISC_USER,
+ (unsigned long) (td->map + 1), &al);
thread__put(thread);
@@ -218,7 +217,7 @@ static int mmap_events(synth_cb synth)
* perf_event__synthesize_threads (global)
*
* We test we can find all memory maps via:
- * thread__find_addr_map
+ * thread__find_map
*
* by using all thread objects.
*/
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 18b0644..b9ebe15 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1309,18 +1309,26 @@ static int test__checkevent_config_cache(struct perf_evlist *evlist)
return 0;
}
+static int test__intel_pt(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+ TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "intel_pt//u") == 0);
+ return 0;
+}
+
static int count_tracepoints(void)
{
struct dirent *events_ent;
DIR *events_dir;
int cnt = 0;
- events_dir = opendir(tracing_events_path);
+ events_dir = tracing_events__opendir();
TEST_ASSERT_VAL("Can't open events dir", events_dir);
while ((events_ent = readdir(events_dir))) {
- char sys_path[PATH_MAX];
+ char *sys_path;
struct dirent *sys_ent;
DIR *sys_dir;
@@ -1331,8 +1339,8 @@ static int count_tracepoints(void)
|| !strcmp(events_ent->d_name, "header_page"))
continue;
- scnprintf(sys_path, PATH_MAX, "%s/%s",
- tracing_events_path, events_ent->d_name);
+ sys_path = get_events_file(events_ent->d_name);
+ TEST_ASSERT_VAL("Can't get sys path", sys_path);
sys_dir = opendir(sys_path);
TEST_ASSERT_VAL("Can't open sys dir", sys_dir);
@@ -1348,6 +1356,7 @@ static int count_tracepoints(void)
}
closedir(sys_dir);
+ put_events_file(sys_path);
}
closedir(events_dir);
@@ -1637,6 +1646,11 @@ static struct evlist_test test__events[] = {
.check = test__checkevent_config_cache,
.id = 51,
},
+ {
+ .name = "intel_pt//u",
+ .check = test__intel_pt,
+ .id = 52,
+ },
};
static struct evlist_test test__events_pmu[] = {
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 1ecc1f0..650b208 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -16,20 +16,18 @@
trace_libc_inet_pton_backtrace() {
idx=0
expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)"
- expected[1]=".*inet_pton[[:space:]]\($libc\)$"
+ expected[1]=".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
case "$(uname -m)" in
s390x)
- eventattr='call-graph=dwarf'
- expected[2]="gaih_inet.*[[:space:]]\($libc|inlined\)$"
- expected[3]="__GI_getaddrinfo[[:space:]]\($libc|inlined\)$"
- expected[4]="main[[:space:]]\(.*/bin/ping.*\)$"
- expected[5]="__libc_start_main[[:space:]]\($libc\)$"
- expected[6]="_start[[:space:]]\(.*/bin/ping.*\)$"
+ eventattr='call-graph=dwarf,max-stack=4'
+ expected[2]="gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
+ expected[3]="(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
+ expected[4]="main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
;;
*)
eventattr='max-stack=3'
- expected[2]="getaddrinfo[[:space:]]\($libc\)$"
- expected[3]=".*\(.*/bin/ping.*\)$"
+ expected[2]="getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$"
+ expected[3]=".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
;;
esac
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 17cb1bb..40e30a2 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -70,6 +70,27 @@ static int check_cpu_topology(char *path, struct cpu_map *map)
session = perf_session__new(&data, false, NULL);
TEST_ASSERT_VAL("can't get session", session);
+ /* On platforms with large numbers of CPUs process_cpu_topology()
+ * might issue an error while reading the perf.data file section
+ * HEADER_CPU_TOPOLOGY and the cpu_topology_map pointed to by member
+ * cpu is a NULL pointer.
+ * Example: On s390
+ * CPU 0 is on core_id 0 and physical_package_id 6
+ * CPU 1 is on core_id 1 and physical_package_id 3
+ *
+ * Core_id and physical_package_id are platform and architecture
+ * dependend and might have higher numbers than the CPU id.
+ * This actually depends on the configuration.
+ *
+ * In this case process_cpu_topology() prints error message:
+ * "socket_id number is too big. You may need to upgrade the
+ * perf tool."
+ *
+ * This is the reason why this test might be skipped.
+ */
+ if (!session->header.env.cpu)
+ return TEST_SKIP;
+
for (i = 0; i < session->header.env.nr_cpus_avail; i++) {
if (!cpu_map__has(map, i))
continue;
@@ -95,7 +116,7 @@ int test__session_topology(struct test *test __maybe_unused, int subtest __maybe
{
char path[PATH_MAX];
struct cpu_map *map;
- int ret = -1;
+ int ret = TEST_FAIL;
TEST_ASSERT_VAL("can't get templ file", !get_temp(path));
@@ -110,12 +131,9 @@ int test__session_topology(struct test *test __maybe_unused, int subtest __maybe
goto free_path;
}
- if (check_cpu_topology(path, map))
- goto free_map;
- ret = 0;
-
-free_map:
+ ret = check_cpu_topology(path, map);
cpu_map__put(map);
+
free_path:
unlink(path);
return ret;
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 1e5adb6..7691980 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -19,8 +19,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
struct symbol *sym;
struct map *kallsyms_map, *vmlinux_map, *map;
struct machine kallsyms, vmlinux;
- enum map_type type = MAP__FUNCTION;
- struct maps *maps = &vmlinux.kmaps.maps[type];
+ struct maps *maps = machine__kernel_maps(&vmlinux);
u64 mem_start, mem_end;
bool header_printed;
@@ -56,7 +55,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
* be compacted against the list of modules found in the "vmlinux"
* code and with the one got from /proc/modules from the "kallsyms" code.
*/
- if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type) <= 0) {
+ if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms") <= 0) {
pr_debug("dso__load_kallsyms ");
goto out;
}
@@ -94,7 +93,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
* maps__reloc_vmlinux will notice and set proper ->[un]map_ip routines
* to fixup the symbols.
*/
- if (machine__load_vmlinux_path(&vmlinux, type) <= 0) {
+ if (machine__load_vmlinux_path(&vmlinux) <= 0) {
pr_debug("Couldn't find a vmlinux that matches the kernel running on this machine, skipping test\n");
err = TEST_SKIP;
goto out;
@@ -108,7 +107,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
* in the kallsyms dso. For the ones that are in both, check its names and
* end addresses too.
*/
- for (nd = rb_first(&vmlinux_map->dso->symbols[type]); nd; nd = rb_next(nd)) {
+ map__for_each_symbol(vmlinux_map, sym, nd) {
struct symbol *pair, *first_pair;
sym = rb_entry(nd, struct symbol, rb_node);
@@ -119,8 +118,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
mem_start = vmlinux_map->unmap_ip(vmlinux_map, sym->start);
mem_end = vmlinux_map->unmap_ip(vmlinux_map, sym->end);
- first_pair = machine__find_kernel_symbol(&kallsyms, type,
- mem_start, NULL);
+ first_pair = machine__find_kernel_symbol(&kallsyms, mem_start, NULL);
pair = first_pair;
if (pair && UM(pair->start) == mem_start) {
@@ -149,7 +147,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
*/
continue;
} else {
- pair = machine__find_kernel_symbol_by_name(&kallsyms, type, sym->name, NULL);
+ pair = machine__find_kernel_symbol_by_name(&kallsyms, sym->name, NULL);
if (pair) {
if (UM(pair->start) == mem_start)
goto next_pair;
@@ -183,7 +181,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
* so use the short name, less descriptive but the same ("[kernel]" in
* both cases.
*/
- pair = map_groups__find_by_name(&kallsyms.kmaps, type,
+ pair = map_groups__find_by_name(&kallsyms.kmaps,
(map->dso->kernel ?
map->dso->short_name :
map->dso->name));
@@ -206,7 +204,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
mem_start = vmlinux_map->unmap_ip(vmlinux_map, map->start);
mem_end = vmlinux_map->unmap_ip(vmlinux_map, map->end);
- pair = map_groups__find(&kallsyms.kmaps, type, mem_start);
+ pair = map_groups__find(&kallsyms.kmaps, mem_start);
if (pair == NULL || pair->priv)
continue;
@@ -228,7 +226,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
header_printed = false;
- maps = &kallsyms.kmaps.maps[type];
+ maps = machine__kernel_maps(&kallsyms);
for (map = maps__first(maps); map; map = map__next(map)) {
if (!map->priv) {
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index 417e3ec..9f68077 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -54,6 +54,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
P_MMAP_FLAG(EXECUTABLE);
P_MMAP_FLAG(FILE);
P_MMAP_FLAG(FIXED);
+#ifdef MAP_FIXED_NOREPLACE
+ P_MMAP_FLAG(FIXED_NOREPLACE);
+#endif
P_MMAP_FLAG(GROWSDOWN);
P_MMAP_FLAG(HUGETLB);
P_MMAP_FLAG(LOCKED);
diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh
index 0be4138..f247221 100755
--- a/tools/perf/trace/beauty/prctl_option.sh
+++ b/tools/perf/trace/beauty/prctl_option.sh
@@ -1,6 +1,6 @@
#!/bin/sh
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
printf "static const char *prctl_options[] = {\n"
regex='^#define[[:space:]]+PR_([GS]ET\w+)[[:space:]]*([[:xdigit:]]+).*'
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 12c099a..8be40fa 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -692,8 +692,10 @@ static int annotate_browser__run(struct annotate_browser *browser,
"J Toggle showing number of jump sources on targets\n"
"n Search next string\n"
"o Toggle disassembler output/simplified view\n"
+ "O Bump offset level (jump targets -> +call -> all -> cycle thru)\n"
"s Toggle source code view\n"
"t Circulate percent, total period, samples view\n"
+ "c Show min/max cycle\n"
"/ Search string\n"
"k Toggle line numbers\n"
"P Print to [symbol_name].annotation file.\n"
@@ -719,6 +721,10 @@ static int annotate_browser__run(struct annotate_browser *browser,
notes->options->use_offset = !notes->options->use_offset;
annotation__update_column_widths(notes);
continue;
+ case 'O':
+ if (++notes->options->offset_level > ANNOTATION__MAX_OFFSET_LEVEL)
+ notes->options->offset_level = ANNOTATION__MIN_OFFSET_LEVEL;
+ continue;
case 'j':
notes->options->jump_arrows = !notes->options->jump_arrows;
continue;
@@ -786,6 +792,13 @@ static int annotate_browser__run(struct annotate_browser *browser,
notes->options->show_total_period = true;
annotation__update_column_widths(notes);
continue;
+ case 'c':
+ if (notes->options->show_minmax_cycle)
+ notes->options->show_minmax_cycle = false;
+ else
+ notes->options->show_minmax_cycle = true;
+ annotation__update_column_widths(notes);
+ continue;
case K_LEFT:
case K_ESC:
case 'q':
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 0eec06c1..e5f2472 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -2714,7 +2714,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
"h/?/F1 Show this window\n" \
"UP/DOWN/PGUP\n" \
"PGDN/SPACE Navigate\n" \
- "q/ESC/CTRL+C Exit browser\n\n" \
+ "q/ESC/CTRL+C Exit browser or go back to previous screen\n\n" \
"For multiple event sessions:\n\n" \
"TAB/UNTAB Switch events\n\n" \
"For symbolic views (--sort has sym):\n\n" \
diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c
index e03fa75..5b8b8c6 100644
--- a/tools/perf/ui/browsers/map.c
+++ b/tools/perf/ui/browsers/map.c
@@ -104,7 +104,7 @@ int map__browse(struct map *map)
{
struct map_browser mb = {
.b = {
- .entries = &map->dso->symbols[map->type],
+ .entries = &map->dso->symbols,
.refresh = ui_browser__rb_tree_refresh,
.seek = ui_browser__rb_tree_seek,
.write = map_browser__write,
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 6832fcb..c1eb476 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -819,8 +819,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
}
if (h->ms.map == NULL && verbose > 1) {
- __map_groups__fprintf_maps(h->thread->mg,
- MAP__FUNCTION, fp);
+ map_groups__fprintf(h->thread->mg, fp);
fprintf(fp, "%.10s end\n", graph_dotted_line);
}
}
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 8052373..5d4c45b 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -152,6 +152,8 @@
libperf-$(CONFIG_CXX) += c++/
CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+CFLAGS_llvm-utils.o += -DPERF_INCLUDE_DIR="BUILD_STR($(perf_include_dir_SQ))"
+
# avoid compiler warnings in 32-bit mode
CFLAGS_genelf_debug.o += -Wno-packed
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index fbad8df..7189768 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -46,6 +46,7 @@
struct annotation_options annotation__default_options = {
.use_offset = true,
.jump_arrows = true,
+ .offset_level = ANNOTATION__OFFSET_JUMP_TARGETS,
};
const char *disassembler_style;
@@ -759,6 +760,15 @@ static int __symbol__account_cycles(struct annotation *notes,
ch[offset].num_aggr++;
ch[offset].cycles_aggr += cycles;
+ if (cycles > ch[offset].cycles_max)
+ ch[offset].cycles_max = cycles;
+
+ if (ch[offset].cycles_min) {
+ if (cycles && cycles < ch[offset].cycles_min)
+ ch[offset].cycles_min = cycles;
+ } else
+ ch[offset].cycles_min = cycles;
+
if (!have_start && ch[offset].have_start)
return 0;
if (ch[offset].num) {
@@ -952,8 +962,11 @@ void annotation__compute_ipc(struct annotation *notes, size_t size)
if (ch->have_start)
annotation__count_and_fill(notes, ch->start, offset, ch);
al = notes->offsets[offset];
- if (al && ch->num_aggr)
+ if (al && ch->num_aggr) {
al->cycles = ch->cycles_aggr / ch->num_aggr;
+ al->cycles_max = ch->cycles_max;
+ al->cycles_min = ch->cycles_min;
+ }
notes->have_cycles = true;
}
}
@@ -1262,6 +1275,9 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start
max_percent = sample->percent;
}
+ if (al->samples_nr > nr_percent)
+ nr_percent = al->samples_nr;
+
if (max_percent < min_pcnt)
return -1;
@@ -1949,6 +1965,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
u64 len;
int width = symbol_conf.show_total_period ? 12 : 8;
int graph_dotted_len;
+ char buf[512];
filename = strdup(dso->long_name);
if (!filename)
@@ -1961,8 +1978,11 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
len = symbol__size(sym);
- if (perf_evsel__is_group_event(evsel))
+ if (perf_evsel__is_group_event(evsel)) {
width *= evsel->nr_members;
+ perf_evsel__group_desc(evsel, buf, sizeof(buf));
+ evsel_name = buf;
+ }
graph_dotted_len = printf(" %-*.*s| Source code & Disassembly of %s for %s (%" PRIu64 " samples)\n",
width, width, symbol_conf.show_total_period ? "Period" :
@@ -2482,13 +2502,38 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
else
obj__printf(obj, "%*s ", ANNOTATION__IPC_WIDTH - 1, "IPC");
- if (al->cycles)
- obj__printf(obj, "%*" PRIu64 " ",
+ if (!notes->options->show_minmax_cycle) {
+ if (al->cycles)
+ obj__printf(obj, "%*" PRIu64 " ",
ANNOTATION__CYCLES_WIDTH - 1, al->cycles);
- else if (!show_title)
- obj__printf(obj, "%*s", ANNOTATION__CYCLES_WIDTH, " ");
- else
- obj__printf(obj, "%*s ", ANNOTATION__CYCLES_WIDTH - 1, "Cycle");
+ else if (!show_title)
+ obj__printf(obj, "%*s",
+ ANNOTATION__CYCLES_WIDTH, " ");
+ else
+ obj__printf(obj, "%*s ",
+ ANNOTATION__CYCLES_WIDTH - 1,
+ "Cycle");
+ } else {
+ if (al->cycles) {
+ char str[32];
+
+ scnprintf(str, sizeof(str),
+ "%" PRIu64 "(%" PRIu64 "/%" PRIu64 ")",
+ al->cycles, al->cycles_min,
+ al->cycles_max);
+
+ obj__printf(obj, "%*s ",
+ ANNOTATION__MINMAX_CYCLES_WIDTH - 1,
+ str);
+ } else if (!show_title)
+ obj__printf(obj, "%*s",
+ ANNOTATION__MINMAX_CYCLES_WIDTH,
+ " ");
+ else
+ obj__printf(obj, "%*s ",
+ ANNOTATION__MINMAX_CYCLES_WIDTH - 1,
+ "Cycle(min/max)");
+ }
}
obj__printf(obj, " ");
@@ -2512,7 +2557,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
if (!notes->options->use_offset) {
printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr);
} else {
- if (al->jump_sources) {
+ if (al->jump_sources &&
+ notes->options->offset_level >= ANNOTATION__OFFSET_JUMP_TARGETS) {
if (notes->options->show_nr_jumps) {
int prev;
printed = scnprintf(bf, sizeof(bf), "%*d ",
@@ -2523,9 +2569,14 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
obj__printf(obj, bf);
obj__set_color(obj, prev);
}
-
+print_addr:
printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ",
notes->widths.target, addr);
+ } else if (ins__is_call(&disasm_line(al)->ins) &&
+ notes->options->offset_level >= ANNOTATION__OFFSET_CALL) {
+ goto print_addr;
+ } else if (notes->options->offset_level == ANNOTATION__MAX_OFFSET_LEVEL) {
+ goto print_addr;
} else {
printed = scnprintf(bf, sizeof(bf), "%-*s ",
notes->widths.addr, " ");
@@ -2642,10 +2693,11 @@ int __annotation__scnprintf_samples_period(struct annotation *notes,
*/
static struct annotation_config {
const char *name;
- bool *value;
+ void *value;
} annotation__configs[] = {
ANNOTATION__CFG(hide_src_code),
ANNOTATION__CFG(jump_arrows),
+ ANNOTATION__CFG(offset_level),
ANNOTATION__CFG(show_linenr),
ANNOTATION__CFG(show_nr_jumps),
ANNOTATION__CFG(show_nr_samples),
@@ -2677,8 +2729,16 @@ static int annotation__config(const char *var, const char *value,
if (cfg == NULL)
pr_debug("%s variable unknown, ignoring...", var);
- else
- *cfg->value = perf_config_bool(name, value);
+ else if (strcmp(var, "annotate.offset_level") == 0) {
+ perf_config_int(cfg->value, name, value);
+
+ if (*(int *)cfg->value > ANNOTATION__MAX_OFFSET_LEVEL)
+ *(int *)cfg->value = ANNOTATION__MAX_OFFSET_LEVEL;
+ else if (*(int *)cfg->value < ANNOTATION__MIN_OFFSET_LEVEL)
+ *(int *)cfg->value = ANNOTATION__MIN_OFFSET_LEVEL;
+ } else {
+ *(bool *)cfg->value = perf_config_bool(name, value);
+ }
return 0;
}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index db8d09be..5080b6d 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -61,6 +61,7 @@ bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
#define ANNOTATION__IPC_WIDTH 6
#define ANNOTATION__CYCLES_WIDTH 6
+#define ANNOTATION__MINMAX_CYCLES_WIDTH 19
struct annotation_options {
bool hide_src_code,
@@ -69,9 +70,19 @@ struct annotation_options {
show_linenr,
show_nr_jumps,
show_nr_samples,
- show_total_period;
+ show_total_period,
+ show_minmax_cycle;
+ u8 offset_level;
};
+enum {
+ ANNOTATION__OFFSET_JUMP_TARGETS = 1,
+ ANNOTATION__OFFSET_CALL,
+ ANNOTATION__MAX_OFFSET_LEVEL,
+};
+
+#define ANNOTATION__MIN_OFFSET_LEVEL ANNOTATION__OFFSET_JUMP_TARGETS
+
extern struct annotation_options annotation__default_options;
struct annotation;
@@ -96,6 +107,8 @@ struct annotation_line {
int jump_sources;
float ipc;
u64 cycles;
+ u64 cycles_max;
+ u64 cycles_min;
size_t privsize;
char *path;
u32 idx;
@@ -177,6 +190,8 @@ struct cyc_hist {
u64 start;
u64 cycles;
u64 cycles_aggr;
+ u64 cycles_max;
+ u64 cycles_min;
u32 num;
u32 num_aggr;
u8 have_start;
@@ -230,6 +245,9 @@ struct annotation {
static inline int annotation__cycles_width(struct annotation *notes)
{
+ if (notes->have_cycles && notes->options->show_minmax_cycle)
+ return ANNOTATION__IPC_WIDTH + ANNOTATION__MINMAX_CYCLES_WIDTH;
+
return notes->have_cycles ? ANNOTATION__IPC_WIDTH + ANNOTATION__CYCLES_WIDTH : 0;
}
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 857de69..d056447 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1679,7 +1679,7 @@ struct sym_args {
static bool kern_sym_match(struct sym_args *args, const char *name, char type)
{
/* A function with the same name, and global or the n'th found or any */
- return symbol_type__is_a(type, MAP__FUNCTION) &&
+ return kallsyms__is_function(type) &&
!strcmp(name, args->name) &&
((args->global && isupper(type)) ||
(args->selected && ++(args->cnt) == args->idx) ||
@@ -1784,7 +1784,7 @@ static int find_entire_kern_cb(void *arg, const char *name __maybe_unused,
{
struct sym_args *args = arg;
- if (!symbol_type__is_a(type, MAP__FUNCTION))
+ if (!kallsyms__is_function(type))
return 0;
if (!args->started) {
@@ -1915,7 +1915,7 @@ static void print_duplicate_syms(struct dso *dso, const char *sym_name)
pr_err("Multiple symbols with name '%s'\n", sym_name);
- sym = dso__first_symbol(dso, MAP__FUNCTION);
+ sym = dso__first_symbol(dso);
while (sym) {
if (dso_sym_match(sym, sym_name, &cnt, -1)) {
pr_err("#%d\t0x%"PRIx64"\t%c\t%s\n",
@@ -1945,7 +1945,7 @@ static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start,
*start = 0;
*size = 0;
- sym = dso__first_symbol(dso, MAP__FUNCTION);
+ sym = dso__first_symbol(dso);
while (sym) {
if (*start) {
if (!*size)
@@ -1972,8 +1972,8 @@ static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start,
static int addr_filter__entire_dso(struct addr_filter *filt, struct dso *dso)
{
- struct symbol *first_sym = dso__first_symbol(dso, MAP__FUNCTION);
- struct symbol *last_sym = dso__last_symbol(dso, MAP__FUNCTION);
+ struct symbol *first_sym = dso__first_symbol(dso);
+ struct symbol *last_sym = dso__last_symbol(dso);
if (!first_sym || !last_sym) {
pr_err("Failed to determine filter for %s\nNo symbols found.\n",
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index af7ad81..cee6587 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -66,7 +66,7 @@ bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name)
}
obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, name);
- if (IS_ERR(obj)) {
+ if (IS_ERR_OR_NULL(obj)) {
pr_debug("bpf: failed to load buffer\n");
return ERR_PTR(-EINVAL);
}
@@ -102,14 +102,14 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source)
pr_debug("bpf: successfull builtin compilation\n");
obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, filename);
- if (!IS_ERR(obj) && llvm_param.dump_obj)
+ if (!IS_ERR_OR_NULL(obj) && llvm_param.dump_obj)
llvm__dump_obj(filename, obj_buf, obj_buf_sz);
free(obj_buf);
} else
obj = bpf_object__open(filename);
- if (IS_ERR(obj)) {
+ if (IS_ERR_OR_NULL(obj)) {
pr_debug("bpf: failed to load %s\n", filename);
return obj;
}
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 537eadd..04b1d53 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -47,9 +47,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
return -1;
}
- thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, &al);
-
- if (al.map != NULL)
+ if (thread__find_map(thread, sample->cpumode, sample->ip, &al))
al.map->dso->hit = 1;
thread__put(thread);
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 84eb939..5ac1570 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -707,6 +707,14 @@ struct perf_config_set *perf_config_set__new(void)
return set;
}
+static int perf_config__init(void)
+{
+ if (config_set == NULL)
+ config_set = perf_config_set__new();
+
+ return config_set == NULL;
+}
+
int perf_config(config_fn_t fn, void *data)
{
int ret = 0;
@@ -714,7 +722,7 @@ int perf_config(config_fn_t fn, void *data)
struct perf_config_section *section;
struct perf_config_item *item;
- if (config_set == NULL)
+ if (config_set == NULL && perf_config__init())
return -1;
perf_config_set__for_each_entry(config_set, section, item) {
@@ -735,12 +743,6 @@ int perf_config(config_fn_t fn, void *data)
return ret;
}
-void perf_config__init(void)
-{
- if (config_set == NULL)
- config_set = perf_config_set__new();
-}
-
void perf_config__exit(void)
{
perf_config_set__delete(config_set);
diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h
index baf82bf..bd0a589 100644
--- a/tools/perf/util/config.h
+++ b/tools/perf/util/config.h
@@ -38,7 +38,6 @@ struct perf_config_set *perf_config_set__new(void);
void perf_config_set__delete(struct perf_config_set *set);
int perf_config_set__collect(struct perf_config_set *set, const char *file_name,
const char *var, const char *value);
-void perf_config__init(void);
void perf_config__exit(void);
void perf_config__refresh(void);
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 640af88..4d5fc37 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -1,6 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * SPDX-License-Identifier: GPL-2.0
- *
* Copyright(C) 2015-2018 Linaro Limited.
*
* Author: Tor Jeremiassen <tor@ti.com>
@@ -97,11 +96,19 @@ int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder,
/* Nothing to do, might as well just return */
if (decoder->packet_count == 0)
return 0;
+ /*
+ * The queueing process in function cs_etm_decoder__buffer_packet()
+ * increments the tail *before* using it. This is somewhat counter
+ * intuitive but it has the advantage of centralizing tail management
+ * at a single location. Because of that we need to follow the same
+ * heuristic with the head, i.e we increment it before using its
+ * value. Otherwise the first element of the packet queue is not
+ * used.
+ */
+ decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1);
*packet = decoder->packet_buffer[decoder->head];
- decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1);
-
decoder->packet_count--;
return 1;
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 1b0d422..822ba91 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -1,6 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * SPDX-License-Identifier: GPL-2.0
- *
* Copyright(C) 2015-2018 Linaro Limited.
*
* Author: Tor Jeremiassen <tor@ti.com>
@@ -240,6 +239,7 @@ static void cs_etm__free(struct perf_session *session)
for (i = 0; i < aux->num_cpu; i++)
zfree(&aux->metadata[i]);
+ thread__zput(aux->unknown_thread);
zfree(&aux->metadata);
zfree(&aux);
}
@@ -270,9 +270,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
thread = etmq->etm->unknown_thread;
}
- thread__find_addr_map(thread, cpumode, MAP__FUNCTION, address, &al);
-
- if (!al.map || !al.map->dso)
+ if (!thread__find_map(thread, cpumode, address, &al) || !al.map->dso)
return 0;
if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR &&
@@ -613,8 +611,8 @@ cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq)
return buff->len;
}
-static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
- struct auxtrace_queue *queue)
+static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
+ struct auxtrace_queue *queue)
{
struct cs_etm_queue *etmq = queue->priv;
@@ -1358,6 +1356,23 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
etm->auxtrace.free = cs_etm__free;
session->auxtrace = &etm->auxtrace;
+ etm->unknown_thread = thread__new(999999999, 999999999);
+ if (!etm->unknown_thread)
+ goto err_free_queues;
+
+ /*
+ * Initialize list node so that at thread__zput() we can avoid
+ * segmentation fault at list_del_init().
+ */
+ INIT_LIST_HEAD(&etm->unknown_thread->node);
+
+ err = thread__set_comm(etm->unknown_thread, "unknown", 0);
+ if (err)
+ goto err_delete_thread;
+
+ if (thread__init_map_groups(etm->unknown_thread, etm->machine))
+ goto err_delete_thread;
+
if (dump_trace) {
cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu);
return 0;
@@ -1372,16 +1387,18 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
err = cs_etm__synth_events(etm, session);
if (err)
- goto err_free_queues;
+ goto err_delete_thread;
err = auxtrace_queues__process_index(&etm->queues, session);
if (err)
- goto err_free_queues;
+ goto err_delete_thread;
etm->data_queued = etm->queues.populated;
return 0;
+err_delete_thread:
+ thread__zput(etm->unknown_thread);
err_free_queues:
auxtrace_queues__free(&etm->queues);
session->auxtrace = NULL;
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index 5864d5d..37f8d48 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -1,18 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright(C) 2015 Linaro Limited. All rights reserved.
* Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program. If not, see <http://www.gnu.org/licenses/>.
*/
#ifndef INCLUDE__UTIL_PERF_CS_ETM_H__
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index b0c2b5c..7123746 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -247,9 +247,9 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al,
*dso_db_id = dso->db_id;
if (!al->sym) {
- al->sym = symbol__new(al->addr, 0, 0, "unknown");
+ al->sym = symbol__new(al->addr, 0, 0, 0, "unknown");
if (al->sym)
- dso__insert_symbol(dso, al->map->type, al->sym);
+ dso__insert_symbol(dso, al->sym);
}
if (al->sym) {
@@ -315,8 +315,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe,
al.addr = node->ip;
if (al.map && !al.sym)
- al.sym = dso__find_symbol(al.map->dso, MAP__FUNCTION,
- al.addr);
+ al.sym = dso__find_symbol(al.map->dso, al.addr);
db_ids_from_al(dbe, &al, &dso_db_id, &sym_db_id, &offset);
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 36ef45b..cdfc2e5 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1014,7 +1014,7 @@ struct map *dso__new_map(const char *name)
struct dso *dso = dso__new(name);
if (dso)
- map = map__new2(0, dso, MAP__FUNCTION);
+ map = map__new2(0, dso);
return map;
}
@@ -1176,19 +1176,19 @@ int dso__name_len(const struct dso *dso)
return dso->short_name_len;
}
-bool dso__loaded(const struct dso *dso, enum map_type type)
+bool dso__loaded(const struct dso *dso)
{
- return dso->loaded & (1 << type);
+ return dso->loaded;
}
-bool dso__sorted_by_name(const struct dso *dso, enum map_type type)
+bool dso__sorted_by_name(const struct dso *dso)
{
- return dso->sorted_by_name & (1 << type);
+ return dso->sorted_by_name;
}
-void dso__set_sorted_by_name(struct dso *dso, enum map_type type)
+void dso__set_sorted_by_name(struct dso *dso)
{
- dso->sorted_by_name |= (1 << type);
+ dso->sorted_by_name = true;
}
struct dso *dso__new(const char *name)
@@ -1196,12 +1196,10 @@ struct dso *dso__new(const char *name)
struct dso *dso = calloc(1, sizeof(*dso) + strlen(name) + 1);
if (dso != NULL) {
- int i;
strcpy(dso->name, name);
dso__set_long_name(dso, dso->name, false);
dso__set_short_name(dso, dso->name, false);
- for (i = 0; i < MAP__NR_TYPES; ++i)
- dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
+ dso->symbols = dso->symbol_names = RB_ROOT;
dso->data.cache = RB_ROOT;
dso->inlined_nodes = RB_ROOT;
dso->srclines = RB_ROOT;
@@ -1231,8 +1229,6 @@ struct dso *dso__new(const char *name)
void dso__delete(struct dso *dso)
{
- int i;
-
if (!RB_EMPTY_NODE(&dso->rb_node))
pr_err("DSO %s is still in rbtree when being deleted!\n",
dso->long_name);
@@ -1240,8 +1236,7 @@ void dso__delete(struct dso *dso)
/* free inlines first, as they reference symbols */
inlines__tree_delete(&dso->inlined_nodes);
srcline__tree_delete(&dso->srclines);
- for (i = 0; i < MAP__NR_TYPES; ++i)
- symbols__delete(&dso->symbols[i]);
+ symbols__delete(&dso->symbols);
if (dso->short_name_allocated) {
zfree((char **)&dso->short_name);
@@ -1451,9 +1446,7 @@ size_t __dsos__fprintf(struct list_head *head, FILE *fp)
size_t ret = 0;
list_for_each_entry(pos, head, node) {
- int i;
- for (i = 0; i < MAP__NR_TYPES; ++i)
- ret += dso__fprintf(pos, i, fp);
+ ret += dso__fprintf(pos, fp);
}
return ret;
@@ -1467,18 +1460,17 @@ size_t dso__fprintf_buildid(struct dso *dso, FILE *fp)
return fprintf(fp, "%s", sbuild_id);
}
-size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
+size_t dso__fprintf(struct dso *dso, FILE *fp)
{
struct rb_node *nd;
size_t ret = fprintf(fp, "dso: %s (", dso->short_name);
if (dso->short_name != dso->long_name)
ret += fprintf(fp, "%s, ", dso->long_name);
- ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type],
- dso__loaded(dso, type) ? "" : "NOT ");
+ ret += fprintf(fp, "%sloaded, ", dso__loaded(dso) ? "" : "NOT ");
ret += dso__fprintf_buildid(dso, fp);
ret += fprintf(fp, ")\n");
- for (nd = rb_first(&dso->symbols[type]); nd; nd = rb_next(nd)) {
+ for (nd = rb_first(&dso->symbols); nd; nd = rb_next(nd)) {
struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
ret += symbol__fprintf(pos, fp);
}
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index c229dbe..ef69de2 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -140,14 +140,14 @@ struct dso {
struct list_head node;
struct rb_node rb_node; /* rbtree node sorted by long name */
struct rb_root *root; /* root of rbtree that rb_node is in */
- struct rb_root symbols[MAP__NR_TYPES];
- struct rb_root symbol_names[MAP__NR_TYPES];
+ struct rb_root symbols;
+ struct rb_root symbol_names;
struct rb_root inlined_nodes;
struct rb_root srclines;
struct {
u64 addr;
struct symbol *symbol;
- } last_find_result[MAP__NR_TYPES];
+ } last_find_result;
void *a2l;
char *symsrc_filename;
unsigned int a2l_fails;
@@ -164,8 +164,8 @@ struct dso {
u8 short_name_allocated:1;
u8 long_name_allocated:1;
u8 is_64_bit:1;
- u8 sorted_by_name;
- u8 loaded;
+ bool sorted_by_name;
+ bool loaded;
u8 rel;
u8 build_id[BUILD_ID_SIZE];
u64 text_offset;
@@ -202,14 +202,13 @@ struct dso {
* @dso: the 'struct dso *' in which symbols itereated
* @pos: the 'struct symbol *' to use as a loop cursor
* @n: the 'struct rb_node *' to use as a temporary storage
- * @type: the 'enum map_type' type of symbols
*/
-#define dso__for_each_symbol(dso, pos, n, type) \
- symbols__for_each_entry(&(dso)->symbols[(type)], pos, n)
+#define dso__for_each_symbol(dso, pos, n) \
+ symbols__for_each_entry(&(dso)->symbols, pos, n)
-static inline void dso__set_loaded(struct dso *dso, enum map_type type)
+static inline void dso__set_loaded(struct dso *dso)
{
- dso->loaded |= (1 << type);
+ dso->loaded = true;
}
struct dso *dso__new(const char *name);
@@ -231,11 +230,16 @@ static inline void __dso__zput(struct dso **dso)
#define dso__zput(dso) __dso__zput(&dso)
-bool dso__loaded(const struct dso *dso, enum map_type type);
+bool dso__loaded(const struct dso *dso);
-bool dso__sorted_by_name(const struct dso *dso, enum map_type type);
-void dso__set_sorted_by_name(struct dso *dso, enum map_type type);
-void dso__sort_by_name(struct dso *dso, enum map_type type);
+static inline bool dso__has_symbols(const struct dso *dso)
+{
+ return !RB_EMPTY_ROOT(&dso->symbols);
+}
+
+bool dso__sorted_by_name(const struct dso *dso);
+void dso__set_sorted_by_name(struct dso *dso);
+void dso__sort_by_name(struct dso *dso);
void dso__set_build_id(struct dso *dso, void *build_id);
bool dso__build_id_equal(const struct dso *dso, u8 *build_id);
@@ -349,9 +353,8 @@ size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
size_t __dsos__fprintf(struct list_head *head, FILE *fp);
size_t dso__fprintf_buildid(struct dso *dso, FILE *fp);
-size_t dso__fprintf_symbols_by_name(struct dso *dso,
- enum map_type type, FILE *fp);
-size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp);
+size_t dso__fprintf_symbols_by_name(struct dso *dso, FILE *fp);
+size_t dso__fprintf(struct dso *dso, FILE *fp);
static inline bool dso__is_vmlinux(struct dso *dso)
{
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 4c84276..59f38c7 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -93,6 +93,37 @@ int perf_env__read_cpu_topology_map(struct perf_env *env)
return 0;
}
+static int perf_env__read_arch(struct perf_env *env)
+{
+ struct utsname uts;
+
+ if (env->arch)
+ return 0;
+
+ if (!uname(&uts))
+ env->arch = strdup(uts.machine);
+
+ return env->arch ? 0 : -ENOMEM;
+}
+
+static int perf_env__read_nr_cpus_avail(struct perf_env *env)
+{
+ if (env->nr_cpus_avail == 0)
+ env->nr_cpus_avail = cpu__max_present_cpu();
+
+ return env->nr_cpus_avail ? 0 : -ENOENT;
+}
+
+const char *perf_env__raw_arch(struct perf_env *env)
+{
+ return env && !perf_env__read_arch(env) ? env->arch : "unknown";
+}
+
+int perf_env__nr_cpus_avail(struct perf_env *env)
+{
+ return env && !perf_env__read_nr_cpus_avail(env) ? env->nr_cpus_avail : 0;
+}
+
void cpu_cache_level__free(struct cpu_cache_level *cache)
{
free(cache->type);
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index c4ef2e5..1f3ccc36 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -76,4 +76,7 @@ int perf_env__read_cpu_topology_map(struct perf_env *env);
void cpu_cache_level__free(struct cpu_cache_level *cache);
const char *perf_env__arch(struct perf_env *env);
+const char *perf_env__raw_arch(struct perf_env *env);
+int perf_env__nr_cpus_avail(struct perf_env *env);
+
#endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index f0a6cbd..0c8ecf0 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -88,10 +88,10 @@ static const char *perf_ns__name(unsigned int id)
return perf_ns__names[id];
}
-static int perf_tool__process_synth_event(struct perf_tool *tool,
- union perf_event *event,
- struct machine *machine,
- perf_event__handler_t process)
+int perf_tool__process_synth_event(struct perf_tool *tool,
+ union perf_event *event,
+ struct machine *machine,
+ perf_event__handler_t process)
{
struct perf_sample synth_sample = {
.pid = -1,
@@ -464,8 +464,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
{
int rc = 0;
struct map *pos;
- struct map_groups *kmaps = &machine->kmaps;
- struct maps *maps = &kmaps->maps[MAP__FUNCTION];
+ struct maps *maps = machine__kernel_maps(machine);
union perf_event *event = zalloc((sizeof(event->mmap) +
machine->id_hdr_size));
if (event == NULL) {
@@ -488,7 +487,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
for (pos = maps__first(maps); pos; pos = map__next(pos)) {
size_t size;
- if (__map__is_kernel(pos))
+ if (!__map__is_kmodule(pos))
continue;
size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
@@ -869,7 +868,7 @@ static int find_symbol_cb(void *arg, const char *name, char type,
* Must be a function or at least an alias, as in PARISC64, where "_text" is
* an 'A' to the same address as "_stext".
*/
- if (!(symbol_type__is_a(type, MAP__FUNCTION) ||
+ if (!(kallsyms__is_function(type) ||
type == 'A') || strcmp(name, args->name))
return 0;
@@ -889,9 +888,16 @@ int kallsyms__get_function_start(const char *kallsyms_filename,
return 0;
}
-int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
- perf_event__handler_t process,
- struct machine *machine)
+int __weak perf_event__synthesize_extra_kmaps(struct perf_tool *tool __maybe_unused,
+ perf_event__handler_t process __maybe_unused,
+ struct machine *machine __maybe_unused)
+{
+ return 0;
+}
+
+static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
+ perf_event__handler_t process,
+ struct machine *machine)
{
size_t size;
struct map *map = machine__kernel_map(machine);
@@ -944,6 +950,19 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
return err;
}
+int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
+ perf_event__handler_t process,
+ struct machine *machine)
+{
+ int err;
+
+ err = __perf_event__synthesize_kernel_mmap(tool, process, machine);
+ if (err < 0)
+ return err;
+
+ return perf_event__synthesize_extra_kmaps(tool, process, machine);
+}
+
int perf_event__synthesize_thread_map2(struct perf_tool *tool,
struct thread_map *threads,
perf_event__handler_t process,
@@ -1421,7 +1440,9 @@ size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp)
{
bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
- const char *in_out = out ? "OUT" : "IN ";
+ const char *in_out = !out ? "IN " :
+ !(event->header.misc & PERF_RECORD_MISC_SWITCH_OUT_PREEMPT) ?
+ "OUT " : "OUT preempt";
if (event->header.type == PERF_RECORD_SWITCH)
return fprintf(fp, " %s\n", in_out);
@@ -1487,9 +1508,8 @@ int perf_event__process(struct perf_tool *tool __maybe_unused,
return machine__process_event(machine, event, sample);
}
-void thread__find_addr_map(struct thread *thread, u8 cpumode,
- enum map_type type, u64 addr,
- struct addr_location *al)
+struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
+ struct addr_location *al)
{
struct map_groups *mg = thread->mg;
struct machine *machine = mg->machine;
@@ -1503,7 +1523,7 @@ void thread__find_addr_map(struct thread *thread, u8 cpumode,
if (machine == NULL) {
al->map = NULL;
- return;
+ return NULL;
}
if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
@@ -1531,10 +1551,10 @@ void thread__find_addr_map(struct thread *thread, u8 cpumode,
!perf_host)
al->filtered |= (1 << HIST_FILTER__HOST);
- return;
+ return NULL;
}
try_again:
- al->map = map_groups__find(mg, type, al->addr);
+ al->map = map_groups__find(mg, al->addr);
if (al->map == NULL) {
/*
* If this is outside of all known maps, and is a negative
@@ -1561,17 +1581,17 @@ void thread__find_addr_map(struct thread *thread, u8 cpumode,
map__load(al->map);
al->addr = al->map->map_ip(al->map, al->addr);
}
+
+ return al->map;
}
-void thread__find_addr_location(struct thread *thread,
- u8 cpumode, enum map_type type, u64 addr,
- struct addr_location *al)
+struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode,
+ u64 addr, struct addr_location *al)
{
- thread__find_addr_map(thread, cpumode, type, addr, al);
- if (al->map != NULL)
+ al->sym = NULL;
+ if (thread__find_map(thread, cpumode, addr, al))
al->sym = map__find_symbol(al->map, al->addr);
- else
- al->sym = NULL;
+ return al->sym;
}
/*
@@ -1588,7 +1608,7 @@ int machine__resolve(struct machine *machine, struct addr_location *al,
return -1;
dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
- thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, al);
+ thread__find_map(thread, sample->cpumode, sample->ip, al);
dump_printf(" ...... dso: %s\n",
al->map ? al->map->dso->long_name :
al->level == 'H' ? "[hypervisor]" : "<not found>");
@@ -1667,10 +1687,7 @@ bool sample_addr_correlates_sym(struct perf_event_attr *attr)
void thread__resolve(struct thread *thread, struct addr_location *al,
struct perf_sample *sample)
{
- thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->addr, al);
- if (!al->map)
- thread__find_addr_map(thread, sample->cpumode, MAP__VARIABLE,
- sample->addr, al);
+ thread__find_map(thread, sample->cpumode, sample->addr, al);
al->cpu = sample->cpu;
al->sym = NULL;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 0f79474..bfa60bc 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -750,6 +750,10 @@ int perf_event__process_exit(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
+int perf_tool__process_synth_event(struct perf_tool *tool,
+ union perf_event *event,
+ struct machine *machine,
+ perf_event__handler_t process);
int perf_event__process(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
@@ -796,6 +800,10 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
bool mmap_data,
unsigned int proc_map_timeout);
+int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
+ perf_event__handler_t process,
+ struct machine *machine);
+
size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a59281d..e7a4b31 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1795,3 +1795,18 @@ bool perf_evlist__exclude_kernel(struct perf_evlist *evlist)
return true;
}
+
+/*
+ * Events in data file are not collect in groups, but we still want
+ * the group display. Set the artificial group and set the leader's
+ * forced_leader flag to notify the display code.
+ */
+void perf_evlist__force_leader(struct perf_evlist *evlist)
+{
+ if (!evlist->nr_groups) {
+ struct perf_evsel *leader = perf_evlist__first(evlist);
+
+ perf_evlist__set_leader(evlist);
+ leader->forced_leader = true;
+ }
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 6c41b2f..dc66436 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -309,4 +309,7 @@ struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
union perf_event *event);
bool perf_evlist__exclude_kernel(struct perf_evlist *evlist);
+
+void perf_evlist__force_leader(struct perf_evlist *evlist);
+
#endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1ac8d92..150db5ed 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -930,8 +930,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
* than leader in case leader 'leads' the sampling.
*/
if ((leader != evsel) && leader->sample_read) {
- attr->sample_freq = 0;
- attr->sample_period = 0;
+ attr->freq = 0;
+ attr->sample_freq = 0;
+ attr->sample_period = 0;
+ attr->write_backward = 0;
+ attr->sample_id_all = 0;
}
if (opts->no_samples)
@@ -1922,7 +1925,8 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
goto fallback_missing_features;
} else if (!perf_missing_features.group_read &&
evsel->attr.inherit &&
- (evsel->attr.read_format & PERF_FORMAT_GROUP)) {
+ (evsel->attr.read_format & PERF_FORMAT_GROUP) &&
+ perf_evsel__is_group_leader(evsel)) {
perf_missing_features.group_read = true;
pr_debug2("switching off group read\n");
goto fallback_missing_features;
@@ -2754,8 +2758,14 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
(paranoid = perf_event_paranoid()) > 1) {
const char *name = perf_evsel__name(evsel);
char *new_name;
+ const char *sep = ":";
- if (asprintf(&new_name, "%s%su", name, strchr(name, ':') ? "" : ":") < 0)
+ /* Is there already the separator in the name. */
+ if (strchr(name, '/') ||
+ strchr(name, ':'))
+ sep = "";
+
+ if (asprintf(&new_name, "%s%su", name, sep) < 0)
return false;
if (evsel->name)
@@ -2852,7 +2862,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
return scnprintf(msg, size,
"Not enough memory to setup event with callchain.\n"
"Hint: Try tweaking /proc/sys/kernel/perf_event_max_stack\n"
- "Hint: Current value: %d", sysctl_perf_event_max_stack);
+ "Hint: Current value: %d", sysctl__max_stack());
break;
case ENODEV:
if (target->cpu_list)
@@ -2870,8 +2880,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
#if defined(__i386__) || defined(__x86_64__)
if (evsel->attr.type == PERF_TYPE_HARDWARE)
return scnprintf(msg, size, "%s",
- "No hardware sampling interrupt available.\n"
- "No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.");
+ "No hardware sampling interrupt available.\n");
#endif
break;
case EBUSY:
@@ -2894,8 +2903,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
return scnprintf(msg, size,
"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
- "/bin/dmesg may provide additional information.\n"
- "No CONFIG_PERF_EVENTS=y kernel support configured?",
+ "/bin/dmesg | grep -i perf may provide additional information.\n",
err, str_error_r(err, sbuf, sizeof(sbuf)),
perf_evsel__name(evsel));
}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d3ee3af..b13f5f2 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -115,6 +115,7 @@ struct perf_evsel {
unsigned int sample_size;
int id_pos;
int is_pos;
+ bool uniquified_name;
bool snapshot;
bool supported;
bool needs_swap;
@@ -126,6 +127,7 @@ struct perf_evsel {
bool precise_max;
bool ignore_missing_thread;
bool forced_leader;
+ bool use_uncore_alias;
/* parse modifier helper */
int exclude_GH;
int nr_members;
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
index c540d47..aafbe54 100644
--- a/tools/perf/util/genelf.c
+++ b/tools/perf/util/genelf.c
@@ -114,7 +114,7 @@ gen_build_id(struct buildid_note *note,
fd = open("/dev/urandom", O_RDONLY);
if (fd == -1)
- err(1, "cannot access /dev/urandom for builid");
+ err(1, "cannot access /dev/urandom for buildid");
sret = read(fd, note->build_id, sz);
diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh
index ff17920..c3cef36 100755
--- a/tools/perf/util/generate-cmdlist.sh
+++ b/tools/perf/util/generate-cmdlist.sh
@@ -38,7 +38,7 @@
done
echo "#endif /* HAVE_LIBELF_SUPPORT */"
-echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)"
+echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)"
sed -n -e 's/^perf-\([^ ]*\)[ ].* audit*/\1/p' command-list.txt |
sort |
while read cmd
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 121df16..a8bff21 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1320,7 +1320,8 @@ static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp)
dir = opendir(path);
if (!dir) {
- pr_warning("failed: can't open node sysfs data\n");
+ pr_debug2("%s: could't read %s, does this arch have topology information?\n",
+ __func__, path);
return -1;
}
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 72db274..7f0c83b 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -335,8 +335,7 @@ static int intel_bts_get_next_insn(struct intel_bts_queue *btsq, u64 ip)
if (!thread)
return -1;
- thread__find_addr_map(thread, cpumode, MAP__FUNCTION, ip, &al);
- if (!al.map || !al.map->dso)
+ if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso)
goto out_put;
len = dso__data_read_addr(al.map->dso, al.map, machine, ip, buf,
diff --git a/tools/perf/util/intel-pt-decoder/insn.h b/tools/perf/util/intel-pt-decoder/insn.h
index e23578c..2669c9f 100644
--- a/tools/perf/util/intel-pt-decoder/insn.h
+++ b/tools/perf/util/intel-pt-decoder/insn.h
@@ -208,4 +208,22 @@ static inline int insn_offset_immediate(struct insn *insn)
return insn_offset_displacement(insn) + insn->displacement.nbytes;
}
+#define POP_SS_OPCODE 0x1f
+#define MOV_SREG_OPCODE 0x8e
+
+/*
+ * Intel SDM Vol.3A 6.8.3 states;
+ * "Any single-step trap that would be delivered following the MOV to SS
+ * instruction or POP to SS instruction (because EFLAGS.TF is 1) is
+ * suppressed."
+ * This function returns true if @insn is MOV SS or POP SS. On these
+ * instructions, single stepping is suppressed.
+ */
+static inline int insn_masking_exception(struct insn *insn)
+{
+ return insn->opcode.bytes[0] == POP_SS_OPCODE ||
+ (insn->opcode.bytes[0] == MOV_SREG_OPCODE &&
+ X86_MODRM_REG(insn->modrm.bytes[0]) == 2);
+}
+
#endif /* _ASM_X86_INSN_H */
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 0effaff..492986a 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -442,8 +442,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
}
while (1) {
- thread__find_addr_map(thread, cpumode, MAP__FUNCTION, *ip, &al);
- if (!al.map || !al.map->dso)
+ if (!thread__find_map(thread, cpumode, *ip, &al) || !al.map->dso)
return -EINVAL;
if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR &&
@@ -596,8 +595,7 @@ static int __intel_pt_pgd_ip(uint64_t ip, void *data)
if (!thread)
return -EINVAL;
- thread__find_addr_map(thread, cpumode, MAP__FUNCTION, ip, &al);
- if (!al.map || !al.map->dso)
+ if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso)
return -EINVAL;
offset = al.map->map_ip(al.map, ip);
@@ -1565,7 +1563,7 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip)
if (map__load(map))
return 0;
- start = dso__first_symbol(map->dso, MAP__FUNCTION);
+ start = dso__first_symbol(map->dso);
for (sym = start; sym; sym = dso__next_symbol(sym)) {
if (sym->binding == STB_GLOBAL &&
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 1cca0a2..976e658 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -14,11 +14,12 @@
#include "config.h"
#include "util.h"
#include <sys/wait.h>
+#include <subcmd/exec-cmd.h>
#define CLANG_BPF_CMD_DEFAULT_TEMPLATE \
"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE " \
- "$CLANG_OPTIONS $KERNEL_INC_OPTIONS " \
+ "$CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS " \
"-Wno-unused-value -Wno-pointer-sign " \
"-working-directory $WORKING_DIR " \
"-c \"$CLANG_SOURCE\" -target bpf -O2 -o -"
@@ -212,7 +213,7 @@ version_notice(void)
" \t\thttp://llvm.org/apt\n\n"
" \tIf you are using old version of clang, change 'clang-bpf-cmd-template'\n"
" \toption in [llvm] section of ~/.perfconfig to:\n\n"
-" \t \"$CLANG_EXEC $CLANG_OPTIONS $KERNEL_INC_OPTIONS \\\n"
+" \t \"$CLANG_EXEC $CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS \\\n"
" \t -working-directory $WORKING_DIR -c $CLANG_SOURCE \\\n"
" \t -emit-llvm -o - | /path/to/llc -march=bpf -filetype=obj -o -\"\n"
" \t(Replace /path/to/llc with path to your llc)\n\n"
@@ -431,9 +432,11 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
const char *clang_opt = llvm_param.clang_opt;
char clang_path[PATH_MAX], abspath[PATH_MAX], nr_cpus_avail_str[64];
char serr[STRERR_BUFSIZE];
- char *kbuild_dir = NULL, *kbuild_include_opts = NULL;
+ char *kbuild_dir = NULL, *kbuild_include_opts = NULL,
+ *perf_bpf_include_opts = NULL;
const char *template = llvm_param.clang_bpf_cmd_template;
- char *command_echo, *command_out;
+ char *command_echo = NULL, *command_out;
+ char *perf_include_dir = system_path(PERF_INCLUDE_DIR);
if (path[0] != '-' && realpath(path, abspath) == NULL) {
err = errno;
@@ -471,12 +474,14 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
snprintf(linux_version_code_str, sizeof(linux_version_code_str),
"0x%x", kernel_version);
-
+ if (asprintf(&perf_bpf_include_opts, "-I%s/bpf", perf_include_dir) < 0)
+ goto errout;
force_set_env("NR_CPUS", nr_cpus_avail_str);
force_set_env("LINUX_VERSION_CODE", linux_version_code_str);
force_set_env("CLANG_EXEC", clang_path);
force_set_env("CLANG_OPTIONS", clang_opt);
force_set_env("KERNEL_INC_OPTIONS", kbuild_include_opts);
+ force_set_env("PERF_BPF_INC_OPTIONS", perf_bpf_include_opts);
force_set_env("WORKING_DIR", kbuild_dir ? : ".");
/*
@@ -512,6 +517,8 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
free(command_out);
free(kbuild_dir);
free(kbuild_include_opts);
+ free(perf_bpf_include_opts);
+ free(perf_include_dir);
if (!p_obj_buf)
free(obj_buf);
@@ -526,6 +533,8 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
free(kbuild_dir);
free(kbuild_include_opts);
free(obj_buf);
+ free(perf_bpf_include_opts);
+ free(perf_include_dir);
if (p_obj_buf)
*p_obj_buf = NULL;
if (p_obj_buf_sz)
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 2eca8478..e7b4a8b 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -24,6 +24,7 @@
#include "sane_ctype.h"
#include <symbol/kallsyms.h>
+#include <linux/mman.h>
static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock);
@@ -81,8 +82,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
machine->kptr_restrict_warned = false;
machine->comm_exec = false;
machine->kernel_start = 0;
-
- memset(machine->vmlinux_maps, 0, sizeof(machine->vmlinux_maps));
+ machine->vmlinux_map = NULL;
machine->root_dir = strdup(root_dir);
if (machine->root_dir == NULL)
@@ -137,13 +137,11 @@ struct machine *machine__new_kallsyms(void)
struct machine *machine = machine__new_host();
/*
* FIXME:
- * 1) MAP__FUNCTION will go away when we stop loading separate maps for
- * functions and data objects.
- * 2) We should switch to machine__load_kallsyms(), i.e. not explicitely
+ * 1) We should switch to machine__load_kallsyms(), i.e. not explicitely
* ask for not using the kcore parsing code, once this one is fixed
* to create a map per module.
*/
- if (machine && machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION) <= 0) {
+ if (machine && machine__load_kallsyms(machine, "/proc/kallsyms") <= 0) {
machine__delete(machine);
machine = NULL;
}
@@ -673,8 +671,7 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start,
if (kmod_path__parse_name(&m, filename))
return NULL;
- map = map_groups__find_by_name(&machine->kmaps, MAP__FUNCTION,
- m.name);
+ map = map_groups__find_by_name(&machine->kmaps, m.name);
if (map) {
/*
* If the map's dso is an offline module, give dso__load()
@@ -689,7 +686,7 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start,
if (dso == NULL)
goto out;
- map = map__new2(start, dso, MAP__FUNCTION);
+ map = map__new2(start, dso);
if (map == NULL)
goto out;
@@ -810,8 +807,8 @@ struct process_args {
u64 start;
};
-static void machine__get_kallsyms_filename(struct machine *machine, char *buf,
- size_t bufsz)
+void machine__get_kallsyms_filename(struct machine *machine, char *buf,
+ size_t bufsz)
{
if (machine__is_default_guest(machine))
scnprintf(buf, bufsz, "%s", symbol_conf.default_guest_kallsyms);
@@ -854,65 +851,171 @@ static int machine__get_running_kernel_start(struct machine *machine,
return 0;
}
+int machine__create_extra_kernel_map(struct machine *machine,
+ struct dso *kernel,
+ struct extra_kernel_map *xm)
+{
+ struct kmap *kmap;
+ struct map *map;
+
+ map = map__new2(xm->start, kernel);
+ if (!map)
+ return -1;
+
+ map->end = xm->end;
+ map->pgoff = xm->pgoff;
+
+ kmap = map__kmap(map);
+
+ kmap->kmaps = &machine->kmaps;
+ strlcpy(kmap->name, xm->name, KMAP_NAME_LEN);
+
+ map_groups__insert(&machine->kmaps, map);
+
+ pr_debug2("Added extra kernel map %s %" PRIx64 "-%" PRIx64 "\n",
+ kmap->name, map->start, map->end);
+
+ map__put(map);
+
+ return 0;
+}
+
+static u64 find_entry_trampoline(struct dso *dso)
+{
+ /* Duplicates are removed so lookup all aliases */
+ const char *syms[] = {
+ "_entry_trampoline",
+ "__entry_trampoline_start",
+ "entry_SYSCALL_64_trampoline",
+ };
+ struct symbol *sym = dso__first_symbol(dso);
+ unsigned int i;
+
+ for (; sym; sym = dso__next_symbol(sym)) {
+ if (sym->binding != STB_GLOBAL)
+ continue;
+ for (i = 0; i < ARRAY_SIZE(syms); i++) {
+ if (!strcmp(sym->name, syms[i]))
+ return sym->start;
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * These values can be used for kernels that do not have symbols for the entry
+ * trampolines in kallsyms.
+ */
+#define X86_64_CPU_ENTRY_AREA_PER_CPU 0xfffffe0000000000ULL
+#define X86_64_CPU_ENTRY_AREA_SIZE 0x2c000
+#define X86_64_ENTRY_TRAMPOLINE 0x6000
+
+/* Map x86_64 PTI entry trampolines */
+int machine__map_x86_64_entry_trampolines(struct machine *machine,
+ struct dso *kernel)
+{
+ struct map_groups *kmaps = &machine->kmaps;
+ struct maps *maps = &kmaps->maps;
+ int nr_cpus_avail, cpu;
+ bool found = false;
+ struct map *map;
+ u64 pgoff;
+
+ /*
+ * In the vmlinux case, pgoff is a virtual address which must now be
+ * mapped to a vmlinux offset.
+ */
+ for (map = maps__first(maps); map; map = map__next(map)) {
+ struct kmap *kmap = __map__kmap(map);
+ struct map *dest_map;
+
+ if (!kmap || !is_entry_trampoline(kmap->name))
+ continue;
+
+ dest_map = map_groups__find(kmaps, map->pgoff);
+ if (dest_map != map)
+ map->pgoff = dest_map->map_ip(dest_map, map->pgoff);
+ found = true;
+ }
+ if (found || machine->trampolines_mapped)
+ return 0;
+
+ pgoff = find_entry_trampoline(kernel);
+ if (!pgoff)
+ return 0;
+
+ nr_cpus_avail = machine__nr_cpus_avail(machine);
+
+ /* Add a 1 page map for each CPU's entry trampoline */
+ for (cpu = 0; cpu < nr_cpus_avail; cpu++) {
+ u64 va = X86_64_CPU_ENTRY_AREA_PER_CPU +
+ cpu * X86_64_CPU_ENTRY_AREA_SIZE +
+ X86_64_ENTRY_TRAMPOLINE;
+ struct extra_kernel_map xm = {
+ .start = va,
+ .end = va + page_size,
+ .pgoff = pgoff,
+ };
+
+ strlcpy(xm.name, ENTRY_TRAMPOLINE_NAME, KMAP_NAME_LEN);
+
+ if (machine__create_extra_kernel_map(machine, kernel, &xm) < 0)
+ return -1;
+ }
+
+ machine->trampolines_mapped = nr_cpus_avail;
+
+ return 0;
+}
+
+int __weak machine__create_extra_kernel_maps(struct machine *machine __maybe_unused,
+ struct dso *kernel __maybe_unused)
+{
+ return 0;
+}
+
static int
__machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
{
- int type;
+ struct kmap *kmap;
+ struct map *map;
/* In case of renewal the kernel map, destroy previous one */
machine__destroy_kernel_maps(machine);
- for (type = 0; type < MAP__NR_TYPES; ++type) {
- struct kmap *kmap;
- struct map *map;
+ machine->vmlinux_map = map__new2(0, kernel);
+ if (machine->vmlinux_map == NULL)
+ return -1;
- machine->vmlinux_maps[type] = map__new2(0, kernel, type);
- if (machine->vmlinux_maps[type] == NULL)
- return -1;
+ machine->vmlinux_map->map_ip = machine->vmlinux_map->unmap_ip = identity__map_ip;
+ map = machine__kernel_map(machine);
+ kmap = map__kmap(map);
+ if (!kmap)
+ return -1;
- machine->vmlinux_maps[type]->map_ip =
- machine->vmlinux_maps[type]->unmap_ip =
- identity__map_ip;
- map = __machine__kernel_map(machine, type);
- kmap = map__kmap(map);
- if (!kmap)
- return -1;
-
- kmap->kmaps = &machine->kmaps;
- map_groups__insert(&machine->kmaps, map);
- }
+ kmap->kmaps = &machine->kmaps;
+ map_groups__insert(&machine->kmaps, map);
return 0;
}
void machine__destroy_kernel_maps(struct machine *machine)
{
- int type;
+ struct kmap *kmap;
+ struct map *map = machine__kernel_map(machine);
- for (type = 0; type < MAP__NR_TYPES; ++type) {
- struct kmap *kmap;
- struct map *map = __machine__kernel_map(machine, type);
+ if (map == NULL)
+ return;
- if (map == NULL)
- continue;
-
- kmap = map__kmap(map);
- map_groups__remove(&machine->kmaps, map);
- if (kmap && kmap->ref_reloc_sym) {
- /*
- * ref_reloc_sym is shared among all maps, so free just
- * on one of them.
- */
- if (type == MAP__FUNCTION) {
- zfree((char **)&kmap->ref_reloc_sym->name);
- zfree(&kmap->ref_reloc_sym);
- } else
- kmap->ref_reloc_sym = NULL;
- }
-
- map__put(machine->vmlinux_maps[type]);
- machine->vmlinux_maps[type] = NULL;
+ kmap = map__kmap(map);
+ map_groups__remove(&machine->kmaps, map);
+ if (kmap && kmap->ref_reloc_sym) {
+ zfree((char **)&kmap->ref_reloc_sym->name);
+ zfree(&kmap->ref_reloc_sym);
}
+
+ map__zput(machine->vmlinux_map);
}
int machines__create_guest_kernel_maps(struct machines *machines)
@@ -989,43 +1092,35 @@ int machines__create_kernel_maps(struct machines *machines, pid_t pid)
return machine__create_kernel_maps(machine);
}
-int machine__load_kallsyms(struct machine *machine, const char *filename,
- enum map_type type)
+int machine__load_kallsyms(struct machine *machine, const char *filename)
{
struct map *map = machine__kernel_map(machine);
int ret = __dso__load_kallsyms(map->dso, filename, map, true);
if (ret > 0) {
- dso__set_loaded(map->dso, type);
+ dso__set_loaded(map->dso);
/*
* Since /proc/kallsyms will have multiple sessions for the
* kernel, with modules between them, fixup the end of all
* sections.
*/
- __map_groups__fixup_end(&machine->kmaps, type);
+ map_groups__fixup_end(&machine->kmaps);
}
return ret;
}
-int machine__load_vmlinux_path(struct machine *machine, enum map_type type)
+int machine__load_vmlinux_path(struct machine *machine)
{
struct map *map = machine__kernel_map(machine);
int ret = dso__load_vmlinux_path(map->dso, map);
if (ret > 0)
- dso__set_loaded(map->dso, type);
+ dso__set_loaded(map->dso);
return ret;
}
-static void map_groups__fixup_end(struct map_groups *mg)
-{
- int i;
- for (i = 0; i < MAP__NR_TYPES; ++i)
- __map_groups__fixup_end(mg, i);
-}
-
static char *get_kernel_version(const char *root_dir)
{
char version[PATH_MAX];
@@ -1062,10 +1157,9 @@ static bool is_kmod_dso(struct dso *dso)
static int map_groups__set_module_path(struct map_groups *mg, const char *path,
struct kmod_path *m)
{
- struct map *map;
char *long_name;
+ struct map *map = map_groups__find_by_name(mg, m->name);
- map = map_groups__find_by_name(mg, MAP__FUNCTION, m->name);
if (map == NULL)
return 0;
@@ -1214,25 +1308,21 @@ static int machine__create_modules(struct machine *machine)
static void machine__set_kernel_mmap(struct machine *machine,
u64 start, u64 end)
{
- int i;
-
- for (i = 0; i < MAP__NR_TYPES; i++) {
- machine->vmlinux_maps[i]->start = start;
- machine->vmlinux_maps[i]->end = end;
-
- /*
- * Be a bit paranoid here, some perf.data file came with
- * a zero sized synthesized MMAP event for the kernel.
- */
- if (start == 0 && end == 0)
- machine->vmlinux_maps[i]->end = ~0ULL;
- }
+ machine->vmlinux_map->start = start;
+ machine->vmlinux_map->end = end;
+ /*
+ * Be a bit paranoid here, some perf.data file came with
+ * a zero sized synthesized MMAP event for the kernel.
+ */
+ if (start == 0 && end == 0)
+ machine->vmlinux_map->end = ~0ULL;
}
int machine__create_kernel_maps(struct machine *machine)
{
struct dso *kernel = machine__get_kernel(machine);
const char *name = NULL;
+ struct map *map;
u64 addr = 0;
int ret;
@@ -1240,9 +1330,8 @@ int machine__create_kernel_maps(struct machine *machine)
return -1;
ret = __machine__create_kernel_maps(machine, kernel);
- dso__put(kernel);
if (ret < 0)
- return -1;
+ goto out_put;
if (symbol_conf.use_modules && machine__create_modules(machine) < 0) {
if (machine__is_host(machine))
@@ -1255,18 +1344,35 @@ int machine__create_kernel_maps(struct machine *machine)
if (!machine__get_running_kernel_start(machine, &name, &addr)) {
if (name &&
- maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) {
+ map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map, name, addr)) {
machine__destroy_kernel_maps(machine);
- return -1;
+ ret = -1;
+ goto out_put;
}
- machine__set_kernel_mmap(machine, addr, 0);
+
+ /* we have a real start address now, so re-order the kmaps */
+ map = machine__kernel_map(machine);
+
+ map__get(map);
+ map_groups__remove(&machine->kmaps, map);
+
+ /* assume it's the last in the kmaps */
+ machine__set_kernel_mmap(machine, addr, ~0ULL);
+
+ map_groups__insert(&machine->kmaps, map);
+ map__put(map);
}
- /*
- * Now that we have all the maps created, just set the ->end of them:
- */
- map_groups__fixup_end(&machine->kmaps);
- return 0;
+ if (machine__create_extra_kernel_maps(machine, kernel))
+ pr_debug("Problems creating extra kernel maps, continuing anyway...\n");
+
+ /* update end address of the kernel map using adjacent module address */
+ map = map__next(machine__kernel_map(machine));
+ if (map)
+ machine__set_kernel_mmap(machine, addr, map->start);
+out_put:
+ dso__put(kernel);
+ return ret;
}
static bool machine__uses_kcore(struct machine *machine)
@@ -1281,6 +1387,32 @@ static bool machine__uses_kcore(struct machine *machine)
return false;
}
+static bool perf_event__is_extra_kernel_mmap(struct machine *machine,
+ union perf_event *event)
+{
+ return machine__is(machine, "x86_64") &&
+ is_entry_trampoline(event->mmap.filename);
+}
+
+static int machine__process_extra_kernel_map(struct machine *machine,
+ union perf_event *event)
+{
+ struct map *kernel_map = machine__kernel_map(machine);
+ struct dso *kernel = kernel_map ? kernel_map->dso : NULL;
+ struct extra_kernel_map xm = {
+ .start = event->mmap.start,
+ .end = event->mmap.start + event->mmap.len,
+ .pgoff = event->mmap.pgoff,
+ };
+
+ if (kernel == NULL)
+ return -1;
+
+ strlcpy(xm.name, event->mmap.filename, KMAP_NAME_LEN);
+
+ return machine__create_extra_kernel_map(machine, kernel, &xm);
+}
+
static int machine__process_kernel_mmap_event(struct machine *machine,
union perf_event *event)
{
@@ -1373,9 +1505,9 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
* time /proc/sys/kernel/kptr_restrict was non zero.
*/
if (event->mmap.pgoff != 0) {
- maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
- symbol_name,
- event->mmap.pgoff);
+ map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map,
+ symbol_name,
+ event->mmap.pgoff);
}
if (machine__is_default_guest(machine)) {
@@ -1384,6 +1516,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
*/
dso__load(kernel, machine__kernel_map(machine));
}
+ } else if (perf_event__is_extra_kernel_mmap(machine, event)) {
+ return machine__process_extra_kernel_map(machine, event);
}
return 0;
out_problem:
@@ -1396,7 +1530,6 @@ int machine__process_mmap2_event(struct machine *machine,
{
struct thread *thread;
struct map *map;
- enum map_type type;
int ret = 0;
if (dump_trace)
@@ -1415,11 +1548,6 @@ int machine__process_mmap2_event(struct machine *machine,
if (thread == NULL)
goto out_problem;
- if (event->header.misc & PERF_RECORD_MISC_MMAP_DATA)
- type = MAP__VARIABLE;
- else
- type = MAP__FUNCTION;
-
map = map__new(machine, event->mmap2.start,
event->mmap2.len, event->mmap2.pgoff,
event->mmap2.maj,
@@ -1427,7 +1555,7 @@ int machine__process_mmap2_event(struct machine *machine,
event->mmap2.ino_generation,
event->mmap2.prot,
event->mmap2.flags,
- event->mmap2.filename, type, thread);
+ event->mmap2.filename, thread);
if (map == NULL)
goto out_problem_map;
@@ -1454,7 +1582,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
{
struct thread *thread;
struct map *map;
- enum map_type type;
+ u32 prot = 0;
int ret = 0;
if (dump_trace)
@@ -1473,16 +1601,14 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
if (thread == NULL)
goto out_problem;
- if (event->header.misc & PERF_RECORD_MISC_MMAP_DATA)
- type = MAP__VARIABLE;
- else
- type = MAP__FUNCTION;
+ if (!(event->header.misc & PERF_RECORD_MISC_MMAP_DATA))
+ prot = PROT_EXEC;
map = map__new(machine, event->mmap.start,
event->mmap.len, event->mmap.pgoff,
- 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, prot, 0,
event->mmap.filename,
- type, thread);
+ thread);
if (map == NULL)
goto out_problem_map;
@@ -1658,7 +1784,7 @@ static void ip__resolve_ams(struct thread *thread,
* Thus, we have to try consecutively until we find a match
* or else, the symbol is unknown
*/
- thread__find_cpumode_addr_location(thread, MAP__FUNCTION, ip, &al);
+ thread__find_cpumode_addr_location(thread, ip, &al);
ams->addr = ip;
ams->al_addr = al.addr;
@@ -1675,15 +1801,7 @@ static void ip__resolve_data(struct thread *thread,
memset(&al, 0, sizeof(al));
- thread__find_addr_location(thread, m, MAP__VARIABLE, addr, &al);
- if (al.map == NULL) {
- /*
- * some shared data regions have execute bit set which puts
- * their mapping in the MAP__FUNCTION type array.
- * Check there as a fallback option before dropping the sample.
- */
- thread__find_addr_location(thread, m, MAP__FUNCTION, addr, &al);
- }
+ thread__find_symbol(thread, m, addr, &al);
ams->addr = addr;
ams->al_addr = al.addr;
@@ -1752,8 +1870,7 @@ static int add_callchain_ip(struct thread *thread,
al.filtered = 0;
al.sym = NULL;
if (!cpumode) {
- thread__find_cpumode_addr_location(thread, MAP__FUNCTION,
- ip, &al);
+ thread__find_cpumode_addr_location(thread, ip, &al);
} else {
if (ip >= PERF_CONTEXT_MAX) {
switch (ip) {
@@ -1778,8 +1895,7 @@ static int add_callchain_ip(struct thread *thread,
}
return 0;
}
- thread__find_addr_location(thread, *cpumode, MAP__FUNCTION,
- ip, &al);
+ thread__find_symbol(thread, *cpumode, ip, &al);
}
if (al.sym != NULL) {
@@ -1804,7 +1920,7 @@ static int add_callchain_ip(struct thread *thread,
}
srcline = callchain_srcline(al.map, al.sym, al.addr);
- return callchain_cursor_append(cursor, al.addr, al.map, al.sym,
+ return callchain_cursor_append(cursor, ip, al.map, al.sym,
branch, flags, nr_loop_iter,
iter_cycles, branch_from, srcline);
}
@@ -2336,6 +2452,20 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
return 0;
}
+/*
+ * Compares the raw arch string. N.B. see instead perf_env__arch() if a
+ * normalized arch is needed.
+ */
+bool machine__is(struct machine *machine, const char *arch)
+{
+ return machine && !strcmp(perf_env__raw_arch(machine->env), arch);
+}
+
+int machine__nr_cpus_avail(struct machine *machine)
+{
+ return machine ? perf_env__nr_cpus_avail(machine->env) : 0;
+}
+
int machine__get_kernel_start(struct machine *machine)
{
struct map *map = machine__kernel_map(machine);
@@ -2352,7 +2482,12 @@ int machine__get_kernel_start(struct machine *machine)
machine->kernel_start = 1ULL << 63;
if (map) {
err = map__load(map);
- if (!err)
+ /*
+ * On x86_64, PTI entry trampolines are less than the
+ * start of kernel text, but still above 2^63. So leave
+ * kernel_start = 1ULL << 63 for x86_64.
+ */
+ if (!err && !machine__is(machine, "x86_64"))
machine->kernel_start = map->start;
}
return err;
@@ -2367,7 +2502,7 @@ char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, ch
{
struct machine *machine = vmachine;
struct map *map;
- struct symbol *sym = map_groups__find_symbol(&machine->kmaps, MAP__FUNCTION, *addrp, &map);
+ struct symbol *sym = machine__find_kernel_symbol(machine, *addrp, &map);
if (sym == NULL)
return NULL;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 66cc200..1de7660 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -49,13 +49,14 @@ struct machine {
struct perf_env *env;
struct dsos dsos;
struct map_groups kmaps;
- struct map *vmlinux_maps[MAP__NR_TYPES];
+ struct map *vmlinux_map;
u64 kernel_start;
pid_t *current_tid;
union { /* Tool specific area */
void *priv;
u64 db_id;
};
+ bool trampolines_mapped;
};
static inline struct threads *machine__threads(struct machine *machine, pid_t tid)
@@ -64,16 +65,22 @@ static inline struct threads *machine__threads(struct machine *machine, pid_t ti
return &machine->threads[(unsigned int)tid % THREADS__TABLE_SIZE];
}
-static inline
-struct map *__machine__kernel_map(struct machine *machine, enum map_type type)
-{
- return machine->vmlinux_maps[type];
-}
-
+/*
+ * The main kernel (vmlinux) map
+ */
static inline
struct map *machine__kernel_map(struct machine *machine)
{
- return __machine__kernel_map(machine, MAP__FUNCTION);
+ return machine->vmlinux_map;
+}
+
+/*
+ * kernel (the one returned by machine__kernel_map()) plus kernel modules maps
+ */
+static inline
+struct maps *machine__kernel_maps(struct machine *machine)
+{
+ return &machine->kmaps.maps;
}
int machine__get_kernel_start(struct machine *machine);
@@ -182,6 +189,9 @@ static inline bool machine__is_host(struct machine *machine)
return machine ? machine->pid == HOST_KERNEL_ID : false;
}
+bool machine__is(struct machine *machine, const char *arch);
+int machine__nr_cpus_avail(struct machine *machine);
+
struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
@@ -190,44 +200,27 @@ struct dso *machine__findnew_dso(struct machine *machine, const char *filename);
size_t machine__fprintf(struct machine *machine, FILE *fp);
static inline
-struct symbol *machine__find_kernel_symbol(struct machine *machine,
- enum map_type type, u64 addr,
+struct symbol *machine__find_kernel_symbol(struct machine *machine, u64 addr,
struct map **mapp)
{
- return map_groups__find_symbol(&machine->kmaps, type, addr, mapp);
+ return map_groups__find_symbol(&machine->kmaps, addr, mapp);
}
static inline
struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine,
- enum map_type type, const char *name,
+ const char *name,
struct map **mapp)
{
- return map_groups__find_symbol_by_name(&machine->kmaps, type, name, mapp);
-}
-
-static inline
-struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr,
- struct map **mapp)
-{
- return machine__find_kernel_symbol(machine, MAP__FUNCTION, addr,
- mapp);
-}
-
-static inline
-struct symbol *machine__find_kernel_function_by_name(struct machine *machine,
- const char *name,
- struct map **mapp)
-{
- return map_groups__find_function_by_name(&machine->kmaps, name, mapp);
+ return map_groups__find_symbol_by_name(&machine->kmaps, name, mapp);
}
struct map *machine__findnew_module_map(struct machine *machine, u64 start,
const char *filename);
int arch__fix_module_text_start(u64 *start, const char *name);
-int machine__load_kallsyms(struct machine *machine, const char *filename,
- enum map_type type);
-int machine__load_vmlinux_path(struct machine *machine, enum map_type type);
+int machine__load_kallsyms(struct machine *machine, const char *filename);
+
+int machine__load_vmlinux_path(struct machine *machine);
size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
bool (skip)(struct dso *dso, int parm), int parm);
@@ -276,4 +269,25 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
*/
char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp);
+void machine__get_kallsyms_filename(struct machine *machine, char *buf,
+ size_t bufsz);
+
+int machine__create_extra_kernel_maps(struct machine *machine,
+ struct dso *kernel);
+
+/* Kernel-space maps for symbols that are outside the main kernel map and module maps */
+struct extra_kernel_map {
+ u64 start;
+ u64 end;
+ u64 pgoff;
+ char name[KMAP_NAME_LEN];
+};
+
+int machine__create_extra_kernel_map(struct machine *machine,
+ struct dso *kernel,
+ struct extra_kernel_map *xm);
+
+int machine__map_x86_64_entry_trampolines(struct machine *machine,
+ struct dso *kernel);
+
#endif /* __PERF_MACHINE_H */
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 8fe5703..6ae97ed 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -22,11 +22,6 @@
static void __maps__insert(struct maps *maps, struct map *map);
-const char *map_type__name[MAP__NR_TYPES] = {
- [MAP__FUNCTION] = "Functions",
- [MAP__VARIABLE] = "Variables",
-};
-
static inline int is_anon_memory(const char *filename, u32 flags)
{
return flags & MAP_HUGETLB ||
@@ -129,10 +124,8 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
return false;
}
-void map__init(struct map *map, enum map_type type,
- u64 start, u64 end, u64 pgoff, struct dso *dso)
+void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso)
{
- map->type = type;
map->start = start;
map->end = end;
map->pgoff = pgoff;
@@ -149,7 +142,7 @@ void map__init(struct map *map, enum map_type type,
struct map *map__new(struct machine *machine, u64 start, u64 len,
u64 pgoff, u32 d_maj, u32 d_min, u64 ino,
u64 ino_gen, u32 prot, u32 flags, char *filename,
- enum map_type type, struct thread *thread)
+ struct thread *thread)
{
struct map *map = malloc(sizeof(*map));
struct nsinfo *nsi = NULL;
@@ -173,7 +166,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
map->flags = flags;
nsi = nsinfo__get(thread->nsinfo);
- if ((anon || no_dso) && nsi && type == MAP__FUNCTION) {
+ if ((anon || no_dso) && nsi && (prot & PROT_EXEC)) {
snprintf(newfilename, sizeof(newfilename),
"/tmp/perf-%d.map", nsi->pid);
filename = newfilename;
@@ -203,7 +196,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
if (dso == NULL)
goto out_delete;
- map__init(map, type, start, start + len, pgoff, dso);
+ map__init(map, start, start + len, pgoff, dso);
if (anon || no_dso) {
map->map_ip = map->unmap_ip = identity__map_ip;
@@ -213,8 +206,8 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
* functions still return NULL, and we avoid the
* unnecessary map__load warning.
*/
- if (type != MAP__FUNCTION)
- dso__set_loaded(dso, map->type);
+ if (!(prot & PROT_EXEC))
+ dso__set_loaded(dso);
}
dso->nsinfo = nsi;
dso__put(dso);
@@ -231,7 +224,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
* they are loaded) and for vmlinux, where only after we load all the
* symbols we'll know where it starts and ends.
*/
-struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
+struct map *map__new2(u64 start, struct dso *dso)
{
struct map *map = calloc(1, (sizeof(*map) +
(dso->kernel ? sizeof(struct kmap) : 0)));
@@ -239,7 +232,7 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
/*
* ->end will be filled after we load all the symbols
*/
- map__init(map, type, start, 0, 0, dso);
+ map__init(map, start, 0, 0, dso);
}
return map;
@@ -256,7 +249,19 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
*/
bool __map__is_kernel(const struct map *map)
{
- return __machine__kernel_map(map->groups->machine, map->type) == map;
+ return machine__kernel_map(map->groups->machine) == map;
+}
+
+bool __map__is_extra_kernel_map(const struct map *map)
+{
+ struct kmap *kmap = __map__kmap((struct map *)map);
+
+ return kmap && kmap->name[0];
+}
+
+bool map__has_symbols(const struct map *map)
+{
+ return dso__has_symbols(map->dso);
}
static void map__exit(struct map *map)
@@ -279,7 +284,7 @@ void map__put(struct map *map)
void map__fixup_start(struct map *map)
{
- struct rb_root *symbols = &map->dso->symbols[map->type];
+ struct rb_root *symbols = &map->dso->symbols;
struct rb_node *nd = rb_first(symbols);
if (nd != NULL) {
struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
@@ -289,7 +294,7 @@ void map__fixup_start(struct map *map)
void map__fixup_end(struct map *map)
{
- struct rb_root *symbols = &map->dso->symbols[map->type];
+ struct rb_root *symbols = &map->dso->symbols;
struct rb_node *nd = rb_last(symbols);
if (nd != NULL) {
struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
@@ -304,7 +309,7 @@ int map__load(struct map *map)
const char *name = map->dso->long_name;
int nr;
- if (dso__loaded(map->dso, map->type))
+ if (dso__loaded(map->dso))
return 0;
nr = dso__load(map->dso, map);
@@ -348,7 +353,7 @@ struct symbol *map__find_symbol(struct map *map, u64 addr)
if (map__load(map) < 0)
return NULL;
- return dso__find_symbol(map->dso, map->type, addr);
+ return dso__find_symbol(map->dso, addr);
}
struct symbol *map__find_symbol_by_name(struct map *map, const char *name)
@@ -356,10 +361,10 @@ struct symbol *map__find_symbol_by_name(struct map *map, const char *name)
if (map__load(map) < 0)
return NULL;
- if (!dso__sorted_by_name(map->dso, map->type))
- dso__sort_by_name(map->dso, map->type);
+ if (!dso__sorted_by_name(map->dso))
+ dso__sort_by_name(map->dso);
- return dso__find_symbol_by_name(map->dso, map->type, name);
+ return dso__find_symbol_by_name(map->dso, name);
}
struct map *map__clone(struct map *from)
@@ -494,10 +499,7 @@ static void maps__init(struct maps *maps)
void map_groups__init(struct map_groups *mg, struct machine *machine)
{
- int i;
- for (i = 0; i < MAP__NR_TYPES; ++i) {
- maps__init(&mg->maps[i]);
- }
+ maps__init(&mg->maps);
mg->machine = machine;
refcount_set(&mg->refcnt, 1);
}
@@ -525,22 +527,12 @@ static void maps__exit(struct maps *maps)
void map_groups__exit(struct map_groups *mg)
{
- int i;
-
- for (i = 0; i < MAP__NR_TYPES; ++i)
- maps__exit(&mg->maps[i]);
+ maps__exit(&mg->maps);
}
bool map_groups__empty(struct map_groups *mg)
{
- int i;
-
- for (i = 0; i < MAP__NR_TYPES; ++i) {
- if (maps__first(&mg->maps[i]))
- return false;
- }
-
- return true;
+ return !maps__first(&mg->maps);
}
struct map_groups *map_groups__new(struct machine *machine)
@@ -566,10 +558,9 @@ void map_groups__put(struct map_groups *mg)
}
struct symbol *map_groups__find_symbol(struct map_groups *mg,
- enum map_type type, u64 addr,
- struct map **mapp)
+ u64 addr, struct map **mapp)
{
- struct map *map = map_groups__find(mg, type, addr);
+ struct map *map = map_groups__find(mg, addr);
/* Ensure map is loaded before using map->map_ip */
if (map != NULL && map__load(map) >= 0) {
@@ -608,13 +599,10 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
}
struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
- enum map_type type,
const char *name,
struct map **mapp)
{
- struct symbol *sym = maps__find_symbol_by_name(&mg->maps[type], name, mapp);
-
- return sym;
+ return maps__find_symbol_by_name(&mg->maps, name, mapp);
}
int map_groups__find_ams(struct addr_map_symbol *ams)
@@ -622,8 +610,7 @@ int map_groups__find_ams(struct addr_map_symbol *ams)
if (ams->addr < ams->map->start || ams->addr >= ams->map->end) {
if (ams->map->groups == NULL)
return -1;
- ams->map = map_groups__find(ams->map->groups, ams->map->type,
- ams->addr);
+ ams->map = map_groups__find(ams->map->groups, ams->addr);
if (ams->map == NULL)
return -1;
}
@@ -646,7 +633,7 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp)
printed += fprintf(fp, "Map:");
printed += map__fprintf(pos, fp);
if (verbose > 2) {
- printed += dso__fprintf(pos->dso, pos->type, fp);
+ printed += dso__fprintf(pos->dso, fp);
printed += fprintf(fp, "--\n");
}
}
@@ -656,24 +643,14 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp)
return printed;
}
-size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
- FILE *fp)
-{
- size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
- return printed += maps__fprintf(&mg->maps[type], fp);
-}
-
size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
{
- size_t printed = 0, i;
- for (i = 0; i < MAP__NR_TYPES; ++i)
- printed += __map_groups__fprintf_maps(mg, i, fp);
- return printed;
+ return maps__fprintf(&mg->maps, fp);
}
static void __map_groups__insert(struct map_groups *mg, struct map *map)
{
- __maps__insert(&mg->maps[map->type], map);
+ __maps__insert(&mg->maps, map);
map->groups = mg;
}
@@ -758,19 +735,18 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
FILE *fp)
{
- return maps__fixup_overlappings(&mg->maps[map->type], map, fp);
+ return maps__fixup_overlappings(&mg->maps, map, fp);
}
/*
* XXX This should not really _copy_ te maps, but refcount them.
*/
-int map_groups__clone(struct thread *thread,
- struct map_groups *parent, enum map_type type)
+int map_groups__clone(struct thread *thread, struct map_groups *parent)
{
struct map_groups *mg = thread->mg;
int err = -ENOMEM;
struct map *map;
- struct maps *maps = &parent->maps[type];
+ struct maps *maps = &parent->maps;
down_read(&maps->lock);
@@ -877,13 +853,20 @@ struct map *map__next(struct map *map)
return NULL;
}
+struct kmap *__map__kmap(struct map *map)
+{
+ if (!map->dso || !map->dso->kernel)
+ return NULL;
+ return (struct kmap *)(map + 1);
+}
+
struct kmap *map__kmap(struct map *map)
{
- if (!map->dso || !map->dso->kernel) {
+ struct kmap *kmap = __map__kmap(map);
+
+ if (!kmap)
pr_err("Internal error: map__kmap with a non-kernel map\n");
- return NULL;
- }
- return (struct kmap *)(map + 1);
+ return kmap;
}
struct map_groups *map__kmaps(struct map *map)
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 0e9bbe0..97e2a06 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -8,19 +8,11 @@
#include <linux/rbtree.h>
#include <pthread.h>
#include <stdio.h>
+#include <string.h>
#include <stdbool.h>
#include <linux/types.h>
#include "rwsem.h"
-enum map_type {
- MAP__FUNCTION = 0,
- MAP__VARIABLE,
-};
-
-#define MAP__NR_TYPES (MAP__VARIABLE + 1)
-
-extern const char *map_type__name[MAP__NR_TYPES];
-
struct dso;
struct ip_callchain;
struct ref_reloc_sym;
@@ -35,7 +27,6 @@ struct map {
};
u64 start;
u64 end;
- u8 /* enum map_type */ type;
bool erange_warned;
u32 priv;
u32 prot;
@@ -56,9 +47,12 @@ struct map {
refcount_t refcnt;
};
+#define KMAP_NAME_LEN 256
+
struct kmap {
struct ref_reloc_sym *ref_reloc_sym;
struct map_groups *kmaps;
+ char name[KMAP_NAME_LEN];
};
struct maps {
@@ -67,7 +61,7 @@ struct maps {
};
struct map_groups {
- struct maps maps[MAP__NR_TYPES];
+ struct maps maps;
struct machine *machine;
refcount_t refcnt;
};
@@ -85,6 +79,7 @@ static inline struct map_groups *map_groups__get(struct map_groups *mg)
void map_groups__put(struct map_groups *mg);
+struct kmap *__map__kmap(struct map *map);
struct kmap *map__kmap(struct map *map);
struct map_groups *map__kmaps(struct map *map);
@@ -125,7 +120,7 @@ struct thread;
* Note: caller must ensure map->dso is not NULL (map is loaded).
*/
#define map__for_each_symbol(map, pos, n) \
- dso__for_each_symbol(map->dso, pos, n, map->type)
+ dso__for_each_symbol(map->dso, pos, n)
/* map__for_each_symbol_with_name - iterate over the symbols in the given map
* that have the given name
@@ -144,13 +139,13 @@ struct thread;
#define map__for_each_symbol_by_name(map, sym_name, pos) \
__map__for_each_symbol_by_name(map, sym_name, (pos))
-void map__init(struct map *map, enum map_type type,
+void map__init(struct map *map,
u64 start, u64 end, u64 pgoff, struct dso *dso);
struct map *map__new(struct machine *machine, u64 start, u64 len,
u64 pgoff, u32 d_maj, u32 d_min, u64 ino,
u64 ino_gen, u32 prot, u32 flags,
- char *filename, enum map_type type, struct thread *thread);
-struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
+ char *filename, struct thread *thread);
+struct map *map__new2(u64 start, struct dso *dso);
void map__delete(struct map *map);
struct map *map__clone(struct map *map);
@@ -185,8 +180,6 @@ void map__fixup_end(struct map *map);
void map__reloc_vmlinux(struct map *map);
-size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
- FILE *fp);
void maps__insert(struct maps *maps, struct map *map);
void maps__remove(struct maps *maps, struct map *map);
struct map *maps__find(struct maps *maps, u64 addr);
@@ -197,34 +190,29 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
void map_groups__init(struct map_groups *mg, struct machine *machine);
void map_groups__exit(struct map_groups *mg);
int map_groups__clone(struct thread *thread,
- struct map_groups *parent, enum map_type type);
+ struct map_groups *parent);
size_t map_groups__fprintf(struct map_groups *mg, FILE *fp);
-int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name,
- u64 addr);
+int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name,
+ u64 addr);
static inline void map_groups__insert(struct map_groups *mg, struct map *map)
{
- maps__insert(&mg->maps[map->type], map);
+ maps__insert(&mg->maps, map);
map->groups = mg;
}
static inline void map_groups__remove(struct map_groups *mg, struct map *map)
{
- maps__remove(&mg->maps[map->type], map);
+ maps__remove(&mg->maps, map);
}
-static inline struct map *map_groups__find(struct map_groups *mg,
- enum map_type type, u64 addr)
+static inline struct map *map_groups__find(struct map_groups *mg, u64 addr)
{
- return maps__find(&mg->maps[type], addr);
+ return maps__find(&mg->maps, addr);
}
-static inline struct map *map_groups__first(struct map_groups *mg,
- enum map_type type)
-{
- return maps__first(&mg->maps[type]);
-}
+struct map *map_groups__first(struct map_groups *mg);
static inline struct map *map_groups__next(struct map *map)
{
@@ -232,11 +220,9 @@ static inline struct map *map_groups__next(struct map *map)
}
struct symbol *map_groups__find_symbol(struct map_groups *mg,
- enum map_type type, u64 addr,
- struct map **mapp);
+ u64 addr, struct map **mapp);
struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
- enum map_type type,
const char *name,
struct map **mapp);
@@ -244,24 +230,26 @@ struct addr_map_symbol;
int map_groups__find_ams(struct addr_map_symbol *ams);
-static inline
-struct symbol *map_groups__find_function_by_name(struct map_groups *mg,
- const char *name, struct map **mapp)
-{
- return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp);
-}
-
int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
FILE *fp);
-struct map *map_groups__find_by_name(struct map_groups *mg,
- enum map_type type, const char *name);
+struct map *map_groups__find_by_name(struct map_groups *mg, const char *name);
bool __map__is_kernel(const struct map *map);
+bool __map__is_extra_kernel_map(const struct map *map);
static inline bool __map__is_kmodule(const struct map *map)
{
- return !__map__is_kernel(map);
+ return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map);
+}
+
+bool map__has_symbols(const struct map *map);
+
+#define ENTRY_TRAMPOLINE_NAME "__entry_SYSCALL_64_trampoline"
+
+static inline bool is_entry_trampoline(const char *name)
+{
+ return !strcmp(name, ENTRY_TRAMPOLINE_NAME);
}
#endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 2fb0272..15eec49 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -156,13 +156,12 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
(strcmp(sys_dirent->d_name, ".")) && \
(strcmp(sys_dirent->d_name, "..")))
-static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir)
+static int tp_event_has_id(const char *dir_path, struct dirent *evt_dir)
{
char evt_path[MAXPATHLEN];
int fd;
- snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", tracing_events_path,
- sys_dir->d_name, evt_dir->d_name);
+ snprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path, evt_dir->d_name);
fd = open(evt_path, O_RDONLY);
if (fd < 0)
return -EINVAL;
@@ -171,12 +170,12 @@ static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir)
return 0;
}
-#define for_each_event(sys_dirent, evt_dir, evt_dirent) \
+#define for_each_event(dir_path, evt_dir, evt_dirent) \
while ((evt_dirent = readdir(evt_dir)) != NULL) \
if (evt_dirent->d_type == DT_DIR && \
(strcmp(evt_dirent->d_name, ".")) && \
(strcmp(evt_dirent->d_name, "..")) && \
- (!tp_event_has_id(sys_dirent, evt_dirent)))
+ (!tp_event_has_id(dir_path, evt_dirent)))
#define MAX_EVENT_LENGTH 512
@@ -190,21 +189,21 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
int fd;
u64 id;
char evt_path[MAXPATHLEN];
- char dir_path[MAXPATHLEN];
+ char *dir_path;
- sys_dir = opendir(tracing_events_path);
+ sys_dir = tracing_events__opendir();
if (!sys_dir)
return NULL;
for_each_subsystem(sys_dir, sys_dirent) {
-
- snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
- sys_dirent->d_name);
+ dir_path = get_events_file(sys_dirent->d_name);
+ if (!dir_path)
+ continue;
evt_dir = opendir(dir_path);
if (!evt_dir)
- continue;
+ goto next;
- for_each_event(sys_dirent, evt_dir, evt_dirent) {
+ for_each_event(dir_path, evt_dir, evt_dirent) {
scnprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path,
evt_dirent->d_name);
@@ -218,6 +217,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
close(fd);
id = atoll(id_buf);
if (id == config) {
+ put_events_file(dir_path);
closedir(evt_dir);
closedir(sys_dir);
path = zalloc(sizeof(*path));
@@ -242,6 +242,8 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
}
}
closedir(evt_dir);
+next:
+ put_events_file(dir_path);
}
closedir(sys_dir);
@@ -512,14 +514,19 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
struct parse_events_error *err,
struct list_head *head_config)
{
- char evt_path[MAXPATHLEN];
+ char *evt_path;
struct dirent *evt_ent;
DIR *evt_dir;
int ret = 0, found = 0;
- snprintf(evt_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_name);
+ evt_path = get_events_file(sys_name);
+ if (!evt_path) {
+ tracepoint_error(err, errno, sys_name, evt_name);
+ return -1;
+ }
evt_dir = opendir(evt_path);
if (!evt_dir) {
+ put_events_file(evt_path);
tracepoint_error(err, errno, sys_name, evt_name);
return -1;
}
@@ -545,6 +552,7 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
ret = -1;
}
+ put_events_file(evt_path);
closedir(evt_dir);
return ret;
}
@@ -570,7 +578,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
DIR *events_dir;
int ret = 0;
- events_dir = opendir(tracing_events_path);
+ events_dir = tracing_events__opendir();
if (!events_dir) {
tracepoint_error(err, errno, sys_name, evt_name);
return -1;
@@ -1219,13 +1227,16 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
int parse_events_add_pmu(struct parse_events_state *parse_state,
struct list_head *list, char *name,
- struct list_head *head_config, bool auto_merge_stats)
+ struct list_head *head_config,
+ bool auto_merge_stats,
+ bool use_alias)
{
struct perf_event_attr attr;
struct perf_pmu_info info;
struct perf_pmu *pmu;
struct perf_evsel *evsel;
struct parse_events_error *err = parse_state->error;
+ bool use_uncore_alias;
LIST_HEAD(config_terms);
pmu = perf_pmu__find(name);
@@ -1244,11 +1255,14 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
memset(&attr, 0, sizeof(attr));
}
+ use_uncore_alias = (pmu->is_uncore && use_alias);
+
if (!head_config) {
attr.type = pmu->type;
evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
if (evsel) {
evsel->pmu_name = name;
+ evsel->use_uncore_alias = use_uncore_alias;
return 0;
} else {
return -ENOMEM;
@@ -1282,6 +1296,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
evsel->metric_expr = info.metric_expr;
evsel->metric_name = info.metric_name;
evsel->pmu_name = name;
+ evsel->use_uncore_alias = use_uncore_alias;
}
return evsel ? 0 : -ENOMEM;
@@ -1317,7 +1332,8 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
list_add_tail(&term->list, head);
if (!parse_events_add_pmu(parse_state, list,
- pmu->name, head, true)) {
+ pmu->name, head,
+ true, true)) {
pr_debug("%s -> %s/%s/\n", str,
pmu->name, alias->str);
ok++;
@@ -1339,7 +1355,120 @@ int parse_events__modifier_group(struct list_head *list,
return parse_events__modifier_event(list, event_mod, true);
}
-void parse_events__set_leader(char *name, struct list_head *list)
+/*
+ * Check if the two uncore PMUs are from the same uncore block
+ * The format of the uncore PMU name is uncore_#blockname_#pmuidx
+ */
+static bool is_same_uncore_block(const char *pmu_name_a, const char *pmu_name_b)
+{
+ char *end_a, *end_b;
+
+ end_a = strrchr(pmu_name_a, '_');
+ end_b = strrchr(pmu_name_b, '_');
+
+ if (!end_a || !end_b)
+ return false;
+
+ if ((end_a - pmu_name_a) != (end_b - pmu_name_b))
+ return false;
+
+ return (strncmp(pmu_name_a, pmu_name_b, end_a - pmu_name_a) == 0);
+}
+
+static int
+parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list,
+ struct parse_events_state *parse_state)
+{
+ struct perf_evsel *evsel, *leader;
+ uintptr_t *leaders;
+ bool is_leader = true;
+ int i, nr_pmu = 0, total_members, ret = 0;
+
+ leader = list_first_entry(list, struct perf_evsel, node);
+ evsel = list_last_entry(list, struct perf_evsel, node);
+ total_members = evsel->idx - leader->idx + 1;
+
+ leaders = calloc(total_members, sizeof(uintptr_t));
+ if (WARN_ON(!leaders))
+ return 0;
+
+ /*
+ * Going through the whole group and doing sanity check.
+ * All members must use alias, and be from the same uncore block.
+ * Also, storing the leader events in an array.
+ */
+ __evlist__for_each_entry(list, evsel) {
+
+ /* Only split the uncore group which members use alias */
+ if (!evsel->use_uncore_alias)
+ goto out;
+
+ /* The events must be from the same uncore block */
+ if (!is_same_uncore_block(leader->pmu_name, evsel->pmu_name))
+ goto out;
+
+ if (!is_leader)
+ continue;
+ /*
+ * If the event's PMU name starts to repeat, it must be a new
+ * event. That can be used to distinguish the leader from
+ * other members, even they have the same event name.
+ */
+ if ((leader != evsel) && (leader->pmu_name == evsel->pmu_name)) {
+ is_leader = false;
+ continue;
+ }
+ /* The name is always alias name */
+ WARN_ON(strcmp(leader->name, evsel->name));
+
+ /* Store the leader event for each PMU */
+ leaders[nr_pmu++] = (uintptr_t) evsel;
+ }
+
+ /* only one event alias */
+ if (nr_pmu == total_members) {
+ parse_state->nr_groups--;
+ goto handled;
+ }
+
+ /*
+ * An uncore event alias is a joint name which means the same event
+ * runs on all PMUs of a block.
+ * Perf doesn't support mixed events from different PMUs in the same
+ * group. The big group has to be split into multiple small groups
+ * which only include the events from the same PMU.
+ *
+ * Here the uncore event aliases must be from the same uncore block.
+ * The number of PMUs must be same for each alias. The number of new
+ * small groups equals to the number of PMUs.
+ * Setting the leader event for corresponding members in each group.
+ */
+ i = 0;
+ __evlist__for_each_entry(list, evsel) {
+ if (i >= nr_pmu)
+ i = 0;
+ evsel->leader = (struct perf_evsel *) leaders[i++];
+ }
+
+ /* The number of members and group name are same for each group */
+ for (i = 0; i < nr_pmu; i++) {
+ evsel = (struct perf_evsel *) leaders[i];
+ evsel->nr_members = total_members / nr_pmu;
+ evsel->group_name = name ? strdup(name) : NULL;
+ }
+
+ /* Take the new small groups into account */
+ parse_state->nr_groups += nr_pmu - 1;
+
+handled:
+ ret = 1;
+out:
+ free(leaders);
+ return ret;
+}
+
+void parse_events__set_leader(char *name, struct list_head *list,
+ struct parse_events_state *parse_state)
{
struct perf_evsel *leader;
@@ -1348,6 +1477,9 @@ void parse_events__set_leader(char *name, struct list_head *list)
return;
}
+ if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state))
+ return;
+
__perf_evlist__set_leader(list);
leader = list_entry(list->next, struct perf_evsel, node);
leader->group_name = name ? strdup(name) : NULL;
@@ -1715,7 +1847,7 @@ int parse_events(struct perf_evlist *evlist, const char *str,
struct perf_evsel *last;
if (list_empty(&parse_state.list)) {
- WARN_ONCE(true, "WARNING: event parser found nothing");
+ WARN_ONCE(true, "WARNING: event parser found nothing\n");
return -1;
}
@@ -1968,13 +2100,13 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
DIR *sys_dir, *evt_dir;
struct dirent *sys_dirent, *evt_dirent;
char evt_path[MAXPATHLEN];
- char dir_path[MAXPATHLEN];
+ char *dir_path;
char **evt_list = NULL;
unsigned int evt_i = 0, evt_num = 0;
bool evt_num_known = false;
restart:
- sys_dir = opendir(tracing_events_path);
+ sys_dir = tracing_events__opendir();
if (!sys_dir)
return;
@@ -1989,13 +2121,14 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
!strglobmatch(sys_dirent->d_name, subsys_glob))
continue;
- snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
- sys_dirent->d_name);
+ dir_path = get_events_file(sys_dirent->d_name);
+ if (!dir_path)
+ continue;
evt_dir = opendir(dir_path);
if (!evt_dir)
- continue;
+ goto next;
- for_each_event(sys_dirent, evt_dir, evt_dirent) {
+ for_each_event(dir_path, evt_dir, evt_dirent) {
if (event_glob != NULL &&
!strglobmatch(evt_dirent->d_name, event_glob))
continue;
@@ -2009,11 +2142,15 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
sys_dirent->d_name, evt_dirent->d_name);
evt_list[evt_i] = strdup(evt_path);
- if (evt_list[evt_i] == NULL)
+ if (evt_list[evt_i] == NULL) {
+ put_events_file(dir_path);
goto out_close_evt_dir;
+ }
evt_i++;
}
closedir(evt_dir);
+next:
+ put_events_file(dir_path);
}
closedir(sys_dir);
@@ -2061,21 +2198,21 @@ int is_valid_tracepoint(const char *event_string)
DIR *sys_dir, *evt_dir;
struct dirent *sys_dirent, *evt_dirent;
char evt_path[MAXPATHLEN];
- char dir_path[MAXPATHLEN];
+ char *dir_path;
- sys_dir = opendir(tracing_events_path);
+ sys_dir = tracing_events__opendir();
if (!sys_dir)
return 0;
for_each_subsystem(sys_dir, sys_dirent) {
-
- snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
- sys_dirent->d_name);
+ dir_path = get_events_file(sys_dirent->d_name);
+ if (!dir_path)
+ continue;
evt_dir = opendir(dir_path);
if (!evt_dir)
- continue;
+ goto next;
- for_each_event(sys_dirent, evt_dir, evt_dirent) {
+ for_each_event(dir_path, evt_dir, evt_dirent) {
snprintf(evt_path, MAXPATHLEN, "%s:%s",
sys_dirent->d_name, evt_dirent->d_name);
if (!strcmp(evt_path, event_string)) {
@@ -2085,6 +2222,8 @@ int is_valid_tracepoint(const char *event_string)
}
}
closedir(evt_dir);
+next:
+ put_events_file(dir_path);
}
closedir(sys_dir);
return 0;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 5015cfd..4473dac 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -167,7 +167,9 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
void *ptr, char *type, u64 len);
int parse_events_add_pmu(struct parse_events_state *parse_state,
struct list_head *list, char *name,
- struct list_head *head_config, bool auto_merge_stats);
+ struct list_head *head_config,
+ bool auto_merge_stats,
+ bool use_alias);
int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
char *str,
@@ -178,7 +180,8 @@ int parse_events_copy_term_list(struct list_head *old,
enum perf_pmu_event_symbol_type
perf_pmu__parse_check(const char *name);
-void parse_events__set_leader(char *name, struct list_head *list);
+void parse_events__set_leader(char *name, struct list_head *list,
+ struct parse_events_state *parse_state);
void parse_events_update_lists(struct list_head *list_event,
struct list_head *list_all);
void parse_events_evlist_error(struct parse_events_state *parse_state,
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 7afeb80..e37608a 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -161,7 +161,7 @@
struct list_head *list = $3;
inc_group_count(list, _parse_state);
- parse_events__set_leader($1, list);
+ parse_events__set_leader($1, list, _parse_state);
$$ = list;
}
|
@@ -170,7 +170,7 @@
struct list_head *list = $2;
inc_group_count(list, _parse_state);
- parse_events__set_leader(NULL, list);
+ parse_events__set_leader(NULL, list, _parse_state);
$$ = list;
}
@@ -232,7 +232,7 @@
YYABORT;
ALLOC_LIST(list);
- if (parse_events_add_pmu(_parse_state, list, $1, $2, false)) {
+ if (parse_events_add_pmu(_parse_state, list, $1, $2, false, false)) {
struct perf_pmu *pmu = NULL;
int ok = 0;
char *pattern;
@@ -251,7 +251,7 @@
free(pattern);
YYABORT;
}
- if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true))
+ if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true, false))
ok++;
parse_events_terms__delete(terms);
}
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 064bdcb..d2fb597 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -539,9 +539,10 @@ static bool pmu_is_uncore(const char *name)
/*
* PMU CORE devices have different name other than cpu in sysfs on some
- * platforms. looking for possible sysfs files to identify as core device.
+ * platforms.
+ * Looking for possible sysfs files to identify the arm core device.
*/
-static int is_pmu_core(const char *name)
+static int is_arm_pmu_core(const char *name)
{
struct stat st;
char path[PATH_MAX];
@@ -550,18 +551,18 @@ static int is_pmu_core(const char *name)
if (!sysfs)
return 0;
- /* Look for cpu sysfs (x86 and others) */
- scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu", sysfs);
- if ((stat(path, &st) == 0) &&
- (strncmp(name, "cpu", strlen("cpu")) == 0))
- return 1;
-
/* Look for cpu sysfs (specific to arm) */
scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/cpus",
sysfs, name);
if (stat(path, &st) == 0)
return 1;
+ /* Look for cpu sysfs (specific to s390) */
+ scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s",
+ sysfs, name);
+ if (stat(path, &st) == 0 && !strncmp(name, "cpum_", 5))
+ return 1;
+
return 0;
}
@@ -580,7 +581,7 @@ char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
* cpuid string generated on this platform.
* Otherwise return non-zero.
*/
-int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
+int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
{
regex_t re;
regmatch_t pmatch[1];
@@ -662,6 +663,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
struct pmu_events_map *map;
struct pmu_event *pe;
const char *name = pmu->name;
+ const char *pname;
map = perf_pmu__find_map(pmu);
if (!map)
@@ -680,11 +682,9 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
break;
}
- if (!is_pmu_core(name)) {
- /* check for uncore devices */
- if (pe->pmu == NULL)
- continue;
- if (strncmp(pe->pmu, name, strlen(pe->pmu)))
+ if (!is_arm_pmu_core(name)) {
+ pname = pe->pmu ? pe->pmu : "cpu";
+ if (strncmp(pname, name, strlen(pname)))
continue;
}
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index e1dbc98..3094f11 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -111,17 +111,6 @@ void exit_probe_symbol_maps(void)
symbol__exit();
}
-static struct symbol *__find_kernel_function_by_name(const char *name,
- struct map **mapp)
-{
- return machine__find_kernel_function_by_name(host_machine, name, mapp);
-}
-
-static struct symbol *__find_kernel_function(u64 addr, struct map **mapp)
-{
- return machine__find_kernel_function(host_machine, addr, mapp);
-}
-
static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void)
{
/* kmap->ref_reloc_sym should be set if host_machine is initialized */
@@ -149,7 +138,7 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr,
if (reloc_sym && strcmp(name, reloc_sym->name) == 0)
*addr = (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr;
else {
- sym = __find_kernel_function_by_name(name, &map);
+ sym = machine__find_kernel_symbol_by_name(host_machine, name, &map);
if (!sym)
return -ENOENT;
*addr = map->unmap_ip(map, sym->start) -
@@ -161,8 +150,7 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr,
static struct map *kernel_get_module_map(const char *module)
{
- struct map_groups *grp = &host_machine->kmaps;
- struct maps *maps = &grp->maps[MAP__FUNCTION];
+ struct maps *maps = machine__kernel_maps(host_machine);
struct map *pos;
/* A file path -- this is an offline module */
@@ -341,7 +329,7 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso)
char module_name[128];
snprintf(module_name, sizeof(module_name), "[%s]", module);
- map = map_groups__find_by_name(&host_machine->kmaps, MAP__FUNCTION, module_name);
+ map = map_groups__find_by_name(&host_machine->kmaps, module_name);
if (map) {
dso = map->dso;
goto found;
@@ -2098,7 +2086,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
}
if (addr) {
addr += tp->offset;
- sym = __find_kernel_function(addr, &map);
+ sym = machine__find_kernel_symbol(host_machine, addr, &map);
}
}
@@ -3504,19 +3492,18 @@ int show_available_funcs(const char *target, struct nsinfo *nsi,
(target) ? : "kernel");
goto end;
}
- if (!dso__sorted_by_name(map->dso, map->type))
- dso__sort_by_name(map->dso, map->type);
+ if (!dso__sorted_by_name(map->dso))
+ dso__sort_by_name(map->dso);
/* Show all (filtered) symbols */
setup_pager();
- for (nd = rb_first(&map->dso->symbol_names[map->type]); nd; nd = rb_next(nd)) {
+ for (nd = rb_first(&map->dso->symbol_names); nd; nd = rb_next(nd)) {
struct symbol_name_rb_node *pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
if (strfilter__compare(_filter, pos->sym.name))
printf("%s\n", pos->sym.name);
- }
-
+ }
end:
map__put(map);
exit_probe_symbol_maps();
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 4ae1123..b76088f 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -84,8 +84,7 @@ int open_trace_file(const char *trace_file, bool readwrite)
char buf[PATH_MAX];
int ret;
- ret = e_snprintf(buf, PATH_MAX, "%s/%s",
- tracing_path, trace_file);
+ ret = e_snprintf(buf, PATH_MAX, "%s/%s", tracing_path_mount(), trace_file);
if (ret >= 0) {
pr_debug("Opening %s write=%d\n", buf, readwrite);
if (readwrite && !probe_event_dry_run)
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 10dd5fc..7f8afac 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -531,6 +531,8 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
PyLong_FromUnsignedLongLong(sample->period));
pydict_set_item_string_decref(dict_sample, "phys_addr",
PyLong_FromUnsignedLongLong(sample->phys_addr));
+ pydict_set_item_string_decref(dict_sample, "addr",
+ PyLong_FromUnsignedLongLong(sample->addr));
set_sample_read_in_dict(dict_sample, sample, evsel);
pydict_set_item_string_decref(dict, "sample", dict_sample);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f4a7a43..b998bb4 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1973,12 +1973,11 @@ bool perf_session__has_traces(struct perf_session *session, const char *msg)
return false;
}
-int maps__set_kallsyms_ref_reloc_sym(struct map **maps,
- const char *symbol_name, u64 addr)
+int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, u64 addr)
{
char *bracket;
- int i;
struct ref_reloc_sym *ref;
+ struct kmap *kmap;
ref = zalloc(sizeof(struct ref_reloc_sym));
if (ref == NULL)
@@ -1996,13 +1995,9 @@ int maps__set_kallsyms_ref_reloc_sym(struct map **maps,
ref->addr = addr;
- for (i = 0; i < MAP__NR_TYPES; ++i) {
- struct kmap *kmap = map__kmap(maps[i]);
-
- if (!kmap)
- continue;
+ kmap = map__kmap(map);
+ if (kmap)
kmap->ref_reloc_sym = ref;
- }
return 0;
}
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 26a68df..4058ade 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2,7 +2,7 @@
#include <errno.h>
#include <inttypes.h>
#include <regex.h>
-#include <sys/mman.h>
+#include <linux/mman.h>
#include "sort.h"
#include "hist.h"
#include "comm.h"
@@ -282,7 +282,7 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level);
if (sym && map) {
- if (map->type == MAP__VARIABLE) {
+ if (sym->type == STT_OBJECT) {
ret += repsep_snprintf(bf + ret, size - ret, "%s", sym->name);
ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx",
ip - map->unmap_ip(map, sym->start));
@@ -1211,7 +1211,7 @@ static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf,
/* print [s] for shared data mmaps */
if ((he->cpumode != PERF_RECORD_MISC_KERNEL) &&
- map && (map->type == MAP__VARIABLE) &&
+ map && !(map->prot & PROT_EXEC) &&
(map->flags & MAP_SHARED) &&
(map->maj || map->min || map->ino ||
map->ino_generation))
@@ -2582,7 +2582,7 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
if (sort__mode != SORT_MODE__MEMORY)
return -EINVAL;
- if (sd->entry == &sort_mem_dcacheline && cacheline_size == 0)
+ if (sd->entry == &sort_mem_dcacheline && cacheline_size() == 0)
return -EINVAL;
if (sd->entry == &sort_mem_daddr_sym)
@@ -2628,7 +2628,7 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str,
if (*tok) {
ret = sort_dimension__add(list, tok, evlist, level);
if (ret == -EINVAL) {
- if (!cacheline_size && !strncasecmp(tok, "dcacheline", strlen(tok)))
+ if (!cacheline_size() && !strncasecmp(tok, "dcacheline", strlen(tok)))
pr_err("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system");
else
pr_err("Invalid --sort key: `%s'", tok);
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 035b62e..9e68962 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -186,13 +186,13 @@ static inline float hist_entry__get_percent_limit(struct hist_entry *he)
static inline u64 cl_address(u64 address)
{
/* return the cacheline of the address */
- return (address & ~(cacheline_size - 1));
+ return (address & ~(cacheline_size() - 1));
}
static inline u64 cl_offset(u64 address)
{
/* return the cacheline of the address */
- return (address & (cacheline_size - 1));
+ return (address & (cacheline_size() - 1));
}
enum sort_mode {
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 3c21fd0..09d6746 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -103,6 +103,7 @@ static struct symbol *new_inline_sym(struct dso *dso,
inline_sym = symbol__new(base_sym ? base_sym->start : 0,
base_sym ? base_sym->end : 0,
base_sym ? base_sym->binding : 0,
+ base_sym ? base_sym->type : 0,
funcname);
if (inline_sym)
inline_sym->inlined = 1;
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 8f56ba4..36efb98 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -7,8 +7,7 @@
#include "xyarray.h"
#include "rblist.h"
-struct stats
-{
+struct stats {
double n, mean, M2;
u64 max, min;
};
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 2de7705..29770ea 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -114,16 +114,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym)
sym->st_shndx != SHN_ABS;
}
-static bool elf_sym__is_a(GElf_Sym *sym, enum map_type type)
+static bool elf_sym__filter(GElf_Sym *sym)
{
- switch (type) {
- case MAP__FUNCTION:
- return elf_sym__is_function(sym);
- case MAP__VARIABLE:
- return elf_sym__is_object(sym);
- default:
- return false;
- }
+ return elf_sym__is_function(sym) || elf_sym__is_object(sym);
}
static inline const char *elf_sym__name(const GElf_Sym *sym,
@@ -150,17 +143,10 @@ static inline bool elf_sec__is_data(const GElf_Shdr *shdr,
return strstr(elf_sec__name(shdr, secstrs), "data") != NULL;
}
-static bool elf_sec__is_a(GElf_Shdr *shdr, Elf_Data *secstrs,
- enum map_type type)
+static bool elf_sec__filter(GElf_Shdr *shdr, Elf_Data *secstrs)
{
- switch (type) {
- case MAP__FUNCTION:
- return elf_sec__is_text(shdr, secstrs);
- case MAP__VARIABLE:
- return elf_sec__is_data(shdr, secstrs);
- default:
- return false;
- }
+ return elf_sec__is_text(shdr, secstrs) ||
+ elf_sec__is_data(shdr, secstrs);
}
static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr)
@@ -256,7 +242,7 @@ static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name)
* And always look at the original dso, not at debuginfo packages, that
* have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS).
*/
-int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map)
+int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss)
{
uint32_t nr_rel_entries, idx;
GElf_Sym sym;
@@ -364,12 +350,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
free(demangled);
f = symbol__new(plt_offset, plt_entry_size,
- STB_GLOBAL, sympltname);
+ STB_GLOBAL, STT_FUNC, sympltname);
if (!f)
goto out_elf_end;
plt_offset += plt_entry_size;
- symbols__insert(&dso->symbols[map->type], f);
+ symbols__insert(&dso->symbols, f);
++nr;
}
} else if (shdr_rel_plt.sh_type == SHT_REL) {
@@ -390,12 +376,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
free(demangled);
f = symbol__new(plt_offset, plt_entry_size,
- STB_GLOBAL, sympltname);
+ STB_GLOBAL, STT_FUNC, sympltname);
if (!f)
goto out_elf_end;
plt_offset += plt_entry_size;
- symbols__insert(&dso->symbols[map->type], f);
+ symbols__insert(&dso->symbols, f);
++nr;
}
}
@@ -811,6 +797,110 @@ static u64 ref_reloc(struct kmap *kmap)
void __weak arch__sym_update(struct symbol *s __maybe_unused,
GElf_Sym *sym __maybe_unused) { }
+static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
+ GElf_Sym *sym, GElf_Shdr *shdr,
+ struct map_groups *kmaps, struct kmap *kmap,
+ struct dso **curr_dsop, struct map **curr_mapp,
+ const char *section_name,
+ bool adjust_kernel_syms, bool kmodule, bool *remap_kernel)
+{
+ struct dso *curr_dso = *curr_dsop;
+ struct map *curr_map;
+ char dso_name[PATH_MAX];
+
+ /* Adjust symbol to map to file offset */
+ if (adjust_kernel_syms)
+ sym->st_value -= shdr->sh_addr - shdr->sh_offset;
+
+ if (strcmp(section_name, (curr_dso->short_name + dso->short_name_len)) == 0)
+ return 0;
+
+ if (strcmp(section_name, ".text") == 0) {
+ /*
+ * The initial kernel mapping is based on
+ * kallsyms and identity maps. Overwrite it to
+ * map to the kernel dso.
+ */
+ if (*remap_kernel && dso->kernel) {
+ *remap_kernel = false;
+ map->start = shdr->sh_addr + ref_reloc(kmap);
+ map->end = map->start + shdr->sh_size;
+ map->pgoff = shdr->sh_offset;
+ map->map_ip = map__map_ip;
+ map->unmap_ip = map__unmap_ip;
+ /* Ensure maps are correctly ordered */
+ if (kmaps) {
+ map__get(map);
+ map_groups__remove(kmaps, map);
+ map_groups__insert(kmaps, map);
+ map__put(map);
+ }
+ }
+
+ /*
+ * The initial module mapping is based on
+ * /proc/modules mapped to offset zero.
+ * Overwrite it to map to the module dso.
+ */
+ if (*remap_kernel && kmodule) {
+ *remap_kernel = false;
+ map->pgoff = shdr->sh_offset;
+ }
+
+ *curr_mapp = map;
+ *curr_dsop = dso;
+ return 0;
+ }
+
+ if (!kmap)
+ return 0;
+
+ snprintf(dso_name, sizeof(dso_name), "%s%s", dso->short_name, section_name);
+
+ curr_map = map_groups__find_by_name(kmaps, dso_name);
+ if (curr_map == NULL) {
+ u64 start = sym->st_value;
+
+ if (kmodule)
+ start += map->start + shdr->sh_offset;
+
+ curr_dso = dso__new(dso_name);
+ if (curr_dso == NULL)
+ return -1;
+ curr_dso->kernel = dso->kernel;
+ curr_dso->long_name = dso->long_name;
+ curr_dso->long_name_len = dso->long_name_len;
+ curr_map = map__new2(start, curr_dso);
+ dso__put(curr_dso);
+ if (curr_map == NULL)
+ return -1;
+
+ if (adjust_kernel_syms) {
+ curr_map->start = shdr->sh_addr + ref_reloc(kmap);
+ curr_map->end = curr_map->start + shdr->sh_size;
+ curr_map->pgoff = shdr->sh_offset;
+ } else {
+ curr_map->map_ip = curr_map->unmap_ip = identity__map_ip;
+ }
+ curr_dso->symtab_type = dso->symtab_type;
+ map_groups__insert(kmaps, curr_map);
+ /*
+ * Add it before we drop the referece to curr_map, i.e. while
+ * we still are sure to have a reference to this DSO via
+ * *curr_map->dso.
+ */
+ dsos__add(&map->groups->machine->dsos, curr_dso);
+ /* kmaps already got it */
+ map__put(curr_map);
+ dso__set_loaded(curr_dso);
+ *curr_mapp = curr_map;
+ *curr_dsop = curr_dso;
+ } else
+ *curr_dsop = curr_map->dso;
+
+ return 0;
+}
+
int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
struct symsrc *runtime_ss, int kmodule)
{
@@ -844,7 +934,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
* have the wrong values for the dso maps, so remove them.
*/
if (kmodule && syms_ss->symtab)
- symbols__delete(&dso->symbols[map->type]);
+ symbols__delete(&dso->symbols);
if (!syms_ss->symtab) {
/*
@@ -921,10 +1011,10 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
dso->adjust_symbols = runtime_ss->adjust_symbols || ref_reloc(kmap);
/*
- * Initial kernel and module mappings do not map to the dso. For
- * function mappings, flag the fixups.
+ * Initial kernel and module mappings do not map to the dso.
+ * Flag the fixups.
*/
- if (map->type == MAP__FUNCTION && (dso->kernel || kmodule)) {
+ if (dso->kernel || kmodule) {
remap_kernel = true;
adjust_kernel_syms = dso->adjust_symbols;
}
@@ -936,7 +1026,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
const char *section_name;
bool used_opd = false;
- if (!is_label && !elf_sym__is_a(&sym, map->type))
+ if (!is_label && !elf_sym__filter(&sym))
continue;
/* Reject ARM ELF "mapping symbols": these aren't unique and
@@ -974,7 +1064,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
gelf_getshdr(sec, &shdr);
- if (is_label && !elf_sec__is_a(&shdr, secstrs, map->type))
+ if (is_label && !elf_sec__filter(&shdr, secstrs))
continue;
section_name = elf_sec__name(&shdr, secstrs);
@@ -982,134 +1072,37 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
/* On ARM, symbols for thumb functions have 1 added to
* the symbol address as a flag - remove it */
if ((ehdr.e_machine == EM_ARM) &&
- (map->type == MAP__FUNCTION) &&
+ (GELF_ST_TYPE(sym.st_info) == STT_FUNC) &&
(sym.st_value & 1))
--sym.st_value;
if (dso->kernel || kmodule) {
- char dso_name[PATH_MAX];
-
- /* Adjust symbol to map to file offset */
- if (adjust_kernel_syms)
- sym.st_value -= shdr.sh_addr - shdr.sh_offset;
-
- if (strcmp(section_name,
- (curr_dso->short_name +
- dso->short_name_len)) == 0)
- goto new_symbol;
-
- if (strcmp(section_name, ".text") == 0) {
- /*
- * The initial kernel mapping is based on
- * kallsyms and identity maps. Overwrite it to
- * map to the kernel dso.
- */
- if (remap_kernel && dso->kernel) {
- remap_kernel = false;
- map->start = shdr.sh_addr +
- ref_reloc(kmap);
- map->end = map->start + shdr.sh_size;
- map->pgoff = shdr.sh_offset;
- map->map_ip = map__map_ip;
- map->unmap_ip = map__unmap_ip;
- /* Ensure maps are correctly ordered */
- if (kmaps) {
- map__get(map);
- map_groups__remove(kmaps, map);
- map_groups__insert(kmaps, map);
- map__put(map);
- }
- }
-
- /*
- * The initial module mapping is based on
- * /proc/modules mapped to offset zero.
- * Overwrite it to map to the module dso.
- */
- if (remap_kernel && kmodule) {
- remap_kernel = false;
- map->pgoff = shdr.sh_offset;
- }
-
- curr_map = map;
- curr_dso = dso;
- goto new_symbol;
- }
-
- if (!kmap)
- goto new_symbol;
-
- snprintf(dso_name, sizeof(dso_name),
- "%s%s", dso->short_name, section_name);
-
- curr_map = map_groups__find_by_name(kmaps, map->type, dso_name);
- if (curr_map == NULL) {
- u64 start = sym.st_value;
-
- if (kmodule)
- start += map->start + shdr.sh_offset;
-
- curr_dso = dso__new(dso_name);
- if (curr_dso == NULL)
- goto out_elf_end;
- curr_dso->kernel = dso->kernel;
- curr_dso->long_name = dso->long_name;
- curr_dso->long_name_len = dso->long_name_len;
- curr_map = map__new2(start, curr_dso,
- map->type);
- dso__put(curr_dso);
- if (curr_map == NULL) {
- goto out_elf_end;
- }
- if (adjust_kernel_syms) {
- curr_map->start = shdr.sh_addr +
- ref_reloc(kmap);
- curr_map->end = curr_map->start +
- shdr.sh_size;
- curr_map->pgoff = shdr.sh_offset;
- } else {
- curr_map->map_ip = identity__map_ip;
- curr_map->unmap_ip = identity__map_ip;
- }
- curr_dso->symtab_type = dso->symtab_type;
- map_groups__insert(kmaps, curr_map);
- /*
- * Add it before we drop the referece to curr_map,
- * i.e. while we still are sure to have a reference
- * to this DSO via curr_map->dso.
- */
- dsos__add(&map->groups->machine->dsos, curr_dso);
- /* kmaps already got it */
- map__put(curr_map);
- dso__set_loaded(curr_dso, map->type);
- } else
- curr_dso = curr_map->dso;
-
- goto new_symbol;
- }
-
- if ((used_opd && runtime_ss->adjust_symbols)
- || (!used_opd && syms_ss->adjust_symbols)) {
+ if (dso__process_kernel_symbol(dso, map, &sym, &shdr, kmaps, kmap, &curr_dso, &curr_map,
+ section_name, adjust_kernel_syms, kmodule, &remap_kernel))
+ goto out_elf_end;
+ } else if ((used_opd && runtime_ss->adjust_symbols) ||
+ (!used_opd && syms_ss->adjust_symbols)) {
pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
"sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__,
(u64)sym.st_value, (u64)shdr.sh_addr,
(u64)shdr.sh_offset);
sym.st_value -= shdr.sh_addr - shdr.sh_offset;
}
-new_symbol:
+
demangled = demangle_sym(dso, kmodule, elf_name);
if (demangled != NULL)
elf_name = demangled;
f = symbol__new(sym.st_value, sym.st_size,
- GELF_ST_BIND(sym.st_info), elf_name);
+ GELF_ST_BIND(sym.st_info),
+ GELF_ST_TYPE(sym.st_info), elf_name);
free(demangled);
if (!f)
goto out_elf_end;
arch__sym_update(f, &sym);
- __symbols__insert(&curr_dso->symbols[curr_map->type], f, dso->kernel);
+ __symbols__insert(&curr_dso->symbols, f, dso->kernel);
nr++;
}
@@ -1117,14 +1110,14 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
* For misannotated, zeroed, ASM function sizes.
*/
if (nr > 0) {
- symbols__fixup_end(&dso->symbols[map->type]);
- symbols__fixup_duplicate(&dso->symbols[map->type]);
+ symbols__fixup_end(&dso->symbols);
+ symbols__fixup_duplicate(&dso->symbols);
if (kmap) {
/*
* We need to fixup this here too because we create new
* maps here, for things like vsyscall sections.
*/
- __map_groups__fixup_end(kmaps, map->type);
+ map_groups__fixup_end(kmaps);
}
}
err = nr;
@@ -1393,8 +1386,16 @@ static off_t kcore__write(struct kcore *kcore)
struct phdr_data {
off_t offset;
+ off_t rel;
u64 addr;
u64 len;
+ struct list_head node;
+ struct phdr_data *remaps;
+};
+
+struct sym_data {
+ u64 addr;
+ struct list_head node;
};
struct kcore_copy_info {
@@ -1404,16 +1405,78 @@ struct kcore_copy_info {
u64 last_symbol;
u64 first_module;
u64 last_module_symbol;
- struct phdr_data kernel_map;
- struct phdr_data modules_map;
+ size_t phnum;
+ struct list_head phdrs;
+ struct list_head syms;
};
+#define kcore_copy__for_each_phdr(k, p) \
+ list_for_each_entry((p), &(k)->phdrs, node)
+
+static struct phdr_data *phdr_data__new(u64 addr, u64 len, off_t offset)
+{
+ struct phdr_data *p = zalloc(sizeof(*p));
+
+ if (p) {
+ p->addr = addr;
+ p->len = len;
+ p->offset = offset;
+ }
+
+ return p;
+}
+
+static struct phdr_data *kcore_copy_info__addnew(struct kcore_copy_info *kci,
+ u64 addr, u64 len,
+ off_t offset)
+{
+ struct phdr_data *p = phdr_data__new(addr, len, offset);
+
+ if (p)
+ list_add_tail(&p->node, &kci->phdrs);
+
+ return p;
+}
+
+static void kcore_copy__free_phdrs(struct kcore_copy_info *kci)
+{
+ struct phdr_data *p, *tmp;
+
+ list_for_each_entry_safe(p, tmp, &kci->phdrs, node) {
+ list_del(&p->node);
+ free(p);
+ }
+}
+
+static struct sym_data *kcore_copy__new_sym(struct kcore_copy_info *kci,
+ u64 addr)
+{
+ struct sym_data *s = zalloc(sizeof(*s));
+
+ if (s) {
+ s->addr = addr;
+ list_add_tail(&s->node, &kci->syms);
+ }
+
+ return s;
+}
+
+static void kcore_copy__free_syms(struct kcore_copy_info *kci)
+{
+ struct sym_data *s, *tmp;
+
+ list_for_each_entry_safe(s, tmp, &kci->syms, node) {
+ list_del(&s->node);
+ free(s);
+ }
+}
+
static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
u64 start)
{
struct kcore_copy_info *kci = arg;
- if (!symbol_type__is_a(type, MAP__FUNCTION))
+ if (!kallsyms__is_function(type))
return 0;
if (strchr(name, '[')) {
@@ -1438,6 +1501,9 @@ static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
return 0;
}
+ if (is_entry_trampoline(name) && !kcore_copy__new_sym(kci, start))
+ return -1;
+
return 0;
}
@@ -1487,27 +1553,39 @@ static int kcore_copy__parse_modules(struct kcore_copy_info *kci,
return 0;
}
-static void kcore_copy__map(struct phdr_data *p, u64 start, u64 end, u64 pgoff,
- u64 s, u64 e)
+static int kcore_copy__map(struct kcore_copy_info *kci, u64 start, u64 end,
+ u64 pgoff, u64 s, u64 e)
{
- if (p->addr || s < start || s >= end)
- return;
+ u64 len, offset;
- p->addr = s;
- p->offset = (s - start) + pgoff;
- p->len = e < end ? e - s : end - s;
+ if (s < start || s >= end)
+ return 0;
+
+ offset = (s - start) + pgoff;
+ len = e < end ? e - s : end - s;
+
+ return kcore_copy_info__addnew(kci, s, len, offset) ? 0 : -1;
}
static int kcore_copy__read_map(u64 start, u64 len, u64 pgoff, void *data)
{
struct kcore_copy_info *kci = data;
u64 end = start + len;
+ struct sym_data *sdat;
- kcore_copy__map(&kci->kernel_map, start, end, pgoff, kci->stext,
- kci->etext);
+ if (kcore_copy__map(kci, start, end, pgoff, kci->stext, kci->etext))
+ return -1;
- kcore_copy__map(&kci->modules_map, start, end, pgoff, kci->first_module,
- kci->last_module_symbol);
+ if (kcore_copy__map(kci, start, end, pgoff, kci->first_module,
+ kci->last_module_symbol))
+ return -1;
+
+ list_for_each_entry(sdat, &kci->syms, node) {
+ u64 s = round_down(sdat->addr, page_size);
+
+ if (kcore_copy__map(kci, start, end, pgoff, s, s + len))
+ return -1;
+ }
return 0;
}
@@ -1520,6 +1598,64 @@ static int kcore_copy__read_maps(struct kcore_copy_info *kci, Elf *elf)
return 0;
}
+static void kcore_copy__find_remaps(struct kcore_copy_info *kci)
+{
+ struct phdr_data *p, *k = NULL;
+ u64 kend;
+
+ if (!kci->stext)
+ return;
+
+ /* Find phdr that corresponds to the kernel map (contains stext) */
+ kcore_copy__for_each_phdr(kci, p) {
+ u64 pend = p->addr + p->len - 1;
+
+ if (p->addr <= kci->stext && pend >= kci->stext) {
+ k = p;
+ break;
+ }
+ }
+
+ if (!k)
+ return;
+
+ kend = k->offset + k->len;
+
+ /* Find phdrs that remap the kernel */
+ kcore_copy__for_each_phdr(kci, p) {
+ u64 pend = p->offset + p->len;
+
+ if (p == k)
+ continue;
+
+ if (p->offset >= k->offset && pend <= kend)
+ p->remaps = k;
+ }
+}
+
+static void kcore_copy__layout(struct kcore_copy_info *kci)
+{
+ struct phdr_data *p;
+ off_t rel = 0;
+
+ kcore_copy__find_remaps(kci);
+
+ kcore_copy__for_each_phdr(kci, p) {
+ if (!p->remaps) {
+ p->rel = rel;
+ rel += p->len;
+ }
+ kci->phnum += 1;
+ }
+
+ kcore_copy__for_each_phdr(kci, p) {
+ struct phdr_data *k = p->remaps;
+
+ if (k)
+ p->rel = p->offset - k->offset + k->rel;
+ }
+}
+
static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,
Elf *elf)
{
@@ -1555,7 +1691,12 @@ static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,
if (kci->first_module && !kci->last_module_symbol)
return -1;
- return kcore_copy__read_maps(kci, elf);
+ if (kcore_copy__read_maps(kci, elf))
+ return -1;
+
+ kcore_copy__layout(kci);
+
+ return 0;
}
static int kcore_copy__copy_file(const char *from_dir, const char *to_dir,
@@ -1678,12 +1819,15 @@ int kcore_copy(const char *from_dir, const char *to_dir)
{
struct kcore kcore;
struct kcore extract;
- size_t count = 2;
int idx = 0, err = -1;
- off_t offset = page_size, sz, modules_offset = 0;
+ off_t offset, sz;
struct kcore_copy_info kci = { .stext = 0, };
char kcore_filename[PATH_MAX];
char extract_filename[PATH_MAX];
+ struct phdr_data *p;
+
+ INIT_LIST_HEAD(&kci.phdrs);
+ INIT_LIST_HEAD(&kci.syms);
if (kcore_copy__copy_file(from_dir, to_dir, "kallsyms"))
return -1;
@@ -1703,20 +1847,17 @@ int kcore_copy(const char *from_dir, const char *to_dir)
if (kcore__init(&extract, extract_filename, kcore.elfclass, false))
goto out_kcore_close;
- if (!kci.modules_map.addr)
- count -= 1;
-
- if (kcore__copy_hdr(&kcore, &extract, count))
+ if (kcore__copy_hdr(&kcore, &extract, kci.phnum))
goto out_extract_close;
- if (kcore__add_phdr(&extract, idx++, offset, kci.kernel_map.addr,
- kci.kernel_map.len))
- goto out_extract_close;
+ offset = gelf_fsize(extract.elf, ELF_T_EHDR, 1, EV_CURRENT) +
+ gelf_fsize(extract.elf, ELF_T_PHDR, kci.phnum, EV_CURRENT);
+ offset = round_up(offset, page_size);
- if (kci.modules_map.addr) {
- modules_offset = offset + kci.kernel_map.len;
- if (kcore__add_phdr(&extract, idx, modules_offset,
- kci.modules_map.addr, kci.modules_map.len))
+ kcore_copy__for_each_phdr(&kci, p) {
+ off_t offs = p->rel + offset;
+
+ if (kcore__add_phdr(&extract, idx++, offs, p->addr, p->len))
goto out_extract_close;
}
@@ -1724,14 +1865,14 @@ int kcore_copy(const char *from_dir, const char *to_dir)
if (sz < 0 || sz > offset)
goto out_extract_close;
- if (copy_bytes(kcore.fd, kci.kernel_map.offset, extract.fd, offset,
- kci.kernel_map.len))
- goto out_extract_close;
+ kcore_copy__for_each_phdr(&kci, p) {
+ off_t offs = p->rel + offset;
- if (modules_offset && copy_bytes(kcore.fd, kci.modules_map.offset,
- extract.fd, modules_offset,
- kci.modules_map.len))
- goto out_extract_close;
+ if (p->remaps)
+ continue;
+ if (copy_bytes(kcore.fd, p->offset, extract.fd, offs, p->len))
+ goto out_extract_close;
+ }
if (kcore_copy__compare_file(from_dir, to_dir, "modules"))
goto out_extract_close;
@@ -1754,6 +1895,9 @@ int kcore_copy(const char *from_dir, const char *to_dir)
if (err)
kcore_copy__unlink(to_dir, "kallsyms");
+ kcore_copy__free_phdrs(&kci);
+ kcore_copy__free_syms(&kci);
+
return err;
}
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index ff48d0d4..7119df7 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -288,8 +288,7 @@ void symsrc__destroy(struct symsrc *ss)
}
int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused,
- struct symsrc *ss __maybe_unused,
- struct map *map __maybe_unused)
+ struct symsrc *ss __maybe_unused)
{
return 0;
}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 62b2dd22..8c84437 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -5,6 +5,7 @@
#include <stdio.h>
#include <string.h>
#include <linux/kernel.h>
+#include <linux/mman.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/param.h>
@@ -70,18 +71,10 @@ static enum dso_binary_type binary_type_symtab[] = {
#define DSO_BINARY_TYPE__SYMTAB_CNT ARRAY_SIZE(binary_type_symtab)
-bool symbol_type__is_a(char symbol_type, enum map_type map_type)
+static bool symbol_type__filter(char symbol_type)
{
symbol_type = toupper(symbol_type);
-
- switch (map_type) {
- case MAP__FUNCTION:
- return symbol_type == 'T' || symbol_type == 'W';
- case MAP__VARIABLE:
- return symbol_type == 'D';
- default:
- return false;
- }
+ return symbol_type == 'T' || symbol_type == 'W' || symbol_type == 'D';
}
static int prefix_underscores_count(const char *str)
@@ -228,9 +221,9 @@ void symbols__fixup_end(struct rb_root *symbols)
curr->end = roundup(curr->start, 4096) + 4096;
}
-void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
+void map_groups__fixup_end(struct map_groups *mg)
{
- struct maps *maps = &mg->maps[type];
+ struct maps *maps = &mg->maps;
struct map *next, *curr;
down_write(&maps->lock);
@@ -256,7 +249,7 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
up_write(&maps->lock);
}
-struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
+struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char *name)
{
size_t namelen = strlen(name) + 1;
struct symbol *sym = calloc(1, (symbol_conf.priv_size +
@@ -274,6 +267,7 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
sym->start = start;
sym->end = len ? start + len : start;
+ sym->type = type;
sym->binding = binding;
sym->namelen = namelen - 1;
@@ -484,45 +478,40 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
void dso__reset_find_symbol_cache(struct dso *dso)
{
- enum map_type type;
-
- for (type = MAP__FUNCTION; type <= MAP__VARIABLE; ++type) {
- dso->last_find_result[type].addr = 0;
- dso->last_find_result[type].symbol = NULL;
- }
+ dso->last_find_result.addr = 0;
+ dso->last_find_result.symbol = NULL;
}
-void dso__insert_symbol(struct dso *dso, enum map_type type, struct symbol *sym)
+void dso__insert_symbol(struct dso *dso, struct symbol *sym)
{
- __symbols__insert(&dso->symbols[type], sym, dso->kernel);
+ __symbols__insert(&dso->symbols, sym, dso->kernel);
/* update the symbol cache if necessary */
- if (dso->last_find_result[type].addr >= sym->start &&
- (dso->last_find_result[type].addr < sym->end ||
+ if (dso->last_find_result.addr >= sym->start &&
+ (dso->last_find_result.addr < sym->end ||
sym->start == sym->end)) {
- dso->last_find_result[type].symbol = sym;
+ dso->last_find_result.symbol = sym;
}
}
-struct symbol *dso__find_symbol(struct dso *dso,
- enum map_type type, u64 addr)
+struct symbol *dso__find_symbol(struct dso *dso, u64 addr)
{
- if (dso->last_find_result[type].addr != addr || dso->last_find_result[type].symbol == NULL) {
- dso->last_find_result[type].addr = addr;
- dso->last_find_result[type].symbol = symbols__find(&dso->symbols[type], addr);
+ if (dso->last_find_result.addr != addr || dso->last_find_result.symbol == NULL) {
+ dso->last_find_result.addr = addr;
+ dso->last_find_result.symbol = symbols__find(&dso->symbols, addr);
}
- return dso->last_find_result[type].symbol;
+ return dso->last_find_result.symbol;
}
-struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
+struct symbol *dso__first_symbol(struct dso *dso)
{
- return symbols__first(&dso->symbols[type]);
+ return symbols__first(&dso->symbols);
}
-struct symbol *dso__last_symbol(struct dso *dso, enum map_type type)
+struct symbol *dso__last_symbol(struct dso *dso)
{
- return symbols__last(&dso->symbols[type]);
+ return symbols__last(&dso->symbols);
}
struct symbol *dso__next_symbol(struct symbol *sym)
@@ -539,24 +528,22 @@ struct symbol *symbol__next_by_name(struct symbol *sym)
}
/*
- * Teturns first symbol that matched with @name.
+ * Returns first symbol that matched with @name.
*/
-struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
- const char *name)
+struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name)
{
- struct symbol *s = symbols__find_by_name(&dso->symbol_names[type], name,
+ struct symbol *s = symbols__find_by_name(&dso->symbol_names, name,
SYMBOL_TAG_INCLUDE__NONE);
if (!s)
- s = symbols__find_by_name(&dso->symbol_names[type], name,
+ s = symbols__find_by_name(&dso->symbol_names, name,
SYMBOL_TAG_INCLUDE__DEFAULT_ONLY);
return s;
}
-void dso__sort_by_name(struct dso *dso, enum map_type type)
+void dso__sort_by_name(struct dso *dso)
{
- dso__set_sorted_by_name(dso, type);
- return symbols__sort_by_name(&dso->symbol_names[type],
- &dso->symbols[type]);
+ dso__set_sorted_by_name(dso);
+ return symbols__sort_by_name(&dso->symbol_names, &dso->symbols);
}
int modules__parse(const char *filename, void *arg,
@@ -621,11 +608,6 @@ int modules__parse(const char *filename, void *arg,
return err;
}
-struct process_kallsyms_args {
- struct map *map;
- struct dso *dso;
-};
-
/*
* These are symbols in the kernel image, so make sure that
* sym is from a kernel DSO.
@@ -661,10 +643,10 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
char type, u64 start)
{
struct symbol *sym;
- struct process_kallsyms_args *a = arg;
- struct rb_root *root = &a->dso->symbols[a->map->type];
+ struct dso *dso = arg;
+ struct rb_root *root = &dso->symbols;
- if (!symbol_type__is_a(type, a->map->type))
+ if (!symbol_type__filter(type))
return 0;
/*
@@ -672,7 +654,7 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
* symbols, setting length to 0, and rely on
* symbols__fixup_end() to fix it up.
*/
- sym = symbol__new(start, 0, kallsyms2elf_binding(type), name);
+ sym = symbol__new(start, 0, kallsyms2elf_binding(type), kallsyms2elf_type(type), name);
if (sym == NULL)
return -ENOMEM;
/*
@@ -689,21 +671,18 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
* so that we can in the next step set the symbol ->end address and then
* call kernel_maps__split_kallsyms.
*/
-static int dso__load_all_kallsyms(struct dso *dso, const char *filename,
- struct map *map)
+static int dso__load_all_kallsyms(struct dso *dso, const char *filename)
{
- struct process_kallsyms_args args = { .map = map, .dso = dso, };
- return kallsyms__parse(filename, &args, map__process_kallsym_symbol);
+ return kallsyms__parse(filename, dso, map__process_kallsym_symbol);
}
-static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map)
+static int map_groups__split_kallsyms_for_kcore(struct map_groups *kmaps, struct dso *dso)
{
- struct map_groups *kmaps = map__kmaps(map);
struct map *curr_map;
struct symbol *pos;
int count = 0;
- struct rb_root old_root = dso->symbols[map->type];
- struct rb_root *root = &dso->symbols[map->type];
+ struct rb_root old_root = dso->symbols;
+ struct rb_root *root = &dso->symbols;
struct rb_node *next = rb_first(root);
if (!kmaps)
@@ -723,7 +702,7 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map)
if (module)
*module = '\0';
- curr_map = map_groups__find(kmaps, map->type, pos->start);
+ curr_map = map_groups__find(kmaps, pos->start);
if (!curr_map) {
symbol__delete(pos);
@@ -733,7 +712,7 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map)
pos->start -= curr_map->start - curr_map->pgoff;
if (pos->end)
pos->end -= curr_map->start - curr_map->pgoff;
- symbols__insert(&curr_map->dso->symbols[curr_map->type], pos);
+ symbols__insert(&curr_map->dso->symbols, pos);
++count;
}
@@ -748,22 +727,25 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map)
* kernel range is broken in several maps, named [kernel].N, as we don't have
* the original ELF section names vmlinux have.
*/
-static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
+static int map_groups__split_kallsyms(struct map_groups *kmaps, struct dso *dso, u64 delta,
+ struct map *initial_map)
{
- struct map_groups *kmaps = map__kmaps(map);
struct machine *machine;
- struct map *curr_map = map;
+ struct map *curr_map = initial_map;
struct symbol *pos;
int count = 0, moved = 0;
- struct rb_root *root = &dso->symbols[map->type];
+ struct rb_root *root = &dso->symbols;
struct rb_node *next = rb_first(root);
int kernel_range = 0;
+ bool x86_64;
if (!kmaps)
return -1;
machine = kmaps->machine;
+ x86_64 = machine__is(machine, "x86_64");
+
while (next) {
char *module;
@@ -778,7 +760,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
*module++ = '\0';
if (strcmp(curr_map->dso->short_name, module)) {
- if (curr_map != map &&
+ if (curr_map != initial_map &&
dso->kernel == DSO_TYPE_GUEST_KERNEL &&
machine__is_default_guest(machine)) {
/*
@@ -788,18 +770,16 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
* symbols are in its kmap. Mark it as
* loaded.
*/
- dso__set_loaded(curr_map->dso,
- curr_map->type);
+ dso__set_loaded(curr_map->dso);
}
- curr_map = map_groups__find_by_name(kmaps,
- map->type, module);
+ curr_map = map_groups__find_by_name(kmaps, module);
if (curr_map == NULL) {
pr_debug("%s/proc/{kallsyms,modules} "
"inconsistency while looking "
"for \"%s\" module!\n",
machine->root_dir, module);
- curr_map = map;
+ curr_map = initial_map;
goto discard_symbol;
}
@@ -809,11 +789,21 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
}
/*
* So that we look just like we get from .ko files,
- * i.e. not prelinked, relative to map->start.
+ * i.e. not prelinked, relative to initial_map->start.
*/
pos->start = curr_map->map_ip(curr_map, pos->start);
pos->end = curr_map->map_ip(curr_map, pos->end);
- } else if (curr_map != map) {
+ } else if (x86_64 && is_entry_trampoline(pos->name)) {
+ /*
+ * These symbols are not needed anymore since the
+ * trampoline maps refer to the text section and it's
+ * symbols instead. Avoid having to deal with
+ * relocations, and the assumption that the first symbol
+ * is the start of kernel text, by simply removing the
+ * symbols at this point.
+ */
+ goto discard_symbol;
+ } else if (curr_map != initial_map) {
char dso_name[PATH_MAX];
struct dso *ndso;
@@ -824,7 +814,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
}
if (count == 0) {
- curr_map = map;
+ curr_map = initial_map;
goto add_symbol;
}
@@ -843,7 +833,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
ndso->kernel = dso->kernel;
- curr_map = map__new2(pos->start, ndso, map->type);
+ curr_map = map__new2(pos->start, ndso);
if (curr_map == NULL) {
dso__put(ndso);
return -1;
@@ -858,9 +848,9 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
pos->end -= delta;
}
add_symbol:
- if (curr_map != map) {
+ if (curr_map != initial_map) {
rb_erase(&pos->rb_node, root);
- symbols__insert(&curr_map->dso->symbols[curr_map->type], pos);
+ symbols__insert(&curr_map->dso->symbols, pos);
++moved;
} else
++count;
@@ -871,10 +861,10 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
symbol__delete(pos);
}
- if (curr_map != map &&
+ if (curr_map != initial_map &&
dso->kernel == DSO_TYPE_GUEST_KERNEL &&
machine__is_default_guest(kmaps->machine)) {
- dso__set_loaded(curr_map->dso, curr_map->type);
+ dso__set_loaded(curr_map->dso);
}
return count + moved;
@@ -1035,7 +1025,12 @@ int compare_proc_modules(const char *from, const char *to)
return ret;
}
-static int do_validate_kcore_modules(const char *filename, struct map *map,
+struct map *map_groups__first(struct map_groups *mg)
+{
+ return maps__first(&mg->maps);
+}
+
+static int do_validate_kcore_modules(const char *filename,
struct map_groups *kmaps)
{
struct rb_root modules = RB_ROOT;
@@ -1046,13 +1041,12 @@ static int do_validate_kcore_modules(const char *filename, struct map *map,
if (err)
return err;
- old_map = map_groups__first(kmaps, map->type);
+ old_map = map_groups__first(kmaps);
while (old_map) {
struct map *next = map_groups__next(old_map);
struct module_info *mi;
- if (old_map == map || old_map->start == map->start) {
- /* The kernel map */
+ if (!__map__is_kmodule(old_map)) {
old_map = next;
continue;
}
@@ -1109,7 +1103,7 @@ static int validate_kcore_modules(const char *kallsyms_filename,
kallsyms_filename))
return -EINVAL;
- if (do_validate_kcore_modules(modules_filename, map, kmaps))
+ if (do_validate_kcore_modules(modules_filename, kmaps))
return -EINVAL;
return 0;
@@ -1138,7 +1132,6 @@ static int validate_kcore_addresses(const char *kallsyms_filename,
struct kcore_mapfn_data {
struct dso *dso;
- enum map_type type;
struct list_head maps;
};
@@ -1147,7 +1140,7 @@ static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data)
struct kcore_mapfn_data *md = data;
struct map *map;
- map = map__new2(start, md->dso, md->type);
+ map = map__new2(start, md->dso);
if (map == NULL)
return -ENOMEM;
@@ -1163,13 +1156,13 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
const char *kallsyms_filename)
{
struct map_groups *kmaps = map__kmaps(map);
- struct machine *machine;
struct kcore_mapfn_data md;
struct map *old_map, *new_map, *replacement_map = NULL;
+ struct machine *machine;
bool is_64_bit;
int err, fd;
char kcore_filename[PATH_MAX];
- struct symbol *sym;
+ u64 stext;
if (!kmaps)
return -EINVAL;
@@ -1177,7 +1170,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
machine = kmaps->machine;
/* This function requires that the map is the kernel map */
- if (map != machine->vmlinux_maps[map->type])
+ if (!__map__is_kernel(map))
return -EINVAL;
if (!filename_from_kallsyms_filename(kcore_filename, "kcore",
@@ -1189,7 +1182,6 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
return -EINVAL;
md.dso = dso;
- md.type = map->type;
INIT_LIST_HEAD(&md.maps);
fd = open(kcore_filename, O_RDONLY);
@@ -1200,7 +1192,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
}
/* Read new maps into temporary lists */
- err = file__read_maps(fd, md.type == MAP__FUNCTION, kcore_mapfn, &md,
+ err = file__read_maps(fd, map->prot & PROT_EXEC, kcore_mapfn, &md,
&is_64_bit);
if (err)
goto out_err;
@@ -1212,7 +1204,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
}
/* Remove old maps */
- old_map = map_groups__first(kmaps, map->type);
+ old_map = map_groups__first(kmaps);
while (old_map) {
struct map *next = map_groups__next(old_map);
@@ -1220,14 +1212,15 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
map_groups__remove(kmaps, old_map);
old_map = next;
}
+ machine->trampolines_mapped = false;
- /* Find the kernel map using the first symbol */
- sym = dso__first_symbol(dso, map->type);
- list_for_each_entry(new_map, &md.maps, node) {
- if (sym && sym->start >= new_map->start &&
- sym->start < new_map->end) {
- replacement_map = new_map;
- break;
+ /* Find the kernel map using the '_stext' symbol */
+ if (!kallsyms__get_function_start(kallsyms_filename, "_stext", &stext)) {
+ list_for_each_entry(new_map, &md.maps, node) {
+ if (stext >= new_map->start && stext < new_map->end) {
+ replacement_map = new_map;
+ break;
+ }
}
}
@@ -1256,6 +1249,19 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
map__put(new_map);
}
+ if (machine__is(machine, "x86_64")) {
+ u64 addr;
+
+ /*
+ * If one of the corresponding symbols is there, assume the
+ * entry trampoline maps are too.
+ */
+ if (!kallsyms__get_function_start(kallsyms_filename,
+ ENTRY_TRAMPOLINE_NAME,
+ &addr))
+ machine->trampolines_mapped = true;
+ }
+
/*
* Set the data type and long name so that kcore can be read via
* dso__data_read_addr().
@@ -1268,7 +1274,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
close(fd);
- if (map->type == MAP__FUNCTION)
+ if (map->prot & PROT_EXEC)
pr_debug("Using %s for kernel object code\n", kcore_filename);
else
pr_debug("Using %s for kernel data\n", kcore_filename);
@@ -1289,14 +1295,10 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
* If the kernel is relocated at boot time, kallsyms won't match. Compute the
* delta based on the relocation reference symbol.
*/
-static int kallsyms__delta(struct map *map, const char *filename, u64 *delta)
+static int kallsyms__delta(struct kmap *kmap, const char *filename, u64 *delta)
{
- struct kmap *kmap = map__kmap(map);
u64 addr;
- if (!kmap)
- return -1;
-
if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->name)
return 0;
@@ -1310,19 +1312,23 @@ static int kallsyms__delta(struct map *map, const char *filename, u64 *delta)
int __dso__load_kallsyms(struct dso *dso, const char *filename,
struct map *map, bool no_kcore)
{
+ struct kmap *kmap = map__kmap(map);
u64 delta = 0;
if (symbol__restricted_filename(filename, "/proc/kallsyms"))
return -1;
- if (dso__load_all_kallsyms(dso, filename, map) < 0)
+ if (!kmap || !kmap->kmaps)
return -1;
- if (kallsyms__delta(map, filename, &delta))
+ if (dso__load_all_kallsyms(dso, filename) < 0)
return -1;
- symbols__fixup_end(&dso->symbols[map->type]);
- symbols__fixup_duplicate(&dso->symbols[map->type]);
+ if (kallsyms__delta(kmap, filename, &delta))
+ return -1;
+
+ symbols__fixup_end(&dso->symbols);
+ symbols__fixup_duplicate(&dso->symbols);
if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
@@ -1330,9 +1336,9 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename,
dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS;
if (!no_kcore && !dso__load_kcore(dso, map, filename))
- return dso__split_kallsyms_for_kcore(dso, map);
+ return map_groups__split_kallsyms_for_kcore(kmap->kmaps, dso);
else
- return dso__split_kallsyms(dso, map, delta);
+ return map_groups__split_kallsyms(kmap->kmaps, dso, delta, map);
}
int dso__load_kallsyms(struct dso *dso, const char *filename,
@@ -1341,8 +1347,7 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
return __dso__load_kallsyms(dso, filename, map, false);
}
-static int dso__load_perf_map(const char *map_path, struct dso *dso,
- struct map *map)
+static int dso__load_perf_map(const char *map_path, struct dso *dso)
{
char *line = NULL;
size_t n;
@@ -1379,12 +1384,12 @@ static int dso__load_perf_map(const char *map_path, struct dso *dso,
if (len + 2 >= line_len)
continue;
- sym = symbol__new(start, size, STB_GLOBAL, line + len);
+ sym = symbol__new(start, size, STB_GLOBAL, STT_FUNC, line + len);
if (sym == NULL)
goto out_delete_line;
- symbols__insert(&dso->symbols[map->type], sym);
+ symbols__insert(&dso->symbols, sym);
nr_syms++;
}
@@ -1509,25 +1514,27 @@ int dso__load(struct dso *dso, struct map *map)
pthread_mutex_lock(&dso->lock);
/* check again under the dso->lock */
- if (dso__loaded(dso, map->type)) {
+ if (dso__loaded(dso)) {
ret = 1;
goto out;
}
- if (dso->kernel) {
- if (dso->kernel == DSO_TYPE_KERNEL)
- ret = dso__load_kernel_sym(dso, map);
- else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
- ret = dso__load_guest_kernel_sym(dso, map);
-
- goto out;
- }
-
if (map->groups && map->groups->machine)
machine = map->groups->machine;
else
machine = NULL;
+ if (dso->kernel) {
+ if (dso->kernel == DSO_TYPE_KERNEL)
+ ret = dso__load_kernel_sym(dso, map);
+ else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+ ret = dso__load_guest_kernel_sym(dso, map);
+
+ if (machine__is(machine, "x86_64"))
+ machine__map_x86_64_entry_trampolines(machine, dso);
+ goto out;
+ }
+
dso->adjust_symbols = 0;
if (perfmap) {
@@ -1542,7 +1549,7 @@ int dso__load(struct dso *dso, struct map *map)
goto out;
}
- ret = dso__load_perf_map(map_path, dso, map);
+ ret = dso__load_perf_map(map_path, dso);
dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
DSO_BINARY_TYPE__NOT_FOUND;
goto out;
@@ -1651,7 +1658,7 @@ int dso__load(struct dso *dso, struct map *map)
if (ret > 0) {
int nr_plt;
- nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss, map);
+ nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss);
if (nr_plt > 0)
ret += nr_plt;
}
@@ -1663,17 +1670,16 @@ int dso__load(struct dso *dso, struct map *map)
if (ret < 0 && strstr(dso->name, " (deleted)") != NULL)
ret = 0;
out:
- dso__set_loaded(dso, map->type);
+ dso__set_loaded(dso);
pthread_mutex_unlock(&dso->lock);
nsinfo__mountns_exit(&nsc);
return ret;
}
-struct map *map_groups__find_by_name(struct map_groups *mg,
- enum map_type type, const char *name)
+struct map *map_groups__find_by_name(struct map_groups *mg, const char *name)
{
- struct maps *maps = &mg->maps[type];
+ struct maps *maps = &mg->maps;
struct map *map;
down_read(&maps->lock);
@@ -1720,7 +1726,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
else
dso->binary_type = DSO_BINARY_TYPE__VMLINUX;
dso__set_long_name(dso, vmlinux, vmlinux_allocated);
- dso__set_loaded(dso, map->type);
+ dso__set_loaded(dso);
pr_debug("Using %s for symbols\n", symfs_vmlinux);
}
@@ -2091,16 +2097,14 @@ static bool symbol__read_kptr_restrict(void)
int symbol__annotation_init(void)
{
+ if (symbol_conf.init_annotation)
+ return 0;
+
if (symbol_conf.initialized) {
pr_err("Annotation needs to be init before symbol__init()\n");
return -1;
}
- if (symbol_conf.init_annotation) {
- pr_warning("Annotation being initialized multiple times\n");
- return 0;
- }
-
symbol_conf.priv_size += sizeof(struct annotation);
symbol_conf.init_annotation = true;
return 0;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 70c16741..1a16438 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -57,7 +57,8 @@ struct symbol {
u64 start;
u64 end;
u16 namelen;
- u8 binding;
+ u8 type:4;
+ u8 binding:4;
u8 idle:1;
u8 ignore:1;
u8 inlined:1;
@@ -259,17 +260,16 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
bool no_kcore);
int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map);
-void dso__insert_symbol(struct dso *dso, enum map_type type,
+void dso__insert_symbol(struct dso *dso,
struct symbol *sym);
-struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
- u64 addr);
-struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
- const char *name);
+struct symbol *dso__find_symbol(struct dso *dso, u64 addr);
+struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name);
+
struct symbol *symbol__next_by_name(struct symbol *sym);
-struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
-struct symbol *dso__last_symbol(struct dso *dso, enum map_type type);
+struct symbol *dso__first_symbol(struct dso *dso);
+struct symbol *dso__last_symbol(struct dso *dso);
struct symbol *dso__next_symbol(struct symbol *sym);
enum dso_type dso__type_fd(int fd);
@@ -288,7 +288,7 @@ void symbol__exit(void);
void symbol__elf_init(void);
int symbol__annotation_init(void);
-struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name);
+struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char *name);
size_t __symbol__fprintf_symname_offs(const struct symbol *sym,
const struct addr_location *al,
bool unknown_as_addr,
@@ -300,7 +300,6 @@ size_t __symbol__fprintf_symname(const struct symbol *sym,
bool unknown_as_addr, FILE *fp);
size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp);
size_t symbol__fprintf(struct symbol *sym, FILE *fp);
-bool symbol_type__is_a(char symbol_type, enum map_type map_type);
bool symbol__restricted_filename(const char *filename,
const char *restricted_filename);
int symbol__config_symfs(const struct option *opt __maybe_unused,
@@ -308,8 +307,7 @@ int symbol__config_symfs(const struct option *opt __maybe_unused,
int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
struct symsrc *runtime_ss, int kmodule);
-int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss,
- struct map *map);
+int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss);
char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name);
@@ -317,7 +315,7 @@ void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel)
void symbols__insert(struct rb_root *symbols, struct symbol *sym);
void symbols__fixup_duplicate(struct rb_root *symbols);
void symbols__fixup_end(struct rb_root *symbols);
-void __map_groups__fixup_end(struct map_groups *mg, enum map_type type);
+void map_groups__fixup_end(struct map_groups *mg);
typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);
int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data,
diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c
index 6dd2cb8..ed0205c 100644
--- a/tools/perf/util/symbol_fprintf.c
+++ b/tools/perf/util/symbol_fprintf.c
@@ -58,13 +58,13 @@ size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp)
}
size_t dso__fprintf_symbols_by_name(struct dso *dso,
- enum map_type type, FILE *fp)
+ FILE *fp)
{
size_t ret = 0;
struct rb_node *nd;
struct symbol_name_rb_node *pos;
- for (nd = rb_first(&dso->symbol_names[type]); nd; nd = rb_next(nd)) {
+ for (nd = rb_first(&dso->symbol_names); nd; nd = rb_next(nd)) {
pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
fprintf(fp, "%s\n", pos->sym.name);
}
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index 895122d..0ee7f56 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -17,7 +17,7 @@
#include <stdlib.h>
#include <linux/compiler.h>
-#ifdef HAVE_SYSCALL_TABLE
+#ifdef HAVE_SYSCALL_TABLE_SUPPORT
#include <string.h>
#include "string2.h"
#include "util.h"
@@ -139,7 +139,7 @@ int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_g
return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx);
}
-#else /* HAVE_SYSCALL_TABLE */
+#else /* HAVE_SYSCALL_TABLE_SUPPORT */
#include <libaudit.h>
@@ -176,4 +176,4 @@ int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_g
{
return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx);
}
-#endif /* HAVE_SYSCALL_TABLE */
+#endif /* HAVE_SYSCALL_TABLE_SUPPORT */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 68b65b1..2048d39 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -302,23 +302,20 @@ int thread__insert_map(struct thread *thread, struct map *map)
static int __thread__prepare_access(struct thread *thread)
{
bool initialized = false;
- int i, err = 0;
+ int err = 0;
+ struct maps *maps = &thread->mg->maps;
+ struct map *map;
- for (i = 0; i < MAP__NR_TYPES; ++i) {
- struct maps *maps = &thread->mg->maps[i];
- struct map *map;
+ down_read(&maps->lock);
- down_read(&maps->lock);
-
- for (map = maps__first(maps); map; map = map__next(map)) {
- err = unwind__prepare_access(thread, map, &initialized);
- if (err || initialized)
- break;
- }
-
- up_read(&maps->lock);
+ for (map = maps__first(maps); map; map = map__next(map)) {
+ err = unwind__prepare_access(thread, map, &initialized);
+ if (err || initialized)
+ break;
}
+ up_read(&maps->lock);
+
return err;
}
@@ -335,8 +332,6 @@ static int thread__prepare_access(struct thread *thread)
static int thread__clone_map_groups(struct thread *thread,
struct thread *parent)
{
- int i;
-
/* This is new thread, we share map groups for process. */
if (thread->pid_ == parent->pid_)
return thread__prepare_access(thread);
@@ -348,9 +343,8 @@ static int thread__clone_map_groups(struct thread *thread,
}
/* But this one is new process, copy maps. */
- for (i = 0; i < MAP__NR_TYPES; ++i)
- if (map_groups__clone(thread, parent->mg, i) < 0)
- return -ENOMEM;
+ if (map_groups__clone(thread, parent->mg) < 0)
+ return -ENOMEM;
return 0;
}
@@ -371,8 +365,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
return thread__clone_map_groups(thread, parent);
}
-void thread__find_cpumode_addr_location(struct thread *thread,
- enum map_type type, u64 addr,
+void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
struct addr_location *al)
{
size_t i;
@@ -384,7 +377,7 @@ void thread__find_cpumode_addr_location(struct thread *thread,
};
for (i = 0; i < ARRAY_SIZE(cpumodes); i++) {
- thread__find_addr_location(thread, cpumodes[i], type, addr, al);
+ thread__find_symbol(thread, cpumodes[i], addr, al);
if (al->map)
break;
}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 14d44c3..07606aa 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -92,16 +92,13 @@ size_t thread__fprintf(struct thread *thread, FILE *fp);
struct thread *thread__main_thread(struct machine *machine, struct thread *thread);
-void thread__find_addr_map(struct thread *thread,
- u8 cpumode, enum map_type type, u64 addr,
- struct addr_location *al);
+struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
+ struct addr_location *al);
-void thread__find_addr_location(struct thread *thread,
- u8 cpumode, enum map_type type, u64 addr,
- struct addr_location *al);
+struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode,
+ u64 addr, struct addr_location *al);
-void thread__find_cpumode_addr_location(struct thread *thread,
- enum map_type type, u64 addr,
+void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
struct addr_location *al);
static inline void *thread__priv(struct thread *thread)
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index d7f2113..c85d0d1 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -103,11 +103,10 @@ static int record_file(const char *file, ssize_t hdr_sz)
static int record_header_files(void)
{
- char *path;
+ char *path = get_events_file("header_page");
struct stat st;
int err = -EIO;
- path = get_tracing_file("events/header_page");
if (!path) {
pr_debug("can't get tracing/events/header_page");
return -ENOMEM;
@@ -128,9 +127,9 @@ static int record_header_files(void)
goto out;
}
- put_tracing_file(path);
+ put_events_file(path);
- path = get_tracing_file("events/header_event");
+ path = get_events_file("header_event");
if (!path) {
pr_debug("can't get tracing/events/header_event");
err = -ENOMEM;
@@ -154,7 +153,7 @@ static int record_header_files(void)
err = 0;
out:
- put_tracing_file(path);
+ put_events_file(path);
return err;
}
@@ -243,7 +242,7 @@ static int record_ftrace_files(struct tracepoint_path *tps)
char *path;
int ret;
- path = get_tracing_file("events/ftrace");
+ path = get_events_file("ftrace");
if (!path) {
pr_debug("can't get tracing/events/ftrace");
return -ENOMEM;
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 0ac9077..b1e5c3a 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -98,7 +98,7 @@ static void register_python_scripting(struct scripting_ops *scripting_ops)
}
}
-#ifdef NO_LIBPYTHON
+#ifndef HAVE_LIBPYTHON_SUPPORT
void setup_python_scripting(void)
{
register_python_scripting(&python_scripting_unsupported_ops);
@@ -161,7 +161,7 @@ static void register_perl_scripting(struct scripting_ops *scripting_ops)
}
}
-#ifdef NO_LIBPERL
+#ifndef HAVE_LIBPERL_SUPPORT
void setup_perl_scripting(void)
{
register_perl_scripting(&perl_scripting_unsupported_ops);
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 16a7763..1aa3686 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -75,6 +75,7 @@ void trace_event__cleanup(struct trace_event *t)
static struct event_format*
tp_format(const char *sys, const char *name)
{
+ char *tp_dir = get_events_file(sys);
struct pevent *pevent = tevent.pevent;
struct event_format *event = NULL;
char path[PATH_MAX];
@@ -82,8 +83,11 @@ tp_format(const char *sys, const char *name)
char *data;
int err;
- scnprintf(path, PATH_MAX, "%s/%s/%s/format",
- tracing_events_path, sys, name);
+ if (!tp_dir)
+ return ERR_PTR(-errno);
+
+ scnprintf(path, PATH_MAX, "%s/%s/format", tp_dir, name);
+ put_events_file(tp_dir);
err = filename__read_str(path, &data, &size);
if (err)
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 7bdd239..538db4e 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -28,10 +28,11 @@ static int __report_module(struct addr_location *al, u64 ip,
{
Dwfl_Module *mod;
struct dso *dso = NULL;
-
- thread__find_addr_location(ui->thread,
- PERF_RECORD_MISC_USER,
- MAP__FUNCTION, ip, al);
+ /*
+ * Some callers will use al->sym, so we can't just use the
+ * cheaper thread__find_map() here.
+ */
+ thread__find_symbol(ui->thread, PERF_RECORD_MISC_USER, ip, al);
if (al->map)
dso = al->map->dso;
@@ -103,19 +104,7 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr,
struct addr_location al;
ssize_t size;
- thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
- MAP__FUNCTION, addr, &al);
- if (!al.map) {
- /*
- * We've seen cases (softice) where DWARF unwinder went
- * through non executable mmaps, which we need to lookup
- * in MAP__VARIABLE tree.
- */
- thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
- MAP__VARIABLE, addr, &al);
- }
-
- if (!al.map) {
+ if (!thread__find_map(ui->thread, PERF_RECORD_MISC_USER, addr, &al)) {
pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
return -1;
}
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index af87304..6a11bc7 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -366,19 +366,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
{
struct addr_location al;
-
- thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
- MAP__FUNCTION, ip, &al);
- if (!al.map) {
- /*
- * We've seen cases (softice) where DWARF unwinder went
- * through non executable mmaps, which we need to lookup
- * in MAP__VARIABLE tree.
- */
- thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
- MAP__VARIABLE, ip, &al);
- }
- return al.map;
+ return thread__find_map(ui->thread, PERF_RECORD_MISC_USER, ip, &al);
}
static int
@@ -586,12 +574,9 @@ static int entry(u64 ip, struct thread *thread,
struct unwind_entry e;
struct addr_location al;
- thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
- MAP__FUNCTION, ip, &al);
-
+ e.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
e.ip = al.addr;
e.map = al.map;
- e.sym = al.sym;
pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
al.sym ? al.sym->name : "''",
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 1019bbc..eac5b85 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -38,11 +38,43 @@ void perf_set_multithreaded(void)
}
unsigned int page_size;
-int cacheline_size;
+
+#ifdef _SC_LEVEL1_DCACHE_LINESIZE
+#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE)
+#else
+static void cache_line_size(int *cacheline_sizep)
+{
+ if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep))
+ pr_debug("cannot determine cache line size");
+}
+#endif
+
+int cacheline_size(void)
+{
+ static int size;
+
+ if (!size)
+ cache_line_size(&size);
+
+ return size;
+}
int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK;
+int sysctl__max_stack(void)
+{
+ int value;
+
+ if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
+ sysctl_perf_event_max_stack = value;
+
+ if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0)
+ sysctl_perf_event_max_contexts_per_stack = value;
+
+ return sysctl_perf_event_max_stack;
+}
+
bool test_attr__enabled;
bool perf_host = true;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index c9626c2..dc58254 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -43,7 +43,9 @@ size_t hex_width(u64 v);
int hex2u64(const char *ptr, u64 *val);
extern unsigned int page_size;
-extern int cacheline_size;
+int __pure cacheline_size(void);
+
+int sysctl__max_stack(void);
int fetch_kernel_version(unsigned int *puint,
char *str, size_t str_sz);
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 0acb1ec..741af20 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -139,12 +139,10 @@ static enum dso_type machine__thread_dso_type(struct machine *machine,
struct thread *thread)
{
enum dso_type dso_type = DSO__TYPE_UNKNOWN;
- struct map *map;
- struct dso *dso;
+ struct map *map = map_groups__first(thread->mg);
- map = map_groups__first(thread->mg, MAP__FUNCTION);
for (; map ; map = map_groups__next(map)) {
- dso = map->dso;
+ struct dso *dso = map->dso;
if (!dso || dso->long_name[0] != '/')
continue;
dso_type = dso__type(dso, machine);
diff --git a/tools/power/acpi/Makefile.config b/tools/power/acpi/Makefile.config
index 2cccbba..f304be7 100644
--- a/tools/power/acpi/Makefile.config
+++ b/tools/power/acpi/Makefile.config
@@ -56,6 +56,7 @@
# to compile vs uClibc, that can be done here as well.
CROSS = #/usr/i386-linux-uclibc/usr/bin/i386-uclibc-
CROSS_COMPILE ?= $(CROSS)
+LD = $(CC)
HOSTCC = gcc
# check if compiler option is supported
diff --git a/tools/power/pm-graph/bootgraph.py b/tools/power/pm-graph/bootgraph.py
index abb4c38..8ee626c 100755
--- a/tools/power/pm-graph/bootgraph.py
+++ b/tools/power/pm-graph/bootgraph.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/python2
#
# Tool for analyzing boot timing
# Copyright (c) 2013, Intel Corporation.
diff --git a/tools/power/pm-graph/sleepgraph.8 b/tools/power/pm-graph/sleepgraph.8
index 18baaf6..070be2c 100644
--- a/tools/power/pm-graph/sleepgraph.8
+++ b/tools/power/pm-graph/sleepgraph.8
@@ -168,6 +168,7 @@
in the current folder. The output page is a table of tests with
suspend and resume values sorted by suspend mode, host, and kernel.
Includes test averages by mode and links to the test html files.
+Use -genhtml to include tests with missing html.
.TP
\fB-modes\fR
List available suspend modes.
@@ -179,6 +180,9 @@
\fB-fpdt\fR
Print out the contents of the ACPI Firmware Performance Data Table.
.TP
+\fB-battery\fR
+Print out battery status and current charge.
+.TP
\fB-sysinfo\fR
Print out system info extracted from BIOS. Reads /dev/mem directly instead of going through dmidecode.
.TP
diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py
index 266409f..0c76047 100755
--- a/tools/power/pm-graph/sleepgraph.py
+++ b/tools/power/pm-graph/sleepgraph.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/python2
#
# Tool for analyzing suspend/resume timing
# Copyright (c) 2013, Intel Corporation.
@@ -69,7 +69,7 @@
# store system values and test parameters
class SystemValues:
title = 'SleepGraph'
- version = '5.0'
+ version = '5.1'
ansi = False
rs = 0
display = 0
@@ -240,7 +240,7 @@
kprobes = dict()
timeformat = '%.3f'
cmdline = '%s %s' % \
- (os.path.basename(sys.argv[0]), string.join(sys.argv[1:], ' '))
+ (os.path.basename(sys.argv[0]), ' '.join(sys.argv[1:]))
def __init__(self):
self.archargs = 'args_'+platform.machine()
self.hostname = platform.node()
@@ -917,12 +917,18 @@
self.devicegroups.append([phase])
self.errorinfo = {'suspend':[],'resume':[]}
def extractErrorInfo(self):
+ elist = {
+ 'HWERROR' : '.*\[ *Hardware Error *\].*',
+ 'FWBUG' : '.*\[ *Firmware Bug *\].*',
+ 'BUG' : '.*BUG.*',
+ 'ERROR' : '.*ERROR.*',
+ 'WARNING' : '.*WARNING.*',
+ 'IRQ' : '.*genirq: .*',
+ 'TASKFAIL': '.*Freezing of tasks failed.*',
+ }
lf = sysvals.openlog(sysvals.dmesgfile, 'r')
i = 0
list = []
- # sl = start line, et = error time, el = error line
- type = 'ERROR'
- sl = et = el = -1
for line in lf:
i += 1
m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line)
@@ -931,43 +937,13 @@
t = float(m.group('ktime'))
if t < self.start or t > self.end:
continue
- if t < self.tSuspended:
- dir = 'suspend'
- else:
- dir = 'resume'
+ dir = 'suspend' if t < self.tSuspended else 'resume'
msg = m.group('msg')
- if re.match('-*\[ *cut here *\]-*', msg):
- type = 'WARNING'
- sl = i
- elif re.match('genirq: .*', msg):
- type = 'IRQ'
- sl = i
- elif re.match('BUG: .*', msg) or re.match('kernel BUG .*', msg):
- type = 'BUG'
- sl = i
- elif re.match('-*\[ *end trace .*\]-*', msg) or \
- re.match('R13: .*', msg):
- if et >= 0 and sl >= 0:
- list.append((type, dir, et, sl, i))
+ for err in elist:
+ if re.match(elist[err], msg):
+ list.append((err, dir, t, i, i))
self.kerror = True
- sl = et = el = -1
- type = 'ERROR'
- elif 'Call Trace:' in msg:
- if el >= 0 and et >= 0:
- list.append((type, dir, et, el, el))
- self.kerror = True
- et, el = t, i
- if sl < 0 or type == 'BUG':
- slval = i
- if sl >= 0:
- slval = sl
- list.append((type, dir, et, slval, i))
- self.kerror = True
- sl = et = el = -1
- type = 'ERROR'
- if el >= 0 and et >= 0:
- list.append((type, dir, et, el, el))
- self.kerror = True
+ break
for e in list:
type, dir, t, idx1, idx2 = e
sysvals.vprint('kernel %s found in %s at %f' % (type, dir, t))
@@ -2331,12 +2307,14 @@
sv.suspendmode = data.stamp['mode']
if sv.suspendmode == 'command' and sv.ftracefile != '':
modes = ['on', 'freeze', 'standby', 'mem', 'disk']
- out = Popen(['grep', 'machine_suspend', sv.ftracefile],
- stderr=PIPE, stdout=PIPE).stdout.read()
- m = re.match('.* machine_suspend\[(?P<mode>.*)\]', out)
- if m and m.group('mode') in ['1', '2', '3', '4']:
- sv.suspendmode = modes[int(m.group('mode'))]
- data.stamp['mode'] = sv.suspendmode
+ fp = sysvals.openlog(sv.ftracefile, 'r')
+ for line in fp:
+ m = re.match('.* machine_suspend\[(?P<mode>.*)\]', line)
+ if m and m.group('mode') in ['1', '2', '3', '4']:
+ sv.suspendmode = modes[int(m.group('mode'))]
+ data.stamp['mode'] = sv.suspendmode
+ break
+ fp.close()
m = re.match(self.cmdlinefmt, self.cmdline)
if m:
sv.cmdline = m.group('cmd')
@@ -2413,7 +2391,7 @@
# markers, and/or kprobes required for primary parsing.
def doesTraceLogHaveTraceEvents():
kpcheck = ['_cal: (', '_cpu_down()']
- techeck = sysvals.traceevents[:]
+ techeck = ['suspend_resume']
tmcheck = ['SUSPEND START', 'RESUME COMPLETE']
sysvals.usekprobes = False
fp = sysvals.openlog(sysvals.ftracefile, 'r')
@@ -2808,7 +2786,7 @@
# -- phase changes --
# start of kernel suspend
if(re.match('suspend_enter\[.*', t.name)):
- if(isbegin):
+ if(isbegin and data.start == data.tKernSus):
data.dmesg[phase]['start'] = t.time
data.tKernSus = t.time
continue
@@ -3072,13 +3050,20 @@
sysvals.vprint('Callgraph found for task %d: %.3fms, %s' % (cg.pid, (cg.end - cg.start)*1000, name))
cg.newActionFromFunction(data)
if sysvals.suspendmode == 'command':
- return testdata
+ return (testdata, '')
# fill in any missing phases
+ error = []
for data in testdata:
+ tn = '' if len(testdata) == 1 else ('%d' % (data.testnumber + 1))
+ terr = ''
lp = data.phases[0]
for p in data.phases:
if(data.dmesg[p]['start'] < 0 and data.dmesg[p]['end'] < 0):
+ if not terr:
+ print 'TEST%s FAILED: %s failed in %s phase' % (tn, sysvals.suspendmode, lp)
+ terr = '%s%s failed in %s phase' % (sysvals.suspendmode, tn, lp)
+ error.append(terr)
sysvals.vprint('WARNING: phase "%s" is missing!' % p)
if(data.dmesg[p]['start'] < 0):
data.dmesg[p]['start'] = data.dmesg[lp]['end']
@@ -3106,7 +3091,7 @@
for j in range(i + 1, tc):
testdata[j].mergeOverlapDevices(devlist)
testdata[0].stitchTouchingThreads(testdata[1:])
- return testdata
+ return (testdata, ', '.join(error))
# Function: loadKernelLog
# Description:
@@ -3173,7 +3158,7 @@
if data:
testruns.append(data)
if len(testruns) < 1:
- doError(' dmesg log has no suspend/resume data: %s' \
+ print('ERROR: dmesg log has no suspend/resume data: %s' \
% sysvals.dmesgfile)
# fix lines with same timestamp/function with the call and return swapped
@@ -3521,68 +3506,144 @@
.summary {border:1px solid;}\n\
th {border: 1px solid black;background:#222;color:white;}\n\
td {font: 16px "Times New Roman";text-align: center;}\n\
- tr.alt td {background:#ddd;}\n\
- tr.avg td {background:#aaa;}\n\
+ tr.head td {border: 1px solid black;background:#aaa;}\n\
+ tr.alt {background-color:#ddd;}\n\
+ tr.notice {color:red;}\n\
+ .minval {background-color:#BBFFBB;}\n\
+ .medval {background-color:#BBBBFF;}\n\
+ .maxval {background-color:#FFBBBB;}\n\
+ .head a {color:#000;text-decoration: none;}\n\
</style>\n</head>\n<body>\n'
+ # extract the test data into list
+ list = dict()
+ tAvg, tMin, tMax, tMed = [0.0, 0.0], [0.0, 0.0], [0.0, 0.0], [[], []]
+ iMin, iMed, iMax = [0, 0], [0, 0], [0, 0]
+ num = 0
+ lastmode = ''
+ cnt = {'pass':0, 'fail':0, 'hang':0}
+ for data in sorted(testruns, key=lambda v:(v['mode'], v['host'], v['kernel'], v['time'])):
+ mode = data['mode']
+ if mode not in list:
+ list[mode] = {'data': [], 'avg': [0,0], 'min': [0,0], 'max': [0,0], 'med': [0,0]}
+ if lastmode and lastmode != mode and num > 0:
+ for i in range(2):
+ s = sorted(tMed[i])
+ list[lastmode]['med'][i] = s[int(len(s)/2)]
+ iMed[i] = tMed[i].index(list[lastmode]['med'][i])
+ list[lastmode]['avg'] = [tAvg[0] / num, tAvg[1] / num]
+ list[lastmode]['min'] = tMin
+ list[lastmode]['max'] = tMax
+ list[lastmode]['idx'] = (iMin, iMed, iMax)
+ tAvg, tMin, tMax, tMed = [0.0, 0.0], [0.0, 0.0], [0.0, 0.0], [[], []]
+ iMin, iMed, iMax = [0, 0], [0, 0], [0, 0]
+ num = 0
+ tVal = [float(data['suspend']), float(data['resume'])]
+ list[mode]['data'].append([data['host'], data['kernel'],
+ data['time'], tVal[0], tVal[1], data['url'], data['result'],
+ data['issues']])
+ idx = len(list[mode]['data']) - 1
+ if data['result'] == 'pass':
+ cnt['pass'] += 1
+ for i in range(2):
+ tMed[i].append(tVal[i])
+ tAvg[i] += tVal[i]
+ if tMin[i] == 0 or tVal[i] < tMin[i]:
+ iMin[i] = idx
+ tMin[i] = tVal[i]
+ if tMax[i] == 0 or tVal[i] > tMax[i]:
+ iMax[i] = idx
+ tMax[i] = tVal[i]
+ num += 1
+ elif data['result'] == 'hang':
+ cnt['hang'] += 1
+ elif data['result'] == 'fail':
+ cnt['fail'] += 1
+ lastmode = mode
+ if lastmode and num > 0:
+ for i in range(2):
+ s = sorted(tMed[i])
+ list[lastmode]['med'][i] = s[int(len(s)/2)]
+ iMed[i] = tMed[i].index(list[lastmode]['med'][i])
+ list[lastmode]['avg'] = [tAvg[0] / num, tAvg[1] / num]
+ list[lastmode]['min'] = tMin
+ list[lastmode]['max'] = tMax
+ list[lastmode]['idx'] = (iMin, iMed, iMax)
+
# group test header
- html += '<div class="stamp">%s (%d tests)</div>\n' % (folder, len(testruns))
+ desc = []
+ for ilk in sorted(cnt, reverse=True):
+ if cnt[ilk] > 0:
+ desc.append('%d %s' % (cnt[ilk], ilk))
+ html += '<div class="stamp">%s (%d tests: %s)</div>\n' % (folder, len(testruns), ', '.join(desc))
th = '\t<th>{0}</th>\n'
td = '\t<td>{0}</td>\n'
+ tdh = '\t<td{1}>{0}</td>\n'
tdlink = '\t<td><a href="{0}">html</a></td>\n'
# table header
html += '<table class="summary">\n<tr>\n' + th.format('#') +\
th.format('Mode') + th.format('Host') + th.format('Kernel') +\
- th.format('Test Time') + th.format('Suspend') + th.format('Resume') +\
- th.format('Detail') + '</tr>\n'
+ th.format('Test Time') + th.format('Result') + th.format('Issues') +\
+ th.format('Suspend') + th.format('Resume') + th.format('Detail') + '</tr>\n'
- # test data, 1 row per test
- avg = '<tr class="avg"><td></td><td></td><td></td><td></td>'+\
- '<td>Average of {0} {1} tests</td><td>{2}</td><td>{3}</td><td></td></tr>\n'
- sTimeAvg = rTimeAvg = 0.0
- mode = ''
- num = 0
- for data in sorted(testruns, key=lambda v:(v['mode'], v['host'], v['kernel'], v['time'])):
- if mode != data['mode']:
- # test average line
- if(num > 0):
- sTimeAvg /= (num - 1)
- rTimeAvg /= (num - 1)
- html += avg.format('%d' % (num - 1), mode,
- '%3.3f ms' % sTimeAvg, '%3.3f ms' % rTimeAvg)
- sTimeAvg = rTimeAvg = 0.0
- mode = data['mode']
- num = 1
- # alternate row color
- if num % 2 == 1:
- html += '<tr class="alt">\n'
+ # export list into html
+ head = '<tr class="head"><td>{0}</td><td>{1}</td>'+\
+ '<td colspan=8 class="sus">Suspend Avg={2} '+\
+ '<span class=minval><a href="#s{10}min">Min={3}</a></span> '+\
+ '<span class=medval><a href="#s{10}med">Med={4}</a></span> '+\
+ '<span class=maxval><a href="#s{10}max">Max={5}</a></span> '+\
+ 'Resume Avg={6} '+\
+ '<span class=minval><a href="#r{10}min">Min={7}</a></span> '+\
+ '<span class=medval><a href="#r{10}med">Med={8}</a></span> '+\
+ '<span class=maxval><a href="#r{10}max">Max={9}</a></span></td>'+\
+ '</tr>\n'
+ headnone = '<tr class="head"><td>{0}</td><td>{1}</td><td colspan=8></td></tr>\n'
+ for mode in list:
+ # header line for each suspend mode
+ num = 0
+ tAvg, tMin, tMax, tMed = list[mode]['avg'], list[mode]['min'],\
+ list[mode]['max'], list[mode]['med']
+ count = len(list[mode]['data'])
+ if 'idx' in list[mode]:
+ iMin, iMed, iMax = list[mode]['idx']
+ html += head.format('%d' % count, mode.upper(),
+ '%.3f' % tAvg[0], '%.3f' % tMin[0], '%.3f' % tMed[0], '%.3f' % tMax[0],
+ '%.3f' % tAvg[1], '%.3f' % tMin[1], '%.3f' % tMed[1], '%.3f' % tMax[1],
+ mode.lower()
+ )
else:
- html += '<tr>\n'
- html += td.format("%d" % num)
- num += 1
- # basic info
- for item in ['mode', 'host', 'kernel', 'time']:
- val = "unknown"
- if(item in data):
- val = data[item]
- html += td.format(val)
- # suspend time
- sTime = float(data['suspend'])
- sTimeAvg += sTime
- html += td.format('%.3f ms' % sTime)
- # resume time
- rTime = float(data['resume'])
- rTimeAvg += rTime
- html += td.format('%.3f ms' % rTime)
- # link to the output html
- html += tdlink.format(data['url']) + '</tr>\n'
- # last test average line
- if(num > 0):
- sTimeAvg /= (num - 1)
- rTimeAvg /= (num - 1)
- html += avg.format('%d' % (num - 1), mode,
- '%3.3f ms' % sTimeAvg, '%3.3f ms' % rTimeAvg)
+ iMin = iMed = iMax = [-1, -1, -1]
+ html += headnone.format('%d' % count, mode.upper())
+ for d in list[mode]['data']:
+ # row classes - alternate row color
+ rcls = ['alt'] if num % 2 == 1 else []
+ if d[6] != 'pass':
+ rcls.append('notice')
+ html += '<tr class="'+(' '.join(rcls))+'">\n' if len(rcls) > 0 else '<tr>\n'
+ # figure out if the line has sus or res highlighted
+ idx = list[mode]['data'].index(d)
+ tHigh = ['', '']
+ for i in range(2):
+ tag = 's%s' % mode if i == 0 else 'r%s' % mode
+ if idx == iMin[i]:
+ tHigh[i] = ' id="%smin" class=minval title="Minimum"' % tag
+ elif idx == iMax[i]:
+ tHigh[i] = ' id="%smax" class=maxval title="Maximum"' % tag
+ elif idx == iMed[i]:
+ tHigh[i] = ' id="%smed" class=medval title="Median"' % tag
+ html += td.format("%d" % (list[mode]['data'].index(d) + 1)) # row
+ html += td.format(mode) # mode
+ html += td.format(d[0]) # host
+ html += td.format(d[1]) # kernel
+ html += td.format(d[2]) # time
+ html += td.format(d[6]) # result
+ html += td.format(d[7]) # issues
+ html += tdh.format('%.3f ms' % d[3], tHigh[0]) if d[3] else td.format('') # suspend
+ html += tdh.format('%.3f ms' % d[4], tHigh[1]) if d[4] else td.format('') # resume
+ html += tdlink.format(d[5]) if d[5] else td.format('') # url
+ html += '</tr>\n'
+ num += 1
# flush the data to file
hf = open(htmlfile, 'w')
@@ -3607,7 +3668,7 @@
# testruns: array of Data objects from parseKernelLog or parseTraceLog
# Output:
# True if the html file was created, false if it failed
-def createHTML(testruns):
+def createHTML(testruns, testfail):
if len(testruns) < 1:
print('ERROR: Not enough test data to build a timeline')
return
@@ -3641,6 +3702,7 @@
'<td class="purple">{4}Firmware Resume: {2} ms</td>'\
'<td class="yellow" title="time from firmware mode to return from kernel enter_state({5}) [kernel time only]">{4}Kernel Resume: {3} ms</td>'\
'</tr>\n</table>\n'
+ html_fail = '<table class="testfail"><tr><td>{0}</td></tr></table>\n'
# html format variables
scaleH = 20
@@ -3708,6 +3770,9 @@
resume_time, testdesc, stitle, rtitle)
devtl.html += thtml
+ if testfail:
+ devtl.html += html_fail.format(testfail)
+
# time scale for potentially multiple datasets
t0 = testruns[0].start
tMax = testruns[-1].end
@@ -4006,6 +4071,7 @@
.blue {background:rgba(169,208,245,0.4);}\n\
.time1 {font:22px Arial;border:1px solid;}\n\
.time2 {font:15px Arial;border-bottom:1px solid;border-left:1px solid;border-right:1px solid;}\n\
+ .testfail {font:bold 22px Arial;color:red;border:1px dashed;}\n\
td {text-align:center;}\n\
r {color:#500000;font:15px Tahoma;}\n\
n {color:#505050;font:15px Tahoma;}\n\
@@ -4927,6 +4993,25 @@
count += 1
return out
+def getBattery():
+ p = '/sys/class/power_supply'
+ bat = dict()
+ for d in os.listdir(p):
+ type = sysvals.getVal(os.path.join(p, d, 'type')).strip().lower()
+ if type != 'battery':
+ continue
+ for v in ['status', 'energy_now', 'capacity_now']:
+ bat[v] = sysvals.getVal(os.path.join(p, d, v)).strip().lower()
+ break
+ ac = True
+ if 'status' in bat and 'discharging' in bat['status']:
+ ac = False
+ charge = 0
+ for v in ['energy_now', 'capacity_now']:
+ if v in bat and bat[v]:
+ charge = int(bat[v])
+ return (ac, charge)
+
# Function: getFPDT
# Description:
# Read the acpi bios tables and pull out FPDT, the firmware data
@@ -5202,8 +5287,9 @@
def processData(live=False):
print('PROCESSING DATA')
+ error = ''
if(sysvals.usetraceevents):
- testruns = parseTraceLog(live)
+ testruns, error = parseTraceLog(live)
if sysvals.dmesgfile:
for data in testruns:
data.extractErrorInfo()
@@ -5220,15 +5306,18 @@
for data in testruns:
data.debugPrint()
sys.exit()
-
+ if len(testruns) < 1:
+ return (testruns, {'error': 'timeline generation failed'})
sysvals.vprint('Creating the html timeline (%s)...' % sysvals.htmlfile)
- createHTML(testruns)
+ createHTML(testruns, error)
print('DONE')
data = testruns[0]
stamp = data.stamp
stamp['suspend'], stamp['resume'] = data.getTimeValues()
if data.fwValid:
stamp['fwsuspend'], stamp['fwresume'] = data.fwSuspend, data.fwResume
+ if error:
+ stamp['error'] = error
return (testruns, stamp)
# Function: rerunTest
@@ -5268,58 +5357,88 @@
sysvals.sudouser(sysvals.testdir)
sysvals.outputResult(stamp, n)
-def find_in_html(html, strs, div=False):
- for str in strs:
- l = len(str)
- i = html.find(str)
- if i >= 0:
+def find_in_html(html, start, end, firstonly=True):
+ n, out = 0, []
+ while n < len(html):
+ m = re.search(start, html[n:])
+ if not m:
break
- if i < 0:
+ i = m.end()
+ m = re.search(end, html[n+i:])
+ if not m:
+ break
+ j = m.start()
+ str = html[n+i:n+i+j]
+ if end == 'ms':
+ num = re.search(r'[-+]?\d*\.\d+|\d+', str)
+ str = num.group() if num else 'NaN'
+ if firstonly:
+ return str
+ out.append(str)
+ n += i+j
+ if firstonly:
return ''
- if not div:
- return re.search(r'[-+]?\d*\.\d+|\d+', html[i+l:i+l+50]).group()
- n = html[i+l:].find('</div>')
- if n < 0:
- return ''
- return html[i+l:i+l+n]
+ return out
# Function: runSummary
# Description:
# create a summary of tests in a sub-directory
-def runSummary(subdir, local=True):
+def runSummary(subdir, local=True, genhtml=False):
inpath = os.path.abspath(subdir)
outpath = inpath
if local:
outpath = os.path.abspath('.')
print('Generating a summary of folder "%s"' % inpath)
+ if genhtml:
+ for dirname, dirnames, filenames in os.walk(subdir):
+ sysvals.dmesgfile = sysvals.ftracefile = sysvals.htmlfile = ''
+ for filename in filenames:
+ if(re.match('.*_dmesg.txt', filename)):
+ sysvals.dmesgfile = os.path.join(dirname, filename)
+ elif(re.match('.*_ftrace.txt', filename)):
+ sysvals.ftracefile = os.path.join(dirname, filename)
+ sysvals.setOutputFile()
+ if sysvals.ftracefile and sysvals.htmlfile and \
+ not os.path.exists(sysvals.htmlfile):
+ print('FTRACE: %s' % sysvals.ftracefile)
+ if sysvals.dmesgfile:
+ print('DMESG : %s' % sysvals.dmesgfile)
+ rerunTest()
testruns = []
for dirname, dirnames, filenames in os.walk(subdir):
for filename in filenames:
if(not re.match('.*.html', filename)):
continue
file = os.path.join(dirname, filename)
- html = open(file, 'r').read(10000)
- suspend = find_in_html(html,
- ['Kernel Suspend: ', 'Kernel Suspend Time: '])
- resume = find_in_html(html,
- ['Kernel Resume: ', 'Kernel Resume Time: '])
- line = find_in_html(html, ['<div class="stamp">'], True)
+ html = open(file, 'r').read()
+ suspend = find_in_html(html, 'Kernel Suspend', 'ms')
+ resume = find_in_html(html, 'Kernel Resume', 'ms')
+ line = find_in_html(html, '<div class="stamp">', '</div>')
stmp = line.split()
- if not suspend or not resume or len(stmp) < 4:
+ if not suspend or not resume or len(stmp) != 8:
continue
+ try:
+ dt = datetime.strptime(' '.join(stmp[3:]), '%B %d %Y, %I:%M:%S %p')
+ except:
+ continue
+ tstr = dt.strftime('%Y/%m/%d %H:%M:%S')
+ error = find_in_html(html, '<table class="testfail"><tr><td>', '</td>')
+ result = 'fail' if error else 'pass'
+ ilist = []
+ e = find_in_html(html, 'class="err"[\w=":;\.%\- ]*>', '→</div>', False)
+ for i in list(set(e)):
+ ilist.append('%sx%d' % (i, e.count(i)) if e.count(i) > 1 else i)
data = {
+ 'mode': stmp[2],
'host': stmp[0],
'kernel': stmp[1],
- 'mode': stmp[2],
- 'time': string.join(stmp[3:], ' '),
+ 'time': tstr,
+ 'result': result,
+ 'issues': ','.join(ilist),
'suspend': suspend,
'resume': resume,
'url': os.path.relpath(file, outpath),
}
- if len(stmp) == 7:
- data['kernel'] = 'unknown'
- data['mode'] = stmp[1]
- data['time'] = string.join(stmp[2:], ' ')
testruns.append(data)
outfile = os.path.join(outpath, 'summary.html')
print('Summary file: %s' % outfile)
@@ -5609,11 +5728,12 @@
print(' -modes List available suspend modes')
print(' -status Test to see if the system is enabled to run this tool')
print(' -fpdt Print out the contents of the ACPI Firmware Performance Data Table')
+ print(' -battery Print out battery info (if available)')
print(' -sysinfo Print out system info extracted from BIOS')
print(' -devinfo Print out the pm settings of all devices which support runtime suspend')
print(' -flist Print the list of functions currently being captured in ftrace')
print(' -flistall Print all functions capable of being captured in ftrace')
- print(' -summary directory Create a summary of all test in this dir')
+ print(' -summary dir Create a summary of tests in this dir [-genhtml builds missing html]')
print(' [redo]')
print(' -ftrace ftracefile Create HTML output using ftrace input (used with -dmesg)')
print(' -dmesg dmesgfile Create HTML output using dmesg (used with -ftrace)')
@@ -5623,8 +5743,9 @@
# ----------------- MAIN --------------------
# exec start (skipped if script is loaded as library)
if __name__ == '__main__':
+ genhtml = False
cmd = ''
- simplecmds = ['-sysinfo', '-modes', '-fpdt', '-flist', '-flistall', '-devinfo', '-status']
+ simplecmds = ['-sysinfo', '-modes', '-fpdt', '-flist', '-flistall', '-devinfo', '-status', '-battery']
if '-f' in sys.argv:
sysvals.cgskip = sysvals.configFile('cgskip.txt')
# loop through the command line arguments
@@ -5660,6 +5781,8 @@
sysvals.skiphtml = True
elif(arg == '-cgdump'):
sysvals.cgdump = True
+ elif(arg == '-genhtml'):
+ genhtml = True
elif(arg == '-addlogs'):
sysvals.dmesglog = sysvals.ftracelog = True
elif(arg == '-verbose'):
@@ -5856,6 +5979,8 @@
statusCheck(True)
elif(cmd == 'fpdt'):
getFPDT(True)
+ elif(cmd == 'battery'):
+ print 'AC Connect: %s\nCharge: %d' % getBattery()
elif(cmd == 'sysinfo'):
sysvals.printSystemInfo(True)
elif(cmd == 'devinfo'):
@@ -5867,7 +5992,7 @@
elif(cmd == 'flistall'):
sysvals.getFtraceFilterFunctions(False)
elif(cmd == 'summary'):
- runSummary(sysvals.outdir, True)
+ runSummary(sysvals.outdir, True, genhtml)
sys.exit()
# if instructed, re-analyze existing data files
@@ -5920,7 +6045,7 @@
print('TEST (%d/%d) COMPLETE' % (i+1, sysvals.multitest['count']))
sysvals.logmsg = ''
if not sysvals.skiphtml:
- runSummary(sysvals.outdir, False)
+ runSummary(sysvals.outdir, False, False)
sysvals.sudouser(sysvals.outdir)
else:
if sysvals.outdir:
diff --git a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
index 29f50d4..84e2b64 100755
--- a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
+++ b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
@@ -28,6 +28,7 @@
import os
import time
import re
+import signal
import sys
import getopt
import Gnuplot
@@ -78,11 +79,12 @@
print(' Or')
print(' ./intel_pstate_tracer.py [--cpu cpus] ---trace_file <trace_file> --name <test_name>')
print(' To generate trace file, parse and plot, use (sudo required):')
- print(' sudo ./intel_pstate_tracer.py [-c cpus] -i <interval> -n <test_name>')
+ print(' sudo ./intel_pstate_tracer.py [-c cpus] -i <interval> -n <test_name> -m <kbytes>')
print(' Or')
- print(' sudo ./intel_pstate_tracer.py [--cpu cpus] --interval <interval> --name <test_name>')
+ print(' sudo ./intel_pstate_tracer.py [--cpu cpus] --interval <interval> --name <test_name> --memory <kbytes>')
print(' Optional argument:')
- print(' cpus: comma separated list of CPUs')
+ print(' cpus: comma separated list of CPUs')
+ print(' kbytes: Kilo bytes of memory per CPU to allocate to the trace buffer. Default: 10240')
print(' Output:')
print(' If not already present, creates a "results/test_name" folder in the current working directory with:')
print(' cpu.csv - comma seperated values file with trace contents and some additional calculations.')
@@ -379,7 +381,7 @@
f_handle.close()
except:
print('IO error clearing trace file ')
- quit()
+ sys.exit(2)
def enable_trace():
""" Enable trace """
@@ -389,7 +391,7 @@
, 'w').write("1")
except:
print('IO error enabling trace ')
- quit()
+ sys.exit(2)
def disable_trace():
""" Disable trace """
@@ -399,17 +401,17 @@
, 'w').write("0")
except:
print('IO error disabling trace ')
- quit()
+ sys.exit(2)
def set_trace_buffer_size():
""" Set trace buffer size """
try:
- open('/sys/kernel/debug/tracing/buffer_size_kb'
- , 'w').write("10240")
+ with open('/sys/kernel/debug/tracing/buffer_size_kb', 'w') as fp:
+ fp.write(memory)
except:
- print('IO error setting trace buffer size ')
- quit()
+ print('IO error setting trace buffer size ')
+ sys.exit(2)
def free_trace_buffer():
""" Free the trace buffer memory """
@@ -418,8 +420,8 @@
open('/sys/kernel/debug/tracing/buffer_size_kb'
, 'w').write("1")
except:
- print('IO error setting trace buffer size ')
- quit()
+ print('IO error freeing trace buffer ')
+ sys.exit(2)
def read_trace_data(filename):
""" Read and parse trace data """
@@ -431,7 +433,7 @@
data = open(filename, 'r').read()
except:
print('Error opening ', filename)
- quit()
+ sys.exit(2)
for line in data.splitlines():
search_obj = \
@@ -489,10 +491,22 @@
# Now seperate the main overall csv file into per CPU csv files.
split_csv()
+def signal_handler(signal, frame):
+ print(' SIGINT: Forcing cleanup before exit.')
+ if interval:
+ disable_trace()
+ clear_trace_file()
+ # Free the memory
+ free_trace_buffer()
+ sys.exit(0)
+
+signal.signal(signal.SIGINT, signal_handler)
+
interval = ""
filename = ""
cpu_list = ""
testname = ""
+memory = "10240"
graph_data_present = False;
valid1 = False
@@ -501,7 +515,7 @@
cpu_mask = zeros((MAX_CPUS,), dtype=int)
try:
- opts, args = getopt.getopt(sys.argv[1:],"ht:i:c:n:",["help","trace_file=","interval=","cpu=","name="])
+ opts, args = getopt.getopt(sys.argv[1:],"ht:i:c:n:m:",["help","trace_file=","interval=","cpu=","name=","memory="])
except getopt.GetoptError:
print_help()
sys.exit(2)
@@ -521,6 +535,8 @@
elif opt in ("-n", "--name"):
valid2 = True
testname = arg
+ elif opt in ("-m", "--memory"):
+ memory = arg
if not (valid1 and valid2):
print_help()
@@ -569,6 +585,11 @@
read_trace_data(filename)
+clear_trace_file()
+# Free the memory
+if interval:
+ free_trace_buffer()
+
if graph_data_present == False:
print('No valid data to plot')
sys.exit(2)
@@ -593,9 +614,4 @@
for f in files:
fix_ownership(f)
-clear_trace_file()
-# Free the memory
-if interval:
- free_trace_buffer()
-
os.chdir('../../')
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index a9bc914..2ab25aa 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -25,4 +25,4 @@
install -d $(DESTDIR)$(PREFIX)/bin
install $(BUILD_OUTPUT)/turbostat $(DESTDIR)$(PREFIX)/bin/turbostat
install -d $(DESTDIR)$(PREFIX)/share/man/man8
- install turbostat.8 $(DESTDIR)$(PREFIX)/share/man/man8
+ install -m 644 turbostat.8 $(DESTDIR)$(PREFIX)/share/man/man8
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index ccf2a69..ca9ef70 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -54,9 +54,12 @@
.PP
\fB--cpu cpu-set\fP limit output to system summary plus the specified cpu-set. If cpu-set is the string "core", then the system summary plus the first CPU in each core are printed -- eg. subsequent HT siblings are not printed. Or if cpu-set is the string "package", then the system summary plus the first CPU in each package is printed. Otherwise, the system summary plus the specified set of CPUs are printed. The cpu-set is ordered from low to high, comma delimited with ".." and "-" permitted to denote a range. eg. 1,2,8,14..17,21-44
.PP
-\fB--hide column\fP do not show the specified columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--hide sysfs" to hide the sysfs statistics columns as a group.
+\fB--hide column\fP do not show the specified built-in columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--hide sysfs" to hide the sysfs statistics columns as a group.
.PP
-\fB--show column\fP show only the specified columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--show sysfs" to show the sysfs statistics columns as a group.
+\fB--enable column\fP show the specified built-in columns, which are otherwise disabled, by default. Currently the only built-in counters disabled by default are "usec" and "Time_Of_Day_Seconds".
+The column name "all" can be used to enable all disabled-by-default built-in counters.
+.PP
+\fB--show column\fP show only the specified built-in columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--show sysfs" to show the sysfs statistics columns as a group.
.PP
\fB--Dump\fP displays the raw counter values.
.PP
@@ -64,6 +67,8 @@
.PP
\fB--interval seconds\fP overrides the default 5.0 second measurement interval.
.PP
+\fB--num_iterations num\fP number of the measurement iterations.
+.PP
\fB--out output_file\fP turbostat output is written to the specified output_file.
The file is truncated if it already exists, and it is created if it does not exist.
.PP
@@ -86,6 +91,8 @@
The system configuration dump (if --quiet is not used) is followed by statistics. The first row of the statistics labels the content of each column (below). The second row of statistics is the system summary line. The system summary line has a '-' in the columns for the Package, Core, and CPU. The contents of the system summary line depends on the type of column. Columns that count items (eg. IRQ) show the sum across all CPUs in the system. Columns that show a percentage show the average across all CPUs in the system. Columns that dump raw MSR values simply show 0 in the summary. After the system summary row, each row describes a specific Package/Core/CPU. Note that if the --cpu parameter is used to limit which specific CPUs are displayed, turbostat will still collect statistics for all CPUs in the system and will still show the system summary for all CPUs in the system.
.SH COLUMN DESCRIPTIONS
.nf
+\fBusec\fP For each CPU, the number of microseconds elapsed during counter collection, including thread migration -- if any. This counter is disabled by default, and is enabled with "--enable usec", or --debug. On the summary row, usec refers to the total elapsed time to collect the counters on all cpus.
+\fBTime_Of_Day_Seconds\fP For each CPU, the gettimeofday(2) value (seconds.subsec since Epoch) when the counters ending the measurement interval were collected. This column is disabled by default, and can be enabled with "--enable Time_Of_Day_Seconds" or "--debug". On the summary row, Time_Of_Day_Seconds refers to the timestamp following collection of counters on the last CPU.
\fBCore\fP processor core number. Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology (HT).
\fBCPU\fP Linux CPU (logical processor) number. Yes, it is okay that on many systems the CPUs are not listed in numerical order -- for efficiency reasons, turbostat runs in topology order, so HT siblings appear together.
\fBPackage\fP processor package number -- not present on systems with a single processor package.
@@ -262,6 +269,21 @@
.fi
+.SH INPUT
+
+For interval-mode, turbostat will immediately end the current interval
+when it sees a newline on standard input.
+turbostat will then start the next interval.
+Control-C will be send a SIGINT to turbostat,
+which will immediately abort the program with no further processing.
+.SH SIGNALS
+
+SIGINT will interrupt interval-mode.
+The end-of-interval data will be collected and displayed before turbostat exits.
+
+SIGUSR1 will end current interval,
+end-of-interval data will be collected and displayed before turbostat
+starts a new interval.
.SH NOTES
.B "turbostat "
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index bd9c6b3..d6cff30 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -29,6 +29,7 @@
#include <sys/types.h>
#include <sys/wait.h>
#include <sys/stat.h>
+#include <sys/select.h>
#include <sys/resource.h>
#include <fcntl.h>
#include <signal.h>
@@ -47,9 +48,13 @@
char *proc_stat = "/proc/stat";
FILE *outf;
int *fd_percpu;
+struct timeval interval_tv = {5, 0};
struct timespec interval_ts = {5, 0};
+struct timespec one_msec = {0, 1000000};
+unsigned int num_iterations;
unsigned int debug;
unsigned int quiet;
+unsigned int shown;
unsigned int sums_need_wide_columns;
unsigned int rapl_joules;
unsigned int summary_only;
@@ -58,6 +63,7 @@ unsigned int dump_only;
unsigned int do_snb_cstates;
unsigned int do_knl_cstates;
unsigned int do_slm_cstates;
+unsigned int do_cnl_cstates;
unsigned int use_c1_residency_msr;
unsigned int has_aperf;
unsigned int has_epb;
@@ -80,6 +86,8 @@ unsigned int do_rapl;
unsigned int do_dts;
unsigned int do_ptm;
unsigned long long gfx_cur_rc6_ms;
+unsigned long long cpuidle_cur_cpu_lpi_us;
+unsigned long long cpuidle_cur_sys_lpi_us;
unsigned int gfx_cur_mhz;
unsigned int tcc_activation_temp;
unsigned int tcc_activation_temp_override;
@@ -87,6 +95,7 @@ double rapl_power_units, rapl_time_units;
double rapl_dram_energy_units, rapl_energy_units;
double rapl_joule_counter_range;
unsigned int do_core_perf_limit_reasons;
+unsigned int has_automatic_cstate_conversion;
unsigned int do_gfx_perf_limit_reasons;
unsigned int do_ring_perf_limit_reasons;
unsigned int crystal_hz;
@@ -147,7 +156,9 @@ char *progname;
#define CPU_SUBSET_MAXCPUS 1024 /* need to use before probe... */
cpu_set_t *cpu_present_set, *cpu_affinity_set, *cpu_subset;
size_t cpu_present_setsize, cpu_affinity_setsize, cpu_subset_size;
-#define MAX_ADDED_COUNTERS 16
+#define MAX_ADDED_COUNTERS 8
+#define MAX_ADDED_THREAD_COUNTERS 24
+#define BITMASK_SIZE 32
struct thread_data {
struct timeval tv_begin;
@@ -162,7 +173,7 @@ struct thread_data {
unsigned int flags;
#define CPU_IS_FIRST_THREAD_IN_CORE 0x2
#define CPU_IS_FIRST_CORE_IN_PACKAGE 0x4
- unsigned long long counter[MAX_ADDED_COUNTERS];
+ unsigned long long counter[MAX_ADDED_THREAD_COUNTERS];
} *thread_even, *thread_odd;
struct core_data {
@@ -183,6 +194,8 @@ struct pkg_data {
unsigned long long pc8;
unsigned long long pc9;
unsigned long long pc10;
+ unsigned long long cpu_lpi;
+ unsigned long long sys_lpi;
unsigned long long pkg_wtd_core_c0;
unsigned long long pkg_any_core_c0;
unsigned long long pkg_any_gfxe_c0;
@@ -203,12 +216,21 @@ struct pkg_data {
#define ODD_COUNTERS thread_odd, core_odd, package_odd
#define EVEN_COUNTERS thread_even, core_even, package_even
-#define GET_THREAD(thread_base, thread_no, core_no, pkg_no) \
- (thread_base + (pkg_no) * topo.num_cores_per_pkg * \
- topo.num_threads_per_core + \
- (core_no) * topo.num_threads_per_core + (thread_no))
-#define GET_CORE(core_base, core_no, pkg_no) \
- (core_base + (pkg_no) * topo.num_cores_per_pkg + (core_no))
+#define GET_THREAD(thread_base, thread_no, core_no, node_no, pkg_no) \
+ ((thread_base) + \
+ ((pkg_no) * \
+ topo.nodes_per_pkg * topo.cores_per_node * topo.threads_per_core) + \
+ ((node_no) * topo.cores_per_node * topo.threads_per_core) + \
+ ((core_no) * topo.threads_per_core) + \
+ (thread_no))
+
+#define GET_CORE(core_base, core_no, node_no, pkg_no) \
+ ((core_base) + \
+ ((pkg_no) * topo.nodes_per_pkg * topo.cores_per_node) + \
+ ((node_no) * topo.cores_per_node) + \
+ (core_no))
+
+
#define GET_PKG(pkg_base, pkg_no) (pkg_base + pkg_no)
enum counter_scope {SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE};
@@ -244,14 +266,25 @@ struct system_summary {
struct pkg_data packages;
} average;
+struct cpu_topology {
+ int physical_package_id;
+ int logical_cpu_id;
+ int physical_node_id;
+ int logical_node_id; /* 0-based count within the package */
+ int physical_core_id;
+ int thread_id;
+ cpu_set_t *put_ids; /* Processing Unit/Thread IDs */
+} *cpus;
struct topo_params {
int num_packages;
int num_cpus;
int num_cores;
int max_cpu_num;
- int num_cores_per_pkg;
- int num_threads_per_core;
+ int max_node_num;
+ int nodes_per_pkg;
+ int cores_per_node;
+ int threads_per_core;
} topo;
struct timeval tv_even, tv_odd, tv_delta;
@@ -273,27 +306,33 @@ int cpu_is_not_present(int cpu)
int for_all_cpus(int (func)(struct thread_data *, struct core_data *, struct pkg_data *),
struct thread_data *thread_base, struct core_data *core_base, struct pkg_data *pkg_base)
{
- int retval, pkg_no, core_no, thread_no;
+ int retval, pkg_no, core_no, thread_no, node_no;
for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) {
- for (core_no = 0; core_no < topo.num_cores_per_pkg; ++core_no) {
- for (thread_no = 0; thread_no <
- topo.num_threads_per_core; ++thread_no) {
- struct thread_data *t;
- struct core_data *c;
- struct pkg_data *p;
+ for (core_no = 0; core_no < topo.cores_per_node; ++core_no) {
+ for (node_no = 0; node_no < topo.nodes_per_pkg;
+ node_no++) {
+ for (thread_no = 0; thread_no <
+ topo.threads_per_core; ++thread_no) {
+ struct thread_data *t;
+ struct core_data *c;
+ struct pkg_data *p;
- t = GET_THREAD(thread_base, thread_no, core_no, pkg_no);
+ t = GET_THREAD(thread_base, thread_no,
+ core_no, node_no,
+ pkg_no);
- if (cpu_is_not_present(t->cpu_id))
- continue;
+ if (cpu_is_not_present(t->cpu_id))
+ continue;
- c = GET_CORE(core_base, core_no, pkg_no);
- p = GET_PKG(pkg_base, pkg_no);
+ c = GET_CORE(core_base, core_no,
+ node_no, pkg_no);
+ p = GET_PKG(pkg_base, pkg_no);
- retval = func(t, c, p);
- if (retval)
- return retval;
+ retval = func(t, c, p);
+ if (retval)
+ return retval;
+ }
}
}
}
@@ -346,6 +385,8 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
* Thus, strings that are proper sub-sets must follow their more specific peers.
*/
struct msr_counter bic[] = {
+ { 0x0, "usec" },
+ { 0x0, "Time_Of_Day_Seconds" },
{ 0x0, "Package" },
{ 0x0, "Avg_MHz" },
{ 0x0, "Bzy_MHz" },
@@ -369,7 +410,9 @@ struct msr_counter bic[] = {
{ 0x0, "Pkg%pc7" },
{ 0x0, "Pkg%pc8" },
{ 0x0, "Pkg%pc9" },
- { 0x0, "Pkg%pc10" },
+ { 0x0, "Pk%pc10" },
+ { 0x0, "CPU%LPI" },
+ { 0x0, "SYS%LPI" },
{ 0x0, "PkgWatt" },
{ 0x0, "CorWatt" },
{ 0x0, "GFXWatt" },
@@ -389,62 +432,72 @@ struct msr_counter bic[] = {
{ 0x0, "Any%C0" },
{ 0x0, "GFX%C0" },
{ 0x0, "CPUGFX%" },
+ { 0x0, "Node%" },
};
#define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
-#define BIC_Package (1ULL << 0)
-#define BIC_Avg_MHz (1ULL << 1)
-#define BIC_Bzy_MHz (1ULL << 2)
-#define BIC_TSC_MHz (1ULL << 3)
-#define BIC_IRQ (1ULL << 4)
-#define BIC_SMI (1ULL << 5)
-#define BIC_Busy (1ULL << 6)
-#define BIC_CPU_c1 (1ULL << 7)
-#define BIC_CPU_c3 (1ULL << 8)
-#define BIC_CPU_c6 (1ULL << 9)
-#define BIC_CPU_c7 (1ULL << 10)
-#define BIC_ThreadC (1ULL << 11)
-#define BIC_CoreTmp (1ULL << 12)
-#define BIC_CoreCnt (1ULL << 13)
-#define BIC_PkgTmp (1ULL << 14)
-#define BIC_GFX_rc6 (1ULL << 15)
-#define BIC_GFXMHz (1ULL << 16)
-#define BIC_Pkgpc2 (1ULL << 17)
-#define BIC_Pkgpc3 (1ULL << 18)
-#define BIC_Pkgpc6 (1ULL << 19)
-#define BIC_Pkgpc7 (1ULL << 20)
-#define BIC_Pkgpc8 (1ULL << 21)
-#define BIC_Pkgpc9 (1ULL << 22)
-#define BIC_Pkgpc10 (1ULL << 23)
-#define BIC_PkgWatt (1ULL << 24)
-#define BIC_CorWatt (1ULL << 25)
-#define BIC_GFXWatt (1ULL << 26)
-#define BIC_PkgCnt (1ULL << 27)
-#define BIC_RAMWatt (1ULL << 28)
-#define BIC_PKG__ (1ULL << 29)
-#define BIC_RAM__ (1ULL << 30)
-#define BIC_Pkg_J (1ULL << 31)
-#define BIC_Cor_J (1ULL << 32)
-#define BIC_GFX_J (1ULL << 33)
-#define BIC_RAM_J (1ULL << 34)
-#define BIC_Core (1ULL << 35)
-#define BIC_CPU (1ULL << 36)
-#define BIC_Mod_c6 (1ULL << 37)
-#define BIC_sysfs (1ULL << 38)
-#define BIC_Totl_c0 (1ULL << 39)
-#define BIC_Any_c0 (1ULL << 40)
-#define BIC_GFX_c0 (1ULL << 41)
-#define BIC_CPUGFX (1ULL << 42)
+#define BIC_USEC (1ULL << 0)
+#define BIC_TOD (1ULL << 1)
+#define BIC_Package (1ULL << 2)
+#define BIC_Avg_MHz (1ULL << 3)
+#define BIC_Bzy_MHz (1ULL << 4)
+#define BIC_TSC_MHz (1ULL << 5)
+#define BIC_IRQ (1ULL << 6)
+#define BIC_SMI (1ULL << 7)
+#define BIC_Busy (1ULL << 8)
+#define BIC_CPU_c1 (1ULL << 9)
+#define BIC_CPU_c3 (1ULL << 10)
+#define BIC_CPU_c6 (1ULL << 11)
+#define BIC_CPU_c7 (1ULL << 12)
+#define BIC_ThreadC (1ULL << 13)
+#define BIC_CoreTmp (1ULL << 14)
+#define BIC_CoreCnt (1ULL << 15)
+#define BIC_PkgTmp (1ULL << 16)
+#define BIC_GFX_rc6 (1ULL << 17)
+#define BIC_GFXMHz (1ULL << 18)
+#define BIC_Pkgpc2 (1ULL << 19)
+#define BIC_Pkgpc3 (1ULL << 20)
+#define BIC_Pkgpc6 (1ULL << 21)
+#define BIC_Pkgpc7 (1ULL << 22)
+#define BIC_Pkgpc8 (1ULL << 23)
+#define BIC_Pkgpc9 (1ULL << 24)
+#define BIC_Pkgpc10 (1ULL << 25)
+#define BIC_CPU_LPI (1ULL << 26)
+#define BIC_SYS_LPI (1ULL << 27)
+#define BIC_PkgWatt (1ULL << 26)
+#define BIC_CorWatt (1ULL << 27)
+#define BIC_GFXWatt (1ULL << 28)
+#define BIC_PkgCnt (1ULL << 29)
+#define BIC_RAMWatt (1ULL << 30)
+#define BIC_PKG__ (1ULL << 31)
+#define BIC_RAM__ (1ULL << 32)
+#define BIC_Pkg_J (1ULL << 33)
+#define BIC_Cor_J (1ULL << 34)
+#define BIC_GFX_J (1ULL << 35)
+#define BIC_RAM_J (1ULL << 36)
+#define BIC_Core (1ULL << 37)
+#define BIC_CPU (1ULL << 38)
+#define BIC_Mod_c6 (1ULL << 39)
+#define BIC_sysfs (1ULL << 40)
+#define BIC_Totl_c0 (1ULL << 41)
+#define BIC_Any_c0 (1ULL << 42)
+#define BIC_GFX_c0 (1ULL << 43)
+#define BIC_CPUGFX (1ULL << 44)
+#define BIC_Node (1ULL << 45)
-unsigned long long bic_enabled = 0xFFFFFFFFFFFFFFFFULL;
-unsigned long long bic_present = BIC_sysfs;
+#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD)
+
+unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT);
+unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs;
#define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME)
+#define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME)
#define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT)
#define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT)
+
#define MAX_DEFERRED 16
char *deferred_skip_names[MAX_DEFERRED];
int deferred_skip_index;
@@ -469,9 +522,10 @@ void help(void)
"--cpu cpu-set limit output to summary plus cpu-set:\n"
" {core | package | j,k,l..m,n-p }\n"
"--quiet skip decoding system configuration header\n"
- "--interval sec Override default 5-second measurement interval\n"
+ "--interval sec.subsec Override default 5-second measurement interval\n"
"--help print this help message\n"
"--list list column headers only\n"
+ "--num_iterations num number of the measurement iterations\n"
"--out file create or truncate \"file\" for all output\n"
"--version print version information\n"
"\n"
@@ -496,6 +550,9 @@ unsigned long long bic_lookup(char *name_list, enum show_hide_mode mode)
if (comma)
*comma = '\0';
+ if (!strcmp(name_list, "all"))
+ return ~0;
+
for (i = 0; i < MAX_BIC; ++i) {
if (!strcmp(name_list, bic[i].name)) {
retval |= (1ULL << i);
@@ -532,10 +589,14 @@ void print_header(char *delim)
struct msr_counter *mp;
int printed = 0;
- if (debug)
- outp += sprintf(outp, "usec %s", delim);
+ if (DO_BIC(BIC_USEC))
+ outp += sprintf(outp, "%susec", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_TOD))
+ outp += sprintf(outp, "%sTime_Of_Day_Seconds", (printed++ ? delim : ""));
if (DO_BIC(BIC_Package))
outp += sprintf(outp, "%sPackage", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_Node))
+ outp += sprintf(outp, "%sNode", (printed++ ? delim : ""));
if (DO_BIC(BIC_Core))
outp += sprintf(outp, "%sCore", (printed++ ? delim : ""));
if (DO_BIC(BIC_CPU))
@@ -576,7 +637,7 @@ void print_header(char *delim)
if (DO_BIC(BIC_CPU_c1))
outp += sprintf(outp, "%sCPU%%c1", (printed++ ? delim : ""));
- if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates)
+ if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates)
outp += sprintf(outp, "%sCPU%%c3", (printed++ ? delim : ""));
if (DO_BIC(BIC_CPU_c6))
outp += sprintf(outp, "%sCPU%%c6", (printed++ ? delim : ""));
@@ -635,6 +696,10 @@ void print_header(char *delim)
outp += sprintf(outp, "%sPkg%%pc9", (printed++ ? delim : ""));
if (DO_BIC(BIC_Pkgpc10))
outp += sprintf(outp, "%sPk%%pc10", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_CPU_LPI))
+ outp += sprintf(outp, "%sCPU%%LPI", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_SYS_LPI))
+ outp += sprintf(outp, "%sSYS%%LPI", (printed++ ? delim : ""));
if (do_rapl && !rapl_joules) {
if (DO_BIC(BIC_PkgWatt))
@@ -739,6 +804,9 @@ int dump_counters(struct thread_data *t, struct core_data *c,
outp += sprintf(outp, "pc8: %016llX\n", p->pc8);
outp += sprintf(outp, "pc9: %016llX\n", p->pc9);
outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
+ outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
+ outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi);
+ outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi);
outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg);
outp += sprintf(outp, "Joules COR: %0X\n", p->energy_cores);
outp += sprintf(outp, "Joules GFX: %0X\n", p->energy_gfx);
@@ -786,7 +854,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
(cpu_subset && !CPU_ISSET_S(t->cpu_id, cpu_subset_size, cpu_subset)))
return 0;
- if (debug) {
+ if (DO_BIC(BIC_USEC)) {
/* on each row, print how many usec each timestamp took to gather */
struct timeval tv;
@@ -794,6 +862,10 @@ int format_counters(struct thread_data *t, struct core_data *c,
outp += sprintf(outp, "%5ld\t", tv.tv_sec * 1000000 + tv.tv_usec);
}
+ /* Time_Of_Day_Seconds: on each row, print sec.usec last timestamp taken */
+ if (DO_BIC(BIC_TOD))
+ outp += sprintf(outp, "%10ld.%06ld\t", t->tv_end.tv_sec, t->tv_end.tv_usec);
+
interval_float = tv_delta.tv_sec + tv_delta.tv_usec/1000000.0;
tsc = t->tsc * tsc_tweak;
@@ -802,6 +874,8 @@ int format_counters(struct thread_data *t, struct core_data *c,
if (t == &average.threads) {
if (DO_BIC(BIC_Package))
outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_Node))
+ outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
if (DO_BIC(BIC_Core))
outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
if (DO_BIC(BIC_CPU))
@@ -813,6 +887,15 @@ int format_counters(struct thread_data *t, struct core_data *c,
else
outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
}
+ if (DO_BIC(BIC_Node)) {
+ if (t)
+ outp += sprintf(outp, "%s%d",
+ (printed++ ? delim : ""),
+ cpus[t->cpu_id].physical_node_id);
+ else
+ outp += sprintf(outp, "%s-",
+ (printed++ ? delim : ""));
+ }
if (DO_BIC(BIC_Core)) {
if (c)
outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), c->core_id);
@@ -882,7 +965,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
goto done;
- if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates)
+ if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates)
outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c3/tsc);
if (DO_BIC(BIC_CPU_c6))
outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c6/tsc);
@@ -959,6 +1042,11 @@ int format_counters(struct thread_data *t, struct core_data *c,
if (DO_BIC(BIC_Pkgpc10))
outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc10/tsc);
+ if (DO_BIC(BIC_CPU_LPI))
+ outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->cpu_lpi / 1000000.0 / interval_float);
+ if (DO_BIC(BIC_SYS_LPI))
+ outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->sys_lpi / 1000000.0 / interval_float);
+
/*
* If measurement interval exceeds minimum RAPL Joule Counter range,
* indicate that results are suspect by printing "**" in fraction place.
@@ -1006,7 +1094,8 @@ int format_counters(struct thread_data *t, struct core_data *c,
}
done:
- outp += sprintf(outp, "\n");
+ if (*(outp - 1) != '\n')
+ outp += sprintf(outp, "\n");
return 0;
}
@@ -1083,6 +1172,8 @@ delta_package(struct pkg_data *new, struct pkg_data *old)
old->pc8 = new->pc8 - old->pc8;
old->pc9 = new->pc9 - old->pc9;
old->pc10 = new->pc10 - old->pc10;
+ old->cpu_lpi = new->cpu_lpi - old->cpu_lpi;
+ old->sys_lpi = new->sys_lpi - old->sys_lpi;
old->pkg_temp_c = new->pkg_temp_c;
/* flag an error when rc6 counter resets/wraps */
@@ -1140,6 +1231,15 @@ delta_thread(struct thread_data *new, struct thread_data *old,
int i;
struct msr_counter *mp;
+ /*
+ * the timestamps from start of measurement interval are in "old"
+ * the timestamp from end of measurement interval are in "new"
+ * over-write old w/ new so we can print end of interval values
+ */
+
+ old->tv_begin = new->tv_begin;
+ old->tv_end = new->tv_end;
+
old->tsc = new->tsc - old->tsc;
/* check for TSC < 1 Mcycles over interval */
@@ -1228,6 +1328,11 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
int i;
struct msr_counter *mp;
+ t->tv_begin.tv_sec = 0;
+ t->tv_begin.tv_usec = 0;
+ t->tv_end.tv_sec = 0;
+ t->tv_end.tv_usec = 0;
+
t->tsc = 0;
t->aperf = 0;
t->mperf = 0;
@@ -1260,6 +1365,8 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
p->pc8 = 0;
p->pc9 = 0;
p->pc10 = 0;
+ p->cpu_lpi = 0;
+ p->sys_lpi = 0;
p->energy_pkg = 0;
p->energy_dram = 0;
@@ -1286,6 +1393,13 @@ int sum_counters(struct thread_data *t, struct core_data *c,
int i;
struct msr_counter *mp;
+ /* remember first tv_begin */
+ if (average.threads.tv_begin.tv_sec == 0)
+ average.threads.tv_begin = t->tv_begin;
+
+ /* remember last tv_end */
+ average.threads.tv_end = t->tv_end;
+
average.threads.tsc += t->tsc;
average.threads.aperf += t->aperf;
average.threads.mperf += t->mperf;
@@ -1341,6 +1455,9 @@ int sum_counters(struct thread_data *t, struct core_data *c,
average.packages.pc9 += p->pc9;
average.packages.pc10 += p->pc10;
+ average.packages.cpu_lpi = p->cpu_lpi;
+ average.packages.sys_lpi = p->sys_lpi;
+
average.packages.energy_pkg += p->energy_pkg;
average.packages.energy_dram += p->energy_dram;
average.packages.energy_cores += p->energy_cores;
@@ -1487,7 +1604,7 @@ int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp)
if (get_msr(cpu, mp->msr_num, counterp))
return -1;
} else {
- char path[128];
+ char path[128 + PATH_BYTES];
if (mp->flags & SYSFS_PERCPU) {
sprintf(path, "/sys/devices/system/cpu/cpu%d/%s",
@@ -1603,7 +1720,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
goto done;
- if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates) {
+ if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates) {
if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
return -6;
}
@@ -1684,6 +1801,11 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
if (get_msr(cpu, MSR_PKG_C10_RESIDENCY, &p->pc10))
return -13;
+ if (DO_BIC(BIC_CPU_LPI))
+ p->cpu_lpi = cpuidle_cur_cpu_lpi_us;
+ if (DO_BIC(BIC_SYS_LPI))
+ p->sys_lpi = cpuidle_cur_sys_lpi_us;
+
if (do_rapl & RAPL_PKG) {
if (get_msr(cpu, MSR_PKG_ENERGY_STATUS, &msr))
return -13;
@@ -1769,7 +1891,7 @@ int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV,
int amt_pkg_cstate_limits[16] = {PCLUNL, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
int bxt_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
-int skx_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
+int skx_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
static void
@@ -2071,12 +2193,9 @@ dump_nhm_cst_cfg(void)
get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr);
-#define SNB_C1_AUTO_UNDEMOTE (1UL << 27)
-#define SNB_C3_AUTO_UNDEMOTE (1UL << 28)
-
fprintf(outf, "cpu%d: MSR_PKG_CST_CONFIG_CONTROL: 0x%08llx", base_cpu, msr);
- fprintf(outf, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: %s)\n",
+ fprintf(outf, " (%s%s%s%s%slocked, pkg-cstate-limit=%d (%s)",
(msr & SNB_C3_AUTO_UNDEMOTE) ? "UNdemote-C3, " : "",
(msr & SNB_C1_AUTO_UNDEMOTE) ? "UNdemote-C1, " : "",
(msr & NHM_C3_AUTO_DEMOTE) ? "demote-C3, " : "",
@@ -2084,6 +2203,15 @@ dump_nhm_cst_cfg(void)
(msr & (1 << 15)) ? "" : "UN",
(unsigned int)msr & 0xF,
pkg_cstate_limit_strings[pkg_cstate_limit]);
+
+#define AUTOMATIC_CSTATE_CONVERSION (1UL << 16)
+ if (has_automatic_cstate_conversion) {
+ fprintf(outf, ", automatic c-state conversion=%s",
+ (msr & AUTOMATIC_CSTATE_CONVERSION) ? "on" : "off");
+ }
+
+ fprintf(outf, ")\n");
+
return;
}
@@ -2184,6 +2312,8 @@ void free_fd_percpu(void)
void free_all_buffers(void)
{
+ int i;
+
CPU_FREE(cpu_present_set);
cpu_present_set = NULL;
cpu_present_setsize = 0;
@@ -2216,6 +2346,12 @@ void free_all_buffers(void)
free(irq_column_2_cpu);
free(irqs_per_cpu);
+
+ for (i = 0; i <= topo.max_cpu_num; ++i) {
+ if (cpus[i].put_ids)
+ CPU_FREE(cpus[i].put_ids);
+ }
+ free(cpus);
}
@@ -2240,44 +2376,6 @@ int parse_int_file(const char *fmt, ...)
}
/*
- * get_cpu_position_in_core(cpu)
- * return the position of the CPU among its HT siblings in the core
- * return -1 if the sibling is not in list
- */
-int get_cpu_position_in_core(int cpu)
-{
- char path[64];
- FILE *filep;
- int this_cpu;
- char character;
- int i;
-
- sprintf(path,
- "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list",
- cpu);
- filep = fopen(path, "r");
- if (filep == NULL) {
- perror(path);
- exit(1);
- }
-
- for (i = 0; i < topo.num_threads_per_core; i++) {
- fscanf(filep, "%d", &this_cpu);
- if (this_cpu == cpu) {
- fclose(filep);
- return i;
- }
-
- /* Account for no separator after last thread*/
- if (i != (topo.num_threads_per_core - 1))
- fscanf(filep, "%c", &character);
- }
-
- fclose(filep);
- return -1;
-}
-
-/*
* cpu_is_first_core_in_package(cpu)
* return 1 if given CPU is 1st core in package
*/
@@ -2296,35 +2394,115 @@ int get_core_id(int cpu)
return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/core_id", cpu);
}
-int get_num_ht_siblings(int cpu)
+void set_node_data(void)
{
char path[80];
FILE *filep;
- int sib1;
- int matches = 0;
- char character;
- char str[100];
- char *ch;
+ int pkg, node, cpu;
- sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu);
- filep = fopen_or_die(path, "r");
+ struct pkg_node_info {
+ int count;
+ int min;
+ } *pni;
- /*
- * file format:
- * A ',' separated or '-' separated set of numbers
- * (eg 1-2 or 1,3,4,5)
- */
- fscanf(filep, "%d%c\n", &sib1, &character);
- fseek(filep, 0, SEEK_SET);
- fgets(str, 100, filep);
- ch = strchr(str, character);
- while (ch != NULL) {
- matches++;
- ch = strchr(ch+1, character);
+ pni = calloc(topo.num_packages, sizeof(struct pkg_node_info));
+ if (!pni)
+ err(1, "calloc pkg_node_count");
+
+ for (pkg = 0; pkg < topo.num_packages; pkg++)
+ pni[pkg].min = topo.num_cpus;
+
+ for (node = 0; node <= topo.max_node_num; node++) {
+ /* find the "first" cpu in the node */
+ sprintf(path, "/sys/bus/node/devices/node%d/cpulist", node);
+ filep = fopen(path, "r");
+ if (!filep)
+ continue;
+ fscanf(filep, "%d", &cpu);
+ fclose(filep);
+
+ pkg = cpus[cpu].physical_package_id;
+ pni[pkg].count++;
+
+ if (node < pni[pkg].min)
+ pni[pkg].min = node;
}
+ for (pkg = 0; pkg < topo.num_packages; pkg++)
+ if (pni[pkg].count > topo.nodes_per_pkg)
+ topo.nodes_per_pkg = pni[0].count;
+
+ for (cpu = 0; cpu < topo.num_cpus; cpu++) {
+ pkg = cpus[cpu].physical_package_id;
+ node = cpus[cpu].physical_node_id;
+ cpus[cpu].logical_node_id = node - pni[pkg].min;
+ }
+ free(pni);
+
+}
+
+int get_physical_node_id(struct cpu_topology *thiscpu)
+{
+ char path[80];
+ FILE *filep;
+ int i;
+ int cpu = thiscpu->logical_cpu_id;
+
+ for (i = 0; i <= topo.max_cpu_num; i++) {
+ sprintf(path, "/sys/devices/system/cpu/cpu%d/node%i/cpulist",
+ cpu, i);
+ filep = fopen(path, "r");
+ if (!filep)
+ continue;
+ fclose(filep);
+ return i;
+ }
+ return -1;
+}
+
+int get_thread_siblings(struct cpu_topology *thiscpu)
+{
+ char path[80], character;
+ FILE *filep;
+ unsigned long map;
+ int so, shift, sib_core;
+ int cpu = thiscpu->logical_cpu_id;
+ int offset = topo.max_cpu_num + 1;
+ size_t size;
+ int thread_id = 0;
+
+ thiscpu->put_ids = CPU_ALLOC((topo.max_cpu_num + 1));
+ if (thiscpu->thread_id < 0)
+ thiscpu->thread_id = thread_id++;
+ if (!thiscpu->put_ids)
+ return -1;
+
+ size = CPU_ALLOC_SIZE((topo.max_cpu_num + 1));
+ CPU_ZERO_S(size, thiscpu->put_ids);
+
+ sprintf(path,
+ "/sys/devices/system/cpu/cpu%d/topology/thread_siblings", cpu);
+ filep = fopen_or_die(path, "r");
+ do {
+ offset -= BITMASK_SIZE;
+ fscanf(filep, "%lx%c", &map, &character);
+ for (shift = 0; shift < BITMASK_SIZE; shift++) {
+ if ((map >> shift) & 0x1) {
+ so = shift + offset;
+ sib_core = get_core_id(so);
+ if (sib_core == thiscpu->physical_core_id) {
+ CPU_SET_S(so, size, thiscpu->put_ids);
+ if ((so != cpu) &&
+ (cpus[so].thread_id < 0))
+ cpus[so].thread_id =
+ thread_id++;
+ }
+ }
+ }
+ } while (!strncmp(&character, ",", 1));
fclose(filep);
- return matches+1;
+
+ return CPU_COUNT_S(size, thiscpu->put_ids);
}
/*
@@ -2339,32 +2517,42 @@ int for_all_cpus_2(int (func)(struct thread_data *, struct core_data *,
struct thread_data *thread_base2, struct core_data *core_base2,
struct pkg_data *pkg_base2)
{
- int retval, pkg_no, core_no, thread_no;
+ int retval, pkg_no, node_no, core_no, thread_no;
for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) {
- for (core_no = 0; core_no < topo.num_cores_per_pkg; ++core_no) {
- for (thread_no = 0; thread_no <
- topo.num_threads_per_core; ++thread_no) {
- struct thread_data *t, *t2;
- struct core_data *c, *c2;
- struct pkg_data *p, *p2;
+ for (node_no = 0; node_no < topo.nodes_per_pkg; ++node_no) {
+ for (core_no = 0; core_no < topo.cores_per_node;
+ ++core_no) {
+ for (thread_no = 0; thread_no <
+ topo.threads_per_core; ++thread_no) {
+ struct thread_data *t, *t2;
+ struct core_data *c, *c2;
+ struct pkg_data *p, *p2;
- t = GET_THREAD(thread_base, thread_no, core_no, pkg_no);
+ t = GET_THREAD(thread_base, thread_no,
+ core_no, node_no,
+ pkg_no);
- if (cpu_is_not_present(t->cpu_id))
- continue;
+ if (cpu_is_not_present(t->cpu_id))
+ continue;
- t2 = GET_THREAD(thread_base2, thread_no, core_no, pkg_no);
+ t2 = GET_THREAD(thread_base2, thread_no,
+ core_no, node_no,
+ pkg_no);
- c = GET_CORE(core_base, core_no, pkg_no);
- c2 = GET_CORE(core_base2, core_no, pkg_no);
+ c = GET_CORE(core_base, core_no,
+ node_no, pkg_no);
+ c2 = GET_CORE(core_base2, core_no,
+ node_no,
+ pkg_no);
- p = GET_PKG(pkg_base, pkg_no);
- p2 = GET_PKG(pkg_base2, pkg_no);
+ p = GET_PKG(pkg_base, pkg_no);
+ p2 = GET_PKG(pkg_base2, pkg_no);
- retval = func(t, c, p, t2, c2, p2);
- if (retval)
- return retval;
+ retval = func(t, c, p, t2, c2, p2);
+ if (retval)
+ return retval;
+ }
}
}
}
@@ -2409,6 +2597,20 @@ void re_initialize(void)
printf("turbostat: re-initialized with num_cpus %d\n", topo.num_cpus);
}
+void set_max_cpu_num(void)
+{
+ FILE *filep;
+ unsigned long dummy;
+
+ topo.max_cpu_num = 0;
+ filep = fopen_or_die(
+ "/sys/devices/system/cpu/cpu0/topology/thread_siblings",
+ "r");
+ while (fscanf(filep, "%lx,", &dummy) == 1)
+ topo.max_cpu_num += BITMASK_SIZE;
+ fclose(filep);
+ topo.max_cpu_num--; /* 0 based */
+}
/*
* count_cpus()
@@ -2416,10 +2618,7 @@ void re_initialize(void)
*/
int count_cpus(int cpu)
{
- if (topo.max_cpu_num < cpu)
- topo.max_cpu_num = cpu;
-
- topo.num_cpus += 1;
+ topo.num_cpus++;
return 0;
}
int mark_cpu_present(int cpu)
@@ -2428,6 +2627,12 @@ int mark_cpu_present(int cpu)
return 0;
}
+int init_thread_id(int cpu)
+{
+ cpus[cpu].thread_id = -1;
+ return 0;
+}
+
/*
* snapshot_proc_interrupts()
*
@@ -2542,6 +2747,52 @@ int snapshot_gfx_mhz(void)
}
/*
+ * snapshot_cpu_lpi()
+ *
+ * record snapshot of
+ * /sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us
+ *
+ * return 1 if config change requires a restart, else return 0
+ */
+int snapshot_cpu_lpi_us(void)
+{
+ FILE *fp;
+ int retval;
+
+ fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", "r");
+
+ retval = fscanf(fp, "%lld", &cpuidle_cur_cpu_lpi_us);
+ if (retval != 1)
+ err(1, "CPU LPI");
+
+ fclose(fp);
+
+ return 0;
+}
+/*
+ * snapshot_sys_lpi()
+ *
+ * record snapshot of
+ * /sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us
+ *
+ * return 1 if config change requires a restart, else return 0
+ */
+int snapshot_sys_lpi_us(void)
+{
+ FILE *fp;
+ int retval;
+
+ fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", "r");
+
+ retval = fscanf(fp, "%lld", &cpuidle_cur_sys_lpi_us);
+ if (retval != 1)
+ err(1, "SYS LPI");
+
+ fclose(fp);
+
+ return 0;
+}
+/*
* snapshot /proc and /sys files
*
* return 1 if configuration restart needed, else return 0
@@ -2558,13 +2809,83 @@ int snapshot_proc_sysfs_files(void)
if (DO_BIC(BIC_GFXMHz))
snapshot_gfx_mhz();
+ if (DO_BIC(BIC_CPU_LPI))
+ snapshot_cpu_lpi_us();
+
+ if (DO_BIC(BIC_SYS_LPI))
+ snapshot_sys_lpi_us();
+
return 0;
}
+int exit_requested;
+
+static void signal_handler (int signal)
+{
+ switch (signal) {
+ case SIGINT:
+ exit_requested = 1;
+ if (debug)
+ fprintf(stderr, " SIGINT\n");
+ break;
+ case SIGUSR1:
+ if (debug > 1)
+ fprintf(stderr, "SIGUSR1\n");
+ break;
+ }
+ /* make sure this manually-invoked interval is at least 1ms long */
+ nanosleep(&one_msec, NULL);
+}
+
+void setup_signal_handler(void)
+{
+ struct sigaction sa;
+
+ memset(&sa, 0, sizeof(sa));
+
+ sa.sa_handler = &signal_handler;
+
+ if (sigaction(SIGINT, &sa, NULL) < 0)
+ err(1, "sigaction SIGINT");
+ if (sigaction(SIGUSR1, &sa, NULL) < 0)
+ err(1, "sigaction SIGUSR1");
+}
+
+void do_sleep(void)
+{
+ struct timeval select_timeout;
+ fd_set readfds;
+ int retval;
+
+ FD_ZERO(&readfds);
+ FD_SET(0, &readfds);
+
+ if (!isatty(fileno(stdin))) {
+ nanosleep(&interval_ts, NULL);
+ return;
+ }
+
+ select_timeout = interval_tv;
+ retval = select(1, &readfds, NULL, NULL, &select_timeout);
+
+ if (retval == 1) {
+ switch (getc(stdin)) {
+ case 'q':
+ exit_requested = 1;
+ break;
+ }
+ /* make sure this manually-invoked interval is at least 1ms long */
+ nanosleep(&one_msec, NULL);
+ }
+}
+
void turbostat_loop()
{
int retval;
int restarted = 0;
+ int done_iters = 0;
+
+ setup_signal_handler();
restart:
restarted++;
@@ -2581,6 +2902,7 @@ void turbostat_loop()
goto restart;
}
restarted = 0;
+ done_iters = 0;
gettimeofday(&tv_even, (struct timezone *)NULL);
while (1) {
@@ -2588,7 +2910,7 @@ void turbostat_loop()
re_initialize();
goto restart;
}
- nanosleep(&interval_ts, NULL);
+ do_sleep();
if (snapshot_proc_sysfs_files())
goto restart;
retval = for_all_cpus(get_counters, ODD_COUNTERS);
@@ -2607,7 +2929,11 @@ void turbostat_loop()
compute_average(EVEN_COUNTERS);
format_all_counters(EVEN_COUNTERS);
flush_output_stdout();
- nanosleep(&interval_ts, NULL);
+ if (exit_requested)
+ break;
+ if (num_iterations && ++done_iters >= num_iterations)
+ break;
+ do_sleep();
if (snapshot_proc_sysfs_files())
goto restart;
retval = for_all_cpus(get_counters, EVEN_COUNTERS);
@@ -2626,6 +2952,10 @@ void turbostat_loop()
compute_average(ODD_COUNTERS);
format_all_counters(ODD_COUNTERS);
flush_output_stdout();
+ if (exit_requested)
+ break;
+ if (num_iterations && ++done_iters >= num_iterations)
+ break;
}
}
@@ -2740,6 +3070,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */
case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */
case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */
+ case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */
pkg_cstate_limits = hsw_pkg_cstate_limits;
has_misc_feature_control = 1;
break;
@@ -2945,6 +3276,7 @@ int has_config_tdp(unsigned int family, unsigned int model)
case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */
case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */
case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */
+ case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */
case INTEL_FAM6_SKYLAKE_X: /* SKX */
case INTEL_FAM6_XEON_PHI_KNL: /* Knights Landing */
@@ -3399,6 +3731,7 @@ void rapl_probe(unsigned int family, unsigned int model)
case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */
case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */
case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */
+ case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */
do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO;
BIC_PRESENT(BIC_PKG__);
BIC_PRESENT(BIC_RAM__);
@@ -3523,6 +3856,12 @@ void perf_limit_reasons_probe(unsigned int family, unsigned int model)
}
}
+void automatic_cstate_conversion_probe(unsigned int family, unsigned int model)
+{
+ if (is_skx(family, model) || is_bdx(family, model))
+ has_automatic_cstate_conversion = 1;
+}
+
int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p)
{
unsigned long long msr;
@@ -3728,6 +4067,7 @@ int has_snb_msrs(unsigned int family, unsigned int model)
case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */
case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */
case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */
+ case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */
case INTEL_FAM6_SKYLAKE_X: /* SKX */
case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */
case INTEL_FAM6_ATOM_GEMINI_LAKE:
@@ -3761,6 +4101,7 @@ int has_hsw_msrs(unsigned int family, unsigned int model)
case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */
case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */
case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */
+ case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */
case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */
case INTEL_FAM6_ATOM_GEMINI_LAKE:
return 1;
@@ -3786,6 +4127,7 @@ int has_skl_msrs(unsigned int family, unsigned int model)
case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */
case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */
case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */
+ case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */
return 1;
}
return 0;
@@ -3815,6 +4157,19 @@ int is_knl(unsigned int family, unsigned int model)
return 0;
}
+int is_cnl(unsigned int family, unsigned int model)
+{
+ if (!genuine_intel)
+ return 0;
+
+ switch (model) {
+ case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */
+ return 1;
+ }
+
+ return 0;
+}
+
unsigned int get_aperf_mperf_multiplier(unsigned int family, unsigned int model)
{
if (is_knl(family, model))
@@ -3947,7 +4302,7 @@ void decode_misc_enable_msr(void)
base_cpu, msr,
msr & MSR_IA32_MISC_ENABLE_TM1 ? "" : "No-",
msr & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP ? "" : "No-",
- msr & MSR_IA32_MISC_ENABLE_MWAIT ? "No-" : "",
+ msr & MSR_IA32_MISC_ENABLE_MWAIT ? "" : "No-",
msr & MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE ? "No-" : "",
msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ? "No-" : "");
}
@@ -4152,7 +4507,6 @@ void process_cpuid()
case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */
crystal_hz = 24000000; /* 24.0 MHz */
break;
- case INTEL_FAM6_SKYLAKE_X: /* SKX */
case INTEL_FAM6_ATOM_DENVERTON: /* DNV */
crystal_hz = 25000000; /* 25.0 MHz */
break;
@@ -4253,6 +4607,7 @@ void process_cpuid()
}
do_slm_cstates = is_slm(family, model);
do_knl_cstates = is_knl(family, model);
+ do_cnl_cstates = is_cnl(family, model);
if (!quiet)
decode_misc_pwr_mgmt_msr();
@@ -4262,6 +4617,7 @@ void process_cpuid()
rapl_probe(family, model);
perf_limit_reasons_probe(family, model);
+ automatic_cstate_conversion_probe(family, model);
if (!quiet)
dump_cstate_pstate_config_info(family, model);
@@ -4280,6 +4636,16 @@ void process_cpuid()
if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
BIC_PRESENT(BIC_GFXMHz);
+ if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", R_OK))
+ BIC_PRESENT(BIC_CPU_LPI);
+ else
+ BIC_NOT_PRESENT(BIC_CPU_LPI);
+
+ if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", R_OK))
+ BIC_PRESENT(BIC_SYS_LPI);
+ else
+ BIC_NOT_PRESENT(BIC_SYS_LPI);
+
if (!quiet)
decode_misc_feature_control();
@@ -4310,14 +4676,10 @@ void topology_probe()
int max_core_id = 0;
int max_package_id = 0;
int max_siblings = 0;
- struct cpu_topology {
- int core_id;
- int physical_package_id;
- } *cpus;
/* Initialize num_cpus, max_cpu_num */
+ set_max_cpu_num();
topo.num_cpus = 0;
- topo.max_cpu_num = 0;
for_all_proc_cpus(count_cpus);
if (!summary_only && topo.num_cpus > 1)
BIC_PRESENT(BIC_CPU);
@@ -4357,6 +4719,7 @@ void topology_probe()
cpu_affinity_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1));
CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set);
+ for_all_proc_cpus(init_thread_id);
/*
* For online cpus
@@ -4370,26 +4733,45 @@ void topology_probe()
fprintf(outf, "cpu%d NOT PRESENT\n", i);
continue;
}
- cpus[i].core_id = get_core_id(i);
- if (cpus[i].core_id > max_core_id)
- max_core_id = cpus[i].core_id;
+ cpus[i].logical_cpu_id = i;
+
+ /* get package information */
cpus[i].physical_package_id = get_physical_package_id(i);
if (cpus[i].physical_package_id > max_package_id)
max_package_id = cpus[i].physical_package_id;
- siblings = get_num_ht_siblings(i);
+ /* get numa node information */
+ cpus[i].physical_node_id = get_physical_node_id(&cpus[i]);
+ if (cpus[i].physical_node_id > topo.max_node_num)
+ topo.max_node_num = cpus[i].physical_node_id;
+
+ /* get core information */
+ cpus[i].physical_core_id = get_core_id(i);
+ if (cpus[i].physical_core_id > max_core_id)
+ max_core_id = cpus[i].physical_core_id;
+
+ /* get thread information */
+ siblings = get_thread_siblings(&cpus[i]);
if (siblings > max_siblings)
max_siblings = siblings;
+ if (cpus[i].thread_id != -1)
+ topo.num_cores++;
+
if (debug > 1)
- fprintf(outf, "cpu %d pkg %d core %d\n",
- i, cpus[i].physical_package_id, cpus[i].core_id);
+ fprintf(outf,
+ "cpu %d pkg %d node %d core %d thread %d\n",
+ i, cpus[i].physical_package_id,
+ cpus[i].physical_node_id,
+ cpus[i].physical_core_id,
+ cpus[i].thread_id);
}
- topo.num_cores_per_pkg = max_core_id + 1;
+
+ topo.cores_per_node = max_core_id + 1;
if (debug > 1)
fprintf(outf, "max_core_id %d, sizing for %d cores per package\n",
- max_core_id, topo.num_cores_per_pkg);
- if (!summary_only && topo.num_cores_per_pkg > 1)
+ max_core_id, topo.cores_per_node);
+ if (!summary_only && topo.cores_per_node > 1)
BIC_PRESENT(BIC_Core);
topo.num_packages = max_package_id + 1;
@@ -4399,33 +4781,38 @@ void topology_probe()
if (!summary_only && topo.num_packages > 1)
BIC_PRESENT(BIC_Package);
- topo.num_threads_per_core = max_siblings;
+ set_node_data();
+ if (debug > 1)
+ fprintf(outf, "nodes_per_pkg %d\n", topo.nodes_per_pkg);
+ if (!summary_only && topo.nodes_per_pkg > 1)
+ BIC_PRESENT(BIC_Node);
+
+ topo.threads_per_core = max_siblings;
if (debug > 1)
fprintf(outf, "max_siblings %d\n", max_siblings);
-
- free(cpus);
}
void
-allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data **p)
+allocate_counters(struct thread_data **t, struct core_data **c,
+ struct pkg_data **p)
{
int i;
+ int num_cores = topo.cores_per_node * topo.nodes_per_pkg *
+ topo.num_packages;
+ int num_threads = topo.threads_per_core * num_cores;
- *t = calloc(topo.num_threads_per_core * topo.num_cores_per_pkg *
- topo.num_packages, sizeof(struct thread_data));
+ *t = calloc(num_threads, sizeof(struct thread_data));
if (*t == NULL)
goto error;
- for (i = 0; i < topo.num_threads_per_core *
- topo.num_cores_per_pkg * topo.num_packages; i++)
+ for (i = 0; i < num_threads; i++)
(*t)[i].cpu_id = -1;
- *c = calloc(topo.num_cores_per_pkg * topo.num_packages,
- sizeof(struct core_data));
+ *c = calloc(num_cores, sizeof(struct core_data));
if (*c == NULL)
goto error;
- for (i = 0; i < topo.num_cores_per_pkg * topo.num_packages; i++)
+ for (i = 0; i < num_cores; i++)
(*c)[i].core_id = -1;
*p = calloc(topo.num_packages, sizeof(struct pkg_data));
@@ -4442,47 +4829,39 @@ allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data
/*
* init_counter()
*
- * set cpu_id, core_num, pkg_num
* set FIRST_THREAD_IN_CORE and FIRST_CORE_IN_PACKAGE
- *
- * increment topo.num_cores when 1st core in pkg seen
*/
void init_counter(struct thread_data *thread_base, struct core_data *core_base,
- struct pkg_data *pkg_base, int thread_num, int core_num,
- int pkg_num, int cpu_id)
+ struct pkg_data *pkg_base, int cpu_id)
{
+ int pkg_id = cpus[cpu_id].physical_package_id;
+ int node_id = cpus[cpu_id].logical_node_id;
+ int core_id = cpus[cpu_id].physical_core_id;
+ int thread_id = cpus[cpu_id].thread_id;
struct thread_data *t;
struct core_data *c;
struct pkg_data *p;
- t = GET_THREAD(thread_base, thread_num, core_num, pkg_num);
- c = GET_CORE(core_base, core_num, pkg_num);
- p = GET_PKG(pkg_base, pkg_num);
+ t = GET_THREAD(thread_base, thread_id, core_id, node_id, pkg_id);
+ c = GET_CORE(core_base, core_id, node_id, pkg_id);
+ p = GET_PKG(pkg_base, pkg_id);
t->cpu_id = cpu_id;
- if (thread_num == 0) {
+ if (thread_id == 0) {
t->flags |= CPU_IS_FIRST_THREAD_IN_CORE;
if (cpu_is_first_core_in_package(cpu_id))
t->flags |= CPU_IS_FIRST_CORE_IN_PACKAGE;
}
- c->core_id = core_num;
- p->package_id = pkg_num;
+ c->core_id = core_id;
+ p->package_id = pkg_id;
}
int initialize_counters(int cpu_id)
{
- int my_thread_id, my_core_id, my_package_id;
-
- my_package_id = get_physical_package_id(cpu_id);
- my_core_id = get_core_id(cpu_id);
- my_thread_id = get_cpu_position_in_core(cpu_id);
- if (!my_thread_id)
- topo.num_cores++;
-
- init_counter(EVEN_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id);
- init_counter(ODD_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id);
+ init_counter(EVEN_COUNTERS, cpu_id);
+ init_counter(ODD_COUNTERS, cpu_id);
return 0;
}
@@ -4630,7 +5009,7 @@ int get_and_dump_counters(void)
}
void print_version() {
- fprintf(outf, "turbostat version 17.06.23"
+ fprintf(outf, "turbostat version 18.06.01"
" - Len Brown <lenb@kernel.org>\n");
}
@@ -4661,7 +5040,7 @@ int add_counter(unsigned int msr_num, char *path, char *name,
msrp->next = sys.tp;
sys.tp = msrp;
sys.added_thread_counters++;
- if (sys.added_thread_counters > MAX_ADDED_COUNTERS) {
+ if (sys.added_thread_counters > MAX_ADDED_THREAD_COUNTERS) {
fprintf(stderr, "exceeded max %d added thread counters\n",
MAX_ADDED_COUNTERS);
exit(-1);
@@ -4820,7 +5199,7 @@ void probe_sysfs(void)
if (!DO_BIC(BIC_sysfs))
return;
- for (state = 10; state > 0; --state) {
+ for (state = 10; state >= 0; --state) {
sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name",
base_cpu, state);
@@ -4847,7 +5226,7 @@ void probe_sysfs(void)
FORMAT_PERCENT, SYSFS_PERCPU);
}
- for (state = 10; state > 0; --state) {
+ for (state = 10; state >= 0; --state) {
sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name",
base_cpu, state);
@@ -4960,34 +5339,6 @@ void parse_cpu_command(char *optarg)
exit(-1);
}
-int shown;
-/*
- * parse_show_hide() - process cmdline to set default counter action
- */
-void parse_show_hide(char *optarg, enum show_hide_mode new_mode)
-{
- /*
- * --show: show only those specified
- * The 1st invocation will clear and replace the enabled mask
- * subsequent invocations can add to it.
- */
- if (new_mode == SHOW_LIST) {
- if (shown == 0)
- bic_enabled = bic_lookup(optarg, new_mode);
- else
- bic_enabled |= bic_lookup(optarg, new_mode);
- shown = 1;
-
- return;
- }
-
- /*
- * --hide: do not show those specified
- * multiple invocations simply clear more bits in enabled mask
- */
- bic_enabled &= ~bic_lookup(optarg, new_mode);
-
-}
void cmdline(int argc, char **argv)
{
@@ -4998,7 +5349,9 @@ void cmdline(int argc, char **argv)
{"cpu", required_argument, 0, 'c'},
{"Dump", no_argument, 0, 'D'},
{"debug", no_argument, 0, 'd'}, /* internal, not documented */
+ {"enable", required_argument, 0, 'e'},
{"interval", required_argument, 0, 'i'},
+ {"num_iterations", required_argument, 0, 'n'},
{"help", no_argument, 0, 'h'},
{"hide", required_argument, 0, 'H'}, // meh, -h taken by --help
{"Joules", no_argument, 0, 'J'},
@@ -5014,7 +5367,7 @@ void cmdline(int argc, char **argv)
progname = argv[0];
- while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:qST:v",
+ while ((opt = getopt_long_only(argc, argv, "+C:c:Dde:hi:Jn:o:qST:v",
long_options, &option_index)) != -1) {
switch (opt) {
case 'a':
@@ -5026,11 +5379,20 @@ void cmdline(int argc, char **argv)
case 'D':
dump_only++;
break;
+ case 'e':
+ /* --enable specified counter */
+ bic_enabled |= bic_lookup(optarg, SHOW_LIST);
+ break;
case 'd':
debug++;
+ ENABLE_BIC(BIC_DISABLED_BY_DEFAULT);
break;
case 'H':
- parse_show_hide(optarg, HIDE_LIST);
+ /*
+ * --hide: do not show those specified
+ * multiple invocations simply clear more bits in enabled mask
+ */
+ bic_enabled &= ~bic_lookup(optarg, HIDE_LIST);
break;
case 'h':
default:
@@ -5046,7 +5408,8 @@ void cmdline(int argc, char **argv)
exit(2);
}
- interval_ts.tv_sec = interval;
+ interval_tv.tv_sec = interval_ts.tv_sec = interval;
+ interval_tv.tv_usec = (interval - interval_tv.tv_sec) * 1000000;
interval_ts.tv_nsec = (interval - interval_ts.tv_sec) * 1000000000;
}
break;
@@ -5054,6 +5417,7 @@ void cmdline(int argc, char **argv)
rapl_joules++;
break;
case 'l':
+ ENABLE_BIC(BIC_DISABLED_BY_DEFAULT);
list_header_only++;
quiet++;
break;
@@ -5063,8 +5427,26 @@ void cmdline(int argc, char **argv)
case 'q':
quiet = 1;
break;
+ case 'n':
+ num_iterations = strtod(optarg, NULL);
+
+ if (num_iterations <= 0) {
+ fprintf(outf, "iterations %d should be positive number\n",
+ num_iterations);
+ exit(2);
+ }
+ break;
case 's':
- parse_show_hide(optarg, SHOW_LIST);
+ /*
+ * --show: show only those specified
+ * The 1st invocation will clear and replace the enabled mask
+ * subsequent invocations can add to it.
+ */
+ if (shown == 0)
+ bic_enabled = bic_lookup(optarg, SHOW_LIST);
+ else
+ bic_enabled |= bic_lookup(optarg, SHOW_LIST);
+ shown = 1;
break;
case 'S':
summary_only++;
diff --git a/tools/power/x86/x86_energy_perf_policy/Makefile b/tools/power/x86/x86_energy_perf_policy/Makefile
index 2447b1b..f4534fb 100644
--- a/tools/power/x86/x86_energy_perf_policy/Makefile
+++ b/tools/power/x86/x86_energy_perf_policy/Makefile
@@ -24,5 +24,5 @@
install -d $(DESTDIR)$(PREFIX)/bin
install $(BUILD_OUTPUT)/x86_energy_perf_policy $(DESTDIR)$(PREFIX)/bin/x86_energy_perf_policy
install -d $(DESTDIR)$(PREFIX)/share/man/man8
- install x86_energy_perf_policy.8 $(DESTDIR)$(PREFIX)/share/man/man8
+ install -m 644 x86_energy_perf_policy.8 $(DESTDIR)$(PREFIX)/share/man/man8
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index cb166be..4ea385b 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -138,6 +138,7 @@ static u32 handle[] = {
};
static unsigned long dimm_fail_cmd_flags[NUM_DCR];
+static int dimm_fail_cmd_code[NUM_DCR];
struct nfit_test_fw {
enum intel_fw_update_state state;
@@ -892,8 +893,11 @@ static int get_dimm(struct nfit_mem *nfit_mem, unsigned int func)
if (i >= ARRAY_SIZE(handle))
return -ENXIO;
- if ((1 << func) & dimm_fail_cmd_flags[i])
+ if ((1 << func) & dimm_fail_cmd_flags[i]) {
+ if (dimm_fail_cmd_code[i])
+ return dimm_fail_cmd_code[i];
return -EIO;
+ }
return i;
}
@@ -1162,12 +1166,12 @@ static int ars_state_init(struct device *dev, struct ars_state *ars_state)
static void put_dimms(void *data)
{
- struct device **dimm_dev = data;
+ struct nfit_test *t = data;
int i;
- for (i = 0; i < NUM_DCR; i++)
- if (dimm_dev[i])
- device_unregister(dimm_dev[i]);
+ for (i = 0; i < t->num_dcr; i++)
+ if (t->dimm_dev[i])
+ device_unregister(t->dimm_dev[i]);
}
static struct class *nfit_test_dimm;
@@ -1176,13 +1180,11 @@ static int dimm_name_to_id(struct device *dev)
{
int dimm;
- if (sscanf(dev_name(dev), "test_dimm%d", &dimm) != 1
- || dimm >= NUM_DCR || dimm < 0)
+ if (sscanf(dev_name(dev), "test_dimm%d", &dimm) != 1)
return -ENXIO;
return dimm;
}
-
static ssize_t handle_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
@@ -1191,7 +1193,7 @@ static ssize_t handle_show(struct device *dev, struct device_attribute *attr,
if (dimm < 0)
return dimm;
- return sprintf(buf, "%#x", handle[dimm]);
+ return sprintf(buf, "%#x\n", handle[dimm]);
}
DEVICE_ATTR_RO(handle);
@@ -1225,8 +1227,39 @@ static ssize_t fail_cmd_store(struct device *dev, struct device_attribute *attr,
}
static DEVICE_ATTR_RW(fail_cmd);
+static ssize_t fail_cmd_code_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ int dimm = dimm_name_to_id(dev);
+
+ if (dimm < 0)
+ return dimm;
+
+ return sprintf(buf, "%d\n", dimm_fail_cmd_code[dimm]);
+}
+
+static ssize_t fail_cmd_code_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int dimm = dimm_name_to_id(dev);
+ unsigned long val;
+ ssize_t rc;
+
+ if (dimm < 0)
+ return dimm;
+
+ rc = kstrtol(buf, 0, &val);
+ if (rc)
+ return rc;
+
+ dimm_fail_cmd_code[dimm] = val;
+ return size;
+}
+static DEVICE_ATTR_RW(fail_cmd_code);
+
static struct attribute *nfit_test_dimm_attributes[] = {
&dev_attr_fail_cmd.attr,
+ &dev_attr_fail_cmd_code.attr,
&dev_attr_handle.attr,
NULL,
};
@@ -1240,6 +1273,23 @@ static const struct attribute_group *nfit_test_dimm_attribute_groups[] = {
NULL,
};
+static int nfit_test_dimm_init(struct nfit_test *t)
+{
+ int i;
+
+ if (devm_add_action_or_reset(&t->pdev.dev, put_dimms, t))
+ return -ENOMEM;
+ for (i = 0; i < t->num_dcr; i++) {
+ t->dimm_dev[i] = device_create_with_groups(nfit_test_dimm,
+ &t->pdev.dev, 0, NULL,
+ nfit_test_dimm_attribute_groups,
+ "test_dimm%d", i + t->dcr_idx);
+ if (!t->dimm_dev[i])
+ return -ENOMEM;
+ }
+ return 0;
+}
+
static void smart_init(struct nfit_test *t)
{
int i;
@@ -1335,17 +1385,8 @@ static int nfit_test0_alloc(struct nfit_test *t)
if (!t->_fit)
return -ENOMEM;
- if (devm_add_action_or_reset(&t->pdev.dev, put_dimms, t->dimm_dev))
+ if (nfit_test_dimm_init(t))
return -ENOMEM;
- for (i = 0; i < NUM_DCR; i++) {
- t->dimm_dev[i] = device_create_with_groups(nfit_test_dimm,
- &t->pdev.dev, 0, NULL,
- nfit_test_dimm_attribute_groups,
- "test_dimm%d", i);
- if (!t->dimm_dev[i])
- return -ENOMEM;
- }
-
smart_init(t);
return ars_state_init(&t->pdev.dev, &t->ars_state);
}
@@ -1377,6 +1418,8 @@ static int nfit_test1_alloc(struct nfit_test *t)
if (!t->spa_set[1])
return -ENOMEM;
+ if (nfit_test_dimm_init(t))
+ return -ENOMEM;
smart_init(t);
return ars_state_init(&t->pdev.dev, &t->ars_state);
}
@@ -2222,6 +2265,9 @@ static void nfit_test1_setup(struct nfit_test *t)
set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_cmd_force_en);
set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_cmd_force_en);
set_bit(ND_INTEL_ENABLE_LSS_STATUS, &acpi_desc->dimm_cmd_force_en);
+ set_bit(ND_CMD_GET_CONFIG_SIZE, &acpi_desc->dimm_cmd_force_en);
+ set_bit(ND_CMD_GET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en);
+ set_bit(ND_CMD_SET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en);
}
static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa,
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index fa7ee36..db66f8a 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -17,7 +17,7 @@
LDFLAGS += -m32
endif
-targets: mapshift $(TARGETS)
+targets: generated/map-shift.h $(TARGETS)
main: $(OFILES)
@@ -42,9 +42,7 @@
idr.c: ../../../lib/idr.c
sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@
-.PHONY: mapshift
-
-mapshift:
+generated/map-shift.h:
@if ! grep -qws $(SHIFT) generated/map-shift.h; then \
echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" > \
generated/map-shift.h; \
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index 6c645eb..ee820fc 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -252,6 +252,13 @@ void idr_checks(void)
idr_remove(&idr, 3);
idr_remove(&idr, 0);
+ assert(idr_alloc(&idr, DUMMY_PTR, 0, 0, GFP_KERNEL) == 0);
+ idr_remove(&idr, 1);
+ for (i = 1; i < RADIX_TREE_MAP_SIZE; i++)
+ assert(idr_alloc(&idr, DUMMY_PTR, 0, 0, GFP_KERNEL) == i);
+ idr_remove(&idr, 1 << 30);
+ idr_destroy(&idr);
+
for (i = INT_MAX - 3UL; i < INT_MAX + 1UL; i++) {
struct item *item = item_create(i, 0);
assert(idr_alloc(&idr, item, i, i + 10, GFP_KERNEL) == i);
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 59245b3..7bf4056 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -16,6 +16,7 @@
#include <linux/radix-tree.h>
#include <linux/slab.h>
#include <linux/errno.h>
+#include <pthread.h>
#include "test.h"
@@ -624,6 +625,67 @@ static void multiorder_account(void)
item_kill_tree(&tree);
}
+bool stop_iteration = false;
+
+static void *creator_func(void *ptr)
+{
+ /* 'order' is set up to ensure we have sibling entries */
+ unsigned int order = RADIX_TREE_MAP_SHIFT - 1;
+ struct radix_tree_root *tree = ptr;
+ int i;
+
+ for (i = 0; i < 10000; i++) {
+ item_insert_order(tree, 0, order);
+ item_delete_rcu(tree, 0);
+ }
+
+ stop_iteration = true;
+ return NULL;
+}
+
+static void *iterator_func(void *ptr)
+{
+ struct radix_tree_root *tree = ptr;
+ struct radix_tree_iter iter;
+ struct item *item;
+ void **slot;
+
+ while (!stop_iteration) {
+ rcu_read_lock();
+ radix_tree_for_each_slot(slot, tree, &iter, 0) {
+ item = radix_tree_deref_slot(slot);
+
+ if (!item)
+ continue;
+ if (radix_tree_deref_retry(item)) {
+ slot = radix_tree_iter_retry(&iter);
+ continue;
+ }
+
+ item_sanity(item, iter.index);
+ }
+ rcu_read_unlock();
+ }
+ return NULL;
+}
+
+static void multiorder_iteration_race(void)
+{
+ const int num_threads = sysconf(_SC_NPROCESSORS_ONLN);
+ pthread_t worker_thread[num_threads];
+ RADIX_TREE(tree, GFP_KERNEL);
+ int i;
+
+ pthread_create(&worker_thread[0], NULL, &creator_func, &tree);
+ for (i = 1; i < num_threads; i++)
+ pthread_create(&worker_thread[i], NULL, &iterator_func, &tree);
+
+ for (i = 0; i < num_threads; i++)
+ pthread_join(worker_thread[i], NULL);
+
+ item_kill_tree(&tree);
+}
+
void multiorder_checks(void)
{
int i;
@@ -644,6 +706,7 @@ void multiorder_checks(void)
multiorder_join();
multiorder_split();
multiorder_account();
+ multiorder_iteration_race();
radix_tree_cpu_dead(0);
}
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 5978ab1..def6015 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -75,6 +75,25 @@ int item_delete(struct radix_tree_root *root, unsigned long index)
return 0;
}
+static void item_free_rcu(struct rcu_head *head)
+{
+ struct item *item = container_of(head, struct item, rcu_head);
+
+ free(item);
+}
+
+int item_delete_rcu(struct radix_tree_root *root, unsigned long index)
+{
+ struct item *item = radix_tree_delete(root, index);
+
+ if (item) {
+ item_sanity(item, index);
+ call_rcu(&item->rcu_head, item_free_rcu);
+ return 1;
+ }
+ return 0;
+}
+
void item_check_present(struct radix_tree_root *root, unsigned long index)
{
struct item *item;
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index d9c031d..31f1d9b 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -5,6 +5,7 @@
#include <linux/rcupdate.h>
struct item {
+ struct rcu_head rcu_head;
unsigned long index;
unsigned int order;
};
@@ -12,9 +13,11 @@ struct item {
struct item *item_create(unsigned long index, unsigned int order);
int __item_insert(struct radix_tree_root *root, struct item *item);
int item_insert(struct radix_tree_root *root, unsigned long index);
+void item_sanity(struct item *item, unsigned long index);
int item_insert_order(struct radix_tree_root *root, unsigned long index,
unsigned order);
int item_delete(struct radix_tree_root *root, unsigned long index);
+int item_delete_rcu(struct radix_tree_root *root, unsigned long index);
struct item *item_lookup(struct radix_tree_root *root, unsigned long index);
void item_check_present(struct radix_tree_root *root, unsigned long index);
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 9cf83f8..5e1ab2f 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -12,3 +12,6 @@
test_verifier_log
feature
test_libbpf_open
+test_sock
+test_sock_addr
+urandom_read
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 983dd25..1eefe21 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -5,3 +5,5 @@
CONFIG_TEST_BPF=m
CONFIG_CGROUP_BPF=y
CONFIG_NETDEVSIM=m
+CONFIG_NET_CLS_ACT=y
+CONFIG_NET_SCH_INGRESS=y
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index faadbe2..4123d0a 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1108,7 +1108,7 @@ static void test_stacktrace_build_id(void)
assert(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null")
== 0);
- assert(system("./urandom_read if=/dev/urandom of=/dev/zero count=4 2> /dev/null") == 0);
+ assert(system("./urandom_read") == 0);
/* disable stack trace collection */
key = 0;
val = 1;
@@ -1158,7 +1158,7 @@ static void test_stacktrace_build_id(void)
} while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0);
CHECK(build_id_matches < 1, "build id match",
- "Didn't find expected build ID from the map");
+ "Didn't find expected build ID from the map\n");
disable_pmu:
ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c
index 73bb20c..f4d99fa 100644
--- a/tools/testing/selftests/bpf/test_sock.c
+++ b/tools/testing/selftests/bpf/test_sock.c
@@ -13,6 +13,7 @@
#include <bpf/bpf.h>
#include "cgroup_helpers.h"
+#include "bpf_rlimit.h"
#ifndef ARRAY_SIZE
# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index d488f20..2950f80ba 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -15,6 +15,7 @@
#include <bpf/libbpf.h>
#include "cgroup_helpers.h"
+#include "bpf_rlimit.h"
#define CG_PATH "/foo"
#define CONNECT4_PROG_PATH "./connect4_prog.o"
diff --git a/tools/testing/selftests/bpf/test_sock_addr.sh b/tools/testing/selftests/bpf/test_sock_addr.sh
index c6e1dcf..9832a87 100755
--- a/tools/testing/selftests/bpf/test_sock_addr.sh
+++ b/tools/testing/selftests/bpf/test_sock_addr.sh
@@ -4,7 +4,7 @@
ping_once()
{
- ping -q -c 1 -W 1 ${1%%/*} >/dev/null 2>&1
+ ping -${1} -q -c 1 -W 1 ${2%%/*} >/dev/null 2>&1
}
wait_for_ip()
@@ -13,7 +13,7 @@
echo -n "Wait for testing IPv4/IPv6 to become available "
for _i in $(seq ${MAX_PING_TRIES}); do
echo -n "."
- if ping_once ${TEST_IPv4} && ping_once ${TEST_IPv6}; then
+ if ping_once 4 ${TEST_IPv4} && ping_once 6 ${TEST_IPv6}; then
echo " OK"
return
fi
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 3e7718b..fd7de7e 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -11713,6 +11713,11 @@ static void get_unpriv_disabled()
FILE *fd;
fd = fopen("/proc/sys/"UNPRIV_SYSCTL, "r");
+ if (!fd) {
+ perror("fopen /proc/sys/"UNPRIV_SYSCTL);
+ unpriv_disabled = true;
+ return;
+ }
if (fgets(buf, 2, fd) == buf && atoi(buf))
unpriv_disabled = true;
fclose(fd);
diff --git a/tools/testing/selftests/filesystems/Makefile b/tools/testing/selftests/filesystems/Makefile
index 4e6d09f..5c7d700 100644
--- a/tools/testing/selftests/filesystems/Makefile
+++ b/tools/testing/selftests/filesystems/Makefile
@@ -1,8 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
-TEST_PROGS := dnotify_test devpts_pts
-all: $(TEST_PROGS)
+
+TEST_GEN_PROGS := devpts_pts
+TEST_GEN_PROGS_EXTENDED := dnotify_test
include ../lib.mk
-
-clean:
- rm -fr $(TEST_PROGS)
diff --git a/tools/testing/selftests/firmware/Makefile b/tools/testing/selftests/firmware/Makefile
index 826f38d..261c81f 100644
--- a/tools/testing/selftests/firmware/Makefile
+++ b/tools/testing/selftests/firmware/Makefile
@@ -4,6 +4,7 @@
all:
TEST_PROGS := fw_run_tests.sh
+TEST_FILES := fw_fallback.sh fw_filesystem.sh fw_lib.sh
include ../lib.mk
diff --git a/tools/testing/selftests/firmware/fw_lib.sh b/tools/testing/selftests/firmware/fw_lib.sh
index 9ea31b5..962d7f4 100755
--- a/tools/testing/selftests/firmware/fw_lib.sh
+++ b/tools/testing/selftests/firmware/fw_lib.sh
@@ -154,11 +154,13 @@
if [ "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then
echo "$OLD_TIMEOUT" >/sys/class/firmware/timeout
fi
- if [ "$OLD_FWPATH" = "" ]; then
- OLD_FWPATH=" "
- fi
if [ "$TEST_REQS_FW_SET_CUSTOM_PATH" = "yes" ]; then
- echo -n "$OLD_FWPATH" >/sys/module/firmware_class/parameters/path
+ if [ "$OLD_FWPATH" = "" ]; then
+ # A zero-length write won't work; write a null byte
+ printf '\000' >/sys/module/firmware_class/parameters/path
+ else
+ echo -n "$OLD_FWPATH" >/sys/module/firmware_class/parameters/path
+ fi
fi
if [ -f $FW ]; then
rm -f "$FW"
diff --git a/tools/testing/selftests/firmware/fw_run_tests.sh b/tools/testing/selftests/firmware/fw_run_tests.sh
index 06d638e..cffdd4e 100755
--- a/tools/testing/selftests/firmware/fw_run_tests.sh
+++ b/tools/testing/selftests/firmware/fw_run_tests.sh
@@ -66,5 +66,5 @@
run_test_config_0003
else
echo "Running basic kernel configuration, working with your config"
- run_test
+ run_tests
fi
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc
index 786dce7..2aabab3 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc
@@ -29,7 +29,7 @@
echo "Test extended error support"
echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_wakeup/trigger
-echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_wakeup/trigger &>/dev/null
+! echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_wakeup/trigger 2> /dev/null
if ! grep -q "ERROR:" events/sched/sched_wakeup/hist; then
fail "Failed to generate extended error in histogram"
fi
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc
new file mode 100644
index 0000000..c193dce
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc
@@ -0,0 +1,44 @@
+#!/bin/sh
+# description: event trigger - test multiple actions on hist trigger
+
+
+do_reset() {
+ reset_trigger
+ echo > set_event
+ clear_trace
+}
+
+fail() { #msg
+ do_reset
+ echo $1
+ exit_fail
+}
+
+if [ ! -f set_event ]; then
+ echo "event tracing is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+ echo "synthetic event is not supported"
+ exit_unsupported
+fi
+
+clear_synthetic_events
+reset_tracer
+do_reset
+
+echo "Test multiple actions on hist trigger"
+echo 'wakeup_latency u64 lat; pid_t pid' >> synthetic_events
+TRIGGER1=events/sched/sched_wakeup/trigger
+TRIGGER2=events/sched/sched_switch/trigger
+
+echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="cyclictest"' > $TRIGGER1
+echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0 if next_comm=="cyclictest"' >> $TRIGGER2
+echo 'hist:keys=next_pid:onmatch(sched.sched_wakeup).wakeup_latency(sched.sched_switch.$wakeup_lat,next_pid) if next_comm=="cyclictest"' >> $TRIGGER2
+echo 'hist:keys=next_pid:onmatch(sched.sched_wakeup).wakeup_latency(sched.sched_switch.$wakeup_lat,prev_pid) if next_comm=="cyclictest"' >> $TRIGGER2
+echo 'hist:keys=next_pid if next_comm=="cyclictest"' >> $TRIGGER2
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index dc44de9..d9d0031 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -4,17 +4,18 @@
UNAME_M := $(shell uname -m)
LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c
-LIBKVM_x86_64 = lib/x86.c
+LIBKVM_x86_64 = lib/x86.c lib/vmx.c
TEST_GEN_PROGS_x86_64 = set_sregs_test
TEST_GEN_PROGS_x86_64 += sync_regs_test
+TEST_GEN_PROGS_x86_64 += vmx_tsc_adjust_test
TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
LIBKVM += $(LIBKVM_$(UNAME_M))
INSTALL_HDR_PATH = $(top_srcdir)/usr
LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
-CFLAGS += -O2 -g -I$(LINUX_HDR_PATH) -Iinclude -I$(<D)
+CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -I..
# After inclusion, $(OUTPUT) is defined and
# $(TEST_GEN_PROGS) starts with $(OUTPUT)/
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 57974ad..637b701 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -112,24 +112,27 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm,
vm_paddr_t paddr_min, uint32_t memslot);
-void kvm_get_supported_cpuid(struct kvm_cpuid2 *cpuid);
+struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
void vcpu_set_cpuid(
struct kvm_vm *vm, uint32_t vcpuid, struct kvm_cpuid2 *cpuid);
-struct kvm_cpuid2 *allocate_kvm_cpuid2(void);
struct kvm_cpuid_entry2 *
-find_cpuid_index_entry(struct kvm_cpuid2 *cpuid, uint32_t function,
- uint32_t index);
+kvm_get_supported_cpuid_index(uint32_t function, uint32_t index);
static inline struct kvm_cpuid_entry2 *
-find_cpuid_entry(struct kvm_cpuid2 *cpuid, uint32_t function)
+kvm_get_supported_cpuid_entry(uint32_t function)
{
- return find_cpuid_index_entry(cpuid, function, 0);
+ return kvm_get_supported_cpuid_index(function, 0);
}
struct kvm_vm *vm_create_default(uint32_t vcpuid, void *guest_code);
void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code);
+typedef void (*vmx_guest_code_t)(vm_vaddr_t vmxon_vaddr,
+ vm_paddr_t vmxon_paddr,
+ vm_vaddr_t vmcs_vaddr,
+ vm_paddr_t vmcs_paddr);
+
struct kvm_userspace_memory_region *
kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
uint64_t end);
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 7ab98e4..ac53730 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -19,6 +19,7 @@
#include <errno.h>
#include <unistd.h>
#include <fcntl.h>
+#include "kselftest.h"
ssize_t test_write(int fd, const void *buf, size_t count);
ssize_t test_read(int fd, void *buf, size_t count);
diff --git a/tools/testing/selftests/kvm/include/vmx.h b/tools/testing/selftests/kvm/include/vmx.h
new file mode 100644
index 0000000..6ed8499
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/vmx.h
@@ -0,0 +1,494 @@
+/*
+ * tools/testing/selftests/kvm/include/vmx.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ */
+
+#ifndef SELFTEST_KVM_VMX_H
+#define SELFTEST_KVM_VMX_H
+
+#include <stdint.h>
+#include "x86.h"
+
+#define CPUID_VMX_BIT 5
+
+#define CPUID_VMX (1 << 5)
+
+/*
+ * Definitions of Primary Processor-Based VM-Execution Controls.
+ */
+#define CPU_BASED_VIRTUAL_INTR_PENDING 0x00000004
+#define CPU_BASED_USE_TSC_OFFSETING 0x00000008
+#define CPU_BASED_HLT_EXITING 0x00000080
+#define CPU_BASED_INVLPG_EXITING 0x00000200
+#define CPU_BASED_MWAIT_EXITING 0x00000400
+#define CPU_BASED_RDPMC_EXITING 0x00000800
+#define CPU_BASED_RDTSC_EXITING 0x00001000
+#define CPU_BASED_CR3_LOAD_EXITING 0x00008000
+#define CPU_BASED_CR3_STORE_EXITING 0x00010000
+#define CPU_BASED_CR8_LOAD_EXITING 0x00080000
+#define CPU_BASED_CR8_STORE_EXITING 0x00100000
+#define CPU_BASED_TPR_SHADOW 0x00200000
+#define CPU_BASED_VIRTUAL_NMI_PENDING 0x00400000
+#define CPU_BASED_MOV_DR_EXITING 0x00800000
+#define CPU_BASED_UNCOND_IO_EXITING 0x01000000
+#define CPU_BASED_USE_IO_BITMAPS 0x02000000
+#define CPU_BASED_MONITOR_TRAP 0x08000000
+#define CPU_BASED_USE_MSR_BITMAPS 0x10000000
+#define CPU_BASED_MONITOR_EXITING 0x20000000
+#define CPU_BASED_PAUSE_EXITING 0x40000000
+#define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS 0x80000000
+
+#define CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR 0x0401e172
+
+/*
+ * Definitions of Secondary Processor-Based VM-Execution Controls.
+ */
+#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
+#define SECONDARY_EXEC_ENABLE_EPT 0x00000002
+#define SECONDARY_EXEC_DESC 0x00000004
+#define SECONDARY_EXEC_RDTSCP 0x00000008
+#define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE 0x00000010
+#define SECONDARY_EXEC_ENABLE_VPID 0x00000020
+#define SECONDARY_EXEC_WBINVD_EXITING 0x00000040
+#define SECONDARY_EXEC_UNRESTRICTED_GUEST 0x00000080
+#define SECONDARY_EXEC_APIC_REGISTER_VIRT 0x00000100
+#define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY 0x00000200
+#define SECONDARY_EXEC_PAUSE_LOOP_EXITING 0x00000400
+#define SECONDARY_EXEC_RDRAND_EXITING 0x00000800
+#define SECONDARY_EXEC_ENABLE_INVPCID 0x00001000
+#define SECONDARY_EXEC_ENABLE_VMFUNC 0x00002000
+#define SECONDARY_EXEC_SHADOW_VMCS 0x00004000
+#define SECONDARY_EXEC_RDSEED_EXITING 0x00010000
+#define SECONDARY_EXEC_ENABLE_PML 0x00020000
+#define SECONDARY_EPT_VE 0x00040000
+#define SECONDARY_ENABLE_XSAV_RESTORE 0x00100000
+#define SECONDARY_EXEC_TSC_SCALING 0x02000000
+
+#define PIN_BASED_EXT_INTR_MASK 0x00000001
+#define PIN_BASED_NMI_EXITING 0x00000008
+#define PIN_BASED_VIRTUAL_NMIS 0x00000020
+#define PIN_BASED_VMX_PREEMPTION_TIMER 0x00000040
+#define PIN_BASED_POSTED_INTR 0x00000080
+
+#define PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR 0x00000016
+
+#define VM_EXIT_SAVE_DEBUG_CONTROLS 0x00000004
+#define VM_EXIT_HOST_ADDR_SPACE_SIZE 0x00000200
+#define VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL 0x00001000
+#define VM_EXIT_ACK_INTR_ON_EXIT 0x00008000
+#define VM_EXIT_SAVE_IA32_PAT 0x00040000
+#define VM_EXIT_LOAD_IA32_PAT 0x00080000
+#define VM_EXIT_SAVE_IA32_EFER 0x00100000
+#define VM_EXIT_LOAD_IA32_EFER 0x00200000
+#define VM_EXIT_SAVE_VMX_PREEMPTION_TIMER 0x00400000
+
+#define VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR 0x00036dff
+
+#define VM_ENTRY_LOAD_DEBUG_CONTROLS 0x00000004
+#define VM_ENTRY_IA32E_MODE 0x00000200
+#define VM_ENTRY_SMM 0x00000400
+#define VM_ENTRY_DEACT_DUAL_MONITOR 0x00000800
+#define VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL 0x00002000
+#define VM_ENTRY_LOAD_IA32_PAT 0x00004000
+#define VM_ENTRY_LOAD_IA32_EFER 0x00008000
+
+#define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR 0x000011ff
+
+#define VMX_MISC_PREEMPTION_TIMER_RATE_MASK 0x0000001f
+#define VMX_MISC_SAVE_EFER_LMA 0x00000020
+
+#define EXIT_REASON_FAILED_VMENTRY 0x80000000
+#define EXIT_REASON_EXCEPTION_NMI 0
+#define EXIT_REASON_EXTERNAL_INTERRUPT 1
+#define EXIT_REASON_TRIPLE_FAULT 2
+#define EXIT_REASON_PENDING_INTERRUPT 7
+#define EXIT_REASON_NMI_WINDOW 8
+#define EXIT_REASON_TASK_SWITCH 9
+#define EXIT_REASON_CPUID 10
+#define EXIT_REASON_HLT 12
+#define EXIT_REASON_INVD 13
+#define EXIT_REASON_INVLPG 14
+#define EXIT_REASON_RDPMC 15
+#define EXIT_REASON_RDTSC 16
+#define EXIT_REASON_VMCALL 18
+#define EXIT_REASON_VMCLEAR 19
+#define EXIT_REASON_VMLAUNCH 20
+#define EXIT_REASON_VMPTRLD 21
+#define EXIT_REASON_VMPTRST 22
+#define EXIT_REASON_VMREAD 23
+#define EXIT_REASON_VMRESUME 24
+#define EXIT_REASON_VMWRITE 25
+#define EXIT_REASON_VMOFF 26
+#define EXIT_REASON_VMON 27
+#define EXIT_REASON_CR_ACCESS 28
+#define EXIT_REASON_DR_ACCESS 29
+#define EXIT_REASON_IO_INSTRUCTION 30
+#define EXIT_REASON_MSR_READ 31
+#define EXIT_REASON_MSR_WRITE 32
+#define EXIT_REASON_INVALID_STATE 33
+#define EXIT_REASON_MWAIT_INSTRUCTION 36
+#define EXIT_REASON_MONITOR_INSTRUCTION 39
+#define EXIT_REASON_PAUSE_INSTRUCTION 40
+#define EXIT_REASON_MCE_DURING_VMENTRY 41
+#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
+#define EXIT_REASON_APIC_ACCESS 44
+#define EXIT_REASON_EOI_INDUCED 45
+#define EXIT_REASON_EPT_VIOLATION 48
+#define EXIT_REASON_EPT_MISCONFIG 49
+#define EXIT_REASON_INVEPT 50
+#define EXIT_REASON_RDTSCP 51
+#define EXIT_REASON_PREEMPTION_TIMER 52
+#define EXIT_REASON_INVVPID 53
+#define EXIT_REASON_WBINVD 54
+#define EXIT_REASON_XSETBV 55
+#define EXIT_REASON_APIC_WRITE 56
+#define EXIT_REASON_INVPCID 58
+#define EXIT_REASON_PML_FULL 62
+#define EXIT_REASON_XSAVES 63
+#define EXIT_REASON_XRSTORS 64
+#define LAST_EXIT_REASON 64
+
+enum vmcs_field {
+ VIRTUAL_PROCESSOR_ID = 0x00000000,
+ POSTED_INTR_NV = 0x00000002,
+ GUEST_ES_SELECTOR = 0x00000800,
+ GUEST_CS_SELECTOR = 0x00000802,
+ GUEST_SS_SELECTOR = 0x00000804,
+ GUEST_DS_SELECTOR = 0x00000806,
+ GUEST_FS_SELECTOR = 0x00000808,
+ GUEST_GS_SELECTOR = 0x0000080a,
+ GUEST_LDTR_SELECTOR = 0x0000080c,
+ GUEST_TR_SELECTOR = 0x0000080e,
+ GUEST_INTR_STATUS = 0x00000810,
+ GUEST_PML_INDEX = 0x00000812,
+ HOST_ES_SELECTOR = 0x00000c00,
+ HOST_CS_SELECTOR = 0x00000c02,
+ HOST_SS_SELECTOR = 0x00000c04,
+ HOST_DS_SELECTOR = 0x00000c06,
+ HOST_FS_SELECTOR = 0x00000c08,
+ HOST_GS_SELECTOR = 0x00000c0a,
+ HOST_TR_SELECTOR = 0x00000c0c,
+ IO_BITMAP_A = 0x00002000,
+ IO_BITMAP_A_HIGH = 0x00002001,
+ IO_BITMAP_B = 0x00002002,
+ IO_BITMAP_B_HIGH = 0x00002003,
+ MSR_BITMAP = 0x00002004,
+ MSR_BITMAP_HIGH = 0x00002005,
+ VM_EXIT_MSR_STORE_ADDR = 0x00002006,
+ VM_EXIT_MSR_STORE_ADDR_HIGH = 0x00002007,
+ VM_EXIT_MSR_LOAD_ADDR = 0x00002008,
+ VM_EXIT_MSR_LOAD_ADDR_HIGH = 0x00002009,
+ VM_ENTRY_MSR_LOAD_ADDR = 0x0000200a,
+ VM_ENTRY_MSR_LOAD_ADDR_HIGH = 0x0000200b,
+ PML_ADDRESS = 0x0000200e,
+ PML_ADDRESS_HIGH = 0x0000200f,
+ TSC_OFFSET = 0x00002010,
+ TSC_OFFSET_HIGH = 0x00002011,
+ VIRTUAL_APIC_PAGE_ADDR = 0x00002012,
+ VIRTUAL_APIC_PAGE_ADDR_HIGH = 0x00002013,
+ APIC_ACCESS_ADDR = 0x00002014,
+ APIC_ACCESS_ADDR_HIGH = 0x00002015,
+ POSTED_INTR_DESC_ADDR = 0x00002016,
+ POSTED_INTR_DESC_ADDR_HIGH = 0x00002017,
+ EPT_POINTER = 0x0000201a,
+ EPT_POINTER_HIGH = 0x0000201b,
+ EOI_EXIT_BITMAP0 = 0x0000201c,
+ EOI_EXIT_BITMAP0_HIGH = 0x0000201d,
+ EOI_EXIT_BITMAP1 = 0x0000201e,
+ EOI_EXIT_BITMAP1_HIGH = 0x0000201f,
+ EOI_EXIT_BITMAP2 = 0x00002020,
+ EOI_EXIT_BITMAP2_HIGH = 0x00002021,
+ EOI_EXIT_BITMAP3 = 0x00002022,
+ EOI_EXIT_BITMAP3_HIGH = 0x00002023,
+ VMREAD_BITMAP = 0x00002026,
+ VMREAD_BITMAP_HIGH = 0x00002027,
+ VMWRITE_BITMAP = 0x00002028,
+ VMWRITE_BITMAP_HIGH = 0x00002029,
+ XSS_EXIT_BITMAP = 0x0000202C,
+ XSS_EXIT_BITMAP_HIGH = 0x0000202D,
+ TSC_MULTIPLIER = 0x00002032,
+ TSC_MULTIPLIER_HIGH = 0x00002033,
+ GUEST_PHYSICAL_ADDRESS = 0x00002400,
+ GUEST_PHYSICAL_ADDRESS_HIGH = 0x00002401,
+ VMCS_LINK_POINTER = 0x00002800,
+ VMCS_LINK_POINTER_HIGH = 0x00002801,
+ GUEST_IA32_DEBUGCTL = 0x00002802,
+ GUEST_IA32_DEBUGCTL_HIGH = 0x00002803,
+ GUEST_IA32_PAT = 0x00002804,
+ GUEST_IA32_PAT_HIGH = 0x00002805,
+ GUEST_IA32_EFER = 0x00002806,
+ GUEST_IA32_EFER_HIGH = 0x00002807,
+ GUEST_IA32_PERF_GLOBAL_CTRL = 0x00002808,
+ GUEST_IA32_PERF_GLOBAL_CTRL_HIGH= 0x00002809,
+ GUEST_PDPTR0 = 0x0000280a,
+ GUEST_PDPTR0_HIGH = 0x0000280b,
+ GUEST_PDPTR1 = 0x0000280c,
+ GUEST_PDPTR1_HIGH = 0x0000280d,
+ GUEST_PDPTR2 = 0x0000280e,
+ GUEST_PDPTR2_HIGH = 0x0000280f,
+ GUEST_PDPTR3 = 0x00002810,
+ GUEST_PDPTR3_HIGH = 0x00002811,
+ GUEST_BNDCFGS = 0x00002812,
+ GUEST_BNDCFGS_HIGH = 0x00002813,
+ HOST_IA32_PAT = 0x00002c00,
+ HOST_IA32_PAT_HIGH = 0x00002c01,
+ HOST_IA32_EFER = 0x00002c02,
+ HOST_IA32_EFER_HIGH = 0x00002c03,
+ HOST_IA32_PERF_GLOBAL_CTRL = 0x00002c04,
+ HOST_IA32_PERF_GLOBAL_CTRL_HIGH = 0x00002c05,
+ PIN_BASED_VM_EXEC_CONTROL = 0x00004000,
+ CPU_BASED_VM_EXEC_CONTROL = 0x00004002,
+ EXCEPTION_BITMAP = 0x00004004,
+ PAGE_FAULT_ERROR_CODE_MASK = 0x00004006,
+ PAGE_FAULT_ERROR_CODE_MATCH = 0x00004008,
+ CR3_TARGET_COUNT = 0x0000400a,
+ VM_EXIT_CONTROLS = 0x0000400c,
+ VM_EXIT_MSR_STORE_COUNT = 0x0000400e,
+ VM_EXIT_MSR_LOAD_COUNT = 0x00004010,
+ VM_ENTRY_CONTROLS = 0x00004012,
+ VM_ENTRY_MSR_LOAD_COUNT = 0x00004014,
+ VM_ENTRY_INTR_INFO_FIELD = 0x00004016,
+ VM_ENTRY_EXCEPTION_ERROR_CODE = 0x00004018,
+ VM_ENTRY_INSTRUCTION_LEN = 0x0000401a,
+ TPR_THRESHOLD = 0x0000401c,
+ SECONDARY_VM_EXEC_CONTROL = 0x0000401e,
+ PLE_GAP = 0x00004020,
+ PLE_WINDOW = 0x00004022,
+ VM_INSTRUCTION_ERROR = 0x00004400,
+ VM_EXIT_REASON = 0x00004402,
+ VM_EXIT_INTR_INFO = 0x00004404,
+ VM_EXIT_INTR_ERROR_CODE = 0x00004406,
+ IDT_VECTORING_INFO_FIELD = 0x00004408,
+ IDT_VECTORING_ERROR_CODE = 0x0000440a,
+ VM_EXIT_INSTRUCTION_LEN = 0x0000440c,
+ VMX_INSTRUCTION_INFO = 0x0000440e,
+ GUEST_ES_LIMIT = 0x00004800,
+ GUEST_CS_LIMIT = 0x00004802,
+ GUEST_SS_LIMIT = 0x00004804,
+ GUEST_DS_LIMIT = 0x00004806,
+ GUEST_FS_LIMIT = 0x00004808,
+ GUEST_GS_LIMIT = 0x0000480a,
+ GUEST_LDTR_LIMIT = 0x0000480c,
+ GUEST_TR_LIMIT = 0x0000480e,
+ GUEST_GDTR_LIMIT = 0x00004810,
+ GUEST_IDTR_LIMIT = 0x00004812,
+ GUEST_ES_AR_BYTES = 0x00004814,
+ GUEST_CS_AR_BYTES = 0x00004816,
+ GUEST_SS_AR_BYTES = 0x00004818,
+ GUEST_DS_AR_BYTES = 0x0000481a,
+ GUEST_FS_AR_BYTES = 0x0000481c,
+ GUEST_GS_AR_BYTES = 0x0000481e,
+ GUEST_LDTR_AR_BYTES = 0x00004820,
+ GUEST_TR_AR_BYTES = 0x00004822,
+ GUEST_INTERRUPTIBILITY_INFO = 0x00004824,
+ GUEST_ACTIVITY_STATE = 0X00004826,
+ GUEST_SYSENTER_CS = 0x0000482A,
+ VMX_PREEMPTION_TIMER_VALUE = 0x0000482E,
+ HOST_IA32_SYSENTER_CS = 0x00004c00,
+ CR0_GUEST_HOST_MASK = 0x00006000,
+ CR4_GUEST_HOST_MASK = 0x00006002,
+ CR0_READ_SHADOW = 0x00006004,
+ CR4_READ_SHADOW = 0x00006006,
+ CR3_TARGET_VALUE0 = 0x00006008,
+ CR3_TARGET_VALUE1 = 0x0000600a,
+ CR3_TARGET_VALUE2 = 0x0000600c,
+ CR3_TARGET_VALUE3 = 0x0000600e,
+ EXIT_QUALIFICATION = 0x00006400,
+ GUEST_LINEAR_ADDRESS = 0x0000640a,
+ GUEST_CR0 = 0x00006800,
+ GUEST_CR3 = 0x00006802,
+ GUEST_CR4 = 0x00006804,
+ GUEST_ES_BASE = 0x00006806,
+ GUEST_CS_BASE = 0x00006808,
+ GUEST_SS_BASE = 0x0000680a,
+ GUEST_DS_BASE = 0x0000680c,
+ GUEST_FS_BASE = 0x0000680e,
+ GUEST_GS_BASE = 0x00006810,
+ GUEST_LDTR_BASE = 0x00006812,
+ GUEST_TR_BASE = 0x00006814,
+ GUEST_GDTR_BASE = 0x00006816,
+ GUEST_IDTR_BASE = 0x00006818,
+ GUEST_DR7 = 0x0000681a,
+ GUEST_RSP = 0x0000681c,
+ GUEST_RIP = 0x0000681e,
+ GUEST_RFLAGS = 0x00006820,
+ GUEST_PENDING_DBG_EXCEPTIONS = 0x00006822,
+ GUEST_SYSENTER_ESP = 0x00006824,
+ GUEST_SYSENTER_EIP = 0x00006826,
+ HOST_CR0 = 0x00006c00,
+ HOST_CR3 = 0x00006c02,
+ HOST_CR4 = 0x00006c04,
+ HOST_FS_BASE = 0x00006c06,
+ HOST_GS_BASE = 0x00006c08,
+ HOST_TR_BASE = 0x00006c0a,
+ HOST_GDTR_BASE = 0x00006c0c,
+ HOST_IDTR_BASE = 0x00006c0e,
+ HOST_IA32_SYSENTER_ESP = 0x00006c10,
+ HOST_IA32_SYSENTER_EIP = 0x00006c12,
+ HOST_RSP = 0x00006c14,
+ HOST_RIP = 0x00006c16,
+};
+
+struct vmx_msr_entry {
+ uint32_t index;
+ uint32_t reserved;
+ uint64_t value;
+} __attribute__ ((aligned(16)));
+
+static inline int vmxon(uint64_t phys)
+{
+ uint8_t ret;
+
+ __asm__ __volatile__ ("vmxon %[pa]; setna %[ret]"
+ : [ret]"=rm"(ret)
+ : [pa]"m"(phys)
+ : "cc", "memory");
+
+ return ret;
+}
+
+static inline void vmxoff(void)
+{
+ __asm__ __volatile__("vmxoff");
+}
+
+static inline int vmclear(uint64_t vmcs_pa)
+{
+ uint8_t ret;
+
+ __asm__ __volatile__ ("vmclear %[pa]; setna %[ret]"
+ : [ret]"=rm"(ret)
+ : [pa]"m"(vmcs_pa)
+ : "cc", "memory");
+
+ return ret;
+}
+
+static inline int vmptrld(uint64_t vmcs_pa)
+{
+ uint8_t ret;
+
+ __asm__ __volatile__ ("vmptrld %[pa]; setna %[ret]"
+ : [ret]"=rm"(ret)
+ : [pa]"m"(vmcs_pa)
+ : "cc", "memory");
+
+ return ret;
+}
+
+/*
+ * No guest state (e.g. GPRs) is established by this vmlaunch.
+ */
+static inline int vmlaunch(void)
+{
+ int ret;
+
+ __asm__ __volatile__("push %%rbp;"
+ "push %%rcx;"
+ "push %%rdx;"
+ "push %%rsi;"
+ "push %%rdi;"
+ "push $0;"
+ "vmwrite %%rsp, %[host_rsp];"
+ "lea 1f(%%rip), %%rax;"
+ "vmwrite %%rax, %[host_rip];"
+ "vmlaunch;"
+ "incq (%%rsp);"
+ "1: pop %%rax;"
+ "pop %%rdi;"
+ "pop %%rsi;"
+ "pop %%rdx;"
+ "pop %%rcx;"
+ "pop %%rbp;"
+ : [ret]"=&a"(ret)
+ : [host_rsp]"r"((uint64_t)HOST_RSP),
+ [host_rip]"r"((uint64_t)HOST_RIP)
+ : "memory", "cc", "rbx", "r8", "r9", "r10",
+ "r11", "r12", "r13", "r14", "r15");
+ return ret;
+}
+
+/*
+ * No guest state (e.g. GPRs) is established by this vmresume.
+ */
+static inline int vmresume(void)
+{
+ int ret;
+
+ __asm__ __volatile__("push %%rbp;"
+ "push %%rcx;"
+ "push %%rdx;"
+ "push %%rsi;"
+ "push %%rdi;"
+ "push $0;"
+ "vmwrite %%rsp, %[host_rsp];"
+ "lea 1f(%%rip), %%rax;"
+ "vmwrite %%rax, %[host_rip];"
+ "vmresume;"
+ "incq (%%rsp);"
+ "1: pop %%rax;"
+ "pop %%rdi;"
+ "pop %%rsi;"
+ "pop %%rdx;"
+ "pop %%rcx;"
+ "pop %%rbp;"
+ : [ret]"=&a"(ret)
+ : [host_rsp]"r"((uint64_t)HOST_RSP),
+ [host_rip]"r"((uint64_t)HOST_RIP)
+ : "memory", "cc", "rbx", "r8", "r9", "r10",
+ "r11", "r12", "r13", "r14", "r15");
+ return ret;
+}
+
+static inline int vmread(uint64_t encoding, uint64_t *value)
+{
+ uint64_t tmp;
+ uint8_t ret;
+
+ __asm__ __volatile__("vmread %[encoding], %[value]; setna %[ret]"
+ : [value]"=rm"(tmp), [ret]"=rm"(ret)
+ : [encoding]"r"(encoding)
+ : "cc", "memory");
+
+ *value = tmp;
+ return ret;
+}
+
+/*
+ * A wrapper around vmread that ignores errors and returns zero if the
+ * vmread instruction fails.
+ */
+static inline uint64_t vmreadz(uint64_t encoding)
+{
+ uint64_t value = 0;
+ vmread(encoding, &value);
+ return value;
+}
+
+static inline int vmwrite(uint64_t encoding, uint64_t value)
+{
+ uint8_t ret;
+
+ __asm__ __volatile__ ("vmwrite %[value], %[encoding]; setna %[ret]"
+ : [ret]"=rm"(ret)
+ : [value]"rm"(value), [encoding]"r"(encoding)
+ : "cc", "memory");
+
+ return ret;
+}
+
+static inline uint32_t vmcs_revision(void)
+{
+ return rdmsr(MSR_IA32_VMX_BASIC);
+}
+
+void prepare_for_vmx_operation(void);
+void prepare_vmcs(void *guest_rip, void *guest_rsp);
+struct kvm_vm *vm_create_default_vmx(uint32_t vcpuid,
+ vmx_guest_code_t guest_code);
+
+#endif /* !SELFTEST_KVM_VMX_H */
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 7ca1bb4..37e2a78 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -50,8 +50,8 @@ int kvm_check_cap(long cap)
int kvm_fd;
kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
- TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i",
- KVM_DEV_PATH, kvm_fd, errno);
+ if (kvm_fd < 0)
+ exit(KSFT_SKIP);
ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap);
TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n"
@@ -91,8 +91,8 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
vm->mode = mode;
kvm_fd = open(KVM_DEV_PATH, perm);
- TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i",
- KVM_DEV_PATH, kvm_fd, errno);
+ if (kvm_fd < 0)
+ exit(KSFT_SKIP);
/* Create VM. */
vm->fd = ioctl(kvm_fd, KVM_CREATE_VM, NULL);
@@ -378,7 +378,7 @@ int kvm_memcmp_hva_gva(void *hva,
* complicated. This function uses a reasonable default length for
* the array and performs the appropriate allocation.
*/
-struct kvm_cpuid2 *allocate_kvm_cpuid2(void)
+static struct kvm_cpuid2 *allocate_kvm_cpuid2(void)
{
struct kvm_cpuid2 *cpuid;
int nent = 100;
@@ -402,26 +402,31 @@ struct kvm_cpuid2 *allocate_kvm_cpuid2(void)
* Input Args: None
*
* Output Args:
- * cpuid - The supported KVM CPUID
*
- * Return: void
+ * Return: The supported KVM CPUID
*
* Get the guest CPUID supported by KVM.
*/
-void kvm_get_supported_cpuid(struct kvm_cpuid2 *cpuid)
+struct kvm_cpuid2 *kvm_get_supported_cpuid(void)
{
+ static struct kvm_cpuid2 *cpuid;
int ret;
int kvm_fd;
+ if (cpuid)
+ return cpuid;
+
+ cpuid = allocate_kvm_cpuid2();
kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
- TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i",
- KVM_DEV_PATH, kvm_fd, errno);
+ if (kvm_fd < 0)
+ exit(KSFT_SKIP);
ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid);
TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n",
ret, errno);
close(kvm_fd);
+ return cpuid;
}
/* Locate a cpuid entry.
@@ -435,12 +440,13 @@ void kvm_get_supported_cpuid(struct kvm_cpuid2 *cpuid)
* Return: A pointer to the cpuid entry. Never returns NULL.
*/
struct kvm_cpuid_entry2 *
-find_cpuid_index_entry(struct kvm_cpuid2 *cpuid, uint32_t function,
- uint32_t index)
+kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
{
+ struct kvm_cpuid2 *cpuid;
struct kvm_cpuid_entry2 *entry = NULL;
int i;
+ cpuid = kvm_get_supported_cpuid();
for (i = 0; i < cpuid->nent; i++) {
if (cpuid->entries[i].function == function &&
cpuid->entries[i].index == index) {
@@ -669,8 +675,8 @@ static int vcpu_mmap_sz(void)
int dev_fd, ret;
dev_fd = open(KVM_DEV_PATH, O_RDONLY);
- TEST_ASSERT(dev_fd >= 0, "%s open %s failed, rc: %i errno: %i",
- __func__, KVM_DEV_PATH, dev_fd, errno);
+ if (dev_fd < 0)
+ exit(KSFT_SKIP);
ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL);
TEST_ASSERT(ret >= sizeof(struct kvm_run),
@@ -1435,7 +1441,7 @@ vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm,
sparsebit_idx_t pg;
TEST_ASSERT((paddr_min % vm->page_size) == 0, "Min physical address "
- "not divisable by page size.\n"
+ "not divisible by page size.\n"
" paddr_min: 0x%lx page_size: 0x%x",
paddr_min, vm->page_size);
diff --git a/tools/testing/selftests/kvm/lib/sparsebit.c b/tools/testing/selftests/kvm/lib/sparsebit.c
index 0c5cf3e..b132bc9 100644
--- a/tools/testing/selftests/kvm/lib/sparsebit.c
+++ b/tools/testing/selftests/kvm/lib/sparsebit.c
@@ -121,7 +121,7 @@
* avoided by moving the setting of the nodes mask bits into
* the previous nodes num_after setting.
*
- * + Node starting index is evenly divisable by the number of bits
+ * + Node starting index is evenly divisible by the number of bits
* within a nodes mask member.
*
* + Nodes never represent a range of bits that wrap around the
@@ -1741,7 +1741,7 @@ void sparsebit_validate_internal(struct sparsebit *s)
/* Validate node index is divisible by the mask size */
if (nodep->idx % MASK_BITS) {
- fprintf(stderr, "Node index not divisable by "
+ fprintf(stderr, "Node index not divisible by "
"mask size,\n"
" nodep: %p nodep->idx: 0x%lx "
"MASK_BITS: %lu\n",
diff --git a/tools/testing/selftests/kvm/lib/vmx.c b/tools/testing/selftests/kvm/lib/vmx.c
new file mode 100644
index 0000000..0231bc0
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/vmx.c
@@ -0,0 +1,243 @@
+/*
+ * tools/testing/selftests/kvm/lib/x86.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "x86.h"
+#include "vmx.h"
+
+/* Create a default VM for VMX tests.
+ *
+ * Input Args:
+ * vcpuid - The id of the single VCPU to add to the VM.
+ * guest_code - The vCPU's entry point
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Pointer to opaque structure that describes the created VM.
+ */
+struct kvm_vm *
+vm_create_default_vmx(uint32_t vcpuid, vmx_guest_code_t guest_code)
+{
+ struct kvm_cpuid2 *cpuid;
+ struct kvm_vm *vm;
+ vm_vaddr_t vmxon_vaddr;
+ vm_paddr_t vmxon_paddr;
+ vm_vaddr_t vmcs_vaddr;
+ vm_paddr_t vmcs_paddr;
+
+ vm = vm_create_default(vcpuid, (void *) guest_code);
+
+ /* Enable nesting in CPUID */
+ vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid());
+
+ /* Setup of a region of guest memory for the vmxon region. */
+ vmxon_vaddr = vm_vaddr_alloc(vm, getpagesize(), 0, 0, 0);
+ vmxon_paddr = addr_gva2gpa(vm, vmxon_vaddr);
+
+ /* Setup of a region of guest memory for a vmcs. */
+ vmcs_vaddr = vm_vaddr_alloc(vm, getpagesize(), 0, 0, 0);
+ vmcs_paddr = addr_gva2gpa(vm, vmcs_vaddr);
+
+ vcpu_args_set(vm, vcpuid, 4, vmxon_vaddr, vmxon_paddr, vmcs_vaddr,
+ vmcs_paddr);
+
+ return vm;
+}
+
+void prepare_for_vmx_operation(void)
+{
+ uint64_t feature_control;
+ uint64_t required;
+ unsigned long cr0;
+ unsigned long cr4;
+
+ /*
+ * Ensure bits in CR0 and CR4 are valid in VMX operation:
+ * - Bit X is 1 in _FIXED0: bit X is fixed to 1 in CRx.
+ * - Bit X is 0 in _FIXED1: bit X is fixed to 0 in CRx.
+ */
+ __asm__ __volatile__("mov %%cr0, %0" : "=r"(cr0) : : "memory");
+ cr0 &= rdmsr(MSR_IA32_VMX_CR0_FIXED1);
+ cr0 |= rdmsr(MSR_IA32_VMX_CR0_FIXED0);
+ __asm__ __volatile__("mov %0, %%cr0" : : "r"(cr0) : "memory");
+
+ __asm__ __volatile__("mov %%cr4, %0" : "=r"(cr4) : : "memory");
+ cr4 &= rdmsr(MSR_IA32_VMX_CR4_FIXED1);
+ cr4 |= rdmsr(MSR_IA32_VMX_CR4_FIXED0);
+ /* Enable VMX operation */
+ cr4 |= X86_CR4_VMXE;
+ __asm__ __volatile__("mov %0, %%cr4" : : "r"(cr4) : "memory");
+
+ /*
+ * Configure IA32_FEATURE_CONTROL MSR to allow VMXON:
+ * Bit 0: Lock bit. If clear, VMXON causes a #GP.
+ * Bit 2: Enables VMXON outside of SMX operation. If clear, VMXON
+ * outside of SMX causes a #GP.
+ */
+ required = FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+ required |= FEATURE_CONTROL_LOCKED;
+ feature_control = rdmsr(MSR_IA32_FEATURE_CONTROL);
+ if ((feature_control & required) != required)
+ wrmsr(MSR_IA32_FEATURE_CONTROL, feature_control | required);
+}
+
+/*
+ * Initialize the control fields to the most basic settings possible.
+ */
+static inline void init_vmcs_control_fields(void)
+{
+ vmwrite(VIRTUAL_PROCESSOR_ID, 0);
+ vmwrite(POSTED_INTR_NV, 0);
+
+ vmwrite(PIN_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_PINBASED_CTLS));
+ vmwrite(CPU_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_PROCBASED_CTLS));
+ vmwrite(EXCEPTION_BITMAP, 0);
+ vmwrite(PAGE_FAULT_ERROR_CODE_MASK, 0);
+ vmwrite(PAGE_FAULT_ERROR_CODE_MATCH, -1); /* Never match */
+ vmwrite(CR3_TARGET_COUNT, 0);
+ vmwrite(VM_EXIT_CONTROLS, rdmsr(MSR_IA32_VMX_EXIT_CTLS) |
+ VM_EXIT_HOST_ADDR_SPACE_SIZE); /* 64-bit host */
+ vmwrite(VM_EXIT_MSR_STORE_COUNT, 0);
+ vmwrite(VM_EXIT_MSR_LOAD_COUNT, 0);
+ vmwrite(VM_ENTRY_CONTROLS, rdmsr(MSR_IA32_VMX_ENTRY_CTLS) |
+ VM_ENTRY_IA32E_MODE); /* 64-bit guest */
+ vmwrite(VM_ENTRY_MSR_LOAD_COUNT, 0);
+ vmwrite(VM_ENTRY_INTR_INFO_FIELD, 0);
+ vmwrite(TPR_THRESHOLD, 0);
+ vmwrite(SECONDARY_VM_EXEC_CONTROL, 0);
+
+ vmwrite(CR0_GUEST_HOST_MASK, 0);
+ vmwrite(CR4_GUEST_HOST_MASK, 0);
+ vmwrite(CR0_READ_SHADOW, get_cr0());
+ vmwrite(CR4_READ_SHADOW, get_cr4());
+}
+
+/*
+ * Initialize the host state fields based on the current host state, with
+ * the exception of HOST_RSP and HOST_RIP, which should be set by vmlaunch
+ * or vmresume.
+ */
+static inline void init_vmcs_host_state(void)
+{
+ uint32_t exit_controls = vmreadz(VM_EXIT_CONTROLS);
+
+ vmwrite(HOST_ES_SELECTOR, get_es());
+ vmwrite(HOST_CS_SELECTOR, get_cs());
+ vmwrite(HOST_SS_SELECTOR, get_ss());
+ vmwrite(HOST_DS_SELECTOR, get_ds());
+ vmwrite(HOST_FS_SELECTOR, get_fs());
+ vmwrite(HOST_GS_SELECTOR, get_gs());
+ vmwrite(HOST_TR_SELECTOR, get_tr());
+
+ if (exit_controls & VM_EXIT_LOAD_IA32_PAT)
+ vmwrite(HOST_IA32_PAT, rdmsr(MSR_IA32_CR_PAT));
+ if (exit_controls & VM_EXIT_LOAD_IA32_EFER)
+ vmwrite(HOST_IA32_EFER, rdmsr(MSR_EFER));
+ if (exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+ vmwrite(HOST_IA32_PERF_GLOBAL_CTRL,
+ rdmsr(MSR_CORE_PERF_GLOBAL_CTRL));
+
+ vmwrite(HOST_IA32_SYSENTER_CS, rdmsr(MSR_IA32_SYSENTER_CS));
+
+ vmwrite(HOST_CR0, get_cr0());
+ vmwrite(HOST_CR3, get_cr3());
+ vmwrite(HOST_CR4, get_cr4());
+ vmwrite(HOST_FS_BASE, rdmsr(MSR_FS_BASE));
+ vmwrite(HOST_GS_BASE, rdmsr(MSR_GS_BASE));
+ vmwrite(HOST_TR_BASE,
+ get_desc64_base((struct desc64 *)(get_gdt_base() + get_tr())));
+ vmwrite(HOST_GDTR_BASE, get_gdt_base());
+ vmwrite(HOST_IDTR_BASE, get_idt_base());
+ vmwrite(HOST_IA32_SYSENTER_ESP, rdmsr(MSR_IA32_SYSENTER_ESP));
+ vmwrite(HOST_IA32_SYSENTER_EIP, rdmsr(MSR_IA32_SYSENTER_EIP));
+}
+
+/*
+ * Initialize the guest state fields essentially as a clone of
+ * the host state fields. Some host state fields have fixed
+ * values, and we set the corresponding guest state fields accordingly.
+ */
+static inline void init_vmcs_guest_state(void *rip, void *rsp)
+{
+ vmwrite(GUEST_ES_SELECTOR, vmreadz(HOST_ES_SELECTOR));
+ vmwrite(GUEST_CS_SELECTOR, vmreadz(HOST_CS_SELECTOR));
+ vmwrite(GUEST_SS_SELECTOR, vmreadz(HOST_SS_SELECTOR));
+ vmwrite(GUEST_DS_SELECTOR, vmreadz(HOST_DS_SELECTOR));
+ vmwrite(GUEST_FS_SELECTOR, vmreadz(HOST_FS_SELECTOR));
+ vmwrite(GUEST_GS_SELECTOR, vmreadz(HOST_GS_SELECTOR));
+ vmwrite(GUEST_LDTR_SELECTOR, 0);
+ vmwrite(GUEST_TR_SELECTOR, vmreadz(HOST_TR_SELECTOR));
+ vmwrite(GUEST_INTR_STATUS, 0);
+ vmwrite(GUEST_PML_INDEX, 0);
+
+ vmwrite(VMCS_LINK_POINTER, -1ll);
+ vmwrite(GUEST_IA32_DEBUGCTL, 0);
+ vmwrite(GUEST_IA32_PAT, vmreadz(HOST_IA32_PAT));
+ vmwrite(GUEST_IA32_EFER, vmreadz(HOST_IA32_EFER));
+ vmwrite(GUEST_IA32_PERF_GLOBAL_CTRL,
+ vmreadz(HOST_IA32_PERF_GLOBAL_CTRL));
+
+ vmwrite(GUEST_ES_LIMIT, -1);
+ vmwrite(GUEST_CS_LIMIT, -1);
+ vmwrite(GUEST_SS_LIMIT, -1);
+ vmwrite(GUEST_DS_LIMIT, -1);
+ vmwrite(GUEST_FS_LIMIT, -1);
+ vmwrite(GUEST_GS_LIMIT, -1);
+ vmwrite(GUEST_LDTR_LIMIT, -1);
+ vmwrite(GUEST_TR_LIMIT, 0x67);
+ vmwrite(GUEST_GDTR_LIMIT, 0xffff);
+ vmwrite(GUEST_IDTR_LIMIT, 0xffff);
+ vmwrite(GUEST_ES_AR_BYTES,
+ vmreadz(GUEST_ES_SELECTOR) == 0 ? 0x10000 : 0xc093);
+ vmwrite(GUEST_CS_AR_BYTES, 0xa09b);
+ vmwrite(GUEST_SS_AR_BYTES, 0xc093);
+ vmwrite(GUEST_DS_AR_BYTES,
+ vmreadz(GUEST_DS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+ vmwrite(GUEST_FS_AR_BYTES,
+ vmreadz(GUEST_FS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+ vmwrite(GUEST_GS_AR_BYTES,
+ vmreadz(GUEST_GS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+ vmwrite(GUEST_LDTR_AR_BYTES, 0x10000);
+ vmwrite(GUEST_TR_AR_BYTES, 0x8b);
+ vmwrite(GUEST_INTERRUPTIBILITY_INFO, 0);
+ vmwrite(GUEST_ACTIVITY_STATE, 0);
+ vmwrite(GUEST_SYSENTER_CS, vmreadz(HOST_IA32_SYSENTER_CS));
+ vmwrite(VMX_PREEMPTION_TIMER_VALUE, 0);
+
+ vmwrite(GUEST_CR0, vmreadz(HOST_CR0));
+ vmwrite(GUEST_CR3, vmreadz(HOST_CR3));
+ vmwrite(GUEST_CR4, vmreadz(HOST_CR4));
+ vmwrite(GUEST_ES_BASE, 0);
+ vmwrite(GUEST_CS_BASE, 0);
+ vmwrite(GUEST_SS_BASE, 0);
+ vmwrite(GUEST_DS_BASE, 0);
+ vmwrite(GUEST_FS_BASE, vmreadz(HOST_FS_BASE));
+ vmwrite(GUEST_GS_BASE, vmreadz(HOST_GS_BASE));
+ vmwrite(GUEST_LDTR_BASE, 0);
+ vmwrite(GUEST_TR_BASE, vmreadz(HOST_TR_BASE));
+ vmwrite(GUEST_GDTR_BASE, vmreadz(HOST_GDTR_BASE));
+ vmwrite(GUEST_IDTR_BASE, vmreadz(HOST_IDTR_BASE));
+ vmwrite(GUEST_DR7, 0x400);
+ vmwrite(GUEST_RSP, (uint64_t)rsp);
+ vmwrite(GUEST_RIP, (uint64_t)rip);
+ vmwrite(GUEST_RFLAGS, 2);
+ vmwrite(GUEST_PENDING_DBG_EXCEPTIONS, 0);
+ vmwrite(GUEST_SYSENTER_ESP, vmreadz(HOST_IA32_SYSENTER_ESP));
+ vmwrite(GUEST_SYSENTER_EIP, vmreadz(HOST_IA32_SYSENTER_EIP));
+}
+
+void prepare_vmcs(void *guest_rip, void *guest_rsp)
+{
+ init_vmcs_control_fields();
+ init_vmcs_host_state();
+ init_vmcs_guest_state(guest_rip, guest_rsp);
+}
diff --git a/tools/testing/selftests/kvm/sync_regs_test.c b/tools/testing/selftests/kvm/sync_regs_test.c
index 428e947..eae1ece 100644
--- a/tools/testing/selftests/kvm/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/sync_regs_test.c
@@ -85,6 +85,9 @@ static void compare_vcpu_events(struct kvm_vcpu_events *left,
{
}
+#define TEST_SYNC_FIELDS (KVM_SYNC_X86_REGS|KVM_SYNC_X86_SREGS|KVM_SYNC_X86_EVENTS)
+#define INVALID_SYNC_FIELD 0x80000000
+
int main(int argc, char *argv[])
{
struct kvm_vm *vm;
@@ -98,9 +101,14 @@ int main(int argc, char *argv[])
setbuf(stdout, NULL);
cap = kvm_check_cap(KVM_CAP_SYNC_REGS);
- TEST_ASSERT((unsigned long)cap == KVM_SYNC_X86_VALID_FIELDS,
- "KVM_CAP_SYNC_REGS (0x%x) != KVM_SYNC_X86_VALID_FIELDS (0x%lx)\n",
- cap, KVM_SYNC_X86_VALID_FIELDS);
+ if ((cap & TEST_SYNC_FIELDS) != TEST_SYNC_FIELDS) {
+ fprintf(stderr, "KVM_CAP_SYNC_REGS not supported, skipping test\n");
+ exit(KSFT_SKIP);
+ }
+ if ((cap & INVALID_SYNC_FIELD) != 0) {
+ fprintf(stderr, "The \"invalid\" field is not invalid, skipping test\n");
+ exit(KSFT_SKIP);
+ }
/* Create VM */
vm = vm_create_default(VCPU_ID, guest_code);
@@ -108,7 +116,14 @@ int main(int argc, char *argv[])
run = vcpu_state(vm, VCPU_ID);
/* Request reading invalid register set from VCPU. */
- run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS << 1;
+ run->kvm_valid_regs = INVALID_SYNC_FIELD;
+ rv = _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(rv < 0 && errno == EINVAL,
+ "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+ rv);
+ vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0;
+
+ run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
rv = _vcpu_run(vm, VCPU_ID);
TEST_ASSERT(rv < 0 && errno == EINVAL,
"Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
@@ -116,7 +131,14 @@ int main(int argc, char *argv[])
vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0;
/* Request setting invalid register set into VCPU. */
- run->kvm_dirty_regs = KVM_SYNC_X86_VALID_FIELDS << 1;
+ run->kvm_dirty_regs = INVALID_SYNC_FIELD;
+ rv = _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(rv < 0 && errno == EINVAL,
+ "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+ rv);
+ vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0;
+
+ run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
rv = _vcpu_run(vm, VCPU_ID);
TEST_ASSERT(rv < 0 && errno == EINVAL,
"Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
@@ -125,7 +147,7 @@ int main(int argc, char *argv[])
/* Request and verify all valid register sets. */
/* TODO: BUILD TIME CHECK: TEST_ASSERT(KVM_SYNC_X86_NUM_FIELDS != 3); */
- run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS;
+ run->kvm_valid_regs = TEST_SYNC_FIELDS;
rv = _vcpu_run(vm, VCPU_ID);
TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
"Unexpected exit reason: %u (%s),\n",
@@ -146,7 +168,7 @@ int main(int argc, char *argv[])
run->s.regs.sregs.apic_base = 1 << 11;
/* TODO run->s.regs.events.XYZ = ABC; */
- run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS;
+ run->kvm_valid_regs = TEST_SYNC_FIELDS;
run->kvm_dirty_regs = KVM_SYNC_X86_REGS | KVM_SYNC_X86_SREGS;
rv = _vcpu_run(vm, VCPU_ID);
TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
@@ -172,7 +194,7 @@ int main(int argc, char *argv[])
/* Clear kvm_dirty_regs bits, verify new s.regs values are
* overwritten with existing guest values.
*/
- run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS;
+ run->kvm_valid_regs = TEST_SYNC_FIELDS;
run->kvm_dirty_regs = 0;
run->s.regs.regs.r11 = 0xDEADBEEF;
rv = _vcpu_run(vm, VCPU_ID);
@@ -211,7 +233,7 @@ int main(int argc, char *argv[])
* with kvm_sync_regs values.
*/
run->kvm_valid_regs = 0;
- run->kvm_dirty_regs = KVM_SYNC_X86_VALID_FIELDS;
+ run->kvm_dirty_regs = TEST_SYNC_FIELDS;
run->s.regs.regs.r11 = 0xBBBB;
rv = _vcpu_run(vm, VCPU_ID);
TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
diff --git a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
new file mode 100644
index 0000000..aaa6332
--- /dev/null
+++ b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
@@ -0,0 +1,231 @@
+/*
+ * gtests/tests/vmx_tsc_adjust_test.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ *
+ * IA32_TSC_ADJUST test
+ *
+ * According to the SDM, "if an execution of WRMSR to the
+ * IA32_TIME_STAMP_COUNTER MSR adds (or subtracts) value X from the TSC,
+ * the logical processor also adds (or subtracts) value X from the
+ * IA32_TSC_ADJUST MSR.
+ *
+ * Note that when L1 doesn't intercept writes to IA32_TSC, a
+ * WRMSR(IA32_TSC) from L2 sets L1's TSC value, not L2's perceived TSC
+ * value.
+ *
+ * This test verifies that this unusual case is handled correctly.
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "x86.h"
+#include "vmx.h"
+
+#include <string.h>
+#include <sys/ioctl.h>
+
+#ifndef MSR_IA32_TSC_ADJUST
+#define MSR_IA32_TSC_ADJUST 0x3b
+#endif
+
+#define PAGE_SIZE 4096
+#define VCPU_ID 5
+
+#define TSC_ADJUST_VALUE (1ll << 32)
+#define TSC_OFFSET_VALUE -(1ll << 48)
+
+enum {
+ PORT_ABORT = 0x1000,
+ PORT_REPORT,
+ PORT_DONE,
+};
+
+struct vmx_page {
+ vm_vaddr_t virt;
+ vm_paddr_t phys;
+};
+
+enum {
+ VMXON_PAGE = 0,
+ VMCS_PAGE,
+ MSR_BITMAP_PAGE,
+
+ NUM_VMX_PAGES,
+};
+
+struct kvm_single_msr {
+ struct kvm_msrs header;
+ struct kvm_msr_entry entry;
+} __attribute__((packed));
+
+/* The virtual machine object. */
+static struct kvm_vm *vm;
+
+/* Array of vmx_page descriptors that is shared with the guest. */
+struct vmx_page *vmx_pages;
+
+#define exit_to_l0(_port, _arg) do_exit_to_l0(_port, (unsigned long) (_arg))
+static void do_exit_to_l0(uint16_t port, unsigned long arg)
+{
+ __asm__ __volatile__("in %[port], %%al"
+ :
+ : [port]"d"(port), "D"(arg)
+ : "rax");
+}
+
+
+#define GUEST_ASSERT(_condition) do { \
+ if (!(_condition)) \
+ exit_to_l0(PORT_ABORT, "Failed guest assert: " #_condition); \
+} while (0)
+
+static void check_ia32_tsc_adjust(int64_t max)
+{
+ int64_t adjust;
+
+ adjust = rdmsr(MSR_IA32_TSC_ADJUST);
+ exit_to_l0(PORT_REPORT, adjust);
+ GUEST_ASSERT(adjust <= max);
+}
+
+static void l2_guest_code(void)
+{
+ uint64_t l1_tsc = rdtsc() - TSC_OFFSET_VALUE;
+
+ wrmsr(MSR_IA32_TSC, l1_tsc - TSC_ADJUST_VALUE);
+ check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
+
+ /* Exit to L1 */
+ __asm__ __volatile__("vmcall");
+}
+
+static void l1_guest_code(struct vmx_page *vmx_pages)
+{
+#define L2_GUEST_STACK_SIZE 64
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+ uint32_t control;
+ uintptr_t save_cr3;
+
+ GUEST_ASSERT(rdtsc() < TSC_ADJUST_VALUE);
+ wrmsr(MSR_IA32_TSC, rdtsc() - TSC_ADJUST_VALUE);
+ check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
+
+ prepare_for_vmx_operation();
+
+ /* Enter VMX root operation. */
+ *(uint32_t *)vmx_pages[VMXON_PAGE].virt = vmcs_revision();
+ GUEST_ASSERT(!vmxon(vmx_pages[VMXON_PAGE].phys));
+
+ /* Load a VMCS. */
+ *(uint32_t *)vmx_pages[VMCS_PAGE].virt = vmcs_revision();
+ GUEST_ASSERT(!vmclear(vmx_pages[VMCS_PAGE].phys));
+ GUEST_ASSERT(!vmptrld(vmx_pages[VMCS_PAGE].phys));
+
+ /* Prepare the VMCS for L2 execution. */
+ prepare_vmcs(l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+ control = vmreadz(CPU_BASED_VM_EXEC_CONTROL);
+ control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETING;
+ vmwrite(CPU_BASED_VM_EXEC_CONTROL, control);
+ vmwrite(MSR_BITMAP, vmx_pages[MSR_BITMAP_PAGE].phys);
+ vmwrite(TSC_OFFSET, TSC_OFFSET_VALUE);
+
+ /* Jump into L2. First, test failure to load guest CR3. */
+ save_cr3 = vmreadz(GUEST_CR3);
+ vmwrite(GUEST_CR3, -1ull);
+ GUEST_ASSERT(!vmlaunch());
+ GUEST_ASSERT(vmreadz(VM_EXIT_REASON) ==
+ (EXIT_REASON_FAILED_VMENTRY | EXIT_REASON_INVALID_STATE));
+ check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
+ vmwrite(GUEST_CR3, save_cr3);
+
+ GUEST_ASSERT(!vmlaunch());
+ GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+ check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
+
+ exit_to_l0(PORT_DONE, 0);
+}
+
+static void allocate_vmx_page(struct vmx_page *page)
+{
+ vm_vaddr_t virt;
+
+ virt = vm_vaddr_alloc(vm, PAGE_SIZE, 0, 0, 0);
+ memset(addr_gva2hva(vm, virt), 0, PAGE_SIZE);
+
+ page->virt = virt;
+ page->phys = addr_gva2gpa(vm, virt);
+}
+
+static vm_vaddr_t allocate_vmx_pages(void)
+{
+ vm_vaddr_t vmx_pages_vaddr;
+ int i;
+
+ vmx_pages_vaddr = vm_vaddr_alloc(
+ vm, sizeof(struct vmx_page) * NUM_VMX_PAGES, 0, 0, 0);
+
+ vmx_pages = (void *) addr_gva2hva(vm, vmx_pages_vaddr);
+
+ for (i = 0; i < NUM_VMX_PAGES; i++)
+ allocate_vmx_page(&vmx_pages[i]);
+
+ return vmx_pages_vaddr;
+}
+
+void report(int64_t val)
+{
+ printf("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n",
+ val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE);
+}
+
+int main(int argc, char *argv[])
+{
+ vm_vaddr_t vmx_pages_vaddr;
+ struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
+
+ if (!(entry->ecx & CPUID_VMX)) {
+ fprintf(stderr, "nested VMX not enabled, skipping test\n");
+ exit(KSFT_SKIP);
+ }
+
+ vm = vm_create_default_vmx(VCPU_ID, (void *) l1_guest_code);
+
+ /* Allocate VMX pages and shared descriptors (vmx_pages). */
+ vmx_pages_vaddr = allocate_vmx_pages();
+ vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_vaddr);
+
+ for (;;) {
+ volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+ struct kvm_regs regs;
+
+ vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Got exit_reason other than KVM_EXIT_IO: %u (%s),\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ vcpu_regs_get(vm, VCPU_ID, ®s);
+
+ switch (run->io.port) {
+ case PORT_ABORT:
+ TEST_ASSERT(false, "%s", (const char *) regs.rdi);
+ /* NOT REACHED */
+ case PORT_REPORT:
+ report(regs.rdi);
+ break;
+ case PORT_DONE:
+ goto done;
+ default:
+ TEST_ASSERT(false, "Unknown port 0x%x.", run->io.port);
+ }
+ }
+
+ kvm_vm_free(vm);
+done:
+ return 0;
+}
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 195e9d4..c1b1a4d 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -20,10 +20,10 @@
.ONESHELL:
define RUN_TESTS
- @export KSFT_TAP_LEVEL=`echo 1`;
- @test_num=`echo 0`;
- @echo "TAP version 13";
- @for TEST in $(1); do \
+ @export KSFT_TAP_LEVEL=`echo 1`; \
+ test_num=`echo 0`; \
+ echo "TAP version 13"; \
+ for TEST in $(1); do \
BASENAME_TEST=`basename $$TEST`; \
test_num=`echo $$test_num+1 | bc`; \
echo "selftests: $$BASENAME_TEST"; \
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 785fc18..3ff81a4 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -6,6 +6,7 @@
TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh
+TEST_PROGS_EXTENDED := in_netns.sh
TEST_GEN_FILES = socket
TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 6a75a3e..7ba089b 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -7,3 +7,8 @@
CONFIG_IPV6=y
CONFIG_IPV6_MULTIPLE_TABLES=y
CONFIG_VETH=y
+CONFIG_INET_XFRM_MODE_TUNNEL=y
+CONFIG_NET_IPVTI=y
+CONFIG_INET6_XFRM_MODE_TUNNEL=y
+CONFIG_IPV6_VTI=y
+CONFIG_DUMMY=y
diff --git a/tools/testing/selftests/net/reuseport_bpf_numa.c b/tools/testing/selftests/net/reuseport_bpf_numa.c
index 365c32e..c9f478b 100644
--- a/tools/testing/selftests/net/reuseport_bpf_numa.c
+++ b/tools/testing/selftests/net/reuseport_bpf_numa.c
@@ -23,6 +23,8 @@
#include <unistd.h>
#include <numa.h>
+#include "../kselftest.h"
+
static const int PORT = 8888;
static void build_rcv_group(int *rcv_fd, size_t len, int family, int proto)
@@ -229,7 +231,7 @@ int main(void)
int *rcv_fd, nodes;
if (numa_available() < 0)
- error(1, errno, "no numa api support");
+ ksft_exit_skip("no numa api support\n");
nodes = numa_max_node() + 1;
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
new file mode 100755
index 0000000..98f650c
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
@@ -0,0 +1,56 @@
+#!/bin/sh
+#
+# Invoke a text editor on all console.log files for all runs with diagnostics,
+# that is, on all such files having a console.log.diags counterpart.
+# Note that both console.log.diags and console.log are passed to the
+# editor (currently defaulting to "vi"), allowing the user to get an
+# idea of what to search for in the console.log file.
+#
+# Usage: kvm-find-errors.sh directory
+#
+# The "directory" above should end with the date/time directory, for example,
+# "tools/testing/selftests/rcutorture/res/2018.02.25-14:27:27".
+
+rundir="${1}"
+if test -z "$rundir" -o ! -d "$rundir"
+then
+ echo Usage: $0 directory
+fi
+editor=${EDITOR-vi}
+
+# Find builds with errors
+files=
+for i in ${rundir}/*/Make.out
+do
+ if egrep -q "error:|warning:" < $i
+ then
+ egrep "error:|warning:" < $i > $i.diags
+ files="$files $i.diags $i"
+ fi
+done
+if test -n "$files"
+then
+ $editor $files
+else
+ echo No build errors.
+fi
+if grep -q -e "--buildonly" < ${rundir}/log
+then
+ echo Build-only run, no console logs to check.
+fi
+
+# Find console logs with errors
+files=
+for i in ${rundir}/*/console.log
+do
+ if test -r $i.diags
+ then
+ files="$files $i.diags $i"
+ fi
+done
+if test -n "$files"
+then
+ $editor $files
+else
+ echo No errors in console logs.
+fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index c2e1bb6..477ecb12 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -34,11 +34,15 @@
configfile=`echo $i | sed -e 's/^.*\///'`
ngps=`grep ver: $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* ver: //' -e 's/ .*$//'`
+stopstate="`grep 'End-test grace-period state: g' $i/console.log 2> /dev/null |
+ tail -1 | sed -e 's/^\[[ 0-9.]*] //' |
+ awk '{ print \"[\" $1 \" \" $5 \" \" $6 \" \" $7 \"]\"; }' |
+ tr -d '\012\015'`"
if test -z "$ngps"
then
- echo "$configfile -------"
+ echo "$configfile ------- " $stopstate
else
- title="$configfile ------- $ngps grace periods"
+ title="$configfile ------- $ngps GPs"
dur=`sed -e 's/^.* rcutorture.shutdown_secs=//' -e 's/ .*$//' < $i/qemu-cmd 2> /dev/null`
if test -z "$dur"
then
@@ -46,9 +50,9 @@
else
ngpsps=`awk -v ngps=$ngps -v dur=$dur '
BEGIN { print ngps / dur }' < /dev/null`
- title="$title ($ngpsps per second)"
+ title="$title ($ngpsps/s)"
fi
- echo $title
+ echo $title $stopstate
nclosecalls=`grep --binary-files=text 'torture: Reader Batch' $i/console.log | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'`
if test -z "$nclosecalls"
then
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index f7e988f..c27e978 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -48,10 +48,6 @@
cat $i/Make.oldconfig.err
fi
parse-build.sh $i/Make.out $configfile
- if test "$TORTURE_SUITE" != rcuperf
- then
- parse-torture.sh $i/console.log $configfile
- fi
parse-console.sh $i/console.log $configfile
if test -r $i/Warnings
then
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index 5f8fbb0..c5b0f94 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -267,5 +267,4 @@
echo Unknown PID, cannot kill qemu command
fi
-parse-torture.sh $resdir/console.log $title
parse-console.sh $resdir/console.log $title
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 08aa7d5..1729343 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -24,57 +24,146 @@
#
# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+T=${TMPDIR-/tmp}/parse-console.sh.$$
file="$1"
title="$2"
+trap 'rm -f $T.seq $T.diags' 0
+
. functions.sh
+# Check for presence and readability of console output file
+if test -f "$file" -a -r "$file"
+then
+ :
+else
+ echo $title unreadable console output file: $file
+ exit 1
+fi
if grep -Pq '\x00' < $file
then
print_warning Console output contains nul bytes, old qemu still running?
fi
-egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $1.diags
-if test -s $1.diags
+cat /dev/null > $file.diags
+
+# Check for proper termination, except that rcuperf runs don't indicate this.
+if test "$TORTURE_SUITE" != rcuperf
then
- print_warning Assertion failure in $file $title
- # cat $1.diags
+ # check for abject failure
+
+ if grep -q FAILURE $file || grep -q -e '-torture.*!!!' $file
+ then
+ nerrs=`grep --binary-files=text '!!!' $file |
+ tail -1 |
+ awk '
+ {
+ for (i=NF-8;i<=NF;i++)
+ sum+=$i;
+ }
+ END { print sum }'`
+ print_bug $title FAILURE, $nerrs instances
+ exit
+ fi
+
+ grep --binary-files=text 'torture:.*ver:' $file |
+ egrep --binary-files=text -v '\(null\)|rtc: 000000000* ' |
+ sed -e 's/^(initramfs)[^]]*] //' -e 's/^\[[^]]*] //' |
+ awk '
+ BEGIN {
+ ver = 0;
+ badseq = 0;
+ }
+
+ {
+ if (!badseq && ($5 + 0 != $5 || $5 <= ver)) {
+ badseqno1 = ver;
+ badseqno2 = $5;
+ badseqnr = NR;
+ badseq = 1;
+ }
+ ver = $5
+ }
+
+ END {
+ if (badseq) {
+ if (badseqno1 == badseqno2 && badseqno2 == ver)
+ print "GP HANG at " ver " torture stat " badseqnr;
+ else
+ print "BAD SEQ " badseqno1 ":" badseqno2 " last:" ver " version " badseqnr;
+ }
+ }' > $T.seq
+
+ if grep -q SUCCESS $file
+ then
+ if test -s $T.seq
+ then
+ print_warning $title `cat $T.seq`
+ echo " " $file
+ exit 2
+ fi
+ else
+ if grep -q "_HOTPLUG:" $file
+ then
+ print_warning HOTPLUG FAILURES $title `cat $T.seq`
+ echo " " $file
+ exit 3
+ fi
+ echo $title no success message, `grep --binary-files=text 'ver:' $file | wc -l` successful version messages
+ if test -s $T.seq
+ then
+ print_warning $title `cat $T.seq`
+ fi
+ exit 2
+ fi
+fi | tee -a $file.diags
+
+egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for' < $file |
+grep -v 'ODEBUG: ' |
+grep -v 'Warning: unable to open an initial console' > $T.diags
+if test -s $T.diags
+then
+ print_warning "Assertion failure in $file $title"
+ # cat $T.diags
summary=""
- n_badness=`grep -c Badness $1`
+ n_badness=`grep -c Badness $file`
if test "$n_badness" -ne 0
then
summary="$summary Badness: $n_badness"
fi
- n_warn=`grep -v 'Warning: unable to open an initial console' $1 | egrep -c 'WARNING:|Warn'`
+ n_warn=`grep -v 'Warning: unable to open an initial console' $file | egrep -c 'WARNING:|Warn'`
if test "$n_warn" -ne 0
then
summary="$summary Warnings: $n_warn"
fi
- n_bugs=`egrep -c 'BUG|Oops:' $1`
+ n_bugs=`egrep -c 'BUG|Oops:' $file`
if test "$n_bugs" -ne 0
then
summary="$summary Bugs: $n_bugs"
fi
- n_calltrace=`grep -c 'Call Trace:' $1`
+ n_calltrace=`grep -c 'Call Trace:' $file`
if test "$n_calltrace" -ne 0
then
summary="$summary Call Traces: $n_calltrace"
fi
- n_lockdep=`grep -c =========== $1`
+ n_lockdep=`grep -c =========== $file`
if test "$n_badness" -ne 0
then
summary="$summary lockdep: $n_badness"
fi
- n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state' $1`
+ n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state' $file`
if test "$n_stalls" -ne 0
then
summary="$summary Stalls: $n_stalls"
fi
- n_starves=`grep -c 'rcu_.*kthread starved for' $1`
+ n_starves=`grep -c 'rcu_.*kthread starved for' $file`
if test "$n_starves" -ne 0
then
summary="$summary Starves: $n_starves"
fi
print_warning Summary: $summary
-else
- rm $1.diags
+ cat $T.diags >> $file.diags
+fi
+if ! test -s $file.diags
+then
+ rm -f $file.diags
fi
diff --git a/tools/testing/selftests/rcutorture/bin/parse-torture.sh b/tools/testing/selftests/rcutorture/bin/parse-torture.sh
deleted file mode 100755
index 5987e50..0000000
--- a/tools/testing/selftests/rcutorture/bin/parse-torture.sh
+++ /dev/null
@@ -1,105 +0,0 @@
-#!/bin/bash
-#
-# Check the console output from a torture run for goodness.
-# The "file" is a pathname on the local system, and "title" is
-# a text string for error-message purposes.
-#
-# The file must contain torture output, but can be interspersed
-# with other dmesg text, as in console-log output.
-#
-# Usage: parse-torture.sh file title
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
-# Copyright (C) IBM Corporation, 2011
-#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
-
-T=${TMPDIR-/tmp}/parse-torture.sh.$$
-file="$1"
-title="$2"
-
-trap 'rm -f $T.seq' 0
-
-. functions.sh
-
-# check for presence of torture output file.
-
-if test -f "$file" -a -r "$file"
-then
- :
-else
- echo $title unreadable torture output file: $file
- exit 1
-fi
-
-# check for abject failure
-
-if grep -q FAILURE $file || grep -q -e '-torture.*!!!' $file
-then
- nerrs=`grep --binary-files=text '!!!' $file | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'`
- print_bug $title FAILURE, $nerrs instances
- echo " " $url
- exit
-fi
-
-grep --binary-files=text 'torture:.*ver:' $file | egrep --binary-files=text -v '\(null\)|rtc: 000000000* ' | sed -e 's/^(initramfs)[^]]*] //' -e 's/^\[[^]]*] //' |
-awk '
-BEGIN {
- ver = 0;
- badseq = 0;
- }
-
- {
- if (!badseq && ($5 + 0 != $5 || $5 <= ver)) {
- badseqno1 = ver;
- badseqno2 = $5;
- badseqnr = NR;
- badseq = 1;
- }
- ver = $5
- }
-
-END {
- if (badseq) {
- if (badseqno1 == badseqno2 && badseqno2 == ver)
- print "GP HANG at " ver " torture stat " badseqnr;
- else
- print "BAD SEQ " badseqno1 ":" badseqno2 " last:" ver " version " badseqnr;
- }
- }' > $T.seq
-
-if grep -q SUCCESS $file
-then
- if test -s $T.seq
- then
- print_warning $title $title `cat $T.seq`
- echo " " $file
- exit 2
- fi
-else
- if grep -q "_HOTPLUG:" $file
- then
- print_warning HOTPLUG FAILURES $title `cat $T.seq`
- echo " " $file
- exit 3
- fi
- echo $title no success message, `grep --binary-files=text 'ver:' $file | wc -l` successful version messages
- if test -s $T.seq
- then
- print_warning $title `cat $T.seq`
- fi
- exit 2
-fi
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 168c66d..e147323 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -134,11 +134,15 @@ struct seccomp_data {
#endif
#ifndef SECCOMP_FILTER_FLAG_TSYNC
-#define SECCOMP_FILTER_FLAG_TSYNC 1
+#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0)
#endif
#ifndef SECCOMP_FILTER_FLAG_LOG
-#define SECCOMP_FILTER_FLAG_LOG 2
+#define SECCOMP_FILTER_FLAG_LOG (1UL << 1)
+#endif
+
+#ifndef SECCOMP_FILTER_FLAG_SPEC_ALLOW
+#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2)
#endif
#ifndef PTRACE_SECCOMP_GET_METADATA
@@ -2072,14 +2076,26 @@ TEST(seccomp_syscall_mode_lock)
TEST(detect_seccomp_filter_flags)
{
unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC,
- SECCOMP_FILTER_FLAG_LOG };
+ SECCOMP_FILTER_FLAG_LOG,
+ SECCOMP_FILTER_FLAG_SPEC_ALLOW };
unsigned int flag, all_flags;
int i;
long ret;
/* Test detection of known-good filter flags */
for (i = 0, all_flags = 0; i < ARRAY_SIZE(flags); i++) {
+ int bits = 0;
+
flag = flags[i];
+ /* Make sure the flag is a single bit! */
+ while (flag) {
+ if (flag & 0x1)
+ bits ++;
+ flag >>= 1;
+ }
+ ASSERT_EQ(1, bits);
+ flag = flags[i];
+
ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
ASSERT_NE(ENOSYS, errno) {
TH_LOG("Kernel does not support seccomp syscall!");
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
index 5b012f4..6f289a4 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
@@ -66,7 +66,7 @@
"cmdUnderTest": "$TC action add action bpf object-file _b.o index 667",
"expExitCode": "0",
"verifyCmd": "$TC action get action bpf index 667",
- "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9]* tag 3b185187f1855c4c default-action pipe.*index 667 ref",
+ "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9]* tag 3b185187f1855c4c( jited)? default-action pipe.*index 667 ref",
"matchCount": "1",
"teardown": [
"$TC action flush action bpf",
@@ -92,10 +92,15 @@
"cmdUnderTest": "$TC action add action bpf object-file _c.o index 667",
"expExitCode": "255",
"verifyCmd": "$TC action get action bpf index 667",
- "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9].*index 667 ref",
+ "matchPattern": "action order [0-9]*: bpf _c.o:\\[action\\] id [0-9].*index 667 ref",
"matchCount": "0",
"teardown": [
- "$TC action flush action bpf",
+ [
+ "$TC action flush action bpf",
+ 0,
+ 1,
+ 255
+ ],
"rm -f _c.o"
]
},
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index d744991..39f66bc 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -11,7 +11,7 @@
TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \
check_initial_reg_state sigreturn iopl mpx-mini-test ioperm \
- protection_keys test_vdso test_vsyscall
+ protection_keys test_vdso test_vsyscall mov_ss_trap
TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
test_FCMOV test_FCOMI test_FISTTP \
vdso_restorer
diff --git a/tools/testing/selftests/x86/mov_ss_trap.c b/tools/testing/selftests/x86/mov_ss_trap.c
new file mode 100644
index 0000000..3c3a0226
--- /dev/null
+++ b/tools/testing/selftests/x86/mov_ss_trap.c
@@ -0,0 +1,285 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * mov_ss_trap.c: Exercise the bizarre side effects of a watchpoint on MOV SS
+ *
+ * This does MOV SS from a watchpointed address followed by various
+ * types of kernel entries. A MOV SS that hits a watchpoint will queue
+ * up a #DB trap but will not actually deliver that trap. The trap
+ * will be delivered after the next instruction instead. The CPU's logic
+ * seems to be:
+ *
+ * - Any fault: drop the pending #DB trap.
+ * - INT $N, INT3, INTO, SYSCALL, SYSENTER: enter the kernel and then
+ * deliver #DB.
+ * - ICEBP: enter the kernel but do not deliver the watchpoint trap
+ * - breakpoint: only one #DB is delivered (phew!)
+ *
+ * There are plenty of ways for a kernel to handle this incorrectly. This
+ * test tries to exercise all the cases.
+ *
+ * This should mostly cover CVE-2018-1087 and CVE-2018-8897.
+ */
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <sys/ptrace.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/user.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+#include <errno.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <err.h>
+#include <string.h>
+#include <setjmp.h>
+#include <sys/prctl.h>
+
+#define X86_EFLAGS_RF (1UL << 16)
+
+#if __x86_64__
+# define REG_IP REG_RIP
+#else
+# define REG_IP REG_EIP
+#endif
+
+unsigned short ss;
+extern unsigned char breakpoint_insn[];
+sigjmp_buf jmpbuf;
+static unsigned char altstack_data[SIGSTKSZ];
+
+static void enable_watchpoint(void)
+{
+ pid_t parent = getpid();
+ int status;
+
+ pid_t child = fork();
+ if (child < 0)
+ err(1, "fork");
+
+ if (child) {
+ if (waitpid(child, &status, 0) != child)
+ err(1, "waitpid for child");
+ } else {
+ unsigned long dr0, dr1, dr7;
+
+ dr0 = (unsigned long)&ss;
+ dr1 = (unsigned long)breakpoint_insn;
+ dr7 = ((1UL << 1) | /* G0 */
+ (3UL << 16) | /* RW0 = read or write */
+ (1UL << 18) | /* LEN0 = 2 bytes */
+ (1UL << 3)); /* G1, RW1 = insn */
+
+ if (ptrace(PTRACE_ATTACH, parent, NULL, NULL) != 0)
+ err(1, "PTRACE_ATTACH");
+
+ if (waitpid(parent, &status, 0) != parent)
+ err(1, "waitpid for child");
+
+ if (ptrace(PTRACE_POKEUSER, parent, (void *)offsetof(struct user, u_debugreg[0]), dr0) != 0)
+ err(1, "PTRACE_POKEUSER DR0");
+
+ if (ptrace(PTRACE_POKEUSER, parent, (void *)offsetof(struct user, u_debugreg[1]), dr1) != 0)
+ err(1, "PTRACE_POKEUSER DR1");
+
+ if (ptrace(PTRACE_POKEUSER, parent, (void *)offsetof(struct user, u_debugreg[7]), dr7) != 0)
+ err(1, "PTRACE_POKEUSER DR7");
+
+ printf("\tDR0 = %lx, DR1 = %lx, DR7 = %lx\n", dr0, dr1, dr7);
+
+ if (ptrace(PTRACE_DETACH, parent, NULL, NULL) != 0)
+ err(1, "PTRACE_DETACH");
+
+ exit(0);
+ }
+}
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+ int flags)
+{
+ struct sigaction sa;
+ memset(&sa, 0, sizeof(sa));
+ sa.sa_sigaction = handler;
+ sa.sa_flags = SA_SIGINFO | flags;
+ sigemptyset(&sa.sa_mask);
+ if (sigaction(sig, &sa, 0))
+ err(1, "sigaction");
+}
+
+static char const * const signames[] = {
+ [SIGSEGV] = "SIGSEGV",
+ [SIGBUS] = "SIBGUS",
+ [SIGTRAP] = "SIGTRAP",
+ [SIGILL] = "SIGILL",
+};
+
+static void sigtrap(int sig, siginfo_t *si, void *ctx_void)
+{
+ ucontext_t *ctx = ctx_void;
+
+ printf("\tGot SIGTRAP with RIP=%lx, EFLAGS.RF=%d\n",
+ (unsigned long)ctx->uc_mcontext.gregs[REG_IP],
+ !!(ctx->uc_mcontext.gregs[REG_EFL] & X86_EFLAGS_RF));
+}
+
+static void handle_and_return(int sig, siginfo_t *si, void *ctx_void)
+{
+ ucontext_t *ctx = ctx_void;
+
+ printf("\tGot %s with RIP=%lx\n", signames[sig],
+ (unsigned long)ctx->uc_mcontext.gregs[REG_IP]);
+}
+
+static void handle_and_longjmp(int sig, siginfo_t *si, void *ctx_void)
+{
+ ucontext_t *ctx = ctx_void;
+
+ printf("\tGot %s with RIP=%lx\n", signames[sig],
+ (unsigned long)ctx->uc_mcontext.gregs[REG_IP]);
+
+ siglongjmp(jmpbuf, 1);
+}
+
+int main()
+{
+ unsigned long nr;
+
+ asm volatile ("mov %%ss, %[ss]" : [ss] "=m" (ss));
+ printf("\tSS = 0x%hx, &SS = 0x%p\n", ss, &ss);
+
+ if (prctl(PR_SET_PTRACER, PR_SET_PTRACER_ANY, 0, 0, 0) == 0)
+ printf("\tPR_SET_PTRACER_ANY succeeded\n");
+
+ printf("\tSet up a watchpoint\n");
+ sethandler(SIGTRAP, sigtrap, 0);
+ enable_watchpoint();
+
+ printf("[RUN]\tRead from watched memory (should get SIGTRAP)\n");
+ asm volatile ("mov %[ss], %[tmp]" : [tmp] "=r" (nr) : [ss] "m" (ss));
+
+ printf("[RUN]\tMOV SS; INT3\n");
+ asm volatile ("mov %[ss], %%ss; int3" :: [ss] "m" (ss));
+
+ printf("[RUN]\tMOV SS; INT 3\n");
+ asm volatile ("mov %[ss], %%ss; .byte 0xcd, 0x3" :: [ss] "m" (ss));
+
+ printf("[RUN]\tMOV SS; CS CS INT3\n");
+ asm volatile ("mov %[ss], %%ss; .byte 0x2e, 0x2e; int3" :: [ss] "m" (ss));
+
+ printf("[RUN]\tMOV SS; CSx14 INT3\n");
+ asm volatile ("mov %[ss], %%ss; .fill 14,1,0x2e; int3" :: [ss] "m" (ss));
+
+ printf("[RUN]\tMOV SS; INT 4\n");
+ sethandler(SIGSEGV, handle_and_return, SA_RESETHAND);
+ asm volatile ("mov %[ss], %%ss; int $4" :: [ss] "m" (ss));
+
+#ifdef __i386__
+ printf("[RUN]\tMOV SS; INTO\n");
+ sethandler(SIGSEGV, handle_and_return, SA_RESETHAND);
+ nr = -1;
+ asm volatile ("add $1, %[tmp]; mov %[ss], %%ss; into"
+ : [tmp] "+r" (nr) : [ss] "m" (ss));
+#endif
+
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; ICEBP\n");
+
+ /* Some emulators (e.g. QEMU TCG) don't emulate ICEBP. */
+ sethandler(SIGILL, handle_and_longjmp, SA_RESETHAND);
+
+ asm volatile ("mov %[ss], %%ss; .byte 0xf1" :: [ss] "m" (ss));
+ }
+
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; CLI\n");
+ sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND);
+ asm volatile ("mov %[ss], %%ss; cli" :: [ss] "m" (ss));
+ }
+
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; #PF\n");
+ sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND);
+ asm volatile ("mov %[ss], %%ss; mov (-1), %[tmp]"
+ : [tmp] "=r" (nr) : [ss] "m" (ss));
+ }
+
+ /*
+ * INT $1: if #DB has DPL=3 and there isn't special handling,
+ * then the kernel will die.
+ */
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; INT 1\n");
+ sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND);
+ asm volatile ("mov %[ss], %%ss; int $1" :: [ss] "m" (ss));
+ }
+
+#ifdef __x86_64__
+ /*
+ * In principle, we should test 32-bit SYSCALL as well, but
+ * the calling convention is so unpredictable that it's
+ * not obviously worth the effort.
+ */
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; SYSCALL\n");
+ sethandler(SIGILL, handle_and_longjmp, SA_RESETHAND);
+ nr = SYS_getpid;
+ /*
+ * Toggle the high bit of RSP to make it noncanonical to
+ * strengthen this test on non-SMAP systems.
+ */
+ asm volatile ("btc $63, %%rsp\n\t"
+ "mov %[ss], %%ss; syscall\n\t"
+ "btc $63, %%rsp"
+ : "+a" (nr) : [ss] "m" (ss)
+ : "rcx"
+#ifdef __x86_64__
+ , "r11"
+#endif
+ );
+ }
+#endif
+
+ printf("[RUN]\tMOV SS; breakpointed NOP\n");
+ asm volatile ("mov %[ss], %%ss; breakpoint_insn: nop" :: [ss] "m" (ss));
+
+ /*
+ * Invoking SYSENTER directly breaks all the rules. Just handle
+ * the SIGSEGV.
+ */
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; SYSENTER\n");
+ stack_t stack = {
+ .ss_sp = altstack_data,
+ .ss_size = SIGSTKSZ,
+ };
+ if (sigaltstack(&stack, NULL) != 0)
+ err(1, "sigaltstack");
+ sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND | SA_ONSTACK);
+ nr = SYS_getpid;
+ asm volatile ("mov %[ss], %%ss; SYSENTER" : "+a" (nr)
+ : [ss] "m" (ss) : "flags", "rcx"
+#ifdef __x86_64__
+ , "r11"
+#endif
+ );
+
+ /* We're unreachable here. SYSENTER forgets RIP. */
+ }
+
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; INT $0x80\n");
+ sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND);
+ nr = 20; /* compat getpid */
+ asm volatile ("mov %[ss], %%ss; int $0x80"
+ : "+a" (nr) : [ss] "m" (ss)
+ : "flags"
+#ifdef __x86_64__
+ , "r8", "r9", "r10", "r11"
+#endif
+ );
+ }
+
+ printf("[OK]\tI aten't dead\n");
+ return 0;
+}
diff --git a/tools/testing/selftests/x86/mpx-mini-test.c b/tools/testing/selftests/x86/mpx-mini-test.c
index 9c0325e..50f7e92 100644
--- a/tools/testing/selftests/x86/mpx-mini-test.c
+++ b/tools/testing/selftests/x86/mpx-mini-test.c
@@ -368,6 +368,11 @@ static int expected_bnd_index = -1;
uint64_t shadow_plb[NR_MPX_BOUNDS_REGISTERS][2]; /* shadow MPX bound registers */
unsigned long shadow_map[NR_MPX_BOUNDS_REGISTERS];
+/* Failed address bound checks: */
+#ifndef SEGV_BNDERR
+# define SEGV_BNDERR 3
+#endif
+
/*
* The kernel is supposed to provide some information about the bounds
* exception in the siginfo. It should match what we have in the bounds
@@ -419,8 +424,6 @@ void handler(int signum, siginfo_t *si, void *vucontext)
br_count++;
dprintf1("#BR 0x%jx (total seen: %d)\n", status, br_count);
-#define SEGV_BNDERR 3 /* failed address bound checks */
-
dprintf2("Saw a #BR! status 0x%jx at %016lx br_reason: %jx\n",
status, ip, br_reason);
dprintf2("si_signo: %d\n", si->si_signo);
diff --git a/tools/testing/selftests/x86/pkey-helpers.h b/tools/testing/selftests/x86/pkey-helpers.h
index b3cb767..254e543 100644
--- a/tools/testing/selftests/x86/pkey-helpers.h
+++ b/tools/testing/selftests/x86/pkey-helpers.h
@@ -26,30 +26,26 @@ static inline void sigsafe_printf(const char *format, ...)
{
va_list ap;
- va_start(ap, format);
if (!dprint_in_signal) {
+ va_start(ap, format);
vprintf(format, ap);
+ va_end(ap);
} else {
int ret;
- int len = vsnprintf(dprint_in_signal_buffer,
- DPRINT_IN_SIGNAL_BUF_SIZE,
- format, ap);
/*
- * len is amount that would have been printed,
- * but actual write is truncated at BUF_SIZE.
+ * No printf() functions are signal-safe.
+ * They deadlock easily. Write the format
+ * string to get some output, even if
+ * incomplete.
*/
- if (len > DPRINT_IN_SIGNAL_BUF_SIZE)
- len = DPRINT_IN_SIGNAL_BUF_SIZE;
- ret = write(1, dprint_in_signal_buffer, len);
+ ret = write(1, format, strlen(format));
if (ret < 0)
- abort();
+ exit(1);
}
- va_end(ap);
}
#define dprintf_level(level, args...) do { \
if (level <= DEBUG_LEVEL) \
sigsafe_printf(args); \
- fflush(NULL); \
} while (0)
#define dprintf0(args...) dprintf_level(0, args)
#define dprintf1(args...) dprintf_level(1, args)
diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c
index f15aa5a..460b4bd 100644
--- a/tools/testing/selftests/x86/protection_keys.c
+++ b/tools/testing/selftests/x86/protection_keys.c
@@ -72,10 +72,9 @@ extern void abort_hooks(void);
test_nr, iteration_nr); \
dprintf0("errno at assert: %d", errno); \
abort_hooks(); \
- assert(condition); \
+ exit(__LINE__); \
} \
} while (0)
-#define raw_assert(cond) assert(cond)
void cat_into_file(char *str, char *file)
{
@@ -87,12 +86,17 @@ void cat_into_file(char *str, char *file)
* these need to be raw because they are called under
* pkey_assert()
*/
- raw_assert(fd >= 0);
+ if (fd < 0) {
+ fprintf(stderr, "error opening '%s'\n", str);
+ perror("error: ");
+ exit(__LINE__);
+ }
+
ret = write(fd, str, strlen(str));
if (ret != strlen(str)) {
perror("write to file failed");
fprintf(stderr, "filename: '%s' str: '%s'\n", file, str);
- raw_assert(0);
+ exit(__LINE__);
}
close(fd);
}
@@ -191,26 +195,30 @@ void lots_o_noops_around_write(int *write_to_me)
#ifdef __i386__
#ifndef SYS_mprotect_key
-# define SYS_mprotect_key 380
+# define SYS_mprotect_key 380
#endif
+
#ifndef SYS_pkey_alloc
-# define SYS_pkey_alloc 381
-# define SYS_pkey_free 382
+# define SYS_pkey_alloc 381
+# define SYS_pkey_free 382
#endif
-#define REG_IP_IDX REG_EIP
-#define si_pkey_offset 0x14
+
+#define REG_IP_IDX REG_EIP
+#define si_pkey_offset 0x14
#else
#ifndef SYS_mprotect_key
-# define SYS_mprotect_key 329
+# define SYS_mprotect_key 329
#endif
+
#ifndef SYS_pkey_alloc
-# define SYS_pkey_alloc 330
-# define SYS_pkey_free 331
+# define SYS_pkey_alloc 330
+# define SYS_pkey_free 331
#endif
-#define REG_IP_IDX REG_RIP
-#define si_pkey_offset 0x20
+
+#define REG_IP_IDX REG_RIP
+#define si_pkey_offset 0x20
#endif
@@ -225,8 +233,14 @@ void dump_mem(void *dumpme, int len_bytes)
}
}
-#define SEGV_BNDERR 3 /* failed address bound checks */
-#define SEGV_PKUERR 4
+/* Failed address bound checks: */
+#ifndef SEGV_BNDERR
+# define SEGV_BNDERR 3
+#endif
+
+#ifndef SEGV_PKUERR
+# define SEGV_PKUERR 4
+#endif
static char *si_code_str(int si_code)
{
@@ -289,13 +303,6 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
dump_mem(pkru_ptr - 128, 256);
pkey_assert(*pkru_ptr);
- si_pkey_ptr = (u32 *)(((u8 *)si) + si_pkey_offset);
- dprintf1("si_pkey_ptr: %p\n", si_pkey_ptr);
- dump_mem(si_pkey_ptr - 8, 24);
- siginfo_pkey = *si_pkey_ptr;
- pkey_assert(siginfo_pkey < NR_PKEYS);
- last_si_pkey = siginfo_pkey;
-
if ((si->si_code == SEGV_MAPERR) ||
(si->si_code == SEGV_ACCERR) ||
(si->si_code == SEGV_BNDERR)) {
@@ -303,6 +310,13 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
exit(4);
}
+ si_pkey_ptr = (u32 *)(((u8 *)si) + si_pkey_offset);
+ dprintf1("si_pkey_ptr: %p\n", si_pkey_ptr);
+ dump_mem((u8 *)si_pkey_ptr - 8, 24);
+ siginfo_pkey = *si_pkey_ptr;
+ pkey_assert(siginfo_pkey < NR_PKEYS);
+ last_si_pkey = siginfo_pkey;
+
dprintf1("signal pkru from xsave: %08x\n", *pkru_ptr);
/* need __rdpkru() version so we do not do shadow_pkru checking */
dprintf1("signal pkru from pkru: %08x\n", __rdpkru());
@@ -311,22 +325,6 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
dprintf1("WARNING: set PRKU=0 to allow faulting instruction to continue\n");
pkru_faults++;
dprintf1("<<<<==================================================\n");
- return;
- if (trapno == 14) {
- fprintf(stderr,
- "ERROR: In signal handler, page fault, trapno = %d, ip = %016lx\n",
- trapno, ip);
- fprintf(stderr, "si_addr %p\n", si->si_addr);
- fprintf(stderr, "REG_ERR: %lx\n",
- (unsigned long)uctxt->uc_mcontext.gregs[REG_ERR]);
- exit(1);
- } else {
- fprintf(stderr, "unexpected trap %d! at 0x%lx\n", trapno, ip);
- fprintf(stderr, "si_addr %p\n", si->si_addr);
- fprintf(stderr, "REG_ERR: %lx\n",
- (unsigned long)uctxt->uc_mcontext.gregs[REG_ERR]);
- exit(2);
- }
dprint_in_signal = 0;
}
@@ -393,10 +391,15 @@ pid_t fork_lazy_child(void)
return forkret;
}
-#define PKEY_DISABLE_ACCESS 0x1
-#define PKEY_DISABLE_WRITE 0x2
+#ifndef PKEY_DISABLE_ACCESS
+# define PKEY_DISABLE_ACCESS 0x1
+#endif
-u32 pkey_get(int pkey, unsigned long flags)
+#ifndef PKEY_DISABLE_WRITE
+# define PKEY_DISABLE_WRITE 0x2
+#endif
+
+static u32 hw_pkey_get(int pkey, unsigned long flags)
{
u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE);
u32 pkru = __rdpkru();
@@ -418,7 +421,7 @@ u32 pkey_get(int pkey, unsigned long flags)
return masked_pkru;
}
-int pkey_set(int pkey, unsigned long rights, unsigned long flags)
+static int hw_pkey_set(int pkey, unsigned long rights, unsigned long flags)
{
u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE);
u32 old_pkru = __rdpkru();
@@ -452,15 +455,15 @@ void pkey_disable_set(int pkey, int flags)
pkey, flags);
pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
- pkey_rights = pkey_get(pkey, syscall_flags);
+ pkey_rights = hw_pkey_get(pkey, syscall_flags);
- dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+ dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
pkey, pkey, pkey_rights);
pkey_assert(pkey_rights >= 0);
pkey_rights |= flags;
- ret = pkey_set(pkey, pkey_rights, syscall_flags);
+ ret = hw_pkey_set(pkey, pkey_rights, syscall_flags);
assert(!ret);
/*pkru and flags have the same format */
shadow_pkru |= flags << (pkey * 2);
@@ -468,8 +471,8 @@ void pkey_disable_set(int pkey, int flags)
pkey_assert(ret >= 0);
- pkey_rights = pkey_get(pkey, syscall_flags);
- dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+ pkey_rights = hw_pkey_get(pkey, syscall_flags);
+ dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
pkey, pkey, pkey_rights);
dprintf1("%s(%d) pkru: 0x%x\n", __func__, pkey, rdpkru());
@@ -483,24 +486,24 @@ void pkey_disable_clear(int pkey, int flags)
{
unsigned long syscall_flags = 0;
int ret;
- int pkey_rights = pkey_get(pkey, syscall_flags);
+ int pkey_rights = hw_pkey_get(pkey, syscall_flags);
u32 orig_pkru = rdpkru();
pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
- dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+ dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
pkey, pkey, pkey_rights);
pkey_assert(pkey_rights >= 0);
pkey_rights |= flags;
- ret = pkey_set(pkey, pkey_rights, 0);
+ ret = hw_pkey_set(pkey, pkey_rights, 0);
/* pkru and flags have the same format */
shadow_pkru &= ~(flags << (pkey * 2));
pkey_assert(ret >= 0);
- pkey_rights = pkey_get(pkey, syscall_flags);
- dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+ pkey_rights = hw_pkey_get(pkey, syscall_flags);
+ dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
pkey, pkey, pkey_rights);
dprintf1("%s(%d) pkru: 0x%x\n", __func__, pkey, rdpkru());
@@ -674,10 +677,12 @@ int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
struct pkey_malloc_record {
void *ptr;
long size;
+ int prot;
};
struct pkey_malloc_record *pkey_malloc_records;
+struct pkey_malloc_record *pkey_last_malloc_record;
long nr_pkey_malloc_records;
-void record_pkey_malloc(void *ptr, long size)
+void record_pkey_malloc(void *ptr, long size, int prot)
{
long i;
struct pkey_malloc_record *rec = NULL;
@@ -709,6 +714,8 @@ void record_pkey_malloc(void *ptr, long size)
(int)(rec - pkey_malloc_records), rec, ptr, size);
rec->ptr = ptr;
rec->size = size;
+ rec->prot = prot;
+ pkey_last_malloc_record = rec;
nr_pkey_malloc_records++;
}
@@ -753,7 +760,7 @@ void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey)
pkey_assert(ptr != (void *)-1);
ret = mprotect_pkey((void *)ptr, PAGE_SIZE, prot, pkey);
pkey_assert(!ret);
- record_pkey_malloc(ptr, size);
+ record_pkey_malloc(ptr, size, prot);
rdpkru();
dprintf1("%s() for pkey %d @ %p\n", __func__, pkey, ptr);
@@ -774,7 +781,7 @@ void *malloc_pkey_anon_huge(long size, int prot, u16 pkey)
size = ALIGN_UP(size, HPAGE_SIZE * 2);
ptr = mmap(NULL, size, PROT_NONE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
pkey_assert(ptr != (void *)-1);
- record_pkey_malloc(ptr, size);
+ record_pkey_malloc(ptr, size, prot);
mprotect_pkey(ptr, size, prot, pkey);
dprintf1("unaligned ptr: %p\n", ptr);
@@ -847,7 +854,7 @@ void *malloc_pkey_hugetlb(long size, int prot, u16 pkey)
pkey_assert(ptr != (void *)-1);
mprotect_pkey(ptr, size, prot, pkey);
- record_pkey_malloc(ptr, size);
+ record_pkey_malloc(ptr, size, prot);
dprintf1("mmap()'d hugetlbfs for pkey %d @ %p\n", pkey, ptr);
return ptr;
@@ -869,7 +876,7 @@ void *malloc_pkey_mmap_dax(long size, int prot, u16 pkey)
mprotect_pkey(ptr, size, prot, pkey);
- record_pkey_malloc(ptr, size);
+ record_pkey_malloc(ptr, size, prot);
dprintf1("mmap()'d for pkey %d @ %p\n", pkey, ptr);
close(fd);
@@ -918,13 +925,21 @@ void *malloc_pkey(long size, int prot, u16 pkey)
}
int last_pkru_faults;
+#define UNKNOWN_PKEY -2
void expected_pk_fault(int pkey)
{
dprintf2("%s(): last_pkru_faults: %d pkru_faults: %d\n",
__func__, last_pkru_faults, pkru_faults);
dprintf2("%s(%d): last_si_pkey: %d\n", __func__, pkey, last_si_pkey);
pkey_assert(last_pkru_faults + 1 == pkru_faults);
- pkey_assert(last_si_pkey == pkey);
+
+ /*
+ * For exec-only memory, we do not know the pkey in
+ * advance, so skip this check.
+ */
+ if (pkey != UNKNOWN_PKEY)
+ pkey_assert(last_si_pkey == pkey);
+
/*
* The signal handler shold have cleared out PKRU to let the
* test program continue. We now have to restore it.
@@ -939,10 +954,11 @@ void expected_pk_fault(int pkey)
last_si_pkey = -1;
}
-void do_not_expect_pk_fault(void)
-{
- pkey_assert(last_pkru_faults == pkru_faults);
-}
+#define do_not_expect_pk_fault(msg) do { \
+ if (last_pkru_faults != pkru_faults) \
+ dprintf0("unexpected PK fault: %s\n", msg); \
+ pkey_assert(last_pkru_faults == pkru_faults); \
+} while (0)
int test_fds[10] = { -1 };
int nr_test_fds;
@@ -1151,12 +1167,15 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
pkey_assert(i < NR_PKEYS*2);
/*
- * There are 16 pkeys supported in hardware. One is taken
- * up for the default (0) and another can be taken up by
- * an execute-only mapping. Ensure that we can allocate
- * at least 14 (16-2).
+ * There are 16 pkeys supported in hardware. Three are
+ * allocated by the time we get here:
+ * 1. The default key (0)
+ * 2. One possibly consumed by an execute-only mapping.
+ * 3. One allocated by the test code and passed in via
+ * 'pkey' to this function.
+ * Ensure that we can allocate at least another 13 (16-3).
*/
- pkey_assert(i >= NR_PKEYS-2);
+ pkey_assert(i >= NR_PKEYS-3);
for (i = 0; i < nr_allocated_pkeys; i++) {
err = sys_pkey_free(allocated_pkeys[i]);
@@ -1165,6 +1184,35 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
}
}
+/*
+ * pkey 0 is special. It is allocated by default, so you do not
+ * have to call pkey_alloc() to use it first. Make sure that it
+ * is usable.
+ */
+void test_mprotect_with_pkey_0(int *ptr, u16 pkey)
+{
+ long size;
+ int prot;
+
+ assert(pkey_last_malloc_record);
+ size = pkey_last_malloc_record->size;
+ /*
+ * This is a bit of a hack. But mprotect() requires
+ * huge-page-aligned sizes when operating on hugetlbfs.
+ * So, make sure that we use something that's a multiple
+ * of a huge page when we can.
+ */
+ if (size >= HPAGE_SIZE)
+ size = HPAGE_SIZE;
+ prot = pkey_last_malloc_record->prot;
+
+ /* Use pkey 0 */
+ mprotect_pkey(ptr, size, prot, 0);
+
+ /* Make sure that we can set it back to the original pkey. */
+ mprotect_pkey(ptr, size, prot, pkey);
+}
+
void test_ptrace_of_child(int *ptr, u16 pkey)
{
__attribute__((__unused__)) int peek_result;
@@ -1228,7 +1276,7 @@ void test_ptrace_of_child(int *ptr, u16 pkey)
pkey_assert(ret != -1);
/* Now access from the current task, and expect NO exception: */
peek_result = read_ptr(plain_ptr);
- do_not_expect_pk_fault();
+ do_not_expect_pk_fault("read plain pointer after ptrace");
ret = ptrace(PTRACE_DETACH, child_pid, ignored, 0);
pkey_assert(ret != -1);
@@ -1241,12 +1289,9 @@ void test_ptrace_of_child(int *ptr, u16 pkey)
free(plain_ptr_unaligned);
}
-void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
+void *get_pointer_to_instructions(void)
{
void *p1;
- int scratch;
- int ptr_contents;
- int ret;
p1 = ALIGN_PTR_UP(&lots_o_noops_around_write, PAGE_SIZE);
dprintf3("&lots_o_noops: %p\n", &lots_o_noops_around_write);
@@ -1256,7 +1301,23 @@ void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
/* Point 'p1' at the *second* page of the function: */
p1 += PAGE_SIZE;
+ /*
+ * Try to ensure we fault this in on next touch to ensure
+ * we get an instruction fault as opposed to a data one
+ */
madvise(p1, PAGE_SIZE, MADV_DONTNEED);
+
+ return p1;
+}
+
+void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
+{
+ void *p1;
+ int scratch;
+ int ptr_contents;
+ int ret;
+
+ p1 = get_pointer_to_instructions();
lots_o_noops_around_write(&scratch);
ptr_contents = read_ptr(p1);
dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
@@ -1272,12 +1333,55 @@ void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
*/
madvise(p1, PAGE_SIZE, MADV_DONTNEED);
lots_o_noops_around_write(&scratch);
- do_not_expect_pk_fault();
+ do_not_expect_pk_fault("executing on PROT_EXEC memory");
ptr_contents = read_ptr(p1);
dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
expected_pk_fault(pkey);
}
+void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey)
+{
+ void *p1;
+ int scratch;
+ int ptr_contents;
+ int ret;
+
+ dprintf1("%s() start\n", __func__);
+
+ p1 = get_pointer_to_instructions();
+ lots_o_noops_around_write(&scratch);
+ ptr_contents = read_ptr(p1);
+ dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
+
+ /* Use a *normal* mprotect(), not mprotect_pkey(): */
+ ret = mprotect(p1, PAGE_SIZE, PROT_EXEC);
+ pkey_assert(!ret);
+
+ dprintf2("pkru: %x\n", rdpkru());
+
+ /* Make sure this is an *instruction* fault */
+ madvise(p1, PAGE_SIZE, MADV_DONTNEED);
+ lots_o_noops_around_write(&scratch);
+ do_not_expect_pk_fault("executing on PROT_EXEC memory");
+ ptr_contents = read_ptr(p1);
+ dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
+ expected_pk_fault(UNKNOWN_PKEY);
+
+ /*
+ * Put the memory back to non-PROT_EXEC. Should clear the
+ * exec-only pkey off the VMA and allow it to be readable
+ * again. Go to PROT_NONE first to check for a kernel bug
+ * that did not clear the pkey when doing PROT_NONE.
+ */
+ ret = mprotect(p1, PAGE_SIZE, PROT_NONE);
+ pkey_assert(!ret);
+
+ ret = mprotect(p1, PAGE_SIZE, PROT_READ|PROT_EXEC);
+ pkey_assert(!ret);
+ ptr_contents = read_ptr(p1);
+ do_not_expect_pk_fault("plain read on recently PROT_EXEC area");
+}
+
void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey)
{
int size = PAGE_SIZE;
@@ -1302,6 +1406,8 @@ void (*pkey_tests[])(int *ptr, u16 pkey) = {
test_kernel_gup_of_access_disabled_region,
test_kernel_gup_write_to_write_disabled_region,
test_executing_on_unreadable_memory,
+ test_implicit_mprotect_exec_only_memory,
+ test_mprotect_with_pkey_0,
test_ptrace_of_child,
test_pkey_syscalls_on_non_allocated_pkey,
test_pkey_syscalls_bad_args,
diff --git a/tools/testing/selftests/x86/test_syscall_vdso.c b/tools/testing/selftests/x86/test_syscall_vdso.c
index 4037035..c9c3281 100644
--- a/tools/testing/selftests/x86/test_syscall_vdso.c
+++ b/tools/testing/selftests/x86/test_syscall_vdso.c
@@ -100,12 +100,19 @@ asm (
" shl $32, %r8\n"
" orq $0x7f7f7f7f, %r8\n"
" movq %r8, %r9\n"
- " movq %r8, %r10\n"
- " movq %r8, %r11\n"
- " movq %r8, %r12\n"
- " movq %r8, %r13\n"
- " movq %r8, %r14\n"
- " movq %r8, %r15\n"
+ " incq %r9\n"
+ " movq %r9, %r10\n"
+ " incq %r10\n"
+ " movq %r10, %r11\n"
+ " incq %r11\n"
+ " movq %r11, %r12\n"
+ " incq %r12\n"
+ " movq %r12, %r13\n"
+ " incq %r13\n"
+ " movq %r13, %r14\n"
+ " incq %r14\n"
+ " movq %r14, %r15\n"
+ " incq %r15\n"
" ret\n"
" .code32\n"
" .popsection\n"
@@ -128,12 +135,13 @@ int check_regs64(void)
int err = 0;
int num = 8;
uint64_t *r64 = ®s64.r8;
+ uint64_t expected = 0x7f7f7f7f7f7f7f7fULL;
if (!kernel_is_64bit)
return 0;
do {
- if (*r64 == 0x7f7f7f7f7f7f7f7fULL)
+ if (*r64 == expected++)
continue; /* register did not change */
if (syscall_addr != (long)&int80) {
/*
@@ -147,18 +155,17 @@ int check_regs64(void)
continue;
}
} else {
- /* INT80 syscall entrypoint can be used by
+ /*
+ * INT80 syscall entrypoint can be used by
* 64-bit programs too, unlike SYSCALL/SYSENTER.
* Therefore it must preserve R12+
* (they are callee-saved registers in 64-bit C ABI).
*
- * This was probably historically not intended,
- * but R8..11 are clobbered (cleared to 0).
- * IOW: they are the only registers which aren't
- * preserved across INT80 syscall.
+ * Starting in Linux 4.17 (and any kernel that
+ * backports the change), R8..11 are preserved.
+ * Historically (and probably unintentionally), they
+ * were clobbered or zeroed.
*/
- if (*r64 == 0 && num <= 11)
- continue;
}
printf("[FAIL]\tR%d has changed:%016llx\n", num, *r64);
err++;
diff --git a/tools/virtio/linux/dma-mapping.h b/tools/virtio/linux/dma-mapping.h
index 1571e24..f91aeb5f 100644
--- a/tools/virtio/linux/dma-mapping.h
+++ b/tools/virtio/linux/dma-mapping.h
@@ -6,8 +6,6 @@
# error Virtio userspace code does not support CONFIG_HAS_DMA
#endif
-#define PCI_DMA_BUS_IS_PHYS 1
-
enum dma_data_direction {
DMA_BIDIRECTIONAL = 0,
DMA_TO_DEVICE = 1,
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index dba629c..a4c1b76 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -63,7 +63,7 @@ static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_arm_running_vcpu);
static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1);
static u32 kvm_next_vmid;
static unsigned int kvm_vmid_bits __read_mostly;
-static DEFINE_SPINLOCK(kvm_vmid_lock);
+static DEFINE_RWLOCK(kvm_vmid_lock);
static bool vgic_present;
@@ -473,11 +473,16 @@ static void update_vttbr(struct kvm *kvm)
{
phys_addr_t pgd_phys;
u64 vmid;
+ bool new_gen;
- if (!need_new_vmid_gen(kvm))
+ read_lock(&kvm_vmid_lock);
+ new_gen = need_new_vmid_gen(kvm);
+ read_unlock(&kvm_vmid_lock);
+
+ if (!new_gen)
return;
- spin_lock(&kvm_vmid_lock);
+ write_lock(&kvm_vmid_lock);
/*
* We need to re-check the vmid_gen here to ensure that if another vcpu
@@ -485,7 +490,7 @@ static void update_vttbr(struct kvm *kvm)
* use the same vmid.
*/
if (!need_new_vmid_gen(kvm)) {
- spin_unlock(&kvm_vmid_lock);
+ write_unlock(&kvm_vmid_lock);
return;
}
@@ -519,7 +524,7 @@ static void update_vttbr(struct kvm *kvm)
vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK(kvm_vmid_bits);
kvm->arch.vttbr = kvm_phys_to_vttbr(pgd_phys) | vmid;
- spin_unlock(&kvm_vmid_lock);
+ write_unlock(&kvm_vmid_lock);
}
static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 7f6a944..8d90de2 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -1401,6 +1401,7 @@ static void kvm_send_hwpoison_signal(unsigned long address,
{
siginfo_t info;
+ clear_siginfo(&info);
info.si_signo = SIGBUS;
info.si_errno = 0;
info.si_code = BUS_MCEERR_AR;
diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c
index 6919352..c4762be 100644
--- a/virt/kvm/arm/psci.c
+++ b/virt/kvm/arm/psci.c
@@ -18,6 +18,7 @@
#include <linux/arm-smccc.h>
#include <linux/preempt.h>
#include <linux/kvm_host.h>
+#include <linux/uaccess.h>
#include <linux/wait.h>
#include <asm/cputype.h>
@@ -427,3 +428,62 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
smccc_set_retval(vcpu, val, 0, 0, 0);
return 1;
}
+
+int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu)
+{
+ return 1; /* PSCI version */
+}
+
+int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+ if (put_user(KVM_REG_ARM_PSCI_VERSION, uindices))
+ return -EFAULT;
+
+ return 0;
+}
+
+int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+ if (reg->id == KVM_REG_ARM_PSCI_VERSION) {
+ void __user *uaddr = (void __user *)(long)reg->addr;
+ u64 val;
+
+ val = kvm_psci_version(vcpu, vcpu->kvm);
+ if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)))
+ return -EFAULT;
+
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
+int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+ if (reg->id == KVM_REG_ARM_PSCI_VERSION) {
+ void __user *uaddr = (void __user *)(long)reg->addr;
+ bool wants_02;
+ u64 val;
+
+ if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id)))
+ return -EFAULT;
+
+ wants_02 = test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features);
+
+ switch (val) {
+ case KVM_ARM_PSCI_0_1:
+ if (wants_02)
+ return -EINVAL;
+ vcpu->kvm->arch.psci_version = val;
+ return 0;
+ case KVM_ARM_PSCI_0_2:
+ case KVM_ARM_PSCI_1_0:
+ if (!wants_02)
+ return -EINVAL;
+ vcpu->kvm->arch.psci_version = val;
+ return 0;
+ }
+ }
+
+ return -EINVAL;
+}
diff --git a/virt/kvm/arm/vgic/vgic-debug.c b/virt/kvm/arm/vgic/vgic-debug.c
index 10b3817..4ffc0b5 100644
--- a/virt/kvm/arm/vgic/vgic-debug.c
+++ b/virt/kvm/arm/vgic/vgic-debug.c
@@ -211,6 +211,7 @@ static int vgic_debug_show(struct seq_file *s, void *v)
struct vgic_state_iter *iter = (struct vgic_state_iter *)v;
struct vgic_irq *irq;
struct kvm_vcpu *vcpu = NULL;
+ unsigned long flags;
if (iter->dist_id == 0) {
print_dist_state(s, &kvm->arch.vgic);
@@ -227,9 +228,9 @@ static int vgic_debug_show(struct seq_file *s, void *v)
irq = &kvm->arch.vgic.spis[iter->intid - VGIC_NR_PRIVATE_IRQS];
}
- spin_lock(&irq->irq_lock);
+ spin_lock_irqsave(&irq->irq_lock, flags);
print_irq_state(s, irq, vcpu);
- spin_unlock(&irq->irq_lock);
+ spin_unlock_irqrestore(&irq->irq_lock, flags);
return 0;
}
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index 68378fe..e07156c 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -423,7 +423,7 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data)
* We cannot rely on the vgic maintenance interrupt to be
* delivered synchronously. This means we can only use it to
* exit the VM, and we perform the handling of EOIed
- * interrupts on the exit path (see vgic_process_maintenance).
+ * interrupts on the exit path (see vgic_fold_lr_state).
*/
return IRQ_HANDLED;
}
diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index a8f07243..4ed79c9 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -52,6 +52,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intid), *oldirq;
+ unsigned long flags;
int ret;
/* In this case there is no put, since we keep the reference. */
@@ -71,7 +72,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
irq->intid = intid;
irq->target_vcpu = vcpu;
- spin_lock(&dist->lpi_list_lock);
+ spin_lock_irqsave(&dist->lpi_list_lock, flags);
/*
* There could be a race with another vgic_add_lpi(), so we need to
@@ -99,7 +100,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
dist->lpi_list_count++;
out_unlock:
- spin_unlock(&dist->lpi_list_lock);
+ spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
/*
* We "cache" the configuration table entries in our struct vgic_irq's.
@@ -280,8 +281,8 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
int ret;
unsigned long flags;
- ret = kvm_read_guest(kvm, propbase + irq->intid - GIC_LPI_OFFSET,
- &prop, 1);
+ ret = kvm_read_guest_lock(kvm, propbase + irq->intid - GIC_LPI_OFFSET,
+ &prop, 1);
if (ret)
return ret;
@@ -315,6 +316,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
struct vgic_irq *irq;
+ unsigned long flags;
u32 *intids;
int irq_count, i = 0;
@@ -330,7 +332,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
if (!intids)
return -ENOMEM;
- spin_lock(&dist->lpi_list_lock);
+ spin_lock_irqsave(&dist->lpi_list_lock, flags);
list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
if (i == irq_count)
break;
@@ -339,7 +341,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
continue;
intids[i++] = irq->intid;
}
- spin_unlock(&dist->lpi_list_lock);
+ spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
*intid_ptr = intids;
return i;
@@ -348,10 +350,11 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu)
{
int ret = 0;
+ unsigned long flags;
- spin_lock(&irq->irq_lock);
+ spin_lock_irqsave(&irq->irq_lock, flags);
irq->target_vcpu = vcpu;
- spin_unlock(&irq->irq_lock);
+ spin_unlock_irqrestore(&irq->irq_lock, flags);
if (irq->hw) {
struct its_vlpi_map map;
@@ -441,8 +444,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
* this very same byte in the last iteration. Reuse that.
*/
if (byte_offset != last_byte_offset) {
- ret = kvm_read_guest(vcpu->kvm, pendbase + byte_offset,
- &pendmask, 1);
+ ret = kvm_read_guest_lock(vcpu->kvm,
+ pendbase + byte_offset,
+ &pendmask, 1);
if (ret) {
kfree(intids);
return ret;
@@ -786,7 +790,7 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id,
return false;
/* Each 1st level entry is represented by a 64-bit value. */
- if (kvm_read_guest(its->dev->kvm,
+ if (kvm_read_guest_lock(its->dev->kvm,
BASER_ADDRESS(baser) + index * sizeof(indirect_ptr),
&indirect_ptr, sizeof(indirect_ptr)))
return false;
@@ -1367,8 +1371,8 @@ static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its)
cbaser = CBASER_ADDRESS(its->cbaser);
while (its->cwriter != its->creadr) {
- int ret = kvm_read_guest(kvm, cbaser + its->creadr,
- cmd_buf, ITS_CMD_SIZE);
+ int ret = kvm_read_guest_lock(kvm, cbaser + its->creadr,
+ cmd_buf, ITS_CMD_SIZE);
/*
* If kvm_read_guest() fails, this could be due to the guest
* programming a bogus value in CBASER or something else going
@@ -1893,7 +1897,7 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, int esz,
int next_offset;
size_t byte_offset;
- ret = kvm_read_guest(kvm, gpa, entry, esz);
+ ret = kvm_read_guest_lock(kvm, gpa, entry, esz);
if (ret)
return ret;
@@ -2263,7 +2267,7 @@ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz)
int ret;
BUG_ON(esz > sizeof(val));
- ret = kvm_read_guest(kvm, gpa, &val, esz);
+ ret = kvm_read_guest_lock(kvm, gpa, &val, esz);
if (ret)
return ret;
val = le64_to_cpu(val);
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v2.c b/virt/kvm/arm/vgic/vgic-mmio-v2.c
index e21e2f4..ffc587b 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v2.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v2.c
@@ -14,6 +14,8 @@
#include <linux/irqchip/arm-gic.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
+#include <linux/nospec.h>
+
#include <kvm/iodev.h>
#include <kvm/arm_vgic.h>
@@ -324,6 +326,9 @@ static unsigned long vgic_mmio_read_apr(struct kvm_vcpu *vcpu,
if (n > vgic_v3_max_apr_idx(vcpu))
return 0;
+
+ n = array_index_nospec(n, 4);
+
/* GICv3 only uses ICH_AP1Rn for memory mapped (GICv2) guests */
return vgicv3->vgic_ap1r[n];
}
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index dbe99d6..ff9655c 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -289,10 +289,16 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
irq->vcpu->cpu != -1) /* VCPU thread is running */
cond_resched_lock(&irq->irq_lock);
- if (irq->hw)
+ if (irq->hw) {
vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu);
- else
+ } else {
+ u32 model = vcpu->kvm->arch.vgic.vgic_model;
+
irq->active = active;
+ if (model == KVM_DEV_TYPE_ARM_VGIC_V2 &&
+ active && vgic_irq_is_sgi(irq->intid))
+ irq->active_source = requester_vcpu->vcpu_id;
+ }
if (irq->active)
vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c
index 45aa433..a5f2e44 100644
--- a/virt/kvm/arm/vgic/vgic-v2.c
+++ b/virt/kvm/arm/vgic/vgic-v2.c
@@ -37,13 +37,6 @@ void vgic_v2_init_lrs(void)
vgic_v2_write_lr(i, 0);
}
-void vgic_v2_set_npie(struct kvm_vcpu *vcpu)
-{
- struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
-
- cpuif->vgic_hcr |= GICH_HCR_NPIE;
-}
-
void vgic_v2_set_underflow(struct kvm_vcpu *vcpu)
{
struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
@@ -71,13 +64,18 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
int lr;
unsigned long flags;
- cpuif->vgic_hcr &= ~(GICH_HCR_UIE | GICH_HCR_NPIE);
+ cpuif->vgic_hcr &= ~GICH_HCR_UIE;
for (lr = 0; lr < vgic_cpu->used_lrs; lr++) {
u32 val = cpuif->vgic_lr[lr];
- u32 intid = val & GICH_LR_VIRTUALID;
+ u32 cpuid, intid = val & GICH_LR_VIRTUALID;
struct vgic_irq *irq;
+ /* Extract the source vCPU id from the LR */
+ cpuid = val & GICH_LR_PHYSID_CPUID;
+ cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
+ cpuid &= 7;
+
/* Notify fds when the guest EOI'ed a level-triggered SPI */
if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid))
kvm_notify_acked_irq(vcpu->kvm, 0,
@@ -90,17 +88,16 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
/* Always preserve the active bit */
irq->active = !!(val & GICH_LR_ACTIVE_BIT);
+ if (irq->active && vgic_irq_is_sgi(intid))
+ irq->active_source = cpuid;
+
/* Edge is the only case where we preserve the pending bit */
if (irq->config == VGIC_CONFIG_EDGE &&
(val & GICH_LR_PENDING_BIT)) {
irq->pending_latch = true;
- if (vgic_irq_is_sgi(intid)) {
- u32 cpuid = val & GICH_LR_PHYSID_CPUID;
-
- cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
+ if (vgic_irq_is_sgi(intid))
irq->source |= (1 << cpuid);
- }
}
/*
@@ -152,8 +149,15 @@ void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
u32 val = irq->intid;
bool allow_pending = true;
- if (irq->active)
+ if (irq->active) {
val |= GICH_LR_ACTIVE_BIT;
+ if (vgic_irq_is_sgi(irq->intid))
+ val |= irq->active_source << GICH_LR_PHYSID_CPUID_SHIFT;
+ if (vgic_irq_is_multi_sgi(irq)) {
+ allow_pending = false;
+ val |= GICH_LR_EOI;
+ }
+ }
if (irq->hw) {
val |= GICH_LR_HW;
@@ -190,8 +194,10 @@ void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
BUG_ON(!src);
val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT;
irq->source &= ~(1 << (src - 1));
- if (irq->source)
+ if (irq->source) {
irq->pending_latch = true;
+ val |= GICH_LR_EOI;
+ }
}
}
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index 8195f52..bdcf8e7 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -27,13 +27,6 @@ static bool group1_trap;
static bool common_trap;
static bool gicv4_enable;
-void vgic_v3_set_npie(struct kvm_vcpu *vcpu)
-{
- struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
-
- cpuif->vgic_hcr |= ICH_HCR_NPIE;
-}
-
void vgic_v3_set_underflow(struct kvm_vcpu *vcpu)
{
struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
@@ -55,17 +48,23 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
int lr;
unsigned long flags;
- cpuif->vgic_hcr &= ~(ICH_HCR_UIE | ICH_HCR_NPIE);
+ cpuif->vgic_hcr &= ~ICH_HCR_UIE;
for (lr = 0; lr < vgic_cpu->used_lrs; lr++) {
u64 val = cpuif->vgic_lr[lr];
- u32 intid;
+ u32 intid, cpuid;
struct vgic_irq *irq;
+ bool is_v2_sgi = false;
- if (model == KVM_DEV_TYPE_ARM_VGIC_V3)
+ cpuid = val & GICH_LR_PHYSID_CPUID;
+ cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
+
+ if (model == KVM_DEV_TYPE_ARM_VGIC_V3) {
intid = val & ICH_LR_VIRTUAL_ID_MASK;
- else
+ } else {
intid = val & GICH_LR_VIRTUALID;
+ is_v2_sgi = vgic_irq_is_sgi(intid);
+ }
/* Notify fds when the guest EOI'ed a level-triggered IRQ */
if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid))
@@ -81,18 +80,16 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
/* Always preserve the active bit */
irq->active = !!(val & ICH_LR_ACTIVE_BIT);
+ if (irq->active && is_v2_sgi)
+ irq->active_source = cpuid;
+
/* Edge is the only case where we preserve the pending bit */
if (irq->config == VGIC_CONFIG_EDGE &&
(val & ICH_LR_PENDING_BIT)) {
irq->pending_latch = true;
- if (vgic_irq_is_sgi(intid) &&
- model == KVM_DEV_TYPE_ARM_VGIC_V2) {
- u32 cpuid = val & GICH_LR_PHYSID_CPUID;
-
- cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
+ if (is_v2_sgi)
irq->source |= (1 << cpuid);
- }
}
/*
@@ -133,10 +130,20 @@ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
{
u32 model = vcpu->kvm->arch.vgic.vgic_model;
u64 val = irq->intid;
- bool allow_pending = true;
+ bool allow_pending = true, is_v2_sgi;
- if (irq->active)
+ is_v2_sgi = (vgic_irq_is_sgi(irq->intid) &&
+ model == KVM_DEV_TYPE_ARM_VGIC_V2);
+
+ if (irq->active) {
val |= ICH_LR_ACTIVE_BIT;
+ if (is_v2_sgi)
+ val |= irq->active_source << GICH_LR_PHYSID_CPUID_SHIFT;
+ if (vgic_irq_is_multi_sgi(irq)) {
+ allow_pending = false;
+ val |= ICH_LR_EOI;
+ }
+ }
if (irq->hw) {
val |= ICH_LR_HW;
@@ -174,8 +181,10 @@ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
BUG_ON(!src);
val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT;
irq->source &= ~(1 << (src - 1));
- if (irq->source)
+ if (irq->source) {
irq->pending_latch = true;
+ val |= ICH_LR_EOI;
+ }
}
}
@@ -335,7 +344,7 @@ int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq)
bit_nr = irq->intid % BITS_PER_BYTE;
ptr = pendbase + byte_offset;
- ret = kvm_read_guest(kvm, ptr, &val, 1);
+ ret = kvm_read_guest_lock(kvm, ptr, &val, 1);
if (ret)
return ret;
@@ -388,7 +397,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
ptr = pendbase + byte_offset;
if (byte_offset != last_byte_offset) {
- ret = kvm_read_guest(kvm, ptr, &val, 1);
+ ret = kvm_read_guest_lock(kvm, ptr, &val, 1);
if (ret)
return ret;
last_byte_offset = byte_offset;
diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
index e74baec..33c8325 100644
--- a/virt/kvm/arm/vgic/vgic.c
+++ b/virt/kvm/arm/vgic/vgic.c
@@ -14,11 +14,13 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/interrupt.h>
+#include <linux/irq.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/list_sort.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
+#include <linux/nospec.h>
+
#include <asm/kvm_hyp.h>
#include "vgic.h"
@@ -41,9 +43,13 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = {
* kvm->lock (mutex)
* its->cmd_lock (mutex)
* its->its_lock (mutex)
- * vgic_cpu->ap_list_lock
- * kvm->lpi_list_lock
- * vgic_irq->irq_lock
+ * vgic_cpu->ap_list_lock must be taken with IRQs disabled
+ * kvm->lpi_list_lock must be taken with IRQs disabled
+ * vgic_irq->irq_lock must be taken with IRQs disabled
+ *
+ * As the ap_list_lock might be taken from the timer interrupt handler,
+ * we have to disable IRQs before taking this lock and everything lower
+ * than it.
*
* If you need to take multiple locks, always take the upper lock first,
* then the lower ones, e.g. first take the its_lock, then the irq_lock.
@@ -70,8 +76,9 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct vgic_irq *irq = NULL;
+ unsigned long flags;
- spin_lock(&dist->lpi_list_lock);
+ spin_lock_irqsave(&dist->lpi_list_lock, flags);
list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
if (irq->intid != intid)
@@ -87,7 +94,7 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid)
irq = NULL;
out_unlock:
- spin_unlock(&dist->lpi_list_lock);
+ spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
return irq;
}
@@ -101,12 +108,16 @@ struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
u32 intid)
{
/* SGIs and PPIs */
- if (intid <= VGIC_MAX_PRIVATE)
+ if (intid <= VGIC_MAX_PRIVATE) {
+ intid = array_index_nospec(intid, VGIC_MAX_PRIVATE);
return &vcpu->arch.vgic_cpu.private_irqs[intid];
+ }
/* SPIs */
- if (intid <= VGIC_MAX_SPI)
+ if (intid <= VGIC_MAX_SPI) {
+ intid = array_index_nospec(intid, VGIC_MAX_SPI);
return &kvm->arch.vgic.spis[intid - VGIC_NR_PRIVATE_IRQS];
+ }
/* LPIs */
if (intid >= VGIC_MIN_LPI)
@@ -128,19 +139,20 @@ static void vgic_irq_release(struct kref *ref)
void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
{
struct vgic_dist *dist = &kvm->arch.vgic;
+ unsigned long flags;
if (irq->intid < VGIC_MIN_LPI)
return;
- spin_lock(&dist->lpi_list_lock);
+ spin_lock_irqsave(&dist->lpi_list_lock, flags);
if (!kref_put(&irq->refcount, vgic_irq_release)) {
- spin_unlock(&dist->lpi_list_lock);
+ spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
return;
};
list_del(&irq->lpi_list);
dist->lpi_list_count--;
- spin_unlock(&dist->lpi_list_lock);
+ spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
kfree(irq);
}
@@ -594,6 +606,7 @@ static void vgic_prune_ap_list(struct kvm_vcpu *vcpu)
list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) {
struct kvm_vcpu *target_vcpu, *vcpuA, *vcpuB;
+ bool target_vcpu_needs_kick = false;
spin_lock(&irq->irq_lock);
@@ -664,11 +677,18 @@ static void vgic_prune_ap_list(struct kvm_vcpu *vcpu)
list_del(&irq->ap_list);
irq->vcpu = target_vcpu;
list_add_tail(&irq->ap_list, &new_cpu->ap_list_head);
+ target_vcpu_needs_kick = true;
}
spin_unlock(&irq->irq_lock);
spin_unlock(&vcpuB->arch.vgic_cpu.ap_list_lock);
spin_unlock_irqrestore(&vcpuA->arch.vgic_cpu.ap_list_lock, flags);
+
+ if (target_vcpu_needs_kick) {
+ kvm_make_request(KVM_REQ_IRQ_PENDING, target_vcpu);
+ kvm_vcpu_kick(target_vcpu);
+ }
+
goto retry;
}
@@ -711,14 +731,6 @@ static inline void vgic_set_underflow(struct kvm_vcpu *vcpu)
vgic_v3_set_underflow(vcpu);
}
-static inline void vgic_set_npie(struct kvm_vcpu *vcpu)
-{
- if (kvm_vgic_global_state.type == VGIC_V2)
- vgic_v2_set_npie(vcpu);
- else
- vgic_v3_set_npie(vcpu);
-}
-
/* Requires the ap_list_lock to be held. */
static int compute_ap_list_depth(struct kvm_vcpu *vcpu,
bool *multi_sgi)
@@ -732,17 +744,15 @@ static int compute_ap_list_depth(struct kvm_vcpu *vcpu,
DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&vgic_cpu->ap_list_lock));
list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
+ int w;
+
spin_lock(&irq->irq_lock);
/* GICv2 SGIs can count for more than one... */
- if (vgic_irq_is_sgi(irq->intid) && irq->source) {
- int w = hweight8(irq->source);
-
- count += w;
- *multi_sgi |= (w > 1);
- } else {
- count++;
- }
+ w = vgic_irq_get_lr_count(irq);
spin_unlock(&irq->irq_lock);
+
+ count += w;
+ *multi_sgi |= (w > 1);
}
return count;
}
@@ -753,7 +763,6 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
struct vgic_irq *irq;
int count;
- bool npie = false;
bool multi_sgi;
u8 prio = 0xff;
@@ -783,10 +792,8 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
if (likely(vgic_target_oracle(irq) == vcpu)) {
vgic_populate_lr(vcpu, irq, count++);
- if (irq->source) {
- npie = true;
+ if (irq->source)
prio = irq->priority;
- }
}
spin_unlock(&irq->irq_lock);
@@ -799,9 +806,6 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
}
}
- if (npie)
- vgic_set_npie(vcpu);
-
vcpu->arch.vgic_cpu.used_lrs = count;
/* Nuke remaining LRs */
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
index 830e815..32c25d4 100644
--- a/virt/kvm/arm/vgic/vgic.h
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -110,6 +110,20 @@ static inline bool vgic_irq_is_mapped_level(struct vgic_irq *irq)
return irq->config == VGIC_CONFIG_LEVEL && irq->hw;
}
+static inline int vgic_irq_get_lr_count(struct vgic_irq *irq)
+{
+ /* Account for the active state as an interrupt */
+ if (vgic_irq_is_sgi(irq->intid) && irq->source)
+ return hweight8(irq->source) + irq->active;
+
+ return irq_is_pending(irq) || irq->active;
+}
+
+static inline bool vgic_irq_is_multi_sgi(struct vgic_irq *irq)
+{
+ return vgic_irq_get_lr_count(irq) > 1;
+}
+
/*
* This struct provides an intermediate representation of the fields contained
* in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 6e865e8..90d30fb 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -397,7 +397,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
* Check if there was an event already pending on the eventfd
* before we registered, and trigger it as if we didn't miss it.
*/
- events = f.file->f_op->poll(f.file, &irqfd->pt);
+ events = vfs_poll(f.file, &irqfd->pt);
if (events & EPOLLIN)
schedule_work(&irqfd->inject);
